Merge branch 'main' of github.com:zarr-developers/zarr-python into feat/fixed-length-strings

Author: d-v-b

.pre-commit-config.yaml

@@ -6,7 +6,7 @@ ci:
 default_stages: [pre-commit, pre-push]
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.4
+    rev: v0.9.9
     hooks:
     - id: ruff
       args: ["--fix", "--show-fixes"]
@@ -22,7 +22,7 @@ repos:
     - id: check-yaml
     - id: trailing-whitespace
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.14.1
+    rev: v1.15.0
     hooks:
       - id: mypy
         files: src|tests

changes/2870.bugfix.rst

@@ -0,0 +1 @@
+Prevent update_attributes calls from deleting old attributes

docs/user-guide/v3_migration.rst

@@ -124,6 +124,30 @@ The Store class
 The Store API has changed significant in Zarr-Python 3. The most notable changes to the
 Store API are:
 
+Store Import Paths
+^^^^^^^^^^^^^^^^^^
+Several store implementations have moved from the top-level module to ``zarr.storage``:
+
+.. code-block:: diff
+   :caption: Store import changes from v2 to v3
+
+   # Before (v2)
+   - from zarr import MemoryStore, DirectoryStore
+   + from zarr.storage import MemoryStore, LocalStore  # LocalStore replaces DirectoryStore
+
+Common replacements:
+
++-------------------------+------------------------------------+
+| v2 Import               | v3 Import                          |
++=========================+====================================+
+| ``zarr.MemoryStore``    | ``zarr.storage.MemoryStore``       |
++-------------------------+------------------------------------+
+| ``zarr.DirectoryStore`` | ``zarr.storage.LocalStore``        |
++-------------------------+------------------------------------+
+| ``zarr.TempStore``      | Use ``tempfile.TemporaryDirectory``|
+|                         | with ``LocalStore``                |
++-------------------------+------------------------------------+
+
 1. Replaced the ``MutableMapping`` base class in favor of a custom abstract base class
    (:class:`zarr.abc.store.Store`).
 2. Switched to an asynchronous interface for all store methods that result in IO. This

src/zarr/codecs/blosc.py

@@ -55,7 +55,7 @@ class BloscCname(Enum):
     zlib = "zlib"
 
 
-# See https://zarr.readthedocs.io/en/stable/tutorial.html#configuring-blosc
+# See https://zarr.readthedocs.io/en/stable/user-guide/performance.html#configuring-blosc
 numcodecs.blosc.use_threads = False
 
 

src/zarr/core/array.py

@@ -1646,8 +1646,6 @@ async def update_attributes(self, new_attributes: dict[str, JSON]) -> Self:
         - The updated attributes will be merged with existing attributes, and any conflicts will be
           overwritten by the new values.
         """
-        # metadata.attributes is "frozen" so we simply clear and update the dict
-        self.metadata.attributes.clear()
         self.metadata.attributes.update(new_attributes)
 
         # Write new metadata

src/zarr/core/attributes.py

@@ -50,6 +50,7 @@ def put(self, d: dict[str, JSON]) -> None:
            >>> attrs
            {'a': 3, 'c': 4}
         """
+        self._obj.metadata.attributes.clear()
         self._obj = self._obj.update_attributes(d)
 
     def asdict(self) -> dict[str, JSON]:

src/zarr/core/common.py

@@ -4,7 +4,7 @@
 import functools
 import operator
 import warnings
-from collections.abc import Iterable, Mapping
+from collections.abc import Iterable, Mapping, Sequence
 from enum import Enum
 from itertools import starmap
 from typing import (
@@ -36,7 +36,7 @@
 ChunkCoordsLike = Iterable[int]
 ZarrFormat = Literal[2, 3]
 NodeType = Literal["array", "group"]
-JSON = str | int | float | Mapping[str, "JSON"] | tuple["JSON", ...] | None
+JSON = str | int | float | Mapping[str, "JSON"] | Sequence["JSON"] | None
 MemoryOrder = Literal["C", "F"]
 AccessModeLiteral = Literal["r", "r+", "a", "w", "w-"]
 

src/zarr/core/group.py

@@ -1254,8 +1254,6 @@ async def update_attributes(self, new_attributes: dict[str, Any]) -> AsyncGroup:
         -------
         self : AsyncGroup
         """
-        # metadata.attributes is "frozen" so we simply clear and update the dict
-        self.metadata.attributes.clear()
         self.metadata.attributes.update(new_attributes)
 
