Add compressor, codec pipeline strategy

Author: dcherian

src/zarr/testing/strategies.py

@@ -1,5 +1,5 @@
 import sys
-from typing import Any
+from typing import Any, Literal
 
 import hypothesis.extra.numpy as npst
 import hypothesis.strategies as st
@@ -86,11 +86,30 @@ def safe_unicode_for_dtype(dtype: np.dtype[np.str_]) -> st.SearchStrategy[str]:
 # i.e. stores.examples() will always return the same object per Store class.
 # So we map a clear to reset the store.
 stores = st.builds(MemoryStore, st.just({})).map(lambda x: sync(x.clear()))
-compressors = st.sampled_from([None, "default"])
 zarr_formats: st.SearchStrategy[ZarrFormat] = st.sampled_from([2, 3])
 array_shapes = npst.array_shapes(max_dims=4, min_side=0)
 
 
+@st.composite  # type: ignore[misc]
+def codecs(
+    draw: st.DrawFn,
+    *,
+    zarr_formats: st.SearchStrategy[Literal[2, 3]] = zarr_formats,
+    dtypes: st.SearchStrategy[np.dtype] | None = None,
+) -> Any:
+    zarr_format = draw(zarr_formats)
+    codec_kwargs = {"filters": draw(st.none() | st.just(()))}
+    zarr_codecs = st.one_of(
+        st.builds(zarr.codecs.ZstdCodec, level=st.integers(min_value=0, max_value=9)),
+        # TODO: other codecs
+    )
+    if zarr_format == 2:
+        codec_kwargs["compressors"] = draw(st.none() | st.just(()))
+    else:
+        codec_kwargs["compressors"] = draw(st.none() | st.just(()) | zarr_codecs)
+    return codec_kwargs
+
+
 @st.composite  # type: ignore[misc]
 def numpy_arrays(
     draw: st.DrawFn,
@@ -139,12 +158,12 @@ def arrays(
     draw: st.DrawFn,
     *,
     shapes: st.SearchStrategy[tuple[int, ...]] = array_shapes,
-    compressors: st.SearchStrategy = compressors,
     stores: st.SearchStrategy[StoreLike] = stores,
     paths: st.SearchStrategy[str | None] = paths,
     array_names: st.SearchStrategy = array_names,
     arrays: st.SearchStrategy | None = None,
     attrs: st.SearchStrategy = attrs,
+    codecs: st.SearchStrategy = codecs,
     zarr_formats: st.SearchStrategy = zarr_formats,
 ) -> Array:
     store = draw(stores)
@@ -157,21 +176,20 @@ def arrays(
     nparray, chunks = draw(np_array_and_chunks(arrays=arrays))
     # test that None works too.
     fill_value = draw(st.one_of([st.none(), npst.from_dtype(nparray.dtype)]))
-    # compressor = draw(compressors)
 
     expected_attrs = {} if attributes is None else attributes
 
     array_path = _dereference_path(path, name)
     root = zarr.open_group(store, mode="w", zarr_format=zarr_format)
-
+    codec_kwargs = draw(codecs(zarr_formats=st.just(zarr_format), dtypes=st.just(nparray.dtype)))
     a = root.create_array(
         array_path,
         shape=nparray.shape,
         chunks=chunks,
         dtype=nparray.dtype,
         attributes=attributes,
-        # compressor=compressor,  # FIXME
         fill_value=fill_value,
+        **codec_kwargs,
     )
 
     assert isinstance(a, Array)