input = open("c:\\sd.sanitized-access.20070110", 'r')
data = input.readlines()
input.close()

clients = set()
dest = set()
pairs = set()
same_dup = 0
other_dup = 0
total = 0

for line in data:
  params = line.split(" ")
  clients.add(params[2])
  if (params[2], params[6]) in pairs:
    same_dup += 1
  elif params[6] in dest:
    other_dup += 1
  pairs.add((params[2], params[6]))
  dest.add(params[6])
  total += 1
