Added pdf analyzer

Analyzer should be moved to ActiveStorage::Analyzer
First there are many bugs with ActiveStorage that needs to be fixed:
Files are not deleted if job is destroyed (dependent: :purge is set)
If a new file is uploaded the old file is not deleted
(has_one_attechment)

Gemfile

@@ -71,3 +71,5 @@ group :test do
 end
 
 gem 'inline_svg', '~> 1.9'
+
+gem "pdf-reader", "~> 2.12"

Gemfile.lock

@@ -1,6 +1,7 @@
 GEM
   remote: https://rubygems.org/
   specs:
+    Ascii85 (1.1.1)
     actioncable (7.1.3.4)
       actionpack (= 7.1.3.4)
       activesupport (= 7.1.3.4)
@@ -77,6 +78,7 @@ GEM
       tzinfo (~> 2.0)
     addressable (2.8.7)
       public_suffix (>= 2.0.2, < 7.0)
+    afm (0.2.2)
     base64 (0.2.0)
     bigdecimal (3.1.8)
     bindex (0.8.1)
@@ -105,6 +107,7 @@ GEM
       i18n (>= 1.8.11, < 2)
     globalid (1.2.1)
       activesupport (>= 6.1)
+    hashery (2.1.2)
     i18n (1.14.5)
       concurrent-ruby (~> 1.0)
     importmap-rails (2.0.1)
@@ -158,6 +161,12 @@ GEM
       racc (~> 1.4)
     nokogiri (1.16.7-x86_64-linux)
       racc (~> 1.4)
+    pdf-reader (2.12.0)
+      Ascii85 (~> 1.0)
+      afm (~> 0.2.1)
+      hashery (~> 2.0)
+      ruby-rc4
+      ttfunk
     psych (5.1.2)
       stringio
     public_suffix (6.0.1)
@@ -213,6 +222,7 @@ GEM
       io-console (~> 0.5)
     rexml (3.3.4)
       strscan
+    ruby-rc4 (0.1.5)
     rubyzip (2.3.2)
     selenium-webdriver (4.23.0)
       base64 (~> 0.2)
@@ -251,6 +261,8 @@ GEM
       railties (>= 7.0.0)
     thor (1.3.1)
     timeout (0.4.1)
+    ttfunk (1.8.0)
+      bigdecimal (~> 3.1)
     turbo-rails (2.0.6)
       actionpack (>= 6.0.0)
       activejob (>= 6.0.0)
@@ -287,6 +299,7 @@ DEPENDENCIES
   importmap-rails
   inline_svg (~> 1.9)
   jbuilder
+  pdf-reader (~> 2.12)
   puma (>= 5.0)
   rails (~> 7.1.3, >= 7.1.3.4)
   redis (>= 4.0.1)

app/models/job.rb

@@ -2,7 +2,7 @@ class Job < ApplicationRecord
   belongs_to :operator, class_name: 'User', optional: true
   belongs_to :costumer, class_name: 'User', optional: true
 
-  has_one_attached :pdf, dependent: :destroy
+  has_one_attached :pdf, dependent: :purge
 
   validates_presence_of :costumer_firstname, :costumer_lastname, :privacy_policy_accepted, :pdf
   validate :acceptable_pdf
@@ -11,6 +11,9 @@ class Job < ApplicationRecord
   before_save :update_paid_at, if: :will_save_change_to_status?
   before_save :update_status_changed_at, if: :will_save_change_to_status?
 
+  # TODO: works only when job is created. Should move analyzer to activestorage :https://discuss.rubyonrails.org/t/active-storage-in-production-lessons-learned-and-in-depth-look-at-how-it-works/83289
+  after_create_commit :analyze_pdf
+
   # NOTE: Multiple status if paing before brinting?
   enum status: {
     open: 0,
@@ -53,12 +56,10 @@ class Job < ApplicationRecord
   def acceptable_pdf
     return unless pdf.attached?
 
