| 1 | #!/usr/bin/env perl |
| 2 | |
| 3 | # Copyright (C) 1999, 2000, 2001 Free Software Foundation, Inc. |
| 4 | |
| 5 | # This file is part of GNU CC. |
| 6 | |
| 7 | # GNU CC is free software; you can redistribute it and/or modify |
| 8 | # it under the terms of the GNU General Public License as published by |
| 9 | # the Free Software Foundation; either version 2, or (at your option) |
| 10 | # any later version. |
| 11 | |
| 12 | # GNU CC is distributed in the hope that it will be useful, |
| 13 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 14 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 15 | # GNU General Public License for more details. |
| 16 | |
| 17 | # You should have received a copy of the GNU General Public License |
| 18 | # along with GNU CC; see the file COPYING. If not, write to |
| 19 | # the Free Software Foundation, 51 Franklin Street, Fifth Floor, |
| 20 | # Boston, MA 02110-1301 USA |
| 21 | |
| 22 | # This does trivial (and I mean _trivial_) conversion of Texinfo |
| 23 | # markup to Perl POD format. It's intended to be used to extract |
| 24 | # something suitable for a manpage from a Texinfo document. |
| 25 | |
| 26 | use warnings; |
| 27 | |
| 28 | $output = 0; |
| 29 | $skipping = 0; |
| 30 | %chapters = (); |
| 31 | @chapters_sequence = (); |
| 32 | $chapter = ""; |
| 33 | @icstack = (); |
| 34 | @endwstack = (); |
| 35 | @skstack = (); |
| 36 | @instack = (); |
| 37 | $shift = ""; |
| 38 | %defs = (); |
| 39 | $fnno = 1; |
| 40 | $inf = ""; |
| 41 | @ibase = (); |
| 42 | |
| 43 | while ($_ = shift) { |
| 44 | if (/^-D(.*)$/) { |
| 45 | if ($1 ne "") { |
| 46 | $flag = $1; |
| 47 | } else { |
| 48 | $flag = shift; |
| 49 | } |
| 50 | $value = ""; |
| 51 | ($flag, $value) = ($flag =~ /^([^=]+)(?:=(.+))?/); |
| 52 | die "no flag specified for -D\n" |
| 53 | unless $flag ne ""; |
| 54 | die "flags may only contain letters, digits, hyphens, dashes and underscores\n" |
| 55 | unless $flag =~ /^[a-zA-Z0-9_-]+$/; |
| 56 | $defs{$flag} = $value; |
| 57 | } elsif (/^-I(.*)$/) { |
| 58 | push @ibase, $1 ne "" ? $1 : shift; |
| 59 | } elsif (/^-/) { |
| 60 | usage(); |
| 61 | } else { |
| 62 | $in = $_, next unless defined $in; |
| 63 | $out = $_, next unless defined $out; |
| 64 | usage(); |
| 65 | } |
| 66 | } |
| 67 | |
| 68 | push @ibase, "."; |
| 69 | |
| 70 | if (defined $in) { |
| 71 | $inf = gensym(); |
| 72 | open($inf, "<$in") or die "opening \"$in\": $!\n"; |
| 73 | push @ibase, $1 if $in =~ m|^(.+)/[^/]+$|; |
| 74 | } else { |
| 75 | $inf = \*STDIN; |
| 76 | } |
| 77 | |
| 78 | if (defined $out) { |
| 79 | open(STDOUT, ">$out") or die "opening \"$out\": $!\n"; |
| 80 | } |
| 81 | |
| 82 | while(defined $inf) { |
| 83 | INF: while(<$inf>) { |
| 84 | # Certain commands are discarded without further processing. |
| 85 | /^\@(?: |
| 86 | [a-z]+index # @*index: useful only in complete manual |
| 87 | |need # @need: useful only in printed manual |
| 88 | |(?:end\s+)?group # @group .. @end group: ditto |
| 89 | |page # @page: ditto |
| 90 | |node # @node: useful only in .info file |
| 91 | |(?:end\s+)?ifnottex # @ifnottex .. @end ifnottex: use contents |
| 92 | )\b/x and next; |
| 93 | |
| 94 | chomp; |
| 95 | |
| 96 | # Look for filename and title markers. |
| 97 | /^\@setfilename\s+([^.]+)/ and $fn = $1, next; |
| 98 | /^\@settitle\s+([^.]+)/ and $tl = postprocess($1), next; |
| 99 | |
| 100 | # Identify a man title but keep only the one we are interested in. |
| 101 | /^\@c\s+man\s+title\s+([A-Za-z0-9-]+)\s+(.+)/ and do { |
| 102 | if (exists $defs{$1}) { |
| 103 | $fn = $1; |
| 104 | $tl = postprocess($2); |
| 105 | } |
| 106 | next; |
| 107 | }; |
| 108 | |
| 109 | /^\@include\s+(.+)$/ and do { |
| 110 | push @instack, $inf; |
| 111 | $inf = gensym(); |
| 112 | |
| 113 | for (@ibase) { |
| 114 | open($inf, "<" . $_ . "/" . $1) and next INF; |
| 115 | } |
| 116 | die "cannot open $1: $!\n"; |
| 117 | }; |
| 118 | |
| 119 | /^\@chapter\s+([A-Za-z ]+)/ and do { |
| 120 | # close old chapter |
| 121 | $chapters{$chapter_name} .= postprocess($chapter) if ($chapter_name); |
| 122 | |
| 123 | # start new chapter |
| 124 | $chapter_name = $1, push (@chapters_sequence, $chapter_name) unless $skipping; |
| 125 | $chapters{$chapter_name} = "" unless exists $chapters{$chapter_name}; |
| 126 | $chapter = ""; |
| 127 | $output = 1; |
| 128 | next; |
| 129 | }; |
| 130 | |
| 131 | /^\@bye/ and do { |
| 132 | # close old chapter |
| 133 | $chapters{$chapter_name} .= postprocess($chapter) if ($chapter_name); |
| 134 | last INF; |
| 135 | }; |
| 136 | |
| 137 | # handle variables |
| 138 | /^\@set\s+([a-zA-Z0-9_-]+)\s*(.*)$/ and do { |
| 139 | $defs{$1} = $2; |
| 140 | next; |
| 141 | }; |
| 142 | /^\@clear\s+([a-zA-Z0-9_-]+)/ and do { |
| 143 | delete $defs{$1}; |
| 144 | next; |
| 145 | }; |
| 146 | |
| 147 | next unless $output; |
| 148 | |
| 149 | # Discard comments. (Can't do it above, because then we'd never see |
| 150 | # @c man lines.) |
| 151 | /^\@c\b/ and next; |
| 152 | |
| 153 | # End-block handler goes up here because it needs to operate even |
| 154 | # if we are skipping. |
| 155 | /^\@end\s+([a-z]+)/ and do { |
| 156 | # Ignore @end foo, where foo is not an operation which may |
| 157 | # cause us to skip, if we are presently skipping. |
| 158 | my $ended = $1; |
| 159 | next if $skipping && $ended !~ /^(?:ifset|ifclear|ignore|menu|iftex|ifhtml|ifnothtml)$/; |
| 160 | |
| 161 | die "\@end $ended without \@$ended at line $.\n" unless defined $endw; |
| 162 | die "\@$endw ended by \@end $ended at line $.\n" unless $ended eq $endw; |
| 163 | |
| 164 | $endw = pop @endwstack; |
| 165 | |
| 166 | if ($ended =~ /^(?:ifset|ifclear|ignore|menu|iftex|ifhtml|ifnothtml)$/) { |
| 167 | $skipping = pop @skstack; |
| 168 | next; |
| 169 | } elsif ($ended =~ /^(?:example|smallexample|display)$/) { |
| 170 | $shift = ""; |
| 171 | $_ = ""; # need a paragraph break |
| 172 | } elsif ($ended =~ /^(?:itemize|enumerate|(?:multi|[fv])?table)$/) { |
| 173 | $_ = "\n=back\n"; |
| 174 | $ic = pop @icstack; |
| 175 | } else { |
| 176 | die "unknown command \@end $ended at line $.\n"; |
