arclight 0.2.0 → 1.6.2

data/lib/arclight/traject/ead2_config.rb

@@ -5,6 +5,8 @@ require 'traject'
 require 'traject/nokogiri_reader'
 require 'traject_plus'
 require 'traject_plus/macros'
+require 'arclight/level_label'
+require 'arclight/normalized_id'
 require 'arclight/normalized_date'
 require 'arclight/normalized_title'
 require 'active_model/conversion' ## Needed for Arclight::Repository
@@ -12,14 +14,14 @@ require 'active_support/core_ext/array/wrap'
 require 'arclight/digital_object'
 require 'arclight/year_range'
 require 'arclight/repository'
-require 'arclight/missing_id_strategy'
-
-NAME_ELEMENTS = %w[corpname famname name persname].freeze
+require 'arclight/traject/nokogiri_namespaceless_reader'
 
 # rubocop:disable Style/MixinUsage
 extend TrajectPlus::Macros
 # rubocop:enable Style/MixinUsage
 
+NAME_ELEMENTS = %w[corpname famname name persname].freeze
+
 SEARCHABLE_NOTES_FIELDS = %w[
   accessrestrict
   accruals
@@ -47,13 +49,17 @@ DID_SEARCHABLE_NOTES_FIELDS = %w[
   abstract
   materialspec
   physloc
+  note
 ].freeze
 
 settings do
-  provide 'nokogiri.namespaces',
-          'xmlns' => 'urn:isbn:1-931666-22-9'
+  provide 'component_traject_config', File.join(__dir__, 'ead2_component_config.rb')
+  provide 'id_normalizer', 'Arclight::NormalizedId'
+  provide 'date_normalizer', 'Arclight::NormalizedDate'
+  provide 'title_normalizer', 'Arclight::NormalizedTitle'
+  provide 'reader_class_name', 'Arclight::Traject::NokogiriNamespacelessReader'
   provide 'solr_writer.commit_on_close', 'true'
-  provide 'repository', ENV['REPOSITORY_ID']
+  provide 'repository', ENV.fetch('REPOSITORY_ID', nil)
   provide 'logger', Logger.new($stderr)
 end
 
@@ -65,51 +71,66 @@ each_record do |_record, context|
   ).name
 end
 
-# Top level
-to_field 'id', extract_xpath('//xmlns:eadid'), strip, gsub('.', '-')
-to_field 'title_filing_si', extract_xpath('//xmlns:titleproper[@type="filing"]')
-to_field 'title_ssm', extract_xpath('//xmlns:archdesc/xmlns:did/xmlns:unittitle')
-to_field 'title_teim', extract_xpath('//xmlns:archdesc/xmlns:did/xmlns:unittitle')
-to_field 'ead_ssi', extract_xpath('//xmlns:eadid')
+# ==================
+# Top level document
+#
+# NOTE: All fields should be stored in Solr
+# ==================
+
+to_field 'id' do |record, accumulator|
+  id = record.at_xpath('/ead/eadheader/eadid')&.text
+  unitid = record.at_xpath('/ead/archdesc/did/unitid')&.text
+  title = record.at_xpath('/ead/archdesc/did/unittitle')&.text
+  repository = settings['repository']
+  accumulator << settings['id_normalizer'].constantize.new(id, unitid: unitid, title: title, repository: repository).to_s
+end
 
-to_field 'unitdate_ssm', extract_xpath('//xmlns:archdesc/xmlns:did/xmlns:unitdate')
-to_field 'unitdate_bulk_ssim', extract_xpath('//xmlns:archdesc/xmlns:did/xmlns:unitdate[@type="bulk"]')
-to_field 'unitdate_inclusive_ssm', extract_xpath('//xmlns:archdesc/xmlns:did/xmlns:unitdate[@type="inclusive"]')
-to_field 'unitdate_other_ssim', extract_xpath('//xmlns:archdesc/xmlns:did/xmlns:unitdate[not(@type)]')
+to_field 'title_filing_ssi', extract_xpath('/ead/eadheader/filedesc/titlestmt/titleproper[@type="filing"]')
+to_field 'title_ssm', extract_xpath('/ead/archdesc/did/unittitle')
+to_field 'title_tesim', extract_xpath('/ead/archdesc/did/unittitle')
+to_field 'ead_ssi', extract_xpath('/ead/eadheader/eadid')
 
