diff --git a/doc/whats-new.rst b/doc/whats-new.rst index acb81f3692a..f66d538ad0a 100644 --- a/doc/whats-new.rst +++ b/doc/whats-new.rst @@ -34,11 +34,15 @@ Bug fixes - Fix error when encoding an empty :py:class:`numpy.datetime64` array (:issue:`10722`, :pull:`10723`). By `Spencer Clark `_. +- Propagate coordinate attrs in :py:meth:`xarray.Dataset.map` (:issue:`9317`, :pull:`10602`). - Fix error from ``to_netcdf(..., compute=False)`` when using Dask Distributed (:issue:`10725`). By `Stephan Hoyer `_. - Propagation coordinate attrs in :py:meth:`xarray.Dataset.map` (:issue:`9317`, :pull:`10602`). By `Justus Magin `_. +- Allow ``combine_attrs="drop_conflicts"`` to handle objects with ``__eq__`` methods that return + non-bool values (e.g., numpy arrays) without raising ``ValueError`` (:pull:`10726`). + By `Maximilian Roos `_. Documentation ~~~~~~~~~~~~~ diff --git a/xarray/core/utils.py b/xarray/core/utils.py index e490fc05c2f..d44aff9ff36 100644 --- a/xarray/core/utils.py +++ b/xarray/core/utils.py @@ -239,17 +239,34 @@ def equivalent(first: T, second: T) -> bool: """Compare two objects for equivalence (identity or equality), using array_equiv if either object is an ndarray. If both objects are lists, equivalent is sequentially called on all the elements. + + Returns False for any comparison that doesn't return a boolean, + making this function safer to use with objects that have non-standard + __eq__ implementations. """ # TODO: refactor to avoid circular import from xarray.core import duck_array_ops if first is second: return True + if isinstance(first, np.ndarray) or isinstance(second, np.ndarray): return duck_array_ops.array_equiv(first, second) + if isinstance(first, list) or isinstance(second, list): return list_equiv(first, second) # type: ignore[arg-type] - return (first == second) or (pd.isnull(first) and pd.isnull(second)) # type: ignore[call-overload] + + # For non-array/list types, use == but require boolean result + result = first == second + if not isinstance(result, bool): + # Accept numpy bool scalars as well + if isinstance(result, np.bool_): + return bool(result) + # Reject any other non-boolean type (Dataset, Series, custom objects, etc.) + return False + + # Check for NaN equivalence + return result or (pd.isnull(first) and pd.isnull(second)) # type: ignore[call-overload] def list_equiv(first: Sequence[T], second: Sequence[T]) -> bool: diff --git a/xarray/structure/merge.py b/xarray/structure/merge.py index 58168ddb024..5bb53036042 100644 --- a/xarray/structure/merge.py +++ b/xarray/structure/merge.py @@ -607,6 +607,25 @@ def merge_coords( return variables, out_indexes +def equivalent_attrs(a: Any, b: Any) -> bool: + """Check if two attribute values are equivalent. + + Returns False if the comparison raises ValueError or TypeError. + This handles cases like numpy arrays with ambiguous truth values + and xarray Datasets which can't be directly converted to numpy arrays. + + Since equivalent() now handles non-boolean returns by returning False, + this wrapper mainly catches exceptions from comparisons that can't be + evaluated at all. + """ + try: + return equivalent(a, b) + except (ValueError, TypeError): + # These exceptions indicate the comparison is truly ambiguous + # (e.g., nested numpy arrays that would raise "ambiguous truth value") + return False + + def merge_attrs(variable_attrs, combine_attrs, context=None): """Combine attributes from different variables according to combine_attrs""" if not variable_attrs: @@ -633,20 +652,18 @@ def merge_attrs(variable_attrs, combine_attrs, context=None): elif combine_attrs == "drop_conflicts": result = {} dropped_keys = set() + for attrs in variable_attrs: - result.update( - { - key: value - for key, value