SIENTIAPDE-1811

Enhance OPC UA communication and metrics tracking

- Updated README.md to include new OPC UA Communication section and detailed metrics for session and write diagnostics.
- Added new metrics in laborious/metrics.py for tracking OPC UA session states and write attempts.
- Refactored OPC activity in laborious/activities/opc.py to handle session errors and improve error reporting.
- Updated e2e tests to cover new scenarios for OPC session/channel errors and reconnect handling.
- Modified .gitignore to include relatorio files and mlruns directory.
- Added ipykernel to requirements-dev.txt for Jupyter notebook support.
This commit is contained in:
2026-05-15 15:28:28 -03:00
parent 473bd0b03f
commit 638d5b70b4
15 changed files with 1370 additions and 424 deletions

View File

@@ -1,12 +1,20 @@
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 OpcRepository
from laborious.utils.repository.opc_repository import (
OpcClientAlreadyExistsError,
OpcClientNotInitializedError,
OpcRepository,
OpcSessionAlreadyConnectedError,
is_reconnectable_opcua_bad,
)
@pytest.fixture
@@ -33,6 +41,11 @@ def opc_repository(mock_logger):
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
@@ -65,7 +78,6 @@ def test_init(opc_repository):
assert opc_repository.reconnection_interval == 60
assert opc_repository.client is None
assert opc_repository.last_reconnection_time is None
assert opc_repository.error_count == 0
@pytest.mark.asyncio
@@ -80,8 +92,8 @@ async def test_set_security(opc_repository, mock_client):
private_key='/path/to/key.pem',
server_certificate='/path/to/server_cert.pem',
)
assert mock_client.secure_channel_timeout == 10000000
assert mock_client.session_timeout == 10000000
assert mock_client.secure_channel_timeout == 600_000
assert mock_client.session_timeout == 600_000
@pytest.mark.asyncio
@@ -106,48 +118,95 @@ async def test_set_security_missing_client(opc_repository):
@pytest.mark.asyncio
async def test_connect_with_security(opc_repository, mock_client):
opc_repository.try_connect = AsyncMock(return_value=(True, {}))
opc_repository._create_client = AsyncMock()
opc_repository._open_session = AsyncMock(return_value=(True, {}))
result = await opc_repository.connect()
opc_repository.try_connect.assert_called_once()
assert opc_repository.client == mock_client
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.try_connect = AsyncMock(return_value=(True, {}))
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.try_connect.assert_called_once()
opc_repository._create_client.assert_called_once()
opc_repository._open_session.assert_called_once()
opc_repository.set_security.assert_not_called()
assert opc_repository.client == mock_client
assert result == (True, {})
@pytest.mark.asyncio
async def test_try_connect_success(opc_repository):
opc_repository.last_reconnection_time = None
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()
result = await opc_repository.try_connect()
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 not None
assert opc_repository.last_reconnection_time is None
assert result == (True, {})
assert opc_repository._session_ready.is_set()
@pytest.mark.asyncio
async def test_try_connect_fail(opc_repository):
opc_repository.last_reconnection_time = None
opc_repository.disconnect = AsyncMock()
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.connect.side_effect = Exception('Test error')
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.try_connect()
is_connected, error_data = await opc_repository._open_session()
opc_repository.disconnect.assert_called_once()
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}'
@@ -158,25 +217,18 @@ async def test_try_connect_fail(opc_repository):
@pytest.mark.asyncio
async def test_try_connect_no_client(opc_repository):
async def test_open_session_raises_when_no_client(opc_repository):
opc_repository.client = None
result = await opc_repository.try_connect()
assert result == (
False,
{
'notification_id': f'OPC_CONNECTION_ERROR_{opc_repository.id}',
'message': 'Client is not initialized',
'block': 'opc_repository',
'level': NotificationLevel.ERROR,
},
)
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()
result = await opc_repository._disconnection_fallback()
mock_client.disconnect.assert_called_once()
assert result == []
@@ -186,7 +238,7 @@ async def test_disconnection_fallback_success(opc_repository, mock_client):
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()
result = await opc_repository._disconnection_fallback()
assert result == [
{'attempt': 1, 'error': 'Test error', 'traceback': ANY},
{'attempt': 2, 'error': 'Test error', 'traceback': ANY},
@@ -200,10 +252,10 @@ async def test_disconnection_fallback_fail(opc_repository, mock_client):
@pytest.mark.asyncio
async def test_disconnect(opc_repository, mock_client):
opc_repository.client = mock_client
opc_repository.disconnection_fallback = AsyncMock(return_value=[])
opc_repository._disconnection_fallback = AsyncMock(return_value=[])
await opc_repository.disconnect()
opc_repository.disconnection_fallback.assert_called_once()
opc_repository._disconnection_fallback.assert_called_once()
assert opc_repository.client is None
@@ -216,12 +268,12 @@ async def test_disconnect_no_client(opc_repository):
@pytest.mark.asyncio
async def test_disconnect_error(opc_repository, mock_client):
opc_repository.client = mock_client
opc_repository.disconnection_fallback = AsyncMock(
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._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}',
@@ -238,91 +290,24 @@ async def test_disconnect_error(opc_repository, mock_client):
@pytest.mark.asyncio
async def test_validate_connection_none_client(opc_repository):
opc_repository.client = None
opc_repository.connect = AsyncMock(return_value=(True, {}))
response = await opc_repository.validate_connection()
