qbloom_filter 0.1.0 → 0.3.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c8384171d7c3a67af223b2425c08ec9fa8ccf4c784d658f5951b37642708a384
-  data.tar.gz: a50a3260fcd55e0284e85a1b78f4f34dce3f5ff9bf4a56add2cdebc3aecd1d07
+  metadata.gz: d3107815ff8ebf8aa327a4f2cd2cfb80d9f0aefbffd84e428adcfc504295d42c
+  data.tar.gz: fb29b08c1f68f5f50a06dfbc3b395c43ff9be36fbe0e2741cecf47c7ccf75f1e
 SHA512:
-  metadata.gz: 9fe8aeae6469952e99be203cbe4c12cf03317b7eb9499a2bde069cf11c980d3f7746d29fcb2853451ae82ff5d244f87491103bd15d9125e445f44bb63bbabbfb
-  data.tar.gz: 4a43600e93388a498797dcb6706801b105c470602e0449da6bd37faf885ea660f17c3a9a5fcbfede9f1860af9c0cc8fc47a960073ba893e523fca13d4a8e6590
+  metadata.gz: 2e6ded653a4c765234dd4f38e874efb50de33952fa7faef0ae9c9f97ad0142eabe5bae0c63029f621c9224f456a5bc04d7de12839d28f2748539f7b0d7d53bab
+  data.tar.gz: 40670964f95d373b7c4d413ae60ad5369760a34bcf511195b4e31a38fbc46782e76f8b8b9745607c010dfb32330e9803388d8e08c7f5ec95fc7ec30ffd514631

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    qbloom_filter (0.1.0)
+    qbloom_filter (0.3.4)
 
 GEM
   remote: https://rubygems.org/

data/README.md

@@ -7,7 +7,7 @@ A Bloom filter is a space-efficient probabilistic data structure
 Add this line to your application's Gemfile:
 
 ```ruby
-gem 'bloom_filter'
+gem 'qbloom_filter'
 ```
 
 And then execute:
@@ -16,7 +16,7 @@ And then execute:
 
 Or install it yourself as:
 
