momblish 0.1.0

data/lib/momblish/corpus.rb

@@ -0,0 +1,30 @@
+require 'json'
+
+class Momblish
+  class Corpus
+    attr_accessor :weighted_bigrams, :occurrences
+
+    def initialize(weighted_bigrams = {}, occurrences = {})
+      @weighted_bigrams = weighted_bigrams
+      @occurrences = occurrences
+    end
+
+    def self.load(path)
+      data = File.read(path)
+      parsed = JSON.parse(data)
+      new(parsed['weighted_bigrams'], parsed['occurrences'])
+    end
+
+    def ==(other)
+      @weighted_bigrams == other.weighted_bigrams && @occurrences == other.occurrences
+    end
+
+    def save(path)
+      saved_corpus = {
+        weighted_bigrams: @weighted_bigrams,
+        occurrences: @occurrences
+      }
+      File.write(path, JSON.dump(saved_corpus))
+    end
+  end
+end

data/lib/momblish/corpus_analyzer.rb

@@ -0,0 +1,65 @@
+require 'json'
+require 'debug'
+
+class Momblish
+  class CorpusAnalyzer
+    PUNCTUATION = "!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~\n".split('')
+
+    attr_accessor :words, :corpus
+
+    def initialize(corpus = [])
+      @words = corpus.map(&:rstrip)
+      @corpus = Corpus.new({}, {})
+      init_weighted_bigrams
+      init_occurrences
+    end
+
+    def init_weighted_bigrams
+      starting_bigrams = Hash.new(0)
+
+      filtered_words = @words.lazy.select do |word|
+        word.length > 2 && (word[0..1].chars & PUNCTUATION).empty?
+      end
+
+      filtered_words.each do |word|
+        bigram = word[0..1].upcase
+        starting_bigrams[bigram] += 1
+      end
+
+      total = starting_bigrams.values.sum
+
+      starting_bigrams.each do |bigram, count|
+        @corpus.weighted_bigrams[bigram] = count.to_f / total
+      end
+    end
+
+    def init_occurrences
+      all_trigrams = @words.each.with_object([]) { |word, memo|
+        word_chars = word.chomp.upcase.chars
+        next if (word_chars & PUNCTUATION).any?
+
+        memo.concat(word_chars.each_cons(3).to_a)
+      }
+
+      occurrences = Hash.new { |h, k| h[k] = Hash.new(0) }
+
+      all_trigrams
+        .group_by { |trigram| trigram[0..1].join }
+        .each_pair do |bigram, trigrams|
+          trigrams.each do |trigram|
+            last_char = trigram.last
+            occurrences[bigram][last_char] += 1
+          end
+        end
+
+      @corpus.occurrences = Hash.new { |h, k| h[k] = Hash.new(&h.default_proc) }
+
+      occurrences.each do |bigram, last_letters|
+        total = last_letters.values.sum.to_f
+        last_letters.each do |last_letter, count|
+          @corpus.occurrences[bigram][last_letter] = count / total
+        end
+      end
+    end
+  end
+end

data/lib/momblish/version.rb

@@ -0,0 +1,3 @@
+class Momblish
+  VERSION = "0.1.0"
+end

data/lib/momblish.rb

@@ -0,0 +1,90 @@
+require "momblish/version"
+require "momblish/corpus_analyzer"
+require "momblish/corpus"
+
+class Momblish
+  class Error < StandardError; end
+
+  module WeightedSample
+    refine Hash do
+      def weighted_sample
+        self.max_by { |_, weight| rand ** (1.0 / weight) }&.first
+      end
+    end
+  end
+
+  using WeightedSample
+
+  DICT = {
+    'english' => ['/usr/share/dict/words', '/usr/dict/words', '/usr/share/dict/web2'],
+    'simple' => ["#{__dir__}/corpuses/simple.txt"],
+    'names' => ['/usr/share/dict/propernames', '/usr/dict/propernames'],
+    'spanish' => ["#{__dir__}/corpuses/spanish.txt"]
+  }
+
+  class EmptyCorpusError < StandardError
+    attr_reader :message
+
+    def initialize(message)
+      @message = message
+    end
+  end
+
+  class << self
+    def lookup_dict(lang)
+      DICT[lang].find { |location| puts location; File.exist?(location) }
+    end
+
+    def method_missing(lang)
+      if(DICT.has_key?(lang.to_s))
+        dict_file = lookup_dict(lang.to_s)
+        corpus = Momblish::CorpusAnalyzer.new(File.readlines(dict_file)).corpus
+        new(corpus)
+      else
+        super
+      end
+    end
+  end
+
+  attr_accessor :corpus
+
+  def initialize(corpus = nil)
+    @corpus = corpus || Corpus.new({}, {})
+
+    if @corpus.weighted_bigrams.empty? || @corpus.occurrences.empty?
+      raise EmptyCorpusError.new('Your corpus has no words')
+    end
+  end
+
+  def word(length = nil)
+    length ||= rand(4..12)
+
+    word = @corpus.weighted_bigrams.keys.sample
+
+    (length - 2).times do
+      last_bigram = word[-2..-1]
+
+      next_letter = @corpus.occurrences[last_bigram].weighted_sample
+
+      return word.downcase if next_letter.nil?
+
+      word += next_letter
+    end
+
+    word.downcase
+  end
+
+  def sentence(count = nil, word_length = nil)
+    raise ArgumentError, 'You must provide a block or a count' if count.nil? && !block_given?
+
+    if block_given?
+      if count.nil?
+        loop { yield word(word_length) }
+      else
+        count.times { yield word(word_length) }
+      end
+    else
+      Array.new(count) { word(word_length) }
+    end
+  end
+end

data/momblish.gemspec

@@ -0,0 +1,29 @@
+
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "momblish/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "momblish"
+  spec.version       = Momblish::VERSION
+  spec.authors       = ["Stephen Prater"]
+  spec.email         = ["me@stephenprater.com"]
+  spec.license       = "MIT"
+
+  spec.summary       = "Generate nonsense words in any language by corpus analysis"
+  spec.homepage      = "https://github.com/stephenprater/momblish-rb"
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 2.4"
+  spec.add_development_dependency "rake", "~> 13.1"
+  spec.add_development_dependency "minitest", "~> 5.20"
+  spec.add_development_dependency "debug", "~> 1.9"
+end

metadata

@@ -0,0 +1,115 @@
+--- !ruby/object:Gem::Specification
+name: momblish
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Stephen Prater
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2023-12-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.4'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.1'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.20'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.20'
+- !ruby/object:Gem::Dependency
+  name: debug
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+description:
+email:
+- me@stephenprater.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".travis.yml"
+- Gemfile
+- Gemfile.lock
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/corpuses/simple.txt
+- lib/corpuses/spanish.txt
+- lib/freq.txt
+- lib/momblish.rb
+- lib/momblish/corpus.rb
+- lib/momblish/corpus_analyzer.rb
+- lib/momblish/version.rb
+- momblish.gemspec
+homepage: https://github.com/stephenprater/momblish-rb
+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: []
+rubygems_version: 3.4.10
+signing_key:
+specification_version: 4
+summary: Generate nonsense words in any language by corpus analysis
+test_files: []