Skip to content

account for endian being possibly None #787

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Sep 3, 2025
Merged

account for endian being possibly None #787

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
45ccec1
account for `endian` being possibly `None`
keewis Aug 26, 2025
59ef115
check that missing endianness works correctly
keewis Aug 27, 2025
7bcb4f6
expect the exact dtype back
keewis Aug 27, 2025
2145ea4
ignore the mypy error
keewis Aug 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 12 additions & 6 deletions virtualizarr/tests/test_writers/test_kerchunk.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -193,30 +193,36 @@ def test_accessor_to_kerchunk_parquet(self, tmp_path, array_v3_metadata):
}


@pytest.mark.parametrize("endian,expected_dtype_char", [("little", "<"), ("big", ">")])
@pytest.mark.parametrize(
["dtype", "endian", "expected_dtype_char"],
[("i8", "little", "<"), ("i8", "big", ">"), ("i1", None, "|")],
)
def test_convert_v3_to_v2_metadata(
array_v3_metadata, endian: str, expected_dtype_char: str
array_v3_metadata, dtype: str, endian: str | None, expected_dtype_char: str
):
shape = (5, 20)
chunks = (5, 10)

codecs = [
{"name": "bytes", "configuration": {"endian": endian}},
{
"name": "numcodecs.delta",
"configuration": {"dtype": f"{expected_dtype_char}i8"},
"configuration": {"dtype": f"{expected_dtype_char}{dtype}"},
},
{
"name": "numcodecs.blosc",
"configuration": {"cname": "zstd", "clevel": 5, "shuffle": 1},
},
]

v3_metadata = array_v3_metadata(shape=shape, chunks=chunks, codecs=codecs)
v3_metadata = array_v3_metadata(
data_type=np.dtype(dtype), shape=shape, chunks=chunks, codecs=codecs
)
v2_metadata = convert_v3_to_v2_metadata(v3_metadata)

assert isinstance(v2_metadata, ArrayV2Metadata)
assert v2_metadata.shape == shape
expected_dtype = np.dtype(f"{expected_dtype_char}i4") # assuming int32
expected_dtype = np.dtype(f"{expected_dtype_char}{dtype}")
assert v2_metadata.dtype.to_native_dtype() == expected_dtype
assert v2_metadata.chunks == chunks
assert v2_metadata.fill_value == 0
Expand All @@ -232,7 +238,7 @@ def test_convert_v3_to_v2_metadata(

filters_config = filter_codec.get_config()
assert filters_config["id"] == "delta"
expected_delta_dtype = f"{expected_dtype_char}i8"
expected_delta_dtype = f"{expected_dtype_char}{dtype}"
assert filters_config["dtype"] == expected_delta_dtype
assert filters_config["astype"] == expected_delta_dtype
assert v2_metadata.attributes == {}
Expand Down
4 changes: 2 additions & 2 deletions virtualizarr/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,8 +145,8 @@ def convert_v3_to_v2_metadata(
# but other codec pipelines could store endianness elsewhere.
big_endian = any(
isinstance(codec, ArrayBytesCodec)
and hasattr(codec, "endian")
and codec.endian.value == "big"
and getattr(codec, "endian", None) is not None
and codec.endian.value == "big" # type: ignore[attr-defined]
for codec in v3_metadata.codecs
)
if big_endian:
Expand Down