guard against storage_options["chunks"]="" + Change ValueError

Author: ArneDefauw

src/spatialdata/_io/io_raster.py

@@ -40,12 +40,16 @@
 
 
 def _is_flat_int_sequence(value: object) -> TypeGuard[Sequence[int]]:
+    if isinstance(value, str | bytes):
+        return False
     if not isinstance(value, Sequence):
         return False
     return all(isinstance(v, int) for v in value)
 
 
 def _is_dask_chunk_grid(value: object) -> TypeGuard[Sequence[Sequence[int]]]:
+    if isinstance(value, str | bytes):
+        return False
     if not isinstance(value, Sequence):
         return False
     return len(value) > 0 and all(_is_flat_int_sequence(axis_chunks) for axis_chunks in value)
@@ -128,8 +132,10 @@ def _normalize_explicit_chunks(chunks: object) -> tuple[int, ...] | int:
     normalized = _chunks_to_zarr_chunks(chunks)
     if normalized is None:
         raise ValueError(
-            "storage_options['chunks'] must be a Zarr chunk shape or a regular Dask chunk grid. "
-            "Irregular Dask chunk grids must be rechunked before writing or omitted."
+            'storage_options["chunks"] must resolve to a Zarr chunk shape or a regular Dask chunk grid. '
+            "The current raster has irregular Dask chunks, which cannot be written to Zarr. "
+            "To fix this, rechunk before writing, for example by passing regular chunks=... "
+            "to Image2DModel.parse(...) / Labels2DModel.parse(...)."
         )
     return normalized
 

tests/io/test_readwrite.py

@@ -656,7 +656,7 @@ def test_write_irregular_dask_chunks_without_explicit_storage_options(tmp_path:
 
     with pytest.raises(
         ValueError,
-        match="storage_options\\['chunks'\\] must be a Zarr chunk shape or a regular Dask chunk grid",
+        match='storage_options\\["chunks"\\] must resolve to a Zarr chunk shape or a regular Dask chunk grid',
     ):
         sdata.write(tmp_path / "data.zarr")
 
@@ -678,11 +678,58 @@ def test_write_image_rejects_explicit_irregular_dask_chunk_grid(tmp_path: Path)
 
     with pytest.raises(
         ValueError,
-        match="storage_options\\['chunks'\\] must be a Zarr chunk shape or a regular Dask chunk grid",
+        match='storage_options\\["chunks"\\] must resolve to a Zarr chunk shape or a regular Dask chunk grid',
     ):
         write_image(image, group, "image", storage_options={"chunks": image.data.chunks})
 
 
+def test_write_image_normalizes_explicit_zarr_chunk_grid(tmp_path: Path) -> None:
+    data = da.from_array(RNG.random((3, 800, 1000)), chunks=((3,), (300, 200, 300), (512, 488)))
+    image = Image2DModel.parse(data, dims=("c", "y", "x"))
+    group = zarr.open_group(tmp_path / "image.zarr", mode="w")
+
+    zarr_chunks = (3, 100, 512)  # ome zarr rechunks when writing
+    write_image(image, group, "image", storage_options={"chunks": zarr_chunks})
+
+    assert group["s0"].chunks == (3, 100, 512)
+
+
+def test_write_image_rejects_string(tmp_path: Path) -> None:
+    data = da.from_array(RNG.random((3, 800, 1000)), chunks=((3,), (300, 300, 200), (512, 488)))
+    image = Image2DModel.parse(data, dims=("c", "y", "x"))
+    group = zarr.open_group(tmp_path / "image.zarr", mode="w")
+
+    with pytest.raises(
+        ValueError,
+        match='storage_options\\["chunks"\\] must resolve to a Zarr chunk shape or a regular Dask chunk grid',
+    ):
+        write_image(image, group, "image", storage_options={"chunks": "auto"})
+
+
+def test_write_image_rejects_empty_string(tmp_path: Path) -> None:
+    data = da.from_array(RNG.random((3, 800, 1000)), chunks=((3,), (300, 300, 200), (512, 488)))
+    image = Image2DModel.parse(data, dims=("c", "y", "x"))
+    group = zarr.open_group(tmp_path / "image.zarr", mode="w")
+
+    with pytest.raises(
+        ValueError,
+        match='storage_options\\["chunks"\\] must resolve to a Zarr chunk shape or a regular Dask chunk grid',
+    ):
+        write_image(image, group, "image", storage_options={"chunks": ""})
+
+
+def test_write_image_rejects_byte_string(tmp_path: Path) -> None:
+    data = da.from_array(RNG.random((3, 800, 1000)), chunks=((3,), (300, 300, 200), (512, 488)))
+    image = Image2DModel.parse(data, dims=("c", "y", "x"))
+    group = zarr.open_group(tmp_path / "image.zarr", mode="w")
+
+    with pytest.raises(
+        ValueError,
+        match='storage_options\\["chunks"\\] must resolve to a Zarr chunk shape or a regular Dask chunk grid',
+    ):
+        write_image(image, group, "image", storage_options={"chunks": b"auto"})
+
+
 def test_single_scale_image_roundtrip_stays_dataarray(tmp_path: Path) -> None:
     image = Image2DModel.parse(RNG.random((3, 64, 64)), dims=("c", "y", "x"))
     sdata = SpatialData(images={"image": image})