random_data 1.3.1 → 1.5.0

data/History.txt

@@ -1,4 +1,15 @@
-== 1.3.1 2008-06--06
+== 1.5.0 2008-11-06
+* 2 major enhancement:
+  * Totally cleaned up and reconfigured hoe using newgem 1.0's conventions
+  * Added Markov model text generator (courtesy of Hugh Sasse)
+
+* 1 minor enhancement:
+  * Added roulette method to Array (courtesy of Hugh Sasse)
+
+* 1 minor fix:
+  * Fixed newline bug in the name generator (courtesy of Harold Gimenez)
+
+== 1.3.1 2008-06-06
 
 * 2 minor enhancements:
   * Added added more last and firstnames (courtesy of Hugh Sasse)

data/Manifest.txt

@@ -1,10 +1,8 @@
 History.txt
 License.txt
 Manifest.txt
-README.txt
+README.rdoc
 Rakefile
-config/hoe.rb
-config/requirements.rb
 lib/random_data.rb
 lib/random_data/array_randomizer.rb
 lib/random_data/booleans.rb
@@ -12,22 +10,15 @@ lib/random_data/contact_info.rb
 lib/random_data/dates.rb
 lib/random_data/grammar.rb
 lib/random_data/locations.rb
+lib/random_data/markov.rb
 lib/random_data/names.rb
 lib/random_data/numbers.rb
 lib/random_data/text.rb
 lib/random_data/version.rb
-log/debug.log
+script/console
 script/destroy
 script/generate
 script/txt2html
-setup.rb
-tasks/deployment.rake
-tasks/environment.rake
-tasks/website.rake
+test/henry_v_prolog.txt
 test/test_helper.rb
 test/test_random_data.rb
-website/index.html
-website/index.txt
-website/javascripts/rounded_corners_lite.inc.js
-website/stylesheets/screen.css
-website/template.rhtml

data/{README.txt → README.rdoc}

@@ -1,4 +1,4 @@
-= Random
+= random_data
 
 This gem provides a Random singleton class with a series of methods for generating random test data including names, mailing addresses, dates, phone numbers, e-mail addresses, and text.  Instead of:
 
@@ -26,7 +26,7 @@ Random.date, Random.date_between
 Random.address_line_1, Random.address_line_2, Random.zipcode, Random.uk_post_code, Random.state, Random.state_full, Random.country, Random.city
 	
 === Name Methods
-Random.firstname, Random.initial, Random.lastname
+Random.firstname, Random.firstname_male, Random.firstname_female, Random.initial, Random.lastname
 
 === Text Methods
 Random.alphanumeric, Random.paragraphs
@@ -40,8 +40,14 @@ Random.number, Random.bit, Random.bits
 === Boolean Methods
 Random.boolean
 
+=== Markov Generator Methods
+Random.MarkovGenerator.new 
+Random.MarkovGenerator.insert
+Random.MarkovGenerator.generate
+
 === Array Extension
 Array.rand
+Array.roulette
 
 === Choose From File Methods
 Random implements a method_missing helper that will choose a line at random from a file in your load path.  See Random::method_missing for details.

data/Rakefile

@@ -1,4 +1,32 @@
-require 'config/requirements'
-require 'config/hoe' # setup Hoe + all gem configuration
+%w[rubygems rake rake/clean fileutils newgem rubigen].each { |f| require f }
+require File.dirname(__FILE__) + '/lib/random_data'
 
-Dir['tasks/**/*.rake'].each { |rake| load rake }
+# Generate all the Rake tasks
+# Run 'rake -T' to see list of generated tasks (from gem root directory)
+$hoe = Hoe.new('random_data', RandomData::VERSION) do |p|
+  p.developer('Mike Subelsky', 'mike@subelsky.com')
+  p.changes              = p.paragraphs_of("History.txt", 0..1).join("\n\n")
+  p.rubyforge_name       = "random-data"
+  p.description = "A Ruby gem that provides a Random class with a series of methods for generating random test data including names, mailing addresses, dates, phone numbers, e-mail addresses, and text."
+  p.summary = "A Ruby gem that provides a Random class with a series of methods for generating random test data including names, mailing addresses, dates, phone numbers, e-mail addresses, and text."
+  p.email = 'random_data@mikeshop.net'
+  # p.remote_rdoc_dir = 'random-data'
+
+  # p.extra_deps         = [
+  #   ['activesupport','>= 2.0.2'],
+  # ]
+  p.extra_dev_deps = [
+    ['newgem', ">= #{::Newgem::VERSION}"]
+  ]
+  
+  p.clean_globs |= %w[**/.DS_Store tmp *.log]
+  path = (p.rubyforge_name == p.name) ? p.rubyforge_name : "\#{p.rubyforge_name}/\#{p.name}"
+  p.remote_rdoc_dir = File.join(path.gsub(/^#{p.rubyforge_name}\/?/,''), 'rdoc')
+  p.rsync_args = '-av --delete --ignore-errors'
+end
+
+require 'newgem/tasks' # load /tasks/*.rake
+Dir['tasks/**/*.rake'].each { |t| load t }
+
+# TODO - want other tests/tasks run by default? Add them to the list
+# task :default => [:spec, :features]

data/lib/random_data.rb

@@ -1,14 +1,16 @@
-$:.unshift File.dirname(__FILE__)
+dir = "#{File.dirname(__FILE__)}/random_data"
 
-require 'random_data/array_randomizer'
-require 'random_data/booleans'
-require 'random_data/contact_info'
-require 'random_data/dates'
-require 'random_data/locations'
-require 'random_data/names'
-require 'random_data/numbers'
-require 'random_data/text'
-require 'random_data/grammar'
+require "#{dir}/array_randomizer"
+require "#{dir}/booleans"
+require "#{dir}/contact_info"
+require "#{dir}/dates"
+require "#{dir}/locations"
+require "#{dir}/names"
+require "#{dir}/numbers"
+require "#{dir}/text"
+require "#{dir}/markov"
+require "#{dir}/grammar"
+require "#{dir}/version"
 
 class Random
   extend RandomData::Booleans

data/lib/random_data/array_randomizer.rb

@@ -12,6 +12,50 @@ module RandomData
       return self[Kernel.rand(self.size)]
     end
 
+    # Takes an array of non-negative weights
+    # and returns the index selected by a 
+    # roulette wheel weighted according to those
+    # weights.
+    # If a block is given then k is used to determine
+    # how many times the block is called.  In this
+    # case nil is returned.
+    def roulette(k=1)
+      wheel = []
+      weight = 0
+      # Create the cumulative array.
+      self.each do |x|
+        raise "Illegal negative weight #{x}" if x < 0
+        wheel.push(weight += x)
+      end
+      # print "wheel is #{wheel.inspect}\n";
+      # print "weight is #{weight.inspect}\n";
+      raise "Array had all zero weights" if weight.zero?
+      wheel.push(weight + 1) #Add extra element
+      if block_given?
+        k.times do 
+          r = Kernel.rand() # so we don't pick up that from array.
+          # print "r is #{r.inspect}\n";
+          roll = weight.to_f * r
+          # print "roll is #{roll.inspect}\n";
+          0.upto(self.size - 1) do |i|
+            if wheel[i+1] > roll
+              yield i 
+              break
+            end # if
+          end # upto
+        end # if block_given?
+        return nil
+      else
+        r = Kernel.rand() # so we don't pick up that from array.
+        # print "r is #{r.inspect}\n";
+        roll = weight.to_f * r
+        # print "roll is #{roll.inspect}\n";
+        0.upto(self.size - 1) do |i|
+          return i if wheel[i+1] > roll
+        end
+      end
+    end
+
   end
 
