Backport PR #58590 on branch 2.2.x (BUG: Use large_string in string array consistently) (#58597)

Backport PR #58590: BUG: Use large_string in string array consistently

Co-authored-by: Patrick Hoefler <[email protected]>

Author: meeseeksmachine

pandas/core/arrays/string_arrow.py

@@ -190,13 +190,13 @@ def _from_sequence(cls, scalars, *, dtype: Dtype | None = None, copy: bool = Fal
             na_values = scalars._mask
             result = scalars._data
             result = lib.ensure_string_array(result, copy=copy, convert_na_value=False)
-            return cls(pa.array(result, mask=na_values, type=pa.string()))
+            return cls(pa.array(result, mask=na_values, type=pa.large_string()))
         elif isinstance(scalars, (pa.Array, pa.ChunkedArray)):
-            return cls(pc.cast(scalars, pa.string()))
+            return cls(pc.cast(scalars, pa.large_string()))
 
         # convert non-na-likes to str
         result = lib.ensure_string_array(scalars, copy=copy)
-        return cls(pa.array(result, type=pa.string(), from_pandas=True))
+        return cls(pa.array(result, type=pa.large_string(), from_pandas=True))
 
     @classmethod
     def _from_sequence_of_strings(
@@ -239,7 +239,7 @@ def isin(self, values: ArrayLike) -> npt.NDArray[np.bool_]:
         value_set = [
             pa_scalar.as_py()
             for pa_scalar in [pa.scalar(value, from_pandas=True) for value in values]
-            if pa_scalar.type in (pa.string(), pa.null())
+            if pa_scalar.type in (pa.string(), pa.null(), pa.large_string())
         ]
 
         # short-circuit to return all False array.
@@ -337,7 +337,9 @@ def _str_map(
             result = lib.map_infer_mask(
                 arr, f, mask.view("uint8"), convert=False, na_value=na_value
             )
-            result = pa.array(result, mask=mask, type=pa.string(), from_pandas=True)
+            result = pa.array(
+                result, mask=mask, type=pa.large_string(), from_pandas=True
+            )
             return type(self)(result)
         else:
             # This is when the result type is object. We reach this when
@@ -658,7 +660,9 @@ def _str_map(
             result = lib.map_infer_mask(
                 arr, f, mask.view("uint8"), convert=False, na_value=na_value
             )
-            result = pa.array(result, mask=mask, type=pa.string(), from_pandas=True)
+            result = pa.array(
+                result, mask=mask, type=pa.large_string(), from_pandas=True
+            )
             return type(self)(result)
         else:
             # This is when the result type is object. We reach this when