add ArrayConfig

Author: normanrz

src/zarr/api/asynchronous.py

@@ -16,6 +16,7 @@
     ChunkCoords,
     MemoryOrder,
     ZarrFormat,
+    _warn_order_kwarg,
     _warn_write_empty_chunks_kwarg,
 )
 from zarr.core.config import config
@@ -725,6 +726,7 @@ async def create(
     read_only: bool | None = None,
     object_codec: Codec | None = None,  # TODO: type has changed
     dimension_separator: Literal[".", "/"] | None = None,
+    write_empty_chunks: bool | None = None,
     zarr_version: ZarrFormat | None = None,  # deprecated
     zarr_format: ZarrFormat | None = None,
     meta_array: Any | None = None,  # TODO: need type
@@ -760,6 +762,7 @@ async def create(
     fill_value : object
         Default value to use for uninitialized portions of the array.
     order : {'C', 'F'}, optional
+        Deprecated in favor of the `array.order` configuration variable.
         Memory layout to be used within each chunk.
         Default is set in Zarr's config (`array.order`).
     store : Store or str
@@ -794,6 +797,19 @@ async def create(
 
         .. versionadded:: 2.8
 
+    write_empty_chunks : bool, optional
+        Deprecated in favor of the `array.write_empty_chunks` configuration variable.
+
+        If True (default), all chunks will be stored regardless of their
+        contents. If False, each chunk is compared to the array's fill value
+        prior to storing. If a chunk is uniformly equal to the fill value, then
+        that chunk is not be stored, and the store entry for that chunk's key
+        is deleted. This setting enables sparser storage, as only chunks with
+        non-fill-value data are stored, at the expense of overhead associated
+        with checking the data of each chunk.
+
+        .. versionadded:: 2.11
+
     zarr_format : {2, 3, None}, optional
         The zarr format to use when saving.
     meta_array : array-like, optional
@@ -839,17 +855,11 @@ async def create(
             raise ValueError(
                 "dimension_separator is not supported for zarr format 3, use chunk_key_encoding instead"
             )
-        else:
-            warnings.warn(
-                "dimension_separator is not yet implemented",
-                RuntimeWarning,
-                stacklevel=2,
-            )
 
-    if "write_empty_chunks" in kwargs:
-        # warn users if the write_empty_chunks kwarg was used
-        write_empty_chunks = kwargs.pop("write_empty_chunks")
-        _warn_write_empty_chunks_kwarg(write_empty_chunks)
+    if order is not None:
+        _warn_order_kwarg()
+    if write_empty_chunks is not None:
+        _warn_write_empty_chunks_kwarg()
 
     if meta_array is not None:
         warnings.warn("meta_array is not yet implemented", RuntimeWarning, stacklevel=2)
@@ -878,6 +888,7 @@ async def create(
         dimension_names=dimension_names,
         attributes=attributes,
         order=order,
+        write_empty_chunks=write_empty_chunks,
         **kwargs,
     )
 
@@ -1051,10 +1062,10 @@ async def open_array(
 
     zarr_format = _handle_zarr_version_or_format(zarr_version=zarr_version, zarr_format=zarr_format)
 
+    if "order" in kwargs:
+        _warn_order_kwarg()
     if "write_empty_chunks" in kwargs:
-        # warn users if the write_empty_chunks kwarg was used
-        write_empty_chunks = kwargs.pop("write_empty_chunks")
-        _warn_write_empty_chunks_kwarg(write_empty_chunks)
+        _warn_write_empty_chunks_kwarg()
 
     try:
         return await AsyncArray.open(store_path, zarr_format=zarr_format)

src/zarr/codecs/pipeline.py

@@ -331,7 +331,6 @@ async def write_batch(
         value: NDBuffer,
         drop_axes: tuple[int, ...] = (),
     ) -> None:
-        write_empty_chunks = config.get("array.write_empty_chunks") == True  # noqa: E712
         if self.supports_partial_encode:
             await self.encode_partial_batch(
                 [
@@ -385,7 +384,9 @@ async def _read_key(
                 if chunk_array is None:
                     chunk_array_batch.append(None)  # type: ignore[unreachable]
                 else:
-                    if not write_empty_chunks and chunk_array.all_equal(chunk_spec.fill_value):
+                    if not chunk_spec.config.write_empty_chunks and chunk_array.all_equal(
+                        chunk_spec.fill_value
+                    ):
                         chunk_array_batch.append(None)
                     else:
                         chunk_array_batch.append(chunk_array)

src/zarr/codecs/sharding.py

@@ -20,7 +20,7 @@
 from zarr.abc.store import ByteGetter, ByteRangeRequest, ByteSetter
 from zarr.codecs.bytes import BytesCodec
 from zarr.codecs.crc32c_ import Crc32cCodec
-from zarr.core.array_spec import ArraySpec
+from zarr.core.array_spec import ArrayConfig, ArraySpec
 from zarr.core.buffer import (
     Buffer,
     BufferPrototype,
@@ -665,7 +665,9 @@ def _get_index_chunk_spec(self, chunks_per_shard: ChunkCoords) -> ArraySpec:
             shape=chunks_per_shard + (2,),
             dtype=np.dtype("<u8"),
             fill_value=MAX_UINT_64,
-            order="C",  # Note: this is hard-coded for simplicity -- it is not surfaced into user code
+            config=ArrayConfig(
+                order="C", write_empty_chunks=False
+            ),  # Note: this is hard-coded for simplicity -- it is not surfaced into user code,
             prototype=numpy_buffer_prototype(),
         )
 
@@ -674,7 +676,7 @@ def _get_chunk_spec(self, shard_spec: ArraySpec) -> ArraySpec:
             shape=self.chunk_shape,
             dtype=shard_spec.dtype,
             fill_value=shard_spec.fill_value,
-            order=shard_spec.order,
+            config=shard_spec.config,
             prototype=shard_spec.prototype,
         )
 

src/zarr/codecs/transpose.py

@@ -84,7 +84,7 @@ def resolve_metadata(self, chunk_spec: ArraySpec) -> ArraySpec:
             shape=tuple(chunk_spec.shape[self.order[i]] for i in range(chunk_spec.ndim)),
             dtype=chunk_spec.dtype,
             fill_value=chunk_spec.fill_value,
-            order=chunk_spec.order,
+            config=chunk_spec.config,
             prototype=chunk_spec.prototype,
         )