BUG: Series.str.slice with negative step

Author: jbrockmendel

doc/source/whatsnew/v2.3.0.rst

@@ -103,8 +103,9 @@ Conversion
 Strings
 ^^^^^^^
 - Bug in :meth:`Series.str.replace` when ``n < 0`` for :class:`StringDtype` with ``storage="pyarrow"`` (:issue:`59628`)
+- Bug in ``ser.str.slice`` with negative ``step`` with :class:`ArrowDtype` giving incorrect results (:issue:`59710`)
 - Bug in the ``center`` method on :class:`Series` and :class:`Index` object ``str`` accessors with pyarrow-backed dtype not matching the python behavior in corner cases with an odd number of fill characters (:issue:`54792`)
-
+-
 
 Interval
 ^^^^^^^^

pandas/core/arrays/arrow/array.py

@@ -2419,6 +2419,10 @@ def _str_rpartition(self, sep: str, expand: bool) -> Self:
     def _str_slice(
         self, start: int | None = None, stop: int | None = None, step: int | None = None
     ) -> Self:
+        if step is not None and step < 0:
+            # GH#59710
+            result = self._apply_elementwise(lambda x: x[start:stop:step])
+            return type(self)(pa.chunked_array(result))
         if start is None:
             start = 0
         if step is None:

pandas/core/arrays/string_arrow.py

@@ -293,6 +293,7 @@ def astype(self, dtype, copy: bool = True):
     _str_startswith = ArrowStringArrayMixin._str_startswith
     _str_endswith = ArrowStringArrayMixin._str_endswith
     _str_pad = ArrowStringArrayMixin._str_pad
+    _str_slice = ArrowExtensionArray._str_slice
 
     def _str_contains(
         self, pat, case: bool = True, flags: int = 0, na=np.nan, regex: bool = True
@@ -351,19 +352,6 @@ def _str_fullmatch(
             pat = f"{pat}$"
         return self._str_match(pat, case, flags, na)
 
-    def _str_slice(
-        self, start: int | None = None, stop: int | None = None, step: int | None = None
-    ) -> Self:
-        if stop is None:
-            return super()._str_slice(start, stop, step)
-        if start is None:
-            start = 0
-        if step is None:
-            step = 1
-        return type(self)(
-            pc.utf8_slice_codeunits(self._pa_array, start=start, stop=stop, step=step)
-        )
-
     def _str_len(self):
         result = pc.utf8_length(self._pa_array)
         return self._convert_int_result(result)

pandas/tests/extension/test_arrow.py

@@ -2045,6 +2045,7 @@ def test_str_join_string_type():
         [None, 2, None, ["ab", None]],
         [None, 2, 1, ["ab", None]],
         [1, 3, 1, ["bc", None]],
+        [None, None, -1, ["dcba", None]],
     ],
 )
 def test_str_slice(start, stop, step, exp):