diff --git a/Lib/test/test_ucn.py b/Lib/test/test_ucn.py index 68a3219560e..ff4c4f1700f 100644 --- a/Lib/test/test_ucn.py +++ b/Lib/test/test_ucn.py @@ -9,6 +9,7 @@ Modified for Python 2.0 by Fredrik Lundh (fredrik@pythonware.com) import unittest import unicodedata +import _testcapi from test import support from http.client import HTTPException @@ -215,6 +216,21 @@ class UnicodeNamesTest(unittest.TestCase): str, b"\\NSPACE", 'unicode-escape', 'strict' ) + @unittest.skipUnless(_testcapi.INT_MAX < _testcapi.PY_SSIZE_T_MAX, + "needs UINT_MAX < SIZE_MAX") + def test_issue16335(self): + # very very long bogus character name + try: + x = b'\\N{SPACE' + b'x' * (_testcapi.UINT_MAX + 1) + b'}' + except MemoryError: + raise unittest.SkipTest("not enough memory") + self.assertEqual(len(x), len(b'\\N{SPACE}') + (_testcapi.UINT_MAX + 1)) + self.assertRaisesRegex(UnicodeError, + 'unknown Unicode character name', + x.decode, 'unicode-escape' + ) + + def test_main(): support.run_unittest(UnicodeNamesTest) diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c index b57a8963b9d..c30245d9f82 100644 --- a/Objects/unicodeobject.c +++ b/Objects/unicodeobject.c @@ -5696,7 +5696,8 @@ PyUnicode_DecodeUnicodeEscape(const char *s, /* found a name. look it up in the unicode database */ message = "unknown Unicode character name"; s++; - if (ucnhash_CAPI->getcode(NULL, start, (int)(s-start-1), + if (s - start - 1 <= INT_MAX && + ucnhash_CAPI->getcode(NULL, start, (int)(s-start-1), &chr, 0)) goto store; }