data-anonymization 0.8.0 → 0.8.5

data/lib/strategy/blacklist.rb

@@ -3,15 +3,16 @@ module DataAnon
     class Blacklist < DataAnon::Strategy::Base
 
       def process_record index, record
+        updates = {}
         @fields.each do |field, strategy|
           database_field_name = record.attributes.select { |k,v| k == field }.keys[0]
           field_value = record.attributes[database_field_name]
           unless field_value.nil? || is_primary_key?(database_field_name)
             field = DataAnon::Core::Field.new(database_field_name, field_value, index, record, @name)
-            record[database_field_name] = strategy.anonymize(field)
+            updates[database_field_name] = strategy.anonymize(field)
           end
         end
-        record.save!
+        record.update_columns(updates) if updates.any?
       end
 
     end

data/lib/strategy/field/datetime/anonymize_time.rb

@@ -58,8 +58,8 @@ module DataAnon
           month = @anonymize_month? DataAnon::Utils::RandomInt.generate(1,12) : original_time.month
           days_in_month = Time.new(year,month,1,1,1,1).end_of_month.day
           day = @anonymize_day? DataAnon::Utils::RandomInt.generate(1,days_in_month) : original_time.day
-          hour = @anonymize_hour? DataAnon::Utils::RandomInt.generate(1,24) : original_time.hour
-          min = @anonymize_min? DataAnon::Utils::RandomInt.generate(1,60) : original_time.min
+          hour = @anonymize_hour? DataAnon::Utils::RandomInt.generate(0,23) : original_time.hour
+          min = @anonymize_min? DataAnon::Utils::RandomInt.generate(0,59) : original_time.min
           sec = original_time.sec
 
           create_object(year, month, day, hour, min, sec)
@@ -74,4 +74,4 @@ module DataAnon
       end
     end
   end
-end
+end

data/lib/strategy/field/default_anon.rb

@@ -5,6 +5,7 @@ module DataAnon
       class DefaultAnon
 
         DEFAULT_STRATEGIES = {:string => FieldStrategy::RandomString.new,
+                              :integer => FieldStrategy::RandomIntegerDelta.new(5),
                               :fixnum => FieldStrategy::RandomIntegerDelta.new(5),
                               :bignum => FieldStrategy::RandomIntegerDelta.new(5000),
                               :float => FieldStrategy::RandomFloatDelta.new(5.0),

data/lib/strategy/field/number/random_big_decimal_delta.rb

@@ -16,7 +16,7 @@ module DataAnon
         end
 
         def anonymize field
-          return BigDecimal.new("#{field.value + DataAnon::Utils::RandomFloat.generate(-@delta, +@delta)}")
+          return BigDecimal("#{field.value + DataAnon::Utils::RandomFloat.generate(-@delta, +@delta)}")
         end
 
       end

data/lib/strategy/field/string/random_url.rb

@@ -5,7 +5,7 @@ module DataAnon
       # Generates a randomized URL while maintaining the structure of the original url
       #
       #    !!!ruby
-      #    anonymize('fb_profile').using FieldStrategy::RandomURL.new
+      #    anonymize('fb_profile').using FieldStrategy::RandomUrl.new
 
     class RandomUrl
 

data/lib/strategy/field/string/select_from_database.rb

@@ -12,16 +12,23 @@ module DataAnon
         include Utils::Logging
 
         def initialize table_name, field_name, connection_spec
-          DataAnon::Utils::SourceDatabase.establish_connection connection_spec
-          source = Utils::SourceTable.create table_name, []
-          @values = source.select(field_name).distinct.collect { |record| record[field_name]}
-          logger.debug "For field strategy #{table_name}:#{field_name} using values #{@values} "
-
+          @table_name = table_name
+          @field_name = field_name
+          @connection_spec = connection_spec
         end
 
-      end
-
+        def anonymize field
+          @values ||= begin
+            DataAnon::Utils::SourceDatabase.establish_connection @connection_spec
+            source = Utils::SourceTable.create @table_name, []
+            values = source.select(@field_name).distinct.collect { |record| record[@field_name]}
+            logger.debug "For field strategy #{@table_name}:#{@field_name} using values #{values} "
+            values
+          end
 
