guillaume 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +21 -0
- data/.rspec +1 -0
- data/Gemfile +8 -0
- data/LICENSE.txt +22 -0
- data/README.markdown +46 -0
- data/Rakefile +4 -0
- data/bin/guillaume +38 -0
- data/config/database.yaml.example +1 -0
- data/data/call_of_the_wild.txt +400 -0
- data/data/heart_of_darkness.txt +228 -0
- data/data/moby_dick.txt +21712 -0
- data/data/the_picture_of_dorian_gray.txt +3118 -0
- data/guillaume.gemspec +23 -0
- data/lib/guillaume/base.rb +2 -0
- data/lib/guillaume/line.rb +29 -0
- data/lib/guillaume/poem.rb +51 -0
- data/lib/guillaume/poetics.rb +13 -0
- data/lib/guillaume/source_text.rb +34 -0
- data/lib/guillaume/version.rb +3 -0
- data/lib/guillaume.rb +13 -0
- data/spec/data/zone.txt +4 -0
- data/spec/source_text_spec.rb +23 -0
- data/spec/spec_helper.rb +5 -0
- metadata +100 -0
data/guillaume.gemspec
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'guillaume/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "guillaume"
|
8
|
+
spec.version = Guillaume::VERSION
|
9
|
+
spec.authors = ["Jamey J. DeOrio"]
|
10
|
+
spec.email = ["jdeorio@gmail.com"]
|
11
|
+
spec.description = %q{Guillaume is a generative poetry creation tool using ngrams for predictive writing and a defined poetics for guiding its creation.}
|
12
|
+
spec.summary = "A generative poetry creation tool"
|
13
|
+
spec.homepage = "http://rubygems.org/gems/guillaume"
|
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_development_dependency "bundler", "~> 1.3"
|
22
|
+
spec.add_development_dependency "rake", "~> 0"
|
23
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
class Guillaume::Line
|
2
|
+
def initialize(seed = nil)
|
3
|
+
@line_parts = seed.split(/ /)
|
4
|
+
end
|
5
|
+
|
6
|
+
def build(ngrams)
|
7
|
+
begin
|
8
|
+
@line_parts << next_word(ngrams)
|
9
|
+
end until @line_parts.last.nil?
|
10
|
+
@line_parts.join(" ").strip
|
11
|
+
end
|
12
|
+
|
13
|
+
def next_word(ngrams, options = { look_behind: 1 })
|
14
|
+
search_words = @line_parts[-options[:look_behind]..-1]
|
15
|
+
choose_word(ngram_matches(ngrams, search_words))
|
16
|
+
end
|
17
|
+
|
18
|
+
def ngram_matches(ngrams, search_words)
|
19
|
+
ngrams.select { |gram| gram[0..search_words.count-1] == search_words }
|
20
|
+
end
|
21
|
+
|
22
|
+
def choose_word(matches)
|
23
|
+
possible_choices(matches).sample
|
24
|
+
end
|
25
|
+
|
26
|
+
def possible_choices(matches)
|
27
|
+
matches.map { |res| res.last }.sort
|
28
|
+
end
|
29
|
+
end
|
@@ -0,0 +1,51 @@
|
|
1
|
+
class Guillaume::Poem
|
2
|
+
attr_accessor :corpora, :lines, :poem
|
3
|
+
|
4
|
+
def initialize(corpora, options = { seed: nil, max_stanzas: 10 })
|
5
|
+
@corpora = corpora
|
6
|
+
@first_seed = options[:seed].nil? ? random_seed(@corpora.unigrams) : options[:seed]
|
7
|
+
@max_stanzas = options[:max_stanzas]
|
8
|
+
@lines = 0
|
9
|
+
@stanzas = 0
|
10
|
+
@poem = write
|
11
|
+
end
|
12
|
+
|
13
|
+
def random_seed(ngrams)
|
14
|
+
ngrams.select { |word| word.first[0] =~ /[A-Z]/ }.sample.first
|
15
|
+
end
|
16
|
+
|
17
|
+
def write(lines_memo = [])
|
18
|
+
if rand(@max_stanzas) < @stanzas
|
19
|
+
return lines_memo
|
20
|
+
else
|
21
|
+
$LOGGER.info("Writing stanza #{@stanzas + 1}...")
