data-anonymization 0.7.1 → 0.7.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: afcaf064c0b8135149e5fb8e559ab95df8088516
-  data.tar.gz: 795dbba88fead534acdcb87b4cf18fd4bdf12ad8
+  metadata.gz: e3354956cfd68076ea4bc342f611a9934f2b7385
+  data.tar.gz: ac064ad09012df2877aa29bd726c9e074749c7ec
 SHA512:
-  metadata.gz: 85daa8177667c232eae29f3ad9a9f021a5d679898679967a5d435d4b3e3b7eb9bf0a6e84cd5441b43d823005a9dc0c295adfa3b9ca9387e1593ff01f4dc950d2
-  data.tar.gz: 2ce7411e57e5427e9fbcd211b37a60acc3669d38a2405364e51aeb27f5ff2d43c027df5e55291e8be39f81ad4543045c318a5d20422c0444780d912da9595c1d
+  metadata.gz: 11b75a2a68c5ec5f80049378a6a23c3b25a7f9368e7063febc5d88107e80dcc165498038e55f8d4b651fcbfd0e30489918be751f7a647f37a535cd8dd40cc2d6
+  data.tar.gz: 65edc1aeaf200ed7ef0774801a690806f2256a60c43aa838ac8717e3f9e8466292cf22a339dac975ee88ae32efea541991c761dec6adc5be88bbbee5ae352a83

data/.ruby-version

@@ -1 +1 @@
-ruby-2.1.5
+ruby-2.2.2

data/.travis.yml

@@ -6,4 +6,5 @@ rvm:
   - 1.9.3
   - 2.0.0
   - 2.1.5
+  - 2.2.2
   - ruby-head

data/Gemfile

@@ -9,7 +9,6 @@ group :development, :test do
   gem 'pry'
   gem 'sqlite3'
   gem 'mongo'
-  gem 'bson_ext'
   gem 'coveralls', require: false
 end
 

data/README.md

@@ -70,13 +70,18 @@ Postgresql database having **composite primary key**
 
 ## Changelog
 
+#### 0.7.2 (Sep 26, 2015)
+1. Upgraded MongoDB to latest gem version 2.1.0 and tested with MongoDB 3.x version.
+2. Upgraded gems to latest version 
+3. Adding limit functionality - Merge pull request #27 from yanismydj/master       
+
 #### 0.7.1 (Jun 13, 2015)
 1. Fixed issues with empty array data for MongoDB
 2. Added feature to skip and continue records during anaonymisation, this is useful to apply different strategies for different types of records.
 
 
 #### 0.7.0 (Mar 9, 2015)
-1. Removed downcase from field name since it was causing issues with upper case field names. So now for databsae where case matters field name case should be maintained. 
+1. Removed downcase from field name since it was causing issues with upper case field names. So now for databsae where case matters field name case should be maintained.
 2. Upgraded gems to latest version
 
 
@@ -204,8 +209,9 @@ Read more about [blacklist and whitelist here](http://sunitspace.blogspot.in/201
 2. Change [default field strategies](#default-field-strategies) to avoid using same strategy again and again in your DSL.
 3. To run anonymization in parallel at Table level, provided no FK constraint on tables use DataAnon::Parallel::Table strategy
 4. For large table to load them in batches from table set 'batch_size' and it will use RoR's batch mode processing. Checkout [example](https://github.com/sunitparekh/data-anonymization/blob/master/examples/whitelist_dsl.rb) on how to use batch processing.
-5. Make sure to give proper case for fields and table names. 
-6. Use skip and continue to apply different strategies for records. 
+5. Make sure to give proper case for fields and table names.
+6. Use skip and continue to apply different strategies for records.
+7. Use 'limit' to limit the number of rows that will be imported in whitelist
 
 ## DSL Generation
 
@@ -268,7 +274,7 @@ The options available are :
 2. database(-d) : The name of the database to generate the whitelist script for
 3. username(-u) : Username for DB authentication
 4. password(-w) : Password for DB authentication
-5. port(-p)     : The port the database service is running on. 
+5. port(-p)     : The port the database service is running on.
 6. whitelist patterns(-r): A regex expression which can be used to match records in the database to list as whitelisted fields in the generated script.
 
