Changeset View
Changeset View
Standalone View
Standalone View
swh/journal/tests/test_write_replay.py
| # Copyright (C) 2019 The Software Heritage developers | # Copyright (C) 2019 The Software Heritage developers | ||||
| # See the AUTHORS file at the top-level directory of this distribution | # See the AUTHORS file at the top-level directory of this distribution | ||||
| # License: GNU General Public License version 3, or any later version | # License: GNU General Public License version 3, or any later version | ||||
| # See top-level LICENSE file for more information | # See top-level LICENSE file for more information | ||||
| import functools | import functools | ||||
| from unittest.mock import patch | |||||
| import attr | import attr | ||||
| from hypothesis import given, settings, HealthCheck | from hypothesis import given, settings, HealthCheck | ||||
| from hypothesis.strategies import lists | from hypothesis.strategies import lists | ||||
| from swh.model.hypothesis_strategies import object_dicts | from swh.model.hypothesis_strategies import object_dicts | ||||
| from swh.storage.in_memory import InMemoryStorage | from swh.storage import get_storage, HashCollision | ||||
| from swh.storage import HashCollision | |||||
| from swh.journal.replay import process_replay_objects | from swh.journal.replay import process_replay_objects | ||||
| from swh.journal.replay import process_replay_objects_content | from swh.journal.replay import process_replay_objects_content | ||||
| from .utils import MockedJournalClient, MockedKafkaWriter | from .utils import MockedJournalClient, MockedKafkaWriter | ||||
| storage_config = { | |||||
| 'cls': 'pipeline', | |||||
| 'steps': [ | |||||
| {'cls': 'validate'}, | |||||
| {'cls': 'memory', 'journal_writer': {'cls': 'memory'}}, | |||||
| ] | |||||
| } | |||||
| def empty_person_name_email(rev_or_rel): | def empty_person_name_email(rev_or_rel): | ||||
| """Empties the 'name' and 'email' fields of the author/committer fields | """Empties the 'name' and 'email' fields of the author/committer fields | ||||
| of a revision or release; leaving only the fullname.""" | of a revision or release; leaving only the fullname.""" | ||||
| if getattr(rev_or_rel, 'author', None): | if getattr(rev_or_rel, 'author', None): | ||||
| rev_or_rel = attr.evolve( | rev_or_rel = attr.evolve( | ||||
| rev_or_rel, | rev_or_rel, | ||||
| author=attr.evolve( | author=attr.evolve( | ||||
| rev_or_rel.author, | rev_or_rel.author, | ||||
| Show All 16 Lines | |||||
| @given(lists(object_dicts(), min_size=1)) | @given(lists(object_dicts(), min_size=1)) | ||||
| @settings(suppress_health_check=[HealthCheck.too_slow]) | @settings(suppress_health_check=[HealthCheck.too_slow]) | ||||
| def test_write_replay_same_order_batches(objects): | def test_write_replay_same_order_batches(objects): | ||||
| queue = [] | queue = [] | ||||
| replayer = MockedJournalClient(queue) | replayer = MockedJournalClient(queue) | ||||
| storage1 = InMemoryStorage() | with patch('swh.journal.writer.inmemory.InMemoryJournalWriter', | ||||
| storage1.journal_writer = MockedKafkaWriter(queue) | return_value=MockedKafkaWriter(queue)): | ||||
| storage1 = get_storage(**storage_config) | |||||
| for (obj_type, obj) in objects: | for (obj_type, obj) in objects: | ||||
| obj = obj.copy() | obj = obj.copy() | ||||
| if obj_type == 'origin_visit': | if obj_type == 'origin_visit': | ||||
| storage1.origin_add_one({'url': obj['origin']}) | storage1.origin_add_one({'url': obj['origin']}) | ||||
| storage1.origin_visit_upsert([obj]) | storage1.origin_visit_upsert([obj]) | ||||
| else: | else: | ||||
| if obj_type == 'content' and obj.get('status') == 'absent': | if obj_type == 'content' and obj.get('status') == 'absent': | ||||
