remont 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 2ffe65eff0fe907d7834a94e028001396ad17937b313cb9197475b66c4938c33
+  data.tar.gz: 7247441b4f59709a8c877da6ae9a9679f27c02916ca553f0f7f9d9f2808c9805
+SHA512:
+  metadata.gz: 60ae2dc780851f4bef7436e65b2143cfd5b8454b2cd5f3dc512985f32ab061f59eed24ff769e34fc26adabe43a7346aaf411b824d8e9979153b7fac342792e05
+  data.tar.gz: 745d82eac997e1bda274f2e5fc20f3f6b10b69043efe0de83746804725fea5b7a5b5bf99c585d9f866ca88e6bd9d1c1a901855c6b7cc034f4ebf1846b56e9446

data/.github/workflows/ci.yml

@@ -0,0 +1,28 @@
+name: CI
+
+on:
+  push:
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Ruby
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: '2.7'
+        bundler-cache: true
+    - name: Run rubocop
+      run: bundle exec rubocop
+  test:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Ruby
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: '2.7'
+        bundler-cache: true
+    - name: Run specs
+      run: bundle exec rspec

data/.gitignore

@@ -0,0 +1,11 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status

data/.rbenv

@@ -0,0 +1 @@
+2.7.2

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.rubocop.yml

@@ -0,0 +1,13 @@
+inherit_gem:
+  rubocop-infinum: rubocop.yml
+
+require: rubocop-infinum
+
+AllCops:
+  TargetRubyVersion: 2.7
+
+RSpec/MultipleExpectations:
+  Max: 5
+
+Style/FrozenStringLiteralComment:
+  Enabled: false

data/.ruby-version

@@ -0,0 +1 @@
+2.7.2

data/.travis.yml

@@ -0,0 +1,7 @@
+---
+sudo: false
+language: ruby
+cache: bundler
+rvm:
+  - 2.6.3
+before_install: gem install bundler -v 1.17.2

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at team.rails@infinum.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,6 @@
+source 'https://rubygems.org'
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in obliviate.gemspec
+gemspec

data/README.md

@@ -0,0 +1,133 @@
+# Remont
+
+A DSL for describing and running the row-level processing of the records in the database (eg. anonymization)
+
+## Installation
+Add this line to your application's Gemfile:
+```ruby
+gem 'remont'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install remont
+
+## Application configuration
+Add `config/initializers/remont.rb`
+```ruby
+Remont.setup do |config|
+  config.process_timestamp_attribute = :processed_at
+  config.script_path = 'db/remont.rb'
+end
+```
+
+| Option                        | Default value    | Description                                |
+| ---                           | :---:            | ---                                        |
+| `process_timestamp_attribute` | `:processed_at`  | processing status attribute identifier     |
+| `script_path`                 | `'db/remont.rb'` | entry point for the schema processing task |
+
+On successful record processing, `process_timestamp_attribute` on the record will be set to the current processing time (`Time.now.getlocal`).
+
+## Usage
+In the following example, the intention is to simulate anonymization of the `users` and `orders` table.
+- configure the global options
+```ruby
+# config/initializers/remont.rb
+Remont.setup do |config|
+  config.process_timestamp_attribute = :anonyzmied_at
+  config.script_path = 'db/anonymize.rb'
+end
+```
+- define processing script
+```ruby
+# db/anonymize.rb
+schema model: User  do
+  attribute(:email) { 'user@example.com' }
+end
+
+schema model: Order do
+  attribute(:billing_address) { '23 Wall Street, NY' }
+end
+```
+- and run `bundle exec rake remont`
+
+Running the rake task would result in updating `email` (and `anonymized_at`) column for each row in the `users` table, and `billing_address` column for each row in the `orders` table.
+
+### Schema
+Defines database table hosting the rows to be processed. The initial dataset is defined through the `model` option in the `schema` method. `model` value must be a subclass of the `ActiveRecord::Base`.
+```ruby
+schema model: Order do
+end
+```
+### Controlling the scope
+Scope of the data that will be processed is controlled
+- with `scope` option in the `schema` method
+- by declaring custom `scope` within the `schema` block
+```ruby
+# skip admin records
+schema model: User, scope: { |scope| scope.where.not(role: :admin) } do
+end
+
+schema model: Order do
+  # process only active records
+  scope { |scope| scope.where(status: :active) }
+end
+```
+### Skipping the processed records
+In some cases, it's desirable to skip already processed records. You can opt-in to this behavior by declaring `without_processed` within the `schema` block. When declared, the processing dataset query will be extended with a condition that excludes already processed records (ie. `where(Remont.process_timestamp_attribute => nil)`)
+```ruby
+schema model: User do
+  without_processed
+  # ...
+end
+```
+### Callbacks
+Custom pre-processing or post-processing behavior can be declared using `before` and `after` callbacks.
+```ruby
+schema model: User do
+  before { |record| Rails.logger.info("Started processing: #{record.id}") }
+  after { |record| Rails.logger.info("Finished processing: #{record.id}") }
+end
+```
+### Attributes
+Attributes are processed using processors (an object which responds to the `call` method). The processor can be defined either as a block or with the `:using` option passed to the `attribute` method.
+```ruby
+require 'securerandom'
+
+class CachedNick
+  def initialize
+    @cache = Hash.new { |hash, nick| hash[nick] = SecureRandom.uuid }
+  end
+
+  def call(nick, _record)
+    @cache[nick]
+  end
+end
+
+schema model: User do
+  attribute(:email) { |email, record| "#{record.id}-#{email}" }
+  attribute(:nickname, using: CachedNick.new)
+end
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `bundle exec rspec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/infinum/remont. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Code of Conduct
+
+Everyone interacting in the Remont project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/infinum/remont/blob/master/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,6 @@
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+
+task default: :spec

