add additional test for custom flags being respected

Author: jorisvandenbossche

pandas/core/arrays/string_arrow.py

@@ -348,6 +348,15 @@ def astype(self, dtype, copy: bool = True):
     _str_len = ArrowStringArrayMixin._str_len
     _str_slice = ArrowStringArrayMixin._str_slice
 
+    @staticmethod
+    def _is_re_pattern_with_flags(pat: str | re.Pattern) -> bool:
+        # check if `pat` is a compiled regex pattern with flags that are not
+        # supported by pyarrow
+        return (
+            isinstance(pat, re.Pattern)
+            and (pat.flags & ~(re.IGNORECASE | re.UNICODE)) != 0
+        )
+
     @staticmethod
     def _preprocess_re_pattern(pat: re.Pattern, case: bool):
         flags = pat.flags
@@ -369,12 +378,11 @@ def _str_contains(
         na=lib.no_default,
         regex: bool = True,
     ):
-        if flags:
+        if flags or self._is_re_pattern_with_flags(pat):
             return super()._str_contains(pat, case, flags, na, regex)
         if isinstance(pat, re.Pattern):
+            # TODO flags passed separately by user are ignored
             pat, case, flags = self._preprocess_re_pattern(pat, case)
-            if flags:
-                return super()._str_contains(pat, case, flags, na, regex)
 
         return ArrowStringArrayMixin._str_contains(self, pat, case, flags, na, regex)
 
@@ -385,12 +393,10 @@ def _str_match(
         flags: int = 0,
         na: Scalar | lib.NoDefault = lib.no_default,
     ):
-        if flags:
+        if flags or self._is_re_pattern_with_flags(pat):
             return super()._str_match(pat, case, flags, na)
         if isinstance(pat, re.Pattern):
             pat, case, flags = self._preprocess_re_pattern(pat, case)
-            if flags:
-                return super()._str_match(pat, case, flags, na)
 
         return ArrowStringArrayMixin._str_match(self, pat, case, flags, na)
 
@@ -401,12 +407,10 @@ def _str_fullmatch(
         flags: int = 0,
         na: Scalar | lib.NoDefault = lib.no_default,
     ):
-        if flags:
+        if flags or self._is_re_pattern_with_flags(pat):
             return super()._str_fullmatch(pat, case, flags, na)
         if isinstance(pat, re.Pattern):
             pat, case, flags = self._preprocess_re_pattern(pat, case)
-            if flags:
-                return super()._str_fullmatch(pat, case, flags, na)
 
         return ArrowStringArrayMixin._str_fullmatch(self, pat, case, flags, na)
 

pandas/tests/strings/test_find_replace.py

@@ -317,6 +317,30 @@ def test_contains_compiled_regex(any_string_dtype):
         ser.str.contains(pat, flags=re.IGNORECASE)
 
 
+def test_contains_compiled_regex_flags(any_string_dtype):
+    # ensure other (than ignorecase) flags are respected
+    expected_dtype = (
+        np.bool_ if is_object_or_nan_string_dtype(any_string_dtype) else "boolean"
+    )
+
+    ser = Series(["foobar", "foo\nbar", "Baz"], dtype=any_string_dtype)
+
+    pat = re.compile("^ba")
+    result = ser.str.contains(pat)
+    expected = Series([False, False, False], dtype=expected_dtype)
+    tm.assert_series_equal(result, expected)
+
+    pat = re.compile("^ba", flags=re.MULTILINE)
+    result = ser.str.contains(pat)
+    expected = Series([False, True, False], dtype=expected_dtype)
+    tm.assert_series_equal(result, expected)
+
+    pat = re.compile("^ba", flags=re.MULTILINE | re.IGNORECASE)
+    result = ser.str.contains(pat)
+    expected = Series([False, True, True], dtype=expected_dtype)
+    tm.assert_series_equal(result, expected)
+
+
 # --------------------------------------------------------------------------------------
 # str.startswith
 # --------------------------------------------------------------------------------------