[3.12] gh-102988: Detect email address parsing errors and return empty tuple to indicate the parsing error (old API) (GH-105127) (#106612)

gh-102988: Detect email address parsing errors and return empty tuple to indicate the parsing error (old API) (GH-105127)

Detect email address parsing errors and return empty tuple to indicate the parsing error (old API). This fixes or at least ameliorates CVE-2023-27043.

---------

(cherry picked from commit 18dfbd035775c15533d13a98e56b1d2bf5c65f00)

Co-authored-by: Thomas Dwyer <github@tomd.tel>
Co-authored-by: Gregory P. Smith <greg@krypto.org>

2 files changed, 135 insertions, 9 deletions

diff --git a/Lib/email/utils.py b/Lib/email/utils.py
index 81da539..11ad75e 100644
--- a/Lib/email/utils.py
+++ b/Lib/email/utils.py
@@ -106,12 +106,54 @@ def formataddr(pair, charset='utf-8'):
     return address
 
 
+def _pre_parse_validation(email_header_fields):
+    accepted_values = []
+    for v in email_header_fields:
+        s = v.replace('\\(', '').replace('\\)', '')
+        if s.count('(') != s.count(')'):
+            v = "('', '')"
+        accepted_values.append(v)
+
+    return accepted_values
+
+
+def _post_parse_validation(parsed_email_header_tuples):
+    accepted_values = []
+    # The parser would have parsed a correctly formatted domain-literal
+    # The existence of an [ after parsing indicates a parsing failure
+    for v in parsed_email_header_tuples:
+        if '[' in v[1]:
+            v = ('', '')
+        accepted_values.append(v)
+
+    return accepted_values
+
 
 def getaddresses(fieldvalues):
-    """Return a list of (REALNAME, EMAIL) for each fieldvalue."""
-    all = COMMASPACE.join(str(v) for v in fieldvalues)
+    """Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue.
+
+    When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in
+    its place.
+
+    If the resulting list of parsed address is not the same as the number of
+    fieldvalues in the input list a parsing error has occurred.  A list
+    containing a single empty 2-tuple [('', '')] is returned in its place.
+    This is done to avoid invalid output.
+    """
+    fieldvalues = [str(v) for v in fieldvalues]
+    fieldvalues = _pre_parse_validation(fieldvalues)
+    all = COMMASPACE.join(v for v in fieldvalues)
     a = _AddressList(all)
-    return a.addresslist
+    result = _post_parse_validation(a.addresslist)
+
+    n = 0
+    for v in fieldvalues:
+        n += v.count(',') + 1
+
+    if len(result) != n:
+        return [('', '')]
+
+    return result
 
 
 def _format_timetuple_and_zone(timetuple, zone):
@@ -212,9 +254,18 @@ def parseaddr(addr):
     Return a tuple of realname and email address, unless the parse fails, in
     which case return a 2-tuple of ('', '').
     """
-    addrs = _AddressList(addr).addresslist
-    if not addrs:
-        return '', ''
+    if isinstance(addr, list):
+        addr = addr[0]
+
+    if not isinstance(addr, str):
+        return ('', '')
+
+    addr = _pre_parse_validation([addr])[0]
+    addrs = _post_parse_validation(_AddressList(addr).addresslist)
+
+    if not addrs or len(addrs) > 1:
+        return ('', '')
+
     return addrs[0]
 
 
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index 44b4057..5238944 100644
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -3319,15 +3319,90 @@ Foo
            [('Al Person', 'aperson@dom.ain'),
             ('Bud Person', 'bperson@dom.ain')])
 
