Merge branch 'main' into coders

.github/workflows/ci-additional.yaml

@@ -123,7 +123,7 @@ jobs:
           python -m mypy --install-types --non-interactive --cobertura-xml-report mypy_report
 
       - name: Upload mypy coverage to Codecov
-        uses: codecov/[email protected].1
+        uses: codecov/[email protected].2
         with:
           file: mypy_report/cobertura.xml
           flags: mypy
@@ -174,7 +174,7 @@ jobs:
           python -m mypy --install-types --non-interactive --cobertura-xml-report mypy_report
 
       - name: Upload mypy coverage to Codecov
-        uses: codecov/[email protected].1
+        uses: codecov/[email protected].2
         with:
           file: mypy_report/cobertura.xml
           flags: mypy-min
@@ -230,7 +230,7 @@ jobs:
           python -m pyright xarray/
 
       - name: Upload pyright coverage to Codecov
-        uses: codecov/[email protected].1
+        uses: codecov/[email protected].2
         with:
           file: pyright_report/cobertura.xml
           flags: pyright
@@ -286,7 +286,7 @@ jobs:
           python -m pyright xarray/
 
       - name: Upload pyright coverage to Codecov
-        uses: codecov/[email protected].1
+        uses: codecov/[email protected].2
         with:
           file: pyright_report/cobertura.xml
           flags: pyright39

.github/workflows/ci.yaml

@@ -159,7 +159,7 @@ jobs:
           path: pytest.xml
 
       - name: Upload code coverage to Codecov
-        uses: codecov/[email protected].1
+        uses: codecov/[email protected].2
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:

.github/workflows/upstream-dev-ci.yaml

@@ -140,7 +140,7 @@ jobs:
         run: |
           python -m mypy --install-types --non-interactive --cobertura-xml-report mypy_report
       - name: Upload mypy coverage to Codecov
-        uses: codecov/[email protected].1
+        uses: codecov/[email protected].2
         with:
           file: mypy_report/cobertura.xml
           flags: mypy

asv_bench/benchmarks/rolling.py

@@ -3,7 +3,7 @@
 
 import xarray as xr
 
-from . import parameterized, randn, requires_dask
+from . import _skip_slow, parameterized, randn, requires_dask
 
 nx = 3000
 long_nx = 30000
@@ -80,6 +80,9 @@ def time_rolling_construct(self, center, stride, use_bottleneck):
 class RollingDask(Rolling):
     def setup(self, *args, **kwargs):
         requires_dask()
+        # TODO: Lazily skipped in CI as it is very demanding and slow.
+        # Improve times and remove errors.
+        _skip_slow()
         super().setup(**kwargs)
         self.ds = self.ds.chunk({"x": 100, "y": 50, "t": 50})
         self.da_long = self.da_long.chunk({"x": 10000})

doc/whats-new.rst

@@ -21,6 +21,8 @@ v.2024.12.0 (unreleased)
 
