Code import - branch 0.5.0

tests/laborious/utils/filters/test_conditional_filters.py

@@ -0,0 +1,44 @@
+from pandas import DataFrame
+
+from laborious.utils.filters.conditional_filters import (
+    filter_empty_data,
+    filter_specific_variables_null_values,
+)
+
+
+def test_filter_specific_variables_null_values():
+    assert (
+        filter_specific_variables_null_values(
+            DataFrame({'variable': ['variable1', 'variable2'], 'value': [1, 2]}),
+            config={'variables': ['variable2']},
+        )
+        is False
+    )
+
+
+def test_filter_specific_variables_null_values_with_empty_data():
+    assert (
+        filter_specific_variables_null_values(DataFrame(), config={'variables': ['variable2']})
+        is False
+    )
+
+
+def test_filter_specific_variables_null_values_with_null_values():
+    assert (
+        filter_specific_variables_null_values(
+            DataFrame({'variable': ['variable1', 'variable2'], 'value': [1, None]}),
+            config={'variables': ['variable2']},
+        )
+        is True
+    )
+
+
+def test_filter_empty_data():
+    assert filter_empty_data(DataFrame(), {}) is True
+
+
+def test_filter_empty_data_with_data():
+    assert (
+        filter_empty_data(DataFrame({'variable': ['variable1', 'variable2'], 'value': [1, 2]}), {})
+        is False
+    )

tests/laborious/utils/filters/test_mlflow_filters.py

@@ -0,0 +1,23 @@
+from pandas import DataFrame
+
+from laborious.utils.filters.mlflow_filters import api_error_filter, nan_values_filter
+
+
+def test_api_error_filter_invalid_response():
+    assert api_error_filter(None, {}) is True  # NOSONAR
+
+
+def test_api_error_filter_valid_response_fail():
+    assert api_error_filter({'success': False}, {}) is True
+
+
+def test_api_error_filter_valid_response_success():
+    assert api_error_filter({'success': True}, {}) is False
+
+
+def test_nan_values_filter_all_nan_values():
+    assert nan_values_filter(DataFrame({'variable': [None, None]}), {}) is True
+
+
+def test_nan_values_filter_no_nan_values():
+    assert nan_values_filter(DataFrame({'variable': [1, 2]}), {}) is False

tests/laborious/utils/models/test_minio_dataframe_payload.py

@@ -0,0 +1,266 @@
+from datetime import datetime
+from io import BytesIO
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+from pandas import DataFrame
+
+from laborious.utils.models.minio_dataframe_payload import (
+    MinioDataFramePayload,
+    _build_object_key,
+)
+
+
+def test_parse_object_timestamp_hyphenated_model():
+    key = 'predictions/sched/my-long-model-initial-2024-06-15_10-30-45.parquet'
+    ts = MinioDataFramePayload.parse_object_timestamp(key)
+    assert ts == datetime(2024, 6, 15, 10, 30, 45)
+
+
+def test_parse_object_timestamp_transform():
+    key = 'p/m-transform-2024-01-02_03-04-05.parquet'
+    ts = MinioDataFramePayload.parse_object_timestamp(key)
+    assert ts == datetime(2024, 1, 2, 3, 4, 5)
+
+
+def test_parse_object_timestamp_invalid():
+    assert MinioDataFramePayload.parse_object_timestamp('bad.parquet') is None
+
+
+def test_estimate_size_bytes_returns_positive_for_nonempty_frame():
+    df = DataFrame({'a': [1, 2]})
+    size = MinioDataFramePayload.estimate_size_bytes(df)
+    assert isinstance(size, int)
+    assert size > 0
+
+
+def test_cleanup_prefix_when_offloaded_returns_object_prefix():
+    payload = MinioDataFramePayload(
+        last_timestamp='t',
+        data=None,
+        object_key='training_datasets/m/m-initial-2024-01-01_00-00-00.parquet',
+        object_prefix='training_datasets/m',
+    )
+    assert MinioDataFramePayload.cleanup_prefix(payload) == 'training_datasets/m'
+
+
+def test_cleanup_prefix_when_inline_returns_none():
+    payload = MinioDataFramePayload(last_timestamp='t', data={'x': [1]}, object_key=None)
+    assert MinioDataFramePayload.cleanup_prefix(payload) is None
+
+
+def test_has_data_true_when_object_key_set():
+    payload = MinioDataFramePayload(last_timestamp='t', data=None, object_key='k')
+    assert payload.has_data() is True
+
+
+@pytest.mark.asyncio
+async def test_retrieve_inline_dict_as_dataframe():
+    payload = MinioDataFramePayload(last_timestamp='t', data={'a': [1, 2]})
+    minio = AsyncMock()
+    out = await payload.retrieve(minio, {'metadata': {}})
+    assert list(out.columns) == ['a']
+    minio.download_file.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_retrieve_downloads_parquet_when_offloaded():
+    source = DataFrame({'a': [1, 2]})
+    buf = BytesIO()
+    source.to_parquet(buf, engine='pyarrow', index=True)
+    file_bytes = buf.getvalue()
+
+    payload = MinioDataFramePayload(
+        last_timestamp='t',
+        data=None,
+        object_key='training_datasets/m/f.parquet',
+        object_prefix='training_datasets/m',
+    )
+    minio = AsyncMock()
+    minio.download_file = AsyncMock(return_value=file_bytes)
+
+    out = await payload.retrieve(minio, {'metadata': {}})
+
+    minio.download_file.assert_awaited_once_with(
+        object_name='training_datasets/m/f.parquet',
+        metadata={'metadata': {}},
+    )
