Replace black and blackdoc with ruff-format (#9506)

* Replace black with ruff-format

* Fix formatting mistakes moving mypy comments

* Replace black with ruff in the contributing guides

.pre-commit-config.yaml

@@ -15,20 +15,15 @@ repos:
     # Ruff version.
     rev: 'v0.6.9'
     hooks:
+      - id: ruff-format
       - id: ruff
         args: ["--fix", "--show-fixes"]
-  # https://github.com/python/black#version-control-integration
-  - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 24.8.0
-    hooks:
-      - id: black-jupyter
   - repo: https://github.com/keewis/blackdoc
     rev: v0.3.9
     hooks:
       - id: blackdoc
         exclude: "generate_aggregations.py"
         additional_dependencies: ["black==24.8.0"]
-      - id: blackdoc-autoupdate-black
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.11.2
     hooks:

CORE_TEAM_GUIDE.md

@@ -271,8 +271,7 @@ resources such as:
    [NumPy documentation guide](https://numpy.org/devdocs/dev/howto-docs.html#documentation-style)
    for docstring conventions.
 - [`pre-commit`](https://pre-commit.com) hooks for autoformatting.
-- [`black`](https://github.com/psf/black) autoformatting.
-- [`flake8`](https://github.com/PyCQA/flake8) linting.
+- [`ruff`](https://github.com/astral-sh/ruff) autoformatting and linting.
 - [python-xarray](https://stackoverflow.com/questions/tagged/python-xarray) on Stack Overflow.
 - [@xarray_dev](https://twitter.com/xarray_dev) on Twitter.
 - [xarray-dev](https://discord.gg/bsSGdwBn) discord community (normally only used for remote synchronous chat during sprints).

ci/min_deps_check.py

@@ -3,6 +3,7 @@
 publication date. Compare it against requirements/min-all-deps.yml to verify the
 policy on obsolete dependencies is being followed. Print a pretty report :)
 """
+
 from __future__ import annotations
 
 import itertools
@@ -16,7 +17,6 @@
 
 CHANNELS = ["conda-forge", "defaults"]
 IGNORE_DEPS = {
-    "black",
     "coveralls",
     "flake8",
     "hypothesis",

ci/requirements/all-but-dask.yml

@@ -3,7 +3,6 @@ channels:
   - conda-forge
   - nodefaults
 dependencies:
-  - black
   - aiobotocore
   - array-api-strict
   - boto3

doc/contributing.rst

@@ -549,11 +549,7 @@ Code Formatting
 
 xarray uses several tools to ensure a consistent code format throughout the project:
 
-- `Black <https://black.readthedocs.io/en/stable/>`_ for standardized
-  code formatting,
-- `blackdoc <https://blackdoc.readthedocs.io/en/stable/>`_ for
-  standardized code formatting in documentation,
-- `ruff <https://github.com/charliermarsh/ruff/>`_ for code quality checks and standardized order in imports
+- `ruff <https://github.com/astral-sh/ruff>`_ for formatting, code quality checks and standardized order in imports
 - `absolufy-imports <https://github.com/MarcoGorelli/absolufy-imports>`_ for absolute instead of relative imports from different files,
 - `mypy <http://mypy-lang.org/>`_ for static type checking on `type hints
   <https://docs.python.org/3/library/typing.html>`_.
@@ -1069,7 +1065,7 @@ PR checklist
   - Test the code using `Pytest <http://doc.pytest.org/en/latest/>`_. Running all tests (type ``pytest`` in the root directory) takes a while, so feel free to only run the tests you think are needed based on your PR (example: ``pytest xarray/tests/test_dataarray.py``). CI will catch any failing tests.
   - By default, the upstream dev CI is disabled on pull request and push events. You can override this behavior per commit by adding a ``[test-upstream]`` tag to the first line of the commit message. For documentation-only commits, you can skip the CI per commit by adding a ``[skip-ci]`` tag to the first line of the commit message.
 
-- **Properly format your code** and verify that it passes the formatting guidelines set by `Black <https://black.readthedocs.io/en/stable/>`_ and `Flake8 <http://flake8.pycqa.org/en/latest/>`_. See `"Code formatting" <https://docs.xarray.dev/en/stablcontributing.html#code-formatting>`_. You can use `pre-commit <https://pre-commit.com/>`_ to run these automatically on each commit.
+- **Properly format your code** and verify that it passes the formatting guidelines set by `ruff <https://github.com/astral-sh/ruff>`_. See `"Code formatting" <https://docs.xarray.dev/en/stablcontributing.html#code-formatting>`_. You can use `pre-commit <https://pre-commit.com/>`_ to run these automatically on each commit.
 
