| 1 |
#!/usr/bin/perl -w |
| 2 |
|
| 3 |
#$example_indent = " "; |
| 4 |
$example_indent = ""; |
| 5 |
|
| 6 |
#$ex_color = "#179C4A"; # dark green -- too light |
| 7 |
#$ex_color = "#14843F"; # dark green -- still too light |
| 8 |
#$ex_color = "#056819"; # dark green -- " |
| 9 |
$ex_color = "#82140F"; # dark red |
| 10 |
|
| 11 |
$usage = " |
| 12 |
texinfo2HTML [-h] [filename] |
| 13 |
|
| 14 |
Convert texinfo doc to HTML format, through processing of |
| 15 |
texinfo comments as follows: |
| 16 |
|
| 17 |
1. Pass single line to HTML but not to other forms of manual |
| 18 |
------------------------------------------------------------ |
| 19 |
|
| 20 |
\@c HTML some-stuff |
| 21 |
|
| 22 |
|
| 23 |
2. Commented-out portions |
| 24 |
------------------------- |
| 25 |
|
| 26 |
\@c HTML <!-- |
| 27 |
This line won't appear in the html |
| 28 |
\@c HTML --> |
| 29 |
|
| 30 |
|
| 31 |
3. Break file here |
| 32 |
------------------ |
| 33 |
|
| 34 |
\@c HTML <!-- newfile filename other_words_for_title --> |
| 35 |
If it occurs on a line all by itself, causes |
| 36 |
this perlscript to chop files here. The filename |
| 37 |
will be as specified. The other_words |
| 38 |
will be used as the title. If neither the |
| 39 |
filename nor the other_words are present, then |
| 40 |
this script makes up filenames using numbers, e.g., |
| 41 |
gri1.html, gri2.html. If the filename is \".\", |
| 42 |
then this same naming scheme is used, but the titles |
| 43 |
are used. |
| 44 |
|
| 45 |
4. Insert latex command |
| 46 |
----------------------- |
| 47 |
|
| 48 |
\@c HTML <!-- latex: some-stuff --> |
| 49 |
Plants a comment to be stripped out as a latex-only command. |
| 50 |
|
| 51 |
BUGS: |
| 52 |
Does not search for closing braces properly, so that lines like |
| 53 |
blah \@code{blah blah |
| 54 |
the end is here} and more blah |
| 55 |
will not get the \@code{} item converted correctly. |
| 56 |
"; |
| 57 |
#require "ctime.pl"; |
| 58 |
use POSIX qw(ctime); |
| 59 |
use Getopt::Std; |
| 60 |
&getopts('h'); |
| 61 |
if ($opt_h) { |
| 62 |
print "$usage"; |
| 63 |
exit 0; |
| 64 |
} |
| 65 |
$debug = 0; |
| 66 |
|
| 67 |
#$date = &ctime(time); |
| 68 |
$date = &ctime(time); |
| 69 |
chop($date); |
| 70 |
|
| 71 |
$CH = 0; # chapter |
| 72 |
$SEC1 = 1; # section |
| 73 |
$SEC2 = 1; # subsection |
| 74 |
$SEC3 = 1; # subsubsection |
| 75 |
|
| 76 |
$allow_P = 0; |
| 77 |
$in_example = 0; |
| 78 |
$last_was_node = 0; |
| 79 |
print "<!-- Created automatically from texinfo source -->\n"; |
| 80 |
print "<!-- $date -->\n"; |
| 81 |
sub get_a_line() { |
| 82 |
if ($_=<>) { |
| 83 |
s/\@noindent//; |
| 84 |
