Update awk to the Jan 22, 2024 version.

4 files changed, 43 insertions, 32 deletions

diff --git a/usr.bin/awk/FIXES b/usr.bin/awk/FIXES
index d77bec29c62..3b059250d5c 100644
--- a/usr.bin/awk/FIXES
+++ b/usr.bin/awk/FIXES
@@ -25,11 +25,22 @@ THIS SOFTWARE.
 This file lists all bug fixes, changes, etc., made since the 
 second edition of the AWK book was published in September 2023.
 
+Jan 22, 2024:
+	Restore the ability to compile with g++. Thanks to
+	Arnold Robbins.
+
+Dec 24, 2023:
+	matchop dereference after free problem fix when the first
+	argument is a function call. thanks to Oguz Ismail Uysal.
+	Fix inconsistent handling of --csv and FS set in the
+	command line. Thanks to Wilbert van der Poel.
+	casting changes to int for is* functions. 
+
 Nov 27, 2023:
 	Fix exit status of system on MacOS. update to REGRESS.
 	Thanks to Arnold Robbins. 
 	Fix inconsistent handling of -F and --csv, and loss of csv
-	mode when FS is set. Thanks to Wilbert van der Poel.
+	mode when FS is set. 
 	
 Nov 24, 2023:
         Fix issue #199: gototab improvements to dynamically resize the
diff --git a/usr.bin/awk/b.c b/usr.bin/awk/b.c
index 523e3ee195c..bc3f06fd320 100644
--- a/usr.bin/awk/b.c
+++ b/usr.bin/awk/b.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: b.c,v 1.49 2023/11/25 16:31:33 millert Exp $	*/
+/*	$OpenBSD: b.c,v 1.50 2024/01/25 16:40:51 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -117,7 +117,7 @@ static int entry_cmp(const void *l, const void *r);
 static int get_gototab(fa*, int, int);
 static int set_gototab(fa*, int, int, int);
 static void clear_gototab(fa*, int);
-extern int u8_rune(int *, const uschar *);
+extern int u8_rune(int *, const char *);
 
 static int *
 intalloc(size_t n, const char *f)
@@ -422,7 +422,7 @@ int *cclenter(const char *argp)	/* add a character class */
 		FATAL("out of space for character class [%.10s...] 1", p);
 	bp = buf;
 	for (i = 0; *p != 0; ) {
-		n = u8_rune(&c, p);
+		n = u8_rune(&c, (const char *) p);
 		p += n;
 		if (c == '\\') {
 			c = quoted(&p);
@@ -430,7 +430,7 @@ int *cclenter(const char *argp)	/* add a character class */
 			if (*p != 0) {
 				c = bp[-1];
 				/* c2 = *p++; */
-				n = u8_rune(&c2, p);
+				n = u8_rune(&c2, (const char *) p);
 				p += n;
 				if (c2 == '\\')
 					c2 = quoted(&p); /* BUG: sets p, has to be u8 size */
@@ -624,7 +624,7 @@ static int get_gototab(fa *f, int state, int ch) /* hide gototab inplementation
 
 	key.ch = ch;
 	key.state = 0;	/* irrelevant */
-	item = bsearch(& key, f->gototab[state].entries,
+	item = (gtte *) bsearch(& key, f->gototab[state].entries,
 			f->gototab[state].inuse, sizeof(gtte),
 			entry_cmp);
 
@@ -668,7 +668,7 @@ static int set_gototab(fa *f, int state, int ch, int val) /* hide gototab inplem
 
 		key.ch = ch;
 		key.state = 0;	/* irrelevant */
-		item = bsearch(& key, f->gototab[state].entries,
+		item = (gtte *) bsearch(& key, f->gototab[state].entries,
 				f->gototab[state].inuse, sizeof(gtte),
 				entry_cmp);
 
