initial import of NetBSD tree

3 files changed, 410 insertions, 0 deletions

diff --git a/usr.bin/cut/Makefile b/usr.bin/cut/Makefile
new file mode 100644
index 00000000000..abea02683d0
--- /dev/null
+++ b/usr.bin/cut/Makefile
@@ -0,0 +1,6 @@
+#	$NetBSD: Makefile,v 1.3 1995/03/26 20:51:24 glass Exp $
+#	@(#)Makefile	8.1 (Berkeley) 6/6/93
+
+PROG=	cut
+
+.include <bsd.prog.mk>
diff --git a/usr.bin/cut/cut.1 b/usr.bin/cut/cut.1
new file mode 100644
index 00000000000..4ea43e4300d
--- /dev/null
+++ b/usr.bin/cut/cut.1
@@ -0,0 +1,122 @@
+.\"	$NetBSD: cut.1,v 1.6 1995/10/02 20:19:26 jtc Exp $
+.\"
+.\" Copyright (c) 1989, 1990, 1993
+.\"	The Regents of the University of California.  All rights reserved.
+.\"
+.\" This code is derived from software contributed to Berkeley by
+.\" the Institute of Electrical and Electronics Engineers, Inc.
+.\"
+.\" Redistribution and use in source and binary forms, with or without
+.\" modification, are permitted provided that the following conditions
+.\" are met:
+.\" 1. Redistributions of source code must retain the above copyright
+.\"    notice, this list of conditions and the following disclaimer.
+.\" 2. Redistributions in binary form must reproduce the above copyright
+.\"    notice, this list of conditions and the following disclaimer in the
+.\"    documentation and/or other materials provided with the distribution.
+.\" 3. All advertising materials mentioning features or use of this software
+.\"    must display the following acknowledgement:
+.\"	This product includes software developed by the University of
+.\"	California, Berkeley and its contributors.
+.\" 4. Neither the name of the University nor the names of its contributors
+.\"    may be used to endorse or promote products derived from this software
+.\"    without specific prior written permission.
+.\"
+.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+.\" ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+.\" SUCH DAMAGE.
+.\"
+.\"     @(#)cut.1	8.1 (Berkeley) 6/6/93
+.\"
+.Dd June 6, 1993
+.Dt CUT 1
+.Os
+.Sh NAME
+.Nm cut
+.Nd select portions of each line of a file
+.Sh SYNOPSIS
+.Nm cut
+.Fl b Ar list
+.Op Fl n
+.Op Ar
+.Nm cut
+.Fl c Ar list
+.Op Ar
+.Nm cut
+.Fl f Ar list
+.Op Fl d Ar delim
+.Op Fl s
+.Op Ar
+.Sh DESCRIPTION
+The
+.Nm cut
+utility selects portions of each line (as specified by
+.Ar list  )
+from each
+.Ar file
+(or the standard input by default), and writes them to the
+standard output.
+The items specified by
+.Ar list
+can be in terms of column position or in terms of fields delimited
+by a special character. Column numbering starts from 1.
+.Pp
+.Ar List
+is a comma or whitespace separated set of increasing numbers and/or
+number ranges.
+Number ranges consist of a number, a dash
+.Pq Li \- ,
+and a second number
+and select the fields or columns from the first number to the second,
+inclusive.
+Numbers or number ranges may be preceded by a dash, which selects all
+fields or columns from 1 to the first number.
+Numbers or number ranges may be followed by a dash, which selects all
+fields or columns from the last number to the end of the line.
+Numbers and number ranges may be repeated, overlapping, and in any order.
+It is not an error to select fields or columns not present in the
+input line.
+.Pp
+The options are as follows:
+.Bl -tag -width Fl
+.It Fl b Ar list
+The 
+.Ar list
+specifies byte positions.
+.It Fl c Ar list
+The
+.Ar list
+specifies character positions.
+.It Fl d Ar string
+Use the first character of
+.Ar string
+as the field delimiter character instead of the tab character.
+.It Fl f Ar list
+The
+.Ar list
+specifies fields, delimited in the input by a single tab character.
+Output fields are separated by a single tab character.
+.It Fl n
+Do not split multi-byte characters.
+.It Fl s
+Suppresses lines with no field delimiter characters.
+Unless specified, lines with no delimiters are passed through unmodified.
+.El
+.Pp
+.Nm Cut
+exits 0 on success, 1 if an error occurred.
+.Sh SEE ALSO
+.Xr paste 1
+.Sh STANDARDS
+The
+.Nm cut
+utility conforms to
+.St -p1003.2-92 .
diff --git a/usr.bin/cut/cut.c b/usr.bin/cut/cut.c
new file mode 100644
index 00000000000..7d820b182d8
--- /dev/null
+++ b/usr.bin/cut/cut.c
@@ -0,0 +1,282 @@
+/*	$NetBSD: cut.c,v 1.9 1995/09/02 05:59:23 jtc Exp $	*/
+
+/*
+ * Copyright (c) 1989, 1993
+ *	The Regents of the University of California.  All rights reserved.
+ *
+ * This code is derived from software contributed to Berkeley by
+ * Adam S. Moskowitz of Menlo Consulting and Marciano Pitargue.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ *    must display the following acknowledgement:
+ *	This product includes software developed by the University of
+ *	California, Berkeley and its contributors.
+ * 4. Neither the name of the University nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#ifndef lint
+static char copyright[] =
+"@(#) Copyright (c) 1989, 1993\n\
+	The Regents of the University of California.  All rights reserved.\n";
+#endif /* not lint */
+
+#ifndef lint
+#if 0
+static char sccsid[] = "@(#)cut.c	8.3 (Berkeley) 5/4/95";
+#endif
+static char rcsid[] = "$NetBSD: cut.c,v 1.9 1995/09/02 05:59:23 jtc Exp $";
+#endif /* not lint */
+
+#include <ctype.h>
+#include <err.h>
+#include <errno.h>
+#include <limits.h>
+#include <locale.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+int	cflag;
+char	dchar;
+int	dflag;
+int	fflag;
+int	sflag;
+
+void	c_cut __P((FILE *, char *));
+void	f_cut __P((FILE *, char *));
+void	get_list __P((char *));
+void	usage __P((void));
+
+int
+main(argc, argv)
+	int argc;
+	char *argv[];
+{
+	FILE *fp;
+	void (*fcn) __P((FILE *, char *));
+	int ch;
+
+	setlocale (LC_ALL, "");
+
+	dchar = '\t';			/* default delimiter is \t */
+
+	/* Since we don't support multi-byte characters, the -c and -b 
+	   options are equivalent, and the -n option is meaningless. */
+	while ((ch = getopt(argc, argv, "b:c:d:f:sn")) != EOF)
+		switch(ch) {
+		case 'b':
+		case 'c':
+			fcn = c_cut;
+			get_list(optarg);
+			cflag = 1;
+			break;
+		case 'd':
+			dchar = *optarg;
+			dflag = 1;
+			break;
+		case 'f':
+			get_list(optarg);
+			fcn = f_cut;
+			fflag = 1;
+			break;
+		case 's':
+			sflag = 1;
+			break;
+		case 'n':
+			break;
+		case '?':
+		default:
+			usage();
+		}
+	argc -= optind;
+	argv += optind;
+
+	if (fflag) {
+		if (cflag)
+			usage();
+	} else if (!cflag || dflag || sflag)
+		usage();
+
+	if (*argv)
+		for (; *argv; ++argv) {
+			if (!(fp = fopen(*argv, "r")))
+				err(1, "%s", *argv);
+			fcn(fp, *argv);
+			(void)fclose(fp);
+		}
+	else
+		fcn(stdin, "stdin");
+	exit(0);
+}
+
+int autostart, autostop, maxval;
+
+char positions[_POSIX2_LINE_MAX + 1];
+
+void
+get_list(list)
+	char *list;
+{
+	register int setautostart, start, stop;
+	register char *pos;
+	char *p;
+
+	/*
+	 * set a byte in the positions array to indicate if a field or
+	 * column is to be selected; use +1, it's 1-based, not 0-based.
