1 files changed, 31 insertions, 9 deletions
diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py
index 0584f19..0e4fa88 100644
--- a/Lib/test/test_re.py
+++ b/Lib/test/test_re.py
@@ -154,8 +154,8 @@ class ReTests(unittest.TestCase):
         self.assertEqual(re.sub('x', r'\09', 'x'), '\0' + '9')
         self.assertEqual(re.sub('x', r'\0a', 'x'), '\0' + 'a')
 
-        self.assertEqual(re.sub('x', r'\400', 'x'), '\0')
-        self.assertEqual(re.sub('x', r'\777', 'x'), '\377')
+        self.assertRaises(re.error, re.sub, 'x', r'\400', 'x')
+        self.assertRaises(re.error, re.sub, 'x', r'\777', 'x')
 
         self.assertRaises(re.error, re.sub, 'x', r'\1', 'x')
         self.assertRaises(re.error, re.sub, 'x', r'\8', 'x')
@@ -193,6 +193,7 @@ class ReTests(unittest.TestCase):
     def test_symbolic_groups(self):
         re.compile('(?P<a>x)(?P=a)(?(a)y)')
         re.compile('(?P<a1>x)(?P=a1)(?(a1)y)')
+        re.compile('(?P<a1>x)\1(?(1)y)')
         self.assertRaises(re.error, re.compile, '(?P<a>)(?P<a>)')
         self.assertRaises(re.error, re.compile, '(?Px)')
         self.assertRaises(re.error, re.compile, '(?P=)')
@@ -212,6 +213,10 @@ class ReTests(unittest.TestCase):
         re.compile('(?P<µ>x)(?P=µ)(?(µ)y)')
         re.compile('(?P<𝔘𝔫𝔦𝔠𝔬𝔡𝔢>x)(?P=𝔘𝔫𝔦𝔠𝔬𝔡𝔢)(?(𝔘𝔫𝔦𝔠𝔬𝔡𝔢)y)')
         self.assertRaises(re.error, re.compile, '(?P<©>x)')
+        # Support > 100 groups.
+        pat = '|'.join('x(?P<a%d>%x)y' % (i, i) for i in range(1, 200 + 1))
+        pat = '(?:%s)(?(200)z|t)' % pat
+        self.assertEqual(re.match(pat, 'xc8yz').span(), (0, 5))
 
     def test_symbolic_refs(self):
         self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<a', 'xx')
@@ -220,14 +225,19 @@ class ReTests(unittest.TestCase):
         self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<a a>', 'xx')
         self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<>', 'xx')
         self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<1a1>', 'xx')
+        self.assertRaises(re.error, re.sub, '(?P<a>x)', r'\g<2>', 'xx')
+        self.assertRaises(re.error, re.sub, '(?P<a>x)', r'\2', 'xx')
         self.assertRaises(IndexError, re.sub, '(?P<a>x)', '\g<ab>', 'xx')
-        self.assertRaises(re.error, re.sub, '(?P<a>x)|(?P<b>y)', '\g<b>', 'xx')
-        self.assertRaises(re.error, re.sub, '(?P<a>x)|(?P<b>y)', '\\2', 'xx')
+        self.assertEqual(re.sub('(?P<a>x)|(?P<b>y)', r'\g<b>', 'xx'), '')
+        self.assertEqual(re.sub('(?P<a>x)|(?P<b>y)', r'\2', 'xx'), '')
         self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<-1>', 'xx')
         # New valid/invalid identifiers in Python 3
         self.assertEqual(re.sub('(?P<µ>x)', r'\g<µ>', 'xx'), 'xx')
         self.assertEqual(re.sub('(?P<𝔘𝔫𝔦𝔠𝔬𝔡𝔢>x)', r'\g<𝔘𝔫𝔦𝔠𝔬𝔡𝔢>', 'xx'), 'xx')
         self.assertRaises(re.error, re.sub, '(?P<a>x)', r'\g<©>', 'xx')
+        # Support > 100 groups.
+        pat = '|'.join('x(?P<a%d>%x)y' % (i, i) for i in range(1, 200 + 1))
+        self.assertEqual(re.sub(pat, '\g<200>', 'xc8yzxc8y'), 'c8zc8')
 
     def test_re_subn(self):
         self.assertEqual(re.subn("(?i)b+", "x", "bbbb BBBB"), ('x x', 2))
@@ -404,6 +414,10 @@ class ReTests(unittest.TestCase):
         self.assertIsNone(p.match('abd'))
         self.assertIsNone(p.match('ac'))
 
