bulkrax 5.3.0 → 5.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 687e8437db3ceb118fd59fae8d1350379749ec42c60f236833b3b198376281c7
-  data.tar.gz: 9f4af8b8e5eda6b48f8a97c7a34216a41476df44b723e54d623b3db6584edcf8
+  metadata.gz: 4561533e5e3bb65767c53d52be32e51848c0c2c81da51eb15709927b3499234f
+  data.tar.gz: 0c35135671a7536ed858246c4e7793c9b0743aef17caeeadd6e045e44b44200f
 SHA512:
-  metadata.gz: 11c7518861a687b5db06ca319f5c3a0c0d9cc6621f55f17e9bb02bdd83f69fb18093f16235c5bcc06a50864b0acfd9f4c242d93477646ca782fdba62cf9ad1d8
-  data.tar.gz: b3728de99a37f6846e83fd27c54be3c3fccfe03d256296f0a3123311797d7ab8eaa8be7a197de3657532adaadd58dd15fadd6b639158f43d1c77512f258cbfce
+  metadata.gz: 26c5cd6fd88dd94546b906f64762fb02ebdd1a830683202352616a3e347b7efc18900ba293d42ad162df176731bd7ccd7a7962db3180f16fcbbff95d2e577b46
+  data.tar.gz: 1aa71ab730fff3055537c003e02e3ea19696316f07b70e0c86ef8babc964f1b40c4aa2dc84736e841bfba31457ff8c81f98e4468eb95b174dd6c06522d2dc733

data/app/factories/bulkrax/object_factory.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 module Bulkrax
-  class ObjectFactory
+  class ObjectFactory # rubocop:disable Metrics/ClassLength
     extend ActiveModel::Callbacks
     include Bulkrax::FileFactory
     include DynamicRecordLookup
@@ -87,7 +87,8 @@ module Bulkrax
     end
 
     def find
-      return find_by_id if attributes[:id].present?
+      found = find_by_id if attributes[:id].present?
+      return found if found.present?
       return search_by_identifier if attributes[work_identifier].present?
     end
 
@@ -102,7 +103,12 @@ module Bulkrax
     end
 
     def search_by_identifier
-      query = { work_identifier =>
+      # TODO(alishaevn): return the proper `work_index` value below
+      # ref: https://github.com/samvera-labs/bulkrax/issues/866
+      # ref:https://github.com/samvera-labs/bulkrax/issues/867
+      # work_index = ::ActiveFedora.index_field_mapper.solr_name(work_identifier, :facetable)
+      work_index = work_identifier
+      query = { work_index =>
                 source_identifier_value }
       # Query can return partial matches (something6 matches both something6 and something68)
       # so we need to weed out any that are not the correct full match. But other items might be

data/app/views/bulkrax/entries/show.html.erb

@@ -2,17 +2,17 @@
 <div class="panel panel-default">
   <div class="panel-body">
     <p class='bulkrax-p-align'>
-      <strong>Identifier:</strong>
+      <strong><%= t('bulkrax.importer.labels.identifier') %>:</strong>
       <%= @entry.identifier %>
     </p>
 
     <p class='bulkrax-p-align'>
-      <strong>Entry ID:</strong>
+      <strong><%= t('bulkrax.importer.labels.entry_id') %>:</strong>
       <%= @entry.id %>
     </p>
 
     <p class='bulkrax-p-align'>
-      <strong>Type:</strong>
+      <strong><%= t('bulkrax.importer.labels.type') %>:</strong>
       <%= @entry.factory_class || 'Unknown' %>
     </p>
     <%= render partial: 'raw_metadata'%>
@@ -23,10 +23,10 @@
 
     <p class="bulkrax-p-align">
       <% if @importer.present? %>
-        <strong>Importer:</strong>
+        <strong><%= t('bulkrax.importer.labels.importer') %>:</strong>
         <%= link_to @importer.name, importer_path(@importer) %>
       <% elsif @exporter.present? %>
-        <strong>Exporter:</strong>
+        <strong><%= t('bulkrax.importer.labels.exporter') %>:</strong>
         <%= link_to @exporter.name, exporter_path(@exporter) %>
       <% end %>
     </p>

data/app/views/bulkrax/importers/_bagit_fields.html.erb

@@ -1,15 +1,15 @@
 <div class='bagit_fields'>
 
-  <%#= fi.input :metadata_type, 
-    collection:  importer.import_metadata_type, 
+  <%#= fi.input :metadata_type,
+    collection:  importer.import_metadata_type,
     selected: importer.parser_fields['metadata_type'],
     include_blank: true,
     input_html: { class: 'form-control' }
     %>
   <%= fi.input :metadata_file_name, as: :string, input_html: { value: importer.parser_fields['metadata_file_name'] } %>
 
