merge 3.4 (#23369)

Lib/test/test_json/test_encode_basestring_ascii.py

@@ -1,5 +1,6 @@
 from collections import OrderedDict
 from test.test_json import PyTest, CTest
+from test.support import bigaddrspacetest
 
 
 CASES = [
@@ -38,4 +39,10 @@ class TestEncodeBasestringAscii:
 
 
 class TestPyEncodeBasestringAscii(TestEncodeBasestringAscii, PyTest): pass
-class TestCEncodeBasestringAscii(TestEncodeBasestringAscii, CTest): pass
+class TestCEncodeBasestringAscii(TestEncodeBasestringAscii, CTest):
+    @bigaddrspacetest
+    def test_overflow(self):
+        s = "\uffff"*((2**32)//6 + 1)
+        with self.assertRaises(OverflowError):
+            self.json.encoder.encode_basestring_ascii(s)
+

Misc/NEWS

@@ -229,6 +229,9 @@ Library
 - Issue #23326: Removed __ne__ implementations.  Since fixing default __ne__
   implementation in issue #21408 they are redundant.
 
+- Issue #23369: Fixed possible integer overflow in
+  _json.encode_basestring_ascii.
+
 - Issue #23353: Fix the exception handling of generators in
   PyEval_EvalFrameEx(). At entry, save or swap the exception state even if
   PyEval_EvalFrameEx() is called with throwflag=0. At exit, the exception state

Modules/_json.c

@@ -182,17 +182,24 @@ ascii_escape_unicode(PyObject *pystr)
     /* Compute the output size */
     for (i = 0, output_size = 2; i < input_chars; i++) {
         Py_UCS4 c = PyUnicode_READ(kind, input, i);
-        if (S_CHAR(c))
-            output_size++;
+        Py_ssize_t d;
+        if (S_CHAR(c)) {
+            d = 1;
+        }
         else {
             switch(c) {
             case '\\': case '"': case '\b': case '\f':
             case '\n': case '\r': case '\t':
-                output_size += 2; break;
+                d = 2; break;
             default:
-                output_size += c >= 0x10000 ? 12 : 6;
+                d = c >= 0x10000 ? 12 : 6;
             }
         }
+        if (output_size > PY_SSIZE_T_MAX - d) {
+            PyErr_SetString(PyExc_OverflowError, "string is too long to escape");
+            return NULL;
+        }
+        output_size += d;
     }
 
     rval = PyUnicode_New(output_size, 127);