New pod2man released

[Zack Weinberg]

On Sun, Nov 19, 2000 at 11:57:38AM +0000, Joseph S. Myers wrote:
> On 18 Nov 2000, Russ Allbery wrote:
> 
> > podlators 1.05 is available from ftp.eyrie.org in /pub/software/modules
> > and shortly from CPAN (and hopefully will make it into Perl 5.6.1).  This
> > version uses \fP for font changes in headings to fix the bug talked about
> > earlier here with headers containing C<> or similar markup.  I think it
> > should even work for nested markup.
> 
> Zack, could you install your modified texi2pod.pl (with the patches you
> previously sent to this list)?  Then I'll produce patches for doing gcov.1
> with this version of pod2man, and start working on invoke.texi.

Done.  Here's the final patch and changelog.

I'm revising the cpp manual; expect a major update sometime this week.

zw
        * texi2pod.pl:
          - Add real command line parsing.
          - Support @ifset, @ifclear, @set, @value, -D switch.
          - Support @sc.  Improve handling of @ref and friends.
          - Discard @subsection, @need, @node lines.
          - Un-nest font changes to match texinfo semantics.
          - Handle @{ and @}.  Oops.
          - Don't emit E<> directives inside verbatim blocks.

===================================================================
Index: contrib/texi2pod.pl
--- contrib/texi2pod.pl	1999/09/04 15:08:53	1.2
+++ contrib/texi2pod.pl	2000/11/19 19:01:31
@@ -4,64 +4,147 @@
 # markup to Perl POD format.  It's intended to be used to extract
 # something suitable for a manpage from a Texinfo document.
 
-$in = $ARGV[0];
-$out = "x";
-die "usage: $0 infile outfile\n" unless defined $in && defined $out;
-
-close STDIN;
-open(IN,$in);
-
 $output = 0;
 $ignore = 0;
+$skipping = 0;
 %sects = ();
 $section = "";
 @icstack = ();
 @endwstack = ();
+@skstack = ();
 $shift = "";
+%defs = ();
 
-while(<IN>)
+while($_ = shift)
 {
+    if (/^-D(.*)$/) {
+	if ($1 ne "") {
+	    $flag = $1;
+	} else {
+	    $flag = shift;
+	}
+	die "no flag specified for -D\n"
+	    unless $flag ne "";
+	die "flags may only contain letters, digits, hyphens, and underscores\n"
+	    unless $flag =~ /^[a-zA-Z0-9_-]+$/;
+	$defs{$flag} = "";
+    } elsif (/^-/) {
+	usage();
+    } else {
+	$in = $_, next unless defined $in;
+	$out = $_, next unless defined $out;
+	usage();
+    }
+}
+
+if (defined $in) {
+    open(STDIN, $in) or die "opening \"$in\": $!\n";
+}
+if (defined $out) {
+    open(STDOUT, ">$out") or die "opening \"$out\": $!\n";
+}
+
+while(<STDIN>)
+{
     chomp;
-    /^\@end ignore/ and $ignore = 0, next;
-    next if $ignore;
     /^\@c man begin ([A-Z]+)/ and $sect = $1, $output = 1, next;
     /^\@c man end/ and do {
 	$_ = $section;
-	s/</</g;
-	s/>/>/g;
 
 	s/\@(?:dfn|var|emph|cite)\{([^\}]*)\}/I<$1>/g;
 	s/\@(?:code|kbd)\{([^\}]*)\}/C<$1>/g;
 	s/\@(?:samp|strong|key)\{([^\}]*)\}/B<$1>/g;
+	s/\@value\{([a-zA-Z0-9_-]+)\}/$defs{$1}/g;
+	s/\@sc\{([^\}]*)\}/\U$1/g;
 	s/\@file\{([^\}]*)\}/F<$1>/g;
 	s/\@(?:url|email)\{([^\}]*)\}/E<lt>C<$1>E<rt>/g;
-	s/\@[a-z]?ref\{(?:[^\}]*)\}.?//g;
-	s/\(\@p[a-z]?ref\{(?:[^\}]*)\}\).?//g;
+	s/\@xref\{(?:[^\}]*)\}[^.]*.//g;
+	s/\s+\(\@p[a-z]?ref\{(?:[^\}]*)\}\)//g;
 	s/\@copyright\{\}//g;
 	s/\@noindent\s*//g;
 	s/\@refill//g;
 	s/\@\././g;
 
