1 /*
2 * Copyright (c) 1989 The Regents of the University of California.
3 * 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
38 char copyright[] =
39 "@(#) Copyright (c) 1989 The Regents of the University of California.\n\
40 All rights reserved.\n";
41 #endif /* not lint */
42
43 #ifndef lint
44 static char sccsid[] = "@(#)cut.c 5.4 (Berkeley) 10/30/90";
45 #endif /* not lint */
46
47 #include <limits.h>
48 #include <stdio.h>
49 #include <ctype.h>
50
51 int cflag;
52 char dchar;
53 int dflag;
54 int fflag;
55 int sflag;
56
main(argc,argv)57 main(argc, argv)
58 int argc;
59 char **argv;
60 {
61 extern char *optarg;
62 extern int errno, optind;
63 FILE *fp;
64 int ch, (*fcn)(), c_cut(), f_cut();
65 char *strerror();
66
67 dchar = '\t'; /* default delimiter is \t */
68
69 while ((ch = getopt(argc, argv, "c:d:f:s")) != EOF)
70 switch(ch) {
71 case 'c':
72 fcn = c_cut;
73 get_list(optarg);
74 cflag = 1;
75 break;
76 case 'd':
77 dchar = *optarg;
78 dflag = 1;
79 break;
80 case 'f':
81 get_list(optarg);
82 fcn = f_cut;
83 fflag = 1;
84 break;
85 case 's':
86 sflag = 1;
87 break;
88 case '?':
89 default:
90 usage();
91 }
92 argc -= optind;
93 argv += optind;
94
95 if (fflag) {
96 if (cflag)
97 usage();
98 } else if (!cflag || dflag || sflag)
99 usage();
100
101 if (*argv)
102 for (; *argv; ++argv) {
103 if (!(fp = fopen(*argv, "r"))) {
104 (void)fprintf(stderr,
105 "cut: %s: %s\n", *argv, strerror(errno));
106 exit(1);
107 }
108 fcn(fp, *argv);
109 }
110 else
111 fcn(stdin, "stdin");
112 exit(0);
113 }
114
115 int autostart, autostop, maxval;
116
117 char positions[_POSIX2_LINE_MAX + 1];
118
get_list(list)119 get_list(list)
120 char *list;
121 {
122 register char *pos;
123 register int setautostart, start, stop;
124 char *p, *strtok();
125
126 /*
127 * set a byte in the positions array to indicate if a field or
128 * column is to be selected; use +1, it's 1-based, not 0-based.
129 * This parser is less restrictive than the Draft 9 POSIX spec.
130 * POSIX doesn't allow lists that aren't in increasing order or
131 * overlapping lists. We also handle "-3-5" although there's no
132 * real reason too.
133 */
134 for (; p = strtok(list, ", \t"); list = NULL) {
135 setautostart = start = stop = 0;
136 if (*p == '-') {
137 ++p;
138 setautostart = 1;
139 }
140 if (isdigit(*p)) {
141 start = stop = strtol(p, &p, 10);
142 if (setautostart && start > autostart)
143 autostart = start;
144 }
145 if (*p == '-') {
146 if (isdigit(p[1]))
147 stop = strtol(p + 1, &p, 10);
148 if (*p == '-') {
149 ++p;
150 if (!autostop || autostop > stop)
151 autostop = stop;
152 }
153 }
154 if (*p)
155 badlist("illegal list value");
156 if (!stop || !start)
157 badlist("values may not include zero");
158 if (stop > _POSIX2_LINE_MAX) {
159 /* positions used rather than allocate a new buffer */
160 (void)sprintf(positions, "%d too large (max %d)",
161 stop, _POSIX2_LINE_MAX);
162 badlist(positions);
163 }
164 if (maxval < stop)
165 maxval = stop;
166 for (pos = positions + start; start++ <= stop; *pos++ = 1);
167 }
168
169 /* overlapping ranges */
170 if (autostop && maxval > autostop)
171 maxval = autostop;
172
173 /* set autostart */
174 if (autostart)
175 memset(positions + 1, '1', autostart);
176 }
177
178 /* ARGSUSED */
c_cut(fp,fname)179 c_cut(fp, fname)
180 FILE *fp;
181 char *fname;
182 {
183 register int ch, col;
184 register char *pos;
185
186 for (;;) {
187 pos = positions + 1;
188 for (col = maxval; col; --col) {
189 if ((ch = getc(fp)) == EOF)
190 return;
191 if (ch == '\n')
192 break;
193 if (*pos++)
194 putchar(ch);
195 }
196 if (ch != '\n')
197 if (autostop)
198 while ((ch = getc(fp)) != EOF && ch != '\n')
199 putchar(ch);
200 else
201 while ((ch = getc(fp)) != EOF && ch != '\n');
202 putchar('\n');
203 }
204 }
205
f_cut(fp,fname)206 f_cut(fp, fname)
207 FILE *fp;
208 char *fname;
209 {
210 register int ch, field, isdelim;
211 register char *pos, *p, sep;
212 int output;
213 char lbuf[_POSIX2_LINE_MAX + 1];
214
215 for (sep = dchar, output = 0; fgets(lbuf, sizeof(lbuf), fp);) {
216 for (isdelim = 0, p = lbuf;; ++p) {
217 if (!(ch = *p)) {
218 (void)fprintf(stderr,
219 "cut: %s: line too long.\n", fname);
220 exit(1);
221 }
222 /* this should work if newline is delimiter */
223 if (ch == sep)
224 isdelim = 1;
225 if (ch == '\n') {
226 if (!isdelim && !sflag)
227 (void)printf("%s", lbuf);
228 break;
229 }
230 }
231 if (!isdelim)
232 continue;
233
234 pos = positions + 1;
235 for (field = maxval, p = lbuf; field; --field, ++pos) {
236 if (*pos) {
237 if (output++)
238 putchar(sep);
239 while ((ch = *p++) != '\n' && ch != sep)
240 putchar(ch);
241 } else
242 while ((ch = *p++) != '\n' && ch != sep);
243 if (ch == '\n')
244 break;
245 }
246 if (ch != '\n')
247 if (autostop) {
248 if (output)
249 putchar(sep);
250 for (; (ch = *p) != '\n'; ++p)
251 putchar(ch);
252 } else
253 for (; (ch = *p) != '\n'; ++p);
254 putchar('\n');
255 }
256 }
257
badlist(msg)258 badlist(msg)
259 char *msg;
260 {
261 (void)fprintf(stderr, "cut: [-cf] list: %s.\n", msg);
262 exit(1);
263 }
264
usage()265 usage()
266 {
267 (void)fprintf(stderr,
268 "usage:\tcut -c list [file1 ...]\n\tcut -f list [-s] [-d delim] [file ...]\n");
269 exit(1);
270 }
271