Add configuration option to skip_full_text_extract default to false

app/services/hyrax/file_set_derivatives_service.rb

@@ -49,17 +49,15 @@ def supported_mime_types
       def create_pdf_derivatives(filename)
         Hydra::Derivatives::PdfDerivatives.create(filename,
                                                   outputs: [{ label: :thumbnail, format: 'jpg', size: '338x493', url: derivative_url('thumbnail') }])
-        Hydra::Derivatives::FullTextExtract.create(filename,
-                                                   outputs: [{ url: uri, container: "extracted_text" }])
+        extract_full_text(filename, uri)
       end
 
       def create_office_document_derivatives(filename)
         Hydra::Derivatives::DocumentDerivatives.create(filename,
                                                        outputs: [{ label: :thumbnail, format: 'jpg',
                                                                    size: '200x150>',
                                                                    url: derivative_url('thumbnail') }])
-        Hydra::Derivatives::FullTextExtract.create(filename,
-                                                   outputs: [{ url: uri, container: "extracted_text" }])
+        extract_full_text(filename, uri)
       end
 
       def create_audio_derivatives(filename)
@@ -83,5 +81,15 @@ def create_image_derivatives(filename)
       def derivative_path_factory
         Hyrax::DerivativePath
       end
+
+      # Calls the Hydra::Derivates::FulltextExtraction unless the extract_full_text
+      # configuration option is set to false
+      # @param [String] filename of the object to be used for full text extraction
+      # @param [String] uri to the file set (deligated to file_set)
+      def extract_full_text(filename, uri)
+        return unless Hyrax.config.extract_full_text?
+        Hydra::Derivatives::FullTextExtract.create(filename,
+                                                   outputs: [{ url: uri, container: "extracted_text" }])
+      end
   end
 end

lib/generators/hyrax/templates/config/hyrax.rb

@@ -74,6 +74,10 @@
   # Path to the file derivatives creation tool
   # config.libreoffice_path = "soffice"
 
+  # Option to enable/disable full text extraction from PDFs
+  # Default is true, set to false to disable full text extraction
+  # config.extract_full_text = true
+
   # How many seconds back from the current time that we should show by default of the user's activity on the user's dashboard
   # config.activity_to_show_default_seconds_since_now = 24*60*60
 

lib/hyrax/configuration.rb

@@ -373,6 +373,12 @@ def subject_prefix
       @subject_prefix ||= "Contact form:"
     end
 
+    attr_writer :extract_full_text
+    def extract_full_text?
+      return @extract_full_text unless @extract_full_text.nil?
+      @extract_full_text = true
+    end
+
     private
 
       # @param [Symbol, #to_s] model_name - symbol representing the model

spec/lib/hyrax/configuration_spec.rb

@@ -55,4 +55,5 @@
   it { is_expected.to respond_to(:translate_uri_to_id) }
   it { is_expected.to respond_to(:upload_path) }
   it { is_expected.to respond_to(:work_requires_files?) }
+  it { is_expected.to respond_to(:extract_full_text?) }
 end