docker-compose.yml

version: '3'

x-airflow-common:
  &airflow-common
  build:
    context: ./containers/airflow/
  environment:
    &airflow-common-env
    AIRFLOW__CORE__EXECUTOR: LocalExecutor
    AIRFLOW__CORE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
    AIRFLOW__CORE__FERNET_KEY: ''
    AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true'
    AIRFLOW__CORE__LOAD_EXAMPLES: 'false'
    AIRFLOW__API__AUTH_BACKEND: 'airflow.api.auth.backend.basic_auth'
    AIRFLOW_CONN_POSTGRES_DEFAULT: postgres://airflow:airflow@postgres:5432/airflow
    WAREHOUSE_USER: ${POSTGRES_USER}
    WAREHOUSE_PASSWORD: ${POSTGRES_PASSWORD}
    WAREHOUSE_DB: ${POSTGRES_DB}
    WAREHOUSE_HOST: ${POSTGRES_HOST}
    WARREHOUSE_PORT: ${POSTGRES_PORT}

  volumes:
    - ./dags:/opt/airflow/dags
    - ./logs:/opt/airflow/logs
    - ./plugins:/opt/airflow/plugins
    - ./tests:/opt/airflow/tests
    - ./temp:/opt/airflow/temp
    - ./migrations:/opt/airflow/migrations
  user: "${AIRFLOW_UID:-50000}:${AIRFLOW_GID:-50000}"
  depends_on:
    postgres:
      condition: service_healthy

services:
  postgres:
    container_name: postgres
    image: postgres:13
    environment:
      POSTGRES_USER: airflow
      POSTGRES_PASSWORD: airflow
      POSTGRES_DB: airflow
    healthcheck:
      test: [ "CMD", "pg_isready", "-U", "airflow" ]
      interval: 5s
      retries: 5
    restart: always
    ports:
      - "5432:5432"

  airflow-webserver:
    <<: *airflow-common
    container_name: webserver
    command: webserver
    ports:
      - 8080:8080
    healthcheck:
      test:
        [
          "CMD",
          "curl",
          "--fail",
          "http://localhost:8080/health"
        ]
      interval: 10s
      timeout: 10s
      retries: 5
    restart: always

  airflow-scheduler:
    <<: *airflow-common
    container_name: scheduler
    command: scheduler
    healthcheck:
      test:
        [
          "CMD-SHELL",
          'airflow jobs check --job-type SchedulerJob --hostname "$${HOSTNAME}"'
        ]
      interval: 10s
      timeout: 10s
      retries: 5
    restart: always

  airflow-init:
    <<: *airflow-common
    command: version
    environment:
      <<: *airflow-common-env
      _AIRFLOW_DB_UPGRADE: 'true'
      _AIRFLOW_WWW_USER_CREATE: 'true'
      _AIRFLOW_WWW_USER_USERNAME: ${_AIRFLOW_WWW_USER_USERNAME:-airflow}
      _AIRFLOW_WWW_USER_PASSWORD: ${_AIRFLOW_WWW_USER_PASSWORD:-airflow}

  local-spark:
    image: local-spark
    container_name: local-spark
    build:
      context: ./
      dockerfile: ./containers/spark/Dockerfile
    environment:
      METADATA_DRIVERNAME: postgresql
      METADATA_HOST: postgres
      METADATA_PORT: '5432'
      METADATA_USERNAME: airflow
      METADATA_PASSWORD: airflow
      METADATA_DATABASE: airflow
    volumes:
      - ./adventureworks:/opt/spark/work-dir/adventureworks

  
  minio:
    image: 'minio/minio:RELEASE.2023-07-21T21-12-44Z'
    hostname: minio
    container_name: minio
    ports:
      - '9000:9000'
      - '9001:9001'
    environment:
      MINIO_ACCESS_KEY: minio
      MINIO_SECRET_KEY: minio123
    command: server --console-address ":9001" /data

  createbuckets:
    image: minio/mc
    container_name: createbuckets
    depends_on:
      - minio
    entrypoint: >
      /bin/sh -c " /usr/bin/mc config host add myminio http://minio:9000 minio minio123; /usr/bin/mc rm -r --force myminio/adventureworks; /usr/bin/mc mb myminio/adventureworks; /usr/bin/mc policy download myminio/adventureworks; exit 0; "