Update awk to Jan 31, 2020 version.

11 files changed, 120 insertions, 54 deletions

diff --git a/usr.bin/awk/FIXES b/usr.bin/awk/FIXES
index d1c3217d28d..04c201fd60b 100644
--- a/usr.bin/awk/FIXES
+++ b/usr.bin/awk/FIXES
@@ -1,4 +1,4 @@
-/*	$OpenBSD: FIXES,v 1.30 2020/06/10 21:04:40 millert Exp $	*/
+/*	$OpenBSD: FIXES,v 1.31 2020/06/10 21:05:02 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -26,6 +26,25 @@ THIS SOFTWARE.
 This file lists all bug fixes, changes, etc., made since the AWK book
 was sent to the printers in August, 1987.
 
+January 31, 2020:
+	Merge PR #70, which avoids use of variable length arrays. Thanks
+	to GitHub user michaelforney.  Fix issue #60 ({0} in interval
+	expressions doesn't work). Thanks to Arnold Robbins.
+
+January 24, 2020:
+	A number of small cleanups from Christos Zoulas.  Add the close
+	on exec flag to files/pipes opened for redirection; courtesy of
+	Arnold Robbins.
+
+January 19, 2020:
+	If POSIXLY_CORRECT is set in the environment, then sub and gsub
+	use POSIX rules for multiple backslashes.  This fixes Issue #66,
+	while maintaining backwards compatibility.
+
+January 9, 2020:
+	Input/output errors on closing files are now fatal instead of
+	mere warnings. Thanks to Martijn Dekker <martijn@inlv.org>.
+
 January 5, 2020:
 	Fix a bug in the concatentation of two string constants into
 	one done in the grammar.  Fixes GitHub issue #61.  Thanks
@@ -64,13 +83,13 @@ October 25, 2019:
 
 October 24, 2019:
 	Import second round of code cleanups from NetBSD. Much thanks
-	to Christos Zoulas (Github user zoulasc). Merges PR 53.
+	to Christos Zoulas (GitHub user zoulasc). Merges PR 53.
 	Add an optimization for string concatenation, also from
 	Christos.
 
 October 17, 2019:
 	Import code cleanups from NetBSD. Much thanks to Christos
-	Zoulas (Github user zoulasc). Merges PR 51.
+	Zoulas (GitHub user zoulasc). Merges PR 51.
 
 October 6, 2019:
 	Import code from NetBSD awk that implements RS as a regular
@@ -78,7 +97,7 @@ October 6, 2019:
 
 September 10, 2019:
 	Fixes for various array / memory overruns found via gcc's
-	-fsanitize=unknown. Thanks to Alexander Richardson (Github
+	-fsanitize=unknown. Thanks to Alexander Richardson (GitHub
 	user arichardson). Merges PRs 47 and 48.
 
 July 28, 2019:
diff --git a/usr.bin/awk/awk.1 b/usr.bin/awk/awk.1
index 770f558d1b5..84e4f057e73 100644
--- a/usr.bin/awk/awk.1
+++ b/usr.bin/awk/awk.1
@@ -1,4 +1,4 @@
-.\"	$OpenBSD: awk.1,v 1.49 2020/06/10 21:02:53 millert Exp $
+.\"	$OpenBSD: awk.1,v 1.50 2020/06/10 21:05:02 millert Exp $
 .\"
 .\" Copyright (C) Lucent Technologies 1997
 .\" All Rights Reserved
@@ -726,6 +726,14 @@ Returns integer argument x shifted by n bits to the left.
 .It Fn rshift x n
 Returns integer argument x shifted by n bits to the right.
 .El
+.Sh ENVIRONMENT
+The following environment variables affect the execution of
+.Nm :
+.Bl -tag -width POSIXLY_CORRECT
+.It Ev POSIXLY_CORRECT
+When set, behave in accordance with the standard, even when it conflicts
+with historical behavior.
+.El
 .Sh EXIT STATUS
 .Ex -std awk
 .Pp
@@ -792,7 +800,12 @@ The
 .Nm
 utility is compliant with the
 .St -p1003.1-2008
-specification.
+specification except that consecutive backslashes in the replacement
+string argument for
+.Fn sub
+and
+.Fn gsub
+are not collapsed.
 .Pp
 The flags
 .Op Fl \&dV
diff --git a/usr.bin/awk/awk.h b/usr.bin/awk/awk.h
index ba604cae6a6..e010dd7184d 100644
--- a/usr.bin/awk/awk.h
+++ b/usr.bin/awk/awk.h
@@ -1,4 +1,4 @@
-/*	$OpenBSD: awk.h,v 1.21 2020/06/10 21:03:56 millert Exp $	*/
+/*	$OpenBSD: awk.h,v 1.22 2020/06/10 21:05:02 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -61,6 +61,7 @@ extern bool	safe;		/* false => unsafe, true => safe */
 #define	RECSIZE	(8 * 1024)	/* sets limit on records, fields, etc., etc. */
 extern int	recsize;	/* size of current record, orig RECSIZE */
 
