布隆过滤器的概述及Python实现方法

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(100, 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()
 

dog is in bloom filter as expected
cat is in bloom filter as expected
giraffe is in bloom filter as expected
fly is in bloom filter as expected
mosquito is in bloom filter as expected
horse is in bloom filter as expected
eagle is in bloom filter as expected
bird is in bloom filter as expected
bison is in bloom filter as expected
boar is in bloom filter as expected
butterfly is in bloom filter as expected
ant is in bloom filter as expected
anaconda is in bloom filter as expected
bear is in bloom filter as expected
chicken is in bloom filter as expected
dolphin is in bloom filter as expected
donkey is in bloom filter as expected
crow is in bloom filter as expected
crocodile is in bloom filter as expected


badger is not in the bloom filter as expected
cow is not in the bloom filter as expected
pig is not in the bloom filter as expected
sheep is not in the bloom, but a false positive
bee is not in the bloom filter as expected
wolf is not in the bloom filter as expected
fox is not in the bloom filter as expected
whale is not in the bloom filter as expected
shark is not in the bloom, but a false positive
fish is not in the bloom, but a false positive
turkey is not in the bloom filter as expected
duck is not in the bloom filter as expected
dove is not in the bloom误报 filter as expected
deer is not in the bloom filter as expected
elephant is not in the bloom, but a false positive
frog is not in the bloom filter as expected
falcon is not in the bloom filter as expected
goat is not in the bloom filter as expected
gorilla is not in the bloom filter as expected
hawk is not in the bloom filter as expected