tomharris-random_data 1.5.1

data/lib/random_data/grammar.rb

@@ -0,0 +1,61 @@
+
+module RandomData
+  
+  # Defines methods for the generation of random data based on a supplied grammar.
+  
+  module Grammar
+  
+    # Returns simple sentences based on a supplied grammar, which must be a hash, the
+    # keys of which are symbols.  The values are either an array of successive values or a grammar 
+    # (i.e, hash with symbols as keys, and hashes or arrays as values.  The arrays contain symbols 
+    # referencing the keys in the present grammar, or strings to be output. The keys are always symbols.
+    #
+    # Example:
+    # Random.grammatical_construct({:story => [:man, " bites ", :dog], :man => { :bob => "Bob"}, :dog => {:a =>"Rex", :b =>"Rover"}}, :story)
+    # => "Bob bites Rover"
+    
+    def grammatical_construct(grammar, what=nil)
+      output = ""
+      if what.nil?
+        case grammar
+        when Hash
+          a_key = grammar.keys.sort_by{rand}[0]
+          output += grammatical_construct(grammar, a_key)
+        when Array
+          grammar.each do |item|
+            output += grammatical_construct(item)
+          end
+        when String
+          output += grammar
+        end
+      else
+        rhs = grammar[what]
+        case rhs
+        when Array
+          rhs.each do |item|
+            case item
+            when Symbol
+              output += grammatical_construct(grammar,item)
+            when String
+              output += item
+            when Hash
+              output += grammatical_construct(item)
+            else
+              raise "#{item.inspect} must be a symbol or string or Hash"
+            end
+          end
+        when Hash
+          output+= grammatical_construct(rhs)
+        when Symbol
+          output += grammatical_construct(rhs)
+        when String
+          output += rhs
+        else
+          raise "#{rhs.inspect} must be a symbol, string, Array or Hash"
+        end
+      end
+      return output
+    end
+
+  end
+end

data/lib/random_data/locations.rb

@@ -0,0 +1,134 @@
+# coding:utf-8
+
+module RandomData
+  
+  # Defines methods to return random location data.
+  
+  module Locations
+
+    
+    trees = %w( Acacia Beech Birch Cedar Cherry Chestnut Elm Larch Laurel
+                Linden Maple Oak Pine Rose Walnut Willow)
+    people = %w( Adams Franklin Jackson Jefferson Lincoln
+                  Madison Washington Wilson)
+    people_uk = %w( Churchill Tyndale Latimer Cranmer )
+    places = %w( Highland Hill Park Woodland Sunset Virginia)
+    numbers = %w( 1st 2nd 4th 5th 34th 42nd )
+    @@streetnames =  trees + people + places + numbers
+                    
+    @@street_types = %w(St Ave Rd Blvd Trl Ter Rdg Pl Pkwy Ct Circle)
+
+    # Returns the first line of a US maiiling address (street number, street name, street type)
+    #
+    # Example:
+    #
+    #Random.address_line_1 = "24317 Jefferson Blvd"
+    
+    def address_line_1
+      "#{rand(40000)} #{@@streetnames.rand} #{@@street_types.rand}"
+    end
+
+    alias :us_address_line_1 :address_line_1
+
+    @@line2types = ["Apt", "Bsmt", "Bldg", "Dept", "Fl", "Frnt", "Hngr", "Lbby", "Lot", "Lowr", "Ofc", "Ph", "Pier", "Rear", "Rm", "Side", "Slip", "Spc", "Stop", "Ste", "Trlr", "Unit", "Uppr"]
+
+    # Returns the first line of a US maiiling address (street number, street name, street type)
+    #
+    # Example:
+    #
+    #Random.address_line_1 = "24317 Jefferson Blvd"
+    
+    def address_line_2
+      "#{@@line2types.rand} #{rand(999)}"    
+    end
+
+    # Returns a random 5-digit string, not guaranteed to be a legitimate zip code.
+    # Legal zip codes can have leading zeroes and thus they need to be strings.  
+    
+    def zipcode
+     "%05d" % rand(99999) 
+    end
+
+
+    # Returns a string providing something in the general form of a UK post code.  Like the zip codes, this might
+    # not actually be valid. Doesn't cover London whose codes are like "SE1".
+
+    def uk_post_code
+      post_towns = %w(BM CB CV LE LI LS KT MK NE OX PL YO)
+      # Can't remember any othes at the moment
+      number_1  = rand(100).to_s
+      number_2  = rand(100).to_s
+      # Easier way to do this? 
+      letters = ("AA".."ZZ").to_a.rand
+
+      return "#{post_towns.rand}#{number_1} #{number_2}#{letters}"
+    end
+
+    # from technoweenie: http://svn.techno-weenie.net/projects/plugins/us_states/lib/us_states.rb
+    @@us_states = [["Alaska", "AK"], ["Alabama", "AL"], ["Arkansas", "AR"], ["Arizona", "AZ"], 
+                   ["California", "CA"], ["Colorado", "CO"], ["Connecticut", "CT"], ["District of Columbia", "DC"], 
+                   ["Delaware", "DE"], ["Florida", "FL"], ["Georgia", "GA"], ["Hawaii", "HI"], ["Iowa", "IA"], 
+                   ["Idaho", "ID"], ["Illinois", "IL"], ["Indiana", "IN"], ["Kansas", "KS"], ["Kentucky", "KY"], 
+                   ["Louisiana", "LA"], ["Massachusetts", "MA"], ["Maryland", "MD"], ["Maine", "ME"], ["Michigan", "MI"], 
+                   ["Minnesota", "MN"], ["Missouri", "MO"], ["Mississippi", "MS"], ["Montana", "MT"], ["North Carolina", "NC"], 
+                   ["North Dakota", "ND"], ["Nebraska", "NE"], ["New Hampshire", "NH"], ["New Jersey", "NJ"], 
+                   ["New Mexico", "NM"], ["Nevada", "NV"], ["New York", "NY"], ["Ohio", "OH"], ["Oklahoma", "OK"], 
+                   ["Oregon", "OR"], ["Pennsylvania", "PA"], ["Rhode Island", "RI"], ["South Carolina", "SC"], ["South Dakota", "SD"], 
+                   ["Tennessee", "TN"], ["Texas", "TX"], ["Utah", "UT"], ["Virginia", "VA"], ["Vermont", "VT"], 
+                   ["Washington", "WA"], ["Wisconsin", "WI"], ["West Virginia", "WV"], ["Wyoming", "WY"]]                    
+
+    # Returns a state 2-character abbreviation
+    # Random.state = "IL"
+    
+    def state
+      @@us_states.rand[1]
+    end
+
+    # Returns a full state name
+    #Random.state_full = "Texas"
+
+    def state_full
+      @@us_states.rand[0]   
+    end
+
