Issue #10459: Update CJK character names to Unicode 5.2.

diff --git a/Misc/NEWS b/Misc/NEWS
index cb9e489716393434a9d8a434ef874f28bc59f533..9edc91d925f34179395261065244e18678f123f7 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -13,6 +13,8 @@ Core and Builtins
 Library
 -------
 
+- Issue #10459: Update CJK character names to Unicode 5.2.
+
 - Issue #4493: urllib2 adds '/' in front of path components which does not
   start with '/. Common behavior exhibited by browsers and other clients.
 

diff --git a/Modules/unicodedata.c b/Modules/unicodedata.c
index 77f36377c781cb5f0a8a709badfc5115ffd2ae0b..b4af29071af56bb4d0be316ddf525838b2dbb684 100644 (file)
--- a/Modules/unicodedata.c
+++ b/Modules/unicodedata.c
@@ -869,8 +869,9 @@ is_unified_ideograph(Py_UCS4 code)
 {
     return (
         (0x3400 <= code && code <= 0x4DB5) || /* CJK Ideograph Extension A */
-        (0x4E00 <= code && code <= 0x9FBB) || /* CJK Ideograph */
-        (0x20000 <= code && code <= 0x2A6D6));/* CJK Ideograph Extension B */
+        (0x4E00 <= code && code <= 0x9FCB) || /* CJK Ideograph, Unicode 5.2 */
+        (0x20000 <= code && code <= 0x2A6D6) || /* CJK Ideograph Extension B */
+        (0x2A700 <= code && code <= 0x2B734));  /* CJK Ideograph Extension C */
 }
 
 static int