texi2pod.pl 13.3 KB
Newer Older
1
#! /usr/bin/env perl
2

ths's avatar
ths committed
3
#   Copyright (C) 1999, 2000, 2001, 2003 Free Software Foundation, Inc.
4

ths's avatar
ths committed
5
# This file is part of GCC.
6

ths's avatar
ths committed
7
# GCC is free software; you can redistribute it and/or modify
8 9 10 11
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2, or (at your option)
# any later version.

ths's avatar
ths committed
12
# GCC is distributed in the hope that it will be useful,
13 14 15 16 17
# 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
18 19
# along with GCC; see the file COPYING.  If not,
# see <http://www.gnu.org/licenses/>.
20 21 22 23 24

# This does trivial (and I mean _trivial_) conversion of Texinfo
# markup to Perl POD format.  It's intended to be used to extract
# something suitable for a manpage from a Texinfo document.

25 26
use warnings;

27 28 29 30 31 32 33 34 35 36 37 38 39
$output = 0;
$skipping = 0;
%sects = ();
$section = "";
@icstack = ();
@endwstack = ();
@skstack = ();
@instack = ();
$shift = "";
%defs = ();
$fnno = 1;
$inf = "";
$ibase = "";
ths's avatar
ths committed
40
@ipath = ();
41
$encoding = undef;
42
@args = ();
43 44 45 46 47 48 49 50 51 52 53 54 55 56 57

while ($_ = shift) {
    if (/^-D(.*)$/) {
	if ($1 ne "") {
	    $flag = $1;
	} else {
	    $flag = shift;
	}
	$value = "";
	($flag, $value) = ($flag =~ /^([^=]+)(?:=(.+))?/);
	die "no flag specified for -D\n"
	    unless $flag ne "";
	die "flags may only contain letters, digits, hyphens, dashes and underscores\n"
	    unless $flag =~ /^[a-zA-Z0-9_-]+$/;
	$defs{$flag} = $value;
ths's avatar
ths committed
58 59 60 61 62 63 64
    } elsif (/^-I(.*)$/) {
	if ($1 ne "") {
	    $flag = $1;
	} else {
	    $flag = shift;
	}
        push (@ipath, $flag);
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
    } elsif (/^-/) {
	usage();
    } else {
	$in = $_, next unless defined $in;
	$out = $_, next unless defined $out;
	usage();
    }
}

if (defined $in) {
    $inf = gensym();
    open($inf, "<$in") or die "opening \"$in\": $!\n";
    $ibase = $1 if $in =~ m|^(.+)/[^/]+$|;
} else {
    $inf = \*STDIN;
}

if (defined $out) {
    open(STDOUT, ">$out") or die "opening \"$out\": $!\n";
}

while(defined $inf) {
while(<$inf>) {
    # Certain commands are discarded without further processing.
    /^\@(?:
	 [a-z]+index		# @*index: useful only in complete manual
	 |need			# @need: useful only in printed manual
	 |(?:end\s+)?group	# @group .. @end group: ditto
	 |page			# @page: ditto
	 |node			# @node: useful only in .info file
	 |(?:end\s+)?ifnottex   # @ifnottex .. @end ifnottex: use contents
	)\b/x and next;

    chomp;

    # Look for filename and title markers.
    /^\@setfilename\s+([^.]+)/ and $fn = $1, next;
    /^\@settitle\s+([^.]+)/ and $tl = postprocess($1), next;

104 105 106 107 108 109
    # Look for document encoding
    /^\@documentencoding\s+([^.]+)/ and do {
        $encoding = $1 unless defined $encoding;
        next;
    };

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
    # Identify a man title but keep only the one we are interested in.
    /^\@c\s+man\s+title\s+([A-Za-z0-9-]+)\s+(.+)/ and do {
	if (exists $defs{$1}) {
	    $fn = $1;
	    $tl = postprocess($2);
	}
	next;
    };