if (/^\@c\s*HTML\s*<!--\s*$/) { |
| 85 |
while(<>) { |
| 86 |
#print STDERR "SKIPPING $_"; |
| 87 |
if (/^\@c\s*HTML\s*-->\s*$/) { |
| 88 |
$_ = <>; |
| 89 |
return $_; |
| 90 |
} |
| 91 |
} |
| 92 |
} |
| 93 |
return $_; |
| 94 |
} else { |
| 95 |
return ""; |
| 96 |
} |
| 97 |
} |
| 98 |
while(get_a_line()) { |
| 99 |
$line++ if $debug; |
| 100 |
print STDERR "$0 at line: $line\n" if ($debug && ($line == 2000 * int($line / 2000))); |
| 101 |
next if /\@cindex/; |
| 102 |
# Prevent unclosed braces |
| 103 |
if (!$in_example) { |
| 104 |
while (/{[^}]*$/o) { |
| 105 |
$a = $_; |
| 106 |
$a =~ s/\n/ /o; |
| 107 |
$_ = get_a_line(); |
| 108 |
$_ = $a . $_; |
| 109 |
} |
| 110 |
} else { |
| 111 |
$_ = "$example_indent$_"; |
| 112 |
} |
| 113 |
# Handle HTML inserts |
| 114 |
if (/^\@c HTML (.*)/o) { |
| 115 |
$_ = "$1 \n"; |
| 116 |
&sub_refs; |
| 117 |
s,\@value\{(.*)\},$value{$1},g; # set/value pair |
| 118 |
print; |
| 119 |
next; |
| 120 |
} |
| 121 |
# Process image commands (NOT...it's there already) |
| 122 |
if (/\@image\{(.*)\}/) { |
| 123 |
#print "<img src=\"$1.gif\" border=\"1\">\n"; |
| 124 |
next; |
| 125 |
} |
| 126 |
next if /^\@top\s/; |
| 127 |
next if /^\@include\s*/; |
| 128 |
# Ignore all other comments |
| 129 |
next if /^\@c\s/; |
| 130 |
next if /^\@comment\s*/; |
| 131 |
# Ignore unnumbered, since special case (see Makefile) |
| 132 |
next if /\@unnumbered/; |
| 133 |
# Ignore special-cases text |
| 134 |
next if /^Copyright/; |
| 135 |
# Ignore texinfo command to input files |
| 136 |
next if /\\input/; |
| 137 |
# Ignore some tex-type commands |
| 138 |
next if /\@summarycontents/; |
| 139 |
next if /\@contents/; |
| 140 |
next if /\@bye/; |
| 141 |
next if /\@message/; |
| 142 |
next if /\@global/; |
| 143 |
next if /\@setfilename/; |
| 144 |
next if /\@setchapternewpage/; |
| 145 |
next if /\@settitle/; |
| 146 |
next if /\@page/; |
| 147 |
next if /\@space/; |
| 148 |
next if /\@sp/; |
| 149 |
next if /\@defindex/; |
| 150 |
next if /\@vskip/; |
| 151 |
s/\@noindent//; |
| 152 |
# Pass contents of ifhtml blocks |
| 153 |
next if /\@ifhtml/; |
| 154 |
next if /\@end ifhtml/; |
| 155 |
# Pass contents of ifinfo blocks |
| 156 |
next if /\@ifinfo/; |
| 157 |
next if /\@end ifinfo/; |
| 158 |
# Pass contents of ifnotinfo blocks |
| 159 |
next if /\@ifnotinfo/; |
| 160 |
next if /\@end ifnotinfo/; |
| 161 |
# Ignore contents of @dircategory and @direntry block |
| 162 |
next if /\@dircategory/; |
| 163 |
if (/^\@direntry/o) { |
| 164 |
while(get_a_line()) { |
| 165 |
if (/^\@end direntry/o) { |
| 166 |
$_ = ""; |
| 167 |
last; |
| 168 |
} |
| 169 |
} |
| 170 |
} |
| 171 |