+    assert list(out.columns) == ['a']
+
+
+def test_build_object_key():
+    key, prefix = _build_object_key('my-model', 'initial', '2024-01-01_00-00-00')
+    assert key == 'prediction_datasets/my-model/my-model-initial-2024-01-01_00-00-00.parquet'
+    assert prefix == 'prediction_datasets/my-model'
+
+
+def test_build_object_key_strips_slashes():
+    key, prefix = _build_object_key(' /my-model/ ', 'transform', '2024-06-15_10-30-45')
+    assert prefix == 'prediction_datasets/my-model'
+    assert key.startswith('prediction_datasets/my-model/')
+
+
+def test_estimate_size_bytes_fallback():
+    df = DataFrame({'a': [1, 2]})
+    with patch.object(df, 'to_dict', side_effect=RuntimeError('to_dict failed')):
+        size = MinioDataFramePayload.estimate_size_bytes(df)
+    assert isinstance(size, int)
+    assert size > 0
+
+
+def test_parse_object_timestamp_bad_datetime():
+    key = 'p/m-initial-9999-99-99_99-99-99.parquet'
+    assert MinioDataFramePayload.parse_object_timestamp(key) is None
+
+
+@pytest.mark.asyncio
+async def test_retrieve_empty_when_no_data():
+    payload = MinioDataFramePayload(last_timestamp='t', data=None, object_key=None)
+    minio = AsyncMock()
+    out = await payload.retrieve(minio, {})
+    assert out.empty
+    minio.download_file.assert_not_called()
+
+
+@pytest.mark.asyncio
+@patch('laborious.utils.models.minio_dataframe_payload.now')
+async def test_from_dataframe_none(mock_now):
+    mock_now.return_value = datetime(2024, 1, 1, 0, 0, 0)
+    minio = AsyncMock()
+    result = await MinioDataFramePayload.from_dataframe(
+        dataframe=None,
+        minio_repo=minio,
+        model_name='m',
+        operation='initial',
+        status={'success': False, 'message': 'no data'},
+    )
+    assert result.data is None
+    assert result.status == {'success': False, 'message': 'no data'}
+    assert result.object_key is None
+
+
+@pytest.mark.asyncio
+@patch('laborious.utils.models.minio_dataframe_payload.now')
+async def test_from_dataframe_empty(mock_now):
+    mock_now.return_value = datetime(2024, 1, 1, 0, 0, 0)
+    minio = AsyncMock()
+    mock_df = MagicMock()
+    mock_df.__bool__ = MagicMock(return_value=True)
+    mock_df.empty = True
+    result = await MinioDataFramePayload.from_dataframe(
+        dataframe=mock_df,
+        minio_repo=minio,
+        model_name='m',
+        operation='initial',
+    )
+    assert result.data is None
+    assert result.object_key is None
+
+
+def _mock_dataframe(data_dict, timestamp_values=None):
+    """Build a MagicMock that behaves enough like a DataFrame for from_dataframe."""
+    mock_df = MagicMock()
+    mock_df.__bool__ = MagicMock(return_value=True)
+    mock_df.empty = False
+    if timestamp_values is None:
+        timestamp_values = data_dict.get('timestamp', ['2024-01-01'])
+    ts_col = MagicMock()
+    ts_col.values.tolist.return_value = timestamp_values
+    mock_df.__getitem__ = MagicMock(return_value=ts_col)
+    mock_df.to_dict.return_value = data_dict
+    buf = BytesIO()
+    DataFrame(data_dict).to_parquet(buf, engine='pyarrow', index=True)
+    mock_df.to_parquet = MagicMock(side_effect=lambda b, **kw: b.write(buf.getvalue()))
+    return mock_df
+
+
+@pytest.mark.asyncio
+@patch('laborious.utils.models.minio_dataframe_payload.OFFLOAD_THRESHOLD_BYTES', 10**9)
+async def test_from_dataframe_inline():
+    minio = AsyncMock()
+    df = _mock_dataframe({'timestamp': ['2024-01-01'], 'value': [42]})
+    result = await MinioDataFramePayload.from_dataframe(
+        dataframe=df,
+        minio_repo=minio,
+        model_name='m',
+        operation='initial',
+    )
+    assert result.data is not None
+    assert result.object_key is None
+    assert result.last_timestamp == '2024-01-01'
+
+
+@pytest.mark.asyncio
+@patch('laborious.utils.models.minio_dataframe_payload.now')
+@patch('laborious.utils.models.minio_dataframe_payload.OFFLOAD_THRESHOLD_BYTES', 0)
+async def test_from_dataframe_offloaded(mock_now):
+    mock_now.return_value = datetime(2024, 1, 1, 0, 0, 0)
+    minio = AsyncMock()
+    minio.upload_file = AsyncMock(return_value={'minio_object_name': 'full/key.parquet'})
+    minio.bucket = 'test-bucket'
+
+    df = _mock_dataframe({'timestamp': ['2024-01-01'], 'value': [42]})
+    result = await MinioDataFramePayload.from_dataframe(
+        dataframe=df,
+        minio_repo=minio,
+        model_name='m',
+        operation='initial',
+        workflow_metadata={'wf': 'data'},
+    )
+    assert result.data is None
+    assert result.object_key == 'full/key.parquet'
+    assert result.bucket == 'test-bucket'
+    assert result.uri == 's3://test-bucket/full/key.parquet'
+    minio.upload_file.assert_awaited_once()
+
+
+def test_from_dict_inline():
+    raw = {
+        'last_timestamp': '2024-01-01T00:00:00+00:00',
+        'status': None,
+        'data': {'col1': {0: 'val1'}},
+        'bucket': None,
+        'object_key': None,
+        'object_prefix': None,
+        'uri': None,
+    }
+    payload = MinioDataFramePayload.from_dict(raw)
+    assert isinstance(payload, MinioDataFramePayload)