 end

data/lib/random_data/markov.rb

@@ -0,0 +1,77 @@
+# Methods to create a markov chain from some input text.
+
+
+module RandomData
+  class MarkovGenerator
+    
+    def initialize(memory = 1)
+      @memory_size = memory
+      @table = Hash.new {|h,k| h[k] = {}}
+      @state = []
+    end
+
+
+    # given the next token of input add it to the
+    # table
+    def insert(result)
+      # puts "insert called with #{result}"
+      tabindex = Marshal.dump(@state)
+      if @table[tabindex].has_key?(result)
+        @table[tabindex][result] += 1
+      else
+        @table[tabindex][result] = 1
+      end
+      # puts "table #{@table.inspect}"
+      next_state(result)
+    end
+
+    def next_state(result)
+      @state.shift if @state.size >= @memory_size
+      @state.push(result)
+      # puts "@state is #{@state.inspect}"
+    end
+
+    def generate(n=1, clear_state=false)
+      @state = [] if clear_state
+      results = []
+      n.times do
+        retry_count = 0
+        begin
+          result_hash = @table[Marshal.dump(@state)]
+          the_keys,the_vals = [],[]
+          result_hash.each_pair do |k,v|
+            the_keys << k
+            the_vals << v
+          end
+          # get the weighted random value, by index.
+          i = the_vals.roulette
+        rescue
+          # puts "results:#{result_hash.inspect}";
+          # puts "keys:#{the_keys.inspect}";
+          # puts "vals:#{the_vals.inspect}";
+          # puts "state:#{@state.inspect}";
+          @state = []
+          retry_count += 1
+          if retry_count < 5
+            retry 
+          else
+            # puts
+            # puts "table:#{@table.inspect}";
+            raise
+          end
+        end
+        result = the_keys[i]
+        # puts "index:#{i.inspect}";
+
+        next_state(result)
+        if block_given?
+          yield result
+        end
+        results << result
+      end
+      return results
+    end
+
+  end
+
+end

data/lib/random_data/names.rb

@@ -9,10 +9,10 @@ module RandomData
       ('A'..'Z').to_a.rand
     end
 
-    @@lastnames = %w(ABEL ANDERSON ANDREWS ANTHONY BAKER BROWN BURROWS CLARK CLARKE CLARKSON DAVIDSON DAVIES DAVIS \
-                     DENT EDWARDS GARCIA GRANT HALL HARRIS HARRISON JACKSON JEFFRIES JEFFERSON JOHNSON JONES \
-                     KIRBY KIRK LAKE LEE LEWIS MARTIN MARTINEZ MAJOR MILLER MOORE OATES PETERS PETERSON ROBERTSON \
-                     ROBINSON RODRIGUEZ SMITH SMYTHE STEVENS TAYLOR THATCHER THOMAS THOMPSON WALKER WASHINGTON WHITE \
+    @@lastnames = %w(ABEL ANDERSON ANDREWS ANTHONY BAKER BROWN BURROWS CLARK CLARKE CLARKSON DAVIDSON DAVIES DAVIS 
+                     DENT EDWARDS GARCIA GRANT HALL HARRIS HARRISON JACKSON JEFFRIES JEFFERSON JOHNSON JONES 
+                     KIRBY KIRK LAKE LEE LEWIS MARTIN MARTINEZ MAJOR MILLER MOORE OATES PETERS PETERSON ROBERTSON 
+                     ROBINSON RODRIGUEZ SMITH SMYTHE STEVENS TAYLOR THATCHER THOMAS THOMPSON WALKER WASHINGTON WHITE 
                      WILLIAMS WILSON YORKE)
 