+          super
+        end
+      end
     end
   end
 end

data/lib/strategy/strategies.rb

@@ -9,5 +9,5 @@ begin
   require 'strategy/mongodb/whitelist'
   require 'strategy/mongodb/blacklist'
 rescue LoadError
-  "Ignoring the mongodb specific libraries if monog driver is not specified in gem"
+  'Ignoring the mongodb specific libraries if monog driver is not specified in gem'
 end

data/lib/thor/helpers/mongodb_dsl_generator.rb

@@ -18,13 +18,13 @@ module DataAnon
 
       def generate
 
-        db = Mongo::Connection.from_uri(@mongodb_uri)[@configuration_hash[:database]]
+        db = Mongo::Client.new(@mongodb_uri, :database => @configuration_hash[:database])
         collections = db.collections
         collections.each do |collection|
           unless collection.name.start_with?('system.')
             depth = 2
             @output << "\tcollection '#{collection.name}' do"
-            document = collection.find_one
+            document = collection.find({}).first
             process_document(depth, document)
             @output << "\tend\n"
           end
@@ -63,4 +63,3 @@ module DataAnon
     end
   end
 end
-

data/lib/utils/database.rb

@@ -25,7 +25,7 @@ module DataAnon
 
       def self.create_table  database, table_name, primary_keys = []
         klass_name = table_name.to_s.downcase.capitalize
-        return database.const_get klass_name if database.const_defined? klass_name
+        return database.const_get(klass_name, false) if database.const_defined?(klass_name, false)
         database.const_set(klass_name, Class.new(database) do
             self.table_name = table_name
             self.primary_keys = primary_keys if primary_keys.length > 1

data/lib/utils/random_int.rb

@@ -4,8 +4,8 @@ module DataAnon
 
       def self.generate min, max
         return 0 if (min == 0 && max == 0)
-        Random.new.rand min...max
+        Random.new.rand min..max
       end
     end
   end
-end
+end

data/lib/utils/template_helper.rb

@@ -5,9 +5,11 @@ module DataAnon
       def self.source_connection_specs_rdbms config_hash
 
         config_hash.keys.reject{|key| config_hash[key].nil? }.collect { |key|
-          if ((config_hash[key].class.to_s.downcase == "string"))
+          if ((config_hash[key].class.to_s.downcase == 'string'))
             ":#{key} => '#{config_hash[key]}'"
-          elsif ((config_hash[key].class.to_s.downcase == "fixnum"))
+          elsif ((config_hash[key].class.to_s.downcase == 'integer'))
+            ":#{key} => #{config_hash[key]}"
+          elsif ((config_hash[key].class.to_s.downcase == 'fixnum'))
             ":#{key} => #{config_hash[key]}"
           end
         }.join ', '

data/lib/version.rb

@@ -1,3 +1,3 @@
 module DataAnonymization
-  VERSION = '0.8.0'
+  VERSION = '0.8.5'
 end

data/spec/acceptance/mongodb_blacklist_spec.rb

@@ -1,56 +1,56 @@
-require "spec_helper"
+require 'spec_helper'
 require 'mongo'
 
-describe "End 2 End MongoDB Blacklist Acceptance Test" do
+describe 'End 2 End MongoDB Blacklist Acceptance Test' do
 
   before(:each) do
-    Mongo::Client.new("mongodb://localhost/test").database().drop()
+    Mongo::Client.new('mongodb://localhost/test').database().drop()
     users = [
         {
-            "_id" => 1,
-            "USER_ID" => "sunitparekh",
-            "date_of_birth" => Time.new(2012, 7, 14, 13, 1, 0),
-            "email" => "parekh-sunit@mailinator.com",
-            "password" => "TfqIK8Pd8GlbMDFZCX4l/5EtnOkfLCeynOL85tJQuxum&382knaflk@@",
-            "failed_attempts" => 0,
-            "first_name" => "Sunit",
-            "last_name" => "Parekh",
-            "password_reset_answer" => "manza",
-            "password_reset_question" => "My new car modal?",
-            "updated_at" => Time.new(2012, 8, 15, 13, 1, 0),
-            "alternate_emails" => ["abc@test.com","abc2@test.com"]
+            '_id' => 1,
+            'USER_ID' => 'sunitparekh',
+            'date_of_birth' => Time.new(2012, 7, 14, 13, 1, 0),
+            'email' => 'parekh-sunit@mailinator.com',
+            'password' => 'TfqIK8Pd8GlbMDFZCX4l/5EtnOkfLCeynOL85tJQuxum&382knaflk@@',
+            'failed_attempts' => 0,
+            'first_name' => 'Sunit',
+            'last_name' => 'Parekh',
+            'password_reset_answer' => 'manza',
+            'password_reset_question' => 'My new car modal?',
+            'updated_at' => Time.new(2012, 8, 15, 13, 1, 0),
+            'alternate_emails' => ['abc@test.com', 'abc2@test.com']
 
