From 0cadb4301d18724e7513d7489cb5bebd262c82f1 Mon Sep 17 00:00:00 2001
From: Russ Cox <russcox@gmail.com>
Date: Fri, 11 Sep 2009 17:03:06 -0400
Subject: convert to 4-byte UTF-8 and 32-bit Rune

http://codereview.appspot.com/116075
---
 include/utf.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/utf.h')

diff --git a/include/utf.h b/include/utf.h
index eb5ea42a..44052f41 100644
--- a/include/utf.h
+++ b/include/utf.h
@@ -4,14 +4,15 @@
 extern "C" { 
 #endif
 
-typedef unsigned short Rune;	/* 16 bits */
+typedef unsigned int Rune;	/* 32 bits */
 
 enum
 {
-	UTFmax		= 3,		/* maximum bytes per rune */
+	UTFmax		= 4,		/* maximum bytes per rune */
 	Runesync	= 0x80,		/* cannot represent part of a UTF sequence (<) */
 	Runeself	= 0x80,		/* rune and UTF sequences are the same (<) */
-	Runeerror	= 0xFFFD		/* decoding error in UTF */
+	Runeerror	= 0xFFFD,	/* decoding error in UTF */
+	Runemax = 0x10FFFF	/* maximum rune value */
 };
 
 /* Edit .+1,/^$/ | cfn $PLAN9/src/lib9/utf/?*.c | grep -v static |grep -v __ */
-- 
cgit v1.2.3