Check parenthesis

Lib/email/utils.py

@@ -104,28 +104,37 @@ def formataddr(pair, charset='utf-8'):
     return address
 
 
+def _iter_escaped_chars(addr):
+    pos = 0
+    escape = False
+    for pos, ch in enumerate(addr):
+        if ch == '\\' and not escape:
+            escape = True
+        else:
+            if escape:
+                yield (pos, '\\' + ch)
+            else:
+                yield (pos, ch)
+            escape = False
+    if escape:
+        yield (pos, '\\')
+
+
 def _strip_quoted_realnames(addr):
     """Strip real names between quotes."""
     if '"' not in addr:
         # Fast path
         return addr
 
-    pos = 0
     start = None
     remove = []
-    previous = None
-    while pos < len(addr):
-        ch = addr[pos]
-        if ch == '"' and previous != '\\':
+    for pos, ch in _iter_escaped_chars(addr):
+        if ch == '"':
             if start is None:
                 start = pos
             else:
                 remove.append((start, pos))
                 start = None
-        elif ch == '\\' and previous == '\\':
-            previous = None
-        previous = ch
-        pos += 1
 
     result = []
     pos = 0
@@ -180,11 +189,25 @@ def getaddresses(fieldvalues, *, strict=True):
     return result
 
 
+def _check_parenthesis(addr):
+    # Ignore parenthesis in quoted real names.
+    addr = _strip_quoted_realnames(addr)
+
+    opens = 0
+    for pos, ch in _iter_escaped_chars(addr):
+        if ch == '(':
+            opens += 1
+        elif ch == ')':
+            opens -= 1
+            if opens < 0:
+                return False
+    return (opens == 0)
+
+
 def _pre_parse_validation(email_header_fields):
     accepted_values = []
     for v in email_header_fields:
-        s = v.replace('\\(', '').replace('\\)', '')
-        if s.count('(') != s.count(')'):
+        if not _check_parenthesis(v):
             v = "('', '')"
         accepted_values.append(v)
 

Lib/test/test_email/test_email.py

@@ -3638,6 +3638,19 @@ def test_mime_classes_policy_argument(self):
                 m = cls(*constructor, policy=email.policy.default)
                 self.assertIs(m.policy, email.policy.default)
 
+    def test_iter_escaped_chars(self):
+        self.assertEqual(list(utils._iter_escaped_chars(r'a\\b\"c\\"d')),
+                         [(0, 'a'),
+                          (2, '\\\\'),
+                          (3, 'b'),
+                          (5, '\\"'),
+                          (6, 'c'),
+                          (8, '\\\\'),
+                          (9, '"'),
+                          (10, 'd')])
+        self.assertEqual(list(utils._iter_escaped_chars('a\\')),
+                         [(0, 'a'), (1, '\\')])
+
     def test_strip_quoted_realnames(self):
         def check(addr, expected):
             self.assertEqual(utils._strip_quoted_realnames(addr), expected)
@@ -3646,9 +3659,19 @@ def check(addr, expected):
               'Jane Doe <[email protected]>, John Doe <[email protected]>')
         check('"Jane Doe" <[email protected]>, "John Doe" <[email protected]>',
               ' <[email protected]>,  <[email protected]>')
-        check(r'"Jane \"Doe"." <[email protected]>',
+        check(r'"Jane \"Doe\"." <[email protected]>',
               ' <[email protected]>')
 
+    def test_check_parenthesis(self):
+        addr = '[email protected]'
+        self.assertTrue(utils._check_parenthesis(f'{addr} (Alice)'))
+        self.assertFalse(utils._check_parenthesis(f'{addr} )Alice('))
+        self.assertFalse(utils._check_parenthesis(f'{addr} (Alice))'))
+        self.assertFalse(utils._check_parenthesis(f'{addr} ((Alice)'))
+
+        # Ignore real name between quotes
+        self.assertTrue(utils._check_parenthesis(f'")Alice((" {addr}'))
+
 
 # Test the iterator/generators
 class TestIterators(TestEmailBase):