Merge branch 'main' into perf/codec-chain

d-v-b · d-v-b · commit 55821b8c876c · 2026-03-16T21:18:09.000+01:00
diff --git a/.github/workflows/check_changelogs.yml b/.github/workflows/check_changelogs.yml
@@ -2,6 +2,10 @@ name: Check changelog entries
 
 on:
   pull_request:
+  workflow_dispatch:
+
+permissions:
+  contents: read
 
 jobs:
   check-changelogs:
diff --git a/.github/workflows/gpu_test.yml b/.github/workflows/gpu_test.yml
@@ -13,6 +13,9 @@ on:
 env:
   LD_LIBRARY_PATH: /usr/local/cuda/extras/CUPTI/lib64:/usr/local/cuda/lib64
 
+permissions:
+  contents: read
+
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
diff --git a/.github/workflows/hypothesis.yaml b/.github/workflows/hypothesis.yaml
@@ -9,6 +9,9 @@ on:
     - cron: "0 0 * * *" # Daily “At 00:00” UTC
   workflow_dispatch: # allows you to trigger manually
 
+permissions:
+  contents: read
+
 env:
   FORCE_COLOR: 3
 
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -7,6 +7,9 @@ on:
     branches: [main, 3.1.x]
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
@@ -17,9 +20,4 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v6
-      - name: Install uv
-        uses: astral-sh/setup-uv@v7
-      - name: Install prek
-        run: uv tool install prek
-      - name: Run prek
-        run: prek run --all-files
+      - uses: j178/prek-action@v1
diff --git a/.github/workflows/needs_release_notes.yml b/.github/workflows/needs_release_notes.yml
@@ -1,7 +1,8 @@
 name: "Pull Request Labeler"
 
 on:
-  - pull_request_target
+  - pull_request_target:
+      types: [opened, reopened, synchronize]
 
 jobs:
   labeler:
diff --git a/.github/workflows/nightly_wheels.yml b/.github/workflows/nightly_wheels.yml
@@ -6,6 +6,9 @@ on:
     - cron: '0 2 * * *'
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 jobs:
   build_and_upload_nightly:
     name: Build and upload nightly wheels
diff --git a/.github/workflows/releases.yml b/.github/workflows/releases.yml
@@ -1,6 +1,14 @@
 name: Wheels
 
-on: [push, pull_request]
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+  workflow_dispatch:
+
+permissions:
+  contents: read
 
 jobs:
 
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -10,6 +10,9 @@ on:
     branches: [ main, 3.1.x ]
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
@@ -150,4 +153,4 @@ jobs:
           contains(needs.*.result, 'cancelled')
         run: exit 1
       - name: Success
-        run: echo Success!
+        run: echo Success!
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -11,7 +11,7 @@ default_language_version:
 
 repos:
   - 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"]
@@ -47,18 +47,22 @@ repos:
           - hypothesis
           - s3fs
   - repo: https://github.com/scientific-python/cookie
-    rev: 2025.11.21
+    rev: 2026.03.02
     hooks:
       - id: sp-repo-review
-  - repo: https://github.com/pre-commit/pygrep-hooks
-    rev: v1.10.0
-    hooks:
-      - id: rst-directive-colons
-      - id: rst-inline-touching-normal
   - repo: https://github.com/numpy/numpydoc
     rev: v1.10.0
     hooks:
       - id: numpydoc-validation
+  - repo: local
+    hooks:
+      - id: ban-lstrip-rstrip
+        name: ban lstrip/rstrip
+        language: pygrep
+        # Matches .lstrip() or .rstrip() where the string argument is 2+ characters.
+        entry: "\\.(lstrip|rstrip)\\([\"'][^\"']{2,}[\"']\\)"
+        types: [python]
+        files: ^(src|tests)/
   - repo: https://github.com/twisted/towncrier
     rev: 25.8.0
     hooks:
diff --git a/changes/3464.doc.md b/changes/3464.doc.md
@@ -0,0 +1 @@
+Add documentation example for creating uncompressed arrays in the Compression section of the user guide.
diff --git a/changes/3710.bugfix.md b/changes/3710.bugfix.md
@@ -0,0 +1 @@
+Add a dedicated in-memory cache for byte-range requests to the experimental `CacheStore`.
diff --git a/changes/3721.misc.md b/changes/3721.misc.md
@@ -0,0 +1 @@
+Adds synchronous (non-async) encoding and decoding methods to CPU-bound codecs. This is necessary for performance optimizations based on avoiding `asyncio` overhead. These new methods are described by a new protocol: `SupportsSyncCodec`.
diff --git a/docs/overrides/stylesheets/extra.css b/docs/overrides/stylesheets/extra.css
@@ -52,14 +52,14 @@
   color: white;
 }
 
