bulkrax 2.1.1 → 2.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a35c9f6307c21a9933950a3d383ab04e5a49e15b9980d76f6cfb52a5378f5dd0
-  data.tar.gz: d5a58eeb2b755c68e6c66103afb5dbc649205aed73b2d85167246ca912bb07bf
+  metadata.gz: 9f7b2dfc04adfdc046ad673018f94058ee54ab76a2975d8f6bc6d0c6eff8efb1
+  data.tar.gz: c21771f67a5d61991fc633423b5e98eb58c85f35e15f3a6b6908d87d270a0881
 SHA512:
-  metadata.gz: d01b9ecd45171f2b20a5c33605fafe645b7c389a141ed70b41a04ecb7bcf1d1f1c4f430ea50fda7d7ef702fd12123cfd904868ba6468a306a41eca5643061e45
-  data.tar.gz: 943eb873c86e40adf96cd7b0badb1ccce719f088d01aada4e18df90ec5a4f4df5b5ebfda5bfe6f74943c6fa371632937a0918f6aed70a4e14a75bcef0b7eaa0b
+  metadata.gz: 4b9b1a69316eb8d9338d90da68d0c8afed8f0a09daa4a4ad6a02395ee4c2ca81ac480d220e96b1a5755bdfbc6b30beef5addfdaef8a34316106ad932192a5bbc
+  data.tar.gz: 316b35cf8dec3d5a0e190acef8bb58c9ed6b571585e6da6aed741cf6c2d623cf6fe26c5303d65f07cb3f2345f1ee155e1e247d345cbad61901978ffd4fa34b83

data/app/models/bulkrax/csv_file_set_entry.rb

@@ -12,7 +12,7 @@ module Bulkrax
 
         parsed_metadata['file'][i] = path_to_file
       end
-      raise ::StandardError, 'one or more file paths are invalid' unless parsed_metadata['file'].map { |file_path| ::File.file?(file_path) }.all?
+      raise ::StandardError, "one or more file paths are invalid: #{parsed_metadata['file'].join(', ')}" unless parsed_metadata['file'].map { |file_path| ::File.file?(file_path) }.all?
 
       parsed_metadata['file']
     end

data/app/models/concerns/bulkrax/download_behavior.rb

@@ -30,7 +30,7 @@ module Bulkrax
 
     # Create some headers for the datastream
     def content_options
-      { disposition: 'inline', type: download_content_type, filename: file_name }
+      { disposition: 'attachment', type: download_content_type, filename: file_name }
     end
 
     # render an HTTP HEAD response

data/app/parsers/bulkrax/csv_parser.rb

@@ -177,40 +177,74 @@ module Bulkrax
     end
 
     def current_work_ids
+      ActiveSupport::Deprication.warn('Bulkrax::CsvParser#current_work_ids will be replaced with #current_record_ids in version 3.0')
+      current_record_ids
+    end
+
+    def current_record_ids
+      @work_ids = []
+      @collection_ids = []
+      @file_set_ids = []
+
       case importerexporter.export_from
       when 'all'
-        ActiveFedora::SolrService.query("has_model_ssim:(#{Hyrax.config.curation_concerns.join(' OR ')}) #{extra_filters}", rows: 2_147_483_647).map(&:id)
+        @work_ids = ActiveFedora::SolrService.query("has_model_ssim:(#{Hyrax.config.curation_concerns.join(' OR ')}) #{extra_filters}", rows: 2_147_483_647).map(&:id)
+        @collection_ids = ActiveFedora::SolrService.query("has_model_ssim:Collection #{extra_filters}", rows: 2_147_483_647).map(&:id)
+        @file_set_ids = ActiveFedora::SolrService.query("has_model_ssim:FileSet #{extra_filters}", rows: 2_147_483_647).map(&:id)
       when 'collection'
-        ActiveFedora::SolrService.query("member_of_collection_ids_ssim:#{importerexporter.export_source + extra_filters}", rows: 2_000_000_000).map(&:id)
+        @work_ids = ActiveFedora::SolrService.query("member_of_collection_ids_ssim:#{importerexporter.export_source + extra_filters}", rows: 2_000_000_000).map(&:id)
       when 'worktype'
-        ActiveFedora::SolrService.query("has_model_ssim:#{importerexporter.export_source + extra_filters}", rows: 2_000_000_000).map(&:id)
+        @work_ids = ActiveFedora::SolrService.query("has_model_ssim:#{importerexporter.export_source + extra_filters}", rows: 2_000_000_000).map(&:id)
       when 'importer'
-        entry_ids = Bulkrax::Importer.find(importerexporter.export_source).entries.pluck(:id)
-        complete_statuses = Bulkrax::Status.latest_by_statusable
-                                           .includes(:statusable)
-                                           .where('bulkrax_statuses.statusable_id IN (?) AND bulkrax_statuses.statusable_type = ? AND status_message = ?', entry_ids, 'Bulkrax::Entry', 'Complete')
+        set_ids_for_exporting_from_importer
+      end
+
+      @work_ids + @collection_ids + @file_set_ids
+    end
+
+    # Set the following instance variables: @work_ids, @collection_ids, @file_set_ids
+    # @see #current_record_ids
+    def set_ids_for_exporting_from_importer
+      entry_ids = Importer.find(importerexporter.export_source).entries.pluck(:id)
+      complete_statuses = Status.latest_by_statusable
+                                .includes(:statusable)
+                                .where('bulkrax_statuses.statusable_id IN (?) AND bulkrax_statuses.statusable_type = ? AND status_message = ?', entry_ids, 'Bulkrax::Entry', 'Complete')
 
