tokenizer.c revision 1.25
1 /* $NetBSD: tokenizer.c,v 1.25 2016/04/11 00:22:48 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. Neither the name of the University nor the names of its contributors 19 * may be used to endorse or promote products derived from this software 20 * without specific prior written permission. 21 * 22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 25 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 32 * SUCH DAMAGE. 33 */ 34 35 #include "config.h" 36 #if !defined(lint) && !defined(SCCSID) 37 #if 0 38 static char sccsid[] = "@(#)tokenizer.c 8.1 (Berkeley) 6/4/93"; 39 #else 40 __RCSID("$NetBSD: tokenizer.c,v 1.25 2016/04/11 00:22:48 christos Exp $"); 41 #endif 42 #endif /* not lint && not SCCSID */ 43 44 /* We build this file twice, once as NARROW, once as WIDE. */ 45 /* 46 * tokenize.c: Bourne shell like tokenizer 47 */ 48 #include <stdlib.h> 49 #include <string.h> 50 51 #include "histedit.h" 52 #include "chartype.h" 53 54 typedef enum { 55 Q_none, Q_single, Q_double, Q_one, Q_doubleone 56 } quote_t; 57 58 #define TOK_KEEP 1 59 #define TOK_EAT 2 60 61 #define WINCR 20 62 #define AINCR 10 63 64 #define IFS STR("\t \n") 65 66 #define tok_malloc(a) malloc(a) 67 #define tok_free(a) free(a) 68 #define tok_realloc(a, b) realloc(a, b) 69 70 #ifdef NARROWCHAR 71 #define FUN(prefix, rest) prefix ## _ ## rest 72 #define TYPE(type) type 73 #define STR(x) x 74 #define Strchr(s, c) strchr(s, c) 75 #define tok_strdup(s) strdup(s) 76 #else 77 #define FUN(prefix, rest) prefix ## _w ## rest 78 #define TYPE(type) type ## W 79 #define STR(x) L ## x 80 #define Strchr(s, c) wcschr(s, c) 81 #define tok_strdup(s) wcsdup(s) 82 #endif 83 84 struct TYPE(tokenizer) { 85 Char *ifs; /* In field separator */ 86 size_t argc, amax; /* Current and maximum number of args */ 87 Char **argv; /* Argument list */ 88 Char *wptr, *wmax; /* Space and limit on the word buffer */ 89 Char *wstart; /* Beginning of next word */ 90 Char *wspace; /* Space of word buffer */ 91 quote_t quote; /* Quoting state */ 92 int flags; /* flags; */ 93 }; 94 95 96 private void FUN(tok,finish)(TYPE(Tokenizer) *); 97 98 99 /* FUN(tok,finish)(): 100 * Finish a word in the tokenizer. 101 */ 102 private void 103 FUN(tok,finish)(TYPE(Tokenizer) *tok) 104 { 105 106 *tok->wptr = '\0'; 107 if ((tok->flags & TOK_KEEP) || tok->wptr != tok->wstart) { 108 tok->argv[tok->argc++] = tok->wstart; 109 tok->argv[tok->argc] = NULL; 110 tok->wstart = ++tok->wptr; 111 } 112 tok->flags &= ~TOK_KEEP; 113 } 114 115 116 /* FUN(tok,init)(): 117 * Initialize the tokenizer 118 */ 119 public TYPE(Tokenizer) * 120 FUN(tok,init)(const Char *ifs) 121 { 122 TYPE(Tokenizer) *tok = tok_malloc(sizeof(*tok)); 123 124 if (tok == NULL) 125 return NULL; 126 tok->ifs = tok_strdup(ifs ? ifs : IFS); 127 if (tok->ifs == NULL) { 128 tok_free(tok); 129 return NULL; 130 } 131 tok->argc = 0; 132 tok->amax = AINCR; 133 tok->argv = tok_malloc(sizeof(*tok->argv) * tok->amax); 134 if (tok->argv == NULL) { 135 tok_free(tok->ifs); 136 tok_free(tok); 137 return NULL; 138 } 139 tok->argv[0] = NULL; 140 tok->wspace = tok_malloc(WINCR * sizeof(*tok->wspace)); 141 if (tok->wspace == NULL) { 142 tok_free(tok->argv); 143 tok_free(tok->ifs); 144 tok_free(tok); 145 return NULL; 146 } 147 tok->wmax = tok->wspace + WINCR; 148 tok->wstart = tok->wspace; 149 tok->wptr = tok->wspace; 150 tok->flags = 0; 151 tok->quote = Q_none; 152 153 return tok; 154 } 155 156 157 /* FUN(tok,reset)(): 158 * Reset the tokenizer 159 */ 160 public void 161 FUN(tok,reset)(TYPE(Tokenizer) *tok) 162 { 163 164 tok->argc = 0; 165 tok->wstart = tok->wspace; 166 tok->wptr = tok->wspace; 167 tok->flags = 0; 168 tok->quote = Q_none; 169 } 170 171 172 /* FUN(tok,end)(): 173 * Clean up 174 */ 175 public void 176 FUN(tok,end)(TYPE(Tokenizer) *tok) 177 { 178 179 tok_free(tok->ifs); 180 tok_free(tok->wspace); 181 tok_free(tok->argv); 182 tok_free(tok); 183 } 184 185 186 187 /* FUN(tok,line)(): 188 * Bourne shell (sh(1)) like tokenizing 189 * Arguments: 190 * tok current tokenizer state (setup with FUN(tok,init)()) 191 * line line to parse 192 * Returns: 193 * -1 Internal error 194 * 3 Quoted return 195 * 2 Unmatched double quote 196 * 1 Unmatched single quote 197 * 0 Ok 198 * Modifies (if return value is 0): 199 * argc number of arguments 200 * argv argument array 201 * cursorc if !NULL, argv element containing cursor 202 * cursorv if !NULL, offset in argv[cursorc] of cursor 203 */ 204 public int 205 FUN(tok,line)(TYPE(Tokenizer) *tok, const TYPE(LineInfo) *line, 206 int *argc, const Char ***argv, int *cursorc, int *cursoro) 207 { 208 const Char *ptr; 209 int cc, co; 210 211 cc = co = -1; 212 ptr = line->buffer; 213 for (ptr = line->buffer; ;ptr++) { 214 if (ptr >= line->lastchar) 215 ptr = STR(""); 216 if (ptr == line->cursor) { 217 cc = (int)tok->argc; 218 co = (int)(tok->wptr - tok->wstart); 219 } 220 switch (*ptr) { 221 case '\'': 222 tok->flags |= TOK_KEEP; 223 tok->flags &= ~TOK_EAT; 224 switch (tok->quote) { 225 case Q_none: 226 tok->quote = Q_single; /* Enter single quote 227 * mode */ 228 break; 229 230 case Q_single: /* Exit single quote mode */ 231 tok->quote = Q_none; 232 break; 233 234 case Q_one: /* Quote this ' */ 235 tok->quote = Q_none; 236 *tok->wptr++ = *ptr; 237 break; 238 239 case Q_double: /* Stay in double quote mode */ 240 *tok->wptr++ = *ptr; 241 break; 242 243 case Q_doubleone: /* Quote this ' */ 244 tok->quote = Q_double; 245 *tok->wptr++ = *ptr; 246 break; 247 248 default: 249 return -1; 250 } 251 break; 252 253 case '"': 254 tok->flags &= ~TOK_EAT; 255 tok->flags |= TOK_KEEP; 256 switch (tok->quote) { 257 case Q_none: /* Enter double quote mode */ 258 tok->quote = Q_double; 259 break; 260 261 case Q_double: /* Exit double quote mode */ 262 tok->quote = Q_none; 263 break; 264 265 case Q_one: /* Quote this " */ 266 tok->quote = Q_none; 267 *tok->wptr++ = *ptr; 268 break; 269 270 case Q_single: /* Stay in single quote mode */ 271 *tok->wptr++ = *ptr; 272 break; 273 274 case Q_doubleone: /* Quote this " */ 275 tok->quote = Q_double; 276 *tok->wptr++ = *ptr; 277 break; 278 279 default: 280 return -1; 281 } 282 break; 283 284 case '\\': 285 tok->flags |= TOK_KEEP; 286 tok->flags &= ~TOK_EAT; 287 switch (tok->quote) { 288 case Q_none: /* Quote next character */ 289 tok->quote = Q_one; 290 break; 291 292 case Q_double: /* Quote next character */ 293 tok->quote = Q_doubleone; 294 break; 295 296 case Q_one: /* Quote this, restore state */ 297 *tok->wptr++ = *ptr; 298 tok->quote = Q_none; 299 break; 300 301 case Q_single: /* Stay in single quote mode */ 302 *tok->wptr++ = *ptr; 303 break; 304 305 case Q_doubleone: /* Quote this \ */ 306 tok->quote = Q_double; 307 *tok->wptr++ = *ptr; 308 break; 309 310 default: 311 return -1; 312 } 313 break; 314 315 case '\n': 316 tok->flags &= ~TOK_EAT; 317 switch (tok->quote) { 318 case Q_none: 319 goto tok_line_outok; 320 321 case Q_single: 322 case Q_double: 323 *tok->wptr++ = *ptr; /* Add the return */ 324 break; 325 326 case Q_doubleone: /* Back to double, eat the '\n' */ 327 tok->flags |= TOK_EAT; 328 tok->quote = Q_double; 329 break; 330 331 case Q_one: /* No quote, more eat the '\n' */ 332 tok->flags |= TOK_EAT; 333 tok->quote = Q_none; 334 break; 335 336 default: 337 return 0; 338 } 339 break; 340 341 case '\0': 342 switch (tok->quote) { 343 case Q_none: 344 /* Finish word and return */ 345 if (tok->flags & TOK_EAT) { 346 tok->flags &= ~TOK_EAT; 347 return 3; 348 } 349 goto tok_line_outok; 350 351 case Q_single: 352 return 1; 353 354 case Q_double: 355 return 2; 356 357 case Q_doubleone: 358 tok->quote = Q_double; 359 *tok->wptr++ = *ptr; 360 break; 361 362 case Q_one: 363 tok->quote = Q_none; 364 *tok->wptr++ = *ptr; 365 break; 366 367 default: 368 return -1; 369 } 370 break; 371 372 default: 373 tok->flags &= ~TOK_EAT; 374 switch (tok->quote) { 375 case Q_none: 376 if (Strchr(tok->ifs, *ptr) != NULL) 377 FUN(tok,finish)(tok); 378 else 379 *tok->wptr++ = *ptr; 380 break; 381 382 case Q_single: 383 case Q_double: 384 *tok->wptr++ = *ptr; 385 break; 386 387 388 case Q_doubleone: 389 *tok->wptr++ = '\\'; 390 tok->quote = Q_double; 391 *tok->wptr++ = *ptr; 392 break; 393 394 case Q_one: 395 tok->quote = Q_none; 396 *tok->wptr++ = *ptr; 397 break; 398 399 default: 400 return -1; 401 402 } 403 break; 404 } 405 406 if (tok->wptr >= tok->wmax - 4) { 407 size_t size = (size_t)(tok->wmax - tok->wspace + WINCR); 408 Char *s = tok_realloc(tok->wspace, 409 size * sizeof(*s)); 410 if (s == NULL) 411 return -1; 412 413 if (s != tok->wspace) { 414 size_t i; 415 for (i = 0; i < tok->argc; i++) { 416 tok->argv[i] = 417 (tok->argv[i] - tok->wspace) + s; 418 } 419 tok->wptr = (tok->wptr - tok->wspace) + s; 420 tok->wstart = (tok->wstart - tok->wspace) + s; 421 tok->wspace = s; 422 } 423 tok->wmax = s + size; 424 } 425 if (tok->argc >= tok->amax - 4) { 426 Char **p; 427 tok->amax += AINCR; 428 p = tok_realloc(tok->argv, tok->amax * sizeof(*p)); 429 if (p == NULL) { 430 tok->amax -= AINCR; 431 return -1; 432 } 433 tok->argv = p; 434 } 435 } 436 tok_line_outok: 437 if (cc == -1 && co == -1) { 438 cc = (int)tok->argc; 439 co = (int)(tok->wptr - tok->wstart); 440 } 441 if (cursorc != NULL) 442 *cursorc = cc; 443 if (cursoro != NULL) 444 *cursoro = co; 445 FUN(tok,finish)(tok); 446 *argv = (const Char **)tok->argv; 447 *argc = (int)tok->argc; 448 return 0; 449 } 450 451 /* FUN(tok,str)(): 452 * Simpler version of tok_line, taking a NUL terminated line 453 * and splitting into words, ignoring cursor state. 454 */ 455 public int 456 FUN(tok,str)(TYPE(Tokenizer) *tok, const Char *line, int *argc, 457 const Char ***argv) 458 { 459 TYPE(LineInfo) li; 460 461 memset(&li, 0, sizeof(li)); 462 li.buffer = line; 463 li.cursor = li.lastchar = Strchr(line, '\0'); 464 return FUN(tok,line)(tok, &li, argc, argv, NULL, NULL); 465 } 466
Indexes created Tue Sep 23 02:09:52 GMT 2025