Merge branch 'main' into extension-keyenc

Author: d-v-b

.github/workflows/check_changelogs.yml

@@ -12,7 +12,7 @@ jobs:
       - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Install uv
-        uses: astral-sh/setup-uv@557e51de59eb14aaaba2ed9621916900a91d50c6 # v6.6.1
+        uses: astral-sh/setup-uv@b75a909f75acd358c2196fb9a5f1299a9a8868a4 # v6.7.0
 
       - name: Check changelog entries
         run: uv run --no-sync python ci/check_changelog_entries.py

changes/3444.feature.rst

@@ -0,0 +1 @@
+Trying to open a group at a path were a array already exists now raises a helpful error.

docs/user-guide/config.rst

@@ -62,7 +62,7 @@ This is the current default configuration::
                'numcodecs.delta': 'zarr.codecs.numcodecs.Delta',
                'numcodecs.fixedscaleoffset': 'zarr.codecs.numcodecs.FixedScaleOffset',
                'numcodecs.fletcher32': 'zarr.codecs.numcodecs.Fletcher32',
-               'numcodecs.gZip': 'zarr.codecs.numcodecs.GZip',
+               'numcodecs.gzip': 'zarr.codecs.numcodecs.GZip',
                'numcodecs.jenkins_lookup3': 'zarr.codecs.numcodecs.JenkinsLookup3',
                'numcodecs.lz4': 'zarr.codecs.numcodecs.LZ4',
                'numcodecs.lzma': 'zarr.codecs.numcodecs.LZMA',

src/zarr/codecs/numcodecs/_codecs.py

@@ -3,6 +3,7 @@
 
 These codecs were previously defined in :py:mod:`numcodecs`, and have now been moved to `zarr`.
 
+>>> import numpy as np
 >>> import zarr
 >>> import zarr.codecs.numcodecs as numcodecs
 >>>
@@ -11,9 +12,9 @@
 ...   shape=(1024, 1024),
 ...   chunks=(64, 64),
 ...   dtype="uint32",
-...   filters=[numcodecs.zarr3.Delta()],
-...   compressors=[numcodecs.zarr3.BZ2(level=5)])
->>> array[:] = np.arange(*array.shape).astype(array.dtype)
+...   filters=[numcodecs.Delta(dtype="uint32")],
+...   compressors=[numcodecs.BZ2(level=5)])
+>>> array[:] = np.arange(np.prod(array.shape), dtype=array.dtype).reshape(*array.shape)
 
 .. note::
 

src/zarr/core/config.py

@@ -138,7 +138,7 @@ def enable_gpu(self) -> ConfigSet:
                 "numcodecs.delta": "zarr.codecs.numcodecs.Delta",
                 "numcodecs.fixedscaleoffset": "zarr.codecs.numcodecs.FixedScaleOffset",
                 "numcodecs.fletcher32": "zarr.codecs.numcodecs.Fletcher32",
-                "numcodecs.gZip": "zarr.codecs.numcodecs.GZip",
+                "numcodecs.gzip": "zarr.codecs.numcodecs.GZip",
                 "numcodecs.jenkins_lookup3": "zarr.codecs.numcodecs.JenkinsLookup3",
                 "numcodecs.pcodec": "zarr.codecs.numcodecs.PCodec",
                 "numcodecs.packbits": "zarr.codecs.numcodecs.PackBits",

src/zarr/core/group.py

@@ -53,6 +53,7 @@
 from zarr.errors import (
     ContainsArrayError,
     ContainsGroupError,
+    GroupNotFoundError,
     MetadataValidationError,
     ZarrDeprecationWarning,
     ZarrUserWarning,
@@ -673,6 +674,13 @@ def from_dict(
         store_path: StorePath,
         data: dict[str, Any],
     ) -> AsyncGroup:
+        node_type = data.pop("node_type", None)
+        if node_type == "array":
+            msg = f"An array already exists in store {store_path.store} at path {store_path.path}."
+            raise ContainsArrayError(msg)
+        elif node_type not in ("group", None):
+            msg = f"Node type in metadata ({node_type}) is not 'group'"
+            raise GroupNotFoundError(msg)
         return cls(
             metadata=GroupMetadata.from_dict(data),
             store_path=store_path,

tests/test_codecs/test_numcodecs.py

@@ -35,7 +35,7 @@ def codec_conf() -> Iterator[Any]:
         "numcodecs.delta": "zarr.codecs.numcodecs.Delta",
         "numcodecs.fixedscaleoffset": "zarr.codecs.numcodecs.FixedScaleOffset",
         "numcodecs.fletcher32": "zarr.codecs.numcodecs.Fletcher32",
-        "numcodecs.gZip": "zarr.codecs.numcodecs.GZip",
+        "numcodecs.gzip": "zarr.codecs.numcodecs.GZip",
         "numcodecs.jenkinslookup3": "zarr.codecs.numcodecs.JenkinsLookup3",
         "numcodecs.pcodec": "zarr.codecs.numcodecs.PCodec",
         "numcodecs.packbits": "zarr.codecs.numcodecs.PackBits",

tests/test_config.py

@@ -86,7 +86,7 @@ def test_config_defaults_set() -> None:
                     "numcodecs.delta": "zarr.codecs.numcodecs.Delta",
                     "numcodecs.fixedscaleoffset": "zarr.codecs.numcodecs.FixedScaleOffset",
                     "numcodecs.fletcher32": "zarr.codecs.numcodecs.Fletcher32",
-                    "numcodecs.gZip": "zarr.codecs.numcodecs.GZip",
+                    "numcodecs.gzip": "zarr.codecs.numcodecs.GZip",
                     "numcodecs.jenkins_lookup3": "zarr.codecs.numcodecs.JenkinsLookup3",
                     "numcodecs.pcodec": "zarr.codecs.numcodecs.PCodec",
                     "numcodecs.packbits": "zarr.codecs.numcodecs.PackBits",

tests/test_group.py

@@ -2234,3 +2234,9 @@ def test_get_roots(roots: tuple[str, ...]):
     }
     data = root_nodes | child_nodes
     assert set(_get_roots(data)) == set(roots)
+
+
+def test_open_array_as_group():
+    z = zarr.create_array(shape=(40, 50), chunks=(10, 10), dtype="f8", store={})
+    with pytest.raises(ContainsArrayError):
+        zarr.open_group(z.store)