Update pyproject.toml and .pre-commit-config.yaml for common SciTools standards

.pre-commit-config.yaml

@@ -1,5 +1,25 @@
 # See https://pre-commit.com for more information
 # See https://pre-commit.com/hooks.html for more hooks
+# See https://pre-commit.ci/#configuration
+# See https://github.com/scientific-python/cookie#sp-repo-review
+
+ci:
+  autofix_prs: false
+  autoupdate_commit_msg: "chore: update pre-commit hooks"
+
+
+# Alphabetised, for lack of a better order.
+files: |
+    (?x)(
+        benchmarks\/.+\.py|
+        docs\/.+\.py|
+        esmf_regrid\/.+\.py|
+        noxfile\.py|
+        pyproject\.toml|
+        setup\.py
+    )
+minimum_pre_commit_version: 1.21.0
+
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
     rev: 'v5.0.0'
@@ -14,22 +34,70 @@ repos:
     -   id: check-merge-conflict
         # Check for debugger imports and py37+ `breakpoint()` calls in Python source.
     -   id: debug-statements
-        # Don't commit to master branch.
+        # Check TOML file syntax.
+    -   id: check-toml
+        # Check YAML file syntax.
+    -   id: check-yaml
+        # Makes sure files end in a newline and only a newline.
+        # Duplicates Ruff W292 but also works on non-Python files.
+    -   id: end-of-file-fixer
+        # Replaces or checks mixed line ending.
+    -   id: mixed-line-ending
+        # Don't commit to main branch.
     -   id: no-commit-to-branch
--   repo: https://github.com/psf/black
-    rev: '24.10.0'
-    hooks:
-    -   id: black
-        # Force black to run on whole repo, using settings from pyproject.toml
-        pass_filenames: false
-        args: [--config=./pyproject.toml, .]
--   repo: https://github.com/PyCQA/flake8
-    rev: '7.1.1'
-    hooks:
-        # Run flake8.
-    -   id: flake8
-        args: [--config=./.flake8]
-        additional_dependencies: [
-            'flake8-docstrings==1.7.0',
-            'flake8-import-order==0.18.2',
-        ]
+        # Trims trailing whitespace.
+        # Duplicates Ruff W291 but also works on non-Python files.
+    -   id: trailing-whitespace
+
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: "v0.4.4"
+    hooks:
+    -   id: ruff
+        types: [file, python]
+        args: [--fix, --show-fixes]
+    -   id: ruff-format
+        types: [file, python]
+
+-   repo: https://github.com/codespell-project/codespell
+    rev: "v2.2.6"
+    hooks:
+    -   id: codespell
+        types_or: [asciidoc, python, markdown, rst]
+        additional_dependencies: [tomli]
+
+-   repo: https://github.com/adamchainz/blacken-docs
+    rev: 1.16.0
+    hooks:
+    -   id: blacken-docs
+        types: [file, rst]
+
+-   repo: https://github.com/aio-libs/sort-all
+    rev: v1.2.0
+    hooks:
+    -   id: sort-all
+        types: [file, python]
+
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: 'v1.10.0'
+    hooks:
+    -   id: mypy
+        exclude: 'noxfile\.py|docs/src/conf\.py|^benchmarks'
+
+-   repo: https://github.com/abravalheri/validate-pyproject
+    # More exhaustive than Ruff RUF200.
+    rev: "v0.18"
+    hooks:
+    - id: validate-pyproject
+
+-   repo: https://github.com/scientific-python/cookie
+    rev: 2024.04.23
+    hooks:
+    - id: sp-repo-review
+      additional_dependencies: ["repo-review[cli]"]
+      args: ["--show=errskip"]
+
+-   repo: https://github.com/numpy/numpydoc
+    rev: v1.7.0
+    hooks:
+      - id: numpydoc-validation
+        types: [file, python]

benchmarks/asv_delegated_conda.py

@@ -14,8 +14,7 @@
 
 
 class CondaDelegated(Conda):
-    """
-    Manage a Conda environment using custom user scripts, run at each commit.
+    """Manage a Conda environment using custom user scripts, run at each commit.
 
     Ignores user input variations - ``matrix`` / ``pythons`` /
     ``conda_environment_file``, since environment is being managed outside ASV.
@@ -36,8 +35,7 @@ def __init__(
         requirements: dict,
         tagged_env_vars: dict,
     ) -> None:
-        """
-        Create the instance.
+        """Create the instance.
 
         Parameters
         ----------

benchmarks/benchmarks/__init__.py

@@ -4,8 +4,7 @@
 
 
 def disable_repeat_between_setup(benchmark_object):
-    """
-    Decorate benchmarks where object persistence would be inappropriate.
+    """Decorate benchmarks where object persistence would be inappropriate.
 
