Update awk to December 18, 2020 version.

Includes the official fix for +-inf and +-nan handling.

4 files changed, 49 insertions, 30 deletions

diff --git a/usr.bin/awk/FIXES b/usr.bin/awk/FIXES
index cb35981b64d..05f47946793 100644
--- a/usr.bin/awk/FIXES
+++ b/usr.bin/awk/FIXES
@@ -1,4 +1,4 @@
-/*	$OpenBSD: FIXES,v 1.39 2020/12/09 20:00:11 millert Exp $	*/
+/*	$OpenBSD: FIXES,v 1.40 2020/12/18 21:36:24 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -26,6 +26,18 @@ THIS SOFTWARE.
 This file lists all bug fixes, changes, etc., made since the AWK book
 was sent to the printers in August, 1987.
 
+December 18, 2020:
+	Fix problems converting inf and NaN values in lib.c:is_valid_number.
+	Enhance number to string conversion to do the right thing for
+	NaN and inf values.  Things are now pretty much the same as in
+	gawk.  (Found a gawk bug while we're at it.) Added a torture
+	test for these values.  Thanks to Arnold Robbins.  Allows closing
+	of PR #101.
+
+December 15, 2020:
+	Merge PR #99, which gets the right header for strcasecmp.
+	Thanks to GitHub user michaelforney.
+
 December 8, 2020:
 	Merge PR #98: Disallow hex data. Allow only +nan, -nan,
 	+inf, -inf (case independent) to give NaN and infinity values.
diff --git a/usr.bin/awk/lib.c b/usr.bin/awk/lib.c
index 61d9b7a05ee..8cbdd6d29c6 100644
--- a/usr.bin/awk/lib.c
+++ b/usr.bin/awk/lib.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: lib.c,v 1.43 2020/12/17 20:06:09 millert Exp $	*/
+/*	$OpenBSD: lib.c,v 1.44 2020/12/18 21:36:24 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -31,6 +31,7 @@ THIS SOFTWARE.
 #include <stdlib.h>
 #include <stdarg.h>
 #include <limits.h>
+#include <math.h>
 #include "awk.h"
 
 char	EMPTY[] = { '\0' };
@@ -784,6 +785,8 @@ bool is_valid_number(const char *s, bool trailing_stuff_ok,
 	double r;
 	char *ep;
 	bool retval = false;
+	bool is_nan = false;
+	bool is_inf = false;
 
 	if (no_trailing)
 		*no_trailing = false;
@@ -792,47 +795,38 @@ bool is_valid_number(const char *s, bool trailing_stuff_ok,
 		s++;
 
 	// no hex floating point, sorry
-	if (s[0] == '0' && (s[1] == 'x' || s[1] == 'X'))
+	if (s[0] == '0' && tolower((uschar)s[1]) == 'x')
 		return false;
 
 	// allow +nan, -nan, +inf, -inf, any other letter, no
 	if (s[0] == '+' || s[0] == '-') {
-		if ((strncasecmp(s+1, "nan", 3) == 0 ||
-		     strncasecmp(s+1, "inf", 3) == 0)) {
-			trailing_stuff_ok = false;
-			ep = (char *)(long)s + 4;
-			if (isspace((uschar)*ep)) {
-			    trailing_stuff_ok = true;
-			    do {
-				    ep++;
-			    } while (isspace((uschar)*ep));
-			}
-			if (no_trailing)
-				*no_trailing = (*ep == '\0');
-			if (*ep != '\0' && !trailing_stuff_ok)
-				return false;
-		} else if (! isdigit((uschar)s[1]) && s[1] != '.')
+		is_nan = (strncasecmp(s+1, "nan", 3) == 0);
+		is_inf = (strncasecmp(s+1, "inf", 3) == 0);
+		if ((is_nan || is_inf)
+		    && (isspace((uschar)s[4]) || s[4] == '\0'))
+			goto convert;
+		else if (! isdigit((uschar)s[1]) && s[1] != '.')
 			return false;
-	} else if (! isdigit((uschar)s[0]) && s[0] != '.')
+	}
+	else if (! isdigit((uschar)s[0]) && s[0] != '.')
 		return false;
 
+convert:
 	errno = 0;
 	r = strtod(s, &ep);
 	if (ep == s || errno == ERANGE)
 		return false;
 
+	if (isnan(r) && s[0] == '-' && signbit(r) == 0)
+		r = -r;
+
 	if (result != NULL)
 		*result = r;
 
-	// check for trailing stuff
-	while (isspace((uschar)*ep))
-		ep++;
+	retval = (isspace((uschar)*ep) || *ep == '\0' || trailing_stuff_ok);
 
-	if (no_trailing)
+	if (no_trailing != NULL)
 		*no_trailing = (*ep == '\0');
 
-	// return true if found the end, or trailing stuff is allowed
-	retval = (*ep == '\0') || trailing_stuff_ok;
-
 	return retval;
 }
diff --git a/usr.bin/awk/main.c b/usr.bin/awk/main.c
index 6aac4d5fa64..5a195940b94 100644
--- a/usr.bin/awk/main.c
+++ b/usr.bin/awk/main.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: main.c,v 1.46 2020/12/09 20:00:11 millert Exp $	*/
+/*	$OpenBSD: main.c,v 1.47 2020/12/18 21:36:24 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 20201208";
+const char	*version = "version 20201218";
 
 #define DEBUG
 #include <stdio.h>
diff --git a/usr.bin/awk/tran.c b/usr.bin/awk/tran.c
index 1ea64d240d8..41a0faa4a4d 100644
--- a/usr.bin/awk/tran.c
+++ b/usr.bin/awk/tran.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: tran.c,v 1.32 2020/12/09 20:00:11 millert Exp $	*/
+/*	$OpenBSD: tran.c,v 1.33 2020/12/18 21:36:24 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -419,10 +419,21 @@ Awkfloat getfval(Cell *vp)	/* get float val of a Cell */
 	return(vp->fval);
 }
 
+static char *get_inf_nan(double d)
+{
+	if (isinf(d)) {
+		return (d < 0 ? "-inf" : "+inf");
+	} else if (isnan(d)) {
+		return (signbit(d) != 0 ? "-nan" : "+nan");
+	} else
+		return NULL;
+}
+
 static char *get_str_val(Cell *vp, char **fmt)        /* get string val of a Cell */
 {
 	int n;
 	double dtemp;
+	char *p;
 
 	if ((vp->tval & (NUM | STR)) == 0)
 		funnyvar(vp, "read value of");
@@ -459,7 +470,9 @@ static char *get_str_val(Cell *vp, char **fmt)        /* get string val of a Cel
 	{ \
 		if (freeable(vp)) \
 			xfree(vp->sval); \
-		if (modf(vp->fval, &dtemp) == 0)	/* it's integral */ \
+		if ((p = get_inf_nan(vp->fval)) != NULL) \
+			n = (vp->sval = strdup(p)) ? 0 : -1; \
+		else if (modf(vp->fval, &dtemp) == 0)	/* it's integral */ \
 			n = asprintf(&vp->sval, "%.30g", vp->fval); \
 		else \
 			n = asprintf(&vp->sval, *fmt, vp->fval); \