From: millert <millert@openbsd.org>
Date: Mon, 18 Sep 2023 19:32:19 +0000 (+0000)
Subject: Disable utf-8 for non-multibyte locales, such as C or POSIX.
X-Git-Url: http://artulab.com/gitweb/?a=commitdiff_plain;h=c35264f9919d4da2cd92f67a07fe5a337f4506ad;p=openbsd

Disable utf-8 for non-multibyte locales, such as C or POSIX.

This makes it possible to get the old awk behavior (where chars are
bytes) by setting LC_CTYPE to C or POSIX.  OK schwarze@
---

diff --git a/usr.bin/awk/awk.h b/usr.bin/awk/awk.h
index bd491ad2908..a57e27eaffd 100644
--- a/usr.bin/awk/awk.h
+++ b/usr.bin/awk/awk.h
@@ -1,4 +1,4 @@
-/*	$OpenBSD: awk.h,v 1.29 2023/09/17 14:49:44 millert Exp $	*/
+/*	$OpenBSD: awk.h,v 1.30 2023/09/18 19:32:19 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -66,6 +66,8 @@ extern bool	do_posix;	/* true if POSIXLY_CORRECT set */
 #define	RECSIZE	(8 * 1024)	/* sets limit on records, fields, etc., etc. */
 extern int	recsize;	/* size of current record, orig RECSIZE */
 
+extern size_t	awk_mb_cur_max;	/* max size of a multi-byte character */
+
 extern char	EMPTY[];	/* this avoid -Wwritable-strings issues */
 extern char	**FS;
 extern char	**RS;
diff --git a/usr.bin/awk/b.c b/usr.bin/awk/b.c
index 8601c7465ec..60b38d43198 100644
--- a/usr.bin/awk/b.c
+++ b/usr.bin/awk/b.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: b.c,v 1.38 2023/09/17 14:49:44 millert Exp $	*/
+/*	$OpenBSD: b.c,v 1.39 2023/09/18 19:32:19 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -834,7 +834,7 @@ bool fnematch(fa *pfa, FILE *f, char **pbuf, int *pbufsize, int quantum)
 				buf[k++] = (c = getc(f)) != EOF ? c : 0;
 			}
 			c = (uschar)buf[j];
-			if (c < 128)
+			if (c < 128 || awk_mb_cur_max == 1)
 				rune = c;
 			else {
 				j--;
diff --git a/usr.bin/awk/main.c b/usr.bin/awk/main.c
index f4a359dac7e..5a976d82814 100644
--- a/usr.bin/awk/main.c
+++ b/usr.bin/awk/main.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: main.c,v 1.60 2023/09/18 15:20:48 jmc Exp $	*/
+/*	$OpenBSD: main.c,v 1.61 2023/09/18 19:32:19 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -56,6 +56,8 @@ bool	CSV = false;		/* true for csv input */
 bool	safe = false;		/* true => "safe" mode */
 bool	do_posix = false;	/* true => POSIX mode */
 
+size_t	awk_mb_cur_max = 1;
+
 static noreturn void fpecatch(int n
 #ifdef SA_SIGINFO
 	, siginfo_t *si, void *uc
@@ -135,6 +137,7 @@ int main(int argc, char *argv[])
 
 	setlocale(LC_CTYPE, "");
 	setlocale(LC_NUMERIC, "C"); /* for parsing cmdline & prog */
+	awk_mb_cur_max = MB_CUR_MAX;
 
 	cmdname = __progname;
 	if (pledge("stdio rpath wpath cpath proc exec", NULL) == -1) {
diff --git a/usr.bin/awk/run.c b/usr.bin/awk/run.c
index c4719bbd516..d6920fa276a 100644
--- a/usr.bin/awk/run.c
+++ b/usr.bin/awk/run.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: run.c,v 1.76 2023/09/18 15:16:22 deraadt Exp $	*/
+/*	$OpenBSD: run.c,v 1.77 2023/09/18 19:32:19 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -606,7 +606,7 @@ int u8_isutf(const char *s)
 	unsigned char c;
 
 	c = s[0];
-	if (c < 128)
+	if (c < 128 || awk_mb_cur_max == 1)
 		return 1; /* what if it's 0? */
 
 	n = strlen(s);
@@ -633,7 +633,7 @@ int u8_rune(int *rune, const char *s)
 	unsigned char c;
 
 	c = s[0];
-	if (c < 128) {
+	if (c < 128 || awk_mb_cur_max == 1) {
 		*rune = c;
 		return 1;
 	}
@@ -680,7 +680,7 @@ int u8_strlen(const char *s)
 	totlen = 0;
 	for (i = 0; i < n; i += len) {
 		c = s[i];
-		if (c < 128) {
+		if (c < 128 || awk_mb_cur_max == 1) {
 			len = 1;
 		} else {
 			len = u8_nextlen(&s[i]);
@@ -1290,7 +1290,7 @@ int format(char **pbuf, int *pbufsize, const char *s, Node *a)	/* printf-like co
 				int charval = (int) getfval(x);
 
 				if (charval != 0) {
-					if (charval < 128)
+					if (charval < 128 || awk_mb_cur_max == 1)
 						snprintf(p, BUFSZ(p), fmt, charval);
 					else {
 						// possible unicode character