in attrs.items() - if key not in result and key not in dropped_keys - } - ) - result = { - key: value - for key, value in result.items() - if key not in attrs or equivalent(attrs[key], value) - } - dropped_keys |= {key for key in attrs if key not in result} + for key, value in attrs.items(): + if key in dropped_keys: + continue + + if key not in result: + result[key] = value + elif not equivalent_attrs(result[key], value): + del result[key] + dropped_keys.add(key) + return result elif combine_attrs == "identical": result = dict(variable_attrs[0]) diff --git a/xarray/tests/test_merge.py b/xarray/tests/test_merge.py index 8ae05fbb261..01bab8ca8b2 100644 --- a/xarray/tests/test_merge.py +++ b/xarray/tests/test_merge.py @@ -1,6 +1,9 @@ from __future__ import annotations +import warnings + import numpy as np +import pandas as pd import pytest import xarray as xr @@ -235,6 +238,267 @@ def test_merge_attrs_drop_conflicts(self): expected = xr.Dataset(attrs={"a": 0, "d": 0, "e": 0}) assert_identical(actual, expected) + def test_merge_attrs_drop_conflicts_numpy_arrays(self): + """Test drop_conflicts with numpy arrays.""" + # Test with numpy arrays (which return arrays from ==) + arr1 = np.array([1, 2, 3]) + arr2 = np.array([1, 2, 3]) + arr3 = np.array([4, 5, 6]) + + ds1 = xr.Dataset(attrs={"arr": arr1, "scalar": 1}) + ds2 = xr.Dataset(attrs={"arr": arr2, "scalar": 1}) # Same array values + ds3 = xr.Dataset(attrs={"arr": arr3, "other": 2}) # Different array values + + # Arrays are considered equivalent if they have the same values + actual = xr.merge([ds1, ds2], combine_attrs="drop_conflicts") + assert "arr" in actual.attrs # Should keep the array since they're equivalent + assert actual.attrs["scalar"] == 1 + + # Different arrays cause the attribute to be dropped + actual = xr.merge([ds1, ds3], combine_attrs="drop_conflicts") + assert "arr" not in actual.attrs # Should drop due to conflict + assert "other" in actual.attrs + + def test_merge_attrs_drop_conflicts_custom_eq_returns_array(self): + """Test drop_conflicts with custom objects that return arrays from __eq__.""" + + # Test with custom objects that return non-bool from __eq__ + class CustomEq: + """Object whose __eq__ returns a non-bool value.""" + + def __init__(self, value): + self.value = value + + def __eq__(self, other): + if not isinstance(other, CustomEq): + return False + # Return a numpy array (truthy if all elements are non-zero) + return np.array([self.value == other.value]) + + def __repr__(self): + return f"CustomEq({self.value})" + + obj1 = CustomEq(42) + obj2 = CustomEq(42) # Same value + obj3 = CustomEq(99) # Different value + + ds4 = xr.Dataset(attrs={"custom": obj1, "x": 1}) + ds5 = xr.Dataset(attrs={"custom": obj2, "x": 1}) + ds6 = xr.Dataset(attrs={"custom": obj3, "y": 2}) + + # Suppress DeprecationWarning from numpy < 2.0 about ambiguous truth values + # when our custom __eq__ returns arrays that are evaluated in boolean context + with warnings.catch_warnings(): + warnings.filterwarnings("ignore", category=DeprecationWarning) + + # Objects returning arrays are dropped (non-boolean return) + actual = xr.merge([ds4, ds5], combine_attrs="drop_conflicts") + assert "custom" not in actual.attrs # Dropped - returns array, not bool + assert actual.attrs["x"] == 1 + + # Different values also dropped (returns array, not bool) + actual = xr.merge([ds4, ds6], combine_attrs="drop_conflicts") + assert "custom" not in actual.attrs # Dropped - returns non-boolean + assert actual.attrs["x"] == 1 + assert actual.attrs["y"] == 2 + + def test_merge_attrs_drop_conflicts_ambiguous_array_returns(self): + """Test drop_conflicts with objects returning ambiguous arrays from __eq__.""" + + # Test edge case: object whose __eq__ returns empty array (ambiguous truth value) + class EmptyArrayEq: + def __eq__(self, other): + if not isinstance(other, EmptyArrayEq): + return False + return np.array([]) # Empty array has ambiguous truth value + + def __repr__(self): + return "EmptyArrayEq()" + + empty_obj1 = EmptyArrayEq() + empty_obj2 = EmptyArrayEq() + + ds7 = xr.Dataset(attrs={"empty": empty_obj1}) + ds8 = xr.Dataset(attrs={"empty": empty_obj2}) + + # With new behavior: ambiguous truth values are treated as non-equivalent + # So the attribute is dropped instead of raising an error + with warnings.catch_warnings(): + warnings.filterwarnings("ignore", category=DeprecationWarning) + actual = xr.merge([ds7, ds8], combine_attrs="drop_conflicts") + assert "empty" not in actual.attrs # Dropped due to ambiguous comparison + + # Test with object that returns multi-element array (also ambiguous) + class MultiArrayEq: + def __eq__(self, other): + if not isinstance(other, MultiArrayEq): + return False + return np.array([True, False]) # Multi-element array is ambiguous + + def __repr__(self): + return "MultiArrayEq()" + + multi_obj1 = MultiArrayEq() + multi_obj2 = MultiArrayEq() + + ds9 = xr.Dataset(attrs={"multi": multi_obj1}) + ds10 = xr.Dataset(attrs={"multi": multi_obj2}) + + # With new behavior: ambiguous arrays are treated as non-equivalent + with warnings.catch_warnings(): + warnings.filterwarnings("ignore", category=DeprecationWarning) + actual = xr.merge([ds9, ds10], combine_attrs="drop_conflicts") + assert "multi" not in actual.attrs # Dropped due to ambiguous comparison + + def test_merge_attrs_drop_conflicts_all_true_array(self): + """Test drop_conflicts with all-True multi-element array from __eq__.""" + + # Test with all-True multi-element array (unambiguous truthy) + class AllTrueArrayEq: + def __eq__(self, other): + if not isinstance(other, AllTrueArrayEq): + return False + return np.array([True, True, True]) # All True, but still multi-element + + def __repr__(self): + return "AllTrueArrayEq()" + + alltrue1 = AllTrueArrayEq() + alltrue2 = AllTrueArrayEq() + + ds11 = xr.Dataset(attrs={"alltrue": alltrue1}) + ds12 = xr.Dataset(attrs={"alltrue": alltrue2}) + + # Multi-element arrays are ambiguous even if all True + actual = xr.merge([ds11, ds12], combine_attrs="drop_conflicts") + assert "alltrue" not in actual.attrs # Dropped due to ambiguous comparison + + def test_merge_attrs_drop_conflicts_nested_arrays(self): + """Test drop_conflicts with NumPy object arrays containing nested arrays.""" + # Test 1: NumPy object arrays with nested arrays + # These can have complex comparison behavior + x = np.array([None], dtype=object) + x[0] = np.arange(3) + y = np.array([None], dtype=object) + y[0] = np.arange(10, 13) + + ds1 = xr.Dataset(attrs={"nested_array": x, "common": 1}) + ds2 = xr.Dataset(attrs={"nested_array": y, "common": 1}) + + # Different nested arrays should cause attribute to be dropped + actual = xr.merge([ds1, ds2], combine_attrs="drop_conflicts") + assert ( + "nested_array" not in actual.attrs + ) # Dropped due to different nested arrays + assert actual.attrs["common"] == 1 + + # Test with identical nested arrays + # Note: Even identical nested arrays will be dropped because comparison + # raises ValueError due to ambiguous truth value + z = np.array([None], dtype=object) + z[0] = np.arange(3) # Same as x + ds3 = xr.Dataset(attrs={"nested_array": z, "other": 2}) + + actual = xr.merge([ds1, ds3], combine_attrs="drop_conflicts") + assert ( + "nested_array" not in actual.attrs + ) # Dropped due to ValueError in comparison + assert actual.attrs["other"] == 2 + + def test_merge_attrs_drop_conflicts_dataset_attrs(self): + """Test drop_conflicts with xarray.Dataset objects as