From bd91a255e49c81e3d20c43359facac95191e041a Mon Sep 17 00:00:00 2001
From: Maxime Coste <mawww@kakoune.org>
Date: Sun, 11 Feb 2024 12:17:21 +1100
Subject: [PATCH] Do not decode utf8 while looking for next regex match start
 candidate

If the first byte in the multi-byte utf8 sequence does not match,
it means the "other" character is not set, so none of the sequence
byte will match (as they are all with the MSB set). This tightens
the critical loop which ends up running faster in most cases.
---
 src/regex_impl.hh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/regex_impl.hh b/src/regex_impl.hh
index f59b2249a..2fd2254a2 100644
--- a/src/regex_impl.hh
+++ b/src/regex_impl.hh
@@ -530,7 +530,7 @@ private:
                 const unsigned char c = *start;
                 if (start_desc.map[(c < StartDesc::count) ? c : StartDesc::other])
                     return;
-                utf8::to_next(start, config.end);
+                ++start;
             }
             else
             {