#!/usr/bin/perl
# Converts usda spread sheet (available for any group at the USDA GRIN website) into a .kml file for google earth, seperates species into different folders. Ignores subspecies and hybrid species denoted with 'x'. Use and/or modify at your own risk.
# usage perl USDA_data_to_GEkml.pl seldata.csv helianthus_usda.kml

use warnings;
use strict;
unless (@ARGV == 2) {die;}

my $in = $ARGV[0];
my $out = $ARGV[1];
open IN, "$in";
open OUT, ">$out";

print OUT '<?xml version="1.0" encoding="UTF-8"?>
<kml xmlns="http://www.opengis.net/kml/2.2">
<Document>
<Style id="red">
  <IconStyle>
    <Icon>
      <href>http://www.google.com/intl/en_us/mapfiles/ms/icons/red-dot.png</href>
    </Icon>
  </IconStyle>
</Style>
';

my $last_species = "first";
while(<IN>){
	chomp;
	unless (/^taxon/){
		s/\r/ /g;
		s/\n//g;
		s/\s+/ /g;
		s/,\s/ /g;
		s/""/-/g;
		s/"//g;		
		s/&//g;
		my $line = "$_";
		my @fields = split(/,/,$_);
		my $name = $fields[9];
		my $lat = $fields[18];
		my $long = $fields[19];
		my $des = "$fields[0] $fields[34] $fields[14]";
		my @species = split(/\s/, $fields[0]);

		unless (($species[1] eq "sp.")or($species[1] eq "x")){

			if ($last_species eq "first"){
				print OUT 
'
  <Folder>
    <name>'.$species[1].'</name>
    <open>1</open>
';
				$last_species = $species[1];
			}

			if ($species[1] ne $last_species){
				print OUT 
' </Folder>
  <Folder>
    <name>H. '.$species[1].'</name>
    <open>1</open>
';
				$last_species = $species[1];
			}

# fix lat long

			$lat =~ s/-/0/g;
			$long =~ s/-/0/g;
			if($lat =~ m/N/){
				$lat =~ s/N//;
				$lat = $lat * 0.0001;
			}
			elsif($lat =~ m/S/){
				$lat =~ s/S//;
				$lat = $lat * -0.0001;
			}
			else{
				next;	
			}
			if($long =~ m/E/){
				$long =~ s/E//;
				$long = $long * 0.0001;
			}
			elsif($long =~ m/W/){
				$long =~ s/W//;
				$long = $long * -0.0001;
			}
			else{
				next;	
			}
			print OUT
	'<Placemark>
	<name>'."$name".'</name>
	  <description>'."$des".'</description>
	  <styleUrl>#red</styleUrl> 
	  <Point>
	    <coordinates>'."$long,$lat".',0</coordinates>
	  </Point>
	</Placemark>
	';
		}
	}
}
print OUT "</Folder>
</Document>
</kml>
";