[Python-checkins] bpo-34155: Dont parse domains containing @ (GH-13079) (GH-14826)

[Ned Deily]

https://github.com/python/cpython/commit/13a19139b5e76175bc95294d54afc9425e4f36c9
commit: 13a19139b5e76175bc95294d54afc9425e4f36c9
branch: 3.6
author: Miss Islington (bot) <31488909+miss-islington at users.noreply.github.com>
committer: Ned Deily <nad at python.org>
date: 2019-08-09T11:22:19-04:00
summary:

bpo-34155: Dont parse domains containing @ (GH-13079) (GH-14826)

Before:

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

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

    After:

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

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

https://bugs.python.org/issue34155
(cherry picked from commit 8cb65d1381b027f0b09ee36bfed7f35bb4dec9a9)

Co-authored-by: jpic <jpic at users.noreply.github.com>

files:
A Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst
M Lib/email/_header_value_parser.py
M Lib/email/_parseaddr.py
M Lib/test/test_email/test__header_value_parser.py
M Lib/test/test_email/test_email.py

diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
index 737951e4b1b1..bc9c9b6241d4 100644
--- a/Lib/email/_header_value_parser.py
+++ b/Lib/email/_header_value_parser.py
@@ -1561,6 +1561,8 @@ 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 cdfa3729adc7..41ff6f8c000d 100644
--- a/Lib/email/_parseaddr.py
+++ b/Lib/email/_parseaddr.py
@@ -379,7 +379,12 @@ def getaddrspec(self):
         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 @@ def getdomain(self):
             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 at 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 a2c900fa7fd2..02ef3e1006c6 100644
--- a/Lib/test/test_email/test__header_value_parser.py
+++ b/Lib/test/test_email/test__header_value_parser.py
@@ -1418,6 +1418,16 @@ def test_get_addr_spec_dot_atom(self):
         self.assertEqual(addr_spec.domain, 'example.com')
         self.assertEqual(addr_spec.addr_spec, 'star.a.star at example.com')
 
+    def test_get_addr_spec_multiple_domains(self):
+        with self.assertRaises(errors.HeaderParseError):
+            parser.get_addr_spec('star at a.star@example.com')
+
+        with self.assertRaises(errors.HeaderParseError):
+            parser.get_addr_spec('star at a@example.com')
+
+        with self.assertRaises(errors.HeaderParseError):
+            parser.get_addr_spec('star at 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 f97ccc6711cc..68d052279987 100644
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -3035,6 +3035,20 @@ def test_parseaddr_empty(self):
         self.assertEqual(utils.parseaddr('<>'), ('', ''))
         self.assertEqual(utils.formataddr(utils.parseaddr('<>')), '')
 
+    def test_parseaddr_multiple_domains(self):
+        self.assertEqual(
+            utils.parseaddr('a at b@c'),
+            ('', '')
+        )
+        self.assertEqual(
+            utils.parseaddr('a at b.c@c'),
+            ('', '')
+        )
+        self.assertEqual(
+            utils.parseaddr('a at 172.17.0.1@c'),
+            ('', '')
+        )
+
     def test_noquote_dump(self):
         self.assertEqual(
             utils.formataddr(('A Silly Person', 'person at 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
index 000000000000..50292e29ed1d
--- /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 at b@c.com.) to not return the part before 2nd ``@`` as valid email address. Patch by maxking & jpic.