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

.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 @@ if __name__ == "__main__":
     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 @@ if __name__ == "__main__":
     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 @@ if __name__ == "__main__":
     </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

@@ -1,4 +1,10 @@
-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.
@@ -6,3 +12,17 @@ LightGBM has been developed and used by many active community members. Your help
 - 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.

docs/conf.py

@@ -34,7 +34,7 @@ from sphinx.application import Sphinx
 from sphinx.errors import VersionRequirementError
 
 CURR_PATH = Path(__file__).absolute().parent
-LIB_PATH = CURR_PATH.parent / 'python-package'
+LIB_PATH = CURR_PATH.parent / "python-package"
 sys.path.insert(0, str(LIB_PATH))
 
 INTERNAL_REF_REGEX = compile(r"(?P<url>\.\/.+)(?P<extension>\.rst)(?P<anchor>$|#)")
@@ -65,29 +65,29 @@ class IgnoredDirective(Directive):
 
 # -- General configuration ------------------------------------------------
 
-os.environ['LIGHTGBM_BUILD_DOC'] = '1'
-C_API = os.environ.get('C_API', '').lower().strip() != 'no'
-RTD = bool(os.environ.get('READTHEDOCS', ''))
+os.environ["LIGHTGBM_BUILD_DOC"] = "1"
+C_API = os.environ.get("C_API", "").lower().strip() != "no"
+RTD = bool(os.environ.get("READTHEDOCS", ""))
 
 # If your documentation needs a minimal Sphinx version, state it here.
-needs_sphinx = '2.1.0'  # Due to sphinx.ext.napoleon, autodoc_typehints
+needs_sphinx = "2.1.0"  # Due to sphinx.ext.napoleon, autodoc_typehints
 if needs_sphinx > sphinx.__version__:
-    message = f'This project needs at least Sphinx v{needs_sphinx}'
+    message = f"This project needs at least Sphinx v{needs_sphinx}"
     raise VersionRequirementError(message)
 
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
-    'sphinx.ext.autodoc',
-    'sphinx.ext.autosummary',
-    'sphinx.ext.todo',
-    'sphinx.ext.viewcode',
-    'sphinx.ext.napoleon',
+    "sphinx.ext.autodoc",
+    "sphinx.ext.autosummary",
+    "sphinx.ext.todo",
+    "sphinx.ext.viewcode",
+    "sphinx.ext.napoleon",
     "sphinx.ext.intersphinx",
 ]
 
-autodoc_default_flags = ['members', 'inherited-members', 'show-inheritance']
+autodoc_default_flags = ["members", "inherited-members", "show-inheritance"]
 autodoc_default_options = {
     "members": True,
     "inherited-members": True,
@@ -95,54 +95,54 @@ autodoc_default_options = {
 }
 # mock out modules
 autodoc_mock_imports = [
-    'dask',
-    'dask.distributed',
-    'datatable',
-    'graphviz',
-    'matplotlib',
-    'numpy',
-    'pandas',
-    'scipy',
-    'scipy.sparse',
+    "dask",
+    "dask.distributed",
+    "datatable",
+    "graphviz",
+    "matplotlib",
+    "numpy",
+    "pandas",
+    "scipy",
+    "scipy.sparse",
 ]
 try:
     import sklearn  # noqa: F401
 except ImportError:
-    autodoc_mock_imports.append('sklearn')
+    autodoc_mock_imports.append("sklearn")
 # hide type hints in API docs
 autodoc_typehints = "none"
 
 # Generate autosummary pages. Output should be set with: `:toctree: pythonapi/`
-autosummary_generate = ['Python-API.rst']
+autosummary_generate = ["Python-API.rst"]
 
 # Only the class' docstring is inserted.
-autoclass_content = 'class'
+autoclass_content = "class"
 
 # If true, `todo` and `todoList` produce output, else they produce nothing.
 todo_include_todos = False
 
 # The master toctree document.
-master_doc = 'index'
+master_doc = "index"
 
 # General information about the project.
-project = 'LightGBM'
-copyright = f'{datetime.datetime.now().year}, Microsoft Corporation'
-author = 'Microsoft Corporation'
+project = "LightGBM"
+copyright = f"{datetime.datetime.now().year}, Microsoft Corporation"
+author = "Microsoft Corporation"
 
