content indexer app

Author: Angela Guette

.gitignore

@@ -0,0 +1,16 @@
+# See https://help.github.com/articles/ignoring-files for more about ignoring files.
+#
+# If you find yourself ignoring temporary files generated by your text editor
+# or operating system, you probably want to add a global ignore instead:
+#   git config --global core.excludesfile '~/.gitignore_global'
+
+# Ignore bundler config.
+/.bundle
+
+# Ignore all logfiles and tempfiles.
+/log/*
+/tmp/*
+!/log/.keep
+!/tmp/.keep
+
+.byebug_history

.rspec

@@ -0,0 +1 @@
+--require spec_helper

Gemfile

@@ -0,0 +1,32 @@
+source 'https://rubygems.org'
+ruby '2.4.0'
+
+git_source(:github) do |repo_name|
+  repo_name = "#{repo_name}/#{repo_name}" unless repo_name.include?("/")
+  "https://github.com/#{repo_name}.git"
+end
+
+# Application
+gem 'rails', '~> 5.1.5'
+gem 'pg', '>= 0.18', '< 2.0'
+gem 'puma', '~> 3.7'
+gem 'jsonapi-resources'
+gem 'tzinfo-data', platforms: [:mingw, :mswin, :x64_mingw, :jruby]
+
+group :development, :test do
+  gem 'rspec-rails', '~> 3.7'
+  gem 'factory_bot_rails'
+  gem 'faker'
+  gem 'byebug', platforms: [:mri, :mingw, :x64_mingw]
+end
+
+group :development do
+  gem 'listen', '>= 3.0.5', '< 3.2'
+  gem 'spring'
+  gem 'spring-watcher-listen', '~> 2.0.0'
+end
+
+group :test do
+  gem 'shoulda-matchers', '~> 3.1'
+  gem 'rails-controller-testing'
+end

