rename base dtype, change type to kind

d-v-b · Feb 26, 2025 · 5000dcb · 5000dcb
1 parent d74e7a4
commit 5000dcb
Show file tree

Hide file tree

Showing 6 changed files with 130 additions and 105 deletions.
diff --git a/src/zarr/core/_info.py b/src/zarr/core/_info.py
@@ -7,7 +7,7 @@
 
 from zarr.abc.codec import ArrayArrayCodec, ArrayBytesCodec, BytesBytesCodec
 from zarr.core.common import ZarrFormat
-from zarr.core.metadata.dtype import BaseDataType
+from zarr.core.metadata.dtype import DtypeBase
 
 # from zarr.core.metadata.v3 import DataType
 
@@ -80,7 +80,7 @@ class ArrayInfo:
 
     _type: Literal["Array"] = "Array"
     _zarr_format: ZarrFormat
-    _data_type: np.dtype[Any] | BaseDataType
+    _data_type: np.dtype[Any] | DtypeBase
     _shape: tuple[int, ...]
     _shard_shape: tuple[int, ...] | None = None
     _chunk_shape: tuple[int, ...] | None = None

diff --git a/src/zarr/core/array.py b/src/zarr/core/array.py
@@ -98,7 +98,7 @@
     ArrayV3MetadataDict,
     T_ArrayMetadata,
 )
-from zarr.core.metadata.dtype import BaseDataType
+from zarr.core.metadata.dtype import DtypeBase
 from zarr.core.metadata.v2 import (
     _default_compressor,
     _default_filters,
@@ -679,7 +679,7 @@ def _create_metadata_v3(
         """
 
         shape = parse_shapelike(shape)
-        codecs = list(codecs) if codecs is not None else _get_default_codecs(np.dtype(dtype))
+        codecs = list(codecs) if codecs is not None else _get_default_codecs(dtype)
         chunk_key_encoding_parsed: ChunkKeyEncodingLike
         if chunk_key_encoding is None:
             chunk_key_encoding_parsed = {"name": "default", "separator": "/"}
@@ -1684,7 +1684,7 @@ async def info_complete(self) -> Any:
     def _info(
         self, count_chunks_initialized: int | None = None, count_bytes_stored: int | None = None
     ) -> Any:
-        _data_type: np.dtype[Any] | BaseDataType
+        _data_type: np.dtype[Any] | DtypeBase
         if isinstance(self.metadata, ArrayV2Metadata):
             _data_type = self.metadata.dtype
         else:
@@ -4207,9 +4207,9 @@ def _get_default_chunk_encoding_v3(
     """
     dtype = get_data_type_from_numpy(np_dtype)
 
-    default_filters = zarr_config.get("array.v3_default_filters").get(dtype.type)
-    default_serializer = zarr_config.get("array.v3_default_serializer").get(dtype.type)
-    default_compressors = zarr_config.get("array.v3_default_compressors").get(dtype.type)
+    default_filters = zarr_config.get("array.v3_default_filters").get(dtype.kind)
+    default_serializer = zarr_config.get("array.v3_default_serializer").get(dtype.kind)
+    default_compressors = zarr_config.get("array.v3_default_compressors").get(dtype.kind)
 
     filters = tuple(_parse_array_array_codec(codec_dict) for codec_dict in default_filters)
     serializer = _parse_array_bytes_codec(default_serializer)

diff --git a/src/zarr/core/common.py b/src/zarr/core/common.py
@@ -19,7 +19,6 @@
 import numpy as np
 
 from zarr.core.config import config as zarr_config
-from zarr.core.strings import _VLEN_STRING_DTYPE
 
 if TYPE_CHECKING:
     from collections.abc import Awaitable, Callable, Iterator
@@ -167,13 +166,7 @@ def parse_bool(data: Any) -> bool:
     raise ValueError(f"Expected bool, got {data} instead.")
 
 
-def parse_dtype(dtype: Any, zarr_format: ZarrFormat) -> np.dtype[Any]:
-    if dtype is str or dtype == "str":
-        if zarr_format == 2:
-            # special case as object
-            return np.dtype("object")
-        else:
-            return _VLEN_STRING_DTYPE
+def parse_dtype(dtype: Any) -> np.dtype[Any]:
     return np.dtype(dtype)