Configure Ruff to apply flake8-bugbear/isort/pyupgrade (zarr-developers#1890)

* config change

* auto changes

* manual fixes

* ci

Author: normanrz

bench/compress_normal.py

@@ -1,9 +1,9 @@
 import sys
 import timeit
 
+import line_profiler
 import numpy as np
 
-import line_profiler
 import zarr
 from zarr import blosc
 

pyproject.toml

@@ -160,12 +160,17 @@ extend-exclude = [
     "build",
     "dist",
     "venv",
-    "docs"
+    "docs",
+    "src/zarr/v2/",
+    "tests/v2/",
 ]
 
 [tool.ruff.lint]
 extend-select = [
-    "RUF"
+    "B",  # flake8-bugbear
+    "I",  # isort
+    "UP",  # pyupgrade
+    "RUF",
 ]
 ignore = [
     "RUF003",

src/zarr/__init__.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import zarr.codecs  # noqa: F401
+from zarr._version import version as __version__
 from zarr.array import Array, AsyncArray
 from zarr.config import config  # noqa: F401
 from zarr.group import AsyncGroup, Group
@@ -9,7 +10,6 @@
     make_store_path,
 )
 from zarr.sync import sync as _sync
-from zarr._version import version as __version__
 
 # in case setuptools scm screw up and find version to be 0.0.0
 assert not __version__.startswith("0.0.0")

src/zarr/abc/codec.py

@@ -1,15 +1,16 @@
 from __future__ import annotations
 
 from abc import abstractmethod
-from typing import TYPE_CHECKING, Generic, Iterable, TypeVar
+from collections.abc import Iterable
+from typing import TYPE_CHECKING, Generic, TypeVar
 
 from zarr.abc.metadata import Metadata
 from zarr.abc.store import ByteGetter, ByteSetter
 from zarr.buffer import Buffer, NDBuffer
 
-
 if TYPE_CHECKING:
     from typing_extensions import Self
+
     from zarr.common import ArraySpec, SliceSelection
     from zarr.metadata import ArrayMetadata
 

src/zarr/abc/metadata.py

@@ -1,11 +1,12 @@
 from __future__ import annotations
-from typing import TYPE_CHECKING, Sequence
+
+from collections.abc import Sequence
+from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
-    from typing import Dict
     from typing_extensions import Self
 
-from dataclasses import fields, dataclass
+from dataclasses import dataclass, fields
 
 from zarr.common import JSON
 
@@ -36,7 +37,7 @@ def to_dict(self) -> JSON:
         return out_dict
 
     @classmethod
-    def from_dict(cls, data: Dict[str, JSON]) -> Self:
+    def from_dict(cls, data: dict[str, JSON]) -> Self:
         """
         Create an instance of the model from a dictionary
         """

src/zarr/abc/store.py

@@ -1,16 +1,16 @@
-from abc import abstractmethod, ABC
+from abc import ABC, abstractmethod
 from collections.abc import AsyncGenerator
-from typing import List, Protocol, Tuple, Optional, runtime_checkable
+from typing import Protocol, runtime_checkable
 
-from zarr.common import BytesLike
 from zarr.buffer import Buffer
+from zarr.common import BytesLike
 
 
 class Store(ABC):
     @abstractmethod
     async def get(
-        self, key: str, byte_range: Optional[Tuple[int, Optional[int]]] = None
-    ) -> Optional[Buffer]:
+        self, key: str, byte_range: tuple[int, int | None] | None = None
+    ) -> Buffer | None:
         """Retrieve the value associated with a given key.
 
         Parameters
@@ -26,8 +26,8 @@ async def get(
 
     @abstractmethod
     async def get_partial_values(
-        self, key_ranges: List[Tuple[str, Tuple[int, int]]]
-    ) -> List[Optional[Buffer]]:
+        self, key_ranges: list[tuple[str, tuple[int, int]]]
+    ) -> list[Buffer | None]:
         """Retrieve possibly partial values from given key_ranges.
 
         Parameters
@@ -150,18 +150,14 @@ def list_dir(self, prefix: str) -> AsyncGenerator[str, None]:
 
 @runtime_checkable
 class ByteGetter(Protocol):
-    async def get(
-        self, byte_range: Optional[Tuple[int, Optional[int]]] = None
-    ) -> Optional[Buffer]: ...
+    async def get(self, byte_range: tuple[int, int | None] | None = None) -> Buffer | None: ...
 
 
 @runtime_checkable
 class ByteSetter(Protocol):
-    async def get(
-        self, byte_range: Optional[Tuple[int, Optional[int]]] = None
-    ) -> Optional[Buffer]: ...
+    async def get(self, byte_range: tuple[int, int | None] | None = None) -> Buffer | None: ...
 
