2 * Copyright (c) 1991, 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. 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
29 * @(#)str.c 8.2 (Berkeley) 4/28/95
30 * $FreeBSD: head/usr.bin/tr/str.c 229403 2012-01-03 18:51:58Z ed $
33 #include <sys/types.h>
47 static int backslash(STR *, int *);
48 static int bracket(STR *);
49 static void genclass(STR *);
50 static void genequiv(STR *);
51 static int genrange(STR *, int);
52 static void genseq(STR *);
73 s->lastch = backslash(s, &is_octal);
80 clen = mbrtowc(&wch, s->str, MB_LEN_MAX, NULL);
81 if (clen == (size_t)-1 || clen == (size_t)-2 ||
83 errc(1, EILSEQ, NULL);
90 /* We can start a range at any time. */
91 if (s->str[0] == '-' && genrange(s, is_octal))
111 ch = nextwctype(s->lastch, s->cclass);
119 if ((ch = s->set[s->cnt++]) == OOBCH) {
137 case ':': /* "[:class:]" */
138 if ((p = strchr(s->str + 2, ']')) == NULL)
140 if (*(p - 1) != ':' || p - s->str < 4)
147 case '=': /* "[=equiv=]" */
148 if (s->str[2] == '\0' || (p = strchr(s->str + 3, ']')) == NULL)
150 if (*(p - 1) != '=' || p - s->str < 4)
155 default: /* "[\###*n]" or "[#*n]" */
157 if ((p = strpbrk(s->str + 2, "*]")) == NULL)
159 if (p[0] != '*' || strchr(p, ']') == NULL)
171 if ((s->cclass = wctype(s->str)) == 0)
172 errx(1, "unknown class %s", s->str);
174 s->lastch = -1; /* incremented before check in next() */
175 if (strcmp(s->str, "upper") == 0)
176 s->state = CCLASS_UPPER;
177 else if (strcmp(s->str, "lower") == 0)
178 s->state = CCLASS_LOWER;
191 if (*s->str == '\\') {
192 s->equiv[0] = backslash(s, NULL);
194 errx(1, "misplaced equivalence equals sign");
197 clen = mbrtowc(&wc, s->str, MB_LEN_MAX, NULL);
198 if (clen == (size_t)-1 || clen == (size_t)-2 || clen == 0)
199 errc(1, EILSEQ, NULL);
201 if (s->str[clen] != '=')
202 errx(1, "misplaced equivalence equals sign");
207 * Calculate the set of all characters in the same equivalence class
208 * as the specified character (they will have the same primary
209 * collation weights).
210 * XXX Knows too much about how strxfrm() is implemented. Assumes
211 * it fills the string with primary collation weight bytes. Only one-
212 * to-one mappings are supported.
213 * XXX Equivalence classes not supported in multibyte locales.
215 src[0] = (char)s->equiv[0];
217 if (MB_CUR_MAX == 1 && strxfrm(dst, src, sizeof(dst)) == 1) {
218 pri = (unsigned char)*dst;
219 for (p = 1, i = 1; i < NCHARS_SB; i++) {
221 if (strxfrm(dst, src, sizeof(dst)) == 1 && pri &&
222 pri == (unsigned char)*dst)
234 genrange(STR *s, int was_octal)
244 if (*++s->str == '\\')
245 stopval = backslash(s, &octal);
247 clen = mbrtowc(&wc, s->str, MB_LEN_MAX, NULL);
248 if (clen == (size_t)-1 || clen == (size_t)-2)
249 errc(1, EILSEQ, NULL);
254 * XXX Characters are not ordered according to collating sequence in
257 if (octal || was_octal || MB_CUR_MAX > 1) {
258 if (stopval < s->lastch) {
262 s->cnt = stopval - s->lastch + 1;
267 if (charcoll((const void *)&stopval, (const void *)&(s->lastch)) < 0) {
271 if ((s->set = p = malloc((NCHARS_SB + 1) * sizeof(int))) == NULL)
272 err(1, "genrange() malloc");
273 for (cnt = 0; cnt < NCHARS_SB; cnt++)
274 if (charcoll((const void *)&cnt, (const void *)&(s->lastch)) >= 0 &&
275 charcoll((const void *)&cnt, (const void *)&stopval) <= 0)
283 mergesort(s->set, n, sizeof(*(s->set)), charcoll);
294 if (s->which == STRING1)
295 errx(1, "sequences only valid in string2");
298 s->lastch = backslash(s, NULL);
300 clen = mbrtowc(&wc, s->str, MB_LEN_MAX, NULL);
301 if (clen == (size_t)-1 || clen == (size_t)-2)
302 errc(1, EILSEQ, NULL);
307 errx(1, "misplaced sequence asterisk");
311 s->cnt = backslash(s, NULL);
318 if (isdigit((u_char)*s->str)) {
319 s->cnt = strtol(s->str, &ep, 0);
325 errx(1, "illegal sequence count");
329 s->state = s->cnt ? SEQUENCE : INFINITE;
333 * Translate \??? into a character. Up to 3 octal digits, if no digits either
334 * an escape code or a literal character.
337 backslash(STR *s, int *is_octal)
341 if (is_octal != NULL)
343 for (cnt = val = 0;;) {
344 ch = (u_char)*++s->str;
345 if (!isdigit(ch) || ch > '7')
347 val = val * 8 + ch - '0';
354 if (is_octal != NULL)
361 case 'a': /* escape characters */
375 case '\0': /* \" -> \ */
378 default: /* \x" -> x */