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 * 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 sccsid[] = "@(#)str.c 8.2 (Berkeley) 4/28/95";
38 #include <sys/types.h>
52 static int backslash(STR *, int *);
53 static int bracket(STR *);
54 static void genclass(STR *);
55 static void genequiv(STR *);
56 static int genrange(STR *, int);
57 static void genseq(STR *);
78 s->lastch = backslash(s, &is_octal);
85 clen = mbrtowc(&wch, s->str, MB_LEN_MAX, NULL);
86 if (clen == (size_t)-1 || clen == (size_t)-2 ||
88 errc(1, EILSEQ, NULL);
95 /* We can start a range at any time. */
96 if (s->str[0] == '-' && genrange(s, is_octal))
116 ch = nextwctype(s->lastch, s->cclass);
124 if ((ch = s->set[s->cnt++]) == OOBCH) {
142 case ':': /* "[:class:]" */
143 if ((p = strchr(s->str + 2, ']')) == NULL)
145 if (*(p - 1) != ':' || p - s->str < 4)
152 case '=': /* "[=equiv=]" */
153 if (s->str[2] == '\0' || (p = strchr(s->str + 3, ']')) == NULL)
155 if (*(p - 1) != '=' || p - s->str < 4)
160 default: /* "[\###*n]" or "[#*n]" */
162 if ((p = strpbrk(s->str + 2, "*]")) == NULL)
164 if (p[0] != '*' || strchr(p, ']') == NULL)
177 if ((s->cclass = wctype(s->str)) == 0)
178 errx(1, "unknown class %s", s->str);
180 s->lastch = -1; /* incremented before check in next() */
181 if (strcmp(s->str, "upper") == 0)
182 s->state = CCLASS_UPPER;
183 else if (strcmp(s->str, "lower") == 0)
184 s->state = CCLASS_LOWER;
197 if (*s->str == '\\') {
198 s->equiv[0] = backslash(s, NULL);
200 errx(1, "misplaced equivalence equals sign");
203 clen = mbrtowc(&wc, s->str, MB_LEN_MAX, NULL);
204 if (clen == (size_t)-1 || clen == (size_t)-2 || clen == 0)
205 errc(1, EILSEQ, NULL);
207 if (s->str[clen] != '=')
208 errx(1, "misplaced equivalence equals sign");
213 * Calculate the set of all characters in the same equivalence class
214 * as the specified character (they will have the same primary
215 * collation weights).
216 * XXX Knows too much about how strxfrm() is implemented. Assumes
217 * it fills the string with primary collation weight bytes. Only one-
218 * to-one mappings are supported.
219 * XXX Equivalence classes not supported in multibyte locales.
221 src[0] = (char)s->equiv[0];
223 if (MB_CUR_MAX == 1 && strxfrm(dst, src, sizeof(dst)) == 1) {
224 pri = (unsigned char)*dst;
225 for (p = 1, i = 1; i < NCHARS_SB; i++) {
227 if (strxfrm(dst, src, sizeof(dst)) == 1 && pri &&
228 pri == (unsigned char)*dst)
240 genrange(STR *s, int was_octal)
250 if (*++s->str == '\\')
251 stopval = backslash(s, &octal);
253 clen = mbrtowc(&wc, s->str, MB_LEN_MAX, NULL);
254 if (clen == (size_t)-1 || clen == (size_t)-2)
255 errc(1, EILSEQ, NULL);
260 * XXX Characters are not ordered according to collating sequence in
263 if (octal || was_octal || MB_CUR_MAX > 1) {
264 if (stopval < s->lastch) {
268 s->cnt = stopval - s->lastch + 1;
273 if (charcoll((const void *)&stopval, (const void *)&(s->lastch)) < 0) {
277 if ((s->set = p = malloc((NCHARS_SB + 1) * sizeof(int))) == NULL)
278 err(1, "genrange() malloc");
279 for (cnt = 0; cnt < NCHARS_SB; cnt++)
280 if (charcoll((const void *)&cnt, (const void *)&(s->lastch)) >= 0 &&
281 charcoll((const void *)&cnt, (const void *)&stopval) <= 0)
289 mergesort(s->set, n, sizeof(*(s->set)), charcoll);
300 if (s->which == STRING1)
301 errx(1, "sequences only valid in string2");
304 s->lastch = backslash(s, NULL);
306 clen = mbrtowc(&wc, s->str, MB_LEN_MAX, NULL);
307 if (clen == (size_t)-1 || clen == (size_t)-2)
308 errc(1, EILSEQ, NULL);
313 errx(1, "misplaced sequence asterisk");
317 s->cnt = backslash(s, NULL);
324 if (isdigit((u_char)*s->str)) {
325 s->cnt = strtol(s->str, &ep, 0);
331 errx(1, "illegal sequence count");
335 s->state = s->cnt ? SEQUENCE : INFINITE;
339 * Translate \??? into a character. Up to 3 octal digits, if no digits either
340 * an escape code or a literal character.
343 backslash(STR *s, int *is_octal)
347 if (is_octal != NULL)
349 for (cnt = val = 0;;) {
350 ch = (u_char)*++s->str;
351 if (!isdigit(ch) || ch > '7')
353 val = val * 8 + ch - '0';
360 if (is_octal != NULL)
367 case 'a': /* escape characters */
381 case '\0': /* \" -> \ */
384 default: /* \x" -> x */