# Ignore contents of tex and iftex blocks |
| 172 |
if (/^\@tex/o) { |
| 173 |
while(get_a_line()) { |
| 174 |
if (/^\@end tex/o) { |
| 175 |
$_ = ""; |
| 176 |
last; |
| 177 |
} |
| 178 |
} |
| 179 |
} |
| 180 |
if (/^\@iftex/o) { |
| 181 |
while(get_a_line()) { |
| 182 |
if (/^\@end iftex/o) { |
| 183 |
$_ = ""; |
| 184 |
last; |
| 185 |
} |
| 186 |
} |
| 187 |
} |
| 188 |
# Ignore indices (for now) |
| 189 |
next if /\@defindex/; |
| 190 |
if (/\@[cfv]index\s*(.*)/o) { |
| 191 |
print "<!-- latex: \\index{$1} -->\n"; |
| 192 |
next; |
| 193 |
} |
| 194 |
next if /\@EGindex/; |
| 195 |
next if /\@printindex/; |
| 196 |
# |
| 197 |
# Save set/value pair. |
| 198 |
if (/\@set\s*(\S*)\s*(\S*)/o) { |
| 199 |
$value{$1} = $2; |
| 200 |
next; |
| 201 |
} |
| 202 |
s,\@value\{([^}]*)\},$value{$1},g; # Substitute set/value pair |
| 203 |
# |
| 204 |
# Fix some texinfo escapes |
| 205 |
s,&,&,og; |
| 206 |
s,>,>,og; |
| 207 |
s,<,<,og; |
| 208 |
# Special tweak to make 'Gri' look cooler. |
| 209 |
# s, Gri , G<FONT SIZE=-1>RI</FONT> ,og; |
| 210 |
s,\@code\{\@\@\},\@code{TEXINFO2HTML-AT-AT},og; |
| 211 |
s,\@},TEXINFO2HTML-CLOSE-BRACE,og; # retain inside e.g. @code{} |
| 212 |
s,\@\@,TEXINFO2HTML-AT-AT,og; |
| 213 |
s,\@\{,{,og; |
| 214 |
s,\@TeX\{\},TeX,og; |
| 215 |
s,\@dots\{\},...,og; |
| 216 |
# Put in place-holders for some accents. I should check for all |
| 217 |
# of them, but for now, I'm just kludging in a couple, |
| 218 |
# to solve an immediate problem and to serve as a place-holder |
| 219 |
# for better coding. A good reference on accents is |
| 220 |
# http://www.w3.org/MarkUp/html-spec/html-spec_13.html |
| 221 |
# which I found on 2002-feb-24. |
| 222 |
s,\@'a,TEXINFO2HTML-ACCENT-ACUTE-a,og; |
| 223 |
s,\@'e,TEXINFO2HTML-ACCENT-ACUTE-e,og; |
| 224 |
s,\@'o,TEXINFO2HTML-ACCENT-ACUTE-o,og; |
| 225 |
if (/^\@titlepage/o) { |
| 226 |
while(get_a_line()) { |
| 227 |
s,\@value\{(.*)\},$value{$1},g; # set/value pair |
| 228 |
if (/\@author\s*(.*)/o) { |
| 229 |
$author = $1; |
| 230 |
$author =~ s/\@\@/\@/; |
| 231 |
} else { |
| 232 |
if (/^\@end titlepage/o) { |
| 233 |
last; |
| 234 |
} |
| 235 |
} |
| 236 |
} |
| 237 |
next; |
| 238 |
} |
| 239 |
while (/\@url\{([^}]*)\}/) { |
| 240 |
$the_url = $1; |
| 241 |
s:\@url\{[^}]*\}:<a href="$the_url">\@code{$the_url}</a>:; |
| 242 |
} |
| 243 |
while (/\@uref\{([^}]*)\}/) { |
| 244 |
@items = split(/,/, $1); |
| 245 |
if ($#items == 0) { |
| 246 |
s:\@uref\{[^}]*\}:<a href="$items[0]">$items[0]</a>:; |
| 247 |
} elsif ($#items == 1) { |
| 248 |
s:\@uref\{[^}]*\}:<a href="$items[0]">$items[1]</a>:; |
| 249 |
} elsif ($#items == 2) { |