-  <%= fi.input :metadata_format, 
-    collection:  importer.import_metadata_format, 
+  <%= fi.input :metadata_format,
+    collection:  importer.import_metadata_format,
     selected: importer.parser_fields['metadata_format'],
     include_blank: true,
     input_html: { class: 'form-control' }
@@ -18,7 +18,8 @@
   <%= fi.input :visibility,
     collection: [
       ['Public', 'open'],
-      ['Private', 'restricted']
+      ['Private', 'restricted'],
+      ['Institution', 'authenticated']
     ],
     selected: importer.parser_fields['visibility'] || 'open',
     input_html: { class: 'form-control' }

data/app/views/bulkrax/importers/_csv_fields.html.erb

@@ -3,7 +3,8 @@
   <%= fi.input :visibility,
     collection: [
       ['Public', 'open'],
-      ['Private', 'restricted']
+      ['Private', 'restricted'],
+      ['Institution', 'authenticated']
     ],
     selected: importer.parser_fields['visibility'] || 'open',
     input_html: { class: 'form-control' }

data/app/views/bulkrax/importers/_oai_fields.html.erb

@@ -1,15 +1,16 @@
 <div class='oai_fields'>
   <%= fi.input :base_url, as: :string, input_html: { value: importer.parser_fields['base_url'] } %>
-  
+
   <%= fi.input :metadata_prefix, as: :string, hint: 'Such as oai_dc, dcterms or oai_qdc', input_html: { value: importer.parser_fields['metadata_prefix'] } %>
-  
+
   <%= fi.input :set, collection: [importer.parser_fields['set']], label: 'Set (source)', selected: importer.parser_fields['set'] %>
   <button type="button" class="btn btn-default refresh-set-source">Refresh Sets</button>
 
   <%= fi.input :visibility,
     collection: [
       ['Public', 'open'],
-      ['Private', 'restricted']
+      ['Private', 'restricted'],
+      ['Institution', 'authenticated']
     ],
     selected: importer.parser_fields['visibility'] || 'open',
     input_html: { class: 'form-control' }

data/app/views/bulkrax/importers/_xml_fields.html.erb

@@ -1,31 +1,32 @@
 <div class='xml_fields'>
 
-  <%# @todo improve on this implementation. 
-    As it stands, it's a hostage to namespaces, 
-    eg. dc:title 
+  <%# @todo improve on this implementation.
+    As it stands, it's a hostage to namespaces,
+    eg. dc:title
     if namespaces aren't in the xml, we would have to specify dc:title
     but if the namespaces ARE present, we remove them so we would need title
   %>
-  <%= fi.input :record_element, 
-    hint: 'Provide the xml element name to use to identify the record, or records, eg. ROW - each record in the attached XML is wrapped in a <ROW> tag.', 
+  <%= fi.input :record_element,
+    hint: 'Provide the xml element name to use to identify the record, or records, eg. ROW - each record in the attached XML is wrapped in a <ROW> tag.',
     input_html: { value: importer.parser_fields['record_element'] }
     %>
 
-  <%= fi.input :import_type, 
+  <%= fi.input :import_type,
 		collection: [
       ['Single Work per Metadata File', 'single'],
-			['Multiple Works per Metadata File', 'multiple'] 
-		], 
+			['Multiple Works per Metadata File', 'multiple']
+		],
     selected: importer.parser_fields['import_type'],
     input_html: { class: 'form-control' }
     %>
-  
+
   <h4>Visiblity</h4>
 
   <%= fi.input :visibility,
     collection: [
       ['Public', 'open'],
-      ['Private', 'restricted']
+      ['Private', 'restricted'],
+      ['Institution', 'authenticated']
     ],
     selected: importer.parser_fields['visibility'] || 'open',
     input_html: { class: 'form-control' }

data/config/locales/bulkrax.en.yml

@@ -46,18 +46,23 @@ en:
         generated_metadata: "These exported fields currently cannot be imported."
     importer:
       labels:
-        name: Name
-        user: User
         admin_set: Admin set
+        collection_entries: Collection Entries
+        entry_id: Entry ID
+        exporter: Exporter
+        file_set_entries: File Set Entries
         frequency: Frequency
-        parser_klass: Parser klass
+        identifier: Identifier
+        importer: Importer
         limit: Limit
-        total_work_entries: Total Works
+        name: Name
+        parser_klass: Parser klass
         total_collections: Total Collections
         total_file_sets: Total File Sets
+        total_work_entries: Total Works
+        type: Type
+        user: User
         work_entries: Work Entries
-        collection_entries: Collection Entries
-        file_set_entries: File Set Entries
     table_header:
       labels:
         identifier: Identifier

