Fix Index.get_indexer for new string dtype and missing value (pandas-dev#62756)

Author: phofl

doc/source/whatsnew/v3.0.0.rst

@@ -1041,6 +1041,7 @@ Indexing
 - Bug in reindexing of :class:`DataFrame` with :class:`PeriodDtype` columns in case of consolidated block (:issue:`60980`, :issue:`60273`)
 - Bug in :meth:`DataFrame.loc.__getitem__` and :meth:`DataFrame.iloc.__getitem__` with a :class:`CategoricalDtype` column with integer categories raising when trying to index a row containing a ``NaN`` entry (:issue:`58954`)
 - Bug in :meth:`Index.__getitem__` incorrectly raising with a 0-dim ``np.ndarray`` key (:issue:`55601`)
+- Bug in :meth:`Index.get_indexer` not casting missing values correctly for new string datatype (:issue:`55833`)
 - Bug in adding new rows with :meth:`DataFrame.loc.__setitem__` or :class:`Series.loc.__setitem__` which failed to retain dtype on the object's index in some cases (:issue:`41626`)
 - Bug in indexing on a :class:`DatetimeIndex` with a ``timestamp[pyarrow]`` dtype or on a :class:`TimedeltaIndex` with a ``duration[pyarrow]`` dtype (:issue:`62277`)
 

pandas/core/indexes/base.py

@@ -6619,6 +6619,14 @@ def _maybe_cast_listlike_indexer(self, target) -> Index:
  # If we started with a list-like, avoid inference to string dtype if self
  # is object dtype (coercing to string dtype will alter the missing values)
  target_index = Index(target, dtype=self.dtype)
+ elif (
+ not hasattr(target, "dtype")
+ and isinstance(self.dtype, StringDtype)
+ and self.dtype.na_value is np.nan
+ and using_string_dtype()
+ ):
+ # Fill missing values to ensure consistent missing value representation
+ target_index = target_index.fillna(np.nan)
  return target_index
 
  @final

pandas/tests/indexes/ranges/test_indexing.py

@@ -46,6 +46,17 @@ def test_get_indexer_decreasing(self, stop):
  expected = np.array([-1, 2, -1, -1, 1, -1, -1, 0, -1], dtype=np.intp)
  tm.assert_numpy_array_equal(result, expected)
 
+ def test_get_indexer_missing_value_casting_string_dtype(self):
+ # GH#55833
+ idx = Index(["a", "b", None])
+ result = idx.get_indexer([None])
+ expected = np.array([2], dtype=np.intp)
+ tm.assert_numpy_array_equal(result, expected)
+
+ result = idx.get_indexer([None, True])
+ expected = np.array([2, -1], dtype=np.intp)
+ tm.assert_numpy_array_equal(result, expected)
+
 
 class TestTake:
  def test_take_preserve_name(self):