from bitarray import bitarray
# 3rd party
import mmh3
class BloomFilter(set):
 def __init__(self, size, hash_count):
 super(BloomFilter, self).__init__()
 self.bit_array = bitarray(size)
 self.bit_array.setall(0)
 self.size = size
 self.hash_count = hash_count
 def __len__(self):
 return self.size
 def __iter__(self):
 return iter(self.bit_array)
 def add(self, item):
 for ii in range(self.hash_count):
  index = mmh3.hash(item, ii) % self.size
  self.bit_array[index] = 1
 return self
 def __contains__(self, item):
 out = True
 for ii in range(self.hash_count):
  index = mmh3.hash(item, ii) % self.size
  if self.bit_array[index] == 0:
  out = False
 return out
def main():
 bloom = BloomFilter(10000, 10)
 animals = ['dog', 'cat', 'giraffe', 'fly', 'mosquito', 'horse', 'eagle',
  'bird', 'bison', 'boar', 'butterfly', 'ant', 'anaconda', 'bear',
  'chicken', 'dolphin', 'donkey', 'crow', 'crocodile']
 # First insertion of animals into the bloom filter
 for animal in animals:
 bloom.add(animal)
 # Membership existence for already inserted animals
 # There should not be any false negatives
 for animal in animals:
 if animal in bloom:
  print('{} is in bloom filter as expected'.format(animal))
 else:
  print('Something is terribly went wrong for {}'.format(animal))
  print('FALSE NEGATIVE!')
 # Membership existence for not inserted animals
 # There could be false positives
 other_animals = ['badger', 'cow', 'pig', 'sheep', 'bee', 'wolf', 'fox',
   'whale', 'shark', 'fish', 'turkey', 'duck', 'dove',
   'deer', 'elephant', 'frog', 'falcon', 'goat', 'gorilla',
   'hawk' ]
 for other_animal in other_animals:
 if other_animal in bloom:
  print('{} is not in the bloom, but a false positive'.format(other_animal))
 else:
  print('{} is not in the bloom filter as expected'.format(other_animal))
if __name__ == '__main__':
 main()

import mmh3
import redis
import math
import time
class PyBloomFilter():
 #內(nèi)置100個隨機種子
 SEEDS = [543, 460, 171, 876, 796, 607, 650, 81, 837, 545, 591, 946, 846, 521, 913, 636, 878, 735, 414, 372,
  344, 324, 223, 180, 327, 891, 798, 933, 493, 293, 836, 10, 6, 544, 924, 849, 438, 41, 862, 648, 338,
  465, 562, 693, 979, 52, 763, 103, 387, 374, 349, 94, 384, 680, 574, 480, 307, 580, 71, 535, 300, 53,
  481, 519, 644, 219, 686, 236, 424, 326, 244, 212, 909, 202, 951, 56, 812, 901, 926, 250, 507, 739, 371,
  63, 584, 154, 7, 284, 617, 332, 472, 140, 605, 262, 355, 526, 647, 923, 199, 518]
 #capacity是預先估計要去重的數(shù)量
 #error_rate表示錯誤率
 #conn表示redis的連接客戶端
 #key表示在redis中的鍵的名字前綴
 def __init__(self, capacity=1000000000, error_rate=0.00000001, conn=None, key='BloomFilter'):
 self.m = math.ceil(capacity*math.log2(math.e)*math.log2(1/error_rate)) #需要的總bit位數(shù)
 self.k = math.ceil(math.log1p(2)*self.m/capacity)    #需要最少的hash次數(shù)
 self.mem = math.ceil(self.m/8/1024/1024)     #需要的多少M內(nèi)存
 self.blocknum = math.ceil(self.mem/512)     #需要多少個512M的內(nèi)存塊,value的第一個字符必須是ascii碼，所有最多有256個內(nèi)存塊
 self.seeds = self.SEEDS[0:self.k]
 self.key = key
 self.N = 2**31-1
 self.redis = conn
 # print(self.mem)
 # print(self.k)
 def add(self, value):
 name = self.key + "_" + str(ord(value[0])%self.blocknum)
 hashs = self.get_hashs(value)
 for hash in hashs:
  self.redis.setbit(name, hash, 1)
 def is_exist(self, value):
 name = self.key + "_" + str(ord(value[0])%self.blocknum)
 hashs = self.get_hashs(value)
 exist = True
 for hash in hashs:
  exist = exist & self.redis.getbit(name, hash)
 return exist
 def get_hashs(self, value):
 hashs = list()
 for seed in self.seeds:
  hash = mmh3.hash(value, seed)
  if hash >= 0:
  hashs.append(hash)
  else:
  hashs.append(self.N - hash)
 return hashs
pool = redis.ConnectionPool(host='127.0.0.1', port=6379, db=0)
conn = redis.StrictRedis(connection_pool=pool)
# 使用方法
# if __name__ == "__main__":
# bf = PyBloomFilter(conn=conn)  # 利用連接池連接Redis
# bf.add('www.jobbole.com')  # 向Redis默認的通道添加一個域名
# bf.add('www.luyin.org')   # 向Redis默認的通道添加一個域名
# print(bf.is_exist('www.zhihu.com')) # 打印此域名在通道里是否存在，存在返回1，不存在返回0
# print(bf.is_exist('www.luyin.org')) # 打印此域名在通道里是否存在，存在返回1，不存在返回0