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

my $InputFile1 = "edited_archaea_master_list.txt";
open FILE1, $InputFile1 or die "Can't read source file: $InputFile1\n";

my $InputFile2 = "testprefix172_single_line_nostrains_aligned_gaps_test.meg";
open FILE2, $InputFile2 or die "Can't read second source file: $InputFile2\n"; 

my $OutputFile3 = "rearrangement_out_test.txt";
open FILE3, ">$OutputFile3" or die "Can't open output file: $OutputFile3\n";

print FILE3 "Input #1: $InputFile1\n";
print FILE3 "Input #2: $InputFile2\n\n";

my @species = <FILE1>; #take file 1 and make into an array
my @align = <FILE2>; #samsies
print "array @align\n";
my $limit = @align; #Number of lines read in the array

my $species; #used in the foreach loop through @species array ...
my $i;
my $j;
my $FoundFlag; #variable used to store names not found and print out at the end
my @notFound; #used to remember species that are not found in order to print at the end ...

#loop through master list ...
foreach $species(@species)
{
	chomp($species); #deletes the enter character at the end the species, so rather than looking for "species\n", it can just find "species"
	#print "$species\n";
	$FoundFlag = 0;

	#Scan second file for a match ...
	for ($i=0; $i<$limit; $i++) #$i is the line number, set to start at zero, $limit is the total number of lines in file, $i++ continues to every consecutive line
	{
		chomp($align[$i]);
		if ($align[$i] =~ /$species/) #if the line in align array matches the line in the species file, then print, and will print to output file
			{
				#print "Found ....\n";
				print $align[$i];
				$j = $i; #$j equals to the species found in the mega file, do then prints the align of $j plus all the lines that follow, until the next # sign.
				do
				{
					print FILE3 "$align[$j]";
					$j = $j + 1;
					
				} while (($j < $limit) && !($align[$j] =~ /^#/)); #align of j will continue to print until the $limit, which is the end of the file, AND until the next pound sign.

				$FoundFlag = 1; #if the species is found, then foundflag equals one, meaning its true.
				last; #quit FOR loop ... and look for the next species
			}
	}
	if ($FoundFlag == 0)
	{
		print "I did not find $species\n";
		#print FILE3 "I did not find $species\n";
		push @notFound, $species;
	}
	#print "Next one ...\n";
}

#Write not found species ...
foreach my $item(@notFound)
{
	print FILE3 "I did not find $item\n";
}

close FILE3;

print "Done!\n";

exit;