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>
61 STR s1 = { STRING1, NORMAL, 0, OOBCH, 0, { 0, OOBCH }, NULL, NULL };
62 STR s2 = { STRING2, NORMAL, 0, OOBCH, 0, { 0, OOBCH }, NULL, NULL };
64 static struct cset *setup(char *, STR *, int, int);
65 static void usage(void);
68 main(int argc, char **argv)
70 static int carray[NCHARS_SB];
72 struct cset *delete, *squeeze;
74 int Cflag, cflag, dflag, sflag, isstring2;
75 wint_t ch, cnt, lastch;
77 (void)setlocale(LC_ALL, "");
79 Cflag = cflag = dflag = sflag = 0;
80 while ((ch = getopt(argc, argv, "Ccdsu")) != -1)
97 setbuf(stdout, (char *)NULL);
120 * tr -ds [-Cc] string1 string2
121 * Delete all characters (or complemented characters) in string1.
122 * Squeeze all characters in string2.
124 if (dflag && sflag) {
128 delete = setup(argv[0], &s1, cflag, Cflag);
129 squeeze = setup(argv[1], &s2, 0, 0);
131 for (lastch = OOBCH; (ch = getwchar()) != WEOF;)
132 if (!cset_in(delete, ch) &&
133 (lastch != ch || !cset_in(squeeze, ch))) {
143 * tr -d [-Cc] string1
144 * Delete all characters (or complemented characters) in string1.
150 delete = setup(argv[0], &s1, cflag, Cflag);
152 while ((ch = getwchar()) != WEOF)
153 if (!cset_in(delete, ch))
161 * tr -s [-Cc] string1
162 * Squeeze all characters (or complemented characters) in string1.
164 if (sflag && !isstring2) {
165 squeeze = setup(argv[0], &s1, cflag, Cflag);
167 for (lastch = OOBCH; (ch = getwchar()) != WEOF;)
168 if (lastch != ch || !cset_in(squeeze, ch)) {
178 * tr [-Ccs] string1 string2
179 * Replace all characters (or complemented characters) in string1 with
180 * the character in the same position in string2. If the -s option is
181 * specified, squeeze all the characters in string2.
189 squeeze = cset_alloc();
195 if (Cflag || cflag) {
196 cmap_default(map, OOBCH);
197 if ((s2.str = strdup(argv[1])) == NULL)
198 errx(1, "strdup(argv[1])");
203 errx(1, "empty string2");
206 * For -s result will contain only those characters defined
207 * as the second characters in each of the toupper or tolower
211 /* If string2 runs out of characters, use the last one specified. */
214 if (s1.state == CCLASS_LOWER &&
215 s2.state == CCLASS_UPPER &&
216 s1.cnt == 1 && s2.cnt == 1) {
218 ch = towupper(s1.lastch);
219 cmap_add(map, s1.lastch, ch);
220 if (sflag && iswupper(ch))
221 cset_add(squeeze, ch);
224 } while (s1.state == CCLASS_LOWER && s1.cnt > 1);
229 } while (s2.state == CCLASS_UPPER && s2.cnt > 1);
231 } else if (s1.state == CCLASS_UPPER &&
232 s2.state == CCLASS_LOWER &&
233 s1.cnt == 1 && s2.cnt == 1) {
235 ch = towlower(s1.lastch);
236 cmap_add(map, s1.lastch, ch);
237 if (sflag && iswlower(ch))
238 cset_add(squeeze, ch);
241 } while (s1.state == CCLASS_UPPER && s1.cnt > 1);
246 } while (s2.state == CCLASS_LOWER && s2.cnt > 1);
249 cmap_add(map, s1.lastch, s2.lastch);
251 cset_add(squeeze, s2.lastch);
256 if (cflag || (Cflag && MB_CUR_MAX > 1)) {
258 * This is somewhat tricky: since the character set is
259 * potentially huge, we need to avoid allocating a map
260 * entry for every character. Our strategy is to set the
261 * default mapping to the last character of string #2
262 * (= the one that gets automatically repeated), then to
263 * add back identity mappings for characters that should
264 * remain unchanged. We don't waste space on identity mappings
265 * for non-characters with the -C option; those are simulated
270 for (cnt = 0; cnt < WCHAR_MAX; cnt++) {
271 if (Cflag && !iswrune(cnt))
273 if (cmap_lookup(map, cnt) == OOBCH) {
275 cmap_add(map, cnt, s2.lastch);
277 cset_add(squeeze, s2.lastch);
279 cmap_add(map, cnt, cnt);
280 if ((s2.state == EOS || s2.state == INFINITE) &&
281 cnt >= cmap_max(map))
284 cmap_default(map, s2.lastch);
286 for (p = carray, cnt = 0; cnt < NCHARS_SB; cnt++) {
287 if (cmap_lookup(map, cnt) == OOBCH && iswrune(cnt))
290 cmap_add(map, cnt, cnt);
294 (void)mergesort(carray, n, sizeof(*carray), charcoll);
298 for (cnt = 0; cnt < n; cnt++) {
300 cmap_add(map, carray[cnt], s2.lastch);
302 * Chars taken from s2 can be different this time
303 * due to lack of complex upper/lower processing,
304 * so fill string2 again to not miss some.
307 cset_add(squeeze, s2.lastch);
315 for (lastch = OOBCH; (ch = getwchar()) != WEOF;) {
316 if (!Cflag || iswrune(ch))
317 ch = cmap_lookup(map, ch);
318 if (lastch != ch || !cset_in(squeeze, ch)) {
324 while ((ch = getwchar()) != WEOF) {
325 if (!Cflag || iswrune(ch))
326 ch = cmap_lookup(map, ch);
335 setup(char *arg, STR *str, int cflag, int Cflag)
344 cset_add(cs, str->lastch);
346 cset_addclass(cs, wctype("rune"), true);
354 charcoll(const void *a, const void *b)
356 static char sa[2], sb[2];
358 sa[0] = *(const int *)a;
359 sb[0] = *(const int *)b;
360 return (strcoll(sa, sb));
366 (void)fprintf(stderr, "%s\n%s\n%s\n%s\n",
367 "usage: tr [-Ccsu] string1 string2",
368 " tr [-Ccu] -d string1",
369 " tr [-Ccu] -s string1",
370 " tr [-Ccu] -ds string1 string2");