markov-generator 0.9.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 2aa1e1c86fea5b2b44acbc8fde22a4cbffc9f17f
+  data.tar.gz: 5ab92534b88d461d14cb603b1d83e0ea4b3488ef
+SHA512:
+  metadata.gz: 3199d76a06a3b42f1b92e8ba3d0ebfaeff5020ac52ad8016a8c8f3206811f45fdfda797f457d0789e738738215f0c5ad7cb08972c883a4194f79f313f9a1baa7
+  data.tar.gz: 1aafb17d5e58b38b8f77d049a4af7d3edabceffb85e7ed435cdec312bcbb5020a3d9aea8b402aec84282617490a4d28a6c8622184a702b61f63f5234f036be01

data/.document

@@ -0,0 +1,5 @@
+lib/**/*.rb
+bin/*
+- 
+features/**/*.feature
+LICENSE.txt

data/Gemfile

@@ -0,0 +1,14 @@
+source "http://rubygems.org"
+# Add dependencies required to use your gem here.
+# Example:
+#   gem "activesupport", ">= 2.3.5"
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development do
+  gem "shoulda", ">= 0"
+  gem "rdoc", "~> 3.12"
+  gem "bundler", "~> 1.0"
+  gem "jeweler", "~> 2.0.1"
+  gem "simplecov", ">= 0"
+end

data/Gemfile.lock

@@ -0,0 +1,80 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    activesupport (4.2.1)
+      i18n (~> 0.7)
+      json (~> 1.7, >= 1.7.7)
+      minitest (~> 5.1)
+      thread_safe (~> 0.3, >= 0.3.4)
+      tzinfo (~> 1.1)
+    addressable (2.3.8)
+    builder (3.2.2)
+    descendants_tracker (0.0.4)
+      thread_safe (~> 0.3, >= 0.3.1)
+    docile (1.1.5)
+    faraday (0.9.1)
+      multipart-post (>= 1.2, < 3)
+    git (1.2.9.1)
+    github_api (0.12.3)
+      addressable (~> 2.3)
+      descendants_tracker (~> 0.0.4)
+      faraday (~> 0.8, < 0.10)
+      hashie (>= 3.3)
+      multi_json (>= 1.7.5, < 2.0)
+      nokogiri (~> 1.6.3)
+      oauth2
+    hashie (3.4.1)
+    highline (1.7.2)
+    i18n (0.7.0)
+    jeweler (2.0.1)
+      builder
+      bundler (>= 1.0)
+      git (>= 1.2.5)
+      github_api
+      highline (>= 1.6.15)
+      nokogiri (>= 1.5.10)
+      rake
+      rdoc
+    json (1.8.2)
+    jwt (1.5.0)
+    mini_portile (0.6.2)
+    minitest (5.6.1)
+    multi_json (1.11.0)
+    multi_xml (0.5.5)
+    multipart-post (2.0.0)
+    nokogiri (1.6.6.2)
+      mini_portile (~> 0.6.0)
+    oauth2 (1.0.0)
+      faraday (>= 0.8, < 0.10)
+      jwt (~> 1.0)
+      multi_json (~> 1.3)
+      multi_xml (~> 0.5)
+      rack (~> 1.2)
+    rack (1.6.1)
+    rake (10.4.2)
+    rdoc (3.12.2)
+      json (~> 1.4)
+    shoulda (3.5.0)
+      shoulda-context (~> 1.0, >= 1.0.1)
+      shoulda-matchers (>= 1.4.1, < 3.0)
+    shoulda-context (1.2.1)
+    shoulda-matchers (2.8.0)
+      activesupport (>= 3.0.0)
+    simplecov (0.10.0)
+      docile (~> 1.1.0)
+      json (~> 1.8)
+      simplecov-html (~> 0.10.0)
+    simplecov-html (0.10.0)
+    thread_safe (0.3.5)
+    tzinfo (1.2.2)
+      thread_safe (~> 0.1)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.0)
+  jeweler (~> 2.0.1)
+  rdoc (~> 3.12)
+  shoulda
+  simplecov