| 250 |
s:\@uref\{[^}]*\}:\@code{$items[2]}:; |
| 251 |
} else { |
| 252 |
die "Cannot have more than 3 items in a 'uref' at \"$_\""; |
| 253 |
} |
| 254 |
} |
| 255 |
# |
| 256 |
# Convert cross-references |
| 257 |
if (/^\@node\s*([^,]*), ([^,]*), ([^,]*), ([^\n]*)/o) { |
| 258 |
$next_node = $2; |
| 259 |
$previous_node = $3; |
| 260 |
$parent_node = $4; |
| 261 |
# Start anchor, and set flag so end put after next heading. |
| 262 |
# Need this flag because xmosaic 1.0 does not accept |
| 263 |
# <A NAME="foo"></a>; it requires <A NAME="foo"><h1>heading</h1></a> |
| 264 |
# or it will not properly search the reference. I think this |
| 265 |
# is a bug, and reported it to the author in an email: |
| 266 |
# From kelley Wed Jun 30 16:31:13 1993 |
| 267 |
# To: marca\@ncsa.uiuc.edu |
| 268 |
chop; print "<!-- $_ -->\n"; |
| 269 |
print "<a name=\"$1\" ></a>\n"; |
| 270 |
$last_was_node = 1; |
| 271 |
next; |
| 272 |
} |
| 273 |
&sub_refs; |
| 274 |
# |
| 275 |
# Convert headings; put the end anchor if needed |
| 276 |
if (/\@chapter/o |
| 277 |
|| /\@section/o |
| 278 |
|| /\@subsection/o |
| 279 |
|| /\@subsubsection/o |
| 280 |
|| /\@subsubsubsection/o |
| 281 |
|| /\@appendixsubsec/o |
| 282 |
|| /\@unnumbered/o |
| 283 |
|| /\@appendixsubsec/o |
| 284 |
|| /\@appendixsec/o |
| 285 |
|| /\@appendix/o) { |
| 286 |
&sub_headings; |
| 287 |
&sub_emphasis; |
| 288 |
print; |
| 289 |
# |
| 290 |
# Last was a node, so put the end anchor in |
| 291 |
if ($last_was_node) { |
| 292 |
print "\n<b>Navigation</b>:\n<a href=\"#$next_node\">next</a>,\n<a href=\"#$previous_node\">previous</a>,\n<a href=\"#$parent_node\">parent</a>.\n"; |
| 293 |
$last_was_node = 0; |
| 294 |
} |
| 295 |
# |
| 296 |
# Done with this line |
| 297 |
next; |
| 298 |
} |
| 299 |
&sub_emphasis; |
| 300 |
# |
| 301 |
# Convert quotations |
| 302 |
s,\@quotation,<BLOCKQUOTE>,; |
| 303 |
s,\@end quotation,</BLOCKQUOTE>,; |
| 304 |
&process_examples(); |
| 305 |
# Convert Menus to UL (was DL before) |
| 306 |
if (/\@menu/o) { |
| 307 |
print "<UL>\n"; |
| 308 |
while(get_a_line()) { |
| 309 |
if (/^\@end menu/o) { |
| 310 |
$_ = ""; |
| 311 |
last; |
| 312 |
} |
| 313 |
&sub_headings; |
| 314 |
&sub_emphasis; |
| 315 |
if (/\*\s([^:]*)::\s*(.*)/o) { |
| 316 |
print "<LI><a href=\"#$1\">$1</a>: $2\n"; |
| 317 |
} |
| 318 |
} |
| 319 |
print "</UL>\n"; |
| 320 |
} |
| 321 |
if (/\@table\s*(.*)/o) { |
| 322 |
if ($1 eq "\@code") { |
| 323 |
$start_item = "<tt>"; $end_item = "</tt>" |
| 324 |
} |
| 325 |
if ($1 eq "\@emph") { |
| 326 |
$start_item = "<i>"; $end_item = "</i>" |
| 327 |
} |
| 328 |
print "<dl>\n"; |
| 329 |
