cut.c revision 97218 
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 const char copyright[] =
39"@(#) Copyright (c) 1989, 1993\n\
40	The Regents of the University of California.  All rights reserved.\n";
41static const char sccsid[] = "@(#)cut.c	8.3 (Berkeley) 5/4/95";
42static const char rcsid[] =
43  "$FreeBSD: head/usr.bin/cut/cut.c 97218 2002-05-24 06:03:12Z tjr $";
44#endif /* not lint */
45
46#include <ctype.h>
47#include <err.h>
48#include <limits.h>
49#include <locale.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 (FILE *, const char *);
62void	f_cut (FILE *, const char *);
63void	get_list (char *);
64int	main (int, char **);
65static 	void usage (void);
66
67int
68main(argc, argv)
69	int argc;
70	char *argv[];
71{
72	FILE *fp;
73	void (*fcn) (FILE *, const char *) = NULL;
74	int ch, rval;
75
76	fcn = NULL;
77	setlocale (LC_ALL, "");
78
79	dchar = '\t';			/* default delimiter is \t */
80
81	/* Since we don't support multi-byte characters, the -c and -b
82	   options are equivalent, and the -n option is meaningless. */
83	while ((ch = getopt(argc, argv, "b:c:d:f:sn")) != -1)
84		switch(ch) {
85		case 'b':
86		case 'c':
87			fcn = c_cut;
88			get_list(optarg);
89			cflag = 1;
90			break;
91		case 'd':
92			dchar = *optarg;
93			dflag = 1;
94			break;
95		case 'f':
96			get_list(optarg);
97			fcn = f_cut;
98			fflag = 1;
99			break;
100		case 's':
101			sflag = 1;
102			break;
103		case 'n':
104			break;
105		case '?':
106		default:
107			usage();
108		}
109	argc -= optind;
110	argv += optind;
111
112	if (fflag) {
113		if (cflag)
114			usage();
115	} else if (!cflag || dflag || sflag)
116		usage();
117
118	rval = 0;
119	if (*argv)
120		for (; *argv; ++argv) {
121			if (!(fp = fopen(*argv, "r"))) {
122				warn("%s", *argv);
123				rval = 1;
124				continue;
125			}
126			fcn(fp, *argv);
127			(void)fclose(fp);
128		}
129	else
130		fcn(stdin, "stdin");
131	exit(rval);
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: %ld too large (max %d)",
180			    (long)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 __unused;
231{
232	int ch, field, isdelim;
233	char *pos, *p, sep;
234	int output;
235	char *lbuf, *mlbuf = NULL;
236	size_t lbuflen;
237
238	for (sep = dchar; (lbuf = fgetln(fp, &lbuflen)) != NULL;) {
239		/* Assert EOL has a newline. */
240		if (*(lbuf + lbuflen - 1) != '\n') {
241			/* Can't have > 1 line with no trailing newline. */
242			mlbuf = malloc(lbuflen + 1);
243			if (mlbuf == NULL)
244				err(1, "malloc");
245			memcpy(mlbuf, lbuf, lbuflen);
246			*(mlbuf + lbuflen) = '\n';
247			lbuf = mlbuf;
248		}
249		output = 0;
250		for (isdelim = 0, p = lbuf;; ++p) {
251			ch = *p;
252			/* this should work if newline is delimiter */
253			if (ch == sep)
254				isdelim = 1;
255			if (ch == '\n') {
256				if (!isdelim && !sflag)
257					(void)fwrite(lbuf, lbuflen, 1, stdout);
258				break;
259			}
260		}
261		if (!isdelim)
262			continue;
263
264		pos = positions + 1;
265		for (field = maxval, p = lbuf; field; --field, ++pos) {
266			if (*pos) {
267				if (output++)
268					(void)putchar(sep);
269				while ((ch = *p++) != '\n' && ch != sep)
270					(void)putchar(ch);
271			} else {
272				while ((ch = *p++) != '\n' && ch != sep)
273					continue;
274			}
275			if (ch == '\n')
276				break;
277		}
278		if (ch != '\n') {
279			if (autostop) {
280				if (output)
281					(void)putchar(sep);
282				for (; (ch = *p) != '\n'; ++p)
283					(void)putchar(ch);
284			} else
285				for (; (ch = *p) != '\n'; ++p);
286		}
287		(void)putchar('\n');
288	}
289	if (mlbuf != NULL)
290		free(mlbuf);
291}
292
293static void
294usage()
295{
296	(void)fprintf(stderr, "%s\n%s\n%s\n",
297		"usage: cut -b list [-n] [file ...]",
298		"       cut -c list [file ...]",
299		"       cut -f list [-s] [-d delim] [file ...]");
300	exit(1);
301}
302