 # The name of an image file (relative to this directory) to place at the top
 # of the sidebar.
-html_logo = str(CURR_PATH / 'logo' / 'LightGBM_logo_grey_text.svg')
+html_logo = str(CURR_PATH / "logo" / "LightGBM_logo_grey_text.svg")
 
 # The name of an image file (relative to this directory) to use as a favicon of
 # the docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
 # pixels large.
-html_favicon = str(CURR_PATH / '_static' / 'images' / 'favicon.ico')
+html_favicon = str(CURR_PATH / "_static" / "images" / "favicon.ico")
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
 # built documents.
 # The short X.Y version.
-version = (CURR_PATH.parent / 'VERSION.txt').read_text(encoding='utf-8').strip().replace('rc', '-rc')
+version = (CURR_PATH.parent / "VERSION.txt").read_text(encoding="utf-8").strip().replace("rc", "-rc")
 # The full version, including alpha/beta/rc tags.
 release = version
 
@@ -151,67 +151,68 @@ release = version
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = 'en'
+language = "en"
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 # This patterns also effect to html_static_path and html_extra_path
-exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 
 # The name of the Pygments (syntax highlighting) style to use.
-pygments_style = 'default'
+pygments_style = "default"
 
 # -- Configuration for C API docs generation ------------------------------
 
 if C_API:
-    extensions.extend([
-        'breathe',
-    ])
-    breathe_projects = {
-        "LightGBM": str(CURR_PATH / 'doxyoutput' / 'xml')
-    }
+    extensions.extend(
+        [
+            "breathe",
+        ]
+    )
+    breathe_projects = {"LightGBM": str(CURR_PATH / "doxyoutput" / "xml")}
     breathe_default_project = "LightGBM"
     breathe_domain_by_extension = {
         "h": "c",
     }
     breathe_show_define_initializer = True
-    c_id_attributes = ['LIGHTGBM_C_EXPORT']
+    c_id_attributes = ["LIGHTGBM_C_EXPORT"]
 
 # -- Options for HTML output ----------------------------------------------
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
-html_theme = 'sphinx_rtd_theme'
+html_theme = "sphinx_rtd_theme"
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
 # documentation.
 html_theme_options = {
-    'includehidden': False,
-    'logo_only': True,
+    "includehidden": False,
+    "logo_only": True,
 }
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]
 
 # -- Options for HTMLHelp output ------------------------------------------
 
 # Output file base name for HTML help builder.
-htmlhelp_basename = 'LightGBMdoc'
+htmlhelp_basename = "LightGBMdoc"
 
 # -- Options for LaTeX output ---------------------------------------------
 
 # The name of an image file (relative to this directory) to place at the top of
 # the title page.
-latex_logo = str(CURR_PATH / 'logo' / 'LightGBM_logo_black_text_small.png')
+latex_logo = str(CURR_PATH / "logo" / "LightGBM_logo_black_text_small.png")
 
 # intersphinx configuration
 intersphinx_mapping = {
     "sklearn": ("https://scikit-learn.org/stable/", None),
 }
 
+
 def generate_doxygen_xml(app: Sphinx) -> None:
     """Generate XML documentation for C API by Doxygen.
 
