Add report emails to preservation workflow

Why these changes are being introduced:

We found a bug in the preservation workflow last month that we
might have identified sooner if the preservation submission job
triggered a report email.

Relevant ticket(s):

https://mitlibraries.atlassian.net/browse/ETD-651

How this addresses that need:

* Removes the Preservation Submission Prep Job
* Updates the Preservation Submission Job to accept an array of theses
* Adds a preservation results email to the Report Mailer that is
enqueued on completion of the Preservation Submission Job
* Updates the preservation rake task to convert the input thesis into
an array, so it will continue to work

Side effects of this change:

We not sure why we implemented the 'prep' job pattern: passing in
an array of theses so the actual job takes a single thesis as a
parameter. There is some risk in removing this job, since we don't
remember why it exists in the first place.

app/jobs/dspace_publication_results_job.rb

@@ -19,7 +19,7 @@ def perform
       results[:errors] << "Error reading from SQS queue: #{e}"
     end
 
-    PreservationSubmissionPrepJob.perform_later(results[:preservation_ready]) if results[:preservation_ready].any?
+    PreservationSubmissionJob.perform_later(results[:preservation_ready]) if results[:preservation_ready].any?
     MarcExportJob.perform_later(results[:marc_exports]) if results[:marc_exports].any?
     ReportMailer.publication_results_email(results).deliver_now if results[:total].positive? ||
                                                                    results[:errors].any?

app/jobs/preservation_submission_job.rb

@@ -1,15 +1,23 @@
 class PreservationSubmissionJob < ActiveJob::Base
   queue_as :default
 
-  def perform(thesis)
-    Rails.logger.info("Thesis #{thesis.id} is now being prepared for preservation")
-    sip = thesis.submission_information_packages.create
-    preserve_sip(sip)
-    Rails.logger.info("Thesis #{thesis.id} has been sent to preservation")
-  rescue StandardError, Aws::Errors => e
-    Rails.logger.info("Thesis #{thesis.id} could not be preserved: #{e}")
-    sip.preservation_status = 'error'
-    sip.save
+  def perform(theses)
+    Rails.logger.info("Preparing to send #{theses.count} theses to preservation")
+    results = { total: theses.count, processed: 0, errors: [] }
+    theses.each do |thesis|
+      Rails.logger.info("Thesis #{thesis.id} is now being prepared for preservation")
+      sip = thesis.submission_information_packages.create
+      preserve_sip(sip)
+      Rails.logger.info("Thesis #{thesis.id} has been sent to preservation")
+      results[:processed] += 1
+    rescue StandardError, Aws::Errors => e
+      preservation_error = "Thesis #{thesis.id} could not be preserved: #{e}"
+      Rails.logger.info(preservation_error)
+      sip.preservation_status = 'error'
+      sip.save
+      results[:errors] << preservation_error
+    end
+    ReportMailer.preservation_results_email(results).deliver_now if results[:total].positive?
   end
 
   private

app/mailers/report_mailer.rb

@@ -19,4 +19,14 @@ def publication_results_email(results)
          cc: ENV['MAINTAINER_EMAIL'],
          subject: 'DSpace publication results summary')
   end
+
+  def preservation_results_email(results)
+    return unless ENV.fetch('DISABLE_ALL_EMAIL', 'true') == 'false' # allows PR builds to disable emails
+
+    @results = results
+    mail(from: "MIT Libraries <#{ENV['ETD_APP_EMAIL']}>",
+         to: ENV['THESIS_ADMIN_EMAIL'],
+         cc: ENV['MAINTAINER_EMAIL'],
+         subject: 'Archivematica preservation submission results summary')
+  end
 end

app/views/report_mailer/preservation_results_email.html.erb

@@ -0,0 +1,21 @@
+<p>Hello,</p>
+
+<p>Below is a report of the Archivematica preservation submission job.</p>
+
+<p>Summary of results:</p>
+
+<ul>
+  <li>Total theses queued for preservation: <%= @results[:total] %></li>
+  <li>Total theses sent to preservation: <%= @results[:processed] %></li>
+  <li>Errors found: <%= @results[:errors].count %></li>
+</ul>
+
+<% if @results[:errors].any? %>
+  <p>The following errors require processor attention:</p>
+
+  <ul>
+    <% @results[:errors].each do |e| %>
+      <li><%= e %></li>
+    <% end %>
+  </ul>
+<% end %>

lib/tasks/preservation.rake

@@ -1,14 +1,15 @@
 namespace :preservation do
   desc 'Sends a single thesis to preservation'
   task :preserve_thesis_by_id, [:thesis_id] => :environment do |_t, args|
+    return Rails.logger.info('.')
     if args.thesis_id
       Rails.logger.info("Attempting to send #{args.thesis_id} to preservation...")
       thesis = Thesis.find(args.thesis_id)
 