-to_field 'level_ssm' do |record, accumulator|
-  accumulator << record.at_xpath('//xmlns:archdesc').attribute('level').value
-end
+to_field 'unitdate_ssm', extract_xpath('/ead/archdesc/did/unitdate')
+to_field 'unitdate_bulk_ssim', extract_xpath('/ead/archdesc/did/unitdate[@type="bulk"]')
+to_field 'unitdate_inclusive_ssm', extract_xpath('/ead/archdesc/did/unitdate[@type="inclusive"]')
+to_field 'unitdate_other_ssim', extract_xpath('/ead/archdesc/did/unitdate[not(@type)]')
 
-to_field 'level_sim' do |record, accumulator|
-  accumulator << record.at_xpath('//xmlns:archdesc').attribute('level').value&.capitalize
+# All top-level docs treated as 'collection' for routing / display purposes
+to_field 'level_ssm' do |_record, accumulator|
+  accumulator << 'collection'
 end
 
-to_field 'unitid_ssm', extract_xpath('//xmlns:archdesc/xmlns:did/xmlns:unitid')
-to_field 'unitid_teim', extract_xpath('//xmlns:archdesc/xmlns:did/xmlns:unitid')
+# Keep the original top-level archdesc/@level for Level facet in addition to 'Collection'
+to_field 'level_ssim' do |record, accumulator|
+  level = record.at_xpath('/ead/archdesc').attribute('level')&.value
+  other_level = record.at_xpath('/ead/archdesc').attribute('otherlevel')&.value
 
-to_field 'normalized_title_ssm' do |_record, accumulator, context|
-  dates = Arclight::NormalizedDate.new(
-    context.output_hash['unitdate_inclusive_ssm'],
-    context.output_hash['unitdate_bulk_ssim'],
-    context.output_hash['unitdate_other_ssim']
-  ).to_s
-  title = context.output_hash['title_ssm'].first
-  accumulator << Arclight::NormalizedTitle.new(title, dates).to_s
+  accumulator << Arclight::LevelLabel.new(level, other_level).to_s
+  accumulator << 'Collection' unless level == 'collection'
 end
 
+to_field 'unitid_ssm', extract_xpath('/ead/archdesc/did/unitid')
+to_field 'unitid_tesim', extract_xpath('/ead/archdesc/did/unitid')
+
 to_field 'normalized_date_ssm' do |_record, accumulator, context|
-  accumulator << Arclight::NormalizedDate.new(
+  accumulator << settings['date_normalizer'].constantize.new(
     context.output_hash['unitdate_inclusive_ssm'],
     context.output_hash['unitdate_bulk_ssim'],
     context.output_hash['unitdate_other_ssim']
   ).to_s
 end
 
-to_field 'collection_ssm' do |_record, accumulator, context|
+to_field 'normalized_title_ssm' do |_record, accumulator, context|
+  title = context.output_hash['title_ssm']&.first
+  date = context.output_hash['normalized_date_ssm']&.first
+  accumulator << settings['title_normalizer'].constantize.new(title, date).to_s
+end
+
+to_field 'collection_title_tesim' do |_record, accumulator, context|
   accumulator.concat context.output_hash.fetch('normalized_title_ssm', [])
 end
-to_field 'collection_sim' do |_record, accumulator, context|
+
+to_field 'collection_ssim' do |_record, accumulator, context|
   accumulator.concat context.output_hash.fetch('normalized_title_ssm', [])
 end
 
@@ -117,58 +138,40 @@ to_field 'repository_ssm' do |_record, accumulator, context|
   accumulator << context.clipboard[:repository]
 end
 
-to_field 'repository_sim' do |_record, accumulator, context|
+to_field 'repository_ssim' do |_record, accumulator, context|
   accumulator << context.clipboard[:repository]
 end
 
-to_field 'geogname_ssm', extract_xpath('//xmlns:archdesc/xmlns:controlaccess/xmlns:geogname')
-
-to_field 'geogname_sim', extract_xpath('//xmlns:archdesc/xmlns:controlaccess/xmlns:geogname')
+to_field 'geogname_ssm', extract_xpath('/ead/archdesc/controlaccess/geogname')
+to_field 'geogname_ssim', extract_xpath('/ead/archdesc/controlaccess/geogname')
 