Gemfile.lock

@@ -0,0 +1,179 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    actioncable (5.1.6)
+      actionpack (= 5.1.6)
+      nio4r (~> 2.0)
+      websocket-driver (~> 0.6.1)
+    actionmailer (5.1.6)
+      actionpack (= 5.1.6)
+      actionview (= 5.1.6)
+      activejob (= 5.1.6)
+      mail (~> 2.5, >= 2.5.4)
+      rails-dom-testing (~> 2.0)
+    actionpack (5.1.6)
+      actionview (= 5.1.6)
+      activesupport (= 5.1.6)
+      rack (~> 2.0)
+      rack-test (>= 0.6.3)
+      rails-dom-testing (~> 2.0)
+      rails-html-sanitizer (~> 1.0, >= 1.0.2)
+    actionview (5.1.6)
+      activesupport (= 5.1.6)
+      builder (~> 3.1)
+      erubi (~> 1.4)
+      rails-dom-testing (~> 2.0)
+      rails-html-sanitizer (~> 1.0, >= 1.0.3)
+    activejob (5.1.6)
+      activesupport (= 5.1.6)
+      globalid (>= 0.3.6)
+    activemodel (5.1.6)
+      activesupport (= 5.1.6)
+    activerecord (5.1.6)
+      activemodel (= 5.1.6)
+      activesupport (= 5.1.6)
+      arel (~> 8.0)
+    activesupport (5.1.6)
+      concurrent-ruby (~> 1.0, >= 1.0.2)
+      i18n (>= 0.7, < 2)
+      minitest (~> 5.1)
+      tzinfo (~> 1.1)
+    arel (8.0.0)
+    builder (3.2.3)
+    byebug (10.0.2)
+    concurrent-ruby (1.0.5)
+    crass (1.0.4)
+    diff-lcs (1.3)
+    erubi (1.7.1)
+    factory_bot (4.8.2)
+      activesupport (>= 3.0.0)
+    factory_bot_rails (4.8.2)
+      factory_bot (~> 4.8.2)
+      railties (>= 3.0.0)
+    faker (1.8.7)
+      i18n (>= 0.7)
+    ffi (1.9.23)
+    globalid (0.4.1)
+      activesupport (>= 4.2.0)
+    i18n (1.0.1)
+      concurrent-ruby (~> 1.0)
+    jsonapi-resources (0.9.0)
+      activerecord (>= 4.1)
+      concurrent-ruby
+      railties (>= 4.1)
+    listen (3.1.5)
+      rb-fsevent (~> 0.9, >= 0.9.4)
+      rb-inotify (~> 0.9, >= 0.9.7)
+      ruby_dep (~> 1.2)
+    loofah (2.2.2)
+      crass (~> 1.0.2)
+      nokogiri (>= 1.5.9)
+    mail (2.7.0)
+      mini_mime (>= 0.1.1)
+    method_source (0.9.0)
+    mini_mime (1.0.0)
+    mini_portile2 (2.3.0)
+    minitest (5.11.3)
+    nio4r (2.3.1)
+    nokogiri (1.8.2)
+      mini_portile2 (~> 2.3.0)
+    pg (1.0.0)
+    puma (3.11.4)
+    rack (2.0.5)
+    rack-test (1.0.0)
+      rack (>= 1.0, < 3)
+    rails (5.1.6)
+      actioncable (= 5.1.6)
+      actionmailer (= 5.1.6)
+      actionpack (= 5.1.6)
+      actionview (= 5.1.6)
+      activejob (= 5.1.6)
+      activemodel (= 5.1.6)
+      activerecord (= 5.1.6)
+      activesupport (= 5.1.6)
+      bundler (>= 1.3.0)
+      railties (= 5.1.6)
+      sprockets-rails (>= 2.0.0)
+    rails-controller-testing (1.0.2)
+      actionpack (~> 5.x, >= 5.0.1)
+      actionview (~> 5.x, >= 5.0.1)
+      activesupport (~> 5.x)
+    rails-dom-testing (2.0.3)
+      activesupport (>= 4.2.0)
+      nokogiri (>= 1.6)
+    rails-html-sanitizer (1.0.4)
+      loofah (~> 2.2, >= 2.2.2)
+    railties (5.1.6)
+      actionpack (= 5.1.6)
+      activesupport (= 5.1.6)
+      method_source
+      rake (>= 0.8.7)
+      thor (>= 0.18.1, < 2.0)
+    rake (12.3.1)
+    rb-fsevent (0.10.3)
+    rb-inotify (0.9.10)
+      ffi (>= 0.5.0, < 2)
+    rspec-core (3.7.1)
+      rspec-support (~> 3.7.0)
+    rspec-expectations (3.7.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.7.0)
+    rspec-mocks (3.7.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.7.0)
+    rspec-rails (3.7.2)
+      actionpack (>= 3.0)
+      activesupport (>= 3.0)
+      railties (>= 3.0)
+      rspec-core (~> 3.7.0)
+      rspec-expectations (~> 3.7.0)
+      rspec-mocks (~> 3.7.0)
+      rspec-support (~> 3.7.0)
+    rspec-support (3.7.1)
+    ruby_dep (1.5.0)
+    shoulda-matchers (3.1.2)
+      activesupport (>= 4.0.0)
+    spring (2.0.2)
+      activesupport (>= 4.2)
+    spring-watcher-listen (2.0.1)
+      listen (>= 2.7, < 4.0)
+      spring (>= 1.2, < 3.0)
+    sprockets (3.7.1)
+      concurrent-ruby (~> 1.0)
+      rack (> 1, < 3)
+    sprockets-rails (3.2.1)
+      actionpack (>= 4.0)
+      activesupport (>= 4.0)
+      sprockets (>= 3.0.0)
+    thor (0.20.0)
+    thread_safe (0.3.6)
+    tzinfo (1.2.5)
+      thread_safe (~> 0.1)
+    websocket-driver (0.6.5)
+      websocket-extensions (>= 0.1.0)
+    websocket-extensions (0.1.3)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  byebug
+  factory_bot_rails
+  faker
+  jsonapi-resources
+  listen (>= 3.0.5, < 3.2)
+  pg (>= 0.18, < 2.0)
+  puma (~> 3.7)
+  rails (~> 5.1.5)
+  rails-controller-testing
+  rspec-rails (~> 3.7)
+  shoulda-matchers (~> 3.1)
+  spring
+  spring-watcher-listen (~> 2.0.0)
+  tzinfo-data
+
+RUBY VERSION
+   ruby 2.4.0p0
+
+BUNDLED WITH
+   1.16.1

README.md

@@ -0,0 +1,24 @@
+# README
+
+This README would normally document whatever steps are necessary to get the
+application up and running.
+
+Things you may want to cover:
+
+* Ruby version
+
+* System dependencies
+
+* Configuration
+
+* Database creation
+
+* Database initialization
+
+* How to run the test suite
+
+* Services (job queues, cache servers, search engines, etc.)
+
+* Deployment instructions
+
+* ...

