data_cleaner 0.0.3 → 0.0.4

data/README.txt

@@ -6,6 +6,9 @@ DataCleaner wants to make sure your data still looks real, and importantly, pass
 
 Only data that need anonymising needs to be specified, foreign keys, non-customer-identifiable data should be left alone.
 
+* rdoc[http://sourcetagsandcodes.com/data_cleaner/doc/]
+* source[https://github.com/matsadler/data_cleaner]
+
 == Installation
 
 gem install data_cleaner
@@ -35,13 +38,17 @@ gem install data_cleaner
   end
   
   module DataCleaner::Formats
+    helper :embarrassing_secret do
+      "I like " + ["the colour pink", "programming PHP", "Judas Priest"].sample
+    end
+    
     format "TopSecret" do |f|
       f.name [:first_name, " ", :last_name]
       f.email :email, &:name # passes the objects name to the email method
-      f.reference do |secret|
-        "#{secret.name[0..2].downcase}#{secret.date.strftime("%y")}"
+      f.reference do |obj| # one off helper
+        "#{obj.name[0..2].downcase}#{obj.date.strftime("%y")}"
       end
-      f.secret "test"
+      f.secret :embarrassing_secret
     end
   end
   
@@ -58,11 +65,123 @@ gem install data_cleaner
 prints:
   
   #<TopSecret:0x1015f7830 @email="mat@foo.com", @date=Mon Jan 17 16:53:19 +0000 2011, @name="Matthew Sadler", @secret="I like kittens", @reference="mat09">
-is valid? true
+  is valid? true
   
-  #<TopSecret:0x1015f7830 @email="javier.kuhlman@franeckikonopelski.co.uk", @date=Mon Jan 17 16:53:19 +0000 2011, @name="Javier Kuhlman", @secret="test", @reference="jav11">
-is valid? true
+  #<TopSecret:0x1015f7830 @email="javier.kuhlman@franeckikonopelski.co.uk", @date=Mon Jan 17 16:53:19 +0000 2011, @name="Javier Kuhlman", @secret="the colour pink", @reference="jav11">
+  is valid? true
+
+== Formats
+There are various ways of specifying the format of an attribute.
+
+=== Basic Symbol
+
+  format "TopSecret" do |f|
+    f.name :first_name
+  end
+In this case the helper :first_name will be used to replace the name attribute
+
+=== Symbol With Arguments
+
+  format "TopSecret" do |f|
+    f.email :email, "Arthur"
+  end
+The helper :email will be used to replace the attribute, and be given the argument "Arthur"
+
+=== Symbol With Block
+
+  format "TopSecret" do |f|
+    f.name :first_name
+    f.email(:email) {|obj| obj.name}
+  end
+In this example the :email helper will be given the objects replacement name as an argument
+
+  format "TopSecret" do |f|
+    f.email(:email) {|obj| obj.name}
+    f.name :first_name
+  end
+Here the :email helper will get the objects original name as an argument
+
+=== String
+
+  format "TopSecret" do |f|
+    f.name "Arthur"
+  end
+In this case the name will simply be replaced with the string specified
+
+=== Array
+
+  format "TopSecret" do |f|
+    f.name [:first_name, " ", :last_name]
+  end
+With an array the individual elements behave like those above, then they are concatenated together, in this example the results from the :first_name and :last_name helpers will be joined with the string " " between them
+
+=== Nested Arrays
+
+   format "TopSecret" do |f|
+     f.emails [[:email, "Arthur"], ", ", [:email, "Ford"]]
+   end
+In this example the :email helper will be called twice, once with the argument "Arthur", then again with the argument "Ford", and these will be joined by the string ", "
+
+=== Block
+
+  format "TopSecret" do |f|
+    f.secret {|obj| rand(100)}
+  end
+When using a block the attribute will be replaced by the result of the block.
+
+== Built-in helpers
+The built-in helpers use the faker gem to generate data, see the faker documentation for more details
+
+:name
+:first_name
+:last_name
+:name_prefix
+:name_suffix
+
+:phone_number
+
+:city
+:city_prefix
+:city_suffix
+:secondary_address
+:street_address
+:street_name
+:street_suffix
+:uk_country
+:uk_county
+:uk_postcode
+:us_state
+:us_state_abbr
+:zip_code
+
+:domain_name
+:domain_suffix
+:domain_word
+:email
+:free_email
+:user_name
+
+:bs
+:catch_phrase
+:company_name
+:company_suffix
+
+:paragraph
+:paragraphs
+:sentence
+:sentences
+:words
+
+== Custom helpers
+Custom helpers can be defined like 
+
+  module DataCleaner::Formats
+    helper :embarrassing_secret do
+      "I like " + ["the colour pink", "programming PHP", "Judas Priest"].sample
+    end
+  end
 
