lorem-ipsum 0.1.0

data/bin/lorem-ipsum

@@ -0,0 +1,58 @@
+#!/usr/bin/env ruby
+
+$LOAD_PATH.unshift File.join(File.dirname(__FILE__), *%w[.. lib])
+$DATA_DIR = File.join(File.dirname(__FILE__), *%w[.. data])
+
+require 'lorem-ipsum'
+require 'optparse'
+
+init_options = { :max_ngraph => 3 }
+gen_options = { :words => 100 }
+
+opts = OptionParser.new do |opts|
+  opts.banner = "Usage: #{$0} [options] data-files"
+
+  def check_int_arg(val, range = { :min => nil , :max => nil })
+    err_msg = "Must specify integer between " \
+        "#{range[:min] || "-INF"} and #{range[:max] || "INF"}"
+
+    int_val = val.to_i
+
+    raise err_msg if range[:min] && int_val < range[:min]
+    raise err_msg if range[:max] && int_val > range[:max]
+
+    int_val
+  end
+
+  opts.on("--max-ngraph MAX",
+      "Maximum length of n-graphs to track. Default is 3") do |v|
+    init_options[:max_ngraph] = check_int_arg(v, :min => 1)
+  end
+
+  opts.on("-w", "--words WORDS",
+      "Number of words to generate. Default is 100") do |v|
+    gen_options[:words] = check_int_arg(v, :min => 1)
+  end
+
+end
+
+begin
+  opts.parse!(ARGV)
+rescue
+  opts.abort
+end
+
+# There has to be a more Ruby way to do this...
+if ARGV.empty?
+  files = Dir.entries($DATA_DIR).reject do |f|
+    f =~ /^\.\.?$/
+  end.collect do |f|
+    "#{$DATA_DIR}/#{f}"
+  end
+else
+  files = ARGV
+end
+
+gen = LoremIpsum::Generator.new(files, init_options)
+puts gen.generate(gen_options).strip
+

data/data/lorem.txt

@@ -0,0 +1,6 @@
+Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor
+incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis
+nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.
+Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu
+fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in
+culpa qui officia deserunt mollit anim id est laborum.

data/lib/lorem-ipsum.rb

@@ -0,0 +1,105 @@
+module LoremIpsum
+
+class Generator
+
+  def initialize(data_files = [], opts = { :max_ngraph => 3 })
+    @letter_count = { :count => 0 }
+    @max_ngraph = opts[:max_ngraph]
+
+    data_files.each { |file| analyze(file) }
+  end
+
+  def analyze(filename)
+    File.open(filename) do |file|
+      while (line = file.gets)
+        # todo - not handling punctuation
+        line = line.strip.downcase.gsub(/[^a-z ]/, '') << ' '
+
+        word = "^"
+        line.chars do |c|
+          word << c
+          n = [@max_ngraph, word.length].min
+          ngraph = word[-n..-1]
+
+          ngraph.chars.inject(@letter_count) do |hash, char|
+            hash[char] ||= { :count => 0 }
+            hash[char][:count] += 1
+            hash = hash[char]
+          end
+
+          if c == ' '
+            word = "^"
+          end
+        end
+      end
+    end
+  end
+
+  def generate(options = { :words => 100 })
+    str = ""
+    if options[:words]
+      to_next_sentence = rand(10) + 5
+      start_of_sentence = true
+      1.upto(options[:words]) do |i|
+        word = next_word
+        if start_of_sentence
+          word.capitalize!
+          start_of_sentence = false
+        end
+
+        to_next_sentence -= 1
+        if to_next_sentence == 0 || i == options[:words]
+          word.gsub!(/ /,'. ')
+          to_next_sentence = rand(10) + 5
+          start_of_sentence = true
+        end
+        
+        str << word
+      end
+    end
+
+    str
+  end
+
+  def next_word
+    word = "^"
+    word << next_char(word) while word[-1..-1] != ' '
+    word[1..-1]
+  end
+
+  def next_char(prev)
+    # Need to make sure our words don't get too long. Not everyone is Charles
+    # Dickens, even in fake-Latin land. These parameters seem to look nice,
+    # but salt to taste.
+    return ' ' if prev.length > 4 && rand(9 + prev.length) < prev.length
+
+    n = [@max_ngraph-1, prev.length].min
+    prev_ngraph = prev[-n..-1]
+
+    # If we don't have statistics for this n-graph, just use the stats
+    # for the (n-1)-graph
+    n_count = nil
+    until n_count
+      n_count = prev_ngraph.chars.inject(@letter_count) do |hash, char|
+        break if ! hash[char]
+        hash = hash[char]
+      end
+      prev_ngraph = prev_ngraph[1..-1]
+
+      n_count = @letter_count if ! prev_ngraph
+    end
+    n_count = n_count.reject { |k,v| k == :count || prev.empty? && k == ' ' }
+
+    num_letters ||= n_count.values.inject(0) { |s,c| s += c[:count] }
+    index = rand(num_letters + 1)
+
+    "abcdefghijklmnopqrstuvqxyz ".chars do |c|
+      index -= n_count[c] && n_count[c][:count] || 0
+      return c if index <= 0
+    end
+  end
+
+end
+
+end
+

metadata

@@ -0,0 +1,69 @@
+--- !ruby/object:Gem::Specification 
+name: lorem-ipsum
+version: !ruby/object:Gem::Version 
+  hash: 27
+  prerelease: 
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- Matt Austin
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-04-24 00:00:00 -04:00
+default_executable: 
+dependencies: []
+
+description: lorem-ipsum is a simple, trainable dummy text generator.
+email: maustin126@gmail.com
+executables: 
+- lorem-ipsum
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/lorem-ipsum.rb
+- data/lorem.txt
+- bin/lorem-ipsum
+has_rdoc: true
+homepage: http://github.com/maafy6/lorem-ipsum
+licenses: 
+- MIT
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.6.2
+signing_key: 
+specification_version: 3
+summary: A simple dummy text generator.
+test_files: []
+