From c596e023b75e2e17a9b338ac0ba09a51fd5995a9 Mon Sep 17 00:00:00 2001
From: Steve Bennett <steveb@workware.net.au>
Date: Fri, 1 Nov 2019 16:56:20 +1000
Subject: regexp,regsub: utf8: Fix incorrect count with . matches

Internally bytes were being counted rather than characters

Reported-by: dbohdan <dbohdan@dbohdan.com>
Signed-off-by: Steve Bennett <steveb@workware.net.au>
---
 jimregexp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'jimregexp.c')

diff --git a/jimregexp.c b/jimregexp.c
index 3771bd7..5b2d60c 100644
--- a/jimregexp.c
+++ b/jimregexp.c
@@ -1612,10 +1612,9 @@ static int regrepeat(regex_t *preg, int p, int max)
 	opnd = OPERAND(p);
 	switch (OP(preg, p)) {
 	case ANY:
-		/* No need to handle utf8 specially here */
 		while (!reg_iseol(preg, *scan) && count < max) {
 			count++;
-			scan++;
+			scan += utf8_charlen(*scan);
 		}
 		break;
 	case EXACTLY:
-- 
cgit v1.1