 The host and database options are mandatory. The others are optional.
@@ -282,7 +288,7 @@ datanon generate_mongo_dsl -h 123.456.7.8 -d production_db
 
 ```
 
-The **mongo** gem is required in order to install the mongo db drivers. The script generates a file named **mongodb_whitelist_generated.rb** in the same location as the project. 
+The **mongo** gem is required in order to install the mongo db drivers. The script generates a file named **mongodb_whitelist_generated.rb** in the same location as the project.
 
 
 
@@ -575,7 +581,7 @@ DataAnon::Utils::Logging.logger.level = Logger::INFO
 
 ## Skip and Continue records
 
-*Skip* is used to skip records during anonymization when condition returns true. This records are ignored, 
+*Skip* is used to skip records during anonymization when condition returns true. This records are ignored,
 in blacklist it remains as it is in database and in case of whitelist this records will not be copied to destination database.
 
 ```ruby
@@ -587,11 +593,11 @@ table 'customers' do
   anonymize 'terms_n_condition', 'age'
 end
 ```
-  
-  
-*Continue* is exactly opposite of Skip and it continue with anonymization only if given condition returns true. 
+
+
+*Continue* is exactly opposite of Skip and it continue with anonymization only if given condition returns true.
 In case of blacklist records are anonymized for matching conditions and for whitelist records are anonymized and copied
-to new database for matching conditions. 
+to new database for matching conditions.
 
 ```ruby
 table 'customers' do
@@ -623,5 +629,3 @@ end
 - [Dan Abel](http://www.linkedin.com/pub/dan-abel/0/61b/9b0) for introducing me to Blacklist and Whitelist approach for data anonymization.
 - [Chirga Doshi](https://twitter.com/chiragsdoshi) for encouraging me to get this done.
 - [Aditya Karle](https://twitter.com/adityakarle) for the Logo. (Coming Soon...)
-
-

data/examples/mongodb_blacklist_dsl.rb

@@ -1,11 +1,13 @@
 require 'data-anonymization'
-
 require 'mongo'
-Mongo::Connection.from_uri("mongodb://localhost/test").drop_database('test')
-system "mongoimport -d test --drop -c users --jsonArray ./sample-data/mongo/users.json"
-system "mongoimport -d test --drop -c plans --jsonArray ./sample-data/mongo/plans.json"
 
 DataAnon::Utils::Logging.logger.level = Logger::INFO
+Mongo::Logger.logger.level = Logger::WARN
+
+Mongo::Client.new("mongodb://localhost/test").database.drop
+system "mongoimport --host=127.0.0.1 -d test --drop -c users --jsonArray ./sample-data/mongo/users.json"
+system "mongoimport --host=127.0.0.1 -d test --drop -c plans --jsonArray ./sample-data/mongo/plans.json"
+
 
 database 'test' do
   strategy DataAnon::Strategy::MongoDB::Blacklist
@@ -21,7 +23,7 @@ database 'test' do
   end
 
   collection 'plans' do
-    anonymize('plan_aliases').using FieldStrategy::AnonymizeArray.new(FieldStrategy::SelectFromList.new(["Free","Team","Business","Paid"]))
+    anonymize('plan_aliases').using FieldStrategy::AnonymizeArray.new(FieldStrategy::SelectFromList.new(%w(Free Team Business Paid)))
     anonymize 'public_sharing','photo_sharing'
 
     document 'features' do

data/examples/mongodb_whitelist_dsl.rb

@@ -1,12 +1,14 @@
 require 'data-anonymization'
-
 require 'mongo'
-Mongo::Connection.from_uri("mongodb://localhost/test").drop_database('test')
-Mongo::Connection.from_uri("mongodb://localhost/dest").drop_database('dest')
-system "mongoimport -d test --drop -c users --jsonArray ./sample-data/mongo/users.json"
-system "mongoimport -d test --drop -c plans --jsonArray ./sample-data/mongo/plans.json"
 
