1 /*-
2 * SPDX-License-Identifier: BSD-3-Clause
3 *
4 * Copyright (c) 1988, 1993
5 * The Regents of the University of California. All rights reserved.
6 *
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
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.
18 *
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
29 * SUCH DAMAGE.
30 */
31
32
33 #ifndef lint
34 static const char copyright[] =
35 "@(#) Copyright (c) 1988, 1993\n\
36 The Regents of the University of California. All rights reserved.\n";
37 #endif
38
39 #ifndef lint
40 static const char sccsid[] = "@(#)tr.c 8.2 (Berkeley) 5/4/95";
41 #endif
42
43 #include <sys/types.h>
44 #include <sys/capsicum.h>
45
46 #include <capsicum_helpers.h>
47 #include <ctype.h>
48 #include <err.h>
49 #include <limits.h>
50 #include <locale.h>
51 #include <stdint.h>
52 #include <stdio.h>
53 #include <stdlib.h>
54 #include <string.h>
55 #include <unistd.h>
56 #include <wchar.h>
57 #include <wctype.h>
58
59 #include "cmap.h"
60 #include "cset.h"
61 #include "extern.h"
62
63 static STR s1 = { STRING1, NORMAL, 0, OOBCH, 0, { 0, OOBCH }, NULL, NULL };
64 static STR s2 = { STRING2, NORMAL, 0, OOBCH, 0, { 0, OOBCH }, NULL, NULL };
65
66 static struct cset *setup(char *, STR *, int, int);
67 static void usage(void) __dead2;
68
69 int
main(int argc,char ** argv)70 main(int argc, char **argv)
71 {
72 static int carray[NCHARS_SB];
73 struct cmap *map;
74 struct cset *delete, *squeeze;
75 int n, *p;
76 int Cflag, cflag, dflag, sflag, isstring2;
77 wint_t ch, cnt, lastch;
78
79 (void)setlocale(LC_ALL, "");
80
81 if (caph_limit_stdio() == -1)
82 err(1, "unable to limit stdio");
83
84 if (caph_enter() < 0)
85 err(1, "unable to enter capability mode");
86
87 Cflag = cflag = dflag = sflag = 0;
88 while ((ch = getopt(argc, argv, "Ccdsu")) != -1)
89 switch((char)ch) {
90 case 'C':
91 Cflag = 1;
92 cflag = 0;
93 break;
94 case 'c':
95 cflag = 1;
96 Cflag = 0;
97 break;
98 case 'd':
99 dflag = 1;
100 break;
101 case 's':
102 sflag = 1;
103 break;
104 case 'u':
105 setbuf(stdout, (char *)NULL);
106 break;
107 case '?':
108 default:
109 usage();
110 }
111 argc -= optind;
112 argv += optind;
113
114 switch(argc) {
115 case 0:
116 default:
117 usage();
118 /* NOTREACHED */
119 case 1:
120 isstring2 = 0;
121 break;
122 case 2:
123 isstring2 = 1;
124 break;
125 }
126
127 /*
128 * tr -ds [-Cc] string1 string2
129 * Delete all characters (or complemented characters) in string1.
130 * Squeeze all characters in string2.
131 */
132 if (dflag && sflag) {
133 if (!isstring2)
134 usage();
135
136 delete = setup(argv[0], &s1, cflag, Cflag);
137 squeeze = setup(argv[1], &s2, 0, 0);
138
139 for (lastch = OOBCH; (ch = getwchar()) != WEOF;)
140 if (!cset_in(delete, ch) &&
141 (lastch != ch || !cset_in(squeeze, ch))) {
142 lastch = ch;
143 (void)putwchar(ch);
144 }
145 if (ferror(stdin))
146 err(1, NULL);
147 exit(0);
148 }
149
150 /*
151 * tr -d [-Cc] string1
152 * Delete all characters (or complemented characters) in string1.
153 */
154 if (dflag) {
155 if (isstring2)
156 usage();
157
158 delete = setup(argv[0], &s1, cflag, Cflag);
159
160 while ((ch = getwchar()) != WEOF)
161 if (!cset_in(delete, ch))
162 (void)putwchar(ch);
163 if (ferror(stdin))
164 err(1, NULL);
165 exit(0);
166 }
167
168 /*
169 * tr -s [-Cc] string1
170 * Squeeze all characters (or complemented characters) in string1.
171 */
172 if (sflag && !isstring2) {
173 squeeze = setup(argv[0], &s1, cflag, Cflag);
174
175 for (lastch = OOBCH; (ch = getwchar()) != WEOF;)
176 if (lastch != ch || !cset_in(squeeze, ch)) {
177 lastch = ch;
178 (void)putwchar(ch);
179 }
180 if (ferror(stdin))
181 err(1, NULL);
182 exit(0);
183 }
184
185 /*
186 * tr [-Ccs] string1 string2
187 * Replace all characters (or complemented characters) in string1 with
188 * the character in the same position in string2. If the -s option is
189 * specified, squeeze all the characters in string2.
190 */
191 if (!isstring2)
192 usage();
193
194 map = cmap_alloc();
195 if (map == NULL)
196 err(1, NULL);
197 squeeze = cset_alloc();
198 if (squeeze == NULL)
199 err(1, NULL);
200
201 s1.str = argv[0];
202
203 if (Cflag || cflag) {
204 cmap_default(map, OOBCH);
205 if ((s2.str = strdup(argv[1])) == NULL)
206 errx(1, "strdup(argv[1])");
207 } else
208 s2.str = argv[1];
209
210 if (!next(&s2))
211 errx(1, "empty string2");
212
213 /*
214 * For -s result will contain only those characters defined
215 * as the second characters in each of the toupper or tolower
216 * pairs.
