rename array_bytes_codec to serializer

Author: normanrz

src/zarr/api/synchronous.py

@@ -19,9 +19,9 @@
     from zarr.abc.codec import Codec
     from zarr.api.asynchronous import ArrayLike, PathLike
     from zarr.core.array import (
-        ArrayBytesCodecParam,
         CompressorsParam,
         FiltersParam,
+        SerializerParam,
         ShardsParam,
     )
     from zarr.core.array_spec import ArrayConfig, ArrayConfigParams
@@ -748,7 +748,7 @@ def create_array(
     shards: ShardsParam | None = None,
     filters: FiltersParam | None = "auto",
     compressors: CompressorsParam = "auto",
-    array_bytes_codec: ArrayBytesCodecParam = "auto",
+    serializer: SerializerParam = "auto",
     fill_value: Any | None = None,
     order: MemoryOrder | None = None,
     zarr_format: ZarrFormat | None = 3,
@@ -814,10 +814,10 @@ def create_array(
         These defaults can be changed by modifying the value of ``array.v2_default_compressor``
         in :mod:`zarr.core.config`.
         Use ``None`` to omit the default compressor.
-    array_bytes_codec : dict[str, JSON] | ArrayBytesCodec, optional
+    serializer : dict[str, JSON] | ArrayBytesCodec, optional
         Array-to-bytes codec to use for encoding the array data.
         Zarr v3 only. Zarr v2 arrays use implicit array-to-bytes conversion.
-        If no ``array_bytes_codec`` is provided, the `zarr.codecs.BytesCodec` codec will be used.
+        If no ``serializer`` is provided, the `zarr.codecs.BytesCodec` codec will be used.
     fill_value : Any, optional
         Fill value for the array.
     order : {"C", "F"}, optional
@@ -875,7 +875,7 @@ def create_array(
                 shards=shards,
                 filters=filters,
                 compressors=compressors,
-                array_bytes_codec=array_bytes_codec,
+                serializer=serializer,
                 fill_value=fill_value,
                 order=order,
                 zarr_format=zarr_format,

src/zarr/core/array.py

@@ -3643,7 +3643,7 @@ def _get_default_codecs(
     | Literal["auto"]
     | None
 )
-ArrayBytesCodecParam: TypeAlias = dict[str, JSON] | ArrayBytesCodec | Literal["auto"]
+SerializerParam: TypeAlias = dict[str, JSON] | ArrayBytesCodec | Literal["auto"]
 
 
 class ShardsConfigParam(TypedDict):
@@ -3664,7 +3664,7 @@ async def create_array(
     shards: ShardsParam | None = None,
     filters: FiltersParam | None = "auto",
     compressors: CompressorsParam = "auto",
-    array_bytes_codec: ArrayBytesCodecParam = "auto",
+    serializer: SerializerParam = "auto",
     fill_value: Any | None = None,
     order: MemoryOrder | None = None,
     zarr_format: ZarrFormat | None = 3,
@@ -3730,10 +3730,10 @@ async def create_array(
         These defaults can be changed by modifying the value of ``array.v2_default_compressor``
         in :mod:`zarr.core.config`.
         Use ``None`` to omit the default compressor.
-    array_bytes_codec : dict[str, JSON] | ArrayBytesCodec, optional
+    serializer : dict[str, JSON] | ArrayBytesCodec, optional
         Array-to-bytes codec to use for encoding the array data.
         Zarr v3 only. Zarr v2 arrays use implicit array-to-bytes conversion.
-        If no ``array_bytes_codec`` is provided, the `zarr.codecs.BytesCodec` codec will be used.
+        If no ``serializer`` is provided, the `zarr.codecs.BytesCodec` codec will be used.
     fill_value : Any, optional
         Fill value for the array.
     order : {"C", "F"}, optional
@@ -3808,8 +3808,8 @@ async def create_array(
             )
 
             raise ValueError(msg)
-        if array_bytes_codec != "auto":
-            raise ValueError("Zarr v2 arrays do not support `array_bytes_codec`.")
+        if serializer != "auto":
+            raise ValueError("Zarr v2 arrays do not support `serializer`.")
 