@@ -238,18 +239,17 @@ def generate_doxygen_xml(app: Sphinx) -> None:
         "SORT_BRIEF_DOCS=YES",
         "WARN_AS_ERROR=YES",
     ]
-    doxygen_input = '\n'.join(doxygen_args)
+    doxygen_input = "\n".join(doxygen_args)
     doxygen_input = bytes(doxygen_input, "utf-8")
-    (CURR_PATH / 'doxyoutput').mkdir(parents=True, exist_ok=True)
+    (CURR_PATH / "doxyoutput").mkdir(parents=True, exist_ok=True)
     try:
         # Warning! The following code can cause buffer overflows on RTD.
         # Consider suppressing output completely if RTD project silently fails.
         # Refer to https://github.com/svenevs/exhale
         # /blob/fe7644829057af622e467bb529db6c03a830da99/exhale/deploy.py#L99-L111
-        process = Popen(["doxygen", "-"],
-                        stdin=PIPE, stdout=PIPE, stderr=PIPE)
+        process = Popen(["doxygen", "-"], stdin=PIPE, stdout=PIPE, stderr=PIPE)
         stdout, stderr = process.communicate(doxygen_input)
-        output = '\n'.join([i.decode('utf-8') for i in (stdout, stderr) if i is not None])
+        output = "\n".join([i.decode("utf-8") for i in (stdout, stderr) if i is not None])
         if process.returncode != 0:
             raise RuntimeError(output)
         else:
@@ -296,11 +296,9 @@ def generate_r_docs(app: Sphinx) -> None:
         # Consider suppressing output completely if RTD project silently fails.
         # Refer to https://github.com/svenevs/exhale
         # /blob/fe7644829057af622e467bb529db6c03a830da99/exhale/deploy.py#L99-L111
-        process = Popen(['/bin/bash'],
-                        stdin=PIPE, stdout=PIPE, stderr=PIPE,
-                        universal_newlines=True)
+        process = Popen(["/bin/bash"], stdin=PIPE, stdout=PIPE, stderr=PIPE, universal_newlines=True)
         stdout, stderr = process.communicate(commands)
-        output = '\n'.join([i for i in (stdout, stderr) if i is not None])
+        output = "\n".join([i for i in (stdout, stderr) if i is not None])
         if process.returncode != 0:
             raise RuntimeError(output)
         else:
@@ -318,19 +316,19 @@ def setup(app: Sphinx) -> None:
     app : sphinx.application.Sphinx
         The application object representing the Sphinx process.
     """
-    first_run = not (CURR_PATH / '_FIRST_RUN.flag').exists()
+    first_run = not (CURR_PATH / "_FIRST_RUN.flag").exists()
     if first_run and RTD:
-        (CURR_PATH / '_FIRST_RUN.flag').touch()
+        (CURR_PATH / "_FIRST_RUN.flag").touch()
     if C_API:
         app.connect("builder-inited", generate_doxygen_xml)
     else:
-        app.add_directive('doxygenfile', IgnoredDirective)
+        app.add_directive("doxygenfile", IgnoredDirective)
     if RTD:  # build R docs only on Read the Docs site
         if first_run:
             app.connect("builder-inited", generate_r_docs)
-        app.connect("build-finished",
-                    lambda app, _: copytree(CURR_PATH.parent / "lightgbm_r" / "docs",
-                                            Path(app.outdir) / "R"))
+        app.connect(
+            "build-finished", lambda app, _: copytree(CURR_PATH.parent / "lightgbm_r" / "docs", Path(app.outdir) / "R")
+        )
     app.add_transform(InternalRefTransform)
-    add_js_file = getattr(app, 'add_js_file', False) or app.add_javascript
+    add_js_file = getattr(app, "add_js_file", False) or app.add_javascript
     add_js_file("js/script.js")

helpers/check_dynamic_dependencies.py

@@ -25,7 +25,7 @@ def check_dependencies(objdump_string: str) -> None:
     objdump_string : str
         The dynamic symbol table entries of the file (result of `objdump -T` command).
     """
-    GLIBC_version = re.compile(r'0{16}[ \(\t]+GLIBC_(\d{1,2})[.](\d{1,3})[.]?\d{,3}[ \)\t]+')
+    GLIBC_version = re.compile(r"0{16}[ \(\t]+GLIBC_(\d{1,2})[.](\d{1,3})[.]?\d{,3}[ \)\t]+")
     versions = GLIBC_version.findall(objdump_string)
     assert len(versions) > 1
     for major, minor in versions:
@@ -33,16 +33,16 @@ def check_dependencies(objdump_string: str) -> None:
         assert int(major) <= 2, error_msg
         assert int(minor) <= 28, error_msg
 
-    GLIBCXX_version = re.compile(r'0{16}[ \(\t]+GLIBCXX_(\d{1,2})[.](\d{1,2})[.]?(\d{,3})[ \)\t]+')
+    GLIBCXX_version = re.compile(r"0{16}[ \(\t]+GLIBCXX_(\d{1,2})[.](\d{1,2})[.]?(\d{,3})[ \)\t]+")
     versions = GLIBCXX_version.findall(objdump_string)
     assert len(versions) > 1
     for major, minor, patch in versions:
         error_msg = f"found unexpected GLIBCXX version: '{major}.{minor}.{patch}'"
         assert int(major) == 3, error_msg
         assert int(minor) == 4, error_msg
-        assert patch == '' or int(patch) <= 22, error_msg
+        assert patch == "" or int(patch) <= 22, error_msg
 