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2015 Michael Kuehl
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,19 @@
+= markov_generator
+
+Description goes here.
+
+== Contributing to markov_generator
+ 
+* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet.
+* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it.
+* Fork the project.
+* Start a feature/bugfix branch.
+* Commit and push until you are happy with your contribution.
+* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
+* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
+
+== Copyright
+
+Copyright (c) 2015 Michael Kuehl. See LICENSE.txt for
+further details.
+

data/Rakefile

@@ -0,0 +1,51 @@
+# encoding: utf-8
+
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://guides.rubygems.org/specification-reference/ for more options
+  gem.name = "markov-generator"
+  gem.homepage = "http://github.com/ratchetcc/markov-generator"
+  gem.license = "MIT"
+  gem.summary = %Q{Markov Chain text generator}
+  gem.description = %Q{A Markov Chain text generator library}
+  gem.email = "hello@ratchet.cc"
+  gem.authors = ["Michael Kuehl"]
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+desc "Code coverage detail"
+task :simplecov do
+  ENV['COVERAGE'] = "true"
+  Rake::Task['test'].execute
+end
+
+task :default => :test
+
+require 'rdoc/task'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "markov-generator #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.9.0

data/lib/markov/generator.rb

@@ -0,0 +1,289 @@
+
+require 'securerandom'
+
+module Markov
+  
+  class Token < Struct.new(:word, :kind)
+    # used as an internal structure to hold words etc
+  end
+  
+  class Generator
+    
+    attr_reader :depth
+    
+    def initialize(depth=3)
+      @depth = depth
+      @split_words = /([',.?!\n-])|[\s]+/
+      @split_sentence = /(?<=[.!?\n])\s+/
+      @dictionary = {}
+      @start_words = {}
+      @unparsed_sentences = []
+      @tokens = []
+      srand
+    end
+    
+    class FileNotFoundError < Exception # :nodoc:
+    end
+    
+    class EmptyDictionaryError < Exception # :nodoc:
+    end
+    
+    def parse_string(sentence)
+      add_unparsed_sentence sentence
+      parse_text
+    end
+    
+    def parse_source_file(source)
+      
+      if File.exists?(source)
+        sentences = File.open(source, "r").read.force_encoding(Encoding::UTF_8).split(@split_sentence)
+      else
+        raise FileNotFoundError.new("#{source} does not exist!")
+      end
+      
+      sentences.each do |sentence|
+        add_unparsed_sentence sentence
+      end
+      
+      parse_text
+      
+    end
+    
+    def generate_sentence(min_length=20)
+      if @dictionary.empty?
+        raise EmptyDictionaryError.new("The dictionary is empty! Parse a source file/string first!")
+      end
+      
+      tokens = []
+      complete_sentence = false
+      
+      # initialize
+      select_start_words.each {|w| tokens << w}
+      prev_token = tokens.last
+      
+      begin
+        token =  select_next_token tokens.last(@depth-1)
+        
+        if token.kind == :stop
+          token =  select_next_word tokens.last(@depth-1) if prev_token.kind == :special
+          tokens << token
+        elsif token.kind == :special
+          token =  select_next_word tokens.last(@depth-1) if prev_token.kind == :special
+          tokens << token
+        elsif token.kind == :noop
+          token = Token.new(".", :stop)
+          tokens[tokens.length-1] = token
+        else
+          tokens << token
+        end
+        
+        prev_token = token
+        
+        if token.kind == :stop
+          if tokens.size < min_length
+            select_start_words.each {|w| tokens << w}
+            prev_token = tokens.last
+          else
+            complete_sentence = true
+          end
+        end
+        
+        # circuit-breaker
+        complete_sentence = true if tokens.size > min_length*2 
+      end until complete_sentence
+      
+      tokens_to_sentence tokens
+    end
+      
+    def dump_start_words
+      @start_words.keys.each do |words|
+        puts "#{words[0]},#{words[1]}"
+      end
+    end
+    
+    def dump_dictionary
+      @dictionary.keys.each do |words|
+        following = @dictionary[words]
+        sentence = "#{words[0]},#{words[1]},"
+        following.each do |s|
+          sentence << "#{s.word},"
+        end
+        
+        puts "#{sentence.slice(0,sentence.length-1)}"
+      end
+    end
+    
+    private
+    
+    def parse_text
+            
+      state = :start # :start, :word, :special, :stop
+      word_seq = []
+      
+      begin
+        while token = next_token
+          
+          if state == :start
+            word_seq << token
+            
+            # fill the array
+            (@depth-word_seq.size).times do
+              word_seq << next_token
+            end
+            
+            # need to store the words in both the dictionary 
+            # and the list of start words
+            add_to_start_words word_seq[0, @depth-1]
+            add_to_dictionary word_seq
+            
+            token = next_token
+            state = :sentence
+          end
+          
+          if state == :sentence
+            # move the array one position
+            word_seq.slice!(0)
+            word_seq << token
+            
+            # add to the dictionary
+            add_to_dictionary word_seq
+            
+            # stop current sequence and start again
+            if token.kind == :stop
+              word_seq = []
+              state = :start
+            end  
+          end
+          
+        end # end while
+        
+      rescue
+        # nothing to rescue
+      end
+      
+    end # end parse_text
+    
+    def next_token
+      if @tokens.empty?
+        sentence = @unparsed_sentences.slice!(0)
+        if sentence
+          sentence.each do |word|
+            
+            if word.include?("'")
+              @tokens << Token.new("'", :special)
+            elsif word.include?(",")
+              @tokens << Token.new(",", :special)
+            elsif word.include?("?")
+              @tokens << Token.new("?", :stop)
+            elsif word.include?("!")
+              @tokens << Token.new("!", :stop)
+            elsif word.include?(":")
+              @tokens << Token.new(":", :special)
+            elsif word.include?(";")
+              @tokens << Token.new(";", :special)
+            elsif word.include?("-")
+              @tokens << Token.new("-", :special)
+            elsif word.include?(".")
+              @tokens << Token.new(".", :stop)
+            elsif word == "\n"
+              # skip
+            else
+              @tokens << Token.new(word, :word)
+            end            
+          end
+        else
+          @tokens = nil
+        end
+      end
+      
+      return @tokens.slice!(0) if @tokens
+      nil  
+    end # end next_token
+    
+    def add_unparsed_sentence(sentence)
+      # replace unwanted characterts
+      sentence.gsub(/["„':_()]/,"")
+      sentence.gsub(/-/,"")
+      sentence.gsub(/,/,"")
+      
+      parts = sentence.split(@split_words)
+      if parts && !parts.empty?
+        @unparsed_sentences << parts
+      end
+      
+    end
+    
+    def add_to_start_words(tokens)
+      return if tokens[0].kind != :word
+      
+      tokens[0].word = tokens[0].word.capitalize
+      start_words = tokens_to_words tokens
+      
+      @start_words[start_words] ||= tokens
+      
+    end
+    
+    def add_to_dictionary(tokens)
+      token = tokens.last
+      return if token.word == ""
+      
+      key_words = tokens_to_words tokens[0, @depth-1]     
+      
+      @dictionary[key_words] ||= []
+      @dictionary[key_words] << token
+    end
+    
+    def tokens_to_words(tokens)
+      words = []
+      tokens.each do |t|
+        words << t.word
+      end
+      words
+    end
+
+    def tokens_to_sentence(tokens)
+      s = ""
+      tokens.each do |t|
+        if t.kind != :word
+          s << t.word
+        else
+          s << " " + t.word
+        end
+      end
+    
+      s[1, s.length-1]
+    end
+    
+    def select_start_words
+      @start_words[ @start_words.keys[random_number( @start_words.keys.length-1)]]
+    end
+    
+    def select_next_token(tokens)
+      token = @dictionary[ tokens_to_words(tokens)]
+      
+      return Token.new("X", :noop) if token == nil  
+      token[random_number(tokens.length-1)]
+    end
+    
+    def select_next_word(tokens)
+      token = nil
+      begin
+        token = select_next_token(tokens)
+      end until token.kind == :word
+      token
+    end
+    
+    def random_number(upper_limit)
+      (SecureRandom.random_number * upper_limit).to_i
+    end
+  end
+  
+end
+
+#markov = Markov::Generator.new
+
+#Dir["../../public/text/seed_*"].each do | f |
+#  markov.parse_source_file f
+#end
+
+#markov.dump_dictionary

