Merge pull request #200 from scientist-softserv/conditional-iiif-print

🎁   Add conditional PDF split or PDF.js

Gemfile.lock

@@ -43,17 +43,15 @@ GIT
 
 GIT
   remote: https://github.com/scientist-softserv/iiif_print.git
-  revision: 8fdf56e151b5adb7e6aab1cd29d39b74554ed48a
+  revision: 50b2659f4584ac85f468c7fcec56398f6221a412
   branch: main
   specs:
     iiif_print (1.0.0)
-      blacklight_iiif_search (~> 1.0)
-      dry-monads (~> 1.4.0)
-      hyrax (>= 2.5, < 4.0)
+      blacklight_iiif_search (>= 1.0, < 3.0)
+      derivative-rodeo (~> 0.5)
+      hyrax (>= 2.5, < 6)
       nokogiri (>= 1.13.2)
-      rails (~> 5.0)
       rdf-vocab (~> 3.0)
-      reform-rails (= 0.2.3)
 
 GIT
   remote: https://github.com/tawan/active-elastic-job.git
@@ -313,6 +311,15 @@ GEM
     declarative-option (0.1.0)
     deprecation (1.1.0)
       activesupport
+    derivative-rodeo (0.5.2)
+      activesupport (>= 5)
+      aws-sdk-s3
+      aws-sdk-sqs
+      httparty
+      marcel
+      mime-types
+      mini_magick
+      nokogiri
     devise (4.8.1)
       bcrypt (~> 3.0)
       orm_adapter (~> 0.1)
@@ -469,6 +476,9 @@ GEM
     hiredis (0.6.3)
     htmlentities (4.3.4)
     http_logger (0.7.0)
+    httparty (0.21.0)
+      mini_mime (>= 1.0.0)
+      multi_xml (>= 0.5.2)
     httpclient (2.8.3)
     hydra-access-controls (11.0.7)
       active-fedora (>= 10.0.0)

app/helpers/iiif_print_helper.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module IiifPrintHelper
+  include IiifPrint::IiifPrintHelperBehavior
+end

app/models/concerns/pdf_behavior.rb

@@ -25,6 +25,11 @@ module PdfBehavior
              end
 
     after_initialize :set_default_show_pdf_viewer, :set_default_show_pdf_download_button
+
+    include IiifPrint.model_configuration(
+      pdf_split_child_model: GenericWork,
+      pdf_splitter_service: IiifPrint::TenantConfig::PdfSplitter
+    )
   end
 
   private

app/presenters/hyku/work_show_presenter.rb

@@ -11,6 +11,12 @@ class WorkShowPresenter < Hyrax::WorkShowPresenter
     include Hyrax::IiifAv::DisplaysIiifAv
     Hyrax::MemberPresenterFactory.file_presenter_class = Hyrax::IiifAv::IiifFileSetPresenter
 
+    ##
+    # NOTE: IIIF Print prepends a IiifPrint::WorkShowPresenterDecorator to Hyrax::WorkShowPresenter
+    # However, with the above `include Hyrax::IiifAv::DisplaysIiifAv` we obliterate that logic.  So
+    # we need to re-introduce that logic.
+    prepend IiifPrint::TenantConfig::WorkShowPresenterDecorator
+
     delegate :title_or_label, :extent, :show_pdf_viewer, :show_pdf_download_button, to: :solr_document
 
     # OVERRIDE Hyrax v2.9.0 here to make featured collections work
@@ -58,15 +64,6 @@ def user_can_feature_collection?
     end
     # End Featured Collections Methods
 
-    # @return [Boolean] render a IIIF viewer
-    def iiif_viewer?
-      Hyrax.config.iiif_image_server? &&
-        representative_id.present? &&
-        representative_presenter.present? &&
-        iiif_media? &&
-        members_include_viewable?
-    end
-
     def video_embed_viewer?
       extract_video_embed_presence
     end
@@ -96,16 +93,6 @@ def extract_video_embed_presence
         solr_document[:video_embed_tesim]&.all?(&:present?)
       end
 
