bloomin 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +3 -0
- data/License.txt +22 -0
- data/README.md +16 -0
- data/Rakefile +1 -0
- data/bloomin.gemspec +22 -0
- data/lib/bloomin.rb +1 -0
- data/lib/bloomin/filter.rb +62 -0
- data/lib/bloomin/version.rb +3 -0
- metadata +86 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/License.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
(The MIT License)
|
2
|
+
|
3
|
+
Copyright (c) 2012-2013 Alex Okolish
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
'Software'), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
19
|
+
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
20
|
+
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
21
|
+
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
22
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
# Bloomin
|
2
|
+
|
3
|
+
Bloomin is a really quickly hacked together example of a bloom filter.
|
4
|
+
In fact, I'm not even sure it's written properly. So, use this at your
|
5
|
+
own risk.
|
6
|
+
|
7
|
+
## Usage
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
filter = Bloomin::Filter.new
|
11
|
+
filter.is_word? "aoeu" # => false
|
12
|
+
filter.is_word? "cats" # => true
|
13
|
+
```
|
14
|
+
|
15
|
+
Bloomin assumes that the file `/usr/share/dict/words` exists. If not,
|
16
|
+
stuff will blow up.
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/bloomin.gemspec
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'bloomin/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "bloomin"
|
8
|
+
gem.version = Bloomin::VERSION
|
9
|
+
gem.authors = ["Alex Okolish"]
|
10
|
+
gem.email = ["alex.okolish@gmail.com"]
|
11
|
+
gem.description = %q{hacked together bloom filter}
|
12
|
+
gem.summary = %q{use at your own risk}
|
13
|
+
gem.homepage = "http://github.com/aokolish/bloomin"
|
14
|
+
|
15
|
+
gem.files = `git ls-files`.split($/)
|
16
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
|
20
|
+
gem.add_runtime_dependency("fnv", [">= 0.2.0"])
|
21
|
+
gem.add_development_dependency("rspec", [">= 2.2.0"])
|
22
|
+
end
|
data/lib/bloomin.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'bloomin/filter'
|
@@ -0,0 +1,62 @@
|
|
1
|
+
require 'fnv'
|
2
|
+
|
3
|
+
module Bloomin
|
4
|
+
class Filter
|
5
|
+
attr_reader :bloom
|
6
|
+
attr_accessor :size
|
7
|
+
|
8
|
+
def initialize(opts = {})
|
9
|
+
@size = opts[:size] || 5000000
|
10
|
+
@bloom = Array.new(self.size).fill(0)
|
11
|
+
|
12
|
+
load_words
|
13
|
+
end
|
14
|
+
|
15
|
+
def is_word?(word)
|
16
|
+
integers = hash(word)
|
17
|
+
integers.each do |i|
|
18
|
+
if self.bloom[i] == 0
|
19
|
+
puts "not a word - #{word}" if debug?
|
20
|
+
false
|
21
|
+
else
|
22
|
+
puts "probably, a word - #{word}, #{probability}" if debug?
|
23
|
+
true
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
private
|
29
|
+
|
30
|
+
def load_words
|
31
|
+
File.open('/usr/share/dict/words','r').each_with_index do |word, i|
|
32
|
+
word.strip!
|
33
|
+
add_to_bloom(word)
|
34
|
+
@dict_size = i
|
35
|
+
end
|
36
|
+
end
|
37
|
+
|
38
|
+
# returns array of integer values
|
39
|
+
def hash(word)
|
40
|
+
hex = FNV.new.fnv1a_32(word) % self.size
|
41
|
+
[hex]
|
42
|
+
end
|
43
|
+
|
44
|
+
# flips bits in bloom if not already set
|
45
|
+
def add_to_bloom(word)
|
46
|
+
integers = hash(word)
|
47
|
+
integers.each do |i|
|
48
|
+
self.bloom[i] = 1 unless self.bloom[i] == 1
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
def probability
|
53
|
+
num_hashes = 1
|
54
|
+
(((1 - Math.exp((-num_hashes * @dict_size) / self.size )) ** num_hashes) * 100).round(2).to_s +
|
55
|
+
'% chance of false positive'
|
56
|
+
end
|
57
|
+
|
58
|
+
def debug?
|
59
|
+
ENV['DEBUG'] == 'true'
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
metadata
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: bloomin
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Alex Okolish
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-01-28 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: fnv
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 0.2.0
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 0.2.0
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: rspec
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: 2.2.0
|
38
|
+
type: :development
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: 2.2.0
|
46
|
+
description: hacked together bloom filter
|
47
|
+
email:
|
48
|
+
- alex.okolish@gmail.com
|
49
|
+
executables: []
|
50
|
+
extensions: []
|
51
|
+
extra_rdoc_files: []
|
52
|
+
files:
|
53
|
+
- .gitignore
|
54
|
+
- Gemfile
|
55
|
+
- License.txt
|
56
|
+
- README.md
|
57
|
+
- Rakefile
|
58
|
+
- bloomin.gemspec
|
59
|
+
- lib/bloomin.rb
|
60
|
+
- lib/bloomin/filter.rb
|
61
|
+
- lib/bloomin/version.rb
|
62
|
+
homepage: http://github.com/aokolish/bloomin
|
63
|
+
licenses: []
|
64
|
+
post_install_message:
|
65
|
+
rdoc_options: []
|
66
|
+
require_paths:
|
67
|
+
- lib
|
68
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
69
|
+
none: false
|
70
|
+
requirements:
|
71
|
+
- - ! '>='
|
72
|
+
- !ruby/object:Gem::Version
|
73
|
+
version: '0'
|
74
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
75
|
+
none: false
|
76
|
+
requirements:
|
77
|
+
- - ! '>='
|
78
|
+
- !ruby/object:Gem::Version
|
79
|
+
version: '0'
|
80
|
+
requirements: []
|
81
|
+
rubyforge_project:
|
82
|
+
rubygems_version: 1.8.23
|
83
|
+
signing_key:
|
84
|
+
specification_version: 3
|
85
|
+
summary: use at your own risk
|
86
|
+
test_files: []
|