+extern char	EMPTY[];	/* this avoid -Wwritable-strings issues */
 extern char	**FS;
 extern char	**RS;
 extern char	**ORS;
@@ -79,8 +80,6 @@ extern int	lineno;		/* line number in awk program */
 extern int	errorflag;	/* 1 if error has occurred */
 extern bool	donefld;	/* true if record broken into fields */
 extern bool	donerec;	/* true if record is valid (no fld has changed */
-extern char	inputFS[];	/* FS at time of input, for field splitting */
-
 extern int	dbg;
 
 extern const char *patbeg;	/* beginning of pattern matched */
diff --git a/usr.bin/awk/awkgram.y b/usr.bin/awk/awkgram.y
index 9a59fc785aa..85034770f07 100644
--- a/usr.bin/awk/awkgram.y
+++ b/usr.bin/awk/awkgram.y
@@ -1,4 +1,4 @@
-/*	$OpenBSD: awkgram.y,v 1.12 2020/06/10 21:03:56 millert Exp $	*/
+/*	$OpenBSD: awkgram.y,v 1.13 2020/06/10 21:05:02 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -51,7 +51,7 @@ Node	*arglist = 0;	/* list of args for current function */
 %token	<i>	NL ',' '{' '(' '|' ';' '/' ')' '}' '[' ']'
 %token	<i>	ARRAY
 %token	<i>	MATCH NOTMATCH MATCHOP
-%token	<i>	FINAL DOT ALL CCL NCCL CHAR OR STAR QUEST PLUS EMPTYRE
+%token	<i>	FINAL DOT ALL CCL NCCL CHAR OR STAR QUEST PLUS EMPTYRE ZERO
 %token	<i>	AND BOR APPEND EQ GE GT LE LT NE IN
 %token	<i>	ARG BLTIN BREAK CLOSE CONTINUE DELETE DO EXIT FOR FUNC
 %token	<i>	SUB GSUB IF INDEX LSUBSTR MATCHFCN NEXT NEXTFILE
diff --git a/usr.bin/awk/b.c b/usr.bin/awk/b.c
index 97719cf1132..687ff5015f8 100644
--- a/usr.bin/awk/b.c
+++ b/usr.bin/awk/b.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: b.c,v 1.30 2020/06/10 21:04:40 millert Exp $	*/
+/*	$OpenBSD: b.c,v 1.31 2020/06/10 21:05:02 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -271,6 +271,8 @@ void penter(Node *p)	/* set up parent pointers and leaf indices */
 		parent(left(p)) = p;
 		parent(right(p)) = p;
 		break;
+	case ZERO:
+		break;
 	default:	/* can't happen */
 		FATAL("can't happen: unknown type %d in penter", type(p));
 		break;
@@ -285,6 +287,7 @@ void freetr(Node *p)	/* free parse tree */
 		xfree(p);
 		break;
 	UNARY
+	case ZERO:
 		freetr(left(p));
 		xfree(p);
 		break;
@@ -444,6 +447,8 @@ void cfoll(fa *f, Node *v)	/* enter follow set of each leaf of vertex v into lfo
 		cfoll(f,left(v));
 		cfoll(f,right(v));
 		break;
+	case ZERO:
+		break;
 	default:	/* can't happen */
 		FATAL("can't happen: unknown type %d in cfoll", type(v));
 	}
@@ -487,6 +492,8 @@ int first(Node *p)	/* collects initially active leaves of p into setvec */
 		b = first(right(p));
 		if (first(left(p)) == 0 || b == 0) return(0);
 		return(1);
+	case ZERO:
+		return 0;
 	}
 	FATAL("can't happen: unknown type %d in first", type(p));	/* can't happen */
 	return(-1);
@@ -846,6 +853,9 @@ Node *unary(Node *np)
 	case QUEST:
 		rtok = relex();
 		return (unary(op2(QUEST, np, NIL)));
+	case ZERO:
+		rtok = relex();
+		return (unary(op2(ZERO, np, NIL)));
 	default:
 		return (np);
 	}
@@ -880,7 +890,7 @@ int (xisblank)(int c)
 
