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

---------

Co-authored-by: Gregory P. Smith <greg@krypto.org>

1 files changed, 57 insertions, 6 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]