[qemu.git] / texi2pod.pl

#! /usr/bin/perl -w

#   Copyright (C) 1999, 2000, 2001, 2003 Free Software Foundation, Inc.

# This file is part of GCC.

# GCC 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 2, or (at your option)
# any later version.

# GCC 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 GCC; see the file COPYING.  If not, write to
# the Free Software Foundation, 51 Franklin Street, Fifth Floor,
# Boston MA 02110-1301, USA.

# 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.

$output = 0;
$skipping = 0;
%sects = ();
$section = "";
@icstack = ();
@endwstack = ();
@skstack = ();
@instack = ();
$shift = "";
%defs = ();
$fnno = 1;
$inf = "";
$ibase = "";
@ipath = ();

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} = $value;
    } elsif (/^-I(.*)$/) {
	if ($1 ne "") {
	    $flag = $1;
	} else {
	    $flag = shift;
	}
        push (@ipath, $flag);
    } 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;

    # 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;
	next if $skipping && $ended !~ /^(?:ifset|ifclear|ignore|menu|iftex|copying)$/;

	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 ($ended =~ /^(?:ifset|ifclear|ignore|menu|iftex)$/) {
	    $skipping = pop @skstack;
	    next;
	} elsif ($ended =~ /^(?:example|smallexample|display)$/) {
	    $shift = "";
	    $_ = "";	# need a paragraph break
	} elsif ($ended =~ /^(?:itemize|enumerate|[fv]?table)$/) {
	    $_ = "\n=back\n";
	    $ic = pop @icstack;
	} elsif ($ended eq "multitable") {
	    $_ = "\n=back\n";
	} 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;
    };

    /^\@(ignore|menu|iftex|copying)\b/ and do {
	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();
	$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;
	next;
    };

    /^\@(?:section|unnumbered|unnumberedsec|center)\s+(.+)$/
	and $_ = "\n=head2 $1\n";
    /^\@subsection\s+(.+)$/
	and $_ = "\n=head3 $1\n";
    /^\@subsubsection\s+(.+)$/
	and $_ = "\n=head4 $1\n";

    # Block command handlers:
    /^\@itemize(?:\s+(\@[a-z]+|\*|-))?/ and do {
	push @endwstack, $endw;
	push @icstack, $ic;
	if (defined $1) {
	    $ic = $1;
	} else {
	    $ic = '*';
	}
	$_ = "\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";
    };

    /^\@multitable\s.*/ and do {
	push @endwstack, $endw;
	$endw = "multitable";
	$_ = "\n=over 4\n";
    };

    /^\@([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/;
	$_ = "\n=over 4\n";
    };

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

    /^\@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
	    $column =~ s/^\@strong{(.*)}$/$1/;
	    push @columns, $column;
	}
	$_ = "\n=item ".join (" : ", @columns)."\n";
    };

    /^\@itemx?\s*(.+)?$/ and do {
	if (defined $1) {
	    # Entity escapes prevent munging by the <> processing below.
	    $_ = "\n=item $ic\&LT;$1\&GT;\n";
	} 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;

$sects{NAME} = "$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;
    s/\@(?:dmn|math)\{([^\}]*)\}/$1/g;