-to_field 'creator_ssm', extract_xpath("//xmlns:archdesc/xmlns:did/xmlns:origination[@label='creator']")
-to_field 'creator_sim', extract_xpath("//xmlns:archdesc/xmlns:did/xmlns:origination[@label='creator']")
-to_field 'creator_ssim', extract_xpath("//xmlns:archdesc/xmlns:did/xmlns:origination[@label='creator']")
+to_field 'creator_ssm', extract_xpath('/ead/archdesc/did/origination')
+to_field 'creator_ssim', extract_xpath('/ead/archdesc/did/origination')
 to_field 'creator_sort' do |record, accumulator|
-  accumulator << record.xpath("//xmlns:archdesc/xmlns:did/xmlns:origination[@label='creator']").map { |c| c.text.strip }.join(', ')
+  accumulator << record.xpath('/ead/archdesc/did/origination').map { |c| c.text.strip }.join(', ')
 end
 
-to_field 'creator_persname_ssm', extract_xpath("//xmlns:archdesc/xmlns:did/xmlns:origination[@label='creator']/xmlns:persname")
-to_field 'creator_persname_ssim', extract_xpath("//xmlns:archdesc/xmlns:did/xmlns:origination[@label='creator']/xmlns:persname")
-to_field 'creator_corpname_ssm', extract_xpath("//xmlns:archdesc/xmlns:did/xmlns:origination[@label='creator']/xmlns:corpname")
-to_field 'creator_corpname_sim', extract_xpath("//xmlns:archdesc/xmlns:did/xmlns:origination[@label='creator']/xmlns:corpname")
-to_field 'creator_corpname_ssim', extract_xpath("//xmlns:archdesc/xmlns:did/xmlns:origination[@label='creator']/xmlns:corpname")
-to_field 'creator_famname_ssm', extract_xpath("//xmlns:archdesc/xmlns:did/xmlns:origination[@label='creator']/xmlns:famname")
-to_field 'creator_famname_ssim', extract_xpath("//xmlns:archdesc/xmlns:did/xmlns:origination[@label='creator']/xmlns:famname")
-
-to_field 'persname_sim', extract_xpath('//xmlns:persname')
+to_field 'creator_persname_ssim', extract_xpath('/ead/archdesc/did/origination/persname')
+to_field 'creator_corpname_ssim', extract_xpath('/ead/archdesc/did/origination/corpname')
+to_field 'creator_famname_ssim', extract_xpath('/ead/archdesc/did/origination/famname')
 
 to_field 'creators_ssim' do |_record, accumulator, context|
-  accumulator.concat context.output_hash['creator_persname_ssm'] if context.output_hash['creator_persname_ssm']
-  accumulator.concat context.output_hash['creator_corpname_ssm'] if context.output_hash['creator_corpname_ssm']
-  accumulator.concat context.output_hash['creator_famname_ssm'] if context.output_hash['creator_famname_ssm']
+  accumulator.concat context.output_hash['creator_persname_ssim'] if context.output_hash['creator_persname_ssim']
+  accumulator.concat context.output_hash['creator_corpname_ssim'] if context.output_hash['creator_corpname_ssim']
+  accumulator.concat context.output_hash['creator_famname_ssim'] if context.output_hash['creator_famname_ssim']
 end
 
-to_field 'places_sim', extract_xpath('//xmlns:archdesc/xmlns:controlaccess/xmlns:geogname')
-to_field 'places_ssim', extract_xpath('//xmlns:archdesc/xmlns:controlaccess/xmlns:geogname')
-to_field 'places_ssm', extract_xpath('//xmlns:archdesc/xmlns:controlaccess/xmlns:geogname')
+to_field 'places_ssim', extract_xpath('/ead/archdesc/controlaccess/geogname')
 
-to_field 'access_terms_ssm', extract_xpath('//xmlns:archdesc/xmlns:userestrict/xmlns:p')
+to_field 'access_terms_ssm', extract_xpath('/ead/archdesc/userestrict/*[local-name()!="head"]')
 
-# Indexes the acquisition group information into the notes field
-# Please see https://www.loc.gov/ead/tglib/elements/acqinfo.html
-to_field 'acqinfo_ssim', extract_xpath('/xmlns:ead/xmlns:archdesc/xmlns:acqinfo/*[local-name()!="head"]')
-to_field 'acqinfo_ssim', extract_xpath('/xmlns:ead/xmlns:archdesc/xmlns:descgrp/xmlns:acqinfo/*[local-name()!="head"]')
-to_field 'acqinfo_ssim', extract_xpath('./xmlns:acqinfo/*[local-name()!="head"]')
-to_field 'acqinfo_ssim', extract_xpath('./xmlns:descgrp/xmlns:acqinfo/*[local-name()!="head"]')
-to_field 'acqinfo_ssm' do |_record, accumulator, context|
-  accumulator.concat(context.output_hash.fetch('acqinfo_ssim', []))
-end
+to_field 'acqinfo_ssim', extract_xpath('/ead/archdesc/acqinfo/*[local-name()!="head"]')
+to_field 'acqinfo_ssim', extract_xpath('/ead/archdesc/descgrp/acqinfo/*[local-name()!="head"]')
 