         # Write new metadata

tests/test_api.py

@@ -209,7 +209,7 @@ def test_save(store: Store, n_args: int, n_kwargs: int) -> None:
         assert isinstance(array, Array)
         assert_array_equal(array[:], data)
     else:
-        save(store, *args, **kwargs)  # type: ignore[arg-type]
+        save(store, *args, **kwargs)  # type: ignore [arg-type]
         group = open(store)
         assert isinstance(group, Group)
         for array in group.array_values():
@@ -1095,25 +1095,31 @@ async def test_open_falls_back_to_open_group_async() -> None:
     assert group.attrs == {"key": "value"}
 
 
-def test_open_mode_write_creates_group(tmp_path: pathlib.Path) -> None:
+@pytest.mark.parametrize("mode", ["r", "r+", "w", "a"])
+def test_open_modes_creates_group(tmp_path: pathlib.Path, mode: str) -> None:
     # https://github.com/zarr-developers/zarr-python/issues/2490
-    zarr_dir = tmp_path / "test.zarr"
-    group = zarr.open(zarr_dir, mode="w")
-    assert isinstance(group, Group)
+    zarr_dir = tmp_path / f"mode-{mode}-test.zarr"
+    if mode in ["r", "r+"]:
+        # Expect FileNotFoundError to be raised if 'r' or 'r+' mode
+        with pytest.raises(FileNotFoundError):
+            zarr.open(store=zarr_dir, mode=mode)
+    else:
+        group = zarr.open(store=zarr_dir, mode=mode)
+        assert isinstance(group, Group)
 
 
 async def test_metadata_validation_error() -> None:
     with pytest.raises(
         MetadataValidationError,
         match="Invalid value for 'zarr_format'. Expected '2, 3, or None'. Got '3.0'.",
     ):
-        await zarr.api.asynchronous.open_group(zarr_format="3.0")  # type: ignore[arg-type]
+        await zarr.api.asynchronous.open_group(zarr_format="3.0")  # type: ignore [arg-type]
 
     with pytest.raises(
         MetadataValidationError,
         match="Invalid value for 'zarr_format'. Expected '2, 3, or None'. Got '3.0'.",
     ):
-        await zarr.api.asynchronous.open_array(shape=(1,), zarr_format="3.0")  # type: ignore[arg-type]
+        await zarr.api.asynchronous.open_array(shape=(1,), zarr_format="3.0")  # type: ignore [arg-type]
 
 
 @pytest.mark.parametrize(

tests/test_attributes.py

@@ -20,3 +20,42 @@ def test_asdict() -> None:
     )
     result = attrs.asdict()
     assert result == {"a": 1, "b": 2}
+
+
+def test_update_attributes_preserves_existing() -> None:
+    """
+    Test that `update_attributes` only updates the specified attributes
+    and preserves existing ones.
+    """
+    store = zarr.storage.MemoryStore()
+    z = zarr.create(10, store=store, overwrite=True)
+    z.attrs["a"] = []
+    z.attrs["b"] = 3
+    assert dict(z.attrs) == {"a": [], "b": 3}
+
+    z.update_attributes({"a": [3, 4], "c": 4})
+    assert dict(z.attrs) == {"a": [3, 4], "b": 3, "c": 4}
+
+
+def test_update_empty_attributes() -> None:
+    """
+    Ensure updating when initial attributes are empty works.
+    """
+    store = zarr.storage.MemoryStore()
+    z = zarr.create(10, store=store, overwrite=True)
+    assert dict(z.attrs) == {}
+    z.update_attributes({"a": [3, 4], "c": 4})
+    assert dict(z.attrs) == {"a": [3, 4], "c": 4}
+
+
+def test_update_no_changes() -> None:
+    """
+    Ensure updating when no new or modified attributes does not alter existing ones.
+    """
+    store = zarr.storage.MemoryStore()
+    z = zarr.create(10, store=store, overwrite=True)
+    z.attrs["a"] = []
+    z.attrs["b"] = 3
+
+    z.update_attributes({})
+    assert dict(z.attrs) == {"a": [], "b": 3}