Independent study. Add db anonymization (expertiza#2744)

* Add db anonyimization

* Updated logic in scrub_database.rb
* Added Faker gem

* Remove Faker gem, fix .sh script

* Add name.yml

* Add comments

* Delete db_anonymization.sh

* Update scrub_database.rake

* Update scrub_database.rake

* Update scrub_database.rake

* Update scrub_database.rb

* Update name.yml

* Fix name generation

* Add anonymization environment

---------

Co-authored-by: Ali Qureshi <[email protected]>

config/environments/anonymization.rb

@@ -0,0 +1,58 @@
+Expertiza::Application.configure do
+    # Settings specified here will take precedence over those in config/environment.rb
+
+    # In the development environment your application's code is reloaded on
+    # every request.  This slows down response time but is perfect for development
+    # since you don't have to restart the webserver when you make code changes.
+    config.cache_classes = false
+    # config.serve_static_assets = false
+    # config.action_mailer.default_url_options = { :host => 'localhost:3000' }
+    host = '152.7.98.82:8080'
+    config.action_mailer.default_url_options = { host: '152.7.98.82:8080', protocol: 'http' }
+    # Do not eager load code on boot.
+    config.eager_load = false
+
+    # Show full error reports and disable caching.
+    config.consider_all_requests_local       = true
+    config.action_controller.perform_caching = false
+    # config.active_record.whitelist_attributes = false # need protected_attributes gem
+
+    # Print deprecation notices to the Rails logger.
+    config.active_support.deprecation = :log
+    # Print development logs
+    config.log_level = :error
+
+    config.log_tags = %i[remote_ip uuid]
+
+    config.log_formatter = proc do |s, ts, pg, msg|
+      if msg.is_a?(LoggerMessage)
+        "TST=[#{ts}] SVT=[#{s}] PNM=[#{pg}] OIP=[#{msg.oip}] RID=[#{msg.req_id}] CTR=[#{msg.generator}] UID=[#{msg.unity_id}] MSG=[#{filter(msg.message)}]\n"
+      else
+        "TST=[#{ts}] SVT=[#{s}] PNM=[#{pg}] OIP=[] RID=[] CTR=[] UID=[] MSG=[#{filter(msg)}]\n"
+      end
+    end
+
+    def filter(msg)
+      msg.tr("\n", ' ')
+    end
+
+    config.action_view.logger = nil
+
+    # Raise an error on page load if there are pending migrations
+    config.active_record.migration_error = :page_load
+
+    # Debug mode disables concatenation and preprocessing of assets.
+    # This option may cause significant delays in view rendering with a large
+    # number of complex assets.
+    config.assets.debug = true
+    config.react.variant = :development
+    config.active_record.logger = nil
+    # Line 63-69 are for 'bullet' gem initialization.
+    config.after_initialize do
+      Bullet.enable = true
+      Bullet.alert = false
+      Bullet.bullet_logger = false
+      Bullet.console = false
+      Bullet.rails_logger = false
+    end
+end

config/google_auth.yml

@@ -12,3 +12,7 @@ test:
 production: 
  client_key: <%= ENV['GOOGLE_KEY'] %>
  client_secret: <%= ENV['GOOGLE_SECRET'] %>
+
+anonymization: 
+ client_key: '1025716012590-2nlv84m8uo3pled9bide8442r2020gc3.apps.googleusercontent.com'
+ client_secret: 'kWjKq314ywRKAF5s5A0F8Wxh'

db/data_migrations/scrub_database.rb

@@ -1,17 +1,48 @@
+require 'yaml'
+
 class ScrubDatabase
   def self.run!
+    # Loop through each user
     User.find_each do |user|
-      user.name = "#{user.role.name.downcase.gsub(/[- ]/, '_')}#{user.id}"
-      user.fullname = "#{user.id}, #{user.role.name.downcase.gsub(/[- ]/, '_')}"
-      user.email = '[email protected]'
-      user.handle = 'handle'
-      user.password = 'password'
-      # user.password_confirmation = "password"
-      user.save(validate: false)
+      # Generate a new fake user record
+      loop do
+        fake_name = FakeNameGenerator.first_name
+        fake_lastname = FakeNameGenerator.last_name
+        num = rand(1..9)
+        role = user.role.name.downcase.gsub(/[- ]/, '_')
+        user.name = role == 'student' ? "#{fake_name}_#{fake_lastname[0..3]}#{num}" : "#{role}_#{fake_name}__#{fake_lastname[0..3]}"
+        user.fullname = role == 'student' ? "#{fake_lastname}, #{fake_name}" : "#{fake_name}, #{role}"
+        user.email = '[email protected]'
+        user.handle = 'handle'
+        user.password = 'password'
+        username = role == 'student' ? "#{fake_name}_#{fake_lastname[0..3]}#{num}" : "#{role}_#{fake_name}__#{fake_lastname[0..3]}"
+        # Checking if username already exists
+        if User.find_by(:name => username) == nil #no record exists of that username
+          # print "new user"
+          user.save(validate: false)
+          break
+        end
+        # if record exists, generate new fake record by going through the loop again
+      end
     end
+
     Participant.find_each do |participant|
       participant.handle = 'handle'
       participant.save(validate: false)
     end
   end
 end
+
+
+class FakeNameGenerator
+  NAMES = YAML.load_file("#{Rails.root}/config/name.yml")['name']
+
+  def self.first_name
+    gender = [:male_first_name, :female_first_name, :neutral_first_name].sample
+    NAMES["#{gender}"].sample
+  end
+
+  def self.last_name
+    NAMES["#{:last_name}"].sample
+  end
+end