-# Indexes only specified controlled terms for archival description into the access_subject field
-to_field 'access_subjects_ssim', extract_xpath('//xmlns:archdesc/xmlns:controlaccess', to_text: false) do |_record, accumulator|
+to_field 'access_subjects_ssim', extract_xpath('/ead/archdesc/controlaccess', to_text: false) do |_record, accumulator|
   accumulator.map! do |element|
     %w[subject function occupation genreform].map do |selector|
-      element.xpath(".//xmlns:#{selector}").map(&:text)
+      element.xpath(".//#{selector}").map(&:text)
     end
   end.flatten!
 end
@@ -177,299 +180,137 @@ to_field 'access_subjects_ssm' do |_record, accumulator, context|
   accumulator.concat Array.wrap(context.output_hash['access_subjects_ssim'])
 end
 
-to_field 'has_online_content_ssim', extract_xpath('.//xmlns:dao') do |_record, accumulator|
+to_field 'has_online_content_ssim', extract_xpath('.//dao') do |_record, accumulator|
   accumulator.replace([accumulator.any?])
 end
 
-to_field 'extent_ssm', extract_xpath('//xmlns:did/xmlns:physdesc/xmlns:extent')
-to_field 'extent_teim', extract_xpath('//xmlns:did/xmlns:physdesc/xmlns:extent')
-to_field 'genreform_sim', extract_xpath('//xmlns:archdesc/xmlns:controlaccess/xmlns:genreform')
-to_field 'genreform_ssm', extract_xpath('//xmlns:archdesc/xmlns:controlaccess/xmlns:genreform')
-
-to_field 'date_range_sim', extract_xpath('.//xmlns:did/xmlns:unitdate/@normal', to_text: false) do |_record, accumulator|
-  range = Arclight::YearRange.new
-  next range.years if accumulator.blank?
-
-  ranges = accumulator.map(&:to_s)
-  range << range.parse_ranges(ranges)
-  accumulator.replace range.years
-end
-
-SEARCHABLE_NOTES_FIELDS.map do |selector|
-  to_field "#{selector}_ssm", extract_xpath("//xmlns:archdesc/xmlns:#{selector}/*[local-name()!='head']")
-  to_field "#{selector}_heading_ssm", extract_xpath("//xmlns:archdesc/xmlns:#{selector}/xmlns:head") unless selector == 'prefercite'
-  to_field "#{selector}_teim", extract_xpath("//xmlns:archdesc/xmlns:#{selector}/*[local-name()!='head']")
-end
-
-DID_SEARCHABLE_NOTES_FIELDS.map do |selector|
-  to_field "#{selector}_ssm", extract_xpath("//xmlns:did/xmlns:#{selector}")
-end
-NAME_ELEMENTS.map do |selector|
-  to_field 'names_coll_ssim', extract_xpath("/xmlns:ead/xmlns:archdesc/xmlns:controlaccess/xmlns:#{selector}")
-  to_field 'names_ssim', extract_xpath("//xmlns:#{selector}")
-  to_field "#{selector}_ssm", extract_xpath("//xmlns:#{selector}")
-end
-to_field 'corpname_sim', extract_xpath('//xmlns:corpname')
-
-to_field 'language_sim', extract_xpath('//xmlns:did/xmlns:langmaterial')
-to_field 'language_ssm', extract_xpath('//xmlns:did/xmlns:langmaterial')
-
-# Each component child document
-# <c> <c01> <c12>
-compose 'components', ->(record, accumulator, _context) { accumulator.concat record.xpath('//*[is_component(.)]', NokogiriXpathExtensions.new) } do
-  to_field 'ref_ssi' do |record, accumulator, context|
-    accumulator << if record.attribute('id').blank?
-                     strategy = Arclight::MissingIdStrategy.selected
-                     hexdigest = strategy.new(record).to_hexdigest
-                     parent_id = context.clipboard[:parent].output_hash['id'].first
-                     logger.warn('MISSING ID WARNING') do
-                       [
-                         "A component in #{parent_id} did not have and ID so one was minted using the #{strategy} strategy.",
-                         "The ID of this document will be #{parent_id}#{hexdigest}."
-                       ].join(' ')
-                     end
-                   else
-                     record.attribute('id')&.value&.strip&.gsub('.', '-')
-                   end
-  end
-  to_field 'ref_ssm' do |_record, accumulator, context|
-    accumulator.concat context.output_hash['ref_ssi']
+to_field 'digital_objects_ssm', extract_xpath('/ead/archdesc/did/dao|/ead/archdesc/dao', to_text: false) do |_record, accumulator|
+  accumulator.map! do |dao|
+    label = dao.attributes['title']&.value ||
+            dao.xpath('daodesc/p')&.text
+    href = (dao.attributes['href'] || dao.attributes['xlink:href'])&.value
+    Arclight::DigitalObject.new(label: label, href: href).to_json
   end
+end
 
