support passing a function to combine_attrs

doc/whats-new.rst

@@ -67,11 +67,12 @@ New Features
   By `Maximilian Roos <https://github.com/max-sixty>`_.
 
 - Performance improvement when constructing DataArrays. Significantly speeds up repr for Datasets with large number of variables.
-  By `Deepak Cherian <https://github.com/dcherian>`_
+  By `Deepak Cherian <https://github.com/dcherian>`_.
 - add ``"drop_conflicts"`` to the strategies supported by the ``combine_attrs`` kwarg
   (:issue:`4749`, :pull:`4827`).
   By `Justus Magin <https://github.com/keewis>`_.
-  By `Deepak Cherian <https://github.com/dcherian>`_.
+- allow passing a function to ``combine_attrs`` (:pull:`4896`).
+  By `Justus Magin <https://github.com/keewis>`_.
 - :py:meth:`DataArray.swap_dims` & :py:meth:`Dataset.swap_dims` now accept dims
   in the form of kwargs as well as a dict, like most similar methods.
   By `Maximilian Roos <https://github.com/max-sixty>`_.

xarray/core/combine.py

@@ -413,8 +413,9 @@ def combine_nested(
           those of the first object with that dimension. Indexes for the same
           dimension must have the same size in all objects.
     combine_attrs : {"drop", "identical", "no_conflicts", "drop_conflicts", \
-                     "override"}, default: "drop"
-        String indicating how to combine attrs of the objects being merged:
+                     "override"} or callable, default: "drop"
+        A callable or a string indicating how to combine attrs of the objects being
+        merged:
 
         - "drop": empty attrs on returned Dataset.
         - "identical": all attrs must be the same on every object.
@@ -425,6 +426,10 @@ def combine_nested(
         - "override": skip comparing and copy attrs from the first dataset to
           the result.
 
+        If a callable, it must expect a sequence of ``attrs`` dicts as its only
+        parameter.
+
+
     Returns
     -------
     combined : xarray.Dataset
@@ -628,8 +633,9 @@ def combine_by_coords(
           those of the first object with that dimension. Indexes for the same
           dimension must have the same size in all objects.
     combine_attrs : {"drop", "identical", "no_conflicts", "drop_conflicts", \
-                     "override"}, default: "drop"
-        String indicating how to combine attrs of the objects being merged:
+                     "override"} or callable, default: "drop"
+        A callable or a string indicating how to combine attrs of the objects being
+        merged:
 
         - "drop": empty attrs on returned Dataset.
         - "identical": all attrs must be the same on every object.
@@ -640,6 +646,9 @@ def combine_by_coords(
         - "override": skip comparing and copy attrs from the first dataset to
           the result.
 
+        If a callable, it must expect a sequence of ``attrs`` dicts as its only
+        parameter.
+
     Returns
     -------
     combined : xarray.Dataset

xarray/core/concat.py

@@ -143,8 +143,9 @@ def concat(
           those of the first object with that dimension. Indexes for the same
           dimension must have the same size in all objects.
     combine_attrs : {"drop", "identical", "no_conflicts", "drop_conflicts", \
-                     "override"}, default: "override"
-        String indicating how to combine attrs of the objects being merged:
+                     "override"} or callable, default: "override"
+        A callable or a string indicating how to combine attrs of the objects being
+        merged:
 
         - "drop": empty attrs on returned Dataset.
         - "identical": all attrs must be the same on every object.
@@ -155,6 +156,9 @@ def concat(
         - "override": skip comparing and copy attrs from the first dataset to
           the result.
 
+        If a callable, it must expect a sequence of ``attrs`` dicts as its only
+        parameter.
+
     Returns
     -------
     concatenated : type of objs

xarray/core/merge.py

@@ -498,7 +498,9 @@ def merge_attrs(variable_attrs, combine_attrs):
         # no attributes to merge
         return None
 
