Merge branch 'main' into store-docstrings

Author: d-v-b

.github/workflows/test.yml

@@ -64,6 +64,7 @@ jobs:
       run: |
         hatch env run --env test.py${{ matrix.python-version }}-${{ matrix.numpy-version }}-${{ matrix.dependency-set }} run-coverage
     - name: Upload coverage
+      if: ${{ matrix.dependency-set == 'optional' && matrix.os == 'ubuntu-latest' }}
       uses: codecov/codecov-action@v5
       with:
         token: ${{ secrets.CODECOV_TOKEN }}

changes/2622.feature.rst

@@ -0,0 +1 @@
+Add ``zarr.from_array`` using concurrent streaming of source data

changes/2718.bugfix.rst

@@ -0,0 +1,3 @@
+0-dimensional arrays are now returning a scalar. Therefore, the return type of ``__getitem__`` changed
+to NDArrayLikeOrScalar. This change is to make the behavior of 0-dimensional arrays consistent with
+``numpy`` scalars.

changes/2991.doc.rst

@@ -0,0 +1 @@
+Updated the 3.0 migration guide to include the removal of "." syntax for getting group members.

changes/2996.bugfix.rst

@@ -0,0 +1,4 @@
+Fixes `ConsolidatedMetadata` serialization of `nan`, `inf`, and `-inf` to be
+consistent with the behavior of `ArrayMetadata`.
+
+

docs/release-notes.rst

@@ -145,6 +145,8 @@ Other
 3.0.1 (Jan. 17, 2025)
 ---------------------
 
+* Implement ``zarr.from_array`` using concurrent streaming (:issue:`2622`).
+
 Bug fixes
 ~~~~~~~~~
 * Fixes ``order`` argument for Zarr format 2 arrays (:issue:`2679`).

docs/user-guide/v3_migration.rst

@@ -117,6 +117,8 @@ The Group class
 
    - Use :func:`zarr.Group.create_array` in place of :func:`zarr.Group.create_dataset`
    - Use :func:`zarr.Group.require_array` in place of :func:`zarr.Group.require_dataset`
+3. Disallow "." syntax for getting group members. To get a member of a group named ``foo``,
+   use ``group["foo"]`` in place of ``group.foo``.
 
 The Store class
 ~~~~~~~~~~~~~~~

pyproject.toml

@@ -73,18 +73,19 @@ gpu = [
 test = [
     "coverage",
     "pytest",
+    "pytest-asyncio",
     "pytest-cov",
+    "pytest-accept",
+    "rich",
+    "mypy",
+    "hypothesis",
+]
+remote_tests = [
     'zarr[remote]',
     "botocore",
     "s3fs",
     "moto[s3,server]",
-    "pytest-asyncio",
-    "pytest-accept",
     "requests",
-    "rich",
-    "mypy",
-    "hypothesis",
-    "universal-pathlib",
 ]
 optional = ["rich", "universal-pathlib"]
 docs = [
@@ -143,28 +144,21 @@ hooks.vcs.version-file = "src/zarr/_version.py"
 [tool.hatch.envs.test]
 dependencies = [
     "numpy~={matrix:numpy}",
-    "universal_pathlib",
 ]
 features = ["test"]
 
 [[tool.hatch.envs.test.matrix]]
 python = ["3.11", "3.12", "3.13"]
 numpy = ["1.25", "2.1"]
-version = ["minimal"]
-
-[[tool.hatch.envs.test.matrix]]
-python = ["3.11", "3.12", "3.13"]
-numpy = ["1.25", "2.1"]
-features = ["optional"]
+deps = ["minimal", "optional"]
 
-[[tool.hatch.envs.test.matrix]]
-python = ["3.11", "3.12", "3.13"]
-numpy = ["1.25", "2.1"]
-features = ["gpu"]
+[tool.hatch.envs.test.overrides]
+matrix.deps.dependencies = [
+  {value = "zarr[remote, remote_tests, test, optional]", if = ["optional"]}
+]
 
