org_fedora_oscap.content_discovery.ContentBringer.reduce_files() - Code Metrics - Inspection of "Handle archives and preferred content better." - OpenSCAP/oscap-anaconda-addon - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — master (#219)

by Matěj

created 2022-10-12 14:27 UTC

ContentBringer.reduce_files() A

↳ Parent: org_fedora_oscap.content_discovery

Complexity

Conditions

Size

Total Lines	13
Code Lines	11

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	5
eloc	11
nop	4
dl	0
loc	13
rs	9.3333
c	0
b	0
f	0

import threading
import logging
import pathlib
import shutil
import os
from glob import glob
from typing import List

from pyanaconda.core import constants
from pyanaconda.threading import threadMgr
from pykickstart.errors import KickstartValueError

from org_fedora_oscap import data_fetch, utils
from org_fedora_oscap import common
from org_fedora_oscap import content_handling
from org_fedora_oscap.content_handling import CONTENT_TYPES
from org_fedora_oscap import rule_handling

from org_fedora_oscap.common import _

log = logging.getLogger("anaconda")


def is_network(scheme):
    return any(
        scheme.startswith(net_prefix)
        for net_prefix in data_fetch.NET_URL_PREFIXES)


def clear_all(data):
    data.content_type = ""
    data.content_url = ""
    data.datastream_id = ""
    data.xccdf_id = ""
    data.profile_id = ""
    data.content_path = ""
    data.cpe_path = ""
    data.tailoring_path = ""

    data.fingerprint = ""

    data.certificates = ""

    # internal values
    data.rule_data = rule_handling.RuleData()
    data.dry_run = False


class ContentBringer:
    CONTENT_DOWNLOAD_LOCATION = pathlib.Path(common.INSTALLATION_CONTENT_DIR)
    DEFAULT_SSG_DATA_STREAM_PATH = f"{common.SSG_DIR}/{common.SSG_CONTENT}"

    def __init__(self, addon_data):
        self.content_uri_scheme = ""
        self.content_uri_path = ""
        self.fetched_content = ""

        self.activity_lock = threading.Lock()
        self.now_fetching_or_processing = False

        self.CONTENT_DOWNLOAD_LOCATION.mkdir(parents=True, exist_ok=True)

        self._addon_data = addon_data

    def get_content_type(self, url):
        if url.endswith(".rpm"):
            return "rpm"
        elif any(url.endswith(arch_type) for arch_type in common.SUPPORTED_ARCHIVES):
            return "archive"
        else:
            return "file"

    @property
    def content_uri(self):
        return self.content_uri_scheme + "://" + self.content_uri_path

    @content_uri.setter
    def content_uri(self, uri):
        scheme, path = uri.split("://", 1)
        self.content_uri_path = path
        self.content_uri_scheme = scheme

    def fetch_content(self, what_if_fail, ca_certs_path=""):
        """
        Initiate fetch of the content into an appropriate directory

        Args:
            what_if_fail: Callback accepting exception as an argument that
                should handle them in the calling layer.
            ca_certs_path: Path to the HTTPS certificate file
        """
        self.content_uri = self._addon_data.content_url
        shutil.rmtree(self.CONTENT_DOWNLOAD_LOCATION, ignore_errors=True)
        self.CONTENT_DOWNLOAD_LOCATION.mkdir(parents=True, exist_ok=True)
        fetching_thread_name = self._fetch_files(
            self.content_uri_scheme, self.content_uri_path,
            self.CONTENT_DOWNLOAD_LOCATION, ca_certs_path, what_if_fail)
        return fetching_thread_name

    def _fetch_files(self, scheme, path, destdir, ca_certs_path, what_if_fail):
        with self.activity_lock:
            if self.now_fetching_or_processing:
                msg = "OSCAP Addon: Strange, it seems that we are already fetching something."
                log.warn(msg)
                return
            self.now_fetching_or_processing = True

        fetching_thread_name = None
        try:
            fetching_thread_name = self._start_actual_fetch(scheme, path, destdir, ca_certs_path)
        except Exception as exc:
            with self.activity_lock:
                self.now_fetching_or_processing = False
            what_if_fail(exc)

        # We are not finished yet with the fetch
        return fetching_thread_name

    def _start_actual_fetch(self, scheme, path, destdir, ca_certs_path):
        fetching_thread_name = None
        url = scheme + "://" + path

        if "/" not in path:
            msg = f"Missing the path component of the '{url}' URL"
            raise KickstartValueError(msg)
        basename = path.rsplit("/", 1)[1]
        if not basename:
            msg = f"Unable to deduce basename from the '{url}' URL"
            raise KickstartValueError(msg)

        dest = destdir / basename

        if is_network(scheme):
            fetching_thread_name = data_fetch.wait_and_fetch_net_data(
                url,
                dest,
                ca_certs_path
            )
        else:  # invalid schemes are handled down the road
            fetching_thread_name = data_fetch.fetch_local_data(
                url,
                dest,
            )
        return fetching_thread_name

    def finish_content_fetch(self, fetching_thread_name, fingerprint, report_callback, dest_filename,
                             what_if_fail):
        """
        Finish any ongoing fetch and analyze what has been fetched.

        After the fetch is completed, it analyzes verifies fetched content if applicable,
        analyzes it and compiles into an instance of ObtainedContent.

        Args:
            fetching_thread_name: Name of the fetching thread
                or None if we are only after the analysis
            fingerprint: A checksum for downloaded file verification
            report_callback: Means for the method to send user-relevant messages outside
            dest_filename: The target of the fetch operation. Can be falsy -
                in this case there is no content filename defined
            what_if_fail: Callback accepting exception as an argument
                that should handle them in the calling layer.

        Returns:
            Instance of ObtainedContent if everything went well, or None.
        """
        try:
            content = self._finish_actual_fetch(fetching_thread_name, fingerprint, report_callback, dest_filename)
        except Exception as exc:
            what_if_fail(exc)
            content = None
        finally:
            with self.activity_lock:
                self.now_fetching_or_processing = False

        return content

    def _verify_fingerprint(self, dest_filename, fingerprint=""):
        if not fingerprint:
            log.info("OSCAP Addon: No fingerprint provided, skipping integrity check")
            return

        hash_obj = utils.get_hashing_algorithm(fingerprint)
        digest = utils.get_file_fingerprint(dest_filename,
                                            hash_obj)
        if digest != fingerprint:
            log.error(
                "OSCAP Addon: "
                f"File {dest_filename} failed integrity check - assumed a "
                f"{hash_obj.name} hash and '{fingerprint}', got '{digest}'"
            )
            msg = _(f"OSCAP Addon: Integrity check of the content failed - {hash_obj.name} hash didn't match")
            raise content_handling.ContentCheckError(msg)
        log.info(f"Integrity check passed using {hash_obj.name} hash")

    def filter_discovered_content(self, labelled_files):
        expected_path = self._addon_data.content_path
        categories = (CONTENT_TYPES["DATASTREAM"], CONTENT_TYPES["XCCDF_CHECKLIST"])
        if expected_path:
            labelled_files = self.reduce_files(labelled_files, expected_path, categories)

        expected_path = self._addon_data.tailoring_path
        categories = (CONTENT_TYPES["TAILORING"], )
        if expected_path:
            labelled_files = self.reduce_files(labelled_files, expected_path, categories)

        expected_path = self._addon_data.cpe_path
        categories = (CONTENT_TYPES["CPE_DICT"], )
        if expected_path:
            labelled_files = self.reduce_files(labelled_files, expected_path, categories)

        return labelled_files

    def reduce_files(self, labelled_files, expected_path, categories):
        reduced_files = dict()
        if expected_path not in labelled_files:
            msg = (
                f"Expected a file {expected_path} to be part of the supplied content, "
                f"but it was not the case, got only {list(labelled_files.keys())}"
            )
            raise RuntimeError(msg)
        for path, label in labelled_files.items():
            if label in categories and path != expected_path:
                continue
            reduced_files[path] = label
        return reduced_files

