🎁 Download Cloud Files later

This commit will bring in changes from `5.3.1-british_library` to move
the download of cloud files to a background job.

app/jobs/bulkrax/download_cloud_file_job.rb

@@ -1,18 +1,31 @@
 # frozen_string_literal: true
-
 module Bulkrax
   class DownloadCloudFileJob < ApplicationJob
     queue_as Bulkrax.config.ingest_queue_name
 
+    include ActionView::Helpers::NumberHelper
+
     # Retrieve cloud file and write to the imports directory
     # Note: if using the file system, the mounted directory in
     #   browse_everything MUST be shared by web and worker servers
     def perform(file, target_file)
       retriever = BrowseEverything::Retriever.new
+      last_logged_time = Time.zone.now
+      log_interval = 3.seconds
+
       retriever.download(file, target_file) do |filename, retrieved, total|
-        # The block is still useful for showing progress, but the
-        # first argument is the filename instead of a chunk of data.
+        percentage = (retrieved.to_f / total.to_f) * 100
+        current_time = Time.zone.now
+
+        if (current_time - last_logged_time) >= log_interval
+          # Use number_to_human_size for formatting
+          readable_retrieved = number_to_human_size(retrieved)
+          readable_total = number_to_human_size(total)
+          Rails.logger.info "Downloaded #{readable_retrieved} of #{readable_total}, #{filename}: #{percentage.round}% complete"
+          last_logged_time = current_time
+        end
       end
+      Rails.logger.info "Download complete: #{file['url']} to #{target_file}"
     end
   end
 end

app/parsers/bulkrax/csv_parser.rb

@@ -205,7 +205,7 @@ def retrieve_cloud_files(files, importer)
         target_files << target_file
         # Now because we want the files in place before the importer runs
         # Problematic for a large upload
-        Bulkrax::DownloadCloudFileJob.perform_now(file, target_file)
+        Bulkrax::DownloadCloudFileJob.perform_later(file, target_file)
       end
       importer[:parser_fields]['original_file_paths'] = target_files
       return nil