Update awk to Oct 6, 2019 version.

6 files changed, 143 insertions, 33 deletions

diff --git a/usr.bin/awk/FIXES b/usr.bin/awk/FIXES
index 109eda9c71b..c2bc5785fce 100644
--- a/usr.bin/awk/FIXES
+++ b/usr.bin/awk/FIXES
@@ -1,4 +1,4 @@
-/*	$OpenBSD: FIXES,v 1.25 2020/06/10 21:02:33 millert Exp $	*/
+/*	$OpenBSD: FIXES,v 1.26 2020/06/10 21:02:53 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -26,6 +26,10 @@ THIS SOFTWARE.
 This file lists all bug fixes, changes, etc., made since the AWK book
 was sent to the printers in August, 1987.
 
+October 6, 2019:
+	Import code from NetBSD awk that implements RS as a regular
+	expression.
+
 September 10, 2019:
 	Fixes for various array / memory overruns found via gcc's
 	-fsanitize=unknown. Thanks to Alexander Richardson (Github
diff --git a/usr.bin/awk/awk.1 b/usr.bin/awk/awk.1
index fb257d029ec..770f558d1b5 100644
--- a/usr.bin/awk/awk.1
+++ b/usr.bin/awk/awk.1
@@ -1,4 +1,4 @@
-.\"	$OpenBSD: awk.1,v 1.48 2020/06/10 21:01:50 millert Exp $
+.\"	$OpenBSD: awk.1,v 1.49 2020/06/10 21:02:53 millert Exp $
 .\"
 .\" Copyright (C) Lucent Technologies 1997
 .\" All Rights Reserved
@@ -419,6 +419,11 @@ The length of the string matched by the
 function.
 .It Va RS
 Input record separator (default newline).
+If empty, blank lines separate records.
+If more than one character long,
+.Va RS
+is treated as a regular expression, and records are
+separated by text matching the expression.
 .It Va RSTART
 The starting position of the string matched by the
 .Fn match
diff --git a/usr.bin/awk/b.c b/usr.bin/awk/b.c
index 73ff3da84ca..3b6b824ef60 100644
--- a/usr.bin/awk/b.c
+++ b/usr.bin/awk/b.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: b.c,v 1.25 2020/06/10 21:02:33 millert Exp $	*/
+/*	$OpenBSD: b.c,v 1.26 2020/06/10 21:02:53 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -621,6 +621,94 @@ int nematch(fa *f, const char *p0)	/* non-empty match, for sub */
 	return (0);
 }
 
+
+/*
+ * NAME
+ *     fnematch
+ *
+ * DESCRIPTION
+ *     A stream-fed version of nematch which transfers characters to a
+ *     null-terminated buffer. All characters up to and including the last
+ *     character of the matching text or EOF are placed in the buffer. If
+ *     a match is found, patbeg and patlen are set appropriately.
+ *
+ * RETURN VALUES
+ *     0    No match found.
+ *     1    Match found.
+ */
+
+int fnematch(fa *pfa, FILE *f, char **pbuf, int *pbufsize, int quantum)
+{
+	char *buf = *pbuf;
+	int bufsize = *pbufsize;
+	int c, i, j, k, ns, s;
+
+	s = pfa->initstat;
+	patlen = 0;
+
+	/*
+	 * All indices relative to buf.
+	 * i <= j <= k <= bufsize
+	 *
+	 * i: origin of active substring
+	 * j: current character
+	 * k: destination of next getc()
+	 */
+	i = -1, k = 0;
+        do {
+		j = i++;
+		do {
+			if (++j == k) {
+				if (k == bufsize)
+					if (!adjbuf(&buf, &bufsize, bufsize+1, quantum, 0, "fnematch"))
+						FATAL("stream '%.30s...' too long", buf);
+				buf[k++] = (c = getc(f)) != EOF ? c : 0;
+			}
+			c = buf[j];
+			/* assert(c < NCHARS); */
+
+			if ((ns = pfa->gototab[s][c]) != 0)
+				s = ns;
+			else
+				s = cgoto(pfa, s, c);
+
+			if (pfa->out[s]) {	/* final state */
+				patlen = j - i + 1;
+				if (c == 0)	/* don't count $ */
+					patlen--;
+			}
+		} while (buf[j] && s != 1);
+		s = 2;
+	} while (buf[i] && !patlen);
+
+	/* adjbuf() may have relocated a resized buffer. Inform the world. */
+	*pbuf = buf;
+	*pbufsize = bufsize;
+
+	if (patlen) {
+		patbeg = buf + i;
+		/*
+		 * Under no circumstances is the last character fed to
+		 * the automaton part of the match. It is EOF's nullbyte,
+		 * or it sent the automaton into a state with no further
+		 * transitions available (s==1), or both. Room for a
+		 * terminating nullbyte is guaranteed.
+		 *
+		 * ungetc any chars after the end of matching text
+		 * (except for EOF's nullbyte, if present) and null
+		 * terminate the buffer.
+		 */
+		do
+			if (buf[--k] && ungetc(buf[k], f) == EOF)
+				FATAL("unable to ungetc '%c'", buf[k]);
+		while (k > i + patlen);
+		buf[k] = 0;
+		return 1;
+	}
+	else
+		return 0;
+}
+
 Node *reparse(const char *p)	/* parses regular expression pointed to by p */
 {			/* uses relex() to scan regular expression */
 	Node *np;
@@ -805,7 +893,7 @@ replace_repeat(const uschar *reptok, int reptoklen, const uschar *atom,
 	       int atomlen, int firstnum, int secondnum, int special_case)
 {
 	int i, j;
-	uschar *buf = 0;
+	uschar *buf = NULL;
 	int ret = 1;
 	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  */
diff --git a/usr.bin/awk/lib.c b/usr.bin/awk/lib.c
index 03e55eaf701..fe828cb38cd 100644
--- a/usr.bin/awk/lib.c
+++ b/usr.bin/awk/lib.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: lib.c,v 1.29 2020/06/10 21:02:33 millert Exp $	*/
+/*	$OpenBSD: lib.c,v 1.30 2020/06/10 21:02:53 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -206,41 +206,53 @@ void nextfile(void)
 