|
22
|
+
lines_memo += stanza
|
23
|
+
@stanzas += 1
|
24
|
+
write(lines_memo)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
#
|
29
|
+
# TODO: which_gram
|
30
|
+
# TODO: thesaurus stuff for topic staying/straying
|
31
|
+
# TODO: explicit num_lines option
|
32
|
+
#
|
33
|
+
def stanza(lines_memo = [])
|
34
|
+
#which_gram = :bigrams
|
35
|
+
|
36
|
+
if rand(100) <= lines_memo.count * 10 # never more than 10 lines this way
|
37
|
+
return lines_memo << ""
|
38
|
+
else
|
39
|
+
line = Guillaume::Line.new(random_seed(@corpora.unigrams)).build(@corpora.bigrams)
|
40
|
+
if line.length > 80
|
41
|
+
line = Guillaume::Poetics.enjamb 40, line # 40% chance to break a long line
|
42
|
+
end
|
43
|
+
lines_memo << line
|
44
|
+
stanza(lines_memo)
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
def formatted
|
49
|
+
@formatted ||= @poem.join("\n")
|
50
|
+
end
|
51
|
+
end
|
@@ -0,0 +1,13 @@
|
|
1
|
+
class Guillaume::Poetics
|
2
|
+
def self.enjamb(chance=100, line)
|
3
|
+
if rand(100) <= chance
|
4
|
+
line_parts = line.split(/(?<=[\.,;!-])/)
|
5
|
+
if line_parts.count > 1 # if the line contains any . , ; ! -
|
6
|
+
random_index = rand(line_parts.count)
|
7
|
+
line_parts[random_index] = line_parts[random_index] + "\n"
|
8
|
+
line_parts.join.strip
|
9
|
+
end
|
10
|
+
end
|
11
|
+
line
|
12
|
+
end
|
13
|
+
end
|
@@ -0,0 +1,34 @@
|
|
1
|
+
require "uri"
|
2
|
+
|
3
|
+
class Guillaume::SourceText
|
4
|
+
def initialize(file_name)
|
5
|
+
@file_name = file_name
|
6
|
+
@raw_source = File.open(file_name, "rb") { |f| f.read }
|
7
|
+
@sentences = normalized.split(/(?<=\.|\?|!) /).reject(&:empty?)
|
8
|
+
end
|
9
|
+
|
10
|
+
def normalized
|
11
|
+
@raw_source.gsub(/[\r\n ]+/, " ").strip
|
12
|
+
end
|
13
|
+
|
14
|
+
def ngrams(n)
|
15
|
+
$LOGGER.info("Grabbing #{n}-grams from #{@file_name}...")
|
16
|
+
result = []
|
17
|
+
@sentences.each do |sentence|
|
18
|
+
result += sentence.split(" ").each_cons(n).to_a
|
19
|
+
end
|
20
|
+
result
|
21
|
+
end
|
22
|
+
|
23
|
+
def unigrams
|
24
|
+
@unigrams ||= ngrams 1
|
25
|
+
end
|
26
|
+
|
27
|
+
def bigrams
|
28
|
+
@bigrams ||= ngrams 2
|
29
|
+
end
|
30
|
+
|
31
|
+
def trigrams
|
32
|
+
@trigrams ||= ngrams 3
|
33
|
+
end
|
34
|
+
end
|
data/lib/guillaume.rb
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
require "net/http"
|
2
|
+
require "logger"
|
3
|
+
require "guillaume/version"
|
4
|
+
require "guillaume/source_text"
|
5
|
+
require "guillaume/line"
|
6
|
+
require "guillaume/poem"
|
7
|
+
require "guillaume/poetics"
|
8
|
+
|
9
|
+
$LOGGER = Logger.new(STDOUT)
|
10
|
+
$LOGGER.level = Logger::ERROR
|
11
|
+
|
12
|
+
module Guillaume
|
13
|
+
end
|
data/spec/data/zone.txt
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
describe Guillaume::SourceText do
|
2
|
+
let(:file_path) { "spec/data/zone.txt" }
|
3
|
+
|
4
|
+
subject do
|
5
|
+
Guillaume::SourceText.new(file_path)
|
6
|
+
end
|
7
|
+
|
8
|
+
it "can normalize the input file" do
