2 * SPDX-License-Identifier: BSD-3-Clause
4 * Copyright (c) 1989, 1993
5 * The Regents of the University of California. All rights reserved.
7 * This code is derived from software contributed to Berkeley by
10 * Redistribution and use in source and binary forms, with or without
11 * modification, are permitted provided that the following conditions
13 * 1. Redistributions of source code must retain the above copyright
14 * notice, this list of conditions and the following disclaimer.
15 * 2. Redistributions in binary form must reproduce the above copyright
16 * notice, this list of conditions and the following disclaimer in the
17 * documentation and/or other materials provided with the distribution.
18 * 3. Neither the name of the University nor the names of its contributors
19 * may be used to endorse or promote products derived from this software
20 * without specific prior written permission.
22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
25 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
36 static const char copyright[] =
37 "@(#) Copyright (c) 1989, 1993\n\
38 The Regents of the University of California. All rights reserved.\n";
43 static char sccsid[] = "@(#)uniq.c 8.3 (Berkeley) 5/4/95";
45 static const char rcsid[] =
49 #include <sys/capsicum.h>
51 #include <capsicum_helpers.h>
68 static int Dflag, cflag, dflag, uflag, iflag;
69 static int numchars, numfields, repeats;
77 static const struct option long_opts[] =
79 {"all-repeated",optional_argument, NULL, 'D'},
80 {"count", no_argument, NULL, 'c'},
81 {"repeated", no_argument, NULL, 'd'},
82 {"skip-fields", required_argument, NULL, 'f'},
83 {"ignore-case", no_argument, NULL, 'i'},
84 {"skip-chars", required_argument, NULL, 's'},
85 {"unique", no_argument, NULL, 'u'},
86 {NULL, no_argument, NULL, 0}
89 static FILE *file(const char *, const char *);
90 static wchar_t *convert(const char *);
91 static int inlcmp(const char *, const char *);
92 static void show(FILE *, const char *);
93 static wchar_t *skip(wchar_t *);
94 static void obsolete(char *[]);
95 static void usage(void);
98 main (int argc, char *argv[])
100 wchar_t *tprev, *tthis;
103 size_t prevbuflen, thisbuflen, b1;
104 char *prevline, *thisline, *p;
108 (void) setlocale(LC_ALL, "");
111 while ((ch = getopt_long(argc, argv, "+D::cdif:s:u", long_opts,
115 if (optarg == NULL || strcasecmp(optarg, "none") == 0)
117 else if (strcasecmp(optarg, "prepend") == 0)
119 else if (strcasecmp(optarg, "separate") == 0)
134 numfields = strtol(optarg, &p, 10);
135 if (numfields < 0 || *p)
136 errx(1, "illegal field skip value: %s", optarg);
139 numchars = strtol(optarg, &p, 10);
140 if (numchars < 0 || *p)
141 errx(1, "illegal character skip value: %s", optarg);
160 if (argc > 0 && strcmp(argv[0], "-") != 0)
161 ifp = file(ifn = argv[0], "r");
162 cap_rights_init(&rights, CAP_FSTAT, CAP_READ);
163 if (caph_rights_limit(fileno(ifp), &rights) < 0)
164 err(1, "unable to limit rights for %s", ifn);
165 cap_rights_init(&rights, CAP_FSTAT, CAP_WRITE);
167 ofp = file(argv[1], "w");
169 cap_rights_set(&rights, CAP_IOCTL);
170 if (caph_rights_limit(fileno(ofp), &rights) < 0) {
171 err(1, "unable to limit rights for %s",
172 argc > 1 ? argv[1] : "stdout");
174 if (cap_rights_is_set(&rights, CAP_IOCTL)) {
177 cmd = TIOCGETA; /* required by isatty(3) in printf(3) */
179 if (caph_ioctls_limit(fileno(ofp), &cmd, 1) < 0) {
180 err(1, "unable to limit ioctls for %s",
181 argc > 1 ? argv[1] : "stdout");
185 caph_cache_catpages();
186 if (caph_enter() < 0)
187 err(1, "unable to enter capability mode");
189 prevbuflen = thisbuflen = 0;
190 prevline = thisline = NULL;
192 if (getline(&prevline, &prevbuflen, ifp) < 0) {
197 tprev = convert(prevline);
200 while (getline(&thisline, &thisbuflen, ifp) >= 0) {
203 tthis = convert(thisline);
205 if (tthis == NULL && tprev == NULL)
206 comp = inlcmp(thisline, prevline);
207 else if (tthis == NULL || tprev == NULL)
210 comp = wcscoll(tthis, tprev);
213 /* If different, print; set previous to new value. */
214 if (Dflag == DF_POSTSEP && repeats > 0)
221 prevbuflen = thisbuflen;
232 if (Dflag == DF_PRESEP)
249 convert(const char *str)
252 wchar_t *buf, *ret, *p;
254 if ((n = mbstowcs(NULL, str, 0)) == (size_t)-1)
256 if (SIZE_MAX / sizeof(*buf) < n + 1)
257 errx(1, "conversion buffer length overflow");
258 if ((buf = malloc((n + 1) * sizeof(*buf))) == NULL)
260 if (mbstowcs(buf, str, n + 1) != n)
261 errx(1, "internal mbstowcs() error");
262 /* The last line may not end with \n. */
263 if (n > 0 && buf[n - 1] == L'\n')
266 /* If requested get the chosen fields + character offsets. */
267 if (numfields || numchars) {
268 if ((ret = wcsdup(skip(buf))) == NULL)
275 for (p = ret; *p != L'\0'; p++)
283 inlcmp(const char *s1, const char *s2)
290 c1 = (unsigned char)*s1;
291 c2 = (unsigned char)*(s2 - 1);
292 /* The last line may not end with \n. */
302 * Output a line depending on the flags and number of repetitions
306 show(FILE *ofp, const char *str)
309 if ((!Dflag && dflag && repeats == 0) || (uflag && repeats > 0))
312 (void)fprintf(ofp, "%4d %s", repeats + 1, str);
314 (void)fprintf(ofp, "%s", str);
322 for (nfields = 0; *str != L'\0' && nfields++ != numfields; ) {
323 while (iswblank(*str))
325 while (*str != L'\0' && !iswblank(*str))
328 for (nchars = numchars; nchars-- && *str != L'\0'; ++str)
334 file(const char *name, const char *mode)
338 if ((fp = fopen(name, mode)) == NULL)
344 obsolete(char *argv[])
347 char *ap, *p, *start;
349 while ((ap = *++argv)) {
350 /* Return if "--" or not an option of any form. */
354 } else if (ap[1] == '-')
356 if (!isdigit((unsigned char)ap[1]))
359 * Digit signifies an old-style option. Malloc space for dash,
360 * new option and argument.
363 if ((start = p = malloc(len + 3)) == NULL)
366 *p++ = ap[0] == '+' ? 's' : 'f';
367 (void)strcpy(p, ap + 1);
375 (void)fprintf(stderr,
376 "usage: uniq [-c | -d | -D | -u] [-i] [-f fields] [-s chars] [input [output]]\n");