         },
         {
-            "_id" => 2,
-            "USER_ID" => "anandagrawal",
-            "date_of_birth" => Time.new(2011, 8, 11, 13, 1, 0),
-            "email" => "anand-agrawal@mailinator.com",
-            "password" => "Tz548O0RWusldVAWkwqfzO3jK/X4l/5EtnOkfLCeynOL85tJQuxum",
-            "failed_attempts" => 0,
-            "first_name" => "Anand",
-            "last_name" => "Agrawal",
-            "password_reset_answer" => "android",
-            "password_reset_question" => "My phone?",
-            "updated_at" => Time.new(2012, 2, 11, 13, 1, 0),
-            "alternate_emails" => ["abc@test.com","abc2@test.com"]
+            '_id' => 2,
+            'USER_ID' => 'anandagrawal',
+            'date_of_birth' => Time.new(2011, 8, 11, 13, 1, 0),
+            'email' => 'anand-agrawal@mailinator.com',
+            'password' => 'Tz548O0RWusldVAWkwqfzO3jK/X4l/5EtnOkfLCeynOL85tJQuxum',
+            'failed_attempts' => 0,
+            'first_name' => 'Anand',
+            'last_name' => 'Agrawal',
+            'password_reset_answer' => 'android',
+            'password_reset_question' => 'My phone?',
+            'updated_at' => Time.new(2012, 2, 11, 13, 1, 0),
+            'alternate_emails' => ['abc@test.com', 'abc2@test.com']
         }
     ]
-    users_coll = Mongo::Client.new("mongodb://localhost/test").database().collection('users')
+    users_coll = Mongo::Client.new('mongodb://localhost/test').database().collection('users')
     users.each { |p| users_coll.insert_one p }
   end
 
-  it "should anonymize plans collection" do
+  it 'should anonymize plans collection' do
 
     database 'test' do
       strategy DataAnon::Strategy::MongoDB::Blacklist
-      source_db :mongodb_uri => "mongodb://localhost/test", :database => 'test'
+      source_db :mongodb_uri => 'mongodb://localhost/test', :database => 'test'
 
       collection 'users' do
         anonymize('date_of_birth').using FieldStrategy::TimeDelta.new(5,30)
         anonymize('USER_ID').using FieldStrategy::StringTemplate.new('user-#{row_number}')
         anonymize('email').using FieldStrategy::RandomMailinatorEmail.new
-        anonymize('password') { |field| "password" }
+        anonymize('password') { |field| 'password'}
         anonymize('first_name').using FieldStrategy::RandomFirstName.new
         anonymize('last_name').using FieldStrategy::RandomLastName.new
         anonymize('alternate_emails').using FieldStrategy::AnonymizeArray.new(FieldStrategy::RandomMailinatorEmail.new)
@@ -58,20 +58,20 @@ describe "End 2 End MongoDB Blacklist Acceptance Test" do
 
     end
 
-    users_coll = Mongo::Client.new("mongodb://localhost/test").database().collection('users')
+    users_coll = Mongo::Client.new('mongodb://localhost/test').database().collection('users')
     users_coll.find.count.to_int.should be 2
     user = users_coll.find({'_id' => 1}).to_a[0]
 
     user['_id'].should == 1
-    user['USER_ID'].should == "user-1"
+    user['USER_ID'].should == 'user-1'
     user['date_of_birth'].to_i.should_not == Time.new(2012, 7, 14, 13, 1, 0).to_i
-    user['email'].should_not == "parekh-sunit@mailinator.com"
-    user['password'].should == "password"
+    user['email'].should_not == 'parekh-sunit@mailinator.com'
+    user['password'].should == 'password'
     user['failed_attempts'].should == 0
-    user['first_name'].should_not be "Sunit"
-    user['last_name'].should_not be "Parekh"
-    user['password_reset_answer'].should == "manza"
-    user['password_reset_question'].should == "My new car modal?"
+    user['first_name'].should_not be 'Sunit'
+    user['last_name'].should_not be 'Parekh'
+    user['password_reset_answer'].should == 'manza'
+    user['password_reset_question'].should == 'My new car modal?'
     user['updated_at'].to_i.should == Time.new(2012, 8, 15, 13, 1, 0).to_i
     user['alternate_emails'].length.should == 2
     user['alternate_emails'][0].should_not == 'abc@test.com'

data/spec/acceptance/mongodb_whitelist_spec.rb

@@ -1,65 +1,65 @@
-require "spec_helper"
+require 'spec_helper'
 require 'mongo'
 
