データエンジニアのためのApache Kafka：ストリーミング、パーティション、面接対策

# docker-compose.yml — Kafka 4.x KRaft cluster (no ZooKeeper)
services:
  kafka-1:
    image: apache/kafka:4.2.0
    environment:
      KAFKA_NODE_ID: 1
      KAFKA_PROCESS_ROLES: broker,controller
      KAFKA_CONTROLLER_QUORUM_VOTERS: 1@kafka-1:9093,2@kafka-2:9093,3@kafka-3:9093
      KAFKA_LISTENERS: PLAINTEXT://:9092,CONTROLLER://:9093
      KAFKA_INTER_BROKER_LISTENER_NAME: PLAINTEXT
      KAFKA_CONTROLLER_LISTENER_NAMES: CONTROLLER
      KAFKA_LOG_DIRS: /var/lib/kafka/data
      KAFKA_NUM_PARTITIONS: 6
      KAFKA_DEFAULT_REPLICATION_FACTOR: 3
      KAFKA_MIN_INSYNC_REPLICAS: 2
    ports:
      - "9092:9092"

# partition_strategy.py — Choosing the right partition key
from confluent_kafka import Producer
import json

def create_producer():
    return Producer({
        'bootstrap.servers': 'kafka-1:9092',
        'acks': 'all',
        'enable.idempotence': True,
        'max.in.flight.requests.per.connection': 5
    })

def publish_order_event(producer, event):
    # Key by customer_id: all events for one customer stay ordered
    key = str(event['customer_id']).encode('utf-8')
    value = json.dumps(event).encode('utf-8')
    producer.produce(
        topic='order-events',
        key=key,
        value=value,
        headers=[('source', b'order-service'), ('version', b'2')]
    )
    producer.flush()

def publish_clickstream(producer, event):
    # Key by session_id: ordering within a session matters
    # NOT by user_id — one user may have multiple sessions
    key = str(event['session_id']).encode('utf-8')
    value = json.dumps(event).encode('utf-8')
    producer.produce(
        topic='clickstream',
        key=key,
        value=value
    )

# consumer_pipeline.py — Consumer group with manual offset management
from confluent_kafka import Consumer, KafkaError
import json

def create_consumer(group_id: str):
    return Consumer({
        'bootstrap.servers': 'kafka-1:9092',
        'group.id': group_id,
        'auto.offset.reset': 'earliest',
        'enable.auto.commit': False,  # Manual commit for at-least-once
        'max.poll.interval.ms': 300000,
        'session.timeout.ms': 45000,
        'isolation.level': 'read_committed'  # Only read committed transactions
    })

def process_batch(consumer: Consumer, batch_size: int = 500):
    """Process records in micro-batches for throughput."""
    consumer.subscribe(['order-events'])
    buffer = []

    while True:
        msg = consumer.poll(timeout=1.0)
        if msg is None:
            continue
        if msg.error():
            if msg.error().code() == KafkaError._PARTITION_EOF:
                continue
            raise Exception(msg.error())

        record = json.loads(msg.value().decode('utf-8'))
        buffer.append(record)

        if len(buffer) >= batch_size:
            # Process the full batch (write to warehouse, etc.)
            write_to_warehouse(buffer)
            # Commit AFTER successful processing
            consumer.commit(asynchronous=False)
            buffer.clear()

def write_to_warehouse(records: list):
    # Insert batch into data warehouse (BigQuery, Snowflake, etc.)
    pass

{
  "name": "postgres-cdc-source",
  "config": {
    "connector.class": "io.debezium.connector.postgresql.PostgresConnector",
    "database.hostname": "postgres-primary",
    "database.port": "5432",
    "database.user": "replication_user",
    "database.dbname": "production",
    "topic.prefix": "cdc",
    "table.include.list": "public.orders,public.customers,public.products",
    "slot.name": "debezium_slot",
    "plugin.name": "pgoutput",
    "publication.name": "dbz_publication",
    "snapshot.mode": "initial",
    "transforms": "route",
    "transforms.route.type": "org.apache.kafka.connect.transforms.RegexRouter",
    "transforms.route.regex": "cdc\\.public\\.(.*)",
    "transforms.route.replacement": "warehouse.$1"
  }
}

# exactly_once_pipeline.py — Transactional consume-transform-produce
from confluent_kafka import Consumer, Producer
import json

def transactional_pipeline():
    consumer = Consumer({
        'bootstrap.servers': 'kafka-1:9092',
        'group.id': 'etl-transformer',
        'enable.auto.commit': False,
        'isolation.level': 'read_committed'
    })

    producer = Producer({
        'bootstrap.servers': 'kafka-1:9092',
        'transactional.id': 'etl-transformer-001',
        'acks': 'all',
        'enable.idempotence': True
    })

    producer.init_transactions()
    consumer.subscribe(['raw-events'])

    while True:
        msg = consumer.poll(1.0)
        if msg is None or msg.error():
            continue

        # Begin atomic transaction
        producer.begin_transaction()
        try:
            raw = json.loads(msg.value())
            enriched = transform(raw)

            # Write transformed record to output topic
            producer.produce(
                'enriched-events',
                key=msg.key(),
                value=json.dumps(enriched).encode('utf-8')
            )

            # Commit consumer offset within the same transaction
            producer.send_offsets_to_transaction(
                consumer.position(consumer.assignment()),
                consumer.consumer_group_metadata()
            )
            producer.commit_transaction()
        except Exception:
            producer.abort_transaction()

def transform(record: dict) -> dict:
    # Apply business logic transformations
    record['processed_at'] = '2026-04-20T00:00:00Z'
    record['pipeline_version'] = '2.1'
    return record