-    GOMP_version = re.compile(r'0{16}[ \(\t]+G?OMP_(\d{1,2})[.](\d{1,2})[.]?\d{,3}[ \)\t]+')
+    GOMP_version = re.compile(r"0{16}[ \(\t]+G?OMP_(\d{1,2})[.](\d{1,2})[.]?\d{,3}[ \)\t]+")
     versions = GOMP_version.findall(objdump_string)
     assert len(versions) > 1
     for major, minor in versions:
@@ -52,4 +52,4 @@ def check_dependencies(objdump_string: str) -> None:
 
 
 if __name__ == "__main__":
-    check_dependencies(Path(sys.argv[1]).read_text(encoding='utf-8'))
+    check_dependencies(Path(sys.argv[1]).read_text(encoding="utf-8"))

helpers/parameter_generator.py

@@ -12,9 +12,7 @@ from pathlib import Path
 from typing import Dict, List, Tuple
 
 
-def get_parameter_infos(
-    config_hpp: Path
-) -> Tuple[List[Tuple[str, int]], List[List[Dict[str, List]]]]:
+def get_parameter_infos(config_hpp: Path) -> Tuple[List[Tuple[str, int]], List[List[Dict[str, List]]]]:
     """Parse config header file.
 
     Parameters
@@ -44,7 +42,7 @@ def get_parameter_infos(
                 cur_key = line.split("region")[1].strip()
                 keys.append((cur_key, key_lvl))
                 member_infos.append([])
-            elif '#pragma endregion' in line:
+            elif "#pragma endregion" in line:
                 key_lvl -= 1
                 if cur_key is not None:
                     cur_key = None
@@ -87,9 +85,7 @@ def get_parameter_infos(
     return keys, member_infos
 
 
-def get_names(
-    infos: List[List[Dict[str, List]]]
-) -> List[str]:
+def get_names(infos: List[List[Dict[str, List]]]) -> List[str]:
     """Get names of all parameters.
 
     Parameters
@@ -109,9 +105,7 @@ def get_names(
     return names
 
 
-def get_alias(
-    infos: List[List[Dict[str, List]]]
-) -> List[Tuple[str, str]]:
+def get_alias(infos: List[List[Dict[str, List]]]) -> List[Tuple[str, str]]:
     """Get aliases of all parameters.
 
     Parameters
@@ -129,16 +123,13 @@ def get_alias(
         for y in x:
             if "alias" in y:
                 name = y["name"][0]
-                alias = y["alias"][0].split(',')
+                alias = y["alias"][0].split(",")
                 for name2 in alias:
                     pairs.append((name2.strip(), name))
     return pairs
 
 
-def parse_check(
-    check: str,
-    reverse: bool = False
-) -> Tuple[str, str]:
+def parse_check(check: str, reverse: bool = False) -> Tuple[str, str]:
     """Parse the constraint.
 
     Parameters
@@ -160,17 +151,13 @@ def parse_check(
         idx = 2
         float(check[idx:])
     if reverse:
-        reversed_sign = {'<': '>', '>': '<', '<=': '>=', '>=': '<='}
+        reversed_sign = {"<": ">", ">": "<", "<=": ">=", ">=": "<="}
         return check[idx:], reversed_sign[check[:idx]]
     else:
         return check[idx:], check[:idx]
 
 
-def set_one_var_from_string(
-    name: str,
-    param_type: str,
-    checks: List[str]
-) -> str:
+def set_one_var_from_string(name: str, param_type: str, checks: List[str]) -> str:
     """Construct code for auto config file for one param value.
 
     Parameters
@@ -209,9 +196,7 @@ def set_one_var_from_string(
 
 
 def gen_parameter_description(
-    sections: List[Tuple[str, int]],
-    descriptions: List[List[Dict[str, List]]],
-    params_rst: Path
+    sections: List[Tuple[str, int]], descriptions: List[List[Dict[str, List]]], params_rst: Path
 ) -> None:
     """Write descriptions of parameters to the documentation file.
 