217 */
218
219 /* If string2 runs out of characters, use the last one specified. */
220 while (next(&s1)) {
221 again:
222 if (s1.state == CCLASS_LOWER &&
223 s2.state == CCLASS_UPPER &&
224 s1.cnt == 1 && s2.cnt == 1) {
225 do {
226 ch = towupper(s1.lastch);
227 cmap_add(map, s1.lastch, ch);
228 if (sflag && iswupper(ch))
229 cset_add(squeeze, ch);
230 if (!next(&s1))
231 goto endloop;
232 } while (s1.state == CCLASS_LOWER && s1.cnt > 1);
233 /* skip upper set */
234 do {
235 if (!next(&s2))
236 break;
237 } while (s2.state == CCLASS_UPPER && s2.cnt > 1);
238 goto again;
239 } else if (s1.state == CCLASS_UPPER &&
240 s2.state == CCLASS_LOWER &&
241 s1.cnt == 1 && s2.cnt == 1) {
242 do {
243 ch = towlower(s1.lastch);
244 cmap_add(map, s1.lastch, ch);
245 if (sflag && iswlower(ch))
246 cset_add(squeeze, ch);
247 if (!next(&s1))
248 goto endloop;
249 } while (s1.state == CCLASS_UPPER && s1.cnt > 1);
250 /* skip lower set */
251 do {
252 if (!next(&s2))
253 break;
254 } while (s2.state == CCLASS_LOWER && s2.cnt > 1);
255 goto again;
256 } else {
257 cmap_add(map, s1.lastch, s2.lastch);
258 if (sflag)
259 cset_add(squeeze, s2.lastch);
260 }
261 (void)next(&s2);
262 }
263 endloop:
264 if (cflag || (Cflag && MB_CUR_MAX > 1)) {
265 /*
266 * This is somewhat tricky: since the character set is
267 * potentially huge, we need to avoid allocating a map
268 * entry for every character. Our strategy is to set the
269 * default mapping to the last character of string #2
270 * (= the one that gets automatically repeated), then to
271 * add back identity mappings for characters that should
272 * remain unchanged. We don't waste space on identity mappings
273 * for non-characters with the -C option; those are simulated
274 * in the I/O loop.
275 */
276 s2.str = argv[1];
277 s2.state = NORMAL;
278 for (cnt = 0; cnt < WINT_MAX; cnt++) {
279 if (Cflag && !iswrune(cnt))
280 continue;
281 if (cmap_lookup(map, cnt) == OOBCH) {
282 if (next(&s2)) {
283 cmap_add(map, cnt, s2.lastch);
284 if (sflag)
285 cset_add(squeeze, s2.lastch);
286 }
287 } else
288 cmap_add(map, cnt, cnt);
289 if ((s2.state == EOS || s2.state == INFINITE) &&
290 cnt >= cmap_max(map))
291 break;
292 }
293 cmap_default(map, s2.lastch);
294 } else if (Cflag) {
295 for (p = carray, cnt = 0; cnt < NCHARS_SB; cnt++) {
296 if (cmap_lookup(map, cnt) == OOBCH && iswrune(cnt))
297 *p++ = cnt;
298 else
299 cmap_add(map, cnt, cnt);
300 }
301 n = p - carray;
302 if (Cflag && n > 1)
303 (void)mergesort(carray, n, sizeof(*carray), charcoll);
304
305 s2.str = argv[1];
306 s2.state = NORMAL;
307 for (cnt = 0; cnt < n; cnt++) {
308 (void)next(&s2);
309 cmap_add(map, carray[cnt], s2.lastch);
310 /*
311 * Chars taken from s2 can be different this time
312 * due to lack of complex upper/lower processing,
313 * so fill string2 again to not miss some.
314 */
315 if (sflag)
316 cset_add(squeeze, s2.lastch);
317 }
318 }
319
320 cset_cache(squeeze);
321 cmap_cache(map);
322
323 if (sflag)
324 for (lastch = OOBCH; (ch = getwchar()) != WEOF;) {
325 if (!Cflag || iswrune(ch))
326 ch = cmap_lookup(map, ch);
327 if (lastch != ch || !cset_in(squeeze, ch)) {
328 lastch = ch;
329 (void)putwchar(ch);
330 }
331 }
332 else
333 while ((ch = getwchar()) != WEOF) {
334 if (!Cflag || iswrune(ch))
335 ch = cmap_lookup(map, ch);
336 (void)putwchar(ch);
337 }
338 if (ferror(stdin))
339 err(1, NULL);
340 exit (0);
341 }
342
343 static struct cset *
setup(char * arg,STR * str,int cflag,int Cflag)344 setup(char *arg, STR *str, int cflag, int Cflag)
345 {
346 struct cset *cs;
347
348 cs = cset_alloc();
349 if (cs == NULL)
350 err(1, NULL);
351 str->str = arg;
352 while (next(str))
353 cset_add(cs, str->lastch);
354 if (Cflag)
355 cset_addclass(cs, wctype("rune"), true);
356 if (cflag || Cflag)
357 cset_invert(cs);
358 cset_cache(cs);
359 return (cs);
360 }
361
362 int
charcoll(const void * a,const void * b)363 charcoll(const void *a, const void *b)
364 {
365 static char sa[2], sb[2];
366
367 sa[0] = *(const int *)a;
368 sb[0] = *(const int *)b;
369 return (strcoll(sa, sb));
370 }
371
372 static void
usage(void)373 usage(void)
374 {
375 (void)fprintf(stderr, "%s\n%s\n%s\n%s\n",
376 "usage: tr [-Ccsu] string1 string2",
377 " tr [-Ccu] -d string1",
378 " tr [-Ccu] -s string1",
379 " tr [-Ccu] -ds string1 string2");
380 exit(1);
381 }
382