string_entropy 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.codeclimate.yml +16 -0
- data/.gitignore +9 -0
- data/.rspec +2 -0
- data/.rubocop.yml +1156 -0
- data/.travis.yml +6 -0
- data/Gemfile +9 -0
- data/LICENSE.txt +21 -0
- data/README.md +137 -0
- data/Rakefile +6 -0
- data/bin/console +7 -0
- data/bin/setup +6 -0
- data/lib/string_entropy.rb +16 -0
- data/lib/string_entropy/error.rb +23 -0
- data/lib/string_entropy/info.rb +64 -0
- data/lib/string_entropy/string.rb +5 -0
- data/lib/string_entropy/version.rb +3 -0
- data/string_entropy.gemspec +36 -0
- metadata +116 -0
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 anothermh
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,137 @@
|
|
1
|
+
# string_entropy
|
2
|
+
|
3
|
+
[](https://travis-ci.org/anothermh/string_entropy)
|
4
|
+
[](https://codeclimate.com/github/anothermh/string_entropy)
|
5
|
+
[](https://codeclimate.com/github/anothermh/string_entropy/coverage)
|
6
|
+
|
7
|
+
Outputs the information entropy, Shannon entropy, and metric entropy of any given `ASCII_8BIT` string.
|
8
|
+
|
9
|
+
More information on entropy:
|
10
|
+
|
11
|
+
* https://en.wikipedia.org/wiki/Entropy_%28information_theory%29
|
12
|
+
* https://en.wikibooks.org/wiki/An_Intuitive_Guide_to_the_Concept_of_Entropy_Arising_in_Various_Sectors_of_Science
|
13
|
+
|
14
|
+
## Installation
|
15
|
+
|
16
|
+
Add this line to your application's Gemfile:
|
17
|
+
|
18
|
+
```ruby
|
19
|
+
gem 'string_entropy'
|
20
|
+
```
|
21
|
+
|
22
|
+
And then execute:
|
23
|
+
|
24
|
+
$ bundle
|
25
|
+
|
26
|
+
Or install it yourself as:
|
27
|
+
|
28
|
+
$ gem install string_entropy
|
29
|
+
|
30
|
+
## Usage
|
31
|
+
|
32
|
+
As an extension to the `String` class:
|
33
|
+
|
34
|
+
```ruby
|
35
|
+
"password".entropy
|
36
|
+
=> 52.55884486664758
|
37
|
+
```
|
38
|
+
|
39
|
+
With the `StringEntropy::Info` class:
|
40
|
+
|
41
|
+
```ruby
|
42
|
+
string_entropy = StringEntropy.info("password")
|
43
|
+
=> #<StringEntropy::Info:0x007fb864091590
|
44
|
+
@count={"p"=>1.0, "a"=>1.0, "s"=>2.0, "w"=>1.0, "o"=>1.0, "r"=>1.0, "d"=>1.0},
|
45
|
+
@frequency=
|
46
|
+
{"p"=>0.125,
|
47
|
+
"a"=>0.125,
|
48
|
+
"s"=>0.25,
|
49
|
+
"w"=>0.125,
|
50
|
+
"o"=>0.125,
|
51
|
+
"r"=>0.125,
|
52
|
+
"d"=>0.125},
|
53
|
+
@information_entropy=52.55884486664758,
|
54
|
+
@metric_entropy=0.34375,
|
55
|
+
@shannon_entropy=2.75,
|
56
|
+
@shannon_formulas=
|
57
|
+
