Populate user subjects based on documents

Gemfile

@@ -11,6 +11,7 @@ gem 'importmap-rails', '~> 2.1'
 gem "omniauth", "~> 2.1"
 gem "omniauth-google-oauth2", '~> 1.2'
 gem "omniauth-rails_csrf_protection", '~> 1.0'
+gem 'pdf-reader'
 gem 'pg', '~> 1.5'
 gem 'puma', '~> 6.5'
 gem 'rollbar', '~> 3.6'

Gemfile.lock

@@ -1,6 +1,7 @@
 GEM
   remote: https://rubygems.org/
   specs:
+    Ascii85 (2.0.1)
     actioncable (8.0.0.1)
       actionpack (= 8.0.0.1)
       activesupport (= 8.0.0.1)
@@ -74,6 +75,7 @@ GEM
       uri (>= 0.13.1)
     addressable (2.8.6)
       public_suffix (>= 2.0.2, < 6.0)
+    afm (0.2.2)
     ast (2.4.2)
     base64 (0.2.0)
     bcrypt (3.1.20)
@@ -126,6 +128,7 @@ GEM
     ffi (1.15.5)
     globalid (1.2.1)
       activesupport (>= 6.1)
+    hashery (2.1.2)
     hashie (5.0.0)
     i18n (1.14.7)
       concurrent-ruby (~> 1.0)
@@ -222,6 +225,12 @@ GEM
     parser (3.3.7.0)
       ast (~> 2.4.1)
       racc
+    pdf-reader (2.13.0)
+      Ascii85 (>= 1.0, < 3.0, != 2.0.0)
+      afm (~> 0.2.1)
+      hashery (~> 2.0)
+      ruby-rc4
+      ttfunk
     pg (1.5.9)
     psych (5.2.2)
       date
@@ -320,6 +329,7 @@ GEM
       rubocop (>= 1.52.0, < 2.0)
       rubocop-ast (>= 1.31.1, < 2.0)
     ruby-progressbar (1.13.0)
+    ruby-rc4 (0.1.5)
     rubyzip (2.4.1)
     sassc (2.4.0)
       ffi (~> 1.9)
@@ -360,6 +370,8 @@ GEM
     thor (1.3.2)
     tilt (2.0.10)
     timeout (0.4.2)
+    ttfunk (1.8.0)
+      bigdecimal (~> 3.1)
     turbo-rails (2.0.11)
       actionpack (>= 6.0.0)
       railties (>= 6.0.0)
@@ -402,6 +414,7 @@ DEPENDENCIES
   omniauth (~> 2.1)
   omniauth-google-oauth2 (~> 1.2)
   omniauth-rails_csrf_protection (~> 1.0)
+  pdf-reader
   pg (~> 1.5)
   puma (~> 6.5)
   rails (~> 8.0.0)

app/assets/stylesheets/_utility.scss

@@ -6,6 +6,35 @@
   color: #19a819 !important;
 }
 
+.color-red {
+  color: #ff0000 !important;
+}
+
 .d-none {
   display: none !important;
 }
+
+@mixin generate-margin-classes($direction, $property) {
+  @for $i from 0 through 6 {
+    .m#{$direction}-#{$i} {
+      margin-#{$property}: #{$i * 0.5}rem !important;
+    }
+  }
+}
+
+@include generate-margin-classes(t, top);
+@include generate-margin-classes(r, right);
+@include generate-margin-classes(b, bottom);
+@include generate-margin-classes(l, left);
+
+@mixin generate-margin-axis-classes($axis, $property1, $property2) {
+  @for $i from 0 through 6 {
+    .m#{$axis}-#{$i} {
+      margin-#{$property1}: #{$i * 0.5}rem !important;
+      margin-#{$property2}: #{$i * 0.5}rem !important;
+    }
+  }
+}
+
+@include generate-margin-axis-classes(x, left, right);
+@include generate-margin-axis-classes(y, top, bottom);

app/assets/stylesheets/application.scss

@@ -222,6 +222,11 @@ body {
   padding-left: 0px;
 }
 
+.subtle-text {
+  font-size: 0.7em;
+  color: #666;
+}
+
 .show-password-button {
   margin-right: -20px;
 }

