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/types.h>
33 #include <sys/capsicum.h>
35 #include <capsicum_helpers.h>
52 static STR s1 = { STRING1, NORMAL, 0, OOBCH, 0, { 0, OOBCH }, NULL, NULL };
53 static STR s2 = { STRING2, NORMAL, 0, OOBCH, 0, { 0, OOBCH }, NULL, NULL };
55 static struct cset *setup(char *, STR *, int, int);
56 static void usage(void) __dead2;
59 main(int argc, char **argv)
61 static int carray[NCHARS_SB];
63 struct cset *delete, *squeeze;
65 int Cflag, cflag, dflag, sflag, isstring2;
66 wint_t ch, cnt, lastch;
68 (void)setlocale(LC_ALL, "");
70 if (caph_limit_stdio() == -1)
71 err(1, "unable to limit stdio");
74 err(1, "unable to enter capability mode");
76 Cflag = cflag = dflag = sflag = 0;
77 while ((ch = getopt(argc, argv, "Ccdsu")) != -1)
94 setbuf(stdout, (char *)NULL);
117 * tr -ds [-Cc] string1 string2
118 * Delete all characters (or complemented characters) in string1.
119 * Squeeze all characters in string2.
121 if (dflag && sflag) {
125 delete = setup(argv[0], &s1, cflag, Cflag);
126 squeeze = setup(argv[1], &s2, 0, 0);
128 for (lastch = OOBCH; (ch = getwchar()) != WEOF;)
129 if (!cset_in(delete, ch) &&
130 (lastch != ch || !cset_in(squeeze, ch))) {
140 * tr -d [-Cc] string1
141 * Delete all characters (or complemented characters) in string1.
147 delete = setup(argv[0], &s1, cflag, Cflag);
149 while ((ch = getwchar()) != WEOF)
150 if (!cset_in(delete, ch))
158 * tr -s [-Cc] string1
159 * Squeeze all characters (or complemented characters) in string1.
161 if (sflag && !isstring2) {
162 squeeze = setup(argv[0], &s1, cflag, Cflag);
164 for (lastch = OOBCH; (ch = getwchar()) != WEOF;)
165 if (lastch != ch || !cset_in(squeeze, ch)) {
175 * tr [-Ccs] string1 string2
176 * Replace all characters (or complemented characters) in string1 with
177 * the character in the same position in string2. If the -s option is
178 * specified, squeeze all the characters in string2.
186 squeeze = cset_alloc();
192 if (Cflag || cflag) {
193 cmap_default(map, OOBCH);
194 if ((s2.str = strdup(argv[1])) == NULL)
195 errx(1, "strdup(argv[1])");
200 errx(1, "empty string2");
203 * For -s result will contain only those characters defined
204 * as the second characters in each of the toupper or tolower
208 /* If string2 runs out of characters, use the last one specified. */
211 if (s1.state == CCLASS_LOWER &&
212 s2.state == CCLASS_UPPER &&
213 s1.cnt == 1 && s2.cnt == 1) {
215 ch = towupper(s1.lastch);
216 cmap_add(map, s1.lastch, ch);
217 if (sflag && iswupper(ch))
218 cset_add(squeeze, ch);
221 } while (s1.state == CCLASS_LOWER && s1.cnt > 1);
226 } while (s2.state == CCLASS_UPPER && s2.cnt > 1);
228 } else if (s1.state == CCLASS_UPPER &&
229 s2.state == CCLASS_LOWER &&
230 s1.cnt == 1 && s2.cnt == 1) {
232 ch = towlower(s1.lastch);
233 cmap_add(map, s1.lastch, ch);
234 if (sflag && iswlower(ch))
235 cset_add(squeeze, ch);
238 } while (s1.state == CCLASS_UPPER && s1.cnt > 1);
243 } while (s2.state == CCLASS_LOWER && s2.cnt > 1);
246 cmap_add(map, s1.lastch, s2.lastch);
248 cset_add(squeeze, s2.lastch);
253 if (cflag || (Cflag && MB_CUR_MAX > 1)) {
255 * This is somewhat tricky: since the character set is
256 * potentially huge, we need to avoid allocating a map
257 * entry for every character. Our strategy is to set the
258 * default mapping to the last character of string #2
259 * (= the one that gets automatically repeated), then to
260 * add back identity mappings for characters that should
261 * remain unchanged. We don't waste space on identity mappings
262 * for non-characters with the -C option; those are simulated
267 for (cnt = 0; cnt < WINT_MAX; cnt++) {
268 if (Cflag && !iswrune(cnt))
270 if (cmap_lookup(map, cnt) == OOBCH) {
272 cmap_add(map, cnt, s2.lastch);
274 cset_add(squeeze, s2.lastch);
277 cmap_add(map, cnt, cnt);
278 if ((s2.state == EOS || s2.state == INFINITE) &&
279 cnt >= cmap_max(map))
282 cmap_default(map, s2.lastch);
284 for (p = carray, cnt = 0; cnt < NCHARS_SB; cnt++) {
285 if (cmap_lookup(map, cnt) == OOBCH && iswrune(cnt))
288 cmap_add(map, cnt, cnt);
292 (void)mergesort(carray, n, sizeof(*carray), charcoll);
296 for (cnt = 0; cnt < n; cnt++) {
298 cmap_add(map, carray[cnt], s2.lastch);
300 * Chars taken from s2 can be different this time
301 * due to lack of complex upper/lower processing,
302 * so fill string2 again to not miss some.
305 cset_add(squeeze, s2.lastch);
313 for (lastch = OOBCH; (ch = getwchar()) != WEOF;) {
314 if (!Cflag || iswrune(ch))
315 ch = cmap_lookup(map, ch);
316 if (lastch != ch || !cset_in(squeeze, ch)) {
322 while ((ch = getwchar()) != WEOF) {
323 if (!Cflag || iswrune(ch))
324 ch = cmap_lookup(map, ch);
333 setup(char *arg, STR *str, int cflag, int Cflag)
342 cset_add(cs, str->lastch);
344 cset_addclass(cs, wctype("rune"), true);
352 charcoll(const void *a, const void *b)
354 static char sa[2], sb[2];
356 sa[0] = *(const int *)a;
357 sb[0] = *(const int *)b;
358 return (strcoll(sa, sb));
364 (void)fprintf(stderr, "%s\n%s\n%s\n%s\n",
365 "usage: tr [-Ccsu] string1 string2",
366 " tr [-Ccu] -d string1",
367 " tr [-Ccu] -s string1",
368 " tr [-Ccu] -ds string1 string2");