dor_indexing 1.3.1 → 1.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 83583cc273179a722bf069396bfab8ee5e67da1cc3562c1e2de31b0c987c6bda
-  data.tar.gz: f823aa9a76740bf9b2ea785aaab80aa69958e16b8b7ad27b92869996de188066
+  metadata.gz: 9c1e2280668e9085122b921fd927b75e9982fa5fda9067a9245899ef93db77ae
+  data.tar.gz: 3e8d89e77994cb62ffcc1c598e47716c3a9c9f8aa8e37f226159e8fef947082d
 SHA512:
-  metadata.gz: 047fb2b8f9050f083201622629419c82a203cb65867f8f1fce35026b50ceaebbe341ab5d2182c0e89e74f43a671ba42a00080e0aab2906d7c4a8f6477e7ebe60
-  data.tar.gz: 2c908c0b6f3d4c1f4380f4e34a502eaa7508aa0037954cd32863982fe33892e9759d8db7f6e3b06ac70c4acedb3c5be728b3defd265e7242cf8566a9e75add86
+  metadata.gz: 24e3bf95ad1c541d3b403b2233018ab1da89be80cdcd3fa9acb2793e2b57673c8364202a4a548f8fe1c9ff60444585b5cf2d020968cb5b50614ad80b118d7bae
+  data.tar.gz: 6c015737932b1f01819d89f5f91948ab43d09e1537d6bf41ba8df85778c9ed0f18dc85b408a7fdc6ceb48ce6cfc4f7127b74da0c415aac6819d7dd460cf8a4eb

data/Gemfile.lock

@@ -1,19 +1,19 @@
 PATH
   remote: .
   specs:
-    dor_indexing (1.3.1)
-      cocina-models (~> 0.95.0)
+    dor_indexing (1.4.1)
+      activesupport
+      cocina-models (~> 0.95.1)
       dor-workflow-client (~> 7.0)
       honeybadger
       marc-vocab (~> 0.3.0)
-      solrizer
       stanford-mods
       zeitwerk
 
