familienarchiv/docker-compose.yml

services:
  # --- Datenbank: PostgreSQL ---
  db:
    image: postgres:16-alpine
    container_name: archive-db
    restart: unless-stopped
    environment:
      POSTGRES_USER: ${POSTGRES_USER}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
      POSTGRES_DB: ${POSTGRES_DB}
    volumes:
      - ./data/postgres:/var/lib/postgresql/data
    ports:
      - "${PORT_DB}:5432"
    networks:
      - archive-net
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER} -d ${POSTGRES_DB}"]
      interval: 5s
      timeout: 5s
      retries: 5

  # --- Object Storage: MinIO (S3 kompatibel) ---
  minio:
    image: minio/minio:latest
    container_name: archive-minio
    restart: unless-stopped
    command: server /data --console-address ":9001"
    environment:
      MINIO_ROOT_USER: ${MINIO_ROOT_USER}
      MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD}
    volumes:
      - ./data/minio:/data
    ports:
      - "${PORT_MINIO_API}:9000"      # API Port
      - "${PORT_MINIO_CONSOLE}:9001"  # Web-Oberfläche
    networks:
      - archive-net
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
      interval: 30s
      timeout: 20s
      retries: 3

  # --- Helper: Erstellt automatisch den Bucket ---
  create-buckets:
    image: minio/mc
    depends_on:
      minio:
        condition: service_healthy
    entrypoint: >
      /bin/sh -c "
      /usr/bin/mc alias set myminio http://minio:9000 ${MINIO_ROOT_USER} ${MINIO_ROOT_PASSWORD};
      /usr/bin/mc mb myminio/${MINIO_DEFAULT_BUCKETS} --ignore-existing;
      /usr/bin/mc anonymous set private myminio/${MINIO_DEFAULT_BUCKETS};
      exit 0;
      "
    networks:
      - archive-net

  # --- Mail catcher: Mailpit (dev only) ---
  # Catches all outgoing emails and displays them in a web UI.
  # Access the inbox at http://localhost:${PORT_MAILPIT_UI} after starting the stack.
  mailpit:
    image: axllent/mailpit:latest
    container_name: archive-mailpit
    restart: unless-stopped
    ports:
      - "${PORT_MAILPIT_UI:-8025}:8025"   # Web UI
      - "${PORT_MAILPIT_SMTP:-1025}:1025" # SMTP
    networks:
      - archive-net

  # --- OCR: Python microservice (Surya + Kraken) ---
  # Single-node only: OCR training reloads the model in-process after each run.
  # Running multiple replicas would cause training conflicts and model-state divergence.
  # See ADR-001 for the architectural rationale.
  ocr-service:
    build:
      context: ./ocr-service
      dockerfile: Dockerfile
    container_name: archive-ocr
    restart: unless-stopped
    expose:
      - "8000"
    mem_limit: 12g
    memswap_limit: 12g
    volumes:
      - ocr_models:/app/models
      - ocr_cache:/root/.cache  # Hugging Face / ketos model download cache — prevents re-downloads on container recreate
    environment:
      KRAKEN_MODEL_PATH: /app/models/german_kurrent.mlmodel
      TRAINING_TOKEN: "${OCR_TRAINING_TOKEN:-}"
      OCR_CONFIDENCE_THRESHOLD: "0.3"
      OCR_CONFIDENCE_THRESHOLD_KURRENT: "0.5"
      RECOGNITION_BATCH_SIZE: "16"
      DETECTOR_BATCH_SIZE: "8"
    networks:
      - archive-net
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 10s
      timeout: 5s
      retries: 12
      start_period: 120s

  # --- Backend: Spring Boot ---
  backend:
    build:
      context: ./backend
      dockerfile: Dockerfile
    container_name: archive-backend
    restart: unless-stopped
    volumes:
      - ./import:/import
    depends_on:
      db:
        condition: service_healthy
      minio:
        condition: service_healthy
      mailpit:
        condition: service_started
      ocr-service:
        condition: service_started
    environment:
      SPRING_DATASOURCE_URL: jdbc:postgresql://db:5432/${POSTGRES_DB}
      SPRING_DATASOURCE_USERNAME: ${POSTGRES_USER}
      SPRING_DATASOURCE_PASSWORD: ${POSTGRES_PASSWORD}
      S3_ENDPOINT: http://minio:9000
      S3_ACCESS_KEY: ${MINIO_ROOT_USER}
      S3_SECRET_KEY: ${MINIO_ROOT_PASSWORD}
      S3_BUCKET_NAME: ${MINIO_DEFAULT_BUCKETS}
      S3_REGION: us-east-1
      SPRING_PROFILES_ACTIVE: dev,e2e
      APP_BASE_URL: ${APP_BASE_URL:-http://localhost:3000}
      # Defaults to the local Mailpit catcher — override in .env for production SMTP
      MAIL_HOST: ${MAIL_HOST:-mailpit}
      MAIL_PORT: ${MAIL_PORT:-1025}
      MAIL_USERNAME: ${MAIL_USERNAME:-}
      MAIL_PASSWORD: ${MAIL_PASSWORD:-}
      APP_MAIL_FROM: ${APP_MAIL_FROM:-noreply@familienarchiv.local}
      # Mailpit needs no auth or STARTTLS; production SMTP overrides these via .env
      SPRING_MAIL_PROPERTIES_MAIL_SMTP_AUTH: ${MAIL_SMTP_AUTH:-false}
      SPRING_MAIL_PROPERTIES_MAIL_SMTP_STARTTLS_ENABLE: ${MAIL_STARTTLS_ENABLE:-false}
      APP_OCR_BASE_URL: http://ocr-service:8000
      APP_OCR_TRAINING_TOKEN: "${OCR_TRAINING_TOKEN:-}"
    ports:
      - "${PORT_BACKEND}:8080"
    networks:
      - archive-net
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:8080/actuator/health | grep -q UP || exit 1"]
      interval: 15s
      timeout: 5s
      retries: 10
      start_period: 30s  # JAR starts in ~15s; was 60s when compilation happened at startup

  # --- Frontend: SvelteKit (Dev Server) ---
  frontend:
    build:
      context: ./frontend
      dockerfile: Dockerfile
    container_name: archive-frontend
    restart: unless-stopped
    depends_on:
      db:
        condition: service_healthy
      minio:
        condition: service_healthy
      backend:
        condition: service_healthy
    volumes:
      - ./frontend:/app
      # Keep container's node_modules separate from host to avoid OS binary conflicts
      - frontend_node_modules:/app/node_modules
    environment:
      # SSR calls (server-side) use the internal Docker network
      API_INTERNAL_URL: http://backend:8080
      # Vite dev proxy forwards /api from browser to the backend container
      API_PROXY_TARGET: http://backend:8080
    ports:
      - "${PORT_FRONTEND}:5173"
    networks:
      - archive-net

networks:
  archive-net:
    driver: bridge

volumes:
  frontend_node_modules:
  ocr_models:
  ocr_cache: