TYP: get_indexer

pandas/core/indexes/base.py

@@ -12,6 +12,7 @@
     Sequence,
     TypeVar,
     cast,
+    overload,
 )
 import warnings
 
@@ -157,6 +158,8 @@
 )
 
 if TYPE_CHECKING:
+    from typing import Literal
+
     from pandas import (
         CategoricalIndex,
         DataFrame,
@@ -5187,17 +5190,18 @@ def set_value(self, arr, key, value):
 
         Returns
         -------
-        indexer : ndarray of int
+        indexer : np.ndarray[np.intp]
             Integers from 0 to n - 1 indicating that the index at these
             positions matches the corresponding target values. Missing values
             in the target are marked by -1.
-        missing : ndarray of int
+        missing : np.ndarray[np.intp]
             An indexer into the target of the values not found.
             These correspond to the -1 in the indexer array.
         """
 
     @Appender(_index_shared_docs["get_indexer_non_unique"] % _index_doc_kwargs)
-    def get_indexer_non_unique(self, target):
+    def get_indexer_non_unique(self, target) -> tuple[np.ndarray, np.ndarray]:
+        # both returned ndarrays are np.intp
         target = ensure_index(target)
 
         if not self._should_compare(target) and not is_interval_dtype(self.dtype):
@@ -5221,7 +5225,7 @@ def get_indexer_non_unique(self, target):
         tgt_values = target._get_engine_target()
 
         indexer, missing = self._engine.get_indexer_non_unique(tgt_values)
-        return ensure_platform_int(indexer), missing
+        return ensure_platform_int(indexer), ensure_platform_int(missing)
 
     @final
     def get_indexer_for(self, target, **kwargs) -> np.ndarray:
@@ -5233,16 +5237,39 @@ def get_indexer_for(self, target, **kwargs) -> np.ndarray:
 
         Returns
         -------
-        numpy.ndarray
+        numpy.ndarray[np.intp]
             List of indices.
         """
         if self._index_as_unique:
             return self.get_indexer(target, **kwargs)
         indexer, _ = self.get_indexer_non_unique(target)
         return indexer
 
+    @overload
+    def _get_indexer_non_comparable(
+        self, target: Index, method, unique: Literal[True] = ...
+    ) -> np.ndarray:
+        # returned ndarray is np.intp
+        ...
+
+    @overload
+    def _get_indexer_non_comparable(
+        self, target: Index, method, unique: Literal[False]
+    ) -> tuple[np.ndarray, np.ndarray]:
+        # both returned ndarrays are np.intp
+        ...
+
+    @overload
+    def _get_indexer_non_comparable(
+        self, target: Index, method, unique: bool = True
+    ) -> np.ndarray | tuple[np.ndarray, np.ndarray]:
+        # any returned ndarrays are np.intp
+        ...
+
     @final
-    def _get_indexer_non_comparable(self, target: Index, method, unique: bool = True):
+    def _get_indexer_non_comparable(
+        self, target: Index, method, unique: bool = True
+    ) -> np.ndarray | tuple[np.ndarray, np.ndarray]:
         """
         Called from get_indexer or get_indexer_non_unique when the target
         is of a non-comparable dtype.

pandas/core/indexes/category.py

@@ -1,8 +1,8 @@
+from __future__ import annotations
+
 from typing import (
     Any,
     Hashable,
-    List,
-    Optional,
 )
 import warnings
 
@@ -216,7 +216,7 @@ def __new__(
         data=None,
         categories=None,
         ordered=None,
-        dtype: Optional[Dtype] = None,
+        dtype: Dtype | None = None,
         copy=False,
         name=None,
     ):
@@ -349,7 +349,7 @@ def _format_attrs(self):
             attrs.append(("length", len(self)))
         return attrs
 
-    def _format_with_header(self, header: List[str], na_rep: str = "NaN") -> List[str]:
+    def _format_with_header(self, header: list[str], na_rep: str = "NaN") -> list[str]:
         from pandas.io.formats.printing import pprint_thing
 
         result = [
@@ -422,10 +422,9 @@ def reindex(self, target, method=None, level=None, limit=None, tolerance=None):
 
         target = ibase.ensure_index(target)
 
-        missing: List[int]
         if self.equals(target):
             indexer = None
-            missing = []
+            missing = np.array([], dtype=np.intp)
         else:
             indexer, missing = self.get_indexer_non_unique(np.array(target))
 
@@ -494,22 +493,27 @@ def _maybe_cast_indexer(self, key) -> int:
     def _get_indexer(
         self,
         target: Index,
-        method: Optional[str] = None,
-        limit: Optional[int] = None,
+        method: str | None = None,
+        limit: int | None = None,
         tolerance=None,
     ) -> np.ndarray:
+        # returned ndarray is np.intp
 
         if self.equals(target):
             return np.arange(len(self), dtype="intp")
 
         return self._get_indexer_non_unique(target._values)[0]
 
     @Appender(_index_shared_docs["get_indexer_non_unique"] % _index_doc_kwargs)
-    def get_indexer_non_unique(self, target):
+    def get_indexer_non_unique(self, target) -> tuple[np.ndarray, np.ndarray]:
+        # both returned ndarrays are np.intp
         target = ibase.ensure_index(target)
         return self._get_indexer_non_unique(target._values)
 
-    def _get_indexer_non_unique(self, values: ArrayLike):
+    def _get_indexer_non_unique(
+        self, values: ArrayLike
+    ) -> tuple[np.ndarray, np.ndarray]:
+        # both returned ndarrays are np.intp
         """
         get_indexer_non_unique but after unrapping the target Index object.
         """
@@ -528,7 +532,7 @@ def _get_indexer_non_unique(self, values: ArrayLike):
             codes = self.categories.get_indexer(values)
 
         indexer, missing = self._engine.get_indexer_non_unique(codes)
-        return ensure_platform_int(indexer), missing
+        return ensure_platform_int(indexer), ensure_platform_int(missing)
 
     @doc(Index._convert_list_indexer)
     def _convert_list_indexer(self, keyarr):
@@ -626,7 +630,7 @@ def map(self, mapper):
         mapped = self._values.map(mapper)
         return Index(mapped, name=self.name)
 
-    def _concat(self, to_concat: List[Index], name: Hashable) -> Index:
+    def _concat(self, to_concat: list[Index], name: Hashable) -> Index:
         # if calling index is category, don't check dtype of others
         try:
             codes = np.concatenate([self._is_dtype_compat(c).codes for c in to_concat])

pandas/core/indexes/interval.py

@@ -721,6 +721,7 @@ def _get_indexer(
         limit: int | None = None,
         tolerance: Any | None = None,
     ) -> np.ndarray:
+        # returned ndarray is np.intp
 
         if isinstance(target, IntervalIndex):
             # equal indexes -> 1:1 positional match
@@ -753,6 +754,7 @@ def _get_indexer(
 
     @Appender(_index_shared_docs["get_indexer_non_unique"] % _index_doc_kwargs)
     def get_indexer_non_unique(self, target: Index) -> tuple[np.ndarray, np.ndarray]:
+        # both returned ndarrays are np.intp
         target = ensure_index(target)
 
         if isinstance(target, IntervalIndex) and not self._should_compare(target):
@@ -772,6 +774,7 @@ def get_indexer_non_unique(self, target: Index) -> tuple[np.ndarray, np.ndarray]
         return ensure_platform_int(indexer), ensure_platform_int(missing)
 
     def _get_indexer_pointwise(self, target: Index) -> tuple[np.ndarray, np.ndarray]:
+        # both returned ndarrays are np.intp
         """
         pointwise implementation for get_indexer and get_indexer_non_unique.
         """