data/db/migrate/20210806044408_remove_unused_last_error.rb

@@ -1,7 +1,7 @@
 class RemoveUnusedLastError < ActiveRecord::Migration[5.1]
   def change
-    remove_column :bulkrax_entries, :last_error
-    remove_column :bulkrax_exporters, :last_error
-    remove_column :bulkrax_importers, :last_error
+    remove_column :bulkrax_entries, :last_error if column_exists?(:bulkrax_entries, :last_error)
+    remove_column :bulkrax_exporters, :last_error if column_exists?(:bulkrax_exporters, :last_error)
+    remove_column :bulkrax_importers, :last_error if column_exists?(:bulkrax_importers, :last_error)
   end
 end

data/db/migrate/20230608153601_add_indices_to_bulkrax.rb

@@ -1,14 +1,14 @@
 class AddIndicesToBulkrax < ActiveRecord::Migration[5.1]
   def change
-    add_index :bulkrax_entries, :identifier
-    add_index :bulkrax_entries, :type
-    add_index :bulkrax_entries, [:importerexporter_id, :importerexporter_type], name: 'bulkrax_entries_importerexporter_idx'
+    add_index :bulkrax_entries, :identifier unless index_exists?(:bulkrax_entries, :identifier)
+    add_index :bulkrax_entries, :type unless index_exists?(:bulkrax_entries, :type)
+    add_index :bulkrax_entries, [:importerexporter_id, :importerexporter_type], name: 'bulkrax_entries_importerexporter_idx' unless index_exists?(:bulkrax_entries, [:importerexporter_id, :importerexporter_type], name: 'bulkrax_entries_importerexporter_idx')
 
-    add_index :bulkrax_pending_relationships, :parent_id
-    add_index :bulkrax_pending_relationships, :child_id
+    add_index :bulkrax_pending_relationships, :parent_id unless index_exists?(:bulkrax_pending_relationships, :parent_id)
+    add_index :bulkrax_pending_relationships, :child_id unless index_exists?(:bulkrax_pending_relationships, :child_id) 
 
-    add_index :bulkrax_statuses, [:statusable_id, :statusable_type], name: 'bulkrax_statuses_statusable_idx'
-    add_index :bulkrax_statuses, [:runnable_id, :runnable_type], name: 'bulkrax_statuses_runnable_idx'
-    add_index :bulkrax_statuses, :error_class
+    add_index :bulkrax_statuses, [:statusable_id, :statusable_type], name: 'bulkrax_statuses_statusable_idx' unless index_exists?(:bulkrax_statuses, [:statusable_id, :statusable_type], name: 'bulkrax_statuses_statusable_idx')
+    add_index :bulkrax_statuses, [:runnable_id, :runnable_type], name: 'bulkrax_statuses_runnable_idx' unless index_exists?(:bulkrax_statuses, [:runnable_id, :runnable_type], name: 'bulkrax_statuses_runnable_idx')
+    add_index :bulkrax_statuses, :error_class unless index_exists?(:bulkrax_statuses, :error_class)
   end
 end

data/lib/bulkrax/engine.rb

@@ -23,15 +23,16 @@ module Bulkrax
     end
 
     config.after_initialize do
-      my_engine_root = Bulkrax::Engine.root.to_s
-      paths = ActionController::Base.view_paths.collect(&:to_s)
-      hyrax_path = paths.detect { |path| path.match(/\/hyrax-[\d\.]+.*/) }
-      paths = if hyrax_path
-                paths.insert(paths.index(hyrax_path), my_engine_root + '/app/views')
-              else
-                paths.insert(0, my_engine_root + '/app/views')
-              end
-      ActionController::Base.view_paths = paths
+      # We want to ensure that Bulkrax is earlier in the lookup for view_paths than Hyrax.  That is
+      # we favor view in Bulkrax over those in Hyrax.
+      if defined?(Hyrax)
+        my_engine_root = Bulkrax::Engine.root.to_s
+        hyrax_engine_root = Hyrax::Engine.root.to_s
+        paths = ActionController::Base.view_paths.collect(&:to_s)
+        hyrax_view_path = paths.detect { |path| path.match(%r{^#{hyrax_engine_root}}) }
+        paths.insert(paths.index(hyrax_view_path), File.join(my_engine_root, 'app', 'views')) if hyrax_view_path
+        ActionController::Base.view_paths = paths.uniq
+      end
     end
   end
 end

data/lib/bulkrax/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Bulkrax
-  VERSION = '5.3.0'
+  VERSION = '5.4.1'
 end

