Skip to content

correct array.nbytes, and add tests #2576

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.

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 3 commits into from
Dec 19, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
24 changes: 20 additions & 4 deletions src/zarr/core/array.py
Original file line number Diff line number Diff line change
Expand Up @@ -977,9 +977,17 @@ def _iter_chunk_regions(
@property
def nbytes(self) -> int:
"""
The number of bytes that can be stored in this array.
The total number of bytes that can be stored in the chunks of this array.

Notes
-----
This value is calculated by multiplying the number of elements in the array and the size
of each element, the latter of which is determined by the dtype of the array.
For this reason, ``nbytes`` will likely be inaccurate for arrays with variable-length
dtypes. It is not possible to determine the size of an array with variable-length elements
from the shape and dtype alone.
"""
return self.nchunks * self.dtype.itemsize
return self.size * self.dtype.itemsize

async def _get_selection(
self,
Expand Down Expand Up @@ -1429,7 +1437,7 @@ def _info(
_order=self.order,
_read_only=self.read_only,
_store_type=type(self.store_path.store).__name__,
_count_bytes=self.dtype.itemsize * self.size,
_count_bytes=self.nbytes,
_count_bytes_stored=count_bytes_stored,
_count_chunks_initialized=count_chunks_initialized,
**kwargs,
Expand Down Expand Up @@ -1740,7 +1748,15 @@ def _iter_chunk_coords(
@property
def nbytes(self) -> int:
"""
The number of bytes that can be stored in this array.
The total number of bytes that can be stored in the chunks of this array.

Notes
-----
This value is calculated by multiplying the number of elements in the array and the size
of each element, the latter of which is determined by the dtype of the array.
For this reason, ``nbytes`` will likely be inaccurate for arrays with variable-length
dtypes. It is not possible to determine the size of an array with variable-length elements
from the shape and dtype alone.
"""
return self._async_array.nbytes

Expand Down
18 changes: 18 additions & 0 deletions tests/test_array.py
Original file line number Diff line number Diff line change
Expand Up @@ -776,3 +776,21 @@ async def test_special_complex_fill_values_roundtrip(fill_value: Any, expected:
assert content is not None
actual = json.loads(content.to_bytes())
assert actual["fill_value"] == expected


@pytest.mark.parametrize("shape", [(1,), (2, 3), (4, 5, 6)])
@pytest.mark.parametrize("dtype", ["uint8", "float32"])
@pytest.mark.parametrize("array_type", ["async", "sync"])
async def test_nbytes(
shape: tuple[int, ...], dtype: str, array_type: Literal["async", "sync"]
) -> None:
"""
Test that the ``nbytes`` attribute of an Array or AsyncArray correctly reports the capacity of
the chunks of that array.
"""
store = MemoryStore()
arr = Array.create(store=store, shape=shape, dtype=dtype, fill_value=0)
if array_type == "async":
assert arr._async_array.nbytes == np.prod(arr.shape) * arr.dtype.itemsize
else:
assert arr.nbytes == np.prod(arr.shape) * arr.dtype.itemsize
Loading