Fixed CVE-2019-14235 -- Fixed potential memory exhaustion in django.utils.encoding.uri_to_iri().

Thanks to Guido Vranken for initial report.

django/utils/encoding.py

@@ -229,13 +229,16 @@ def repercent_broken_unicode(path):
     repercent-encode any octet produced that is not part of a strictly legal
     UTF-8 octet sequence.
     """
-    try:
-        path.decode()
-    except UnicodeDecodeError as e:
-        repercent = quote(path[e.start:e.end], safe=b"/#%[]=:;$&()+,!?*@'~")
-        path = repercent_broken_unicode(
-            path[:e.start] + force_bytes(repercent) + path[e.end:])
-    return path
+    while True:
+        try:
+            path.decode()
+        except UnicodeDecodeError as e:
+            # CVE-2019-14235: A recursion shouldn't be used since the exception
+            # handling uses massive amounts of memory
+            repercent = quote(path[e.start:e.end], safe=b"/#%[]=:;$&()+,!?*@'~")
+            path = path[:e.start] + force_bytes(repercent) + path[e.end:]
+        else:
+            return path
 
 
 def filepath_to_uri(path):

docs/releases/1.11.23.txt

@@ -45,3 +45,13 @@ CVE-2019-14234: SQL injection possibility in key and index lookups for ``JSONFie
 <hstorefield.key>` for :class:`~django.contrib.postgres.fields.HStoreField`
 were subject to SQL injection, using a suitably crafted dictionary, with
 dictionary expansion, as the ``**kwargs`` passed to ``QuerySet.filter()``.
+
+CVE-2019-14235: Potential memory exhaustion in ``django.utils.encoding.uri_to_iri()``
+=====================================================================================
+
+If passed certain inputs, :func:`django.utils.encoding.uri_to_iri` could lead
+to significant memory usage due to excessive recursion when re-percent-encoding
+invalid UTF-8 octet sequences.
+
+``uri_to_iri()`` now avoids recursion when re-percent-encoding invalid UTF-8
+octet sequences.

docs/releases/2.1.11.txt

@@ -45,3 +45,13 @@ CVE-2019-14234: SQL injection possibility in key and index lookups for ``JSONFie
 <hstorefield.key>` for :class:`~django.contrib.postgres.fields.HStoreField`
 were subject to SQL injection, using a suitably crafted dictionary, with
 dictionary expansion, as the ``**kwargs`` passed to ``QuerySet.filter()``.
+
+CVE-2019-14235: Potential memory exhaustion in ``django.utils.encoding.uri_to_iri()``
+=====================================================================================
+
+If passed certain inputs, :func:`django.utils.encoding.uri_to_iri` could lead
+to significant memory usage due to excessive recursion when re-percent-encoding
+invalid UTF-8 octet sequences.
+
+``uri_to_iri()`` now avoids recursion when re-percent-encoding invalid UTF-8
+octet sequences.

docs/releases/2.2.4.txt

@@ -46,6 +46,16 @@ CVE-2019-14234: SQL injection possibility in key and index lookups for ``JSONFie
 were subject to SQL injection, using a suitably crafted dictionary, with
 dictionary expansion, as the ``**kwargs`` passed to ``QuerySet.filter()``.
 
+CVE-2019-14235: Potential memory exhaustion in ``django.utils.encoding.uri_to_iri()``
+=====================================================================================
+
+If passed certain inputs, :func:`django.utils.encoding.uri_to_iri` could lead
+to significant memory usage due to excessive recursion when re-percent-encoding
+invalid UTF-8 octet sequences.
+
+``uri_to_iri()`` now avoids recursion when re-percent-encoding invalid UTF-8
+octet sequences.
+
 Bugfixes
 ========
 

tests/utils_tests/test_encoding.py

@@ -1,4 +1,5 @@
 import datetime
+import sys
 import unittest
 from unittest import mock
 from urllib.parse import quote_plus
@@ -6,8 +7,8 @@ from urllib.parse import quote_plus
 from django.test import SimpleTestCase
 from django.utils.encoding import (
     DjangoUnicodeDecodeError, escape_uri_path, filepath_to_uri, force_bytes,
-    force_str, get_system_encoding, iri_to_uri, smart_bytes, smart_str,
-    uri_to_iri,
+    force_str, get_system_encoding, iri_to_uri, repercent_broken_unicode,
+    smart_bytes, smart_str, uri_to_iri,
 )
 from django.utils.functional import SimpleLazyObject
 from django.utils.translation import gettext_lazy
@@ -90,6 +91,15 @@ class TestEncodingUtils(SimpleTestCase):
         with mock.patch('locale.getdefaultlocale', side_effect=Exception):
             self.assertEqual(get_system_encoding(), 'ascii')
 
+    def test_repercent_broken_unicode_recursion_error(self):
+        # Prepare a string long enough to force a recursion error if the tested
+        # function uses recursion.
+        data = b'\xfc' * sys.getrecursionlimit()
+        try:
+            self.assertEqual(repercent_broken_unicode(data), b'%FC' * sys.getrecursionlimit())
+        except RecursionError:
+            self.fail('Unexpected RecursionError raised.')
+
 
 class TestRFC3987IEncodingUtils(unittest.TestCase):