 #endif
 
-struct charclass {
+static const struct charclass {
 	const char *cc_name;
 	int cc_namelen;
 	int (*cc_func)(int);
@@ -916,7 +926,7 @@ replace_repeat(const uschar *reptok, int reptoklen, const uschar *atom,
 	int i, j;
 	uschar *buf = NULL;
 	int ret = 1;
-	bool init_q = (firstnum == 0);		/* first added char will be ? */
+	int init_q = (firstnum == 0);		/* first added char will be ? */
 	int n_q_reps = secondnum-firstnum;	/* m>n, so reduce until {1,m-n} left  */
 	int prefix_length = reptok - basestr;	/* prefix includes first rep	*/
 	int suffix_length = strlen((const char *) reptok) - reptoklen;	/* string after rep specifier	*/
@@ -1024,7 +1034,7 @@ int relex(void)		/* lexical analyzer for reparse */
 	static uschar *buf = NULL;
 	static int bufsz = 100;
 	uschar *bp;
-	struct charclass *cc;
+	const struct charclass *cc;
 	int i;
 	int num, m;
 	bool commafound, digitfound;
@@ -1198,7 +1208,7 @@ rescan:
 				if (repeat(starttok, prestr-starttok, lastatom,
 					   startreptok - lastatom, n, m) > 0) {
 					if (n == 0 && m == 0) {
-						return EMPTYRE;
+						return ZERO;
 					}
 					/* must rescan input for next token */
 					goto rescan;
diff --git a/usr.bin/awk/lex.c b/usr.bin/awk/lex.c
index 9861c7d25b4..4e7a546d019 100644
--- a/usr.bin/awk/lex.c
+++ b/usr.bin/awk/lex.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: lex.c,v 1.17 2020/06/10 21:04:40 millert Exp $	*/
+/*	$OpenBSD: lex.c,v 1.18 2020/06/10 21:05:02 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -44,7 +44,7 @@ typedef struct Keyword {
 	int	type;
 } Keyword;
 
-Keyword keywords[] ={	/* keep sorted: binary searched */
+const Keyword keywords[] = {	/* keep sorted: binary searched */
 	{ "BEGIN",	XBEGIN,		XBEGIN },
 	{ "END",	XEND,		XEND },
 	{ "NF",		VARNF,		VARNF },
@@ -102,14 +102,14 @@ int peek(void);
 int gettok(char **, int *);
 int binsearch(char *, Keyword *, int);
 
-int peek(void)
+static int peek(void)
 {
 	int c = input();
 	unput(c);
 	return c;
 }
 
-int gettok(char **pbuf, int *psz)	/* get next input token */
+static int gettok(char **pbuf, int *psz)	/* get next input token */
 {
 	int c, retc;
 	char *buf = *pbuf;
@@ -401,7 +401,7 @@ int string(void)
 			case 'r': *bp++ = '\r'; break;
 			case 'b': *bp++ = '\b'; break;
 			case 'v': *bp++ = '\v'; break;
-			case 'a': *bp++ = '\007'; break;
+			case 'a': *bp++ = '\a'; break;
 			case '\\': *bp++ = '\\'; break;
 
 			case '0': case '1': case '2': /* octal: \d \dd \ddd */
@@ -451,7 +451,7 @@ int string(void)
 }
 
 
-int binsearch(char *w, Keyword *kp, int n)
+static int binsearch(char *w, const Keyword *kp, int n)
 {
 	int cond, low, mid, high;
 
