Fix pandas-dev#61072: inconsistent fullmatch results with regex alternation in PyArrow strings

Fixes an issue where regex patterns with alternation (|) produce
different results between str dtype and string[pyarrow] dtype. When
using patterns like "(as)|(as)", PyArrow implementation would
incorrectly match "asdf" while Python's implementation correctly
rejects it. The fix adds special handling to ensure alternation
patterns are properly parenthesized when using PyArrow-backed strings.

Author: Pedro-Santos04

pandas/core/strings/accessor.py

@@ -1504,7 +1504,6 @@ def fullmatch(self, pat, case: bool = True, flags: int = 0, na=lib.no_default):
 
         # Handle pattern modification for PyArrow implementation
         if is_pyarrow and "|" in pat:
-            # For patterns with alternation, ensure they're properly grouped for PyArrow
             def _is_fully_wrapped(pattern):
                 if not (pattern.startswith('(') and pattern.endswith(')')):
                     return False
@@ -1535,9 +1534,11 @@ def _is_fully_wrapped(pattern):
                                 return False
                             level -= 1
 
-                # If we end with zero level, the outer parentheses fully wrap the pattern
+                # If we end with zero level, 
+                #        the outer parentheses fully wrap the pattern
                 return level == 0
 
+            
             if not (pat.startswith('(') and pat.endswith(')') and 
                     _is_fully_wrapped(pat)):
                 pat = f"({pat})"

pandas/tests/test.py

@@ -2,12 +2,6 @@
 print(pandas.__version__)
 
 
-ser = pandas.Series(["cat", "duck", "dove"])
-print(ser.str.fullmatch(r"d.+"))
-#False
-#True
-#True
-
 test_series = pandas.Series(['asdf', 'as'], dtype='string[pyarrow]')
 regex = r'((as)|(as))'
 regex2 = r'(as)|(as)'
@@ -27,4 +21,11 @@
 # True
 print(test_series2.str.fullmatch(regex2))
 # False
-# True
+# True
+
+
+ser = pandas.Series(["cat", "duck", "dove"])
+print(ser.str.fullmatch(r"d.+"))
+#False
+#True
+#True