1 /*- 2 * Copyright (c) 1991, 1993 3 * The Regents of the University of California. All rights reserved. 4 * 5 * Redistribution and use in source and binary forms, with or without 6 * modification, are permitted provided that the following conditions 7 * are met: 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. 20 * 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 31 * SUCH DAMAGE. 32 */ 33 34 #include <sys/cdefs.h> 35 36 __FBSDID("$FreeBSD$"); 37 38 #ifndef lint 39 static const char sccsid[] = "@(#)str.c 8.2 (Berkeley) 4/28/95"; 40 #endif 41 42 #include <sys/cdefs.h> 43 #include <sys/types.h> 44 45 #include <ctype.h> 46 #include <err.h> 47 #include <stddef.h> 48 #include <stdio.h> 49 #include <stdlib.h> 50 #include <string.h> 51 52 #include "extern.h" 53 54 static int backslash(STR *); 55 static int bracket(STR *); 56 static int c_class(const void *, const void *); 57 static void genclass(STR *); 58 static void genequiv(STR *); 59 static int genrange(STR *); 60 static void genseq(STR *); 61 62 int 63 next(s) 64 STR *s; 65 { 66 int ch; 67 68 switch (s->state) { 69 case EOS: 70 return (0); 71 case INFINITE: 72 return (1); 73 case NORMAL: 74 switch (ch = (u_char)*s->str) { 75 case '\0': 76 s->state = EOS; 77 return (0); 78 case '\\': 79 s->lastch = backslash(s); 80 break; 81 case '[': 82 if (bracket(s)) 83 return (next(s)); 84 /* FALLTHROUGH */ 85 default: 86 ++s->str; 87 s->lastch = ch; 88 break; 89 } 90 91 /* We can start a range at any time. */ 92 if (s->str[0] == '-' && genrange(s)) 93 return (next(s)); 94 return (1); 95 case RANGE: 96 if (s->cnt-- == 0) { 97 s->state = NORMAL; 98 return (next(s)); 99 } 100 ++s->lastch; 101 return (1); 102 case SEQUENCE: 103 if (s->cnt-- == 0) { 104 s->state = NORMAL; 105 return (next(s)); 106 } 107 return (1); 108 case SET: 109 if ((s->lastch = s->set[s->cnt++]) == OOBCH) { 110 s->state = NORMAL; 111 return (next(s)); 112 } 113 return (1); 114 default: 115 return (0); 116 } 117 /* NOTREACHED */ 118 } 119 120 static int 121 bracket(s) 122 STR *s; 123 { 124 char *p; 125 126 switch (s->str[1]) { 127 case ':': /* "[:class:]" */ 128 if ((p = strchr(s->str + 2, ']')) == NULL) 129 return (0); 130 if (*(p - 1) != ':' || p - s->str < 4) 131 goto repeat; 132 *(p - 1) = '\0'; 133 s->str += 2; 134 genclass(s); 135 s->str = p + 1; 136 return (1); 137 case '=': /* "[=equiv=]" */ 138 if ((p = strchr(s->str + 2, ']')) == NULL) 139 return (0); 140 if (*(p - 1) != '=' || p - s->str < 4) 141 goto repeat; 142 s->str += 2; 143 genequiv(s); 144 return (1); 145 default: /* "[\###*n]" or "[#*n]" */ 146 repeat: 147 if ((p = strpbrk(s->str + 2, "*]")) == NULL) 148 return (0); 149 if (p[0] != '*' || index(p, ']') == NULL) 150 return (0); 151 s->str += 1; 152 genseq(s); 153 return (1); 154 } 155 /* NOTREACHED */ 156 } 157 158 typedef struct { 159 const char *name; 160 int (*func)(int); 161 int *set; 162 } CLASS; 163 164 static CLASS classes[] = { 165 #undef isalnum 166 { "alnum", isalnum, NULL }, 167 #undef isalpha 168 { "alpha", isalpha, NULL }, 169 #undef isblank 170 { "blank", isblank, NULL }, 171 #undef iscntrl 172 { "cntrl", iscntrl, NULL }, 173 #undef isdigit 174 { "digit", isdigit, NULL }, 175 #undef isgraph 176 { "graph", isgraph, NULL }, 177 #undef islower 178 { "lower", islower, NULL }, 179 #undef isprint 180 { "print", isprint, NULL }, 181 #undef ispunct 182 { "punct", ispunct, NULL }, 183 #undef isspace 184 { "space", isspace, NULL }, 185 #undef isupper 186 { "upper", isupper, NULL }, 187 #undef isxdigit 188 { "xdigit", isxdigit, NULL }, 189 }; 190 191 static void 192 genclass(s) 193 STR *s; 194 { 195 int cnt, (*func)(int); 196 CLASS *cp, tmp; 197 int *p; 198 199 tmp.name = s->str; 200 if ((cp = (CLASS *)bsearch(&tmp, classes, sizeof(classes) / 201 sizeof(CLASS), sizeof(CLASS), c_class)) == NULL) 202 errx(1, "unknown class %s", s->str); 203 204 if ((cp->set = p = malloc((NCHARS + 1) * sizeof(int))) == NULL) 205 err(1, "malloc"); 206 bzero(p, (NCHARS + 1) * sizeof(int)); 207 for (cnt = 0, func = cp->func; cnt < NCHARS; ++cnt) 208 if ((func)(cnt)) 209 *p++ = cnt; 210 *p = OOBCH; 211 212 s->cnt = 0; 213 s->state = SET; 214 s->set = cp->set; 215 } 216 217 static int 218 c_class(a, b) 219 const void *a, *b; 220 { 221 return (strcmp(((const CLASS *)a)->name, ((const CLASS *)b)->name)); 222 } 223 224 static void 225 genequiv(s) 226 STR *s; 227 { 228 int i, p, pri; 229 char src[2], dst[3]; 230 231 if (*s->str == '\\') { 232 s->equiv[0] = backslash(s); 233 if (*s->str != '=') 234 errx(1, "misplaced equivalence equals sign"); 235 s->str += 2; 236 } else { 237 s->equiv[0] = s->str[0]; 238 if (s->str[1] != '=') 239 errx(1, "misplaced equivalence equals sign"); 240 s->str += 3; 241 } 242 243 /* 244 * Calculate the set of all characters in the same equivalence class 245 * as the specified character (they will have the same primary 246 * collation weights). 247 * XXX Knows too much about how strxfrm() is implemented. Assumes 248 * it fills the string with primary collation weight bytes. Only one- 249 * to-one mappings are supported. 250 */ 251 src[0] = s->equiv[0]; 252 src[1] = '\0'; 253 if (strxfrm(dst, src, sizeof(dst)) == 1) { 254 pri = (unsigned char)*dst; 255 for (p = 1, i = 1; i < NCHARS; i++) { 256 *src = i; 257 if (strxfrm(dst, src, sizeof(dst)) == 1 && pri && 258 pri == (unsigned char)*dst) 259 s->equiv[p++] = i; 260 } 261 s->equiv[p] = OOBCH; 262 } 263 264 s->cnt = 0; 265 s->state = SET; 266 s->set = s->equiv; 267 } 268 269 static int 270 genrange(s) 271 STR *s; 272 { 273 int stopval; 274 char *savestart; 275 276 savestart = s->str; 277 stopval = *++s->str == '\\' ? backslash(s) : (u_char)*s->str++; 278 if (stopval < (u_char)s->lastch) { 279 s->str = savestart; 280 return (0); 281 } 282 s->cnt = stopval - s->lastch + 1; 283 s->state = RANGE; 284 --s->lastch; 285 return (1); 286 } 287 288 static void 289 genseq(s) 290 STR *s; 291 { 292 char *ep; 293 294 if (s->which == STRING1) 295 errx(1, "sequences only valid in string2"); 296 297 if (*s->str == '\\') 298 s->lastch = backslash(s); 299 else 300 s->lastch = *s->str++; 301 if (*s->str != '*') 302 errx(1, "misplaced sequence asterisk"); 303 304 switch (*++s->str) { 305 case '\\': 306 s->cnt = backslash(s); 307 break; 308 case ']': 309 s->cnt = 0; 310 ++s->str; 311 break; 312 default: 313 if (isdigit((u_char)*s->str)) { 314 s->cnt = strtol(s->str, &ep, 0); 315 if (*ep == ']') { 316 s->str = ep + 1; 317 break; 318 } 319 } 320 errx(1, "illegal sequence count"); 321 /* NOTREACHED */ 322 } 323 324 s->state = s->cnt ? SEQUENCE : INFINITE; 325 } 326 327 /* 328 * Translate \??? into a character. Up to 3 octal digits, if no digits either 329 * an escape code or a literal character. 330 */ 331 static int 332 backslash(s) 333 STR *s; 334 { 335 int ch, cnt, val; 336 337 for (cnt = val = 0;;) { 338 ch = (u_char)*++s->str; 339 if (!isascii(ch) || !isdigit(ch)) 340 break; 341 val = val * 8 + ch - '0'; 342 if (++cnt == 3) { 343 ++s->str; 344 break; 345 } 346 } 347 if (cnt) 348 return (val); 349 if (ch != '\0') 350 ++s->str; 351 switch (ch) { 352 case 'a': /* escape characters */ 353 return ('\7'); 354 case 'b': 355 return ('\b'); 356 case 'f': 357 return ('\f'); 358 case 'n': 359 return ('\n'); 360 case 'r': 361 return ('\r'); 362 case 't': 363 return ('\t'); 364 case 'v': 365 return ('\13'); 366 case '\0': /* \" -> \ */ 367 s->state = EOS; 368 return ('\\'); 369 default: /* \x" -> x */ 370 return (ch); 371 } 372 } 373