Repo checker (#9450)

* Remove default mypy option

* Implement mypy ignore-without-code option

* Enable mypy redundant-expr

* Fix erroneous tuple types

* Remove ruff target-version, redundant with project

* Use extend selections for ruff

* Fix B009 and B010 with ruff

* Fix test parametrization

* Fix FutureWarning

* Make zips strict unless it is causing errors

In which case set them to explicit False

* Add a commit message for pre-commit autoupdate

Author: Armavica

.pre-commit-config.yaml

@@ -1,6 +1,7 @@
 # https://pre-commit.com/
 ci:
     autoupdate_schedule: monthly
+    autoupdate_commit_msg: 'Update pre-commit hooks'
 exclude: 'xarray/datatree_.*'
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks

asv_bench/benchmarks/dataset_io.py

@@ -724,7 +724,7 @@ class PerformanceBackend(xr.backends.BackendEntrypoint):
             def open_dataset(
                 self,
                 filename_or_obj: str | os.PathLike | None,
-                drop_variables: tuple[str] = None,
+                drop_variables: tuple[str, ...] = None,
                 *,
                 mask_and_scale=True,
                 decode_times=True,

asv_bench/benchmarks/groupby.py

@@ -174,7 +174,7 @@ def setup(self, use_cftime, use_flox):
         # GH9426 - deep-copying CFTime object arrays is weirdly slow
         asda = xr.DataArray(time)
         labeled_time = []
-        for year, month in zip(asda.dt.year, asda.dt.month):
+        for year, month in zip(asda.dt.year, asda.dt.month, strict=True):
             labeled_time.append(cftime.datetime(year, month, 1))
 
         self.da = xr.DataArray(

asv_bench/benchmarks/rolling.py

@@ -64,7 +64,7 @@ def time_rolling_long(self, func, pandas, use_bottleneck):
     def time_rolling_np(self, window_, min_periods, use_bottleneck):
         with xr.set_options(use_bottleneck=use_bottleneck):
             self.ds.rolling(x=window_, center=False, min_periods=min_periods).reduce(
-                getattr(np, "nansum")
+                np.nansum
             ).load()
 
     @parameterized(

doc/user-guide/testing.rst

@@ -193,7 +193,7 @@ different type:
 
 .. ipython:: python
 
-    def sparse_random_arrays(shape: tuple[int]) -> sparse._coo.core.COO:
+    def sparse_random_arrays(shape: tuple[int, ...]) -> sparse._coo.core.COO:
         """Strategy which generates random sparse.COO arrays"""
         if shape is None:
             shape = npst.array_shapes()

properties/test_pandas_roundtrip.py

@@ -80,7 +80,7 @@ def test_roundtrip_dataarray(data, arr) -> None:
             tuple
         )
     )
-    coords = {name: np.arange(n) for (name, n) in zip(names, arr.shape)}
+    coords = {name: np.arange(n) for (name, n) in zip(names, arr.shape, strict=True)}
     original = xr.DataArray(arr, dims=names, coords=coords)
     roundtripped = xr.DataArray(original.to_pandas())
     xr.testing.assert_identical(original, roundtripped)

pyproject.toml

@@ -84,14 +84,13 @@ source = ["xarray"]
 exclude_lines = ["pragma: no cover", "if TYPE_CHECKING"]
 
 [tool.mypy]
-enable_error_code = "redundant-self"
+enable_error_code = ["ignore-without-code", "redundant-self", "redundant-expr"]
 exclude = [
   'build',
   'xarray/util/generate_.*\.py',
   'xarray/datatree_/doc/.*\.py',
 ]
 files = "xarray"
-show_error_codes = true
 show_error_context = true
 warn_redundant_casts = true
 warn_unused_configs = true
@@ -240,7 +239,6 @@ extend-exclude = [
   "doc",
   "_typed_ops.pyi",
 ]
-target-version = "py310"
 
 [tool.ruff.lint]
 # E402: module level import not at top of file
@@ -249,13 +247,13 @@ target-version = "py310"
 extend-safe-fixes = [
   "TID252", # absolute imports
 ]
-ignore = [
+extend-ignore = [
   "E402",
   "E501",
   "E731",
   "UP007",
 ]
-select = [
+extend-select = [
   "F", # Pyflakes
   "E", # Pycodestyle
   "W",

xarray/backends/api.py

@@ -51,7 +51,7 @@
     try:
         from dask.delayed import Delayed
     except ImportError:
-        Delayed = None  # type: ignore
+        Delayed = None  # type: ignore[assignment, misc]
     from io import BufferedIOBase
 
     from xarray.backends.common import BackendEntrypoint
@@ -1113,7 +1113,7 @@ def open_mfdataset(
             list(combined_ids_paths.keys()),
             list(combined_ids_paths.values()),
         )
-    elif combine == "by_coords" and concat_dim is not None:
+    elif concat_dim is not None:
         raise ValueError(
             "When combine='by_coords', passing a value for `concat_dim` has no "
             "effect. To manually combine along a specific dimension you should "
@@ -1432,7 +1432,7 @@ def to_netcdf(
             store.sync()
             return target.getvalue()
     finally:
-        if not multifile and compute:
+        if not multifile and compute:  # type: ignore[redundant-expr]
             store.close()
 
     if not compute:
@@ -1585,8 +1585,9 @@ def save_mfdataset(
                 multifile=True,
                 **kwargs,
             )
-            for ds, path, group in zip(datasets, paths, groups)
-        ]
+            for ds, path, group in zip(datasets, paths, groups, strict=True)
+        ],
+        strict=True,
     )
 
     try:
@@ -1600,7 +1601,10 @@ def save_mfdataset(
         import dask
 
         return dask.delayed(
-            [dask.delayed(_finalize_store)(w, s) for w, s in zip(writes, stores)]
+            [
+                dask.delayed(_finalize_store)(w, s)
+                for w, s in zip(writes, stores, strict=True)
+            ]
         )
 
 

xarray/backends/common.py

@@ -431,7 +431,7 @@ def set_dimensions(self, variables, unlimited_dims=None):
         for v in unlimited_dims:  # put unlimited_dims first
             dims[v] = None
         for v in variables.values():
-            dims.update(dict(zip(v.dims, v.shape)))
+            dims.update(dict(zip(v.dims, v.shape, strict=True)))
 
         for dim, length in dims.items():
             if dim in existing_dims and length != existing_dims[dim]:

xarray/backends/file_manager.py

@@ -276,7 +276,7 @@ def __getstate__(self):
     def __setstate__(self, state) -> None:
         """Restore from a pickle."""
         opener, args, mode, kwargs, lock, manager_id = state
-        self.__init__(  # type: ignore
+        self.__init__(  # type: ignore[misc]
             opener, *args, mode=mode, kwargs=kwargs, lock=lock, manager_id=manager_id
         )