Lots of changes. Working basic search.

Gemfile

@@ -2,6 +2,7 @@ source 'https://rubygems.org'
 
 gem 'paperclip', '~> 5.0.0'
 gem 'docsplit', '~> 0.7.6'
+gem 'filewatcher', '~> 0.5.3'
 
 # Bundle edge Rails instead: gem 'rails', github: 'rails/rails'
 gem 'rails', '~> 5.0.0', '>= 5.0.0.1'

Gemfile.lock

@@ -59,6 +59,8 @@ GEM
     erubis (2.7.0)
     execjs (2.7.0)
     ffi (1.9.14)
+    filewatcher (0.5.3)
+      trollop (~> 2.0)
     globalid (0.3.7)
       activesupport (>= 4.1.0)
     i18n (0.7.0)
@@ -147,6 +149,7 @@ GEM
     thor (0.19.1)
     thread_safe (0.3.5)
     tilt (2.0.5)
+    trollop (2.1.2)
     turbolinks (5.0.1)
       turbolinks-source (~> 5)
     turbolinks-source (5.0.0)
@@ -171,6 +174,7 @@ DEPENDENCIES
   byebug
   coffee-rails (~> 4.2)
   docsplit (~> 0.7.6)
+  filewatcher (~> 0.5.3)
   jbuilder (~> 2.5)
   jquery-rails
   listen (~> 3.0.5)

