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[] = "from: @(#)str.c 5.9 (Berkeley) 3/4/93";*/ 36 static char rcsid[] = "$Id: str.c,v 1.5 1993/10/22 22:40:17 jtc Exp $"; 37 #endif /* not lint */ 38 39 #include <sys/cdefs.h> 40 #include <sys/types.h> 41 42 #include <errno.h> 43 #include <stddef.h> 44 #include <stdio.h> 45 #include <stdlib.h> 46 #include <string.h> 47 #include <ctype.h> 48 49 #include "extern.h" 50 51 static int backslash __P((STR *)); 52 static int bracket __P((STR *)); 53 static int c_class __P((const void *, const void *)); 54 static void genclass __P((STR *)); 55 static void genequiv __P((STR *)); 56 static int genrange __P((STR *)); 57 static void genseq __P((STR *)); 58 59 int 60 next(s) 61 register STR *s; 62 { 63 register int ch; 64 65 switch (s->state) { 66 case EOS: 67 return (0); 68 case INFINITE: 69 return (1); 70 case NORMAL: 71 switch (ch = *s->str) { 72 case '\0': 73 s->state = EOS; 74 return (0); 75 case '\\': 76 s->lastch = backslash(s); 77 break; 78 case '[': 79 if (bracket(s)) 80 return (next(s)); 81 /* FALLTHROUGH */ 82 default: 83 ++s->str; 84 s->lastch = ch; 85 break; 86 } 87 88 /* We can start a range at any time. */ 89 if (s->str[0] == '-' && genrange(s)) 90 return (next(s)); 91 return (1); 92 case RANGE: 93 if (s->cnt-- == 0) { 94 s->state = NORMAL; 95 return (next(s)); 96 } 97 ++s->lastch; 98 return (1); 99 case SEQUENCE: 100 if (s->cnt-- == 0) { 101 s->state = NORMAL; 102 return (next(s)); 103 } 104 return (1); 105 case SET: 106 if ((s->lastch = s->set[s->cnt++]) == OOBCH) { 107 s->state = NORMAL; 108 return (next(s)); 109 } 110 return (1); 111 } 112 /* NOTREACHED */ 113 } 114 115 static int 116 bracket(s) 117 register STR *s; 118 { 119 register char *p; 120 121 switch (s->str[1]) { 122 case ':': /* "[:class:]" */ 123 if ((p = strstr(s->str + 2, ":]")) == NULL) 124 return (0); 125 *p = '\0'; 126 s->str += 2; 127 genclass(s); 128 s->str = p + 2; 129 return (1); 130 case '=': /* "[=equiv=]" */ 131 if ((p = strstr(s->str + 2, "=]")) == NULL) 132 return (0); 133 s->str += 2; 134 genequiv(s); 135 return (1); 136 default: /* "[\###*n]" or "[#*n]" */ 137 if ((p = strpbrk(s->str + 2, "*]")) == NULL) 138 return (0); 139 if (p[0] != '*' || index(p, ']') == NULL) 140 return (0); 141 s->str += 1; 142 genseq(s); 143 return (1); 144 } 145 /* NOTREACHED */ 146 } 147 148 typedef struct { 149 char *name; 150 int (*func) __P((int)); 151 int *set; 152 } CLASS; 153 154 static CLASS classes[] = { 155 { "alnum", isalnum, }, 156 { "alpha", isalpha, }, 157 { "blank", isblank, }, 158 { "cntrl", iscntrl, }, 159 { "digit", isdigit, }, 160 { "graph", isgraph, }, 161 { "lower", islower, }, 162 { "print", isupper, }, 163 { "punct", ispunct, }, 164 { "space", isspace, }, 165 { "upper", isupper, }, 166 { "xdigit", isxdigit, }, 167 }; 168 169 static void 170 genclass(s) 171 STR *s; 172 { 173 register int cnt, (*func) __P((int)); 174 CLASS *cp, tmp; 175 int *p; 176 177 tmp.name = s->str; 178 if ((cp = (CLASS *)bsearch(&tmp, classes, sizeof(classes) / 