attributes.""" + # xarray.Dataset objects as attributes (raises TypeError in equivalent) + attr_ds1 = xr.Dataset({"foo": 1}) + attr_ds2 = xr.Dataset({"bar": 1}) # Different dataset + attr_ds3 = xr.Dataset({"foo": 1}) # Same as attr_ds1 + + ds4 = xr.Dataset(attrs={"dataset_attr": attr_ds1, "scalar": 42}) + ds5 = xr.Dataset(attrs={"dataset_attr": attr_ds2, "scalar": 42}) + ds6 = xr.Dataset(attrs={"dataset_attr": attr_ds3, "other": 99}) + + # Different datasets raise TypeError and should be dropped + actual = xr.merge([ds4, ds5], combine_attrs="drop_conflicts") + assert "dataset_attr" not in actual.attrs # Dropped due to TypeError + assert actual.attrs["scalar"] == 42 + + # Identical datasets are also dropped (comparison returns Dataset, not bool) + actual = xr.merge([ds4, ds6], combine_attrs="drop_conflicts") + assert "dataset_attr" not in actual.attrs # Dropped - returns Dataset, not bool + assert actual.attrs["other"] == 99 + + def test_merge_attrs_drop_conflicts_pandas_series(self): + """Test drop_conflicts with Pandas Series as attributes.""" + # Pandas Series (raises ValueError due to ambiguous truth value) + series1 = pd.Series([1, 2]) + series2 = pd.Series([3, 4]) # Different values + series3 = pd.Series([1, 2]) # Same as series1 + + ds7 = xr.Dataset(attrs={"series": series1, "value": "a"}) + ds8 = xr.Dataset(attrs={"series": series2, "value": "a"}) + ds9 = xr.Dataset(attrs={"series": series3, "value": "a"}) + + # Suppress potential warnings from pandas comparisons + with warnings.catch_warnings(): + warnings.filterwarnings("ignore", category=DeprecationWarning) + warnings.filterwarnings("ignore", category=FutureWarning) + + # Different series raise ValueError and get dropped + actual = xr.merge([ds7, ds8], combine_attrs="drop_conflicts") + assert "series" not in actual.attrs # Dropped due to ValueError + assert actual.attrs["value"] == "a" + + # Even identical series raise ValueError in equivalent() and get dropped + # because Series comparison returns another Series with ambiguous truth value + actual = xr.merge([ds7, ds9], combine_attrs="drop_conflicts") + assert "series" not in actual.attrs # Dropped due to ValueError + assert actual.attrs["value"] == "a" + + def test_merge_attrs_drop_conflicts_eq_returns_string(self): + """Test objects whose __eq__ returns strings are dropped.""" + + # Case 1: Objects whose __eq__ returns non-boolean strings + class ReturnsString: + def __init__(self, value): + self.value = value + + def __eq__(self, other): + # Always returns a string (non-boolean) + return "comparison result" + + obj1 = ReturnsString("A") + obj2 = ReturnsString("B") # Different object + + ds1 = xr.Dataset(attrs={"obj": obj1}) + ds2 = xr.Dataset(attrs={"obj": obj2}) + + actual = xr.merge([ds1, ds2], combine_attrs="drop_conflicts") + + # Strict behavior: drops attribute because __eq__ returns non-boolean + assert "obj" not in actual.attrs + + def test_merge_attrs_drop_conflicts_eq_returns_number(self): + """Test objects whose __eq__ returns numbers are dropped.""" + + # Case 2: Objects whose __eq__ returns numbers + class ReturnsZero: + def __init__(self, value): + self.value = value + + def __eq__(self, other): + # Always returns 0 (non-boolean) + return 0 + + obj3 = ReturnsZero("same") + obj4 = ReturnsZero("same") # Different object, same value + + ds3 = xr.Dataset(attrs={"zero": obj3}) + ds4 = xr.Dataset(attrs={"zero": obj4}) + + actual = xr.merge([ds3, ds4], combine_attrs="drop_conflicts") + + # Strict behavior: drops attribute because __eq__ returns non-boolean + assert "zero" not in actual.attrs + def test_merge_attrs_no_conflicts_compat_minimal(self): """make sure compat="minimal" does not silence errors""" ds1 = xr.Dataset({"a": ("x", [], {"a": 0})})