def _find_similar_file_for(self, file, parent_id, potential_matches):
hash_one = self.database.get_ssdeep_hash(file)
if hash_one:
id1 = '{}:{}'.format(parent_id, file)
for potential_match in potential_matches.files_included:
id2 = '{}:{}'.format(potential_matches.uid, potential_match)
hash_two = self.database.get_ssdeep_hash(potential_match)
if hash_two and get_ssdeep_comparison(hash_one, hash_two) > self.ssdeep_ignore_threshold:
yield [id1, id2], get_ssdeep_comparison(hash_one, hash_two)
def _find_similar_file_for(self, file, parent_id, potential_matches):
fo_one = self.database.get_object(uid=file)
id1 = '{}:{}'.format(parent_id, fo_one.get_uid())
hash_one = fo_one.processed_analysis['file_hashes']['ssdeep']
for potential_match in potential_matches.files_included:
fo_two = self.database.get_object(uid=potential_match)
id2 = '{}:{}'.format(potential_matches.get_uid(), fo_two.get_uid())
hash_two = fo_two.processed_analysis['file_hashes']['ssdeep']
if get_ssdeep_comparison(hash_one, hash_two) > self.SSDEEP_IGNORE:
yield [id1, id2], get_ssdeep_comparison(hash_one, hash_two)
def test_get_ssdeep_comparison():
factor = get_ssdeep_comparison(
'192:3xaGk2v7RNOrG4D9tVwTiGTUwMyKP3JDddt2vT3GiH3gnK:BHTWy66gnK',
'192:3xaGk2v7RNOrG4D9tVwTiGTUwMyKP3JDddt2vT3GK:B')
assert factor == 96, 'ssdeep similarity seems to be out of shape'