self = <swh.indexer.tests.test_mimetype.TestMimetypePartitionIndexer testMethod=test__index_contents_with_indexed_data> def test__index_contents_with_indexed_data(self): """Indexing contents with existing data results in less indexed data """ _start, _end = [self.contents[0], self.contents[2]] # output hex ids start, end = map(hashutil.hash_to_bytes, (_start, _end)) data_indexed = [self.id0, self.id2] # given actual_results = self.indexer._index_contents( start, end, indexed=set(map(hash_to_bytes, data_indexed)) ) # craft the expected results expected_results = self.expected_results.copy() for already_indexed_key in data_indexed: expected_results.pop(already_indexed_key) > self.assert_results_ok(start, end, actual_results, expected_results) .tox/py3/lib/python3.7/site-packages/swh/indexer/tests/utils.py:732: _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ .tox/py3/lib/python3.7/site-packages/swh/indexer/tests/utils.py:692: in assert_results_ok actual_results = list(actual_results) .tox/py3/lib/python3.7/site-packages/swh/indexer/indexer.py:426: in _index_contents for sha1 in self._list_contents_to_index(partition_id, nb_partitions, indexed): _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ self = <swh.indexer.mimetype.MimetypePartitionIndexer object at 0x7ff7a4e0ee48> partition_id = b'\x01\xc97\x9d\xfc3\x809c\xd0|\x1c\xcct\x8d?\xe4\xc9k\xb5' nb_partitions = b'\x10;\xc0\x87\xdb\x1d&\xaf\xc3\xa0(?8f=\x08\x1e\x9b\x01\xe6' indexed = {b'\x01\xc97\x9d\xfc3\x809c\xd0|\x1c\xcct\x8d?\xe4\xc9k\xb5', b'\x10;\xc0\x87\xdb\x1d&\xaf\xc3\xa0(?8f=\x08\x1e\x9b\x01\xe6'} def _list_contents_to_index( self, partition_id: int, nb_partitions: int, indexed: Set[Sha1] ) -> Iterator[Sha1]: """Compute from storage the new contents to index in the partition_id . The already indexed contents are skipped. Args: partition_id: Index of the partition to fetch data from nb_partitions: Total number of partition indexed: Set of content already indexed. Yields: Sha1 id (bytes) of contents to index """ if not isinstance(partition_id, int) or not isinstance(nb_partitions, int): raise TypeError( > f"identifiers must be int, not {partition_id!r} and {nb_partitions!r}." ) E TypeError: identifiers must be int, not b'\x01\xc97\x9d\xfc3\x809c\xd0|\x1c\xcct\x8d?\xe4\xc9k\xb5' and b'\x10;\xc0\x87\xdb\x1d&\xaf\xc3\xa0(?8f=\x08\x1e\x9b\x01\xe6'. .tox/py3/lib/python3.7/site-packages/swh/indexer/indexer.py:395: TypeError