     E.g:
         * Data is realised during testing.
@@ -30,8 +29,7 @@ def disable_repeat_between_setup(benchmark_object):
 
 
 def skip_benchmark(benchmark_object):
-    """
-    Decorate benchmarks to be skipped.
+    """Decorate benchmarks to be skipped.
 
     Simply doesn't return the object.
 
@@ -43,12 +41,10 @@ def skip_benchmark(benchmark_object):
     (e.g. ``def time_something(self):`` ).
 
     """
-    pass
 
 
 def on_demand_benchmark(benchmark_object):
-    """
-    Decorate benchmark(s) that are disabled unless ON_DEMAND_BENCHARKS env var is set.
+    """Decorate benchmark(s) that are disabled unless ON_DEMAND_BENCHARKS env var is set.
 
     For benchmarks that, for whatever reason, should not be run by default.
     E.g:

benchmarks/benchmarks/esmf_regridder/__init__.py

@@ -15,6 +15,7 @@
     MeshToGridESMFRegridder,
 )
 from esmf_regrid.schemes import ESMFAreaWeightedRegridder
+
 from ..generate_data import _curvilinear_cube, _grid_cube, _gridlike_mesh_cube
 
 

benchmarks/benchmarks/esmf_regridder/scalability.py

@@ -14,6 +14,7 @@
     MeshToGridESMFRegridder,
 )
 from esmf_regrid.schemes import ESMFAreaWeightedRegridder
+
 from .. import on_demand_benchmark, skip_benchmark
 from ..generate_data import _grid_cube, _gridlike_mesh_cube
 
@@ -64,7 +65,7 @@ def time_prepare(self, n):
 class PrepareScalabilityMeshToGrid(PrepareScalabilityMixin):
     """Benchmarks for the prepare step of :class:`~esmf_regrid.esmf_regrid.schemes.MeshToGridESMFRegridder`."""
 
-    regridder = MeshToGridESMFRegridder
+    regridder = MeshToGridESMFRegridder  # type: ignore[assignment]
 
     def src_cube(self, n):
         """Cube to regrid from."""
@@ -114,7 +115,7 @@ def time_prepare(self, _, n):
 class PrepareScalabilityGridToMesh(PrepareScalabilityMixin):
     """Benchmarks for the prepare step of :class:`~esmf_regrid.esmf_regrid.schemes.GridToMeshESMFRegridder`."""
 
-    regridder = GridToMeshESMFRegridder
+    regridder = GridToMeshESMFRegridder  # type: ignore[assignment]
 
     def tgt_cube(self, n):
         """Cube containing the regridding target grid."""
@@ -257,7 +258,7 @@ def time_lazy_perform(self, cache, height):
 class PerformScalabilityMeshToGrid(PerformScalabilityMixin):
     """Benchmarks for the perform step of :class:`~esmf_regrid.esmf_regrid.schemes.MeshToGridESMFRegridder`."""
 
-    regridder = MeshToGridESMFRegridder
+    regridder = MeshToGridESMFRegridder  # type: ignore[assignment]
     chunk_size = [PerformScalabilityMixin.grid_size ^ 2, 10]
     file_name = "chunked_cube_1d.nc"
 
@@ -298,7 +299,7 @@ def time_lazy_perform(self, cache, height):
 class PerformScalabilityGridToMesh(PerformScalabilityMixin):
     """Benchmarks for the perform step of :class:`~esmf_regrid.esmf_regrid.schemes.GridToMeshESMFRegridder`."""
 
-    regridder = GridToMeshESMFRegridder
+    regridder = GridToMeshESMFRegridder  # type: ignore[assignment]
 
     def setup_cache(self):
         """ASV setup_cache method."""

benchmarks/benchmarks/generate_data.py

@@ -1,5 +1,4 @@
-"""
-Scripts for generating supporting data for benchmarking.
+"""Scripts for generating supporting data for benchmarking.
 
 Data generated using iris-esmf-regrid should use
 :func:`run_function_elsewhere`, which means that data is generated using a
@@ -43,7 +42,7 @@
 default_data_dir = (Path(__file__).parent.parent / ".data").resolve()
 # Optionally override the default data location with environment variable.
 BENCHMARK_DATA = Path(environ.get("BENCHMARK_DATA", default_data_dir))
-if BENCHMARK_DATA == default_data_dir:
+if default_data_dir == BENCHMARK_DATA:
     BENCHMARK_DATA.mkdir(exist_ok=True)
     message = (
         f"No BENCHMARK_DATA env var, defaulting to {BENCHMARK_DATA}. "
@@ -62,8 +61,7 @@
 
 
 def run_function_elsewhere(func_to_run, *args, **kwargs):
-    """
-    Run a given function using the :const:`DATA_GEN_PYTHON` executable.
+    """Run a given function using the :const:`DATA_GEN_PYTHON` executable.
 