 DataAnon::Utils::Logging.logger.level = Logger::INFO
+Mongo::Logger.logger.level = Logger::WARN
+
+
+Mongo::Client.new("mongodb://localhost/test").database.drop
+Mongo::Client.new("mongodb://localhost/dest").database.drop
+system "mongoimport --host=127.0.0.1 -d test --drop -c users --jsonArray ./sample-data/mongo/users.json"
+system "mongoimport --host=127.0.0.1 -d test --drop -c plans --jsonArray ./sample-data/mongo/plans.json"
 
 database 'test' do
   strategy DataAnon::Strategy::MongoDB::Whitelist
@@ -26,7 +28,7 @@ database 'test' do
 
   collection 'plans' do
     whitelist '_id', 'name','term', 'created_at'
-    anonymize('plan_aliases').using FieldStrategy::AnonymizeArray.new(FieldStrategy::SelectFromList.new(["Free","Team","Business","Paid"]))
+    anonymize('plan_aliases').using FieldStrategy::AnonymizeArray.new(FieldStrategy::SelectFromList.new(%w(Free Team Business Paid)))
     anonymize 'public_sharing','photo_sharing'
 
     collection 'features' do

data/examples/whitelist_dsl.rb

@@ -29,6 +29,7 @@ database 'Chinook' do
   table 'Customer' do
     primary_key 'CustomerId'
     batch_size 5  # batch_size works only if the primary_key is defined for the table
+    limit 10 # will only take last 10 records
 
     whitelist 'CustomerId', 'SupportRepId', 'Company'
     anonymize('Phone').using FieldStrategy::RandomPhoneNumber.new
@@ -64,4 +65,3 @@ database 'Chinook' do
 
 
 end
-

data/lib/strategy/base.rb

@@ -33,6 +33,10 @@ module DataAnon
         @batch_size = size
       end
 
+      def limit limit
+        @limit = limit
+      end
+
       def whitelist *fields
         fields.each { |f| @fields[f] = DataAnon::Strategy::Field::Whitelist.new }
       end
@@ -98,7 +102,8 @@ module DataAnon
 
       def process_table progress
         index = 0
-        source_table.all.each do |record|
+
+        source_table_limited.each do |record|
           index += 1
           begin
             process_record_if index, record
@@ -112,7 +117,8 @@ module DataAnon
       def process_table_in_batches progress
         logger.info "Processing table #{@name} records in batch size of #{@batch_size}"
         index = 0
-        source_table.find_each(:batch_size => @batch_size) do |record|
+
+        source_table_limited.find_each(:batch_size => @batch_size) do |record|
           index += 1
           begin
             process_record_if index, record
@@ -123,6 +129,16 @@ module DataAnon
         end
       end
 
+      def source_table_limited
+        @source_table_limited ||= begin
+          if @limit.present?
+            source_table.all.limit(@limit).order(created_at: :desc)
+          else
+            source_table.all
+          end
+        end
+      end
+
       def process_record_if index, record
         return if @skip_block && @skip_block.call(index, record)
         return if @continue_block && !@continue_block.call(index, record)
@@ -141,4 +157,4 @@ module DataAnon
 
     end
   end
-end
+end

data/lib/strategy/mongodb/blacklist.rb

@@ -8,7 +8,8 @@ module DataAnon
         end
 
         def process_record index, document
-          source_collection.save anonymize_document(document, index, @fields)
+          anonymized_document = anonymize_document(document, index, @fields)
+          source_collection.find({'_id' => anonymized_document['_id']}).update_one(anonymized_document)
         end
 
         def anonymize_document document, index, field_strategies = {}

data/lib/strategy/mongodb/whitelist.rb

@@ -23,7 +23,7 @@ module DataAnon
 
         def mongo_collection(database)
           options = database[:options] || {}
-          Mongo::Connection.from_uri(database[:mongodb_uri], options)[database[:database]][@name]
+          Mongo::Client.new(database[:mongodb_uri], options).database.collection(@name)
         end
 
