cut.c revision 71726 
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 * $FreeBSD: head/usr.bin/cut/cut.c 71726 2001-01-28 00:35:40Z will $
37 *
38 */
39
40#ifndef lint
41static const char copyright[] =
42"@(#) Copyright (c) 1989, 1993\n\
43	The Regents of the University of California.  All rights reserved.\n";
44static const char sccsid[] = "@(#)cut.c	8.3 (Berkeley) 5/4/95";
45static const char rcsid[] =
46  "$FreeBSD: head/usr.bin/cut/cut.c 71726 2001-01-28 00:35:40Z will $";
47#endif /* not lint */
48
49#include <ctype.h>
50#include <err.h>
51#include <errno.h>
52#include <limits.h>
53#include <locale.h>
54#include <stdio.h>
55#include <stdlib.h>
56#include <string.h>
57#include <unistd.h>
58
59int	cflag;
60char	dchar;
61int	dflag;
62int	fflag;
63int	sflag;
64
65void	c_cut (FILE *, const char *);
66void	f_cut (FILE *, const char *);
67void	get_list (char *);
68int	main (int, char **);
69static 	void usage (void);
70
71int
72main(argc, argv)
73	int argc;
74	char *argv[];
75{
76	FILE *fp;
77	void (*fcn) (FILE *, const char *) = NULL;
78	int ch;
79
80	fcn = NULL;
81	setlocale (LC_ALL, "");
82
83	dchar = '\t';			/* default delimiter is \t */
84
85	/* Since we don't support multi-byte characters, the -c and -b
86	   options are equivalent, and the -n option is meaningless. */
87	while ((ch = getopt(argc, argv, "b:c:d:f:sn")) != -1)
88		switch(ch) {
89		case 'b':
90		case 'c':
91			fcn = c_cut;
92			get_list(optarg);
93			cflag = 1;
94			break;
95		case 'd':
96			dchar = *optarg;
97			dflag = 1;
98			break;
99		case 'f':
100			get_list(optarg);
101			fcn = f_cut;
102			fflag = 1;
103			break;
104		case 's':
105			sflag = 1;
106			break;
107		case 'n':
108			break;
109		case '?':
110		default:
111			usage();
112		}
113	argc -= optind;
114	argv += optind;
115
116	if (fflag) {
117		if (cflag)
118			usage();
119	} else if (!cflag || dflag || sflag)
120		usage();
121
122	if (*argv)
123		for (; *argv; ++argv) {
124			if (!(fp = fopen(*argv, "r")))
125				err(1, "%s", *argv);
126			fcn(fp, *argv);
127			(void)fclose(fp);
128		}
129	else
130		fcn(stdin, "stdin");
131	exit(0);
132}
133
134size_t autostart, autostop, maxval;
135
136char positions[_POSIX2_LINE_MAX + 1];
137
138void
139get_list(list)
140	char *list;
141{
142	size_t setautostart, start, stop;
143	char *pos;
144	char *p;
145
146	/*
147	 * set a byte in the positions array to indicate if a field or
148	 * column is to be selected; use +1, it's 1-based, not 0-based.
149	 * This parser is less restrictive than the Draft 9 POSIX spec.
150	 * POSIX doesn't allow lists that aren't in increasing order or
151	 * overlapping lists.  We also handle "-3-5" although there's no
152	 * real reason too.
153	 */
154	for (; (p = strsep(&list, ", \t")) != NULL;) {
155		setautostart = start = stop = 0;
156		if (*p == '-') {
157			++p;
158			setautostart = 1;
159		}
160		if (isdigit((unsigned char)*p)) {
161			start = stop = strtol(p, &p, 10);
162			if (setautostart && start > autostart)
163				autostart = start;
164		}
165		if (*p == '-') {
166			if (isdigit((unsigned char)p[1]))
167				stop = strtol(p + 1, &p, 10);
168			if (*p == '-') {
169				++p;
170				if (!autostop || autostop > stop)
171					autostop = stop;
172			}
173		}
174		if (*p)
175			errx(1, "[-cf] list: illegal list value");
176		if (!stop || !start)
177			errx(1, "[-cf] list: values may not include zero");
178		if (stop > _POSIX2_LINE_MAX)
179			errx(1, "[-cf] list: %d too large (max %d)",
180			    stop, _POSIX2_LINE_MAX);
181		if (maxval < stop)
182			maxval = stop;
183		for (pos = positions + start; start++ <= stop; *pos++ = 1);
184	}
185
186	/* overlapping ranges */
187	if (autostop && maxval > autostop)
188		maxval = autostop;
189
190	/* set autostart */
191	if (autostart)
192		memset(positions + 1, '1', autostart);
193}
194
195/* ARGSUSED */
196void
197c_cut(fp, fname)
198	FILE *fp;
199	const char *fname;
200{
201	int ch, col;
202	char *pos;
203	fname = NULL;
204
205	ch = 0;
206	for (;;) {
207		pos = positions + 1;
208		for (col = maxval; col; --col) {
209			if ((ch = getc(fp)) == EOF)
210				return;
211			if (ch == '\n')
212				break;
213			if (*pos++)
214				(void)putchar(ch);
215		}
216		if (ch != '\n') {
217			if (autostop)
218				while ((ch = getc(fp)) != EOF && ch != '\n')
219					(void)putchar(ch);
220			else
221				while ((ch = getc(fp)) != EOF && ch != '\n');
222		}
223		(void)putchar('\n');
224	}
225}
226
227void
228f_cut(fp, fname)
229	FILE *fp;
230	const char *fname;
231{
232	int ch, field, isdelim;
233	char *pos, *p, sep;
234	int output;
235	char lbuf[_POSIX2_LINE_MAX + 1];
236
237	for (sep = dchar; fgets(lbuf, sizeof(lbuf), fp);) {
238		output = 0;
239		for (isdelim = 0, p = lbuf;; ++p) {
240			if (!(ch = *p))
241				errx(1, "%s: line too long.", fname);
242			/* this should work if newline is delimiter */
243			if (ch == sep)
244				isdelim = 1;
245			if (ch == '\n') {
246				if (!isdelim && !sflag)
247					(void)printf("%s", lbuf);
248				break;
249			}
250		}
251		if (!isdelim)
252			continue;
253
254		pos = positions + 1;
255		for (field = maxval, p = lbuf; field; --field, ++pos) {
256			if (*pos) {
257				if (output++)
258					(void)putchar(sep);
259				while ((ch = *p++) != '\n' && ch != sep)
260					(void)putchar(ch);
261			} else {
262				while ((ch = *p++) != '\n' && ch != sep)
263					continue;
264			}
265			if (ch == '\n')
266				break;
267		}
268		if (ch != '\n') {
269			if (autostop) {
270				if (output)
271					(void)putchar(sep);
272				for (; (ch = *p) != '\n'; ++p)
273					(void)putchar(ch);
274			} else
275				for (; (ch = *p) != '\n'; ++p);
276		}
277		(void)putchar('\n');
278	}
279}
280
281static void
282usage()
283{
284	(void)fprintf(stderr, "%s\n%s\n%s\n",
285		"usage: cut -b list [-n] [file ...]",
286		"       cut -c list [file ...]",
287		"       cut -f list [-s] [-d delim] [file ...]");
288	exit(1);
289}
290