conda-build.yml

name: Build data-validation with Conda

on:
  push:
    branches:
      - master
  pull_request:
    branches:
      - master
  release:
    types: [published]
  workflow_dispatch:

jobs:
  build:
    runs-on: ${{ matrix.os }}
    strategy:
      fail-fast: false
      matrix:
        os: [ubuntu-latest, macos-latest]
        python-version: ["3.10", "3.11", "3.12", "3.13"]

    steps:
    - name: Checkout
      uses: actions/checkout@v4

    - name: Setup Micromamba
      uses: mamba-org/setup-micromamba@v1
      with:
        environment-name: tfdv-build
        cache-environment: true
        create-args: >-
          python=${{ matrix.python-version }}

    - name: Display environment info
      shell: bash -l {0}
      run: |
        micromamba info
        micromamba list

    - name: Install Bazel
      shell: bash -l {0}
      run: |
        # Install Bazelisk (manages Bazel versions)
        if [ "$RUNNER_OS" == "Linux" ]; then
          curl -Lo /tmp/bazelisk https://github.com/bazelbuild/bazelisk/releases/download/v1.20.0/bazelisk-linux-amd64
        elif [ "$RUNNER_OS" == "macOS" ]; then
          curl -Lo /tmp/bazelisk https://github.com/bazelbuild/bazelisk/releases/download/v1.20.0/bazelisk-darwin-amd64
        fi
        chmod +x /tmp/bazelisk
        sudo mv /tmp/bazelisk /usr/local/bin/bazel
        bazel --version

    # Needed for Xcode 26.x in some CI environments; without this patch,
    # Bazel Apple toolchain may fail with an "LC_UUID missing" linker error.
    # Currently CI is passing, so keep this disabled. Uncomment if CI starts
    # failing with an "LC_UUID missing" error.
    # - name: Patch Apple CC toolchain (macOS only)
    #   if: runner.os == 'macOS'
    #   shell: bash -l {0}
    #   run: bazel build //:patch_local_config_apple_cc

    - name: Install build tooling
      shell: bash -l {0}
      run: |
        python -m pip install numpy>=1.22.0
        python -m pip install --upgrade pip build wheel "setuptools<69.3"

    - name: Build the package
      shell: bash -l {0}
      run: |
        python -m build --wheel --no-isolation

    - name: Install wheel and dependencies
      shell: bash -l {0}
      run: |
        export TFX_DEPENDENCY_SELECTOR=GIT_MASTER
        export USE_BAZEL_VERSION=7.7.0
        python -m pip install "apache-beam[gcp]>=2.53,<3" "pandas>=1.0,<3" "numpy>=1.22.0"
        python -m pip install git+https://github.com/tensorflow/metadata.git@master --no-deps
        # Bypasses PyPI lack of uncompiled prebuilt wheels over modern setups stably
        python -m pip install git+https://github.com/tensorflow/tfx-bsl.git@master --no-deps
        python -m pip install "tensorflow>=2.21,<2.22"
        python -m pip install "absl-py>=0.9,<2.0.0" "joblib>=1.2.0" "pyarrow>=14" "pyfarmhash>=0.2.2,<0.4" "six>=1.12,<2" "dill" "scipy" "scikit-learn"
        python -m pip install "protobuf==6.31.1" --force-reinstall
        python -m pip install dist/*.whl --no-deps
        python -m pip install pytest

    - name: Run tests
      shell: bash -l {0}
      run: |
        export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python
        SITE_DIR=$(python -c "import site; print(site.getsitepackages()[0])")
        RV_PATH="${SITE_DIR}/google/protobuf/runtime_version.py"
        if [ -f "$RV_PATH" ]; then
          echo "" >> "$RV_PATH"
          echo "def ValidateProtobufRuntimeVersion(*args, **kwargs):" >> "$RV_PATH"
          echo "    pass" >> "$RV_PATH"
        fi
        mv tensorflow_data_validation tensorflow_data_validation_bak
        SITE_DIR=$(python -c "import site; print(site.getsitepackages()[0])")
        cp -r tensorflow_data_validation_bak/statistics/generators/testdata $SITE_DIR/tensorflow_data_validation/statistics/generators/
        mkdir -p /tmp/test_dir
        cd /tmp/test_dir
        python -m pytest --pyargs tensorflow_data_validation
        cd -
        mv tensorflow_data_validation_bak tensorflow_data_validation

    - name: Upload wheel artifact
      uses: actions/upload-artifact@v4.4.0
      with:
        name: data-validation-wheel-${{ matrix.os }}-py${{ matrix.python-version }}
        path: dist/*.whl

  upload_to_pypi:
    name: Upload to PyPI
    runs-on: ubuntu-latest
    if: (github.event_name == 'release' && startsWith(github.ref, 'refs/tags')) || (github.event_name == 'workflow_dispatch')
    needs: [build]
    environment:
      name: pypi
      url: https://pypi.org/p/tensorflow-data-validation/
    permissions:
      id-token: write
    steps:
      - name: Retrieve wheels
        uses: actions/download-artifact@v4.1.8
        with:
          merge-multiple: true
          path: wheels

      - name: List the build artifacts
        run: |
          ls -lAs wheels/

      - name: Upload to PyPI
        uses: pypa/gh-action-pypi-publish@release/v1.9
        with:
          packages_dir: wheels/