data-anonymization 0.1.2 → 0.2.0

data/spec/acceptance/rdbms_blacklist_spec.rb

@@ -17,12 +17,12 @@ describe "End 2 End RDBMS Blacklist Acceptance Test using SQLite database" do
 
       table 'customers' do
         primary_key 'cust_id'
-        anonymize('email').using DataAnon::Strategy::Field::StringTemplate.new('test+#{row_number}@gmail.com')
+        anonymize('email').using FieldStrategy::StringTemplate.new('test+#{row_number}@gmail.com')
       end
     end
 
     DataAnon::Utils::SourceDatabase.establish_connection connection_spec
-    source = DataAnon::Utils::SourceTable.create 'customers', 'cust_id'
+    source = DataAnon::Utils::SourceTable.create 'customers', ['cust_id']
     new_rec = source.find(CustomerSample::SAMPLE_DATA[:cust_id])
     new_rec['email'].should == 'test+1@gmail.com'
 

data/spec/acceptance/rdbms_whitelist_spec.rb

@@ -15,8 +15,6 @@ describe "End 2 End RDBMS Whitelist Acceptance Test using SQLite database" do
 
   it "should anonymize customer table record " do
 
-    DF = DataAnon::Strategy::Field
-
     database "Customer" do
       strategy DataAnon::Strategy::Whitelist
       source_db source_connection_spec
@@ -25,16 +23,16 @@ describe "End 2 End RDBMS Whitelist Acceptance Test using SQLite database" do
       table 'customers' do
         primary_key 'cust_id'
         whitelist 'cust_id', 'address', 'zipcode'
-        anonymize('first_name').using DF::RandomFirstName.new
-        anonymize('last_name').using DF::RandomLastName.new
-        anonymize('state').using DF::RandomSelection.new(['Gujrat','Karnataka'])
-        anonymize('phone').using DF::RandomPhoneNumber.new
-        anonymize('email').using DF::StringTemplate.new('test+#{row_number}@gmail.com')
+        anonymize('first_name').using FieldStrategy::RandomFirstName.new
+        anonymize('last_name').using FieldStrategy::RandomLastName.new
+        anonymize('state').using FieldStrategy::SelectFromList.new(['Gujrat','Karnataka'])
+        anonymize('phone').using FieldStrategy::RandomPhoneNumber.new
+        anonymize('email').using FieldStrategy::StringTemplate.new('test+#{row_number}@gmail.com')
       end
     end
 
     DataAnon::Utils::DestinationDatabase.establish_connection dest_connection_spec
-    dest_table = DataAnon::Utils::DestinationTable.create 'customers', 'cust_id'
+    dest_table = DataAnon::Utils::DestinationTable.create 'customers', ['cust_id']
     new_rec = dest_table.find(CustomerSample::SAMPLE_DATA[:cust_id])
     new_rec.first_name.should_not be("Sunit")
     new_rec.last_name.should_not be("Parekh")

data/spec/resource/sample.geojson

@@ -0,0 +1 @@
+{"geometry": {"type": "Point", "coordinates": [-134.412039, 58.30057]}, "type": "Feature", "id": "SG_5xejzYOfDRcyoVHXqvO2hB_58.300570_-134.412039@1293731153", "properties": {"province": "AK", "city": "Juneau", "name": "Purchasing Dept", "tags": ["state"], "country": "US", "classifiers": [{"category": "Government", "type": "Public Place", "subcategory": "Office"}], "phone": "+1 907 465 2250", "href": "http://api.simplegeo.com/1.0/features/SG_5xejzYOfDRcyoVHXqvO2hB_58.300570_-134.412039@1293731153.json", "address": "333 Willoughby Ave", "owner": "simplegeo", "postcode": "99801"}}

data/spec/spec_helper.rb

@@ -2,11 +2,12 @@ require 'rspec'
 require "pry"
 require 'data-anonymization'
 
+
+ENV['show_progress'] = 'false'
+
 Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
 
