From 8211e36d281990a39db1853bcd454ac59e53d521 Mon Sep 17 00:00:00 2001 From: Hiltjo Posthuma Date: Sat, 9 May 2020 13:56:28 +0200 Subject: [PATCH] fix for incorrect (partial) written sequences when libc wcwidth() == -1 Fix an issue with incorrect (partial) written sequences when libc wcwidth() == -1. The sequence is updated to on wcwidth(u) == -1: c = "\357\277\275" but len isn't. A way to reproduce in practise: * st -o dump.txt * In the terminal: printf '\xcd\xb8' - This is codepoint 888, on OpenBSD it reports wcwidth() == -1. - Quit the terminal. - Look in dump.txt (partial written sequence of "UTF_INVALID"). This was introduced in: " commit 11625c7166b7e4dad414606227acec2de1c36464 Author: czarkoff@gmail.com Date: Tue Oct 28 12:55:28 2014 +0100 Replace character with U+FFFD if wcwidth() is -1 Helpful when new Unicode codepoints are not recognized by libc." Change: Remove setting the sequence. If this happens to break something, another solution could be setting len = 3 for the sequence. --- st.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/st.c b/st.c index c161497..5d4054f 100644 --- a/st.c +++ b/st.c @@ -2312,10 +2312,8 @@ tputc(Rune u) width = len = 1; } else { len = utf8encode(u, c); - if (!control && (width = wcwidth(u)) == -1) { - memcpy(c, "\357\277\275", 4); /* UTF_INVALID */ + if (!control && (width = wcwidth(u)) == -1) width = 1; - } } if (IS_SET(MODE_PRINT))