       # Only published theses may be sent to preservation. We already check for this in SubmissionInformationPackage
       # validations, but double-checking here to save potential confusion.
       if thesis.publication_status == 'Published'
-        PreservationSubmissionJob.perform_now(thesis)
+        PreservationSubmissionJob.perform_now([thesis])
       else
         Rails.logger.info("Thesis status of #{thesis.publication_status} cannot be preserved.")
       end

test/jobs/dspace_publication_results_job_test.rb

@@ -182,7 +182,7 @@ def teardown
   end
 
   test 'enqueues preservation submission prep job' do
-    assert_enqueued_with(job: PreservationSubmissionPrepJob) do
+    assert_enqueued_with(job: PreservationSubmissionJob) do
       DspacePublicationResultsJob.perform_now
     end
   end

test/jobs/preservation_submission_job_test.rb

@@ -16,38 +16,50 @@ def setup_thesis
     thesis
   end
 
+  test 'sends report emails' do
+    ClimateControl.modify DISABLE_ALL_EMAIL: 'false' do
+      assert_difference('ActionMailer::Base.deliveries.size', 1) do
+        PreservationSubmissionJob.perform_now([setup_thesis])
+      end
+    end
+  end
+
   test 'creates a SIP' do
     thesis = setup_thesis
     assert_equal 0, thesis.submission_information_packages.count
 
-    PreservationSubmissionJob.perform_now(thesis)
+    PreservationSubmissionJob.perform_now([thesis])
     assert_equal 1, thesis.submission_information_packages.count
   end
 
+  test 'creates multiple SIPs' do
+    theses = [setup_thesis, theses(:published)]
+  end
+
   test 'updates preservation_status to "preserved" after successfully processing a thesis' do
     thesis = setup_thesis
-    PreservationSubmissionJob.perform_now(thesis)
+    PreservationSubmissionJob.perform_now([thesis])
     assert_equal 'preserved', thesis.submission_information_packages.last.preservation_status
   end
 
   test 'updates preserved_at to the current time after successfully processing a thesis' do
     time = DateTime.new.getutc
     Timecop.freeze(time) do
       thesis = setup_thesis
-      PreservationSubmissionJob.perform_now(thesis)
+      PreservationSubmissionJob.perform_now([thesis])
       assert_equal time, thesis.submission_information_packages.last.preserved_at
     end
   end
 
   test 'rescues exceptions by updating preservation_status to "error"' do
     thesis = theses(:one)
-    PreservationSubmissionJob.perform_now(thesis)
+    PreservationSubmissionJob.perform_now([thesis])
     assert_equal 'error', thesis.submission_information_packages.last.preservation_status
   end
 
   test 'does not update preserved_at if the job enters an error state' do
     thesis = theses(:one)
-    PreservationSubmissionJob.perform_now(thesis)
+    PreservationSubmissionJob.perform_now([thesis])
     assert_nil thesis.submission_information_packages.last.preserved_at
   end
 end

test/mailers/report_mailer_test.rb

@@ -43,4 +43,23 @@ class ReportMailerTest < ActionMailer::TestCase
       assert_match 'Couldn&#39;t find Thesis with &#39;id&#39;=9999999999999', email.body.to_s
     end
   end
+
+  test 'sends reports for preservation submission results' do
+    ClimateControl.modify DISABLE_ALL_EMAIL: 'false' do
+      results = { total: 2, processed: 1, errors: ["Couldn't find Thesis with 'id'=9999999999999"] }
+      email = ReportMailer.preservation_results_email(results)
+
+      assert_emails 1 do
+        email.deliver_now
+      end
+
+      assert_equal ['app@example.com'], email.from
+      assert_equal ['test@example.com'], email.to
+      assert_equal 'Archivematica preservation submission results summary', email.subject.to_s
+      assert_match 'Total theses queued for preservation: 2', email.body.to_s
+      assert_match 'Total theses sent to preservation: 1', email.body.to_s
+      assert_match 'Errors found: 1', email.body.to_s
+      assert_match 'Couldn&#39;t find Thesis with &#39;id&#39;=9999999999999', email.body.to_s
+    end
+  end
 end