rust-data-processing 0.3.4

Schema-first ingestion (CSV, JSON, Parquet, Excel) into an in-memory DataSet, plus Polars-backed pipelines, SQL, profiling, validation, and map/reduce-style processing.
# MinIO (S3-compatible) for platform connector integration tests — development / CI opt-in only.
#
# Buckets: rdp-snowflake-stage, rdp-databricks-warehouse, rdp-spark-handoff
#
# Usage:
#   cd integration_testing/MinIO
#   cp .env.example .env   # optional
#   docker compose up -d
#   docker compose logs -f minio-init

networks:
  rdp-platform:
    name: rdp-platform-net

services:
  # minio/minio and minio/mc use different release tags on Docker Hub (mc has no 2024-12-18 tag).
  minio:
    image: minio/minio:RELEASE.2024-12-18T13-15-44Z
    container_name: rdp-minio-test
    restart: "no"
    command: server /data --console-address ":9001"
    ports:
      - "${MINIO_PORT:-9000}:9000"
      - "${MINIO_CONSOLE_PORT:-9001}:9001"
    environment:
      MINIO_ROOT_USER: ${MINIO_ROOT_USER:-rdp_minio}
      MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-rdp_minio_secret}
    volumes:
      - minio-data:/data
    networks:
      - rdp-platform
    healthcheck:
      test: ["CMD-SHELL", "curl -sf http://localhost:9000/minio/health/live || exit 1"]
      interval: 5s
      timeout: 5s
      retries: 24
      start_period: 10s

  minio-init:
    image: minio/mc:RELEASE.2025-08-13T08-35-41Z
    container_name: rdp-minio-init
    restart: "no"
    depends_on:
      minio:
        condition: service_healthy
    networks:
      - rdp-platform
    environment:
      MINIO_ROOT_USER: ${MINIO_ROOT_USER:-rdp_minio}
      MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-rdp_minio_secret}
    entrypoint: >
      /bin/sh -c "
      mc alias set local http://minio:9000 $$MINIO_ROOT_USER $$MINIO_ROOT_PASSWORD &&
      mc mb --ignore-existing local/rdp-snowflake-stage &&
      mc mb --ignore-existing local/rdp-databricks-warehouse &&
      mc mb --ignore-existing local/rdp-spark-handoff &&
      mc anonymous set download local/rdp-snowflake-stage &&
      echo 'MinIO buckets ready (rdp-snowflake-stage: anonymous download for emulator READ_PARQUET)'
      "

volumes:
  minio-data: