datacite 0.7.0 → 0.8.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 66112a3d3c17ff31745747464ca733f9154f41e1b135a9494a85f5a3c113c3d1
-  data.tar.gz: 77b577598b0e2ce56ef4123c6f8353d1079c254c43b2613898702e25f40a971b
+  metadata.gz: a4e41bbe60c1bb9cab7315f2a5b48348cec51cfdd41950f3daa7097cb7135e6d
+  data.tar.gz: 30aff4a9d851eea079ab657b19765b6c6027ced8e9a20dff62f4a40f3a898ccd
 SHA512:
-  metadata.gz: 18f4f54d95b7cfc2678a2068fd2a084c48d12707f451d5b8d5f84a9978a6a6d9d9739d3a21e5284cc25de3637124a46d597ab00b9e998e496afbaca11849d7d7
-  data.tar.gz: 90eb6d4920b6f4006c4bf0a2e0ffbca77c8fdc3abc0160400a5a7ba3ab2124075f6f12401a8e64b5e16318551bdac633bc2e91a95e996cc71483050d4f2d1c84
+  metadata.gz: c636aa314c1e154c62badf517aded67ae2e00e69172563a0207bb288513e0d577e5c548616ecd4c6b44fbc5df2ae40974435e462ef9e4dba22b43d6ef4b17765
+  data.tar.gz: 8e61aba2ca1229458c456c4293c2ebce17c63ad4e7eff9c779c74f65861573e7f3933579f71435cb60cfde265e85baad91ae4bcd11895a930599bd6324182e20

data/.rubocop.yml

@@ -19,6 +19,9 @@ RSpec/MultipleMemoizedHelpers:
 Layout/LineLength:
   Max: 120
 
+RSpec/ExampleLength:
+  Enabled: false
+
 Gemspec/DeprecatedAttributeAssignment: # new in 1.30
   Enabled: true
 Gemspec/DevelopmentDependencies: # new in 1.44

data/Gemfile

@@ -8,6 +8,7 @@ gemspec
 # Specify development dependencies here
 gem 'base64'
 gem 'byebug'
+gem 'cocina-models' # only used in tests
 gem 'rake', '~> 13.0'
 gem 'rspec', '~> 3.0'
 gem 'rubocop', '~> 1.7'

