#!/usr/bin/perl
use strict;
# define the subclass
package ProcExternal;
use base "HTML::Parser";
#specifying filename to open
if (($ARGV[0] eq "?") || ($#ARGV != 1)) {die "usage $0 file_name  ordering (name/number)\n";};
my $file_name=$ARGV[0];
my $order = $ARGV[1];

my $skip = 1;
my ($product_url, $product_bigurl, $product_id, $product_name, $dir_name);
my (@tarray, @sarray);
my ($orig_text, $orig_self, $product_line);

@sarray = split /\\/,$file_name;
pop @sarray;
$dir_name = join ('\\', @sarray);
if (!open(OFILE,">index.xml")) { die "Can't open $product_name: $!"; };
print OFILE "<Products>\n";
&proc_html($file_name);
print OFILE "</Products>\n"; 
close OFILE;

sub text {
    my ($self, $text) = @_;
  $orig_self = $self;
  $orig_text = $text;
    if (!$skip) {

@tarray =  split(/ /,$text);
if ($order eq "name") 
{
	$product_id = pop @tarray;
	}
elsif ($order eq "number") 
{
	$product_id = shift @tarray; 
	}
elsif ($order eq "none") 
{
	$product_id = "999"; 
	}	
else {
die "invalid ordering parameter\n";	
}
if ($product_id !~/[0-9]/)
{
print "number format error: $text\n";	
}
foreach (@tarray)
{
$_ =~ s/\s+//g;
}
$product_name = join(' ',@tarray);
$product_name =~ s/^\s//g;



if (($product_id) && ($product_name)) 
{
	print OFILE "<Product>\n";
if ($#tarray < 2) 
	{	
	print OFILE "\t<EditLine>$orig_text</EditLine>\n"; 
	print "EditLine #: $product_id $product_name\n";
	};
	print OFILE "\t<Name>$product_name</Name>\n";
	print OFILE "\t<PDF>$product_url</PDF>\n";
	print OFILE "\t<Number>$product_id</Number>\n";
	print OFILE "</Product>\n\n"; 
#	}
}

$skip = 1;

}
}
sub comment {
    my ($self, $comment) = @_;
}

sub start {
    my ($self, $tag, $attr, $attrseq, $origtext) = @_;
if ($tag eq "a") {
	$skip = 0;
	$product_line = $origtext;
	$product_bigurl = $attr->{href};
	@sarray = split('/',$product_bigurl);
	$product_url = uc(pop @sarray);
}
}

sub end {
    my ($self, $tag, $origtext) = @_;
if ($tag eq "a") {
# print $origtext;
}
}

sub proc_html {
my $htmlcontent = shift (@_);
	my $p = new ProcExternal;
	$p->parse_file($htmlcontent);
	$p->eof;
	return;
}