bpo-34155: Dont parse domains containing @ (GH-13079)

Before:

        >>> email.message_from_string('From: a@malicious.org@important.com', policy=email.policy.default)['from'].addresses
        (Address(display_name='', username='a', domain='malicious.org'),)

        >>> parseaddr('a@malicious.org@important.com')
        ('', 'a@malicious.org')

    After:

        >>> email.message_from_string('From: a@malicious.org@important.com', policy=email.policy.default)['from'].addresses
        (Address(display_name='', username='', domain=''),)

        >>> parseaddr('a@malicious.org@important.com')
        ('', 'a@')

https://bugs.python.org/issue34155

diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
index daff57b9cfa215a9c3dcb4c29f7edd3e5825506b..641e0979f3d78548469087b11b3ab5c01cf7e227 100644 (file)
--- a/Lib/email/_header_value_parser.py
+++ b/Lib/email/_header_value_parser.py
@@ -1587,6 +1587,8 @@ def get_domain(value):
         token, value = get_dot_atom(value)
     except errors.HeaderParseError:
         token, value = get_atom(value)
+    if value and value[0] == '@':
+        raise errors.HeaderParseError('Invalid Domain')
     if leader is not None:
         token[:0] = [leader]
     domain.append(token)

diff --git a/Lib/email/_parseaddr.py b/Lib/email/_parseaddr.py
index cdfa3729adc79efa0b8fc2cf972a76f301c24fdb..41ff6f8c000d57d23445fa529b33297b1ffa07fc 100644 (file)
--- a/Lib/email/_parseaddr.py
+++ b/Lib/email/_parseaddr.py
@@ -379,7 +379,12 @@ class AddrlistClass:
         aslist.append('@')
         self.pos += 1
         self.gotonext()
-        return EMPTYSTRING.join(aslist) + self.getdomain()
+        domain = self.getdomain()
+        if not domain:
+            # Invalid domain, return an empty address instead of returning a
+            # local part to denote failed parsing.
+            return EMPTYSTRING
+        return EMPTYSTRING.join(aslist) + domain
 
     def getdomain(self):
         """Get the complete domain name from an address."""
@@ -394,6 +399,10 @@ class AddrlistClass:
             elif self.field[self.pos] == '.':
                 self.pos += 1
                 sdlist.append('.')
+            elif self.field[self.pos] == '@':
+                # bpo-34155: Don't parse domains with two `@` like
+                # `a@malicious.org@important.com`.
+                return EMPTYSTRING
             elif self.field[self.pos] in self.atomends:
                 break
             else:

diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py
index 4fa56b16c47854f6956e3fae50cbe658bfec3498..877cd3effe1d0a1182ac66ee0597cf437c5ffd2f 100644 (file)
--- a/Lib/test/test_email/test__header_value_parser.py
+++ b/Lib/test/test_email/test__header_value_parser.py
@@ -1448,6 +1448,16 @@ class TestParser(TestParserMixin, TestEmailBase):
         self.assertEqual(addr_spec.domain, 'example.com')
         self.assertEqual(addr_spec.addr_spec, 'star.a.star@example.com')
 
+    def test_get_addr_spec_multiple_domains(self):
+        with self.assertRaises(errors.HeaderParseError):
+            parser.get_addr_spec('star@a.star@example.com')
+
+        with self.assertRaises(errors.HeaderParseError):
+            parser.get_addr_spec('star@a@example.com')
+
+        with self.assertRaises(errors.HeaderParseError):
+            parser.get_addr_spec('star@172.17.0.1@example.com')
+
     # get_obs_route
 
     def test_get_obs_route_simple(self):

diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index c29cc56203b1f7b902aa1882e25db23c576aa08a..aa775881c5521aee488e8c8fa14c46b44d6ee80c 100644 (file)
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -3041,6 +3041,20 @@ class TestMiscellaneous(TestEmailBase):
         self.assertEqual(utils.parseaddr('<>'), ('', ''))
         self.assertEqual(utils.formataddr(utils.parseaddr('<>')), '')
 
+    def test_parseaddr_multiple_domains(self):
+        self.assertEqual(
+            utils.parseaddr('a@b@c'),
+            ('', '')
+        )
+        self.assertEqual(
+            utils.parseaddr('a@b.c@c'),
+            ('', '')
+        )
+        self.assertEqual(
+            utils.parseaddr('a@172.17.0.1@c'),
+            ('', '')
+        )
+
     def test_noquote_dump(self):
         self.assertEqual(
             utils.formataddr(('A Silly Person', 'person@dom.ain')),

diff --git a/Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst b/Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst
new file mode 100644 (file)
index 0000000..50292e2
--- /dev/null
+++ b/Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst
@@ -0,0 +1 @@
+Fix parsing of invalid email addresses with more than one ``@`` (e.g. a@b@c.com.) to not return the part before 2nd ``@`` as valid email address. Patch by maxking & jpic.