1 /* $NetBSD: str.c,v 1.9 1999/03/16 14:57:48 kleink Exp $ */ 2 3 /*- 4 * Copyright (c) 1991, 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. All advertising materials mentioning features or use of this software 16 * must display the following acknowledgement: 17 * This product includes software developed by the University of 18 * California, Berkeley and its contributors. 19 * 4. Neither the name of the University nor the names of its contributors 20 * may be used to endorse or promote products derived from this software 21 * without specific prior written permission. 22 * 23 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 24 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 26 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 27 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 28 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 29 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 30 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 31 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 32 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 33 * SUCH DAMAGE. 34 */ 35 36 #include <sys/cdefs.h> 37 #ifndef lint 38 #if 0 39 static char sccsid[] = "@(#)str.c 8.2 (Berkeley) 4/28/95"; 40 #endif 41 __RCSID("$NetBSD: str.c,v 1.9 1999/03/16 14:57:48 kleink Exp $"); 42 #endif /* not lint */ 43 44 #include <sys/cdefs.h> 45 #include <sys/types.h> 46 47 #include <err.h> 48 #include <errno.h> 49 #include <stddef.h> 50 #include <stdio.h> 51 #include <stdlib.h> 52 #include <string.h> 53 #include <ctype.h> 54 55 #include "extern.h" 56 57 static int backslash __P((STR *)); 58 static int bracket __P((STR *)); 59 static int c_class __P((const void *, const void *)); 60 static void genclass __P((STR *)); 61 static void genequiv __P((STR *)); 62 static int genrange __P((STR *)); 63 static void genseq __P((STR *)); 64 65 int 66 next(s) 67 STR *s; 68 { 69 int ch; 70 71 switch (s->state) { 72 case EOS: 73 return (0); 74 case INFINITE: 75 return (1); 76 case NORMAL: 77 switch (ch = *s->str) { 78 case '\0': 79 s->state = EOS; 80 return (0); 81 case '\\': 82 s->lastch = backslash(s); 83 break; 84 case '[': 85 if (bracket(s)) 86 return (next(s)); 87 /* FALLTHROUGH */ 88 default: 89 ++s->str; 90 s->lastch = ch; 91 break; 92 } 93 94 /* We can start a range at any time. */ 95 if (s->str[0] == '-' && genrange(s)) 96 return (next(s)); 97 return (1); 98 case RANGE: 99 if (s->cnt-- == 0) { 100 s->state = NORMAL; 101 return (next(s)); 102 } 103 ++s->lastch; 104 return (1); 105 case SEQUENCE: 106 if (s->cnt-- == 0) { 107 s->state = NORMAL; 108 return (next(s)); 109 } 110 return (1); 111 case SET: 112 if ((s->lastch = s->set[s->cnt++]) == OOBCH) { 113 s->state = NORMAL; 114 return (next(s)); 115 } 116 return (1); 117 } 118 /* NOTREACHED */ 119 return (0); 120 } 121 122 static int 123 bracket(s) 124 STR *s; 125 { 126 char *p; 127 128 switch (s->str[1]) { 129 case ':': /* "[:class:]" */ 130 if ((p = strstr(s->str + 2, ":]")) == NULL) 131 return (0); 132 *p = '\0'; 133 s->str += 2; 134 genclass(s); 135 s->str = p + 2; 136 return (1); 137 case '=': /* "[=equiv=]" */ 138 if ((p = strstr(s->str + 2, "=]")) == NULL) 139 return (0); 140 s->str += 2; 141 genequiv(s); 142 return (1); 143 default: /* "[\###*n]" or "[#*n]" */ 144 if ((p = strpbrk(s->str + 2, "*]")) == NULL) 145 return (0); 146 if (p[0] != '*' || strchr(p, ']') == NULL) 147 return (0); 148 s->str += 1; 149 genseq(s); 150 return (1); 151 } 152 /* NOTREACHED */ 153 } 154 155 typedef struct { 156 char *name; 157 int (*func) __P((int)); 158 int *set; 159 } CLASS; 160 