    # Look for blocks surrounded by @c man begin SECTION ... @c man end.
    # This really oughta be @ifman ... @end ifman and the like, but such
    # would require rev'ing all other Texinfo translators.
    /^\@c\s+man\s+begin\s+([A-Z]+)\s+([A-Za-z0-9-]+)/ and do {
	$output = 1 if exists $defs{$2};
        $sect = $1;
	next;
    };
    /^\@c\s+man\s+begin\s+([A-Z]+)/ and $sect = $1, $output = 1, next;
    /^\@c\s+man\s+end/ and do {
	$sects{$sect} = "" unless exists $sects{$sect};
	$sects{$sect} .= postprocess($section);
	$section = "";
	$output = 0;
	next;
    };

    # handle variables
    /^\@set\s+([a-zA-Z0-9_-]+)\s*(.*)$/ and do {
	$defs{$1} = $2;
	next;
    };
    /^\@clear\s+([a-zA-Z0-9_-]+)/ and do {
	delete $defs{$1};
	next;
    };

    next unless $output;

    # Discard comments.  (Can't do it above, because then we'd never see
    # @c man lines.)
    /^\@c\b/ and next;

    # End-block handler goes up here because it needs to operate even
    # if we are skipping.
    /^\@end\s+([a-z]+)/ and do {
	# Ignore @end foo, where foo is not an operation which may
	# cause us to skip, if we are presently skipping.
	my $ended = $1;
ths's avatar
ths committed
158
	next if $skipping && $ended !~ /^(?:ifset|ifclear|ignore|menu|iftex|copying)$/;
159 160 161 162 163 164 165 166 167

	die "\@end $ended without \@$ended at line $.\n" unless defined $endw;
	die "\@$endw ended by \@end $ended at line $.\n" unless $ended eq $endw;

	$endw = pop @endwstack;

	if ($ended =~ /^(?:ifset|ifclear|ignore|menu|iftex)$/) {
	    $skipping = pop @skstack;
	    next;
168 169
	} elsif ($ended =~ /^(?:example|smallexample|display
                            |quotation|deftp|deftypefn)$/x) {
170 171 172 173 174
	    $shift = "";
	    $_ = "";	# need a paragraph break
	} elsif ($ended =~ /^(?:itemize|enumerate|[fv]?table)$/) {
	    $_ = "\n=back\n";
	    $ic = pop @icstack;
ths's avatar
ths committed
175 176
	} elsif ($ended eq "multitable") {
	    $_ = "\n=back\n";
177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200
	} else {
	    die "unknown command \@end $ended at line $.\n";
	}
    };

    # We must handle commands which can cause skipping even while we
    # are skipping, otherwise we will not process nested conditionals
    # correctly.
    /^\@ifset\s+([a-zA-Z0-9_-]+)/ and do {
	push @endwstack, $endw;
	push @skstack, $skipping;
	$endw = "ifset";
	$skipping = 1 unless exists $defs{$1};
	next;
    };

    /^\@ifclear\s+([a-zA-Z0-9_-]+)/ and do {
	push @endwstack, $endw;
	push @skstack, $skipping;
	$endw = "ifclear";
	$skipping = 1 if exists $defs{$1};
	next;
    };

ths's avatar
ths committed
201
    /^\@(ignore|menu|iftex|copying)\b/ and do {
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
	push @endwstack, $endw;
	push @skstack, $skipping;
	$endw = $1;
	$skipping = 1;
	next;
    };

    next if $skipping;

    # Character entities.  First the ones that can be replaced by raw text
    # or discarded outright:
    s/\@copyright\{\}/(c)/g;
    s/\@dots\{\}/.../g;
    s/\@enddots\{\}/..../g;
    s/\@([.!? ])/$1/g;
    s/\@[:-]//g;
    s/\@bullet(?:\{\})?/*/g;
    s/\@TeX\{\}/TeX/g;
    s/\@pounds\{\}/\#/g;
    s/\@minus(?:\{\})?/-/g;
    s/\\,/,/g;