-    async def set(self, value: Buffer, byte_range: Optional[Tuple[int, int]] = None) -> None: ...
+    async def set(self, value: Buffer, byte_range: tuple[int, int] | None = None) -> None: ...
 
     async def delete(self) -> None: ...
 

src/zarr/array.py

@@ -1,29 +1,28 @@
 from __future__ import annotations
 
+import json
+
 # Notes on what I've changed here:
 # 1. Split Array into AsyncArray and Array
 # 3. Added .size and .attrs methods
 # 4. Temporarily disabled the creation of ArrayV2
 # 5. Added from_dict to AsyncArray
-
 # Questions to consider:
 # 1. Was splitting the array into two classes really necessary?
-
-
 from asyncio import gather
+from collections.abc import Iterable
 from dataclasses import dataclass, replace
-
-import json
-from typing import Any, Iterable, Literal
+from typing import Any, Literal
 
 import numpy as np
 import numpy.typing as npt
+
 from zarr.abc.codec import Codec
 from zarr.abc.store import set_or_delete
-
-
 from zarr.attributes import Attributes
 from zarr.buffer import Factory, NDArrayLike, NDBuffer
+from zarr.chunk_grids import RegularChunkGrid
+from zarr.chunk_key_encodings import ChunkKeyEncoding, DefaultChunkKeyEncoding, V2ChunkKeyEncoding
 from zarr.codecs import BytesCodec
 from zarr.common import (
     JSON,
@@ -36,11 +35,8 @@
     concurrent_map,
 )
 from zarr.config import config
-
 from zarr.indexing import BasicIndexer
-from zarr.chunk_grids import RegularChunkGrid
-from zarr.chunk_key_encodings import ChunkKeyEncoding, DefaultChunkKeyEncoding, V2ChunkKeyEncoding
-from zarr.metadata import ArrayMetadata, ArrayV3Metadata, ArrayV2Metadata, parse_indexing_order
+from zarr.metadata import ArrayMetadata, ArrayV2Metadata, ArrayV3Metadata, parse_indexing_order
 from zarr.store import StoreLike, StorePath, make_store_path
 from zarr.sync import sync
 

src/zarr/attributes.py

@@ -1,13 +1,13 @@
 from __future__ import annotations
 
-from collections.abc import MutableMapping
-from typing import TYPE_CHECKING, Iterator
+from collections.abc import Iterator, MutableMapping
+from typing import TYPE_CHECKING
 
 from zarr.common import JSON
 
 if TYPE_CHECKING:
-    from zarr.group import Group
     from zarr.array import Array
+    from zarr.group import Group
 
 
 class Attributes(MutableMapping[str, JSON]):

src/zarr/buffer.py

@@ -1,22 +1,20 @@
 from __future__ import annotations
 
 import sys
+from collections.abc import Callable, Iterable
 from typing import (
     TYPE_CHECKING,
     Any,
-    Callable,
-    Iterable,
     Literal,
-    Optional,
     Protocol,
-    Tuple,
     TypeAlias,
 )
 
 import numpy as np
 
 if TYPE_CHECKING:
     from typing_extensions import Self
+
     from zarr.codecs.bytes import Endian
     from zarr.common import BytesLike
 
@@ -44,7 +42,7 @@ def __call__(
             shape: Iterable[int],
             dtype: np.DTypeLike,
             order: Literal["C", "F"],
-            fill_value: Optional[Any],
+            fill_value: Any | None,
         ) -> NDBuffer:
             """Factory function to create a new NDBuffer (or subclass)
 
@@ -227,7 +225,7 @@ def __add__(self, other: Buffer) -> Self:
         return self.__class__(np.concatenate((self._data, other_array)))
 
     def __eq__(self, other: Any) -> bool:
-        if isinstance(other, (bytes, bytearray)):
+        if isinstance(other, bytes | bytearray):
             # Many of the tests compares `Buffer` with `bytes` so we
             # convert the bytes to a Buffer and try again
             return self == self.from_bytes(other)
@@ -275,7 +273,7 @@ def create(
         shape: Iterable[int],
         dtype: np.DTypeLike,
         order: Literal["C", "F"] = "C",
-        fill_value: Optional[Any] = None,
+        fill_value: Any | None = None,
     ) -> Self:
         """Create a new buffer and its underlying ndarray-like object
 
@@ -380,7 +378,7 @@ def dtype(self) -> np.dtype[Any]:
         return self._data.dtype
 
     @property
-    def shape(self) -> Tuple[int, ...]:
+    def shape(self) -> tuple[int, ...]:
         return self._data.shape
 
