Changeset View
Changeset View
Standalone View
Standalone View
swh/indexer/tests/test_origin_metadata.py
# Copyright (C) 2018-2019 The Software Heritage developers | # Copyright (C) 2018-2019 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 pytest | import pytest | ||||
from unittest import mock | from unittest.mock import patch | ||||
from swh.objstorage.objstorage_in_memory import InMemoryObjStorage | |||||
from swh.model.hashutil import hash_to_bytes | from swh.model.hashutil import hash_to_bytes | ||||
from swh.storage.in_memory import Storage | |||||
from swh.indexer.metadata import OriginMetadataIndexer | from swh.indexer.metadata import OriginMetadataIndexer | ||||
from swh.indexer.storage.in_memory import IndexerStorage | |||||
from .utils import fill_storage, fill_obj_storage, BASE_TEST_CONFIG | from .utils import BASE_TEST_CONFIG, YARN_PARSER_METADATA | ||||
from .test_metadata import REVISION_METADATA_CONFIG | from .test_metadata import REVISION_METADATA_CONFIG | ||||
ORIGIN_HEAD_CONFIG = { | ORIGIN_HEAD_CONFIG = { | ||||
**BASE_TEST_CONFIG, | **BASE_TEST_CONFIG, | ||||
'tools': { | 'tools': { | ||||
'name': 'origin-metadata', | 'name': 'origin-metadata', | ||||
'version': '0.0.1', | 'version': '0.0.1', | ||||
'configuration': {}, | 'configuration': {}, | ||||
}, | }, | ||||
'tasks': { | 'tasks': { | ||||
'revision_metadata': 'revision_metadata', | 'revision_metadata': 'revision_metadata', | ||||
'origin_intrinsic_metadata': 'origin_intrinsic_metadata', | 'origin_intrinsic_metadata': 'origin_intrinsic_metadata', | ||||
} | } | ||||
} | } | ||||
@pytest.mark.db | @pytest.fixture | ||||
ardumont: this is voluntary because during the debian build for now, test depending on this won't work. | |||||
@mock.patch('swh.indexer.metadata.RevisionMetadataIndexer.parse_config_file') | def origin_metadata_indexer(): | ||||
@mock.patch('swh.indexer.origin_head.OriginHeadIndexer.parse_config_file') | prefix = 'swh.indexer.' | ||||
@mock.patch('swh.indexer.storage.in_memory.IndexerStorage') | suffix = '.parse_config_file' | ||||
@mock.patch('swh.storage.in_memory.Storage') | with patch(prefix + 'metadata.OriginMetadataIndexer' + suffix) as omi, \ | ||||
def test_full_origin_metadata_indexer( | patch(prefix + 'origin_head.OriginHeadIndexer' + suffix) as ohi, \ | ||||
storage_mock, idx_storage_mock, origin_head_parse_config, | patch(prefix + 'metadata.RevisionMetadataIndexer' + suffix) as rmi: | ||||
revision_metadata_parse_config): | omi.return_value = BASE_TEST_CONFIG | ||||
# Always returns the same instance of the idx storage, because | ohi.return_value = ORIGIN_HEAD_CONFIG | ||||
# this function is called by each of the three indexers. | rmi.return_value = REVISION_METADATA_CONFIG | ||||
objstorage = InMemoryObjStorage() | yield OriginMetadataIndexer() | ||||
storage = Storage() | |||||
Not Done Inline Actionsnevermind, it's indeed an in-memory storage, i missed that initially ;) ardumont: nevermind, it's indeed an in-memory storage, i missed that initially ;) | |||||
idx_storage = IndexerStorage() | |||||
def test_origin_metadata_indexer( | |||||
origin_head_parse_config.return_value = ORIGIN_HEAD_CONFIG | idx_storage, storage, obj_storage, origin_metadata_indexer): | ||||
revision_metadata_parse_config.return_value = REVISION_METADATA_CONFIG | |||||
storage_mock.return_value = storage | |||||
idx_storage_mock.return_value = idx_storage | |||||
fill_obj_storage(objstorage) | |||||
fill_storage(storage) | |||||
# TODO: find a better way to share the ContentMetadataIndexer use | |||||
# the same objstorage instance. | |||||
import swh.objstorage | |||||
old_inmem_objstorage = swh.objstorage._STORAGE_CLASSES['memory'] | |||||
swh.objstorage._STORAGE_CLASSES['memory'] = lambda: objstorage | |||||
try: | |||||
indexer = OriginMetadataIndexer() | indexer = OriginMetadataIndexer() | ||||
indexer.storage = storage | |||||
indexer.idx_storage = idx_storage | |||||
indexer.run(["git+https://github.com/librariesio/yarn-parser"]) | indexer.run(["git+https://github.com/librariesio/yarn-parser"]) | ||||
finally: | |||||
swh.objstorage._STORAGE_CLASSES['memory'] = old_inmem_objstorage | |||||
origin = storage.origin_get({ | origin = storage.origin_get({ | ||||
'type': 'git', | 'type': 'git', | ||||
'url': 'https://github.com/librariesio/yarn-parser'}) | 'url': 'https://github.com/librariesio/yarn-parser'}) | ||||
rev_id = hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f') | rev_id = hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f') | ||||
metadata = { | |||||
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0', | |||||
'url': | |||||
'https://github.com/librariesio/yarn-parser#readme', | |||||
'codeRepository': | |||||
'git+git+https://github.com/librariesio/yarn-parser.git', | |||||
'author': [{ | |||||
'type': 'Person', | |||||
'name': 'Andrew Nesbitt' | |||||
}], | |||||
'license': 'https://spdx.org/licenses/AGPL-3.0', | |||||
'version': '1.0.0', | |||||
'description': | |||||
'Tiny web service for parsing yarn.lock files', | |||||
'issueTracker': | |||||
'https://github.com/librariesio/yarn-parser/issues', | |||||
'name': 'yarn-parser', | |||||
'keywords': ['yarn', 'parse', 'lock', 'dependencies'], | |||||
} | |||||
rev_metadata = { | rev_metadata = { | ||||
'id': rev_id, | 'id': rev_id, | ||||
'translated_metadata': metadata, | 'translated_metadata': YARN_PARSER_METADATA, | ||||
'mappings': ['npm'], | 'mappings': ['npm'], | ||||
} | } | ||||
origin_metadata = { | origin_metadata = { | ||||
'origin_id': origin['id'], | 'origin_id': origin['id'], | ||||
'from_revision': rev_id, | 'from_revision': rev_id, | ||||
'metadata': metadata, | 'metadata': YARN_PARSER_METADATA, | ||||
'mappings': ['npm'], | 'mappings': ['npm'], | ||||
} | } | ||||
results = list(indexer.idx_storage.revision_metadata_get([rev_id])) | results = list(indexer.idx_storage.revision_metadata_get([rev_id])) | ||||
for result in results: | for result in results: | ||||
del result['tool'] | del result['tool'] | ||||
assert results == [rev_metadata] | assert results == [rev_metadata] | ||||
results = list(indexer.idx_storage.origin_intrinsic_metadata_get([ | results = list(indexer.idx_storage.origin_intrinsic_metadata_get([ | ||||
origin['id']])) | origin['id']])) | ||||
for result in results: | for result in results: | ||||
del result['tool'] | del result['tool'] | ||||
assert results == [origin_metadata] | assert results == [origin_metadata] |
this is voluntary because during the debian build for now, test depending on this won't work.