161 static CLASS classes[] = { 162 { "alnum", isalnum, }, 163 { "alpha", isalpha, }, 164 { "blank", isblank, }, 165 { "cntrl", iscntrl, }, 166 { "digit", isdigit, }, 167 { "graph", isgraph, }, 168 { "lower", islower, }, 169 { "print", isprint, }, 170 { "punct", ispunct, }, 171 { "space", isspace, }, 172 { "upper", isupper, }, 173 { "xdigit", isxdigit, }, 174 }; 175 176 static void 177 genclass(s) 178 STR *s; 179 { 180 int cnt, (*func) __P((int)); 181 CLASS *cp, tmp; 182 int *p; 183 184 tmp.name = s->str; 185 if ((cp = (CLASS *)bsearch(&tmp, classes, sizeof(classes) / 186 sizeof(CLASS), sizeof(CLASS), c_class)) == NULL) 187 errx(1, "unknown class %s", s->str); 188 189 if ((cp->set = p = malloc((NCHARS + 1) * sizeof(int))) == NULL) 190 err(1, "malloc"); 191 memset(p, 0, (NCHARS + 1) * sizeof(int)); 192 for (cnt = 0, func = cp->func; cnt < NCHARS; ++cnt) 193 if ((func)(cnt)) 194 *p++ = cnt; 195 *p = OOBCH; 196 197 s->cnt = 0; 198 s->state = SET; 199 s->set = cp->set; 200 } 201 202 static int 203 c_class(a, b) 204 const void *a, *b; 205 { 206 return (strcmp(((CLASS *)a)->name, ((CLASS *)b)->name)); 207 } 208 209 /* 210 * English doesn't have any equivalence classes, so for now 211 * we just syntax check and grab the character. 212 */ 213 static void 214 genequiv(s) 215 STR *s; 216 { 217 if (*s->str == '\\') { 218 s->equiv[0] = backslash(s); 219 if (*s->str != '=') 220 errx(1, "misplaced equivalence equals sign"); 221 } else { 222 s->equiv[0] = s->str[0]; 223 if (s->str[1] != '=') 224 errx(1, "misplaced equivalence equals sign"); 225 } 226 s->str += 2; 227 s->cnt = 0; 228 s->state = SET; 229 s->set = s->equiv; 230 } 231 232 static int 233 genrange(s) 234 STR *s; 235 { 236 int stopval; 237 char *savestart; 238 239 savestart = s->str; 240 stopval = *++s->str == '\\' ? backslash(s) : *s->str++; 241 if (stopval < (u_char)s->lastch) { 242 s->str = savestart; 243 return (0); 244 } 245 s->cnt = stopval - s->lastch + 1; 246 s->state = RANGE; 247 --s->lastch; 248 return (1); 249 } 250 251 static void 252 genseq(s) 253 STR *s; 254 { 255 char *ep; 256 257 if (s->which == STRING1) 258 errx(1, "sequences only valid in string2"); 259 260 if (*s->str == '\\') 261 s->lastch = backslash(s); 262 else 263 s->lastch = *s->str++; 264 if (*s->str != '*') 265 errx(1, "misplaced sequence asterisk"); 266 267 switch (*++s->str) { 268 case '\\': 269 s->cnt = backslash(s); 270 break; 271 case ']': 272 s->cnt = 0; 273 ++s->str; 274 break; 275 default: 276 if (isdigit(*s->str)) { 277 s->cnt = strtol(s->str, &ep, 0); 278 if (*ep == ']') { 279 s->str = ep + 1; 280 break; 281 } 282 } 283 errx(1, "illegal sequence count"); 284 /* NOTREACHED */ 285 } 286 287 s->state = s->cnt ? SEQUENCE : INFINITE; 288 } 289 290 /* 291 * Translate \??? into a character. Up to 3 octal digits, if no digits either 292 * an escape code or a literal character. 293 */ 294 static int 295 backslash(s) 296 STR *s; 297 { 298 int ch, cnt, val; 299 300 for (cnt = val = 0;;) { 301 ch = *++s->str; 302 if (!isascii(ch) || !isdigit(ch)) 303 break; 304 val = val * 8 + ch - '0'; 305 if (++cnt == 3) { 306 ++s->str; 307 break; 308 } 309 } 310 if (cnt) 311 return (val); 312 if (ch != '\0') 313 ++s->str; 314 switch (ch) { 315 case 'a': /* escape characters */ 316 return ('\7'); 317 case 'b': 318 return ('\b'); 319 case 'f': 320 return ('\f'); 321 case 'n': 322 return ('\n'); 323 case 'r': 324 return ('\r'); 325 case 't': 326 return ('\t'); 327 case 'v': 328 return ('\13'); 329 case '\0': /* \" -> \ */ 330 s->state = EOS; 331 return ('\\'); 332 default: /* \x" -> x */ 333 return (ch); 334 } 335 } 336