179 sizeof(CLASS), sizeof(CLASS), c_class)) == NULL) 180 err("unknown class %s", s->str); 181 182 if ((cp->set = p = malloc((NCHARS + 1) * sizeof(int))) == NULL) 183 err("%s", strerror(errno)); 184 bzero(p, (NCHARS + 1) * sizeof(int)); 185 for (cnt = 0, func = cp->func; cnt < NCHARS; ++cnt) 186 if ((func)(cnt)) 187 *p++ = cnt; 188 *p = OOBCH; 189 190 s->cnt = 0; 191 s->state = SET; 192 s->set = cp->set; 193 } 194 195 static int 196 c_class(a, b) 197 const void *a, *b; 198 { 199 return (strcmp(((CLASS *)a)->name, ((CLASS *)b)->name)); 200 } 201 202 /* 203 * English doesn't have any equivalence classes, so for now 204 * we just syntax check and grab the character. 205 */ 206 static void 207 genequiv(s) 208 STR *s; 209 { 210 if (*s->str == '\\') { 211 s->equiv[0] = backslash(s); 212 if (*s->str != '=') 213 err("misplaced equivalence equals sign"); 214 } else { 215 s->equiv[0] = s->str[0]; 216 if (s->str[1] != '=') 217 err("misplaced equivalence equals sign"); 218 } 219 s->str += 2; 220 s->cnt = 0; 221 s->state = SET; 222 s->set = s->equiv; 223 } 224 225 static int 226 genrange(s) 227 STR *s; 228 { 229 int stopval; 230 char *savestart; 231 232 savestart = s->str; 233 stopval = *++s->str == '\\' ? backslash(s) : *s->str++; 234 if (stopval < s->lastch) { 235 s->str = savestart; 236 return (0); 237 } 238 s->cnt = stopval - s->lastch + 1; 239 s->state = RANGE; 240 --s->lastch; 241 return (1); 242 } 243 244 static void 245 genseq(s) 246 STR *s; 247 { 248 char *ep; 249 250 if (s->which == STRING1) 251 err("sequences only valid in string2"); 252 253 if (*s->str == '\\') 254 s->lastch = backslash(s); 255 else 256 s->lastch = *s->str++; 257 if (*s->str != '*') 258 err("misplaced sequence asterisk"); 259 260 switch (*++s->str) { 261 case '\\': 262 s->cnt = backslash(s); 263 break; 264 case ']': 265 s->cnt = 0; 266 ++s->str; 267 break; 268 default: 269 if (isdigit(*s->str)) { 270 s->cnt = strtol(s->str, &ep, 0); 271 if (*ep == ']') { 272 s->str = ep + 1; 273 break; 274 } 275 } 276 err("illegal sequence count"); 277 /* NOTREACHED */ 278 } 279 280 s->state = s->cnt ? SEQUENCE : INFINITE; 281 } 282 283 /* 284 * Translate \??? into a character. Up to 3 octal digits, if no digits either 285 * an escape code or a literal character. 286 */ 287 static int 288 backslash(s) 289 register STR *s; 290 { 291 register int ch, cnt, val; 292 293 for (cnt = val = 0;;) { 294 ch = *++s->str; 295 if (!isascii(ch) || !isdigit(ch)) 296 break; 297 val = val * 8 + ch - '0'; 298 if (++cnt == 3) { 299 ++s->str; 300 break; 301 } 302 } 303 if (cnt) 304 return (val); 305 if (ch != '\0') 306 ++s->str; 307 switch (ch) { 308 case 'a': /* escape characters */ 309 return ('\7'); 310 case 'b': 311 return ('\b'); 312 case 'f': 313 return ('\f'); 314 case 'n': 315 return ('\n'); 316 case 'r': 317 return ('\r'); 318 case 't': 319 return ('\t'); 320 case 'v': 321 return ('\13'); 322 case '\0': /* \" -> \ */ 323 s->state = EOS; 324 return ('\\'); 325 default: /* \x" -> x */ 326 return (ch); 327 } 328 } 329