BUG (string dtype): comparison of string column to mixed object column fails pandas-dev#60228

Author: TEARFEAR

pandas/core/arrays/arrow/array.py

@@ -726,7 +726,13 @@ def _cmp_method(self, other, op) -> ArrowExtensionArray:
             other, (ArrowExtensionArray, np.ndarray, list, BaseMaskedArray)
         ) or isinstance(getattr(other, "dtype", None), CategoricalDtype):
             try:
-                result = pc_func(self._pa_array, self._box_pa(other))
+                if pa.types.is_string(self._pa_array.type):
+                    other_array = self._box_pa(other)
+                    if pa.types.is_string(other_array.type):
+                        other_array = other_array.cast(pa.large_string())
+                    result = pc_func(self._pa_array, other_array)
+                else:
+                    result = pc_func(self._pa_array, self._box_pa(other))
             except pa.ArrowNotImplementedError:
                 # TODO: could this be wrong if other is object dtype?
                 #  in which case we need to operate pointwise?

pandas/core/ops/array_ops.py

@@ -40,7 +40,6 @@
     is_numeric_v_string_like,
     is_object_dtype,
     is_scalar,
-    is_string_dtype,
 )
 from pandas.core.dtypes.generic import (
     ABCExtensionArray,
@@ -54,10 +53,7 @@
 
 from pandas.core import roperator
 from pandas.core.computation import expressions
-from pandas.core.construction import (
-    array as pd_array,
-    ensure_wrapped_if_datetimelike,
-)
+from pandas.core.construction import ensure_wrapped_if_datetimelike
 from pandas.core.ops import missing
 from pandas.core.ops.dispatch import should_extension_dispatch
 from pandas.core.ops.invalid import invalid_comparison
@@ -325,16 +321,6 @@ def comparison_op(left: ArrayLike, right: Any, op) -> ArrayLike:
                 "Lengths must match to compare", lvalues.shape, rvalues.shape
             )
 
-    if (is_string_dtype(lvalues) and is_object_dtype(rvalues)) or (
-        is_object_dtype(lvalues) and is_string_dtype(rvalues)
-    ):
-        if lvalues.dtype.name == "string" and rvalues.dtype == object:
-            lvalues = lvalues.astype("string")
-            rvalues = pd_array(rvalues, dtype="string")
-        elif rvalues.dtype.name == "string" and lvalues.dtype == object:
-            rvalues = rvalues.astype("string")
-            lvalues = pd_array(lvalues, dtype="string")
-
     if should_extension_dispatch(lvalues, rvalues) or (
         (isinstance(rvalues, (Timedelta, BaseOffset, Timestamp)) or right is NaT)
         and lvalues.dtype != object