-      def iiif_media?(presenter: representative_presenter)
-        presenter.image? || presenter.video? || presenter.audio?
-      end
-
-      def members_include_viewable?
-        file_set_presenters.any? do |presenter|
-          iiif_media?(presenter: presenter) && current_ability.can?(:read, presenter.id)
-        end
-      end
-
       def extract_from_identifier(rgx)
         if solr_document['identifier_tesim'].present?
           ref = solr_document['identifier_tesim'].map do |str|

app/services/iiif_print/tenant_config.rb

@@ -0,0 +1,202 @@
+# frozen_string_literal: true
+
+# rubocop:disable Metrics/LineLength
+module IiifPrint
+  ##
+  # This module encapsulates the logic for whether or not we'll use the IIIF Print services for the
+  # current tenant/account.  The IIIF Print services does the following:
+  #
+  # - Skipping IIIF Print based derivative generation
+  # - Skipping PDF Splitting
+  # - Ignoring showing PDFs in the UV
+  #
+  # @note I am specifically isolating as much of this code into one module as possible, so that it
+  #       it is hopefully easier to understand the configuration requirements and scope to this
+  #       change.  At some point, this might make sense to bring into IIIF Print directly.
+  #
+  # @see https://github.com/scientist-softserv/palni-palci/issues/656 palni-palci#656
+  # @see https://github.com/scientist-softserv/palni-palci/issues/657 palni-palci#657
+  # @see https://github.com/scientist-softserv/palni-palci/issues/658 palni-palci#658
+  # @see https://github.com/scientist-softserv/palni-palci/issues/659 palni-palci#659
+  module TenantConfig
+    ##
+    # When we were not planning on calling the underlying IiifPrint service but did due to some kind
+    # of faulty programming logic.
+    #
+    # @note This is raised as a guard to say "Hey, you thought you weren't using IIIF Print but your
+    #       code's logic paths say otherwise."
+    class LeakyAbstractionError < StandardError
+      def initialize(klass:, method_name:)
+        super("Called #{klass}##{method_name} when we had said that #{klass} was not valid because we weren't using IIIF Print")
+      end
+    end
+
+    ##
+    # If the default PDF viewer (PDF.js) is enabled, this method returns false,
+    # meaning the application should not use IIIF Print. If the default viewer is
+    # disabled, this method returns true, meaning the application should use IIIF Print.
+    def self.use_iiif_print?
+      !::Flipflop.default_pdf_viewer?
+    end
+
+    ##
+    # This class implements the interface of the Hyrax::DerivativeService.  It is responsible for
+    # negotiating whether or not the DerivativeService is "on" for the current tenant.
+    #
+    # @see https://github.com/samvera/hyrax/blob/08ef6c9a4fac489972eea9be53403e173f4ffb29/app/services/hyrax/derivative_service.rb Hyrax::DerivativeService
+    class DerivativeService
+      ##
+      # This allows you to specify the IIIF derivative service to use when the tenant has chosen to
+      # use IIIF Print for processing PDFs.
+      #
+      # If you are using the DerivativeRodeo, you'd specify something else.
+      class_attribute :iiif_service_class, default: ::IiifPrint::PluggableDerivativeService
+
+      def initialize(file_set)
+        @file_set = file_set
+      end
+
+      delegate :use_iiif_print?, to: TenantConfig
+
+      def valid?
+        return false unless use_iiif_print?
+
+        iiif_print_service_instance.valid?
+      end
+
+      %i[create_derivatives cleanup_derivatives].each do |method_name|
+        define_method(method_name) do |*args|
+          raise LeakyAbstractionError.new(klass: self.class, method_name: method_name) unless use_iiif_print?
+
+          iiif_print_service_instance.public_send(method_name, *args)
+        end
+      end
+
+      ##
+      # @api private
+      #
+      # @note Public to ease testing.
+      def iiif_print_service_instance
+        @iiif_print_service_instance ||= iiif_service_class.new(@file_set)
+      end
+    end
+
+    ##
+    # This is the pdf_splitter_service that will be used.  If the tenant does not allow PDF splitting
+    # we will return an empty array.
+    #
+    # @example
+    #
+    #  class MyWork
+    #    include IiifPrint.model_configuration(
+    #      pdf_split_child_model: Attachment,
+    #      pdf_splitter_service: IiifPrint::TenantConfig::PdfSplitter,
+    #      derivative_service_plugins: [ IiifPrint::TextExtractionDerivativeService ])
+    #  end
+    #
