Try with zarr main

Author: dstansby

docs/usage_zarr_v2.md

@@ -46,7 +46,7 @@ print(spec.model_dump())
             'order': 'C',
             'filters': [],
             'dimension_separator': '.',
-            'compressor': {'id': 'zstd', 'level': 0, 'checksum': False},
+            'compressor': None,
         }
     },
 }
@@ -90,7 +90,7 @@ print(ArraySpec.from_array(np.arange(10)).model_dump())
     'dtype': '<i8',
     'fill_value': 0,
     'order': 'C',
-    'filters': None,
+    'filters': [],
     'dimension_separator': '/',
     'compressor': None,
 }
@@ -143,7 +143,7 @@ print(GroupSpec.from_flat(tree).model_dump())
                     'dtype': '|u1',
                     'fill_value': 0,
                     'order': 'C',
-                    'filters': None,
+                    'filters': [],
                     'dimension_separator': '/',
                     'compressor': None,
                 }
@@ -183,7 +183,7 @@ print(root.to_flat())
         dtype='|u1',
         fill_value=0,
         order='C',
-        filters=None,
+        filters=[],
         dimension_separator='/',
         compressor=None,
     ),
@@ -223,7 +223,7 @@ print(GroupSpec.from_flat(tree).model_dump())
                             'dtype': '|u1',
                             'fill_value': 0,
                             'order': 'C',
-                            'filters': None,
+                            'filters': [],
                             'dimension_separator': '/',
                             'compressor': None,
                         }
@@ -269,15 +269,15 @@ arr_a_stored = arr_a.to_zarr(store, path='arr_a')
 
 # arr_a is like the zarr.Array version of itself
 print(arr_a.like(arr_a_stored))
-#> False
+#> True
 
 # Returns False, because of mismatched shape
 print(arr_b.like(arr_a_stored))
 #> False
 
 # Returns True, because we exclude shape.
 print(arr_b.like(arr_a_stored, exclude={'shape'}))
-#> False
+#> True
 
 # The same thing, but for groups
 g_a = GroupSpec(attributes={'foo': 10}, members={'a': arr_a, 'b': arr_b})
@@ -297,7 +297,7 @@ print(g_a.like(g_b, exclude={'attributes'}))
 