 New Features
 ~~~~~~~~~~~~
+- Improve the error message raised when using chunked-array methods if no chunk manager is available or if the requested chunk manager is missing (:pull:`9676`)
+  By `Justus Magin <https://github.com/keewis>`_. (:pull:`9676`)
 - Better support wrapping additional array types (e.g. ``cupy`` or ``jax``) by calling generalized
   duck array operations throughout more xarray methods. (:issue:`7848`, :pull:`9798`).
   By `Sam Levang <https://github.com/slevang>`_.

xarray/backends/api.py

@@ -156,13 +156,13 @@ def check_name(name: Hashable):
                 raise ValueError(
                     f"Invalid name {name!r} for DataArray or Dataset key: "
                     "string must be length 1 or greater for "
-                    "serialization to netCDF files"
+                    "serialization to netCDF or zarr files"
                 )
         elif name is not None:
             raise TypeError(
                 f"Invalid name {name!r} for DataArray or Dataset key: "
                 "must be either a string or None for serialization to netCDF "
-                "files"
+                "or zarr files"
             )
 
     for k in dataset.variables:

xarray/backends/zarr.py

@@ -1471,7 +1471,7 @@ def open_zarr(
             )  # attempt to import that parallel backend
 
             chunks = {}
-        except ValueError:
+        except (ValueError, ImportError):
             chunks = None
 
     if kwargs:

xarray/core/dataset.py

@@ -2921,19 +2921,11 @@ def _validate_interp_indexers(
         """Variant of _validate_indexers to be used for interpolation"""
         for k, v in self._validate_indexers(indexers):
             if isinstance(v, Variable):
-                if v.ndim == 1:
-                    yield k, v.to_index_variable()
-                else:
-                    yield k, v
-            elif isinstance(v, int):
+                yield k, v
+            elif is_scalar(v):
                 yield k, Variable((), v, attrs=self.coords[k].attrs)
             elif isinstance(v, np.ndarray):
-                if v.ndim == 0:
-                    yield k, Variable((), v, attrs=self.coords[k].attrs)
-                elif v.ndim == 1:
-                    yield k, IndexVariable((k,), v, attrs=self.coords[k].attrs)
-                else:
-                    raise AssertionError()  # Already tested by _validate_indexers
+                yield k, Variable(dims=(k,), data=v, attrs=self.coords[k].attrs)
             else:
                 raise TypeError(type(v))
 
@@ -4127,18 +4119,6 @@ def interp(
 
         coords = either_dict_or_kwargs(coords, coords_kwargs, "interp")
         indexers = dict(self._validate_interp_indexers(coords))
-
-        if coords:
-            # This avoids broadcasting over coordinates that are both in
-            # the original array AND in the indexing array. It essentially
-            # forces interpolation along the shared coordinates.
-            sdims = (
-                set(self.dims)
-                .intersection(*[set(nx.dims) for nx in indexers.values()])
-                .difference(coords.keys())
-            )
-            indexers.update({d: self.variables[d] for d in sdims})
-
         obj = self if assume_sorted else self.sortby(list(coords))
 
         def maybe_variable(obj, k):
@@ -4169,16 +4149,18 @@ def _validate_interp_indexer(x, new_x):
             for k, v in indexers.items()
         }
 
-        # optimization: subset to coordinate range of the target index
-        if method in ["linear", "nearest"]:
-            for k, v in validated_indexers.items():
-                obj, newidx = missing._localize(obj, {k: v})
-                validated_indexers[k] = newidx[k]
-
-        # optimization: create dask coordinate arrays once per Dataset
-        # rather than once per Variable when dask.array.unify_chunks is called later
-        # GH4739
-        if obj.__dask_graph__():
+        has_chunked_array = bool(
+            any(is_chunked_array(v._data) for v in obj._variables.values())
+        )
+        if has_chunked_array:
+            # optimization: subset to coordinate range of the target index
+            if method in ["linear", "nearest"]:
+                for k, v in validated_indexers.items():
+                    obj, newidx = missing._localize(obj, {k: v})
+                    validated_indexers[k] = newidx[k]
+            # optimization: create dask coordinate arrays once per Dataset
+            # rather than once per Variable when dask.array.unify_chunks is called later
+            # GH4739
             dask_indexers = {
                 k: (index.to_base_variable().chunk(), dest.to_base_variable().chunk())
                 for k, (index, dest) in validated_indexers.items()
@@ -4190,10 +4172,9 @@ def _validate_interp_indexer(x, new_x):
             if name in indexers:
                 continue
 
-            if is_duck_dask_array(var.data):
-                use_indexers = dask_indexers
-            else:
-                use_indexers = validated_indexers
+            use_indexers = (
+                dask_indexers if is_duck_dask_array(var.data) else validated_indexers
+            )
 
             dtype_kind = var.dtype.kind
             if dtype_kind in "uifc":