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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472
|
/*=============================================================================
GNU UnRTF, a command-line program to convert RTF documents to other formats.
Copyright (C) 2000,2001 Zachary Thayer Smith
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 3 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
The author is reachable by electronic mail at tuorfa@yahoo.com.
=============================================================================*/
/*----------------------------------------------------------------------
* Module name: parse
* Author name: Zach Smith
* Create date: 01 Sep 00
* Purpose: Parsing of the RTF file into a structure of Word objects.
*----------------------------------------------------------------------
* Changes:
* 15 Oct 00, tuorfa@yahoo.com: parse.c created with functions taken from word.c
* 15 Oct 00, tuorfa@yahoo.com: backslash before newline is now \par
* 08 Apr 01, tuorfa@yahoo.com: removed limit on word length
* 03 Aug 01, tuorfa@yahoo.com: added input buffering
* 19 Sep 01, tuorfa@yahoo.com: cleaned up read_word()
* 22 Sep 01, tuorfa@yahoo.com: moved word_dump() to word.c
* 22 Sep 01, tuorfa@yahoo.com: added function-level comment blocks
* 08 Sep 03, daved@physiol.usyd.edu.au: type fixes; ANSI C fixes
* 29 Mar 05, daved@physiol.usyd.edu.au: changes requested by ZT Smith
* 16 Dec 07, daved@physiol.usyd.edu.au: updated to GPL v3
*--------------------------------------------------------------------*/
#ifdef LMMS_HAVE_CONFIG_H
#include <config.h>
#endif
#ifdef LMMS_HAVE_STDIO_H
#include <stdio.h>
#endif
#ifdef LMMS_HAVE_STDLIB_H
#include <stdlib.h>
#endif
#ifdef LMMS_HAVE_CTYPE_H
#include <ctype.h>
#endif
#ifdef LMMS_HAVE_STRING_H
#include <string.h>
#endif
#include "defs.h"
#include "parse.h"
#include "ur_malloc.h"
#include "main.h"
#include "error.h"
#include "word.h"
#include "hash.h"
/* local to getchar stuff */
#if 0 /* daved - 0.19.0 */
static int ungot_char=-1;
static int ungot_char2=-1;
static int ungot_char3=-1;
#else
static int ungot_char = -1;
static int ungot_char2 = -1;
static int ungot_char3 = -1;
#endif
/*========================================================================
* Name: my_unget_char
* Purpose: My own unget routine, handling up to 3 ungot characters.
* Args: Character.
* Returns: None.
*=======================================================================*/
static void my_unget_char (int ch)
{
if (ungot_char>=0 && ungot_char2>=0 && ungot_char3>=0)
error_handler("More than 3 ungot chars");
ungot_char3 = ungot_char2;
ungot_char2 = ungot_char;
ungot_char = ch;
}
static int last_returned_ch=0;
#define READ_BUF_LEN 2048
static int buffer_size = 0;
static char *read_buf = NULL;
static int read_buf_end = 0;
static int read_buf_index = 0;
/*========================================================================
* Name: my_getchar
* Purpose: Gets a character: either an ungot one, or a buffered one.
* Args: Input file.
* Returns: Character, or EOF.
*=======================================================================*/
static int my_getchar (QBuffer* f)
{
int ch;
CHECK_PARAM_NOT_NULL(f, "parse.c");
if (ungot_char>=0) {
ch = ungot_char;
#if 0 /* daved - 0.19.0 */
ungot_char=ungot_char2;
ungot_char2=ungot_char3;
ungot_char3=-1;
#else
ungot_char = ungot_char2;
ungot_char2 = ungot_char3;
ungot_char3 = -1;
#endif
last_returned_ch = ch;
if(ch > 255)
{
fprintf(stderr, "returning bad ch = '%c' (0%o)\n",
ch, ch);
}
return ch;
}
do {
if (read_buf_index >= read_buf_end) {
if (!read_buf) {
buffer_size = READ_BUF_LEN;
read_buf = my_malloc (buffer_size);
if (!read_buf) {
buffer_size /= 4;
read_buf = my_malloc (buffer_size);
if (!read_buf)
error_handler("Cannot allocate read buffer");
}
}
read_buf_end = f->read(read_buf, buffer_size);
read_buf_index = 0;
if (!read_buf_end)
return EOF;
}
ch = read_buf [read_buf_index++];
if (ch=='\n') {
lineno++;
/* Convert \(newline) into \par here */
if (last_returned_ch=='\\') {
my_unget_char (' ');
my_unget_char ('r');
my_unget_char ('a');
ch = 'p';
break;
}
}
}
while (ch=='\r' /* || ch=='\n' */ );
if (ch=='\t') ch = ' ';
last_returned_ch = ch;
if(ch > 255)
{
fprintf(stderr,"returning bad ch '%c' (0%o)\n", ch, ch);
exit(1);
}
return ch;
}
/* local to read_word */
static char *input_str = NULL;
static unsigned long current_max_length = 1;
/*========================================================================
* Name: expand_word_buffer
* Purpose: Expands the buffer used to store an incoming word.
* This allows us to remove the limit on word length.
* Args: None.
* Returns: None.
