2 * SPDX-License-Identifier: BSD-3-Clause
4 * Copyright (c) 1988, 1993
5 * The Regents of the University of California. All rights reserved.
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
15 * 3. Neither the name of the University nor the names of its contributors
16 * may be used to endorse or promote products derived from this software
17 * without specific prior written permission.
19 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
20 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
21 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
22 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
23 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
24 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
25 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
26 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
27 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
28 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
32 #include <sys/cdefs.h>
34 __FBSDID("$FreeBSD$");
37 static const char copyright[] =
38 "@(#) Copyright (c) 1988, 1993\n\
39 The Regents of the University of California. All rights reserved.\n";
43 static const char sccsid[] = "@(#)tr.c 8.2 (Berkeley) 5/4/95";
46 #include <sys/types.h>
47 #include <sys/capsicum.h>
49 #include <capsicum_helpers.h>
66 static STR s1 = { STRING1, NORMAL, 0, OOBCH, 0, { 0, OOBCH }, NULL, NULL };
67 static STR s2 = { STRING2, NORMAL, 0, OOBCH, 0, { 0, OOBCH }, NULL, NULL };
69 static struct cset *setup(char *, STR *, int, int);
70 static void usage(void);
73 main(int argc, char **argv)
75 static int carray[NCHARS_SB];
77 struct cset *delete, *squeeze;
79 int Cflag, cflag, dflag, sflag, isstring2;
80 wint_t ch, cnt, lastch;
82 (void)setlocale(LC_ALL, "");
84 if (caph_limit_stdio() == -1)
85 err(1, "unable to limit stdio");
88 err(1, "unable to enter capability mode");
90 Cflag = cflag = dflag = sflag = 0;
91 while ((ch = getopt(argc, argv, "Ccdsu")) != -1)
108 setbuf(stdout, (char *)NULL);
131 * tr -ds [-Cc] string1 string2
132 * Delete all characters (or complemented characters) in string1.
133 * Squeeze all characters in string2.
135 if (dflag && sflag) {
139 delete = setup(argv[0], &s1, cflag, Cflag);
140 squeeze = setup(argv[1], &s2, 0, 0);
142 for (lastch = OOBCH; (ch = getwchar()) != WEOF;)
143 if (!cset_in(delete, ch) &&
144 (lastch != ch || !cset_in(squeeze, ch))) {
154 * tr -d [-Cc] string1
155 * Delete all characters (or complemented characters) in string1.
161 delete = setup(argv[0], &s1, cflag, Cflag);
163 while ((ch = getwchar()) != WEOF)
164 if (!cset_in(delete, ch))
172 * tr -s [-Cc] string1
173 * Squeeze all characters (or complemented characters) in string1.
175 if (sflag && !isstring2) {
176 squeeze = setup(argv[0], &s1, cflag, Cflag);
178 for (lastch = OOBCH; (ch = getwchar()) != WEOF;)
179 if (lastch != ch || !cset_in(squeeze, ch)) {
189 * tr [-Ccs] string1 string2
190 * Replace all characters (or complemented characters) in string1 with
191 * the character in the same position in string2. If the -s option is
192 * specified, squeeze all the characters in string2.
200 squeeze = cset_alloc();
206 if (Cflag || cflag) {
207 cmap_default(map, OOBCH);
208 if ((s2.str = strdup(argv[1])) == NULL)
209 errx(1, "strdup(argv[1])");
214 errx(1, "empty string2");
217 * For -s result will contain only those characters defined
218 * as the second characters in each of the toupper or tolower
222 /* If string2 runs out of characters, use the last one specified. */
225 if (s1.state == CCLASS_LOWER &&
226 s2.state == CCLASS_UPPER &&
227 s1.cnt == 1 && s2.cnt == 1) {
229 ch = towupper(s1.lastch);
230 cmap_add(map, s1.lastch, ch);
231 if (sflag && iswupper(ch))
232 cset_add(squeeze, ch);
235 } while (s1.state == CCLASS_LOWER && s1.cnt > 1);
240 } while (s2.state == CCLASS_UPPER && s2.cnt > 1);
242 } else if (s1.state == CCLASS_UPPER &&
243 s2.state == CCLASS_LOWER &&
244 s1.cnt == 1 && s2.cnt == 1) {
246 ch = towlower(s1.lastch);
247 cmap_add(map, s1.lastch, ch);
248 if (sflag && iswlower(ch))
249 cset_add(squeeze, ch);
252 } while (s1.state == CCLASS_UPPER && s1.cnt > 1);
257 } while (s2.state == CCLASS_LOWER && s2.cnt > 1);
260 cmap_add(map, s1.lastch, s2.lastch);
262 cset_add(squeeze, s2.lastch);
267 if (cflag || (Cflag && MB_CUR_MAX > 1)) {
269 * This is somewhat tricky: since the character set is
270 * potentially huge, we need to avoid allocating a map
271 * entry for every character. Our strategy is to set the
272 * default mapping to the last character of string #2
273 * (= the one that gets automatically repeated), then to
274 * add back identity mappings for characters that should
275 * remain unchanged. We don't waste space on identity mappings
276 * for non-characters with the -C option; those are simulated
281 for (cnt = 0; cnt < WINT_MAX; cnt++) {
282 if (Cflag && !iswrune(cnt))
284 if (cmap_lookup(map, cnt) == OOBCH) {
286 cmap_add(map, cnt, s2.lastch);
288 cset_add(squeeze, s2.lastch);
291 cmap_add(map, cnt, cnt);
292 if ((s2.state == EOS || s2.state == INFINITE) &&
293 cnt >= cmap_max(map))
296 cmap_default(map, s2.lastch);
298 for (p = carray, cnt = 0; cnt < NCHARS_SB; cnt++) {
299 if (cmap_lookup(map, cnt) == OOBCH && iswrune(cnt))
302 cmap_add(map, cnt, cnt);
306 (void)mergesort(carray, n, sizeof(*carray), charcoll);
310 for (cnt = 0; cnt < n; cnt++) {
312 cmap_add(map, carray[cnt], s2.lastch);
314 * Chars taken from s2 can be different this time
315 * due to lack of complex upper/lower processing,
316 * so fill string2 again to not miss some.
319 cset_add(squeeze, s2.lastch);
327 for (lastch = OOBCH; (ch = getwchar()) != WEOF;) {
328 if (!Cflag || iswrune(ch))
329 ch = cmap_lookup(map, ch);
330 if (lastch != ch || !cset_in(squeeze, ch)) {
336 while ((ch = getwchar()) != WEOF) {
337 if (!Cflag || iswrune(ch))
338 ch = cmap_lookup(map, ch);
347 setup(char *arg, STR *str, int cflag, int Cflag)
356 cset_add(cs, str->lastch);
358 cset_addclass(cs, wctype("rune"), true);
366 charcoll(const void *a, const void *b)
368 static char sa[2], sb[2];
370 sa[0] = *(const int *)a;
371 sb[0] = *(const int *)b;
372 return (strcoll(sa, sb));
378 (void)fprintf(stderr, "%s\n%s\n%s\n%s\n",
379 "usage: tr [-Ccsu] string1 string2",
380 " tr [-Ccu] -d string1",
381 " tr [-Ccu] -s string1",
382 " tr [-Ccu] -ds string1 string2");