[ci] enable ruff-format on some files, add pre-commit config (#6308)

Author: jameslamb

.ci/get_workflow_status.py

@@ -32,25 +32,26 @@ def get_runs(trigger_phrase):
     """
     pr_runs = []
     if environ.get("GITHUB_EVENT_NAME", "") == "pull_request":
-        pr_number = int(environ.get("GITHUB_REF").split('/')[-2])
+        pr_number = int(environ.get("GITHUB_REF").split("/")[-2])
         page = 1
         while True:
             req = request.Request(
                 url="{}/repos/microsoft/LightGBM/issues/{}/comments?page={}&per_page=100".format(
-                    environ.get("GITHUB_API_URL"),
-                    pr_number,
-                    page
+                    environ.get("GITHUB_API_URL"), pr_number, page
                 ),
-                headers={"Accept": "application/vnd.github.v3+json"}
+                headers={"Accept": "application/vnd.github.v3+json"},
             )
             url = request.urlopen(req)
-            data = json.loads(url.read().decode('utf-8'))
+            data = json.loads(url.read().decode("utf-8"))
             url.close()
             if not data:
                 break
-            runs_on_page = [i for i in data
-                            if i['author_association'].lower() in {'owner', 'member', 'collaborator'}
-                            and i['body'].startswith('/gha run {}'.format(trigger_phrase))]
+            runs_on_page = [
+                i
+                for i in data
+                if i["author_association"].lower() in {"owner", "member", "collaborator"}
+                and i["body"].startswith("/gha run {}".format(trigger_phrase))
+            ]
             pr_runs.extend(runs_on_page)
             page += 1
     return pr_runs[::-1]
@@ -70,20 +71,20 @@ def get_status(runs):
         The most recent status of workflow.
         Can be 'success', 'failure' or 'in-progress'.
     """
-    status = 'success'
+    status = "success"
     for run in runs:
-        body = run['body']
+        body = run["body"]
         if "Status: " in body:
             if "Status: skipped" in body:
                 continue
             if "Status: failure" in body:
-                status = 'failure'
+                status = "failure"
                 break
             if "Status: success" in body:
-                status = 'success'
+                status = "success"
                 break
         else:
-            status = 'in-progress'
+            status = "in-progress"
             break
     return status
 
@@ -92,8 +93,8 @@ def get_status(runs):
     trigger_phrase = argv[1]
     while True:
         status = get_status(get_runs(trigger_phrase))
-        if status != 'in-progress':
+        if status != "in-progress":
             break
         sleep(60)
-    if status == 'failure':
+    if status == "failure":
         exit(1)

.ci/lint-python.sh

@@ -1,19 +1,8 @@
 #!/bin/sh
 
-echo "running ruff"
-ruff check \
-    --config=./python-package/pyproject.toml \
-    . \
-|| exit 1
-echo "done running ruff"
-
-echo "running isort"
-isort \
-    --check-only \
-    --settings-path=./python-package/pyproject.toml \
-    . \
-|| exit 1
-echo "done running isort"
+echo "running pre-commit checks"
+pre-commit run --all-files || exit 1
+echo "done running pre-commit checks"
 
 echo "running mypy"
 mypy \

.ci/test.sh

@@ -74,10 +74,9 @@ if [[ $TASK == "lint" ]]; then
         ${CONDA_PYTHON_REQUIREMENT} \
         cmakelint \
         cpplint \
-        isort \
         mypy \
-        'r-lintr>=3.1' \
-        ruff
+        'pre-commit>=3.6.0' \
+        'r-lintr>=3.1'
     source activate $CONDA_ENV
     echo "Linting Python code"
     sh ${BUILD_DIRECTORY}/.ci/lint-python.sh || exit 1

.nuget/create_nuget.py

@@ -20,7 +20,7 @@
     copyfile(source / "lib_lightgbm.dylib", osx_folder_path / "lib_lightgbm.dylib")
     copyfile(source / "lib_lightgbm.dll", windows_folder_path / "lib_lightgbm.dll")
     copyfile(source / "lightgbm.exe", windows_folder_path / "lightgbm.exe")
-    version = (current_dir.parent / 'VERSION.txt').read_text(encoding='utf-8').strip().replace('rc', '-rc')
+    version = (current_dir.parent / "VERSION.txt").read_text(encoding="utf-8").strip().replace("rc", "-rc")
     nuget_str = rf"""<?xml version="1.0"?>
     <package xmlns="http://schemas.microsoft.com/packaging/2013/05/nuspec.xsd">
     <metadata>
@@ -75,6 +75,6 @@
     </Target>
     </Project>
     """
-    (current_dir / "LightGBM.nuspec").write_text(nuget_str, encoding='utf-8')
-    (current_dir / "build" / "LightGBM.props").write_text(prop_str, encoding='utf-8')
-    (current_dir / "build" / "LightGBM.targets").write_text(target_str, encoding='utf-8')
+    (current_dir / "LightGBM.nuspec").write_text(nuget_str, encoding="utf-8")
+    (current_dir / "build" / "LightGBM.props").write_text(prop_str, encoding="utf-8")
+    (current_dir / "build" / "LightGBM.targets").write_text(target_str, encoding="utf-8")

.pre-commit-config.yaml

@@ -0,0 +1,25 @@
+exclude: |
+  (?x)^(
+      build|
+      external_libs|
+      lightgbm-python|
+      lightgbm_r|
+  )$
+
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.2.1
+    hooks:
+      # Run the linter.
+      - id: ruff
+        args: ["--config", "python-package/pyproject.toml"]
+      # Run the formatter.
+      - id: ruff-format
+        args: ["--config", "python-package/pyproject.toml"]
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        name: isort (python)
+        args: ["--settings-path", "python-package/pyproject.toml"]

CONTRIBUTING.md

@@ -1,8 +1,28 @@
-LightGBM has been developed and used by many active community members. Your help is very valuable to make it better for everyone.
+# contributing
+
+LightGBM has been developed and used by many active community members.
+
+Your help is very valuable to make it better for everyone.
+
+## How to Contribute
 
 - Check for the [Roadmap](https://github.com/microsoft/LightGBM/projects/1) and the [Feature Requests Hub](https://github.com/microsoft/LightGBM/issues/2302), and submit pull requests to address chosen issue. If you need development guideline, you can check the [Development Guide](https://github.com/microsoft/LightGBM/blob/master/docs/Development-Guide.rst) or directly ask us in Issues/Pull Requests.
 - Contribute to the [tests](https://github.com/microsoft/LightGBM/tree/master/tests) to make it more reliable.
 - Contribute to the [documentation](https://github.com/microsoft/LightGBM/tree/master/docs) to make it clearer for everyone.
 - Contribute to the [examples](https://github.com/microsoft/LightGBM/tree/master/examples) to share your experience with other users.
 - Add your stories and experience to [Awesome LightGBM](https://github.com/microsoft/LightGBM/blob/master/examples/README.md). If LightGBM helped you in a machine learning competition or some research application, we want to hear about it!
 - [Open an issue](https://github.com/microsoft/LightGBM/issues) to report problems or recommend new features.
+
+## Development Guide
+
+### Linting
+
+Every commit in the repository is tested with multiple static analyzers.
+
+When developing locally, run some of them using `pre-commit` ([pre-commit docs](https://pre-commit.com/)).
+
+```shell
+pre-commit run --all-files
+```
+
+That command will check for some issues and automatically reformat the code.