data/lib/bulkrax.rb

@@ -152,7 +152,7 @@ module Bulkrax
         "publisher" => { from: ["publisher"] },
         "related_url" => { from: ["relation"] },
         "rights_statement" => { from: ["rights"] },
-        "source" => { from: ["source"] },
+        # "source" => { from: ["source"], source_identifier: true },
         "subject" => { from: ["subject"], parsed: true },
         "title" => { from: ["title"] },
         "resource_type" => { from: ["type"], parsed: true },
@@ -172,7 +172,7 @@ module Bulkrax
         "related_url" => { from: ["relation"] },
         "rights_holder" => { from: ["rightsHolder"] },
         "rights_statement" => { from: ["rights"] },
-        "source" => { from: ["source"] },
+        # "source" => { from: ["source"], source_identifier: true },
         "subject" => { from: ["subject"], parsed: true },
         "title" => { from: ["title"] },
         "resource_type" => { from: ["type"], parsed: true },
@@ -182,6 +182,9 @@ module Bulkrax
       "Bulkrax::CsvParser" => {},
       'Bulkrax::BagitParser' => {},
       'Bulkrax::XmlParser' => {}
+      # "Bulkrax::CsvParser" => { "source" => { from: ["source"], source_identifier: true } },
+      # 'Bulkrax::BagitParser' => { "source" => { from: ["source"], source_identifier: true } },
+      # 'Bulkrax::XmlParser' => { "source" => { from: ["source"], source_identifier: true } }
     }
 
     # Lambda to set the default field mapping

data/lib/tasks/bulkrax_tasks.rake

@@ -1,6 +1,108 @@
 # frozen_string_literal: true
 
 namespace :bulkrax do
+  # Usage example: rails bulkrax:generate_test_csvs['5','100','GenericWork']
+  desc 'Generate CSVs with fake data for testing purposes'
+  task :generate_test_csvs, [:num_of_csvs, :csv_rows, :record_type] => :environment do |_t, args|
+    # NOTE: If this line throws an error, run `gem install faker` inside your Docker container
+    require 'faker'
+    require 'csv'
+
+    FileUtils.mkdir_p(Rails.root.join('tmp', 'imports'))
+
+    IGNORED_PROPERTIES = %w[
+      admin_set_id
+      alternate_ids
+      arkivo_checksum
+      created_at
+      date_modified
+      date_uploaded
+      depositor
+      embargo
+      has_model
+      head
+      internal_resource
+      label
+      lease
+      member_ids
+      member_of_collection_ids
+      modified_date
+      new_record
+      on_behalf_of
+      owner
+      proxy_depositor
+      rendering_ids
+      representative_id
+      state
+      tail
+      thumbnail_id
+      updated_at
+    ].freeze
+
+    BULKRAX_PROPERTIES = %w[
+      source_identifier
+      model
+    ].freeze
+
+    num_of_csvs = args.num_of_csvs.presence&.to_i || 5
+    csv_rows = args.csv_rows.presence&.to_i || 100
+    record_type = args.record_type.presence&.constantize || GenericWork
+
+    csv_header = if Hyrax.config.try(:use_valkyrie?)
+                   record_type.schema.map { |k| k.name.to_s }
+                 else
+                   record_type.properties.keys
+                 end
+
+    csv_header -= IGNORED_PROPERTIES
+    csv_header.unshift(*BULKRAX_PROPERTIES)
+
+    num_of_csvs.times do |i|
+      CSV.open(Rails.root.join('tmp', 'imports', "importer_#{i}.csv"), 'wb') do |csv|
+        csv << csv_header
+        csv_rows.times do |_index|
+          row = []
+          csv_header.each do |prop_name|
+            row << case prop_name
+                   when 'id', 'source_identifier'
+                     Faker::Number.number(digits: 4)
+                   when 'model'
+                     record_type.to_s
+                   when 'rights_statement'
+                     'http://rightsstatements.org/vocab/CNE/1.0/'
+                   when 'license'
+                     'https://creativecommons.org/licenses/by-nc/4.0/'
+                   when 'based_near'
+                     # FIXME: Set a proper :based_near value
+                     nil
+                   else
+                     Faker::Lorem.sentence
+                   end
+          end
+          csv << row
+        end
+      end
+    end
+
+    num_of_csvs.times do |i|
+      Bulkrax::Importer.create(
+        name: "Generated CSV #{i}",
+        admin_set_id: 'admin_set/default',
+        user_id: User.find_by(email: 'admin@example.com').id,
+        frequency: 'PT0S',
+        parser_klass: 'Bulkrax::CsvParser',
+        parser_fields: {
+          'visibility' => 'open',
+          'rights_statement' => '',
+          'override_rights_statement' => '0',
+          'file_style' => 'Specify a Path on the Server',
+          'import_file_path' => "tmp/imports/importer_#{i}.csv",
+          'update_files' => false
+        }
+      )
+    end
+  end
+
   desc "Remove old exported zips and create new ones with the new file structure"
   task rerun_all_exporters: :environment do
     # delete the existing folders and zip files

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bulkrax
 version: !ruby/object:Gem::Version
-  version: 5.3.0
+  version: 5.4.1
 platform: ruby
 authors:
 - Rob Kaufman
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-08-02 00:00:00.000000000 Z
+date: 2023-10-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rails