arclight 1.0.0 → 1.6.2

data/app/helpers/arclight/ead_format_helpers.rb

@@ -23,13 +23,34 @@ module Arclight
             .scrub!(:strip).to_html
     end
 
+    # rubocop:disable Metrics/AbcSize
     def ead_to_html_scrubber
       Loofah::Scrubber.new do |node|
         format_render_attributes(node) if node.attr('render').present?
+        convert_to_span(node) if CONVERT_TO_SPAN_TAGS.include? node.name
+        convert_to_br(node) if CONVERT_TO_BR_TAG.include? node.name
+        format_links(node) if %w[extptr extref extrefloc ptr ref].include? node.name
         format_lists(node) if %w[list chronlist].include? node.name
+        format_indexes(node) if node.name == 'index'
+        format_tables(node) if node.name == 'table'
         node
       end
     end
+    # rubocop:enable Metrics/AbcSize
+
+    # Tags that should be converted to <span> tags because of formatting conflicts between XML and HTML
+    CONVERT_TO_SPAN_TAGS = ['title'].freeze
+
+    # Tags that should be converted to HTML <br/> tags
+    CONVERT_TO_BR_TAG = ['lb'].freeze
+
+    def convert_to_span(node)
+      node.name = 'span'
+    end
+
+    def convert_to_br(node)
+      node.name = 'br'
+    end
 
     def condense_whitespace(str)
       str.squish.strip.gsub(/>[\n\s]+</, '><')
@@ -91,6 +112,17 @@ module Arclight
       end
     end
 
+    def format_links(node)
+      node.remove_attribute('target')
+      node.remove_attribute('type')
+      if %w[extptr extref extrefloc].include? node.name
+        node['target'] = '_blank'
+        node['class'] = 'external-link'
+      end
+      node.content = node['title'] if (%w[extptr ptr].include? node.name) && node['title'].present?
+      node.name = 'a' if node['href'].present?
+    end
+
     def format_lists(node)
       format_simple_lists(node) if node.name == 'list' && node['type'] != 'deflist'
       format_deflists(node) if node.name == 'list' && node['type'] == 'deflist'
@@ -218,5 +250,60 @@ module Arclight
       end
       multi_events.each { |event_node| event_node.name = 'div' }
     end
+
+    # Format EAD <index> elements
+    def format_indexes(node)
+      index_head = node.at_css('head')
+      index_head&.name = 'h3'
+      index_head&.add_class('index-head')
+      index_head['id'] = ['index-', index_head.text].join.parameterize if index_head.present?
+      format_indexentries(node)
+      node.name = 'div'
+    end
+
+    # Grab all of the <indexentry> children as a nodeset, move them into
+    # a <table>, wrap each entry in a <tr> & each value in a <td>.
+    def format_indexentries(node)
+      indexentries = node.css('indexentry')
+      return if indexentries.blank?
+
+      indexentries.first.previous = '<table class="table indexentries" />'
+      indexentries.map do |i|
+        i.parent = node.at_css('table.table.indexentries')
+        i.wrap('<tr/>')
+        i.element_children.map { |c| c.wrap('<td/>') }
+        # Assuming two columns in an index, create a blank cell for entries
+        # with a missing value.
+        i.add_child('<td/>') if i.element_children.count == 1
+      end
+    end
+
+    # Format EAD <table> elements, converting <tgroup> to HTML <table>.
+    # Ignoring <colspec>, @colname, @colwidth complex rendering
+    # logic for now.
+    # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
+    def format_tables(node)
+      node.remove_attribute('frame')
+      node.name = 'div' if node.css('tgroup').present?
+      format_table_head(node)
+      tgroups = node.css('tgroup')
+      tgroups&.map do |t|
+        t.name = 'table'
+        t.remove_attribute('cols')
+        t.add_class('table')
+        t.css('row').map { |r| r.name = 'tr' }
+        t.css('thead entry').map { |e| e.name = 'th' }
+        t.css('tbody entry').map { |e| e.name = 'td' }
+      end
+    end
+    # rubocop:enable Metrics/AbcSize, Metrics/MethodLength
+
+    def format_table_head(node)
+      table_head = node.at_css('head')
+      return if table_head.blank?
+
+      table_head.name = 'h3'
+      table_head.add_class('table-head')
+    end
   end
 end

