Backport PR #60940: ENH: Add dtype argument to str.decode (#60968)

* ENH: Improved error message and raise new error for small-string NaN edge case in HDFStore.append (#60829)

* Add clearer error messages for datatype mismatch in HDFStore.append. Raise ValueError when nan_rep too large for pytable column. Add and modify applicable test code.

* Fix missed tests and correct mistake in error message.

* Remove excess comments. Reverse error type change to avoid api changes. Move nan_rep tests into separate function.

(cherry picked from commit 57340ec)

* TST(string dtype): Resolve xfails in pytables (#60795)

(cherry picked from commit 4511251)

* BUG(string dtype): Resolve pytables xfail when reading with condition (#60943)

(cherry picked from commit 0ec5f26)

* Backport PR #60940: ENH: Add dtype argument to str.decode

---------

Co-authored-by: Jake Thomas Trevallion <[email protected]>

Author: rhshadrach

doc/source/whatsnew/v2.3.0.rst

@@ -37,6 +37,7 @@ Other enhancements
   updated to raise FutureWarning with NumPy >= 2 (:issue:`60340`)
 - :meth:`Series.str.decode` result now has ``StringDtype`` when ``future.infer_string`` is True (:issue:`60709`)
 - :meth:`~Series.to_hdf` and :meth:`~DataFrame.to_hdf` now round-trip with ``StringDtype``  (:issue:`60663`)
+- The :meth:`Series.str.decode` has gained the argument ``dtype`` to control the dtype of the result (:issue:`60940`)
 - The :meth:`~Series.cumsum`, :meth:`~Series.cummin`, and :meth:`~Series.cummax` reductions are now implemented for ``StringDtype`` columns when backed by PyArrow (:issue:`60633`)
 - The :meth:`~Series.sum` reduction is now implemented for ``StringDtype`` columns (:issue:`59853`)
 

pandas/core/strings/accessor.py

@@ -33,6 +33,7 @@
     is_list_like,
     is_object_dtype,
     is_re,
+    is_string_dtype,
 )
 from pandas.core.dtypes.dtypes import (
     ArrowDtype,
@@ -1981,7 +1982,9 @@ def slice_replace(self, start=None, stop=None, repl=None):
         result = self._data.array._str_slice_replace(start, stop, repl)
         return self._wrap_result(result)
 
-    def decode(self, encoding, errors: str = "strict"):
+    def decode(
+        self, encoding, errors: str = "strict", dtype: str | DtypeObj | None = None
+    ):
         """
         Decode character string in the Series/Index using indicated encoding.
 
@@ -1992,6 +1995,14 @@ def decode(self, encoding, errors: str = "strict"):
         ----------
         encoding : str
         errors : str, optional
+            Specifies the error handling scheme.
+            Possible values are those supported by :meth:`bytes.decode`.
+        dtype : str or dtype, optional
+            The dtype of the result. When not ``None``, must be either a string or
+            object dtype. When ``None``, the dtype of the result is determined by
+            ``pd.options.future.infer_string``.
+
+            .. versionadded:: 2.3.0
 
         Returns
         -------
@@ -2008,6 +2019,10 @@ def decode(self, encoding, errors: str = "strict"):
         2   ()
         dtype: object
         """
+        if dtype is not None and not is_string_dtype(dtype):
+            raise ValueError(f"dtype must be string or object, got {dtype=}")
+        if dtype is None and get_option("future.infer_string"):
+            dtype = "str"
         # TODO: Add a similar _bytes interface.
         if encoding in _cpython_optimized_decoders:
             # CPython optimized implementation
@@ -2017,7 +2032,6 @@ def decode(self, encoding, errors: str = "strict"):
             f = lambda x: decoder(x, errors)[0]
         arr = self._data.array
         result = arr._str_map(f)
-        dtype = "str" if get_option("future.infer_string") else None
         return self._wrap_result(result, dtype=dtype)
 
     @forbid_nonstring_types(["bytes"])

pandas/tests/strings/test_strings.py

@@ -599,6 +599,30 @@ def test_decode_errors_kwarg():
     tm.assert_series_equal(result, expected)
 
 
+def test_decode_string_dtype(string_dtype):
+    # https://github.com/pandas-dev/pandas/pull/60940
+    ser = Series([b"a", b"b"])
+    result = ser.str.decode("utf-8", dtype=string_dtype)
+    expected = Series(["a", "b"], dtype=string_dtype)
+    tm.assert_series_equal(result, expected)
+
+
+def test_decode_object_dtype(object_dtype):
+    # https://github.com/pandas-dev/pandas/pull/60940
+    ser = Series([b"a", rb"\ud800"])
+    result = ser.str.decode("utf-8", dtype=object_dtype)
+    expected = Series(["a", r"\ud800"], dtype=object_dtype)
+    tm.assert_series_equal(result, expected)
+
+
+def test_decode_bad_dtype():
+    # https://github.com/pandas-dev/pandas/pull/60940
+    ser = Series([b"a", b"b"])
+    msg = "dtype must be string or object, got dtype='int64'"
+    with pytest.raises(ValueError, match=msg):
+        ser.str.decode("utf-8", dtype="int64")
+
+
 @pytest.mark.parametrize(
     "form, expected",
     [