+    assert payload.last_timestamp == '2024-01-01T00:00:00+00:00'
+    assert payload.data == {'col1': {0: 'val1'}}
+    assert payload.object_key is None
+
+
+def test_from_dict_offloaded():
+    raw = {
+        'last_timestamp': '2024-06-15T10:30:45+00:00',
+        'status': {'success': True},
+        'data': None,
+        'bucket': 'my-bucket',
+        'object_key': 'training_datasets/model/model-initial-2024-06-15_10-30-45.parquet',
+        'object_prefix': 'training_datasets/model',
+        'uri': 's3://my-bucket/training_datasets/model/model-initial-2024-06-15_10-30-45.parquet',
+    }
+    payload = MinioDataFramePayload.from_dict(raw)
+    assert isinstance(payload, MinioDataFramePayload)
+    assert payload.data is None
+    assert payload.bucket == 'my-bucket'
+    assert payload.object_key == raw['object_key']
+    assert payload.object_prefix == 'training_datasets/model'
+    assert payload.uri == raw['uri']
+    assert payload.status == {'success': True}
+
+
+def test_from_dict_minimal_keys():
+    raw = {'last_timestamp': '2024-01-01'}
+    payload = MinioDataFramePayload.from_dict(raw)
+    assert payload.last_timestamp == '2024-01-01'
+    assert payload.data is None
+    assert payload.bucket is None
+    assert payload.object_key is None
+
+
+def test_from_dict_passthrough_existing_instance():
+    original = MinioDataFramePayload(last_timestamp='2024-01-01', data={'a': 1}, bucket='b')
+    result = MinioDataFramePayload.from_dict(original)
+    assert result is original

tests/laborious/utils/repository/test_opc_repository.py

@@ -0,0 +1,610 @@
+import asyncio
+import json
+from datetime import datetime
+from unittest.mock import ANY, AsyncMock, MagicMock, Mock, patch
+
+import pytest
+from asyncua.crypto.security_policies import SecurityPolicyBasic256
+from asyncua.ua.uaerrors import BadNodeIdUnknown, BadSessionIdInvalid
+from sientia_do.notifications.models import NotificationLevel
+
+from laborious.utils.repository.opc_repository import (
+    OpcClientAlreadyExistsError,
+    OpcClientNotInitializedError,
+    OpcRepository,
+    OpcSessionAlreadyConnectedError,
+    is_reconnectable_opcua_bad,
+)
+
+
+@pytest.fixture
+def mock_logger():
+    return Mock()
+
+
+@pytest.fixture
+def opc_repository(mock_logger):
+    repository = OpcRepository(
+        opc_id='test_repo',
+        server_name='test_server',
+        url='opc.tcp://localhost:4840',
+        logger=mock_logger,
+        notification_handler=Mock(),
+        reconnection_interval=60,
+        server_uri='urn:test:server',
+        cert_path='/path/to/cert.pem',
+        private_key_path='/path/to/key.pem',
+        server_cert_path='/path/to/server_cert.pem',
+        metrics_controller=AsyncMock(),
+    )
+    repository.disconnection_interval = 0.1
+    repository.send_notification = MagicMock()
+    repository.send_notification_async = AsyncMock()
+    repository.emit_metric = AsyncMock()
+    repository.info = MagicMock()
+    repository.error = MagicMock()
+    repository.warning = MagicMock()
+    repository.debug = MagicMock()
+    repository._session_ready.set()
+    return repository
+
+
+@pytest.fixture
+def mock_client():
+    with patch('laborious.utils.repository.opc_repository.Client') as mock:
+        client_instance = AsyncMock()
+        mock.return_value = client_instance
+        yield client_instance
+
+
+metadata = {
+    'metadata': {
+        'model_id': 'test_model',
+        'model_name': 'test_model',
+        'workflow_name': 'test_workflow',
+        'schema_name': 'test_schedule',
+    },
+}
+
+
+def test_init(opc_repository):
+    assert opc_repository.id == 'test_repo'
+    assert opc_repository.server_name == 'test_server'
+    assert opc_repository.url == 'opc.tcp://localhost:4840'
+    assert opc_repository.server_uri == 'urn:test:server'
+    assert opc_repository.cert_path == '/path/to/cert.pem'
+    assert opc_repository.private_key_path == '/path/to/key.pem'
+    assert opc_repository.server_cert_path == '/path/to/server_cert.pem'
+    assert opc_repository.reconnection_interval == 60
+    assert opc_repository.client is None
+    assert opc_repository.last_reconnection_time is None
+
+
+@pytest.mark.asyncio
+async def test_set_security(opc_repository, mock_client):
+    opc_repository.client = mock_client
+    await opc_repository.set_security()
+
+    mock_client.application_uri = 'urn:test:server'
+    mock_client.set_security.assert_called_once_with(
+        SecurityPolicyBasic256,
+        certificate='/path/to/cert.pem',
+        private_key='/path/to/key.pem',
+        server_certificate='/path/to/server_cert.pem',
+    )
+    assert mock_client.secure_channel_timeout == 600_000
+    assert mock_client.session_timeout == 600_000
+
+
+@pytest.mark.asyncio
+async def test_set_security_missing_certificates(opc_repository):
+    opc_repository.cert_path = None
+    opc_repository.private_key_path = None
+
+    try:
+        await opc_repository.set_security()
+    except ValueError as e:
+        assert str(e) == 'Certificate and private key paths must be provided for secure connection.'