data/app/helpers/arclight_helper.rb

@@ -5,6 +5,7 @@
 module ArclightHelper
   include Arclight::EadFormatHelpers
   include Arclight::FieldConfigHelpers
+  include Blacklight::DocumentHelperBehavior
   include Blacklight::LayoutHelperBehavior
 
   def repository_collections_path(repository)
@@ -91,6 +92,16 @@ module ArclightHelper
     end
   end
 
+  ##
+  # Override of BL core https://github.com/projectblacklight/blacklight/blob/v8.1.0/app/helpers/blacklight/document_helper_behavior.rb#L55
+  # Remove document_type check. It isn't a method on arclight documents
+  # Check if the document is in the user's bookmarks
+  # @param [Blacklight::Document] document
+  # @return [Boolean]
+  def bookmarked?(document)
+    current_bookmarks.any? { |x| x.document_id == document.id }
+  end
+
   def current_context_document
     @document
   end

data/app/models/arclight/document_downloads.rb

@@ -33,7 +33,7 @@ module Arclight
     class << self
       def config
         @config ||= begin
-          YAML.safe_load(::File.read(config_filename))
+          YAML.safe_load_file(config_filename)
         rescue Errno::ENOENT
           {}
         end

data/app/models/arclight/parent.rb

@@ -7,6 +7,9 @@ module Arclight
   class Parent
     attr_reader :id, :label, :eadid, :level
 
+    alias global_id id
+    Arclight.deprecation.deprecate_methods(self, global_id: 'Call `id` instead')
+
     def initialize(id:, label:, eadid:, level:)
       @id = id
       @label = label
@@ -17,15 +20,5 @@ module Arclight
     def collection?
       level == 'collection'
     end
-
-    ##
-    # Concatenates the eadid and the id, to return an "id" in the context of
-    # Blacklight and Solr
-    # @return [String]
-    def global_id
-      return id if eadid == id
-
-      "#{eadid}#{id}"
-    end
   end
 end

data/app/models/arclight/parents.rb

@@ -5,10 +5,11 @@ module Arclight
   # Object for parsing and formalizing Solr_Ead "Parents"
   # https://github.com/awead/solr_ead/blob/8cf7ffaa66e0e4c9c0b12f5646d6c2e20984cd99/lib/solr_ead/behaviors.rb#L54-L57
   class Parents
-    attr_reader :ids, :labels, :levels
+    attr_reader :ids, :legacy_ids, :labels, :levels
 
-    def initialize(ids:, labels:, eadid:, levels:)
+    def initialize(ids:, legacy_ids:, labels:, eadid:, levels:)
       @ids = ids
+      @legacy_ids = legacy_ids
       @labels = labels
       @eadid = eadid
       @levels = levels
@@ -21,17 +22,18 @@ module Arclight
     ##
     # @return [Array[Arclight::Parent]]
     def as_parents
-      ids.map.with_index { |id, idx| Arclight::Parent.new(id: id, label: labels[idx], eadid: eadid, level: levels[idx]) }
+      (ids.presence || legacy_ids).map.with_index { |id, idx| Arclight::Parent.new(id: id, label: labels[idx], eadid: eadid, level: levels[idx]) }
     end
 