| obj_type = 'skipped_content' | obj_type = 'skipped_content' | ||||
| method = getattr(storage1, obj_type + '_add') | method = getattr(storage1, obj_type + '_add') | ||||
| try: | try: | ||||
| method([obj]) | method([obj]) | ||||
| except HashCollision: | except HashCollision: | ||||
| pass | pass | ||||
| queue_size = len(queue) | queue_size = len(queue) | ||||
| assert replayer.max_messages == 0 | assert replayer.max_messages == 0 | ||||
| replayer.max_messages = queue_size | replayer.max_messages = queue_size | ||||
| storage2 = InMemoryStorage() | storage2 = get_storage(**storage_config) | ||||
| worker_fn = functools.partial(process_replay_objects, storage=storage2) | worker_fn = functools.partial(process_replay_objects, storage=storage2) | ||||
| nb_messages = 0 | nb_messages = 0 | ||||
| while nb_messages < queue_size: | while nb_messages < queue_size: | ||||
| nb_messages += replayer.process(worker_fn) | nb_messages += replayer.process(worker_fn) | ||||
| assert replayer.consumer.committed | assert replayer.consumer.committed | ||||
| for attr_name in ('_contents', '_directories', | for attr_name in ('_contents', '_directories', | ||||
| Show All 21 Lines | |||||
| @given(lists(object_dicts(), min_size=1)) | @given(lists(object_dicts(), min_size=1)) | ||||
| @settings(suppress_health_check=[HealthCheck.too_slow]) | @settings(suppress_health_check=[HealthCheck.too_slow]) | ||||
| def test_write_replay_content(objects): | def test_write_replay_content(objects): | ||||
| queue = [] | queue = [] | ||||
| replayer = MockedJournalClient(queue) | replayer = MockedJournalClient(queue) | ||||
| storage1 = InMemoryStorage() | with patch('swh.journal.writer.inmemory.InMemoryJournalWriter', | ||||
| storage1.journal_writer = MockedKafkaWriter(queue) | return_value=MockedKafkaWriter(queue)): | ||||
| storage1 = get_storage(**storage_config) | |||||
| contents = [] | contents = [] | ||||
| for (obj_type, obj) in objects: | for (obj_type, obj) in objects: | ||||
| obj = obj.copy() | obj = obj.copy() | ||||
| if obj_type == 'content': | if obj_type == 'content': | ||||
| # avoid hash collision | # avoid hash collision | ||||
| if not storage1.content_find(obj): | if not storage1.content_find(obj): | ||||
| if obj.get('status') != 'absent': | if obj.get('status') != 'absent': | ||||
| storage1.content_add([obj]) | storage1.content_add([obj]) | ||||
| contents.append(obj) | contents.append(obj) | ||||
| queue_size = len(queue) | queue_size = len(queue) | ||||
| assert replayer.max_messages == 0 | assert replayer.max_messages == 0 | ||||
| replayer.max_messages = queue_size | replayer.max_messages = queue_size | ||||
| storage2 = InMemoryStorage() | storage2 = get_storage(**storage_config) | ||||
| worker_fn = functools.partial(process_replay_objects_content, | worker_fn = functools.partial(process_replay_objects_content, | ||||
| src=storage1.objstorage, | src=storage1.objstorage, | ||||
| dst=storage2.objstorage) | dst=storage2.objstorage) | ||||
| nb_messages = 0 | nb_messages = 0 | ||||
| while nb_messages < queue_size: | while nb_messages < queue_size: | ||||
| nb_messages += replayer.process(worker_fn) | nb_messages += replayer.process(worker_fn) | ||||
| # only content with status visible will be copied in storage2 | # only content with status visible will be copied in storage2 | ||||
| expected_objstorage_state = { | expected_objstorage_state = { | ||||
| c['sha1']: c['data'] for c in contents if c['status'] == 'visible' | c['sha1']: c['data'] for c in contents if c['status'] == 'visible' | ||||
| } | } | ||||
| assert expected_objstorage_state == storage2.objstorage.state | assert expected_objstorage_state == storage2.objstorage.state | ||||