-	s/</E<lt>/g;
-	s/>/E<gt>/g;
+	# Turn B<blah I<blah> blah> into B<blah> I<blah> B<blah> to
+	# match Texinfo semantics of @emph inside @samp.
+
 	s/</</g;
 	s/>/>/g;
+	1 while (s/B<([^<>]*)I<([^>]+)>/B<$1>I<$2>B</g);
+	1 while (s/I<([^<>]*)B<([^>]+)>/I<$1>B<$2>I</g);
+	s/[BI]<>//g;
+	s/([BI])<(\s+)([^>]+)>/$2$1<$3>/g;
+	s/([BI])<([^>]+?)(\s+)>/$1<$2>$3/g;
 
+	s/</E<lt>/g;
+	s/>/E<gt>/g;
+	s/{/\{/g;
+	s/}/\}/g;
+
 	$sects{$sect} = $_;
 	$section = "";
 	$output = 0;
 	next;
     };
-    
+
     /^\@(c|[a-z]+index)\b/ and next;
+    /^\@subsection/ and next;
+    /^\@need/ and next;
+    /^\@node/ and next;
 
     /^\@setfilename\s+([^.]+)/ and $fn = $1, next;
     /^\@settitle\s+([^.]+)/ and $tl = $1, next;
 
     next unless $output;
 
+    /^\@end\s+([a-z]+)/ and do {
+	if(defined $endw)
+	{
+	    die "\@$endw ended by \@end $1 at line $.\n"
+		unless $1 eq $endw;
+
+	    if($endw =~ /example$/)
+	    {
+		$shift = "";
+		$_ = "";
+	    }
+	    elsif($endw =~ /^if/)
+	    {
+		$skipping = pop @skstack;
+		$_ = "";
+	    }
+	    else
+	    {
+		$_ = "\n=back\n";
+		$ic = pop @icstack;
+	    }
+	    $endw = pop @endwstack;
+	}
+    };
+
+    /^\@end ignore/ and $ignore = 0, next;
+    next if $ignore;
+    next if $skipping;
+
     /^\@ignore/ and $ignore = 1, next;
 
+    /^\@set\s+([a-zA-Z0-9_-]+)\s*(.*)$/ and $defs{$1} = $2, next;
+    /^\@clear\s+([a-zA-Z0-9_-]+)/ and delete $defs{$1}, next;
+
+    /^\@ifset\s+([a-zA-Z0-9_-]+)/ and do {
+	push @endwstack, $endw;
+	push @skstack, $skipping;
+	$endw = "ifset";
+	$skipping = 1 unless exists $defs{$1};
+    };
+
+    /^\@ifclear\s+([a-zA-Z0-9_-]+)/ and do {
+	push @endwstack, $endw;
+	push @skstack, $skipping;
+	$endw = "ifset";
+	$skipping = 1 if exists $defs{$1};
+    };
+
     /^\@itemize (\@[a-z]+)/ and do {
 	push @endwstack, $endw;
 	push @icstack, $ic;
@@ -99,27 +182,6 @@ while(<IN>)
 	next;
     };
 
-    /^\@end\s+([a-z]+)/ and do {
-	if(defined $endw)
-	{
-	    die "\@$endw ended by \@end $1 at line $.\n"
-		unless $1 eq $endw;
-
-	    if($endw =~ /example$/)
-	    {
-		$shift = "";
-		$_ = "";
-	    }
-	    else
-	    {
-		$_ = "\n=back\n";
-		undef $endw;
-		$ic = pop @icstack;
-	    }
-	    $endw = pop @endwstack;
-	}
-    };
-
     /^\@itemx?\s*(.+)?$/ and do {
 	if(defined $1)
 	{
@@ -130,8 +192,22 @@ while(<IN>)
 	    $_ = "=item $ic\n";
 	    $ic =~ y/A-Ya-y1-8/B-Zb-z2-9/;
 	}
+    };
+
+    /^\@section\s+(.+)$/ and do {
+	$_ = "\n=head2 $1\n";
     };
-	
+
+    # POD doesn't interpret E<> inside a verbatim block.
+    if ($shift eq "") {
+	s/</</g;
+	s/>/>/g;
+    } else {
+	s/</</g;
+	s/>/>/g;
+    }
+    s/\@\{/{/g;
+    s/\@\}/}/g;
     $section .= $shift.$_."\n";
 }
 
@@ -148,4 +224,9 @@ for $sect (qw(NAME SYNOPSIS DESCRIPTION 
 	print $sects{$sect};
 	print "\n";
     }
+}
+
+sub usage
+{
+    die "usage: $0 [-D toggle...] [infile [outfile]]\n";
 }