Merge remote-tracking branch 'upstream/main' into test-dask-cudf

Author: TomAugspurger

.github/workflows/cron.yaml

@@ -9,7 +9,7 @@ on:
     # currently set to 5:00 UTC and takes ~12 hours
     - cron: "15 18 * * *"
   workflow_dispatch: {}
-  
+
 jobs:
   setup:
     runs-on: ubuntu-latest

.github/workflows/pr.yaml

@@ -0,0 +1,25 @@
+name: pr
+
+on:
+  push:
+    branches:
+      - "main"
+  pull_request:
+    branches:
+      - "main"
+  workflow_dispatch: # allows you to trigger manually
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  check-style:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+    - uses: actions/setup-python@v3
+    - uses: pre-commit/[email protected]

.pre-commit-config.yaml

@@ -16,3 +16,39 @@ repos:
             ^cpp/cmake/thirdparty/patches/.*|
             ^python/cudf/cudf/tests/data/subword_tokenizer_data/.*
           )
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
+    hooks:
+      - id: codespell
+        exclude: |
+          (?x)^(
+            .*test.*|
+            ^CHANGELOG.md$
+          )
+  # Include this if we add any Python code
+  # - repo: https://github.com/astral-sh/ruff-pre-commit
+  #   rev: v0.9.3
+  #   hooks:
+  #     - id: ruff
+  #       args: ["--fix"]
+  #     - id: ruff-format
+  - repo: https://github.com/rapidsai/pre-commit-hooks
+    rev: v0.6.0
+    hooks:
+      - id: verify-copyright
+        exclude: |
+          (?x)^(
+            cpp/include/cudf_test/cxxopts[.]hpp$|
+            cpp/src/io/parquet/ipc/Message_generated[.]h$|
+            cpp/src/io/parquet/ipc/Schema_generated[.]h$|
+            cpp/cmake/Modules/FindCUDAToolkit[.]cmake$
+          )
+      - id: verify-alpha-spec
+      - id: verify-codeowners
+        args: [--fix, --project-prefix=cudf]
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: v0.10.0.1
+    hooks:
+      - id: shellcheck
+        args: ["--severity=warning"]
+        files: ^scripts/

README.md

@@ -1,5 +1,7 @@
 # Dask Upstream Testing
 
+[![Test dask-upstream](https://github.com/rapidsai/dask-upstream-testing/actions/workflows/cron.yaml/badge.svg)](https://github.com/rapidsai/dask-upstream-testing/actions/workflows/cron.yaml)
+
 This repository contains the scripts to run Dask's `gpu`-marked tests on a schedule.
 
 ## Version Policy