cut.c revision 24360 
1/*
2 * Copyright (c) 1989, 1993
3 *	The Regents of the University of California.  All rights reserved.
4 *
5 * This code is derived from software contributed to Berkeley by
6 * Adam S. Moskowitz of Menlo Consulting and Marciano Pitargue.
7 *
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
10 * are met:
11 * 1. Redistributions of source code must retain the above copyright
12 *    notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 *    notice, this list of conditions and the following disclaimer in the
15 *    documentation and/or other materials provided with the distribution.
16 * 3. All advertising materials mentioning features or use of this software
17 *    must display the following acknowledgement:
18 *	This product includes software developed by the University of
19 *	California, Berkeley and its contributors.
20 * 4. Neither the name of the University nor the names of its contributors
21 *    may be used to endorse or promote products derived from this software
22 *    without specific prior written permission.
23 *
24 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
27 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
34 * SUCH DAMAGE.
35 */
36
37#ifndef lint
38static char copyright[] =
39"@(#) Copyright (c) 1989, 1993\n\
40	The Regents of the University of California.  All rights reserved.\n";
41#endif /* not lint */
42
43#ifndef lint
44static char sccsid[] = "@(#)cut.c	8.3 (Berkeley) 5/4/95";
45#endif /* not lint */
46
47#include <ctype.h>
48#include <errno.h>
49#include <limits.h>
50#include <stdio.h>
51#include <stdlib.h>
52#include <string.h>
53#include <unistd.h>
54
55int	cflag;
56char	dchar;
57int	dflag;
58int	fflag;
59int	sflag;
60
61void	c_cut __P((FILE *, char *));
62void	err __P((const char *, ...));
63void	f_cut __P((FILE *, char *));
64void	get_list __P((char *));
65void	usage __P((void));
66
67int
68main(argc, argv)
69	int argc;
70	char *argv[];
71{
72	FILE *fp;
73	void (*fcn) __P((FILE *, char *));
74	int ch;
75
76	dchar = '\t';			/* default delimiter is \t */
77
78	while ((ch = getopt(argc, argv, "c:d:f:s")) != -1)
79		switch(ch) {
80		case 'c':
81			fcn = c_cut;
82			get_list(optarg);
83			cflag = 1;
84			break;
85		case 'd':
86			dchar = *optarg;
87			dflag = 1;
88			break;
89		case 'f':
90			get_list(optarg);
91			fcn = f_cut;
92			fflag = 1;
93			break;
94		case 's':
95			sflag = 1;
96			break;
97		case '?':
98		default:
99			usage();
100		}
101	argc -= optind;
102	argv += optind;
103
104	if (fflag) {
105		if (cflag)
106			usage();
107	} else if (!cflag || dflag || sflag)
108		usage();
109
110	if (*argv)
111		for (; *argv; ++argv) {
112			if (!(fp = fopen(*argv, "r")))
113				err("%s: %s\n", *argv, strerror(errno));
114			fcn(fp, *argv);
115			(void)fclose(fp);
116		}
117	else
118		fcn(stdin, "stdin");
119	exit(0);
120}
121
122int autostart, autostop, maxval;
123
124char positions[_POSIX2_LINE_MAX + 1];
125
126void
127get_list(list)
128	char *list;
129{
130	register int setautostart, start, stop;
131	register char *pos;
132	char *p;
133
134	/*
135	 * set a byte in the positions array to indicate if a field or
136	 * column is to be selected; use +1, it's 1-based, not 0-based.
137	 * This parser is less restrictive than the Draft 9 POSIX spec.
138	 * POSIX doesn't allow lists that aren't in increasing order or
139	 * overlapping lists.  We also handle "-3-5" although there's no
140	 * real reason too.
