Skip to content
Open
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
5 changes: 5 additions & 0 deletions doc/whats-new.rst
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,11 @@ New Features
Breaking Changes
~~~~~~~~~~~~~~~~

- Change the default value for ``chunk`` in ``open_zarr`` to ``_default`` and remove special mapping of ``"auto"``
to ``{}`` or ``None`` in ``open_zarr``. If ``chunks`` is not set, the default behavior is the same as before.
Explicitly setting ``chunks="auto"`` will match the behavior of ``chunks="auto"`` in
``open_dataset(..., engine="zarr")`` (:issue:`11002` :pull:`11010`).
By `Julia Signell <https://github.com/jsignell>`_.
- :py:meth:`Dataset.identical`,` :py:meth:`DataArray.identical`, and
:py:func:`testings.assert_identical` now compare indexes (xindexes).
Two objects with identical data but different indexes will no longer
Expand Down
10 changes: 6 additions & 4 deletions xarray/backends/zarr.py
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@
from xarray.core.utils import (
FrozenDict,
HiddenKeyDict,
_default,
attempt_import,
close_on_error,
emit_user_level_warning,
Expand Down Expand Up @@ -1400,7 +1401,7 @@ def open_zarr(
store,
group=None,
synchronizer=None,
chunks="auto",
chunks=_default,
decode_cf=True,
mask_and_scale=True,
decode_times=True,
Expand Down Expand Up @@ -1436,8 +1437,9 @@ def open_zarr(
Array synchronizer provided to zarr
group : str, optional
Group path. (a.k.a. `path` in zarr terminology.)
chunks : int, dict, 'auto' or None, default: 'auto'
If provided, used to load the data into dask arrays.
chunks : int, dict, "auto" or None, optional
Used to load the data into dask arrays. Default behavior is to use
``chunks={}`` if dask is available, otherwise ``chunks=None``.

- ``chunks='auto'`` will use dask ``auto`` chunking taking into account the
engine preferred chunks.
Expand Down Expand Up @@ -1558,7 +1560,7 @@ def open_zarr(
if from_array_kwargs is None:
from_array_kwargs = {}

if chunks == "auto":
if chunks is _default:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

let's issue a DeprecationWarning saying the default will switch to chunks=None to match open_dataset. If they want the current behaviour with dask et al, users should pass in chunks={}

try:
guess_chunkmanager(
chunked_array_type
Expand Down
12 changes: 12 additions & 0 deletions xarray/tests/test_backends.py
Original file line number Diff line number Diff line change
Expand Up @@ -3637,6 +3637,18 @@
) as ds1:
assert_equal(ds1, original)

@requires_dask
def test_chunk_auto_with_small_dask_chunks(self) -> None:
original = Dataset({"u": (("x",), np.zeros(10))}).chunk({"x": 2})
with self.create_zarr_target() as store:
original.to_zarr(store, **self.version_kwargs)
with xr.open_zarr(store, **self.version_kwargs) as default:
assert default.chunks == {"x": (2, 2, 2, 2, 2)}
with xr.open_zarr(store, chunks="auto", **self.version_kwargs) as auto:
assert_identical(auto, original)
assert auto.chunks == {"x": (10,)}
assert auto.chunks != default.chunks

@requires_cftime
def test_open_zarr_use_cftime(self) -> None:
ds = create_test_data()
Expand Down Expand Up @@ -6574,7 +6586,7 @@
session.cache.clear()
url = "https://test.opendap.org/opendap/hyrax/data/nc/coads_climatology.nc"

ds = open_dataset(

Check failure on line 6589 in xarray/tests/test_backends.py

View workflow job for this annotation

GitHub Actions / ubuntu-latest | test-py313 (flaky)

test_batchdap4_downloads[dap4] Failed: Timeout (>180.0s) from pytest-timeout.

Check failure on line 6589 in xarray/tests/test_backends.py

View workflow job for this annotation

GitHub Actions / ubuntu-latest | test-py313 (flaky)

test_batchdap4_downloads[dap2] Failed: Timeout (>180.0s) from pytest-timeout.
url.replace("https", protocol),
session=session,
engine="pydap",
Expand Down
Loading