|
9
|
+
expect(subject.normalized).to eq("A la fin tu es las de ce monde ancien")
|
10
|
+
end
|
11
|
+
|
12
|
+
it "has unigrams" do
|
13
|
+
expect(subject.unigrams).to eq([%w(A), %w(la), %w(fin), %w(tu), %w(es), %w(las), %w(de), %w(ce), %w(monde), %w(ancien)])
|
14
|
+
end
|
15
|
+
|
16
|
+
it "has bigrams" do
|
17
|
+
expect(subject.bigrams).to eq([%w(A la), %w(la fin), %w(fin tu), %w(tu es), %w(es las), %w(las de), %w(de ce), %w(ce monde), %w(monde ancien)])
|
18
|
+
end
|
19
|
+
|
20
|
+
it "has trigrams" do
|
21
|
+
expect(subject.trigrams).to eq([%w(A la fin), %w(la fin tu), %w(fin tu es), %w(tu es las), %w(es las de), %w(las de ce), %w( de ce monde), %w(ce monde ancien)])
|
22
|
+
end
|
23
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,100 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: guillaume
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Jamey J. DeOrio
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-07-03 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: '1.3'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
description: Guillaume is a generative poetry creation tool using ngrams for predictive
|
42
|
+
writing and a defined poetics for guiding its creation.
|
43
|
+
email:
|
44
|
+
- jdeorio@gmail.com
|
45
|
+
executables:
|
46
|
+
- guillaume
|
47
|
+
extensions: []
|
48
|
+
extra_rdoc_files: []
|
49
|
+
files:
|
50
|
+
- ".gitignore"
|
51
|
+
- ".rspec"
|
52
|
+
- Gemfile
|
53
|
+
- LICENSE.txt
|
54
|
+
- README.markdown
|
55
|
+
- Rakefile
|
56
|
+
- bin/guillaume
|
57
|
+
- config/database.yaml.example
|
58
|
+
- data/call_of_the_wild.txt
|
59
|
+
- data/heart_of_darkness.txt
|
60
|
+
- data/moby_dick.txt
|
61
|
+
- data/the_picture_of_dorian_gray.txt
|
62
|
+
- guillaume.gemspec
|
63
|
+
- lib/guillaume.rb
|
64
|
+
- lib/guillaume/base.rb
|
65
|
+
- lib/guillaume/line.rb
|
66
|
+
- lib/guillaume/poem.rb
|
67
|
+
- lib/guillaume/poetics.rb
|
68
|
+
- lib/guillaume/source_text.rb
|
69
|
+
- lib/guillaume/version.rb
|
70
|
+
- spec/data/zone.txt
|
71
|
+
- spec/source_text_spec.rb
|
72
|
+
- spec/spec_helper.rb
|
73
|
+
homepage: http://rubygems.org/gems/guillaume
|
74
|
+
licenses:
|
75
|
+
- MIT
|
76
|
+
metadata: {}
|
77
|
+
post_install_message:
|
78
|
+
rdoc_options: []
|
79
|
+
require_paths:
|
80
|
+
- lib
|
81
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
82
|
+
requirements:
|
83
|
+
- - ">="
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: '0'
|
86
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
87
|
+
requirements:
|
88
|
+
- - ">="
|
89
|
+
- !ruby/object:Gem::Version
|
90
|
+
version: '0'
|
91
|
+
requirements: []
|
92
|
+
rubyforge_project:
|
93
|
+
rubygems_version: 2.2.2
|
94
|
+
signing_key:
|
95
|
+
specification_version: 4
|
96
|
+
summary: A generative poetry creation tool
|
97
|
+
test_files:
|
98
|
+
- spec/data/zone.txt
|
99
|
+
- spec/source_text_spec.rb
|
100
|
+
- spec/spec_helper.rb
|