tokenizer.c revision 148814
1/*- 2 * Copyright (c) 1992, 1993 3 * The Regents of the University of California. All rights reserved. 4 * 5 * This code is derived from software contributed to Berkeley by 6 * Christos Zoulas of Cornell University. 7 * 8 * Redistribution and use in source and binary forms, with or without 9 * modification, are permitted provided that the following conditions 10 * are met: 11 * 1. Redistributions of source code must retain the above copyright 12 * notice, this list of conditions and the following disclaimer. 13 * 2. Redistributions in binary form must reproduce the above copyright 14 * notice, this list of conditions and the following disclaimer in the 15 * documentation and/or other materials provided with the distribution. 16 * 3. All advertising materials mentioning features or use of this software 17 * must display the following acknowledgement: 18 * This product includes software developed by the University of 19 * California, Berkeley and its contributors. 20 * 4. Neither the name of the University nor the names of its contributors 21 * may be used to endorse or promote products derived from this software 22 * without specific prior written permission. 23 * 24 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 27 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 34 * SUCH DAMAGE. 35 * 36 * $NetBSD: tokenizer.c,v 1.6 2000/09/04 22:06:33 lukem Exp $ 37 */ 38 39#if !defined(lint) && !defined(SCCSID) 40static char sccsid[] = "@(#)tokenizer.c 8.1 (Berkeley) 6/4/93"; 41#endif /* not lint && not SCCSID */ 42#include <sys/cdefs.h> 43__FBSDID("$FreeBSD: head/lib/libedit/tokenizer.c 148814 2005-08-07 08:35:39Z stefanf $"); 44 45/* 46 * tokenize.c: Bourne shell like tokenizer 47 */ 48#include "sys.h" 49#include <string.h> 50#include <stdlib.h> 51#include "tokenizer.h" 52 53typedef enum { 54 Q_none, Q_single, Q_double, Q_one, Q_doubleone 55} quote_t; 56 57#define IFS "\t \n" 58 59#define TOK_KEEP 1 60#define TOK_EAT 2 61 62#define WINCR 20 63#define AINCR 10 64 65#define tok_malloc(a) malloc(a) 66#define tok_free(a) free(a) 67#define tok_realloc(a, b) realloc(a, b) 68 69 70struct tokenizer { 71 char *ifs; /* In field separator */ 72 int argc, amax; /* Current and maximum number of args */ 73 char **argv; /* Argument list */ 74 char *wptr, *wmax; /* Space and limit on the word buffer */ 75 char *wstart; /* Beginning of next word */ 76 char *wspace; /* Space of word buffer */ 77 quote_t quote; /* Quoting state */ 78 int flags; /* flags; */ 79}; 80 81 82private void tok_finish(Tokenizer *); 83 84 85/* tok_finish(): 86 * Finish a word in the tokenizer. 87 */ 88private void 89tok_finish(Tokenizer *tok) 90{ 91 92 *tok->wptr = '\0'; 93 if ((tok->flags & TOK_KEEP) || tok->wptr != tok->wstart) { 94 tok->argv[tok->argc++] = tok->wstart; 95 tok->argv[tok->argc] = NULL; 96 tok->wstart = ++tok->wptr; 97 } 98 tok->flags &= ~TOK_KEEP; 99} 100 101 102/* tok_init(): 103 * Initialize the tokenizer 104 */ 105public Tokenizer * 106tok_init(const char *ifs) 107{ 108 Tokenizer *tok = (Tokenizer *) tok_malloc(sizeof(Tokenizer)); 109 110 tok->ifs = strdup(ifs ? ifs : IFS); 111 tok->argc = 0; 112 tok->amax = AINCR; 113 tok->argv = (char **) tok_malloc(sizeof(char *) * tok->amax); 114 if (tok->argv == NULL) 115 return (NULL); 116 tok->argv[0] = NULL; 117 tok->wspace = (char *) tok_malloc(WINCR); 118 if (tok->wspace == NULL) 119 return (NULL); 120 tok->wmax = tok->wspace + WINCR; 121 tok->wstart = tok->wspace; 122 tok->wptr = tok->wspace; 123 tok->flags = 0; 124 tok->quote = Q_none; 125 126 return (tok); 127} 128 129 130/* tok_reset(): 131 * Reset the tokenizer 132 */ 133public void 134tok_reset(Tokenizer *tok) 135{ 136 137 tok->argc = 0; 138 tok->wstart = tok->wspace; 139 tok->wptr = tok->wspace; 140 tok->flags = 0; 141 tok->quote = Q_none; 142} 143 144 145/* tok_end(): 146 * Clean up 147 */ 148public void 149tok_end(Tokenizer *tok) 150{ 151 152 tok_free((ptr_t) tok->ifs); 153 tok_free((ptr_t) tok->wspace); 154 tok_free((ptr_t) tok->argv); 155 tok_free((ptr_t) tok); 156} 157 158 159 160/* tok_line(): 161 * Bourne shell like tokenizing 162 * Return: 163 * -1: Internal error 164 * 3: Quoted return 165 * 2: Unmatched double quote 166 * 1: Unmatched single quote 167 * 0: Ok 168 */ 169public int 170tok_line(Tokenizer *tok, const char *line, int *argc, char ***argv) 171{ 172 const char *ptr; 173 174 for (;;) { 175 switch (*(ptr = line++)) { 176 case '\'': 177 tok->flags |= TOK_KEEP; 178 tok->flags &= ~TOK_EAT; 179 switch (tok->quote) { 180 case Q_none: 181 tok->quote = Q_single; /* Enter single quote 182 * mode */ 183 break; 184 185 case Q_single: /* Exit single quote mode */ 186 tok->quote = Q_none; 187 break; 188 189 case Q_one: /* Quote this ' */ 190 tok->quote = Q_none; 191 *tok->wptr++ = *ptr; 192 break; 193 194 case Q_double: /* Stay in double quote mode */ 195 *tok->wptr++ = *ptr; 196 break; 197 198 case Q_doubleone: /* Quote this ' */ 199 tok->quote = Q_double; 200 *tok->wptr++ = *ptr; 201 break; 202 203 default: 204 return (-1); 205 } 206 break; 207 208 case '"': 209 tok->flags &= ~TOK_EAT; 210 tok->flags |= TOK_KEEP; 211 switch (tok->quote) { 212 case Q_none: /* Enter double quote mode */ 213 tok->quote = Q_double; 214 break; 215 216 case Q_double: /* Exit double quote mode */ 217 tok->quote = Q_none; 218 break; 219 220 case Q_one: /* Quote this " */ 221 tok->quote = Q_none; 222 *tok->wptr++ = *ptr; 223 break; 224 225 case Q_single: /* Stay in single quote mode */ 226 *tok->wptr++ = *ptr; 227 break; 228 229 case Q_doubleone: /* Quote this " */ 230 tok->quote = Q_double; 231 *tok->wptr++ = *ptr; 232 break; 233 234 default: 235 return (-1); 236 } 237 break; 238 239 case '\\': 240 tok->flags |= TOK_KEEP; 241 tok->flags &= ~TOK_EAT; 242 switch (tok->quote) { 243 case Q_none: /* Quote next character */ 244 tok->quote = Q_one; 245 break; 246 247 case Q_double: /* Quote next character */ 248 tok->quote = Q_doubleone; 249 break; 250 251 case Q_one: /* Quote this, restore state */ 252 *tok->wptr++ = *ptr; 253 tok->quote = Q_none; 254 break; 255 256 case Q_single: /* Stay in single quote mode */ 257 *tok->wptr++ = *ptr; 258 break; 259 260 case Q_doubleone: /* Quote this \ */ 261 tok->quote = Q_double; 262 *tok->wptr++ = *ptr; 263 break; 264 265 default: 266 return (-1); 267 } 268 break; 269 270 case '\n': 271 tok->flags &= ~TOK_EAT; 272 switch (tok->quote) { 273 case Q_none: 274 tok_finish(tok); 275 *argv = tok->argv; 276 *argc = tok->argc; 277 return (0); 278 279 case Q_single: 280 case Q_double: 281 *tok->wptr++ = *ptr; /* Add the return */ 282 break; 283 284 case Q_doubleone: /* Back to double, eat the '\n' */ 285 tok->flags |= TOK_EAT; 286 tok->quote = Q_double; 287 break; 288 289 case Q_one: /* No quote, more eat the '\n' */ 290 tok->flags |= TOK_EAT; 291 tok->quote = Q_none; 292 break; 293 294 default: 295 return (0); 296 } 297 break; 298 299 case '\0': 300 switch (tok->quote) { 301 case Q_none: 302 /* Finish word and return */ 303 if (tok->flags & TOK_EAT) { 304 tok->flags &= ~TOK_EAT; 305 return (3); 306 } 307 tok_finish(tok); 308 *argv = tok->argv; 309 *argc = tok->argc; 310 return (0); 311 312 case Q_single: 313 return (1); 314 315 case Q_double: 316 return (2); 317 318 case Q_doubleone: 319 tok->quote = Q_double; 320 *tok->wptr++ = *ptr; 321 break; 322 323 case Q_one: 324 tok->quote = Q_none; 325 *tok->wptr++ = *ptr; 326 break; 327 328 default: 329 return (-1); 330 } 331 break; 332 333 default: 334 tok->flags &= ~TOK_EAT; 335 switch (tok->quote) { 336 case Q_none: 337 if (strchr(tok->ifs, *ptr) != NULL) 338 tok_finish(tok); 339 else 340 *tok->wptr++ = *ptr; 341 break; 342 343 case Q_single: 344 case Q_double: 345 *tok->wptr++ = *ptr; 346 break; 347 348 349 case Q_doubleone: 350 *tok->wptr++ = '\\'; 351 tok->quote = Q_double; 352 *tok->wptr++ = *ptr; 353 break; 354 355 case Q_one: 356 tok->quote = Q_none; 357 *tok->wptr++ = *ptr; 358 break; 359 360 default: 361 return (-1); 362 363 } 364 break; 365 } 366 367 if (tok->wptr >= tok->wmax - 4) { 368 size_t size = tok->wmax - tok->wspace + WINCR; 369 char *s = (char *) tok_realloc(tok->wspace, size); 370 /* SUPPRESS 22 */ 371 int offs = s - tok->wspace; 372 if (s == NULL) 373 return (-1); 374 375 if (offs != 0) { 376 int i; 377 for (i = 0; i < tok->argc; i++) 378 tok->argv[i] = tok->argv[i] + offs; 379 tok->wptr = tok->wptr + offs; 380 tok->wstart = tok->wstart + offs; 381 tok->wmax = s + size; 382 tok->wspace = s; 383 } 384 } 385 if (tok->argc >= tok->amax - 4) { 386 char **p; 387 tok->amax += AINCR; 388 p = (char **) tok_realloc(tok->argv, 389 tok->amax * sizeof(char *)); 390 if (p == NULL) 391 return (-1); 392 tok->argv = p; 393 } 394 } 395} 396