Files
sientia-dataops-laborious-l…/tests/laborious/activities/test_storage.py
vitor-aignosi a3da800cab SIENTIAPDE-1325
Refactor monitoring and metrics integration across various components

- Removed coverage options from `pyproject.toml`.
- Updated prediction metrics in `README.md` to replace `pipeline_name` with `workflow_name`.
- Upgraded `sientia-dataops-library` dependency version in `requirements-light.txt` and `requirements.txt`.
- Enhanced metrics handling in `laborious` activities, including `Activities`, `Gates`, `MLFlow`, and `OPC`, to utilize a new `MetricsController`.
- Refactored metric emission methods to improve clarity and consistency across the codebase.
- Updated tests to reflect changes in metrics handling and ensure proper functionality.
2025-11-04 16:49:10 -03:00

225 lines
6.8 KiB
Python

import datetime
from unittest.mock import ANY, AsyncMock, MagicMock, patch
from pytest import fixture, mark, raises
from sientia_do.notifications.models import NotificationLevel
from sientia_do.temporal.activities.postgres import Postgres
from laborious.activities.storage import Storage
metadata = {
'metadata': {
'model_id': 'test_model_id',
'model_name': 'test_model',
'workflow_name': 'test_workflow',
'schedule_name': 'test_schedule',
}
}
@fixture
@patch('laborious.activities.storage.MinioRepository')
def storage(mock_minio_repository):
return Storage(
host='localhost',
port=5432,
user='postgres',
password='postgres',
dbname='postgres',
min_connections=1,
max_connections=10,
minio_config={
'endpoint_url': 'localhost:9000',
'access_key': 'minio',
'secret_key': 'minio123',
'region_name': 'us-east-1',
'default_bucket': 'test',
},
logger=MagicMock(),
notification_handler=MagicMock(),
metrics_controller=AsyncMock(),
)
@patch('laborious.activities.storage.MinioRepository')
def test___init___not_hasattr(mock_minio_repository):
logger = MagicMock()
notification_handler = MagicMock()
metrics_controller = AsyncMock()
storage = Storage(
host='localhost',
port=5432,
user='postgres',
password='postgres',
dbname='postgres',
min_connections=1,
max_connections=10,
minio_config={
'endpoint_url': 'localhost:9000',
'access_key': 'minio',
'secret_key': 'minio123',
'region_name': 'us-east-1',
'default_bucket': 'test',
},
logger=logger,
notification_handler=notification_handler,
metrics_controller=metrics_controller,
)
assert isinstance(storage, Postgres)
mock_minio_repository.assert_called_once_with(
logger=logger,
notification_handler=notification_handler,
minio_endpoint_url='localhost:9000',
minio_access_key='minio',
minio_secret_key='minio123',
minio_region_name='us-east-1',
minio_default_bucket='test',
metrics_controller=metrics_controller,
)
@patch('laborious.activities.storage.MinioRepository')
def test___init___none_minio_repository(mock_minio_repository, storage):
storage.minio_repository = None
logger = MagicMock()
notification_handler = MagicMock()
metrics_controller = AsyncMock()
storage.__init__(
host='localhost',
port=5432,
user='postgres',
password='postgres',
dbname='postgres',
min_connections=1,
max_connections=10,
minio_config={
'endpoint_url': 'localhost:9000',
'access_key': 'minio',
'secret_key': 'minio123',
'region_name': 'us-east-1',
'default_bucket': 'test',
},
logger=logger,
notification_handler=notification_handler,
metrics_controller=metrics_controller,
)
mock_minio_repository.assert_called_once_with(
logger=logger,
notification_handler=notification_handler,
minio_endpoint_url='localhost:9000',
minio_access_key='minio',
minio_secret_key='minio123',
minio_region_name='us-east-1',
minio_default_bucket='test',
metrics_controller=metrics_controller,
)
@patch('laborious.activities.storage.MinioRepository')
def test___init___done_repository(mock_minio_repository, storage):
storage.__init__(
host='localhost',
port=5432,
user='postgres',
password='postgres',
dbname='postgres',
min_connections=1,
max_connections=10,
minio_config={
'endpoint_url': 'localhost:9000',
'access_key': 'minio',
'secret_key': 'minio123',
'region_name': 'us-east-1',
'default_bucket': 'test',
},
logger=MagicMock(),
notification_handler=MagicMock(),
metrics_controller=AsyncMock(),
)
mock_minio_repository.assert_not_called()
assert storage.minio_repository is not None
@mark.asyncio
async def test_query_to_minio_minio_repository_not_initialized(storage):
storage.minio_repository = None
with raises(ValueError) as e:
await storage.query_to_minio({})
assert str(e.value) == 'Minio repository not initialized'
@mark.asyncio
async def test_query_to_minio_not_data(storage):
storage.load_custom_query = AsyncMock(return_value=None)
result = await storage.query_to_minio({})
storage.load_custom_query.assert_called_once_with({})
assert result['success'] is False
assert result['message'] == 'No data returned from query'
@mark.asyncio
@patch('laborious.activities.storage.pd.DataFrame')
@patch('laborious.activities.storage.now')
async def test_query_to_minio_success(now, dataframe, storage):
data = [{'a': 1}, {'a': 2}, {'a': 3}]
storage.load_custom_query = AsyncMock(return_value=data)
now.return_value = datetime.datetime(2024, 1, 1, 0, 0, 0)
storage.minio_repository.store_dataframe_as_parquet = AsyncMock()
storage.minio_repository.minio_bucket = 'test'
result = await storage.query_to_minio({'object_prefix': 'test', **metadata})
dataframe.assert_called_once_with(data)
storage.minio_repository.store_dataframe_as_parquet.assert_called_once_with(
dataframe=dataframe.return_value,
uri='s3://test/test_2024-01-01_00-00-00.parquet',
object_name='test_2024-01-01_00-00-00.parquet',
metadata=metadata['metadata'],
)
assert result['success'] is True
assert result['object_key'] == 'test_2024-01-01_00-00-00.parquet'
assert result['uri'] == 's3://test/test_2024-01-01_00-00-00.parquet'
@mark.asyncio
async def test_query_to_minio_error(storage):
storage.send_notification = MagicMock()
storage.send_notification_async = AsyncMock()
storage.minio_repository.store_dataframe_as_parquet = AsyncMock()
storage.load_custom_query = AsyncMock(side_effect=Exception('test'))
result = await storage.query_to_minio({**metadata, 'object_prefix': 'test'})
assert result['success'] is False
assert result['message'] == 'test'
storage.send_notification_async.assert_called_once_with(
metadata=metadata['metadata'],
notification_id='ERROR_STORING_QUERY_TO_MINIO',
message='Error storing query to MinIO: test',
block='query_to_minio',
level=NotificationLevel.ERROR,
attachment_content=ANY,
)
def test_close(storage):
storage.minio_repository = MagicMock()
storage.close()
assert storage.minio_repository is None
def test___del__(storage):
storage.close = MagicMock()
storage.__del__()
storage.close.assert_called_once()