data/Gemfile.lock

@@ -1,59 +1,156 @@
 PATH
   remote: .
   specs:
-    datacite (0.7.0)
+    datacite (0.8.1)
+      activesupport
       dry-monads (~> 1.3)
       faraday (~> 2.0)
+      json_schemer
       zeitwerk (~> 2.4)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    addressable (2.8.7)
-      public_suffix (>= 2.0.2, < 7.0)
+    activesupport (8.1.2)
+      base64
+      bigdecimal
+      concurrent-ruby (~> 1.0, >= 1.3.1)
+      connection_pool (>= 2.2.5)
+      drb
+      i18n (>= 1.6, < 2)
+      json
+      logger (>= 1.4.2)
+      minitest (>= 5.1)
+      securerandom (>= 0.3)
+      tzinfo (~> 2.0, >= 2.0.5)
+      uri (>= 0.13.1)
+    addressable (2.8.8)
+      public_suffix (>= 2.0.2, < 8.0)
     ast (2.4.3)
+    attr_extras (7.1.0)
     base64 (0.3.0)
-    bigdecimal (3.3.1)
-    byebug (12.0.0)
-    concurrent-ruby (1.3.5)
-    crack (1.0.0)
+    bigdecimal (4.0.1)
+    byebug (13.0.0)
+      reline (>= 0.6.0)
+    cocina-models (0.110.1)
+      activesupport
+      deprecation
+      dry-struct (~> 1.0)
+      dry-types (~> 1.1)
+      edtf
+      equivalent-xml
+      i18n
+      json_schemer (~> 2.0)
+      jsonpath
+      marc (~> 1.3)
+      nokogiri
+      super_diff
+      thor
+      zeitwerk (~> 2.1)
+    concurrent-ruby (1.3.6)
+    connection_pool (3.0.2)
+    crack (1.0.1)
       bigdecimal
       rexml
+    deprecation (1.1.0)
+      activesupport
     diff-lcs (1.6.2)
     docile (1.4.1)
-    dry-core (1.1.0)
+    drb (2.2.3)
+    dry-core (1.2.0)
       concurrent-ruby (~> 1.0)
       logger
       zeitwerk (~> 2.6)
+    dry-inflector (1.3.1)
+    dry-logic (1.6.0)
+      bigdecimal
+      concurrent-ruby (~> 1.0)
+      dry-core (~> 1.1)
+      zeitwerk (~> 2.6)
     dry-monads (1.9.0)
       concurrent-ruby (~> 1.0)
       dry-core (~> 1.1)
       zeitwerk (~> 2.6)
-    faraday (2.14.0)
+    dry-struct (1.8.0)
+      dry-core (~> 1.1)
+      dry-types (~> 1.8, >= 1.8.2)
+      ice_nine (~> 0.11)
+      zeitwerk (~> 2.6)
+    dry-types (1.9.1)
+      bigdecimal (>= 3.0)
+      concurrent-ruby (~> 1.0)
+      dry-core (~> 1.0)
+      dry-inflector (~> 1.0)
+      dry-logic (~> 1.4)
+      zeitwerk (~> 2.6)
+    edtf (3.2.0)
+      activesupport (>= 3.0, < 9.0)
+    equivalent-xml (0.6.0)
+      nokogiri (>= 1.4.3)
+    faraday (2.14.1)
       faraday-net_http (>= 2.0, < 3.5)
       json
       logger
-    faraday-net_http (3.4.1)
-      net-http (>= 0.5.0)
+    faraday-net_http (3.4.2)
+      net-http (~> 0.5)
+    hana (1.3.7)
     hashdiff (1.2.1)
-    json (2.15.1)
+    i18n (1.14.8)
+      concurrent-ruby (~> 1.0)
+    ice_nine (0.11.2)
+    io-console (0.8.2)
+    json (2.18.1)
+    json_schemer (2.5.0)
+      bigdecimal
+      hana (~> 1.3)
+      regexp_parser (~> 2.0)
+      simpleidn (~> 0.2)
+    jsonpath (1.1.5)
+      multi_json
     language_server-protocol (3.17.0.5)
     lint_roller (1.1.0)
     logger (1.7.0)
-    net-http (0.6.0)
-      uri
+    marc (1.4.0)