-    $ gem install bloom_filter
+    $ gem install qbloom_filter
 
 ## Usage
 
@@ -30,7 +30,7 @@ And two parameters can be used to describe the bloom filter:
 bloom_filter = BloomFilter::Filter.new(1000, 0.001)
 ```
 
-#### API
+#### Methods
 __add(value)__ - add item into filter
 
 __includes?(value)__ - check if filter includes the value
@@ -39,7 +39,23 @@ __contains?(value)__ - alias of __includes?(value)__
 
 __count__ - returns number of inserted items
 
+__capacity__ - returns initial capacity
+
+__probability__ - returns initial probability
+
+__bit_size__ - returns number of bits in the bit array
+
+__get_bit(position)__ - returns value of a bit(true/false) in the bit array, rises an error if position is out of range of the bit array
+
+__set_bit(position)__ - set a bit to TRUE in the bit array, rises an error if position is out of range of the bit array
+
+__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
+Bug reports and pull requests are welcome on GitHub at https://github.com/superedriver/qbloom_filter
 

data/bin/console

@@ -1,7 +1,7 @@
 #!/usr/bin/env ruby
 
 require "bundler/setup"
-require "bloom_filter"
+require "qbloom_filter"
 
 # You can add fixtures and/or initialization code here to make experimenting
 # with your gem easier. You can also use a different console, if you like.

data/lib/qbloom_filter.rb

@@ -0,0 +1,115 @@
+require "bloom_filter/version"
+require "bitset"
+require 'digest/md5'
+
+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, :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
+
+      @bitset = Bitset.new(@m)
+
+      #number of hash functions that minimizes the probability of false positives
+      @k = (Math.log(2) * (@m / capacity)).ceil
+    end
+
+    def add(value)
+      x = get_hash(value)
+      was_inserted = true
+      @k.times do |i|
+        a, b = get_hash_params(i)
+        position = get_position(a, b, x)
+        was_inserted = false unless self.get_bit(position)
+        self.set_bit(position)
+      end
+      @count += 1 unless was_inserted
+      value
+    end
+
+    def contains?(value)
+      x = get_hash(value)
+      result = true
+      @k.times do |i|
+        a, b = get_hash_params(i)
+        result = false unless self.get_bit(get_position(a, b, x))
+      end
+
+      result
+    end
+    alias :includes? :contains?
+
+    def bit_size
+      @m
+    end
+
+    def get_bit(position)
+      valid_position?(position)
+      @bitset[position]
+    end
+
+    def set_bit(position)
+      valid_position?(position)
+      @bitset[position] = true
+    end
+
+    def clear_bit(position)
+      valid_position?(position)
+      @bitset[position] = false
+    end
+
+    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
+
+    def get_position(a, b, val)
+      ((a * val + b) % PRIME) % @m
+    end
+
+    def get_hash(value)
+      Digest::MD5.hexdigest(value.to_s).to_i(16)
+    end
+
+    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
+  end
+end

data/lib/{bloom_filter → qbloom_filter}/version.rb

@@ -1,3 +1,3 @@
 module BloomFilter
-  VERSION = "0.1.0"
+  VERSION = "0.3.4"
 end

data/{bloom_filter.gemspec → qbloom_filter.gemspec}

@@ -1,4 +1,4 @@
-require_relative 'lib/bloom_filter/version'
+require_relative 'lib/qbloom_filter/version'
 
 Gem::Specification.new do |spec|
   spec.name          = "qbloom_filter"
@@ -8,15 +8,15 @@ Gem::Specification.new do |spec|
 
   spec.licenses    = ['MIT']
   spec.summary       = %q{Bloom Filter}
-  spec.description   = %q{Simple Bloom Filter}
-  spec.homepage      = "https://github.com/superedriver/bloom-filter"
+  spec.description   = %q{Bloom Filter with union and intersection}
+  spec.homepage      = "https://github.com/superedriver/qbloom_filter"
   spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
 
   spec.metadata["allowed_push_host"] = "https://rubygems.org"
 
   spec.metadata["homepage_uri"] = spec.homepage
-  spec.metadata["source_code_uri"] = "https://github.com/superedriver/bloom-filter"
-  spec.metadata["changelog_uri"] = "https://github.com/superedriver/bloom-filter"
+  spec.metadata["source_code_uri"] = "https://github.com/superedriver/qbloom_filter"
+  spec.metadata["changelog_uri"] = "https://github.com/superedriver/qbloom_filter"
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.

metadata

@@ -1,16 +1,16 @@
 --- !ruby/object:Gem::Specification
 name: qbloom_filter
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.3.4
 platform: ruby
 authors:
 - qaz
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-09-27 00:00:00.000000000 Z
+date: 2020-09-29 00:00:00.000000000 Z
 dependencies: []
-description: Simple Bloom Filter
+description: Bloom Filter with union and intersection
 email:
 - qaz@qaz.qaz
 executables: []
@@ -30,17 +30,17 @@ files:
 - bin/rake
 - bin/rspec
 - bin/setup
-- bloom_filter.gemspec
-- lib/bloom_filter.rb
-- lib/bloom_filter/version.rb
-homepage: https://github.com/superedriver/bloom-filter
+- lib/qbloom_filter.rb
+- lib/qbloom_filter/version.rb
+- qbloom_filter.gemspec
+homepage: https://github.com/superedriver/qbloom_filter
 licenses:
 - MIT
 metadata:
   allowed_push_host: https://rubygems.org
-  homepage_uri: https://github.com/superedriver/bloom-filter
-  source_code_uri: https://github.com/superedriver/bloom-filter
-  changelog_uri: https://github.com/superedriver/bloom-filter
+  homepage_uri: https://github.com/superedriver/qbloom_filter
+  source_code_uri: https://github.com/superedriver/qbloom_filter
+  changelog_uri: https://github.com/superedriver/qbloom_filter
 post_install_message: 
 rdoc_options: []
 require_paths:

data/lib/bloom_filter.rb

@@ -1,63 +0,0 @@
-require "bloom_filter/version"
-require "bitset"
-require 'digest/md5'
-
-module BloomFilter
-  PRIME = 100_000_000_003
-  MAX_HASH_PARAM = 1000
-  class Filter
-    attr_reader :count
-
-    def initialize(capacity = 100, probability = 0.01)
-      # amount of inserted elements
-      @count = 0
-
-      #number of bits in the array
-      @m = (-(capacity * Math.log(probability)) / (Math.log(2) ** 2)).ceil
-
-      @bitset = Bitset.new(@m)
-
-      #number of hash functions that minimizes the probability of false positives
-      @k = (Math.log(2) * (@m / capacity)).ceil
-
-      # a, b params for hash functions
-      @hash_params = []
-      @k.times { @hash_params.push([rand(1000), rand(1000)]) }
-    end
-
-    def add(value)
-      x = get_hash(value)
-      was_inserted = true
-      @k.times do |i|
-        a, b = @hash_params[i]
-        position = get_position(a, b, x)
-        was_inserted = false unless @bitset[position]
-        @bitset[position] = true
-      end
-      @count += 1 unless was_inserted
-      value
-    end
-
-    def contains?(value)
-      x = get_hash(value)
-      result = true
-      @k.times do |i|
-        a, b = @hash_params[i]
-        result = false unless @bitset[get_position(a, b, x)]
-      end
-
-      result
-    end
-    alias :includes? :contains?
-
-    private
-
-    def get_position(a, b, val)
-      ((a * val + b) % PRIME) % @m
-    end
-
-    def get_hash(value)
-      Digest::MD5.hexdigest(value.to_s).to_i(16)
-    end
-  end
-end