    def _finish_actual_fetch(self, wait_for, fingerprint, report_callback, dest_filename):
        if wait_for:
            log.info(f"OSCAP Addon: Waiting for thread {wait_for}")
            threadMgr.wait(wait_for)
            log.info(f"OSCAP Addon: Finished waiting for thread {wait_for}")
        actually_fetched_content = wait_for is not None

        if fingerprint and dest_filename:
            self._verify_fingerprint(dest_filename, fingerprint)

        fpaths = self._gather_available_files(actually_fetched_content, dest_filename)

        structured_content = ObtainedContent(self.CONTENT_DOWNLOAD_LOCATION)
        content_type = self.get_content_type(str(dest_filename))
        log.info(f"OSCAP Addon: started to look at the content")
        if content_type in ("archive", "rpm"):
            structured_content.add_content_archive(dest_filename)

        labelled_filenames = content_handling.identify_files(fpaths)
        labelled_relative_filenames = {
            os.path.relpath(path, self.CONTENT_DOWNLOAD_LOCATION): label
            for path, label in labelled_filenames.items()}
        labelled_relative_filenames = self.filter_discovered_content(labelled_relative_filenames)

        for rel_fname, label in labelled_relative_filenames.items():
            fname = self.CONTENT_DOWNLOAD_LOCATION / rel_fname
            structured_content.add_file(str(fname), label)

        if fingerprint and dest_filename:
            structured_content.record_verification(dest_filename)

        log.info(f"OSCAP Addon: finished looking at the content")
        return structured_content

    def _gather_available_files(self, actually_fetched_content, dest_filename):
        fpaths = []
        if not actually_fetched_content:
            if not dest_filename:  # using scap-security-guide
                fpaths = [self.DEFAULT_SSG_DATA_STREAM_PATH]
            else:  # Using downloaded XCCDF/OVAL/DS/tailoring
                fpaths = pathlib.Path(self.CONTENT_DOWNLOAD_LOCATION).rglob("*")
                fpaths = [str(p) for p in fpaths if p.is_file()]
        else:
            dest_filename = pathlib.Path(dest_filename)
            # RPM is an archive at this phase
            content_type = self.get_content_type(str(dest_filename))
            if content_type in ("archive", "rpm"):
                try:
                    fpaths = common.extract_data(
                        str(dest_filename),
                        str(dest_filename.parent)
                    )
                except common.ExtractionError as err:
                    msg = f"Failed to extract the '{dest_filename}' archive: {str(err)}"
                    log.error("OSCAP Addon: " + msg)
                    raise err

            elif content_type == "file":
                fpaths = [str(dest_filename)]
            else:
                raise common.OSCAPaddonError("Unsupported content type")
        return fpaths

    def use_downloaded_content(self, content):
        preferred_content = self.get_preferred_content(content)

        # We know that we have ended up with a datastream-like content,
        # but if we can't convert an archive to a datastream.
        # self._addon_data.content_type = "datastream"
        self._addon_data.content_path = str(preferred_content.relative_to(content.root))

        preferred_tailoring = self.get_preferred_tailoring(content)
        if content.tailoring:
            self._addon_data.tailoring_path = str(preferred_tailoring.relative_to(content.root))

    def use_system_content(self, content=None):
        clear_all(self._addon_data)
        self._addon_data.content_type = "scap-security-guide"
        self._addon_data.content_path = common.get_ssg_path()

    def get_preferred_content(self, content):
        if self._addon_data.content_path:
            preferred_content = content.find_expected_usable_content(self._addon_data.content_path)
        else:
            preferred_content = content.select_main_usable_content()
        return preferred_content