@@ -716,7 +716,7 @@ int match(fa *f, const char *p0)	/* shortest match ? */
 		return(1);
 	do {
 		/* assert(*p < NCHARS); */
-		n = u8_rune(&rune, p);
+		n = u8_rune(&rune, (const char *) p);
 		if ((ns = get_gototab(f, s, rune)) != 0)
 			s = ns;
 		else
@@ -749,7 +749,7 @@ int pmatch(fa *f, const char *p0)	/* longest match, for sub */
 			if (f->out[s])		/* final state */
 				patlen = q-p;
 			/* assert(*q < NCHARS); */
-			n = u8_rune(&rune, q);
+			n = u8_rune(&rune, (const char *) q);
 			if ((ns = get_gototab(f, s, rune)) != 0)
 				s = ns;
 			else
@@ -780,7 +780,7 @@ int pmatch(fa *f, const char *p0)	/* longest match, for sub */
 		s = 2;
 		if (*p == 0)
 			break;
-		n = u8_rune(&rune, p);
+		n = u8_rune(&rune, (const char *) p);
 		p += n;
 	} while (1); /* was *p++ */
 	return (0);
@@ -805,7 +805,7 @@ int nematch(fa *f, const char *p0)	/* non-empty match, for sub */
 			if (f->out[s])		/* final state */
 				patlen = q-p;
 			/* assert(*q < NCHARS); */
-			n = u8_rune(&rune, q);
+			n = u8_rune(&rune, (const char *) q);
 			if ((ns = get_gototab(f, s, rune)) != 0)
 				s = ns;
 			else
@@ -893,7 +893,7 @@ bool fnematch(fa *pfa, FILE *f, char **pbuf, int *pbufsize, int quantum)
 			}
 		}
 
-		j += u8_rune(&c, (uschar *)j);
+		j += u8_rune(&c, j);
 
 		if ((ns = get_gototab(pfa, s, c)) != 0)
 			s = ns;
@@ -913,7 +913,7 @@ bool fnematch(fa *pfa, FILE *f, char **pbuf, int *pbufsize, int quantum)
 			break;     /* best match found */
 
 		/* no match at origin i, next i and start over */
-		i += u8_rune(&c, (uschar *)i);
+		i += u8_rune(&c, i);
 		if (c == 0)
 			break;    /* no match */
 		j = i;
@@ -1234,8 +1234,6 @@ static int repeat(const uschar *reptok, int reptoklen, const uschar *atom,
 	return 0;
 }
 
-extern int u8_rune(int *, const uschar *); /* run.c; should be in header file */
-
 int relex(void)		/* lexical analyzer for reparse */
 {
 	int c, n;
@@ -1253,7 +1251,7 @@ int relex(void)		/* lexical analyzer for reparse */
 rescan:
 	starttok = prestr;
 
-	if ((n = u8_rune(&rlxval, prestr)) > 1) {
+	if ((n = u8_rune(&rlxval, (const char *) prestr)) > 1) {
 		prestr += n;
 		starttok = prestr;
 		return CHAR;
@@ -1300,7 +1298,7 @@ rescan:
 		if (!adjbuf((char **) &buf, &bufsz, n, n, (char **) &bp, "relex1"))
 			FATAL("out of space for reg expr %.10s...", lastre);
 		for (; ; ) {
-			if ((n = u8_rune(&rlxval, prestr)) > 1) {
+			if ((n = u8_rune(&rlxval, (const char *) prestr)) > 1) {
 				for (i = 0; i < n; i++)
 					*bp++ = *prestr++;
 				continue;
diff --git a/usr.bin/awk/main.c b/usr.bin/awk/main.c
index 3ec64332ff5..481e98b078a 100644
--- a/usr.bin/awk/main.c
+++ b/usr.bin/awk/main.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: main.c,v 1.67 2023/11/28 20:54:38 millert Exp $	*/
+/*	$OpenBSD: main.c,v 1.68 2024/01/25 16:40:51 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -23,7 +23,7 @@ ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
 THIS SOFTWARE.
 ****************************************************************/
 
-const char	*version = "version 20231127";
+const char	*version = "version 20240122";
 
