Merged revisions 75931 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/trunk

........
  r75931 | benjamin.peterson | 2009-10-28 20:49:07 -0500 (Wed, 28 Oct 2009) | 5 lines

  do a backport of r75928

  The added test does not fail without the patch, but we still fix the issue of
  surrogates being used in wide builds where they should not be.
........

Lib/test/test_pep263.py

-#! -*- coding: koi8-r -*-
+# -*- coding: koi8-r -*-
 
 import unittest
 from test import test_support
@@ -23,6 +23,13 @@ class PEP263Test(unittest.TestCase):
         self.assertEqual(d['u'], u'\xf3')
 
 
+    def test_issue3297(self):
+        c = compile("a, b = '\U0001010F', '\\U0001010F'", "dummy", "exec")
+        d = {}
+        exec(c, d)
+        self.assertEqual(d['a'], d['b'])
+        self.assertEqual(len(d['a']), len(d['b']))
+
 def test_main():
     test_support.run_unittest(PEP263Test)
 

Python/ast.c

@@ -3248,10 +3248,11 @@ decode_unicode(struct compiling *c, const char *s, size_t len, int rawmode, cons
                 u = NULL;
         } else {
                 /* check for integer overflow */
-                if (len > PY_SIZE_MAX / 4)
+                if (len > PY_SIZE_MAX / 6)
                         return NULL;
-                /* "\XX" may become "\u005c\uHHLL" (12 bytes) */
-                u = PyString_FromStringAndSize((char *)NULL, len * 4);
+		/* "<C3><A4>" (2 bytes) may become "\U000000E4" (10 bytes), or 1:5
+		   "\ä" (3 bytes) may become "\u005c\U000000E4" (16 bytes), or ~1:6 */
+                u = PyString_FromStringAndSize((char *)NULL, len * 6);
                 if (u == NULL)
                         return NULL;
                 p = buf = PyString_AsString(u);
@@ -3268,19 +3269,21 @@ decode_unicode(struct compiling *c, const char *s, size_t len, int rawmode, cons
                                 PyObject *w;
                                 char *r;
                                 Py_ssize_t rn, i;
-                                w = decode_utf8(c, &s, end, "utf-16-be");
+                                w = decode_utf8(c, &s, end, "utf-32-be");
                                 if (w == NULL) {
                                         Py_DECREF(u);
                                         return NULL;
                                 }
                                 r = PyString_AsString(w);
                                 rn = PyString_Size(w);
-                                assert(rn % 2 == 0);
-                                for (i = 0; i < rn; i += 2) {
-                                        sprintf(p, "\\u%02x%02x",
+                                assert(rn % 4 == 0);
+                                for (i = 0; i < rn; i += 4) {
+                                        sprintf(p, "\\U%02x%02x%02x%02x",
                                                 r[i + 0] & 0xFF,
-                                                r[i + 1] & 0xFF);
-                                        p += 6;
+                                                r[i + 1] & 0xFF,
+						r[i + 2] & 0xFF,
+						r[i + 3] & 0xFF);
+                                        p += 10;
                                 }
                                 Py_DECREF(w);
                         } else {