-    errors.add(:pdf, 'is too big') unless pdf.blob.byte_size <= 100.megabyte
-
     acceptable_types = ['application/pdf']
-    return if acceptable_types.include?(pdf.content_type)
 
-    errors.add(:pdf, 'must be a PDF')
+    errors.add(:pdf, 'is too big') unless pdf.blob.byte_size <= 100.megabyte
+    errors.add(:pdf, 'must be a PDF') unless acceptable_types.include?(pdf.content_type)
   end
 
   def able_to_cancel?
@@ -84,4 +85,29 @@ class Job < ApplicationRecord
   def update_status_changed_at
     self.status_changed_at = Time.now
   end
+
+  def analyze_pdf
+    # return unless pdf.attached? && pdf.new_record?
+
+    # TODO: add any check if attachment has changed
+
+    # pdfs.each do |pdf|
+    pdf.blob.open do |file|
+      self.number_of_plans_a0 = 0
+      self.number_of_plans_a1 = 0
+      self.number_of_plans_a2 = 0
+      self.number_of_plans_a3 = 0
+      self.costum_qm_plan = 0
+      # file = ActiveStorage::Blob.service.path_for(pdf.key).to_s
+      pdf_analyzer = Services::PdfAnalyzer.new(file)
+      pdf_analyzer.analyze
+      self.number_of_plans_a0 += pdf_analyzer.pages_a0
+      self.number_of_plans_a1 += pdf_analyzer.pages_a1
+      self.number_of_plans_a2 += pdf_analyzer.pages_a2
+      self.number_of_plans_a3 += pdf_analyzer.pages_a3
+      self.costum_qm_plan += pdf_analyzer.costum_qm
+      save
+    end
+    # end
+  end
 end

app/views/jobs/_job_tr.html.erb

@@ -5,13 +5,16 @@
   <td class="p-3 text-sm text-hsrm-gray whitespace-nowrap"> <%= job.fullname %> </td>
   <td class="p-3 text-sm text-hsrm-gray whitespace-nowrap">
     <% if job.pdf.attached? %>
-      <%= job.pdf.filename %><span class="p-1.5 bg-gray-300 font-medium rounded-lg ml-2"><%=number_to_human_size job.pdf.blob.byte_size%></span>
+      <%#= link_to job.pdf.filename, rails_blob_path(job.pdf, disposition: "attachment") %>
+      <%= link_to job.pdf.filename, job.pdf, download:true %>
+      <span class="p-1.5 bg-gray-300 font-medium rounded-lg ml-2"><%=number_to_human_size job.pdf.blob.byte_size%></span>
     <% end %>
   </td>
   <td class="p-3 text-sm text-left text-hsrm-gray whitespace-nowrap"><span class="p-1.5 bg-gray-300 bg-opacity-50 font-medium rounded-lg"><%= job.number_of_plans_a0 %></span></td>
   <td class="p-3 text-sm text-left text-hsrm-gray whitespace-nowrap"><span class="p-1.5 bg-gray-300 bg-opacity-50 font-medium rounded-lg"><%= job.number_of_plans_a1 %></span></td>
   <td class="p-3 text-sm text-left text-hsrm-gray whitespace-nowrap"><span class="p-1.5 bg-gray-300 bg-opacity-50 font-medium rounded-lg"><%= job.number_of_plans_a2 %></span></td>
   <td class="p-3 text-sm text-left text-hsrm-gray whitespace-nowrap"><span class="p-1.5 bg-gray-300 bg-opacity-50 font-medium rounded-lg"><%= job.number_of_plans_a3 %></span></td>
+  <td class="p-3 text-sm text-left text-hsrm-gray whitespace-nowrap"><span class="p-1.5 bg-gray-300 bg-opacity-50 font-medium rounded-lg"><%= job.costum_qm_plan.round(2)  %></span></td>
   <td class="p-3 text-sm text-left text-hsrm-gray whitespace-nowrap">
     <span class="p-1.5 text-xs font-medium uppercase tracking-wider bg-opacity-50 text-status-<%= job.status.to_sym %> bg-status-<%= job.status %>-light rounded-lg"><%= job.status %></span>
   </td>

app/views/jobs/index.html.erb

@@ -17,6 +17,7 @@
           <th class="p-3 text-sm font-semibold tracking-wide text-left w-1"> A1 </th>
           <th class="p-3 text-sm font-semibold tracking-wide text-left w-1"> A2 </th>
           <th class="p-3 text-sm font-semibold tracking-wide text-left w-1"> A3 </th>
+          <th class="p-3 text-sm font-semibold tracking-wide text-left w-1"> qm </th>
           <th class="p-3 text-sm font-semibold tracking-wide text-left w-1"> Status </th>
           <th class="p-3 text-sm font-semibold tracking-wide text-left w-1"> Actions </th>
         </tr>

