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
|
/* -*- c -*- */
/* Butchered version of html2html.l to post-process RTF files
*
* Steve Tynor (tynor@atlanta.twr.com). I'm not proud of this code. It's a hack
* foisted upon a hack, nested within another hack or two. It sort of works
* well enough for my purposes (generating WinHelp .RTF files for my documents),
* but it could definitely use a redesign/rewrite. I shamelessly blame the RTF
* format for most of the hackery here -- RTF is not a _language_ like LaTeX or
* ROFF -- it's just a file format. So, we can't rely on RTF to do even simple
* things like "insert a paragraph break here only if the previous token was not
* also a paragraph break. Since the SGML front end has no conditional processing
* capabilities, multiple blank likes in the SGML get translated to multiple para
* breaks in the RTF (actually, that's why I use the <@@par> crap....).
*
* XREF: BROKEN_DELIMITERS: We say "{}K{\footnote .." instead of just
* "\nK{\footnote .." since the MicroS$ft RTF parser does not (always?) treat
* white space as a delimeter before a hyperlink markup.
*
* ESR reordered the @@indent rules to eliminate a generation-time warning.
*/
%{
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
/* #define DEBUG */
/* NOTE: must be kept in sync with the <p></p> defs in mapping */
#define LEFTMARGIN 500
#define NEWPAR "\\par\\pard\\plain\\li500\\sb200\\fi0"
#define INDENT_AMT 500 /* twips for each level of indentation */
const static char* header =
"{\\rtf1\\ansi\n"
"{\\fonttbl\n"
"{\\f0\\fswiss Helvetica;}\n"
"{\\f1\\fmodern Courier;}\n"
"{\\f2\\froman Times;}\n"
"{\\f3\\froman Symbol;}\n"
"}\n"
"{\\info{\\comment Translated from SGML to RTF w/ Linuxdoc-SGML}}\n"
;
int big_page_mode = 1; /* default is backwards compatible */
/* <report> style uses <chapt> as the top-level section; <article> uses
<sect>. We need to know whether a <sect> should be numbered as "n"
or "n.m". We assume <article> more unless we see a <chapt> */
int chapter_mode = 0;
int section_id = 0; /* used for TOC hyperlinks */
int in_appendix = 0;
FILE *out;
FILE *idx_fp;
char buf[2048], sectname[256], labeltxt[256];
char firstname[256], outname[262];
char ssectname[256], Tmp1[4096], Tmp2[256], headname[256];
char urlname[256], Headbuf[4096], refname[256];
int indent = 0;
int nofill = 0;
int filenum = 1;
int filecount = 1;
int tmpfn;
int secnr = 0;
int ssecnr;
int current;
int skipnewline = 0;
extern char *yytext;
#if (YY_FLEX_MAJOR_VERSION == 2 && YY_FLEX_MINOR_VERSION == 5 && YY_FLEX_SUBMINOR_VERSION > 35) \
|| (YY_FLEX_MAJOR_VERSION == 2 && YY_FLEX_MINOR_VERSION == 6 && YY_FLEX_SUBMINOR_VERSION == 0)
extern yy_size_t yyleng;
#else
extern int yyleng;
#endif
#define CHAPTER 1
#define SECTION 2
#define SUBSECT 3
void fatal_perror ( char *fmt, char *arg )
{
fprintf( stderr, "rtf2rtf: Fatal: " );
fprintf( stderr, fmt, arg);
perror( "\nReason");
exit(1);
}
int getstr( char *str, int n )
{
#ifdef DEBUG
fprintf( stderr, "DEBUG: yytext: <<%s>>\n", yytext );
#endif
if( strlen( yytext ) == n )
return 0;
strncpy( str, yytext+n, yyleng-n);
str[ yyleng-n ] = 0;
return 1;
}
void
put_reference (FILE *fp, char *str)
{
char *p;
char buf[2] = {0, 0};
