english.py

import redis

def encode(word):
    return word.encode('rot13')

def cleanup():
    db.delete('eng')
    db.delete('eng-rot13')

if __name__ == "__main__":
    count = 0
    db = redis.Redis()
    cleanup()

    for line in open('/usr/share/dict/words', 'r'):
        count += 1
        db.sadd('eng', line)
        db.sadd('eng-rot13', encode(line))
        if (count % 10000 == 0):
            print "Loaded %d words so far" % count

    db.sinterstore('eng-intersect', 'eng', 'eng-rot13')
    msg = "English dictionary contains %d words, and %d rot13'ed words"
    print  msg % (db.scard('eng'), db.scard('eng-rot13'))
    print "Cardinality of intersection: %d " % db.scard('eng-intersect')
    cleanup()