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (7.1.3)
+    activesupport (7.1.3.2)
       base64
       bigdecimal
       concurrent-ruby (~> 1.0, >= 1.0.2)
@@ -28,7 +28,7 @@ GEM
     base64 (0.2.0)
     bigdecimal (3.1.6)
     byebug (11.1.3)
-    cocina-models (0.95.0)
+    cocina-models (0.95.1)
       activesupport
       deprecation
       dry-struct (~> 1.0)
@@ -49,7 +49,7 @@ GEM
     connection_pool (2.4.1)
     deprecation (1.1.0)
       activesupport
-    diff-lcs (1.5.0)
+    diff-lcs (1.5.1)
     docile (1.4.0)
     dor-workflow-client (7.0.2)
       activesupport (>= 3.2.1, < 8)
@@ -58,8 +58,7 @@ GEM
       faraday-retry (~> 2.0)
       nokogiri (~> 1.6)
       zeitwerk (~> 2.1)
-    drb (2.2.0)
-      ruby2_keywords
+    drb (2.2.1)
     dry-core (1.0.1)
       concurrent-ruby (~> 1.0)
       zeitwerk (~> 2.6)
@@ -90,8 +89,8 @@ GEM
       net-http
     faraday-retry (2.2.0)
       faraday (~> 2.0)
-    honeybadger (5.4.1)
-    i18n (1.14.1)
+    honeybadger (5.6.0)
+    i18n (1.14.4)
       concurrent-ruby (~> 1.0)
     ice_nine (0.11.2)
     iso-639 (0.3.6)
@@ -100,7 +99,7 @@ GEM
       multi_json
     language_server-protocol (3.17.0.3)
     marc-vocab (0.3.0)
-    minitest (5.21.2)
+    minitest (5.22.2)
     mods (3.0.4)
       edtf (~> 3.0)
       iso-639
@@ -110,9 +109,9 @@ GEM
     mutex_m (0.2.0)
     net-http (0.4.1)
       uri
-    nokogiri (1.16.0-x86_64-darwin)
+    nokogiri (1.16.2-x86_64-darwin)
       racc (~> 1.4)
-    nokogiri (1.16.0-x86_64-linux)
+    nokogiri (1.16.2-x86_64-linux)
       racc (~> 1.4)
     nom-xml (1.2.0)
       i18n
@@ -132,22 +131,22 @@ GEM
     rake (13.1.0)
     regexp_parser (2.9.0)
     rexml (3.2.6)
-    rspec (3.12.0)
-      rspec-core (~> 3.12.0)
-      rspec-expectations (~> 3.12.0)
-      rspec-mocks (~> 3.12.0)
-    rspec-core (3.12.2)
-      rspec-support (~> 3.12.0)
-    rspec-expectations (3.12.3)
+    rspec (3.13.0)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.0)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.12.0)
-    rspec-mocks (3.12.6)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.12.0)
-    rspec-support (3.12.1)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.1)
     rss (0.3.0)
       rexml
-    rubocop (1.60.2)
+    rubocop (1.62.0)
       json (~> 2.3)
       language_server-protocol (>= 3.17.0)
       parallel (~> 1.10)
@@ -155,11 +154,11 @@ GEM
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8, < 3.0)
       rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.30.0, < 2.0)
+      rubocop-ast (>= 1.31.1, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.30.0)
-      parser (>= 3.2.1.0)
+    rubocop-ast (1.31.2)
+      parser (>= 3.3.0.4)
     rubocop-capybara (2.20.0)
       rubocop (~> 1.41)
     rubocop-factory_bot (2.25.1)
@@ -167,37 +166,30 @@ GEM
     rubocop-performance (1.20.2)
       rubocop (>= 1.48.1, < 2.0)
       rubocop-ast (>= 1.30.0, < 2.0)
-    rubocop-rspec (2.26.1)
+    rubocop-rspec (2.27.1)
       rubocop (~> 1.40)
       rubocop-capybara (~> 2.17)
       rubocop-factory_bot (~> 2.22)
     ruby-progressbar (1.13.0)
-    ruby2_keywords (0.0.5)
     simplecov (0.22.0)
       docile (~> 1.1)
       simplecov-html (~> 0.11)
       simplecov_json_formatter (~> 0.1)
     simplecov-html (0.12.3)
     simplecov_json_formatter (0.1.4)
-    solrizer (4.1.0)
-      activesupport
-      nokogiri
-      xml-simple
     stanford-mods (3.3.9)
       activesupport
       mods (~> 3.0, >= 3.0.4)
-    super_diff (0.10.0)
+    super_diff (0.11.0)
       attr_extras (>= 6.2.4)
       diff-lcs
       patience_diff
-    thor (1.3.0)
+    thor (1.3.1)
     tzinfo (2.0.6)
       concurrent-ruby (~> 1.0)
     unicode-display_width (2.5.0)
     uri (0.13.0)
-    xml-simple (1.1.9)
-      rexml
-    zeitwerk (2.6.12)
+    zeitwerk (2.6.13)
 
 PLATFORMS
   x86_64-darwin-21

data/dor_indexing.gemspec

@@ -31,11 +31,11 @@ Gem::Specification.new do |spec|
   spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
-  spec.add_dependency 'cocina-models', '~> 0.95.0'
+  spec.add_dependency 'activesupport'
+  spec.add_dependency 'cocina-models', '~> 0.95.1'
   spec.add_dependency 'dor-workflow-client', '~> 7.0'
   spec.add_dependency 'honeybadger'
   spec.add_dependency 'marc-vocab', '~> 0.3.0'
-  spec.add_dependency 'solrizer'
   spec.add_dependency 'stanford-mods'
   spec.add_dependency 'zeitwerk'
 end

data/lib/dor_indexing/builders/document_builder.rb

@@ -33,7 +33,7 @@ class DorIndexing
         DorIndexing::Indexers::IdentityMetadataIndexer,
         DorIndexing::Indexers::DescriptiveMetadataIndexer,
         DorIndexing::Indexers::EmbargoMetadataIndexer,
-        DorIndexing::Indexers::ContentMetadataIndexer,
+        DorIndexing::Indexers::ObjectFilesIndexer,
         DorIndexing::Indexers::IdentifiableIndexer,
         DorIndexing::Indexers::CollectionTitleIndexer,
         DorIndexing::Indexers::ReleasableIndexer,

data/lib/dor_indexing/indexers/administrative_tag_indexer.rb

@@ -2,14 +2,12 @@
 
 class DorIndexing
   module Indexers
-    # Index administrative tags for an object.
-    # NOTE: Most of this code was extracted from the dor-services gem:
-    #       https://github.com/sul-dlss/dor-services/blob/v9.0.0/lib/dor/datastreams/identity_metadata_ds.rb#L196-L218
+    # Index administrative tags for an object
     class AdministrativeTagIndexer
       TAG_PART_DELIMITER = ' : '
       SPECIAL_TAG_TYPES_TO_INDEX = ['Project', 'Registered By'].freeze
 