+	 * This parser is less restrictive than the Draft 9 POSIX spec.
+	 * POSIX doesn't allow lists that aren't in increasing order or
+	 * overlapping lists.  We also handle "-3-5" although there's no
+	 * real reason too.
+	 */
+	for (; p = strtok(list, ", \t"); list = NULL) {
+		setautostart = start = stop = 0;
+		if (*p == '-') {
+			++p;
+			setautostart = 1;
+		}
+		if (isdigit(*p)) {
+			start = stop = strtol(p, &p, 10);
+			if (setautostart && start > autostart)
+				autostart = start;
+		}
+		if (*p == '-') {
+			if (isdigit(p[1]))
+				stop = strtol(p + 1, &p, 10);
+			if (*p == '-') {
+				++p;
+				if (!autostop || autostop > stop)
+					autostop = stop;
+			}
+		}
+		if (*p)
+			errx(1, "[-cf] list: illegal list value\n");
+		if (!stop || !start)
+			errx(1, "[-cf] list: values may not include zero\n");
+		if (stop > _POSIX2_LINE_MAX)
+			errx(1, "[-cf] list: %d too large (max %d)\n",
+			    stop, _POSIX2_LINE_MAX);
+		if (maxval < stop)
+			maxval = stop;
+		for (pos = positions + start; start++ <= stop; *pos++ = 1);
+	}
+
+	/* overlapping ranges */
+	if (autostop && maxval > autostop)
+		maxval = autostop;
+
+	/* set autostart */
+	if (autostart)
+		memset(positions + 1, '1', autostart);
+}
+
+/* ARGSUSED */
+void
+c_cut(fp, fname)
+	FILE *fp;
+	char *fname;
+{
+	register int ch, col;
+	register char *pos;
+
+	for (;;) {
+		pos = positions + 1;
+		for (col = maxval; col; --col) {
+			if ((ch = getc(fp)) == EOF)
+				return;
+			if (ch == '\n')
+				break;
+			if (*pos++)
+				(void)putchar(ch);
+		}
+		if (ch != '\n')
+			if (autostop)
+				while ((ch = getc(fp)) != EOF && ch != '\n')
+					(void)putchar(ch);
+			else
+				while ((ch = getc(fp)) != EOF && ch != '\n');
+		(void)putchar('\n');
+	}
+}
+
+void
+f_cut(fp, fname)
+	FILE *fp;
+	char *fname;
+{
+	register int ch, field, isdelim;
+	register char *pos, *p, sep;
+	int output;
+	char lbuf[_POSIX2_LINE_MAX + 1];
+
+	for (sep = dchar; fgets(lbuf, sizeof(lbuf), fp);) {
+		output = 0;
+		for (isdelim = 0, p = lbuf;; ++p) {
+			if (!(ch = *p))
+				errx(1, "%s: line too long.\n", fname);
+			/* this should work if newline is delimiter */
+			if (ch == sep)
+				isdelim = 1;
+			if (ch == '\n') {
+				if (!isdelim && !sflag)
+					(void)printf("%s", lbuf);
+				break;
+			}
+		}
+		if (!isdelim)
+			continue;
+
+		pos = positions + 1;
+		for (field = maxval, p = lbuf; field; --field, ++pos) {
+			if (*pos) {
+				if (output++)
+					(void)putchar(sep);
+				while ((ch = *p++) != '\n' && ch != sep)
+					(void)putchar(ch);
+			} else
+				while ((ch = *p++) != '\n' && ch != sep);
+			if (ch == '\n')
+				break;
+		}
+		if (ch != '\n')
+			if (autostop) {
+				if (output)
+					(void)putchar(sep);
+				for (; (ch = *p) != '\n'; ++p)
+					(void)putchar(ch);
+			} else
+				for (; (ch = *p) != '\n'; ++p);
+		(void)putchar('\n');
+	}
+}
+
+void
+usage()
+{
+	(void)fprintf(stderr,
+"usage:\tcut -c list [file1 ...]\n\tcut -f list [-s] [-d delim] [file ...]\n");
+	exit(1);
+}