@@ -225,58 +210,57 @@ def gen_parameter_description(
         Path to the file with parameters documentation.
     """
     params_to_write = []
-    lvl_mapper = {1: '-', 2: '~'}
+    lvl_mapper = {1: "-", 2: "~"}
     for (section_name, section_lvl), section_params in zip(sections, descriptions):
         heading_sign = lvl_mapper[section_lvl]
-        params_to_write.append(f'{section_name}\n{heading_sign * len(section_name)}')
+        params_to_write.append(f"{section_name}\n{heading_sign * len(section_name)}")
         for param_desc in section_params:
-            name = param_desc['name'][0]
-            default_raw = param_desc['default'][0]
+            name = param_desc["name"][0]
+            default_raw = param_desc["default"][0]
             default = default_raw.strip('"') if len(default_raw.strip('"')) > 0 else default_raw
-            param_type = param_desc.get('type', param_desc['inner_type'])[0].split(':')[-1].split('<')[-1].strip('>')
-            options = param_desc.get('options', [])
+            param_type = param_desc.get("type", param_desc["inner_type"])[0].split(":")[-1].split("<")[-1].strip(">")
+            options = param_desc.get("options", [])
             if len(options) > 0:
-                opts = '``, ``'.join([x.strip() for x in options[0].split(',')])
-                options_str = f', options: ``{opts}``'
+                opts = "``, ``".join([x.strip() for x in options[0].split(",")])
+                options_str = f", options: ``{opts}``"
             else:
-                options_str = ''
-            aliases = param_desc.get('alias', [])
+                options_str = ""
+            aliases = param_desc.get("alias", [])
             if len(aliases) > 0:
-                aliases_joined = '``, ``'.join([x.strip() for x in aliases[0].split(',')])
-                aliases_str = f', aliases: ``{aliases_joined}``'
+                aliases_joined = "``, ``".join([x.strip() for x in aliases[0].split(",")])
+                aliases_str = f", aliases: ``{aliases_joined}``"
             else:
-                aliases_str = ''
-            checks = sorted(param_desc.get('check', []))
+                aliases_str = ""
+            checks = sorted(param_desc.get("check", []))
             checks_len = len(checks)
             if checks_len > 1:
                 number1, sign1 = parse_check(checks[0])
                 number2, sign2 = parse_check(checks[1], reverse=True)
-                checks_str = f', constraints: ``{number2} {sign2} {name} {sign1} {number1}``'
+                checks_str = f", constraints: ``{number2} {sign2} {name} {sign1} {number1}``"
             elif checks_len == 1:
                 number, sign = parse_check(checks[0])
-                checks_str = f', constraints: ``{name} {sign} {number}``'
+                checks_str = f", constraints: ``{name} {sign} {number}``"
             else:
-                checks_str = ''
+                checks_str = ""
             main_desc = f'-  ``{name}`` :raw-html:`<a id="{name}" title="Permalink to this parameter" href="#{name}">&#x1F517;&#xFE0E;</a>`, default = ``{default}``, type = {param_type}{options_str}{aliases_str}{checks_str}'
             params_to_write.append(main_desc)
-            params_to_write.extend([f"{' ' * 3 * int(desc[0][-1])}-  {desc[1]}" for desc in param_desc['desc']])
+            params_to_write.extend([f"{' ' * 3 * int(desc[0][-1])}-  {desc[1]}" for desc in param_desc["desc"]])
 
     with open(params_rst) as original_params_file:
         all_lines = original_params_file.read()
-        before, start_sep, _ = all_lines.partition('.. start params list\n\n')
-        _, end_sep, after = all_lines.partition('\n\n.. end params list')
+        before, start_sep, _ = all_lines.partition(".. start params list\n\n")
+        _, end_sep, after = all_lines.partition("\n\n.. end params list")
 
     with open(params_rst, "w") as new_params_file:
         new_params_file.write(before)
         new_params_file.write(start_sep)
-        new_params_file.write('\n\n'.join(params_to_write))
+        new_params_file.write("\n\n".join(params_to_write))
         new_params_file.write(end_sep)
         new_params_file.write(after)
 
 
 def gen_parameter_code(
-    config_hpp: Path,
-    config_out_cpp: Path
+    config_hpp: Path, config_out_cpp: Path
 ) -> Tuple[List[Tuple[str, int]], List[List[Dict[str, List]]]]:
     """Generate auto config file.
 
