C10000035 12 C 4 ....^>. HHFCC C10000035 13 C 6 .....^>. HHFFCC C10000035 14 C 6 ...... JHFFCC C10000035 15 C 6 ...... IHFFFC C10000035 16 A 4 .GG...^>G JGHFFFC C10000035 17 C 7 ....... JGHFFFC C10000035 18 C 8 .......^]. JIHHFFC@ C10000035 19 A 8 ........ IJHHFFFC C10000035 20 C 9 ..T...T.^]. JIHGHFF@C C10000035 21 G 10 A........^]. AJJHHHFDCC C10000040 30 C 5 ....^>. HHFCC C10000040 31 C 6 .....^>. HHFFCC C10000040 32 C 6 ...... JHFFCC C10000040 33 C 6 ...... IHFFFC C10000040 34 C 4 ...... IHFFFC C10000040 35 C 4 ...... IHFFFC C10000040 36 C 4 ...... IHFFFC C10000040 37 C 6 ...... IHFFFC C10000040 38 C 6 ...... IHFFFC ##

##


C10000035,13,15,3
C10000035,17,21,5
C10000040,30,33,4
C10000040,37,38,2


##

##


#!/usr/bin/perl


use strict;
use warnings;

#usage: perl script.pl 


my $pileup =$ARGV[0];   # get filename from command line argument


open (IN, $pileup) or die ("Could not open file.\n");   #test for file

my @chroms;         #initialize chroms array
my @positions;      #initialize positions array
my $count = 0;      #initialize count


while ( my $line = ){          #while line read from input file
    
    #split line into array from tab-delimited fields
    my @line = split("\t",$line);
    
    #check if element [3] (coverage depth) less than 5
    if($line[3]<5){
        
        #if above condition met, move to next line
        next;
    }
    else{

        do{
            #if above conditions not met, push element [0] 
            #(chromosome name) into chroms array
            push @chroms, $line[0];
            
            #push element [1] (position on chromosome) into 
            #positions array
            push @positions, $line[1];
            
            #increment count by one
            $count++;
        
        }

        
        #do the above until element added to chrom array does 
        #not match previous elements OR
        #until position is not in sequence OR
        #element [3] of line (coverage depth) is less than 5
        
        until ($chroms[0] ne $chroms[$count-1] || 
        $positions[0] != $positions[$count-1]-length(@positions) ||
        $line[3]<5);
        next;
        

        }
    }

#print initial chromosome name, first position, last position, 
#length of span of consecutive positions

print   $chroms[0],"\t",
        $positions[0],"\t",
        $positions[$count-2],"\t",
        $positions[$count-2]-$positions[0]+1,"\n";

##

##


C10000035	13	37	25