#1477: ur'\U0010FFFF' used to raise in narrow unicode builds.

Corrected the raw-unicode-escape codec to use UTF-16 surrogates in
this case, like the unicode-escape codec does.

Backport of r61793 and r61853

1 files changed, 15 insertions, 2 deletions

diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
index 4f75771..55fb8e1 100644
--- a/Lib/test/test_unicode.py
+++ b/Lib/test/test_unicode.py
@@ -736,12 +736,25 @@ class UnicodeTest(
         print >>out, u'def\n'
 
     def test_ucs4(self):
-        if sys.maxunicode == 0xFFFF:
-            return
         x = u'\U00100000'
         y = x.encode("raw-unicode-escape").decode("raw-unicode-escape")
         self.assertEqual(x, y)
 
+        y = r'\U00100000'
+        x = y.decode("raw-unicode-escape").encode("raw-unicode-escape")
+        self.assertEqual(x, y)
+        y = r'\U00010000'
+        x = y.decode("raw-unicode-escape").encode("raw-unicode-escape")
+        self.assertEqual(x, y)
+
+        try:
+            '\U11111111'.decode("raw-unicode-escape")
+        except UnicodeDecodeError, e:
+            self.assertEqual(e.start, 0)
+            self.assertEqual(e.end, 10)
+        else:
+            self.fail("Should have raised UnicodeDecodeError")
+
     def test_conversion(self):
         # Make sure __unicode__() works properly
         class Foo0: