REF: move implementations to mixin

Author: jbrockmendel

pandas/core/arrays/_arrow_string_mixins.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 from functools import partial
+import re
 from typing import (
     TYPE_CHECKING,
     Any,
@@ -159,6 +160,33 @@ def _str_slice_replace(
             stop = np.iinfo(np.int64).max
         return type(self)(pc.utf8_replace_slice(self._pa_array, start, stop, repl))
 
+    def _str_replace(
+        self,
+        pat: str | re.Pattern,
+        repl: str | Callable,
+        n: int = -1,
+        case: bool = True,
+        flags: int = 0,
+        regex: bool = True,
+    ) -> Self:
+        if isinstance(pat, re.Pattern) or callable(repl) or not case or flags:
+            raise NotImplementedError(
+                "replace is not supported with a re.Pattern, callable repl, "
+                "case=False, or flags!=0"
+            )
+
+        func = pc.replace_substring_regex if regex else pc.replace_substring
+        # https://github.com/apache/arrow/issues/39149
+        # GH 56404, unexpected behavior with negative max_replacements with pyarrow.
+        pa_max_replacements = None if n < 0 else n
+        result = func(
+            self._pa_array,
+            pattern=pat,
+            replacement=repl,
+            max_replacements=pa_max_replacements,
+        )
+        return type(self)(result)
+
     def _str_capitalize(self) -> Self:
         return type(self)(pc.utf8_capitalize(self._pa_array))
 
@@ -168,6 +196,16 @@ def _str_title(self) -> Self:
     def _str_swapcase(self) -> Self:
         return type(self)(pc.utf8_swapcase(self._pa_array))
 
+    def _str_removeprefix(self, prefix: str):
+        if not pa_version_under13p0:
+            starts_with = pc.starts_with(self._pa_array, pattern=prefix)
+            removed = pc.utf8_slice_codeunits(self._pa_array, len(prefix))
+            result = pc.if_else(starts_with, removed, self._pa_array)
+            return type(self)(result)
+        predicate = lambda val: val.removeprefix(prefix)
+        result = self._apply_elementwise(predicate)
+        return type(self)(pa.chunked_array(result))
+
     def _str_removesuffix(self, suffix: str):
         ends_with = pc.ends_with(self._pa_array, pattern=suffix)
         removed = pc.utf8_slice_codeunits(self._pa_array, 0, stop=-len(suffix))

pandas/core/arrays/arrow/array.py

@@ -2323,33 +2323,6 @@ def _str_count(self, pat: str, flags: int = 0) -> Self:
             raise NotImplementedError(f"count not implemented with {flags=}")
         return type(self)(pc.count_substring_regex(self._pa_array, pat))
 
-    def _str_replace(
-        self,
-        pat: str | re.Pattern,
-        repl: str | Callable,
-        n: int = -1,
-        case: bool = True,
-        flags: int = 0,
-        regex: bool = True,
-    ) -> Self:
-        if isinstance(pat, re.Pattern) or callable(repl) or not case or flags:
-            raise NotImplementedError(
-                "replace is not supported with a re.Pattern, callable repl, "
-                "case=False, or flags!=0"
-            )
-
-        func = pc.replace_substring_regex if regex else pc.replace_substring
-        # https://github.com/apache/arrow/issues/39149
-        # GH 56404, unexpected behavior with negative max_replacements with pyarrow.
-        pa_max_replacements = None if n < 0 else n
-        result = func(
-            self._pa_array,
-            pattern=pat,
-            replacement=repl,
-            max_replacements=pa_max_replacements,
-        )
-        return type(self)(result)
-
     def _str_repeat(self, repeats: int | Sequence[int]) -> Self:
         if not isinstance(repeats, int):
             raise NotImplementedError(
@@ -2377,16 +2350,6 @@ def _str_rpartition(self, sep: str, expand: bool) -> Self:
         result = self._apply_elementwise(predicate)
         return type(self)(pa.chunked_array(result))
 
-    def _str_removeprefix(self, prefix: str):
-        if not pa_version_under13p0:
-            starts_with = pc.starts_with(self._pa_array, pattern=prefix)
-            removed = pc.utf8_slice_codeunits(self._pa_array, len(prefix))
-            result = pc.if_else(starts_with, removed, self._pa_array)
-            return type(self)(result)
-        predicate = lambda val: val.removeprefix(prefix)
-        result = self._apply_elementwise(predicate)
-        return type(self)(pa.chunked_array(result))
-
     def _str_casefold(self) -> Self:
         predicate = lambda val: val.casefold()
         result = self._apply_elementwise(predicate)