+
+
+@pytest.mark.asyncio
+async def test_set_security_missing_client(opc_repository):
+    opc_repository.client = None
+    try:
+        await opc_repository.set_security()
+    except ValueError as e:
+        assert str(e) == 'Client must be initialized before setting security'
+
+
+@pytest.mark.asyncio
+async def test_connect_with_security(opc_repository, mock_client):
+    opc_repository._create_client = AsyncMock()
+    opc_repository._open_session = AsyncMock(return_value=(True, {}))
+    result = await opc_repository.connect()
+
+    opc_repository._create_client.assert_called_once()
+    opc_repository._open_session.assert_called_once()
+    assert result == (True, {})
+
+
+@pytest.mark.asyncio
+async def test_connect_without_security(opc_repository, mock_client):
+    opc_repository.cert_path = None
+    opc_repository._create_client = AsyncMock()
+    opc_repository._open_session = AsyncMock(return_value=(True, {}))
+    opc_repository.set_security = AsyncMock()
+    result = await opc_repository.connect()
+
+    opc_repository._create_client.assert_called_once()
+    opc_repository._open_session.assert_called_once()
+    opc_repository.set_security.assert_not_called()
+    assert result == (True, {})
+
+
+@pytest.mark.asyncio
+async def test_connect_raises_when_session_already_open(opc_repository, mock_client):
+    opc_repository.client = mock_client
+    proto = MagicMock()
+    proto.state = 'open'
+    mock_client.uaclient = MagicMock(protocol=proto)
+
+    with pytest.raises(OpcSessionAlreadyConnectedError, match='disconnect'):
+        await opc_repository.connect()
+
+
+@pytest.mark.asyncio
+async def test_create_client_raises_when_client_exists(opc_repository, mock_client):
+    opc_repository.client = mock_client
+
+    with pytest.raises(OpcClientAlreadyExistsError, match='already exists'):
+        await opc_repository._create_client()
+
+
+@pytest.mark.asyncio
+async def test_open_session_success(opc_repository):
+    closed_proto = MagicMock()
+    closed_proto.state = 'closed'
+    opc_repository.client = AsyncMock()
+    opc_repository.client.uaclient = MagicMock(protocol=closed_proto)
+    opc_repository.client.session_timeout = 600_000
+    opc_repository.client.secure_channel_timeout = 600_000
+
+    open_proto = MagicMock()
+    open_proto.state = 'open'
+    open_proto.authentication_token = 'tok'
+
+    async def connect_side_effect():
+        opc_repository.client.uaclient.protocol = open_proto
+
+    opc_repository.client.connect = AsyncMock(side_effect=connect_side_effect)
+
+    result = await opc_repository._open_session()
+
+    opc_repository.client.connect.assert_called_once()
+    assert opc_repository.last_reconnection_time is None
+    assert result == (True, {})
+    assert opc_repository._session_ready.is_set()
+
+
+@pytest.mark.asyncio
+async def test_open_session_raises_when_already_connected(opc_repository, mock_client):
+    opc_repository.client = mock_client
+    proto = MagicMock()
+    proto.state = 'open'
+    mock_client.uaclient = MagicMock(protocol=proto)
+
+    with pytest.raises(OpcSessionAlreadyConnectedError, match='disconnect'):
+        await opc_repository._open_session()
+
+
+@pytest.mark.asyncio
+async def test_open_session_fail(opc_repository):
+    opc_repository._disconnect_locked = AsyncMock()
+    opc_repository.client = MagicMock()
+    opc_repository.client.uaclient = MagicMock(protocol=MagicMock(state='closed'))
+    opc_repository.client.connect = AsyncMock(side_effect=Exception('Test error'))
+
+    is_connected, error_data = await opc_repository._open_session()
+
+    opc_repository._disconnect_locked.assert_called_once()
+    opc_repository.client.connect.assert_called_once()
+    assert is_connected is False
+    assert error_data['notification_id'] == f'OPC_CONNECTION_ERROR_{opc_repository.id}'
+    assert error_data['message'] == 'Failed to connect to OPC server: Test error'
+    assert error_data['block'] == 'opc_repository'
+    assert error_data['level'] == NotificationLevel.ERROR
+    assert error_data['attachment_content'] is not None
+
+
+@pytest.mark.asyncio
+async def test_open_session_raises_when_no_client(opc_repository):
+    opc_repository.client = None
+
+    with pytest.raises(OpcClientNotInitializedError, match='not initialized'):
+        await opc_repository._open_session()
+
+
+@pytest.mark.asyncio
+async def test_disconnection_fallback_success(opc_repository, mock_client):
+    opc_repository.client = mock_client
+    mock_client.disconnect.return_value = True
+    result = await opc_repository._disconnection_fallback()
+
+    mock_client.disconnect.assert_called_once()
+    assert result == []
+
+
+@pytest.mark.asyncio
