def add_to_redis(CONN, hashes): logger.info(type(hashes)) objs = [] for k, v in hashes.iteritems(): a = Simhash('a') a.value = int(k) objs.append((v, a)) logger.info(objs[0]) logger.info('Number of objects: {}'.format(len(objs))) index = SimhashIndex(CONN, objs, k=3) return index
def find_cluster(s, index): a = Simhash('a') a.value = int(s['simhash']) dups = index.get_near_dups(a) return dups