   - Run ``pre-commit run --all-files`` in the root directory. This may modify some files. Confirm and commit any formatting changes.
 

pyproject.toml

@@ -233,7 +233,7 @@ extend-exclude = [
 
 [tool.ruff.lint]
 # E402: module level import not at top of file
-# E501: line too long - let black worry about that
+# E501: line too long - let the formatter worry about that
 # E731: do not assign a lambda expression, use a def
 extend-safe-fixes = [
   "TID252", # absolute imports

xarray/backends/common.py

@@ -206,13 +206,10 @@ def load(self):
         For example::
 
             class SuffixAppendingDataStore(AbstractDataStore):
-
                 def load(self):
                     variables, attributes = AbstractDataStore.load(self)
-                    variables = {'%s_suffix' % k: v
-                                 for k, v in variables.items()}
-                    attributes = {'%s_suffix' % k: v
-                                  for k, v in attributes.items()}
+                    variables = {"%s_suffix" % k: v for k, v in variables.items()}
+                    attributes = {"%s_suffix" % k: v for k, v in attributes.items()}
                     return variables, attributes
 
         This function will be called anytime variables or attributes

xarray/backends/file_manager.py

@@ -65,7 +65,7 @@ class CachingFileManager(FileManager):
 
     Example usage::
 
-        manager = FileManager(open, 'example.txt', mode='w')
+        manager = FileManager(open, "example.txt", mode="w")
         f = manager.acquire()
         f.write(...)
         manager.close()  # ensures file is closed

xarray/backends/h5netcdf_.py

@@ -474,7 +474,6 @@ def open_datatree(
         driver_kwds=None,
         **kwargs,
     ) -> DataTree:
-
         from xarray.core.datatree import DataTree
 
         groups_dict = self.open_groups_as_dict(
@@ -520,7 +519,6 @@ def open_groups_as_dict(
         driver_kwds=None,
         **kwargs,
     ) -> dict[str, Dataset]:
-
         from xarray.backends.common import _iter_nc_groups
         from xarray.core.treenode import NodePath
         from xarray.core.utils import close_on_error

xarray/backends/netCDF4_.py

@@ -710,7 +710,6 @@ def open_datatree(
         autoclose=False,
         **kwargs,
     ) -> DataTree:
-
         from xarray.core.datatree import DataTree
 
         groups_dict = self.open_groups_as_dict(

xarray/backends/plugins.py

@@ -80,7 +80,7 @@ def backends_dict_from_pkg(
 
 
 def set_missing_parameters(
-    backend_entrypoints: dict[str, type[BackendEntrypoint]]
+    backend_entrypoints: dict[str, type[BackendEntrypoint]],
 ) -> None:
     for _, backend in backend_entrypoints.items():
         if backend.open_dataset_parameters is None:
@@ -89,7 +89,7 @@ def set_missing_parameters(
 
 
 def sort_backends(
-    backend_entrypoints: dict[str, type[BackendEntrypoint]]
+    backend_entrypoints: dict[str, type[BackendEntrypoint]],
 ) -> dict[str, type[BackendEntrypoint]]:
     ordered_backends_entrypoints = {}
     for be_name in STANDARD_BACKENDS_ORDER:

xarray/backends/zarr.py

@@ -496,7 +496,6 @@ def open_store(
         zarr_version=None,
         write_empty: bool | None = None,
     ):
-
         zarr_group, consolidate_on_close, close_store_on_close = _get_open_params(
             store=store,
             mode=mode,
@@ -542,7 +541,6 @@ def open_group(
         zarr_version=None,
         write_empty: bool | None = None,
     ):
-
         zarr_group, consolidate_on_close, close_store_on_close = _get_open_params(
             store=store,
             mode=mode,
@@ -1338,7 +1336,6 @@ def open_groups_as_dict(
         zarr_version=None,
         **kwargs,
     ) -> dict[str, Dataset]:
-
         from xarray.core.treenode import NodePath
 
         filename_or_obj = _normalize_path(filename_or_obj)
@@ -1385,7 +1382,6 @@ def open_groups_as_dict(
 
 
 def _iter_zarr_groups(root: ZarrGroup, parent: str = "/") -> Iterable[str]:
-
     parent_nodepath = NodePath(parent)
     yield str(parent_nodepath)
     for path, group in root.groups():

xarray/convert.py

@@ -1,5 +1,4 @@
-"""Functions for converting to and from xarray objects
-"""
+"""Functions for converting to and from xarray objects"""
 
 from collections import Counter
 

xarray/core/dataarray.py

@@ -1582,7 +1582,7 @@ def sel(
           Do not try to assign values when using any of the indexing methods
           ``isel`` or ``sel``::
 