data/test/helper.rb

@@ -0,0 +1,34 @@
+require 'simplecov'
+
+module SimpleCov::Configuration
+  def clean_filters
+    @filters = []
+  end
+end
+
+SimpleCov.configure do
+  clean_filters
+  load_adapter 'test_frameworks'
+end
+
+ENV["COVERAGE"] && SimpleCov.start do
+  add_filter "/.rvm/"
+end
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'markov_generator'
+
+class Test::Unit::TestCase
+end

data/test/test_markov_generator.rb

@@ -0,0 +1,7 @@
+require 'helper'
+
+class TestMarkovGenerator < Test::Unit::TestCase
+  should "probably rename this file and start testing for real" do
+    flunk "hey buddy, you should probably rename this file and start testing for real"
+  end
+end

metadata

@@ -0,0 +1,125 @@
+--- !ruby/object:Gem::Specification
+name: markov-generator
+version: !ruby/object:Gem::Version
+  version: 0.9.0
+platform: ruby
+authors:
+- Michael Kuehl
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-05-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: shoulda
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.12'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: jeweler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.0.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.0.1
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: A Markov Chain text generator library
+email: hello@ratchet.cc
+executables: []
+extensions: []
+extra_rdoc_files:
+- LICENSE.txt
+- README.rdoc
+files:
+- ".document"
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.rdoc
+- Rakefile
+- VERSION
+- lib/markov/generator.rb
+- test/helper.rb
+- test/test_markov_generator.rb
+homepage: http://github.com/ratchetcc/markov-generator
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.5
+signing_key: 
+specification_version: 4
+summary: Markov Chain text generator
+test_files: []