Raise TypeError when Dataset passed as data_vars to Dataset constructor (#11139)

Dataset(ds) silently dropped attrs because Dataset inherits from Mapping,
so the constructor iterated over data variable keys while ignoring attrs.
This was never intended behavior. Raise TypeError with a message directing
users to ds.copy() instead.

Closes GH11095

Co-authored-by: Claude <noreply@anthropic.com>

Author: kkollsga

doc/whats-new.rst

@@ -186,6 +186,11 @@ Breaking Changes
   not intended to be visible to end-users so this version of xarray
   switches to using ``FutureWarning`` everywhere (:pull:`11112`).
   By `Julia Signell <https://github.com/jsignell>`_.
+- Passing a :py:class:`Dataset` as ``data_vars`` to the :py:class:`Dataset`
+  constructor now raises :py:class:`TypeError`. This was never intended behavior
+  and silently dropped ``attrs``. Use :py:meth:`Dataset.copy` instead
+  (:issue:`11095`).
+  By `Kristian Kollsga <https://github.com/kkollsga>`_.
 
 Bug Fixes
 ~~~~~~~~~

xarray/core/dataset.py

@@ -385,6 +385,11 @@ def __init__(
     ) -> None:
         if data_vars is None:
             data_vars = {}
+        if isinstance(data_vars, Dataset):
+            raise TypeError(
+                "Passing a Dataset as `data_vars` to the Dataset constructor is"
+                " not supported. Use `ds.copy()` to create a copy of a Dataset."
+            )
         if coords is None:
             coords = {}
 

xarray/tests/test_dataset.py

@@ -494,6 +494,14 @@ def test_constructor(self) -> None:
         actual = Dataset({"z": expected["z"]})
         assert_identical(expected, actual)
 
+    def test_constructor_dataset_as_data_vars_raises(self) -> None:
+        ds = Dataset({"x": ("x", [1, 2, 3])}, attrs={"key": "value"})
+        with pytest.raises(
+            TypeError,
+            match=r"Passing a Dataset as `data_vars`.*Use `ds\.copy\(\)`",
+        ):
+            Dataset(ds)
+
     def test_constructor_1d(self) -> None:
         expected = Dataset({"x": (["x"], 5.0 + np.arange(5))})
         actual = Dataset({"x": 5.0 + np.arange(5)})