-      attr_reader :id
+      attr_reader :id, :administrative_tags
 
       def initialize(id:, administrative_tags:, **)
         @id = id
@@ -30,18 +28,23 @@ class DorIndexing
           tag_prefix, rest = tag.split(TAG_PART_DELIMITER, 2)
           prefix = tag_prefix.downcase.strip.gsub(/\s/, '_')
 
-          solr_doc['tag_ssim'] << tag # for facet and display
-          solr_doc['tag_text_unstemmed_im'] << tag # for search
+          solr_doc['tag_ssim'] << tag # for Argo display and fq
+          solr_doc['tag_text_unstemmed_im'] << tag # for Argo search
 
-          solr_doc['exploded_nonproject_tag_ssim'] += exploded_tags_from(tag) unless prefix == 'project'
+          # exploded tags are for hierarchical facets in Argo
+          solr_doc['exploded_nonproject_tag_ssim'] += explode_tag_hierarchy(tag) unless prefix == 'project'
 
-          next if SPECIAL_TAG_TYPES_TO_INDEX.exclude?(tag_prefix) || rest.nil?
+          next if rest.blank?
+
+          # Index specific tag types that are used in Argo:
+          #  project tags for search results and registered by tags for reports ...
+          next unless SPECIAL_TAG_TYPES_TO_INDEX.include?(tag_prefix)
 
           (solr_doc["#{prefix}_tag_ssim"] ||= []) << rest.strip
 
           if prefix == 'project'
             solr_doc['exploded_project_tag_ssim'] ||= []
-            solr_doc['exploded_project_tag_ssim'] += exploded_tags_from(rest.strip)
+            solr_doc['exploded_project_tag_ssim'] += explode_tag_hierarchy(rest.strip)
           end
         end
         solr_doc
@@ -52,12 +55,10 @@ class DorIndexing
 
       private
 
-      attr_reader :administrative_tags
-
-      # solrize each possible prefix for the tag, inclusive of the full tag.
-      # e.g., for a tag such as "A : B : C", this will solrize to an _ssim field
-      # that contains ["A",  "A : B",  "A : B : C"].
-      def exploded_tags_from(tag)
+      # index each possible path, inclusive of the full tag.
+      # e.g., for "A : B : C", return ["A",  "A : B",  "A : B : C"].
+      # this is for the blacklight-hierarchy plugin for faceting on each level of the hierarchy
+      def explode_tag_hierarchy(tag)
         tag_parts = tag.split(TAG_PART_DELIMITER)
 
         1.upto(tag_parts.count).map do |i|

data/lib/dor_indexing/indexers/basic_indexer.rb

@@ -2,7 +2,7 @@
 
 class DorIndexing
   module Indexers
-    # Basic indexing for all objects
+    # Basic indexing for any object
     class BasicIndexer
       attr_reader :cocina, :workflow_client
 
@@ -11,6 +11,7 @@ class DorIndexing
         @workflow_client = workflow_client
       end
 
+      # @return [Hash] the partial solr document for basic data
       # rubocop:disable Metrics/AbcSize
       # rubocop:disable Metrics/MethodLength
       def to_solr

data/lib/dor_indexing/indexers/collection_title_indexer.rb

@@ -2,7 +2,7 @@
 
 class DorIndexing
   module Indexers
-    # Indexes the collection title
+    # Indexes collection titles for an object
     class CollectionTitleIndexer
       attr_reader :cocina, :parent_collections
 
@@ -11,14 +11,17 @@ class DorIndexing
         @parent_collections = parent_collections
       end
 
-      # @return [Hash] the partial solr document for identifiable concerns
+      # @return [Hash] the partial solr document for collection title concerns
       def to_solr
         {}.tap do |solr_doc|
-          parent_collections.each do |related_obj|
-            coll_title = Cocina::Models::Builders::TitleBuilder.build(related_obj.description.title)
+          parent_collections.each do |collection_obj|
+            coll_title = Cocina::Models::Builders::TitleBuilder.build(collection_obj.description.title)
+            next if coll_title.blank?
 
-            # create/append collection_title_tesim and collection_title_ssim
-            ::Solrizer.insert_field(solr_doc, 'collection_title', coll_title, :stored_searchable, :symbol)
+            solr_doc['collection_title_ssim'] ||= []
+            solr_doc['collection_title_ssim'] << coll_title
+            solr_doc['collection_title_tesim'] ||= []
+            solr_doc['collection_title_tesim'] << coll_title
           end
         end
       end

data/lib/dor_indexing/indexers/composite_indexer.rb

@@ -2,6 +2,7 @@
 
 class DorIndexing
   module Indexers
+    # Allows DorIndexing::Builders::DocumentBuilder class (which builds the solr doc for an object) to be much more readable
     # Borrowed from https://github.com/samvera/valkyrie/blob/master/lib/valkyrie/persistence/solr/composite_indexer.rb
     class CompositeIndexer
       attr_reader :indexers

data/lib/dor_indexing/indexers/descriptive_metadata_indexer.rb

@@ -4,8 +4,8 @@ require 'stanford-mods'
 
 class DorIndexing
   module Indexers
-    # rubocop:disable Metrics/ClassLength
     # Indexes the descriptive metadata
+    # rubocop:disable Metrics/ClassLength
     class DescriptiveMetadataIndexer
       attr_reader :cocina, :stanford_mods_record
 
@@ -25,11 +25,10 @@ class DorIndexing
           'full_title_tenim' => full_title, # for searching; 1 more field type is copyField in solr schema.xml
           'additional_titles_tenim' => additional_titles, # for searching; 1 more field type is copyField in solr schema.xml
           'display_title_ss' => display_title, # for display in Argo
-          'sw_display_title_tesim' => display_title, # for display in Argo DEPRECATED in favor of display_title_ss
 
           # contributor
           'author_text_nostem_im' => author_primary, # primary author tokenized but not stemmed
-          'sw_author_tesim' => author_primary, # used for author display in Argo
+          'author_display_ss' => author_primary, # used for author display in Argo
           'contributor_text_nostem_im' => author_all, # author names should be tokenized but not stemmed
           'contributor_orcids_ssim' => orcids,
 
@@ -43,8 +42,6 @@ class DorIndexing
           'originInfo_place_placeTerm_tesim' => event_place, # do we want this?
           'sw_pub_date_facet_ssi' => stanford_mods_record.pub_year_int.to_s, # SW Date facet
 
-          'metadata_format_ssim' => 'mods', # no longer used? https://github.com/search?q=org%3Asul-dlss+metadata_format_ssim&type=code
-
           # SW facets plus a friend facet
           'sw_format_ssim' => sw_format, # SW Resource Type facet
           'mods_typeOfResource_ssim' => resource_type, # MODS Resource Type facet

data/lib/dor_indexing/indexers/identifiable_indexer.rb

@@ -2,7 +2,7 @@
 
 class DorIndexing
   module Indexers
-    # Indexes the identifiable concerns
+    # Indexes the druid, metadata sources, and the apo titles
     class IdentifiableIndexer
       attr_reader :cocina, :cocina_repository
 
@@ -13,8 +13,8 @@ class DorIndexing
         @cocina_repository = cocina_repository
       end
 
-      ## Module-level variables, shared between ALL mixin includers (and ALL *their* includers/extenders)!
-      ## used for caching found values
+      ## Module-level variable, shared between ALL mixin includers (and ALL *their* includers/extenders)!
+      ## used for caching apo titles
       @@apo_hash = {} # rubocop:disable Style/ClassVars
 
       # @return [Hash] the partial solr document for identifiable concerns
@@ -23,13 +23,18 @@ class DorIndexing
           add_apo_titles(solr_doc, cocina.administrative.hasAdminPolicy)
 
           solr_doc['metadata_source_ssim'] = identity_metadata_sources unless cocina.is_a? Cocina::Models::AdminPolicyWithMetadata
-          # This used to be added to the index by https://github.com/sul-dlss/dor-services/commit/11b80d249d19326ef591411ffeb634900e75c2c3
-          # and was called dc_identifier_druid_tesim
-          # It is used to search based on druid.
-          solr_doc['objectId_tesim'] = [cocina.externalIdentifier, cocina.externalIdentifier.delete_prefix('druid:')]
+          solr_doc['druid_prefixed_ssi'] = cocina.externalIdentifier
+          solr_doc['druid_bare_ssi'] = cocina.externalIdentifier.delete_prefix('druid:')
         end
       end
 
