Update pre-commit hooks (#11211)

* Update pre-commit hooks

updates:
- [github.com/astral-sh/ruff-pre-commit: v0.14.14 → v0.15.4](astral-sh/ruff-pre-commit@v0.14.14...v0.15.4)
- [github.com/abravalheri/validate-pyproject: v0.24.1 → v0.25](abravalheri/validate-pyproject@v0.24.1...v0.25)
- [github.com/adhtruong/mirrors-typos: v1.42.3 → v1.44.0](adhtruong/mirrors-typos@v1.42.3...v1.44.0)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* apply ruff changes

* fix mypy stuff

* fix stubtest, don't ask me why or how

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Michael Niklas <mick.niklas@gmail.com>
Co-authored-by: Julia Signell <jsignell@gmail.com>

Author: 3 people

.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: rst-inline-touching-normal
       - id: text-unicode-replacement-char
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.14.14
+    rev: v0.15.4
     hooks:
       - id: ruff-check
         args: ["--fix", "--show-fixes"]
@@ -71,11 +71,11 @@ repos:
       - id: taplo-lint
         args: ["--no-schema"]
   - repo: https://github.com/abravalheri/validate-pyproject
-    rev: v0.24.1
+    rev: v0.25
     hooks:
       - id: validate-pyproject
         additional_dependencies: ["validate-pyproject-schema-store[all]"]
   - repo: https://github.com/adhtruong/mirrors-typos
-    rev: v1.42.3
+    rev: v1.44.0
     hooks:
       - id: typos

xarray/backends/zarr.py

@@ -123,19 +123,19 @@ class FillValueCoder:
 
     @classmethod
     def encode(cls, value: int | float | str | bytes, dtype: np.dtype[Any]) -> Any:
-        if dtype.kind in "S":
+        if dtype.kind == "S":
             # byte string, this implies that 'value' must also be `bytes` dtype.
             assert isinstance(value, bytes)
             return base64.standard_b64encode(value).decode()
-        elif dtype.kind in "b":
+        elif dtype.kind == "b":
             # boolean
             return bool(value)
         elif dtype.kind in "iu":
             # todo: do we want to check for decimals?
             return int(value)
-        elif dtype.kind in "f":
+        elif dtype.kind == "f":
             return base64.standard_b64encode(struct.pack("<d", float(value))).decode()
-        elif dtype.kind in "U":
+        elif dtype.kind == "U":
             return str(value)
         else:
             raise ValueError(f"Failed to encode fill_value. Unsupported dtype {dtype}")
@@ -150,10 +150,10 @@ def decode(cls, value: int | float | str | bytes, dtype: str | np.dtype[Any]):
             assert isinstance(value, str | bytes)
             return base64.standard_b64decode(value)
         np_dtype = np.dtype(dtype)
-        if np_dtype.kind in "f":
+        if np_dtype.kind == "f":
             assert isinstance(value, str | bytes)
             return struct.unpack("<d", base64.standard_b64decode(value))[0]
-        elif np_dtype.kind in "b":
+        elif np_dtype.kind == "b":
             return bool(value)
         elif np_dtype.kind in "iu":
             return int(value)
@@ -1650,7 +1650,7 @@ def guess_can_open(self, filename_or_obj: T_PathFileOrDataStore) -> bool:
             # allow a trailing slash to account for an autocomplete
             # adding it.
             _, ext = os.path.splitext(str(filename_or_obj).rstrip("/"))
-            return ext in [".zarr"]
+            return ext == ".zarr"
 
         return False
 

xarray/coding/times.py

@@ -397,7 +397,7 @@ def _check_date_for_units_since_refdate(
     delta = date * np.timedelta64(1, unit)
     if not np.isnan(delta):
         # this will raise on dtype overflow for integer dtypes
-        if date.dtype.kind in "u" and not np.int64(delta) == date:
+        if date.dtype.kind == "u" and not np.int64(delta) == date:
             raise OutOfBoundsTimedelta(
                 "DType overflow in Datetime/Timedelta calculation."
             )
@@ -421,7 +421,7 @@ def _check_timedelta_range(value, data_unit, time_unit):
         delta = value * np.timedelta64(1, data_unit)
     if not np.isnan(delta):
         # this will raise on dtype overflow for integer dtypes
-        if value.dtype.kind in "u" and not np.int64(delta) == value:
+        if value.dtype.kind == "u" and not np.int64(delta) == value:
             raise OutOfBoundsTimedelta(
                 "DType overflow in Datetime/Timedelta calculation."
             )
@@ -521,7 +521,7 @@ def _decode_datetime_with_pandas(
     # timedelta64 value, and therefore would raise an error in the lines above.
     if flat_num_dates.dtype.kind in "iu":
         flat_num_dates = flat_num_dates.astype(np.int64)
-    elif flat_num_dates.dtype.kind in "f":
+    elif flat_num_dates.dtype.kind == "f":
         flat_num_dates = flat_num_dates.astype(np.float64)
 
     timedeltas = _numbers_to_timedelta(

xarray/core/dataset.py

@@ -7299,6 +7299,7 @@ def _set_sparse_data_from_dataframe(
     ) -> None:
         from sparse import COO
 