app/controllers/academic_histories_controller.rb

@@ -0,0 +1,46 @@
+require 'pdf-reader'
+
+class AcademicHistoriesController < ApplicationController
+  def index
+    redirect_to new_academic_history_path
+  end
+
+  def new
+  end
+
+  def create
+    file = params[:file]
+    @failed_entries = []
+    @successful_entries = []
+
+    if file && file.content_type == 'application/pdf'
+      academic_entries = AcademicHistory::PdfProcessor.process(file)
+      academic_entries.each do |entry|
+        save_academic_entry(entry) if entry.approved?
+      end
+    else
+      flash[:error] = 'Please upload a valid PDF file'
+    end
+    render :new
+  end
+
+  private
+
+  def save_academic_entry(entry)
+    subject_match = Subject.where("lower(unaccent(name)) = lower(unaccent(?))", entry.name)
+    subject_match = subject_match.select { |subject| subject.credits == entry.credits.to_i }
+    active_subjects = subject_match.select { |subject| !subject.inactive? }
+    if subject_match.length == 1
+      save_subject(subject_match.first)
+    elsif active_subjects.length == 1
+      save_subject(active_subjects.first)
+    else
+      @failed_entries << entry
+    end
+  end
+
+  def save_subject(subject)
+    current_student.force_add_subject(subject)
+    @successful_entries << subject
+  end
+end

app/models/base_student.rb

@@ -11,6 +11,12 @@ def add(approvable)
     end
   end
 
+  def force_add_subject(subject)
+    ids << subject.exam.id if subject.exam
+    ids << subject.course.id if subject.course
+    save!
+  end
+
   def remove(approvable)
     ids.delete(approvable.id)
     if !approvable.is_exam? && approvable.subject.exam.present? && ids.include?(approvable.subject.exam.id)

app/views/academic_histories/new.html.erb

@@ -0,0 +1,35 @@
+<h3 class="mdc-deprecated-list-group__subheader mdc-typography--headline5 sign-in mb-3">Resumen por Grupo</h3>
+<p class="mb-3">Carga tu escolaridad para marcar automaticamente las materias que ya cursaste.</p>
+<p>1) Entrar a <a href="https://bedelias.udelar.edu.uy/" target="_blank">Bedelias</a> e iniciar session</p>
+<p>2) Entrar a "Estudiante" -> "Escolaridad" -> "Solicitar Escolaridad"</p>
+<p>3) Seleccionar tu carrera y "No" en "Resultados Intermedios"</p>
+<%= form_with url: academic_histories_path, method: :post, local: true, html: { multipart: true } do |form| %>
+  <div class="sign-in my-6">
+    <%= form.label :file, "Upload PDF" %>
+    <%= form.file_field :file, accept: "application/pdf" %>
+
+    <%= form.button class: "mdc-button mdc-button--raised" do %>
+      <span class="mdc-button__ripple"></span>
+      <span class='mdc-button__label'>
+        Subir
+      </span>
+    <% end %>
+  </div>
+<% end %>
+<div class="sign-in">
+  <% if @successful_entries&.present? %>
+    <p class="color-green mb-2"><%= @successful_entries.length %> Materias marcadas correctamente</p>
+    <% @successful_entries.each do |entry| %>
+      <p><%= entry.code %> - <%= entry.name %></p>
+    <% end %>
+  <% end %>
+  <% if @failed_entries&.present? %>
+    <p class="color-red my-2"><%= @failed_entries.length %> Materias no encontradas</p>
+    <% @failed_entries.each do |entry| %>
+      <p><%= entry.name %></p>
+    <% end %>
+  <% end %>
+</div>
+<p class="subtle-text sign-in mt-3">
+La escolaridad no incluye codigos de materias, por lo que en caso de multiples candidatos con el mismo nombre, se marca la materia mas reciente y actualmente activa
+</p>

app/views/shared/_user_menu.html.erb

@@ -29,6 +29,12 @@
           Editar Perfil
         <span>
       <% end %>
+      <%= link_to new_academic_history_path, class: "mdc-deprecated-list-item", tabindex: 0 do %>
+        <span class="mdc-deprecated-list-item__ripple"></span>
+        <span class="mdc-deprecated-list-item__text">
+          Importar Materias
+        <span>
+      <% end %>
       <%= link_to destroy_user_session_path, method: :delete, class: "mdc-deprecated-list-item", tabindex: 0 do %>
         <span class="mdc-deprecated-list-item__ripple"></span>
         <span class="mdc-deprecated-list-item__text">

config/routes.rb

@@ -30,5 +30,7 @@
 
   resources :current_optional_subjects, only: :index
 
+  resources :academic_histories, only: [:new, :create, :index]
+
   resources :planned_subjects, only: [:index, :create, :destroy], param: :subject_id
 end