@@ -367,7 +351,7 @@ def gen_parameter_code(
         if names_with_aliases[name]:
             str_to_write += '{"' + '", "'.join(names_with_aliases[name]) + '"}},'
         else:
-            str_to_write += '{}},'
+            str_to_write += "{}},"
     str_to_write += """
   });
   return map;
@@ -376,22 +360,22 @@ def gen_parameter_code(
 """
     str_to_write += """const std::unordered_map<std::string, std::string>& Config::ParameterTypes() {
   static std::unordered_map<std::string, std::string> map({"""
-    int_t_pat = re.compile(r'int\d+_t')
+    int_t_pat = re.compile(r"int\d+_t")
     # the following are stored as comma separated strings but are arrays in the wrappers
     overrides = {
-        'categorical_feature': 'vector<int>',
-        'ignore_column': 'vector<int>',
-        'interaction_constraints': 'vector<vector<int>>',
+        "categorical_feature": "vector<int>",
+        "ignore_column": "vector<int>",
+        "interaction_constraints": "vector<vector<int>>",
     }
     for x in infos:
         for y in x:
             name = y["name"][0]
-            if name == 'task':
+            if name == "task":
                 continue
             if name in overrides:
                 param_type = overrides[name]
             else:
-                param_type = int_t_pat.sub('int', y["inner_type"][0]).replace('std::', '')
+                param_type = int_t_pat.sub("int", y["inner_type"][0]).replace("std::", "")
             str_to_write += '\n    {"' + name + '", "' + param_type + '"},'
     str_to_write += """
   });
@@ -409,8 +393,8 @@ def gen_parameter_code(
 
 if __name__ == "__main__":
     current_dir = Path(__file__).absolute().parent
-    config_hpp = current_dir.parent / 'include' / 'LightGBM' / 'config.h'
-    config_out_cpp = current_dir.parent / 'src' / 'io' / 'config_auto.cpp'
-    params_rst = current_dir.parent / 'docs' / 'Parameters.rst'
+    config_hpp = current_dir.parent / "include" / "LightGBM" / "config.h"
+    config_out_cpp = current_dir.parent / "src" / "io" / "config_auto.cpp"
+    params_rst = current_dir.parent / "docs" / "Parameters.rst"
     sections, descriptions = gen_parameter_code(config_hpp, config_out_cpp)
     gen_parameter_description(sections, descriptions, params_rst)

python-package/pyproject.toml

@@ -95,11 +95,29 @@ ignore_missing_imports = true
 exclude = [
     "build",
     "compile",
-    "docs",
     "external_libs",
     "lightgbm-python",
-    "setup.py"
 ]
+line-length = 120
+
+# this should be set to the oldest version of python LightGBM supports
+target-version = "py37"
+
+[tool.ruff.format]
+docstring-code-format = false
+exclude = [
+    "build/*.py",
+    "compile/*.py",
+    "examples/*.py",
+    "external_libs/*.py",
+    "lightgbm-python/*.py",
+    "python-package/*.py",
+    "tests/*.py"
+]
+indent-style = "space"
+quote-style = "double"
+
+[tool.ruff.lint]
 ignore = [
     # (pydocstyle) Missing docstring in magic method
     "D105",
@@ -125,10 +143,13 @@ select = [
     "T",
 ]
 
-# this should be set to the oldest version of python LightGBM supports
-target-version = "py37"
-
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
+"docs/conf.py" = [
+    # (flake8-bugbear) raise exceptions with "raise ... from errr"
+    "B904",
+    # (flake8-print) flake8-print
+    "T"
+]
 "examples/*" = [
     # pydocstyle
     "D",
@@ -144,6 +165,5 @@ target-version = "py37"
     "T"
 ]
 
-[tool.ruff.pydocstyle]
-
+[tool.ruff.lint.pydocstyle]
 convention = "numpy"