 DataAnon::Utils::Logging.logger.level = Logger::INFO
-DataAnon::Utils::Logging.progress_logger.level = Logger::WARN
-
 
 RSpec.configure do |config|
   config.expect_with :rspec

data/spec/strategy/field/contact/random_address_spec.rb

@@ -0,0 +1,12 @@
+require "spec_helper"
+
+describe DataAnon::Strategy::Field::RandomAddress do
+
+  RandomAddress = DataAnon::Strategy::Field::RandomAddress
+  let(:field) {DataAnon::Core::Field.new('address','1 Infinite Loop',1,nil)}
+
+  describe 'anonymized address should be different from original address' do
+    let(:anonymized_address) {RandomAddress.region_US.anonymize(field)}
+    it {anonymized_address.should_not eq("1 Infinite Loop")}
+  end
+end

data/spec/strategy/field/contact/random_city_spec.rb

@@ -0,0 +1,14 @@
+require "spec_helper"
+
+describe DataAnon::Strategy::Field::RandomCity do
+
+  RandomCity = DataAnon::Strategy::Field::RandomCity
+  let(:field) { DataAnon::Core::Field.new('city', 'Atlanta', 1, nil) }
+
+  describe 'anonymized city should be different from original city' do
+    let(:anonymized_city) { RandomCity.region_US.anonymize(field) }
+
+    it { anonymized_city.should_not be_nil }
+    it { anonymized_city.should_not eq("Atlanta") }
+  end
+end

data/spec/strategy/field/contact/random_phone_number_spec.rb

@@ -0,0 +1,16 @@
+require "spec_helper"
+
+describe FieldStrategy::RandomPhoneNumber do
+
+  RandomPhoneNumber = FieldStrategy::RandomPhoneNumber
+  let(:field) { DataAnon::Core::Field.new('phone_number', "+0 (123) 456-7890", 1, nil) }
+
+  describe 'anonymized phone number preserving the format' do
+    let(:anonymized_number) { RandomPhoneNumber.new().anonymize(field) }
+
+    it { anonymized_number.should_not equal field.value }
+    it { anonymized_number.should match /\+\d\ \(\d{3}\)\ \d{3}-\d{4}$/ }
+  end
+
+
+end

data/spec/strategy/field/contact/random_province_spec.rb

@@ -0,0 +1,14 @@
+require "spec_helper"
+
+describe DataAnon::Strategy::Field::RandomProvince do
+
+  RandomProvince = DataAnon::Strategy::Field::RandomProvince
+  let(:field) { DataAnon::Core::Field.new('province', 'Atlanta', 1, nil) }
+
+  describe 'anonymized province should be different from original province' do
+    let(:anonymized_province) { RandomProvince.region_US.anonymize(field) }
+
+    it { anonymized_province.should_not be_nil }
+    it { anonymized_province.should_not eq("Atlanta") }
+  end
+end

data/spec/strategy/field/contact/random_zipcode_spec.rb

@@ -0,0 +1,14 @@
+require "spec_helper"
+
+describe DataAnon::Strategy::Field::RandomZipcode do
+
+  RandomZipcode = DataAnon::Strategy::Field::RandomZipcode
+  let(:field) { DataAnon::Core::Field.new('zipcode', '12345', 1, nil) }
+
+  describe 'anonymized zipcode should be different from original zipcode' do
+    let(:anonymized_zipcode) { RandomZipcode.region_US.anonymize(field) }
+
+    it { anonymized_zipcode.should_not be_nil }
+    it { anonymized_zipcode.should_not eq("12345") }
+  end
+end