-            da = xr.DataArray([0, 1, 2, 3], dims=['x'])
+            da = xr.DataArray([0, 1, 2, 3], dims=["x"])
             # DO NOT do this
             da.isel(x=[0, 1, 2])[1] = -1
 

xarray/core/datatree.py

@@ -801,7 +801,6 @@ def _replace_node(
         data: Dataset | Default = _default,
         children: dict[str, DataTree] | Default = _default,
     ) -> None:
-
         ds = self.to_dataset(inherit=False) if data is _default else data
 
         if children is _default:

xarray/core/formatting.py

@@ -1,5 +1,4 @@
-"""String formatting routines for __repr__.
-"""
+"""String formatting routines for __repr__."""
 
 from __future__ import annotations
 

xarray/core/groupby.py

@@ -235,7 +235,9 @@ def to_array(self) -> DataArray:
 T_Group = Union["T_DataArray", _DummyGroup]
 
 
-def _ensure_1d(group: T_Group, obj: T_DataWithCoords) -> tuple[
+def _ensure_1d(
+    group: T_Group, obj: T_DataWithCoords
+) -> tuple[
     T_Group,
     T_DataWithCoords,
     Hashable | None,
@@ -462,7 +464,10 @@ def factorize(self) -> EncodedGroups:
         )
         # NaNs; as well as values outside the bins are coded by -1
         # Restore these after the raveling
-        mask = functools.reduce(np.logical_or, [(code == -1) for code in broadcasted_codes])  # type: ignore[arg-type]
+        mask = functools.reduce(
+            np.logical_or,  # type: ignore[arg-type]
+            [(code == -1) for code in broadcasted_codes],
+        )
         _flatcodes[mask] = -1
 
         midx = pd.MultiIndex.from_product(
@@ -1288,7 +1293,6 @@ def _concat_shortcut(self, applied, dim, positions=None):
         return self._obj._replace_maybe_drop_dims(reordered)
 
     def _restore_dim_order(self, stacked: DataArray) -> DataArray:
-
         def lookup_order(dimension):
             for grouper in self.groupers:
                 if dimension == grouper.name and grouper.group.ndim == 1:

xarray/core/indexes.py

@@ -1768,7 +1768,7 @@ def indexes_equal(
 
 
 def indexes_all_equal(
-    elements: Sequence[tuple[Index, dict[Hashable, Variable]]]
+    elements: Sequence[tuple[Index, dict[Hashable, Variable]]],
 ) -> bool:
     """Check if indexes are all equal.
 

xarray/core/parallel.py

@@ -372,7 +372,8 @@ def _wrapper(
 
             # ChainMap wants MutableMapping, but xindexes is Mapping
             merged_indexes = collections.ChainMap(
-                expected["indexes"], merged_coordinates.xindexes  # type: ignore[arg-type]
+                expected["indexes"],
+                merged_coordinates.xindexes,  # type: ignore[arg-type]
             )
             expected_index = merged_indexes.get(name, None)
             if expected_index is not None and not index.equals(expected_index):

xarray/core/resample.py

@@ -188,7 +188,9 @@ def _interpolate(self, kind="linear", **kwargs) -> T_Xarray:
 
 
 # https://github.com/python/mypy/issues/9031
-class DataArrayResample(Resample["DataArray"], DataArrayGroupByBase, DataArrayResampleAggregations):  # type: ignore[misc]
+class DataArrayResample(  # type: ignore[misc]
+    Resample["DataArray"], DataArrayGroupByBase, DataArrayResampleAggregations
+):
     """DataArrayGroupBy object specialized to time resampling operations over a
     specified dimension
     """
@@ -329,7 +331,9 @@ def asfreq(self) -> DataArray:
 