 #define DEBUG
 #include <stdio.h>
@@ -180,8 +180,6 @@ int main(int argc, char *argv[])
 		}
 		if (strcmp(argv[1], "--csv") == 0) {	/* turn on csv input processing */
 			CSV = true;
-			if (fs)
-				WARNING("danger: don't set FS when --csv is in effect");
 			argc--;
 			argv++;
 			continue;
@@ -203,8 +201,6 @@ int main(int argc, char *argv[])
  			break;
 		case 'F':	/* set field separator */
 			fs = setfs(getarg(&argc, &argv, "no field separator"));
-			if (CSV)
-				WARNING("danger: don't set FS when --csv is in effect");
 			break;
 		case 'v':	/* -v a=1 to be done NOW.  one -v for each */
 			vn = getarg(&argc, &argv, "no variable name");
@@ -238,6 +234,9 @@ int main(int argc, char *argv[])
 		}
 	}
 
+	if (CSV && (fs != NULL || lookup("FS", symtab) != NULL))
+		WARNING("danger: don't set FS when --csv is in effect");
+
 	/* argv[1] is now the first argument */
 	if (npfile == 0) {	/* no -f; first argument is program */
 		if (argc <= 1) {
diff --git a/usr.bin/awk/run.c b/usr.bin/awk/run.c
index af1153f6b7d..73ab148952b 100644
--- a/usr.bin/awk/run.c
+++ b/usr.bin/awk/run.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: run.c,v 1.83 2023/11/28 20:54:38 millert Exp $	*/
+/*	$OpenBSD: run.c,v 1.84 2024/01/25 16:40:51 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -796,7 +796,7 @@ int runetochar(char *str, int c)
 
 Cell *matchop(Node **a, int n)	/* ~ and match() */
 {
-	Cell *x, *y;
+	Cell *x, *y, *z;
 	char *s, *t;
 	int i;
 	int cstart, cpatlen, len;
@@ -818,7 +818,7 @@ Cell *matchop(Node **a, int n)	/* ~ and match() */
 		i = (*mf)(pfa, s);
 		tempfree(y);
 	}
-	tempfree(x);
+	z = x;
 	if (n == MATCHFCN) {
 		int start = patbeg - s + 1; /* origin 1 */
 		if (patlen < 0) {
@@ -840,11 +840,13 @@ Cell *matchop(Node **a, int n)	/* ~ and match() */
 		x = gettemp();
 		x->tval = NUM;
 		x->fval = start;
-		return x;
 	} else if ((n == MATCH && i == 1) || (n == NOTMATCH && i == 0))
-		return(True);
+		x = True;
 	else
-		return(False);
+		x = False;
+
+	tempfree(z);
+	return x;
 }
 
 
@@ -1299,7 +1301,8 @@ int format(char **pbuf, int *pbufsize, const char *s, Node *a)	/* printf-like co
 
 						if (bs == NULL)	{ // invalid character
 							// use unicode invalid character, 0xFFFD
-							bs = "\357\277\275";
+							static char invalid_char[] = "\357\277\275";
+							bs = invalid_char;
 							count = 3;
 						}
 						t = bs;
@@ -2567,7 +2570,7 @@ Cell *dosub(Node **a, int subop)        /* sub and gsub */
 	start = getsval(x);
 	while (pmatch(pfa, start)) {
 		if (buf == NULL) {
-			if ((pb = buf = malloc(bufsz)) == NULL)
+			if ((pb = buf = (char *) malloc(bufsz)) == NULL)
 				FATAL("out of memory in dosub");
 			tempstat = pfa->initstat;
 			pfa->initstat = 2;
@@ -2672,7 +2675,7 @@ Cell *gensub(Node **a, int nnn)	/* global selective substitute */
 	int mflag, tempstat, num, whichm;
 	int bufsz = recsize;
 
-	if ((buf = malloc(bufsz)) == NULL)
+	if ((buf = (char *) malloc(bufsz)) == NULL)
 		FATAL("out of memory in gensub");
 	mflag = 0;	/* if mflag == 0, can replace empty string */
 	num = 0;