#!/space/imail/perl/bin/perl

=head1 NAME
  HTML - Prototype HTML parser.

=head1 SYNOPSIS
  HTML [file]..

=head1 DESCRIPTION
  This is the bare bones of a program that reads HTML and
  splits it into tags and text.  It passes these chunks to
  the &tag() and &txt() routines, to do with as they wish.

=head1 OPTIONS

=head1 EXAMPLES

=head1 FILES

=head1 BUGS

=head1 SEE ALSO

=head1 AUTHOR
  John Chambers <jc@trillian.mit.edu>
=cut

$| = 1;
$intag = 0;

line:
	for $line (<>) {
	chunk:
		while ($line) {
			if ($intag) {
				if ($line =~ s/^([^>]*)>//) {
					print "Atr: $1\n" if $1;
					$intag = 0;
					next chunk;
				}
				print "Atr: $line\n";
				next line;
			}
			if ($line =~ s/^<([^\s\r>]*)//) {
				# $1 contains an HTML tag that is now removed.
				# The tag's attributes and the '>' are still in $line.
				&tag($1);
				$intag = 1;
				next chunk;
			}
			# $line starts with a non-tag.
			if ($line =~ s/^([^<]*)//) {
				# $1 is a chunk of text.
				&txt($1);
				next chunk;
			}
			# $line contains no more tags.
			&txt($line) if $line;
			next line;
		}
	}

sub tag {
	local($t) = @_;
	print "TAG: $t\n";
}
sub txt {
	local($t) = @_;
	print "Txt: $t\n";
}