text_generator 0.0.1
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/.gitignore +14 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +51 -0
- data/Rakefile +9 -0
- data/lib/text_generator/version.rb +3 -0
- data/lib/text_generator.rb +50 -0
- data/test/mg_test.rb +38 -0
- data/text_generator.gemspec +25 -0
- metadata +97 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 84ced4a5632f45b91e4f0d52e3f0452e73c9fed8
|
4
|
+
data.tar.gz: b5be156962d102f093f46ea9a94bfc7d4cdea2f6
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: b31f52848becb75c5b34836d6061abdf6919fdad6a60887bbead75f7586c6a279fd4c77363ba968fdce7d2842396d721db4d4de0d19f625f112b597851f4b392
|
7
|
+
data.tar.gz: f8a34e9a2f58ad0e4e97e9d23ca2b9d195e55aa6e7de147df11d7c5e1e4910623682f2adf1df452d9abb429ac713ab993ca09c09f66e80d5ae8b64d9206529ca
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2015 McFreely
|
2
|
+
|
3
|
+
MIT License
|
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
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,51 @@
|
|
1
|
+
# TextGenerator
|
2
|
+
|
3
|
+
A gem to automatically generate text, using various schemes.
|
4
|
+
At the moment, the only scheme available is a Markov-like algorithm, but more are to come soon.
|
5
|
+
|
6
|
+
## Installation
|
7
|
+
|
8
|
+
Add this line to your application's Gemfile:
|
9
|
+
|
10
|
+
```ruby
|
11
|
+
gem 'text_generator'
|
12
|
+
```
|
13
|
+
|
14
|
+
And then execute:
|
15
|
+
|
16
|
+
$ bundle
|
17
|
+
|
18
|
+
Or install it yourself as:
|
19
|
+
|
20
|
+
$ gem install text_generator
|
21
|
+
|
22
|
+
## Usage
|
23
|
+
|
24
|
+
### Markov Generator
|
25
|
+
Three simple steps:
|
26
|
+
|
27
|
+
First you need to initiate a new generator. The default values are an ngram of size 1 and a maximum length of text generated of 15 words. Play with those value to get the best results depending on your source text.
|
28
|
+
```ruby
|
29
|
+
generator = MarkovGenerator.new(n = 1, genmax = 15)
|
30
|
+
```
|
31
|
+
|
32
|
+
Second you need to feed the generator some source text for it to be able to output something original later.
|
33
|
+
```ruby
|
34
|
+
generator.feed(line)
|
35
|
+
```
|
36
|
+
|
37
|
+
Finally, generate a brand new piece of text, unknown until now to all humanity, past, present and future.
|
38
|
+
|
39
|
+
```ruby
|
40
|
+
generator.generate
|
41
|
+
```
|
42
|
+
|
43
|
+
Voila.
|
44
|
+
|
45
|
+
## Contributing
|
46
|
+
|
47
|
+
1. Fork it ( https://github.com/[my-github-username]/text_generator/fork )
|
48
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
49
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
50
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
51
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,50 @@
|
|
1
|
+
require "text_generator/version"
|
2
|
+
|
3
|
+
class MarkovGenerator
|
4
|
+
attr_accessor :ngrams, :beginnings, :genmax
|
5
|
+
|
6
|
+
def initialize(n, genmax)
|
7
|
+
@size = n
|
8
|
+
@ngrams = {}
|
9
|
+
@genmax = genmax
|
10
|
+
@beginnings = []
|
11
|
+
end
|
12
|
+
|
13
|
+
def tokenize(line)
|
14
|
+
line.strip.split(" ")
|
15
|
+
end
|
16
|
+
|
17
|
+
def feed(line)
|
18
|
+
tokens = tokenize(line)
|
19
|
+
|
20
|
+
return if tokens.length < @size
|
21
|
+
|
22
|
+
@beginnings << tokens[0..@size-1]
|
23
|
+
|
24
|
+
(0..(tokens.length - @size)).each do |i|
|
25
|
+
ngram = tokens[i..i+@size-1].to_a
|
26
|
+
next_gram = [tokens[i+@size]]
|
27
|
+
if @ngrams.has_key? ngram
|
28
|
+
@ngrams[ngram] << next_gram
|
29
|
+
else
|
30
|
+
@ngrams[ngram] = next_gram
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
def generate
|
36
|
+
current = @beginnings.sample
|
37
|
+
output = current.to_a
|
38
|
+
while output.length <= @genmax-1
|
39
|
+
if @ngrams.has_key? current