| 177 | } |
| 178 | }; |
| 179 | |
| 180 | # We must handle commands which can cause skipping even while we |
| 181 | # are skipping, otherwise we will not process nested conditionals |
| 182 | # correctly. |
| 183 | /^\@ifset\s+([a-zA-Z0-9_-]+)/ and do { |
| 184 | push @endwstack, $endw; |
| 185 | push @skstack, $skipping; |
| 186 | $endw = "ifset"; |
| 187 | $skipping = 1 unless exists $defs{$1}; |
| 188 | next; |
| 189 | }; |
| 190 | |
| 191 | /^\@ifclear\s+([a-zA-Z0-9_-]+)/ and do { |
| 192 | push @endwstack, $endw; |
| 193 | push @skstack, $skipping; |
| 194 | $endw = "ifclear"; |
| 195 | $skipping = 1 if exists $defs{$1}; |
| 196 | next; |
| 197 | }; |
| 198 | |
| 199 | /^\@(ignore|menu|iftex|ifhtml|ifnothtml)\b/ and do { |
| 200 | push @endwstack, $endw; |
| 201 | push @skstack, $skipping; |
| 202 | $endw = $1; |
| 203 | $skipping = $endw !~ /ifnothtml/; |
| 204 | next; |
| 205 | }; |
| 206 | |
| 207 | next if $skipping; |
| 208 | |
| 209 | # Character entities. First the ones that can be replaced by raw text |
| 210 | # or discarded outright: |
| 211 | s/\@copyright\{\}/(c)/g; |
| 212 | s/\@dots\{\}/.../g; |
| 213 | s/\@enddots\{\}/..../g; |
| 214 | s/\@([.!? ])/$1/g; |
| 215 | s/\@[:-]//g; |
| 216 | s/\@bullet(?:\{\})?/*/g; |
| 217 | s/\@TeX\{\}/TeX/g; |
| 218 | s/\@pounds\{\}/\#/g; |
| 219 | s/\@minus(?:\{\})?/-/g; |
| 220 | |
| 221 | # Now the ones that have to be replaced by special escapes |
| 222 | # (which will be turned back into text by unmunge()) |
| 223 | s/&/&/g; |
| 224 | s/\@\{/{/g; |
| 225 | s/\@\}/}/g; |
| 226 | s/\@\@/&at;/g; |
| 227 | |
| 228 | # Inside a verbatim block, handle @var specially. |
| 229 | if ($shift ne "") { |
| 230 | s/\@var\{([^\}]*)\}/<$1>/g; |
| 231 | } |
| 232 | |
| 233 | # POD doesn't interpret E<> inside a verbatim block. |
| 234 | if ($shift eq "") { |
| 235 | s/</</g; |
| 236 | s/>/>/g; |
| 237 | } else { |
| 238 | s/</</g; |
| 239 | s/>/>/g; |
| 240 | } |
| 241 | |
| 242 | # Single line command handlers. |
| 243 | |
| 244 | /^\@(?:section|unnumbered|unnumberedsec|center|heading)\s+(.+)$/ |
| 245 | and $_ = "\n=head2 $1\n"; |
| 246 | /^\@(?:subsection|subheading)\s+(.+)$/ |
| 247 | and $_ = "\n=head3 $1\n"; |
| 248 | /^\@(?:subsubsection|subsubheading)\s+(.+)$/ |
| 249 | and $_ = "\n=head4 $1\n"; |
| 250 | |
| 251 | # Block command handlers: |
| 252 | /^\@itemize\s*(\@[a-z]+|\*|-)?/ and do { |
| 253 | push @endwstack, $endw; |
| 254 | push @icstack, $ic; |
| 255 | $ic = $1 ? $1 : "*"; |
| 256 | $_ = "\n=over 4\n"; |
| 257 | $endw = "itemize"; |
| 258 | }; |
| 259 | |
| 260 | /^\@enumerate(?:\s+([a-zA-Z0-9]+))?/ and do { |
| 261 | push @endwstack, $endw; |
| 262 | push @icstack, $ic; |
| 263 | if (defined $1) { |
| 264 | $ic = $1 . "."; |
| 265 | } else { |
| 266 | $ic = "1."; |
| 267 | } |
| 268 | $_ = "\n=over 4\n"; |
| 269 | $endw = "enumerate"; |
| 270 | }; |
| 271 | |
| 272 | /^\@((?:multi|[fv])?table)\s+(\@[a-z]+)/ and do { |
| 273 | push @endwstack, $endw; |
| 274 | push @icstack, $ic; |
| 275 | $endw = $1; |
| 276 | $ic = $2; |
