如何通过 Kafka 向 Elasticsearch 摄取数据

version: "3"

services:

  zookeeper:
    image: confluentinc/cp-zookeeper:latest
    container_name: zookeeper
    environment:
      ZOOKEEPER_CLIENT_PORT: 2181

  kafka:
    image: confluentinc/cp-kafka:latest
    container_name: kafka
    depends_on:
      - zookeeper
    ports:
      - "9092:9092"
      - "9094:9094"
    environment:
      KAFKA_BROKER_ID: 1
      KAFKA_ZOOKEEPER_CONNECT: zookeeper:2181
      KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://kafka:29092,PLAINTEXT_HOST:${HOST_IP}:9092
      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT
      KAFKA_INTER_BROKER_LISTENER_NAME: PLAINTEXT
      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1

  elasticsearch:
    image: docker.elastic.co/elasticsearch/elasticsearch:8.15.1
    container_name: elasticsearch-8.15.1
    environment:
      - node.name=elasticsearch
      - xpack.security.enabled=false
      - discovery.type=single-node
      - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
    volumes:
      - ./elasticsearch:/usr/share/elasticsearch/data
    ports:
      - 9200:9200

  kibana:
    image: docker.elastic.co/kibana/kibana:8.15.1
    container_name: kibana-8.15.1
    ports:
      - 5601:5601
    environment:
      ELASTICSEARCH_URL: http://elasticsearch:9200
      ELASTICSEARCH_HOSTS: '["http://elasticsearch:9200"]'

producer = KafkaProducer(
   bootstrap_servers=['localhost:9092'],  # Specifies the Kafka server to connect
   value_serializer=lambda x: json.dumps(x).encode('utf-8'),  # Serializes data as JSON and encodes it to UTF-8 before sending
   batch_size=16384,     # Sets the maximum batch size in bytes (here, 16 KB) for buffered messages before sending
   linger_ms=10,         # Sets the maximum delay (in milliseconds) before sending the batch
   acks='all'            # Specifies acknowledgment level; 'all' ensures message durability by waiting for all replicas to acknowledge
)


def generate_log_message():
   levels = ["INFO", "WARNING", "ERROR", "DEBUG"]
   messages = [
       "User login successful",
       "User login failed",
       "Database connection established",
       "Database connection failed",
       "Service started",
       "Service stopped",
       "Payment processed",
       "Payment failed"
   ]
   log_entry = {
       "level": random.choice(levels),
       "message": random.choice(messages),
       "timestamp": time.time()
   }
   return log_entry

def send_log_batches(topic, num_batches=5, batch_size=10):
   for i in range(num_batches):
       logger.info(f"Sending batch {i + 1}/{num_batches}")
       for _ in range(batch_size):
           log_message = generate_log_message()
           producer.send(topic, value=log_message)
       producer.flush()


if __name__ == "__main__":
   topic = "logs"
   send_log_batches(topic)
   producer.close()

INFO:kafka.conn:Set configuration …
INFO:log_producer:Sending batch 1/5 
INFO:log_producer:Sending batch 2/5
INFO:log_producer:Sending batch 3/5
INFO:log_producer:Sending batch 4/5

consumer = KafkaConsumer(
   'logs',                               
   bootstrap_servers=['localhost:9092'],
   auto_offset_reset='latest',            # Ensures reading from the latest offset if the group has no offset stored
   enable_auto_commit=True,               # Automatically commits the offset after processing
   group_id='log_consumer_group',         # Specifies the consumer group to manage offset tracking
   max_poll_records=10,                   # Maximum number of messages per batch
   fetch_max_wait_ms=2000                 # Maximum wait time to form a batch (in ms)
)

def create_bulk_actions(logs):
   for log in logs:
       yield {
           "_index": "logs",
           "_source": {
               'level': log['level'],
               'message': log['message'],
               'timestamp': log['timestamp']
           }
       }

if __name__ == "__main__":
   try:
       print("Starting message processing…")
       while True:

           messages = consumer.poll(timeout_ms=1000)  # Poll receive messages

           # process each batch messages
           for _, records in messages.items():
               logs = [json.loads(record.value) for record in records]
               bulk_actions = create_bulk_actions(logs)
               response = helpers.bulk(es, bulk_actions)
               print(f"Indexed {response[0]} logs.")
   except Exception as e:
       print(f"Erro: {e}")
   finally:
       consumer.close()
       print(f"Finish")

GET /logs/_search
{
  "query": {
    "match_all": {}
  }
}

curl --location '{{url}}/connectors' \
--header 'Content-Type: application/json' \
--data '{
    "name": "elasticsearch-sink-connector",
    "config": {
        "connector.class": "io.confluent.connect.elasticsearch.ElasticsearchSinkConnector",
        "topics": "logs",
        "connection.url": "http://elasticsearch:9200",
        "type.name": "_doc",
        "value.converter": "org.apache.kafka.connect.json.JsonConverter",
        "value.converter.schemas.enable": "false",
        "schema.ignore": "true",
        "key.ignore": "true"
    }
}'