     @property

src/zarr/chunk_grids.py

@@ -1,9 +1,11 @@
 from __future__ import annotations
+
 import itertools
-from typing import TYPE_CHECKING, Any, Dict, Iterator
+from collections.abc import Iterator
 from dataclasses import dataclass
-from zarr.abc.metadata import Metadata
+from typing import TYPE_CHECKING, Any
 
+from zarr.abc.metadata import Metadata
 from zarr.common import (
     JSON,
     ChunkCoords,
@@ -20,7 +22,7 @@
 @dataclass(frozen=True)
 class ChunkGrid(Metadata):
     @classmethod
-    def from_dict(cls, data: Dict[str, JSON]) -> ChunkGrid:
+    def from_dict(cls, data: dict[str, JSON]) -> ChunkGrid:
         if isinstance(data, ChunkGrid):
             return data
 
@@ -43,15 +45,15 @@ def __init__(self, *, chunk_shape: ChunkCoordsLike) -> None:
         object.__setattr__(self, "chunk_shape", chunk_shape_parsed)
 
     @classmethod
-    def from_dict(cls, data: Dict[str, Any]) -> Self:
+    def from_dict(cls, data: dict[str, Any]) -> Self:
         _, configuration_parsed = parse_named_configuration(data, "regular")
 
         return cls(**configuration_parsed)  # type: ignore[arg-type]
 
-    def to_dict(self) -> Dict[str, JSON]:
+    def to_dict(self) -> dict[str, JSON]:
         return {"name": "regular", "configuration": {"chunk_shape": list(self.chunk_shape)}}
 
     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))
+            *(range(0, _ceildiv(s, c)) for s, c in zip(array_shape, self.chunk_shape, strict=False))
         )

src/zarr/chunk_key_encodings.py

@@ -1,9 +1,10 @@
 from __future__ import annotations
+
 from abc import abstractmethod
-from typing import TYPE_CHECKING, Dict, Literal, cast
 from dataclasses import dataclass
-from zarr.abc.metadata import Metadata
+from typing import TYPE_CHECKING, Literal, cast
 
+from zarr.abc.metadata import Metadata
 from zarr.common import (
     JSON,
     ChunkCoords,
@@ -33,7 +34,7 @@ def __init__(self, *, separator: SeparatorLiteral) -> None:
         object.__setattr__(self, "separator", separator_parsed)
 
     @classmethod
-    def from_dict(cls, data: Dict[str, JSON]) -> ChunkKeyEncoding:
+    def from_dict(cls, data: dict[str, JSON]) -> ChunkKeyEncoding:
         if isinstance(data, ChunkKeyEncoding):
             return data
 
@@ -44,7 +45,7 @@ def from_dict(cls, data: Dict[str, JSON]) -> ChunkKeyEncoding:
             return V2ChunkKeyEncoding(**configuration_parsed)  # type: ignore[arg-type]
         raise ValueError(f"Unknown chunk key encoding. Got {name_parsed}.")
 
-    def to_dict(self) -> Dict[str, JSON]:
+    def to_dict(self) -> dict[str, JSON]:
         return {"name": self.name, "configuration": {"separator": self.separator}}
 
     @abstractmethod

src/zarr/codecs/__init__.py

@@ -1,10 +1,10 @@
 from __future__ import annotations
 
-from zarr.codecs.blosc import BloscCodec, BloscCname, BloscShuffle  # noqa: F401
+from zarr.codecs.blosc import BloscCname, BloscCodec, BloscShuffle  # noqa: F401
 from zarr.codecs.bytes import BytesCodec, Endian  # noqa: F401
 from zarr.codecs.crc32c_ import Crc32cCodec  # noqa: F401
 from zarr.codecs.gzip import GzipCodec  # noqa: F401
+from zarr.codecs.pipeline import BatchedCodecPipeline  # noqa: F401
 from zarr.codecs.sharding import ShardingCodec, ShardingCodecIndexLocation  # noqa: F401
 from zarr.codecs.transpose import TransposeCodec  # noqa: F401
 from zarr.codecs.zstd import ZstdCodec  # noqa: F401
-from zarr.codecs.pipeline import BatchedCodecPipeline  # noqa: F401

src/zarr/codecs/_v2.py

@@ -2,13 +2,13 @@
 
 from dataclasses import dataclass
 
+import numcodecs
+from numcodecs.compat import ensure_bytes, ensure_ndarray
+
 from zarr.buffer import Buffer, NDBuffer
 from zarr.codecs.mixins import ArrayArrayCodecBatchMixin, ArrayBytesCodecBatchMixin
 from zarr.common import JSON, ArraySpec, to_thread
 
-import numcodecs
-from numcodecs.compat import ensure_bytes, ensure_ndarray
-
 
 @dataclass(frozen=True)
 class V2Compressor(ArrayBytesCodecBatchMixin):