+This can also be used to redefine the built-in helpers.
 
 == Licence
 

data/lib/data_cleaner/cleaner.rb

@@ -1,4 +1,4 @@
-module DataCleaner
+module DataCleaner # :nodoc:
   # DataCleaner::Cleaner is a module which can either be mixed-in, or used
   # standalone to anonymise the data held within objects.
   # 
@@ -6,57 +6,6 @@ module DataCleaner
   # DataCleaner::Formats.
   # 
   module Cleaner
-    # In the format 
-    #   :specifier => instance
-    # the method specifier will be called on instance
-    # 
-    # whereas with
-    #   :specifier => [instance, :method]
-    # the method method will be called on instance.
-    # 
-    # :specifier is used when describing the format of your object's attributes
-    # 
-    MAPPING = {
-      :name => Faker::Name,
-      :first_name => Faker::Name,
-      :last_name => Faker::Name,
-      :name_prefix => [Faker::Name, :prefix],
-      :name_suffix => [Faker::Name, :suffix],
-      
-      :phone_number => Faker::PhoneNumber,
-      
-      :city => Faker::Address,
-      :city_prefix => Faker::Address,
-      :city_suffix => Faker::Address,
-      :secondary_address => Faker::Address,
-      :street_address => Faker::Address,
-      :street_name => Faker::Address,
-      :street_suffix => Faker::Address,
-      :uk_country => Faker::Address,
-      :uk_county => Faker::Address,
-      :uk_postcode => Faker::Address,
-      :us_state => Faker::Address,
-      :us_state_abbr => Faker::Address,
-      :zip_code => Faker::Address,
-      
-      :domain_name => Faker::Internet,
-      :domain_suffix => Faker::Internet,
-      :domain_word => Faker::Internet,
-      :email => Faker::Internet,
-      :free_email => Faker::Internet,
-      :user_name => Faker::Internet,
-      
-      :bs => Faker::Company,
-      :catch_phrase => Faker::Company,
-      :company_name => [Faker::Company, :name],
-      :company_suffix => [Faker::Company, :suffix],
-      
-      :paragraph => Faker::Lorem,
-      :paragraphs => Faker::Lorem,
-      :sentence => Faker::Lorem,
-      :sentences => Faker::Lorem,
-      :words => Faker::Lorem,
-    }
     
     # :call-seq: Cleaner.clean_value(attr, klass, instance=nil) -> clean_value
     #
@@ -112,7 +61,7 @@ module DataCleaner
         first
       when Symbol
         args.map! {|arg| if arg.is_a?(Proc) then arg.call(object) end || arg}
-        __data__(first, *args)
+        DataCleaner::Formats.helpers[first].call(*args)
       when Array
         first.map do |e|
           e = [e] unless e.is_a?(Array)
@@ -123,10 +72,5 @@ module DataCleaner
       end
     end
     