-  to_field 'id' do |_record, accumulator, context|
-    accumulator << [
-      context.clipboard[:parent].output_hash['id'],
-      context.output_hash['ref_ssi']
-    ].join('')
-  end
+# This accumulates direct text from a physdesc, ignoring child elements handled elsewhere
+to_field 'physdesc_tesim', extract_xpath('/ead/archdesc/did/physdesc', to_text: false) do |_record, accumulator|
+  accumulator.map! do |element|
+    physdesc = []
+    element.children.map do |child|
+      next if child.instance_of?(Nokogiri::XML::Element)
 
-  to_field 'ead_ssi' do |_record, accumulator, context|
-    accumulator << context.clipboard[:parent].output_hash['ead_ssi'].first
+      physdesc << child.text&.strip unless child.text&.strip&.empty?
+    end.flatten
+    physdesc.join(' ') unless physdesc.empty?
   end
+end
 
-  to_field 'title_filing_si', extract_xpath('./xmlns:did/xmlns:unittitle'), first_only
-  to_field 'title_ssm', extract_xpath('./xmlns:did/xmlns:unittitle')
-  to_field 'title_teim', extract_xpath('./xmlns:did/xmlns:unittitle')
-
-  to_field 'unitdate_bulk_ssim', extract_xpath('./xmlns:did/xmlns:unitdate[@type="bulk"]')
-  to_field 'unitdate_inclusive_ssm', extract_xpath('./xmlns:did/xmlns:unitdate[@type="inclusive"]')
-  to_field 'unitdate_other_ssim', extract_xpath('./xmlns:did/xmlns:unitdate[not(@type)]')
-
-  to_field 'normalized_title_ssm' do |_record, accumulator, context|
-    dates = Arclight::NormalizedDate.new(
-      context.output_hash['unitdate_inclusive_ssm'],
-      context.output_hash['unitdate_bulk_ssim'],
-      context.output_hash['unitdate_other_ssim']
-    ).to_s
-    title = context.output_hash['title_ssm']&.first
-    accumulator << Arclight::NormalizedTitle.new(title, dates).to_s
+to_field 'extent_ssm' do |record, accumulator|
+  physdescs = record.xpath('/ead/archdesc/did/physdesc')
+  extents_per_physdesc = physdescs.map do |physdesc|
+    extents = physdesc.xpath('./extent').map { |e| e.text.strip }
+    # Join extents within the same physdesc with an empty string
+    extents.join(' ') unless extents.empty?
   end
 
-  to_field 'normalized_date_ssm' do |_record, accumulator, context|
-    accumulator << Arclight::NormalizedDate.new(
-      context.output_hash['unitdate_inclusive_ssm'],
-      context.output_hash['unitdate_bulk_ssim'],
-      context.output_hash['unitdate_other_ssim']
-    ).to_s
-  end
+  # Add each physdesc separately to the accumulator
+  accumulator.concat(extents_per_physdesc)
+end
 
-  to_field 'component_level_isim' do |record, accumulator|
-    accumulator << 1 + record.ancestors.count { |node| node.name == 'c' }
-  end
+to_field 'extent_tesim' do |_record, accumulator, context|
+  accumulator.concat context.output_hash['extent_ssm'] || []
+end
 
-  to_field 'parent_ssm' do |record, accumulator, context|
-    accumulator << context.clipboard[:parent].output_hash['id'].first
-    accumulator.concat NokogiriXpathExtensions.new.is_component(record.ancestors).reverse.map { |n| n.attribute('id').value }
-  end
+to_field 'physfacet_tesim', extract_xpath('/ead/archdesc/did/physdesc/physfacet')
+to_field 'dimensions_tesim', extract_xpath('/ead/archdesc/did/physdesc/dimensions')
 
-  to_field 'parent_ssi' do |_record, accumulator, context|
-    accumulator << context.output_hash['parent_ssm'].last
-  end
+to_field 'genreform_ssim', extract_xpath('/ead/archdesc/controlaccess/genreform')
 
