1/*-
2 * SPDX-License-Identifier: BSD-3-Clause
3 *
4 * Copyright (c) 1989, 1993
5 *	The Regents of the University of California.  All rights reserved.
6 *
7 * This code is derived from software contributed to Berkeley by
8 * Case Larsen.
9 *
10 * Redistribution and use in source and binary forms, with or without
11 * modification, are permitted provided that the following conditions
12 * are met:
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.
21 *
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
32 * SUCH DAMAGE.
33 */
34
35#include <sys/capsicum.h>
36
37#include <capsicum_helpers.h>
38#include <ctype.h>
39#include <err.h>
40#include <errno.h>
41#include <getopt.h>
42#include <limits.h>
43#include <locale.h>
44#include <nl_types.h>
45#include <stdbool.h>
46#include <stdint.h>
47#include <stdio.h>
48#include <stdlib.h>
49#include <string.h>
50#include <termios.h>
51#include <unistd.h>
52#include <wchar.h>
53#include <wctype.h>
54
55static enum { DF_NONE, DF_NOSEP, DF_PRESEP, DF_POSTSEP } Dflag;
56static bool cflag, dflag, uflag, iflag;
57static long long numchars, numfields, repeats;
58
59static const struct option long_opts[] =
60{
61	{"all-repeated",optional_argument,	NULL, 'D'},
62	{"count",	no_argument,		NULL, 'c'},
63	{"repeated",	no_argument,		NULL, 'd'},
64	{"skip-fields",	required_argument,	NULL, 'f'},
65	{"ignore-case",	no_argument,		NULL, 'i'},
66	{"skip-chars",	required_argument,	NULL, 's'},
67	{"unique",	no_argument,		NULL, 'u'},
68	{NULL,		no_argument,		NULL, 0}
69};
70
71static FILE	*file(const char *, const char *);
72static wchar_t	*convert(const char *);
73static int	 inlcmp(const char *, const char *);
74static void	 show(FILE *, const char *);
75static wchar_t	*skip(wchar_t *);
76static void	 obsolete(char *[]);
77static void	 usage(void);
78
79int
80main (int argc, char *argv[])
81{
82	wchar_t *tprev, *tthis;
83	FILE *ifp, *ofp;
84	int ch, comp;
85	size_t prevbuflen, thisbuflen, b1;
86	char *prevline, *thisline, *p;
87	const char *errstr, *ifn, *ofn;
88	cap_rights_t rights;
89
90	(void) setlocale(LC_ALL, "");
91
92	obsolete(argv);
93	while ((ch = getopt_long(argc, argv, "+D::cdif:s:u", long_opts,
94	    NULL)) != -1)
95		switch (ch) {
96		case 'D':
97			if (optarg == NULL || strcasecmp(optarg, "none") == 0)
98				Dflag = DF_NOSEP;
99			else if (strcasecmp(optarg, "prepend") == 0)
100				Dflag = DF_PRESEP;
101			else if (strcasecmp(optarg, "separate") == 0)
102				Dflag = DF_POSTSEP;
103			else
104				usage();
105			break;
106		case 'c':
107			cflag = true;
108			break;
109		case 'd':
110			dflag = true;
111			break;
112		case 'i':
113			iflag = true;
114			break;
115		case 'f':
116			numfields = strtonum(optarg, 0, INT_MAX, &errstr);
117			if (errstr)
118				errx(1, "field skip value is %s: %s", errstr, optarg);
119			break;
120		case 's':
121			numchars = strtonum(optarg, 0, INT_MAX, &errstr);
122			if (errstr != NULL)
123				errx(1, "character skip value is %s: %s", errstr, optarg);
124			break;
125		case 'u':
126			uflag = true;
127			break;
128		case '?':
129		default:
130			usage();
131		}
132
133	argc -= optind;
134	argv += optind;
135
136	if (argc > 2)
137		usage();
138
139	if (Dflag && dflag)
140		dflag = false;
141
142	ifp = stdin;
143	ifn = "stdin";
144	ofp = stdout;
145	ofn = "stdout";
146	if (argc > 0 && strcmp(argv[0], "-") != 0)
147		ifp = file(ifn = argv[0], "r");
148	cap_rights_init(&rights, CAP_FSTAT, CAP_READ);
149	if (caph_rights_limit(fileno(ifp), &rights) < 0)
150		err(1, "unable to limit rights for %s", ifn);
151	cap_rights_init(&rights, CAP_FSTAT, CAP_WRITE);
152	if (argc > 1)
153		ofp = file(ofn = argv[1], "w");
154	else
155		cap_rights_set(&rights, CAP_IOCTL);
156	if (caph_rights_limit(fileno(ofp), &rights) < 0) {
157		err(1, "unable to limit rights for %s",
158		    argc > 1 ? argv[1] : "stdout");
159	}
160	if (cap_rights_is_set(&rights, CAP_IOCTL)) {
161		unsigned long cmd;
162
163		cmd = TIOCGETA; /* required by isatty(3) in printf(3) */
164
165		if (caph_ioctls_limit(fileno(ofp), &cmd, 1) < 0) {
166			err(1, "unable to limit ioctls for %s",
167			    argc > 1 ? argv[1] : "stdout");
168		}
169	}
170
171	caph_cache_catpages();
172	if (caph_enter() < 0)
173		err(1, "unable to enter capability mode");
174
175	prevbuflen = thisbuflen = 0;
176	prevline = thisline = NULL;
177
178	if (getline(&prevline, &prevbuflen, ifp) < 0) {
179		if (ferror(ifp))
180			err(1, "%s", ifn);
181		exit(0);
182	}
183	if (!cflag && !Dflag && !dflag && !uflag)