    # Now the ones that have to be replaced by special escapes
    # (which will be turned back into text by unmunge())
    s/&/&amp;/g;
    s/\@\{/&lbrace;/g;
    s/\@\}/&rbrace;/g;
    s/\@\@/&at;/g;

    # Inside a verbatim block, handle @var specially.
    if ($shift ne "") {
	s/\@var\{([^\}]*)\}/<$1>/g;
    }

    # POD doesn't interpret E<> inside a verbatim block.
    if ($shift eq "") {
	s/</&lt;/g;
	s/>/&gt;/g;
    } else {
	s/</&LT;/g;
	s/>/&GT;/g;
    }

    # Single line command handlers.

    /^\@include\s+(.+)$/ and do {
	push @instack, $inf;
	$inf = gensym();
ths's avatar
ths committed
250 251 252 253 254 255 256 257 258 259
	$file = postprocess($1);

	# Try cwd and $ibase, then explicit -I paths.
	$done = 0;
	foreach $path ("", $ibase, @ipath) {
	    $mypath = $file;
	    $mypath = $path . "/" . $mypath if ($path ne "");
	    open($inf, "<" . $mypath) and ($done = 1, last);
	}
	die "cannot find $file" if !$done;
260 261 262 263 264 265 266
	next;
    };

    /^\@(?:section|unnumbered|unnumberedsec|center)\s+(.+)$/
	and $_ = "\n=head2 $1\n";
    /^\@subsection\s+(.+)$/
	and $_ = "\n=head3 $1\n";
ths's avatar
ths committed
267 268
    /^\@subsubsection\s+(.+)$/
	and $_ = "\n=head4 $1\n";
269 270

    # Block command handlers:
ths's avatar
ths committed
271
    /^\@itemize(?:\s+(\@[a-z]+|\*|-))?/ and do {
272 273
	push @endwstack, $endw;
	push @icstack, $ic;
ths's avatar
ths committed
274 275 276 277 278
	if (defined $1) {
	    $ic = $1;
	} else {
	    $ic = '*';
	}
279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294
	$_ = "\n=over 4\n";
	$endw = "itemize";
    };

    /^\@enumerate(?:\s+([a-zA-Z0-9]+))?/ and do {
	push @endwstack, $endw;
	push @icstack, $ic;
	if (defined $1) {
	    $ic = $1 . ".";
	} else {
	    $ic = "1.";
	}
	$_ = "\n=over 4\n";
	$endw = "enumerate";
    };

ths's avatar
ths committed
295 296 297 298 299 300
    /^\@multitable\s.*/ and do {
	push @endwstack, $endw;
	$endw = "multitable";
	$_ = "\n=over 4\n";
    };

301 302 303 304 305 306 307 308 309
    /^\@([fv]?table)\s+(\@[a-z]+)/ and do {
	push @endwstack, $endw;
	push @icstack, $ic;
	$endw = $1;
	$ic = $2;
	$ic =~ s/\@(?:samp|strong|key|gcctabopt|option|env)/B/;
	$ic =~ s/\@(?:code|kbd)/C/;
	$ic =~ s/\@(?:dfn|var|emph|cite|i)/I/;
	$ic =~ s/\@(?:file)/F/;
310
	$ic =~ s/\@(?:asis)//;
311 312 313 314 315 316 317 318 319 320
	$_ = "\n=over 4\n";
    };

    /^\@((?:small)?example|display)/ and do {
	push @endwstack, $endw;
	$endw = $1;
	$shift = "\t";
	$_ = "";	# need a paragraph break
    };

ths's avatar
ths committed
321 322 323 324
    /^\@item\s+(.*\S)\s*$/ and $endw eq "multitable" and do {
	@columns = ();
	for $column (split (/\s*\@tab\s*/, $1)) {
	    # @strong{...} is used a @headitem work-alike
325
	    $column =~ s/^\@strong\{(.*)\}$/$1/;
ths's avatar
ths committed
326 327 328 329 330
	    push @columns, $column;
	}
	$_ = "\n=item ".join (" : ", @columns)."\n";
    };