-    if combine_attrs == "drop":
+    if callable(combine_attrs):
+        return combine_attrs(variable_attrs)
+    elif combine_attrs == "drop":
         return {}
     elif combine_attrs == "override":
         return dict(variable_attrs[0])
@@ -575,7 +577,7 @@ def merge_core(
     join : {"outer", "inner", "left", "right"}, optional
         How to combine objects with different indexes.
     combine_attrs : {"drop", "identical", "no_conflicts", "drop_conflicts", \
-                     "override"}, optional
+                     "override"} or callable, default: "override"
         How to combine attributes of objects
     priority_arg : int, optional
         Optional argument in `objects` that takes precedence over the others.
@@ -688,8 +690,9 @@ def merge(
         variable names to fill values. Use a data array's name to
         refer to its values.
     combine_attrs : {"drop", "identical", "no_conflicts", "drop_conflicts", \
-                     "override"}, default: "drop"
-        String indicating how to combine attrs of the objects being merged:
+                    "override"} or callable, default: "drop"
+        A callable or a string indicating how to combine attrs of the objects being
+        merged:
 
         - "drop": empty attrs on returned Dataset.
         - "identical": all attrs must be the same on every object.
@@ -700,6 +703,9 @@ def merge(
         - "override": skip comparing and copy attrs from the first dataset to
           the result.
 
+        If a callable, it must expect a sequence of ``attrs`` dicts as its only
+        parameter.
+
     Returns
     -------
     Dataset

xarray/tests/test_combine.py

@@ -518,6 +518,9 @@ def test_auto_combine_2d_combine_attrs_kwarg(self):
         }
         expected_dict["override"] = expected.copy(deep=True)
         expected_dict["override"].attrs = {"a": 1}
+        f = lambda _: {"a": -1, "b": 1}
+        expected_dict[f] = expected.copy(deep=True)
+        expected_dict[f].attrs = f(None)
 
         datasets = [[ds(0), ds(1), ds(2)], [ds(3), ds(4), ds(5)]]
 
@@ -695,6 +698,10 @@ def test_combine_coords_join_exact(self):
                 Dataset({"x": [0, 1], "y": [0, 1]}, attrs={"a": 1, "b": 2}),
             ),
             ("override", Dataset({"x": [0, 1], "y": [0, 1]}, attrs={"a": 1})),
+            (
+                lambda _: {"a": 1, "b": 2},
+                Dataset({"x": [0, 1], "y": [0, 1]}, attrs={"a": 1, "b": 2}),
+            ),
         ],
     )
     def test_combine_coords_combine_attrs(self, combine_attrs, expected):

xarray/tests/test_concat.py

@@ -294,6 +294,13 @@ def test_concat_join_kwarg(self):
                 {"a": 41, "c": 43, "d": 44},
                 False,
             ),
+            (
+                lambda _: {"a": -1, "b": 0, "c": 1},
+                {"a": 41, "b": 42, "c": 43},
+                {"b": 2, "c": 43, "d": 44},
+                {"a": -1, "b": 0, "c": 1},
+                False,
+            ),
         ],
     )
     def test_concat_combine_attrs_kwarg(
@@ -350,6 +357,13 @@ def test_concat_combine_attrs_kwarg(
                 {"a": 41, "c": 43, "d": 44},
                 False,
             ),
+            (
+                lambda _: {"a": -1, "b": 0, "c": 1},
+                {"a": 41, "b": 42, "c": 43},
+                {"b": 2, "c": 43, "d": 44},
+                {"a": -1, "b": 0, "c": 1},
+                False,
+            ),
         ],
     )
     def test_concat_combine_attrs_kwarg_variables(

xarray/tests/test_merge.py

@@ -106,6 +106,13 @@ def test_merge_arrays_attrs_default(self):
                 {"a": 1, "c": np.array([3]), "d": 4},
                 False,
             ),
+            (
+                lambda attrs: attrs[1],
+                {"a": 1, "b": 2, "c": 3},
+                {"a": 4, "b": 3, "c": 1},
+                {"a": 4, "b": 3, "c": 1},
+                False,
+            ),
         ],
     )
     def test_merge_arrays_attrs(
@@ -160,6 +167,13 @@ def test_merge_arrays_attrs(
                 {"a": 1, "c": 3, "d": 4},
                 False,
             ),
+            (
+                lambda attrs: attrs[1],
+                {"a": 1, "b": 2, "c": 3},
+                {"a": 4, "b": 3, "c": 1},
+                {"a": 4, "b": 3, "c": 1},
+                False,
+            ),
         ],
     )
     def test_merge_arrays_attrs_variables(