         def dest_collection
@@ -39,7 +39,7 @@ module DataAnon
         alias :dest_table :dest_collection
 
         def process_record index, document
-          dest_collection.insert anonymize_document(document, index, @fields)
+          dest_collection.insert_one anonymize_document(document, index, @fields)
         end
 
         def anonymize_document document, index, field_strategies = {}

data/lib/version.rb

@@ -1,3 +1,3 @@
 module DataAnonymization
-  VERSION = '0.7.1'
+  VERSION = '0.7.2'
 end

data/spec/acceptance/mongodb_blacklist_spec.rb

@@ -4,7 +4,7 @@ require 'mongo'
 describe "End 2 End MongoDB Blacklist Acceptance Test" do
 
   before(:each) do
-    Mongo::Connection.from_uri("mongodb://localhost/test").drop_database('test')
+    Mongo::Client.new("mongodb://localhost/test").database().drop()
     users = [
         {
             "_id" => 1,
@@ -36,8 +36,8 @@ describe "End 2 End MongoDB Blacklist Acceptance Test" do
             "alternate_emails" => ["abc@test.com","abc2@test.com"]
         }
     ]
-    users_coll = Mongo::Connection.from_uri("mongodb://localhost/dest")['test']['users']
-    users.each { |p| users_coll.save p }
+    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
@@ -58,9 +58,9 @@ describe "End 2 End MongoDB Blacklist Acceptance Test" do
 
     end
 
-    users_coll = Mongo::Connection.from_uri("mongodb://localhost/test")['test']['users']
-    users_coll.count.should be 2
-    user = users_coll.find_one({'_id' => 1})
+    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"

data/spec/acceptance/mongodb_whitelist_spec.rb

@@ -4,8 +4,8 @@ require 'mongo'
 describe "End 2 End MongoDB Whitelist Acceptance Test" do
 
   before(:each) do
-    Mongo::Connection.from_uri("mongodb://localhost/test").drop_database('test')
-    Mongo::Connection.from_uri("mongodb://localhost/dest").drop_database('dest')
+    Mongo::Client.new("mongodb://localhost/test").database.drop
+    Mongo::Client.new("mongodb://localhost/dest").database.drop
     plans = [
         {
             "_id" => 1,
@@ -50,20 +50,20 @@ describe "End 2 End MongoDB Whitelist Acceptance Test" do
             "created_at" => Time.new(2012, 8, 11, 13, 1, 0)
         }
     ]
-    plans_coll = Mongo::Connection.from_uri("mongodb://localhost/dest")['test']['plans']
-    plans.each { |p| plans_coll.save p }
+    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
 
-    database 'test' 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'
 
       collection 'plans' do
         whitelist '_id', 'name', 'term', 'created_at'
-        anonymize('plan_aliases').using FieldStrategy::SelectFromList.new(["Free", "Team", "Business", "Paid"])
+        anonymize('plan_aliases').using FieldStrategy::SelectFromList.new(%w(Free Team Business Paid))
         anonymize 'public_sharing', 'photo_sharing'
 
         collection 'features' do
@@ -78,9 +78,9 @@ describe "End 2 End MongoDB Whitelist Acceptance Test" do
 
     end
 
-    plans_coll = Mongo::Connection.from_uri("mongodb://localhost/dest")['dest']['plans']
-    plans_coll.count.should be 2
-    plan = plans_coll.find_one({ '_id' => 1})
+    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"
@@ -99,7 +99,7 @@ describe "End 2 End MongoDB Whitelist Acceptance Test" do
     [true,false].should include(feature1['users']['additional'])
 
 
-    plan = plans_coll.find_one({ '_id' => 2})
+    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])

data/spec/acceptance/rdbms_blacklist_spec.rb

@@ -6,7 +6,7 @@ describe 'End 2 End RDBMS Blacklist Acceptance Test using SQLite database' do
   before(:each) do
     CustomerSample.clean
     CustomerSample.create_schema connection_spec
-    CustomerSample.insert_record connection_spec, CustomerSample::SAMPLE_DATA
+    CustomerSample.insert_record connection_spec, CustomerSample::SAMPLE_DATA[0]
   end
 
   it 'should anonymize customer table record ' do
@@ -24,7 +24,7 @@ describe 'End 2 End RDBMS Blacklist Acceptance Test using SQLite database' do
 