-describe "End 2 End MongoDB Whitelist Acceptance Test" do
+describe 'End 2 End MongoDB Whitelist Acceptance Test' do
 
   before(:each) do
-    Mongo::Client.new("mongodb://localhost/test").database.drop
-    Mongo::Client.new("mongodb://localhost/dest").database.drop
+    Mongo::Client.new('mongodb://localhost/test').database.drop
+    Mongo::Client.new('mongodb://localhost/dest').database.drop
     plans = [
         {
-            "_id" => 1,
-            "name" => "Free",
-            "nick_names" => ["Name1","Name2"],
-            "features" => [
+            '_id' => 1,
+            'name' => 'Free',
+            'nick_names' => ['Name1', 'Name2'],
+            'features' => [
                 {
-                    "max_storage" => 21474836480,
-                    "type" => "AmazonS3",
-                    "users" => {"max" => 1, "additional" => false}
+                    'max_storage' => 21474836480,
+                    'type' => 'AmazonS3',
+                    'users' => {'max' => 1, 'additional' => false}
                 },
                 {
-                    "max_storage" => 21474836480,
-                    "type" => "DropBox",
-                    "users" => {"max" => 1, "additional" => false}
+                    'max_storage' => 21474836480,
+                    'type' => 'DropBox',
+                    'users' => {'max' => 1, 'additional' => false}
                 }
             ],
-            "term" => "month",
-            "public_sharing" => false,
-            "photo_sharing" => true,
-            "created_at" => Time.new(2012, 6, 21, 13, 30, 0)
+            'term' => 'month',
+            'public_sharing' => false,
+            'photo_sharing' => true,
+            'created_at' => Time.new(2012, 6, 21, 13, 30, 0)
         },
         {
-            "_id" => 2,
-            "name" => "Team",
-            "plan_aliases" => ["Business", "Paid"],
-            "features" => [
+            '_id' => 2,
+            'name' => 'Team',
+            'plan_aliases' => ['Business', 'Paid'],
+            'features' => [
                 {
-                    "max_storage" => 53687091200,
-                    "type" => "AmazonS3",
-                    "users" => {"max" => 5, "additional" => true}
+                    'max_storage' => 53687091200,
+                    'type' => 'AmazonS3',
+                    'users' => {'max' => 5, 'additional' => true}
                 },
                 {
-                    "max_storage" => 53687091200,
-                    "type" => "DropBox",
-                    "users" => {"max" => 5, "additional" => true}
+                    'max_storage' => 53687091200,
+                    'type' => 'DropBox',
+                    'users' => {'max' => 5, 'additional' => true}
                 }
             ],
-            "term" => "month",
-            "public_sharing" => true,
-            "photo_sharing" => true,
-            "created_at" => Time.new(2012, 8, 11, 13, 1, 0)
+            'term' => 'month',
+            'public_sharing' => true,
+            'photo_sharing' => true,
+            'created_at' => Time.new(2012, 8, 11, 13, 1, 0)
         }
     ]
-    plans_coll =  Mongo::Client.new("mongodb://localhost/test").database.collection('plans')
+    plans_coll =  Mongo::Client.new('mongodb://localhost/test').database.collection('plans')
     plans.each { |p| plans_coll.insert_one p }
   end
 
-  it "should anonymize plans collection" do
+  it 'should anonymize plans collection' do
 
     database 'dest' do
       strategy DataAnon::Strategy::MongoDB::Whitelist
-      source_db :mongodb_uri => "mongodb://localhost/test", :database => 'test'
-      destination_db :mongodb_uri => "mongodb://localhost/dest", :database => 'dest'
+      source_db :mongodb_uri => 'mongodb://localhost/test', :database => 'test'
+      destination_db :mongodb_uri => 'mongodb://localhost/dest', :database => 'dest'
 
       collection 'plans' do
         whitelist '_id', 'name', 'term', 'created_at'
@@ -78,15 +78,15 @@ describe "End 2 End MongoDB Whitelist Acceptance Test" do
 