while(get_a_line()) { |
| 330 |
next if /\@sp/; |
| 331 |
next if /\@cindex/; |
| 332 |
s|\@anchor\{([^}]*)\}|<a name=\"$1\"></a>|g; |
| 333 |
&process_examples(); |
| 334 |
# Handle HTML inserts |
| 335 |
if (/^\@c HTML (.*)/o) { |
| 336 |
$_ = "$1 \n"; |
| 337 |
&sub_refs; |
| 338 |
s,\@value\{(.*)\},$value{$1},g; # set/value pair |
| 339 |
print; |
| 340 |
next; |
| 341 |
} |
| 342 |
if (/^\s*\@end\s*table/o) { |
| 343 |
$_ = ""; |
| 344 |
last; |
| 345 |
} |
| 346 |
if (/\s*\@item\s*(.*)/o) { |
| 347 |
$the_item = $1; |
| 348 |
$the_item =~ s:\@\{:{:og; |
| 349 |
$the_item =~ s:\@\}:}:og; |
| 350 |
$the_item =~ s:\@\@:\@:og; |
| 351 |
$the_item =~ s:\@code\{([^}]*)\}:`<font color="$ex_color"><code>$1</code></font>':og; |
| 352 |
print "<dt> $start_item$the_item$end_item\n<dd>"; |
| 353 |
} else { |
| 354 |
print "<p>" if (/^$/o); |
| 355 |
&sub_refs; |
| 356 |
&sub_headings; |
| 357 |
&sub_emphasis; |
| 358 |
print; |
| 359 |
} |
| 360 |
} |
| 361 |
print "</dl>\n"; |
| 362 |
} |
| 363 |
# |
| 364 |
# Convert lists |
| 365 |
s,\@itemize.*,<ul>,; |
| 366 |
s,\@end\s*itemize,</ul>,; |
| 367 |
s,\@enumerate,<ol>,; |
| 368 |
s,\@end\s*enumerate,</ol>,; |
| 369 |
s,\@itemx,<li>,; |
| 370 |
s,\@item,<li>,; |
| 371 |
s,\@bullet,,; # HTML does not use |
| 372 |
# |
| 373 |
# Multiple blanks lines are paragraph separators in texinfo |
| 374 |
if (/^$/o) { |
| 375 |
if ($allow_P) { |
| 376 |
print "<p>"; |
| 377 |
} |
| 378 |
$allow_P = 0; |
| 379 |
} elsif (/<H/o) { |
| 380 |
$allow_P = 0; |
| 381 |
} else { |
| 382 |
$allow_P = 1; |
| 383 |
} |
| 384 |
# |
| 385 |
# Finally, print modified line |
| 386 |
print; |
| 387 |
} |
| 388 |
#print "____________________________________________________________________\n"; |
| 389 |
#print "<ADDRESS> $title / $author </ADDRESS>\n"; |
| 390 |
|
| 391 |
print "</BODY>\n"; |
| 392 |
print "</HTML>\n"; |
| 393 |
|
| 394 |
sub process_examples() { |
| 395 |
if (/\@example/o) { |
| 396 |
s,\s*\@example,<TABLE SUMMARY="Example" BORDER="0" BGCOLOR="#efefef" WIDTH="100%">\n<TR>\n<TD>\n<PRE>\n<font color="$ex_color">,; |
| 397 |
$in_example = 1; |
| 398 |
} elsif (/^\s*\@end example/o) { |
| 399 |
s,\s*\@end example,</font></PRE>\n</TD>\n</TR>\n</TABLE>,; |
| 400 |
$in_example = 0; |
| 401 |
} else { |
| 402 |
s,\@value\{([^}]*)\},$value{$1},g; # Substitute set/value pair |
| 403 |
s,\@},},og; |
| 404 |
s,\@\{,{,og; |
| 405 |
} |
| 406 |
} |
| 407 |
|
| 408 |
|
| 409 |
sub sub_refs { |
| 410 |
die "line $. of file: cannot have multiple refs on one line" if (/\@[px]*ref\{(.*)\}(.*)\@[px]*ref\{(.*)\}/); |
| 411 |
# anchors |
| 412 |
s|\@anchor\{([^}]*)\}|<a name=\"$1\"></a>|g; |
