qbloom_filter 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: c8384171d7c3a67af223b2425c08ec9fa8ccf4c784d658f5951b37642708a384
+  data.tar.gz: a50a3260fcd55e0284e85a1b78f4f34dce3f5ff9bf4a56add2cdebc3aecd1d07
+SHA512:
+  metadata.gz: 9fe8aeae6469952e99be203cbe4c12cf03317b7eb9499a2bde069cf11c980d3f7746d29fcb2853451ae82ff5d244f87491103bd15d9125e445f44bb63bbabbfb
+  data.tar.gz: 4a43600e93388a498797dcb6706801b105c470602e0449da6bd37faf885ea660f17c3a9a5fcbfede9f1860af9c0cc8fc47a960073ba893e523fca13d4a8e6590

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+/.idea/

data/.rspec

@@ -0,0 +1 @@
+--require spec_helper

data/Gemfile

@@ -0,0 +1,9 @@
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in bloom_filter.gemspec
+gemspec
+
+gem "rake", "~> 12.0"
+
+gem "bitset", "~> 1.2"
+gem "rspec", "~> 3.0"

data/Gemfile.lock

@@ -0,0 +1,36 @@
+PATH
+  remote: .
+  specs:
+    qbloom_filter (0.1.0)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    bitset (1.2.0)
+    diff-lcs (1.4.4)
+    rake (12.3.3)
+    rspec (3.9.0)
+      rspec-core (~> 3.9.0)
+      rspec-expectations (~> 3.9.0)
+      rspec-mocks (~> 3.9.0)
+    rspec-core (3.9.2)
+      rspec-support (~> 3.9.3)
+    rspec-expectations (3.9.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.9.0)
+    rspec-mocks (3.9.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.9.0)
+    rspec-support (3.9.3)
+
+PLATFORMS
+  x64-mingw32
+
+DEPENDENCIES
+  bitset (~> 1.2)
+  qbloom_filter!
+  rake (~> 12.0)
+  rspec (~> 3.0)
+
+BUNDLED WITH
+   2.1.4

data/README.md

@@ -0,0 +1,45 @@
+# BloomFilter
+
+A Bloom filter is a space-efficient probabilistic data structure
+[Wiki](https://en.wikipedia.org/wiki/Bloom_filter)
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'bloom_filter'
+```
+
+And then execute:
+
+    $ bundle install
+
+Or install it yourself as:
+
+    $ gem install bloom_filter
+
+## Usage
+
+After installation the instance can be created. 
+And two parameters can be used to describe the bloom filter: 
+
+* first - number of items that are be inserted(default: 100)
+* second - False Positive probability(default: 0.01)
+
+```ruby
+bloom_filter = BloomFilter::Filter.new(1000, 0.001)
+```
+
+#### API
+__add(value)__ - add item into filter
+
+__includes?(value)__ - check if filter includes the value
+
+__contains?(value)__ - alias of __includes?(value)__
+
+__count__ - returns number of inserted items
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/superedriver/bloom_filter
+

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+task :default => :spec

data/bin/bundle

@@ -0,0 +1,114 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+#
+# This file was generated by Bundler.
+#
+# The application 'bundle' is installed as part of a gem, and
+# this file is here to facilitate running it.
+#
+
+require "rubygems"
+
+m = Module.new do
+  module_function
+
+  def invoked_as_script?
+    File.expand_path($0) == File.expand_path(__FILE__)
+  end
+
+  def env_var_version
+    ENV["BUNDLER_VERSION"]
+  end
+
+  def cli_arg_version
+    return unless invoked_as_script? # don't want to hijack other binstubs
+    return unless "update".start_with?(ARGV.first || " ") # must be running `bundle update`
+    bundler_version = nil
+    update_index = nil
+    ARGV.each_with_index do |a, i|
+      if update_index && update_index.succ == i && a =~ Gem::Version::ANCHORED_VERSION_PATTERN
+        bundler_version = a
+      end
+      next unless a =~ /\A--bundler(?:[= ](#{Gem::Version::VERSION_PATTERN}))?\z/
+      bundler_version = $1
+      update_index = i
+    end
+    bundler_version
+  end
+
+  def gemfile
+    gemfile = ENV["BUNDLE_GEMFILE"]
+    return gemfile if gemfile && !gemfile.empty?
+
+    File.expand_path("../../Gemfile", __FILE__)
+  end
+
+  def lockfile
+    lockfile =
+      case File.basename(gemfile)
+      when "gems.rb" then gemfile.sub(/\.rb$/, gemfile)
+      else "#{gemfile}.lock"
+      end
+    File.expand_path(lockfile)
+  end
+
+  def lockfile_version
+    return unless File.file?(lockfile)
+    lockfile_contents = File.read(lockfile)
+    return unless lockfile_contents =~ /\n\nBUNDLED WITH\n\s{2,}(#{Gem::Version::VERSION_PATTERN})\n/
+    Regexp.last_match(1)
+  end
+
+  def bundler_version
+    @bundler_version ||=
+      env_var_version || cli_arg_version ||
+        lockfile_version
+  end
+
+  def bundler_requirement
+    return "#{Gem::Requirement.default}.a" unless bundler_version
+
+    bundler_gem_version = Gem::Version.new(bundler_version)
+
+    requirement = bundler_gem_version.approximate_recommendation
+
+    return requirement unless Gem::Version.new(Gem::VERSION) < Gem::Version.new("2.7.0")
+
+    requirement += ".a" if bundler_gem_version.prerelease?
+
+    requirement
+  end
+
+  def load_bundler!
+    ENV["BUNDLE_GEMFILE"] ||= gemfile
+
+    activate_bundler
+  end
+
+  def activate_bundler
+    gem_error = activation_error_handling do
+      gem "bundler", bundler_requirement
+    end
+    return if gem_error.nil?
+    require_error = activation_error_handling do
+      require "bundler/version"
+    end
+    return if require_error.nil? && Gem::Requirement.new(bundler_requirement).satisfied_by?(Gem::Version.new(Bundler::VERSION))
+    warn "Activating bundler (#{bundler_requirement}) failed:\n#{gem_error.message}\n\nTo install the version of bundler this project requires, run `gem install bundler -v '#{bundler_requirement}'`"
+    exit 42
+  end
+
+  def activation_error_handling
+    yield
+    nil
+  rescue StandardError, LoadError => e
+    e
+  end
+end
+
+m.load_bundler!
+
+if m.invoked_as_script?
+  load Gem.bin_path("bundler", "bundle")
+end