@@ -471,7 +471,7 @@ int binsearch(char *w, Keyword *kp, int n)
 
 int word(char *w)
 {
-	Keyword *kp;
+	const Keyword *kp;
 	int c, n;
 
 	n = binsearch(w, keywords, sizeof(keywords)/sizeof(keywords[0]));
@@ -587,6 +587,8 @@ int input(void)	/* get next lexical input character */
 
 void unput(int c)	/* put lexical character back on input */
 {
+	if (c == '\n')  
+		lineno--;
 	if (yysptr >= yysbuf + sizeof(yysbuf))
 		FATAL("pushed back too much: %.20s...", yysbuf);
 	*yysptr++ = c;
diff --git a/usr.bin/awk/lib.c b/usr.bin/awk/lib.c
index ee3e187aa77..f00a5ec856b 100644
--- a/usr.bin/awk/lib.c
+++ b/usr.bin/awk/lib.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: lib.c,v 1.32 2020/06/10 21:03:56 millert Exp $	*/
+/*	$OpenBSD: lib.c,v 1.33 2020/06/10 21:05:02 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -31,18 +31,21 @@ THIS SOFTWARE.
 #include <stdlib.h>
 #include <unistd.h>
 #include <stdarg.h>
+#include <limits.h>
 #include "awk.h"
 #include "ytab.h"
 
+char	EMPTY[] = { '\0' };
 FILE	*infile	= NULL;
-char	*file	= "";
+char	*file	= EMPTY;
 char	*record;
 int	recsize	= RECSIZE;
 char	*fields;
 int	fieldssize = RECSIZE;
 
 Cell	**fldtab;	/* pointers to Cells */
-char	inputFS[100] = " ";
+static size_t	len_inputFS = 0;
+static char	*inputFS = NULL; /* FS at time of input, for field splitting */
 
 #define	MAXFLD	2
 int	nfields	= MAXFLD;	/* last allocated slot for $i */
@@ -54,8 +57,8 @@ int	lastfld	= 0;	/* last used field */
 int	argno	= 1;	/* current input argument number */
 extern	Awkfloat *ARGC;
 
-static Cell dollar0 = { OCELL, CFLD, NULL, "", 0.0, REC|STR|DONTFREE };
-static Cell dollar1 = { OCELL, CFLD, NULL, "", 0.0, FLD|STR|DONTFREE };
+static Cell dollar0 = { OCELL, CFLD, NULL, EMPTY, 0.0, REC|STR|DONTFREE };
+static Cell dollar1 = { OCELL, CFLD, NULL, EMPTY, 0.0, FLD|STR|DONTFREE };
 
 void recinit(unsigned int n)
 {
@@ -118,9 +121,17 @@ void initgetrec(void)
  */
 void savefs(void)
 {
-	if (strlen(getsval(fsloc)) >= sizeof (inputFS))
+	size_t len;
+	if ((len = strlen(getsval(fsloc))) < len_inputFS) {
+		strlcpy(inputFS, *FS, sizeof(inputFS));	/* for subsequent field splitting */
+		return;
+	}
+
+	len_inputFS = len + 1;
+	inputFS = realloc(inputFS, len_inputFS);
+	if (inputFS == NULL)
 		FATAL("field separator %.10s... is too long", *FS);
-	strlcpy(inputFS, *FS, sizeof(inputFS));
+	memcpy(inputFS, *FS, len_inputFS);
 }
 
 static bool firsttime = true;
@@ -335,14 +346,14 @@ void fldbld(void)	/* create fields from current record */
 		*fr = 0;
 	} else if ((sep = *inputFS) == 0) {		/* new: FS="" => 1 char/field */
 		for (i = 0; *r != '\0'; r += n) {
-			char buf[MB_CUR_MAX + 1];
+			char buf[MB_LEN_MAX + 1];
 
 			i++;
 			if (i > nfields)
 				growfldtab(i);
 			if (freeable(fldtab[i]))
 				xfree(fldtab[i]->sval);
-			n = mblen(r, MB_CUR_MAX);
+			n = mblen(r, MB_LEN_MAX);
 			if (n < 0)
 				n = 1;
 			memcpy(buf, r, n);
@@ -406,7 +417,7 @@ void cleanfld(int n1, int n2)	/* clean out fields n1 .. n2 inclusive */
 		p = fldtab[i];
 		if (freeable(p))
 			xfree(p->sval);
-		p->sval = "";
+		p->sval = EMPTY,
 		p->tval = FLD | STR | DONTFREE;
 	}
 }
diff --git a/usr.bin/awk/main.c b/usr.bin/awk/main.c
index cb23a884667..9c4e47874a9 100644
--- a/usr.bin/awk/main.c
+++ b/usr.bin/awk/main.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: main.c,v 1.35 2020/06/10 21:04:40 millert Exp $	*/
+/*	$OpenBSD: main.c,v 1.36 2020/06/10 21:05:02 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 20200105";
+const char	*version = "version 20200131";
 