| 277 | $ic =~ s/\@(?:samp|strong|key|gcctabopt|option|env|command)/B/; |
| 278 | $ic =~ s/\@(?:code|kbd)/C/; |
| 279 | $ic =~ s/\@(?:dfn|var|emph|cite|i)/I/; |
| 280 | $ic =~ s/\@(?:file)/F/; |
| 281 | $ic =~ s/\@(?:columnfractions)//; |
| 282 | $_ = "\n=over 4\n"; |
| 283 | }; |
| 284 | |
| 285 | /^\@(multitable)\s+{.*/ and do { |
| 286 | push @endwstack, $endw; |
| 287 | push @icstack, $ic; |
| 288 | $endw = $1; |
| 289 | $ic = ""; |
| 290 | $_ = "\n=over 4\n"; |
| 291 | }; |
| 292 | |
| 293 | /^\@((?:small)?example|display)/ and do { |
| 294 | push @endwstack, $endw; |
| 295 | $endw = $1; |
| 296 | $shift = "\t"; |
| 297 | $_ = ""; # need a paragraph break |
| 298 | }; |
| 299 | |
| 300 | /^\@item\s+(.*\S)\s*$/ and $endw eq "multitable" and do { |
| 301 | my $columns = $1; |
| 302 | $columns =~ s/\@tab/ : /; |
| 303 | |
| 304 | $_ = "\n=item B<". $columns .">\n"; |
| 305 | }; |
| 306 | |
| 307 | /^\@tab\s+(.*\S)\s*$/ and $endw eq "multitable" and do { |
| 308 | my $columns = $1; |
| 309 | $columns =~ s/\@tab//; |
| 310 | |
| 311 | $_ = $columns; |
| 312 | $chapter =~ s/$//; |
| 313 | }; |
| 314 | |
| 315 | /^\@itemx?\s*(.+)?$/ and do { |
| 316 | if (defined $1) { |
| 317 | # Entity escapes prevent munging by the <> processing below. |
| 318 | $_ = "\n=item $ic\<$1\>\n"; |
| 319 | } else { |
| 320 | $_ = "\n=item $ic\n"; |
| 321 | $ic =~ y/A-Ya-y/B-Zb-z/; |
| 322 | $ic =~ s/(\d+)/$1 + 1/eg; |
| 323 | } |
| 324 | }; |
| 325 | |
| 326 | $chapter .= $shift.$_."\n"; |
| 327 | } |
| 328 | # End of current file. |
| 329 | close($inf); |
| 330 | $inf = pop @instack; |
| 331 | } |
| 332 | |
| 333 | die "No filename or title\n" unless defined $fn && defined $tl; |
| 334 | |
| 335 | # always use utf8 |
| 336 | print "=encoding utf8\n\n"; |
| 337 | |
| 338 | $chapters{NAME} = "$fn \- $tl\n"; |
| 339 | $chapters{FOOTNOTES} .= "=back\n" if exists $chapters{FOOTNOTES}; |
| 340 | |
| 341 | unshift @chapters_sequence, "NAME"; |
| 342 | for $chapter (@chapters_sequence) { |
| 343 | if (exists $chapters{$chapter}) { |
| 344 | $head = uc($chapter); |
| 345 | print "=head1 $head\n\n"; |
| 346 | print scalar unmunge ($chapters{$chapter}); |
| 347 | print "\n"; |
| 348 | } |
| 349 | } |
| 350 | |
| 351 | sub usage |
| 352 | { |
| 353 | die "usage: $0 [-D toggle...] [infile [outfile]]\n"; |
| 354 | } |
| 355 | |
| 356 | sub postprocess |
| 357 | { |
| 358 | local $_ = $_[0]; |
| 359 | |
| 360 | # @value{foo} is replaced by whatever 'foo' is defined as. |
| 361 | while (m/(\@value\{([a-zA-Z0-9_-]+)\})/g) { |
| 362 | if (! exists $defs{$2}) { |
| 363 | print STDERR "Option $2 not defined\n"; |
| 364 | s/\Q$1\E//; |
| 365 | } else { |
| 366 | $value = $defs{$2}; |
| 367 | s/\Q$1\E/$value/; |
| 368 | } |
| 369 | } |
| 370 | |
| 371 | # Formatting commands. |
| 372 | # Temporary escape for @r. |
| 373 | s/\@r\{([^\}]*)\}/R<$1>/g; |
| 374 | s/\@(?:dfn|var|emph|cite|i)\{([^\}]*)\}/I<$1>/g; |
| 375 | s/\@(?:code|kbd)\{([^\}]*)\}/C<$1>/g; |
| 376 | s/\@(?:gccoptlist|samp|strong|key|option|env|command|b)\{([^\}]*)\}/B<$1>/g; |