+      # Clears out the cache of apos. Used primarily in testing.
+      def self.reset_cache!
+        @@apo_hash = {} # rubocop:disable Style/ClassVars
+      end
+
+      private
+
       # @return [Array<String>] calculated values for Solr index
       def identity_metadata_sources
         return ['DOR'] if !cocina.identification.respond_to?(:catalogLinks) || distinct_current_catalog_types.empty?
@@ -37,13 +42,6 @@ class DorIndexing
         distinct_current_catalog_types.map(&:capitalize)
       end
 
-      # Clears out the cache of items. Used primarily in testing.
-      def self.reset_cache!
-        @@apo_hash = {} # rubocop:disable Style/ClassVars
-      end
-
-      private
-
       def distinct_current_catalog_types
         # Filter out e.g. "previous symphony", "previous folio"
         @distinct_current_catalog_types ||=
@@ -57,15 +55,18 @@ class DorIndexing
 
       # @param [Hash] solr_doc
       # @param [String] admin_policy_id
-      def add_apo_titles(solr_doc, admin_policy_id)
+      def add_apo_titles(solr_doc, admin_policy_id) # rubocop:disable Metrics/MethodLength
         row = populate_cache(admin_policy_id)
         title = row['related_obj_title']
         if row['is_from_hydrus']
-          ::Solrizer.insert_field(solr_doc, 'hydrus_apo_title', title, :symbol)
+          solr_doc['hydrus_apo_title_ssim'] ||= []
+          solr_doc['hydrus_apo_title_ssim'] << title
         else
-          ::Solrizer.insert_field(solr_doc, 'nonhydrus_apo_title', title, :symbol)
+          solr_doc['nonhydrus_apo_title_ssim'] ||= []
+          solr_doc['nonhydrus_apo_title_ssim'] << title
         end
-        ::Solrizer.insert_field(solr_doc, 'apo_title', title, :symbol)
+        solr_doc['apo_title_ssim'] ||= []
+        solr_doc['apo_title_ssim'] << title
       end
 
       # populate cache if necessary

data/lib/dor_indexing/indexers/identity_metadata_indexer.rb

@@ -2,7 +2,7 @@
 
 class DorIndexing
   module Indexers
-    # Indexes the identity metadata
+    # Indexes the identity metadata from cocina.identification
     class IdentityMetadataIndexer
       attr_reader :cocina_object
 
@@ -11,24 +11,21 @@ class DorIndexing
       end
 
       # @return [Hash] the partial solr document for identityMetadata
-      # rubocop:disable Metrics/AbcSize
       # rubocop:disable Metrics/MethodLength
       def to_solr
-        return { 'objectType_ssim' => [object_type] } if object_type == 'adminPolicy' || cocina_object.identification.nil?
+        return { 'objectType_ssim' => [object_type] } if object_type == 'adminPolicy' || cocina_object.identification.blank?
 
         {
           'objectType_ssim' => [object_type],
-          'dor_id_tesim' => [source_id_value, barcode, folio_instance_hrid, previous_ils_ids].flatten.compact,
-          'identifier_ssim' => prefixed_identifiers,
-          'identifier_tesim' => prefixed_identifiers,
+          'identifier_ssim' => prefixed_identifiers, # sourceid, barcode, folio_instance_hrid for display
+          'identifier_tesim' => prefixed_identifiers, # ditto ^^, for search, tokenized (can search prefix and value as separate tokens)
           'barcode_id_ssim' => [barcode].compact,
-          'source_id_ssi' => source_id,
-          'source_id_text_nostem_i' => source_id,
+          'source_id_ssi' => source_id, # for search and display (reports, track_sheet)
+          'source_id_text_nostem_i' => source_id, # for search, tokenized per request from accessioneers
           'folio_instance_hrid_ssim' => [folio_instance_hrid].compact,
           'doi_ssim' => [doi].compact
         }
       end
-      # rubocop:enable Metrics/AbcSize
       # rubocop:enable Metrics/MethodLength
 
       private
@@ -37,10 +34,6 @@ class DorIndexing
         @source_id ||= cocina_object.identification.sourceId
       end
 