    def get_preferred_tailoring(self, content):
        tailoring_path = self._addon_data.tailoring_path
        if tailoring_path:
            if tailoring_path != str(content.tailoring.relative_to(content.root)):
                msg = f"Expected a tailoring {tailoring_path}, but it couldn't be found"
                raise content_handling.ContentHandlingError(msg)
        return content.tailoring


class ObtainedContent:
    """
    This class aims to assist the gathered files discovery -
    the addon can downloaded files directly, or they can be extracted for an archive.
    The class enables user to quickly understand what is available,
    and whether the current set of contents is usable for further processing.
    """
    def __init__(self, root):
        self.labelled_files = dict()
        self.datastream = None  # type: Pathlib.Path
        self.xccdf = None  # type: Pathlib.Path
        self.ovals = []  # type: List[Pathlib.Path]
        self.tailoring = None  # type: Pathlib.Path
        self.archive = None  # type: Pathlib.Path
        self.verified = None  # type: Pathlib.Path
        self.root = pathlib.Path(root)

    def record_verification(self, path):
        """
        Declare a file as verified (typically by means of a checksum)
        """
        path = pathlib.Path(path)
        assert path in self.labelled_files
        self.verified = path

    def add_content_archive(self, fname):
        """
        If files come from an archive, record this information using this function.
        """
        path = pathlib.Path(fname)
        self.labelled_files[path] = None
        self.archive = path

    def _assign_content_type(self, attribute_name, new_value):
        old_value = getattr(self, attribute_name)
        if old_value and old_value != new_value:
            msg = (
                f"When dealing with {attribute_name}, "
                f"there was already the {old_value.name} when setting the new {new_value.name}")
            raise content_handling.ContentHandlingError(msg)
        setattr(self, attribute_name, new_value)

    def add_file(self, fname, label=None):
        if not label:
            label = content_handling.identify_files([fname])[fname]
        path = pathlib.Path(fname)
        if label == content_handling.CONTENT_TYPES["TAILORING"]:
            self._assign_content_type("tailoring", path)
        elif label == content_handling.CONTENT_TYPES["DATASTREAM"]:
            self._assign_content_type("datastream", path)
        elif label == content_handling.CONTENT_TYPES["OVAL"]:
            self.ovals.append(path)
        elif label == content_handling.CONTENT_TYPES["XCCDF_CHECKLIST"]:
            self._assign_content_type("xccdf", path)
        self.labelled_files[path] = label

    def _datastream_content(self):
        if not self.datastream:
            return None
        if not self.datastream.exists():
            return None
        return self.datastream

    def _xccdf_content(self):
        if not self.xccdf or not self.ovals:
            return None
        some_ovals_exist = any([path.exists() for path in self.ovals])
        if not (self.xccdf.exists() and some_ovals_exist):
            return None
        return self.xccdf

    def find_expected_usable_content(self, relative_expected_content_path):
        content_path = self.root / relative_expected_content_path
        eligible_main_content = (self._datastream_content(), self._xccdf_content())

        if content_path in eligible_main_content:
            return content_path
        else:
            if not content_path.exists():
                msg = f"Couldn't find '{content_path}' among the available content"
            else:
                msg = (
                    f"File '{content_path}' is not a valid datastream "
                    "or a valid XCCDF of a XCCDF-OVAL file tuple")
            raise content_handling.ContentHandlingError(msg)

    def select_main_usable_content(self):
        if self._datastream_content():
            return self._datastream_content()
        elif self._xccdf_content():
            return self._xccdf_content()
        else:
            msg = (
                "Couldn't find a valid datastream or a valid XCCDF-OVAL file tuple "
                "among the available content")
            raise content_handling.ContentHandlingError(msg)


