1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460
|
/* parseconf.c - state machine-driven dynamic configuration file parser
Copyright (C) 2002 Russell Kroll <rkroll@exploits.org>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
/* This is the third take on the Network UPS Tools configuration parser.
*
* This time around, the states have been split out into their own
* functions for readability. The old version did some evil tricks
* involving switch(), and was probably quite confusing as a result.
* This one aims for better readability and a flow that makes sense.
*
* Interface:
*
* You now call parseconf("file") and it calls your arghandler function
* with the number of arguments and an array of pointers to them. It
* also calls your errhandler function when an error happens, so there
* should no longer be any NUT dependencies in here. Hopefully this
* will prove useful to other programmers who want to parse things this
* way.
*
* Input vs. Output:
*
* What it reads --> What ends up in each argument
*
* this is a line --> "this" "is" "a" "line"
* this "is also" a line --> "this" "is also" "a" "line"
* embedded\ space --> "embedded space"
* embedded\\backslash --> "embedded\backslash"
*
* Arguments are split by whitespace (isspace()) unless that whitespace
* occurs inside a "quoted pair like this".
*
* You can also escape the double quote (") character. The backslash
* also allows you to join lines, allowing you to have logical lines
* that span physical lines, just like you can do in some shells.
*
* Lines normally end with a newline, but reaching EOF will also force
* parsing on what's been scanned so far.
*
* Design:
*
* Characters are read one at a time to drive the state machine.
* As words are completed (by hitting whitespace or ending a "" item),
* they are committed to the next buffer in the arglist. realloc is
* used, so the buffer can grow to handle bigger words.
*
* The arglist also grows as necessary with a similar approach. As a
* result, you can parse extremely long words and lines with an insane
* number of elements.
*
* Finally, there is argsize, which remembers how long each of the
* arglist elements are. This is how we know when to expand them.
*
* Error handling:
*
* Right now the only non-fatal error involves the case where the user
* drops a # into a quoted block, which is ambiguous. All other errors
* come from memory allocation failures, and parseconf calls exit() once
* control returns from parseconf_error.
*
*/
#include <ctype.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include "parseconf.h"
/* possible states */
#define STATE_FINDWORDSTART 1
#define STATE_FINDEOL 2
#define STATE_QUOTECOLLECT 3
#define STATE_QC_LITERAL 4
#define STATE_COLLECT 5
#define STATE_COLLECTLITERAL 6
static char **arglist;
static int *argsize;
static int numargs, maxargs;
static char *wordbuf, *wordptr;
static int wordbufsize;
static int linenum;
static void (*user_arg)(int numargs, char **arglist);
static void (*user_err)(int linenum, char *errtest);
/* format the error and give it to the caller's error handler */
static void report_error(char *errtext)
{
user_err(linenum, errtext);
}
/* restart with a fresh list (but with the same memory for now) */
static void reset_arg_list(void)
{
numargs = 0;
}
static void add_arg_word(char *val)
{
int argpos;
/* this is where the new value goes */
argpos = numargs;
numargs++;
/* when facing more args than ever before, expand the list */
if (numargs > maxargs) {
maxargs = numargs;
/* resize the lists */
arglist = realloc(arglist, sizeof(char *) * numargs);
if (!arglist) {
report_error("realloc arglist failed");
exit(1);
}
argsize = realloc(argsize, sizeof(int *) * numargs);
if (!argsize) {
report_error("realloc argsize failed");
exit(1);
}
/* ensure sane starting values */
arglist[argpos] = NULL;
argsize[argpos] = 0;
}
/* now see if the string itself grew compared to last time */
if (strlen(val) >= argsize[argpos]) {
int newlen;
/* allow for the trailing NULL */
newlen = strlen(val) + 1;
/* expand the string storage */
arglist[argpos] = realloc(arglist[argpos], newlen);
if (!arglist[argpos]) {
report_error("realloc arglist member failed");
exit(1);
}
/* remember the new size */
argsize[argpos] = newlen;
}
/* strncpy doesn't give us a trailing NULL, so prep the space */
memset(arglist[argpos], '\0', argsize[argpos]);
/* finally copy the new value into the provided space */
strncpy(arglist[argpos], val, strlen(val));
}
static void addchar(char ch)
{
/* allow for the null */
if (strlen(wordbuf) >= (wordbufsize - 1)) {
