# File:	matchHash1.pl
# Title: 	Take all groups of n chars from a string (non-overlapping)
#           $s =~ m/(.{$n})/g;  
# means match(m) first n chars .{$n} - that is repeat . n times
#       () means set result in variable $1
#        g - globally will find all solutions by turn
#        and put them in a hash (array with index as string)
# Author:	Mihaela  Malita
#	Input string? abcxxxabcyyyabc
#	Input integer? 3
#   Hash is pairs of kmers of size 3 with their last position
#   abc 	12
#   xxx		3
#   yyy		9
print "Input string? ";	 $s = <STDIN>; chop($s);		
print "Input integer? "; $k = <STDIN>; chop($k);		
%groupHash = (); # initialize hash (string-index)
$i = 0; 	     # initialize index- how many groups
$pos = 0;        # position 
while ( $s =~ m/(.{$k})/g ) {   # each time variable $1 takes the value of the match
	$groupHash{$1} = $pos;      # value = the number of groups
	$i++;             # next group
    $pos = $k * $i;   # position is how many groups multiplied with their size
}
print("Hash is pairs of kmers of size $k  with their last position\n");
printHash( %groupHash);
exit;

sub printHash {	# prints a hash key-value on each line
	my(%D) = @_;
	foreach $key (keys %D) { # keys are the strings
		print $key, "\t", $D{$key},"\n";
	}
	return;
}