+        coords: np.ndarray[tuple[int, int], np.dtype[np.signedinteger]]
         if isinstance(idx, pd.MultiIndex):
             coords = np.stack([np.asarray(code) for code in idx.codes], axis=0)
             is_sorted = idx.is_monotonic_increasing

xarray/core/datatree.py

@@ -1695,8 +1695,9 @@ def prune(self, drop_size_zero_vars: bool = False) -> DataTree:
         """
         non_empty_cond: Callable[[DataTree], bool]
         if drop_size_zero_vars:
-            non_empty_cond = lambda node: len(node.data_vars) > 0 and any(
-                var.size > 0 for var in node.data_vars.values()
+            non_empty_cond = lambda node: (
+                len(node.data_vars) > 0
+                and any(var.size > 0 for var in node.data_vars.values())
             )
         else:
             non_empty_cond = lambda node: len(node.data_vars) > 0

xarray/core/formatting_html.py

@@ -500,7 +500,7 @@ def _build_datatree_displays(tree: DataTree) -> dict[str, _DataTreeDisplay]:
     for node in tree.subtree:  # breadth-first
         parent = node.parent
         if parent is not None:
-            parent_display = displays.get(parent.path, None)
+            parent_display = displays.get(parent.path)
             if parent_display is not None and parent_display.disabled:
                 break  # no need to build display
 

xarray/core/variable.py

@@ -12,7 +12,6 @@
 
 import numpy as np
 import pandas as pd
-from numpy.typing import ArrayLike
 from packaging.version import Version
 
 import xarray as xr  # only for Dataset and DataArray
@@ -244,7 +243,7 @@ def _possibly_convert_objects(values):
 
 
 def as_compatible_data(
-    data: T_DuckArray | ArrayLike, fastpath: bool = False
+    data: T_DuckArray | np.typing.ArrayLike, fastpath: bool = False
 ) -> T_DuckArray:
     """Prepare and wrap data to put in a Variable.
 
@@ -371,7 +370,7 @@ class Variable(NamedArray, AbstractArray, VariableArithmetic):
     def __init__(
         self,
         dims,
-        data: T_DuckArray | ArrayLike,
+        data: T_DuckArray | np.typing.ArrayLike,
         attrs=None,
         encoding=None,
         fastpath=False,
@@ -466,7 +465,7 @@ def data(self):
         return duck_array
 
     @data.setter  # type: ignore[override,unused-ignore]
-    def data(self, data: T_DuckArray | ArrayLike) -> None:
+    def data(self, data: T_DuckArray | np.typing.ArrayLike) -> None:
         data = as_compatible_data(data)
         self._check_shape(data)
         self._data = data
@@ -931,7 +930,7 @@ def drop_encoding(self) -> Self:
     def _copy(
         self,
         deep: bool = True,
-        data: T_DuckArray | ArrayLike | None = None,
+        data: T_DuckArray | np.typing.ArrayLike | None = None,
         memo: dict[int, Any] | None = None,
     ) -> Self:
         if data is None:
@@ -1914,7 +1913,7 @@ def no_conflicts(self, other, equiv=duck_array_ops.array_notnull_equiv):
 
     def quantile(
         self,
-        q: ArrayLike,
+        q: np.typing.ArrayLike,
         dim: str | Sequence[Hashable] | None = None,
         method: QuantileMethods = "linear",
         keep_attrs: bool | None = None,
@@ -2872,7 +2871,9 @@ def concat(
 
         return cls(first_var.dims, data, attrs)
 
-    def copy(self, deep: bool = True, data: T_DuckArray | ArrayLike | None = None):
+    def copy(
+        self, deep: bool = True, data: T_DuckArray | np.typing.ArrayLike | None = None
+    ):
         """Returns a copy of this object.
 
         `deep` is ignored since data is stored in the form of

xarray/namedarray/core.py

@@ -194,7 +194,7 @@ def from_array(
 
     # TODO: dask.array.ma.MaskedArray also exists, better way?
     if isinstance(data, np.ma.MaskedArray):
-        mask = np.ma.getmaskarray(data)  # type: ignore[no-untyped-call]
+        mask = np.ma.getmaskarray(data)
         if mask.any():
             # TODO: requires refactoring/vendoring xarray.core.dtypes and
             # xarray.core.duck_array_ops

xarray/tests/test_backends.py

@@ -2067,8 +2067,8 @@ def test_mask_and_scale(self) -> None:
 
             # now check xarray
             with open_dataset(tmp_file) as ds:
-                expected = create_masked_and_scaled_data(np.dtype(dtype))
-                assert_identical(expected, ds)
+                expected_ds = create_masked_and_scaled_data(np.dtype(dtype))
+                assert_identical(expected_ds, ds)
 
     def test_0dimensional_variable(self) -> None:
         # This fix verifies our work-around to this netCDF4-python bug:

xarray/tests/test_datatree_mapping.py

@@ -44,7 +44,7 @@ def test_single_tree_arg(self, create_test_datatree):
 
     def test_single_tree_arg_plus_arg(self, create_test_datatree):
         dt = create_test_datatree()
-        expected = create_test_datatree(modify=lambda ds: (10.0 * ds))
+        expected = create_test_datatree(modify=lambda ds: 10.0 * ds)
         result_tree = map_over_datasets(lambda x, y: x * y, dt, 10.0)
         assert_equal(result_tree, expected)
 
@@ -53,7 +53,7 @@ def test_single_tree_arg_plus_arg(self, create_test_datatree):
 
     def test_single_tree_arg_plus_kwarg(self, create_test_datatree):
         dt = create_test_datatree()
-        expected = create_test_datatree(modify=lambda ds: (10.0 * ds))
+        expected = create_test_datatree(modify=lambda ds: 10.0 * ds)
 
         def multiply_by_kwarg(ds, **kwargs):
             ds = ds * kwargs.pop("multiplier")