dor_indexing 1.4.0 → 1.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 108a49c639925b8e1ba4e892d0ed3e4d903f7e741311f480ce85dd1be88d17c0
-  data.tar.gz: 5483c10c3b7fa972097e6b8f8cc889a6abc8a67e82bc864253ea003b97e6e578
+  metadata.gz: ae485a8233c79356bffbc42bef8d8e9f3ef1afbf3db962a2ba43b4ce522d7cd7
+  data.tar.gz: 1a05728e58b24d5f94164881a92326c9232402e241ce589dab14231e448ce60a
 SHA512:
-  metadata.gz: d2f7554c2a2d7dc5ab0eebe685b309f88706cef647ee0aeeeded3da2dc252016b7b43b4328303cfcc0da63c6c45d89ae1f883b6e120f982bcabf750c2a90040a
-  data.tar.gz: 5fdf32e3282b995903bc70892cc0baa9c8db8139668c40fbc92f1aff0ee0e40957c3242f07bffcd5d9512bf748697024c407f1708109f4a2837f638ea49012a3
+  metadata.gz: 24cfdc3e6be2af97c092e893825af54f8e3e3e47d65b9b955ea90c4ebda86072dbd87f32e2b3778e5fbee005be00c6877efac710e4d87b178f2521cee42f8b62
+  data.tar.gz: 7a1fc488f95678830e07fb919371e3ef8f5125d8bfcbf40d62109c51f87203fb6c424bef4da4fd8b7a9ec77a87bfee3f92274325482ab58d602599d069bbafe7

data/Gemfile.lock

@@ -1,9 +1,10 @@
 PATH
   remote: .
   specs:
-    dor_indexing (1.4.0)
+    dor_indexing (1.5.0)
       activesupport
-      cocina-models (~> 0.95.0)
+      cocina-models (~> 0.95.1)
+      dor-services-client (~> 14.0)
       dor-workflow-client (~> 7.0)
       honeybadger
       marc-vocab (~> 0.3.0)
@@ -13,7 +14,7 @@ PATH
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (7.1.3)
+    activesupport (7.1.3.2)
       base64
       bigdecimal
       concurrent-ruby (~> 1.0, >= 1.0.2)
@@ -26,9 +27,9 @@ GEM
     ast (2.4.2)
     attr_extras (7.1.0)
     base64 (0.2.0)
-    bigdecimal (3.1.6)
+    bigdecimal (3.1.7)
     byebug (11.1.3)
-    cocina-models (0.95.0)
+    cocina-models (0.95.1)
       activesupport
       deprecation
       dry-struct (~> 1.0)
@@ -51,6 +52,13 @@ GEM
       activesupport
     diff-lcs (1.5.1)
     docile (1.4.0)
+    dor-services-client (14.4.0)
+      activesupport (>= 4.2, < 8)
+      cocina-models (~> 0.95.1)
+      deprecation
+      faraday (~> 2.0)
+      faraday-retry
+      zeitwerk (~> 2.1)
     dor-workflow-client (7.0.2)
       activesupport (>= 3.2.1, < 8)
       deprecation (>= 0.99.0)
@@ -58,8 +66,7 @@ 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 +97,8 @@ GEM
       net-http
     faraday-retry (2.2.0)
       faraday (~> 2.0)
-    honeybadger (5.4.1)
-    i18n (1.14.1)
+    honeybadger (5.8.0)
+    i18n (1.14.4)
       concurrent-ruby (~> 1.0)
     ice_nine (0.11.2)
     iso-639 (0.3.6)
@@ -100,7 +107,7 @@ GEM
       multi_json
     language_server-protocol (3.17.0.3)
     marc-vocab (0.3.0)
-    minitest (5.22.2)
+    minitest (5.22.3)
     mods (3.0.4)
       edtf (~> 3.0)
       iso-639
@@ -110,9 +117,9 @@ GEM
     mutex_m (0.2.0)
     net-http (0.4.1)
       uri
-    nokogiri (1.16.2-x86_64-darwin)
+    nokogiri (1.16.3-x86_64-darwin)
       racc (~> 1.4)
-    nokogiri (1.16.2-x86_64-linux)
+    nokogiri (1.16.3-x86_64-linux)
       racc (~> 1.4)
     nom-xml (1.2.0)
       i18n
@@ -144,10 +151,10 @@ GEM
     rspec-mocks (3.13.0)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
-    rspec-support (3.13.0)
+    rspec-support (3.13.1)
     rss (0.3.0)
       rexml
-    rubocop (1.60.2)
+    rubocop (1.62.1)
       json (~> 2.3)
       language_server-protocol (>= 3.17.0)
       parallel (~> 1.10)
@@ -155,11 +162,11 @@ 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)
@@ -167,12 +174,11 @@ 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)
@@ -186,7 +192,7 @@ GEM
       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)

data/README.md

@@ -26,12 +26,25 @@ If bundler is not being used to manage dependencies, install the gem by executin
 