Rakefile

@@ -0,0 +1,6 @@
+# Add your own tasks in files placed in lib/tasks ending in .rake,
+# for example lib/tasks/capistrano.rake, and they will automatically be available to Rake.
+
+require_relative 'config/application'
+
+Rails.application.load_tasks

app/channels/application_cable/channel.rb

@@ -0,0 +1,4 @@
+module ApplicationCable
+  class Channel < ActionCable::Channel::Base
+  end
+end

app/channels/application_cable/connection.rb

@@ -0,0 +1,4 @@
+module ApplicationCable
+  class Connection < ActionCable::Connection::Base
+  end
+end

app/controllers/api/v1/elements_controller.rb

@@ -0,0 +1,6 @@
+module API
+  module V1
+    class ElementsController < ApplicationController
+    end
+  end
+end

app/controllers/api/v1/pages_controller.rb

@@ -0,0 +1,16 @@
+module API
+  module V1
+    class PagesController < ApplicationController
+      def create
+        super
+
+        if response.successful?
+          response_body = JSON.parse(response.body)
+          page_created = Page.find(response_body['data']['id'])
+
+          PageIndexCreator.call(page_created)
+        end
+      end
+    end
+  end
+end

app/controllers/application_controller.rb

@@ -0,0 +1,3 @@
+class ApplicationController < ActionController::API
+  include JSONAPI::ActsAsResourceController
+end

app/controllers/concerns/.keep

@@ -0,0 +1,2 @@
+class ApplicationJob < ActiveJob::Base
+end

app/jobs/application_job.rb

@@ -0,0 +1,4 @@
+class ApplicationMailer < ActionMailer::Base
+  default from: '[email protected]'
+  layout 'mailer'
+end

app/mailers/application_mailer.rb

@@ -0,0 +1,3 @@
+class ApplicationRecord < ActiveRecord::Base
+  self.abstract_class = true
+end

app/models/application_record.rb

@@ -0,0 +1,5 @@
+class Element < ApplicationRecord
+  belongs_to :page
+
+  validates :tag, :content, :page, presence: true
+end

app/models/concerns/.keep

@@ -0,0 +1,5 @@
+class Page < ApplicationRecord
+  has_many :elements
+
+  validates :url, presence: true
+end

app/models/element.rb

@@ -0,0 +1,9 @@
+module API
+  module V1
+    class ElementResource < JSONAPI::Resource
+      attributes :tag, :content
+
+      belongs_to :page
+    end
+  end
+end

app/models/page.rb

@@ -0,0 +1,9 @@
+module API
+  module V1
+    class PageResource < JSONAPI::Resource
+      attributes :url
+
+      has_many :elements
+    end
+  end
+end

app/resources/api/v1/element_resource.rb

@@ -0,0 +1,5 @@
+class ApplicationService
+  def self.call(*args, &block)
+    new(*args, &block).call
+  end
+end

app/resources/api/v1/page_resource.rb

@@ -0,0 +1,30 @@
+require 'nokogiri'
+require 'open-uri'
+
+class PageIndexCreator< ApplicationService
+  attr_reader :page
+
+  def initialize(page)
+    @page = page
+  end
+
+  def call
+    doc = Nokogiri::HTML(open(@page.url))
+
+    process_elements(doc, page)
+  end
+
+  private
+
+  def process_elements(doc, page)
+    %w[h1 h2 h3 a].each do |tag|
+      process_element_content(page, doc, tag)
+    end
+  end
+
+  def process_element_content(page, doc, tag)
+    doc.css(tag).each do |tag|
+      page.elements.create(tag: tag.name, content: tag.content)
+    end
+  end
+end

app/services/application_service.rb

@@ -0,0 +1,13 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+    <style>
+      /* Email styles need to be inline */
+    </style>
+  </head>
+
+  <body>
+    <%= yield %>
+  </body>
+</html>

app/services/page_index_creator.rb

@@ -0,0 +1 @@
+<%= yield %>