 # g_a is like its zarr.Group counterpart
 print(g_a.like(g_a.to_zarr(store, path='g_a')))
-#> False
+#> True
 ```
 
 ## Using generic types
@@ -376,7 +376,7 @@ print(ArraysOnlyGroup(attributes={}, members=items).model_dump())
             'dtype': '|u1',
             'fill_value': 0,
             'order': 'C',
-            'filters': None,
+            'filters': [],
             'dimension_separator': '/',
             'compressor': None,
         }

pyproject.toml

@@ -23,7 +23,10 @@ classifiers = [
   "Programming Language :: Python :: 3.12",
   "Programming Language :: Python :: Implementation :: CPython",
 ]
-dependencies = ["zarr>=3", "pydantic>2.0.0"]
+dependencies = [
+    "zarr@git+https://github.com/zarr-developers/zarr-python.git@main",
+    "pydantic>2.0.0",
+]
 
 [project.urls]
 Documentation = "https://zarr.dev/pydantic-zarr/"
@@ -49,6 +52,9 @@ docs = [
 version.source = "vcs"
 build.hooks.vcs.version-file = "src/pydantic_zarr/_version.py"
 
+[tool.hatch.metadata]
+allow-direct-references = true
+
 [tool.hatch.envs.test]
 features = ["test"]
 

src/pydantic_zarr/v2.py

@@ -20,7 +20,7 @@
 import numpy.typing as npt
 import zarr
 from numcodecs.abc import Codec
-from pydantic import AfterValidator, model_validator
+from pydantic import AfterValidator, Field, model_validator
 from pydantic.functional_validators import BeforeValidator
 from zarr.abc.store import Store
 from zarr.core.sync_group import get_node
@@ -174,7 +174,7 @@ class ArraySpec(NodeSpec, Generic[TAttr]):
     dtype: DtypeStr
     fill_value: int | float | None = 0
     order: Literal["C", "F"] = "C"
-    filters: list[CodecDict] | None = None
+    filters: list[CodecDict] = Field(default=[])
     dimension_separator: Annotated[
         Literal["/", "."], BeforeValidator(parse_dimension_separator)
     ] = "/"
@@ -247,7 +247,7 @@ def from_array(
         >>> import numpy as np
         >>> x = ArraySpec.from_array(np.arange(10))
         >>> x
-        ArraySpec(zarr_version=2, attributes={}, shape=(10,), chunks=(10,), dtype='<i8', fill_value=0, order='C', filters=None, dimension_separator='/', compressor=None)
+        ArraySpec(zarr_version=2, attributes={}, shape=(10,), chunks=(10,), dtype='<i8', fill_value=0, order='C', filters=[], dimension_separator='/', compressor=None)
 
 
         """
@@ -321,7 +321,7 @@ def from_zarr(cls, array: zarr.Array) -> Self:
         >>> from pydantic_zarr.v2 import ArraySpec
         >>> x = zarr.create((10,10))
         >>> ArraySpec.from_zarr(x)
-        ArraySpec(zarr_version=2, attributes={}, shape=(10, 10), chunks=(10, 10), dtype='<f8', fill_value=0.0, order='C', filters=None, dimension_separator='.', compressor={'id': 'blosc', 'cname': 'lz4', 'clevel': 5, 'shuffle': 1, 'blocksize': 0})
+        ArraySpec(zarr_version=2, attributes={}, shape=(10, 10), chunks=(10, 10), dtype='<f8', fill_value=0.0, order='C', filters=[], dimension_separator='.', compressor={'id': 'blosc', 'cname': 'lz4', 'clevel': 5, 'shuffle': 1, 'blocksize': 0})
 
         """
         return cls(
@@ -334,7 +334,7 @@ def from_zarr(cls, array: zarr.Array) -> Self:
             order=array.order,
             filters=array.filters,
             dimension_separator=array.metadata.dimension_separator,
-            compressor=array.compressors[0].get_config(),
+            compressor=array.compressors[0].get_config() if len(array.compressors) else None,
             attributes=array.attrs.asdict(),
         )
 
@@ -717,7 +717,7 @@ def from_flat(cls, data: dict[str, ArraySpec | GroupSpec]) -> Self:
             '': GroupSpec(attributes={'foo': 10}, members=None),
             '/a': ArraySpec.from_array(np.arange(10))}
         >>> GroupSpec.from_flat(flat)
-        GroupSpec(zarr_version=2, attributes={'foo': 10}, members={'a': ArraySpec(zarr_version=2, attributes={}, shape=(10,), chunks=(10,), dtype='<i8', fill_value=0, order='C', filters=None, dimension_separator='/', compressor=None)})
+        GroupSpec(zarr_version=2, attributes={'foo': 10}, members={'a': ArraySpec(zarr_version=2, attributes={}, shape=(10,), chunks=(10,), dtype='<i8', fill_value=0, order='C', filters=[], dimension_separator='/', compressor=None)})
         """
         from_flated = from_flat_group(data)
         return cls(**from_flated.model_dump())
@@ -895,7 +895,7 @@ def from_flat(data: dict[str, ArraySpec | GroupSpec]) -> ArraySpec | GroupSpec:
     ArraySpec(zarr_version=2, attributes={}, shape=(10,), chunks=(10,), dtype='<i8', fill_value=0, order='C', filters=[], dimension_separator='/', compressor=None)
     >>> tree = {'/foo': ArraySpec.from_array(np.arange(10))}
     >>> from_flat(tree) # note that an implicit Group is created
-    GroupSpec(zarr_version=2, attributes={}, members={'foo': ArraySpec(zarr_version=2, attributes={}, shape=(10,), chunks=(10,), dtype='<i8', fill_value=0, order='C', filters=None, dimension_separator='/', compressor=None)})
+    GroupSpec(zarr_version=2, attributes={}, members={'foo': ArraySpec(zarr_version=2, attributes={}, shape=(10,), chunks=(10,), dtype='<i8', fill_value=0, order='C', filters=[], dimension_separator='/', compressor=None)})
     """
 
     # minimal check that the keys are valid
@@ -934,7 +934,7 @@ def from_flat_group(data: dict[str, ArraySpec | GroupSpec]) -> GroupSpec:
     >>> import numpy as np
     >>> tree = {'/foo': ArraySpec.from_array(np.arange(10))}
     >>> from_flat_group(tree) # note that an implicit Group is created
-    GroupSpec(zarr_version=2, attributes={}, members={'foo': ArraySpec(zarr_version=2, attributes={}, shape=(10,), chunks=(10,), dtype='<i8', fill_value=0, order='C', filters=None, dimension_separator='/', compressor=None)})
+    GroupSpec(zarr_version=2, attributes={}, members={'foo': ArraySpec(zarr_version=2, attributes={}, shape=(10,), chunks=(10,), dtype='<i8', fill_value=0, order='C', filters=[], dimension_separator='/', compressor=None)})
     """
     root_name = ""
     sep = "/"
@@ -1034,13 +1034,13 @@ def auto_compresser(data: Any) -> Codec | None:
     return None
 
 
-def auto_filters(data: Any) -> list[Codec] | None:
+def auto_filters(data: Any) -> list[Codec]:
     """
     Guess filters from an input with a `filters` attribute, returning `None` otherwise.
     """
     if hasattr(data, "filters"):
         return data.filters
-    return None
+    return []
 
 
 def auto_order(data: Any) -> Literal["C", "F"]:

tests/test_pydantic_zarr/test_v2.py

@@ -134,10 +134,10 @@ def test_array_spec(
     # the correct approach would be to use an empty list to express "no filters".
     assert spec.filters == [f.get_config() for f in array.filters]
 
-    if array.compressors is not None:
+    if len(array.compressors):
         assert spec.compressor == array.compressors[0].get_config()
     else:
-        assert spec.compressor == array.compressors[0]
+        assert spec.compressor is None
 
     assert spec.order == array.order
 
@@ -148,10 +148,10 @@ def test_array_spec(
     assert spec.attributes == array2.attrs
     assert spec.chunks == array2.chunks
 
-    if array2.compressors is not None:
+    if len(array2.compressors):
         assert spec.compressor == array2.compressors[0].get_config()
     else:
-        assert spec.compressor == array2.compressors[0]
+        assert spec.compressor is None
 
     if array2.filters is not None:
         assert spec.filters == [f.get_config() for f in array2.filters]
@@ -584,6 +584,8 @@ def test_array_like_with_zarr() -> None:
     arr = ArraySpec(shape=(1,), dtype="uint8", chunks=(1,))
     store = zarr.storage.MemoryStore()
     arr_stored = arr.to_zarr(store, path="arr")
+    print(arr)
+    print(ArraySpec.from_zarr(arr_stored))
     assert arr.like(arr_stored)