Update to the One True Awk, 2nd edition (Sep 12, 2023).

This corresponds to the 2nd edition of "The AWK Programming Language"
and adds support for UTF-8 and comma-separated value inputs.

1 files changed, 13 insertions, 3 deletions

diff --git a/usr.bin/awk/awk.h b/usr.bin/awk/awk.h
index 1c389ce8c20..bd491ad2908 100644
--- a/usr.bin/awk/awk.h
+++ b/usr.bin/awk/awk.h
@@ -1,4 +1,4 @@
-/*	$OpenBSD: awk.h,v 1.28 2022/09/01 15:21:28 millert Exp $	*/
+/*	$OpenBSD: awk.h,v 1.29 2023/09/17 14:49:44 millert Exp $	*/
 /****************************************************************
 Copyright (C) Lucent Technologies 1997
 All Rights Reserved
@@ -80,6 +80,8 @@ extern char	**SUBSEP;
 extern Awkfloat *RSTART;
 extern Awkfloat *RLENGTH;
 
+extern bool	CSV;		/* true for csv input */
+
 extern char	*record;	/* points to $0 */
 extern int	lineno;		/* line number in awk program */
 extern int	errorflag;	/* 1 if error has occurred */
@@ -236,7 +238,8 @@ extern	int	pairstack[], paircnt;
 
 /* structures used by regular expression matching machinery, mostly b.c: */
 
-#define NCHARS	(256+3)		/* 256 handles 8-bit chars; 128 does 7-bit */
+#define NCHARS	(1256+3)		/* 256 handles 8-bit chars; 128 does 7-bit */
+				/* BUG: some overflows (caught) if we use 256 */
 				/* watch out in match(), etc. */
 #define	HAT	(NCHARS+2)	/* matches ^ in regular expr */
 #define NSTATES	32
@@ -247,12 +250,19 @@ typedef struct rrow {
 		int i;
 		Node *np;
 		uschar *up;
+		int *rp; /* rune representation of char class */
 	} lval;		/* because Al stores a pointer in it! */
 	int	*lfollow;
 } rrow;
 
+typedef struct gtt { /* gototab entry */
+	unsigned int ch;
+	unsigned int state;
+} gtt;
+
 typedef struct fa {
-	unsigned int	**gototab;
+	gtt	**gototab;
+	int	gototab_len;
 	uschar	*out;
 	uschar	*restr;
 	int	**posns;