-      def source_id_value
-        @source_id_value ||= source_id ? source_id.split(':', 2)[1] : nil
-      end
-
       def barcode
         @barcode ||= object_type == 'collection' ? nil : cocina_object.identification.barcode
       end
@@ -53,15 +46,6 @@ class DorIndexing
         @folio_instance_hrid ||= Array(cocina_object.identification.catalogLinks).find { |link| link.catalog == 'folio' }&.catalogRecordId
       end
 
-      def previous_folio_instance_hrids
-        @previous_folio_instance_hrids ||=
-          Array(cocina_object.identification.catalogLinks).filter_map { |link| link.catalogRecordId if link.catalog == 'previous folio' }
-      end
-
-      def previous_ils_ids
-        @previous_ils_ids ||= previous_folio_instance_hrids
-      end
-
       def object_type
         case cocina_object
         when Cocina::Models::AdminPolicyWithMetadata

data/lib/dor_indexing/indexers/{content_metadata_indexer.rb → object_files_indexer.rb}

@@ -2,15 +2,15 @@
 
 class DorIndexing
   module Indexers
-    # Indexes the content metadata
-    class ContentMetadataIndexer
+    # Indexes the information about files in the object
+    class ObjectFilesIndexer
       attr_reader :cocina
 
       def initialize(cocina:, **)
         @cocina = cocina
       end
 
-      # @return [Hash] the partial solr document for contentMetadata
+      # @return [Hash] the partial solr document for files in the object
       def to_solr
         {
           'content_type_ssim' => type(cocina.type),

data/lib/dor_indexing/indexers/role_metadata_indexer.rb

@@ -2,7 +2,7 @@
 
 class DorIndexing
   module Indexers
-    # Indexes the role metadata
+    # Indexes the administrative role metadata
     class RoleMetadataIndexer
       attr_reader :cocina
 

data/lib/dor_indexing/indexers/workflow_indexer.rb

@@ -2,7 +2,7 @@
 
 class DorIndexing
   module Indexers
-    # Indexes the objects position in workflows
+    # Indexes the object's state for each process in a single workflow
     class WorkflowIndexer
       # @param [Workflow::Response::Workflow] workflow the workflow document to index
       def initialize(workflow:, workflow_client:)
@@ -10,14 +10,14 @@ class DorIndexing
         @workflow_client = workflow_client
       end
 
-      # @return [Hash] the partial solr document for the workflow document
+      # @return [Hash] the partial solr document for all the workflow processes
       def to_solr
         WorkflowSolrDocument.new do |solr_doc|
           solr_doc.name = workflow_name
 
           errors = 0 # The error count is used by the Report class in Argo
           processes.each do |process|
-            ProcessIndexer.new(solr_doc:, workflow_name:, process:).to_solr
+            WorkflowProcessIndexer.new(solr_doc:, workflow_name:, process:).to_solr
             errors += 1 if process.status == 'error'
           end
           solr_doc.status = [workflow_name, workflow_status, errors].join('|')

data/lib/dor_indexing/indexers/{process_indexer.rb → workflow_process_indexer.rb}

@@ -2,8 +2,8 @@
 
 class DorIndexing
   module Indexers
-    # Indexes the process for a workflow
-    class ProcessIndexer
+    # Creates solr doc fields (and values) for a process for a workflow (which is for an object)
+    class WorkflowProcessIndexer
       ERROR_OMISSION = '... (continued)'
       private_constant :ERROR_OMISSION
 
@@ -13,14 +13,14 @@ class DorIndexing
 
       # @param [WorkflowSolrDocument] solr_doc
       # @param [String] workflow_name
-      # @param [Dor::Workflow::Response::Process] process
+      # @param [Dor::Workflow::Response::Process] process containing data for a process in a workflow for an object
       def initialize(solr_doc:, workflow_name:, process:)
         @solr_doc = solr_doc
         @workflow_name = workflow_name
         @process = process
       end
 