-/* Search box styling */
-.md-search__input {
+/* Search box styling in the header */
+.md-header .md-search__input {
   background-color: rgba(255, 255, 255, 0.15);
   border: 1px solid rgba(255, 255, 255, 0.2);
   color: white;
 }
 
-.md-search__input::placeholder {
+.md-header .md-search__input::placeholder {
   color: rgba(255, 255, 255, 0.7);
 }
 
diff --git a/docs/user-guide/arrays.md b/docs/user-guide/arrays.md
@@ -224,6 +224,13 @@ print(z.info_complete())
 If you don't specify a compressor, by default Zarr uses the Zstandard
 compressor.
 
+To create an array without any compression, set `compressors=None`:
+
+```python exec="true" session="arrays" source="above" result="ansi"
+z_no_compress = zarr.create_array(store='data/example-uncompressed.zarr', shape=(10000, 10000), chunks=(1000, 1000), dtype='int32', compressors=None)
+print(f"Compressors: {z_no_compress.compressors}")
+```
+
 In addition to Blosc and Zstandard, other compression libraries can also be used. For example,
 here is an array using Gzip compression, level 1:
 
diff --git a/pyproject.toml b/pyproject.toml
@@ -422,6 +422,7 @@ markers = [
 [tool.repo-review]
 ignore = [
 	"PC111",  # fix Python code in documentation - enable later
+    "PC170",  # use PyGrep hooks - no *.rst files to check
 	"PC180",  # for JavaScript - not interested
 	"PC902",  # pre-commit.ci custom autofix message - not using autofix
 ]
diff --git a/src/zarr/_cli/cli.py b/src/zarr/_cli/cli.py
@@ -1,5 +1,5 @@
 import logging
-from enum import Enum
+from enum import StrEnum
 from typing import Annotated, Literal, cast
 
 import typer
@@ -24,12 +24,12 @@ def _set_logging_level(*, verbose: bool) -> None:
     zarr.set_format("%(message)s")
 
 
-class CLIZarrFormat(str, Enum):
+class CLIZarrFormat(StrEnum):
     v2 = "v2"
     v3 = "v3"
 
 
-class CLIZarrFormatV3(str, Enum):
+class CLIZarrFormatV3(StrEnum):
     """Limit CLI choice to only v3"""
 
     v3 = "v3"
diff --git a/src/zarr/abc/store.py b/src/zarr/abc/store.py
@@ -29,7 +29,7 @@
 ]
 
 
-@dataclass
+@dataclass(frozen=True, slots=True)
 class RangeByteRequest:
     """Request a specific byte range"""
 
@@ -39,15 +39,15 @@ class RangeByteRequest:
     """The end of the byte range request (exclusive)."""
 
 
-@dataclass
+@dataclass(frozen=True, slots=True)
 class OffsetByteRequest:
     """Request all bytes starting from a given byte offset"""
 
     offset: int
     """The byte offset for the offset range request."""
 
 
-@dataclass
+@dataclass(frozen=True, slots=True)
 class SuffixByteRequest:
     """Request up to the last `n` bytes"""
 
diff --git a/src/zarr/codecs/blosc.py b/src/zarr/codecs/blosc.py
@@ -318,6 +318,8 @@ def _encode_sync(
         chunk_bytes: Buffer,
         chunk_spec: ArraySpec,
     ) -> Buffer | None:
+        # Since blosc only support host memory, we convert the input and output of the encoding
+        # between numpy array and buffer
         return chunk_spec.prototype.buffer.from_bytes(
             self._blosc_codec.encode(chunk_bytes.as_numpy_array())
         )
diff --git a/src/zarr/core/array.py b/src/zarr/core/array.py
@@ -1235,24 +1235,28 @@ def basename(self) -> str:
     @property
     def cdata_shape(self) -> tuple[int, ...]:
         """
-        The shape of the chunk grid for this array.
+        The number of chunks along each dimension.
+
+        When sharding is used, this counts inner chunks (not shards) per dimension.
 
         Returns
         -------
         tuple[int, ...]
-            The shape of the chunk grid for this array.
+            The number of chunks along each dimension.
         """
         return self._chunk_grid_shape
 
     @property
     def _chunk_grid_shape(self) -> tuple[int, ...]:
         """
-        The shape of the chunk grid for this array.
+        The number of chunks along each dimension.
+
+        When sharding is used, this counts inner chunks (not shards) per dimension.
 