+    def test_getaddresses_parsing_errors(self):
+        """Test for parsing errors from CVE-2023-27043"""
+        eq = self.assertEqual
+        eq(utils.getaddresses(['alice@example.org(<bob@example.com>']),
+           [('', '')])
+        eq(utils.getaddresses(['alice@example.org)<bob@example.com>']),
+           [('', '')])
+        eq(utils.getaddresses(['alice@example.org<<bob@example.com>']),
+           [('', '')])
+        eq(utils.getaddresses(['alice@example.org><bob@example.com>']),
+           [('', '')])
+        eq(utils.getaddresses(['alice@example.org@<bob@example.com>']),
+           [('', '')])
+        eq(utils.getaddresses(['alice@example.org,<bob@example.com>']),
+           [('', 'alice@example.org'), ('', 'bob@example.com')])
+        eq(utils.getaddresses(['alice@example.org;<bob@example.com>']),
+           [('', '')])
+        eq(utils.getaddresses(['alice@example.org:<bob@example.com>']),
+           [('', '')])
+        eq(utils.getaddresses(['alice@example.org.<bob@example.com>']),
+           [('', '')])
+        eq(utils.getaddresses(['alice@example.org"<bob@example.com>']),
+           [('', '')])
+        eq(utils.getaddresses(['alice@example.org[<bob@example.com>']),
+           [('', '')])
+        eq(utils.getaddresses(['alice@example.org]<bob@example.com>']),
+           [('', '')])
+
+    def test_parseaddr_parsing_errors(self):
+        """Test for parsing errors from CVE-2023-27043"""
+        eq = self.assertEqual
+        eq(utils.parseaddr(['alice@example.org(<bob@example.com>']),
+           ('', ''))
+        eq(utils.parseaddr(['alice@example.org)<bob@example.com>']),
+           ('', ''))
+        eq(utils.parseaddr(['alice@example.org<<bob@example.com>']),
+           ('', ''))
+        eq(utils.parseaddr(['alice@example.org><bob@example.com>']),
+           ('', ''))
+        eq(utils.parseaddr(['alice@example.org@<bob@example.com>']),
+           ('', ''))
+        eq(utils.parseaddr(['alice@example.org,<bob@example.com>']),
+           ('', ''))
+        eq(utils.parseaddr(['alice@example.org;<bob@example.com>']),
+           ('', ''))
+        eq(utils.parseaddr(['alice@example.org:<bob@example.com>']),
+           ('', ''))
+        eq(utils.parseaddr(['alice@example.org.<bob@example.com>']),
+           ('', ''))
+        eq(utils.parseaddr(['alice@example.org"<bob@example.com>']),
+           ('', ''))
+        eq(utils.parseaddr(['alice@example.org[<bob@example.com>']),
+           ('', ''))
+        eq(utils.parseaddr(['alice@example.org]<bob@example.com>']),
+           ('', ''))
+
     def test_getaddresses_nasty(self):
         eq = self.assertEqual
         eq(utils.getaddresses(['foo: ;']), [('', '')])
-        eq(utils.getaddresses(
-           ['[]*-- =~$']),
-           [('', ''), ('', ''), ('', '*--')])
+        eq(utils.getaddresses(['[]*-- =~$']), [('', '')])
         eq(utils.getaddresses(
            ['foo: ;', '"Jason R. Mastaler" <jason@dom.ain>']),
            [('', ''), ('Jason R. Mastaler', 'jason@dom.ain')])
+        eq(utils.getaddresses(
+           [r'Pete(A nice \) chap) <pete(his account)@silly.test(his host)>']),
+           [('Pete (A nice ) chap his account his host)', 'pete@silly.test')])
+        eq(utils.getaddresses(
+           ['(Empty list)(start)Undisclosed recipients  :(nobody(I know))']),
+           [('', '')])
+        eq(utils.getaddresses(
+           ['Mary <@machine.tld:mary@example.net>, , jdoe@test   . example']),
+           [('Mary', 'mary@example.net'), ('', ''), ('', 'jdoe@test.example')])
+        eq(utils.getaddresses(
+           ['John Doe <jdoe@machine(comment).  example>']),
+           [('John Doe (comment)', 'jdoe@machine.example')])
+        eq(utils.getaddresses(
+           ['"Mary Smith: Personal Account" <smith@home.example>']),
+           [('Mary Smith: Personal Account', 'smith@home.example')])
+        eq(utils.getaddresses(
+           ['Undisclosed recipients:;']),
+           [('', '')])
+        eq(utils.getaddresses(
+           [r'<boss@nil.test>, "Giant; \"Big\" Box" <bob@example.net>']),
+           [('', 'boss@nil.test'), ('Giant; "Big" Box', 'bob@example.net')])
 
     def test_getaddresses_embedded_comment(self):
         """Test proper handling of a nested comment"""