     end
 
-    plans_coll = Mongo::Client.new("mongodb://localhost/dest").database.collection('plans')
+    plans_coll = Mongo::Client.new('mongodb://localhost/dest').database.collection('plans')
     plans_coll.find.count.to_int.should be 2
     plan = plans_coll.find({ '_id' => 1}).to_a[0]
 
     plan['_id'].should == 1
-    plan['name'].should == "Free"
-    plan['nick_names'][0].should_not == "Name1"
-    plan['nick_names'][1].should_not == "Name2"
-    plan['term'].should == "month"
+    plan['name'].should == 'Free'
+    plan['nick_names'][0].should_not == 'Name1'
+    plan['nick_names'][1].should_not == 'Name2'
+    plan['term'].should == 'month'
     plan['created_at'].should == Time.new(2012, 6, 21, 13, 30, 0)
     plan['plan_aliases'].should be_nil
     [true,false].should include(plan['public_sharing'])
@@ -94,14 +94,14 @@ describe "End 2 End MongoDB Whitelist Acceptance Test" do
     plan['features'].length.should == 2
     feature1 = plan['features'][0]
     [10737418240, 21474836480, 53687091200].should include(feature1['max_storage'])
-    feature1['type'].should == "AmazonS3"
-    feature1['users']['max'].should be_kind_of(Fixnum)
+    feature1['type'].should == 'AmazonS3'
+    feature1['users']['max'].should be_kind_of(Integer)
     [true,false].should include(feature1['users']['additional'])
 
 
     plan = plans_coll.find({ '_id' => 2}).to_a[0]
     plan['plan_aliases'].length.should == 2
-    ["Free", "Team", "Business", "Paid"].should include(plan['plan_aliases'][0])
-    ["Free", "Team", "Business", "Paid"].should include(plan['plan_aliases'][1])
+    ['Free', 'Team', 'Business', 'Paid'].should include(plan['plan_aliases'][0])
+    ['Free', 'Team', 'Business', 'Paid'].should include(plan['plan_aliases'][1])
   end
 end

data/spec/acceptance/rdbms_whitelist_spec.rb

@@ -1,4 +1,4 @@
-require "spec_helper"
+require 'spec_helper'
 
 describe 'End 2 End RDBMS Whitelist Acceptance Test using SQLite database' do
 

data/spec/acceptance/rdbms_whitelist_with_primary_key_spec.rb

@@ -1,6 +1,6 @@
-require "spec_helper"
+require 'spec_helper'
 
-describe "End 2 End RDBMS Whitelist Acceptance Test using SQLite database" do
+describe 'End 2 End RDBMS Whitelist Acceptance Test using SQLite database' do
 
   source_connection_spec = {:adapter => 'sqlite3', :database => 'tmp/customer.sqlite'}
   dest_connection_spec = {:adapter => 'sqlite3', :database => 'tmp/customer-dest.sqlite'}
@@ -13,9 +13,9 @@ describe "End 2 End RDBMS Whitelist Acceptance Test using SQLite database" do
     CustomerSample.create_schema dest_connection_spec
   end
 
-  it "should anonymize customer table record " do
+  it 'should anonymize customer table record ' do
 
-    database "Customer" do
+    database 'Customer' do
       strategy DataAnon::Strategy::Whitelist
       source_db source_connection_spec
       destination_db dest_connection_spec
@@ -37,14 +37,14 @@ describe "End 2 End RDBMS Whitelist Acceptance Test using SQLite database" do
 
     DataAnon::Utils::DestinationDatabase.establish_connection dest_connection_spec
     dest_table = DataAnon::Utils::DestinationTable.create 'customers'
-    new_rec = dest_table.where("cust_id" => CustomerSample::SAMPLE_DATA[0][:cust_id]).first
-    new_rec.first_name.should_not be("Sunit")
-    new_rec.last_name.should_not be("Parekh")
+    new_rec = dest_table.where('cust_id' => CustomerSample::SAMPLE_DATA[0][:cust_id]).first
+    new_rec.first_name.should_not be('Sunit')
+    new_rec.last_name.should_not be('Parekh')
     new_rec.birth_date.should_not be(Date.new(1977,7,8))
     new_rec.address.should == 'F 501 Shanti Nagar'
     ['Gujrat','Karnataka'].should include(new_rec.state)
     new_rec.zipcode.should == '411048'
-    new_rec.phone.should_not be "9923700662"
+    new_rec.phone.should_not be '9923700662'
     new_rec.email.should == 'test+1@gmail.com'
     [true,false].should include(new_rec.terms_n_condition)
     new_rec.age.should be_between(0,100)