Merge pull request #204 from peytondmurray/17-lint-workflow

Add pre-commit and associated CI

.github/workflows/lint.yml

@@ -0,0 +1,14 @@
+name: pre-commit
+
+on:
+  pull_request:
+  push:
+     branches: [master]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v5
+    - uses: pre-commit/action@v3.0.1

.gitignore

@@ -0,0 +1,138 @@
+# LINT.IfChange
+# Byte-compiled / optimized / DLL files
+__pycache__/
+**/*.py[cod]
+**/*$py.class
+
+# C extensions
+**/*.so
+
+# Distribution / packaging
+.Python
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don’t work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# Intellij project settings
+.idea
+
+# VSCode project settings
+.vscode
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Bazel generated files
+bazel-*
+**/*_pb2.py
+**/*_pb2_grpc.py
+# LINT.ThenChange(.dockerignore)
+
+MODULE.bazel
+MODULE.bazel.lock

.pre-commit-config.yaml

@@ -0,0 +1,37 @@
+# pre-commit is a tool to perform a predefined set of tasks manually and/or
+# automatically before git commits are made.
+#
+# Config reference: https://pre-commit.com/#pre-commit-configyaml---top-level
+#
+# Common tasks
+#
+# - Register git hooks: pre-commit install
+# - Run on all files:   pre-commit run --all-files
+#
+# These pre-commit hooks are run as CI.
+#
+# NOTE: if it can be avoided, add configs/args in pyproject.toml or below instead of creating a new `.config.file`.
+# https://pre-commit.ci/#configuration
+ci:
+  autoupdate_schedule: monthly
+  autofix_commit_msg: |
+    [pre-commit.ci] Apply automatic pre-commit fixes
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: end-of-file-fixer
+        exclude: '\.svg$'
+      - id: trailing-whitespace
+        exclude: '\.svg$'
+      - id: check-json
+      - id: check-yaml
+        args: [--allow-multiple-documents, --unsafe]
+      - id: check-toml
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.5.6
+    hooks:
+      - id: ruff
+        args: ["--fix"]

CONTRIBUTING.md

@@ -21,3 +21,36 @@ All submissions, including submissions by project members, require review. We
 use GitHub pull requests for this purpose. Consult
 [GitHub Help](https://help.github.com/articles/about-pull-requests/) for more
 information on using pull requests.
+
+## Using `pre-commit`
+
+To enforce style and coding standards, this repository uses
+[`pre-commit`](https://pre-commit.com/). To get started:
+
+```shell
+pip install pre-commit
+pre-commit install
+```
+
+### Run pre-commit on all files
+
+By default, `pre-commit` will run its checks on files that have been modified in
+a commit. To instead run it on all files, use this command:
+
+```console
+$ pre-commit run --all-files
+
+# Alternatively
+$ pre-commit run -a
+```
+
+### Skip the pre-commit checks
+
+Run the following command:
+
+```console
+$ git commit --no-verify
+```
+
+Be aware the pre-commit checks are run on CI, so any violations will need to be
+fixed before code gets merged.

pyproject.toml

@@ -19,3 +19,101 @@ requires = [
   # Required for using org_tensorflow bazel repository.
   "numpy~=1.22.0",
 ]
+
+[tool.ruff]
+line-length = 88
+
+[tool.ruff.lint]
+select = [
+    # pycodestyle
+    "E",
+    "W",
+    # Pyflakes
+    "F",
+    # pyupgrade
+    "UP",
+    # flake8-bugbear
+    "B",
+    # flake8-simplify
+    "SIM",
+    # isort
+    "I",
+    # pep8 naming
+    "N",
+    # pydocstyle
+    "D",
+    # annotations
+    "ANN",
+    # debugger
+    "T10",
+    # flake8-pytest
+    "PT",
+    # flake8-return
+    "RET",
+    # flake8-unused-arguments
+    "ARG",
+    # flake8-fixme
+    "FIX",
+    # flake8-eradicate
+    "ERA",
+    # pandas-vet
+    "PD",
+    # numpy-specific rules
+    "NPY",
+]
+ignore = [
+    "D104", # Missing docstring in public package
+    "D100", # Missing docstring in public module
+    "D211", # No blank line before class
+    "D213", # Multiline summary second line
+    "PD901", # Avoid using 'df' for pandas dataframes. Perfectly fine in functions with limited scope
+    "ANN201", # Missing return type annotation for public function (makes no sense for NoneType return types...)
+    "ANN101", # Missing type annotation for `self`
+    "ANN204", # Missing return type annotation for special method
+    "ANN002", # Missing type annotation for `*args`
+    "ANN003", # Missing type annotation for `**kwargs`
+    "D105", # Missing docstring in magic method
+    "D203", # 1 blank line before after class docstring
+    "D204", # 1 blank line required after class docstring
+    "D413", # 1 blank line after parameters
+    "SIM108", # Simplify if/else to one line; not always clearer
+    "D206", # Advised to disable by ruff-format
+    "E501", # Advised to disable by ruff-format
+    "W191", # Advised to disable by ruff-format
+    "N802", # Function name should be lowercase; unittest uses mixed case
+    "D107", # Missing docstring in `__init__`
+
+    # These are issues which remain to be fixed
+    "D102", # Missing docstring in public method
+    "D103", # Missing docstring in public function
+    "D401", # First line of docstring should be in imperative mood
+    "D404", # First word of the docstring should not be "This"
+    "ANN001", # Missing type annotation for function argument
+    "ANN202", # Missing return type for private function
+    "B024", # <class> is an abstract base class,  but it has no abstract methods
+    "FIX002", # Line contains TODO, consider resolving the issue
+    "ANN401", # Dynamically typed expressions (typing.Any) are disallowed
+    "UP008", # Use `super()` instead of `super(__class__, self)`
+    "SIM102", # Use a single `if` statement instead of nested `if` statements
+]
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = [
+    "F401", # Unused import
+]
+"*_test.py" = [
+    "ANN001", # Type annotations aren't needed for tests; these are fixtures or parametrizations
+    "PT009", # Use a regular `assert` instead of a unittest-style `assertEqual`
+    "PT027", # Use `pytest.raises` instead of unittest-style `assertRaisesRegex`
+
+    # Missing docstrings; probably want to fill these out for tests. For now, we just disable
+    "D101", # Missing docstring in public class
+    "D102", # Missing docstring in public method
+
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.isort]
+profile = "black"

setup.py

@@ -13,23 +13,21 @@
 # limitations under the License.
 """Package Setup script for ML Metadata."""
 
-import os
+import os  # noqa: I001
 import platform
 import shutil
 import subprocess
 import sys
 
 import setuptools
-from setuptools import find_packages
-from setuptools import setup
+from setuptools import find_packages, setup
 from setuptools.command.install import install
 from setuptools.dist import Distribution
-# pylint: disable=g-bad-import-order
+
 # It is recommended to import setuptools prior to importing distutils to avoid
 # using legacy behavior from distutils.
 # https://setuptools.readthedocs.io/en/latest/history.html#v48-0-0
 from distutils.command import build
-# pylint: enable=g-bad-import-order
 
 _IS_PY311 = sys.version_info >= (3, 11)
 
@@ -166,6 +164,9 @@ def run(self):
         f'protobuf>={"4.25.2" if _IS_PY311 else "3.20.3"},<5',
         'six>=1.10,<2',
     ],
+    extras_require={
+        'lint': ['pre-commit'],
+    },
     python_requires='>=3.9,<4',
     packages=find_packages(),
     include_package_data=True,