qbloom_filter 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1a5c8c820e92cec2133acd196b0b42ff9713b5b3446226db27dfa1d8db7ba28f
-  data.tar.gz: f2074640b8228181c145500e39cba8467d7fd7d743c94fecc11c8aefc5a013ba
+  metadata.gz: 4437f90c178eb577a2082d8f0dd39fd791821a66fe4f6158564104d09e0482fc
+  data.tar.gz: 31b0ef142afe7125b9ccd7b64714f3b5272d6d966e3ff1c5a15997b95486dd29
 SHA512:
-  metadata.gz: c76fb3bea4b43e1ede2ddfcc6570ace55bd7e3e6a1e5fd3f3b6cb1845f082b8f55716345d40b7202c9d6798e61b84619d0e83a2158c050b966be3451cec83a73
-  data.tar.gz: bb76e4786858a0b0c86fecbd49e6971cccad8b34aaeca4d802940184ca6b38343b39df76da9bdb37fbfe4e9e478260874b400fc2f1ad31b0c3b015cbd3fbc829
+  metadata.gz: 1f0e7a61344a58862c5b489e8bf8268643983f3184320ae1778c083edf298d5f704996ef12c3c80bca234a9035f8ccb943cdd5ca41e5bab3989baed2af90e8f1
+  data.tar.gz: 488f71cd0878139b930103567962f66f671edabff8e69aa3080e9cce834aa9756c4936d52083e1bd9d9f5670911bf2517a13227dd9e2cde57a7a7b216b566a4f

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    qbloom_filter (0.1.0)
+    qbloom_filter (0.3.0)
 
 GEM
   remote: https://rubygems.org/

data/README.md

@@ -39,7 +39,9 @@ __contains?(value)__ - alias of __includes?(value)__
 
 __count__ - returns number of inserted items
 
-##### Methods for union and intersection several bloom filters
+__capacity__ - returns initial capacity
+
+__probability__ - returns initial probability
 
 __bit_size__ - returns number of bits in the bit array
 
@@ -49,6 +51,10 @@ __set_bit(position)__ - set a bit to TRUE in the bit array, rises an error if po
 
 __clear_bit(position)__ - set a bit to FALSE in the bit array, rises an error if position is out of range of the bit array
 
+__union_with(bloom_filter)__ - unions current bloom filter with another one, bloom filters should be the instances of this module and have the same initial params(capacity, probability)
+
+__intersect_with(bloom_filter)__ - intersects current bloom filter with another one, bloom filters should be the instances of this module and have the same initial params(capacity, probability)
+
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at https://github.com/superedriver/bloom_filter

data/lib/bloom_filter.rb

@@ -6,14 +6,19 @@ module BloomFilter
   PRIME = 100_000_000_003
   MAX_HASH_PARAM = 1000
   OUT_OF_RANGE = "Position is out of range"
+  DIFFERENT_INITIAL_PARAMS = "Bloom filters have different initial params"
 
   class Filter
-    attr_reader :count
+    attr_reader :count, :capacity, :probability
 
     def initialize(capacity = 100, probability = 0.01)
       # amount of inserted elements
       @count = 0
 
+      # params ob filter, are used for comparison with params of other bloom filters
+      @capacity = capacity
+      @probability = probability
+
       #number of bits in the array
       @m = (-(capacity * Math.log(probability)) / (Math.log(2) ** 2)).ceil
 
@@ -48,20 +53,39 @@ module BloomFilter
     end
     alias :includes? :contains?
 
+    def bit_size
+      @m
+    end
+
     def get_bit(position)
-      @bitset[position] if is_valid_position(position)
+      valid_position?(position)
+      @bitset[position]
     end
 
     def set_bit(position)
-      @bitset[position] = true if is_valid_position(position)
+      valid_position?(position)
+      @bitset[position] = true
     end
 
     def clear_bit(position)
-      @bitset[position] = false if is_valid_position(position)
+      valid_position?(position)
+      @bitset[position] = false
     end
 
-    def bit_size
-      @m
+    def union_with(bloom_filter)
+      same_params?(bloom_filter)
+
+      @m.times do |i|
+        @bitset[i] = self.get_bit(i) || bloom_filter.get_bit(i)
+      end
+    end
+
+    def intersect_with(bloom_filter)
+      same_params?(bloom_filter)
+
+      @m.times do |i|
+        @bitset[i] = self.get_bit(i) && bloom_filter.get_bit(i)
+      end
     end
 
     private
@@ -74,11 +98,16 @@ module BloomFilter
       Digest::MD5.hexdigest(value.to_s).to_i(16)
     end
 
-    def is_valid_position(position)
+    def valid_position?(position)
       raise OUT_OF_RANGE if position >= @m
       true
     end
 
+    def same_params?(bf)
+      raise DIFFERENT_INITIAL_PARAMS if self.class != bf.class || bf.capacity != @capacity || bf.probability != @probability
+      true
+    end
+
     def get_hash_params(i)
       return 2*i + 1, 2*i + 2
     end

data/lib/bloom_filter/version.rb

@@ -1,3 +1,3 @@
 module BloomFilter
-  VERSION = "0.2.0"
+  VERSION = "0.3.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: qbloom_filter
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - qaz
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-09-28 00:00:00.000000000 Z
+date: 2020-09-29 00:00:00.000000000 Z
 dependencies: []
 description: Simple Bloom Filter
 email: