tokenizer.c revision 1.11
1 /* $NetBSD: tokenizer.c,v 1.11 2002/10/27 20:24:29 christos Exp $ */ 2 3 /*- 4 * Copyright (c) 1992, 1993 5 * The Regents of the University of California. All rights reserved. 6 * 7 * This code is derived from software contributed to Berkeley by 8 * Christos Zoulas of Cornell University. 9 * 10 * Redistribution and use in source and binary forms, with or without 11 * modification, are permitted provided that the following conditions 12 * are met: 13 * 1. Redistributions of source code must retain the above copyright 14 * notice, this list of conditions and the following disclaimer. 15 * 2. Redistributions in binary form must reproduce the above copyright 16 * notice, this list of conditions and the following disclaimer in the 17 * documentation and/or other materials provided with the distribution. 18 * 3. All advertising materials mentioning features or use of this software 19 * must display the following acknowledgement: 20 * This product includes software developed by the University of 21 * California, Berkeley and its contributors. 22 * 4. Neither the name of the University nor the names of its contributors 23 * may be used to endorse or promote products derived from this software 24 * without specific prior written permission. 25 * 26 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 27 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 28 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 29 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 30 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 31 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 32 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 33 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 34 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 35 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 36 * SUCH DAMAGE. 37 */ 38 39 #include "config.h" 40 #if !defined(lint) && !defined(SCCSID) 41 #if 0 42 static char sccsid[] = "@(#)tokenizer.c 8.1 (Berkeley) 6/4/93"; 43 #else 44 __RCSID("$NetBSD: tokenizer.c,v 1.11 2002/10/27 20:24:29 christos Exp $"); 45 #endif 46 #endif /* not lint && not SCCSID */ 47 48 /* 49 * tokenize.c: Bourne shell like tokenizer 50 */ 51 #include <string.h> 52 #include <stdlib.h> 53 #include "tokenizer.h" 54 55 typedef enum { 56 Q_none, Q_single, Q_double, Q_one, Q_doubleone 57 } quote_t; 58 59 #define IFS "\t \n" 60 61 #define TOK_KEEP 1 62 #define TOK_EAT 2 63 64 #define WINCR 20 65 #define AINCR 10 66 67 #define tok_malloc(a) malloc(a) 68 #define tok_free(a) free(a) 69 #define tok_realloc(a, b) realloc(a, b) 70 71 72 struct tokenizer { 73 char *ifs; /* In field separator */ 74 int argc, amax; /* Current and maximum number of args */ 75 char **argv; /* Argument list */ 76 char *wptr, *wmax; /* Space and limit on the word buffer */ 77 char *wstart; /* Beginning of next word */ 78 char *wspace; /* Space of word buffer */ 79 quote_t quote; /* Quoting state */ 80 int flags; /* flags; */ 81 }; 82 83 84 private void tok_finish(Tokenizer *); 85 86 87 /* tok_finish(): 88 * Finish a word in the tokenizer. 