BUG fix for str.startswith and str.endswith with tuple arg for "string[pyarrow]" dtype (GH#54942) (#54943)

* TST: added failing tuple tests for `str.startswith` and `str.startswith` (#54942)

* FIX: added fix for `str.startswith` and `str.endswith` with tuple arg for `"string[pyarrow]"` dtype (GH#54942)

* DOCS: added entry to whatsnew

* DOCS: moved contrib note to `Strings` section and fixed typos

* PERF: exchanged boolean array creation to method with less overhead

* CLN: removed unnecessary type checks

* DOCS: removed extra space before GH reference

---------

Co-authored-by: Matthew Roeschke <[email protected]>

Author: ChronoJon

doc/source/whatsnew/v2.2.0.rst

@@ -332,7 +332,7 @@ Conversion
 Strings
 ^^^^^^^
 - Bug in :func:`pandas.api.types.is_string_dtype` while checking object array with no elements is of the string dtype (:issue:`54661`)
--
+- Bug in :meth:`Series.str.startswith` and :meth:`Series.str.endswith` with arguments of type ``tuple[str, ...]`` for ``string[pyarrow]`` (:issue:`54942`)
 -
 
 Interval

pandas/core/arrays/string_arrow.py

@@ -336,14 +336,40 @@ def _str_contains(
             result[isna(result)] = bool(na)
         return result
 
-    def _str_startswith(self, pat: str, na=None):
-        result = pc.starts_with(self._pa_array, pattern=pat)
+    def _str_startswith(self, pat: str | tuple[str, ...], na: Scalar | None = None):
+        if isinstance(pat, str):
+            result = pc.starts_with(self._pa_array, pattern=pat)
+        else:
+            if len(pat) == 0:
+                # mimic existing behaviour of string extension array
+                # and python string method
+                result = pa.array(
+                    np.zeros(len(self._pa_array), dtype=bool), mask=isna(self._pa_array)
+                )
+            else:
+                result = pc.starts_with(self._pa_array, pattern=pat[0])
+
+                for p in pat[1:]:
+                    result = pc.or_(result, pc.starts_with(self._pa_array, pattern=p))
         if not isna(na):
             result = result.fill_null(na)
         return self._result_converter(result)
 
-    def _str_endswith(self, pat: str, na=None):
-        result = pc.ends_with(self._pa_array, pattern=pat)
+    def _str_endswith(self, pat: str | tuple[str, ...], na: Scalar | None = None):
+        if isinstance(pat, str):
+            result = pc.ends_with(self._pa_array, pattern=pat)
+        else:
+            if len(pat) == 0:
+                # mimic existing behaviour of string extension array
+                # and python string method
+                result = pa.array(
+                    np.zeros(len(self._pa_array), dtype=bool), mask=isna(self._pa_array)
+                )
+            else:
+                result = pc.ends_with(self._pa_array, pattern=pat[0])
+
+                for p in pat[1:]:
+                    result = pc.or_(result, pc.ends_with(self._pa_array, pattern=p))
         if not isna(na):
             result = result.fill_null(na)
         return self._result_converter(result)

pandas/tests/strings/conftest.py

@@ -13,6 +13,10 @@
     ("decode", ("UTF-8",), {}),
     ("encode", ("UTF-8",), {}),
     ("endswith", ("a",), {}),
+    ("endswith", ((),), {}),
+    ("endswith", (("a",),), {}),
+    ("endswith", (("a", "b"),), {}),
+    ("endswith", (("a", "MISSING"),), {}),
     ("endswith", ("a",), {"na": True}),
     ("endswith", ("a",), {"na": False}),
     ("extract", ("([a-z]*)",), {"expand": False}),
@@ -44,6 +48,10 @@
     ("split", (" ",), {"expand": False}),
     ("split", (" ",), {"expand": True}),
     ("startswith", ("a",), {}),
+    ("startswith", (("a",),), {}),
+    ("startswith", (("a", "b"),), {}),
+    ("startswith", (("a", "MISSING"),), {}),
+    ("startswith", ((),), {}),
     ("startswith", ("a",), {"na": True}),
     ("startswith", ("a",), {"na": False}),
     ("removeprefix", ("a",), {}),