/* trim trailing spaces: */
while (str[strlen(str)-1] == ' ') {
str[strlen(str)-1] = '\0';
}
/* replace non-legal topic-id characters with underscores */
p = str;
while (*p) {
buf[0] = *p;
if (! strpbrk(buf,
"abcdegfhijklmnopqrstuvwxyz"
"ABCDEGFHIJKLMNOPQRSTUVWXYZ"
"0123456789")) {
fprintf (fp, "_");
} else {
fprintf (fp, "%c", *p);
}
p++;
}
}
void
put_secnum (FILE *fp, int s1, int s2)
{
if (in_appendix) {
if (s2 == 0) {
fprintf (fp, "%c", 'A'-1+s1);
} else {
fprintf (fp, "%c.%d", 'A'-1+s1, s2);
}
} else {
if (s2 == 0) {
fprintf (fp, "%d", s1);
} else {
fprintf (fp, "%d.%d", s1, s2);
}
}
}
void
heading (char *str, int s1, int s2, int newpage)
{
if (newpage && (out == stdout))
{
sprintf (outname, "%s-0.rtf", firstname);
out = fopen (outname, "w");
if (! out )
{
fatal_perror ("Could not open file \"%s\"", outname);
}
fputs (header, out);
}
/* fprintf (out, "\n\\page{\\pard\\plain\\s2\\f0\\fs%d\\b\\fi0\\li576\\sb160\\sa160\\tx576 { }",
(s2==0 ? 36 : 24) ); */
if (newpage)
{
fprintf (out, "\n\\page{\\pard\\plain\\keepn\\f0\\fs%d\\b\\tx576{",
(s2==0 ? 36 : 24) );
}
else
{
fprintf (out, "\n{\\pard\\sb200\\plain\\f0\\fs%d\\b\\tx576{",
(s2==0 ? 36 : 24) );
}
put_secnum (out, s1, s2);
fprintf (out, " %s}}", str);
/* Used as a target for the link on the TOC page. Use a SECT_ prefix
just in case the document has any explicit <label>'s with the same
`id' as a section header */
/* XREF: BROKEN_DELIMITERS: See above for why we say "{}#{\footnote .."
* instead of just "\n#{\footnote ..".
*/
fprintf (out, "\n{}#{\\footnote TOC_%d}\n", section_id);
if (newpage)
{
fprintf (out, "\n${\\footnote ");
put_reference (out, str);
fprintf (out, "}\n");
fprintf (out, "+{\\footnote browse}\n");
fprintf (out, "%s\n", NEWPAR);
}
/* XREF: BROKEN_DELIMITERS: See above for why we say "{}K{\footnote .."
* instead of just "\nK{\footnote ..".
*/
fprintf (out, "{}K{\\footnote %s}\n", str);
/* fprintf (out, "\\par\\pard\n");*/
fprintf (idx_fp, "\\li%d\\fi-200{\\f3\\\'B7} ",
(s2==0 ? 1 : 2) * 500);
put_secnum (idx_fp, s1, s2);
fprintf (idx_fp, " {\\uldb ");
fprintf (idx_fp, "%s}{\\v TOC_%d}\\par\n", str, section_id);
section_id++;
}
void
subheading (char *str, int chapter_size)
{
/* fprintf (fp, "\n{\\pard\\plain\\s2\\f0\\fs%d\\b \\fi0\\li576\\sb160\\sa160\\tx576 { }%s}\n",
(chapter_size ? 36 : 24), str);*/
fprintf (out, "\n{\\pard\\plain\\f0\\sb200\\fs%d\\b\\tx576{%s}}\n",
(chapter_size ? 36 : 24), str);
/* XREF: BROKEN_DELIMITERS: See above for why we say "{}K{\footnote .."
* instead of just "\nK{\footnote ..".
*/
fprintf (out, "{}K{\\footnote %s}%s\n", str, NEWPAR);
}
%}
%s SECT
%%
"<@@indent+>\n" { indent++; }
"<@@indent->\n" { indent--; }
"<@@indent>\n" { fprintf( out, "\\li%d{}", LEFTMARGIN+indent*INDENT_AMT); }
(\\par\\pard\\plain\n"<@@indent>"\n\\sb200\\fi0\n)+ {
/* HACK: Filter out redundant paragraph marks. I'd rather not put them
* in in the first place, but it's just TOO HARD.
*/
fprintf (out, "\\par\\pard\\plain\n\\li%d{}\n\\sb200\\fi0\n",
LEFTMARGIN+indent*INDENT_AMT);
}
(("<@@par>"\n)|("<@@indent"[\+\-]">"\n))+ {
/* Unfortunately, <@@par>'s and <@@indent+>'s get mixed together at the start
* of <itemize>'s and <descrip>'s. This hack allows us to treat them as a
* single <@@par>.