     ##
     # @param [SolrDocument] document
     def self.from_solr_document(document)
       ids = document.parent_ids
+      legacy_ids = document.legacy_parent_ids.map { |legacy_id| document.root == legacy_id ? legacy_id : "#{document.root}#{legacy_id}" }
       labels = document.parent_labels
       eadid = document.eadid
       levels = document.parent_levels
-      new(ids: ids, labels: labels, eadid: eadid, levels: levels)
+      new(ids: ids, legacy_ids: legacy_ids, labels: labels, eadid: eadid, levels: levels)
     end
   end
 end

data/app/models/concerns/arclight/solr_document.rb

@@ -7,11 +7,15 @@ module Arclight
     extend ActiveSupport::Concern
 
     included do
-      attribute :parent_ids, :array, 'parent_ssim'
+      attribute :collection_id, :string, '_root_'
+      Arclight.deprecation.deprecate_methods(self, collection_id: 'Use `root` instead')
+      attribute :parent_ids, :array, 'parent_ids_ssim'
+      attribute :legacy_parent_ids, :array, 'parent_ssim'
+      Arclight.deprecation.deprecate_methods(self, legacy_parent_ids: 'Use `parent_ids` instead')
       attribute :parent_labels, :array, 'parent_unittitles_ssm'
       attribute :parent_levels, :array, 'parent_levels_ssm'
       attribute :unitid, :string, 'unitid_ssm'
-      attribute :extent, :string, 'extent_ssm'
+      attribute :extent, :array, 'extent_ssm'
       attribute :abstract, :string, 'abstract_html_tesm'
       attribute :scope, :string, 'scopecontent_html_tesm'
       attribute :creator, :string, 'creator_ssm'
@@ -48,6 +52,7 @@ module Arclight
     def normalized_eadid
       Arclight::NormalizedId.new(eadid).to_s
     end
+    Arclight.deprecation.deprecate_methods(self, normalized_eadid: 'Use `root` instead')
 
     def repository
       first('repository_ssm') || collection&.first('repository_ssm')
@@ -111,8 +116,13 @@ module Arclight
     end
 
     def containers
-      # NOTE: that .titlecase strips punctuation, like hyphens, we want to keep
-      fetch('containers_ssim', []).map(&:capitalize)
+      # NOTE: Keep uppercase characters if present, but upcase the first if not already
+      containers_field = fetch('containers_ssim', []).reject(&:empty?)
+      return [] if containers_field.blank?
+
+      containers_field.map do |container|
+        container.dup.sub!(/\A./, &:upcase)
+      end
     end
 
     # @return [Array<String>] with embedded highlights using <em>...</em>

data/app/views/catalog/_document_list.html.erb

@@ -0,0 +1,8 @@
+<% # Override to conditionally add id="documents" on div. When documents are grouped it causes duplicate id issues %>
+<% # https://github.com/projectblacklight/blacklight/blob/v8.1.0/app/views/catalog/_document_list.html.erb %>
+<% # container for all documents in index list view -%>
+<% view_config = local_assigns[:view_config] || blacklight_config&.view_config(document_index_view_type) %>
+<div <%= 'id="documents"'.html_safe unless grouped? %> class="al-document-listings documents-<%= view_config&.key || document_index_view_type %>">
+  <% document_presenters = documents.map { |doc| document_presenter(doc) } -%>
+  <%= render view_config.document_component.with_collection(document_presenters, partials: view_config.partials, counter_offset: @response&.start || 0) %>
+</div>

data/app/views/catalog/_group.html.erb

@@ -1,4 +1,4 @@
 <% # container for all groups in index view -%>
-<div class='al-grouped-results'>
+<div id="documents" class='al-grouped-results'>
   <%= render (blacklight_config.view_config(document_index_view_type).group_component || Arclight::GroupComponent).with_collection(@response.groups) %>
 </div>

data/app/views/shared/_main_menu_links.html.erb

@@ -1,6 +1,6 @@
 <li class="nav-item <%= repositories_active_class %>">
   <%= link_to t('arclight.routes.repositories'), arclight_engine.repositories_path, class: 'nav-link' %>
 </li>
-<li class="nav-item ml-3 ms-3 <%= collection_active_class %>">
+<li class="nav-item ms-3 <%= collection_active_class %>">
   <%= link_to t('arclight.routes.collections'), arclight_engine.collections_path, class: 'nav-link' %>
 </li>

data/arclight.gemspec

@@ -26,7 +26,7 @@ Gem::Specification.new do |spec|
 
   spec.add_dependency 'blacklight', '>= 8.0.0', '< 9'
   spec.add_dependency 'gretel'
-  spec.add_dependency 'rails', '~> 7.0'
+  spec.add_dependency 'rails', '>= 7.1', '< 9'
   spec.add_dependency 'traject', '~> 3.0'
   spec.add_dependency 'traject_plus', '~> 2.0'
 
