use XML::TokeParser;
my $file = 'REC-xml-19980210.xml';
my $i = 0;
my $p = XML::TokeParser->new($file);


my $Ret = "";

while(defined(my $t = $p->get_token() )){
    if($t->[0] eq 'S' and $t->[1] eq 'lhs') {
        $i++;
        $Ret = join '', "[$i] ", $p->get_text('/lhs'), " ::= ";
    }elsif( $t->[0] eq 'S' and $t->[1] eq 'rhs'){
        $Ret .= $p->get_text('/rhs');
    }elsif($t->[0] eq 'E' and $t->[1] eq 'prod'){ 
        print clean($Ret),"\n";
        $Ret = "";
    }
}

undef $Ret;
undef $p;

## mirod already did this, so I'm borrowing

sub prod {
    my( $twig, $prod)= @_;
    my $lhs= $prod->field( 'lhs');
    my $rhs= join '', map {$_->text} $prod->children( 'rhs');

    $i++;
    my $prod_text = "[$i] $lhs ::= $rhs";
    print clean( $prod_text) . "\n";
}


sub clean { 
        my( $string)= @_;
        $string =~ s/\xc2\xa0/ /sg;
        $string =~ s/\s+/ /g; $string=~ s{\s$}{}g;
        return $string;
}