     DataAnon::Utils::SourceDatabase.establish_connection connection_spec
     source = DataAnon::Utils::SourceTable.create 'customers', ['cust_id']
-    new_rec = source.find(CustomerSample::SAMPLE_DATA[:cust_id])
+    new_rec = source.find(CustomerSample::SAMPLE_DATA[0][:cust_id])
     new_rec['email'].should == 'test+1@gmail.com'
 
   end
@@ -45,7 +45,7 @@ describe 'End 2 End RDBMS Blacklist Acceptance Test using SQLite database' do
 
     DataAnon::Utils::SourceDatabase.establish_connection connection_spec
     source = DataAnon::Utils::SourceTable.create 'customers', ['cust_id']
-    new_rec = source.find(CustomerSample::SAMPLE_DATA[:cust_id])
+    new_rec = source.find(CustomerSample::SAMPLE_DATA[0][:cust_id])
     new_rec['email'].should_not == 'test+1@gmail.com'
 
   end
@@ -66,10 +66,10 @@ describe 'End 2 End RDBMS Blacklist Acceptance Test using SQLite database' do
 
     DataAnon::Utils::SourceDatabase.establish_connection connection_spec
     source = DataAnon::Utils::SourceTable.create 'customers', ['cust_id']
-    new_rec = source.find(CustomerSample::SAMPLE_DATA[:cust_id])
+    new_rec = source.find(CustomerSample::SAMPLE_DATA[0][:cust_id])
     new_rec['email'].should == 'test+1@gmail.com'
 
 
 
   end
-end
+end

data/spec/acceptance/rdbms_whitelist_spec.rb

@@ -8,7 +8,7 @@ describe 'End 2 End RDBMS Whitelist Acceptance Test using SQLite database' do
   before(:each) do
     CustomerSample.clean
     CustomerSample.create_schema source_connection_spec
-    CustomerSample.insert_record source_connection_spec, CustomerSample::SAMPLE_DATA
+    CustomerSample.insert_records source_connection_spec, CustomerSample::SAMPLE_DATA
 
     CustomerSample.create_schema dest_connection_spec
   end
@@ -35,7 +35,8 @@ 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[:cust_id]).first
+    dest_table.count.should == 2
+    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))
@@ -52,4 +53,24 @@ describe 'End 2 End RDBMS Whitelist Acceptance Test using SQLite database' do
     new_rec.updated_at.should == Time.new(2010,5,5)
   end
 
+  describe 'limiting' do
+    it 'returns only last record' do
+      database 'Customer' do
+        strategy DataAnon::Strategy::Whitelist
+        source_db source_connection_spec
+        destination_db dest_connection_spec
+
+        table 'customers' do
+          limit 1
+          whitelist 'cust_id', 'first_name', 'created_at','updated_at'
+        end
+      end
+
+      DataAnon::Utils::DestinationDatabase.establish_connection dest_connection_spec
+      dest_table = DataAnon::Utils::DestinationTable.create 'customers'
+      dest_table.count.should == 1
+      new_rec = dest_table.first
+      new_rec.first_name.should eq('Rohit')
+    end
+  end
 end

data/spec/acceptance/rdbms_whitelist_with_primary_key_spec.rb

@@ -8,7 +8,7 @@ describe "End 2 End RDBMS Whitelist Acceptance Test using SQLite database" do
   before(:each) do
     CustomerSample.clean
     CustomerSample.create_schema source_connection_spec
-    CustomerSample.insert_record source_connection_spec, CustomerSample::SAMPLE_DATA
+    CustomerSample.insert_record source_connection_spec, CustomerSample::SAMPLE_DATA[0]
 