data/bin/console

@@ -0,0 +1,7 @@
+#!/usr/bin/env ruby
+
+require 'bundler/setup'
+require 'remont'
+
+require 'pry'
+Pry.start

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/remont/attribute.rb

@@ -0,0 +1,26 @@
+module Remont
+  class Attribute
+    # @return [Symbol]
+    attr_reader :name
+
+    # @param [Symbol] name
+    # @param [Hash] opts
+    # @option [#call] :using
+    # @param [Proc] processor
+    def initialize(name, opts = {}, &processor)
+      @name = name
+      @processor = opts.fetch(:using, processor)
+    end
+
+    # @param [Object] value
+    # @param [ActiveRecord::Base] record
+    # @return [Object]
+    def process(value, record)
+      processor.call(value, record)
+    end
+
+    private
+
+    attr_reader :processor
+  end
+end

data/lib/remont/config.rb

@@ -0,0 +1,16 @@
+module Remont
+  class Config
+    DEFAULT_SCRIPT_PATH = 'db/remont.rb'.freeze
+
+    # @return [Symbol]
+    attr_accessor :process_timestamp_attribute
+
+    # @return [String]
+    attr_accessor :script_path
+
+    def initialize
+      @process_timestamp_attribute = :processed_at
+      @script_path = DEFAULT_SCRIPT_PATH
+    end
+  end
+end

data/lib/remont/railtie.rb

@@ -0,0 +1,8 @@
+module Remont
+  class Railtie < Rails::Railtie
+    rake_tasks do
+      path = File.expand_path(__dir__)
+      Dir.glob("#{path}/tasks/**/*.rake").each { |f| load f }
+    end
+  end
+end

data/lib/remont/record_processor.rb

@@ -0,0 +1,48 @@
+module Remont
+  class RecordProcessor
+    NOOP = proc {}
+
+    # @param [Array<Remont::Attribute>] attributes
+    # @param [Proc] before
+    # @param [Proc] after
+    def initialize(attributes, before, after)
+      @attributes = attributes
+      @before = before || NOOP
+      @after = after || NOOP
+    end
+
+    # @param [ActiveRecord::Base] record
+    # @return [ActiveRecord::Base] record
+    def process!(record)
+      before.call(record)
+      record.update_columns( # rubocop:disable Rails/SkipsModelValidations
+        processed_attributes(record)
+      )
+      after.call(record)
+
+      record
+    end
+
+    private
+
+    attr_reader :attributes
+    attr_reader :before
+    attr_reader :after
+
+    def processed_attributes(record)
+      attributes
+        .select { |attribute| record.send(attribute.name).present? }
+        .reduce(default_processed_attributes) do |memo, attribute|
+          memo.merge(attribute.name => attribute.process(record.send(attribute.name), record))
+        end
+    end
+
+    def default_processed_attributes
+      return {} unless Remont.config.process_timestamp_attribute
+
+      {
+        Remont.config.process_timestamp_attribute => Time.now.getlocal
+      }
+    end
+  end
+end

data/lib/remont/schema.rb

@@ -0,0 +1,87 @@
+module Remont
+  class Schema
+    DEFAULT_SCOPE = proc { |scope| scope }
+    WITHOUT_PROCESSED = proc { |scope| scope.where(Remont.config.process_timestamp_attribute => nil) }
+
+    # @param [Hash] opts
+    # @option [Class] :model
+    # @option [Proc] :scope
+    # @param [Proc] block
+    def initialize(opts = {}, &block)
+      @model = opts.fetch(:model)
+      @model_scope = opts.fetch(:scope, DEFAULT_SCOPE)
+      @without_processed_scope = DEFAULT_SCOPE
+      @before_cb = nil
+      @after_cb = nil
+      @attributes = []
+
+      instance_eval(&block)
+    end
+
+    # @return [Remont::Schema]
+    def without_processed
+      @without_processed_scope = WITHOUT_PROCESSED
+
+      self
+    end
+
+    # @param [Proc] scope
+    # @return [Remont::Schema]
+    def scope(&scope)
+      @model_scope = scope
+
+      self
+    end
+
+    # @param [Symbol] name
+    # @param [Hash] opts
+    # @option [#call] :using
+    # @param [Proc] processor
+    # @return [Remont::Schema]
+    def attribute(...)
+      @attributes << Attribute.new(...)
+
+      self
+    end
+
+    # @param [Proc] block
+    # @return [Remont::Schema]
+    def before(&block)
+      @before_cb = block
+
+      self
+    end
+
+    # @param [Proc] block
+    # @return [Remont::Schema]
+    def after(&block)
+      @after_cb = block
+
+      self
+    end
+
+    # @return [Any]
+    def process!
+      records_for_processing.find_each { |record| processor.process!(record) }
+    end
+
+    private
+
+    attr_reader :model
+    attr_reader :without_processed_scope
+    attr_reader :model_scope
+    attr_reader :attributes
+    attr_reader :before_cb
+    attr_reader :after_cb
+
+    def processor
+      @processor ||= RecordProcessor.new(attributes, before_cb, after_cb)
+    end
+
+    def records_for_processing
+      model_scope.call(
+        without_processed_scope.call(model.all)
+      )
+    end
+  end
+end