-    def __data__(type, *args)
-      klass, method = DataCleaner::Cleaner::MAPPING[type]
-      klass.send(method || type, *args)
-    end
-    
   end
 end

data/lib/data_cleaner/format.rb

@@ -1,4 +1,4 @@
-module DataCleaner
+module DataCleaner # :nodoc:
   # DataCleaner::Format can be used to describe the format of an object's
   # attributes.
   # 
@@ -6,7 +6,7 @@ module DataCleaner
   #   f = DataCleaner::Format.new("Person")
   #   f.name [:first_name, " ", :last_name]
   # 
-  # You most likely do not want to use this class directly, bu instead though
+  # You most likely do not want to use this class directly, but instead through
   # DataCleaner::Formats.
   # 
   class Format < if defined? BasicObject then BasicObject else Object end

data/lib/data_cleaner/formats.rb

@@ -1,17 +1,4 @@
-unless :Symbol.respond_to?(:to_proc)
-  class Symbol
-    def to_proc
-      Proc.new(&method(:__apply__))
-    end
-    
-    private
-    def __apply__(*args)
-      args.shift.send(self, *args)
-    end
-  end
-end
-
-module DataCleaner
+module DataCleaner # :nodoc:
   # DataCleaner::Formats provides a DSL for describing, and method for looking
   # up the format of object's attributes, such that they can be replaced with
   # fake data, but still pass validation.
@@ -33,8 +20,28 @@ module DataCleaner
   #   end
   # 
   module Formats
-    class << self; attr_accessor :formats end
+    class << self; attr_accessor :formats, :helpers end
     self.formats = {}
+    self.helpers = {}
+    
+    # :call-seq: Formats.helper(name) {|*args| block } -> helper
+    # 
+    # Define a format helper, which can then be used in a format block
+    # 
+    # Example:
+    #   module DataCleaner::Formats
+    #     helper :ip_address do
+    #       Array.new(4).map {rand(255)}.join(".")
+    #     end
+    #     
+    #     format "Server" do |f|
+    #       f.ip :ip_address
+    #     end
+    #   end
+    # 
+    def self.helper(name, &block)
+      helpers[name] = block
+    end
     
     # :call-seq: Formats.format(klass) {|format| block } -> format
     # 
@@ -59,5 +66,61 @@ module DataCleaner
       end
     end
     
+    # Set up default helpers
+    # 
+    # In the format
+    #   :name => receiver
+    # the method name will be called on receiver
+    # 
+    # whereas with
+    #   :name => [receiver, :method]
+    # the method method will be called on receiver.
+    # 
+    # :name is used when describing the format of your object's attributes
+    # 
+    {
+      :name => Faker::Name,
+      :first_name => Faker::Name,
+      :last_name => Faker::Name,
+      :name_prefix => [Faker::Name, :prefix],
+      :name_suffix => [Faker::Name, :suffix],
+      
+      :phone_number => Faker::PhoneNumber,
+      
+      :city => Faker::Address,
+      :city_prefix => Faker::Address,
+      :city_suffix => Faker::Address,
+      :secondary_address => Faker::Address,
+      :street_address => Faker::Address,
+      :street_name => Faker::Address,
+      :street_suffix => Faker::Address,
+      :uk_country => Faker::Address,
+      :uk_county => Faker::Address,
+      :uk_postcode => Faker::Address,
+      :us_state => Faker::Address,
+      :us_state_abbr => Faker::Address,
+      :zip_code => Faker::Address,
+      
+      :domain_name => Faker::Internet,
+      :domain_suffix => Faker::Internet,
+      :domain_word => Faker::Internet,
+      :email => Faker::Internet,
+      :free_email => Faker::Internet,
+      :user_name => Faker::Internet,
+      
+      :bs => Faker::Company,
+      :catch_phrase => Faker::Company,
+      :company_name => [Faker::Company, :name],
+      :company_suffix => [Faker::Company, :suffix],
+      
+      :paragraph => Faker::Lorem,
+      :paragraphs => Faker::Lorem,
+      :sentence => Faker::Lorem,
+      :sentences => Faker::Lorem,
+      :words => Faker::Lorem,
+    }.each do |name, (receiver, method)|
+      helper(name, &receiver.method(method || name))
+    end
+    
   end
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: data_cleaner
 version: !ruby/object:Gem::Version 
-  hash: 25
+  hash: 23
   prerelease: false
   segments: 
   - 0
   - 0
-  - 3
-  version: 0.0.3
+  - 4
+  version: 0.0.4
 platform: ruby
 authors: 
 - Matthew Sadler
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-02-04 00:00:00 +00:00
+date: 2011-02-09 00:00:00 +00:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency