Display VTT transcripts in audio/video players

.dassie/config/metadata_profiles/m3_profile.yaml

@@ -942,3 +942,17 @@ properties:
     view:
       render_as: faceted
       html_dl: true
+  transcript_ids:
+    available_on:
+      class:
+        - Hyrax::FileSet
+    indexing:
+      - transcript_ids_ssim
+    data_type: array
+    display_label:
+      default: Transcripts
+    form:
+      display: true
+      primary: false
+    range: http://www.w3.org/2001/XMLSchema#string
+    property_uri: http://vocabulary.samvera.org/ns#transcriptIds

.koppie/config/metadata_profiles/m3_profile.yaml

@@ -914,3 +914,17 @@ properties:
     view:
       render_as: faceted
       html_dl: true
+  transcript_ids:
+    available_on:
+      class:
+        - FileSet
+    indexing:
+      - transcript_ids_ssim
+    data_type: array
+    display_label:
+      default: Transcripts
+    form:
+      display: true
+      primary: false
+    range: http://www.w3.org/2001/XMLSchema#string
+    property_uri: http://vocabulary.samvera.org/ns#transcriptIds

app/assets/stylesheets/hyrax/_viewer.scss

@@ -11,9 +11,17 @@
   left: 0;
 }
 
+// Universal Viewer:
 // Show various footer, header, left and right panels on larger screens only
 @media only screen and (min-width: 640px) {
   .viewer-wrapper {
     height: 640px;
   }
+}
+
+// Clover IIIF Viewer:
+// Increase the height so that thumbnails below the player are visible
+// (for works with multiple audio/video files)
+.viewer-wrapper.clover-viewer-wrapper {
+  height: 775px;
 }

app/controllers/concerns/hyrax/works_controller_behavior.rb

@@ -139,12 +139,15 @@ def inspect_work
     end
 
     def manifest
-      headers['Access-Control-Allow-Origin'] = '*'
+      locale = params[:locale] || current_user&.preferred_locale || I18n.default_locale
+      I18n.with_locale(locale) do
+        headers['Access-Control-Allow-Origin'] = '*'
 
-      json = iiif_manifest_builder.manifest_for(presenter: iiif_manifest_presenter)
+        json = iiif_manifest_builder.manifest_for(presenter: iiif_manifest_presenter)
 
-      respond_to do |wants|
-        wants.any { render json: json }
+        respond_to do |wants|
+          wants.any { render json: json }
+        end
       end
     end
 

app/controllers/hyrax/transcripts_controller.rb

@@ -0,0 +1,31 @@
+# frozen_string_literal: true
+
+module Hyrax
+  class TranscriptsController < DownloadsController
+    def show
+      # Using the extracted text from the index is blocked
+      # by https://github.com/samvera/hyrax/issues/7410, so we
+      # need to get the original file instead.
+      file_metadata = find_file_metadata(file_set: Hyrax.query_service.find_by(id: params.require(:id)))
+      file = Hyrax.storage_adapter.find_by(id: file_metadata.file_identifier)
+
+      prepare_file_headers_valkyrie(metadata: file_metadata, file: file)
+      response.headers['Access-Control-Allow-Origin'] = '*'
+      send_file file.disk_path, data_options(file_metadata)
+    end
+
+    private
+
+    def disposition
+      'inline'
+    end
+
+    def data_options(file_metadata)
+      {
+        type: "#{file_metadata.mime_type}; charset=utf-8",
+        filename: file_metadata.original_filename,
+        disposition: disposition
+      }
+    end
+  end
+end

app/forms/concerns/hyrax/transcripts_behavior.rb

@@ -0,0 +1,40 @@
+# frozen_string_literal: true
+module Hyrax
+  module TranscriptsBehavior
+    extend ActiveSupport::Concern
+
+    class_methods do
+      def available_transcripts(parent:, current_ability:)
+         member_ids = Hyrax.custom_queries.find_child_file_set_ids(resource: parent)
+         Hyrax::SolrQueryService.new
+                                # Cast Valkyrie::IDs to strings
+                                .with_ids(ids: member_ids.map(&:to_s).to_a)
+                                .accessible_by(ability: current_ability, action: :edit)
+                                .solr_documents(
+                                  # Using "has_model_ssim:*FileSet" in fq will return both FileSet
+                                  # and Hyrax::FileSet documents. In test mode, Koppie and Sirenia 
+                                  # index file sets with has_model_ssim:Hyrax::FileSet. 
+                                  # But in dev mode, they index file sets with 
+                                  # has_model_ssim:FileSet instead. This query covers both cases.
+                                  fq: [mime_type_filter_query.to_s, "has_model_ssim:*FileSet"],
+                                  fl: "id,title_tesim",
+                                  rows: 1000
+                                )
+      end
+
+      private
+
+      def mime_type_filter_query
+        valid_mime_types.map { |type| "mime_type_ssi:\"#{type}\"" }.join(" OR ")
+      end
+
+      # According to IIIF, .srt and .ttml are also acceptable but may
+      # not be supported by viewers. Clover and Ramp are confirmed to work
+      # with .vtt. (https://iiif.io/api/cookbook/recipe/0219-using-caption-file/).
+      # When Hyrax supports Ramp, we may want to add "text/plain" (.srt) to this list.
+      def valid_mime_types
+        ["text/vtt"]
+      end
+    end
+  end
+end

app/forms/hyrax/forms/file_set_edit_form.rb

@@ -12,7 +12,7 @@ class FileSetEditForm
 
     self.terms = [:resource_type, :title, :creator, :contributor, :description,
                   :keyword, :license, :publisher, :date_created, :subject, :language,
-                  :identifier, :based_near, :related_url,
+                  :identifier, :based_near, :related_url, :transcript_ids,
                   :visibility_during_embargo, :visibility_after_embargo, :embargo_release_date,
                   :visibility_during_lease, :visibility_after_lease, :lease_expiration_date,
                   :visibility]

app/forms/hyrax/forms/file_set_form.rb

@@ -14,6 +14,7 @@ class FileSetForm < Hyrax::Forms::ResourceForm
       include Hyrax::ContainedInWorksBehavior
       include Hyrax::LeaseabilityBehavior
       include Hyrax::PermissionBehavior
+      include Hyrax::TranscriptsBehavior
 
       property :representative_id, type: Valkyrie::Types::String, writeable: false
       property :thumbnail_id, type: Valkyrie::Types::String, writeable: false

app/helpers/hyrax/file_set_form_helper.rb

@@ -0,0 +1,24 @@
+# frozen_string_literal: true
+
+module Hyrax
+  module FileSetFormHelper
+    def render_transcript_ids_field?(file_set)
+      return unless file_set.persisted?
+      return if @parent.nil?
+      case file_set
+      when ActiveFedora::Base
+        file_set.video? || file_set.audio?
+      when Valkyrie::Resource
+        service = Hyrax::FileSetTypeService.new(file_set: file_set)
+        service.video? || service.audio?
+      end
+    end
+
+    def transcript_ids_select_options
+      options = Forms::FileSetForm.available_transcripts(parent: @parent, current_ability: current_ability)
+      options.each_with_object({}) do |doc, hash|
+        hash[doc.title_or_label] = doc.id.to_s
+      end
+    end
+  end
+end

app/helpers/hyrax/hyrax_helper_behavior.rb

@@ -21,6 +21,7 @@ module HyraxHelperBehavior
     include Hyrax::FacetsHelper
     include Hyrax::AttributesHelper
     include Hyrax::WorksHelper
+    include Hyrax::FileSetFormHelper
 
     ##
     # @return [Array<String>] the list of admin sets available for creating works for this user

app/indexers/hyrax/file_set_indexer.rb

@@ -9,6 +9,7 @@ def generate_solr_document # rubocop:disable Metrics/AbcSize, Metrics/MethodLeng
       super.tap do |solr_doc|
         solr_doc['hasRelatedMediaFragment_ssim'] = object.representative_id
         solr_doc['hasRelatedImage_ssim'] = object.thumbnail_id
+        solr_doc['transcript_ids_ssim'] = object.transcript_ids
         # Label is the actual file name. It's not editable by the user.
         solr_doc['label_tesim'] = object.label
         solr_doc['label_ssi']   = object.label

app/indexers/hyrax/indexers/file_set_indexer.rb

@@ -24,6 +24,7 @@ def to_solr # rubocop:disable Metrics/AbcSize, Metrics/CyclomaticComplexity, Met
           solr_doc['extracted_text_id_ssi']        = resource.extracted_text_id.to_s
           solr_doc['hasRelatedMediaFragment_ssim'] = resource.representative_id.to_s
           solr_doc['hasRelatedImage_ssim']         = resource.thumbnail_id.to_s
+          solr_doc['transcript_ids_ssim']          = resource.transcript_ids&.map(&:to_s)
 
           index_lease(solr_doc)
           index_embargo(solr_doc)

app/models/concerns/hyrax/file_set/transcripts.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+module Hyrax
+  class FileSet
+    module Transcripts
+      extend ActiveSupport::Concern
+
+      included do
+        if Hyrax.config.file_set_include_metadata?
+          property :transcript_ids, predicate: ::RDF::URI.new('http://vocabulary.samvera.org/ns#transcriptIds'), multiple: true do |index|
+            index.as :stored_sortable
+          end
+        end
+      end
+    end
+  end
+end

app/models/concerns/hyrax/file_set_behavior.rb

@@ -14,6 +14,7 @@ module FileSetBehavior
     include Hyrax::FileSet::Indexing
     include Hyrax::FileSet::BelongsToWorks
     include Hyrax::FileSet::Querying
+    include Hyrax::FileSet::Transcripts
     include HumanReadableType
     include CoreMetadata
     include Hyrax::BasicMetadata

app/models/concerns/hyrax/solr_document_behavior.rb

@@ -12,6 +12,8 @@ module Hyrax
   #   end
   #
   # @see https://github.com/projectblacklight/blacklight/wiki/Understanding-Rails-and-Blacklight#models
+
+  # rubocop:disable Metrics/ModuleLength
   module SolrDocumentBehavior
     ModelWrapper = ActiveFedoraDummyModel # alias for backward compatibility
 
@@ -164,10 +166,15 @@ def flexible?
       schema_version.present?
     end
 
+    def transcript_ids
+      self['transcript_ids_ssim']
+    end
+
     private
 
     def model_classifier(classifier)
       classifier || ActiveFedora.model_mapper
     end
   end
+  # rubocop:enable Metrics/ModuleLength
 end

app/presenters/hyrax/annotates_content.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+module Hyrax
+  module AnnotatesContent
+    extend ActiveSupport::Concern
+
+    include DisplaysTranscripts
+
+    def annotation_content
+      transcription_content if video? || audio?
+    end
+
+    private
+
+    def transcription_content
+      transcripts.map do |doc|
+        options = {
+          type: 'Text',
+          motivation: 'supplementing',
+          body_id: transcript_url(doc, host: hostname, file_ext: file_ext(doc.mime_type)),
+          format: doc.mime_type,
+          label: doc.title_or_label
+        }
+        options[:language] = language_code(doc.language) if language_code(doc.language)
+        IIIFManifest::V3::AnnotationContent.new(**options)
+      end
+    end
+
+    # If you change the accepted mime types in Hyrax::TranscriptsBehavior,
+    # you may also want to override this method
+    def file_ext(_mime_type)
+      "vtt"
+    end
+  end
+end

app/presenters/hyrax/displays_transcripts.rb

@@ -0,0 +1,59 @@
+# frozen_string_literal: true
+module Hyrax
+  module DisplaysTranscripts
+    extend ActiveSupport::Concern
+
+    # @return [Array<SolrDocument>] the solr documents represented by
+    # the audio/video file set's transcript_ids
+    def transcripts
+      return [] if transcript_ids.blank?
+      @transcripts ||= begin
+                          results = Hyrax::SolrQueryService.new
+                                                           .accessible_by(
+                                                             ability: (try(:current_ability) || ability),
+                                                             action: :read
+                                                           )
+                                                           .with_ids(ids: transcript_ids)
+                                                           .solr_documents
+                          sort_transcripts_by_language(results)
+                        end
+    end
+
+    def transcript_url(document, host: request.base_url, file_ext: "vtt")
+      Hyrax::Engine.routes.url_helpers.transcript_url(document.id, host: host, file_ext: file_ext)
+    end
+
+    # Try our best to convert language field to an ISO 639-1 code for use in the IIIF manifest.
+    # @param [Array<String>] - a solr document's language field. Parseable values include an ISO 639-1 code,
+    #                          an ISO 639-3 code, or the English name for a language
+    #                          Examples: https://github.com/scsmith/language_list#examples
+    # @return [String or NilClass] - the 2-letter code, or nil if no value or value is unparseable
+    def language_code(language)
+      return if language.empty?
+      value = language.first
+      if URI.parse(value).scheme
+        # This is probably a Library of Congress languages URI
+        # like http://id.loc.gov/vocabulary/iso639-3/eng, which can
+        # be configured with the Questioning Authority gem.
+        # Try to extract the code from the URI.
+        LanguageList::LanguageInfo.find(value.split("/").last).try(:iso_639_1)
+      else
+        # Otherwise, assume it is a language code or name and try
+        # to convert it to a 2-letter code
+        LanguageList::LanguageInfo.find(value).try(:iso_639_1)
+      end
+    end
+
+    private
+
+    def sort_transcripts_by_language(results)
+      current_locale = I18n.locale.to_s
+
+      # Sort alphabetically by language code
+      sorted = results.sort_by { |doc| language_code(doc.language) || '' }
+
+      # Move current locale to front
+      sorted.partition { |doc| language_code(doc.language) == current_locale }.flatten
+    end
+  end
+end

app/presenters/hyrax/file_set_presenter.rb

@@ -7,6 +7,7 @@ class FileSetPresenter
     include WithEvents
     include DisplaysImage
     include MissingMethodBehavior
+    include DisplaysTranscripts
 
     attr_accessor :solr_document, :current_ability, :request
 

app/presenters/hyrax/iiif_manifest_presenter.rb

@@ -129,6 +129,21 @@ def sequence_rendering
       end
     end
 
+    ##
+    # Provides a link to the work page as the homepage for the object
+    # represented by the IIIF manifest (see
+    # https://iiif.io/api/cookbook/recipe/0047-homepage/).
+    # This can be helpful if the IIIF manifest is reused on an external site.
+    # @return [Array<Hash{String => String}>]
+    def homepage
+      [{
+        'id' => Rails.application.routes.url_helpers.polymorphic_url(model, host: hostname),
+        'type' => 'Text',
+        'format' => 'text/html',
+        'label' => { 'none' => [Array(title).first || ''] }
+      }]
+    end
+
     ##
     # @return [Boolean]
     def work?
@@ -189,6 +204,7 @@ class DisplayImagePresenter < Draper::Decorator
 
       include Hyrax::DisplaysImage
       include Hyrax::DisplaysContent
+      include Hyrax::AnnotatesContent
 
       ##
       # @!attribute [w] ability