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
    /^\@(quotation)\s*(.+)?$/ and do {
        push @endwstack, $endw;
        $endw = $1;
        $_ = "\n$2:"
    };

    /^{(.*)}$|^(.*)$/ and $#args > 0 and do {
        $kind = $args[0];
        $arguments = $1 // "";
        if ($endw eq "deftypefn") {
            $ret = $args[1];
            $fname = "B<$args[2]>";
            $_ = $ret ? "$ret " : "";
            $_ .= "$fname $arguments ($kind)";
        } else {
            $_ = "B<$args[1]> ($kind)\n\n$arguments";
        }
        @args = ();
    };

    /^\@(deftp)\s*(.+)?$/ and do {
        push @endwstack, $endw;
        $endw = $1;
        $arg = $2;
        $arg =~ s/{([^}]*)}/$1/g;
        $arg =~ s/\@$//;
        @args = split (/ /, $arg);
        $_ = "";
    };

    /^\@(deftypefn)\s*(.+)?$/ and do {
        push @endwstack, $endw;
        $endw = $1;
        $arg = $2;
        $arg =~ s/{([^}]*)}/$1/g;
        $arg =~ s/\@$//;
        @args = split (/ /, $arg);
        $_ = "";
    };

371 372
    /^\@itemx?\s*(.+)?$/ and do {
	if (defined $1) {
373 374 375 376 377 378
            if ($ic eq "") {
                $_ = "\n=item $1\n";
            } else {
                # Entity escapes prevent munging by the <> processing below.
                $_ = "\n=item $ic\&LT;$1\&GT;\n";
            }
379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394
	} else {
	    $_ = "\n=item $ic\n";
	    $ic =~ y/A-Ya-y/B-Zb-z/;
	    $ic =~ s/(\d+)/$1 + 1/eg;
	}
    };

    $section .= $shift.$_."\n";
}
# End of current file.
close($inf);
$inf = pop @instack;
}

die "No filename or title\n" unless defined $fn && defined $tl;

395 396
print "=encoding $encoding\n\n" if defined $encoding;

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
$sects{NAME} = "$fn \- $tl\n";
$sects{FOOTNOTES} .= "=back\n" if exists $sects{FOOTNOTES};

for $sect (qw(NAME SYNOPSIS DESCRIPTION OPTIONS ENVIRONMENT FILES
	      BUGS NOTES FOOTNOTES SEEALSO AUTHOR COPYRIGHT)) {
    if(exists $sects{$sect}) {
	$head = $sect;
	$head =~ s/SEEALSO/SEE ALSO/;
	print "=head1 $head\n\n";
	print scalar unmunge ($sects{$sect});
	print "\n";
    }
}

sub usage
{
    die "usage: $0 [-D toggle...] [infile [outfile]]\n";
}

sub postprocess
{
    local $_ = $_[0];

    # @value{foo} is replaced by whatever 'foo' is defined as.
    while (m/(\@value\{([a-zA-Z0-9_-]+)\})/g) {
	if (! exists $defs{$2}) {
	    print STDERR "Option $2 not defined\n";
	    s/\Q$1\E//;
	} else {
	    $value = $defs{$2};
	    s/\Q$1\E/$value/;
	}
    }

    # Formatting commands.
    # Temporary escape for @r.
    s/\@r\{([^\}]*)\}/R<$1>/g;
    s/\@(?:dfn|var|emph|cite|i)\{([^\}]*)\}/I<$1>/g;
    s/\@(?:code|kbd)\{([^\}]*)\}/C<$1>/g;
    s/\@(?:gccoptlist|samp|strong|key|option|env|command|b)\{([^\}]*)\}/B<$1>/g;
    s/\@sc\{([^\}]*)\}/\U$1/g;
    s/\@file\{([^\}]*)\}/F<$1>/g;
    s/\@w\{([^\}]*)\}/S<$1>/g;
440
    s/\@t\{([^\}]*)\}/$1/g;
441 442
    s/\@(?:dmn|math)\{([^\}]*)\}/$1/g;

ths's avatar
ths committed
443 444 445 446 447 448 449
    # keep references of the form @ref{...}, print them bold
    s/\@(?:ref)\{([^\}]*)\}/B<$1>/g;