+async def test_disconnection_fallback_fail(opc_repository, mock_client):
+    opc_repository.client = mock_client
+    mock_client.disconnect.side_effect = Exception('Test error')
+    result = await opc_repository._disconnection_fallback()
+    assert result == [
+        {'attempt': 1, 'error': 'Test error', 'traceback': ANY},
+        {'attempt': 2, 'error': 'Test error', 'traceback': ANY},
+        {'attempt': 3, 'error': 'Test error', 'traceback': ANY},
+        {'attempt': 4, 'error': 'Test error', 'traceback': ANY},
+        {'attempt': 5, 'error': 'Test error', 'traceback': ANY},
+    ]
+    assert mock_client.disconnect.call_count == 5
+
+
+@pytest.mark.asyncio
+async def test_disconnect(opc_repository, mock_client):
+    opc_repository.client = mock_client
+    opc_repository._disconnection_fallback = AsyncMock(return_value=[])
+    await opc_repository.disconnect()
+
+    opc_repository._disconnection_fallback.assert_called_once()
+    assert opc_repository.client is None
+    assert opc_repository._allow_reconnect is False
+
+
+@pytest.mark.asyncio
+async def test_disconnect_no_client(opc_repository):
+    opc_repository.client = None
+    assert await opc_repository.disconnect() is None
+
+
+@pytest.mark.asyncio
+async def test_disconnect_error(opc_repository, mock_client):
+    opc_repository.client = mock_client
+    opc_repository._disconnection_fallback = AsyncMock(
+        return_value=[{'attempt': 1, 'error': 'Test error', 'traceback': 'text'}]
+    )
+    await opc_repository.disconnect()
+
+    opc_repository._disconnection_fallback.assert_called_once()
+    opc_repository.send_notification_async.assert_called_once_with(
+        metadata=opc_repository.metadata,
+        notification_id=f'OPC_DISCONNECTION_ERROR_{opc_repository.id}',
+        message='Failed to disconnect from OPC server in 5 attempts.',
+        block='opc_repository',
+        level=NotificationLevel.ERROR,
+        attachment_content=json.dumps(
+            [{'attempt': 1, 'error': 'Test error', 'traceback': 'text'}], indent=4
+        ),
+    )
+    assert opc_repository.client is None
+
+
+@pytest.mark.asyncio
+async def test_validate_connection_none_client(opc_repository):
+    opc_repository.client = None
+    response = await opc_repository.validate_connection()
+    assert response == (False, opc_repository._not_connected_error())
+
+
+@pytest.mark.asyncio
+async def test_validate_connection_session_not_open(opc_repository):
+    opc_repository.client = MagicMock()
+    opc_repository.client.uaclient.protocol = None
+
+    response = await opc_repository.validate_connection()
+
+    assert response == (False, opc_repository._not_connected_error())
+    opc_repository.error.assert_called_once()
+
+
+@pytest.mark.asyncio
+async def test_validate_connection_success(opc_repository):
+    opc_repository.client = MagicMock()
+    opc_repository.client.uaclient.protocol = MagicMock()
+    opc_repository.client.uaclient.protocol.state = 'open'
+
+    output = await opc_repository.validate_connection()
+    assert output == (True, {})
+
+
+@pytest.mark.asyncio
+async def test_write_data_validate_connection_do_nothing(opc_repository):
+    opc_repository.validate_connection = AsyncMock(return_value=(True, {}))
+    opc_repository.client = AsyncMock(get_node=MagicMock())
+    mock_node = AsyncMock()
+    opc_repository.client.get_node.return_value = mock_node
+
+    result = await opc_repository.write_data('ns=2;s=TestNode', 42.0, 'float', metadata['metadata'])
+
+    opc_repository.validate_connection.assert_called_once()
+    opc_repository.client.get_node.assert_called_once_with('ns=2;s=TestNode')
+    assert result == (True, {'response_time': ANY})
+
+
+@pytest.mark.asyncio
+async def test_write_data_validate_connection_failed(opc_repository):
+    opc_repository.client = MagicMock()
+    opc_repository.client.uaclient.protocol = MagicMock(state='closed')
+    opc_repository._start_reconnect = AsyncMock()
+
+    is_success, error_data = await opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
+    )
+
+    opc_repository._start_reconnect.assert_called_once()
+    assert opc_repository._start_reconnect.call_args.args[0] == 'ProtocolClosed'
+    assert is_success is False
+    assert error_data['opc_error_kind'] == 'connection_lost'
+    assert error_data['opc_status'] == 'ProtocolClosed'
+
+
+@pytest.mark.asyncio
+async def test_write_data_get_node_failed(opc_repository):
+    opc_repository.validate_connection = AsyncMock(return_value=(True, {}))
+    opc_repository.client = AsyncMock()
+    opc_repository.client.get_node = MagicMock(side_effect=Exception('Test error'))
+
+    is_success, error_data = await opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
