def main():
orphans = {}
elements_index = lib_search.ElementsIndex(message)
for elempath in lib_repo.get_element_paths_iterator():
oval_id = lib_repo.path_to_oval_id(elempath)
oval_ids = { oval_id }
upstream_ids = elements_index.find_upstream_ids(oval_ids, set())
downstream_ids = elements_index.find_downstream_ids(oval_ids, set())
#message("INFO", "OVAL ID '%s' had %i upstream ids and %i downstream ids" % (oval_id, len(upstream_ids), len(downstream_ids)))
if len(upstream_ids) == 0 and len(downstream_ids) == 0:
message("INFO", "Found Orphan '%s'" % oval_id)
orphans[oval_id] = elempath
response = input("\n :::: Remove all orphans? (N[o] / y[es]): ")
if response != 'y' and response != 'Y':
return
message("INFO", "\n\n")
for ok in orphans.keys():
message("INFO", "Deleting Orphan '%s'" % ok)
os.remove(orphans[ok])
def get_last(self):
for xml_file in lib_repo.get_element_paths_iterator():
if (self.tst_or_obj_or_ste in xml_file) and (self.family in xml_file):
current_id = int(lib_repo.path_to_oval_id(xml_file).split(':')[3])
if current_id > self.new_id:
self.new_id = current_id
self.path = os.path.split(xml_file)[0]
self.new_filename = os.path.split(xml_file)[1]
return
def get_last_def(self):
for xml_file in lib_repo.get_element_paths_iterator():
if 'vulnerability' in xml_file:
current_id = int(lib_repo.path_to_oval_id(xml_file).split(':')[3])
if current_id > self.new_id:
self.new_id = current_id
self.path = os.path.split(xml_file)[0]
self.new_filename = os.path.split(xml_file)[1]
return
def get_last_def(self):
for xml_file in lib_repo.get_element_paths_iterator():
if 'vulnerability' in xml_file:
current_id = int(
lib_repo.path_to_oval_id(xml_file).split(':')[3])
if current_id > self.new_id:
self.new_id = current_id
self.path = os.path.split(xml_file)[0]
self.new_filename = os.path.split(xml_file)[1]
return
def get_last(self):
for xml_file in lib_repo.get_element_paths_iterator():
if (self.tst_or_obj_or_ste in xml_file) and (self.family
in xml_file):
current_id = int(
lib_repo.path_to_oval_id(xml_file).split(':')[3])
if current_id > self.new_id:
self.new_id = current_id
self.path = os.path.split(xml_file)[0]
self.new_filename = os.path.split(xml_file)[1]
return
def document_iterator(self, paths=False):
""" Iterator yielding elements files in repo as indexable documents. """
if not paths:
# get all in repo
paths = lib_repo.get_element_paths_iterator()
for path in paths:
try:
document = lib_xml.get_element_metadata(path)
except lib_xml.InvalidPathError as e:
yield { 'path': e.path, 'deleted': True }
else:
document = self.whoosh_escape_document(document)
yield document
def document_iterator(self, paths=False):
""" Iterator yielding elements files in repo as indexable documents. """
if not paths:
# get all in repo
paths = lib_repo.get_element_paths_iterator()
for path in paths:
try:
document = lib_xml.get_element_metadata(path)
except lib_xml.InvalidPathError as e:
yield {'path': e.path, 'deleted': True}
except lib_xml.InvalidXmlError as e:
raise
else:
document = self.whoosh_escape_document(document)
yield document
def main():
orphans = {}
elements_index = lib_search.ElementsIndex(message)
for elempath in lib_repo.get_element_paths_iterator():
oval_id = lib_repo.path_to_oval_id(elempath)
oval_ids = { oval_id }
upstream_ids = elements_index.find_upstream_ids(oval_ids, set())
downstream_ids = elements_index.find_downstream_ids(oval_ids, set())
message("INFO", "OVAL ID '%s' had %i upstream ids and %i downstream ids" % (oval_id, len(upstream_ids), len(downstream_ids)))
if len(upstream_ids) == 0 and len(downstream_ids) == 0:
orphans[oval_id] = elempath
for ok in orphans.keys():
message("INFO", "Found Orphan '%s'" % ok)
os.remove(orphans[ok])
def main():
orphans = {}
elements_index = lib_search.ElementsIndex(message)
for elempath in lib_repo.get_element_paths_iterator():
oval_id = lib_repo.path_to_oval_id(elempath)
oval_ids = {oval_id}
upstream_ids = elements_index.find_upstream_ids(oval_ids, set())
downstream_ids = elements_index.find_downstream_ids(oval_ids, set())
message(
"INFO", "OVAL ID '%s' had %i upstream ids and %i downstream ids" %
(oval_id, len(upstream_ids), len(downstream_ids)))
if len(upstream_ids) == 0 and len(downstream_ids) == 0:
orphans[oval_id] = elempath
for ok in orphans.keys():
message("INFO", "Found Orphan '%s'" % ok)
os.remove(orphans[ok])
def main():
start_time = time.time()
tracking = dict()
elements_index = lib_search.ElementsIndex(message)
# getting all definitions
all_def_ids = set()
message('info', 'getting all definitions')
for defpath in lib_repo.get_definition_paths_iterator():
all_def_ids.add(lib_repo.path_to_oval_id(defpath))