 #define DEBUG
 #include <stdio.h>
diff --git a/usr.bin/awk/maketab.c b/usr.bin/awk/maketab.c
index a488d7ed187..6c25233503a 100644
--- a/usr.bin/awk/maketab.c
+++ b/usr.bin/awk/maketab.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: maketab.c,v 1.16 2020/06/10 21:03:36 millert Exp $	*/
+/*	$OpenBSD: maketab.c,v 1.17 2020/06/10 21:05:02 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -123,8 +123,6 @@ int main(int argc, char *argv[])
 	printf("#include <stdio.h>\n");
 	printf("#include \"awk.h\"\n");
 	printf("#include \"ytab.h\"\n\n");
-	for (i = SIZE; --i >= 0; )
-		names[i] = "";
 
 	if (argc != 2) {
 		fprintf(stderr, "usage: maketab YTAB_H\n");
@@ -161,10 +159,8 @@ int main(int argc, char *argv[])
 		table[p->token-FIRSTTOKEN] = p->name;
 	printf("\nCell *(*proctab[%d])(Node **, int) = {\n", SIZE);
 	for (i=0; i<SIZE; i++)
-		if (table[i]==NULL)
-			printf("\tnullproc,\t/* %s */\n", names[i]);
-		else
-			printf("\t%s,\t/* %s */\n", table[i], names[i]);
+		printf("\t%s,\t/* %s */\n",
+		    table[i] ? table[i] : "nullproc", names[i] ? names[i] : "");
 	printf("};\n\n");
 
 	printf("const char *tokname(int n)\n");	/* print a tokname() function */
diff --git a/usr.bin/awk/run.c b/usr.bin/awk/run.c
index 605b71e47f6..c4a4254de64 100644
--- a/usr.bin/awk/run.c
+++ b/usr.bin/awk/run.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: run.c,v 1.55 2020/06/10 21:04:40 millert Exp $	*/
+/*	$OpenBSD: run.c,v 1.56 2020/06/10 21:05:02 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -27,6 +27,7 @@ THIS SOFTWARE.
 #include <stdio.h>
 #include <ctype.h>
 #include <errno.h>
+#include <fcntl.h>
 #include <setjmp.h>
 #include <limits.h>
 #include <math.h>
@@ -91,7 +92,7 @@ static Cell	exitcell	={ OJUMP, JEXIT, 0, 0, 0.0, NUM, NULL };
 Cell	*jexit	= &exitcell;
 static Cell	retcell		={ OJUMP, JRET, 0, 0, 0.0, NUM, NULL };
 Cell	*jret	= &retcell;
-static Cell	tempcell	={ OCELL, CTEMP, 0, "", 0.0, NUM|STR|DONTFREE, NULL };
+static Cell	tempcell	={ OCELL, CTEMP, 0, EMPTY, 0.0, NUM|STR|DONTFREE, NULL };
 
 Node	*curnode = NULL;	/* the node being executed, for debugging */
 
@@ -226,7 +227,7 @@ struct Frame *fp = NULL;	/* frame pointer. bottom level unused */
 