assert response == (True, {})
opc_repository.connect.assert_called_once()
# @pytest.mark.asyncio
# async def test_validate_connection_error_count_disconnect_error(opc_repository):
# opc_repository.error_count = 6
# opc_repository.client = AsyncMock()
# opc_repository.disconnect = AsyncMock(side_effect=Exception('Test error'))
# opc_repository.connect = AsyncMock(return_value=(True, {}))
# response = await opc_repository.validate_connection()
# assert response == opc_repository.connect.return_value
# opc_repository.disconnect.assert_called_once()
# opc_repository.connect.assert_called_once()
# opc_repository.logger.custom_error.assert_has_calls(
# [
# call('Failed to disconnect from OPC server: Test error', ANY),
# ]
# )
assert response == (False, opc_repository._not_connected_error())
@pytest.mark.asyncio
async def test_validate_connection_error_validate_connection_error(opc_repository):
opc_repository.client = MagicMock(uaclient=Exception('Test error'))
opc_repository.error_count = 0
response = await opc_repository.validate_connection()
assert response == (
False,
{
'notification_id': f'OPC_CONNECTION_CHECK_ERROR_{opc_repository.id}',
'message': "Failed to validate connection to OPC server: 'Exception' object has no attribute 'protocol'",
'block': 'opc_repository',
'level': NotificationLevel.ERROR,
'attachment_content': ANY,
},
)
@pytest.mark.asyncio
@patch('laborious.utils.repository.opc_repository.datetime')
async def test_validate_connection_lost_not_time_to_reconnect(_mock_datetime, opc_repository):
_mock_datetime.now = MagicMock(return_value=datetime(2025, 1, 1, 0, 0, 0))
opc_repository.error_count = 0
async def test_validate_connection_session_not_open(opc_repository):
opc_repository.client = MagicMock()
opc_repository.client.uaclient.protocol = None
opc_repository.last_reconnection_time = datetime(2025, 1, 1, 0, 0, 0)
opc_repository.connect = MagicMock(return_value=(True, {}))
response = await opc_repository.validate_connection()
opc_repository.connect.assert_not_called()
assert response == (
False,
{
'notification_id': f'OPC_CONNECTION_AWAITING_RECONNECTION_WINDOW_{opc_repository.id}',
'message': f'OPC server {opc_repository.id} is not connected, waiting for next reconnection window...',
'block': 'opc_repository',
'level': NotificationLevel.WARNING,
},
)
@pytest.mark.asyncio
@patch('laborious.utils.repository.opc_repository.datetime')
async def test_validate_connection_lost_time_to_reconnect(mock_datetime, opc_repository):
mock_datetime.now = MagicMock(return_value=datetime(2025, 1, 1, 1, 0, 0))
opc_repository.error_count = 0
opc_repository.client = AsyncMock()
opc_repository.client.uaclient.protocol = None
opc_repository.last_reconnection_time = datetime(2025, 1, 1, 0, 0, 0)
opc_repository.connect = AsyncMock(return_value=(True, {}))
response = await opc_repository.validate_connection()
opc_repository.connect.assert_called_once()
assert response == opc_repository.connect.return_value
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.error_count = 0
opc_repository.client.uaclient.protocol = MagicMock()
opc_repository.client.uaclient.protocol.state = 'open'
@@ -337,9 +322,7 @@ async def test_write_data_validate_connection_do_nothing(opc_repository):
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', opc_repository.logger, metadata['metadata']
)
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')
@@ -350,11 +333,8 @@ async def test_write_data_validate_connection_do_nothing(opc_repository):
async def test_write_data_validate_connection_failed(opc_repository):
opc_repository.validate_connection = AsyncMock(return_value=(False, {}))
opc_repository.client = AsyncMock()
opc_repository.error_count = 0
result = await opc_repository.write_data(
'ns=2;s=TestNode', 42.0, 'float', opc_repository.logger, metadata['metadata']
)
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_not_called()
@@ -365,11 +345,10 @@ async def test_write_data_validate_connection_failed(opc_repository):
async def test_write_data_get_node_failed(opc_repository):
opc_repository.validate_connection = AsyncMock(return_value=(True, {}))
opc_repository.client = AsyncMock()
opc_repository.error_count = 0
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', opc_repository.logger, metadata['metadata']
'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
)
opc_repository.validate_connection.assert_called_once()
@@ -393,7 +372,7 @@ async def test_write_data_invalid_data_type(opc_repository, mock_client):
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', opc_repository.logger, metadata['metadata']
'ns=2;s=TestNode', 42.0, 'invalid_type', metadata['metadata']
)
opc_repository.validate_connection.assert_called_once()
@@ -417,9 +396,7 @@ async def test_write_data(opc_repository, 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', opc_repository.logger, metadata['metadata']
)
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()
@@ -431,12 +408,11 @@ 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()
opc_repository.error_count = 0
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', opc_repository.logger, metadata['metadata']
'ns=2;s=TestNode', 42.0, 'float', metadata['metadata']
)
opc_repository.validate_connection.assert_called_once()
@@ -451,3 +427,108 @@ async def test_write_data_write_value_failed(opc_repository, mock_client):
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_on_bad = 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_on_bad.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_on_bad_skips_within_interval(opc_repository):
opc_repository.last_reconnection_time = datetime.now()
opc_repository.reconnection_interval = 3600
await opc_repository._start_reconnect_on_bad('BadSessionIdInvalid', 'tok')
assert opc_repository._reconnect_task is None
@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)