Internal refactor of label-based data selection

doc/whats-new.rst

@@ -56,6 +56,13 @@ Documentation
 Internal Changes
 ~~~~~~~~~~~~~~~~
 
+- Explicit indexes refactor: add a ``xarray.Index.query()`` method in which
+  one may eventually provide a custom implementation of label-based data
+  selection (not ready yet for public use). Also refactor the internal,
+  pandas-specific implementation into ``PandasIndex.query()`` and
+  ``PandasMultiIndex.query()`` (:pull:`5322`).
+  By `Benoit Bovy <https://github.com/benbovy>`_.
+
 .. _whats-new.0.18.2:
 
 v0.18.2 (19 May 2021)

xarray/core/alignment.py

@@ -18,8 +18,7 @@
 import pandas as pd
 
 from . import dtypes
-from .indexes import Index, PandasIndex
-from .indexing import get_indexer_nd
+from .indexes import Index, PandasIndex, get_indexer_nd, wrap_pandas_index
 from .utils import is_dict_like, is_full_slice, maybe_coerce_to_str, safe_cast_to_index
 from .variable import IndexVariable, Variable
 
@@ -561,7 +560,7 @@ def reindex_variables(
                 "from that to be indexed along {:s}".format(str(indexer.dims), dim)
             )
 
-        target = new_indexes[dim] = PandasIndex(safe_cast_to_index(indexers[dim]))
+        target = new_indexes[dim] = wrap_pandas_index(safe_cast_to_index(indexers[dim]))
 
         if dim in indexes:
             # TODO (benbovy - flexible indexes): support other indexes than pd.Index?

xarray/core/dataarray.py

@@ -51,7 +51,13 @@
 )
 from .dataset import Dataset, split_indexes
 from .formatting import format_item
-from .indexes import Index, Indexes, PandasIndex, default_indexes, propagate_indexes
+from .indexes import (
+    Index,
+    Indexes,
+    default_indexes,
+    propagate_indexes,
+    wrap_pandas_index,
+)
 from .indexing import is_fancy_indexer
 from .merge import PANDAS_TYPES, MergeError, _extract_indexes_from_coords
 from .options import OPTIONS, _get_keep_attrs
@@ -1005,7 +1011,7 @@ def copy(self, deep: bool = True, data: Any = None) -> "DataArray":
             # TODO: benbovy: flexible indexes: support all xarray indexes (not just pandas.Index)
             # xarray Index needs a copy method.
             indexes = {
-                k: PandasIndex(v.to_pandas_index().copy(deep=deep))
+                k: wrap_pandas_index(v.to_pandas_index().copy(deep=deep))
                 for k, v in self._indexes.items()
             }
         return self._replace(variable, coords, indexes=indexes)

xarray/core/dataset.py

@@ -63,11 +63,13 @@
     Index,
     Indexes,
     PandasIndex,
+    PandasMultiIndex,
     default_indexes,
     isel_variable_and_index,
     propagate_indexes,
     remove_unused_levels_categories,
     roll_index,
+    wrap_pandas_index,
 )
 from .indexing import is_fancy_indexer
 from .merge import (
@@ -3284,10 +3286,9 @@ def _rename_indexes(self, name_dict, dims_set):
                 continue
             if isinstance(index, pd.MultiIndex):
                 new_names = [name_dict.get(k, k) for k in index.names]
-                new_index = index.rename(names=new_names)
+                indexes[new_name] = PandasMultiIndex(index.rename(names=new_names))
             else:
-                new_index = index.rename(new_name)
-            indexes[new_name] = PandasIndex(new_index)
+                indexes[new_name] = PandasIndex(index.rename(new_name))
         return indexes
 
     def _rename_all(self, name_dict, dims_dict):
@@ -3516,7 +3517,7 @@ def swap_dims(
                     if new_index.nlevels == 1:
                         # make sure index name matches dimension name
                         new_index = new_index.rename(k)
-                    indexes[k] = PandasIndex(new_index)
+                    indexes[k] = wrap_pandas_index(new_index)
             else:
                 var = v.to_base_variable()
             var.dims = dims
@@ -3789,7 +3790,7 @@ def reorder_levels(
                 raise ValueError(f"coordinate {dim} has no MultiIndex")
             new_index = index.reorder_levels(order)
             variables[dim] = IndexVariable(coord.dims, new_index)
-            indexes[dim] = PandasIndex(new_index)
+            indexes[dim] = PandasMultiIndex(new_index)
 
         return self._replace(variables, indexes=indexes)
 
@@ -3817,7 +3818,7 @@ def _stack_once(self, dims, new_dim):
         coord_names = set(self._coord_names) - set(dims) | {new_dim}
 
         indexes = {k: v for k, v in self.xindexes.items() if k not in dims}
-        indexes[new_dim] = PandasIndex(idx)
+        indexes[new_dim] = wrap_pandas_index(idx)
 
         return self._replace_with_new_dims(
             variables, coord_names=coord_names, indexes=indexes