From 6b77da2fbfadb69091bbb1339704e7b86aa6a7b7 Mon Sep 17 00:00:00 2001
From: Martijn Dekker <martijn@inlv.org>
Date: Sat, 12 Feb 2022 21:27:36 +0000
Subject: [PATCH] Disable broken KEYBD trap for multibyte characters

In UTF-8 locales, ksh breaks when a KEYBD trap is active, even a
dummy no-op one like 'trap : KEYBD'. Entering multi-byte characters
fails (the input is interrupted and a new prompt is displayed) and
pasting content with multi-byte characters produces corrupted
results.

The cause is that the KEYBD trap code is not multibyte-ready.
Unfortunately nobody yet understands the edit.c code well enough
to implement a proper fix. Pending that, this commit implements
a workaround that at least avoids breaking the shell.

src/cmd/ksh93/edit/edit.c: ed_getchar():
- When a multi-byte locale is active, do not trigger the the KEYBD
  trap except for ASCII characters (1-127).

Resolves: https://github.com/ksh93/ksh/issues/307
---
 NEWS                            | 6 ++++++
 src/cmd/ksh93/edit/edit.c       | 5 ++++-
 src/cmd/ksh93/include/version.h | 2 +-
 src/cmd/ksh93/sh.1              | 4 ++++
 4 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/NEWS b/NEWS
index 8877d3975503..fe810fe52ed5 100644
--- a/NEWS
+++ b/NEWS
@@ -3,6 +3,12 @@ For full details, see the git log at: https://github.com/ksh93/ksh
 
 Any uppercase BUG_* names are modernish shell bug IDs.
 
+2022-02-12:
+
+- In multibyte locales such as UTF-8, shell input is no longer corrupted when
+  a KEYBD trap is active. However, the KEYBD trap is not yet multibyte ready
+  and is now only triggered for ASCII characters (1-127) in a multibyte locale.
+
 2022-02-11:
 
 - On the interactive shell, tab/esc completion is no longer disabled as a side
diff --git a/src/cmd/ksh93/edit/edit.c b/src/cmd/ksh93/edit/edit.c
index d9933b63bb6a..371f5a9ec8fb 100644
--- a/src/cmd/ksh93/edit/edit.c
+++ b/src/cmd/ksh93/edit/edit.c
@@ -1122,7 +1122,10 @@ int ed_getchar(register Edit_t *ep,int mode)
 				killpg(getpgrp(),SIGINT);
 				siglongjmp(ep->e_env, UINTR);
 			}
-			if(mode<=0 && sh.st.trap[SH_KEYTRAP])
+			if(mode<=0 && sh.st.trap[SH_KEYTRAP]
+			/* workaround for <https://github.com/ksh93/ksh/issues/307>:
+			 * do not trigger KEYBD for non-ASCII in multibyte locale */
+			&& (CC_NATIVE!=CC_ASCII || !mbwide() || c > -128))
 			{
 				ep->e_keytrap = 1;
 				n=1;
diff --git a/src/cmd/ksh93/include/version.h b/src/cmd/ksh93/include/version.h
index 5e8abd6eb654..bc51faed1213 100644
--- a/src/cmd/ksh93/include/version.h
+++ b/src/cmd/ksh93/include/version.h
@@ -21,7 +21,7 @@
 
 #define SH_RELEASE_FORK	"93u+m"		/* only change if you develop a new ksh93 fork */
 #define SH_RELEASE_SVER	"1.1.0-alpha"	/* semantic version number: https://semver.org */
-#define SH_RELEASE_DATE	"2022-02-11"	/* must be in this format for $((.sh.version)) */
+#define SH_RELEASE_DATE	"2022-02-12"	/* must be in this format for $((.sh.version)) */
 #define SH_RELEASE_CPYR	"(c) 2020-2022 Contributors to ksh " SH_RELEASE_FORK
 
 /* Scripts sometimes field-split ${.sh.version}, so don't change amount of whitespace. */
diff --git a/src/cmd/ksh93/sh.1 b/src/cmd/ksh93/sh.1
index 841c28a43bb8..61f71c2d1698 100644
--- a/src/cmd/ksh93/sh.1
+++ b/src/cmd/ksh93/sh.1
@@ -9062,6 +9062,10 @@ Thus, a trap on
 .B CHLD
 won't be executed until the foreground job terminates.
 .PP
+In locales that use a multibyte character set such as UTF-8, the
+.B KEYBD
+trap is only triggered for ASCII characters (1-127).
+.PP
 It is a good idea to leave a space after the comma operator in
 arithmetic expressions to prevent the comma from being interpreted
 as the decimal point character in certain locales.