*=======================================================================*/
static int
expand_word_buffer ()
{
char *new_ptr;
unsigned long old_length;
if (!input_str)
error_handler("No input buffer allocated");
old_length = current_max_length;
current_max_length *= 2;
new_ptr = my_malloc (current_max_length);
if (!new_ptr)
error_handler("Out of memory while resizing buffer");
memcpy (new_ptr, input_str, old_length);
my_free(input_str);
input_str = new_ptr;
return true;
}
/*========================================================================
* Name: read_word
* Purpose: The core of the parser, this reads a word.
* Args: Input file.
* Returns: Number of characters in the word, or zero.
* Note: The word buffer is static and local to this file.
*=======================================================================*/
static int
read_word (QBuffer*f)
{
#if 0 /* daved - 0.19.0 */
int ch, ch2, ix=0;
#else
int ch, ch2;
unsigned long ix=0;
#endif
int have_whitespace=false;
int is_control_word=false;
int has_numeric_param=false; /* if is_control_word==true */
int need_unget=false;
CHECK_PARAM_NOT_NULL(f, "parse.c");
current_max_length = 10; /* XX */
/* Get some storage for a word.
*/
input_str = my_malloc (current_max_length);
if (!input_str)
error_handler("Cannot allocate word storage");
do {
ch = my_getchar(f);
}
while (ch=='\n');
if (ch==' ')
{
/* Compress multiple space chars down to one.
*/
while (ch == ' ') {
ch = my_getchar(f);
have_whitespace=true;
}
if (have_whitespace) {
my_unget_char (ch);
input_str[0]=' ';
input_str[1]=0;
return 1;
}
}
switch(ch)
{
case EOF:
return 0;
case '\\':
ch2 = my_getchar(f);
/* Look for two-character command words.
*/
switch (ch2)
{
case '\n':
strcpy (input_str, "\\par");
return 4;
case '~':
case '{':
case '}':
case '\\':
case '_':
case '-':
input_str[0] = '\\';
input_str[1] = ch2;
input_str[2] = 0;
return 2;
case '\'':
/* Preserve \'## expressions (hex char exprs) for later.
*/
input_str[0]='\\';
input_str[1]='\'';
ix=2;
if(ix==current_max_length) {
if (!expand_word_buffer ())
error_handler("Word too long");
}
ch = my_getchar(f);
input_str[ix++]=ch;
if(ix==current_max_length) {
if (!expand_word_buffer ())
error_handler("Word too long");
}
ch = my_getchar(f);
input_str[ix++]=ch;
if(ix==current_max_length) {
if (!expand_word_buffer ())
error_handler("Word too long");
}
input_str[ix]=0;
return ix;
}
is_control_word=true;
ix=1;
input_str[0]=ch;
ch=ch2;
break;
case '\t':
/* In RTF, a tab char is the same as \tab.
*/
strcpy (input_str, "\\tab");
return 4;
case '{':
case '}':
case ';':
input_str[0]=ch;
input_str[1]=0;
return 1;
}
while (ch!=EOF)
{
/* Several chars always ends a word, and we need to save them.
*/
if (ch=='\t' || ch=='{' || ch=='}' || ch=='\\') {
need_unget=true;
break;
}
/* A newline always ends a command word; we don't save it.
* A newline is ignored if this is not a command word.
*/
if (ch=='\n') {
if (is_control_word)
break;
ch = my_getchar(f);
continue;
}
/* A semicolon always ends a command word; we do save it.
* A semicolon never ends a regular word.
*/
if (ch==';') {
if (is_control_word) {
need_unget=true;
break;
}
}
/* In this parser, a space character terminates
* any word, and if it does not follow a command,
* then it is a word in itself.
*/
if (ch==' ') {
if (!is_control_word)
need_unget=true;
break;
}
/* Identify a control word's numeric parameter.
*/
if (is_control_word) {
if (!has_numeric_param && (isdigit(ch) || ch=='-'))
has_numeric_param = true;
else
if (has_numeric_param && !isdigit(ch)) {
if (ch!=' ')
need_unget=true;
break;
}
}
input_str[ix++] = ch;
if (ix==current_max_length) {
if (!expand_word_buffer ())
error_handler("Word too long");
}
ch = my_getchar (f);
}
if (need_unget)
my_unget_char(ch);
input_str[ix]=0;
return ix;
}
/*========================================================================
* Name: word_read
* Purpose: This is the recursive metareader which pieces together the
* structure of Word objects.
* Args: Input file.
* Returns: Tree of Word objects.
*=======================================================================*/
Word *
word_read (QBuffer* f) {
Word * prev_word = NULL;
Word * first_word = NULL;
Word * new_word = NULL; /* temp */
CHECK_PARAM_NOT_NULL(f, "parse.c");
do {
if (!read_word(f))
return first_word;
if (input_str[0] == '{') {
/* Process subwords */
/* Create a dummy word to point to a sublist */
new_word = word_new(NULL);
if (!new_word)
error_handler("Cannot allocate word");
/* Get the sublist */
new_word->child = word_read(f);
} else if (input_str[0] == '}') {
return first_word;
} else {
new_word = word_new(input_str);
}
if (prev_word)
prev_word->next = new_word;
if (!first_word)
first_word = new_word;
prev_word = new_word;
/* Free up the memory allocated by read_word. */
my_free(input_str);
input_str = NULL;
} while (1);
}
|