+    )
+
+    opc_repository.validate_connection.assert_called_once()
+    opc_repository.client.get_node.assert_called_once_with('ns=2;s=TestNode')
+    assert is_success is False
+    assert error_data['notification_id'] == f'OPC_WRITE_GET_NODE_ERROR_{opc_repository.id}'
+    assert (
+        error_data['message']
+        == "Failed to get node from OPC server: Test error | metadata: {'model_id': 'test_model', 'model_name': 'test_model', 'workflow_name': 'test_workflow', 'schema_name': 'test_schedule'}"
+    )
+    assert error_data['block'] == 'opc_repository'
+    assert error_data['level'] == NotificationLevel.ERROR
+    assert error_data['attachment_content'] is not None
+
+
+@pytest.mark.asyncio
+async def test_write_data_invalid_data_type(opc_repository, mock_client):
+    opc_repository.validate_connection = AsyncMock(return_value=(True, {}))
+    opc_repository.client = mock_client
+    mock_node = AsyncMock()
+    mock_client.get_node = MagicMock(return_value=mock_node)
+
+    is_success, error_data = await opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'invalid_type', metadata['metadata']
+    )
+
+    opc_repository.validate_connection.assert_called_once()
+    mock_client.get_node.assert_called_once_with('ns=2;s=TestNode')
+
+    assert is_success is False
+    assert error_data['notification_id'] == f'OPC_WRITE_DATA_TYPE_ERROR_{opc_repository.id}'
+    assert (
+        error_data['message']
+        == "Unsupported data type: invalid_type | metadata: {'model_id': 'test_model', 'model_name': 'test_model', 'workflow_name': 'test_workflow', 'schema_name': 'test_schedule'}"
+    )
+    assert error_data['block'] == 'opc_repository'
+    assert error_data['level'] == NotificationLevel.ERROR
+    assert error_data.get('attachment_content') is None
+
+
+@pytest.mark.asyncio
+async def test_write_data(opc_repository, mock_client):
+    opc_repository.validate_connection = AsyncMock(return_value=(True, {}))
+    opc_repository.client = mock_client
+    mock_node = AsyncMock()
+    mock_client.get_node = MagicMock(return_value=mock_node)
+
+    result = await opc_repository.write_data('ns=2;s=TestNode', 42.0, 'float', metadata['metadata'])
+
+    mock_client.get_node.assert_called_once_with('ns=2;s=TestNode')
+    mock_node.write_value.assert_called_once()
+    assert result == (True, {'response_time': ANY})
+
+
+@pytest.mark.asyncio
+async def test_write_data_write_value_failed(opc_repository, mock_client):
+    opc_repository.validate_connection = AsyncMock(return_value=(True, {}))
+    opc_repository.client = mock_client
+    mock_node = AsyncMock()
+    mock_client.get_node = MagicMock(return_value=mock_node)
+    mock_node.write_value.side_effect = Exception('Test error')
+
+    is_success, error_data = await opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
+    )
+
+    opc_repository.validate_connection.assert_called_once()
+    mock_client.get_node.assert_called_once_with('ns=2;s=TestNode')
+    mock_node.write_value.assert_called_once()
+    assert is_success is False
+    assert error_data['notification_id'] == f'OPC_WRITE_DATA_ERROR_{opc_repository.id}'
+    assert (
+        error_data['message']
+        == "Failed to write data to OPC server: Test error | metadata: {'model_id': 'test_model', 'model_name': 'test_model', 'workflow_name': 'test_workflow', 'schema_name': 'test_schedule'}"
+    )
+    assert error_data['block'] == 'opc_repository'
+    assert error_data['level'] == NotificationLevel.ERROR
+    assert error_data['attachment_content'] is not None
+
+
+def test_is_reconnectable_opcua_bad():
+    assert is_reconnectable_opcua_bad(BadSessionIdInvalid()) is True
+    assert is_reconnectable_opcua_bad(BadNodeIdUnknown()) is False
+    assert is_reconnectable_opcua_bad(Exception('other')) is False
+
+
+@pytest.mark.asyncio
+async def test_write_data_bad_session_id_invalid_schedules_reconnect(opc_repository, mock_client):
+    opc_repository.validate_connection = AsyncMock(return_value=(True, {}))
+    opc_repository.client = mock_client
+    opc_repository._start_reconnect = AsyncMock()
+    mock_node = AsyncMock()
+    mock_client.get_node = MagicMock(return_value=mock_node)
+    mock_node.write_value.side_effect = BadSessionIdInvalid()
+
+    is_success, error_data = await opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
+    )
+
+    mock_node.write_value.assert_called_once()
+    opc_repository._start_reconnect.assert_called_once()
+    assert is_success is False
+    assert error_data['opc_error_kind'] == 'session_bad'
+    assert error_data['opc_status'] == 'BadSessionIdInvalid'
+
+
+@pytest.mark.asyncio
+async def test_write_data_reconnect_in_progress_immediate(opc_repository):
