##################################
#                                #
# Last modified 4/10/2011        # 
#                                #
# Georgi Marinov                 #
#                                # 
##################################

import sys
import string
from commoncode import *


def run():

    if len(sys.argv) < 2:
        print 'usage: python %s SAMfile outputfilename ' % sys.argv[0]

        sys.exit(1)
    
    SAM = sys.argv[1]
    outfilename = sys.argv[2]

    outfile = open(outfilename, 'w')

    linelist=open(SAM)

    Seen={}

    i=0
    for line in linelist:
        i+=1
        if i % 10000000 == 0:
            print i, 'lines processed'
        if line.startswith('#'):
            continue
        fields=line.strip().split('\t')
        if Seen.has_key(fields[2]):
            continue
        else:
            Seen[fields[2]]=''
            outfile.write(fields[2]+'\n')

    outfile.close()
   
run()