wordbufsize++;
wordbuf = realloc(wordbuf, wordbufsize);
if (!wordbuf) {
report_error("realloc wordbuf failed");
exit(1);
}
/* repoint as wordbuf may have moved */
wordptr = &wordbuf[strlen(wordbuf)];
}
*wordptr++ = ch;
*wordptr = '\0';
}
static void endofword(void)
{
add_arg_word(wordbuf);
wordptr = wordbuf;
*wordptr = '\0';
}
static void endofline(void)
{
linenum++;
/* only call back if there's something to do */
if ((numargs != 0) && (arglist)) {
/* send the data back to the caller */
user_arg(numargs, arglist);
}
/* start over for the next line */
reset_arg_list();
}
/* look for the beginning of a word */
static int findwordstart(char ch)
{
/* newline = the physical line is over, so the logical one is too */
if (ch == 10) {
endofline();
return STATE_FINDWORDSTART;
}
/* the rest of the line is a comment */
if (ch == '#')
return STATE_FINDEOL;
/* space = not in a word yet, so loop back */
if (isspace(ch))
return STATE_FINDWORDSTART;
/* \ = literal = accept the next char blindly */
if (ch == '\\')
return STATE_COLLECTLITERAL;
/* " = begin word bounded by quotes */
if (ch == '"')
return STATE_QUOTECOLLECT;
/* at this point the word just started */
addchar(ch);
return STATE_COLLECT;
}
/* eat characters until the end of the line is found */
static int findeol(char ch)
{
/* newline = found it, so start a new line */
if (ch == 10) {
endofline();
return STATE_FINDWORDSTART;
}
/* come back here */
return STATE_FINDEOL;
}
/* quote characters inside a word bounded by "quotes" */
static int quotecollect(char ch)
{
/* user is trying to break us */
if (ch == '#') {
report_error("Unbalanced word due to unescaped # in quotes");
endofword();
return STATE_FINDEOL;
}
/* another " means we're done with this word */
if (ch == '"') {
endofword();
return STATE_FINDWORDSTART;
}
/* literal - special case since it needs to return here */
if (ch == '\\')
return STATE_QC_LITERAL;
/* otherwise save it and loop back */
addchar(ch);
return STATE_QUOTECOLLECT;
}
/* take almost anything literally, but return to quotecollect */
static int qc_literal(char ch)
{
/* continue onto the next line of the file */
if (ch == 10)
return STATE_QUOTECOLLECT;
addchar(ch);
return STATE_QUOTECOLLECT;
}
/* collect characters inside a word */
static int collect(char ch)
{
/* comment means the word is done, and skip to the end of the line */
if (ch == '#') {
endofword();
return STATE_FINDEOL;
}
/* newline means the word is done, and the line is done */
if (ch == 10) {
endofword();
endofline();
return STATE_FINDWORDSTART;
}
/* space means the word is done */
if (isspace(ch)) {
endofword();
return STATE_FINDWORDSTART;
}
/* \ = literal = accept the next char blindly */
if (ch == '\\')
return STATE_COLLECTLITERAL;
/* otherwise store it and come back for more */
addchar(ch);
return STATE_COLLECT;
}
/* take almost anything literally */
static int collectliteral(char ch)
{
/* continue to the next line */
if (ch == 10)
return STATE_COLLECT;
addchar(ch);
return STATE_COLLECT;
}
/* clean up memory before going back to the user */
static void free_storage(void)
{
int i;
if (wordbuf)
free(wordbuf);
/* clear out the individual words first */
for (i = 0; i < maxargs; i++)
free(arglist[i]);
if (arglist)
free(arglist);
if (argsize)
free(argsize);
/* put things back to the initial state */
arglist = NULL;
argsize = NULL;
numargs = 0;
maxargs = 0;
}
int parseconf(char *fn, void *arghandler, void *errhandler)
{
FILE *f;
int state, ch;
/* initialize things */
numargs = 0;
maxargs = 0;
linenum = 0;
arglist = NULL;
argsize = NULL;
wordbufsize = 16;
user_arg = arghandler;
user_err = errhandler;
wordbuf = malloc(wordbufsize);
memset(wordbuf, '\0', wordbufsize);
if (!wordbuf) {
report_error("malloc wordbuf failed");
exit(1);
}
/* points at current word - advances with each character */
wordptr = wordbuf;
f = fopen(fn, "r");
if (!f) {
report_error("Can't open configuration file");
return -1; /* failed */
}
linenum = 1;
state = STATE_FINDWORDSTART;
reset_arg_list();
while ((ch = fgetc(f)) != EOF) {
switch(state) {
case STATE_FINDWORDSTART:
state = findwordstart(ch);
break;
case STATE_FINDEOL:
state = findeol(ch);
break;
case STATE_QUOTECOLLECT:
state = quotecollect(ch);
break;
case STATE_QC_LITERAL:
state = qc_literal(ch);
break;
case STATE_COLLECT:
state = collect(ch);
break;
case STATE_COLLECTLITERAL:
state = collectliteral(ch);
break;
} /* switch */
} /* while fgetc */
fclose(f);
/* deal with a file that didn't end with a newline */
if (wordptr != wordbuf) {
endofword();
endofline();
}
/* clean up memory */
free_storage();
return 0; /* OK */
}
|