-      # @return [Hash] the partial solr document for the workflow document
+      # @return [Hash] the partial solr document for a single workflow process
       # rubocop:disable Metrics/AbcSize
       def to_solr
         return unless status

data/lib/dor_indexing/indexers/workflows_indexer.rb

@@ -2,7 +2,7 @@
 
 class DorIndexing
   module Indexers
-    # Indexes the objects position in workflows
+    # Indexes the object's state in the most recent execution of every one of its workflows
     class WorkflowsIndexer
       attr_reader :id
 
@@ -11,7 +11,7 @@ class DorIndexing
         @workflow_client = workflow_client
       end
 
-      # @return [Hash] the partial solr document for workflow concerns
+      # @return [Hash] the partial solr document for workflows concerns
       def to_solr
         WorkflowSolrDocument.new do |combined_doc|
           workflows.each do |wf|
@@ -30,7 +30,6 @@ class DorIndexing
         all_workflows.workflows
       end
 
-      # TODO: remove Dor::Workflow::Document
       # @return [Workflow::Response::Workflows]
       def all_workflows
         @all_workflows ||= workflow_client.workflow_routes.all_workflows pid: id

data/lib/dor_indexing/selectors/event_selector.rb

@@ -61,7 +61,7 @@ class DorIndexing
 
           event_dates = Array(event.date) + Array(event.parallelEvent&.map(&:date))
           event_dates.flatten.compact.find do |date|
-            date_type(date).nil?
+            date_type(date).blank?
           end
         end
       end

data/lib/dor_indexing/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class DorIndexing
-  VERSION = '1.3.1'
+  VERSION = '1.4.1'
 end

data/lib/dor_indexing.rb

@@ -1,14 +1,18 @@
 # frozen_string_literal: true
 
 require 'zeitwerk'
-require 'stanford-mods'
-require 'cocina/models'
-require 'solrizer'
-require 'marc/vocab'
-require 'honeybadger'
 
 Zeitwerk::Loader.for_gem.setup
 
+# Zeitwerk doesn't auto-load these dependencies
+require 'active_support'
+require 'active_support/core_ext/object/blank'
+require 'active_support/core_ext/enumerable'
+require 'active_support/core_ext/string'
+require 'cocina/models'
+require 'honeybadger'
+require 'marc/vocab'
+
 # Builds solr documents for indexing.
 class DorIndexing
   # @return [Hash] the solr document

metadata

@@ -1,29 +1,43 @@
 --- !ruby/object:Gem::Specification
 name: dor_indexing
 version: !ruby/object:Gem::Version
-  version: 1.3.1
+  version: 1.4.1
 platform: ruby
 authors:
 - Justin Littman
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-01-31 00:00:00.000000000 Z
+date: 2024-03-11 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: cocina-models
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.95.0
+        version: 0.95.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.95.0
+        version: 0.95.1
 - !ruby/object:Gem::Dependency
   name: dor-workflow-client
   requirement: !ruby/object:Gem::Requirement
@@ -66,20 +80,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 0.3.0
-- !ruby/object:Gem::Dependency
-  name: solrizer
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: stanford-mods
   requirement: !ruby/object:Gem::Requirement
@@ -140,17 +140,17 @@ files:
 - lib/dor_indexing/indexers/basic_indexer.rb
 - lib/dor_indexing/indexers/collection_title_indexer.rb
 - lib/dor_indexing/indexers/composite_indexer.rb
-- lib/dor_indexing/indexers/content_metadata_indexer.rb
 - lib/dor_indexing/indexers/default_object_rights_indexer.rb
 - lib/dor_indexing/indexers/descriptive_metadata_indexer.rb
 - lib/dor_indexing/indexers/embargo_metadata_indexer.rb
 - lib/dor_indexing/indexers/identifiable_indexer.rb
 - lib/dor_indexing/indexers/identity_metadata_indexer.rb
-- lib/dor_indexing/indexers/process_indexer.rb
+- lib/dor_indexing/indexers/object_files_indexer.rb
 - lib/dor_indexing/indexers/releasable_indexer.rb
 - lib/dor_indexing/indexers/rights_metadata_indexer.rb
 - lib/dor_indexing/indexers/role_metadata_indexer.rb
 - lib/dor_indexing/indexers/workflow_indexer.rb
+- lib/dor_indexing/indexers/workflow_process_indexer.rb
 - lib/dor_indexing/indexers/workflows_indexer.rb
 - lib/dor_indexing/marc_country.rb
 - lib/dor_indexing/selectors/event_selector.rb