["H(X) = -[ ((0.125 * Math.log2(0.125))+(0.125 * Math.log2(0.125))+(0.25 * Math.log2(0.25))+(0.125 * Math.log2(0.125))+(0.125 * Math.log2(0.125))+(0.125 * Math.log2(0.125))+(0.125 * Math.log2(0.125))) ]",
|
58
|
+
"H(X) = -[ ((-0.375)+(-0.375)+(-0.5)+(-0.375)+(-0.375)+(-0.375)+(-0.375)) ]",
|
59
|
+
"H(X) = -[ (-2.75) ]",
|
60
|
+
"H(X) = 2.75"],
|
61
|
+
@string="password">
|
62
|
+
|
63
|
+
# Original string
|
64
|
+
string_entropy.string
|
65
|
+
=> "password"
|
66
|
+
|
67
|
+
# String encoding, currently only supports ASCII_8BIT
|
68
|
+
string_entropy.encoding
|
69
|
+
=> "ASCII-8BIT"
|
70
|
+
|
71
|
+
# The commonly described "entropy" of a string; Math.log2(total_possible_chars^string_length)
|
72
|
+
string_entropy.entropy
|
73
|
+
=> 52.55884486664758
|
74
|
+
|
75
|
+
# Alias for .entropy method
|
76
|
+
string_entropy.information_entropy
|
77
|
+
=> 52.55884486664758
|
78
|
+
|
79
|
+
# The Shannon entropy value
|
80
|
+
string_entropy.shannon_entropy
|
81
|
+
=> 2.75
|
82
|
+
|
83
|
+
# The metric entropy value (Shannon entropy divided by string length)
|
84
|
+
string_entropy.metric_entropy
|
85
|
+
=> 0.34375
|
86
|
+
|
87
|
+
# The count of each character
|
88
|
+
string_entropy.count
|
89
|
+
=> {
|
90
|
+
"p" => 1.0,
|
91
|
+
"a" => 1.0,
|
92
|
+
"s" => 2.0,
|
93
|
+
"w" => 1.0,
|
94
|
+
"o" => 1.0,
|
95
|
+
"r" => 1.0,
|
96
|
+
"d" => 1.0
|
97
|
+
}
|
98
|
+
|
99
|
+
# The frequency/percentage of each character
|
100
|
+
string_entropy.frequency
|
101
|
+
=> {
|
102
|
+
"p" => 0.125,
|
103
|
+
"a" => 0.125,
|
104
|
+
"s" => 0.25,
|
105
|
+
"w" => 0.125,
|
106
|
+
"o" => 0.125,
|
107
|
+
"r" => 0.125,
|
108
|
+
"d" => 0.125
|
109
|
+
}
|
110
|
+
|
111
|
+
# This is how the Shannon entropy is calculated
|
112
|
+
string_entropy.shannon_formulas
|
113
|
+
=> [
|
114
|
+
[0] "H(X) = -[ ((0.125 * Math.log2(0.125))+(0.125 * Math.log2(0.125))+(0.25 * Math.log2(0.25))+(0.125 * Math.log2(0.125))+(0.125 * Math.log2(0.125))+(0.125 * Math.log2(0.125))+(0.125 * Math.log2(0.125))) ]",
|
115
|
+
[1] "H(X) = -[ ((-0.375)+(-0.375)+(-0.5)+(-0.375)+(-0.375)+(-0.375)+(-0.375)) ]",
|
116
|
+
[2] "H(X) = -[ (-2.75) ]",
|
117
|
+
[3] "H(X) = 2.75"
|
118
|
+
]
|
119
|
+
```
|
120
|
+
|
121
|
+
## Development
|
122
|
+
|
123
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
124
|
+
|
125
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
126
|
+
|
127
|
+
## Credits
|
128
|
+
|
129
|
+
Inspired by http://www.shannonentropy.netmark.pl.
|
130
|
+
|
131
|
+
## Contributing
|
132
|
+
|
133
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/anothermh/string_entropy.
