Bug fix in interval expressions.

ChangeLog

@@ -1,3 +1,10 @@
+2019-12-27         Arnold D. Robbins     <arnold@skeeve.com>
+
+	* b.c (replace_repeat): Fix a bug whereby a{0,3} could match
+	four a's.  Thanks to Anonymous AWK fan <awkfan77@mailfence.com>
+	for the report. Also, minor code formatting cleanups.
+	* testdir/T.int-expr: New file.
+
 2019-12-11         Arnold D. Robbins     <arnold@skeeve.com>
 
 	* README: Renamed to ...

FIXES

@@ -25,6 +25,10 @@ THIS SOFTWARE.
 This file lists all bug fixes, changes, etc., made since the AWK book
 was sent to the printers in August, 1987.
 
+December 27, 2019:
+	Fix a bug whereby a{0,3} could match four a's.  Thanks to
+	"Anonymous AWK fan" for the report.
+
 December 11, 2019:
 	Further printf-related fixes for 32 bit systems.
 	Thanks again to Christos Zoulas.

b.c

@@ -908,7 +908,7 @@ replace_repeat(const uschar *reptok, int reptoklen, const uschar *atom,
 	int i, j;
 	uschar *buf = 0;
 	int ret = 1;
-	int init_q = (firstnum == 0);		/* first added char will be ? */
+	bool 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	*/
@@ -935,7 +935,7 @@ replace_repeat(const uschar *reptok, int reptoklen, const uschar *atom,
 		buf[j++] = '(';
 		buf[j++] = ')';
 	}
-	for (i=1; i < firstnum; i++) {		/* copy x reps 	*/
+	for (i = 1; i < firstnum; i++) {	/* copy x reps 	*/
 		memcpy(&buf[j], atom, atomlen);
 		j += atomlen;
 	}
@@ -944,7 +944,7 @@ replace_repeat(const uschar *reptok, int reptoklen, const uschar *atom,
 	} else if (special_case == REPEAT_WITH_Q) {
 		if (init_q)
 			buf[j++] = '?';
-		for (i = 0; i < n_q_reps; i++) {	/* copy x? reps */
+		for (i = init_q; i < n_q_reps; i++) {	/* copy x? reps */
 			memcpy(&buf[j], atom, atomlen);
 			j += atomlen;
 			buf[j++] = '?';
@@ -1166,15 +1166,17 @@ rescan:
 				if (commafound) {
 					if (digitfound) { /* {n,m} */
 						m = num;
-						if (m<n)
+						if (m < n)
 							FATAL("illegal repetition expression: class %.20s",
 								lastre);
-						if ((n==0) && (m==1)) {
+						if (n == 0 && m == 1) {
 							return QUEST;
 						}
 					} else {	/* {n,} */
-						if (n==0) return STAR;
+						if (n == 0)
-						if (n==1) return PLUS;
+							return STAR;
+						else if (n == 1)
+							return PLUS;
 					}
 				} else {
 					if (digitfound) { /* {n} same as {n,n} */
@@ -1187,7 +1189,7 @@ rescan:
 				}
 				if (repeat(starttok, prestr-starttok, lastatom,
 					   startreptok - lastatom, n, m) > 0) {
-					if ((n==0) && (m==0)) {
+					if (n == 0 && m == 0) {
 						return EMPTYRE;
 					}
 					/* must rescan input for next token */
@@ -1313,7 +1315,7 @@ void freefa(fa *f)	/* free a finite automaton */
 	for (i = 0; i <= f->accept; i++) {
 		xfree(f->re[i].lfollow);
 		if (f->re[i].ltype == CCL || f->re[i].ltype == NCCL)
-			xfree((f->re[i].lval.np));
+			xfree(f->re[i].lval.np);
 	}
 	xfree(f->restr);
 	xfree(f->out);

main.c

@@ -22,7 +22,7 @@ ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
 THIS SOFTWARE.
 ****************************************************************/
 
-const char	*version = "version 20191211";
+const char	*version = "version 20191227";
 
 #define DEBUG
 #include <stdio.h>

testdir/T.int-expr

@@ -0,0 +1,82 @@
+echo T.int-expr: test interval expressions
+
+awk=${awk-../a.out}
+
+rm -f foo
+
+cat << \EOF > prog
+NF == 0		{ next }
+$1 == "pat"	{ pattern = $2; next }
+{
+	check = ($1 ~ pattern)
+	printf("%s ~ /%s/ -> should be %d, is %d\n", $1, pattern, $2, check)
+}
+EOF
+
+cat << \EOF > foo.in
+pat	ab{0}c
+ac	1
+abc	0
+
+pat	ab{1}c
+ac	0
+abc	1
+abbc	0
+
+pat	ab{1,}c
+ac	0
+abc	1
+abbc	1
+abbbc	1
+abbbbc	1
+
+pat	ab{0,1}c
+ac	1
+abc	1
+abbc	0
+
+pat	ab{0,3}c
+ac	1
+abc	1
+abbc	1
+abbbc	1
+abbbbc	0
+
+pat	ab{1,3}c
+ac	0
+abc	1
+abbc	1
+abbbc	1
+abbbbc	0
+EOF
+
+cat << \EOF > foo1
+ac ~ /ab{0}c/ -> should be 1, is 1
+abc ~ /ab{0}c/ -> should be 0, is 0
+ac ~ /ab{1}c/ -> should be 0, is 0
+abc ~ /ab{1}c/ -> should be 1, is 1
+abbc ~ /ab{1}c/ -> should be 0, is 0
+ac ~ /ab{1,}c/ -> should be 0, is 0
+abc ~ /ab{1,}c/ -> should be 1, is 1
+abbc ~ /ab{1,}c/ -> should be 1, is 1
+abbbc ~ /ab{1,}c/ -> should be 1, is 1
+abbbbc ~ /ab{1,}c/ -> should be 1, is 1
+ac ~ /ab{0,1}c/ -> should be 1, is 1
+abc ~ /ab{0,1}c/ -> should be 1, is 1
+abbc ~ /ab{0,1}c/ -> should be 0, is 0
+ac ~ /ab{0,3}c/ -> should be 1, is 1
+abc ~ /ab{0,3}c/ -> should be 1, is 1
+abbc ~ /ab{0,3}c/ -> should be 1, is 1
+abbbc ~ /ab{0,3}c/ -> should be 1, is 1
+abbbbc ~ /ab{0,3}c/ -> should be 0, is 0
+ac ~ /ab{1,3}c/ -> should be 0, is 0
+abc ~ /ab{1,3}c/ -> should be 1, is 1
+abbc ~ /ab{1,3}c/ -> should be 1, is 1
+abbbc ~ /ab{1,3}c/ -> should be 1, is 1
+abbbbc ~ /ab{1,3}c/ -> should be 0, is 0
+EOF
+
+
+$awk -f prog foo.in > foo2
+diff foo1 foo2 || echo 'BAD: T.int-expr (1)'
+rm -f prog