REF: move implementation to ArrowStringArrayMixin

Author: jbrockmendel

pandas/core/arrays/_arrow_string_mixins.py

@@ -23,6 +23,10 @@ class ArrowStringArrayMixin:
     def __init__(self, *args, **kwargs) -> None:
         raise NotImplementedError
 
+    def _convert_int_dtype(self, result):
+        # Convert an int-dtype arrow result to an appropriate output type.
+        raise NotImplementedError
+
     def _str_pad(
         self,
         width: int,
@@ -89,3 +93,26 @@ def _str_removesuffix(self, suffix: str):
         removed = pc.utf8_slice_codeunits(self._pa_array, 0, stop=-len(suffix))
         result = pc.if_else(ends_with, removed, self._pa_array)
         return type(self)(result)
+
+    def _str_find(self, sub: str, start: int = 0, end: int | None = None):
+        if (start == 0 or start is None) and end is None:
+            result = pc.find_substring(self._pa_array, sub)
+        else:
+            if sub == "":
+                # GH#56792
+                result = self._apply_elementwise(lambda val: val.find(sub, start, end))
+                return self._convert_int_dtype(pa.chunked_array(result))
+            if start is None:
+                start_offset = 0
+                start = 0
+            elif start < 0:
+                start_offset = pc.add(start, pc.utf8_length(self._pa_array))
+                start_offset = pc.if_else(pc.less(start_offset, 0), 0, start_offset)
+            else:
+                start_offset = start
+            slices = pc.utf8_slice_codeunits(self._pa_array, start, stop=end)
+            result = pc.find_substring(slices, sub)
+            found = pc.not_equal(result, pa.scalar(-1, type=result.type))
+            offset_result = pc.add(result, start_offset)
+            result = pc.if_else(found, offset_result, -1)
+        return self._convert_int_dtype(result)

pandas/core/arrays/arrow/array.py

@@ -2390,29 +2390,6 @@ def _str_fullmatch(
     def _convert_int_dtype(self, result):
         return type(self)(result)
 
-    def _str_find(self, sub: str, start: int = 0, end: int | None = None) -> Self:
-        if (start == 0 or start is None) and end is None:
-            result = pc.find_substring(self._pa_array, sub)
-        else:
-            if sub == "":
-                # GH 56792
-                result = self._apply_elementwise(lambda val: val.find(sub, start, end))
-                return self._convert_int_dtype(pa.chunked_array(result))
-            if start is None:
-                start_offset = 0
-                start = 0
-            elif start < 0:
-                start_offset = pc.add(start, pc.utf8_length(self._pa_array))
-                start_offset = pc.if_else(pc.less(start_offset, 0), 0, start_offset)
-            else:
-                start_offset = start
-            slices = pc.utf8_slice_codeunits(self._pa_array, start, stop=end)
-            result = pc.find_substring(slices, sub)
-            found = pc.not_equal(result, pa.scalar(-1, type=result.type))
-            offset_result = pc.add(result, start_offset)
-            result = pc.if_else(found, offset_result, -1)
-        return self._convert_int_dtype(result)
-
     def _str_join(self, sep: str) -> Self:
         if pa.types.is_string(self._pa_array.type) or pa.types.is_large_string(
             self._pa_array.type

pandas/core/arrays/string_arrow.py

@@ -482,7 +482,7 @@ def _str_find(self, sub: str, start: int = 0, end: int | None = None):
         ):
             # https://github.com/pandas-dev/pandas/pull/59562/files#r1725688888
             return super()._str_find(sub, start, end)
-        return ArrowExtensionArray._str_find(self, sub, start, end)
+        return ArrowStringArrayMixin._str_find(self, sub, start, end)
 
     def _str_get_dummies(self, sep: str = "|"):
         dummies_pa, labels = ArrowExtensionArray(self._pa_array)._str_get_dummies(sep)