 ## Usage
 
-DorIndexing that a configured Workflow Client and a Cocina Repository be injected.
+DorIndexing that a configured Workflow Client, DOR Services Client, and a Cocina Repository be injected.
 
 The Cocina Repository provides methods for finding Cocina objects and administrative tags. One possible implementation of a Cocina Repository would be to use DOR Services Client.
 
 ```ruby
 require 'dor_indexing'
 
-doc = DorIndexing.build(cocina_with_metadata:, workflow_client:, cocina_repository:)
+doc = DorIndexing.build(cocina_with_metadata:, workflow_client:, dor_services_client:, cocina_repository:)
 ```
+
+## Testing
+
+### Integration Testing with Solr
+
+We build and update the Solr index via dor-indexing-app amd dor-services-app, both of which use this gem for indexing logic.
+
+Argo is the blacklight app that uses the Solr index extensively, and it already has the docker containers to create new test objects in dor-services-app and index them (via dor_indexing_app to Solr).  And Argo is the app built on top of the Solr index, so a good place to check results.
+
+To ensure our indexing behavior produces the desired results, it was easiest to put
+the full stack integration tests in the argo repository -- they can be found in
+https://github.com/sul-dlss/argo/tree/main/spec/features/indexing_xxx_spec.rb
+

data/dor_indexing.gemspec

@@ -31,11 +31,12 @@ Gem::Specification.new do |spec|
   spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
-  spec.add_dependency 'activesupport' # for blank? method
-  spec.add_dependency 'cocina-models', '~> 0.95.0'
+  spec.add_dependency 'activesupport'
+  spec.add_dependency 'cocina-models', '~> 0.95.1'
+  spec.add_dependency 'dor-services-client', '~> 14.0'
   spec.add_dependency 'dor-workflow-client', '~> 7.0'
   spec.add_dependency 'honeybadger'
-  spec.add_dependency 'marc-vocab', '~> 0.3.0' # for marcgac and marccountry
+  spec.add_dependency 'marc-vocab', '~> 0.3.0'
   spec.add_dependency 'stanford-mods'
   spec.add_dependency 'zeitwerk'
 end

data/lib/dor_indexing/builders/document_builder.rb

@@ -48,17 +48,18 @@ class DorIndexing
 
       @@parent_collections = {} # rubocop:disable Style/ClassVars
 
-      def self.for(model:, workflow_client:, cocina_repository:)
-        new(model:, workflow_client:, cocina_repository:).for
+      def self.for(model:, workflow_client:, dor_services_client:, cocina_repository:)
+        new(model:, workflow_client:, dor_services_client:, cocina_repository:).for
       end
 
       def self.reset_parent_collections
         @@parent_collections = {} # rubocop:disable Style/ClassVars
       end
 
-      def initialize(model:, workflow_client:, cocina_repository:)
+      def initialize(model:, workflow_client:, dor_services_client:, cocina_repository:)
         @model = model
         @workflow_client = workflow_client
+        @dor_services_client = dor_services_client
         @cocina_repository = cocina_repository
       end
 
@@ -69,12 +70,13 @@ class DorIndexing
                                          parent_collections:,
                                          administrative_tags:,
                                          workflow_client:,
+                                         dor_services_client:,
                                          cocina_repository:)
       end
 
       private
 
-      attr_reader :model, :workflow_client, :cocina_repository
+      attr_reader :model, :workflow_client, :dor_services_client, :cocina_repository
 
       def id
         model.externalIdentifier

data/lib/dor_indexing/indexers/descriptive_metadata_indexer.rb

@@ -25,11 +25,9 @@ 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, # DEPRECATED - 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,

data/lib/dor_indexing/indexers/identifiable_indexer.rb

@@ -18,14 +18,13 @@ class DorIndexing
       @@apo_hash = {} # rubocop:disable Style/ClassVars
 