+    # @see https://github.com/scientist-softserv/iiif_print/blob/9e7837ce4bd08bf8fff9126455d0e0e2602f6018/lib/iiif_print.rb#L86-L138 Documentation for configuring
+    # @see https://github.com/scientist-softserv/adventist-dl/blob/d7676bdac2c672f09b28086d7145b68306978950/app/models/image.rb#L14-L20 Example implementation
+    module PdfSplitter
+      mattr_accessor :iiif_print_splitter
+      self.iiif_print_splitter = ::IiifPrint::SplitPdfs::PagesToJpgsSplitter
+
+      ##
+      # @api public
+      def self.call(*args)
+        return [] unless TenantConfig.use_iiif_print?
+
+        iiif_print_splitter.call(*args)
+      end
+    end
+
+    ##
+    # @see https://github.com/scientist-softserv/iiif_print/blob/9e7837ce4bd08bf8fff9126455d0e0e2602f6018/lib/iiif_print/split_pdfs/child_work_creation_from_pdf_service.rb#L10-L46 Interface of FileSetActor#service
+    module SkipSplittingPdfService
+      ##
+      # @return [Symbol] Always :tenant_does_not_split_pdfs
+      def self.conditionally_enqueue(*_args)
+        :tenant_does_not_split_pdfs
+      end
+    end
+
+    ##
+    # This decorator should ensure that we don't call model configured :pdf_splitter_service as
+    # documented in {TenantConfig::PdfSplitter} and the IIIF Print gem.  It avoids the potentially
+    # expensive conditionally enqueue logic of the super class.
+    #
+    # Why not make an `app/actors/hyrax/actors/file_set_actor_decorator.rb`?  It would be lost in that
+    # it is decorating the decoration of the IIIF Print gem.  Beside, in bringing this here, we have
+    # a relatively singular place for all of the configurations.
+    module FileSetActorDecorator
+      ##
+      # @see https://github.com/scientist-softserv/iiif_print/blob/9e7837ce4bd08bf8fff9126455d0e0e2602f6018/app/actors/iiif_print/actors/file_set_actor_decorator.rb#L33-L35 Method we're overriding
+      def service
+        return TenantConfig::SkipSplittingPdfService unless TenantConfig.use_iiif_print?
+
+        super
+      end
+    end
+
+    ##
+    # OVERRIDE IiifPrint::WorkShowPresenterDecorator
+    # OVERRIDE Hyrax::WorkShowPresenter
+    #
+    # In IiifPrint we overrided #members_include_viewable_image? to query for both file sets and
+    # child works.  (Child works being the pages split off of a PDF)
+    #
+    # In Hyrax::WorkShowPresenter we're only looking at the underlying file_sets.  But IiifPrint
+    # needs to look at multiple places.
+    module WorkShowPresenterDecorator
+      ##
+      # @return [Array<Symbol>] predicate methods (e.g. ending in "?") that reflect the types
+      #         of files we want to consider for showing in the IIIF Viewer.
+      def iiif_media_predicates
+        if TenantConfig.use_iiif_print?
+          %i[image? audio? video? pdf?]
+        else
+          %i[image? audio? video?]
+        end
+      end
+
+      def iiif_media?(presenter: representative_presenter)
+        iiif_media_predicates.any? { |predicate| presenter.try(predicate) || presenter.try(:solr_document).try(predicate) }
+      end
+
+      ##
+      # @return [Boolean] render a IIIF viewer
+      #
+      # OVERRIDE Hyrax::WorkShowPresenter; this override introduces behavior to handle over-rides.
+      def iiif_viewer?
+        Hyrax.config.iiif_image_server? &&
+          representative_id.present? &&
+          representative_presenter.present? &&
+          iiif_media? &&
+          members_include_iiif_viewable?
+      end
+
+      def members_include_iiif_viewable?
+        iiif_presentable_member_presenters.any? do |presenter|
+          iiif_media?(presenter: presenter) && current_ability.can?(:read, presenter.id)
+        end
+      end
+
+      ##
+      # @return [Array<Object>] An array of presenter objects
+      #
+      # In a non-IIIF Print using scenario, we use the file_set_presenters value; that is for
+      # objects that are very specifically file_sets.
+      #
+      # In a IIIF Print using scenario, we use the ill-named 'file_set_ids_ssim', because a
+      # long-standing decision is that this field will have both file_set IDs and child work IDs.
+      def iiif_presentable_member_presenters
+        if TenantConfig.use_iiif_print?
+          presentable_member_ids = Array.wrap(solr_document.try(:file_set_ids) || solr_document.try(:[], 'file_set_ids_ssim'))
+          member_presenters_for(presentable_member_ids)
+        else
+          file_set_presenters
+        end
+      end
+    end
+  end
+end
+# rubocop:enable Metrics/LineLength