lib/academic_history/pdf_processor.rb

@@ -0,0 +1,41 @@
+require 'pdf-reader'
+
+module AcademicHistory
+  module PdfProcessor
+    AcademicEntry = Struct.new(:name, :credits, :number_of_failures, :date_of_completion, :grade) do
+      def approved?
+        grade != '***'
+      end
+    end
+    extend self
+
+    def process(file)
+      Enumerator.new do |yielder|
+        reader = PDF::Reader.new(file.path)
+
+        reader.pages.each do |page|
+          page.text.split("\n").each do |line|
+            line.match(subject_regex) do |match|
+              yielder << AcademicEntry.new(match[1], match[2], match[3], match[4], match[5])
+            end
+          end
+        end
+      end
+    end
+
+    # SubjectName Credits NumberOfFailures DateOfCompletion Concept
+    def subject_regex
+      /\s*(.*?)\s+(\d+)\s+(\d+)\s+(#{date_regex.source})\s+(#{concept_regex.source})/
+    end
+
+    # The date can be either a date in the format DD/MM/YYYY or **********
+    def date_regex
+      /\*{10}|\d\d\/\d\d\/\d\d\d\d/
+    end
+
+    # The concept can be either a number from 0 to 12, S/N or ***
+    def concept_regex
+      /Aceptable|Bueno|Muy Bueno|Excelente|S\/C|\*{3}/
+    end
+  end
+end

spec/lib/academic_history/pdf_processor_spec.rb

@@ -0,0 +1,79 @@
+require 'rails_helper'
+
+RSpec.describe AcademicHistory::PdfProcessor, type: :lib do
+  # rubocop:disable Layout/LineLength
+  let(:pdf_mock) {
+    [
+      double('page', text: "  Test Subject 1                                                                10        0     20/02/2024 Aceptable"),
+      double('page', text: "  Test Subject 2                                                                 9        0     20/02/2024 Bueno"),
+      double('page', text: "  Test Subject 3                                                                 8        0     20/02/2024 Muy Bueno"),
+      double('page', text: "  Test Subject 4                                                                 7        0     20/02/2024 Excelente"),
+      double('page', text: "  Test Subject 5                                                                 6        0     20/02/2024 S/C"),
+      double('page', text: "  Failed Subject 1                                                               8        1     ********** ***")
+    ]
+  }
+  # rubocop:enable Layout/LineLength
+
+  let(:academic_entries) { described_class::AcademicEntry }
+
+  describe '.process' do
+    let(:file) { double('file', path: 'path') }
+    let(:reader) { double('reader') }
+    let(:academic_entries_list) {
+      [
+        academic_entries.new('Test Subject 1', '10', '0', '20/02/2024', 'Aceptable'),
+        academic_entries.new('Test Subject 2', '9', '0', '20/02/2024', 'Bueno'),
+        academic_entries.new('Test Subject 3', '8', '0', '20/02/2024', 'Muy Bueno'),
+        academic_entries.new('Test Subject 4', '7', '0', '20/02/2024', 'Excelente'),
+        academic_entries.new('Test Subject 5', '6', '0', '20/02/2024', 'S/C'),
+        academic_entries.new('Failed Subject 1', '8', '1', '**********', '***')
+      ]
+    }
+
+    before do
+      allow(PDF::Reader).to receive(:new).with('path').and_return(reader)
+      allow(reader).to receive(:pages).and_return(pdf_mock)
+    end
+
+    it 'returns a list of academic entries' do
+      expect(described_class.process(file).to_a).to all(be_an(academic_entries))
+    end
+
+    it 'parses the text from the pdf file' do
+      expect(described_class.process(file).to_a).to eq(academic_entries_list)
+    end
+  end
+
+  describe 'academic entry' do
+    let(:entry) { academic_entries.new('Test Subject', '10', '0', '20/02/2024', 'Aceptable') }
+    let(:failed_entry) { academic_entries.new('Failed Subject', '10', '1', '**********', '***') }
+
+    it 'has a name' do
+      expect(entry.name).to eq('Test Subject')
+    end
+
+    it 'has a number of credits' do
+      expect(entry.credits).to eq('10')
+    end
+
+    it 'has a number of failures' do
+      expect(entry.number_of_failures).to eq('0')
+    end
+
+    it 'has a date of completion' do
+      expect(entry.date_of_completion).to eq('20/02/2024')
+    end
+
+    it 'has a grade' do
+      expect(entry.grade).to eq('Aceptable')
+    end
+
+    it 'is approved if the grade is not ***' do
+      expect(entry).to be_approved
+    end
+
+    it 'is not approved if the grade is ***' do
+      expect(failed_entry).not_to be_approved
+    end
+  end
+end