Files
sientia-dataops-opc-ingestor/ingestor/managers/data_manager.py
vitor-aignosi b9ef69a865 SIENTIAPDE-988
Refactor OpcManager initialization and unsubscribe method; enhance logging

- Removed the `initialize_from_config` method from `OpcManager` class and adjusted the constructor to handle configuration directly.
- Improved the `unsubscribe` method to include detailed logging for non-existent subscriptions.
- Updated tests in `test_opc_manager.py` to reflect changes in the `OpcManager` class.
- Commented out Docker-related fixtures in `conftest.py` for potential future use.
- Enhanced test coverage in `test_single_node.py` and `test_data_manager.py` with additional scenarios and assertions.
- Introduced new methods in `Ingestor` and `IngestorManager` classes to manage server subscriptions and leases more effectively.
- Added new tests for `Ingestor` class to validate initialization and slot management logic.
- Implemented logging improvements across various classes to ensure better traceability of actions and errors.
2025-04-23 18:24:49 -03:00

95 lines
3.6 KiB
Python

import json
from logging import Logger
from time import sleep
from kafka import KafkaProducer
from kafka.errors import NoBrokersAvailable
class DataManager():
def __init__(self, kafka_servers: str, logger: Logger) -> None:
"""
Initializes the DataManager instance with a Kafka producer.
This constructor attempts to establish a connection to the specified Kafka servers
and initializes a Kafka producer for sending messages. It retries the connection
up to 3 times if the Kafka servers are unavailable.
Args:
kafka_servers (str): A comma-separated string of Kafka server addresses.
logger (Logger): A logger instance for logging messages.
Raises:
NoBrokersAvailable: If the connection to Kafka servers fails after 3 attempts.
"""
self.kafka_producer = None
for i in range(0, 3):
logger.info(
f"Trying ({i}) to initializing DataManager with Kafka servers: {kafka_servers}")
try:
self.kafka_producer = KafkaProducer(
bootstrap_servers=kafka_servers,
value_serializer=lambda v: json.dumps(v).encode(
'utf-8'), # Serialize JSON messages
key_serializer=lambda k: str(
k).encode('utf-8') if k else None,
)
break
except NoBrokersAvailable:
logger.error(
f"Kafka servers {kafka_servers} are not available. Retrying...")
sleep(5)
else:
logger.error(
f"Failed to connect to Kafka servers {kafka_servers} after 3 attempts.")
raise NoBrokersAvailable(
f"Failed to connect to Kafka servers {kafka_servers} after 3 attempts.")
logger.info(
f"DataManager initialized with Kafka servers: {kafka_servers}")
self.logger = logger
def __del__(self):
"""Destructor to close the producer connection."""
print("Closing Kafka producer...")
if self.kafka_producer:
self.kafka_producer.flush(timeout=10)
self.kafka_producer.close()
else:
print("Kafka producer is already closed or not initialized.")
def delivery_report(self, msg: str):
"""Callback for delivery reports from Kafka."""
self.logger.debug(
f"Record successfully produced to {msg.topic} [{msg.partition}] at offset {msg.offset}")
def delivery_error(self, err: str):
"""Callback for delivery reports from Kafka."""
self.logger.error(f"Delivery failed for record : {err}")
def publish(self, topic: str, data: dict) -> None:
"""
Publishes a message to a specified Kafka topic.
Args:
topic (str): The name of the Kafka topic to which the message will be published.
data (dict): The message data to be sent to the Kafka topic.
Returns:
None
Raises:
Exception: If there is an error during message delivery, it will be handled by the `delivery_error` callback.
"""
try:
self.logger.debug(
f"Publishing message to topic {topic}: {data}")
self.kafka_producer.send(
topic=topic, value=data).add_callback(
self.delivery_report).add_errback(
self.delivery_error)
self.kafka_producer.flush(timeout=10)
except Exception as e:
self.logger.error(f"Failed to publish message: {e}")