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "bloom_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.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/htmldiff

@@ -0,0 +1,29 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+#
+# This file was generated by Bundler.
+#
+# The application 'htmldiff' is installed as part of a gem, and
+# this file is here to facilitate running it.
+#
+
+require "pathname"
+ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../../Gemfile",
+  Pathname.new(__FILE__).realpath)
+
+bundle_binstub = File.expand_path("../bundle", __FILE__)
+
+if File.file?(bundle_binstub)
+  if File.read(bundle_binstub, 300) =~ /This file was generated by Bundler/
+    load(bundle_binstub)
+  else
+    abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
+Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
+  end
+end
+
+require "rubygems"
+require "bundler/setup"
+
+load Gem.bin_path("diff-lcs", "htmldiff")

data/bin/ldiff

@@ -0,0 +1,29 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+#
+# This file was generated by Bundler.
+#
+# The application 'ldiff' is installed as part of a gem, and
+# this file is here to facilitate running it.
+#
+
+require "pathname"
+ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../../Gemfile",
+  Pathname.new(__FILE__).realpath)
+
+bundle_binstub = File.expand_path("../bundle", __FILE__)
+
+if File.file?(bundle_binstub)
+  if File.read(bundle_binstub, 300) =~ /This file was generated by Bundler/
+    load(bundle_binstub)
+  else
+    abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
+Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
+  end
+end
+
+require "rubygems"
+require "bundler/setup"
+
+load Gem.bin_path("diff-lcs", "ldiff")

data/bin/rake

@@ -0,0 +1,29 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+#
+# This file was generated by Bundler.
+#
+# The application 'rake' is installed as part of a gem, and
+# this file is here to facilitate running it.
+#
+
+require "pathname"
+ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../../Gemfile",
+  Pathname.new(__FILE__).realpath)
+
+bundle_binstub = File.expand_path("../bundle", __FILE__)
+
+if File.file?(bundle_binstub)
+  if File.read(bundle_binstub, 300) =~ /This file was generated by Bundler/
+    load(bundle_binstub)
+  else
+    abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
+Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
+  end
+end
+
+require "rubygems"
+require "bundler/setup"
+
+load Gem.bin_path("rake", "rake")

data/bin/rspec

@@ -0,0 +1,29 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+#
+# This file was generated by Bundler.
+#
+# The application 'rspec' is installed as part of a gem, and
+# this file is here to facilitate running it.
+#
+
+require "pathname"
+ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../../Gemfile",
+  Pathname.new(__FILE__).realpath)
+
+bundle_binstub = File.expand_path("../bundle", __FILE__)
+
+if File.file?(bundle_binstub)
+  if File.read(bundle_binstub, 300) =~ /This file was generated by Bundler/
+    load(bundle_binstub)
+  else
+    abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
+Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
+  end
+end
+
+require "rubygems"
+require "bundler/setup"
+
+load Gem.bin_path("rspec-core", "rspec")

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/bloom_filter.gemspec

@@ -0,0 +1,29 @@
+require_relative 'lib/bloom_filter/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "qbloom_filter"
+  spec.version       = BloomFilter::VERSION
+  spec.authors       = ["qaz"]
+  spec.email         = ["qaz@qaz.qaz"]
+
+  spec.licenses    = ['MIT']
+  spec.summary       = %q{Bloom Filter}
+  spec.description   = %q{Simple Bloom Filter}
+  spec.homepage      = "https://github.com/superedriver/bloom-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"
+
+  # 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.
+  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+end

data/lib/bloom_filter.rb

@@ -0,0 +1,63 @@
+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

data/lib/bloom_filter/version.rb

@@ -0,0 +1,3 @@
+module BloomFilter
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,63 @@
+--- !ruby/object:Gem::Specification
+name: qbloom_filter
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- qaz
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2020-09-27 00:00:00.000000000 Z
+dependencies: []
+description: Simple Bloom Filter
+email:
+- qaz@qaz.qaz
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- Gemfile
+- Gemfile.lock
+- README.md
+- Rakefile
+- bin/bundle
+- bin/console
+- bin/htmldiff
+- bin/ldiff
+- 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
+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
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.3.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: Bloom Filter
+test_files: []