Merge pull request #12200 from rapidsai/branch-22.12

.github/labeler.yml

@@ -3,14 +3,14 @@
 cuDF (Python):
   - 'python/**'
   - 'notebooks/**'
-  
+
 libcudf:
   - 'cpp/**'
 
 CMake:
   - '**/CMakeLists.txt'
   - '**/cmake/**'
-  
+
 cuDF (Java):
   - 'java/**'
 

.github/workflows/add_to_project.yml

@@ -0,0 +1,20 @@
+name: Add new issue/PR to project
+
+on:
+  issues:
+    types:
+      - opened
+
+  pull_request_target:
+    types:
+      - opened
+
+jobs:
+  add-to-project:
+    name: Add issue or PR to project
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/[email protected]
+        with:
+          project-url: https://github.com/orgs/rapidsai/projects/51
+          github-token: ${{ secrets.ADD_TO_PROJECT_GITHUB_TOKEN }}

.github/workflows/dependency-files.yml

@@ -0,0 +1,12 @@
+name: pr
+
+on:
+  pull_request:
+
+jobs:
+  checks:
+    secrets: inherit
+    uses: rapidsai/shared-action-workflows/.github/workflows/checks.yaml@main
+    with:
+      enable_check_size: false
+      enable_check_style: false

.github/workflows/wheels.yml

@@ -0,0 +1,77 @@
+name: cuDF wheels
+
+on:
+  workflow_call:
+    inputs:
+      versioneer-override:
+        type: string
+        default: ''
+      build-tag:
+        type: string
+        default: ''
+      branch:
+        required: true
+        type: string
+      date:
+        required: true
+        type: string
+      sha:
+        required: true
+        type: string
+      build-type:
+        type: string
+        default: nightly
+
+concurrency:
+  group: "cudf-${{ github.workflow }}-${{ github.ref }}"
+  cancel-in-progress: true
+
+jobs:
+  cudf-wheels:
+    uses: rapidsai/shared-action-workflows/.github/workflows/wheels-manylinux.yml@main
+    with:
+      repo: rapidsai/cudf
+
+      build-type: ${{ inputs.build-type }}
+      branch: ${{ inputs.branch }}
+      sha: ${{ inputs.sha }}
+      date: ${{ inputs.date }}
+
+      package-dir: python/cudf
+      package-name: cudf
+
+      python-package-versioneer-override: ${{ inputs.versioneer-override }}
+      python-package-build-tag: ${{ inputs.build-tag }}
+
+      skbuild-configure-options: "-DCUDF_BUILD_WHEELS=ON -DDETECT_CONDA_ENV=OFF"
+
+      test-extras:  test
+
+      # Have to manually specify the cupy install location on arm.
+      # Have to also manually install tokenizers==0.10.2, which is the last tokenizers
+      # to have a binary aarch64 wheel available on PyPI
+      # Otherwise, the tokenizers sdist is used, which needs a Rust compiler
+      test-before-arm64: "pip install tokenizers==0.10.2 cupy-cuda11x -f https://pip.cupy.dev/aarch64"
+
+      test-unittest: "pytest -v -n 8 ./python/cudf/cudf/tests"
+    secrets: inherit
+  dask_cudf-wheel:
+    needs: cudf-wheels
+    uses: rapidsai/shared-action-workflows/.github/workflows/wheels-pure.yml@main
+    with:
+      repo: rapidsai/cudf
+
+      build-type: ${{ inputs.build-type }}
+      branch: ${{ inputs.branch }}
+      sha: ${{ inputs.sha }}
+      date: ${{ inputs.date }}
+
+      package-dir: python/dask_cudf
+      package-name: dask_cudf
+
+      python-package-versioneer-override: ${{ inputs.versioneer-override }}
+      python-package-build-tag: ${{ inputs.build-tag }}
+
+      test-extras:  test
+      test-unittest: "pytest -v -n 8 ./python/dask_cudf/dask_cudf/tests"
+    secrets: inherit

.gitignore

@@ -70,7 +70,6 @@ junit-cudf.xml
 test-results
 
 ## Patching
-*.diff
 *.orig
 *.rej
 
@@ -166,3 +165,8 @@ dask-worker-space/
 # Sphinx docs & build artifacts
 docs/cudf/source/api_docs/generated/*
 docs/cudf/source/api_docs/api/*
+docs/cudf/source/user_guide/example_output/*
+docs/cudf/source/user_guide/cudf.*Dtype.*.rst
+
+# cibuildwheel
+/wheelhouse

.pre-commit-config.yaml

@@ -1,6 +1,19 @@
 # Copyright (c) 2019-2022, NVIDIA CORPORATION.
 
 repos:
+      - repo: https://github.com/pre-commit/pre-commit-hooks
+        rev: v4.3.0
+        hooks:
+              - id: trailing-whitespace
+                exclude: |
+                  (?x)^(
+                    ^python/cudf/cudf/tests/data/subword_tokenizer_data/.*
+                  )
+              - id: end-of-file-fixer
+                exclude: |
+                  (?x)^(
+                    ^python/cudf/cudf/tests/data/subword_tokenizer_data/.*
+                  )
       - repo: https://github.com/PyCQA/isort
         rev: 5.10.1
         hooks:
@@ -18,12 +31,18 @@ repos:
                 # Explicitly specify the pyproject.toml at the repo root, not per-project.
                 args: ["--config", "pyproject.toml"]
       - repo: https://github.com/PyCQA/flake8
-        rev: 3.8.3
+        rev: 5.0.4
         hooks:
               - id: flake8
                 args: ["--config=setup.cfg"]
-                files: python/.*\.(py|pyx|pxd)$
+                files: python/.*$
                 types: [file]
+                types_or: [python, cython]
+                additional_dependencies: ["flake8-force"]
+      - repo: https://github.com/MarcoGorelli/cython-lint
+        rev: v0.1.10
+        hooks:
+              - id: cython-lint
       - repo: https://github.com/pre-commit/mirrors-mypy
         rev: 'v0.971'
         hooks:
@@ -46,6 +65,16 @@ repos:
               - id: clang-format
                 types_or: [c, c++, cuda]
                 args: ["-fallback-style=none", "-style=file", "-i"]
+      - repo: https://github.com/sirosen/texthooks
+        rev: 0.4.0
+        hooks:
+              - id: fix-smartquotes
+                exclude: |
+                  (?x)^(
+                    ^cpp/include/cudf_test/cxxopts.hpp|
+                    ^python/cudf/cudf/tests/data/subword_tokenizer_data/.*|
+                    ^python/cudf/cudf/tests/test_text.py
+                  )
       - repo: local
         hooks:
               - id: no-deprecationwarning