| 413 |
# Change e.g. |
| 414 |
# @xref{Viewing} |
| 415 |
# into |
| 416 |
# <a href="#Viewing">see Viewing</a> |
| 417 |
|
| 418 |
#if (/\@ref/){print "AAA[$_]AAA\n"; |
| 419 |
s|\@ref\{([^}]*)\}|see <a href="#$1">$1</a>|g; |
| 420 |
#print "BBB[$_]BBB\n";} |
| 421 |
|
| 422 |
s|\@xref\{([^}]*)\}|see <a href="#$1">$1</a>|g; |
| 423 |
s|\@pxref\{([^}]*)\}|see <a href="#$1">$1.</a>|g; |
| 424 |
while (/\@url\{([^}]*)\}/) { |
| 425 |
$the_url = $1; |
| 426 |
s:\@url\{[^}]*\}:<a href="$the_url">\@code{$the_url}</a>:; |
| 427 |
} |
| 428 |
while (/\@uref\{([^}]*)\}/) { |
| 429 |
@items = split(/,/, $1); |
| 430 |
if ($#items == 0) { |
| 431 |
s:\@uref\{[^}]*\}:<a href="$items[0]">$items[0]</a>:; |
| 432 |
} elsif ($#items == 1) { |
| 433 |
s:\@uref\{[^}]*\}:<a href="$items[0]">$items[1]</a>:; |
| 434 |
} elsif ($#items == 2) { |
| 435 |
s:\@uref\{[^}]*\}:\@code{$items[2]}:; |
| 436 |
} else { |
| 437 |
die "Cannot have more than 3 items in a 'uref' at \"$_\""; |
| 438 |
} |
| 439 |
} |
| 440 |
} |
| 441 |
|
| 442 |
sub sub_headings { |
| 443 |
if (/\@chapter/) { |
| 444 |
$CH++; |
| 445 |
$SEC1 = 0; |
| 446 |
s,\@chapter\s*(.*),<h1>$CH: $1</h1>,; |
| 447 |
} elsif (/\@unnumbered/) { |
| 448 |
$CH++; |
| 449 |
$SEC1 = 0; |
| 450 |
s,\@unnumbered\s*(.*),<h1>$CH: $1</h1>,; |
| 451 |
} elsif (/\@section/) { |
| 452 |
$SEC1++; |
| 453 |
$SEC2 = 0; |
| 454 |
s,\@section\s*(.*),<h2>$CH.$SEC1: $1</h2>,; |
| 455 |
} elsif (/\@subsection/) { |
| 456 |
$SEC2++; |
| 457 |
$SEC3 = 0; |
| 458 |
s,\@subsection\s*(.*),<h3>$CH.$SEC1.$SEC2: $1</h3>,; |
| 459 |
} elsif (/\@subsubsection/) { |
| 460 |
$SEC3++; |
| 461 |
s,\@subsubsection\s*(.*),<h4>$CH.$SEC1.$SEC2.$SEC3: $1</h4>,; |
| 462 |
} |
| 463 |
} |
| 464 |
|
| 465 |
sub sub_emphasis { |
| 466 |
s,<<,<<,g; |
| 467 |
s,>>,>>,g; |
| 468 |
s,\@emph\{([^}]*)\},<em>$1</em>,g; |
| 469 |
s,\@strong\{([^}]*)\},<b>$1</b>,g; |
| 470 |
s,\@footnote\{([^}]*)\}, [$1],g; |
| 471 |
s,\@b\{([^}]*)\},<b>$1</b>,g; |
| 472 |
|
| 473 |
s,\@code\{([^}]*)\},`<font color="$ex_color"><code>$1</code></font>',g; |
| 474 |
s,\@\@,\@,g; |
| 475 |
s,\@samp\{([^}]*)\},`<font color="$ex_color"><samp>$1</samp></font>',g; |
| 476 |
s,\@key\{([^}]*)\},`<font color="$ex_color"><kbd>$1</kbd></font>',g; |
| 477 |
s,\@kbd\{([^}]*)\},`<font color="$ex_color"><kbd>$1</kbd></font>',g; |
| 478 |
s,\@file\{([^}]*)\},`<font color="$ex_color"><samp>$1</samp></font>',g; |
| 479 |
s,TEXINFO2HTML-CLOSE-BRACE,},g; |
| 480 |
s,TEXINFO2HTML-AT-AT,\@,g; |
| 481 |
s,TEXINFO2HTML-ACCENT-ACUTE-a,á,g; |
| 482 |
s,TEXINFO2HTML-ACCENT-ACUTE-e,é,g; |
| 483 |
s,TEXINFO2HTML-ACCENT-ACUTE-o,ó,g; |
| 484 |
} |
| 485 |
|