 
 # https://github.com/python/mypy/issues/9031
-class DatasetResample(Resample["Dataset"], DatasetGroupByBase, DatasetResampleAggregations):  # type: ignore[misc]
+class DatasetResample(  # type: ignore[misc]
+    Resample["Dataset"], DatasetGroupByBase, DatasetResampleAggregations
+):
     """DatasetGroupBy object specialized to resampling a specified dimension"""
 
     def map(

xarray/core/variable.py

@@ -839,7 +839,6 @@ def _getitem_with_mask(self, key, fill_value=dtypes.NA):
         dims, indexer, new_order = self._broadcast_indexes(key)
 
         if self.size:
-
             if is_duck_dask_array(self._data):
                 # dask's indexing is faster this way; also vindex does not
                 # support negative indices yet:

xarray/namedarray/_array_api.py

@@ -79,7 +79,8 @@ def astype(
 
 
 def imag(
-    x: NamedArray[_ShapeType, np.dtype[_SupportsImag[_ScalarType]]], /  # type: ignore[type-var]
+    x: NamedArray[_ShapeType, np.dtype[_SupportsImag[_ScalarType]]],  # type: ignore[type-var]
+    /,
 ) -> NamedArray[_ShapeType, np.dtype[_ScalarType]]:
     """
     Returns the imaginary component of a complex number for each element x_i of the
@@ -111,7 +112,8 @@ def imag(
 
 
 def real(
-    x: NamedArray[_ShapeType, np.dtype[_SupportsReal[_ScalarType]]], /  # type: ignore[type-var]
+    x: NamedArray[_ShapeType, np.dtype[_SupportsReal[_ScalarType]]],  # type: ignore[type-var]
+    /,
 ) -> NamedArray[_ShapeType, np.dtype[_ScalarType]]:
     """
     Returns the real component of a complex number for each element x_i of the

xarray/plot/utils.py

@@ -986,7 +986,7 @@ def legend_elements(
     This is useful for obtaining a legend for a `~.Axes.scatter` plot;
     e.g.::
 
-        scatter = plt.scatter([1, 2, 3],  [4, 5, 6],  c=[7, 2, 3])
+        scatter = plt.scatter([1, 2, 3], [4, 5, 6], c=[7, 2, 3])
         plt.legend(*scatter.legend_elements())
 
     creates three legend elements, one for each color with the numerical

xarray/tests/test_cftime_offsets.py

@@ -1673,7 +1673,6 @@ def test_new_to_legacy_freq_anchored(year_alias, n):
     ),
 )
 def test_legacy_to_new_freq_pd_freq_passthrough(freq, expected):
-
     result = _legacy_to_new_freq(freq)
     assert result == expected
 
@@ -1699,7 +1698,6 @@ def test_legacy_to_new_freq_pd_freq_passthrough(freq, expected):
     ),
 )
 def test_new_to_legacy_freq_pd_freq_passthrough(freq, expected):
-
     result = _new_to_legacy_freq(freq)
     assert result == expected
 
@@ -1786,7 +1784,6 @@ def test_date_range_no_freq(start, end, periods):
 )
 @pytest.mark.parametrize("has_year_zero", [False, True])
 def test_offset_addition_preserves_has_year_zero(offset, has_year_zero):
-
     with warnings.catch_warnings():
         warnings.filterwarnings("ignore", message="this date/calendar/year zero")
         datetime = cftime.DatetimeGregorian(-1, 12, 31, has_year_zero=has_year_zero)

xarray/tests/test_coordinates.py

@@ -64,7 +64,10 @@ def test_init_index_error(self) -> None:
             Coordinates(indexes={"x": idx})
 
         with pytest.raises(TypeError, match=".* is not an `xarray.indexes.Index`"):
-            Coordinates(coords={"x": ("x", [1, 2, 3])}, indexes={"x": "not_an_xarray_index"})  # type: ignore[dict-item]
+            Coordinates(
+                coords={"x": ("x", [1, 2, 3])},
+                indexes={"x": "not_an_xarray_index"},  # type: ignore[dict-item]
+            )
 
     def test_init_dim_sizes_conflict(self) -> None:
         with pytest.raises(ValueError):

xarray/tests/test_dataset.py

@@ -297,9 +297,7 @@ def test_repr(self) -> None:
                 var2     (dim1, dim2) float64 576B 1.162 -1.097 -2.123 ... 1.267 0.3328
                 var3     (dim3, dim1) float64 640B 0.5565 -0.2121 0.4563 ... -0.2452 -0.3616
             Attributes:
-                foo:      bar""".format(
-                data["dim3"].dtype
-            )
+                foo:      bar""".format(data["dim3"].dtype)
         )
         actual = "\n".join(x.rstrip() for x in repr(data).split("\n"))
         print(actual)