141	 */
142	for (; p = strtok(list, ", \t"); list = NULL) {
143		setautostart = start = stop = 0;
144		if (*p == '-') {
145			++p;
146			setautostart = 1;
147		}
148		if (isdigit(*p)) {
149			start = stop = strtol(p, &p, 10);
150			if (setautostart && start > autostart)
151				autostart = start;
152		}
153		if (*p == '-') {
154			if (isdigit(p[1]))
155				stop = strtol(p + 1, &p, 10);
156			if (*p == '-') {
157				++p;
158				if (!autostop || autostop > stop)
159					autostop = stop;
160			}
161		}
162		if (*p)
163			err("[-cf] list: illegal list value\n");
164		if (!stop || !start)
165			err("[-cf] list: values may not include zero\n");
166		if (stop > _POSIX2_LINE_MAX)
167			err("[-cf] list: %d too large (max %d)\n",
168			    stop, _POSIX2_LINE_MAX);
169		if (maxval < stop)
170			maxval = stop;
171		for (pos = positions + start; start++ <= stop; *pos++ = 1);
172	}
173
174	/* overlapping ranges */
175	if (autostop && maxval > autostop)
176		maxval = autostop;
177
178	/* set autostart */
179	if (autostart)
180		memset(positions + 1, '1', autostart);
181}
182
183/* ARGSUSED */
184void
185c_cut(fp, fname)
186	FILE *fp;
187	char *fname;
188{
189	register int ch, col;
190	register char *pos;
191
192	for (;;) {
193		pos = positions + 1;
194		for (col = maxval; col; --col) {
195			if ((ch = getc(fp)) == EOF)
196				return;
197			if (ch == '\n')
198				break;
199			if (*pos++)
200				(void)putchar(ch);
201		}
202		if (ch != '\n')
203			if (autostop)
204				while ((ch = getc(fp)) != EOF && ch != '\n')
205					(void)putchar(ch);
206			else
207				while ((ch = getc(fp)) != EOF && ch != '\n');
208		(void)putchar('\n');
209	}
210}
211
212void
213f_cut(fp, fname)
214	FILE *fp;
215	char *fname;
216{
217	register int ch, field, isdelim;
218	register char *pos, *p, sep;
219	int output;
220	char lbuf[_POSIX2_LINE_MAX + 1];
221
222	for (sep = dchar; fgets(lbuf, sizeof(lbuf), fp);) {
223		output = 0;
224		for (isdelim = 0, p = lbuf;; ++p) {
225			if (!(ch = *p))
226				err("%s: line too long.\n", fname);
227			/* this should work if newline is delimiter */
228			if (ch == sep)
229				isdelim = 1;
230			if (ch == '\n') {
231				if (!isdelim && !sflag)
232					(void)printf("%s", lbuf);
233				break;
234			}
235		}
236		if (!isdelim)
237			continue;
238
239		pos = positions + 1;
240		for (field = maxval, p = lbuf; field; --field, ++pos) {
241			if (*pos) {
242				if (output++)
243					(void)putchar(sep);
244				while ((ch = *p++) != '\n' && ch != sep)
245					(void)putchar(ch);
246			} else
247				while ((ch = *p++) != '\n' && ch != sep);
248			if (ch == '\n')
249				break;
250		}
251		if (ch != '\n')
252			if (autostop) {
253				if (output)
254					(void)putchar(sep);
255				for (; (ch = *p) != '\n'; ++p)
256					(void)putchar(ch);
257			} else
258				for (; (ch = *p) != '\n'; ++p);
259		(void)putchar('\n');
260	}
261}
262
263void
264usage()
265{
266	(void)fprintf(stderr,
267"usage:\tcut -c list [file1 ...]\n\tcut -f list [-s] [-d delim] [file ...]\n");
268	exit(1);
269}
270
271#if __STDC__
272#include <stdarg.h>
273#else
274#include <varargs.h>
275#endif
276
277void
278#if __STDC__
279err(const char *fmt, ...)
280#else
281err(fmt, va_alist)
282	char *fmt;
283        va_dcl
284#endif
285{
286	va_list ap;
287#if __STDC__
288	va_start(ap, fmt);
289#else
290	va_start(ap);
291#endif
292	(void)fprintf(stderr, "cut: ");
293	(void)vfprintf(stderr, fmt, ap);
294	va_end(ap);
295	(void)fprintf(stderr, "\n");
296	exit(1);
297	/* NOTREACHED */
298}
299