1			import threading
2			import logging
3			import pathlib
4			import shutil
5			import os
6			from glob import glob
7			from typing import List
8
9			from pyanaconda.core import constants
10			from pyanaconda.threading import threadMgr
11			from pykickstart.errors import KickstartValueError
12
13			from org_fedora_oscap import data_fetch, utils
14			from org_fedora_oscap import common
15			from org_fedora_oscap import content_handling
16			from org_fedora_oscap.content_handling import CONTENT_TYPES
17			from org_fedora_oscap import rule_handling
18
19			from org_fedora_oscap.common import _
20
21			log = logging.getLogger("anaconda")
22
23
24			def is_network(scheme):
25			return any(
26			scheme.startswith(net_prefix)
27			for net_prefix in data_fetch.NET_URL_PREFIXES)
28
29
30			def clear_all(data):
31			data.content_type = ""
32			data.content_url = ""
33			data.datastream_id = ""
34			data.xccdf_id = ""
35			data.profile_id = ""
36			data.content_path = ""
37			data.cpe_path = ""
38			data.tailoring_path = ""
39
40			data.fingerprint = ""
41
42			data.certificates = ""
43
44			# internal values
45			data.rule_data = rule_handling.RuleData()
46			data.dry_run = False
47
48
49			class ContentBringer:
50			CONTENT_DOWNLOAD_LOCATION = pathlib.Path(common.INSTALLATION_CONTENT_DIR)
51			DEFAULT_SSG_DATA_STREAM_PATH = f"{common.SSG_DIR}/{common.SSG_CONTENT}"
52
53			def __init__(self, addon_data):
54			self.content_uri_scheme = ""
55			self.content_uri_path = ""
56			self.fetched_content = ""
57
58			self.activity_lock = threading.Lock()
59			self.now_fetching_or_processing = False
60
61			self.CONTENT_DOWNLOAD_LOCATION.mkdir(parents=True, exist_ok=True)
62
63			self._addon_data = addon_data
64
65			def get_content_type(self, url):
66			if url.endswith(".rpm"):
67			return "rpm"
68			elif any(url.endswith(arch_type) for arch_type in common.SUPPORTED_ARCHIVES):
69			return "archive"
70			else:
71			return "file"
72
73			@property
74			def content_uri(self):
75			return self.content_uri_scheme + "://" + self.content_uri_path
76
77			@content_uri.setter
78			def content_uri(self, uri):
79			scheme, path = uri.split("://", 1)
80			self.content_uri_path = path
81			self.content_uri_scheme = scheme
82
83			def fetch_content(self, what_if_fail, ca_certs_path=""):
84			"""
85			Initiate fetch of the content into an appropriate directory
86
87			Args:
88			what_if_fail: Callback accepting exception as an argument that
89			should handle them in the calling layer.
90			ca_certs_path: Path to the HTTPS certificate file
91			"""
92			self.content_uri = self._addon_data.content_url
93			shutil.rmtree(self.CONTENT_DOWNLOAD_LOCATION, ignore_errors=True)
94			self.CONTENT_DOWNLOAD_LOCATION.mkdir(parents=True, exist_ok=True)
95			fetching_thread_name = self._fetch_files(
96			self.content_uri_scheme, self.content_uri_path,
97			self.CONTENT_DOWNLOAD_LOCATION, ca_certs_path, what_if_fail)
98			return fetching_thread_name
99
100			def _fetch_files(self, scheme, path, destdir, ca_certs_path, what_if_fail):
101			with self.activity_lock:
102			if self.now_fetching_or_processing:
103			msg = "OSCAP Addon: Strange, it seems that we are already fetching something."
104			log.warn(msg)
105			return
106			self.now_fetching_or_processing = True
107
108			fetching_thread_name = None
109			try:
110			fetching_thread_name = self._start_actual_fetch(scheme, path, destdir, ca_certs_path)
111			except Exception as exc:
112			with self.activity_lock:
113			self.now_fetching_or_processing = False
114			what_if_fail(exc)
115
116			# We are not finished yet with the fetch
117			return fetching_thread_name
118
119			def _start_actual_fetch(self, scheme, path, destdir, ca_certs_path):
120			fetching_thread_name = None
121			url = scheme + "://" + path
122
123			if "/" not in path:
124			msg = f"Missing the path component of the '{url}' URL"
125			raise KickstartValueError(msg)
126			basename = path.rsplit("/", 1)[1]
