collisions = [fc for fc in D if size(fc)==size(f)]
size_hash = 4*1024
while (len(collisions) > 0) and (size_hash<=size(f)):
  H[(f,size_hash)] = md5(f,size_hash)
  for fc in collisions:
    if (fc,size_hash) not in H:
      H[(fc,size_hash)] = md5(fc,size_hash)
  collisions = [fc for fc in collisions if H[(fc,size_hash)]==H[(f,size_hash)]]
  size_hash *= 2
for fc in collisions:
  # Painstakingly read and compare content to that of f...