+        # Support > 100 groups.
+        pat = '|'.join('x(?P<a%d>%x)y' % (i, i) for i in range(1, 200 + 1))
+        pat = '(?:%s)(?(200)z)' % pat
+        self.assertEqual(re.match(pat, 'xc8yz').span(), (0, 5))
 
     def test_re_groupref(self):
         self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', '|a|').groups(),
@@ -427,6 +441,10 @@ class ReTests(unittest.TestCase):
                                   "first second")
                                   .expand(r"\2 \1 \g<second> \g<first>"),
                          "second first second first")
+        self.assertEqual(re.match("(?P<first>first)|(?P<second>second)",
+                                  "first")
+                                  .expand(r"\2 \g<second>"),
+                         " ")
 
     def test_repeat_minmax(self):
         self.assertIsNone(re.match("^(\w){1}$", "abc"))
@@ -700,7 +718,7 @@ class ReTests(unittest.TestCase):
         self.assertTrue(re.match(r"\08", "\0008"))
         self.assertTrue(re.match(r"\01", "\001"))
         self.assertTrue(re.match(r"\018", "\0018"))
-        self.assertTrue(re.match(r"\567", chr(0o167)))
+        self.assertRaises(re.error, re.match, r"\567", "")
         self.assertRaises(re.error, re.match, r"\911", "")
         self.assertRaises(re.error, re.match, r"\x1", "")
         self.assertRaises(re.error, re.match, r"\x1z", "")
@@ -728,12 +746,13 @@ class ReTests(unittest.TestCase):
             self.assertTrue(re.match(r"[\U%08x]" % i, chr(i)))
             self.assertTrue(re.match(r"[\U%08x0]" % i, chr(i)+"0"))
             self.assertTrue(re.match(r"[\U%08xz]" % i, chr(i)+"z"))
-        self.assertTrue(re.match(r"[\U0001d49c-\U0001d4b5]", "\U0001d49e"))
+        self.assertRaises(re.error, re.match, r"[\567]", "")
         self.assertRaises(re.error, re.match, r"[\911]", "")
         self.assertRaises(re.error, re.match, r"[\x1z]", "")
         self.assertRaises(re.error, re.match, r"[\u123z]", "")
         self.assertRaises(re.error, re.match, r"[\U0001234z]", "")
         self.assertRaises(re.error, re.match, r"[\U00110000]", "")
+        self.assertTrue(re.match(r"[\U0001d49c-\U0001d4b5]", "\U0001d49e"))
 
     def test_sre_byte_literals(self):
         for i in [0, 8, 16, 32, 64, 127, 128, 255]:
@@ -749,7 +768,7 @@ class ReTests(unittest.TestCase):
         self.assertTrue(re.match(br"\08", b"\0008"))
         self.assertTrue(re.match(br"\01", b"\001"))
         self.assertTrue(re.match(br"\018", b"\0018"))
-        self.assertTrue(re.match(br"\567", bytes([0o167])))
+        self.assertRaises(re.error, re.match, br"\567", b"")
         self.assertRaises(re.error, re.match, br"\911", b"")
         self.assertRaises(re.error, re.match, br"\x1", b"")
         self.assertRaises(re.error, re.match, br"\x1z", b"")
@@ -766,6 +785,7 @@ class ReTests(unittest.TestCase):
             self.assertTrue(re.match((r"[\x%02xz]" % i).encode(), bytes([i])))
         self.assertTrue(re.match(br"[\u]", b'u'))
         self.assertTrue(re.match(br"[\U]", b'U'))
+        self.assertRaises(re.error, re.match, br"[\567]", b"")
         self.assertRaises(re.error, re.match, br"[\911]", b"")
         self.assertRaises(re.error, re.match, br"[\x1z]", b"")
 
@@ -1068,8 +1088,10 @@ class ReTests(unittest.TestCase):
         # a RuntimeError is raised instead of OverflowError.
         long_overflow = 2**128
         self.assertRaises(TypeError, re.finditer, "a", {})
-        self.assertRaises(OverflowError, _sre.compile, "abc", 0, [long_overflow])
-        self.assertRaises(TypeError, _sre.compile, {}, 0, [])
+        with self.assertRaises(OverflowError):
+            _sre.compile("abc", 0, [long_overflow], 0, [], [])
+        with self.assertRaises(TypeError):
+            _sre.compile({}, 0, [], 0, [], [])
 
     def test_search_dot_unicode(self):
         self.assertTrue(re.search("123.*-", '123abc-'))