     # Returns a random lastname
@@ -25,13 +25,13 @@ module RandomData
       @@lastnames.rand.capitalize
     end
 
-    @@male_first_names = %w(ADAM ANTHONY ARTHUR BRIAN CHARLES CHRISTOPHER DANIEL DAVID DONALD EDGAR EDWARD EDWIN \
-                            GEORGE HAROLD HERBERT HUGH JAMES JASON JOHN JOSEPH KENNETH KEVIN MARCUS MARK MATTHEW \
+    @@male_first_names = %w(ADAM ANTHONY ARTHUR BRIAN CHARLES CHRISTOPHER DANIEL DAVID DONALD EDGAR EDWARD EDWIN 
+                            GEORGE HAROLD HERBERT HUGH JAMES JASON JOHN JOSEPH KENNETH KEVIN MARCUS MARK MATTHEW 
                             MICHAEL PAUL PHILIP RICHARD ROBERT ROGER RONALD SIMON STEVEN TERRY THOMAS WILLIAM)
 
-    @@female_first_names = %w(ALISON ANN ANNA ANNE BARBARA BETTY BERYL CAROL CHARLOTTE CHERYL DEBORAH DIANA DONNA \
-                              DOROTHY ELIZABETH EVE FELICITY FIONA HELEN HELENA JENNIFER JESSICA JUDITH KAREN KIMBERLY \
-                              LAURA LINDA LISA LUCY MARGARET MARIA MARY MICHELLE NANCY PATRICIA POLLY ROBYN RUTH SANDRA \
+    @@female_first_names = %w(ALISON ANN ANNA ANNE BARBARA BETTY BERYL CAROL CHARLOTTE CHERYL DEBORAH DIANA DONNA 
+                              DOROTHY ELIZABETH EVE FELICITY FIONA HELEN HELENA JENNIFER JESSICA JUDITH KAREN KIMBERLY 
+                              LAURA LINDA LISA LUCY MARGARET MARIA MARY MICHELLE NANCY PATRICIA POLLY ROBYN RUTH SANDRA 
                               SARAH SHARON SUSAN TABITHA URSULA VICTORIA WENDY)
 
     @@first_names = @@male_first_names + @@female_first_names

data/lib/random_data/version.rb

@@ -1,9 +1,3 @@
 module RandomData #:nodoc:
-  module VERSION #:nodoc:
-    MAJOR = 1
-    MINOR = 3
-    TINY  = 1
-
-    STRING = [MAJOR, MINOR, TINY].join('.')
-  end
+  VERSION = '1.5.0' #:nodoc:
 end

data/script/console

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+# File: script/console
+irb = RUBY_PLATFORM =~ /(:?mswin|mingw)/ ? 'irb.bat' : 'irb'
+
+libs =  " -r irb/completion"
+# Perhaps use a console_lib to store any extra methods I may want available in the cosole
+# libs << " -r #{File.dirname(__FILE__) + '/../lib/console_lib/console_logger.rb'}"
+libs <<  " -r #{File.dirname(__FILE__) + '/../lib/random_data.rb'}"
+puts "Loading random_data gem"
+exec "#{irb} #{libs} --simple-prompt"

data/script/destroy

@@ -1,5 +1,5 @@
 #!/usr/bin/env ruby
-APP_ROOT = File.join(File.dirname(__FILE__), '..')
+APP_ROOT = File.expand_path(File.join(File.dirname(__FILE__), '..'))
 
 begin
   require 'rubigen'
@@ -10,5 +10,5 @@ end
 require 'rubigen/scripts/destroy'
 
 ARGV.shift if ['--help', '-h'].include?(ARGV[0])
-RubiGen::Base.use_component_sources! [:rubygems, :newgem, :newgem_theme]
+RubiGen::Base.use_component_sources! [:rubygems, :newgem, :newgem_theme, :test_unit]
 RubiGen::Scripts::Destroy.new.run(ARGV)

data/script/generate

@@ -1,5 +1,5 @@
 #!/usr/bin/env ruby
-APP_ROOT = File.join(File.dirname(__FILE__), '..')
+APP_ROOT = File.expand_path(File.join(File.dirname(__FILE__), '..'))
 
 begin
   require 'rubigen'
@@ -10,5 +10,5 @@ end
 require 'rubigen/scripts/generate'
 