    # 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;

    # 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;

    # Anchors are thrown away
    s/\@anchor\{(?:[^\}]*)\}//g;

    # @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;

    # Un-escape <> at this point.
    s/&LT;/</g;
    s/&GT;/>/g;

    # 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;
    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;
    }
}
Commit	Line	Data
5a67135a FB	1	#! /usr/bin/perl -w
5a67135a FB	2
3aba3d86	3	# Copyright (C) 1999, 2000, 2001, 2003 Free Software Foundation, Inc.
5a67135a	4
3aba3d86	5	# This file is part of GCC.
5a67135a	6
3aba3d86	7	# GCC is free software; you can redistribute it and/or modify
5a67135a FB	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
3aba3d86	12	# GCC is distributed in the hope that it will be useful,
5a67135a FB	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
3aba3d86 TS	18	# along with GCC; see the file COPYING. If not, write to
	19	# the Free Software Foundation, 51 Franklin Street, Fifth Floor,
	20	# Boston MA 02110-1301, USA.
5a67135a FB	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	$output = 0;
	27	$skipping = 0;
	28	%sects = ();
	29	$section = "";
	30	@icstack = ();
	31	@endwstack = ();
	32	@skstack = ();
	33	@instack = ();
	34	$shift = "";
	35	%defs = ();
	36	$fnno = 1;
	37	$inf = "";
	38	$ibase = "";
3aba3d86	39	@ipath = ();
5a67135a FB	40
	41	while ($_ = shift) {
	42	if (/^-D(.*)$/) {
	43	if ($1 ne "") {
	44	$flag = $1;
	45	} else {
	46	$flag = shift;
	47	}
	48	$value = "";
	49	($flag, $value) = ($flag =~ /^([^=]+)(?:=(.+))?/);
	50	die "no flag specified for -D\n"
	51	unless $flag ne "";
	52	die "flags may only contain letters, digits, hyphens, dashes and underscores\n"
	53	unless $flag =~ /^[a-zA-Z0-9_-]+$/;
	54	$defs{$flag} = $value;
3aba3d86 TS	55	} elsif (/^-I(.*)$/) {
	56	if ($1 ne "") {
	57	$flag = $1;
	58	} else {
	59	$flag = shift;
	60	}
	61	push (@ipath, $flag);
5a67135a FB	62	} elsif (/^-/) {
	63	usage();
	64	} else {
	65	$in = $_, next unless defined $in;
	66	$out = $_, next unless defined $out;
	67	usage();
	68	}
	69	}
	70
	71	if (defined $in) {
	72	$inf = gensym();
	73	open($inf, "<$in") or die "opening \"$in\": $!\n";
	74	$ibase = $1 if $in =~ m\|^(.+)/[^/]+$\|;
	75	} else {
	76	$inf = \*STDIN;
	77	}
	78
	79	if (defined $out) {
	80	open(STDOUT, ">$out") or die "opening \"$out\": $!\n";
	81	}
	82
	83	while(defined $inf) {
	84	while(<$inf>) {
	85	# Certain commands are discarded without further processing.
	86	/^\@(?:
	87	[a-z]+index # @*index: useful only in complete manual
	88	\|need # @need: useful only in printed manual
	89	\|(?:end\s+)?group # @group .. @end group: ditto
	90	\|page # @page: ditto
	91	\|node # @node: useful only in .info file
	92	\|(?:end\s+)?ifnottex # @ifnottex .. @end ifnottex: use contents
	93	)\b/x and next;
	94
	95	chomp;
	96
	97	# Look for filename and title markers.
	98	/^\@setfilename\s+([^.]+)/ and $fn = $1, next;
	99	/^\@settitle\s+([^.]+)/ and $tl = postprocess($1), next;
	100
	101	# Identify a man title but keep only the one we are interested in.
	102	/^\@c\s+man\s+title\s+([A-Za-z0-9-]+)\s+(.+)/ and do {
	103	if (exists $defs{$1}) {
	104	$fn = $1;
	105	$tl = postprocess($2);
	106	}
	107	next;
	108	};
	109
	110	# Look for blocks surrounded by @c man begin SECTION ... @c man end.
	111	# This really oughta be @ifman ... @end ifman and the like, but such
	112	# would require rev'ing all other Texinfo translators.
	113	/^\@c\s+man\s+begin\s+([A-Z]+)\s+([A-Za-z0-9-]+)/ and do {
	114	$output = 1 if exists $defs{$2};
	115	$sect = $1;
	116	next;
	117	};
	118	/^\@c\s+man\s+begin\s+([A-Z]+)/ and $sect = $1, $output = 1, next;
	119	/^\@c\s+man\s+end/ and do {
	120	$sects{$sect} = "" unless exists $sects{$sect};
	121	$sects{$sect} .= postprocess($section);
	122	$section = "";
	123	$output = 0;
	124	next;
	125	};
126
127	# handle variables
128	/^\@set\s+([a-zA-Z0-9_-]+)\s(.)$/ and do {
129	$defs{$1} = $2;
130	next;
131	};
132	/^\@clear\s+([a-zA-Z0-9_-]+)/ and do {
133	delete $defs{$1};
134	next;
135	};
136
137	next unless $output;
138
139	# Discard comments. (Can't do it above, because then we'd never see
140	# @c man lines.)
141	/^\@c\b/ and next;
142
143	# End-block handler goes up here because it needs to operate even
144	# if we are skipping.
145	/^\@end\s+([a-z]+)/ and do {
146	# Ignore @end foo, where foo is not an operation which may
147	# cause us to skip, if we are presently skipping.
148	my $ended = $1;
3aba3d86	149	next if $skipping && $ended !~ /^(?:ifset\|ifclear\|ignore\|menu\|iftex\|copying)$/;
5a67135a FB	150
	151	die "\@end $ended without \@$ended at line $.\n" unless defined $endw;
	152	die "\@$endw ended by \@end $ended at line $.\n" unless $ended eq $endw;
	153
	154	$endw = pop @endwstack;
	155
	156	if ($ended =~ /^(?:ifset\|ifclear\|ignore\|menu\|iftex)$/) {
	157	$skipping = pop @skstack;
	158	next;
	159	} elsif ($ended =~ /^(?:example\|smallexample\|display)$/) {
	160	$shift = "";
	161	$_ = ""; # need a paragraph break
	162	} elsif ($ended =~ /^(?:itemize\|enumerate\|[fv]?table)$/) {
	163	$_ = "\n=back\n";
	164	$ic = pop @icstack;
3aba3d86 TS	165	} elsif ($ended eq "multitable") {
3aba3d86 TS	166	$_ = "\n=back\n";
5a67135a FB	167	} else {
	168	die "unknown command \@end $ended at line $.\n";
	169	}
	170	};
	171
	172	# We must handle commands which can cause skipping even while we
	173	# are skipping, otherwise we will not process nested conditionals
	174	# correctly.
	175	/^\@ifset\s+([a-zA-Z0-9_-]+)/ and do {
	176	push @endwstack, $endw;
	177	push @skstack, $skipping;
	178	$endw = "ifset";
	179	$skipping = 1 unless exists $defs{$1};
	180	next;
	181	};
	182
	183	/^\@ifclear\s+([a-zA-Z0-9_-]+)/ and do {
	184	push @endwstack, $endw;
	185	push @skstack, $skipping;
	186	$endw = "ifclear";
	187	$skipping = 1 if exists $defs{$1};
	188	next;
	189	};
	190
3aba3d86	191	/^\@(ignore\|menu\|iftex\|copying)\b/ and do {
5a67135a FB	192	push @endwstack, $endw;
	193	push @skstack, $skipping;
	194	$endw = $1;
	195	$skipping = 1;
	196	next;
	197	};
	198
	199	next if $skipping;
	200
	201	# Character entities. First the ones that can be replaced by raw text
	202	# or discarded outright:
	203	s/\@copyright\{\}/(c)/g;
	204	s/\@dots\{\}/.../g;
	205	s/\@enddots\{\}/..../g;
	206	s/\@([.!? ])/$1/g;
	207	s/\@[:-]//g;
	208	s/\@bullet(?:\{\})?/*/g;
	209	s/\@TeX\{\}/TeX/g;
	210	s/\@pounds\{\}/\#/g;
	211	s/\@minus(?:\{\})?/-/g;
	212	s/\\,/,/g;
	213
	214	# Now the ones that have to be replaced by special escapes
	215	# (which will be turned back into text by unmunge())
	216	s/&/&/g;
	217	s/\@\{/{/g;
	218	s/\@\}/}/g;
	219	s/\@\@/&at;/g;
	220
	221	# Inside a verbatim block, handle @var specially.
	222	if ($shift ne "") {
	223	s/\@var\{([^\}]*)\}/<$1>/g;
	224	}
	225
	226	# POD doesn't interpret E<> inside a verbatim block.
	227	if ($shift eq "") {
	228	s/</</g;
	229	s/>/>/g;
	230	} else {
	231	s/</&LT;/g;