127			if not basename:
128			msg = f"Unable to deduce basename from the '{url}' URL"
129			raise KickstartValueError(msg)
130
131			dest = destdir / basename
132
133			if is_network(scheme):
134			fetching_thread_name = data_fetch.wait_and_fetch_net_data(
135			url,
136			dest,
137			ca_certs_path
138			)
139			else: # invalid schemes are handled down the road
140			fetching_thread_name = data_fetch.fetch_local_data(
141			url,
142			dest,
143			)
144			return fetching_thread_name
145
146			def finish_content_fetch(self, fetching_thread_name, fingerprint, report_callback, dest_filename,
147			what_if_fail):
148			"""
149			Finish any ongoing fetch and analyze what has been fetched.
150
151			After the fetch is completed, it analyzes verifies fetched content if applicable,
152			analyzes it and compiles into an instance of ObtainedContent.
153
154			Args:
155			fetching_thread_name: Name of the fetching thread
156			or None if we are only after the analysis
157			fingerprint: A checksum for downloaded file verification
158			report_callback: Means for the method to send user-relevant messages outside
159			dest_filename: The target of the fetch operation. Can be falsy -
160			in this case there is no content filename defined
161			what_if_fail: Callback accepting exception as an argument
162			that should handle them in the calling layer.
163
164			Returns:
165			Instance of ObtainedContent if everything went well, or None.
166			"""
167			try:
168			content = self._finish_actual_fetch(fetching_thread_name, fingerprint, report_callback, dest_filename)
169			except Exception as exc:
170			what_if_fail(exc)
171			content = None
172			finally:
173			with self.activity_lock:
174			self.now_fetching_or_processing = False
175
176			return content
177
178			def _verify_fingerprint(self, dest_filename, fingerprint=""):
179			if not fingerprint:
180			log.info("OSCAP Addon: No fingerprint provided, skipping integrity check")
181			return
182
183			hash_obj = utils.get_hashing_algorithm(fingerprint)
184			digest = utils.get_file_fingerprint(dest_filename,
185			hash_obj)
186			if digest != fingerprint:
187			log.error(
188			"OSCAP Addon: "
189			f"File {dest_filename} failed integrity check - assumed a "
190			f"{hash_obj.name} hash and '{fingerprint}', got '{digest}'"
191			)
192			msg = _(f"OSCAP Addon: Integrity check of the content failed - {hash_obj.name} hash didn't match")
193			raise content_handling.ContentCheckError(msg)
194			log.info(f"Integrity check passed using {hash_obj.name} hash")
195
196			def filter_discovered_content(self, labelled_files):
197			expected_path = self._addon_data.content_path
198			categories = (CONTENT_TYPES["DATASTREAM"], CONTENT_TYPES["XCCDF_CHECKLIST"])
199			if expected_path:
200			labelled_files = self.reduce_files(labelled_files, expected_path, categories)
201
202			expected_path = self._addon_data.tailoring_path
203			categories = (CONTENT_TYPES["TAILORING"], )
204			if expected_path:
205			labelled_files = self.reduce_files(labelled_files, expected_path, categories)
206
207			expected_path = self._addon_data.cpe_path
208			categories = (CONTENT_TYPES["CPE_DICT"], )
209			if expected_path:
210			labelled_files = self.reduce_files(labelled_files, expected_path, categories)
211
212			return labelled_files
213
214			def reduce_files(self, labelled_files, expected_path, categories):
215			reduced_files = dict()
216			if expected_path not in labelled_files:
217			msg = (
218			f"Expected a file {expected_path} to be part of the supplied content, "
219			f"but it was not the case, got only {list(labelled_files.keys())}"
220			)
221			raise RuntimeError(msg)
222			for path, label in labelled_files.items():
223			if label in categories and path != expected_path:
224			continue
225			reduced_files[path] = label
226			return reduced_files
227
228			def _finish_actual_fetch(self, wait_for, fingerprint, report_callback, dest_filename):