data/spec/strategy/field/datetime/anonymize_date_spec.rb

@@ -0,0 +1,27 @@
+require "spec_helper"
+
+describe FieldStrategy::AnonymizeDate do
+
+  AnonymizeDate = FieldStrategy::AnonymizeDate
+  let(:field) { DataAnon::Core::Field.new('date', Date.new(2011,7,5), 1, nil) }
+
+  describe 'providing true only for month should randomize only the month field' do
+
+    let(:anonymized_time) { AnonymizeDate.only_month.anonymize(field) }
+
+    it { anonymized_time.should be_kind_of Date}
+    it { anonymized_time.year.should be 2011 }
+    it { anonymized_time.month.should be_between(1,12)}
+    it { anonymized_time.day.should be 5 }
+  end
+
+  describe 'providing true only for date should randomize only the date field' do
+
+    let(:anonymized_time) { AnonymizeDate.only_day.anonymize(field) }
+
+    it { anonymized_time.year.should be 2011 }
+    it { anonymized_time.month.should be 7}
+    it { anonymized_time.day.should be_between(1,31) }
+  end
+
+end

data/spec/strategy/field/datetime/anonymize_datetime_spec.rb

@@ -0,0 +1,57 @@
+require "spec_helper"
+
+describe FieldStrategy::AnonymizeDateTime do
+
+  AnonymizeDateTime = FieldStrategy::AnonymizeDateTime
+  let(:field) { DataAnon::Core::Field.new('date', DateTime.new(2000,1,1,12,12,12), 1, nil) }
+
+  describe 'providing true only for month should randomize only the month field' do
+
+    let(:anonymized_time) { AnonymizeDateTime.only_month.anonymize(field) }
+
+    it { anonymized_time.should be_kind_of DateTime}
+    it { anonymized_time.year.should be 2000 }
+    it { anonymized_time.month.should be_between(1,12)}
+    it { anonymized_time.day.should be 1 }
+    it { anonymized_time.hour.should be 12}
+    it { anonymized_time.min.should be 12}
+    it { anonymized_time.sec.should be 12}
+  end
+
+  describe 'providing true only for date should randomize only the date field' do
+
+    let(:anonymized_time) { AnonymizeDateTime.only_day.anonymize(field) }
+
+    it { anonymized_time.year.should be 2000 }
+    it { anonymized_time.month.should be 1}
+    it { anonymized_time.day.should be_between(1,31) }
+    it { anonymized_time.hour.should be 12}
+    it { anonymized_time.min.should be 12}
+    it { anonymized_time.sec.should be 12}
+  end
+
+  describe 'providing true only for hour should randomize only the hour field' do
+
+    let(:anonymized_time) { AnonymizeDateTime.only_hour.anonymize(field) }
+
+    it { anonymized_time.year.should be 2000 }
+    it { anonymized_time.month.should be 1}
+    it { anonymized_time.day.should be 1 }
+    it { anonymized_time.hour.should be_between(1,24)}
+    it { anonymized_time.min.should be 12}
+    it { anonymized_time.sec.should be 12}
+  end
+
+  describe 'providing true only for minute should randomize only the minute field' do
+
+    let(:anonymized_time) { AnonymizeDateTime.only_minute.anonymize(field) }
+
+    it { anonymized_time.year.should be 2000 }
+    it { anonymized_time.month.should be 1}
+    it { anonymized_time.day.should be 1 }
+    it { anonymized_time.hour.should be 12}
+    it { anonymized_time.min.should be_between(1,60)}
+    it { anonymized_time.sec.should be 12}
+  end
+
+end