+    opc_repository._session_ready.clear()
+    opc_repository._reconnect_task = asyncio.create_task(asyncio.sleep(60))
+    opc_repository.validate_connection = AsyncMock()
+
+    is_success, error_data = await opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
+    )
+
+    opc_repository._reconnect_task.cancel()
+    with pytest.raises(asyncio.CancelledError):
+        await opc_repository._reconnect_task
+    opc_repository._reconnect_task = None
+
+    opc_repository.validate_connection.assert_not_called()
+    assert is_success is False
+    assert error_data['opc_error_kind'] == 'reconnect_in_progress'
+
+
+@pytest.mark.asyncio
+async def test_start_reconnect_skips_within_interval(opc_repository):
+    opc_repository.last_reconnection_time = datetime.now()
+    opc_repository.reconnection_interval = 3600
+
+    await opc_repository._start_reconnect('BadSessionIdInvalid', 'tok')
+
+    assert opc_repository._reconnect_task is None
+
+
+@pytest.mark.asyncio
+async def test_write_data_protocol_closed_schedules_reconnect(opc_repository):
+    opc_repository.client = MagicMock()
+    opc_repository.client.uaclient.protocol = MagicMock(state='closed')
+    opc_repository._start_reconnect = AsyncMock()
+
+    is_success, error_data = await opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
+    )
+
+    opc_repository._start_reconnect.assert_called_once()
+    assert opc_repository._start_reconnect.call_args.args[0] == 'ProtocolClosed'
+    assert is_success is False
+    assert error_data['opc_error_kind'] == 'connection_lost'
+    assert error_data['opc_status'] == 'ProtocolClosed'
+
+
+@pytest.mark.asyncio
+async def test_write_data_protocol_closed_skips_reconnect_within_interval(opc_repository):
+    opc_repository.client = MagicMock()
+    opc_repository.client.uaclient.protocol = MagicMock(state='closed')
+    opc_repository.last_reconnection_time = datetime.now()
+    opc_repository.reconnection_interval = 3600
+
+    is_success, error_data = await opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
+    )
+
+    assert opc_repository._reconnect_task is None
+    assert is_success is False
+    assert error_data['opc_error_kind'] == 'connection_lost'
+
+
+@pytest.mark.asyncio
+async def test_write_data_after_failed_reconnect_schedules_again(opc_repository):
+    opc_repository._session_ready.clear()
+    opc_repository.reconnection_interval = 0
+    opc_repository.last_reconnection_time = None
+    opc_repository._reconnect_locked = AsyncMock(
+        return_value=(False, {'message': 'connect failed'})
+    )
+
+    await opc_repository.write_data('ns=2;s=TestNode', 42.0, 'float', metadata['metadata'])
+    await asyncio.sleep(0.1)
+    assert opc_repository._reconnect_locked.call_count == 1
+    assert not opc_repository._reconnect_task_in_progress()
+
+    await opc_repository.write_data('ns=2;s=TestNode', 42.0, 'float', metadata['metadata'])
+    await asyncio.sleep(0.1)
+    assert opc_repository._reconnect_locked.call_count == 2
+
+
+@pytest.mark.asyncio
+async def test_write_data_after_disconnect_does_not_schedule_reconnect(opc_repository, mock_client):
+    opc_repository.client = mock_client
+    proto = MagicMock()
+    proto.state = 'closed'
+    mock_client.uaclient = MagicMock(protocol=proto)
+    opc_repository._disconnection_fallback = AsyncMock(return_value=[])
+    await opc_repository.disconnect()
+
+    is_success, error_data = await opc_repository.write_data(
+        'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
+    )
+
+    assert opc_repository._reconnect_task is None
+    assert is_success is False
+    assert error_data['opc_error_kind'] == 'connection_lost'
+
+
+@pytest.mark.asyncio
+async def test_parallel_bad_writes_single_reconnect_task(opc_repository, mock_client):
+    opc_repository.validate_connection = AsyncMock(return_value=(True, {}))
+    opc_repository.client = mock_client
+    opc_repository.reconnection_interval = 0
+    opc_repository.last_reconnection_time = None
+    mock_node = AsyncMock()
+    mock_client.get_node = MagicMock(return_value=mock_node)
+    mock_node.write_value.side_effect = BadSessionIdInvalid()
+
+    connect_count = 0
+
+    async def slow_reconnect():
+        nonlocal connect_count
+        connect_count += 1
+        await asyncio.sleep(0.05)
+        opc_repository._session_ready.set()
+        return True, {}
+
+    opc_repository._reconnect_locked = slow_reconnect
+
+    results = await asyncio.gather(
+        opc_repository.write_data('ns=2;s=TestNode', 1.0, 'float', metadata['metadata']),
+        opc_repository.write_data('ns=2;s=TestNode2', 2.0, 'float', metadata['metadata']),
+    )
+    await asyncio.sleep(0.15)