         filters_parsed, compressor_parsed = _parse_chunk_encoding_v2(
             compressor=compressors, filters=filters, dtype=np.dtype(dtype)
@@ -3840,7 +3840,7 @@ async def create_array(
         array_array, array_bytes, bytes_bytes = _parse_chunk_encoding_v3(
             compressors=compressors,
             filters=filters,
-            array_bytes_codec=array_bytes_codec,
+            serializer=serializer,
             dtype=dtype_parsed,
         )
         sub_codecs = cast(tuple[Codec, ...], (*array_array, array_bytes, *bytes_bytes))
@@ -4017,7 +4017,7 @@ def _parse_chunk_encoding_v3(
     *,
     compressors: CompressorsParam | None,
     filters: FiltersParam | None,
-    array_bytes_codec: ArrayBytesCodecParam,
+    serializer: SerializerParam,
     dtype: np.dtype[Any],
 ) -> tuple[tuple[ArrayArrayCodec, ...], ArrayBytesCodec, tuple[BytesBytesCodec, ...]]:
     """
@@ -4058,9 +4058,9 @@ def _parse_chunk_encoding_v3(
             maybe_array_array = cast(Iterable[Codec | dict[str, JSON]], filters)
         out_array_array = tuple(_parse_array_array_codec(c) for c in maybe_array_array)
 
-    if array_bytes_codec == "auto":
+    if serializer == "auto":
         out_array_bytes = default_array_bytes
     else:
-        out_array_bytes = _parse_array_bytes_codec(array_bytes_codec)
+        out_array_bytes = _parse_array_bytes_codec(serializer)
 
     return out_array_array, out_array_bytes, out_bytes_bytes

tests/test_array.py

@@ -461,7 +461,7 @@ def test_vlen_errors() -> None:
         match="For string dtype, ArrayBytesCodec must be `VLenUTF8Codec`, got `BytesCodec`.",
     ):
         zarr.create_array(
-            MemoryStore(), shape=(5,), chunks=(5,), dtype="<U4", array_bytes_codec=BytesCodec()
+            MemoryStore(), shape=(5,), chunks=(5,), dtype="<U4", serializer=BytesCodec()
         )
 
 
@@ -1084,7 +1084,7 @@ async def test_create_array_v3_chunk_encoding(
         compressors=compressors,
     )
     aa_codecs_expected, _, bb_codecs_expected = _parse_chunk_encoding_v3(
-        filters=filters, compressors=compressors, array_bytes_codec="auto", dtype=np.dtype(dtype)
+        filters=filters, compressors=compressors, serializer="auto", dtype=np.dtype(dtype)
     )
     # TODO: find a better way to get the filters / compressors from the array.
     assert arr.codec_pipeline.array_array_codecs == aa_codecs_expected  # type: ignore[attr-defined]

tests/test_codecs/test_codecs.py

@@ -372,7 +372,7 @@ def test_invalid_metadata_create_array(store: Store) -> None:
             chunks=(16, 16),
             dtype=np.dtype("uint8"),
             fill_value=0,
-            array_bytes_codec=ShardingCodec(chunk_shape=(8, 8)),
+            serializer=ShardingCodec(chunk_shape=(8, 8)),
             compressors=[
                 GzipCodec(),
             ],

tests/test_codecs/test_endian.py

@@ -24,7 +24,7 @@ async def test_endian(store: Store, endian: Literal["big", "little"]) -> None:
         dtype=data.dtype,
         fill_value=0,
         chunk_key_encoding={"name": "v2", "separator": "."},
-        array_bytes_codec=BytesCodec(endian=endian),
+        serializer=BytesCodec(endian=endian),
     )
 
     await _AsyncArrayProxy(a)[:, :].set(data)
@@ -50,7 +50,7 @@ async def test_endian_write(
         dtype="uint16",
         fill_value=0,
         chunk_key_encoding={"name": "v2", "separator": "."},
-        array_bytes_codec=BytesCodec(endian=dtype_store_endian),
+        serializer=BytesCodec(endian=dtype_store_endian),
     )
 
     await _AsyncArrayProxy(a)[:, :].set(data)

tests/test_codecs/test_sharding.py

@@ -280,7 +280,7 @@ def test_nested_sharding_create_array(
         chunks=(32, 32, 32),
         dtype=data.dtype,
         fill_value=0,
-        array_bytes_codec=ShardingCodec(
+        serializer=ShardingCodec(
             chunk_shape=(32, 32, 32),
             codecs=[ShardingCodec(chunk_shape=(16, 16, 16), index_location=inner_index_location)],
             index_location=outer_index_location,