From 7803361518dc7dd95304f6c38ff6ad08fb601fac Mon Sep 17 00:00:00 2001
From: Patrick Hoefler <61934744+phofl@users.noreply.github.com>
Date: Sat, 2 Sep 2023 14:59:01 +0200
Subject: [PATCH] ENH: Implement more string accessors through PyArrow

---
 pandas/core/arrays/string_arrow.py | 31 ++++++++++++++++++++++--------
 1 file changed, 23 insertions(+), 8 deletions(-)

diff --git a/pandas/core/arrays/string_arrow.py b/pandas/core/arrays/string_arrow.py
index f438f75707265..0fd0979103c44 100644
--- a/pandas/core/arrays/string_arrow.py
+++ b/pandas/core/arrays/string_arrow.py
@@ -47,6 +47,8 @@
 
 
 if TYPE_CHECKING:
+    from collections.abc import Sequence
+
     from pandas._typing import (
         Dtype,
         Scalar,
@@ -334,19 +336,13 @@ def _str_startswith(self, pat: str, na=None):
         result = pc.starts_with(self._pa_array, pattern=pat)
         if not isna(na):
             result = result.fill_null(na)
-        result = self._result_converter(result)
-        if not isna(na):
-            result[isna(result)] = bool(na)
-        return result
+        return self._result_converter(result)
 
     def _str_endswith(self, pat: str, na=None):
         result = pc.ends_with(self._pa_array, pattern=pat)
         if not isna(na):
             result = result.fill_null(na)
-        result = self._result_converter(result)
-        if not isna(na):
-            result[isna(result)] = bool(na)
-        return result
+        return self._result_converter(result)
 
     def _str_replace(
         self,
@@ -365,6 +361,12 @@ def _str_replace(
         result = func(self._pa_array, pattern=pat, replacement=repl, max_replacements=n)
         return type(self)(result)
 
+    def _str_repeat(self, repeats: int | Sequence[int]):
+        if not isinstance(repeats, int):
+            return super()._str_repeat(repeats)
+        else:
+            return type(self)(pc.binary_repeat(self._pa_array, repeats))
+
     def _str_match(
         self, pat: str, case: bool = True, flags: int = 0, na: Scalar | None = None
     ):
@@ -379,6 +381,19 @@ def _str_fullmatch(
             pat = f"{pat}$"
         return self._str_match(pat, case, flags, na)
 
+    def _str_slice(
+        self, start: int | None = None, stop: int | None = None, step: int | None = None
+    ):
+        if stop is None:
+            return super()._str_slice(start, stop, step)
+        if start is None:
+            start = 0
+        if step is None:
+            step = 1
+        return type(self)(
+            pc.utf8_slice_codeunits(self._pa_array, start=start, stop=stop, step=step)
+        )
+
     def _str_isalnum(self):
         result = pc.utf8_is_alnum(self._pa_array)
         return self._result_converter(result)