@@ -43,5 +43,4 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency 'selenium-webdriver'
   spec.add_development_dependency 'simplecov'
   spec.add_development_dependency 'solr_wrapper'
-  spec.add_development_dependency 'webdrivers'
 end

data/lib/arclight/normalized_date.rb

@@ -39,16 +39,11 @@ module Arclight
 
     # @see http://www2.archivists.org/standards/DACS/part_I/chapter_2/4_date for rules
     def normalize
-      if inclusive.present?
-        result = inclusive.to_s
-        result << ", bulk #{bulk}" if bulk.present?
-      elsif other.present?
-        result = other.to_s
-      else
-        result = nil
-      end
-
-      result&.strip
+      result = []
+      result << inclusive if inclusive.present?
+      result << other if other.present?
+      result << "bulk #{bulk}" if bulk.present?
+      result.compact.map(&:strip).join(', ').presence
     end
   end
 end

data/lib/arclight/normalized_id.rb

@@ -5,9 +5,11 @@ require 'arclight/exceptions'
 module Arclight
   ##
   # A simple utility class to normalize identifiers
-  # to be used around the application for linking
   class NormalizedId
-    def initialize(id)
+    # Accepts unused kwargs from the ead2_config.rb id to_field directive
+    # (:title and :repository) so that applications can provide a custom
+    # id_normalizer class to traject to form the collection id from these attributes.
+    def initialize(id, **_kwargs)
       @id = id
     end
 

data/lib/arclight/repository.rb

@@ -72,7 +72,7 @@ module Arclight
     # @return [Hash<Slug,Repository>]
     def self.from_yaml(file)
       repos = {}
-      data = YAML.safe_load(File.read(file))
+      data = YAML.safe_load_file(file)
       data.each_key do |slug|
         repos[slug] = new(data[slug].merge(slug: slug))
       end

data/lib/arclight/traject/ead2_component_config.rb

@@ -29,6 +29,7 @@ settings do
   provide 'title_normalizer', 'Arclight::NormalizedTitle'
   provide 'reader_class_name', 'Arclight::Traject::NokogiriNamespacelessReader'
   provide 'logger', Logger.new($stderr)
+  provide 'component_identifier_format', '%<root_id>s_%<ref_id>s'
 end
 
 NAME_ELEMENTS = %w[corpname famname name persname].freeze
@@ -60,6 +61,7 @@ DID_SEARCHABLE_NOTES_FIELDS = %w[
   abstract
   materialspec
   physloc
+  note
 ].freeze
 
 # ==================
@@ -67,7 +69,9 @@ DID_SEARCHABLE_NOTES_FIELDS = %w[
 #
 # NOTE: All fields should be stored in Solr
 # ==================
-to_field 'ref_ssi' do |record, accumulator, _context|
+to_field 'ref_ssi' do |record, accumulator, context|
+  next if context.output_hash['ref_ssi']
+
   accumulator << if record.attribute('id').blank?
                    strategy = Arclight::MissingIdStrategy.selected
                    hexdigest = strategy.new(record).to_hexdigest
@@ -82,7 +86,7 @@ to_field 'ref_ssi' do |record, accumulator, _context|
                    record['id'] = hexdigest
                    hexdigest
                  else
-                   record.attribute('id')&.value&.strip&.gsub('.', '-')
+                   record.attribute('id')&.value&.strip&.gsub('.', '-') # rubocop:disable Style/SafeNavigationChainLength
                  end
 end
 to_field 'ref_ssm' do |_record, accumulator, context|
@@ -90,10 +94,14 @@ to_field 'ref_ssm' do |_record, accumulator, context|
 end
 
