From 6ad0e25fa41bf51f6ee5302ac62842cf5546223d Mon Sep 17 00:00:00 2001
From: drh <drh@noemail.net>
Date: Thu, 19 Dec 2019 21:11:48 +0000
Subject: Fix the regexp extension so that it correctly translates all
 over-length 3-byte UTF8 sequences into 0xfffd.

FossilOrigin-Name: 3d4c0bf8904135fa68c75801bfa738715cacc3b19dc8ad6ef550b11798d4b121
---
 ext/misc/regexp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'ext/misc/regexp.c')

diff --git a/ext/misc/regexp.c b/ext/misc/regexp.c
index 3359109ab..a97290511 100644
--- a/ext/misc/regexp.c
+++ b/ext/misc/regexp.c
@@ -156,7 +156,7 @@ static unsigned re_next_char(ReInput *p){
            && (p->z[p->i+1]&0xc0)==0x80 ){
       c = (c&0x0f)<<12 | ((p->z[p->i]&0x3f)<<6) | (p->z[p->i+1]&0x3f);
       p->i += 2;
-      if( c<=0x3ff || (c>=0xd800 && c<=0xdfff) ) c = 0xfffd;
+      if( c<=0x7ff || (c>=0xd800 && c<=0xdfff) ) c = 0xfffd;
     }else if( (c&0xf8)==0xf0 && p->i+3<p->mx && (p->z[p->i]&0xc0)==0x80
            && (p->z[p->i+1]&0xc0)==0x80 && (p->z[p->i+2]&0xc0)==0x80 ){
       c = (c&0x07)<<18 | ((p->z[p->i]&0x3f)<<12) | ((p->z[p->i+1]&0x3f)<<6)
-- 
cgit v1.2.3