#!/usr/local/bin/perl -w
#formerly class4A.pl or ex4-2.pl

#open and read in file with GI numbers
unless(@ARGV==1) {die "please provide name of the file in the command line!!\n";}
$filename=$ARGV[0];
#the file to be read contains a  list of GI numbers
#could need a check for contents
open(IN, "< $filename") or die "cannot open $filename:$!";
#again, the program will exit, if it cannot open the file 
#(good against typos in the filename)
@gi=(); #initialized an array where I will store GI numbers

while(defined($line=<IN>)){   #populate array @gi with GI numbers

	chomp($line);
	if ($line!='') {push(@gi,$line)};
}

close(IN);
# Done with input##########################
 
# determine number of GI numbers read!
$number_gis=scalar (@gi);
print "\nI read in $number_gis GI numbers\n\n";

######################################
#       task 4.2 :                   #
# HOW MANY DUPLICATES PER GI NUMBER? #
######################################

%gi_hash=();

foreach (@gi)  #populate gi_hash with key=gi-number and value how often encountered
	{
        $gi_hash{$_} += 1 ; #Hash contains Key: gi number  Values: how often did it occur?
        }

@gi_names = sort(keys(%gi_hash)); #assigns keys to an array

$number_gis=@gi_names; # determines number of different keys, i.e different GI numbers
print "I read $number_gis different gi numbers\n\n"; 

#next loop prints out GI numbers and how often they occured
#foreach (@gi_names){
#        print "$_  occurred $gi_hash{$_} times\n";
#        }


#########################################################
# sort on values numerically, then on keys 
@sorted_by_value = sort by_value (keys (%gi_hash));  
sub by_value { 
	$gi_hash{$a} <=> $gi_hash{$b}
	or
	$a <=> $b  #if the values are the same, then sort ascibethically (cmp) or numerically (<=>) on the keys
	} # defines the order smaller befor larger (a before b)

#####Next loop prints sorted keys and values
foreach (@sorted_by_value)
	{ 
 	printf  "GI number %-9d occurred %4d times\n", $_, $gi_hash{$_};
	}
# exit;



################################
#          task 4.3:
#count how many unique GI numbers are in the list, i.e. count number of elements 
#in our %gi_hash hash.
###############################
$unique_count=0;
%gi_unique=();
foreach  (@gi_names) # could have used @gi
	{
	if ($gi_hash{$_}==1) #if the value is exactly 1
		{
		$unique_count++;    #increase the uncique counter
		$gi_unique{$_}=1 #
		};
	
	};

printf "\n%3d gi numbers occurred only once.\n\n", $unique_count ;

#print unique GI numbers
@gi_unique_array = sort(keys(%gi_unique));
print "\nThe following $unique_count GI numbers occurred once:\n"; 
foreach (@gi_unique_array){
        printf "%9d \n", $_ ;
        }
print "\n\n";

#### fine ###