Finish fixing indirect call of builtins.

6 files changed, 153 insertions, 6 deletions

diff --git a/ChangeLog b/ChangeLog
index be2116fa..6f99be92 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,24 @@
+2022-02-07         Arnold D. Robbins     <arnold@skeeve.com>
+
+	Continue fixing indirect calls of builtins.
+
+	* awk.h (check_exact_args, check_args_min_max): Add declarations.
+	* builtin.c (check_exact_args, check_args_min_max): New functions.
+	(do_exp, do_fflush, do_index, do_int, do_isarray, do_length, do_log,
+	do_sqrt, do_strftime, do_systime, do_mktime, do_system, do_tolower,
+	do_toupper, do_atan2, do_sin, do_cos, do_rand, do_srand, do_match,
+	do_sub, do_lshift, do_rshift, do_compl, do_strtonum, do_dcgettext,
+	do_dcngettext, do_bindtextdomain, do_intdiv, do_typeof): Call
+	the argument checking functions.
+	(call_sub, call_match): Manually check argument count.
+	* field.c (do_split, do_patsplit): Call the argument checking
+	functions.
+	* interpret.h (r_interpret): For indirect call of extension functions,
+	pop the function name off the stack when done.
+	* mpfr.c (do_atan2, do_mpfr_func, do_mpfr_int, do_mpfr_compl,
+	do_mpfr_lshift, do_mpfr_rshift, do_mpfr_strtonum, do_mpfr_rand,
+	do_mpfr_srand, do_mpfr_intdiv): Call the argument checking functions.
+
 2022-02-04         Arnold D. Robbins     <arnold@skeeve.com>
 
 	Start fixing issues with indirect calls of builtins.
diff --git a/awk.h b/awk.h
index 9b09eab0..09c929c2 100644
--- a/awk.h
+++ b/awk.h
@@ -1514,6 +1514,8 @@ extern int strncasecmpmbs(const unsigned char *,
 			  const unsigned char *, size_t);
 extern int sanitize_exit_status(int status);
 extern void check_symtab_functab(NODE *dest, const char *fname, const char *msg);
+extern void check_exact_args(int nargs, const char *fname, int count);
+extern void check_args_min_max(int nargs, const char *fname, int min, int max);
 /* debug.c */
 extern void init_debug(void);
 extern int debug_prog(INSTRUCTION *pc);
diff --git a/builtin.c b/builtin.c
index 125468ba..060b2f28 100644
--- a/builtin.c
+++ b/builtin.c
@@ -90,6 +90,22 @@ fatal(_("attempt to use array `%s' in a scalar context"), array_vname(s1)); \
 }} while (false)
 
 
+/* check argument counts --- for use when called indirectly */
+
+void
+check_exact_args(int nargs, const char *fname, int count)
+{
+	if (nargs != count)
+		fatal(_("%s: called with %d arguments"), fname, nargs);
+}
+
+void
+check_args_min_max(int nargs, const char *fname, int min, int max)
+{
+	if (nargs < min || nargs > max)
+		fatal(_("%s: called with %d arguments"), fname, nargs);
+}
+
 /*
  * Since we supply the version of random(), we know what
  * value to use here.
@@ -173,6 +189,8 @@ do_exp(int nargs)
 	NODE *tmp;
 	double d, res;
 
+	check_exact_args(nargs, "exp", 1);
+
 	tmp = POP_SCALAR();
 	if (do_lint && (fixtype(tmp)->flags & NUMBER) == 0)
 		lintwarn(_("%s: received non-numeric argument"), "exp");
@@ -235,6 +253,8 @@ do_fflush(int nargs)
 	 * Now, both calls flush everything.
 	 */
 
+	check_args_min_max(nargs, "fflush", 0, 1);
+
 	/* fflush() */
 	if (nargs == 0) {
 		status = flush_io();	// ERRNO updated
@@ -381,6 +401,8 @@ do_index(int nargs)
 	bool do_single_byte = false;
 	mbstate_t mbs1, mbs2;
 
+	check_exact_args(nargs, "index", 2);
+
 	if (gawk_mb_cur_max > 1) {
 		memset(& mbs1, 0, sizeof(mbstate_t));
 		memset(& mbs2, 0, sizeof(mbstate_t));
@@ -503,6 +525,8 @@ do_int(int nargs)
 	NODE *tmp;
 	double d;
 
