Allow multidimensional variable with same name as dim when constructing dataset via coords (#8886)

* regression test

* remove unnecessary check

* whatsnew

* remove outdated test

Author: TomNicholas

doc/whats-new.rst

@@ -73,6 +73,9 @@ Bug fixes
 - Warn and return bytes undecoded in case of UnicodeDecodeError in h5netcdf-backend
   (:issue:`5563`, :pull:`8874`).
   By `Kai Mühlbauer <https://github.com/kmuehlbauer>`_.
+- Fix bug incorrectly disallowing creation of a dataset with a multidimensional coordinate variable with the same name as one of its dims.
+  (:issue:`8884`, :pull:`8886`)
+  By `Tom Nicholas <https://github.com/TomNicholas>`_.
 
 
 Documentation

xarray/core/merge.py

@@ -562,25 +562,6 @@ def merge_coords(
     return variables, out_indexes
 
 
-def assert_valid_explicit_coords(
-    variables: Mapping[Any, Any],
-    dims: Mapping[Any, int],
-    explicit_coords: Iterable[Hashable],
-) -> None:
-    """Validate explicit coordinate names/dims.
-
-    Raise a MergeError if an explicit coord shares a name with a dimension
-    but is comprised of arbitrary dimensions.
-    """
-    for coord_name in explicit_coords:
-        if coord_name in dims and variables[coord_name].dims != (coord_name,):
-            raise MergeError(
-                f"coordinate {coord_name} shares a name with a dataset dimension, but is "
-                "not a 1D variable along that dimension. This is disallowed "
-                "by the xarray data model."
-            )
-
-
 def merge_attrs(variable_attrs, combine_attrs, context=None):
     """Combine attributes from different variables according to combine_attrs"""
     if not variable_attrs:
@@ -728,7 +709,6 @@ def merge_core(
         # coordinates may be dropped in merged results
         coord_names.intersection_update(variables)
     if explicit_coords is not None:
-        assert_valid_explicit_coords(variables, dims, explicit_coords)
         coord_names.update(explicit_coords)
     for dim, size in dims.items():
         if dim in variables:

xarray/tests/test_coordinates.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import numpy as np
 import pandas as pd
 import pytest
 
@@ -8,7 +9,7 @@
 from xarray.core.dataarray import DataArray
 from xarray.core.dataset import Dataset
 from xarray.core.indexes import PandasIndex, PandasMultiIndex
-from xarray.core.variable import IndexVariable
+from xarray.core.variable import IndexVariable, Variable
 from xarray.tests import assert_identical, source_ndarray
 
 
@@ -174,3 +175,10 @@ def test_align(self) -> None:
         left2, right2 = align(left, right, join="override")
         assert_identical(left2, left)
         assert_identical(left2, right2)
+
+    def test_dataset_from_coords_with_multidim_var_same_name(self):
+        # regression test for GH #8883
+        var = Variable(data=np.arange(6).reshape(2, 3), dims=["x", "y"])
+        coords = Coordinates(coords={"x": var}, indexes={})
+        ds = Dataset(coords=coords)
+        assert ds.coords["x"].dims == ("x", "y")

xarray/tests/test_dataset.py

@@ -486,14 +486,6 @@ def test_constructor(self) -> None:
         actual = Dataset({"z": expected["z"]})
         assert_identical(expected, actual)
 
-    def test_constructor_invalid_dims(self) -> None:
-        # regression for GH1120
-        with pytest.raises(MergeError):
-            Dataset(
-                data_vars=dict(v=("y", [1, 2, 3, 4])),
-                coords=dict(y=DataArray([0.1, 0.2, 0.3, 0.4], dims="x")),
-            )
-
     def test_constructor_1d(self) -> None:
         expected = Dataset({"x": (["x"], 5.0 + np.arange(5))})
         actual = Dataset({"x": 5.0 + np.arange(5)})