#!/usr/local/bin/perl
use strict;
use warnings;

use lib "$ENV{HOME}/mylib/lib/perl5";
use HTML::TableParser;
use WWW::Mechanize;
use HTML::TreeBuilder;
use LWP::Simple;


# Define debugging variable - set to positive integer to enable
my $DEBUG_FLAG = 1;

# Define variable that will contain the URL we will parse
my $URL = 'Path to URL speakers.html';

# Define our tree using HTML::Treebuilder and parse the document
my $tree = HTML::TreeBuilder->new;
$tree->parse( get( $URL ) );

# Define our hash that will contain speaker names and their count
my %speakers;

# Look for the elements (speakers) we are searching for based on the anchor "a" tag
my @elements = $tree->look_down( _tag => "a", \&find_speakers );

# Populate our speaker hash and intialize the value to 0
for my $element ( @elements )
{
  $speakers{$element->as_text} = 0;
}

# Print list of speakers if debug mode is enabled
if ( defined $DEBUG_FLAG )
{
  foreach (sort keys %speakers)
  {
    print "$_\n";
  }
}


# Loop through each speaker - the goal here is eventually count all Session and Tutorial 
# links for each speaker
foreach (keys %speakers)
  {
     #check_sessions($_);
#     my $element = $tree->look_down( _tag => "a",
#     					sub { shift->as_text eq $_ } );

#    print $element->as_text() . "\n";
#    my @rightlist = $element->right();
    
#    print "@rightlist\n";				
				
#     my $count = 0;
#     while ($element->look_down( _tag => "li", \&count_sessions ) )
#     {
#       $count++;
#     }
     
#     print "$_ = $count\n";
     
     #$element->dump();
  }


sub check_sessions
{
  #print "@_\n";
  
  my $speaker = shift;
  
  my $element = $tree->look_down( _tag => "li" );
  
  my $parent = $element->look_up( _tag => "a",
     					sub { shift->as_text eq $speaker } );
 
  if (defined $parent)
   {
     if ( $element->as_text() =~ /[Session:]|[Tutorial:]/ )
     {
       print $element->as_text() . "\n";
      return 1;
     }
     else
     {
      return 0;
     }
   }
   else
   {
    return 0;
   }


}



# find_speakers subroutine finds the 'speakers' within the HTML being parsed
# based on the source being an anchor tag, it's parent tag not being a line and
# it is within a span tag
sub find_speakers
{
  my $element = shift;

  my ($parent_tag) = $element->lineage_tag_names;
  # Our parent tag should NOT be a line and the element should be a 'span' tag
  $parent_tag ne 'li' && $element->look_up( _tag => 'span' );
}


# count_sessions subroutine - this was one attempt at trying to get at the Session and tutorial links
sub count_sessions
{
  my $element = shift;
  
  print "Got to count_sessions\n";
  my ($parent_tag) = $element->lineage_tag_names;
  $parent_tag eq 'ul' && ( $element->as_text eq "Session" || $element->as_text eq "Tutorial" );

}

# in_list subroutine - not presently used
sub in_list
{
  my $element = shift;

  my ($parent_tag) = $element->lineage_tag_names;
  # Our parent tag should be a line and the element should be a 'span' tag
  $parent_tag eq 'li' && $element->look_up( _tag => 'span' );
}

# find_top_speakers - placeholder code for subroutine that will find our top 3 speakers
sub find_top_speakers
{

}