 ARGV.shift if ['--help', '-h'].include?(ARGV[0])
-RubiGen::Base.use_component_sources! [:rubygems, :newgem, :newgem_theme]
+RubiGen::Base.use_component_sources! [:rubygems, :newgem, :newgem_theme, :test_unit]
 RubiGen::Scripts::Generate.new.run(ARGV)

data/script/txt2html

@@ -1,20 +1,17 @@
 #!/usr/bin/env ruby
 
-require 'rubygems'
-begin
-  require 'newgem'
-rescue LoadError
-  puts "\n\nGenerating the website requires the newgem RubyGem"
-  puts "Install: gem install newgem\n\n"
-  exit(1)
-end
+load File.dirname(__FILE__) + "/../Rakefile"
+require 'rubyforge'
 require 'redcloth'
 require 'syntax/convertors/html'
 require 'erb'
-require File.dirname(__FILE__) + '/../lib/random_data/version.rb'
 
-version  = RandomData::VERSION::STRING
-download = 'http://rubyforge.org/projects/random_data'
+download = "http://rubyforge.org/projects/#{$hoe.rubyforge_name}"
+version  = $hoe.version
+
+def rubyforge_project_id
+  RubyForge.new.configure.autoconfig["group_ids"][$hoe.rubyforge_name]
+end
 
 class Fixnum
   def ordinal
@@ -42,10 +39,9 @@ end
 
 if ARGV.length >= 1
   src, template = ARGV
-  template ||= File.join(File.dirname(__FILE__), '/../website/template.rhtml')
-  
+  template ||= File.join(File.dirname(__FILE__), '/../website/template.html.erb')
 else
-  puts("Usage: #{File.split($0).last} source.txt [template.rhtml] > output.html")
+  puts("Usage: #{File.split($0).last} source.txt [template.html.erb] > output.html")
   exit!
 end
 
@@ -55,7 +51,8 @@ title = nil
 body = nil
 File.open(src) do |fsrc|
   title_text = fsrc.readline
-  body_text = fsrc.read
+  body_text_template = fsrc.read
+  body_text = ERB.new(body_text_template).result(binding)
   syntax_items = []
   body_text.gsub!(%r!<(pre|code)[^>]*?syntax=['"]([^'"]+)[^>]*>(.*?)</\1>!m){
     ident = syntax_items.length

data/test/henry_v_prolog.txt

@@ -0,0 +1,41 @@
+PROLOGUE
+
+Enter CHORUS
+
+CHORUS.
+    O for a Muse of fire, that would ascend
+    The brightest heaven of invention,
+    A kingdom for a stage, princes to act,
+    And monarchs to behold the swelling scene!
+    Then should the warlike Harry, like himself,
+    Assume the port of Mars; and at his heels,
+    Leash'd in like hounds, should famine, sword, and fire,
+    Crouch for employment. But pardon, gentles all,
+    The flat unraised spirits that hath dar'd
+    On this unworthy scaffold to bring forth
+    So great an object. Can this cockpit hold
+    The vasty fields of France? Or may we cram
+    Within this wooden O the very casques
+    That did affright the air at Agincourt?
+    O, pardon! since a crooked figure may
+    Attest in little place a million;
+    And let us, ciphers to this great accompt,
+    On your imaginary forces work.
+    Suppose within the girdle of these walls
+    Are now confin'd two mighty monarchies,
+    Whose high upreared and abutting fronts
+    The perilous narrow ocean parts asunder.
+    Piece out our imperfections with your thoughts:
+    Into a thousand parts divide one man,
+    And make imaginary puissance;
+    Think, when we talk of horses, that you see them
+    Printing their proud hoofs i' th' receiving earth;
+    For 'tis your thoughts that now must deck our kings,
+    Carry them here and there, jumping o'er times,
+    Turning th' accomplishment of many years
+    Into an hour-glass; for the which supply,
+    Admit me Chorus to this history;
+    Who prologue-like, your humble patience pray
+    Gently to hear, kindly to judge, our play. 
+
+