|
40
|
+
possible_next = @ngrams[current].flatten
|
41
|
+
next_gram = possible_next.sample
|
42
|
+
output << next_gram
|
43
|
+
current = output.last(@size)
|
44
|
+
else
|
45
|
+
break
|
46
|
+
end
|
47
|
+
end
|
48
|
+
return output.join(" ")
|
49
|
+
end
|
50
|
+
end
|
data/test/mg_test.rb
ADDED
@@ -0,0 +1,38 @@
|
|
1
|
+
require "minitest/autorun"
|
2
|
+
|
3
|
+
require "text_generator"
|
4
|
+
|
5
|
+
class MarkovTest < Minitest::Unit::TestCase
|
6
|
+
|
7
|
+
def setup
|
8
|
+
@text = "Le chat aime les souris vertes et grasses"
|
9
|
+
@text_array = @text.split(" ")
|
10
|
+
@n = rand(1..5)
|
11
|
+
@genmax = rand(1..50)
|
12
|
+
@generator = MarkovGenerator.new(@n, @genmax)
|
13
|
+
@generator.feed(@text)
|
14
|
+
end
|
15
|
+
|
16
|
+
def test_tokenize_is_correct
|
17
|
+
assert_equal @generator.tokenize(@text), @text_array
|
18
|
+
end
|
19
|
+
|
20
|
+
def test_feed_line
|
21
|
+
assert_equal @generator.beginnings, [@text_array.first(@n)]
|
22
|
+
end
|
23
|
+
|
24
|
+
def test_ngram_length
|
25
|
+
@generator.ngrams.each_key do |k|
|
26
|
+
assert_equal k.length, @n
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
def test_genmax
|
31
|
+
sentence = @generator.generate.split(" ")
|
32
|
+
assert_operator sentence.length, :<=, @genmax
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
|
37
|
+
|
38
|
+
|
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'text_generator/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "text_generator"
|
8
|
+
spec.version = TextGenerator::VERSION
|
9
|
+
spec.authors = ["McFreely"]
|
10
|
+
spec.email = ["paulmcfreely@gmail.com"]
|
11
|
+
spec.summary = %q{A gem to automatically generate text, using various schemas}
|
12
|
+
spec.description = %q{A gem to generate text. At the moment, the only method available is a Markov Model Generator, but more are to come later.}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_runtime_dependency 'scalpel'
|
22
|
+
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.7"
|
24
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
25
|
+
end
|
metadata
ADDED
@@ -0,0 +1,97 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: text_generator
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- McFreely
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-01-18 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: scalpel
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.7'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.7'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
description: A gem to generate text. At the moment, the only method available is a
|
56
|
+
Markov Model Generator, but more are to come later.
|
57
|
+
email:
|
58
|
+
- paulmcfreely@gmail.com
|
59
|
+
executables: []
|
60
|
+
extensions: []
|
61
|
+
extra_rdoc_files: []
|
62
|
+
files:
|
63
|
+
- ".gitignore"
|
64
|
+
- Gemfile
|
65
|
+
- LICENSE.txt
|
66
|
+
- README.md
|
67
|
+
- Rakefile
|
68
|
+
- lib/text_generator.rb
|
69
|
+
- lib/text_generator/version.rb
|
70
|
+
- test/mg_test.rb
|
71
|
+
- text_generator.gemspec
|
72
|
+
homepage: ''
|
73
|
+
licenses:
|
74
|
+
- MIT
|
75
|
+
metadata: {}
|
76
|
+
post_install_message:
|
77
|
+
rdoc_options: []
|
78
|
+
require_paths:
|
79
|
+
- lib
|
80
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
81
|
+
requirements:
|
82
|
+
- - ">="
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
version: '0'
|
85
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
requirements: []
|
91
|
+
rubyforge_project:
|
92
|
+
rubygems_version: 2.4.2
|
93
|
+
signing_key:
|
94
|
+
specification_version: 4
|
95
|
+
summary: A gem to automatically generate text, using various schemas
|
96
|
+
test_files:
|
97
|
+
- test/mg_test.rb
|