cut.c revision 43533 
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";
41#endif /* not lint */
42
43#ifndef lint
44static const char sccsid[] = "@(#)cut.c	8.3 (Berkeley) 5/4/95";
45#endif /* not lint */
46
47#include <ctype.h>
48#include <err.h>
49#include <errno.h>
50#include <limits.h>
51#include <locale.h>
52#include <stdio.h>
53#include <stdlib.h>
54#include <string.h>
55#include <unistd.h>
56
57int	cflag;
58char	dchar;
59int	dflag;
60int	fflag;
61int	sflag;
62
63void	c_cut __P((FILE *, char *));
64void	f_cut __P((FILE *, char *));
65void	get_list __P((char *));
66int	main __P((int, char **));
67static 	void usage __P((void));
68
69int
70main(argc, argv)
71	int argc;
72	char *argv[];
73{
74	FILE *fp;
75	void (*fcn) __P((FILE *, char *)) = NULL;
76	int ch;
77
78	fcn = NULL;
79	setlocale (LC_ALL, "");
80
81	dchar = '\t';			/* default delimiter is \t */
82
83	/* Since we don't support multi-byte characters, the -c and -b
84	   options are equivalent, and the -n option is meaningless. */
85	while ((ch = getopt(argc, argv, "b:c:d:f:sn")) != -1)
86		switch(ch) {
87		case 'b':
88		case 'c':
89			fcn = c_cut;
90			get_list(optarg);
91			cflag = 1;
92			break;
93		case 'd':
94			dchar = *optarg;
95			dflag = 1;
96			break;
97		case 'f':
98			get_list(optarg);
99			fcn = f_cut;
100			fflag = 1;
101			break;
102		case 's':
103			sflag = 1;
104			break;
105		case 'n':
106			break;
107		case '?':
108		default:
109			usage();
110		}
111	argc -= optind;
112	argv += optind;
113
114	if (fflag) {
115		if (cflag)
116			usage();
117	} else if (!cflag || dflag || sflag)
118		usage();
119
120	if (*argv)
121		for (; *argv; ++argv) {
122			if (!(fp = fopen(*argv, "r")))
123				err(1, "%s", *argv);
124			fcn(fp, *argv);
125			(void)fclose(fp);
126		}
127	else
128		fcn(stdin, "stdin");
129	exit(0);
130}
131
132int autostart, autostop, maxval;
133
134char positions[_POSIX2_LINE_MAX + 1];
135
136void
137get_list(list)
138	char *list;
139{
140	int setautostart, start, stop;
141	char *pos;
142	char *p;
143
144	/*
145	 * set a byte in the positions array to indicate if a field or
146	 * column is to be selected; use +1, it's 1-based, not 0-based.
147	 * This parser is less restrictive than the Draft 9 POSIX spec.
148	 * POSIX doesn't allow lists that aren't in increasing order or
149	 * overlapping lists.  We also handle "-3-5" although there's no
150	 * real reason too.
151	 */
152	for (; (p = strsep(&list, ", \t")) != NULL;) {
153		setautostart = start = stop = 0;
154		if (*p == '-') {
155			++p;
156			setautostart = 1;
157		}
158		if (isdigit((unsigned char)*p)) {
159			start = stop = strtol(p, &p, 10);
160			if (setautostart && start > autostart)
161				autostart = start;
162		}
163		if (*p == '-') {
164			if (isdigit((unsigned char)p[1]))
165				stop = strtol(p + 1, &p, 10);
166			if (*p == '-') {
167				++p;
168				if (!autostop || autostop > stop)
169					autostop = stop;
170			}
171		}
172		if (*p)
173			errx(1, "[-cf] list: illegal list value");
174		if (!stop || !start)
175			errx(1, "[-cf] list: values may not include zero");
176		if (stop > _POSIX2_LINE_MAX)
177			errx(1, "[-cf] list: %d too large (max %d)",
178			    stop, _POSIX2_LINE_MAX);
179		if (maxval < stop)
180			maxval = stop;
181		for (pos = positions + start; start++ <= stop; *pos++ = 1);
182	}
183
184	/* overlapping ranges */
185	if (autostop && maxval > autostop)
186		maxval = autostop;
187
188	/* set autostart */
189	if (autostart)
190		memset(positions + 1, '1', autostart);
191}
192
193/* ARGSUSED */
194void
195c_cut(fp, fname)
196	FILE *fp;
197	char *fname;
198{
199	int ch, col;
200	char *pos;
201
202	ch = 0;
203	for (;;) {
204		pos = positions + 1;
205		for (col = maxval; col; --col) {
206			if ((ch = getc(fp)) == EOF)
207				return;
208			if (ch == '\n')
209				break;
210			if (*pos++)
211				(void)putchar(ch);
212		}
213		if (ch != '\n') {
214			if (autostop)
215				while ((ch = getc(fp)) != EOF && ch != '\n')
216					(void)putchar(ch);
217			else
218				while ((ch = getc(fp)) != EOF && ch != '\n');
219		}
220		(void)putchar('\n');
221	}
222}
223
224void
225f_cut(fp, fname)
226	FILE *fp;
227	char *fname;
228{
229	int ch, field, isdelim;
230	char *pos, *p, sep;
231	int output;
232	char lbuf[_POSIX2_LINE_MAX + 1];
233
234	for (sep = dchar; fgets(lbuf, sizeof(lbuf), fp);) {
235		output = 0;
236		for (isdelim = 0, p = lbuf;; ++p) {
237			if (!(ch = *p))
238				errx(1, "%s: line too long.", fname);
239			/* this should work if newline is delimiter */
240			if (ch == sep)
241				isdelim = 1;
242			if (ch == '\n') {
243				if (!isdelim && !sflag)
244					(void)printf("%s", lbuf);
245				break;
246			}
247		}
248		if (!isdelim)
249			continue;
250
251		pos = positions + 1;
252		for (field = maxval, p = lbuf; field; --field, ++pos) {
253			if (*pos) {
254				if (output++)
255					(void)putchar(sep);
256				while ((ch = *p++) != '\n' && ch != sep)
257					(void)putchar(ch);
258			} else {
259				while ((ch = *p++) != '\n' && ch != sep)
260					continue;
261			}
262			if (ch == '\n')
263				break;
264		}
265		if (ch != '\n') {
266			if (autostop) {
267				if (output)
268					(void)putchar(sep);
269				for (; (ch = *p) != '\n'; ++p)
270					(void)putchar(ch);
271			} else
272				for (; (ch = *p) != '\n'; ++p);
273		}
274		(void)putchar('\n');
275	}
276}
277
278static void
279usage()
280{
281	(void)fprintf(stderr, "%s\n%s\n%s\n",
282		"usage: cut -b list [-n] [file ...]",
283		"       cut -c list [file ...]",
284		"       cut -f list [-s] [-d delim] [file ...]");
285	exit(1);
286}
287