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 * 3. All advertising materials mentioning features or use of this software
14 * must display the following acknowledgement:
15 * This product includes software developed by the University of
16 * California, Berkeley and its contributors.
17 * 4. Neither the name of the University nor the names of its contributors
18 * may be used to endorse or promote products derived from this software
19 * without specific prior written permission.
21 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
22 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
23 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
24 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
25 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
26 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
27 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
28 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
29 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
30 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
34 #include <sys/cdefs.h>
36 __FBSDID("$FreeBSD$");
39 static const char copyright[] =
40 "@(#) Copyright (c) 1988, 1993\n\
41 The Regents of the University of California. All rights reserved.\n";
45 static const char sccsid[] = "@(#)tr.c 8.2 (Berkeley) 5/4/95";
48 #include <sys/types.h>
65 STR s1 = { STRING1, NORMAL, 0, OOBCH, 0, { 0, OOBCH }, NULL, NULL };
66 STR s2 = { STRING2, NORMAL, 0, OOBCH, 0, { 0, OOBCH }, NULL, NULL };
68 static struct cset *setup(char *, STR *, int, int);
69 static void usage(void);
72 main(int argc, char **argv)
74 static int carray[NCHARS_SB];
76 struct cset *delete, *squeeze;
78 int Cflag, cflag, dflag, sflag, isstring2;
79 wint_t ch, cnt, lastch;
81 (void)setlocale(LC_ALL, "");
83 Cflag = cflag = dflag = sflag = 0;
84 while ((ch = getopt(argc, argv, "Ccdsu")) != -1)
101 setbuf(stdout, (char *)NULL);
124 * tr -ds [-Cc] string1 string2
125 * Delete all characters (or complemented characters) in string1.
126 * Squeeze all characters in string2.
128 if (dflag && sflag) {
132 delete = setup(argv[0], &s1, cflag, Cflag);
133 squeeze = setup(argv[1], &s2, 0, 0);
135 for (lastch = OOBCH; (ch = getwchar()) != WEOF;)
136 if (!cset_in(delete, ch) &&
137 (lastch != ch || !cset_in(squeeze, ch))) {
147 * tr -d [-Cc] string1
148 * Delete all characters (or complemented characters) in string1.
154 delete = setup(argv[0], &s1, cflag, Cflag);
156 while ((ch = getwchar()) != WEOF)
157 if (!cset_in(delete, ch))
165 * tr -s [-Cc] string1
166 * Squeeze all characters (or complemented characters) in string1.
168 if (sflag && !isstring2) {
169 squeeze = setup(argv[0], &s1, cflag, Cflag);
171 for (lastch = OOBCH; (ch = getwchar()) != WEOF;)
172 if (lastch != ch || !cset_in(squeeze, ch)) {
182 * tr [-Ccs] string1 string2
183 * Replace all characters (or complemented characters) in string1 with
184 * the character in the same position in string2. If the -s option is
185 * specified, squeeze all the characters in string2.
193 squeeze = cset_alloc();
199 if (Cflag || cflag) {
200 cmap_default(map, OOBCH);
201 if ((s2.str = strdup(argv[1])) == NULL)
202 errx(1, "strdup(argv[1])");
207 errx(1, "empty string2");
210 * For -s result will contain only those characters defined
211 * as the second characters in each of the toupper or tolower
215 /* If string2 runs out of characters, use the last one specified. */
218 if (s1.state == CCLASS_LOWER &&
219 s2.state == CCLASS_UPPER &&
220 s1.cnt == 1 && s2.cnt == 1) {
222 ch = towupper(s1.lastch);
223 cmap_add(map, s1.lastch, ch);
224 if (sflag && iswupper(ch))
225 cset_add(squeeze, ch);
228 } while (s1.state == CCLASS_LOWER && s1.cnt > 1);
233 } while (s2.state == CCLASS_UPPER && s2.cnt > 1);
235 } else if (s1.state == CCLASS_UPPER &&
236 s2.state == CCLASS_LOWER &&
237 s1.cnt == 1 && s2.cnt == 1) {
239 ch = towlower(s1.lastch);
240 cmap_add(map, s1.lastch, ch);
241 if (sflag && iswlower(ch))
242 cset_add(squeeze, ch);
245 } while (s1.state == CCLASS_UPPER && s1.cnt > 1);
250 } while (s2.state == CCLASS_LOWER && s2.cnt > 1);
253 cmap_add(map, s1.lastch, s2.lastch);
255 cset_add(squeeze, s2.lastch);
260 if (cflag || (Cflag && MB_CUR_MAX > 1)) {
262 * This is somewhat tricky: since the character set is
263 * potentially huge, we need to avoid allocating a map
264 * entry for every character. Our strategy is to set the
265 * default mapping to the last character of string #2
266 * (= the one that gets automatically repeated), then to
267 * add back identity mappings for characters that should
268 * remain unchanged. We don't waste space on identity mappings
269 * for non-characters with the -C option; those are simulated
274 for (cnt = 0; cnt < WCHAR_MAX; cnt++) {
275 if (Cflag && !iswrune(cnt))
277 if (cmap_lookup(map, cnt) == OOBCH) {
279 cmap_add(map, cnt, s2.lastch);
281 cset_add(squeeze, s2.lastch);
283 cmap_add(map, cnt, cnt);
284 if ((s2.state == EOS || s2.state == INFINITE) &&
285 cnt >= cmap_max(map))
288 cmap_default(map, s2.lastch);
290 for (p = carray, cnt = 0; cnt < NCHARS_SB; cnt++) {
291 if (cmap_lookup(map, cnt) == OOBCH && iswrune(cnt))
294 cmap_add(map, cnt, cnt);
298 (void)mergesort(carray, n, sizeof(*carray), charcoll);
302 for (cnt = 0; cnt < n; cnt++) {
304 cmap_add(map, carray[cnt], s2.lastch);
306 * Chars taken from s2 can be different this time
307 * due to lack of complex upper/lower processing,
308 * so fill string2 again to not miss some.
311 cset_add(squeeze, s2.lastch);
319 for (lastch = OOBCH; (ch = getwchar()) != WEOF;) {
320 if (!Cflag || iswrune(ch))
321 ch = cmap_lookup(map, ch);
322 if (lastch != ch || !cset_in(squeeze, ch)) {
328 while ((ch = getwchar()) != WEOF) {
329 if (!Cflag || iswrune(ch))
330 ch = cmap_lookup(map, ch);
339 setup(char *arg, STR *str, int cflag, int Cflag)
348 cset_add(cs, str->lastch);
350 cset_addclass(cs, wctype("rune"), true);
358 charcoll(const void *a, const void *b)
360 static char sa[2], sb[2];
362 sa[0] = *(const int *)a;
363 sb[0] = *(const int *)b;
364 return (strcoll(sa, sb));
370 (void)fprintf(stderr, "%s\n%s\n%s\n%s\n",
371 "usage: tr [-Ccsu] string1 string2",
372 " tr [-Ccu] -d string1",
373 " tr [-Ccu] -s string1",
374 " tr [-Ccu] -ds string1 string2");