 Cell *call(Node **a, int n)	/* function call.  very kludgy and fragile */
 {
-	static Cell newcopycell = { OCELL, CCOPY, 0, "", 0.0, NUM|STR|DONTFREE, NULL };
+	static Cell newcopycell = { OCELL, CCOPY, 0, EMPTY, 0.0, NUM|STR|DONTFREE, NULL };
 	int i, ncall, ndef;
 	int freed = 0; /* handles potential double freeing when fcn & param share a tempcell */
 	Node *x;
@@ -1254,7 +1255,8 @@ Cell *split(Node **a, int nnn)	/* split(a[0], a[1], a[2]); a[3] is type */
 {
 	Cell *x = NULL, *y, *ap;
 	const char *s, *origs, *t;
-	char *fs = NULL, *origfs = NULL;
+	const char *fs = NULL;
+	char *origfs = NULL;
 	int sep;
 	char temp, num[50];
 	int n, tempstat, arg3type;
@@ -1268,7 +1270,7 @@ Cell *split(Node **a, int nnn)	/* split(a[0], a[1], a[2]); a[3] is type */
 		fs = getsval(fsloc);
 	else if (arg3type == STRING) {	/* split(str,arr,"string") */
 		x = execute(a[2]);
-		origfs = fs = strdup(getsval(x));
+		fs = origfs = strdup(getsval(x));
 		if (fs == NULL)
 			FATAL("out of space in split");
 		tempfree(x);
@@ -1820,6 +1822,8 @@ FILE *openfile(int a, const char *us)
 		files[i].fname = tostring(s);
 		files[i].fp = fp;
 		files[i].mode = m;
+		if (fp != stdin && fp != stdout && fp != stderr)
+			(void) fcntl(fileno(fp), F_SETFD, FD_CLOEXEC);
 	}
 	return fp;
 }
@@ -1845,13 +1849,13 @@ Cell *closefile(Node **a, int n)
 	for (i = 0; i < nfiles; i++) {
 		if (files[i].fname && strcmp(x->sval, files[i].fname) == 0) {
 			if (ferror(files[i].fp))
-				WARNING( "i/o error occurred on %s", files[i].fname );
+				FATAL( "i/o error occurred on %s", files[i].fname );
 			if (files[i].mode == '|' || files[i].mode == LE)
 				stat = pclose(files[i].fp);
 			else
 				stat = fclose(files[i].fp);
 			if (stat == EOF)
-				WARNING( "i/o error occurred closing %s", files[i].fname );
+				FATAL( "i/o error occurred closing %s", files[i].fname );
 			if (i > 2)	/* don't do /dev/std... */
 				xfree(files[i].fname);
 			files[i].fname = NULL;	/* watch out for ref thru this */
@@ -1871,13 +1875,13 @@ void closeall(void)
 	for (i = 0; i < FOPEN_MAX; i++) {
 		if (files[i].fp) {
 			if (ferror(files[i].fp))
-				WARNING( "i/o error occurred on %s", files[i].fname );
+				FATAL( "i/o error occurred on %s", files[i].fname );
 			if (files[i].mode == '|' || files[i].mode == LE)
 				stat = pclose(files[i].fp);
 			else
 				stat = fclose(files[i].fp);
 			if (stat == EOF)
-				WARNING( "i/o error occurred while closing %s", files[i].fname );
+				FATAL( "i/o error occurred while closing %s", files[i].fname );
 		}
 	}
 }
@@ -2059,6 +2063,13 @@ void backsub(char **pb_ptr, const char **sptr_ptr)	/* handle \\& variations */
 {						/* sptr[0] == '\\' */
 	char *pb = *pb_ptr;
 	const char *sptr = *sptr_ptr;
+	static bool first = true;
+	static bool do_posix = false;
+
+	if (first) {
+		first = false;
+		do_posix = (getenv("POSIXLY_CORRECT") != NULL);
+	}
 
 	if (sptr[1] == '\\') {
 		if (sptr[2] == '\\' && sptr[3] == '&') { /* \\\& -> \& */
@@ -2068,6 +2079,9 @@ void backsub(char **pb_ptr, const char **sptr_ptr)	/* handle \\& variations */
 		} else if (sptr[2] == '&') {	/* \\& -> \ + matched */
 			*pb++ = '\\';
 			sptr += 2;
+		} else if (do_posix) {		/* \\x -> \x */
+			sptr++;
+			*pb++ = *sptr++;
 		} else {			/* \\x -> \\x */
 			*pb++ = *sptr++;
 			*pb++ = *sptr++;
diff --git a/usr.bin/awk/tran.c b/usr.bin/awk/tran.c
index 0318be0c57d..8e8b755f9bb 100644
--- a/usr.bin/awk/tran.c
+++ b/usr.bin/awk/tran.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: tran.c,v 1.25 2020/06/10 21:04:40 millert Exp $	*/
+/*	$OpenBSD: tran.c,v 1.26 2020/06/10 21:05:02 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -529,12 +529,14 @@ Cell *catstr(Cell *a, Cell *b) /* concatenate a and b */
 	if (p == NULL)
 		FATAL("out of space concatenating %s and %s", sa, sb);
 	snprintf(p, l, "%s%s", sa, sb);
-	char *newbuf = malloc(strlen(p) + 2);
+
+	l++;	// add room for ' '
+	char *newbuf = malloc(l);
 	if (newbuf == NULL)
 		FATAL("out of space concatenating %s and %s", sa, sb);
 	// See string() in lex.c; a string "xx" is stored in the symbol
 	// table as "xx ".
-	sprintf(newbuf, "%s ", p);
+	snprintf(newbuf, l, "%s ", p);
 	c = setsymtab(newbuf, p, 0.0, CON|STR|DONTFREE, symtab);
 	free(p);
 	free(newbuf);