+    # from http://siteresources.worldbank.org/DATASTATISTICS/Resources/CLASS.XLS
+    @@countries = ["Afghanistan", "Albania", "Algeria", "American Samoa", "Andorra", "Angola", "Antigua and Barbuda", "Argentina", "Armenia", "Aruba", "Australia", 
+                  "Austria", "Azerbaijan", "Bahamas, The", "Bahrain", "Bangladesh", "Barbados", "Belarus", "Belgium", "Belize", "Benin", "Bermuda", "Bhutan", 
+                  "Bolivia", "Bosnia and Herzegovina", "Botswana", "Brazil", "Brunei Darussalam", "Bulgaria", "Burkina Faso", "Burundi", "Cambodia", "Cameroon", 
+                  "Canada", "Cape Verde", "Cayman Islands", "Central African Republic", "Chad", "Channel Islands", "Chile", "China", "Colombia", "Comoros", "Congo, Dem. Rep.", 
+                  "Congo, Rep.", "Costa Rica", "Côte d'Ivoire", "Croatia", "Cuba", "Cyprus", "Czech Republic", "Denmark", "Djibouti", "Dominica", "Dominican Republic", "Ecuador", 
+                  "Egypt, Arab Rep.", "El Salvador", "Equatorial Guinea", "Eritrea", "Estonia", "Ethiopia", "Faeroe Islands", "Fiji", "Finland", "France", "French Polynesia", 
+                  "Gabon", "Gambia, The", "Georgia", "Germany", "Ghana", "Greece", "Greenland", "Grenada", "Guam", "Guatemala", "Guinea", "Guinea-Bissau", "Guyana", "Haiti", 
+                  "Honduras", "Hong Kong, China", "Hungary", "Iceland", "India", "Indonesia", "Iran, Islamic Rep.", "Iraq", "Ireland", "Isle of Man", "Israel", "Italy", "Jamaica", 
+                  "Japan", "Jordan", "Kazakhstan", "Kenya", "Kiribati", "Korea, Dem. Rep.", "Korea, Rep.", "Kuwait", "Kyrgyz Republic", "Lao PDR", "Latvia", "Lebanon", "Lesotho", 
+                  "Liberia", "Libya", "Liechtenstein", "Lithuania", "Luxembourg", "Macao, China", "Macedonia, FYR", "Madagascar", "Malawi", "Malaysia", "Maldives", "Mali", "Malta", 
+                  "Marshall Islands", "Mauritania", "Mauritius", "Mayotte", "Mexico", "Micronesia, Fed. Sts.", "Moldova", "Monaco", "Mongolia", "Montenegro", "Morocco", 
+                  "Mozambique", "Myanmar", "Namibia", "Nepal", "Netherlands", "Netherlands Antilles", "New Caledonia", "New Zealand", "Nicaragua", "Niger", "Nigeria", 
+                  "Northern Mariana Islands", "Norway", "Oman", "Pakistan", "Palau", "Panama", "Papua New Guinea", "Paraguay", "Peru", "Philippines", "Poland", "Portugal",
+                  "Puerto Rico", "Qatar", "Romania", "Russian Federation", "Rwanda", "Samoa", "San Marino", "São Tomé and Principe", "Saudi Arabia", "Senegal", "Serbia", 
+                  "Seychelles", "Sierra Leone", "Singapore", "Slovak Republic", "Slovenia", "Solomon Islands", "Somalia", "South Africa", "Spain", "Sri Lanka", "St. Kitts and Nevis", 
+                  "St. Lucia", "St. Vincent and the Grenadines", "Sudan", "Suriname", "Swaziland", "Sweden", "Switzerland", "Syrian Arab Republic", "Tajikistan", "Tanzania", "Thailand", 
+                  "Timor-Leste", "Togo", "Tonga", "Trinidad and Tobago", "Tunisia", "Turkey", "Turkmenistan", "Uganda", "Ukraine", "United Arab Emirates", "United Kingdom", 
+                  "United States", "Uruguay", "Uzbekistan", "Vanuatu", "Venezuela, RB", "Vietnam", "Virgin Islands (U.S.)", "West Bank and Gaza", "Yemen, Rep.", "Zambia", "Zimbabwe"]
+
+    # Returns a country name, as listed by the World Bank
+    #
+    #Random.country = "Kenya"
+    
+    def country
+      @@countries.rand
+    end
+
+    @@cities = %w(Midway Mount\ Pleasant Greenwood Franklin Oak Grove Centerville Salem Georgetown Fairview Riverside Rotorua Tauranga Whakatane Taupo Wanganui 
+                  Nababeep Aggeneys Pofadder Polokwane Bela Bela Goukamma Karatara Tswane Prieska Upington Hoopstad Bultfontein Wesselsbron Bothaville Trompsburg 
+                  Henneman Musina Ogies Kgatlahong Tembisa Tekoza Sebokeng Muntaung Umnkomaaz)
+
+    # Returns a generic city name, with an attempt to have some internationl appeal
+    #
+    # Random.city = "Tekoza"
+     
+    def city
+      @@cities.rand
+    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