184		show(ofp, prevline);
185	tprev = convert(prevline);
186
187	tthis = NULL;
188	while (getline(&thisline, &thisbuflen, ifp) >= 0) {
189		if (tthis != NULL)
190			free(tthis);
191		tthis = convert(thisline);
192
193		if (tthis == NULL && tprev == NULL)
194			comp = inlcmp(thisline, prevline);
195		else if (tthis == NULL || tprev == NULL)
196			comp = 1;
197		else
198			comp = wcscoll(tthis, tprev);
199
200		if (comp) {
201			/* If different, print; set previous to new value. */
202			if (Dflag == DF_POSTSEP && repeats > 0)
203				fputc('\n', ofp);
204			if (!cflag && !Dflag && !dflag && !uflag)
205				show(ofp, thisline);
206			else if (!Dflag &&
207			    (!dflag || (cflag && repeats > 0)) &&
208			    (!uflag || repeats == 0))
209				show(ofp, prevline);
210			p = prevline;
211			b1 = prevbuflen;
212			prevline = thisline;
213			prevbuflen = thisbuflen;
214			if (tprev != NULL)
215				free(tprev);
216			tprev = tthis;
217			thisline = p;
218			thisbuflen = b1;
219			tthis = NULL;
220			repeats = 0;
221		} else {
222			if (Dflag) {
223				if (repeats == 0) {
224					if (Dflag == DF_PRESEP)
225						fputc('\n', ofp);
226					show(ofp, prevline);
227				}
228				show(ofp, thisline);
229			} else if (dflag && !cflag) {
230				if (repeats == 0)
231					show(ofp, prevline);
232			}
233			++repeats;
234		}
235	}
236	if (ferror(ifp))
237		err(1, "%s", ifn);
238	if (!cflag && !Dflag && !dflag && !uflag)
239		/* already printed */ ;
240	else if (!Dflag &&
241	    (!dflag || (cflag && repeats > 0)) &&
242	    (!uflag || repeats == 0))
243		show(ofp, prevline);
244	if (fflush(ofp) != 0)
245		err(1, "%s", ofn);
246	exit(0);
247}
248
249static wchar_t *
250convert(const char *str)
251{
252	size_t n;
253	wchar_t *buf, *ret, *p;
254
255	if ((n = mbstowcs(NULL, str, 0)) == (size_t)-1)
256		return (NULL);
257	if (SIZE_MAX / sizeof(*buf) < n + 1)
258		errx(1, "conversion buffer length overflow");
259	if ((buf = malloc((n + 1) * sizeof(*buf))) == NULL)
260		err(1, "malloc");
261	if (mbstowcs(buf, str, n + 1) != n)
262		errx(1, "internal mbstowcs() error");
263	/* The last line may not end with \n. */
264	if (n > 0 && buf[n - 1] == L'\n')
265		buf[n - 1] = L'\0';
266
267	/* If requested get the chosen fields + character offsets. */
268	if (numfields || numchars) {
269		if ((ret = wcsdup(skip(buf))) == NULL)
270			err(1, "wcsdup");
271		free(buf);
272	} else
273		ret = buf;
274
275	if (iflag) {
276		for (p = ret; *p != L'\0'; p++)
277			*p = towlower(*p);
278	}
279
280	return (ret);
281}
282
283static int
284inlcmp(const char *s1, const char *s2)
285{
286	int c1, c2;
287
288	while (*s1 == *s2++)
289		if (*s1++ == '\0')
290			return (0);
291	c1 = (unsigned char)*s1;
292	c2 = (unsigned char)*(s2 - 1);
293	/* The last line may not end with \n. */
294	if (c1 == '\n')
295		c1 = '\0';
296	if (c2 == '\n')
297		c2 = '\0';
298	return (c1 - c2);
299}
300
301/*
302 * show --
303 *	Output a line depending on the flags and number of repetitions
304 *	of the line.
305 */
306static void
307show(FILE *ofp, const char *str)
308{
309	if (cflag)
310		(void)fprintf(ofp, "%4lld %s", repeats + 1, str);
311	else
312		(void)fprintf(ofp, "%s", str);
313}
314
315static wchar_t *
316skip(wchar_t *str)
317{
318	long long nchars, nfields;
319
320	for (nfields = 0; *str != L'\0' && nfields++ != numfields; ) {
321		while (iswblank(*str))
322			str++;
323		while (*str != L'\0' && !iswblank(*str))
324			str++;
325	}
326	for (nchars = numchars; nchars-- && *str != L'\0'; ++str)
327		;
328	return(str);
329}
330
331static FILE *
332file(const char *name, const char *mode)
333{
334	FILE *fp;
335
336	if ((fp = fopen(name, mode)) == NULL)
337		err(1, "%s", name);
338	return(fp);
339}
340
341static void
342obsolete(char *argv[])
343{
344	char *ap, *p;
345
346	while ((ap = *++argv)) {
347		/* Return if "--" or not an option of any form. */
348		if (ap[0] != '-') {
349			if (ap[0] != '+')
350				return;
351		} else if (ap[1] == '-') {
352			return;
353		}
354		if (!isdigit((unsigned char)ap[1]))
355			continue;
356		/*
357		 * Digit signifies an old-style option.  Malloc space for dash,
358		 * new option and argument.
359		 */
360		if (asprintf(&p, "-%c%s", ap[0] == '+' ? 's' : 'f', ap + 1) < 0)
361			err(1, "malloc");
362		*argv = p;
363	}
364}
365
366static void
367usage(void)
368{
369	(void)fprintf(stderr,
370"usage: uniq [-c | -d | -D | -u] [-i] [-f fields] [-s chars] [input [output]]\n");
371	exit(1);
372}
373