 int readrec(char **pbuf, int *pbufsize, FILE *inf)	/* read one record into buf */
 {
-	int sep, c;
+	int sep, c, isrec;
 	char *rr, *buf = *pbuf;
 	int bufsize = *pbufsize;
 	char *rs = getsval(rsloc);
 
-	if ((sep = *rs) == 0) {
-		sep = '\n';
-		while ((c=getc(inf)) == '\n' && c != EOF)	/* skip leading \n's */
-			;
-		if (c != EOF)
-			ungetc(c, inf);
-	}
-	for (rr = buf; ; ) {
-		for (; (c=getc(inf)) != sep && c != EOF; ) {
-			if (rr-buf+1 > bufsize)
-				if (!adjbuf(&buf, &bufsize, 1+rr-buf, recsize, &rr, "readrec 1"))
-					FATAL("input record `%.30s...' too long", buf);
+	if (*rs && rs[1]) {
+		int found;
+
+		fa *pfa = makedfa(rs, 1);
+		found = fnematch(pfa, inf, &buf, &bufsize, recsize);
+		if (found)
+			*patbeg = 0;
+	} else {
+		if ((sep = *rs) == 0) {
+			sep = '\n';
+			while ((c=getc(inf)) == '\n' && c != EOF)	/* skip leading \n's */
+				;
+			if (c != EOF)
+				ungetc(c, inf);
+		}
+		for (rr = buf; ; ) {
+			for (; (c=getc(inf)) != sep && c != EOF; ) {
+				if (rr-buf+1 > bufsize)
+					if (!adjbuf(&buf, &bufsize, 1+rr-buf,
+					    recsize, &rr, "readrec 1"))
+						FATAL("input record `%.30s...' too long", buf);
+				*rr++ = c;
+			}
+			if (*rs == sep || c == EOF)
+				break;
+			if ((c = getc(inf)) == '\n' || c == EOF)	/* 2 in a row */
+				break;
+			if (!adjbuf(&buf, &bufsize, 2+rr-buf, recsize, &rr,
+			    "readrec 2"))
+				FATAL("input record `%.30s...' too long", buf);
+			*rr++ = '\n';
 			*rr++ = c;
 		}
-		if (*rs == sep || c == EOF)
-			break;
-		if ((c = getc(inf)) == '\n' || c == EOF) /* 2 in a row */
-			break;
-		if (!adjbuf(&buf, &bufsize, 2+rr-buf, recsize, &rr, "readrec 2"))
+		if (!adjbuf(&buf, &bufsize, 1+rr-buf, recsize, &rr, "readrec 3"))
 			FATAL("input record `%.30s...' too long", buf);
-		*rr++ = '\n';
-		*rr++ = c;
+		*rr = 0;
 	}
-	if (!adjbuf(&buf, &bufsize, 1+rr-buf, recsize, &rr, "readrec 3"))
-		FATAL("input record `%.30s...' too long", buf);
-	*rr = 0;
-	   DPRINTF( ("readrec saw <%s>, returns %d\n", buf, c == EOF && rr == buf ? 0 : 1) );
 	*pbuf = buf;
 	*pbufsize = bufsize;
-	return c == EOF && rr == buf ? 0 : 1;
+	isrec = *buf || !feof(inf);
+	DPRINTF( ("readrec saw <%s>, returns %d\n", buf, isrec) );
+	return isrec;
 }
 
 char *getargv(int n)	/* get ARGV[n] */
diff --git a/usr.bin/awk/main.c b/usr.bin/awk/main.c
index bd5cd7ca627..a0e4e1415dc 100644
--- a/usr.bin/awk/main.c
+++ b/usr.bin/awk/main.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: main.c,v 1.30 2020/06/10 21:02:33 millert Exp $	*/
+/*	$OpenBSD: main.c,v 1.31 2020/06/10 21:02:53 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 20190910";
+const char	*version = "version 20191006";
 
 #define DEBUG
 #include <stdio.h>
diff --git a/usr.bin/awk/proto.h b/usr.bin/awk/proto.h
index 3ec687028d8..0abcf78437b 100644
--- a/usr.bin/awk/proto.h
+++ b/usr.bin/awk/proto.h
@@ -1,4 +1,4 @@
-/*	$OpenBSD: proto.h,v 1.13 2020/06/10 21:02:33 millert Exp $	*/
+/*	$OpenBSD: proto.h,v 1.14 2020/06/10 21:02:53 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -55,6 +55,7 @@ extern	int	member(int, const char *);
 extern	int	match(fa *, const char *);
 extern	int	pmatch(fa *, const char *);
 extern	int	nematch(fa *, const char *);
+extern	int	fnematch(fa *, FILE *, char **, int *, int);
 extern	Node	*reparse(const char *);
 extern	Node	*regexp(void);
 extern	Node	*primary(void);