     This structure allows the function to be written natively.
 
@@ -90,7 +88,7 @@ def run_function_elsewhere(func_to_run, *args, **kwargs):
     func_string = dedent(getsource(func_to_run))
     func_string = func_string.replace("@staticmethod\n", "")
     func_call_term_strings = [repr(arg) for arg in args]
-    func_call_term_strings += [f"{name}={repr(val)}" for name, val in kwargs.items()]
+    func_call_term_strings += [f"{name}={val!r}" for name, val in kwargs.items()]
     func_call_string = (
         f"{func_to_run.__name__}(" + ",".join(func_call_term_strings) + ")"
     )
@@ -115,8 +113,7 @@ def _grid_cube(
     """Call _grid_cube via :func:`run_function_elsewhere`."""
 
     def external(*args, **kwargs):
-        """
-        Prep and call _grid_cube, saving to a NetCDF file.
+        """Prep and call _grid_cube, saving to a NetCDF file.
 
         Saving to a file allows the original python executable to pick back up.
 
@@ -178,8 +175,7 @@ def _curvilinear_cube(
     """Call _curvilinear_cube via :func:`run_function_elsewhere`."""
 
     def external(*args, **kwargs):
-        """
-        Prep and call _curvilinear_cube, saving to a NetCDF file.
+        """Prep and call _curvilinear_cube, saving to a NetCDF file.
 
         Saving to a file allows the original python executable to pick back up.
 
@@ -227,8 +223,7 @@ def _gridlike_mesh_cube(n_lons, n_lats):
     """Call _gridlike_mesh via :func:`run_function_elsewhere`."""
 
     def external(*args, **kwargs):
-        """
-        Prep and call _gridlike_mesh, saving to a NetCDF file.
+        """Prep and call _gridlike_mesh, saving to a NetCDF file.
 
         Saving to a file allows the original python executable to pick back up.
 

benchmarks/bm_runner.py

@@ -11,7 +11,6 @@
 import shlex
 import subprocess
 from tempfile import NamedTemporaryFile
-from typing import Literal
 
 # The threshold beyond which shifts are 'notable'. See `asv compare`` docs
 #  for more.
@@ -29,7 +28,7 @@
 def _echo(echo_string: str):
     # Use subprocess for printing to reduce chance of printing out of sequence
     #  with the subsequent calls.
-    subprocess.run(["echo", f"BM_RUNNER DEBUG: {echo_string}"])
+    subprocess.run(["echo", f"BM_RUNNER DEBUG: {echo_string}"], check=False)
 
 
 def _subprocess_runner(args, asv=False, **kwargs):
@@ -103,10 +102,10 @@ def _setup_common() -> None:
 
 def _asv_compare(*commits: str) -> None:
     """Run through a list of commits comparing each one to the next."""
-    commits = [commit[:8] for commit in commits]
-    for i in range(len(commits) - 1):
-        before = commits[i]
-        after = commits[i + 1]
+    _commits = [commit[:8] for commit in commits]
+    for i in range(len(_commits) - 1):
+        before = _commits[i]
+        after = _commits[i + 1]
         asv_command = shlex.split(
             f"compare {before} {after} --factor={COMPARE_FACTOR} --split"
         )
@@ -124,7 +123,7 @@ class _SubParserGenerator(ABC):
     description: str = NotImplemented
     epilog: str = NotImplemented
 
-    def __init__(self, subparsers: ArgumentParser.add_subparsers) -> None:
+    def __init__(self, subparsers: argparse._SubParsersAction) -> None:
         self.subparser: ArgumentParser = subparsers.add_parser(
             self.name,
             description=self.description,
@@ -249,18 +248,20 @@ def func(args: argparse.Namespace) -> None:
         )
 
         # Only do a single round.
-        asv_command = shlex.split(re.sub(r"rounds=\d", "rounds=1", asv_command))
+        _asv_command = shlex.split(re.sub(r"rounds=\d", "rounds=1", asv_command))
         try:
-            _subprocess_runner([*asv_command, *args.asv_args], asv=True)
+            _subprocess_runner([*_asv_command, *args.asv_args], asv=True)
         except subprocess.CalledProcessError as err:
             # C/SPerf benchmarks are much bigger than the CI ones:
             # Don't fail the whole run if memory blows on 1 benchmark.
             # ASV produces return code of 2 if the run includes crashes.
             if err.returncode != 2:
                 raise
 
-        asv_command = shlex.split(f"publish {commit_range} --html-dir={publish_subdir}")
-        _subprocess_runner(asv_command, asv=True)
+        _asv_command = shlex.split(
+            f"publish {commit_range} --html-dir={publish_subdir}"
+        )
+        _subprocess_runner(_asv_command, asv=True)
 
         # Print completion message.
         location = BENCHMARKS_DIR / ".asv"