+	check_exact_args(nargs, "int", 1);
+
 	tmp = POP_SCALAR();
 	if (do_lint && (fixtype(tmp)->flags & NUMBER) == 0)
 		lintwarn(_("%s: received non-numeric argument"), "int");
@@ -520,6 +544,8 @@ do_isarray(int nargs)
 	NODE *tmp;
 	int ret = 1;
 
+	check_exact_args(nargs, "isarray", 1);
+
 	tmp = POP();
 	if (tmp->type != Node_var_array) {
 		ret = 0;
@@ -538,9 +564,7 @@ do_length(int nargs)
 	NODE *tmp;
 	size_t len;
 
-	// indirect call can pass too many arguments
-	if (nargs != 1)
-		fatal(_("length: called with %d arguments"), nargs);
+	check_exact_args(nargs, "length", 1);
 
 	tmp = POP();
 	if (tmp->type == Node_var_array) {
@@ -601,6 +625,8 @@ do_log(int nargs)
 	NODE *tmp;
 	double d, arg;
 
+	check_exact_args(nargs, "log", 1);
+
 	tmp = POP_SCALAR();
 	if (do_lint && (fixtype(tmp)->flags & NUMBER) == 0)
 		lintwarn(_("%s: received non-numeric argument"), "log");
@@ -1804,6 +1830,8 @@ do_sqrt(int nargs)
 	NODE *tmp;
 	double arg;
 
+	check_exact_args(nargs, "sqrt", 1);
+
 	tmp = POP_SCALAR();
 	if (do_lint && (fixtype(tmp)->flags & NUMBER) == 0)
 		lintwarn(_("%s: received non-numeric argument"), "sqrt");
@@ -1826,6 +1854,8 @@ do_substr(int nargs)
 	double d_index = 0, d_length = 0;
 	size_t src_len;
 
+	check_args_min_max(nargs, "substr", 2, 3);
+
 	if (nargs == 3) {
 		t1 = POP_NUMBER();
 		d_length = get_number_d(t1);
@@ -1990,6 +2020,8 @@ do_strftime(int nargs)
 	(void) time(& fclock);	/* current time of day */
 	do_gmt = false;
 
+	check_args_min_max(nargs, "strftime", 0, 3);
+
 	if (PROCINFO_node != NULL) {
 		sub = make_string("strftime", 8);
 		val = in_array(PROCINFO_node, sub);
@@ -2106,6 +2138,8 @@ do_systime(int nargs ATTRIBUTE_UNUSED)
 {
 	time_t lclock;
 
+	check_exact_args(nargs, "systime", 0);
+
 	(void) time(& lclock);
 	return make_number((AWKNUM) lclock);
 }
@@ -2124,6 +2158,8 @@ do_mktime(int nargs)
 	char save;
 	bool do_gmt;
 
+	check_args_min_max(nargs, "mktime", 1, 2);
+
 	if (nargs == 2) {
 		t2 = POP_SCALAR();
 		do_gmt = boolval(t2);
@@ -2187,6 +2223,8 @@ do_system(int nargs)
 	char save;
 	int status;
 
+	check_exact_args(nargs, "system", 1);
+
 	if (do_sandbox)
 		fatal(_("'system' function not allowed in sandbox mode"));
 
@@ -2443,6 +2481,8 @@ do_tolower(int nargs)
 {
 	NODE *t1, *t2;
 
+	check_exact_args(nargs, "tolower", 1);
+
 	t1 = POP_SCALAR();
 	if (do_lint && (fixtype(t1)->flags & STRING) == 0)
 		lintwarn(_("%s: received non-string argument"), "tolower");
@@ -2474,6 +2514,8 @@ do_toupper(int nargs)
 {
 	NODE *t1, *t2;
 
+	check_exact_args(nargs, "toupper", 1);
+
 	t1 = POP_SCALAR();
 	if (do_lint && (fixtype(t1)->flags & STRING) == 0)
 		lintwarn(_("%s: received non-string argument"), "toupper");
@@ -2506,6 +2548,8 @@ do_atan2(int nargs)
 	NODE *t1, *t2;
 	double d1, d2;
 