| 377 | s/\@sc\{([^\}]*)\}/\U$1/g; |
| 378 | s/\@file\{([^\}]*)\}/F<$1>/g; |
| 379 | s/\@w\{([^\}]*)\}/S<$1>/g; |
| 380 | s/\@(?:dmn|math)\{([^\}]*)\}/$1/g; |
| 381 | |
| 382 | # Cross references are thrown away, as are @noindent and @refill. |
| 383 | # (@noindent is impossible in .pod, and @refill is unnecessary.) |
| 384 | # @* is also impossible in .pod; we discard it and any newline that |
| 385 | # follows it. Similarly, our macro @gol must be discarded. |
| 386 | |
| 387 | s/\@anchor{(?:[^\}]*)\}//g; |
| 388 | s/\(?\@xref\{(?:[^\}]*)\}(?:[^.<]|(?:<[^<>]*>))*\.\)?//g; |
| 389 | s/\s+\(\@pxref\{(?:[^\}]*)\}\)//g; |
| 390 | s/;\s+\@pxref\{(?:[^\}]*)\}//g; |
| 391 | s/\@ref\{(?:[^,\}]*,)(?:[^,\}]*,)([^,\}]*).*\}/B<$1>/g; |
| 392 | s/\@ref\{([^\}]*)\}/B<$1>/g; |
| 393 | s/\@noindent\s*//g; |
| 394 | s/\@refill//g; |
| 395 | s/\@gol//g; |
| 396 | s/\@\*\s*\n?//g; |
| 397 | |
| 398 | # @uref can take one, two, or three arguments, with different |
| 399 | # semantics each time. @url and @email are just like @uref with |
| 400 | # one argument, for our purposes. |
| 401 | s/\@(?:uref|url|email)\{([^\},]*),?[^\}]*\}/<B<$1>>/g; |
| 402 | s/\@uref\{([^\},]*),([^\},]*)\}/$2 (C<$1>)/g; |
| 403 | s/\@uref\{([^\},]*),([^\},]*),([^\},]*)\}/$3/g; |
| 404 | |
| 405 | # Turn B<blah I<blah> blah> into B<blah> I<blah> B<blah> to |
| 406 | # match Texinfo semantics of @emph inside @samp. Also handle @r |
| 407 | # inside bold. |
| 408 | s/</</g; |
| 409 | s/>/>/g; |
| 410 | 1 while s/B<((?:[^<>]|I<[^<>]*>)*)R<([^>]*)>/B<$1>${2}B</g; |
| 411 | 1 while (s/B<([^<>]*)I<([^>]+)>/B<$1>I<$2>B</g); |
| 412 | 1 while (s/I<([^<>]*)B<([^>]+)>/I<$1>B<$2>I</g); |
| 413 | s/[BI]<>//g; |
| 414 | s/([BI])<(\s+)([^>]+)>/$2$1<$3>/g; |
| 415 | s/([BI])<([^>]+?)(\s+)>/$1<$2>$3/g; |
| 416 | |
| 417 | # Extract footnotes. This has to be done after all other |
| 418 | # processing because otherwise the regexp will choke on formatting |
| 419 | # inside @footnote. |
| 420 | while (/\@footnote/g) { |
| 421 | s/\@footnote\{([^\}]+)\}/[$fnno]/; |
| 422 | add_footnote($1, $fnno); |
| 423 | $fnno++; |
| 424 | } |
| 425 | |
| 426 | return $_; |
| 427 | } |
| 428 | |
| 429 | sub unmunge |
| 430 | { |
| 431 | # Replace escaped symbols with their equivalents. |
| 432 | local $_ = $_[0]; |
| 433 | |
| 434 | s/</E<lt>/g; |
| 435 | s/>/E<gt>/g; |
| 436 | s/{/\{/g; |
| 437 | s/}/\}/g; |
| 438 | s/&at;/\@/g; |
| 439 | s/&/&/g; |
| 440 | return $_; |
| 441 | } |
| 442 | |
| 443 | sub add_footnote |
| 444 | { |
| 445 | unless (exists $chapters{FOOTNOTES}) { |
| 446 | $chapters{FOOTNOTES} = "\n=over 4\n\n"; |
| 447 | } |
| 448 | |
| 449 | $chapters{FOOTNOTES} .= "=item $fnno.\n\n"; $fnno++; |
| 450 | $chapters{FOOTNOTES} .= $_[0]; |
| 451 | $chapters{FOOTNOTES} .= "\n\n"; |
| 452 | } |
| 453 | |
| 454 | # stolen from Symbol.pm |
| 455 | { |
| 456 | my $genseq = 0; |
| 457 | sub gensym |
| 458 | { |
| 459 | my $name = "GEN" . $genseq++; |
| 460 | my $ref = \*{$name}; |
| 461 | delete $::{$name}; |
| 462 | return $ref; |
| 463 | } |
| 464 | } |