 to_field 'id' do |_record, accumulator, context|
-  accumulator << [
-    settings[:root].output_hash['id'],
-    context.output_hash['ref_ssi']
-  ].join
+  next if context.output_hash['id']
+
+  data = {
+    root_id: settings[:root].output_hash['id']&.first,
+    ref_id: context.output_hash['ref_ssi']&.first
+  }
+
+  accumulator << (settings[:component_identifier_format] % data)
 end
 
 to_field 'title_filing_ssi', extract_xpath('./did/unittitle'), first_only
@@ -131,6 +139,11 @@ to_field 'parent_ssi' do |_record, accumulator, _context|
   accumulator.concat settings[:parent].output_hash['ref_ssi'] || settings[:parent].output_hash['id']
 end
 
+to_field 'parent_ids_ssim' do |_record, accumulator, _context|
+  accumulator.concat(settings[:parent].output_hash['parent_ids_ssim'] || [])
+  accumulator.concat settings[:parent].output_hash['id']
+end
+
 to_field 'parent_unittitles_ssm' do |_rec, accumulator, _context|
   accumulator.concat(settings[:parent].output_hash['parent_unittitles_ssm'] || [])
   accumulator.concat settings[:parent].output_hash['normalized_title_ssm'] || []
@@ -155,12 +168,42 @@ to_field 'collection_ssim' do |_record, accumulator, _context|
   accumulator.concat settings[:root].output_hash['normalized_title_ssm']
 end
 
-to_field 'extent_ssm', extract_xpath('./did/physdesc/extent')
-to_field 'extent_tesim', extract_xpath('./did/physdesc/extent')
+# This accumulates direct text from a physdesc, ignoring child elements handled elsewhere
+to_field 'physdesc_tesim', extract_xpath('./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)
+
+      physdesc << child.text&.strip unless child.text&.strip&.empty?
+    end.flatten
+    physdesc.join(' ') unless physdesc.empty?
+  end
+end
+
+to_field 'extent_ssm' do |record, accumulator|
+  physdescs = record.xpath('./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
+
+  # Add each physdesc separately to the accumulator
+  accumulator.concat(extents_per_physdesc)
+end
+
+to_field 'extent_tesim' do |_record, accumulator, context|
+  accumulator.concat context.output_hash['extent_ssm'] || []
+end
+
+to_field 'physfacet_tesim', extract_xpath('./did/physdesc/physfacet')
+to_field 'dimensions_tesim', extract_xpath('./did/physdesc/dimensions')
+
+to_field 'indexes_html_tesm', extract_xpath('./index', to_text: false)
+to_field 'indexes_tesim', extract_xpath('./index')
 
-to_field 'creator_ssm', extract_xpath('./did/origination')
 to_field 'creator_ssim', extract_xpath('./did/origination')
-to_field 'creators_ssim', extract_xpath('./did/origination')
 to_field 'creator_sort' do |record, accumulator|
   accumulator << record.xpath('./did/origination').map(&:text).join(', ')
 end
@@ -214,7 +257,7 @@ to_field 'digital_objects_ssm', extract_xpath('./dao|./did/dao', to_text: false)
   end
 end
 
-to_field 'date_range_ssim', extract_xpath('./did/unitdate/@normal', to_text: false) do |_record, accumulator|
+to_field 'date_range_isim', extract_xpath('./did/unitdate/@normal', to_text: false) do |_record, accumulator|
   range = Arclight::YearRange.new
   next range.years if accumulator.blank?
 
@@ -225,6 +268,7 @@ end
 
 NAME_ELEMENTS.map do |selector|
   to_field 'names_ssim', extract_xpath("./controlaccess/#{selector}"), unique
+  to_field 'names_ssim', extract_xpath(".//#{selector}"), unique
   to_field "#{selector}_ssim", extract_xpath(".//#{selector}")
 end
 
@@ -244,8 +288,6 @@ to_field 'access_subjects_ssm' do |_record, accumulator, context|
   accumulator.concat(context.output_hash.fetch('access_subjects_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"]')
 to_field 'acqinfo_ssim', extract_xpath('./acqinfo/*[local-name()!="head"]')
 to_field 'acqinfo_ssim', extract_xpath('./descgrp/acqinfo/*[local-name()!="head"]')
 