+	check_exact_args(nargs, "atan2", 2);
+
 	POP_TWO_SCALARS(t1, t2);
 	if (do_lint) {
 		if ((fixtype(t1)->flags & NUMBER) == 0)
@@ -2528,6 +2572,8 @@ do_sin(int nargs)
 	NODE *tmp;
 	double d;
 
+	check_exact_args(nargs, "sin", 1);
+
 	tmp = POP_SCALAR();
 	if (do_lint && (fixtype(tmp)->flags & NUMBER) == 0)
 		lintwarn(_("%s: received non-numeric argument"), "sin");
@@ -2544,6 +2590,8 @@ do_cos(int nargs)
 	NODE *tmp;
 	double d;
 
+	check_exact_args(nargs, "cos", 1);
+
 	tmp = POP_SCALAR();
 	if (do_lint && (fixtype(tmp)->flags & NUMBER) == 0)
 		lintwarn(_("%s: received non-numeric argument"), "cos");
@@ -2565,6 +2613,9 @@ NODE *
 do_rand(int nargs ATTRIBUTE_UNUSED)
 {
 	double tmprand;
+
+	check_exact_args(nargs, "rand", 0);
+
 #define RAND_DIVISOR ((double)GAWK_RANDOM_MAX+1.0)
 	if (firstrand) {
 		(void) initstate((unsigned) 1, state, SIZEOF_STATE);
@@ -2655,6 +2706,8 @@ do_srand(int nargs)
 		(void) setstate(state);
 	}
 
+	check_args_min_max(nargs, "srand", 0, 1);
+
 	if (nargs == 0)
 		srandom((unsigned int) (save_seed = (long) time((time_t *) 0)));
 	else {
@@ -2687,6 +2740,8 @@ do_match(int nargs)
 	char *subsepstr;
 	size_t subseplen;
 
+	check_args_min_max(nargs, "match", 2, 3);
+
 	dest = NULL;
 	if (nargs == 3) {	/* 3rd optional arg for the subpatterns */
 		dest = POP_PARAM();
@@ -2915,6 +2970,8 @@ do_sub(int nargs, unsigned int flags)
 		double d;
 		NODE *glob_flag;
 
+		check_exact_args(nargs, "gensub", 4);
+
 		tmp = PEEK(3);
 		rp = re_update(tmp);
 
@@ -2943,6 +3000,12 @@ do_sub(int nargs, unsigned int flags)
 		}
 		DEREF(glob_flag);
 	} else {
+		if ((flags & GSUB) != 0) {
+			check_exact_args(nargs, "gsub", 3);
+		} else {
+			check_exact_args(nargs, "sub", 3);
+		}
+
 		/* take care of regexp early, in case re_update is fatal */
 
 		tmp = PEEK(2);
@@ -3309,6 +3372,9 @@ call_sub(const char *name, int nargs)
 		PUSH_ADDRESS(lhs);
 	} else {
 		/* gensub */
+		if (nargs < 3 || nargs > 4)
+			fatal(_("indirect call to gensub requires three to four arguments"));
+
 		if (nargs == 4)
 			rhs = POP();
 		else
@@ -3368,6 +3434,9 @@ call_match(int nargs)
 	NODE *regex, *text, *array;
 	NODE *result;
 
+	if (nargs < 2 || nargs > 3)
+		fatal(_("indirect call to match requires two or three arguments"));
+
 	regex = text = array = NULL;
 	if (nargs == 3)
 		array = POP();
@@ -3409,8 +3478,8 @@ call_split_func(const char *name, int nargs)
 	NODE *result;
 
 	regex = seps = NULL;
-	if (nargs < 2)
-		fatal(_("indirect call to %s requires at least two arguments"),
+	if (nargs < 2 || nargs > 4)
+		fatal(_("indirect call to %s requires two to four arguments"),
 				name);
 
 	if (nargs == 4)
@@ -3474,6 +3543,8 @@ do_lshift(int nargs)
 	uintmax_t uval, ushift, res;
 	AWKNUM val, shift;
 
+	check_exact_args(nargs, "lshift", 2);
+
 	POP_TWO_SCALARS(s1, s2);
 	if (do_lint) {
 		if ((fixtype(s1)->flags & NUMBER) == 0)
@@ -3513,6 +3584,8 @@ do_rshift(int nargs)
 	uintmax_t uval, ushift, res;
 	AWKNUM val, shift;
 