     CustomerSample.create_schema dest_connection_spec
   end
@@ -37,7 +37,7 @@ 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[:cust_id]).first
+    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))
@@ -52,4 +52,4 @@ describe "End 2 End RDBMS Whitelist Acceptance Test using SQLite database" do
     new_rec.longitude.should be_between( -84.044636, -64.044636)
 
   end
-end
+end

data/spec/spec_helper.rb

@@ -11,6 +11,7 @@ ENV['show_progress'] = 'false'
 Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
 
 DataAnon::Utils::Logging.logger.level = Logger::WARN
+Mongo::Logger.logger.level = Logger::WARN
 
 RSpec.configure do |config|
   config.expect_with :rspec do |c|

data/spec/support/customer_sample.rb

@@ -20,7 +20,7 @@ class CustomerSample
         t.float :latitude
         t.float :longitude
 
-        t.timestamps null: true
+        t.timestamps null: false
       end
     end
   end
@@ -36,14 +36,26 @@ class CustomerSample
     CreateCustomer.migrate :up
   end
 
-  SAMPLE_DATA = {:cust_id => 100, :first_name => "Sunit", :last_name => "Parekh",
-                 :birth_date => Date.new(1977,7,8), :address => "F 501 Shanti Nagar",
-                 :state => "Maharastra", :zipcode => "411048", :phone => "9923700662",
-                 :email => "parekh.sunit@gmail.com", :terms_n_condition => true,
-                 :age => 34, :longitude => -74.044636, :latitude => +40.689060,
-                 :created_at => Time.new(2010,10,10), :updated_at => Time.new(2010,5,5)}
+  SAMPLE_DATA = [
+  {
+    :cust_id => 100, :first_name => "Sunit", :last_name => "Parekh",
+    :birth_date => Date.new(1977,7,8), :address => "F 501 Shanti Nagar",
+    :state => "Maharastra", :zipcode => "411048", :phone => "9923700662",
+    :email => "parekh.sunit@gmail.com", :terms_n_condition => true,
+    :age => 34, :longitude => -74.044636, :latitude => +40.689060,
+    :created_at => Time.new(2010,10,10), :updated_at => Time.new(2010,5,5)
+  },
+  {
+    :cust_id => 101, :first_name => "Rohit", :last_name => "Parekh",
+    :birth_date => Date.new(1977,7,8), :address => "F 501 Shanti Nagar",
+    :state => "Maharastra", :zipcode => "411048", :phone => "9923700662",
+    :email => "parekh.sunit@gmail.com", :terms_n_condition => true,
+    :age => 34, :longitude => -74.044636, :latitude => +40.689060,
+    :created_at => Time.now, :updated_at => Time.now
+  }
+  ]
 
-  def self.insert_record connection_spec, data_hash = SAMPLE_DATA
+  def self.insert_record connection_spec, data_hash = SAMPLE_DATA[0]
     DataAnon::Utils::TempDatabase.establish_connection connection_spec
     source = DataAnon::Utils::BaseTable.create_table DataAnon::Utils::TempDatabase, 'customers', 'cust_id'
     cust = source.new data_hash
@@ -51,4 +63,13 @@ class CustomerSample
     cust.save!
   end
 
-end
+  def self.insert_records connection_spec, data_hash = SAMPLE_DATA
+    DataAnon::Utils::TempDatabase.establish_connection connection_spec
+    source = DataAnon::Utils::BaseTable.create_table DataAnon::Utils::TempDatabase, 'customers', 'cust_id'
+    data_hash.each do |data_row|
+      cust = source.new data_row
+      cust.cust_id = data_row[:cust_id]
+      cust.save!
+    end
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: data-anonymization
 version: !ruby/object:Gem::Version
-  version: 0.7.1
+  version: 0.7.2
 platform: ruby
 authors:
 - Sunit Parekh
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-06-13 00:00:00.000000000 Z
+date: 2015-10-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activerecord
@@ -311,7 +311,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.3
+rubygems_version: 2.4.8
 signing_key: 
 specification_version: 4
 summary: Tool to create anonymized production data dump to use for PREF and other