-  to_field 'parent_unittitles_ssm' do |_record, accumulator, context|
-    ## Top level document
-    accumulator.concat context.clipboard[:parent].output_hash['normalized_title_ssm']
-    ## Other components
-    context.output_hash['parent_ssm']&.drop(1)&.each do |id|
-      accumulator.concat Array
-        .wrap(context.clipboard[:parent].output_hash['components'])
-        .find { |c| c['ref_ssi'] == [id] }&.[]('normalized_title_ssm')
-    end
-  end
-  to_field 'parent_unittitles_teim' do |_record, accumulator, context|
-    accumulator.concat context.output_hash['parent_unittitles_ssm']
-  end
+to_field 'date_range_isim', extract_xpath('/ead/archdesc/did/unitdate/@normal', to_text: false) do |_record, accumulator|
+  range = Arclight::YearRange.new
+  next range.years if accumulator.blank?
 
-  to_field 'unitid_ssm', extract_xpath('./xmlns:did/xmlns:unitid')
-  to_field 'repository_ssm' do |_record, accumulator, context|
-    accumulator << context.clipboard[:parent].clipboard[:repository]
-  end
-  to_field 'repository_sim' do |_record, accumulator, context|
-    accumulator << context.clipboard[:parent].clipboard[:repository]
-  end
-  to_field 'collection_ssm' do |_record, accumulator, context|
-    accumulator.concat context.clipboard[:parent].output_hash['normalized_title_ssm']
-  end
-  to_field 'collection_sim' do |_record, accumulator, context|
-    accumulator.concat context.clipboard[:parent].output_hash['normalized_title_ssm']
-  end
+  ranges = accumulator.map(&:to_s)
+  range << range.parse_ranges(ranges)
+  accumulator.replace range.years
+end
 
-  to_field 'extent_ssm', extract_xpath('./xmlns:did/xmlns:physdesc/xmlns:extent')
-  to_field 'creator_ssm', extract_xpath("./xmlns:did/xmlns:origination[@label='creator']")
-  to_field 'creator_ssim', extract_xpath("./xmlns:did/xmlns:origination[@label='creator']")
-  to_field 'creators_ssim', extract_xpath("./xmlns:did/xmlns:origination[@label='creator']")
-  to_field 'creator_sort' do |record, accumulator|
-    accumulator << record.xpath("./xmlns:did/xmlns:origination[@label='creator']").map(&:text).join(', ')
-  end
-  to_field 'collection_creator_ssm' do |_record, accumulator, context|
-    accumulator.concat Array.wrap(context.clipboard[:parent].output_hash['creator_ssm'])
-  end
-  to_field 'has_online_content_ssim', extract_xpath('.//xmlns:dao') do |_record, accumulator|
-    accumulator.replace([accumulator.any?])
-  end
-  to_field 'child_component_count_isim', extract_xpath('xmlns:c') do |_record, accumulator|
-    accumulator.replace([accumulator.length])
-  end
+to_field 'indexes_html_tesm', extract_xpath('/ead/archdesc/index', to_text: false)
+to_field 'indexes_tesim', extract_xpath('/ead/archdesc/index')
 
-  to_field 'ref_ssm' do |record, accumulator|
-    accumulator << record.attribute('id')
+SEARCHABLE_NOTES_FIELDS.map do |selector|
+  to_field "#{selector}_html_tesm", extract_xpath("/ead/archdesc/#{selector}/*[local-name()!='head']", to_text: false) do |_record, accumulator|
+    accumulator.map!(&:to_html)
   end
+  to_field "#{selector}_heading_ssm", extract_xpath("/ead/archdesc/#{selector}/head") unless selector == 'prefercite'
+  to_field "#{selector}_tesim", extract_xpath("/ead/archdesc/#{selector}/*[local-name()!='head']")
+end
 
-  to_field 'level_ssm' do |record, accumulator|
-    level = record.attribute('level')&.value
-    other_level = record.attribute('otherlevel')&.value
-
-    accumulator << if level == 'otherlevel'
-                     alternative_level = other_level if other_level
-                     alternative_level.present? ? alternative_level : 'Other'
-                   elsif level.present?
-                     level&.capitalize
-                   end
-  end
+DID_SEARCHABLE_NOTES_FIELDS.map do |selector|
+  to_field "#{selector}_html_tesm", extract_xpath("/ead/archdesc/did/#{selector}", to_text: false)
+  to_field "#{selector}_tesim", extract_xpath("/ead/archdesc/did/#{selector}")
+end
 
