Add more ruff rules (#2460)

* Enforce ruff/flake8-executable rules (EXE)

* Enforce ruff/flake8-future-annotations rules (FA)

* Enforce ruff/flake8-logging rules (LOG)

* Apply ruff/flake8-pie rule PIE790

PIE790 Unnecessary `pass` statement
PIE790 Unnecessary `...` literal

* Apply ruff/flake8-pie rule PIE800

PIE800 Unnecessary spread `**`

* Apply ruff/flake8-pie rule PIE808

PIE808 Unnecessary `start` argument in `range`

* Enforce ruff/flake8-pie rules (PIE)

* Apply ruff preview rule RUF022

RUF022 `__all__` is not sorted

* Sort pyproject.toml

* Apply ruff/flake8-simplify rule SIM102

SIM102 Use a single `if` statement instead of nested `if` statements

* Apply ruff/flake8-simplify rule SIM114

SIM114 Combine `if` branches using logical `or` operator

* Apply ruff/flake8-simplify rule SIM118

SIM118 Use `key in dict` instead of `key in dict.keys()`

* Enforce ruff/flake8-simplify rules (SIM)

* Enforce ruff/flake8-slots rules (SLOT)

Author: DimitriPapadopoulos

pyproject.toml

@@ -269,19 +269,25 @@ extend-exclude = [
 extend-select = [
     "ANN",  # flake8-annotations
     "B",    # flake8-bugbear
+    "EXE",  # flake8-executable
     "C4",   # flake8-comprehensions
+    "FA",   # flake8-future-annotations
     "FLY",  # flynt
     "FURB", # refurb
     "G",    # flake8-logging-format
     "I",    # isort
     "ISC",  # flake8-implicit-str-concat
+    "LOG",  # flake8-logging
     "PERF", # Perflint
+    "PIE",  # flake8-pie
     "PGH",  # pygrep-hooks
     "PT",   # flake8-pytest-style
     "PYI",  # flake8-pyi
-    "RSE",  # flake8-raise
     "RET",  # flake8-return
+    "RSE",  # flake8-raise
     "RUF",
+    "SIM",  # flake8-simplify
+    "SLOT", # flake8-slots
     "TCH",  # flake8-type-checking
     "TRY",  # tryceratops
     "UP",   # pyupgrade
@@ -298,6 +304,7 @@ ignore = [
     "RET505",
     "RET506",
     "RUF005",
+    "SIM108",
     "TRY003",
     "UP027",  # deprecated
     "UP038",  # https://github.com/astral-sh/ruff/issues/7871
@@ -319,7 +326,7 @@ ignore = [
 ]
 
 [tool.ruff.lint.extend-per-file-ignores]
-"tests/**" = ["ANN001", "ANN201"]
+"tests/**" = ["ANN001", "ANN201", "RUF029", "SIM117", "SIM300"]
 
 [tool.mypy]
 python_version = "3.11"

src/zarr/abc/codec.py

@@ -106,7 +106,6 @@ def validate(self, *, shape: ChunkCoords, dtype: np.dtype[Any], chunk_grid: Chun
         chunk_grid : ChunkGrid
             The array chunk grid
         """
-        ...
 
     async def _decode_single(self, chunk_data: CodecOutput, chunk_spec: ArraySpec) -> CodecInput:
         raise NotImplementedError

src/zarr/abc/metadata.py

@@ -42,6 +42,5 @@ def from_dict(cls, data: dict[str, JSON]) -> Self:
         """
         Create an instance of the model from a dictionary
         """
-        ...
 
         return cls(**data)

src/zarr/api/asynchronous.py

@@ -878,9 +878,8 @@ async def create(
         warnings.warn("meta_array is not yet implemented", RuntimeWarning, stacklevel=2)
 
     mode = kwargs.pop("mode", None)
-    if mode is None:
-        if not isinstance(store, Store | StorePath):
-            mode = "a"
+    if mode is None and not isinstance(store, Store | StorePath):
+        mode = "a"
 
     store_path = await make_store_path(store, path=path, mode=mode, storage_options=storage_options)
 

src/zarr/codecs/gzip.py

@@ -21,7 +21,7 @@
 def parse_gzip_level(data: JSON) -> int:
     if not isinstance(data, (int)):
         raise TypeError(f"Expected int, got {type(data)}")
-    if data not in range(0, 10):
+    if data not in range(10):
         raise ValueError(
             f"Expected an integer from the inclusive range (0, 9). Got {data} instead."
         )

src/zarr/core/chunk_grids.py

@@ -182,7 +182,7 @@ def to_dict(self) -> dict[str, JSON]:
 