	232	s/>/&GT;/g;
	233	}
	234
	235	# Single line command handlers.
	236
	237	/^\@include\s+(.+)$/ and do {
	238	push @instack, $inf;
	239	$inf = gensym();
3aba3d86 TS	240	$file = postprocess($1);
	241
	242	# Try cwd and $ibase, then explicit -I paths.
	243	$done = 0;
	244	foreach $path ("", $ibase, @ipath) {
	245	$mypath = $file;
	246	$mypath = $path . "/" . $mypath if ($path ne "");
	247	open($inf, "<" . $mypath) and ($done = 1, last);
	248	}
	249	die "cannot find $file" if !$done;
5a67135a FB	250	next;
	251	};
	252
	253	/^\@(?:section\|unnumbered\|unnumberedsec\|center)\s+(.+)$/
	254	and $_ = "\n=head2 $1\n";
	255	/^\@subsection\s+(.+)$/
	256	and $_ = "\n=head3 $1\n";
3aba3d86 TS	257	/^\@subsubsection\s+(.+)$/
3aba3d86 TS	258	and $_ = "\n=head4 $1\n";
5a67135a FB	259
5a67135a FB	260	# Block command handlers:
3aba3d86	261	/^\@itemize(?:\s+(\@[a-z]+\|\*\|-))?/ and do {
5a67135a FB	262	push @endwstack, $endw;
5a67135a FB	263	push @icstack, $ic;
3aba3d86 TS	264	if (defined $1) {
	265	$ic = $1;
	266	} else {
	267	$ic = '*';
	268	}
5a67135a FB	269	$_ = "\n=over 4\n";
	270	$endw = "itemize";
	271	};
	272
	273	/^\@enumerate(?:\s+([a-zA-Z0-9]+))?/ and do {
	274	push @endwstack, $endw;
	275	push @icstack, $ic;
	276	if (defined $1) {
	277	$ic = $1 . ".";
	278	} else {
	279	$ic = "1.";
	280	}
	281	$_ = "\n=over 4\n";
	282	$endw = "enumerate";
	283	};
	284
3aba3d86 TS	285	/^\@multitable\s.*/ and do {
	286	push @endwstack, $endw;
	287	$endw = "multitable";
	288	$_ = "\n=over 4\n";
	289	};
	290
5a67135a FB	291	/^\@([fv]?table)\s+(\@[a-z]+)/ and do {
	292	push @endwstack, $endw;
	293	push @icstack, $ic;
	294	$endw = $1;
	295	$ic = $2;
	296	$ic =~ s/\@(?:samp\|strong\|key\|gcctabopt\|option\|env)/B/;
	297	$ic =~ s/\@(?:code\|kbd)/C/;
	298	$ic =~ s/\@(?:dfn\|var\|emph\|cite\|i)/I/;
	299	$ic =~ s/\@(?:file)/F/;
	300	$_ = "\n=over 4\n";
	301	};
	302
	303	/^\@((?:small)?example\|display)/ and do {
	304	push @endwstack, $endw;
	305	$endw = $1;
	306	$shift = "\t";
	307	$_ = ""; # need a paragraph break
	308	};
	309
3aba3d86 TS	310	/^\@item\s+(.\S)\s$/ and $endw eq "multitable" and do {
	311	@columns = ();
	312	for $column (split (/\s\@tab\s/, $1)) {
	313	# @strong{...} is used a @headitem work-alike
	314	$column =~ s/^\@strong{(.*)}$/$1/;
	315	push @columns, $column;
	316	}
	317	$_ = "\n=item ".join (" : ", @columns)."\n";
	318	};
	319
5a67135a FB	320	/^\@itemx?\s*(.+)?$/ and do {
	321	if (defined $1) {
	322	# Entity escapes prevent munging by the <> processing below.
5a67135a FB	323	$_ = "\n=item $ic\&LT;$1\&GT;\n";
	324	} else {
	325	$_ = "\n=item $ic\n";
	326	$ic =~ y/A-Ya-y/B-Zb-z/;
	327	$ic =~ s/(\d+)/$1 + 1/eg;
	328	}
	329	};
	330
	331	$section .= $shift.$_."\n";
	332	}
	333	# End of current file.
	334	close($inf);
	335	$inf = pop @instack;
	336	}
	337
	338	die "No filename or title\n" unless defined $fn && defined $tl;
	339
	340	$sects{NAME} = "$fn \- $tl\n";
	341	$sects{FOOTNOTES} .= "=back\n" if exists $sects{FOOTNOTES};
	342
	343	for $sect (qw(NAME SYNOPSIS DESCRIPTION OPTIONS ENVIRONMENT FILES
	344	BUGS NOTES FOOTNOTES SEEALSO AUTHOR COPYRIGHT)) {
	345	if(exists $sects{$sect}) {
	346	$head = $sect;
	347	$head =~ s/SEEALSO/SEE ALSO/;
	348	print "=head1 $head\n\n";
	349	print scalar unmunge ($sects{$sect});
	350	print "\n";
	351	}
	352	}
	353
	354	sub usage
	355	{
	356	die "usage: $0 [-D toggle...] [infile [outfile]]\n";
	357	}
	358
	359	sub postprocess
	360	{
	361	local $_ = $_[0];
	362