229			if wait_for:
230			log.info(f"OSCAP Addon: Waiting for thread {wait_for}")
231			threadMgr.wait(wait_for)
232			log.info(f"OSCAP Addon: Finished waiting for thread {wait_for}")
233			actually_fetched_content = wait_for is not None
234
235			if fingerprint and dest_filename:
236			self._verify_fingerprint(dest_filename, fingerprint)
237
238			fpaths = self._gather_available_files(actually_fetched_content, dest_filename)
239
240			structured_content = ObtainedContent(self.CONTENT_DOWNLOAD_LOCATION)
241			content_type = self.get_content_type(str(dest_filename))
242			log.info(f"OSCAP Addon: started to look at the content")
243			if content_type in ("archive", "rpm"):
244			structured_content.add_content_archive(dest_filename)
245
246			labelled_filenames = content_handling.identify_files(fpaths)
247			labelled_relative_filenames = {
248			os.path.relpath(path, self.CONTENT_DOWNLOAD_LOCATION): label
249			for path, label in labelled_filenames.items()}
250			labelled_relative_filenames = self.filter_discovered_content(labelled_relative_filenames)
251
252			for rel_fname, label in labelled_relative_filenames.items():
253			fname = self.CONTENT_DOWNLOAD_LOCATION / rel_fname
254			structured_content.add_file(str(fname), label)
255
256			if fingerprint and dest_filename:
257			structured_content.record_verification(dest_filename)
258
259			log.info(f"OSCAP Addon: finished looking at the content")
260			return structured_content
261
262			def _gather_available_files(self, actually_fetched_content, dest_filename):
263			fpaths = []
264			if not actually_fetched_content:
265			if not dest_filename: # using scap-security-guide
266			fpaths = [self.DEFAULT_SSG_DATA_STREAM_PATH]
267			else: # Using downloaded XCCDF/OVAL/DS/tailoring
268			fpaths = pathlib.Path(self.CONTENT_DOWNLOAD_LOCATION).rglob("*")
269			fpaths = [str(p) for p in fpaths if p.is_file()]
270			else:
271			dest_filename = pathlib.Path(dest_filename)
272			# RPM is an archive at this phase
273			content_type = self.get_content_type(str(dest_filename))
274			if content_type in ("archive", "rpm"):
275			try:
276			fpaths = common.extract_data(
277			str(dest_filename),
278			str(dest_filename.parent)
279			)
280			except common.ExtractionError as err:
281			msg = f"Failed to extract the '{dest_filename}' archive: {str(err)}"
282			log.error("OSCAP Addon: " + msg)
283			raise err
284
285			elif content_type == "file":
286			fpaths = [str(dest_filename)]
287			else:
288			raise common.OSCAPaddonError("Unsupported content type")
289			return fpaths
290
291			def use_downloaded_content(self, content):
292			preferred_content = self.get_preferred_content(content)
293
294			# We know that we have ended up with a datastream-like content,
295			# but if we can't convert an archive to a datastream.
296			# self._addon_data.content_type = "datastream"
297			self._addon_data.content_path = str(preferred_content.relative_to(content.root))
298
299			preferred_tailoring = self.get_preferred_tailoring(content)
300			if content.tailoring:
301			self._addon_data.tailoring_path = str(preferred_tailoring.relative_to(content.root))
302
303			def use_system_content(self, content=None):
304			clear_all(self._addon_data)
305			self._addon_data.content_type = "scap-security-guide"
306			self._addon_data.content_path = common.get_ssg_path()
307
308			def get_preferred_content(self, content):
309			if self._addon_data.content_path:
310			preferred_content = content.find_expected_usable_content(self._addon_data.content_path)
311			else:
312			preferred_content = content.select_main_usable_content()
313			return preferred_content
314
315			def get_preferred_tailoring(self, content):
316			tailoring_path = self._addon_data.tailoring_path
317			if tailoring_path:
318			if tailoring_path != str(content.tailoring.relative_to(content.root)):
319			msg = f"Expected a tailoring {tailoring_path}, but it couldn't be found"
320			raise content_handling.ContentHandlingError(msg)