-        complete_entry_identifiers = complete_statuses.map { |s| s.statusable&.identifier&.gsub(':', '\:') }
-        extra_filters = extra_filters.presence || '*:*'
+      complete_entry_identifiers = complete_statuses.map { |s| s.statusable&.identifier&.gsub(':', '\:') }
+      extra_filters = extra_filters.presence || '*:*'
 
-        ActiveFedora::SolrService.get(
+      { :@work_ids => ::Hyrax.config.curation_concerns, :@collection_ids => [::Collection], :@file_set_ids => [::FileSet] }.each do |instance_var, models_to_search|
+        instance_variable_set(instance_var, ActiveFedora::SolrService.get(
           extra_filters.to_s,
-          fq: "#{work_identifier}_sim:(#{complete_entry_identifiers.join(' OR ')})",
+          fq: [
+            "#{work_identifier}_sim:(#{complete_entry_identifiers.join(' OR ')})",
+            "has_model_ssim:(#{models_to_search.join(' OR ')})"
+          ],
           fl: 'id',
           rows: 2_000_000_000
-        )['response']['docs'].map { |obj| obj['id'] }
+        )['response']['docs'].map { |obj| obj['id'] })
       end
     end
 
     def create_new_entries
-      current_work_ids.each_with_index do |wid, index|
+      current_record_ids.each_with_index do |id, index|
         break if limit_reached?(limit, index)
-        new_entry = find_or_create_entry(entry_class, wid, 'Bulkrax::Exporter')
+
+        this_entry_class = if @collection_ids.include?(id)
+                             collection_entry_class
+                           elsif @file_set_ids.include?(id)
+                             file_set_entry_class
+                           else
+                             entry_class
+                           end
+        new_entry = find_or_create_entry(this_entry_class, id, 'Bulkrax::Exporter')
+
         begin
-          entry = Bulkrax::ExportWorkJob.perform_now(new_entry.id, current_run.id)
+          entry = ExportWorkJob.perform_now(new_entry.id, current_run.id)
         rescue => e
           Rails.logger.info("#{e.message} was detected during export")
         end
+
         self.headers |= entry.parsed_metadata.keys if entry
       end
     end
@@ -267,7 +301,7 @@ module Bulkrax
 
     def write_files
       CSV.open(setup_export_file, "w", headers: export_headers, write_headers: true) do |csv|
-        importerexporter.entries.where(identifier: current_work_ids)[0..limit || total].each do |e|
+        importerexporter.entries.where(identifier: current_record_ids)[0..limit || total].each do |e|
           csv << e.parsed_metadata
         end
       end

data/lib/bulkrax/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Bulkrax
-  VERSION = '2.1.1'
+  VERSION = '2.2.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bulkrax
 version: !ruby/object:Gem::Version
-  version: 2.1.1
+  version: 2.2.0
 platform: ruby
 authors:
 - Rob Kaufman
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-02-03 00:00:00.000000000 Z
+date: 2022-02-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rails