pr.yaml

name: pr

on:
  push:
    branches:
      - "pull-request/[0-9]+"

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

jobs:
  pr-builder:
    needs:
      - changed-files
      - checks
      # TODO: Remove this check before merging this PR and make sure the copy
      # in test.yaml is up-to-date.
      - clang-tidy
      - conda-cpp-build
      - conda-cpp-checks
      - conda-cpp-tests
      - conda-python-build
      - conda-python-cudf-tests
      - conda-python-other-tests
      - conda-java-tests
      - static-configure
      - conda-notebook-tests
      - docs-build
      - wheel-build-libcudf
      - wheel-build-pylibcudf
      - wheel-build-cudf
      - wheel-tests-cudf
      - wheel-build-cudf-polars
      - wheel-tests-cudf-polars
      - cudf-polars-polars-tests
      - wheel-build-dask-cudf
      - wheel-tests-dask-cudf
      - devcontainer
      - unit-tests-cudf-pandas
      - pandas-tests
      - pandas-tests-diff
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/pr-builder.yaml@branch-24.12
    if: always()
    with:
      needs: ${{ toJSON(needs) }}
  changed-files:
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/changed-files.yaml@branch-24.12
    with:
      files_yaml: |
        test_cpp:
          - '**'
          - '!CONTRIBUTING.md'
          - '!README.md'
          - '!ci/cudf_pandas_scripts/**'
          - '!docs/**'
          - '!img/**'
          - '!java/**'
          - '!notebooks/**'
          - '!python/**'
        test_cudf_pandas:
          - '**'
          - '!CONTRIBUTING.md'
          - '!README.md'
          - '!docs/**'
          - '!img/**'
          - '!java/**'
          - '!notebooks/**'
        test_java:
          - '**'
          - '!CONTRIBUTING.md'
          - '!README.md'
          - '!ci/cudf_pandas_scripts/**'
          - '!docs/**'
          - '!img/**'
          - '!notebooks/**'
          - '!python/**'
        test_notebooks:
          - '**'
          - '!CONTRIBUTING.md'
          - '!README.md'
          - '!ci/cudf_pandas_scripts/**'
          - '!java/**'
        test_python:
          - '**'
          - '!CONTRIBUTING.md'
          - '!README.md'
          - '!ci/cudf_pandas_scripts/**'
          - '!docs/**'
          - '!img/**'
          - '!java/**'
          - '!notebooks/**'
  checks:
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/checks.yaml@branch-24.12
    with:
      enable_check_generated_files: false
  clang-tidy:
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@branch-24.12
    with:
      build_type: pull-request
      run_script: "ci/cpp_linters.sh"
      file_to_upload: iwyu_results.txt
  conda-cpp-build:
    needs: checks
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/conda-cpp-build.yaml@branch-24.12
    with:
      build_type: pull-request
  conda-cpp-checks:
    needs: conda-cpp-build
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/conda-cpp-post-build-checks.yaml@branch-24.12
    with:
      build_type: pull-request
      enable_check_symbols: true
  conda-cpp-tests:
    needs: [conda-cpp-build, changed-files]
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/conda-cpp-tests.yaml@branch-24.12
    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_cpp
    with:
      build_type: pull-request
  conda-python-build:
    needs: conda-cpp-build
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/conda-python-build.yaml@branch-24.12
    with:
      build_type: pull-request
  conda-python-cudf-tests:
    needs: [conda-python-build, changed-files]
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/conda-python-tests.yaml@branch-24.12
    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
    with:
      build_type: pull-request
      script: "ci/test_python_cudf.sh"
  conda-python-other-tests:
    # Tests for dask_cudf, custreamz, cudf_kafka are separated for CI parallelism
    needs: [conda-python-build, changed-files]
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/conda-python-tests.yaml@branch-24.12
    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
    with:
      build_type: pull-request
      script: "ci/test_python_other.sh"
  conda-java-tests:
    needs: [conda-cpp-build, changed-files]
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@branch-24.12
    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_java
    with:
      build_type: pull-request
      node_type: "gpu-v100-latest-1"
      arch: "amd64"
      container_image: "rapidsai/ci-conda:cuda12.5.1-ubuntu22.04-py3.11"
      run_script: "ci/test_java.sh"
  static-configure:
    needs: checks
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@branch-24.12
    with:
      build_type: pull-request
      # Use the wheel container so we can skip conda solves and since our
      # primary static consumers (Spark) are not in conda anyway.
      container_image: "rapidsai/ci-wheel:latest"
      run_script: "ci/configure_cpp_static.sh"
  conda-notebook-tests:
    needs: [conda-python-build, changed-files]
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@branch-24.12
    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_notebooks
    with:
      build_type: pull-request
      node_type: "gpu-v100-latest-1"
      arch: "amd64"
      container_image: "rapidsai/ci-conda:cuda12.5.1-ubuntu22.04-py3.11"
      run_script: "ci/test_notebooks.sh"
  docs-build:
    needs: conda-python-build
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@branch-24.12
    with:
      build_type: pull-request
      node_type: "gpu-v100-latest-1"
      arch: "amd64"
      container_image: "rapidsai/ci-conda:cuda12.5.1-ubuntu22.04-py3.11"
      run_script: "ci/build_docs.sh"
  wheel-build-libcudf:
    needs: checks
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/wheels-build.yaml@branch-24.12
    with:
      # build for every combination of arch and CUDA version, but only for the latest Python
      matrix_filter: group_by([.ARCH, (.CUDA_VER|split(".")|map(tonumber)|.[0])]) | map(max_by(.PY_VER|split(".")|map(tonumber)))
      build_type: pull-request
      script: "ci/build_wheel_libcudf.sh"
  wheel-build-pylibcudf:
    needs: [checks, wheel-build-libcudf]
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/wheels-build.yaml@branch-24.12
    with:
      build_type: pull-request
      script: "ci/build_wheel_pylibcudf.sh"
  wheel-build-cudf:
    needs: wheel-build-pylibcudf
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/wheels-build.yaml@branch-24.12
    with:
      build_type: pull-request
      script: "ci/build_wheel_cudf.sh"
  wheel-tests-cudf:
    needs: [wheel-build-cudf, changed-files]
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/wheels-test.yaml@branch-24.12
    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
    with:
      build_type: pull-request
      script: ci/test_wheel_cudf.sh
  wheel-build-cudf-polars:
    needs: wheel-build-pylibcudf
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/wheels-build.yaml@branch-24.12
    with:
      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
      build_type: pull-request
      script: "ci/build_wheel_cudf_polars.sh"
  wheel-tests-cudf-polars:
    needs: [wheel-build-cudf-polars, changed-files]
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/wheels-test.yaml@branch-24.12
    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
    with:
      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
      build_type: pull-request
      # This always runs, but only fails if this PR touches code in
      # pylibcudf or cudf_polars
      script: "ci/test_wheel_cudf_polars.sh"
  cudf-polars-polars-tests:
    needs: wheel-build-cudf-polars
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/wheels-test.yaml@branch-24.12
    with:
      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
      build_type: pull-request
      # This always runs, but only fails if this PR touches code in
      # pylibcudf or cudf_polars
      script: "ci/test_cudf_polars_polars_tests.sh"
  wheel-build-dask-cudf:
    needs: wheel-build-cudf
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/wheels-build.yaml@branch-24.12
    with:
      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
      build_type: pull-request
      script: "ci/build_wheel_dask_cudf.sh"
  wheel-tests-dask-cudf:
    needs: [wheel-build-dask-cudf, changed-files]
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/wheels-test.yaml@branch-24.12
    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
    with:
      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
      build_type: pull-request
      script: ci/test_wheel_dask_cudf.sh
  devcontainer:
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/build-in-devcontainer.yaml@branch-24.12
    with:
      arch: '["amd64"]'
      cuda: '["12.5"]'
      build_command: |
        sccache -z;
        build-all -DBUILD_BENCHMARKS=ON --verbose;
        sccache -s;
  unit-tests-cudf-pandas:
    needs: [wheel-build-cudf, changed-files]
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/wheels-test.yaml@branch-24.12
    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python || fromJSON(needs.changed-files.outputs.changed_file_groups).test_cudf_pandas
    with:
      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
      build_type: pull-request
      script: ci/cudf_pandas_scripts/run_tests.sh
  pandas-tests:
    # run the Pandas unit tests using PR branch
    needs: [wheel-build-cudf, changed-files]
    secrets: inherit
    uses: rapidsai/shared-workflows/.github/workflows/wheels-test.yaml@branch-24.12
    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python || fromJSON(needs.changed-files.outputs.changed_file_groups).test_cudf_pandas
    with:
      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
      build_type: pull-request
      script: ci/cudf_pandas_scripts/pandas-tests/run.sh pr
      # Hide test failures because they exceed the GITHUB_STEP_SUMMARY output limit.
      test_summary_show: "none"
  pandas-tests-diff:
    # diff the results of running the Pandas unit tests and publish a job summary
    needs: pandas-tests
    uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@branch-24.12
    with:
        node_type: cpu4
        build_type: pull-request
        run_script: "ci/cudf_pandas_scripts/pandas-tests/diff.sh"