         Returns
         -------
         tuple[int, ...]
-            The shape of the chunk grid for this array.
+            The number of chunks along each dimension.
         """
         return tuple(starmap(ceildiv, zip(self.shape, self.chunks, strict=True)))
 
@@ -2399,14 +2403,23 @@ def compressors(self) -> tuple[Numcodec, ...] | tuple[BytesBytesCodec, ...]:
     @property
     def cdata_shape(self) -> tuple[int, ...]:
         """
-        The shape of the chunk grid for this array.
+        The number of chunks along each dimension.
+
+        When sharding is used, this counts inner chunks (not shards) per dimension.
         """
         return self.async_array._chunk_grid_shape
 
     @property
     def _chunk_grid_shape(self) -> tuple[int, ...]:
         """
-        The shape of the chunk grid for this array.
+        The number of chunks along each dimension.
+
+        When sharding is used, this counts inner chunks (not shards) per dimension.
+
+        Returns
+        -------
+        tuple[int, ...]
+            The number of chunks along each dimension.
         """
         return self.async_array._chunk_grid_shape
 
diff --git a/src/zarr/core/chunk_key_encodings.py b/src/zarr/core/chunk_key_encodings.py
@@ -42,7 +42,7 @@ class ChunkKeyEncoding(ABC, Metadata):
     @classmethod
     def from_dict(cls, data: dict[str, JSON]) -> Self:
         _, config_parsed = parse_named_configuration(data, require_configuration=False)
-        return cls(**config_parsed if config_parsed else {})
+        return cls(**config_parsed or {})
 
     def to_dict(self) -> dict[str, JSON]:
         return {"name": self.name, "configuration": super().to_dict()}
diff --git a/src/zarr/core/dtype/__init__.py b/src/zarr/core/dtype/__init__.py
@@ -81,7 +81,6 @@
     "TBaseDType",
     "TBaseScalar",
     "TimeDelta64",
-    "TimeDelta64",
     "TimeDelta64JSON_V2",
     "TimeDelta64JSON_V3",
     "UInt8",
diff --git a/src/zarr/core/dtype/npy/float.py b/src/zarr/core/dtype/npy/float.py
@@ -201,6 +201,16 @@ def _check_scalar(self, data: object) -> TypeGuard[FloatLike]:
         TypeGuard[FloatLike]
             True if the input is a valid scalar value, False otherwise.
         """
+        if isinstance(data, str):
+            # Only accept strings that are valid float representations (e.g. "NaN", "inf").
+            # Plain strings that cannot be converted should return False so that cast_scalar
+            # raises TypeError rather than a confusing ValueError.
+            try:
+                self.to_native_dtype().type(data)
+            except (ValueError, OverflowError):
+                return False
+            else:
+                return True
         return isinstance(data, FloatLike)
 
     def _cast_scalar_unchecked(self, data: FloatLike) -> TFloatScalar_co:
diff --git a/src/zarr/core/indexing.py b/src/zarr/core/indexing.py
@@ -209,7 +209,7 @@ def _iter_regions(
     # ((slice(0, 1, 1), slice(0, 2, 1)), (slice(1, 2, 1), slice(0, 2, 1)))
     ```
     """
-    grid_shape = tuple(ceildiv(d, s) for d, s in zip(domain_shape, region_shape, strict=True))
+    grid_shape = tuple(itertools.starmap(ceildiv, zip(domain_shape, region_shape, strict=True)))
     for grid_position in _iter_grid(
         grid_shape=grid_shape, origin=origin, selection_shape=selection_shape, order=order
     ):
diff --git a/src/zarr/dtype.py b/src/zarr/dtype.py
@@ -72,7 +72,6 @@
     "StructuredJSON_V2",
     "StructuredJSON_V3",
     "TimeDelta64",
-    "TimeDelta64",
     "TimeDelta64JSON_V2",
     "TimeDelta64JSON_V3",
     "UInt8",
@@ -85,6 +84,5 @@
     "VariableLengthUTF8JSON_V2",
     "ZDType",
     "data_type_registry",
-    "data_type_registry",
     "parse_dtype",
 ]
diff --git a/src/zarr/experimental/cache_store.py b/src/zarr/experimental/cache_store.py
diff --git a/tests/test_api.py b/tests/test_api.py
diff --git a/tests/test_array.py b/tests/test_array.py
diff --git a/tests/test_dtype/test_npy/test_float.py b/tests/test_dtype/test_npy/test_float.py
diff --git a/tests/test_examples.py b/tests/test_examples.py
diff --git a/tests/test_experimental/test_cache_store.py b/tests/test_experimental/test_cache_store.py
diff --git a/tests/test_properties.py b/tests/test_properties.py

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	`+Add documentation example for creating uncompressed arrays in the Compression section of the user guide.`