data/spec/strategy/field/datetime/anonymize_time_spec.rb

@@ -0,0 +1,57 @@
+require "spec_helper"
+
+describe FieldStrategy::AnonymizeTime do
+
+  AnonymizeTime = FieldStrategy::AnonymizeTime
+  let(:field) { DataAnon::Core::Field.new('date', Time.new(2000,1,1,12,12,12), 1, nil) }
+
+  describe 'providing true only for month should randomize only the month field' do
+
+    let(:anonymized_time) { AnonymizeTime.only_month.anonymize(field) }
+
+    it { anonymized_time.should be_kind_of Time}
+    it { anonymized_time.year.should be 2000 }
+    it { anonymized_time.month.should be_between(1,12)}
+    it { anonymized_time.day.should be 1 }
+    it { anonymized_time.hour.should be 12}
+    it { anonymized_time.min.should be 12}
+    it { anonymized_time.sec.should be 12}
+  end
+
+  describe 'providing true only for date should randomize only the date field' do
+
+    let(:anonymized_time) { AnonymizeTime.only_day.anonymize(field) }
+
+    it { anonymized_time.year.should be 2000 }
+    it { anonymized_time.month.should be 1}
+    it { anonymized_time.day.should be_between(1,31) }
+    it { anonymized_time.hour.should be 12}
+    it { anonymized_time.min.should be 12}
+    it { anonymized_time.sec.should be 12}
+  end
+
+  describe 'providing true only for hour should randomize only the hour field' do
+
+    let(:anonymized_time) { AnonymizeTime.only_hour.anonymize(field) }
+
+    it { anonymized_time.year.should be 2000 }
+    it { anonymized_time.month.should be 1}
+    it { anonymized_time.day.should be 1 }
+    it { anonymized_time.hour.should be_between(1,24)}
+    it { anonymized_time.min.should be 12}
+    it { anonymized_time.sec.should be 12}
+  end
+
+  describe 'providing true only for minute should randomize only the minute field' do
+
+    let(:anonymized_time) { AnonymizeTime.only_minute.anonymize(field) }
+
+    it { anonymized_time.year.should be 2000 }
+    it { anonymized_time.month.should be 1}
+    it { anonymized_time.day.should be 1 }
+    it { anonymized_time.hour.should be 12}
+    it { anonymized_time.min.should be_between(1,60)}
+    it { anonymized_time.sec.should be 12}
+  end
+
+end

data/spec/strategy/field/datetime/date_delta_spec.rb

@@ -0,0 +1,36 @@
+require "spec_helper"
+
+describe FieldStrategy::DateDelta do
+
+  DateDelta = FieldStrategy::DateDelta
+  let(:field) { DataAnon::Core::Field.new('date', Date.new(2011,4,7), 1, nil) }
+
+  describe 'date should not remain the same' do
+
+    let(:anonymized_value) { DateDelta.new().anonymize(field) }
+    let(:date_difference) {anonymized_value - field.value}
+
+    it { anonymized_value.should be_kind_of Date}
+    it { anonymized_value.should_not == Date.new(2011,4,7) }
+    it { date_difference.should be_between(-5.days, 5.days) }
+  end
+
+  describe 'date should not change when provided with 0 delta for both date and time' do
+
+    let(:anonymized_date) { DateDelta.new(0).anonymize(field) }
+
+    it {anonymized_date.should == Date.new(2011,4,7) }
+
+  end
+
+  describe 'date should be anonymized within provided delta' do
+
+    let(:anonymized_value) { DateDelta.new(5).anonymize(field) }
+    let(:date_difference) {anonymized_value - field.value}
+
+    it { date_difference.should be_between(-5.days, 5.days) }
+
+  end
+
+
+end

data/spec/strategy/field/{date_time_delta_spec.rb → datetime/date_time_delta_spec.rb}

@@ -1,8 +1,8 @@
 require "spec_helper"
 
-describe DataAnon::Strategy::Field::DateTimeDelta do
+describe FieldStrategy::DateTimeDelta do
 
-  DateTimeDelta = DataAnon::Strategy::Field::DateTimeDelta
+  DateTimeDelta = FieldStrategy::DateTimeDelta
   let(:field) { DataAnon::Core::Field.new('date', DateTime.new(2000,1,1), 1, nil) }
 
   describe 'datetime should not remain the same' do
@@ -10,6 +10,7 @@ describe DataAnon::Strategy::Field::DateTimeDelta do
     let(:anonymized_value) { DateTimeDelta.new().anonymize(field) }
     let(:date_difference) {anonymized_value.to_i - field.value.to_i}
 
