########################################################################
#This script is used to convert BWA-generated .sam files to the IGB .gr
#file format.
########################################################################

import re
import string
import sys
from math import *
from Bio import SeqIO
import numpy as np
from array import array

#set the constant for the start and end of the genome -- adjust this for different genome
#for subtilis genome, this is from version 3 file
GENOME_START_POS = 1
GENOME_END_POS = 4215606

geno = array('I')
for x in range(GENOME_END_POS-1):
    geno.append(0)


with open(sys.argv[1]) as f:
    for line in f:
        if not line.startswith('@'):
            read = line.split()
            pos = int(read[3])
            for i in range(pos+1,pos+51):
                #print pos
                geno[i] = geno[i]+1

outfile=open(sys.argv[2],'w')
x=0
percent = 0
part = GENOME_END_POS / 20
for i in geno:
    x+=1
    outfile.write(str(x)+' '+str(i)+'\n')
    if (x % part == 0):
        percent+=5
        print str(percent)+"%"
outfile.close()
print 'done'