+      nokogiri (~> 1.0)
+      rexml
+    minitest (6.0.1)
+      prism (~> 1.5)
+    multi_json (1.19.1)
+    net-http (0.9.1)
+      uri (>= 0.11.1)
+    nokogiri (1.19.0-aarch64-linux-gnu)
+      racc (~> 1.4)
+    nokogiri (1.19.0-aarch64-linux-musl)
+      racc (~> 1.4)
+    nokogiri (1.19.0-arm-linux-gnu)
+      racc (~> 1.4)
+    nokogiri (1.19.0-arm-linux-musl)
+      racc (~> 1.4)
+    nokogiri (1.19.0-arm64-darwin)
+      racc (~> 1.4)
+    nokogiri (1.19.0-x86_64-darwin)
+      racc (~> 1.4)
+    nokogiri (1.19.0-x86_64-linux-gnu)
+      racc (~> 1.4)
+    nokogiri (1.19.0-x86_64-linux-musl)
+      racc (~> 1.4)
+    optimist (3.2.1)
     parallel (1.27.0)
-    parser (3.3.9.0)
+    parser (3.3.10.1)
       ast (~> 2.4.1)
       racc
-    prism (1.6.0)
-    public_suffix (6.0.2)
+    patience_diff (1.2.0)
+      optimist (~> 3.0)
+    prism (1.9.0)
+    public_suffix (7.0.2)
     racc (1.8.1)
     rainbow (3.1.1)
-    rake (13.3.0)
+    rake (13.3.1)
     regexp_parser (2.11.3)
+    reline (0.6.3)
+      io-console (~> 0.5)
     rexml (3.4.4)
-    rspec (3.13.1)
+    rspec (3.13.2)
       rspec-core (~> 3.13.0)
       rspec-expectations (~> 3.13.0)
       rspec-mocks (~> 3.13.0)
@@ -62,11 +159,11 @@ GEM
     rspec-expectations (3.13.5)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
-    rspec-mocks (3.13.6)
+    rspec-mocks (3.13.7)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
-    rspec-support (3.13.6)
-    rubocop (1.81.1)
+    rspec-support (3.13.7)
+    rubocop (1.84.1)
       json (~> 2.3)
       language_server-protocol (~> 3.17.0.2)
       lint_roller (~> 1.1.0)
@@ -74,46 +171,58 @@ GEM
       parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 2.9.3, < 3.0)
-      rubocop-ast (>= 1.47.1, < 2.0)
+      rubocop-ast (>= 1.49.0, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 2.4.0, < 4.0)
-    rubocop-ast (1.47.1)
+    rubocop-ast (1.49.0)
       parser (>= 3.3.7.2)
-      prism (~> 1.4)
+      prism (~> 1.7)
     rubocop-rake (0.7.1)
       lint_roller (~> 1.1)
       rubocop (>= 1.72.1)
-    rubocop-rspec (3.7.0)
+    rubocop-rspec (3.9.0)
       lint_roller (~> 1.1)
-      rubocop (~> 1.72, >= 1.72.1)
+      rubocop (~> 1.81)
     ruby-progressbar (1.13.0)
+    securerandom (0.4.1)
     simplecov (0.22.0)
       docile (~> 1.1)
       simplecov-html (~> 0.11)
       simplecov_json_formatter (~> 0.1)
     simplecov-html (0.13.2)
     simplecov_json_formatter (0.1.4)
+    simpleidn (0.2.3)
+    super_diff (0.18.0)
+      attr_extras (>= 6.2.4)
+      diff-lcs
+      patience_diff
+    thor (1.5.0)
+    tzinfo (2.0.6)
+      concurrent-ruby (~> 1.0)
     unicode-display_width (3.2.0)
       unicode-emoji (~> 4.1)
-    unicode-emoji (4.1.0)
-    uri (1.0.4)
-    webmock (3.25.1)
+    unicode-emoji (4.2.0)
+    uri (1.1.1)
+    webmock (3.26.1)
       addressable (>= 2.8.0)
       crack (>= 0.3.2)
       hashdiff (>= 0.4.0, < 2.0.0)
-    zeitwerk (2.7.3)
+    zeitwerk (2.7.4)
 
