python_build.yml

name: python_build

on:
  merge_group:
  push:
    branches: [main]
  pull_request:
    branches: [main]

defaults:
  run:
    working-directory: ./python

jobs:
  lint:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3

      - name: Setup Environment
        uses: ./.github/actions/setup-env

      - name: Check Python
        run: |
          python -m venv venv
          source venv/bin/activate
          pip install ruff==0.5.2 mypy==1.10.1 types-dataclasses typing-extensions
          make check-python

      - name: Check Rust
        run: make check-rust

  test-minimal:
    name: Python Build (Python 3.8 PyArrow 16.0.0)
    runs-on: ubuntu-latest
    env:
      RUSTFLAGS: "-C debuginfo=line-tables-only"
      CARGO_INCREMENTAL: 0

    steps:
      - uses: actions/checkout@v3

      - name: Setup Environment
        uses: ./.github/actions/setup-env
        with:
          python-version: 3.8

      - name: Build and install deltalake
        run: |
          python -m venv venv
          source venv/bin/activate
          make setup
          # Install minimum PyArrow version
          pip install -e .[pandas,devel] pyarrow==16.0.0
        env:
          RUSTFLAGS: "-C debuginfo=line-tables-only"

      - name: Run tests
        run: |
          source venv/bin/activate
          make unit-test

  test:
    name: Python Build (Python 3.10 PyArrow latest)
    runs-on: ubuntu-latest
    env:
      RUSTFLAGS: "-C debuginfo=1"
      CARGO_INCREMENTAL: 0

    steps:
      - uses: actions/checkout@v3

      - name: Setup Environment
        uses: ./.github/actions/setup-env

      - name: Start emulated services
        run: docker compose up -d

      - name: Build and install deltalake
        run: |
          python -m venv venv
          source venv/bin/activate
          make develop

      - name: Download Data Acceptance Tests (DAT) files
        run: make setup-dat

      - name: Run tests
        run: |
          source venv/bin/activate
          python -m pytest -m '((s3 or azure) and integration) or not integration and not benchmark' --doctest-modules

      - name: Test without pandas
        run: |
          source venv/bin/activate
          pip uninstall --yes pandas
          python -m pytest -m "not pandas and not integration and not benchmark"
          pip install pandas

  benchmark:
    name: Python Benchmark
    runs-on: ubuntu-latest
    env:
      RUSTFLAGS: "-C debuginfo=line-tables-only"
      CARGO_INCREMENTAL: 0

    steps:
      - uses: actions/checkout@v2

      - name: Setup Environment
        uses: ./.github/actions/setup-env

      - name: Build deltalake in release mode
        run: |
          python -m venv venv
          source venv/bin/activate
          MATURIN_EXTRA_ARGS=--release make develop

      # Download previous benchmark result from cache (if exists)
      - name: Download previous benchmark data
        uses: actions/cache@v2
        with:
          path: ./cache
          key: ${{ runner.os }}-benchmark

      - name: Run benchmark
        run: |
          source venv/bin/activate
          pytest tests/test_benchmark.py -m benchmark --benchmark-json output.json

      - name: Store benchmark result
        uses: benchmark-action/github-action-benchmark@v1
        with:
          tool: "pytest"
          output-file-path: python/output.json
          external-data-json-path: ./cache/benchmark-data.json
          fail-on-alert: true

  test-pyspark:
    name: PySpark Integration Tests
    runs-on: ubuntu-latest
    env:
      RUSTFLAGS: "-C debuginfo=line-tables-only"
      CARGO_INCREMENTAL: 0

    steps:
      - uses: actions/checkout@v3

      - name: Setup Environment
        uses: ./.github/actions/setup-env

      - uses: actions/setup-java@v2
        with:
          distribution: "zulu"
          java-version: "11"

      - name: Build and install deltalake
        run: |
          python -m venv venv
          source venv/bin/activate
          make develop-pyspark

      - name: Run tests
        run: |
          source venv/bin/activate
          make test-pyspark

  multi-python-running:
    name: Running with Python ${{ matrix.python-version }}
    runs-on: ubuntu-latest
    env:
      RUSTFLAGS: "-C debuginfo=line-tables-only"
      CARGO_INCREMENTAL: 0

    strategy:
      matrix:
        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]

    steps:
      - uses: actions/checkout@v3

      - name: Setup Environment
        uses: ./.github/actions/setup-env
        with:
          python-version: ${{ matrix.python-version }}

      - name: Build and install deltalake
        run: |
          python -m venv venv
          source venv/bin/activate
          make setup
          maturin develop

      - name: Run deltalake
        run: |
          source venv/bin/activate
          python -c 'import deltalake'