BUG: 35977 Adding regex support for ExtensionBlock replace method

doc/source/whatsnew/v1.2.0.rst

@@ -462,9 +462,11 @@ Sparse
 ExtensionArray
 ^^^^^^^^^^^^^^
 
+
 - Fixed Bug where :class:`DataFrame` column set to scalar extension type via a dict instantion was considered an object type rather than the extension type (:issue:`35965`)
 - Fixed bug where ``astype()`` with equal dtype and ``copy=False`` would return a new object (:issue:`284881`)
 - Fixed bug when applying a NumPy ufunc with multiple outputs to a :class:`pandas.arrays.IntegerArray` returning None (:issue:`36913`)
+- Fixed bug in :meth:`Dataframe.replace` not working for ``regex=True`` and ``dtype='string'`` Now working as expected (:issue:`35977`)
 
 
 Other

pandas/core/internals/blocks.py

@@ -1961,6 +1961,33 @@ def _unstack(self, unstacker, fill_value, new_placement):
         ]
         return blocks, mask
 
+    def replace(
+        self,
+        to_replace,
+        value,
+        inplace: bool = False,
+        regex: bool = False,
+        convert: bool = True,
+    ):
+        """
+        replace the to_replace value with value, regex is not supported by super class
+        when regex is required ObjectBlock replace method is called
+        """
+        inplace = validate_bool_kwarg(inplace, "inplace")
+        regex = validate_bool_kwarg(regex, "regex")
+        if regex:
+            dtype = self.values.dtype
+            blocks = self.astype(object)
+            if not inplace:
+                return [
+                    b.astype(dtype)
+                    for b in blocks.replace(to_replace, value, inplace, regex, convert)
+                ]
+            blocks.replace(to_replace, value, inplace, regex, convert)
+            return blocks.astype(dtype)
+        else:
+            return super().replace(to_replace, value, inplace, regex, convert)
+
 
 class ObjectValuesExtensionBlock(ExtensionBlock):
     """

pandas/tests/arrays/categorical/test_replace.py

@@ -45,3 +45,41 @@ def test_replace(to_replace, value, expected, flip_categories):
 
     tm.assert_series_equal(expected, result, check_category_order=False)
     tm.assert_series_equal(expected, s, check_category_order=False)
+
+
+@pytest.mark.parametrize(
+    "to_replace,value,input_data,expected_data,inplace",
+    [
+        (r"^\s*$", pd.NA, ["d", "ee", "f", ""], ["d", "ee", "f", pd.NA], False),
+        (r"e{2}", "replace", ["d", "ee", "f", ""], ["d", "replace", "f", ""], False),
+        (r"f", "replace", ["d", "ee", "f", ""], ["d", "ee", "replace", ""], False),
+        (r"^\s*$", pd.NA, ["d", "ee", "f", ""], ["d", "ee", "f", pd.NA], True),
+        (r"e{2}", "replace", ["d", "ee", "f", ""], ["d", "replace", "f", ""], True),
+        (r"f", "replace", ["d", "ee", "f", ""], ["d", "ee", "replace", ""], True),
+    ],
+)
+def test_replace_regex(to_replace, value, input_data, expected_data, inplace):
+    # GH35977
+    input_df = pd.DataFrame({"col1": input_data}, dtype="string")
+    expected_df = pd.DataFrame({"col1": expected_data}, dtype="string")
+    converted = input_df.replace(to_replace, value, inplace=inplace, regex=True)
+    if inplace:
+        tm.assert_frame_equal(expected_df, input_df)
+    else:
+        tm.assert_frame_equal(expected_df, converted)
+
+
+@pytest.mark.parametrize(
+    "to_replace,value,input_data,expected_data",
+    [
+        ("", pd.NA, ["d", "ee", "f", ""], ["d", "ee", "f", pd.NA]),
+        ("ee", "replace", ["d", "ee", "f", ""], ["d", "replace", "f", ""]),
+        ("f", "replace", ["d", "ee", "f", ""], ["d", "ee", "replace", ""]),
+    ],
+)
+def test_replace_string(to_replace, value, input_data, expected_data):
+    # GH35977
+    input_df = pd.DataFrame({"col1": input_data}, dtype="string")
+    expected_df = pd.DataFrame({"col1": expected_data}, dtype="string")
+    input_df = input_df.replace(to_replace, value, inplace=False, regex=False)
+    tm.assert_frame_equal(expected_df, input_df)