Fix merge with compat=minimal (coord names) (#8104)

* fix coord names after merge / compat minimal

* update what's new

* add assert in len(data_vars)

Author: benbovy

doc/whats-new.rst

@@ -43,6 +43,10 @@ Bug fixes
 - Improved handling of multi-coordinate indexes when updating coordinates, including bug fixes
   (and improved warnings for deprecated features) for pandas multi-indexes (:pull:`8094`).
   By `Benoît Bovy <https://github.com/benbovy>`_.
+- Fixed a bug in :py:func:`merge` with ``compat='minimal'`` where the coordinate
+  names were not updated properly internally (:issue:`7405`, :issue:`7588`,
+  :pull:`8104`).
+  By `Benoît Bovy <https://github.com/benbovy>`_.
 
 Documentation
 ~~~~~~~~~~~~~

xarray/core/dataset.py

@@ -438,7 +438,9 @@ def __iter__(self) -> Iterator[Hashable]:
         )
 
     def __len__(self) -> int:
-        return len(self._dataset._variables) - len(self._dataset._coord_names)
+        length = len(self._dataset._variables) - len(self._dataset._coord_names)
+        assert length >= 0, "something is wrong with Dataset._coord_names"
+        return length
 
     def __contains__(self, key: Hashable) -> bool:
         return key in self._dataset._variables and key not in self._dataset._coord_names

xarray/core/merge.py

@@ -723,6 +723,9 @@ def merge_core(
     dims = calculate_dimensions(variables)
 
     coord_names, noncoord_names = determine_coords(coerced)
+    if compat == "minimal":
+        # 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)

xarray/tests/test_dataset.py

@@ -1046,6 +1046,17 @@ def test_data_vars_properties(self) -> None:
             "bar": np.dtype("float64"),
         }
 
+        # len
+        ds.coords["x"] = [1]
+        assert len(ds.data_vars) == 2
+
+        # https://github.com/pydata/xarray/issues/7588
+        with pytest.raises(
+            AssertionError, match="something is wrong with Dataset._coord_names"
+        ):
+            ds._coord_names = {"w", "x", "y", "z"}
+            len(ds.data_vars)
+
     def test_equals_and_identical(self) -> None:
         data = create_test_data(seed=42)
         assert data.equals(data)

xarray/tests/test_merge.py

@@ -382,6 +382,16 @@ def test_merge_compat(self):
 
         assert ds1.identical(ds1.merge(ds2, compat="override"))
 
+    def test_merge_compat_minimal(self) -> None:
+        # https://github.com/pydata/xarray/issues/7405
+        # https://github.com/pydata/xarray/issues/7588
+        ds1 = xr.Dataset(coords={"foo": [1, 2, 3], "bar": 4})
+        ds2 = xr.Dataset(coords={"foo": [1, 2, 3], "bar": 5})
+
+        actual = xr.merge([ds1, ds2], compat="minimal")
+        expected = xr.Dataset(coords={"foo": [1, 2, 3]})
+        assert_identical(actual, expected)
+
     def test_merge_auto_align(self):
         ds1 = xr.Dataset({"a": ("x", [1, 2]), "x": [0, 1]})
         ds2 = xr.Dataset({"b": ("x", [3, 4]), "x": [1, 2]})