2 * SPDX-License-Identifier: BSD-3-Clause
4 * Copyright (c) 1991, 1993
5 * The Regents of the University of California. All rights reserved.
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
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.
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
32 #include <sys/cdefs.h>
34 __FBSDID("$FreeBSD$");
37 static const char sccsid[] = "@(#)str.c 8.2 (Berkeley) 4/28/95";
40 #include <sys/types.h>
54 static int backslash(STR *, int *);
55 static int bracket(STR *);
56 static void genclass(STR *);
57 static void genequiv(STR *);
58 static int genrange(STR *, int);
59 static void genseq(STR *);
80 s->lastch = backslash(s, &is_octal);
87 clen = mbrtowc(&wch, s->str, MB_LEN_MAX, NULL);
88 if (clen == (size_t)-1 || clen == (size_t)-2 ||
90 errc(1, EILSEQ, NULL);
97 /* We can start a range at any time. */
98 if (s->str[0] == '-' && genrange(s, is_octal))
118 ch = nextwctype(s->lastch, s->cclass);
126 if ((ch = s->set[s->cnt++]) == OOBCH) {
144 case ':': /* "[:class:]" */
145 if ((p = strchr(s->str + 2, ']')) == NULL)
147 if (*(p - 1) != ':' || p - s->str < 4)
154 case '=': /* "[=equiv=]" */
155 if (s->str[2] == '\0' || (p = strchr(s->str + 3, ']')) == NULL)
157 if (*(p - 1) != '=' || p - s->str < 4)
162 default: /* "[\###*n]" or "[#*n]" */
164 if ((p = strpbrk(s->str + 2, "*]")) == NULL)
166 if (p[0] != '*' || strchr(p, ']') == NULL)
179 if ((s->cclass = wctype(s->str)) == 0)
180 errx(1, "unknown class %s", s->str);
182 s->lastch = -1; /* incremented before check in next() */
183 if (strcmp(s->str, "upper") == 0)
184 s->state = CCLASS_UPPER;
185 else if (strcmp(s->str, "lower") == 0)
186 s->state = CCLASS_LOWER;
199 if (*s->str == '\\') {
200 s->equiv[0] = backslash(s, NULL);
202 errx(1, "misplaced equivalence equals sign");
205 clen = mbrtowc(&wc, s->str, MB_LEN_MAX, NULL);
206 if (clen == (size_t)-1 || clen == (size_t)-2 || clen == 0)
207 errc(1, EILSEQ, NULL);
209 if (s->str[clen] != '=')
210 errx(1, "misplaced equivalence equals sign");
215 * Calculate the set of all characters in the same equivalence class
216 * as the specified character (they will have the same primary
217 * collation weights).
218 * XXX Knows too much about how strxfrm() is implemented. Assumes
219 * it fills the string with primary collation weight bytes. Only one-
220 * to-one mappings are supported.
221 * XXX Equivalence classes not supported in multibyte locales.
223 src[0] = (char)s->equiv[0];
225 if (MB_CUR_MAX == 1 && strxfrm(dst, src, sizeof(dst)) == 1) {
226 pri = (unsigned char)*dst;
227 for (p = 1, i = 1; i < NCHARS_SB; i++) {
229 if (strxfrm(dst, src, sizeof(dst)) == 1 && pri &&
230 pri == (unsigned char)*dst)
242 genrange(STR *s, int was_octal)
252 if (*++s->str == '\\')
253 stopval = backslash(s, &octal);
255 clen = mbrtowc(&wc, s->str, MB_LEN_MAX, NULL);
256 if (clen == (size_t)-1 || clen == (size_t)-2)
257 errc(1, EILSEQ, NULL);
262 * XXX Characters are not ordered according to collating sequence in
265 if (octal || was_octal || MB_CUR_MAX > 1) {
266 if (stopval < s->lastch) {
270 s->cnt = stopval - s->lastch + 1;
275 if (charcoll((const void *)&stopval, (const void *)&(s->lastch)) < 0) {
279 if ((s->set = p = malloc((NCHARS_SB + 1) * sizeof(int))) == NULL)
280 err(1, "genrange() malloc");
281 for (cnt = 0; cnt < NCHARS_SB; cnt++)
282 if (charcoll((const void *)&cnt, (const void *)&(s->lastch)) >= 0 &&
283 charcoll((const void *)&cnt, (const void *)&stopval) <= 0)
291 mergesort(s->set, n, sizeof(*(s->set)), charcoll);
302 if (s->which == STRING1)
303 errx(1, "sequences only valid in string2");
306 s->lastch = backslash(s, NULL);
308 clen = mbrtowc(&wc, s->str, MB_LEN_MAX, NULL);
309 if (clen == (size_t)-1 || clen == (size_t)-2)
310 errc(1, EILSEQ, NULL);
315 errx(1, "misplaced sequence asterisk");
319 s->cnt = backslash(s, NULL);
326 if (isdigit((u_char)*s->str)) {
327 s->cnt = strtol(s->str, &ep, 0);
333 errx(1, "illegal sequence count");
337 s->state = s->cnt ? SEQUENCE : INFINITE;
341 * Translate \??? into a character. Up to 3 octal digits, if no digits either
342 * an escape code or a literal character.
345 backslash(STR *s, int *is_octal)
349 if (is_octal != NULL)
351 for (cnt = val = 0;;) {
352 ch = (u_char)*++s->str;
353 if (!isdigit(ch) || ch > '7')
355 val = val * 8 + ch - '0';
362 if (is_octal != NULL)
369 case 'a': /* escape characters */
383 case '\0': /* \" -> \ */
386 default: /* \x" -> x */