 [tool.hatch.envs.test.scripts]
 run-coverage = "pytest --cov-config=pyproject.toml --cov=pkg --cov-report xml --cov=src --junitxml=junit.xml -o junit_family=legacy"
-run-coverage-gpu = "pip install cupy-cuda12x && pytest -m gpu --cov-config=pyproject.toml --cov=pkg --cov-report xml --cov=src --junitxml=junit.xml -o junit_family=legacy"
 run-coverage-html = "pytest --cov-config=pyproject.toml --cov=pkg --cov-report html --cov=src"
 run = "run-coverage --no-cov"
 run-pytest = "run"
@@ -174,7 +168,7 @@ run-hypothesis = "run-coverage --hypothesis-profile ci --run-slow-hypothesis tes
 list-env = "pip list"
 
 [tool.hatch.envs.doctest]
-features = ["test", "optional", "remote"]
+features = ["test", "optional", "remote", "remote_tests"]
 description = "Test environment for doctests"
 
 [tool.hatch.envs.doctest.scripts]
@@ -255,6 +249,7 @@ dependencies = [
     'universal_pathlib==0.0.22',
     'typing_extensions==4.9.*',
     'donfig==0.8.*',
+    'obstore==0.5.*',
     # test deps
     'zarr[test]',
 ]

src/zarr/__init__.py

@@ -11,6 +11,7 @@
     create_hierarchy,
     empty,
     empty_like,
+    from_array,
     full,
     full_like,
     group,
@@ -54,6 +55,7 @@
     "create_hierarchy",
     "empty",
     "empty_like",
+    "from_array",
     "full",
     "full_like",
     "group",

src/zarr/api/asynchronous.py

@@ -9,7 +9,7 @@
 import numpy.typing as npt
 from typing_extensions import deprecated
 
-from zarr.core.array import Array, AsyncArray, create_array, get_array_metadata
+from zarr.core.array import Array, AsyncArray, create_array, from_array, get_array_metadata
 from zarr.core.array_spec import ArrayConfig, ArrayConfigLike, ArrayConfigParams
 from zarr.core.buffer import NDArrayLike
 from zarr.core.common import (
@@ -38,6 +38,7 @@
     from collections.abc import Iterable
 
     from zarr.abc.codec import Codec
+    from zarr.core.buffer import NDArrayLikeOrScalar
     from zarr.core.chunk_key_encodings import ChunkKeyEncoding
     from zarr.storage import StoreLike
 
@@ -56,6 +57,7 @@
     "create_hierarchy",
     "empty",
     "empty_like",
+    "from_array",
     "full",
     "full_like",
     "group",
@@ -238,7 +240,7 @@ async def load(
     path: str | None = None,
     zarr_format: ZarrFormat | None = None,
     zarr_version: ZarrFormat | None = None,
-) -> NDArrayLike | dict[str, NDArrayLike]:
+) -> NDArrayLikeOrScalar | dict[str, NDArrayLikeOrScalar]:
     """Load data from an array or group into memory.
 
     Parameters
@@ -533,7 +535,7 @@ async def tree(grp: AsyncGroup, expand: bool | None = None, level: int | None =
 
 
 async def array(
-    data: npt.ArrayLike, **kwargs: Any
+    data: npt.ArrayLike | Array, **kwargs: Any
 ) -> AsyncArray[ArrayV2Metadata] | AsyncArray[ArrayV3Metadata]:
     """Create an array filled with `data`.
 
@@ -550,13 +552,16 @@ async def array(
         The new array.
     """
 
+    if isinstance(data, Array):
+        return await from_array(data=data, **kwargs)
+
     # ensure data is array-like
     if not hasattr(data, "shape") or not hasattr(data, "dtype"):
         data = np.asanyarray(data)
 
     # setup dtype
     kw_dtype = kwargs.get("dtype")
-    if kw_dtype is None:
+    if kw_dtype is None and hasattr(data, "dtype"):
         kwargs["dtype"] = data.dtype
     else:
         kwargs["dtype"] = kw_dtype