---
x-airflow-common:
  &airflow-common
  # In order to add custom dependencies or upgrade provider packages you can use your extended image.
  # Comment the image line, place your Dockerfile in the directory where you placed the docker-compose.yaml
  # and uncomment the "build" line below, Then run `docker-compose build` to build the images.
  #image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:2.6.0}
  build: ./docker/airflow
  # build: .
  environment:
    &airflow-common-env
    AIRFLOW__CORE__EXECUTOR: CeleryExecutor
    AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
    AIRFLOW__CELERY__RESULT_BACKEND: db+postgresql://airflow:airflow@postgres/airflow
    AIRFLOW__CELERY__BROKER_URL: redis://:@redis:6379/0
    AIRFLOW__CORE__FERNET_KEY: ''
    AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true'
    AIRFLOW__CORE__LOAD_EXAMPLES: 'False'
    AIRFLOW__API__AUTH_BACKENDS: 'airflow.api.auth.backend.basic_auth,airflow.api.auth.backend.session'
    AIRFLOW_CONN_RAW_DATA: 'mysql://${MYSQL_USER}:${MYSQL_PASSWORD}@db_raw:${MYSQL_RAW_PORT}/${MYSQL_RAW_DATABASE}'
    AIRFLOW_CONN_CLEAN_DATA: 'mysql://${MYSQL_USER}:${MYSQL_PASSWORD}@db_clean:${MYSQL_CLEAN_PORT}/${MYSQL_CLEAN_DATABASE}'
    # yamllint disable rule:line-length
    # Use simple http server on scheduler for health checks
    # See https://airflow.apache.org/docs/apache-airflow/stable/administration-and-deployment/logging-monitoring/check-health.html#scheduler-health-check-server
    # yamllint enable rule:line-length
    AIRFLOW__SCHEDULER__ENABLE_HEALTH_CHECK: 'true'
    # WARNING: Use _PIP_ADDITIONAL_REQUIREMENTS option ONLY for a quick checks
    # for other purpose (development, test and especially production usage) build/extend Airflow image.
    _PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:-}
  volumes:
    - ${AIRFLOW_PROJ_DIR:-.}/dags:/opt/airflow/dags
    - ${AIRFLOW_PROJ_DIR:-.}/logs:/opt/airflow/logs
    - ${AIRFLOW_PROJ_DIR:-.}/plugins:/opt/airflow/plugins
  user: "${AIRFLOW_UID:-50000}:0"
  depends_on:
    &airflow-common-depends-on
    redis:
      condition: service_healthy
    postgres:
      condition: service_healthy

services:
  db:
    restart: always
    image: mysql/mysql-server:5.7.28
    container_name: mlflow_db
    ports:
      - "${MYSQL_PORT}:3306"
    networks:
      - backend
    environment:
      - MYSQL_DATABASE=${MYSQL_DATABASE}
      - MYSQL_USER=${MYSQL_USER}
      - MYSQL_PASSWORD=${MYSQL_PASSWORD}
      - MYSQL_ROOT_PASSWORD=${MYSQL_ROOT_PASSWORD}
    volumes:
      - ./db_ml_data:/var/lib/mysql

  db_raw:
    restart: always
    image: mysql/mysql-server:5.7.28
    container_name: raw_data_db
    ports:
      - "${MYSQL_RAW_PORT}:3306"
    networks:
      - backend
    environment:
      - MYSQL_DATABASE=${MYSQL_RAW_DATABASE}
      - MYSQL_USER=${MYSQL_USER}
      - MYSQL_PASSWORD=${MYSQL_PASSWORD}
      - MYSQL_ROOT_PASSWORD=${MYSQL_ROOT_PASSWORD}
    volumes:
      - ./db_raw_data:/var/lib/mysql
  
  db_clean:
    restart: always
    image: mysql/mysql-server:5.7.28
    container_name: clean_data_db
    ports:
      - "${MYSQL_CLEAN_PORT}:3306"
    networks:
      - backend
    environment:
      - MYSQL_DATABASE=${MYSQL_CLEAN_DATABASE}
      - MYSQL_USER=${MYSQL_USER}
      - MYSQL_PASSWORD=${MYSQL_PASSWORD}
      - MYSQL_ROOT_PASSWORD=${MYSQL_ROOT_PASSWORD}
    volumes:
      - ./db_clean_data:/var/lib/mysql

