implement config-sensitive write_empty_chunks in write_batch, and add a test

Author: d-v-b

src/zarr/codecs/pipeline.py

@@ -361,7 +361,7 @@ async def _read_key(
                 _read_key,
                 config.get("async.concurrency"),
             )
-            chunk_array_batch = await self.decode_batch(
+            chunk_array_decoded = await self.decode_batch(
                 [
                     (chunk_bytes, chunk_spec)
                     for chunk_bytes, (_, chunk_spec, _, _) in zip(
@@ -370,19 +370,20 @@ async def _read_key(
                 ],
             )
 
-            chunk_array_batch = [
+            chunk_array_merged = [
                 self._merge_chunk_array(
                     chunk_array, value, out_selection, chunk_spec, chunk_selection, drop_axes
                 )
                 for chunk_array, (_, chunk_spec, chunk_selection, out_selection) in zip(
-                    chunk_array_batch, batch_info, strict=False
+                    chunk_array_decoded, batch_info, strict=False
                 )
             ]
+            chunk_array_batch: list[NDBuffer | None] = []
             for chunk_array, (_, chunk_spec, _, _) in zip(
-                chunk_array_batch, batch_info, strict=False
+                chunk_array_merged, batch_info, strict=False
             ):
                 if chunk_array is None:
-                    chunk_array_batch.append(None)
+                    chunk_array_batch.append(None)  # type: ignore[unreachable]
                 else:
                     if not write_empty_chunks and chunk_array.all_equal(chunk_spec.fill_value):
                         chunk_array_batch.append(None)

tests/test_array.py

@@ -11,6 +11,7 @@
 from zarr.core.array import chunks_initialized
 from zarr.core.buffer.cpu import NDBuffer
 from zarr.core.common import JSON, MemoryOrder, ZarrFormat
+from zarr.core.config import config
 from zarr.core.group import AsyncGroup
 from zarr.core.indexing import ceildiv
 from zarr.core.sync import sync
@@ -436,3 +437,22 @@ def test_array_create_order(
         assert vals.flags.f_contiguous
     else:
         raise AssertionError
+
+
+@pytest.mark.parametrize("store", ["memory"], indirect=True)
+@pytest.mark.parametrize("write_empty_chunks", [True, False])
+@pytest.mark.parametrize("fill_value", [0, 5])
+def test_write_empty_chunks(
+    zarr_format: ZarrFormat, store: MemoryStore, write_empty_chunks: bool, fill_value: int
+) -> None:
+    arr = Array.create(
+        store=store, shape=(1,), zarr_format=zarr_format, dtype="i4", fill_value=fill_value
+    )
+
+    with config.set({"array.write_empty_chunks": write_empty_chunks}):
+        arr[:] = fill_value
+
+    if not write_empty_chunks:
+        assert arr.nchunks_initialized == 0
+    else:
+        assert arr.nchunks_initialized == arr.nchunks