321			return content.tailoring
322
323
324			class ObtainedContent:
325			"""
326			This class aims to assist the gathered files discovery -
327			the addon can downloaded files directly, or they can be extracted for an archive.
328			The class enables user to quickly understand what is available,
329			and whether the current set of contents is usable for further processing.
330			"""
331			def __init__(self, root):
332			self.labelled_files = dict()
333			self.datastream = None # type: Pathlib.Path
334			self.xccdf = None # type: Pathlib.Path
335			self.ovals = [] # type: List[Pathlib.Path]
336			self.tailoring = None # type: Pathlib.Path
337			self.archive = None # type: Pathlib.Path
338			self.verified = None # type: Pathlib.Path
339			self.root = pathlib.Path(root)
340
341			def record_verification(self, path):
342			"""
343			Declare a file as verified (typically by means of a checksum)
344			"""
345			path = pathlib.Path(path)
346			assert path in self.labelled_files
347			self.verified = path
348
349			def add_content_archive(self, fname):
350			"""
351			If files come from an archive, record this information using this function.
352			"""
353			path = pathlib.Path(fname)
354			self.labelled_files[path] = None
355			self.archive = path
356
357			def _assign_content_type(self, attribute_name, new_value):
358			old_value = getattr(self, attribute_name)
359			if old_value and old_value != new_value:
360			msg = (
361			f"When dealing with {attribute_name}, "
362			f"there was already the {old_value.name} when setting the new {new_value.name}")
363			raise content_handling.ContentHandlingError(msg)
364			setattr(self, attribute_name, new_value)
365
366			def add_file(self, fname, label=None):
367			if not label:
368			label = content_handling.identify_files([fname])[fname]
369			path = pathlib.Path(fname)
370			if label == content_handling.CONTENT_TYPES["TAILORING"]:
371			self._assign_content_type("tailoring", path)
372			elif label == content_handling.CONTENT_TYPES["DATASTREAM"]:
373			self._assign_content_type("datastream", path)
374			elif label == content_handling.CONTENT_TYPES["OVAL"]:
375			self.ovals.append(path)
376			elif label == content_handling.CONTENT_TYPES["XCCDF_CHECKLIST"]:
377			self._assign_content_type("xccdf", path)
378			self.labelled_files[path] = label
379
380			def _datastream_content(self):
381			if not self.datastream:
382			return None
383			if not self.datastream.exists():
384			return None
385			return self.datastream
386
387			def _xccdf_content(self):
388			if not self.xccdf or not self.ovals:
389			return None
390			some_ovals_exist = any([path.exists() for path in self.ovals])
391			if not (self.xccdf.exists() and some_ovals_exist):
392			return None
393			return self.xccdf
394
395			def find_expected_usable_content(self, relative_expected_content_path):
396			content_path = self.root / relative_expected_content_path
397			eligible_main_content = (self._datastream_content(), self._xccdf_content())
398
399			if content_path in eligible_main_content:
400			return content_path
401			else:
402			if not content_path.exists():
403			msg = f"Couldn't find '{content_path}' among the available content"
404			else:
405			msg = (
406			f"File '{content_path}' is not a valid datastream "
407			"or a valid XCCDF of a XCCDF-OVAL file tuple")
408			raise content_handling.ContentHandlingError(msg)
409
410			def select_main_usable_content(self):
411			if self._datastream_content():
412			return self._datastream_content()
413			elif self._xccdf_content():
414			return self._xccdf_content()
415			else:
416			msg = (
417			"Couldn't find a valid datastream or a valid XCCDF-OVAL file tuple "
418			"among the available content")
419			raise content_handling.ContentHandlingError(msg)
420

OpenSCAP / oscap-anaconda-addon

Pull Request — master (#219)

ContentBringer.reduce_files() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like