  fast_api:
    build: ./docker/fast_api
    ports:
      - 8086:8086
    container_name: fast_api
    depends_on:
      - db_raw
      - db_clean
    networks:
      - backend
    volumes:
      - ./src/back:/opt/code/
    command: "uvicorn opt.code.main:app --host 0.0.0.0 --port 8086 --reload"

  minio:
    container_name: minio
    command: server /data --console-address ":${MINIO_CONSOLE_PORT}" --address ':${MINIO_PORT}'
    environment:
      - MINIO_ROOT_USER=${MINIO_ROOT_USER}
      - MINIO_ROOT_PASSWORD=${MINIO_ROOT_PASSWORD}
    image: quay.io/minio/minio:latest
    ports:
      - "${MINIO_PORT}:8081"
      - "${MINIO_CONSOLE_PORT}:8082"
    networks:
      - backend
    volumes:
      - ./minio_data:/data
    restart: unless-stopped

  mlflow:
    restart: always
    build: ./docker/mlflow
    image: mlflow
    container_name: mlflow
    depends_on:
      - db
      - minio
    ports:
      - "${MLFLOW_PORT}:8083"
    networks:
      - backend
    environment:
      - AWS_ACCESS_KEY_ID=${MINIO_ACCESS_KEY}
      - AWS_SECRET_ACCESS_KEY=${MINIO_SECRET_ACCESS_KEY}
      - MLFLOW_S3_ENDPOINT_URL=http://minio:${MINIO_PORT}
      - MLFLOW_TRACKING_URI=http://mlflow:${MLFLOW_PORT}
      - BACKEND_STORE_URI=mysql+pymysql://${MYSQL_USER}:${MYSQL_PASSWORD}@db:${MYSQL_PORT}/${MYSQL_DATABASE}
      - DEFAULT_ARTIFACT_ROOT=s3://minio:${MINIO_PORT}
      - MLFLOW_S3_IGNORE_TLS=true
    command: >
      mlflow server
      --backend-store-uri mysql+pymysql://${MYSQL_USER}:${MYSQL_PASSWORD}@db:${MYSQL_PORT}/${MYSQL_DATABASE}
      --host 0.0.0.0
      --port ${MLFLOW_PORT}
      --serve-artifacts
      --artifacts-destination s3://${MLFLOW_BUCKET_NAME}/
      --default-artifact-root s3://${MLFLOW_BUCKET_NAME}/
  
  work_jupyter:
    build: ./docker/jupyter
    volumes:
      - ./:/home/jovyan/work
    ports:
      - 8085:8888
    container_name: jupyter
    networks:
      - backend
    command: "jupyter lab --ip=0.0.0.0 --allow-root --NotebookApp.token='' --NotebookApp.password=''"

  postgres:
    image: postgres:13
    environment:
      POSTGRES_USER: airflow
      POSTGRES_PASSWORD: airflow
      POSTGRES_DB: airflow
    volumes:
      - postgres-db-volume:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD", "pg_isready", "-U", "airflow"]
      interval: 10s
      retries: 5
      start_period: 5s
    restart: always
    networks:
      - backend

  redis:
    image: redis:7.2-bookworm
    expose:
      - 6379
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 30s
      retries: 50
      start_period: 30s
    restart: always
    networks:
      - backend

  airflow-webserver:
    <<: *airflow-common
    command: webserver
    ports:
      - "8080:8080"
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully
    networks:
      - backend

  airflow-scheduler:
    <<: *airflow-common
    command: scheduler
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8974/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully
    networks:
      - backend

  airflow-worker:
    <<: *airflow-common
    command: celery worker
    healthcheck:
      test:
        - "CMD-SHELL"
        - 'celery --app airflow.providers.celery.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}" || celery --app airflow.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}"'
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    environment:
      <<: *airflow-common-env
      # Required to handle warm shutdown of the celery workers properly
      # See https://airflow.apache.org/docs/docker-stack/entrypoint.html#signal-propagation
      DUMB_INIT_SETSID: "0"
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully
    networks:
      - backend

