support get_indexer

Author: jorisvandenbossche

pandas/core/indexes/base.py

@@ -6222,6 +6222,10 @@ def _maybe_downcast_for_indexing(self, other: Index) -> tuple[Index, Index]:
                 # let's instead try with a straight Index
                 self = Index(self._values)
 
+        elif self.dtype == "string" and other.dtype == "object":
+            if lib.is_string_array(other._values, skipna=True):
+                return self, other.astype(self.dtype)
+
         if not is_object_dtype(self.dtype) and is_object_dtype(other.dtype):
             # Reverse op so we dont need to re-implement on the subclasses
             other, self = other._maybe_downcast_for_indexing(self)

pandas/tests/indexes/string/test_indexing.py

@@ -72,21 +72,41 @@ def test_get_indexer_strings_raises(self, any_string_dtype):
                 ["a", "b", "c", "d"], method="pad", tolerance=[2, 2, 2, 2]
             )
 
+    @pytest.mark.parametrize("null", [None, np.nan, float("nan"), pd.NA])
+    def test_get_indexer_missing(self, any_string_dtype, null):
+        # NaT and Decimal("NaN") from null_fixture are not supported for string dtype
+        index = Index(["a", "b", null], dtype=any_string_dtype)
+        result = index.get_indexer(["a", null, "c"])
+        expected = np.array([0, 2, -1], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
 
 class TestGetIndexerNonUnique:
-    @pytest.mark.xfail(reason="TODO(infer_string)", strict=False)
-    def test_get_indexer_non_unique_nas(self, any_string_dtype, nulls_fixture):
-        index = Index(["a", "b", None], dtype=any_string_dtype)
-        indexer, missing = index.get_indexer_non_unique([nulls_fixture])
+    @pytest.mark.parametrize("null", [None, np.nan, float("nan"), pd.NA])
+    def test_get_indexer_non_unique_nas(self, request, any_string_dtype, null):
+        if (
+            any_string_dtype == "string"
+            and any_string_dtype.na_value is pd.NA
+            and isinstance(null, float)
+        ):
+            # TODO(infer_string)
+            request.applymarker(
+                pytest.mark.xfail(
+                    reason="NA-variant string dtype does not work with NaN"
+                )
+            )
+
+        index = Index(["a", "b", null], dtype=any_string_dtype)
+        indexer, missing = index.get_indexer_non_unique([null])
 
         expected_indexer = np.array([2], dtype=np.intp)
         expected_missing = np.array([], dtype=np.intp)
         tm.assert_numpy_array_equal(indexer, expected_indexer)
         tm.assert_numpy_array_equal(missing, expected_missing)
 
         # actually non-unique
-        index = Index(["a", None, "b", None], dtype=any_string_dtype)
-        indexer, missing = index.get_indexer_non_unique([nulls_fixture])
+        index = Index(["a", null, "b", null], dtype=any_string_dtype)
+        indexer, missing = index.get_indexer_non_unique([null])
 
         expected_indexer = np.array([1, 3], dtype=np.intp)
         tm.assert_numpy_array_equal(indexer, expected_indexer)