Add codecs, shards to array 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,
@@ -110,6 +129,32 @@ def numpy_arrays(
     return draw(npst.arrays(dtype=dtype, shape=shapes))
 
 
+@st.composite  # type: ignore[misc]
+def chunk_shapes(draw: st.DrawFn, *, shape: tuple[int, ...]) -> tuple[int, ...]:
+    # We want this strategy to shrink towards arrays with smaller number of chunks
+    # 1. st.integers() shrinks towards smaller values. So we use that to generate number of chunks
+    numchunks = draw(
+        st.tuples(*[st.integers(min_value=0 if size == 0 else 1, max_value=size) for size in shape])
+    )
+    # 2. and now generate the chunks tuple
+    return tuple(
+        size // nchunks if nchunks > 0 else 0
+        for size, nchunks in zip(shape, numchunks, strict=True)
+    )
+
+
+@st.composite  # type: ignore[misc]
+def shard_shapes(
+    draw: st.DrawFn, *, shape: tuple[int, ...], chunk_shape: tuple[int, ...]
+) -> tuple[int, ...]:
+    # We want this strategy to shrink towards arrays with smaller number of shards
+    # shards must be an integral number of chunks
+    assert all(c != 0 for c in chunk_shape)
+    numchunks = tuple(s // c for s, c in zip(shape, chunk_shape, strict=True))
+    multiples = tuple(draw(st.integers(min_value=1, max_value=nc)) for nc in numchunks)
+    return tuple(m * c for m, c in zip(multiples, chunk_shape, strict=True))
+
+
 @st.composite  # type: ignore[misc]
 def np_array_and_chunks(
     draw: st.DrawFn, *, arrays: st.SearchStrategy[np.ndarray] = numpy_arrays
@@ -119,32 +164,20 @@ def np_array_and_chunks(
     Returns: a tuple of the array and a suitable random chunking for it.
     """
     array = draw(arrays)
-    # We want this strategy to shrink towards arrays with smaller number of chunks
-    # 1. st.integers() shrinks towards smaller values. So we use that to generate number of chunks
-    numchunks = draw(
-        st.tuples(
-            *[st.integers(min_value=0 if size == 0 else 1, max_value=size) for size in array.shape]
-        )
-    )
-    # 2. and now generate the chunks tuple
-    chunks = tuple(
-        size // nchunks if nchunks > 0 else 0
-        for size, nchunks in zip(array.shape, numchunks, strict=True)
-    )
-    return (array, chunks)
+    return (array, draw(chunk_shapes, array.shape))
 
 
 @st.composite  # type: ignore[misc]
 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)
@@ -154,24 +187,29 @@ def arrays(
     zarr_format = draw(zarr_formats)
     if arrays is None:
         arrays = numpy_arrays(shapes=shapes, zarr_formats=st.just(zarr_format))
-    nparray, chunks = draw(np_array_and_chunks(arrays=arrays))
+    nparray = draw(arrays)
+    chunk_shape = draw(chunk_shapes(shape=nparray.shape))
+    if zarr_format == 3 and all(c > 0 for c in chunk_shape):
+        shard_shape = draw(st.none() | shard_shapes(shape=nparray.shape, chunk_shape=chunk_shape))
+    else:
+        shard_shape = None
     # 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,
+        chunks=chunk_shape,
+        shards=shard_shape,
         dtype=nparray.dtype,
         attributes=attributes,
-        # compressor=compressor,  # FIXME
         fill_value=fill_value,
+        **codec_kwargs,
     )
 
     assert isinstance(a, Array)
@@ -180,7 +218,8 @@ def arrays(
     assert a.name is not None
     assert isinstance(root[array_path], Array)
     assert nparray.shape == a.shape
-    assert chunks == a.chunks
+    assert chunk_shape == a.chunks
+    assert shard_shape == a.shards
     assert array_path == a.path, (path, name, array_path, a.name, a.path)
     assert a.basename == name, (a.basename, name)
     assert dict(a.attrs) == expected_attrs