Restore workflow and add if and needs to pr-builder

.github/workflows/pr.yaml

@@ -12,24 +12,261 @@ concurrency:
 jobs:
   pr-builder:
     needs:
-      - never-run-test
-      - never-run
+      - changed-files
+      - checks
+      - 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-pylibcudf
+      - wheel-build-cudf
+      - wheel-tests-cudf
+      - wheel-build-cudf-polars
+      - wheel-tests-cudf-polars
+      - 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@pr-builder-needs-check
+    uses: rapidsai/shared-workflows/.github/workflows/pr-builder.yaml@branch-24.10
     if: always()
     with:
       needs: ${{ toJSON(needs) }}
-  never-run-test:
+  changed-files:
     runs-on: ubuntu-latest
+    name: "Check changed files"
     outputs:
-      run-never-run: false
+      test_cpp: ${{ steps.changed-files.outputs.cpp_any_changed == 'true' }}
+      test_python: ${{ steps.changed-files.outputs.python_any_changed == 'true' }}
+      test_java: ${{ steps.changed-files.outputs.java_any_changed == 'true' }}
     steps:
-      - run: exit 0
-  never-run:
-    needs: never-run-test
-    runs-on: ubuntu-latest
-    if: ${{ needs.never-run-test.outputs.run-never-run == 'true' }}
-    steps:
-      - run: |
-          echo "This should never run!"
-          exit 1
+      - name: Get PR info
+        id: get-pr-info
+        uses: rapidsai/shared-actions/get-pr-info@main
+      - name: Checkout code repo
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.sha }}
+          fetch-depth: ${{ fromJSON(steps.get-pr-info.outputs.pr-info).commits }}
+          persist-credentials: false
+      - name: Get changed files
+        id: changed-files
+        uses: tj-actions/changed-files@v45
+        with:
+          base_sha: ${{ fromJSON(steps.get-pr-info.outputs.pr-info).base.sha }}
+          files_yaml: |
+            cpp:
+              - '**'
+              - '!docs/**'
+              - '!java/**'
+              - '!notebooks/**'
+              - '!python/**'
+            python:
+              - '**'
+              - '!docs/**'
+              - '!java/**'
+            java:
+              - '**'
+              - '!docs/**'
+              - '!notebooks/**'
+              - '!python/**'
+  checks:
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    with:
+      enable_check_generated_files: false
+  conda-cpp-build:
+    needs: checks
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    with:
+      build_type: pull-request
+  conda-cpp-checks:
+    needs: conda-cpp-build
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    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/[email protected]
+    if: needs.changed-files.outputs.test_cpp == 'true'
+    with:
+      build_type: pull-request
+  conda-python-build:
+    needs: conda-cpp-build
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    with:
+      build_type: pull-request
+  conda-python-cudf-tests:
+    needs: [conda-python-build, changed-files]
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    if: needs.changed-files.outputs.test_python == 'true'
+    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/[email protected]
+    if: needs.changed-files.outputs.test_python == 'true'
+    with:
+      build_type: pull-request
+      script: "ci/test_python_other.sh"
+  conda-java-tests:
+    needs: conda-cpp-build
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    if: needs.changed-files.outputs.test_java == 'true'
+    with:
+      build_type: pull-request
+      node_type: "gpu-v100-latest-1"
+      arch: "amd64"
+      container_image: "rapidsai/ci-conda:latest"
+      run_script: "ci/test_java.sh"
+  static-configure:
+    needs: checks
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    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
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    with:
+      build_type: pull-request
+      node_type: "gpu-v100-latest-1"
+      arch: "amd64"
+      container_image: "rapidsai/ci-conda:latest"
+      run_script: "ci/test_notebooks.sh"
+  docs-build:
+    needs: conda-python-build
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    with:
+      build_type: pull-request
+      node_type: "gpu-v100-latest-1"
+      arch: "amd64"
+      container_image: "rapidsai/ci-conda:latest"
+      run_script: "ci/build_docs.sh"
+  wheel-build-pylibcudf:
+    needs: checks
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    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/[email protected]
+    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/[email protected]
+    if: needs.changed-files.outputs.test_python == 'true'
+    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/[email protected]
+    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/[email protected]
+    if: needs.changed-files.outputs.test_python == 'true'
+    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"
+  wheel-build-dask-cudf:
+    needs: wheel-build-cudf
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    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/[email protected]
+    if: needs.changed-files.outputs.test_python == 'true'
+    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/[email protected]
+    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
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    if: needs.changed-files.outputs.test_python == 'true'
+    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
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    if: needs.changed-files.outputs.test_python == 'true'
+    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/[email protected]
+    with:
+        node_type: cpu4
+        build_type: pull-request
+        run_script: "ci/cudf_pandas_scripts/pandas-tests/diff.sh"