Print out duplicate entries

duplicates.py

## untested!

def main():
  try:
    f = open("r", sys.argv[1])
  except:
    print "usage: %s file" % (sys.argv[0])
  
  entries = {}
  for line in f.readlines():
    if not entries.has_item(line):
      entries[line] = 1
    else:
      entries[line] += 1
      
  for entry, count in entries.items():
    if count > 1:
      print "%s: %d occurances" % (entry, count)
      

    
  
main()

duplicates2.py

#!/usr/bin/env python

def hash(r):
    """
    hashes 'ABCxyz'.

    ABC is always uppercase. Some characters not present.
    A, B, C is 0..28, i.e. 5 bits == A<<10 | B<<5 | C.
    Max size of xyz is 999 i.e. 10 bits.
    
    Therefore, format:

    A<<20 | B<<15 | C<<10 | xyz
    """
    assert len(r) == 6

    base = ord('A')
    return (ord(r[0])-base) << 20 | \
           (ord(r[1])-base) << 15 | \
           (ord(r[2])-base) << 10 | \
           (int(r[3])*100) + (int(r[4])*10) + int(r[5])


def main():
    hashes = [0] * (1<<25)

    duplicates = False
    for line in open("regnr.txt", "r"):
        h = hash(line[:6])
        hashes[h] += 1
        if hashes[h] > 1:
            duplicates = True
            break

    if duplicates:
        print "duplicates"



if __name__ == '__main__':
    main()