     def all_chunk_coords(self, array_shape: ChunkCoords) -> Iterator[ChunkCoords]:
         return itertools.product(
-            *(range(0, ceildiv(s, c)) for s, c in zip(array_shape, self.chunk_shape, strict=False))
+            *(range(ceildiv(s, c)) for s, c in zip(array_shape, self.chunk_shape, strict=False))
         )
 
     def get_nchunks(self, array_shape: ChunkCoords) -> int:

src/zarr/core/group.py

@@ -1225,7 +1225,7 @@ def _members_consolidated(
 
         # we kind of just want the top-level keys.
         if consolidated_metadata is not None:
-            for key in consolidated_metadata.metadata.keys():
+            for key in consolidated_metadata.metadata:
                 obj = self._getitem_consolidated(
                     self.store_path, key, prefix=self.name
                 )  # Metadata -> Group/Array

src/zarr/core/indexing.py

@@ -241,12 +241,13 @@ def is_pure_fancy_indexing(selection: Any, ndim: int) -> bool:
         # is mask selection
         return True
 
-    if ndim == 1:
-        if is_integer_list(selection) or is_integer_array(selection) or is_bool_list(selection):
-            return True
+    if ndim == 1 and (
+        is_integer_list(selection) or is_integer_array(selection) or is_bool_list(selection)
+    ):
+        return True
 
-        # if not, we go through the normal path below, because a 1-tuple
-        # of integers is also allowed.
+    # if not, we go through the normal path below, because a 1-tuple
+    # of integers is also allowed.
     no_slicing = (
         isinstance(selection, tuple)
         and len(selection) == ndim

src/zarr/core/metadata/__init__.py

@@ -8,10 +8,10 @@
 T_ArrayMetadata = TypeVar("T_ArrayMetadata", ArrayV2Metadata, ArrayV3Metadata)
 
 __all__ = [
-    "ArrayV2Metadata",
-    "ArrayV3Metadata",
     "ArrayMetadata",
     "ArrayMetadataDict",
-    "ArrayV3MetadataDict",
+    "ArrayV2Metadata",
     "ArrayV2MetadataDict",
+    "ArrayV3Metadata",
+    "ArrayV3MetadataDict",
 ]

src/zarr/core/metadata/v3.py

@@ -481,9 +481,9 @@ def parse_fill_value(
     except (ValueError, OverflowError, TypeError) as e:
         raise ValueError(f"fill value {fill_value!r} is not valid for dtype {data_type}") from e
     # Check if the value is still representable by the dtype
-    if fill_value == "NaN" and np.isnan(casted_value):
-        pass
-    elif fill_value in ["Infinity", "-Infinity"] and not np.isfinite(casted_value):
+    if (fill_value == "NaN" and np.isnan(casted_value)) or (
+        fill_value in ["Infinity", "-Infinity"] and not np.isfinite(casted_value)
+    ):
         pass
     elif np_dtype.kind == "f":
         # float comparison is not exact, especially when dtype <float64

src/zarr/core/strings.py

@@ -61,10 +61,9 @@ def cast_to_string_dtype(
         return cast_array(data)
         # out = data.astype(STRING_DTYPE, copy=False)
         # return cast(np.ndarray[Any, np.dtypes.StringDType | np.dtypes.ObjectDType], out)
-    if _NUMPY_SUPPORTS_VLEN_STRING:
-        if np.issubdtype(data.dtype, _STRING_DTYPE):
-            # already a valid string variable length string dtype
-            return cast_array(data)
+    if _NUMPY_SUPPORTS_VLEN_STRING and np.issubdtype(data.dtype, _STRING_DTYPE):
+        # already a valid string variable length string dtype
+        return cast_array(data)
     if np.issubdtype(data.dtype, np.object_):
         # object arrays require more careful handling
         if _NUMPY_SUPPORTS_VLEN_STRING:

tests/test_api.py

@@ -154,7 +154,7 @@ def test_save(store: Store, n_args: int, n_kwargs: int) -> None:
         assert isinstance(group, Group)
         for array in group.array_values():
             assert_array_equal(array[:], data)
-        for k in kwargs.keys():
+        for k in kwargs:
             assert k in group
         assert group.nmembers() == n_args + n_kwargs
 

tests/test_codecs/test_codecs.py

@@ -56,7 +56,6 @@ def test_sharding_pickle() -> None:
     """
     Test that sharding codecs can be pickled
     """
-    pass
 
 
 @pytest.mark.parametrize("store", ["local", "memory"], indirect=["store"])