Shell Programming and Scripting

C1 C2 C3 
A A G
T T A
G C C

C1 C2 2
C1 C3 0
C2 C3 1

#!/usr/bin/perl
open I, $ARGV[0];
while (chomp($line=<I>)) {
  @col_names=split / /,$line if $.==1;
  if ($.>1) {
    @fields=split / /,$line;
    for ($i=0;$i<=$#col_names;$i++) {
      $col[$i].=$fields[$i];
    }
  }
}
for ($i=0;$i<=$#col;$i++) {
  for ($j=$i+1;$j<=$#col;$j++) {
    @chars1=split //, $col[$i];
    @chars2=split //, $col[$j];
    $max=($#chars1>=$#chars2)?$#chars1:$#chars2;
    $matches=0;
    for ($k=0;$k<=$max;$k++) {
      $matches++ if $chars1[$k] eq $chars2[$k];
    }
    print "$col_names[$i] $col_names[$j] $matches\n";
  }
}

./script.pl file > output

#!/usr/bin/perl
open I, $ARGV[0];
print STDERR "Reading columns (one dot is 100000 lines)\n";
while (chomp($line=<I>)) {
  print STDERR "." if $.%100000==0;
  @col_names=split / /,$line if $.==1;
  if ($.>1) {
    @fields=split / /,$line;
    for ($i=0;$i<=$#col_names;$i++) {
      $col[$i].=$fields[$i];
    }
  }
}
for ($i=0;$i<=$#col;$i++) {
  for ($j=$i+1;$j<=$#col;$j++) {
    @chars1=split //, $col[$i];
    @chars2=split //, $col[$j];
    $max=($#chars1>=$#chars2)?$#chars1:$#chars2;
    $matches=0;
    for ($k=0;$k<=$max;$k++) {
      $matches++ if $chars1[$k] eq $chars2[$k];
    }
    print "$col_names[$i] $col_names[$j] $matches\n";
  }
}

awk '{
        if(NR==1){
                for(i=1;i<NF;i++){
                        for(j=i+1;j<=NF;j++){
                                _[i"-"j] = $i" "$j
                                __[i"-"j] = 0
                        }
                }
        }
        else{
                for(i=1;i<NF;i++){
                        for(j=i+1;j<=NF;j++){
                                if($i == $j){
                                        __[i"-"j] ++
                                }
                        }
                }
        }
}
END{
        for(i in _)
                print _[i]" "__[i]
}' yourfile