@@ -263,8 +305,8 @@ SEARCHABLE_NOTES_FIELDS.map do |selector|
 end
 DID_SEARCHABLE_NOTES_FIELDS.map do |selector|
   to_field "#{selector}_html_tesm", extract_xpath("./did/#{selector}", to_text: false)
+  to_field "#{selector}_tesim", extract_xpath("./did/#{selector}")
 end
-to_field 'did_note_ssm', extract_xpath('./did/note')
 
 # =============================
 # Each component child document
@@ -280,6 +322,7 @@ to_field 'components' do |record, accumulator, context|
       provide :counter, context.settings[:counter]
       provide :depth, context.settings[:depth].to_i + 1
       provide :component_traject_config, context.settings[:component_traject_config]
+      provide :component_identifier_format, context.settings[:component_identifier_format]
     end
 
     i.load_config_file(context.settings[:component_traject_config])

data/lib/arclight/traject/ead2_config.rb

@@ -6,6 +6,7 @@ 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
@@ -48,14 +49,18 @@ DID_SEARCHABLE_NOTES_FIELDS = %w[
   abstract
   materialspec
   physloc
+  note
 ].freeze
 
 settings do
+  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.fetch('REPOSITORY_ID', nil)
   provide 'logger', Logger.new($stderr)
-  provide 'component_traject_config', File.join(__dir__, 'ead2_component_config.rb')
 end
 
 each_record do |_record, context|
@@ -72,7 +77,14 @@ end
 # NOTE: All fields should be stored in Solr
 # ==================
 
-to_field 'id', extract_xpath('/ead/eadheader/eadid'), strip, gsub('.', '-')
+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 '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')
@@ -100,22 +112,18 @@ end
 to_field 'unitid_ssm', extract_xpath('/ead/archdesc/did/unitid')
 to_field 'unitid_tesim', extract_xpath('/ead/archdesc/did/unitid')
 
-to_field 'normalized_title_ssm' do |_record, accumulator, context|
-  dates = Arclight::NormalizedDate.new(
+to_field 'normalized_date_ssm' do |_record, accumulator, context|
+  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
-  title = context.output_hash['title_ssm'].first
-  accumulator << Arclight::NormalizedTitle.new(title, dates).to_s
 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
+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|
@@ -185,11 +193,41 @@ to_field 'digital_objects_ssm', extract_xpath('/ead/archdesc/did/dao|/ead/archde
   end
 end
 
-to_field 'extent_ssm', extract_xpath('/ead/archdesc/did/physdesc/extent')
-to_field 'extent_tesim', extract_xpath('/ead/archdesc/did/physdesc/extent')
+# 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)
+
+      physdesc << child.text&.strip unless child.text&.strip&.empty?
+    end.flatten
+    physdesc.join(' ') unless physdesc.empty?
+  end
+end
+
+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
+
+  # Add each physdesc separately to the accumulator
+  accumulator.concat(extents_per_physdesc)
+end
+
+to_field 'extent_tesim' do |_record, accumulator, context|
+  accumulator.concat context.output_hash['extent_ssm'] || []
+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 'genreform_ssim', extract_xpath('/ead/archdesc/controlaccess/genreform')
 
-to_field 'date_range_ssim', extract_xpath('/ead/archdesc/did/unitdate/@normal', to_text: false) do |_record, accumulator|
+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?
 
@@ -198,6 +236,9 @@ to_field 'date_range_ssim', extract_xpath('/ead/archdesc/did/unitdate/@normal',
   accumulator.replace range.years
 end
 
+to_field 'indexes_html_tesm', extract_xpath('/ead/archdesc/index', to_text: false)
+to_field 'indexes_tesim', extract_xpath('/ead/archdesc/index')
+
 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)
@@ -208,6 +249,7 @@ 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
 
 NAME_ELEMENTS.map do |selector|

data/lib/arclight/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Arclight
-  VERSION = '1.0.0'
+  VERSION = '1.6.2'
 end