    # Change double single quotes to double quotes.
    s/''/"/g;
    s/``/"/g;

450 451 452 453 454 455 456 457 458 459 460 461 462
    # Cross references are thrown away, as are @noindent and @refill.
    # (@noindent is impossible in .pod, and @refill is unnecessary.)
    # @* is also impossible in .pod; we discard it and any newline that
    # follows it.  Similarly, our macro @gol must be discarded.

    s/\(?\@xref\{(?:[^\}]*)\}(?:[^.<]|(?:<[^<>]*>))*\.\)?//g;
    s/\s+\(\@pxref\{(?:[^\}]*)\}\)//g;
    s/;\s+\@pxref\{(?:[^\}]*)\}//g;
    s/\@noindent\s*//g;
    s/\@refill//g;
    s/\@gol//g;
    s/\@\*\s*\n?//g;

ths's avatar
ths committed
463 464 465
    # Anchors are thrown away
    s/\@anchor\{(?:[^\}]*)\}//g;

466 467 468 469 470 471 472
    # @uref can take one, two, or three arguments, with different
    # semantics each time.  @url and @email are just like @uref with
    # one argument, for our purposes.
    s/\@(?:uref|url|email)\{([^\},]*)\}/&lt;B<$1>&gt;/g;
    s/\@uref\{([^\},]*),([^\},]*)\}/$2 (C<$1>)/g;
    s/\@uref\{([^\},]*),([^\},]*),([^\},]*)\}/$3/g;

ths's avatar
ths committed
473
    # Un-escape <> at this point.
474 475
    s/&LT;/</g;
    s/&GT;/>/g;
ths's avatar
ths committed
476 477 478 479 480 481 482 483 484

    # Now un-nest all B<>, I<>, R<>.  Theoretically we could have
    # indefinitely deep nesting; in practice, one level suffices.
    1 while s/([BIR])<([^<>]*)([BIR])<([^<>]*)>/$1<$2>$3<$4>$1</g;

    # Replace R<...> with bare ...; eliminate empty markup, B<>;
    # shift white space at the ends of [BI]<...> expressions outside
    # the expression.
    s/R<([^<>]*)>/$1/g;
485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536
    s/[BI]<>//g;
    s/([BI])<(\s+)([^>]+)>/$2$1<$3>/g;
    s/([BI])<([^>]+?)(\s+)>/$1<$2>$3/g;

    # Extract footnotes.  This has to be done after all other
    # processing because otherwise the regexp will choke on formatting
    # inside @footnote.
    while (/\@footnote/g) {
	s/\@footnote\{([^\}]+)\}/[$fnno]/;
	add_footnote($1, $fnno);
	$fnno++;
    }

    return $_;
}

sub unmunge
{
    # Replace escaped symbols with their equivalents.
    local $_ = $_[0];

    s/&lt;/E<lt>/g;
    s/&gt;/E<gt>/g;
    s/&lbrace;/\{/g;
    s/&rbrace;/\}/g;
    s/&at;/\@/g;
    s/&amp;/&/g;
    return $_;
}

sub add_footnote
{
    unless (exists $sects{FOOTNOTES}) {
	$sects{FOOTNOTES} = "\n=over 4\n\n";
    }

    $sects{FOOTNOTES} .= "=item $fnno.\n\n"; $fnno++;
    $sects{FOOTNOTES} .= $_[0];
    $sects{FOOTNOTES} .= "\n\n";
}

# stolen from Symbol.pm
{
    my $genseq = 0;
    sub gensym
    {
	my $name = "GEN" . $genseq++;
	my $ref = \*{$name};
	delete $::{$name};
	return $ref;
    }
}