config/application.rb

@@ -60,5 +60,21 @@ class Application < Rails::Application
 
       Object.include(AccountSwitch)
     end
+
+    config.after_initialize do
+      ##
+      # The first "#valid?" service is the one that we'll use for generating derivatives.
+      Hyrax::DerivativeService.services = [
+        IiifPrint::TenantConfig::DerivativeService,
+        Hyrax::FileSetDerivativesService
+      ]
+
+      ##
+      # This needs to be in the after initialize so that the IiifPrint gem can do it's decoration.
+      #
+      # @see https://github.com/scientist-softserv/iiif_print/blob/9e7837ce4bd08bf8fff9126455d0e0e2602f6018/lib/iiif_print/engine.rb#L54 Where we do the override.
+      Hyrax::Actors::FileSetActor.prepend(IiifPrint::TenantConfig::FileSetActorDecorator)
+      Hyrax::WorkShowPresenter.prepend(IiifPrint::TenantConfig::WorkShowPresenterDecorator)
+    end
   end
 end

db/migrate/20231128191136_add_model_details_to_iiif_print_pending_relationships.iiif_print.rb

@@ -0,0 +1,8 @@
+# This migration comes from iiif_print (originally 20231110163052)
+class AddModelDetailsToIiifPrintPendingRelationships < ActiveRecord::Migration[5.2]
+  def change
+    add_column :iiif_print_pending_relationships, :parent_model, :string
+    add_column :iiif_print_pending_relationships, :child_model, :string
+    add_column :iiif_print_pending_relationships, :file_id, :string
+  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: 2023_06_08_153601) do
+ActiveRecord::Schema.define(version: 2023_11_28_191136) do
 
   # These are extensions that must be enabled in order to support this database
   enable_extension "plpgsql"
@@ -382,6 +382,9 @@
     t.string "child_order", null: false
     t.datetime "created_at", null: false
     t.datetime "updated_at", null: false
+    t.string "parent_model"
+    t.string "child_model"
+    t.string "file_id"
     t.index ["parent_id"], name: "index_iiif_print_pending_relationships_on_parent_id"
   end
 

docker-compose.bundle.yml

@@ -0,0 +1,9 @@
+# Copy file to docker-compose.override.yml to override docker-compose.yml
+# Only use for local development
+version: '3.8'
+services:
+  web:
+    command: sh -l -c "bundle && bundle exec puma -v -b tcp://0.0.0.0:3000"
+  worker:
+    command: sh -l -c "bundle && bundle exec sidekiq"
+

spec/presenters/concerns/hyrax/iiif_av/displays_content_decorator_spec.rb

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+RSpec.describe Hyrax::IiifAv::DisplaysContentDecorator do
+  # We're prepending the DisplaysContentDecorator to the Hyrax::IiifAv::DisplaysContent
+  describe Hyrax::IiifAv::DisplaysContent do
+    describe '.public_instance_methods' do
+      subject { Hyrax::IiifAv::DisplaysContent.public_instance_methods }
+
+      it { is_expected.to include(:solr_document) }
+      it { is_expected.to include(:current_ability) }
+    end
+  end
+end