       # @return [Hash] the partial solr document for identifiable concerns
-      def to_solr # rubocop:disable Metrics/AbcSize
+      def to_solr
         {}.tap do |solr_doc|
           add_apo_titles(solr_doc, cocina.administrative.hasAdminPolicy)
 
           solr_doc['metadata_source_ssim'] = identity_metadata_sources unless cocina.is_a? Cocina::Models::AdminPolicyWithMetadata
           solr_doc['druid_prefixed_ssi'] = cocina.externalIdentifier
           solr_doc['druid_bare_ssi'] = cocina.externalIdentifier.delete_prefix('druid:')
-          solr_doc['objectId_tesim'] = [cocina.externalIdentifier, cocina.externalIdentifier.delete_prefix('druid:')] # DEPRECATED
         end
       end
 

data/lib/dor_indexing/indexers/releasable_indexer.rb

@@ -4,11 +4,12 @@ class DorIndexing
   module Indexers
     # Indexes the object's release tags
     class ReleasableIndexer
-      attr_reader :cocina, :parent_collections
+      attr_reader :cocina, :parent_collections, :dor_services_client
 
-      def initialize(cocina:, parent_collections:, **)
+      def initialize(cocina:, parent_collections:, dor_services_client:, **)
         @cocina = cocina
         @parent_collections = parent_collections
+        @dor_services_client = dor_services_client
       end
 
       # @return [Hash] the partial solr document for releasable concerns
@@ -40,8 +41,11 @@ class DorIndexing
 
       def tags_from_collection
         parent_collections.each_with_object({}) do |collection, result|
-          Array(collection.administrative.releaseTags)
-            .select { |tag| tag.what == 'collection' }
+          collection_object_client = dor_services_client.object(collection.externalIdentifier)
+          collection_object_client
+            .release_tags
+            .list
+            .select { |tag| tag.what == 'self' }
             .group_by(&:to).map do |project, releases_for_project|
               result[project] = releases_for_project.max_by(&:date)
             end
@@ -49,13 +53,14 @@ class DorIndexing
       end
 
       def tags_from_item
-        released_for.group_by(&:to).transform_values do |releases_for_project|
-          releases_for_project.max_by(&:date)
-        end
-      end
-
-      def released_for
-        Array(cocina.administrative.releaseTags)
+        object_client = dor_services_client.object(cocina.externalIdentifier)
+        object_client
+          .release_tags
+          .list
+          .select { |tag| tag.what == 'self' }
+          .group_by(&:to).transform_values do |releases_for_project|
+            releases_for_project.max_by(&:date)
+          end
       end
     end
   end

data/lib/dor_indexing/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class DorIndexing
-  VERSION = '1.4.0'
+  VERSION = '1.5.0'
 end

data/lib/dor_indexing.rb

@@ -1,18 +1,29 @@
 # frozen_string_literal: true
 
 require 'zeitwerk'
-require 'stanford-mods'
-require 'cocina/models'
-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 'dor/services/client'
+require 'honeybadger'
+require 'marc/vocab'
+
 # Builds solr documents for indexing.
 class DorIndexing
   # @return [Hash] the solr document
-  def self.build(cocina_with_metadata:, workflow_client:, cocina_repository:)
+  def self.build(cocina_with_metadata:, workflow_client:, dor_services_client:, cocina_repository:)
     Honeybadger.context({ identifier: cocina_with_metadata.externalIdentifier })
-    DorIndexing::Builders::DocumentBuilder.for(model: cocina_with_metadata, workflow_client:, cocina_repository:).to_solr
+    DorIndexing::Builders::DocumentBuilder.for(
+      model: cocina_with_metadata,
+      workflow_client:,
+      dor_services_client:,
+      cocina_repository:
+    ).to_solr
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: dor_indexing
 version: !ruby/object:Gem::Version
-  version: 1.4.0
+  version: 1.5.0
 platform: ruby
 authors:
 - Justin Littman
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-02-17 00:00:00.000000000 Z
+date: 2024-03-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -30,14 +30,28 @@ dependencies:
     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-services-client
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '14.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '14.0'
 - !ruby/object:Gem::Dependency
   name: dor-workflow-client
   requirement: !ruby/object:Gem::Requirement
@@ -180,7 +194,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.13
+rubygems_version: 3.4.18
 signing_key:
 specification_version: 4
 summary: Library for creating Solr documents for SDR indexing.