db/seeds.rb

@@ -17,18 +17,18 @@ end
 ['GanzWichtig.pdf', 'IchBinIn5MinDran.pdf', 'DerPlanDerImmerProblemeMacht.pdf',
  'DieFarbenGefallenMirNicht.pdf', 'MachHinIchHabsEilig.pdf', 'WarumDauertDasSoLange.pdf',
  'DenPlanBezahleIchNicht.pdf', 'IchWarAlsErstesDran.pdf', 'WarumIstDerPlotterDefekt.pdf', 'DasNächsteMalGeheIchWoAndersHin.pdf'].shuffle.each do |pdf|
-  a0 = rand(0...7)
+  # a0 = rand(0...7)
-  a1 = rand(0...7)
+  # a1 = rand(0...7)
-  a2 = rand(0...7)
+  # a2 = rand(0...7)
-  a3 = rand(0...7)
+  # a3 = rand(0...7)
-  a0.zero? || a1 = 0 && a2 = 0 && a3 = 0
+  # a0.zero? || a1 = 0 && a2 = 0 && a3 = 0
-  a1.zero? || a2 = 0 && a3 = 0
+  # a1.zero? || a2 = 0 && a3 = 0
-  a2.zero? || a3 = 0
+  # a2.zero? || a3 = 0
   status = %i[open open open open open open open open open open open open open open
               printing ready_for_pickup paid canceled].sample
 
   job = Job.new(costumer_firstname: Faker::Name.unique.first_name, costumer_lastname: Faker::Name.unique.last_name,
-                number_of_plans_a0: a0, number_of_plans_a1: a1, number_of_plans_a2: a2, number_of_plans_a3: a3,
+                # number_of_plans_a0: a0, number_of_plans_a1: a1, number_of_plans_a2: a2, number_of_plans_a3: a3,
                 status:, privacy_policy_accepted: true)
   job.pdf = File.open(Rails.root.join('db/pdfs/', pdf))
   job.save!

lib/services/pdf_analyzer.rb

@@ -0,0 +1,80 @@
+module Services
+  # Class to analyze PDF to extract number of pages from a0 to a3 and costum qm
+  class PdfAnalyzer
+    require 'pdf/reader'
+    require 'bigdecimal'
+
+    attr_reader :costum_qm, :pages_a0, :pages_a1, :pages_a2, :pages_a3
+
+    def initialize(file)
+      @reader = PDF::Reader.new(file)
+
+      @pages_a0 = 0
+      @pages_a1 = 0
+      @pages_a2 = 0
+      @pages_a3 = 0
+      @costum_qm = 0
+
+      @page_width = 0
+      @page_height = 0
+    end
+
+    def analyze
+      @reader.pages.each do |page|
+        format = extract_format(page)
+        case format
+        when 'a0'
+          @pages_a0 += 1
+        when 'a1'
+          @pages_a1 += 1
+        when 'a2'
+          @pages_a2 += 1
+        when 'a3'
+          @pages_a3 += 1
+        else
+          @costum_qm += calculate_qm
+        end
+      end
+    end
+
+    private
+
+    def calculate_qm
+      (@page_width / 1000) * (@page_height / 1000)
+    end
+
+    def extract_format(page)
+      # debugger
+      extract_size(page)
+      return 'a0'  if @page_width.round == 841 && @page_height.round == 1189
+      return 'a1'  if @page_width.round == 594 && @page_height.round == 841
+      return 'a2' if @page_width.round == 420 && @page_height.round == 594
+      return 'a3' if @page_width.round == 297 && @page_height.round == 420
+
+      'costum'
+    end
+
+    def extract_size(page)
+      # debugger
+      bbox   = page.attributes[:MediaBox] # CropBox
+      width  = bbox[2] - bbox[0]
+      height = bbox[3] - bbox[1]
+      width_in_mm = pt2mm(width)
+      height_in_mm = pt2mm(height)
+      width_in_mm, height_in_mm = height_in_mm, width_in_mm if width_in_mm > height_in_mm
+
+      @page_width = width_in_mm
+      @page_height = height_in_mm
+
+      nil
+    end
+
+    def pt2mm(pt)
+      (pt2in(pt) * BigDecimal('25.4')).round(2)
+    end
+
+    def pt2in(pt)
+      (pt / BigDecimal('72')).round(2)
+    end
+  end
+end