+	check_exact_args(nargs, "rshift", 2);
+
 	POP_TWO_SCALARS(s1, s2);
 	if (do_lint) {
 		if ((fixtype(s1)->flags & NUMBER) == 0)
@@ -3645,6 +3718,8 @@ do_compl(int nargs)
 	double d;
 	uintmax_t uval;
 
+	check_exact_args(nargs, "compl", 1);
+
 	tmp = POP_SCALAR();
 	if (do_lint && (fixtype(tmp)->flags & NUMBER) == 0)
 		lintwarn(_("%s: received non-numeric argument"), "compl");
@@ -3670,6 +3745,8 @@ do_strtonum(int nargs)
 	NODE *tmp;
 	AWKNUM d;
 
+	check_exact_args(nargs, "strtonum", 1);
+
 	tmp = fixtype(POP_SCALAR());
 	if ((tmp->flags & NUMBER) != 0)
 		d = (AWKNUM) tmp->numbr;
@@ -3871,6 +3948,8 @@ do_dcgettext(int nargs)
 	char *domain;
 	char save1 = '\0', save2 = '\0';
 
+	check_args_min_max(nargs, "dcgettext", 1, 3);
+
 	if (nargs == 3) {	/* third argument */
 		tmp = POP_STRING();
 		lc_cat = localecategory_from_argument(tmp);
@@ -3932,6 +4011,8 @@ do_dcngettext(int nargs)
 	char save = '\0', save1 = '\0', save2 = '\0';
 	bool saved_end = false;
 
+	check_args_min_max(nargs, "dcngettext", 3, 5);
+
 	if (nargs == 5) {	/* fifth argument */
 		tmp = POP_STRING();
 		lc_cat = localecategory_from_argument(tmp);
@@ -4013,6 +4094,8 @@ do_bindtextdomain(int nargs)
 	const char *directory, *domain;
 	const char *the_result;
 
+	check_args_min_max(nargs, "bindtextdomain", 1, 2);
+
 	t1 = t2 = NULL;
 	/* set defaults */
 	directory = NULL;
@@ -4066,6 +4149,8 @@ do_intdiv(int nargs)
 	NODE *numerator, *denominator, *result;
 	double num, denom, quotient, remainder;
 
+	check_exact_args(nargs, "intdiv", 3);
+
 	result = POP_PARAM();
 	if (result->type != Node_var_array)
 		fatal(_("intdiv: third argument is not an array"));
@@ -4123,6 +4208,8 @@ do_typeof(int nargs)
 	bool deref = true;
 	NODE *dbg;
 
+	check_args_min_max(nargs, "typeof", 1, 2);
+
 	if (nargs == 2) {	/* 2nd optional arg for debugging */
 		dbg = POP_PARAM();
 		if (dbg->type != Node_var_array)
diff --git a/field.c b/field.c
index 1cbd547d..88309a88 100644
--- a/field.c
+++ b/field.c
@@ -979,6 +979,8 @@ do_split(int nargs)
 			 Regexp *, Setfunc, NODE *, NODE *, bool);
 	Regexp *rp = NULL;
 
+	check_args_min_max(nargs, "split", 3, 4);
+
 	if (nargs == 4) {
 		static bool warned = false;
 
@@ -1081,6 +1083,8 @@ do_patsplit(int nargs)
 	char *s;
 	Regexp *rp = NULL;
 
+	check_args_min_max(nargs, "patsplit", 3, 4);
+
 	if (nargs == 4) {
 		sep_arr = POP_PARAM();
 		if (sep_arr->type != Node_var_array)
diff --git a/interpret.h b/interpret.h
index 071d6497..86a5c412 100644
--- a/interpret.h
+++ b/interpret.h
@@ -67,6 +67,7 @@ r_interpret(INSTRUCTION *code)
 	Regexp *rp;
 	NODE *set_array = NULL;	/* array with a post-assignment routine */
 	NODE *set_idx = NULL;	/* the index of the array element */
+	bool in_indirect_call = false;
 
 
 /* array subscript */
@@ -1059,6 +1060,14 @@ arrayfor:
 					DEREF(t1);
 			}
 			free_api_string_copies();
+
+			if (in_indirect_call) {
+				// pop function name off the stack
+				NODE *fname = POP();
+				DEREF(fname);
+				in_indirect_call = false;
+			}
+
 			PUSH(r);
 		}
 			break;
@@ -1175,7 +1184,10 @@ match_re:
 					r = the_func(arg_count);
 				str_restore(t1, save);
 