@@ -0,0 +1,73 @@
+module RandomData
+
+  # Methods to create realistic-looking names
+  module Names
+    
+    # Returns a random letter
+    
+    def initial
+      ('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 
+                     WILLIAMS WILSON YORKE)
+
+    # Returns a random lastname
+    #
+    # >> Random.lastname
+    #
+    # "Harris"
+
+    def lastname
+      @@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 
+                            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 
+                              SARAH SHARON SUSAN TABITHA URSULA VICTORIA WENDY)
+
+    @@first_names = @@male_first_names + @@female_first_names
+
+
+    # Returns a random firstname
+    #
+    # >> Random.firstname
+    # 
+    # "Sandra"
+
+    def firstname
+      @@first_names.rand.capitalize
+    end
+
+
+    # Returns a random male firstname
+    #
+    # >> Random.firstname_male
+    # 
+    # "James"
+
+    def firstname_male
+      @@male_first_names.rand.capitalize
+    end
+
+
+    # Returns a random female firstname
+    #
+    # >> Random.firstname_female
+    # 
+    # "Mary"
+
+    def firstname_female
+      @@female_first_names.rand.capitalize
+    end
+
+  end
+end

data/lib/random_data/numbers.rb

@@ -0,0 +1,31 @@
+module RandomData
+  module Numbers
+    #n can be an Integer or a Range.  If it is an Integer, it just returns a random
+    #number greater than or equal to 0 and less than n.  If it is a Range, it
+    #returns a random number within the range
+    # Examples
+    #
+    # >> Random.number(5)
+    # => 4
+    # >> Random.number(5)
+    # => 2
+    # >> Random.number(5)
+    # => 1
+    def number(n)
+      n.is_a?(Range) ? n.to_a.rand : rand(n) 
+    end
+
+    # return a random bit, 0 or 1.
+    def bit
+      rand(2)
+    end
+
+    # return an array of n random bits.
+    def bits(n)
+      x = []
+      n.times {x << bit}
+      x
+    end
+
+  end
+end

data/lib/random_data/text.rb

@@ -0,0 +1,70 @@
+module RandomData
+  
+  module Text
+
+    # Methods to create random strings and paragraphs.
+    
+     # Returns a string of random upper- and lowercase alphanumeric characters.  Accepts a size parameters, defaults to 16 characters.
+     #
+     # >> Random.alphanumeric
+     #
+     # "Ke2jdknPYAI8uCXj"
+     #
+     # >> Random.alphanumeric(5)
+     #
+     # "7sj7i"
+
+    def alphanumeric(size=16)
+      s = ""
+      size.times { s << (i = Kernel.rand(62); i += ((i < 10) ? 48 : ((i < 36) ? 55 : 61 ))).chr }
+      s
+    end
+    
+    # TODO make these more coherent #:nodoc:
+
+    @@sentences = [
+     "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",
+     "There's a voice that keeps on calling me",
+     "Down the road that's where I'll always be",
+     "Every stop I make I make a new friend; Can't stay for long just turn around and I'm gone again",
+     "Maybe tomorrow I'll want to settle down - until tomorrow I'll just keep moving on",
+     "Hong Kong Phooey number one super guy, Hong Kong Phooey quicker than the human eye",
+     "He's got style, a groovy style, and a car that just won't stop",
+     "Hey there where ya goin, not exactly knowin'",
+     "Who says you have to call just one place home?",
+     "He's going everywhere, B.J. McKay and his best friend Bear",
+     "He just keeps on movin' and ladies keep improvin'",
+     "Every day is better than the last, with new dreams and better scenes and best of all I don't pay property tax",
+     "Rolling  down to Dallas - who is providin' my palace?",
+     "Off to New Orleans or who knows where",
+     "Soaring through all the galaxies in search of Earth flying in to the night",
+     "Ulysses, fighting evil and tyranny with all his power and with all of his might",
+     "No-one else can do the things you do, like a bolt of thunder from the blue",
+     "Always fighting all the evil forces bringing peace and justice to all",
+     "I've gotten burned over Cheryl Tiegs and blown up for Raquel Welch, but when I end up in the hay it's only hay, hey hey",
+     "I might jump an open drawbridge or Tarzan from a vine, beause I'm the unknown stuntman that makes Eastwood look so fine"] 
+
+    # Returns a given number of paragraphs delimited by two newlines (defaults to two paragraphs), using a small pool of generic sentences.
+    # >> Random.paragraphs  
+    #
+    # "I might jump an open drawbridge or Tarzan from a vine, beause I'm the unknown stuntman that makes Eastwood look so fine.\n\n \Always fighting all the evil forces bringing peace and justice to all. \n\n"
+     
+   def paragraphs(num = 2)
+     text = ''
+ 
+     num.times do 
+       (rand(5)+1).times do
+         text += @@sentences.rand + '. '
+       end
+       text += "\n\n"
+     end
+ 
+     return text
+ 
+   end
+
+ end
+end