From e2e88ad814a1839b34a163832975620fe0e44fac Mon Sep 17 00:00:00 2001
Message-Id: <e2e88ad814a1839b34a163832975620fe0e44fac.1715005492.git.mdw@distorted.org.uk>
From: Mark Wooding <mdw@chiark.greenend.org.uk>
Date: Sun, 5 Apr 2009 10:45:15 +0100
Subject: [PATCH] Update grapheme break algorithm to Unicode 5.1.0 (based on
 UAX #29)
Organization: Straylight/Edgeware

From: Richard Kettlewell <rjk@greenend.org.uk>

---
 lib/unicode.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/lib/unicode.c b/lib/unicode.c
index 55390eb..16c5932 100644
--- a/lib/unicode.c
+++ b/lib/unicode.c
@@ -603,6 +603,12 @@ int utf32_iterator_grapheme_boundary(utf32_iterator it) {
   /* GB9 */
   if(gbafter == unicode_Grapheme_Break_Extend)
     return 0;
+  /* GB9a */
+  if(gbafter == unicode_Grapheme_Break_SpacingMark)
+    return 0;
+  /* GB9b */
+  if(gbbefore == unicode_Grapheme_Break_Prepend)
+    return 0;
   /* GB10 */
   return 1;
 
-- 
[mdw]