gh-111259: Optimize complementary character sets in RE (GH-120742)

Patterns like "[\s\S]" or "\s|\S" which match any character are now compiled
to the same effective code as a dot with the DOTALL modifier ("(?s:.)").

1 files changed, 18 insertions, 0 deletions

diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py
index 1f2ab60..a93c2ae 100644
--- a/Lib/test/test_re.py
+++ b/Lib/test/test_re.py
@@ -2473,6 +2473,24 @@ class ReTests(unittest.TestCase):
     def test_fail(self):
         self.assertEqual(re.search(r'12(?!)|3', '123')[0], '3')
 
+    def test_character_set_any(self):
+        # The union of complementary character sets mathes any character
+        # and is equivalent to "(?s:.)".
+        s = '1x\n'
+        for p in r'[\s\S]', r'[\d\D]', r'[\w\W]', r'[\S\s]', r'\s|\S':
+            with self.subTest(pattern=p):
+                self.assertEqual(re.findall(p, s), list(s))
+                self.assertEqual(re.fullmatch('(?:' + p + ')+', s).group(), s)
+
+    def test_character_set_none(self):
+        # Negation of the union of complementary character sets does not match
+        # any character.
+        s = '1x\n'
+        for p in r'[^\s\S]', r'[^\d\D]', r'[^\w\W]', r'[^\S\s]':
+            with self.subTest(pattern=p):
+                self.assertIsNone(re.search(p, s))
+                self.assertIsNone(re.search('(?s:.)' + p, s))
+
 
 def get_debug_out(pat):
     with captured_stdout() as out: