#!/usr/bin/perl -w

use strict;
use warnings;

my @fileHeaders;
my %usedHeaders;
my $sortname = "sortfile.tmp";
  # If you have more than one disk, consider putting
  # a disk different from most of your data.
  # Beware of disk space.

open SORTFILE, ">", $sortname
   or die "Cannot create $sortname: $!\n";


# first pass, write to sortfile
foreach my $filename (@ARGV) {

    open GSE, "<", $filename 
       or die "Cannot open $filename: $!\n";

    my $headerline = <GSE>;
    chomp($headerline);
    $headerline =~ s/\r$//;
    my @thisfileHeaders = split /\t/, $headerline;
    shift @thisfileHeaders;
    push @fileHeaders, \@thisfileHeaders;
    my $filekey = sprintf "%04d", $#fileHeaders;
    while(<GSE>) {
       y/\r//d;
       s/^([^\t]*)/$1\t$filekey/;
       print SORTFILE $_ 
	  or die "print SORTFILE failed: $!\n";
    }
    if ($. > 1) { # if any data past headers
      $usedHeaders{$_}++ for @thisfileHeaders;
    }
    close GSE;
}

close SORTFILE
  or die "close SORTFILE failed: $!\n";
# Yes, close can fail.  Buffered I/O, for one thing


system("sort -o sortfile.tmp sortfile.tmp") == 0
  or die "Sort failed!\n";



# second pass; consolidate data from multiple files
my $prevkey;
open SORTFILE, "<", $sortname 
   or die "Cannot open $sortname: $!\n";
my @samples = sort keys %usedHeaders;

print "Probe\t".join("\t",@samples)."\n";

my %data;
while (my $ligne = <SORTFILE>) {
  chomp($ligne);
  my @t = split(/\t/, $ligne);
  my $probe = shift @t;
  my $filenum = shift @t;
  if (!$prevkey || $probe ne $prevkey) {
    dumpdata();
    $prevkey = $probe;
  }
  @data{@{$fileHeaders[$filenum]}} = @t;
}
dumpdata();

sub dumpdata {
  if (defined($prevkey)) {
     print "$prevkey\t", join("\t", @data{@samples}), "\n";
  }
  $data{$_} = "" for @samples;
    #initialize to blanks so no warnings on printing undef
}