+    it { anonymized_value.should be_kind_of DateTime}
     it {date_difference.should_not be 0 }
   end
 

data/spec/strategy/field/datetime/time_delta_spec.rb

@@ -0,0 +1,44 @@
+require "spec_helper"
+
+describe FieldStrategy::TimeDelta do
+
+  TimeDelta = FieldStrategy::TimeDelta
+  let(:field) { DataAnon::Core::Field.new('date', Time.new(2012,10,10,13,20,10), 1, nil) }
+
+  describe 'time should not remain the same' do
+
+    let(:anonymized_value) { TimeDelta.new().anonymize(field) }
+    let(:date_difference) {anonymized_value.to_i - field.value.to_i}
+
+    it { anonymized_value.should be_kind_of Time}
+    it {date_difference.should_not be 0 }
+  end
+
+  describe 'time should not change when provided with 0 delta for both date and time' do
+
+    let(:anonymized_value) { TimeDelta.new(0,0).anonymize(field) }
+    let(:date_difference) {anonymized_value.to_i - field.value.to_i}
+
+    it {date_difference.should be 0 }
+
+  end
+
+  describe 'date should be anonymized within provided delta' do
+
+    let(:anonymized_value) { TimeDelta.new(5,0).anonymize(field) }
+    let(:date_difference) {anonymized_value.to_i - field.value.to_i}
+
+    it { date_difference.should be_between(-5.days, 5.days) }
+
+  end
+
+  describe 'time should be anonymized within provided delta' do
+
+    let(:anonymized_value) { TimeDelta.new(0,10).anonymize(field) }
+    let(:date_difference) {anonymized_value.to_i - field.value.to_i}
+
+    it { date_difference.should be_between(-10.minutes, 10.minutes)}
+  end
+
+
+end

data/spec/strategy/field/default_anon_spec.rb

@@ -0,0 +1,42 @@
+require "spec_helper"
+
+describe FieldStrategy::DefaultAnon do
+
+  DefaultAnon = FieldStrategy::DefaultAnon
+
+  describe 'anonymized boolean true value' do
+    let(:field) {DataAnon::Core::Field.new('boolean_field',true,1,nil)}
+    let(:anonymized_value) {DefaultAnon.new.anonymize(field)}
+
+    it { [TrueClass,FalseClass].should include(anonymized_value.class)  }
+  end
+
+  describe 'anonymized boolean false value' do
+    let(:field) {DataAnon::Core::Field.new('boolean_field',false,1,nil)}
+    let(:anonymized_value) {DefaultAnon.new.anonymize(field)}
+
+    it { [TrueClass,FalseClass].should include(anonymized_value.class)  }
+  end
+
+  describe 'anonymized float value' do
+    let(:field) {DataAnon::Core::Field.new('float_field',2.0,1,nil)}
+    let(:anonymized_value) {DefaultAnon.new.anonymize(field)}
+
+    it { anonymized_value.should be_kind_of Float  }
+  end
+
+  describe 'anonymized int value' do
+    let(:field) {DataAnon::Core::Field.new('int_field',2,1,nil)}
+    let(:anonymized_value) {DefaultAnon.new.anonymize(field)}
+
+    it { anonymized_value.should be_kind_of Fixnum  }
+  end
+
+  describe 'anonymized string value' do
+    let(:field) {DataAnon::Core::Field.new('string_field','String',1,nil)}
+    let(:anonymized_value) {DefaultAnon.new.anonymize(field)}
+
+    it { anonymized_value.should be_kind_of String  }
+  end
+
+end

data/spec/strategy/field/email/gmail_template_spec.rb

@@ -0,0 +1,17 @@
+require "spec_helper"
+
+describe FieldStrategy::GmailTemplate do
+
+  GmailTemplate = FieldStrategy::GmailTemplate
+  let(:field) { DataAnon::Core::Field.new('email', 'user@company.com', 456, nil) }
+
+  describe 'generated email using default username' do
+    let(:anonymized_email) { GmailTemplate.new.anonymize(field) }
+    it { anonymized_email.should eq('someusername+456@gmail.com') }
+  end
+
+  describe 'generated email using given username' do
+    let(:anonymized_email) { GmailTemplate.new("fake").anonymize(field) }
+    it { anonymized_email.should eq('fake+456@gmail.com') }
+  end
+end