BUG: Fix Series.str.zfill for ArrowDtype string arrays #61485 (#61533)

Co-authored-by: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>

Author: iabhi4

doc/source/whatsnew/v3.0.0.rst

@@ -1008,8 +1008,8 @@ Conversion
 
 Strings
 ^^^^^^^
+- Bug in :meth:`Series.str.zfill` raising ``AttributeError`` for :class:`ArrowDtype` (:issue:`61485`)
 - Bug in :meth:`Series.value_counts` would not respect ``sort=False`` for series having ``string`` dtype (:issue:`55224`)
--
 
 Interval
 ^^^^^^^^

pandas/core/arrays/arrow/array.py

@@ -2808,6 +2808,13 @@ def _str_wrap(self, width: int, **kwargs) -> Self:
  result = self._apply_elementwise(predicate)
  return self._from_pyarrow_array(pa.chunked_array(result))
 
+ def _str_zfill(self, width: int) -> Self:
+ # TODO: Replace with pc.utf8_zfill when supported by arrow
+ # Arrow ENH - https://github.com/apache/arrow/issues/46683
+ predicate = lambda val: val.zfill(width)
+ result = self._apply_elementwise(predicate)
+ return type(self)(pa.chunked_array(result))
+
  @property
  def _dt_days(self) -> Self:
  return self._from_pyarrow_array(

pandas/core/arrays/string_.py

@@ -1134,3 +1134,6 @@ def _cmp_method(self, other, op):
  return res_arr
 
  _arith_method = _cmp_method
+
+ def _str_zfill(self, width: int) -> Self:
+ return self._str_map(lambda x: x.zfill(width))

pandas/core/strings/accessor.py

@@ -1912,8 +1912,8 @@ def zfill(self, width: int):
  if not is_integer(width):
  msg = f"width must be of integer type, not {type(width).__name__}"
  raise TypeError(msg)
- f = lambda x: x.zfill(width)
- result = self._data.array._str_map(f)
+
+ result = self._data.array._str_zfill(width)
  return self._wrap_result(result)
 
  def slice(self, start=None, stop=None, step=None):

pandas/core/strings/object_array.py

@@ -544,3 +544,6 @@ def f(x):
  return empty_row
 
  return [f(val) for val in np.asarray(self)]
+
+ def _str_zfill(self, width: int):
+ return self._str_map(lambda x: x.zfill(width))

pandas/tests/strings/test_string_array.py

@@ -110,3 +110,19 @@ def test_string_array_extract(nullable_string_dtype):
 
  result = result.astype(object)
  tm.assert_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+ "values, width, expected",
+ [
+ (["a", "ab", "abc", None], 4, ["000a", "00ab", "0abc", None]),
+ (["1", "-1", "+1", None], 4, ["0001", "-001", "+001", None]),
+ (["1234", "-1234"], 3, ["1234", "-1234"]),
+ ],
+)
+def test_string_array_zfill(nullable_string_dtype, values, width, expected):
+ # GH #61485
+ s = Series(values, dtype=nullable_string_dtype)
+ result = s.str.zfill(width)
+ expected = Series(expected, dtype=nullable_string_dtype)
+ tm.assert_series_equal(result, expected)