	363	# @value{foo} is replaced by whatever 'foo' is defined as.
	364	while (m/(\@value\{([a-zA-Z0-9_-]+)\})/g) {
	365	if (! exists $defs{$2}) {
	366	print STDERR "Option $2 not defined\n";
	367	s/\Q$1\E//;
	368	} else {
	369	$value = $defs{$2};
	370	s/\Q$1\E/$value/;
	371	}
	372	}
	373
	374	# Formatting commands.
	375	# Temporary escape for @r.
	376	s/\@r\{([^\}]*)\}/R<$1>/g;
	377	s/\@(?:dfn\|var\|emph\|cite\|i)\{([^\}]*)\}/I<$1>/g;
	378	s/\@(?:code\|kbd)\{([^\}]*)\}/C<$1>/g;
	379	s/\@(?:gccoptlist\|samp\|strong\|key\|option\|env\|command\|b)\{([^\}]*)\}/B<$1>/g;
	380	s/\@sc\{([^\}]*)\}/\U$1/g;
	381	s/\@file\{([^\}]*)\}/F<$1>/g;
	382	s/\@w\{([^\}]*)\}/S<$1>/g;
	383	s/\@(?:dmn\|math)\{([^\}]*)\}/$1/g;
	384
3aba3d86 TS	385	# keep references of the form @ref{...}, print them bold
	386	s/\@(?:ref)\{([^\}]*)\}/B<$1>/g;
	387
	388	# Change double single quotes to double quotes.
	389	s/''/"/g;
	390	s/``/"/g;
	391
5a67135a FB	392	# Cross references are thrown away, as are @noindent and @refill.
	393	# (@noindent is impossible in .pod, and @refill is unnecessary.)
	394	# @* is also impossible in .pod; we discard it and any newline that
	395	# follows it. Similarly, our macro @gol must be discarded.
	396
	397	s/\(?\@xref\{(?:[^\}])\}(?:[^.<]\|(?:<[^<>]>))*\.\)?//g;
	398	s/\s+\(\@pxref\{(?:[^\}]*)\}\)//g;
	399	s/;\s+\@pxref\{(?:[^\}]*)\}//g;
	400	s/\@noindent\s*//g;
	401	s/\@refill//g;
	402	s/\@gol//g;
	403	s/\@\\s\n?//g;
	404
3aba3d86 TS	405	# Anchors are thrown away
	406	s/\@anchor\{(?:[^\}]*)\}//g;
	407
5a67135a FB	408	# @uref can take one, two, or three arguments, with different
	409	# semantics each time. @url and @email are just like @uref with
	410	# one argument, for our purposes.
	411	s/\@(?:uref\|url\|email)\{([^\},]*)\}/<B<$1>>/g;
	412	s/\@uref\{([^\},]),([^\},])\}/$2 (C<$1>)/g;
	413	s/\@uref\{([^\},]),([^\},]),([^\},]*)\}/$3/g;
	414
3aba3d86	415	# Un-escape <> at this point.
5a67135a FB	416	s/&LT;/</g;
5a67135a FB	417	s/&GT;/>/g;
3aba3d86 TS	418
	419	# Now un-nest all B<>, I<>, R<>. Theoretically we could have
	420	# indefinitely deep nesting; in practice, one level suffices.
	421	1 while s/([BIR])<([^<>])([BIR])<([^<>])>/$1<$2>$3<$4>$1</g;
	422
	423	# Replace R<...> with bare ...; eliminate empty markup, B<>;
	424	# shift white space at the ends of [BI]<...> expressions outside
	425	# the expression.
	426	s/R<([^<>]*)>/$1/g;
5a67135a FB	427	s/[BI]<>//g;
	428	s/([BI])<(\s+)([^>]+)>/$2$1<$3>/g;
	429	s/([BI])<([^>]+?)(\s+)>/$1<$2>$3/g;
	430
	431	# Extract footnotes. This has to be done after all other
	432	# processing because otherwise the regexp will choke on formatting
	433	# inside @footnote.
	434	while (/\@footnote/g) {
	435	s/\@footnote\{([^\}]+)\}/[$fnno]/;
	436	add_footnote($1, $fnno);
	437	$fnno++;
	438	}
	439
	440	return $_;
	441	}
	442
	443	sub unmunge
	444	{
	445	# Replace escaped symbols with their equivalents.
	446	local $_ = $_[0];
	447
	448	s/</E<lt>/g;
	449	s/>/E<gt>/g;
	450	s/{/\{/g;
	451	s/}/\}/g;
	452	s/&at;/\@/g;
	453	s/&/&/g;
	454	return $_;
	455	}
	456
	457	sub add_footnote
	458	{
	459	unless (exists $sects{FOOTNOTES}) {
	460	$sects{FOOTNOTES} = "\n=over 4\n\n";
	461	}
	462
	463	$sects{FOOTNOTES} .= "=item $fnno.\n\n"; $fnno++;
	464	$sects{FOOTNOTES} .= $_[0];
	465	$sects{FOOTNOTES} .= "\n\n";
	466	}
	467
	468	# stolen from Symbol.pm
	469	{
	470	my $genseq = 0;
	471	sub gensym
	472	{
	473	my $name = "GEN" . $genseq++;
	474	my $ref = \*{$name};
	475	delete $::{$name};
	476	return $ref;
	477	}
	478	}