|
134
|
+
|
135
|
+
## License
|
136
|
+
|
137
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/bin/console
ADDED
data/bin/setup
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
require "string_entropy/error"
|
2
|
+
require "string_entropy/info"
|
3
|
+
require "string_entropy/version"
|
4
|
+
require "string_entropy/string"
|
5
|
+
|
6
|
+
module StringEntropy
|
7
|
+
|
8
|
+
def self.info(string)
|
9
|
+
StringEntropy::Info.new(string)
|
10
|
+
end
|
11
|
+
|
12
|
+
def self.example
|
13
|
+
StringEntropy::Info.new("password")
|
14
|
+
end
|
15
|
+
|
16
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
module StringEntropy
|
2
|
+
|
3
|
+
class Error < StandardError; end
|
4
|
+
|
5
|
+
class BadEncoding < Error
|
6
|
+
def initialize
|
7
|
+
super("The string could not be converted to ASCII_8BIT encoding")
|
8
|
+
end
|
9
|
+
end
|
10
|
+
|
11
|
+
class StringMismatch < Error
|
12
|
+
def initialize
|
13
|
+
super("The string contains invalid ASCII_8BIT characters (only character codes 32..126 are valid)")
|
14
|
+
end
|
15
|
+
end
|
16
|
+
|
17
|
+
class NilHasZeroEntropy < Error
|
18
|
+
def initialize
|
19
|
+
super("nil values cannot be evaluated as strings and have zero entropy")
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
end
|
@@ -0,0 +1,64 @@
|
|
1
|
+
module StringEntropy
|
2
|
+
class Info
|
3
|
+
|
4
|
+
attr_reader :string,
|
5
|
+
:encoding,
|
6
|
+
:count,
|
7
|
+
:frequency,
|
8
|
+
:information_entropy,
|
9
|
+
:shannon_entropy,
|
10
|
+
:metric_entropy
|
11
|
+
|
12
|
+
# The common defintion of "entropy" when working with strings
|
13
|
+
alias_method :entropy, :information_entropy
|
14
|
+
|
15
|
+
# Supports only ASCII_8BIT encoding
|
16
|
+
POSSIBLE_CHARS = 95.freeze
|
17
|
+
|
18
|
+
def initialize(string=nil)
|
19
|
+
@string = ascii(string)
|
20
|
+
@count = @string.split("").each.with_object(Hash.new(0.to_f)) { |char, hash| hash[char] += 1 }.freeze
|
21
|
+
@frequency = @count.each_with_object(Hash.new) { |(char,count),frequency| frequency[char] = (count / @string.length) }.freeze
|
22
|
+
|
23
|
+
@information_entropy = Math.log2(POSSIBLE_CHARS**@string.length).freeze
|
24
|
+
@shannon_entropy = -(@frequency.values.map { |x| x * Math.log2(x) }.inject(:+)).freeze
|
25
|
+
@metric_entropy = (@shannon_entropy / @string.length).freeze
|
26
|
+
|
27
|
+
@shannon_formulas = shannon_formulas
|
28
|
+
|
29
|
+
self.freeze
|
30
|
+
end
|
31
|
+
|
32
|
+
# Show the math behind calculating Shannon Entropy as an array of the steps taken
|
33
|
+
def shannon_formulas
|
34
|
+
formulas = []
|
35
|
+
formulas << @frequency.values.map { |x| "(#{x} * Math.log2(#{x}))" }.join("+")
|
36
|
+
formulas << @frequency.values.map { |x| "(#{x * Math.log2(x)})" }.join("+")
|
37
|
+
formulas << "#{@frequency.values.map { |x| x * Math.log2(x) }.inject(:+)}"
|
38
|
+
formulas.map! { |x| "-[ (#{x}) ]" }
|
39
|
+
formulas << "#{@shannon_entropy}"
|
40
|
+
formulas.map! { |x| "H(X) = #{x}"}
|
41
|
+
formulas.freeze
|
42
|
+
end
|
43
|
+
|
44
|
+
private
|
45
|
+
|
46
|
+
def ascii(string)
|
47
|
+
raise NilHasZeroEntropy unless string
|
48
|
+
|
49
|
+
begin
|
50
|
+
ascii = string.encode(Encoding::ASCII_8BIT)
|
51
|
+
rescue Encoding::UndefinedConversionError
|
52
|
+
raise BadEncoding
|
53
|
+
end
|
54
|
+
|
55
|
+
safe_ascii = ascii.split("").select { |x| true if (32..126) === x.ord }.join("")
|
56
|
+
raise StringMismatch unless ascii == safe_ascii && ascii == string
|
57
|
+
|
58
|
+
@encoding = Encoding::ASCII_8BIT.name
|
59
|
+
|
60
|
+
safe_ascii.freeze
|
61
|
+
end
|
62
|
+
|
63
|
+
end
|
64
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'string_entropy/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "string_entropy"
|
8
|
+
spec.version = StringEntropy::VERSION
|
9
|
+
spec.authors = ["anothermh"]
|
10
|
+
|
11
|
+
spec.summary = "Gets the entropy for a given string"
|
12
|
+
spec.description = "Outputs a variety of information on the entropy of a given string"
|
13
|
+
spec.homepage = "https://github.com/anothermh/string_entropy"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
# Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
|
17
|
+
# to allow pushing to a single host or delete this section to allow pushing to any host.
|
18
|
+
# if spec.respond_to?(:metadata)
|
19
|
+
# spec.metadata['allowed_push_host'] = "TODO: Set to 'http://mygemserver.com'"
|
20
|
+
# else
|
21
|
+
# raise "RubyGems 2.0 or newer is required to protect against " \
|
22
|
+
# "public gem pushes."
|
23
|
+
# end
|
24
|
+
|
25
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
26
|
+
f.match(%r{^(test|spec|features)/})
|
27
|
+
end
|
28
|
+
spec.bindir = "exe"
|
29
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
30
|
+
spec.require_paths = ["lib"]
|
31
|
+
|
32
|
+
spec.add_development_dependency "bundler", "~> 1.13"
|
33
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
34
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
35
|
+
spec.add_development_dependency "pry", "~> 0.10.4"
|
36
|
+
end
|
metadata
ADDED
@@ -0,0 +1,116 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: string_entropy
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- anothermh
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-11-20 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.13'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.13'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: pry
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 0.10.4
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 0.10.4
|
69
|
+
description: Outputs a variety of information on the entropy of a given string
|
70
|
+
email:
|
71
|
+
executables: []
|
72
|
+
extensions: []
|
73
|
+
extra_rdoc_files: []
|
74
|
+
files:
|
75
|
+
- ".codeclimate.yml"
|
76
|
+
- ".gitignore"
|
77
|
+
- ".rspec"
|
78
|
+
- ".rubocop.yml"
|
79
|
+
- ".travis.yml"
|
80
|
+
- Gemfile
|
81
|
+
- LICENSE.txt
|
82
|
+
- README.md
|
83
|
+
- Rakefile
|
84
|
+
- bin/console
|
85
|
+
- bin/setup
|
86
|
+
- lib/string_entropy.rb
|
87
|
+
- lib/string_entropy/error.rb
|
88
|
+
- lib/string_entropy/info.rb
|
89
|
+
- lib/string_entropy/string.rb
|
90
|
+
- lib/string_entropy/version.rb
|
91
|
+
- string_entropy.gemspec
|
92
|
+
homepage: https://github.com/anothermh/string_entropy
|
93
|
+
licenses:
|
94
|
+
- MIT
|
95
|
+
metadata: {}
|
96
|
+
post_install_message:
|
97
|
+
rdoc_options: []
|
98
|
+
require_paths:
|
99
|
+
- lib
|
100
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
101
|
+
requirements:
|
102
|
+
- - ">="
|
103
|
+
- !ruby/object:Gem::Version
|
104
|
+
version: '0'
|
105
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
106
|
+
requirements:
|
107
|
+
- - ">="
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '0'
|
110
|
+
requirements: []
|
111
|
+
rubyforge_project:
|
112
|
+
rubygems_version: 2.5.1
|
113
|
+
signing_key:
|
114
|
+
specification_version: 4
|
115
|
+
summary: Gets the entropy for a given string
|
116
|
+
test_files: []
|