2 * Copyright (c) 1988, 1993
3 * The Regents of the University of California. All rights reserved.
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
8 * 1. Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 * notice, this list of conditions and the following disclaimer in the
12 * documentation and/or other materials provided with the distribution.
13 * 4. Neither the name of the University nor the names of its contributors
14 * may be used to endorse or promote products derived from this software
15 * without specific prior written permission.
17 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
18 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
19 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
20 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
21 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
22 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
23 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
24 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
25 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
26 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
30 #include <sys/cdefs.h>
32 __FBSDID("$FreeBSD$");
35 static const char copyright[] =
36 "@(#) Copyright (c) 1988, 1993\n\
37 The Regents of the University of California. All rights reserved.\n";
41 static const char sccsid[] = "@(#)tr.c 8.2 (Berkeley) 5/4/95";
44 #include <sys/types.h>
62 static STR s1 = { STRING1, NORMAL, 0, OOBCH, 0, { 0, OOBCH }, NULL, NULL };
63 static STR s2 = { STRING2, NORMAL, 0, OOBCH, 0, { 0, OOBCH }, NULL, NULL };
65 static struct cset *setup(char *, STR *, int, int);
66 static void usage(void);
69 main(int argc, char **argv)
71 static int carray[NCHARS_SB];
73 struct cset *delete, *squeeze;
75 int Cflag, cflag, dflag, sflag, isstring2;
76 wint_t ch, cnt, lastch;
78 (void)setlocale(LC_ALL, "");
80 Cflag = cflag = dflag = sflag = 0;
81 while ((ch = getopt(argc, argv, "Ccdsu")) != -1)
98 setbuf(stdout, (char *)NULL);
121 * tr -ds [-Cc] string1 string2
122 * Delete all characters (or complemented characters) in string1.
123 * Squeeze all characters in string2.
125 if (dflag && sflag) {
129 delete = setup(argv[0], &s1, cflag, Cflag);
130 squeeze = setup(argv[1], &s2, 0, 0);
132 for (lastch = OOBCH; (ch = getwchar()) != WEOF;)
133 if (!cset_in(delete, ch) &&
134 (lastch != ch || !cset_in(squeeze, ch))) {
144 * tr -d [-Cc] string1
145 * Delete all characters (or complemented characters) in string1.
151 delete = setup(argv[0], &s1, cflag, Cflag);
153 while ((ch = getwchar()) != WEOF)
154 if (!cset_in(delete, ch))
162 * tr -s [-Cc] string1
163 * Squeeze all characters (or complemented characters) in string1.
165 if (sflag && !isstring2) {
166 squeeze = setup(argv[0], &s1, cflag, Cflag);
168 for (lastch = OOBCH; (ch = getwchar()) != WEOF;)
169 if (lastch != ch || !cset_in(squeeze, ch)) {
179 * tr [-Ccs] string1 string2
180 * Replace all characters (or complemented characters) in string1 with
181 * the character in the same position in string2. If the -s option is
182 * specified, squeeze all the characters in string2.
190 squeeze = cset_alloc();
196 if (Cflag || cflag) {
197 cmap_default(map, OOBCH);
198 if ((s2.str = strdup(argv[1])) == NULL)
199 errx(1, "strdup(argv[1])");
204 errx(1, "empty string2");
207 * For -s result will contain only those characters defined
208 * as the second characters in each of the toupper or tolower
212 /* If string2 runs out of characters, use the last one specified. */
215 if (s1.state == CCLASS_LOWER &&
216 s2.state == CCLASS_UPPER &&
217 s1.cnt == 1 && s2.cnt == 1) {
219 ch = towupper(s1.lastch);
220 cmap_add(map, s1.lastch, ch);
221 if (sflag && iswupper(ch))
222 cset_add(squeeze, ch);
225 } while (s1.state == CCLASS_LOWER && s1.cnt > 1);
230 } while (s2.state == CCLASS_UPPER && s2.cnt > 1);
232 } else if (s1.state == CCLASS_UPPER &&
233 s2.state == CCLASS_LOWER &&
234 s1.cnt == 1 && s2.cnt == 1) {
236 ch = towlower(s1.lastch);
237 cmap_add(map, s1.lastch, ch);
238 if (sflag && iswlower(ch))
239 cset_add(squeeze, ch);
242 } while (s1.state == CCLASS_UPPER && s1.cnt > 1);
247 } while (s2.state == CCLASS_LOWER && s2.cnt > 1);
250 cmap_add(map, s1.lastch, s2.lastch);
252 cset_add(squeeze, s2.lastch);
257 if (cflag || (Cflag && MB_CUR_MAX > 1)) {
259 * This is somewhat tricky: since the character set is
260 * potentially huge, we need to avoid allocating a map
261 * entry for every character. Our strategy is to set the
262 * default mapping to the last character of string #2
263 * (= the one that gets automatically repeated), then to
264 * add back identity mappings for characters that should
265 * remain unchanged. We don't waste space on identity mappings
266 * for non-characters with the -C option; those are simulated
271 for (cnt = 0; cnt < WINT_MAX; cnt++) {
272 if (Cflag && !iswrune(cnt))
274 if (cmap_lookup(map, cnt) == OOBCH) {
276 cmap_add(map, cnt, s2.lastch);
278 cset_add(squeeze, s2.lastch);
281 cmap_add(map, cnt, cnt);
282 if ((s2.state == EOS || s2.state == INFINITE) &&
283 cnt >= cmap_max(map))
286 cmap_default(map, s2.lastch);
288 for (p = carray, cnt = 0; cnt < NCHARS_SB; cnt++) {
289 if (cmap_lookup(map, cnt) == OOBCH && iswrune(cnt))
292 cmap_add(map, cnt, cnt);
296 (void)mergesort(carray, n, sizeof(*carray), charcoll);
300 for (cnt = 0; cnt < n; cnt++) {
302 cmap_add(map, carray[cnt], s2.lastch);
304 * Chars taken from s2 can be different this time
305 * due to lack of complex upper/lower processing,
306 * so fill string2 again to not miss some.
309 cset_add(squeeze, s2.lastch);
317 for (lastch = OOBCH; (ch = getwchar()) != WEOF;) {
318 if (!Cflag || iswrune(ch))
319 ch = cmap_lookup(map, ch);
320 if (lastch != ch || !cset_in(squeeze, ch)) {
326 while ((ch = getwchar()) != WEOF) {
327 if (!Cflag || iswrune(ch))
328 ch = cmap_lookup(map, ch);
337 setup(char *arg, STR *str, int cflag, int Cflag)
346 cset_add(cs, str->lastch);
348 cset_addclass(cs, wctype("rune"), true);
356 charcoll(const void *a, const void *b)
358 static char sa[2], sb[2];
360 sa[0] = *(const int *)a;
361 sb[0] = *(const int *)b;
362 return (strcoll(sa, sb));
368 (void)fprintf(stderr, "%s\n%s\n%s\n%s\n",
369 "usage: tr [-Ccsu] string1 string2",
370 " tr [-Ccu] -d string1",
371 " tr [-Ccu] -s string1",
372 " tr [-Ccu] -ds string1 string2");