data/lib/remont/script.rb

@@ -0,0 +1,30 @@
+module Remont
+  class Script
+    # @path [String] path
+    def initialize(path)
+      @path = path
+      @schemas = []
+    end
+
+    # @return [Object]
+    def run!
+      instance_eval(File.read(path))
+
+      schemas.each(&:process!)
+    end
+
+    # @param [Hash] opts
+    # @option [Proc] :model
+    # @option [Proc] :scope
+    # @param [Proc] block
+    # @return [Remont::Schema]
+    def schema(...)
+      @schemas << Schema.new(...)
+    end
+
+    private
+
+    attr_reader :schemas
+    attr_reader :path
+  end
+end

data/lib/remont/tasks/remont.rake

@@ -0,0 +1,5 @@
+desc 'Run schema processing'
+task remont: :environment do
+  path = Rails.root.join(Remont.config.script_path)
+  Remont::Script.new(path).run!
+end

data/lib/remont/version.rb

@@ -0,0 +1,3 @@
+module Remont
+  VERSION = '0.1.0'.freeze
+end

data/lib/remont.rb

@@ -0,0 +1,20 @@
+require 'remont/version'
+
+require 'remont/config'
+require 'remont/attribute'
+require 'remont/railtie' if defined?(Rails::Railtie)
+require 'remont/record_processor'
+require 'remont/schema'
+require 'remont/script'
+
+module Remont
+  # @yield [Remont::Config]
+  def self.setup
+    yield config
+  end
+
+  # @return [Remont::Config]
+  def self.config
+    @config ||= Config.new
+  end
+end

data/remont.gemspec

@@ -0,0 +1,36 @@
+require_relative 'lib/remont/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'remont'
+  spec.version       = Remont::VERSION
+  spec.authors       = ['Rails Team']
+  spec.email         = ['team.rails@infinum.com']
+
+  spec.summary       = 'DSL for row level data processing.'
+  spec.homepage      = 'https://github.com/infinum/remont'
+  spec.required_ruby_version = Gem::Requirement.new('>= 2.7.0')
+
+  spec.metadata['allowed_push_host'] = 'https://rubygems.org'
+
+  spec.metadata['homepage_uri'] = spec.homepage
+  spec.metadata['source_code_uri'] = spec.homepage
+  spec.metadata['changelog_uri'] = "#{spec.homepage}/blob/master/CHANGELOG.md"
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+  spec.bindir        = 'exe'
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.add_development_dependency 'activerecord'
+  spec.add_development_dependency 'pry'
+  spec.add_development_dependency 'rake'
+  spec.add_development_dependency 'rspec'
+  spec.add_development_dependency 'rubocop-infinum'
+  spec.add_development_dependency 'sqlite3'
+  spec.add_development_dependency 'timecop'
+  spec.metadata['rubygems_mfa_required'] = 'true'
+end

metadata

@@ -0,0 +1,169 @@
+--- !ruby/object:Gem::Specification
+name: remont
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Rails Team
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2022-03-08 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: activerecord
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rubocop-infinum
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: sqlite3
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: timecop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: 
+email:
+- team.rails@infinum.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".github/workflows/ci.yml"
+- ".gitignore"
+- ".rbenv"
+- ".rspec"
+- ".rubocop.yml"
+- ".ruby-version"
+- ".travis.yml"
+- CHANGELOG.md
+- CODE_OF_CONDUCT.md
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/remont.rb
+- lib/remont/attribute.rb
+- lib/remont/config.rb
+- lib/remont/railtie.rb
+- lib/remont/record_processor.rb
+- lib/remont/schema.rb
+- lib/remont/script.rb
+- lib/remont/tasks/remont.rake
+- lib/remont/version.rb
+- remont.gemspec
+homepage: https://github.com/infinum/remont
+licenses: []
+metadata:
+  allowed_push_host: https://rubygems.org
+  homepage_uri: https://github.com/infinum/remont
+  source_code_uri: https://github.com/infinum/remont
+  changelog_uri: https://github.com/infinum/remont/blob/master/CHANGELOG.md
+  rubygems_mfa_required: 'true'
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.7.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.1.4
+signing_key: 
+specification_version: 4
+summary: DSL for row level data processing.
+test_files: []