89 */ 90 private void 91 tok_finish(Tokenizer *tok) 92 { 93 94 *tok->wptr = '\0'; 95 if ((tok->flags & TOK_KEEP) || tok->wptr != tok->wstart) { 96 tok->argv[tok->argc++] = tok->wstart; 97 tok->argv[tok->argc] = NULL; 98 tok->wstart = ++tok->wptr; 99 } 100 tok->flags &= ~TOK_KEEP; 101 } 102 103 104 /* tok_init(): 105 * Initialize the tokenizer 106 */ 107 public Tokenizer * 108 tok_init(const char *ifs) 109 { 110 Tokenizer *tok = (Tokenizer *) tok_malloc(sizeof(Tokenizer)); 111 112 if (tok == NULL) 113 return NULL; 114 tok->ifs = strdup(ifs ? ifs : IFS); 115 if (tok->ifs == NULL) { 116 tok_free((ptr_t)tok); 117 return NULL; 118 } 119 tok->argc = 0; 120 tok->amax = AINCR; 121 tok->argv = (char **) tok_malloc(sizeof(char *) * tok->amax); 122 if (tok->argv == NULL) { 123 tok_free((ptr_t)tok->ifs); 124 tok_free((ptr_t)tok); 125 return NULL; 126 } 127 tok->argv[0] = NULL; 128 tok->wspace = (char *) tok_malloc(WINCR); 129 if (tok->wspace == NULL) { 130 tok_free((ptr_t)tok->argv); 131 tok_free((ptr_t)tok->ifs); 132 tok_free((ptr_t)tok); 133 return NULL; 134 } 135 tok->wmax = tok->wspace + WINCR; 136 tok->wstart = tok->wspace; 137 tok->wptr = tok->wspace; 138 tok->flags = 0; 139 tok->quote = Q_none; 140 141 return (tok); 142 } 143 144 145 /* tok_reset(): 146 * Reset the tokenizer 147 */ 148 public void 149 tok_reset(Tokenizer *tok) 150 { 151 152 tok->argc = 0; 153 tok->wstart = tok->wspace; 154 tok->wptr = tok->wspace; 155 tok->flags = 0; 156 tok->quote = Q_none; 157 } 158 159 160 /* tok_end(): 161 * Clean up 162 */ 163 public void 164 tok_end(Tokenizer *tok) 165 { 166 167 tok_free((ptr_t) tok->ifs); 168 tok_free((ptr_t) tok->wspace); 169 tok_free((ptr_t) tok->argv); 170 tok_free((ptr_t) tok); 171 } 172 173 174 175 /* tok_line(): 176 * Bourne shell like tokenizing 177 * Return: 178 * -1: Internal error 179 * 3: Quoted return 180 * 2: Unmatched double quote 181 * 1: Unmatched single quote 182 * 0: Ok 183 */ 184 public int 185 tok_line(Tokenizer *tok, const char *line, int *argc, const char ***argv) 186 { 187 const char *ptr; 188 189 for (;;) { 190 switch (*(ptr = line++)) { 191 case '\'': 192 tok->flags |= TOK_KEEP; 193 tok->flags &= ~TOK_EAT; 194 switch (tok->quote) { 195 case Q_none: 196 tok->quote = Q_single; /* Enter single quote 197 * mode */ 198 break; 199 200 case Q_single: /* Exit single quote mode */ 201 tok->quote = Q_none; 202 break; 203 204 case Q_one: /* Quote this ' */ 205 tok->quote = Q_none; 206 *tok->wptr++ = *ptr; 207 break; 208 209 case Q_double: /* Stay in double quote mode */ 210 *tok->wptr++ = *ptr; 211 break; 212 213 case Q_doubleone: /* Quote this ' */ 214 tok->quote = Q_double; 215 *tok->wptr++ = *ptr; 216 break; 217 218 default: 219 return (-1); 220 } 221 break; 222 223 case '"': 224 tok->flags &= ~TOK_EAT; 225 tok->flags |= TOK_KEEP; 226 switch (tok->quote) { 227 case Q_none: /* Enter double quote mode */ 228 tok->quote = Q_double; 229 break; 230 231 case Q_double: /* Exit double quote mode */ 232 tok->quote = Q_none; 233 break; 234 235 case Q_one: /* Quote this " */ 236 tok->quote = Q_none; 237 *tok->wptr++ = *ptr; 238 break; 239 240 case Q_single: /* Stay in single quote mode */ 241 *tok->wptr++ = *ptr; 242 break; 243 244 case Q_doubleone: /* Quote this " */ 245 tok->quote = Q_double; 246 *tok->wptr++ = *ptr; 247 break; 248 249 default: 250 return (-1); 251 } 252 break; 253 254 case '\\': 255 tok->flags |= TOK_KEEP; 256 tok->flags &= ~TOK_EAT; 257 switch (tok->quote) { 258 case Q_none: /* Quote next character */ 259 tok->quote = Q_one; 260 break; 261 262 case Q_double: /* Quote next character */ 263 tok->quote = Q_doubleone; 264 break; 265 266 case Q_one: /* Quote this, restore state */ 267 *tok->wptr++ = *ptr; 268 tok->quote = Q_none; 269 break; 270 271 case Q_single: /* Stay in single quote mode */ 272 *tok->wptr++ = *ptr; 273 break; 274 275 case Q_doubleone: /* Quote this \ */ 276 tok->quote = Q_double; 277 *tok->wptr++ = *ptr; 278 break; 279 280 default: 281 return (-1); 282 } 283 break; 284 285 case '\n': 286 tok->flags &= ~TOK_EAT; 287 switch (tok->quote) { 288 case Q_none: 289 tok_finish(tok); 290 *argv = (const char **)tok->argv; 291 *argc = tok->argc; 292 return (0); 293 294 case Q_single: 295 case Q_double: 296 *tok->wptr++ = *ptr; /* Add the return */ 297 break; 298 299 case Q_doubleone: /* Back to double, eat the '\n' */ 300 tok->flags |= TOK_EAT; 301 tok->quote = Q_double; 302 break; 303 304 case Q_one: /* No quote, more eat the '\n' */ 305 tok->flags |= TOK_EAT; 306 tok->quote = Q_none; 307 break; 308 309 default: 310 return (0); 311 } 312 break; 313 314 case '\0': 315 switch (tok->quote) { 316 case Q_none: 317 /* Finish word and return */ 318 if (tok->flags & TOK_EAT) { 319 tok->flags &= ~TOK_EAT; 320 return (3); 321 } 322 tok_finish(tok); 323 *argv = (const char **)tok->argv; 324 *argc = tok->argc; 325 return (0); 326 327 case Q_single: 328 return (1); 329 330 case Q_double: 331 return (2); 332 333 case Q_doubleone: 334 tok->quote = Q_double; 335 *tok->wptr++ = *ptr; 336 break; 337 338 case Q_one: 339 tok->quote = Q_none; 340 *tok->wptr++ = *ptr; 341 break; 342 343 default: 344 return (-1); 345 } 346 break; 347 348 default: 349 tok->flags &= ~TOK_EAT; 350 switch (tok->quote) { 351 case Q_none: 352 if (strchr(tok->ifs, *ptr) != NULL) 353 tok_finish(tok); 354 else 355 *tok->wptr++ = *ptr; 356 break; 357 358 case Q_single: 359 case Q_double: 360 *tok->wptr++ = *ptr; 361 break; 362 363 364 case Q_doubleone: 365 *tok->wptr++ = '\\'; 366 tok->quote = Q_double; 367 *tok->wptr++ = *ptr; 368 break; 369 370 case Q_one: 371 tok->quote = Q_none; 372 *tok->wptr++ = *ptr; 373 break; 374 375 default: 376 return (-1); 377 378 } 379 break; 380 } 381 382 if (tok->wptr >= tok->wmax - 4) { 383 size_t size = tok->wmax - tok->wspace + WINCR; 384 char *s = (char *) tok_realloc(tok->wspace, size); 385 if (s == NULL) 386 return (-1); 387 388 if (s != tok->wspace) { 389 int i; 390 for (i = 0; i < tok->argc; i++) { 391 tok->argv[i] = 392 (tok->argv[i] - tok->wspace) + s; 393 } 394 tok->wptr = (tok->wptr - tok->wspace) + s; 395 tok->wstart = (tok->wstart - tok->wspace) + s; 396 tok->wspace = s; 397 } 398 tok->wmax = s + size; 399 } 400 if (tok->argc >= tok->amax - 4) { 401 char **p; 402 tok->amax += AINCR; 403 p = (char **) tok_realloc(tok->argv, 404 tok->amax * sizeof(char *)); 405 if (p == NULL) 406 return (-1); 407 tok->argv = p; 408 } 409 } 410 } 411
Indexes created Mon Sep 22 05:09:51 GMT 2025