README.md

@@ -8,9 +8,10 @@ Things you may want to cover:
 * Ruby version
 
 Ruby 2.3.1
-```
+```ruby
 gem 'paperclip', '~> 5.0.0'
 gem 'docsplit', '~> 0.7.6'
+gem 'filewatcher', '~> 0.5.3'
 ```
 
 * System dependencies

app/controllers/documents_controller.rb

@@ -4,7 +4,11 @@ class DocumentsController < ApplicationController
   # GET /documents
   # GET /documents.json
   def index
-    @documents = User.find(session[:user_id]).documents
+    if params[:search]
+      @documents = User.find(session[:user_id]).documents.contains_word(params[:search])
+    else
+      @documents = User.find(session[:user_id]).documents
+    end
   end
 
   # GET /documents/1
@@ -67,6 +71,12 @@ class DocumentsController < ApplicationController
     end
   end
 
+  # GET /documents/search
+  def search
+  end
+
+  # GET
+
   private
     # Use callbacks to share common setup or constraints between actions.
     def set_document

app/jobs/content_generation_job.rb

@@ -0,0 +1,27 @@
+class ContentGenerationJob < ApplicationJob
+  require 'docsplit'
+
+  @document_id = nil
+
+  queue_as :default
+
+  after_perform :generate_tags
+
+  def perform(document_id)
+    @document_id = document_id
+    document = Document.find(document_id)
+    Docsplit.extract_text(document.doc.path, output: 'tmp/raw_content')
+    file_path = 'tmp/raw_content/' + File.basename(document.doc.path, 'pdf') + 'txt'
+    text = IO.read(file_path)
+
+    content = document.build_content(text: text)
+    content.save!
+
+    File.delete(file_path) if File.exist?(file_path)
+  end
+
+  private
+    def generate_tags
+      TagGenerationJob.perform_now @document_id
+    end
+end

app/jobs/tag_generation_job.rb

@@ -0,0 +1,16 @@
+class TagGenerationJob < ApplicationJob
+  queue_as :default
+
+  def perform(document_id)
+    document = Document.find(document_id)
+    content = document.content
+
+    words = content.text.squish.split(/\s+/)
+
+    h = Hash.new(0)
+    content.text.squish.split(/\s+/).delete_if{ |w| w.length <= 3 }.each { |w| h[w] += 1 }
+    h.sort_by { |key, value| value }
+
+    # stop list...
+  end
+end

app/models/content.rb

@@ -0,0 +1,3 @@
+class Content < ApplicationRecord
+  belongs_to :document
+end

app/models/document.rb

@@ -1,6 +1,7 @@
 class Document < ApplicationRecord
   belongs_to :user
   belongs_to :category
+  has_one :content, dependent: :destroy, required: false
   has_and_belongs_to_many :tags
 
   has_attached_file :doc,
@@ -10,4 +11,16 @@ class Document < ApplicationRecord
     hash_secret: Rails.application.secrets.secret_key_base
   }
   validates_attachment_content_type :doc, content_type: 'application/pdf'
+
+  after_save :generate_content
+
+  scope :contains_word, -> (word) { joins(:content).where("text like ?", "%#{word}%") }
+
+
+  private
+    def generate_content
+      if self.doc_content_type == 'application/pdf'
+        ContentGenerationJob.perform_now self.id
+      end
+    end
 end

app/views/documents/_form.html.erb

@@ -1,4 +1,4 @@
-<%= form_for document, url: documents_path, html: { multipart: true } do |f| %>
+<%= form_for document, html: { multipart: true } do |f| %>
   <% if document.errors.any? %>
     <div id="error_explanation">
       <h2><%= pluralize(document.errors.count, "error") %> prohibited this document from being saved:</h2>

app/views/documents/search.html.erb

@@ -0,0 +1,11 @@
+<p id="notice"><%= notice %></p>
+
+<h1>Search documents</h1>
+
+<%= form_tag documents_path, :method => 'get' do %>
+  <p>
+    <%= label_tag 'Search string' %>
+    <%= text_field_tag :search, params[:search] %>
+    <%= submit_tag 'Search' %>
+  </p>
+<% end %>

app/views/documents/show.html.erb

@@ -14,5 +14,17 @@
   <%= link_to @document.doc_file_name, @document.doc.url %>
 </p>
 
+<% if @document.content %>
+  <p>
+    <strong>Content:</strong>
+    <%= @document.content.text.truncate_words(30) %>
+  </p>
+  <p>
+    <strong>Words (length > 3):</strong>
+    <%= @document.content.text.squish.split(/\s+/).uniq.delete_if { |w| w.length <= 3 } %>
+  </p>
+<% end %>
+
+
 <%= link_to 'Edit', edit_document_path(@document) %> |
 <%= link_to 'Back', documents_path %>

app/views/layouts/application.html.erb

@@ -27,7 +27,10 @@
           </ul>
           <ul>
             <li>
-              <a href="documents/new">New</a>
+              <%= link_to 'New', new_document_path %>
+            </li>
+            <li>
+              <%= link_to 'Search', search_documents_path %>
             </li>
           </ul>
           <%= button_to 'Logout', logout_path, method: :delete %>

config/routes.rb

@@ -2,7 +2,14 @@ Rails.application.routes.draw do
   root 'documents#index', as: 'documents_index'
 
   resources :categories
-  resources :documents
+
+  resources :documents do
+    get :search, on: :collection
+    # collection do
+    #   get 'search'
+    # end
+  end
+
   resources :users
 
   controller :sessions do

db/migrate/20161125164350_create_contents.rb

@@ -0,0 +1,10 @@
+class CreateContents < ActiveRecord::Migration[5.0]
+  def change
+    create_table :contents do |t|
+      t.text :content
+      t.references :document
+
+      t.timestamps
+    end
+  end
+end

db/migrate/20161125201757_rename_content_column_to_text.rb

@@ -0,0 +1,5 @@
+class RenameContentColumnToText < ActiveRecord::Migration[5.0]
+  def change
+    rename_column :contents, :content, :text
+  end
+end

db/schema.rb

@@ -10,7 +10,7 @@
 #
 # It's strongly recommended that you check this file into your version control system.
 
-ActiveRecord::Schema.define(version: 20161124223446) do
+ActiveRecord::Schema.define(version: 20161125201757) do
 
   create_table "categories", force: :cascade do |t|
     t.string   "name"
@@ -22,6 +22,14 @@ ActiveRecord::Schema.define(version: 20161124223446) do
     t.index ["user_id"], name: "index_categories_on_user_id"
   end
 
+  create_table "contents", force: :cascade do |t|
+    t.text     "text"
+    t.integer  "document_id"
+    t.datetime "created_at",  null: false
+    t.datetime "updated_at",  null: false
+    t.index ["document_id"], name: "index_contents_on_document_id"
+  end
+
   create_table "documents", force: :cascade do |t|
     t.string   "name"
     t.datetime "created_at",       null: false

test/fixtures/contents.yml

@@ -0,0 +1,9 @@
+# Read about fixtures at http://api.rubyonrails.org/classes/ActiveRecord/FixtureSet.html
+
+one:
+  content: MyText
+  document: 
+
+two:
+  content: MyText
+  document: 

test/jobs/content_generation_job_test.rb

@@ -0,0 +1,7 @@
+require 'test_helper'
+
+class ContentGenerationJobTest < ActiveJob::TestCase
+  # test "the truth" do
+  #   assert true
+  # end
+end

test/jobs/tag_generation_job_test.rb

@@ -0,0 +1,7 @@
+require 'test_helper'
+
+class TagGenerationJobTest < ActiveJob::TestCase
+  # test "the truth" do
+  #   assert true
+  # end
+end

test/models/content_test.rb

@@ -0,0 +1,7 @@
+require 'test_helper'
+
+class ContentTest < ActiveSupport::TestCase
+  # test "the truth" do
+  #   assert true
+  # end
+end