-  to_field 'level_sim' do |_record, accumulator, context|
-    next unless context.output_hash['level_ssm']
+NAME_ELEMENTS.map do |selector|
+  to_field 'names_coll_ssim', extract_xpath("/ead/archdesc/controlaccess/#{selector}")
+  to_field 'names_ssim', extract_xpath("//#{selector}"), unique
+  to_field "#{selector}_ssim", extract_xpath("//#{selector}"), unique
+end
 
-    accumulator.concat context.output_hash['level_ssm']&.map(&:capitalize)
-  end
+to_field 'language_ssim', extract_xpath('/ead/archdesc/did/langmaterial')
 
-  to_field 'parent_access_restrict_ssm', extract_xpath('./xmlns:accessrestrict/xmlns:p')
+to_field 'descrules_ssm', extract_xpath('/ead/eadheader/profiledesc/descrules')
 
-  to_field 'parent_access_restrict_ssm' do |_record, accumulator, context|
-    next unless context.output_hash['accessrestrict_ssm'].nil?
+# count all descendant components from the top-level
+to_field 'total_component_count_is', first_only do |record, accumulator|
+  accumulator << record.xpath('//c|//c01|//c02|//c03|//c04|//c05|//c06|//c07|//c08|//c09|//c10|//c11|//c12').count
+end
 
-    context.output_hash['parent_ssm']&.each do |id|
-      accumulator.concat Array
-        .wrap(context.clipboard[:parent]&.output_hash&.[]('components'))
-        .select { |c| c['ref_ssi'] == [id] }.map { |c| c['accessrestrict_ssm'] }
-    end
-  end
+# count all digital objects from the top-level
+to_field 'online_item_count_is', first_only do |record, accumulator|
+  accumulator << record.xpath('//dao').count
+end
 
-  to_field 'parent_access_restrict_ssm' do |_record, accumulator, context|
-    next unless context.output_hash['parent_access_restrict_ssm'].nil?
+to_field 'component_level_isim' do |_record, accumulator, _context|
+  accumulator << 0
+end
 
-    accumulator.concat Array.wrap(context.clipboard[:parent]&.output_hash&.[]('accessrestrict_ssm'))
-  end
+to_field 'sort_isi' do |_record, accumulator, _context|
+  accumulator << 0
+end
 
-  to_field 'parent_access_terms_ssm', extract_xpath('xmlns:userestrict/xmlns:p')
+# =============================
+# Each component child document
+# <c> <c01> <c12>
+# =============================
 
-  to_field 'parent_access_terms_ssm' do |_record, accumulator, context|
-    next unless context.output_hash['userestrict_ssm'].nil?
+to_field 'components' do |record, accumulator, context|
+  child_components = record.xpath("/ead/archdesc/dsc/c|#{('/ead/archdesc/dsc/c01'..'/ead/archdesc/dsc/c12').to_a.join('|')}")
+  next unless child_components.any?
 