*
* Adjust the indentation based on the number of <@@indent+/->'s we see
*/
char *p = yytext;
while (*p) {
if (*p == '+') {
indent++;
} else if (*p == '-') {
indent--;
}
p++;
}
fprintf (out, "\\par\\pard\\plain\n\\li%d{}\n\\sb200\\fi0\n",
LEFTMARGIN+indent*INDENT_AMT);
}
^"<@@chapt><@@head>".*$ {
chapter_mode = 1;
/* skipnewline=1; */
getstr( sectname, 17 ) ;
current=SECTION;
secnr++;
ssecnr=0;
heading( sectname, secnr, 0, 1);
}
^"<@@sect><@@head>".*$ {
/* skipnewline=1; */
if (chapter_mode)
{
getstr( ssectname, 16 ) ;
current=SECTION;
ssecnr++;
heading( ssectname, secnr, ssecnr, !big_page_mode);
}
else
{
getstr( sectname, 16 ) ;
current=CHAPTER;
secnr++;
ssecnr=0;
heading( sectname, secnr, 0, 1);
}
}
^"<@@ssect><@@head>".*$ {
/* skipnewline=1;*/
getstr( ssectname, 17 ) ;
current=SUBSECT;
if (! chapter_mode)
{
ssecnr++;
heading( ssectname, secnr, ssecnr, !big_page_mode );
}
else
{
current=SUBSECT;
subheading( ssectname, 0 );
}
}
^"<@@appendix>".*$ {
in_appendix = 1; secnr=0; ssecnr=0;
fprintf (idx_fp, "\\par\\pard\\qc{\\b Appendix}\\par\\pard\n");
}
^"<@@part><@@head>".*$ {
fprintf (idx_fp, "\\par\\pard\\qc{\\b %s}\\par\\pard\n", yytext+16);
}
^"<@@head>".*$ {
/* skipnewline=1; */
getstr( ssectname, 8 ) ;
current=SUBSECT;
subheading( ssectname, 0 );
}
^"<@@label>".*$ {
/* XREF: BROKEN_DELIMITERS: See above for why we say "{}K{\footnote .."
* instead of just "\nK{\footnote ..".
*/
fprintf (out, "{}#{\\footnote ");
put_reference (out, yytext+9 );
fprintf (out, "}\n");
/* Grrr. WinHelp uses K footnotes for references from without the .HLP file */
/* (e.g. via the WinHelp API) */
fprintf (out, "{}K{\\footnote ");
put_reference (out, yytext+9 );
fprintf (out, "}\n");
}
^"<@@title>".*$ {
/* skipnewline=1;*/
getstr( ssectname, 9 ) ;
subheading( ssectname, 1 );
}
"<@@nofill>\n" { indent++; nofill = 1; fprintf( out, "\\par\\pard\\sb200\\keep\\li%d{}", LEFTMARGIN+indent*INDENT_AMT); }
"<@@endnofill>\n" { indent--; nofill = 0; fprintf( out, "\\par\\pard\\sb200\\li%d{}", LEFTMARGIN+indent*INDENT_AMT); }
..* {
if (skipnewline) {
/* strcat(Headbuf, yytext ); */
} else if( out != stdout ) {
fprintf( out, "%s", yytext );
} else {
ECHO;
}
}
\n {
/* fprintf( out, " ");*/ /* Add a space at the end of each line since RTF does
not treat EOL as whitespace and will concatenate
tokents spanning lines */
if (nofill)
{
fprintf( out, "\\line");
}
if(!skipnewline)
{
if( out != stdout )
{
fprintf( out, "%s", yytext );
}
else
{
ECHO;
}
}
}
%%
int
main( int argc, char **argv )
{
int i;
out = stdout;
idx_fp = stdout;
strcpy( firstname, "RTF" );
for (i = 1; i < argc; i++)
{
if (0 == strcmp("-2", argv[i]))
{
big_page_mode = 0;
}
else if (argv[i][0] != '-')
{
strncpy( firstname, argv[i], 256 );
}
else
{
fprintf (stderr,
"%s: Warning: unhandled command line option \"%s\"\n",
argv[0], argv[i]);
}
}
fputs (header, out);
fprintf (out, "+{\\footnote browse}\n");
secnr=0;
yylex();
if( out != stdout )
{
fclose( out );
}
fputs ("\n}\n", idx_fp);
fclose( idx_fp );
exit( 0 );
}
/* Use the existing indentation style:
Local variables:
c-indent-level: 2
c-continued-statement-offset: 2
c-brace-offset: 0
c-label-offset: -2
End:
*/
|