def generic_search(self, search_dict, skip=0, limit=0, only_fo_parent_firmware=False):
try:
if isinstance(search_dict, str):
search_dict = json.loads(search_dict)
query = self.firmwares.find(search_dict, {'_id': 1}, skip=skip, limit=limit, sort=[('vendor', 1)])
result = [match['_id'] for match in query]
if len(result) < limit or limit == 0:
max_firmware_results = self.get_firmware_number(query=search_dict)
skip_fo = skip - max_firmware_results if skip > max_firmware_results else 0
limit_fo = limit - len(result) if limit > 0 else 0
if not only_fo_parent_firmware:
query = self.file_objects.find(search_dict, {'_id': 1}, skip=skip_fo, limit=limit_fo, sort=[('file_name', 1)])
result.extend([match['_id'] for match in query])
else: # only searching for parents of matching file objects
query = self.file_objects.find(search_dict, {'virtual_file_path': 1})
parent_uids = {uid for match in query for uid in match['virtual_file_path'].keys()}
query_filter = {'$nor': [{'_id': {'$nin': list(parent_uids)}}, search_dict]}
query = self.firmwares.find(query_filter, {'_id': 1}, skip=skip_fo, limit=limit_fo, sort=[('file_name', 1)])
parents = [match['_id'] for match in query]
result = remove_duplicates_from_list(result + parents)
except Exception as exception:
error_message = 'could not process search request: {} {}'.format(sys.exc_info()[0].__name__, exception)
logging.warning(error_message)
return error_message
return result
def _get_similar_files(self, fo_list: List[FileObject], exclusive_files: Dict[str, List[str]]) -> Tuple[List[list], dict]:
similar_files = []
similarity = {}
for parent_one, parent_two in combinations(fo_list, 2):
for file_one in exclusive_files[parent_one.uid]:
for similar_file_pair, value in self._find_similar_file_for(file_one, parent_one.uid, parent_two):
similar_files.append(similar_file_pair)
similarity[convert_uid_list_to_compare_id(similar_file_pair)] = value
similarity_sets = generate_similarity_sets(remove_duplicates_from_list(similar_files))
return similarity_sets, similarity
def get_all_uids_in_string(string):
result = re.findall(r'[a-f0-9]{64}_[0-9]+', string)
result = remove_duplicates_from_list(result)
result.sort()
return result
