1 /*- 2 * Copyright (c) 1991 The Regents of the University of California. 3 * 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 #ifndef lint 35 static char sccsid[] = "@(#)str.c 5.9 (Berkeley) 3/4/93"; 36 #endif /* not lint */ 37 38 #include <sys/cdefs.h> 39 #include <sys/types.h> 40 41 #include <errno.h> 42 #include <stddef.h> 43 #include <stdio.h> 44 #include <stdlib.h> 45 #include <string.h> 46 47 #include "extern.h" 48 49 static int backslash __P((STR *)); 50 static int bracket __P((STR *)); 51 static int c_class __P((const void *, const void *)); 52 static void genclass __P((STR *)); 53 static void genequiv __P((STR *)); 54 static int genrange __P((STR *)); 55 static void genseq __P((STR *)); 56 57 int 58 next(s) 59 register STR *s; 60 { 61 register int ch; 62 63 switch (s->state) { 64 case EOS: 65 return (0); 66 case INFINITE: 67 return (1); 68 case NORMAL: 69 switch (ch = *s->str) { 70 case '\0': 71 s->state = EOS; 72 return (0); 73 case '\\': 74 s->lastch = backslash(s); 75 break; 76 case '[': 77 if (bracket(s)) 78 return (next(s)); 79 /* FALLTHROUGH */ 80 default: 81 ++s->str; 82 s->lastch = ch; 83 break; 84 } 85 86 /* We can start a range at any time. */ 87 if (s->str[0] == '-' && genrange(s)) 88 return (next(s)); 89 return (1); 90 case RANGE: 91 if (s->cnt-- == 0) { 92 s->state = NORMAL; 93 return (next(s)); 94 } 95 ++s->lastch; 96 return (1); 97 case SEQUENCE: 98 if (s->cnt-- == 0) { 99 s->state = NORMAL; 100 return (next(s)); 101 } 102 return (1); 103 case SET: 104 if ((s->lastch = s->set[s->cnt++]) == OOBCH) { 105 s->state = NORMAL; 106 return (next(s)); 107 } 108 return (1); 109 } 110 /* NOTREACHED */ 111 } 112 113 static int 114 bracket(s) 115 register STR *s; 116 { 117 register char *p; 118 119 switch (s->str[1]) { 120 case ':': /* "[:class:]" */ 121 if ((p = strstr(s->str + 2, ":]")) == NULL) 122 return (0); 123 *p = '\0'; 124 s->str += 2; 125 genclass(s); 126 s->str = p + 2; 127 return (1); 128 case '=': /* "[=equiv=]" */ 129 if ((p = strstr(s->str + 2, "=]")) == NULL) 130 return (0); 131 s->str += 2; 132 genequiv(s); 133 return (1); 134 default: /* "[\###*n]" or "[#*n]" */ 135 if ((p = strpbrk(s->str + 2, "*]")) == NULL) 136 return (0); 137 if (p[0] != '*' || index(p, ']') == NULL) 138 return (0); 139 s->str += 1; 140 genseq(s); 141 return (1); 142 } 143 /* NOTREACHED */ 144 } 145 146 int isalnum __P((int)), 147 isalpha __P((int)), 148 isblank __P((int)), 149 isspace __P((int)), 150 iscntrl __P((int)), 151 isdigit __P((int)), 152 isgraph __P((int)), 153 islower __P((int)), 154 isprint __P((int)), 155 ispunct __P((int)), 156 isupper __P((int)), 157 isxdigit __P((int)); 158 159 160 static int isblank(x) /* until 4.4 */ 161 int x; 162 { 163 if ((x == ' ') || (x== '\t')) return 1; 164 return 0; 165 } 166 167 168 typedef struct { 169 char *name; 170 int (*func) __P((int)); 171 int *set; 172 } CLASS; 173 174 static CLASS classes[] = { 175 { "alnum", isalnum, }, 176 { "alpha", isalpha, }, 177 { "blank", isblank, }, 178 { "cntrl", iscntrl, }, 179 { "digit", isdigit, }, 180 { "graph", isgraph, }, 181 { "lower", islower, }, 182 { "print", isupper, }, 183 { "punct", ispunct, }, 184 { "space", isspace, }, 185 { "upper", isupper, }, 186 { "xdigit", isxdigit, }, 187 }; 188 189 static void 190 genclass(s) 191 STR *s; 192 { 193 register int cnt, (*func) __P((int)); 194 CLASS *cp, tmp; 195 int *p; 196 197 tmp.name = s->str; 198 if ((cp = (CLASS *)bsearch(&tmp, classes, sizeof(classes) / 199 sizeof(CLASS), sizeof(CLASS), c_class)) == NULL) 200 err("unknown class %s", s->str); 201 202 if ((cp->set = p = malloc((NCHARS + 1) * sizeof(int))) == NULL) 203 err("%s", strerror(errno)); 204 bzero(p, (NCHARS + 1) * sizeof(int)); 205 for (cnt = 0, func = cp->func; cnt < NCHARS; ++cnt) 206 if ((func)(cnt)) 207 *p++ = cnt; 208 *p = OOBCH; 209 210 s->cnt = 0; 211 s->state = SET; 212 s->set = cp->set; 213 } 214 215 static int 216 c_class(a, b) 217 const void *a, *b; 218 { 219 return (strcmp(((CLASS *)a)->name, ((CLASS *)b)->name)); 220 } 221 222 /* 223 * English doesn't have any equivalence classes, so for now 224 * we just syntax check and grab the character. 225 */ 226 static void 227 genequiv(s) 228 STR *s; 229 { 230 if (*s->str == '\\') { 231 s->equiv[0] = backslash(s); 232 if (*s->str != '=') 233 err("misplaced equivalence equals sign"); 234 } else { 235 s->equiv[0] = s->str[0]; 236 if (s->str[1] != '=') 237 err("misplaced equivalence equals sign"); 238 } 239 s->str += 2; 240 s->cnt = 0; 241 s->state = SET; 242 s->set = s->equiv; 243 } 244 245 static int 246 genrange(s) 247 STR *s; 248 { 249 int stopval; 250 char *savestart; 251 252 savestart = s->str; 253 stopval = *++s->str == '\\' ? backslash(s) : *s->str; 254 if (stopval < s->lastch) { 255 s->str = savestart; 256 return (0); 257 } 258 s->cnt = stopval - s->lastch + 1; 259 s->state = RANGE; 260 ++s->str; 261 --s->lastch; 262 return (1); 263 } 264 265 static void 266 genseq(s) 267 STR *s; 268 { 269 char *ep; 270 271 if (s->which == STRING1) 272 err("sequences only valid in string2"); 273 274 if (*s->str == '\\') 275 s->lastch = backslash(s); 276 else 277 s->lastch = *s->str++; 278 if (*s->str != '*') 279 err("misplaced sequence asterisk"); 280 281 switch (*++s->str) { 282 case '\\': 283 s->cnt = backslash(s); 284 break; 285 case ']': 286 s->cnt = 0; 287 ++s->str; 288 break; 289 default: 290 if (isdigit(*s->str)) { 291 s->cnt = strtol(s->str, &ep, 0); 292 if (*ep == ']') { 293 s->str = ep + 1; 294 break; 295 } 296 } 297 err("illegal sequence count"); 298 /* NOTREACHED */ 299 } 300 301 s->state = s->cnt ? SEQUENCE : INFINITE; 302 } 303 304 /* Use the #defines isXXX() here, DON'T use them above. */ 305 #include <ctype.h> 306 307 /* 308 * Translate \??? into a character. Up to 3 octal digits, if no digits either 309 * an escape code or a literal character. 310 */ 311 static int 312 backslash(s) 313 register STR *s; 314 { 315 register int ch, cnt, val; 316 317 for (cnt = val = 0;;) { 318 ch = *++s->str; 319 if (!isascii(ch) || !isdigit(ch)) 320 break; 321 val = val * 8 + ch - '0'; 322 if (++cnt == 3) { 323 ++s->str; 324 break; 325 } 326 } 327 if (cnt) 328 return (val); 329 if (ch != '\0') 330 ++s->str; 331 switch (ch) { 332 case 'a': /* escape characters */ 333 return ('\7'); 334 case 'b': 335 return ('\b'); 336 case 'f': 337 return ('\f'); 338 case 'n': 339 return ('\n'); 340 case 'r': 341 return ('\r'); 342 case 't': 343 return ('\t'); 344 case 'v': 345 return ('\13'); 346 case '\0': /* \" -> \ */ 347 s->state = EOS; 348 return ('\\'); 349 default: /* \x" -> x */ 350 return (ch); 351 } 352 } 353