message('info', 'found {0} definitions'.format(len(all_def_ids)))
# getting all element ids downstream from any definition
message('info', 'getting all downstream element ids')
all_downstream_ids = elements_index.find_downstream_ids(all_def_ids)
message('info',
'found {0} downstream element ids'.format(len(all_downstream_ids)))
# get elements that aren't in all_downstream_ids
message('info', 'checking all elements')
cur_element_type = None
for elempath in lib_repo.get_element_paths_iterator():
oval_id = lib_repo.path_to_oval_id(elempath)
element_type = lib_repo.get_element_type_from_oval_id(oval_id)
# skip definitions... we're only pruning child elements
if element_type == 'definition':
continue
# write status msg
if element_type != cur_element_type:
cur_element_type = element_type
i_element_type = 0
i_element_type = i_element_type + 1
sys.stdout.write(
'Analyzing {0}s: {1} \r'.format(
cur_element_type, i_element_type))
sys.stdout.flush()
# it's an orphan if it's not downsteam of a definition
track_as = 'orphan' if oval_id not in all_downstream_ids else 'in_use'
if not track_as in tracking:
tracking[track_as] = dict()
if not element_type in tracking[track_as]:
tracking[track_as][element_type] = set()
tracking[track_as][element_type].add(oval_id)
sys.stdout.write(
' \r'.
format(cur_element_type, i_element_type))
sys.stdout.flush()
# generate report
report = []
for track_as, elements_by_type in tracking.items():
report.append('\t{0}:'.format(track_as.replace('_', ' ').capitalize()))
for element_type, oval_ids in elements_by_type.items():
report.append('\t\t{0} {1}s'.format(len(oval_ids), element_type))
message('found', '\n'.join(report))
response = input("\n :::: Remove all orphans? (N[o] / y[es]): ")
if response.lower() == 'y':
orphan_ids = set()
for element_type, oval_ids in tracking['orphan'].items():
orphan_ids.update(oval_ids)
file_paths = elements_index.get_paths_from_ids(orphan_ids)
for file_path in file_paths:
message("INFO",
"Deleting Orphan '%s'" % os.path.basename(file_path))
os.remove(file_path)
seconds_elapsed = time.time() - start_time
message('info',
'Completed in {0}!'.format(format_duration(seconds_elapsed)))
def main():
start_time = time.time()
tracking = dict()
elements_index = lib_search.ElementsIndex(message)
# getting all definitions
all_def_ids = set()
message('info', 'getting all definitions')
for defpath in lib_repo.get_definition_paths_iterator():
all_def_ids.add(lib_repo.path_to_oval_id(defpath))
message('info', 'found {0} definitions'.format(len(all_def_ids)))
# getting all element ids downstream from any definition
message('info', 'getting all downstream element ids')
all_downstream_ids = elements_index.find_downstream_ids(all_def_ids)
message('info', 'found {0} downstream element ids'.format(len(all_downstream_ids)))
# get elements that aren't in all_downstream_ids
message('info', 'checking all elements')
cur_element_type = None
for elempath in lib_repo.get_element_paths_iterator():
oval_id = lib_repo.path_to_oval_id(elempath)
element_type = lib_repo.get_element_type_from_oval_id(oval_id)
# skip definitions... we're only pruning child elements
if element_type == 'definition':
continue
# write status msg
if element_type != cur_element_type:
cur_element_type = element_type
i_element_type = 0
i_element_type = i_element_type + 1
sys.stdout.write('Analyzing {0}s: {1} \r'.format(cur_element_type, i_element_type))
sys.stdout.flush()
# it's an orphan if it's not downsteam of a definition
track_as = 'orphan' if oval_id not in all_downstream_ids else 'in_use'
if not track_as in tracking:
tracking[track_as] = dict()
if not element_type in tracking[track_as]:
tracking[track_as][element_type] = set()
tracking[track_as][element_type].add(oval_id)
sys.stdout.write(' \r'.format(cur_element_type, i_element_type))
sys.stdout.flush()
# generate report
report = []
for track_as, elements_by_type in tracking.items():
report.append('\t{0}:'.format(track_as.replace('_', ' ').capitalize()))
for element_type, oval_ids in elements_by_type.items():
report.append('\t\t{0} {1}s'.format(len(oval_ids), element_type))
message('found', '\n'.join(report))
response = input("\n :::: Remove all orphans? (N[o] / y[es]): ")
if response.lower() == 'y':
orphan_ids = set()
for element_type, oval_ids in tracking['orphan'].items():
orphan_ids.update(oval_ids)
file_paths = elements_index.get_paths_from_ids(orphan_ids)
for file_path in file_paths:
message("INFO", "Deleting Orphan '%s'" % os.path.basename(file_path))
os.remove(file_path)
seconds_elapsed = time.time() - start_time
message('info','Completed in {0}!'.format(format_duration(seconds_elapsed)))
