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. 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
33 * @(#)str.c 8.2 (Berkeley) 4/28/95
34 * $FreeBSD: src/usr.bin/tr/str.c,v 1.10.2.2 2002/07/29 12:59:33 tjr Exp $
35 * $DragonFly: src/usr.bin/tr/str.c,v 1.4 2004/08/30 18:06:50 eirikn Exp $
38 #include <sys/cdefs.h>
39 #include <sys/types.h>
50 static int backslash(STR *);
51 static int bracket(STR *);
52 static int c_class(const void *, const void *);
53 static void genclass(STR *);
54 static void genequiv(STR *);
55 static int genrange(STR *);
56 static void genseq(STR *);
69 switch (ch = (u_char)*s->str) {
74 s->lastch = backslash(s);
86 /* We can start a range at any time. */
87 if (s->str[0] == '-' && genrange(s))
104 if ((s->lastch = s->set[s->cnt++]) == OOBCH) {
121 case ':': /* "[:class:]" */
122 if ((p = strchr(s->str + 2, ']')) == NULL)
124 if (*(p - 1) != ':' || p - s->str < 4)
131 case '=': /* "[=equiv=]" */
132 if ((p = strchr(s->str + 2, ']')) == NULL)
134 if (*(p - 1) != '=' || p - s->str < 4)
139 default: /* "[\###*n]" or "[#*n]" */
141 if ((p = strpbrk(s->str + 2, "*]")) == NULL)
143 if (p[0] != '*' || strchr(p, ']') == NULL)
158 static CLASS classes[] = {
160 { "alnum", isalnum, NULL },
162 { "alpha", isalpha, NULL },
164 { "blank", isblank, NULL },
166 { "cntrl", iscntrl, NULL },
168 { "digit", isdigit, NULL },
170 { "graph", isgraph, NULL },
172 { "lower", islower, NULL },
174 { "print", isprint, NULL },
176 { "punct", ispunct, NULL },
178 { "space", isspace, NULL },
180 { "upper", isupper, NULL },
182 { "xdigit", isxdigit, NULL },
188 int cnt, (*func)(int);
193 if ((cp = (CLASS *)bsearch(&tmp, classes, sizeof(classes) /
194 sizeof(CLASS), sizeof(CLASS), c_class)) == NULL)
195 errx(1, "unknown class %s", s->str);
197 if ((cp->set = p = malloc((NCHARS + 1) * sizeof(int))) == NULL)
199 bzero(p, (NCHARS + 1) * sizeof(int));
200 for (cnt = 0, func = cp->func; cnt < NCHARS; ++cnt)
211 c_class(const void *a, const void *b)
213 return (strcmp(((const CLASS *)a)->name, ((const CLASS *)b)->name));
222 if (*s->str == '\\') {
223 s->equiv[0] = backslash(s);
225 errx(1, "misplaced equivalence equals sign");
228 s->equiv[0] = s->str[0];
229 if (s->str[1] != '=')
230 errx(1, "misplaced equivalence equals sign");
235 * Calculate the set of all characters in the same equivalence class
236 * as the specified character (they will have the same primary
237 * collation weights).
238 * XXX Knows too much about how strxfrm() is implemented. Assumes
239 * it fills the string with primary collation weight bytes. Only one-
240 * to-one mappings are supported.
242 src[0] = s->equiv[0];
244 if (strxfrm(dst, src, sizeof(dst)) == 1) {
245 pri = (unsigned char)*dst;
246 for (p = 1, i = 1; i < NCHARS; i++) {
248 if (strxfrm(dst, src, sizeof(dst)) == 1 && pri &&
249 pri == (unsigned char)*dst)
267 stopval = *++s->str == '\\' ? backslash(s) : (u_char)*s->str++;
268 if (stopval < (u_char)s->lastch) {
272 s->cnt = stopval - s->lastch + 1;
283 if (s->which == STRING1)
284 errx(1, "sequences only valid in string2");
287 s->lastch = backslash(s);
289 s->lastch = *s->str++;
291 errx(1, "misplaced sequence asterisk");
295 s->cnt = backslash(s);
302 if (isdigit((u_char)*s->str)) {
303 s->cnt = strtol(s->str, &ep, 0);
309 errx(1, "illegal sequence count");
313 s->state = s->cnt ? SEQUENCE : INFINITE;
317 * Translate \??? into a character. Up to 3 octal digits, if no digits either
318 * an escape code or a literal character.
325 for (cnt = val = 0;;) {
326 ch = (u_char)*++s->str;
327 if (!isascii(ch) || !isdigit(ch))
329 val = val * 8 + ch - '0';
340 case 'a': /* escape characters */
354 case '\0': /* \" -> \ */
357 default: /* \x" -> x */