-				function_name = POP();	// pop function name off stack
+				// Normally, setup_frame() handles getting rid of the
+				// function name.  Since we have called the builtin directly,
+				// we have to manually do this here.
+				function_name = POP();
 				DEREF(function_name);
 
 				PUSH(r);
@@ -1199,6 +1211,7 @@ match_re:
 					npc[1] = pc[1];
 					npc[1].func_name = fname;	/* name of the builtin */
 					npc[1].c_function = bc->c_function;
+					in_indirect_call = true;
 					ni = npc;
 					JUMPTO(ni);
 				} else
diff --git a/mpfr.c b/mpfr.c
index 4010d0c1..25b7b467 100644
--- a/mpfr.c
+++ b/mpfr.c
@@ -720,6 +720,8 @@ do_mpfr_atan2(int nargs)
 	mpfr_ptr p1, p2;
 	int tval;
 
+	check_exact_args(nargs, "atan2", 2);
+
 	t2 = POP_SCALAR();
 	t1 = POP_SCALAR();
 
@@ -756,6 +758,8 @@ do_mpfr_func(const char *name,
 	int tval;
 	mpfr_prec_t argprec;
 
+	check_exact_args(nargs, name, 1);
+
 	t1 = POP_SCALAR();
 	if (do_lint && (fixtype(t1)->flags & NUMBER) == 0)
 		lintwarn(_("%s: received non-numeric argument"), name);
@@ -827,6 +831,8 @@ do_mpfr_int(int nargs)
 {
 	NODE *tmp, *r;
 
+	check_exact_args(nargs, "int", 1);
+
 	tmp = POP_SCALAR();
 	if (do_lint && (fixtype(tmp)->flags & NUMBER) == 0)
 		lintwarn(_("int: received non-numeric argument"));
@@ -857,6 +863,8 @@ do_mpfr_compl(int nargs)
 	NODE *tmp, *r;
 	mpz_ptr zptr;
 
+	check_exact_args(nargs, "compl", 1);
+
 	tmp = POP_SCALAR();
 	if (do_lint && (fixtype(tmp)->flags & NUMBER) == 0)
 		lintwarn(_("compl: received non-numeric argument"));
@@ -976,6 +984,8 @@ do_mpfr_lshift(int nargs)
 	unsigned long shift;
 	mpz_ptr pz1, pz2;
 
+	check_exact_args(nargs, "lshift", 2);
+
 	t2 = POP_SCALAR();
 	t1 = POP_SCALAR();
 
@@ -1008,6 +1018,8 @@ do_mpfr_rshift(int nargs)
 	unsigned long shift;
 	mpz_ptr pz1, pz2;
 
+	check_exact_args(nargs, "rshift", 2);
+
 	t2 = POP_SCALAR();
 	t1 = POP_SCALAR();
 
@@ -1128,6 +1140,8 @@ do_mpfr_strtonum(int nargs)
 {
 	NODE *tmp, *r;
 
+	check_exact_args(nargs, "strtonum", 1);
+
 	tmp = fixtype(POP_SCALAR());
 	if ((tmp->flags & NUMBER) == 0) {
 		r = mpg_integer();	/* will be changed to MPFR float if necessary in force_mpnum() */
@@ -1165,6 +1179,8 @@ do_mpfr_rand(int nargs ATTRIBUTE_UNUSED)
 	NODE *res;
 	int tval;
 
+	check_exact_args(nargs, "rand", 0);
+
 	if (firstrand) {
 #if 0
 		/* Choose the default algorithm */
@@ -1215,6 +1231,8 @@ do_mpfr_srand(int nargs)
 		firstrand = false;
 	}
 
+	check_args_min_max(nargs, "srand", 0, 1);
+
 	res = mpg_integer();
 	mpz_set(res->mpg_i, seed);	/* previous seed */
 
@@ -1256,6 +1274,8 @@ do_mpfr_intdiv(int nargs)
 	NODE *quotient, *remainder;
 	NODE *sub, **lhs;
 
+	check_exact_args(nargs, "intdiv", 3);
+
 	result = POP_PARAM();
 	if (result->type != Node_var_array)
 		fatal(_("intdiv: third argument is not an array"));