docker-compose.yml

---
version: '2'
services:
  zookeeper:
    image: "confluentinc/cp-zookeeper:5.0.1"
    environment:
      ZOOKEEPER_CLIENT_PORT: 2181
      ZOOKEEPER_TICK_TIME: 2000

  kafka:
    image: "confluentinc/cp-enterprise-kafka:5.0.1"
    ports:
      - '9092:9092'
    depends_on:
      - zookeeper
    environment:
      KAFKA_BROKER_ID: 1
      KAFKA_ZOOKEEPER_CONNECT: zookeeper:2181
      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT
      KAFKA_INTER_BROKER_LISTENER_NAME: PLAINTEXT
      KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://kafka:29092,PLAINTEXT_HOST://localhost:9092
      KAFKA_AUTO_CREATE_TOPICS_ENABLE: "true"
      KAFKA_METRIC_REPORTERS: io.confluent.metrics.reporter.ConfluentMetricsReporter
      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
      KAFKA_GROUP_INITIAL_REBALANCE_DELAY_MS: 100
      CONFLUENT_METRICS_REPORTER_BOOTSTRAP_SERVERS: kafka:29092
      CONFLUENT_METRICS_REPORTER_ZOOKEEPER_CONNECT: zookeeper:2181
      CONFLUENT_METRICS_REPORTER_TOPIC_REPLICAS: 1
      CONFLUENT_METRICS_ENABLE: 'true'
      CONFLUENT_SUPPORT_CUSTOMER_ID: 'anonymous'

  # schema-registry:
  #   image: "confluentinc/cp-schema-registry:5.0.1"
  #   depends_on:
  #     - kafka
  #   ports:
  #     - '8081:8081'
  #   environment:
  #     SCHEMA_REGISTRY_HOST_NAME: schema-registry
  #     SCHEMA_REGISTRY_KAFKASTORE_CONNECTION_URL: zookeeper:2181

  ksql-server:
    image: confluentinc/cp-ksql-server:5.0.1
    depends_on:
      - kafka
      # - schema-registry
    environment:
      KSQL_BOOTSTRAP_SERVERS: kafka:29092
      KSQL_LISTENERS: http://0.0.0.0:8088
      # KSQL_KSQL_SCHEMA_REGISTRY_URL: http://schema-registry:8081
      # KSQL_KSQL_SERVICE_ID: confluent_rmoff_01

  ksql-cli:
    image: confluentinc/cp-ksql-cli:5.0.1
    depends_on:
      - ksql-server
    entrypoint: /bin/sh
    tty: true

# Two options for getting dummy data in here, one calls out to a 
# test generator on the web, another uses a local file. 
# Both running isn't a problem, you'll just get twice the throughput.
  kafkacat-from-file:
    image: confluentinc/cp-kafkacat:latest
    depends_on:
      - kafka
# echo "Waiting for Kafka ⏳"
# cub kafka-ready -b kafka:29092 1 300 &&       
    command: 
      - bash 
      - -c 
      - |
        while [ 1 -eq 1 ]
          do awk '{print $$0;system("sleep 0.5");}' /data/data.json | \
              kafkacat -b kafka:29092 -P -t user_logons
          done
    volumes: 
      - $PWD:/data

  # kafkacat-from-net:
  # # kafkacat image doesn't have curl :( 
  #   image: confluentinc/cp-kafkacat:latest
  #   depends_on:
  #     - kafka
  #   command: 
  #     - bash 
  #     - -c 
  #     - |
  #       while [ 1 -eq 1 ]
  #         do curl "https://api.mockaroo.com/api/bce1b030?count=5000&key=ff7856d0" | \
  #            awk '{print $$0;system("sleep 0.5");}' | \
  #             kafkacat -b kafka:29092 -P -t user_logons
  #         done