  airflow-triggerer:
    <<: *airflow-common
    command: triggerer
    healthcheck:
      test: ["CMD-SHELL", 'airflow jobs check --job-type TriggererJob --hostname "$${HOSTNAME}"']
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully
    networks:
      - backend

  airflow-init:
    <<: *airflow-common
    entrypoint: /bin/bash
    # yamllint disable rule:line-length
    command:
      - -c
      - |
        if [[ -z "${AIRFLOW_UID}" ]]; then
          echo
          echo -e "\033[1;33mWARNING!!!: AIRFLOW_UID not set!\e[0m"
          echo "If you are on Linux, you SHOULD follow the instructions below to set "
          echo "AIRFLOW_UID environment variable, otherwise files will be owned by root."
          echo "For other operating systems you can get rid of the warning with manually created .env file:"
          echo "    See: https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#setting-the-right-airflow-user"
          echo
        fi
        one_meg=1048576
        mem_available=$$(($$(getconf _PHYS_PAGES) * $$(getconf PAGE_SIZE) / one_meg))
        cpus_available=$$(grep -cE 'cpu[0-9]+' /proc/stat)
        disk_available=$$(df / | tail -1 | awk '{print $$4}')
        warning_resources="false"
        if (( mem_available < 4000 )) ; then
          echo
          echo -e "\033[1;33mWARNING!!!: Not enough memory available for Docker.\e[0m"
          echo "At least 4GB of memory required. You have $$(numfmt --to iec $$((mem_available * one_meg)))"
          echo
          warning_resources="true"
        fi
        if (( cpus_available < 2 )); then
          echo
          echo -e "\033[1;33mWARNING!!!: Not enough CPUS available for Docker.\e[0m"
          echo "At least 2 CPUs recommended. You have $${cpus_available}"
          echo
          warning_resources="true"
        fi
        if (( disk_available < one_meg * 10 )); then
          echo
          echo -e "\033[1;33mWARNING!!!: Not enough Disk space available for Docker.\e[0m"
          echo "At least 10 GBs recommended. You have $$(numfmt --to iec $$((disk_available * 1024 )))"
          echo
          warning_resources="true"
        fi
        if [[ $${warning_resources} == "true" ]]; then
          echo
          echo -e "\033[1;33mWARNING!!!: You have not enough resources to run Airflow (see above)!\e[0m"
          echo "Please follow the instructions to increase amount of resources available:"
          echo "   https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#before-you-begin"
          echo
        fi
        mkdir -p /sources/logs /sources/dags /sources/plugins
        chown -R "${AIRFLOW_UID}:0" /sources/{logs,dags,plugins}
        exec /entrypoint airflow version
    # yamllint enable rule:line-length
    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}
      _PIP_ADDITIONAL_REQUIREMENTS: ''
    user: "0:0"
    volumes:
      - ${AIRFLOW_PROJ_DIR:-.}:/sources
    networks:
      - backend

  airflow-cli:
    <<: *airflow-common
    profiles:
      - debug
    environment:
      <<: *airflow-common-env
      CONNECTION_CHECK_MAX_COUNT: "0"
    # Workaround for entrypoint issue. See: https://github.com/apache/airflow/issues/16252
    command:
      - bash
      - -c
      - airflow
    networks:
      - backend

  # You can enable flower by adding "--profile flower" option e.g. docker-compose --profile flower up
  # or by explicitly targeted on the command line e.g. docker-compose up flower.
  # See: https://docs.docker.com/compose/profiles/
  flower:
    <<: *airflow-common
    command: celery flower
    profiles:
      - flower
    ports:
      - "5555:5555"
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:5555/"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully
    networks:
      - backend

volumes:
  postgres-db-volume:
  db_ml_data:
  db_raw_data:
  db_clean_data:
  minio_data:


networks:
  backend:
    driver: bridge