Enforce ruff/flake8-comprehensions rules (C4) (zarr-developers#2239)

* Apply ruff/flake8-comprehensions rule C401

C401 Unnecessary generator (rewrite as a `set` comprehension)

* Apply ruff/flake8-comprehensions rule C408

C408 Unnecessary `dict` call (rewrite as a literal)

* Apply ruff/flake8-comprehensions rule C409

C409 Unnecessary list comprehension passed to `tuple()` (rewrite as a generator)

* Apply ruff/flake8-comprehensions rule C416

C416 Unnecessary `list` comprehension (rewrite using `list()`)

* Enforce ruff/flake8-comprehensions rules (C4)

---------

Co-authored-by: Joe Hamman <[email protected]>

Author: DimitriPapadopoulos

bench/compress_normal.py

@@ -16,7 +16,7 @@
         a,
         chunks=1000000,
         compression="blosc",
-        compression_opts=dict(cname="lz4", clevel=5, shuffle=2),
+        compression_opts={"cname": "lz4", "clevel": 5, "shuffle": 2},
     )
     print(z)
 

pyproject.toml

@@ -208,6 +208,7 @@ extend-exclude = [
 [tool.ruff.lint]
 extend-select = [
     "B",   # flake8-bugbear
+    "C4",  # flake8-comprehensions
     "FLY", # flynt
     "I",   # isort
     "ISC", # flake8-implicit-str-concat

src/zarr/codecs/sharding.py

@@ -151,7 +151,7 @@ def is_dense(self, chunk_byte_length: int) -> bool:
 
         # Are all non-empty offsets unique?
         if len(
-            set(offset for offset, _ in sorted_offsets_and_lengths if offset != MAX_UINT_64)
+            {offset for offset, _ in sorted_offsets_and_lengths if offset != MAX_UINT_64}
         ) != len(sorted_offsets_and_lengths):
             return False
 
@@ -380,8 +380,8 @@ def to_dict(self) -> dict[str, JSON]:
             "name": "sharding_indexed",
             "configuration": {
                 "chunk_shape": self.chunk_shape,
-                "codecs": tuple([s.to_dict() for s in self.codecs]),
-                "index_codecs": tuple([s.to_dict() for s in self.index_codecs]),
+                "codecs": tuple(s.to_dict() for s in self.codecs),
+                "index_codecs": tuple(s.to_dict() for s in self.index_codecs),
                 "index_location": self.index_location.value,
             },
         }
@@ -477,7 +477,7 @@ async def _decode_partial_single(
         )
 
         indexed_chunks = list(indexer)
-        all_chunk_coords = set(chunk_coords for chunk_coords, _, _ in indexed_chunks)
+        all_chunk_coords = {chunk_coords for chunk_coords, _, _ in indexed_chunks}
 
         # reading bytes of all requested chunks
         shard_dict: ShardMapping = {}

src/zarr/store/memory.py

@@ -135,7 +135,7 @@ async def list_dir(self, prefix: str) -> AsyncGenerator[str, None]:
             prefix = prefix[:-1]
 
         if prefix == "":
-            keys_unique = set(k.split("/")[0] for k in self._store_dict)
+            keys_unique = {k.split("/")[0] for k in self._store_dict}
         else:
             # Our dictionary doesn't contain directory markers, but we want to include
             # a pseudo directory when there's a nested item and we're listing an

src/zarr/store/zip.py

@@ -232,7 +232,7 @@ async def list_dir(self, prefix: str) -> AsyncGenerator[str, None]:
         keys = self._zf.namelist()
         seen = set()
         if prefix == "":
-            keys_unique = set(k.split("/")[0] for k in keys)
+            keys_unique = {k.split("/")[0] for k in keys}
             for key in keys_unique:
                 if key not in seen:
                     seen.add(key)

tests/v3/test_group.py

@@ -271,7 +271,7 @@ def test_group_iter(store: Store, zarr_format: ZarrFormat) -> None:
 
     group = Group.from_store(store, zarr_format=zarr_format)
     with pytest.raises(NotImplementedError):
-        [x for x in group]
+        list(group)
 
 
 def test_group_len(store: Store, zarr_format: ZarrFormat) -> None:

tests/v3/test_store/test_remote.py

@@ -92,7 +92,7 @@ async def test_basic() -> None:
     store = RemoteStore.from_url(
         f"s3://{test_bucket_name}",
         mode="w",
-        storage_options=dict(endpoint_url=endpoint_url, anon=False),
+        storage_options={"endpoint_url": endpoint_url, "anon": False},
     )
     assert await _collect_aiterator(store.list()) == ()
     assert not await store.exists("foo")