+
+    assert connect_count <= 1
+    assert 1 <= mock_node.write_value.call_count <= 2
+    error_kinds = [r[1].get('opc_error_kind') for r in results]
+    assert error_kinds.count('session_bad') >= 1
+    assert all(k in ('session_bad', 'reconnect_in_progress') for k in error_kinds)
+
+
+@pytest.mark.asyncio
+@patch('laborious.utils.repository.opc_repository.datetime')
+async def test_reconnect_locked_sets_last_reconnection_time(mock_datetime, opc_repository):
+    mock_datetime.now = MagicMock(return_value=datetime(2025, 1, 1, 12, 0, 0))
+    opc_repository._disconnect_locked = AsyncMock()
+    opc_repository._connect_locked = AsyncMock(return_value=(True, {}))
+
+    result = await opc_repository._reconnect_locked()
+
+    opc_repository._disconnect_locked.assert_called_once()
+    opc_repository._connect_locked.assert_called_once()
+    assert result == (True, {})
+    assert opc_repository.last_reconnection_time == datetime(2025, 1, 1, 12, 0, 0)

tests/laborious/utils/test_connectors_config.py

@@ -0,0 +1,122 @@
+from os import environ
+
+from laborious.utils.connectors_config import (
+    build_minio_config,
+    build_mlflow_config,
+    build_opc_config,
+)
+
+
+def test_build_mlflow_config_with_env_vars():
+    # Arrange
+    environ['MLFLOW_HOST'] = 'http://test-host'
+    environ['MLFLOW_PORT'] = '8080'
+    environ['MLFLOW_USERNAME'] = 'test-user'
+    environ['MLFLOW_PASSWORD'] = 'test-pass'
+
+    # Act
+    config = build_mlflow_config()
+
+    # Assert
+    assert config['host'] == 'http://test-host'
+    assert config['port'] == 8080
+    assert config['username'] == 'test-user'
+    assert config['password'] == 'test-pass'
+
+
+def test_build_mlflow_config_with_defaults():
+    # Arrange
+    # Clear any existing env vars
+    environ.pop('MLFLOW_HOST', None)
+    environ.pop('MLFLOW_PORT', None)
+    environ.pop('MLFLOW_USERNAME', None)
+    environ.pop('MLFLOW_PASSWORD', None)
+
+    # Act
+    config = build_mlflow_config()
+
+    # Assert
+    assert config['host'] == 'http://localhost'
+    assert config['port'] == 5080
+    assert config['username'] == 'aignosi'
+    assert config['password'] == 'aignosi'
+
+
+def test_build_opc_config_with_env_vars():
+    # Arrange
+    environ['OPC_CONFIG'] = '{"opc": {"name": "test-opc", "url": "opc.tcp://test:4840"}}'
+
+    # Act
+    config = build_opc_config()
+
+    # Assert
+    assert config['opc']['name'] == 'test-opc'
+    assert config['opc']['url'] == 'opc.tcp://test:4840'
+
+
+def test_build_opc_config_with_individual_env_vars():
+    # Arrange
+    environ.pop('OPC_CONFIG', None)
+    environ['OPC_ID'] = '1'
+    environ['OPC_URL'] = 'opc.tcp://test:4840'
+    environ['OPC_SERVER_URI'] = 'opc.tcp://test:4840'
+    environ['OPC_RECONNECTION_INTERVAL'] = '300'
+
+    # Act
+    config = build_opc_config()
+
+    # Assert
+    assert config['1']['id'] == '1'
+    assert config['1']['url'] == 'opc.tcp://test:4840'
+    assert config['1']['server_uri'] == 'opc.tcp://test:4840'
+    assert config['1']['reconnection_interval'] == 300
+
+
+def test_build_opc_config_with_defaults():
+    # Arrange
+    environ.pop('OPC_CONFIG', None)
+    environ.pop('OPC_ID', None)
+    environ.pop('OPC_URL', None)
+    environ.pop('OPC_SERVER_URI', None)
+    environ.pop('OPC_RECONNECTION_INTERVAL', None)
+
+    # Act
+    config = build_opc_config()
+
+    # Assert
+    assert config['1']['id'] == '1'
+    assert config['1']['url'] == 'opc.tcp://localhost:4840'
+    assert config['1']['server_uri'] == 'opc.tcp://localhost:4840'
+    assert config['1']['reconnection_interval'] == 120
+
+
+def test_build_minio_config_with_env_vars():
+    environ['MINIO_ENDPOINT_URL'] = 'http://test-host'
+    environ['MINIO_ACCESS_KEY'] = 'test-key'
+    environ['MINIO_SECRET_KEY'] = 'test-secret'
+    environ['MINIO_REGION_NAME'] = 'test-region'
+    environ['MINIO_DEFAULT_BUCKET'] = 'test-bucket'
+    assert build_minio_config() == {
+        'endpoint_url': 'http://test-host',
+        'access_key': 'test-key',
+        'secret_key': 'test-secret',
+        'default_bucket': 'test-bucket',
+        'retention_hours': 24,
+        'secure': False,
+    }
+
+
+def test_build_minio_config_with_defaults():
+    environ.pop('MINIO_ENDPOINT_URL', None)
+    environ.pop('MINIO_ACCESS_KEY', None)
+    environ.pop('MINIO_SECRET_KEY', None)
+    environ.pop('MINIO_REGION_NAME', None)
+    environ.pop('MINIO_DEFAULT_BUCKET', None)
+    assert build_minio_config() == {
+        'endpoint_url': 'http://localhost:9000',
+        'access_key': 'minioadmin',
+        'secret_key': 'minioadmin',
+        'default_bucket': 'laborious',
+        'retention_hours': 24,
+        'secure': False,
+    }