-    context.output_hash['parent_ssm']&.each do |id|
-      accumulator.concat Array
-        .wrap(context.clipboard[:parent]&.output_hash&.[]('components'))
-        .select { |c| c['ref_ssi'] == [id] }.map { |c| c['userestrict_ssm'] }
+  counter = Class.new do
+    def increment
+      @counter ||= 0
+      @counter += 1
     end
-  end
-
-  to_field 'parent_access_terms_ssm' do |_record, accumulator, context|
-    next unless context.output_hash['parent_access_terms_ssm'].nil?
-
-    accumulator << context.clipboard[:parent]&.output_hash&.[]('access_terms_ssm')&.first
-  end
-
-  to_field 'digital_objects_ssm', extract_xpath('./xmlns:dao') do |record, accumulator|
-    accumulator.concat(record.xpath('.//xmlns:dao', xmlns: 'urn:isbn:1-931666-22-9').map do |dao|
-      label = dao.attributes['title']&.value ||
-        dao.xpath('xmlns:daodesc/xmlns:p', xmlns: 'urn:isbn:1-931666-22-9')&.text
-      href = (dao.attributes['href'] || dao.attributes['xlink:href'])&.value
-      Arclight::DigitalObject.new(label: label, href: href).to_json
-    end.to_a)
-  end
-
-  to_field 'date_range_sim', extract_xpath('.//xmlns:did/xmlns:unitdate/@normal', to_text: false) do |_record, accumulator|
-    range = Arclight::YearRange.new
-    next range.years if accumulator.blank?
-
-    ranges = accumulator.map(&:to_s)
-    range << range.parse_ranges(ranges)
-    accumulator.replace range.years
-  end
-
-  NAME_ELEMENTS.map do |selector|
-    to_field 'names_ssim', extract_xpath("./xmlns:controlaccess/xmlns:#{selector}")
-    to_field "#{selector}_ssm", extract_xpath(".//xmlns:#{selector}")
-  end
-
-  to_field 'geogname_sim', extract_xpath('./xmlns:controlaccess/xmlns:geogname')
-  to_field 'geogname_ssm', extract_xpath('./xmlns:controlaccess/xmlns:geogname')
-  to_field 'places_ssim', extract_xpath('xmlns:controlaccess/xmlns:geogname')
-
-  # Indexes only specified controlled terms for archival description into the access_subject field
-  to_field 'access_subjects_ssim', extract_xpath('./xmlns:controlaccess', to_text: false) do |_record, accumulator|
-    accumulator.map! do |element|
-      %w[subject function occupation genreform].map do |selector|
-        element.xpath(".//xmlns:#{selector}").map(&:text)
-      end
-    end.flatten!
-  end
-
-  to_field 'access_subjects_ssm' do |_record, accumulator, context|
-    accumulator.concat(context.output_hash.fetch('access_subjects_ssim', []))
-  end
-
-  # Indexes the acquisition group information into the notes field
-  # Please see https://www.loc.gov/ead/tglib/elements/acqinfo.html
-  to_field 'acqinfo_ssim', extract_xpath('/xmlns:ead/xmlns:archdesc/xmlns:acqinfo/*[local-name()!="head"]')
-  to_field 'acqinfo_ssim', extract_xpath('/xmlns:ead/xmlns:archdesc/xmlns:descgrp/xmlns:acqinfo/*[local-name()!="head"]')
-  to_field 'acqinfo_ssim', extract_xpath('./xmlns:acqinfo/*[local-name()!="head"]')
-  to_field 'acqinfo_ssim', extract_xpath('./xmlns:descgrp/xmlns:acqinfo/*[local-name()!="head"]')
-  to_field 'acqinfo_ssm' do |_record, accumulator, context|
-    accumulator.concat(context.output_hash.fetch('acqinfo_ssim', []))
-  end
-
-  to_field 'language_ssm', extract_xpath('./xmlns:did/xmlns:langmaterial')
-  to_field 'containers_ssim' do |record, accumulator|
-    record.xpath('./xmlns:did/xmlns:container').each do |node|
-      accumulator << [node.attribute('type'), node.text].join(' ').strip
+  end.new
+
+  component_indexer = Traject::Indexer::NokogiriIndexer.new.tap do |i|
+    i.settings do
+      provide :parent, context
+      provide :root, context
+      provide :counter, counter
+      provide :depth, 1
+      provide :logger, context.settings[:logger]
+      provide :component_traject_config, context.settings[:component_traject_config]
     end
-  end
-  SEARCHABLE_NOTES_FIELDS.map do |selector|
-    to_field "#{selector}_ssm", extract_xpath(".//xmlns:#{selector}/*[local-name()!='head']")
-    to_field "#{selector}_heading_ssm", extract_xpath(".//xmlns:archdesc/xmlns:#{selector}/xmlns:head")
-    to_field "#{selector}_teim", extract_xpath(".//xmlns:#{selector}/*[local-name()!='head']")
-  end
-  DID_SEARCHABLE_NOTES_FIELDS.map do |selector|
-    to_field "#{selector}_ssm", extract_xpath(".//xmlns:did/xmlns:#{selector}")
-  end
-  to_field 'did_note_ssm', extract_xpath('.//xmlns:did/xmlns:note')
-end
 
-each_record do |_record, context|
-  context.output_hash['components'] &&= context.output_hash['components'].select { |c| c.keys.any? }
-end
+    i.load_config_file(context.settings[:component_traject_config])
+  end
 
-##
-# Used for evaluating xpath components to find
-class NokogiriXpathExtensions
-  # rubocop:disable Naming/PredicateName, Style/FormatString
-  def is_component(node_set)
-    node_set.find_all do |node|
-      component_elements = (1..12).map { |i| "c#{'%02d' % i}" }
-      component_elements.push 'c'
-      component_elements.include? node.name
-    end
+  child_components.each do |child_component|
+    output = component_indexer.map_record(child_component)
+    accumulator << output if output.keys.any?
   end
-  # rubocop:enable Naming/PredicateName, Style/FormatString
 end