 PLATFORMS
-  arm64-darwin-23
-  arm64-darwin-24
-  x86_64-darwin-19
-  x86_64-darwin-21
-  x86_64-darwin-22
-  x86_64-linux
+  aarch64-linux-gnu
+  aarch64-linux-musl
+  arm-linux-gnu
+  arm-linux-musl
+  arm64-darwin
+  x86_64-darwin
+  x86_64-linux-gnu
+  x86_64-linux-musl
 
 DEPENDENCIES
   base64
   byebug
+  cocina-models
   datacite!
   rake (~> 13.0)
   rspec (~> 3.0)
@@ -124,4 +233,4 @@ DEPENDENCIES
   webmock (~> 3.13)
 
 BUNDLED WITH
-   2.7.2
+  4.0.6

data/README.md

@@ -97,6 +97,26 @@ result.either(
 )
 ```
 
+## Working with Cocina
+
+### Validating
+
+This gem provides a method for mapping and validating a `Cocina::Models::DRO` object to a DataCite request based on the DataCite JSON Schema (v4.6), without sending any data to the DataCite API:
+
+```ruby
+cocina_object = Cocina::Models::DRO.new(...)
+validator = Datacite::Validators::CocinaValidator.new(cocina_object:)
+puts validator.errors.join(', ') unless validator.valid?
+```
+
+NOTE: A Datacite request payload can be validated without first translating from Cocina if you build the request manually or use your own metadata mapping library, e.g.:
+
+```ruby
+datacite_attributes = { ... }
+validator = Datacite::Validators::AttributesValidator.new(attributes: datacite_attributes)
+puts validator.errors.join(', ') unless validator.valid?
+```
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.

data/datacite.gemspec

@@ -28,8 +28,10 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
+  spec.add_dependency 'activesupport'
   spec.add_dependency 'dry-monads', '~> 1.3'
   spec.add_dependency 'faraday', '~> 2.0'
+  spec.add_dependency 'json_schemer'
   spec.add_dependency 'zeitwerk', '~> 2.4'
   spec.metadata['rubygems_mfa_required'] = 'true'
 end

data/lib/datacite/mapping/from_cocina/alternate_identifiers.rb

@@ -0,0 +1,30 @@
+# frozen_string_literal: true
+
+module Datacite
+  module Mapping
+    module FromCocina
+      # Maps alternative identifiers from cocina description to DataCite JSON
+      class AlternateIdentifiers
+        # @param [Cocina::Models::Description] description
+        def self.build(...)
+          new(...).call
+        end
+
+        def initialize(description:)
+          @description = description
+        end
+
+        attr_reader :description
+
+        delegate :purl, to: :description
+
+        def call
+          [{
+            alternateIdentifier: purl,
+            alternateIdentifierType: 'PURL'
+          }]
+        end
+      end
+    end
+  end
+end

data/lib/datacite/mapping/from_cocina/attributes.rb

@@ -0,0 +1,74 @@
+# frozen_string_literal: true
+
+require 'active_support/all'
+require 'cocina/models'
+
+module Datacite
+  module Mapping
+    module FromCocina
+      # Transform the Cocina::Models::DRO to a DataCite request attributes payload
+      class Attributes
+        # @param [Cocina::Models::DRO] cocina_object
+        # @return [Hash] Hash of DataCite attributes, conforming to the DataCite API Schema
+        def self.build(...)
+          new(...).call
+        end
+
+        def initialize(cocina_object:)
+          @cocina_object = cocina_object
+
+          # Set the time zone
+          Time.zone = 'Pacific Time (US & Canada)'
+        end
+
+        attr_reader :cocina_object
+
+        delegate :access, :description, :identification, to: :cocina_object
+
+        def call # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
+          {
+            event: 'publish',
+            url: description.purl,
+            identifiers: Identifiers.build(identification:),
+            titles: Titles.build(description:),
+            publisher: { name: 'Stanford Digital Repository' }, # per DataCite schema
+            publicationYear: publication_year,
+            subjects: Subject.build(description:),
+            dates: Date.build(cocina_object:),
+            language: 'en',
+            types: Types.build(description:),
+            alternateIdentifiers: AlternateIdentifiers.build(description:),
+            relatedIdentifiers: related_identifiers,
+            rightsList: RightsList.build(access:),
+            descriptions: Descriptions.build(description:),
+            relatedItems: related_items,
+            schemaVersion: 'http://datacite.org/schema/kernel-4'
+          }.merge(ContributorAttributes.build(description:)).compact
+        end
+
+        private
+
+        def publication_year
+          date = if access.embargo
+                   access.embargo.releaseDate.to_datetime
+                 else
+                   Time.zone.today
+                 end
+          date.year.to_s
+        end
+
+        def related_identifiers
+          Array(description&.relatedResource).filter_map do |related_resource|
+            RelatedResource.related_identifier_attributes(related_resource:)
+          end
+        end
+
+        def related_items
+          Array(description&.relatedResource).filter_map do |related_resource|
+            RelatedResource.related_item_attributes(related_resource:)
+          end
+        end
+      end
+    end
+  end
+end

data/lib/datacite/mapping/from_cocina/contributor_attributes.rb

@@ -0,0 +1,209 @@
+# frozen_string_literal: true
+
+module Datacite
+  module Mapping
+    module FromCocina
+      # Transform the Cocina::Models::Description to contributor attributes
+      #  see https://support.datacite.org/reference/dois-2#put_dois-id
+      class ContributorAttributes # rubocop:disable Metrics/ClassLength
+        DATACITE_PERSON_CONTRIBUTOR_TYPES = {
+          'copyright holder' => 'RightsHolder',
+          'compiler' => 'DataCollector',
+          'editor' => 'Editor',
+          'organizer' => 'Supervisor',
+          'research team head' => 'ProjectLeader',
+          'researcher' => 'Researcher'
+        }.freeze
+
+        DATACITE_ORGANIZATION_CONTRIBUTOR_TYPES = {
+          'copyright holder' => 'RightsHolder',
+          'compiler' => 'DataCollector',
+          'distributor' => 'Distributor',
+          'host institution' => 'HostingInstitution',
+          'issuing body' => 'Distributor',
+          'publisher' => 'Distributor',
+          'researcher' => 'ResearchGroup',
+          'sponsor' => 'Sponsor'
+        }.freeze
+
+        # @param [Cocina::Models::Description] description
+        # @return [Hash] Hash of DataCite attributes containing creators, contributors, and fundingReferences keys
+        def self.build(...)
+          new(...).call
+        end
+
+        def initialize(description:)
+          @description = description
+        end
+
+        # @return [Hash] Hash of DataCite attributes containing creators, contributors, and fundingReferences keys
+        def call
+          {
+            creators: datacite_creators,
+            contributors: datacite_contributors,
+            fundingReferences: datacite_funders
+          }
+        end
+
+        private
+
+        attr_reader :description
+
+        def cocina_creators
+          @cocina_creators ||= Array(description.contributor).select do |cocina_contributor|
+            datacite_creator?(cocina_contributor)
+          end
+        end
+
+        def cocina_contributors
+          @cocina_contributors ||= Array(description.contributor).select do |cocina_contributor|
+            datacite_contributor?(cocina_contributor)
+          end
+        end
+
+        def cocina_funders
+          @cocina_funders ||= Array(description.contributor).select do |cocina_contributor|
+            datacite_funder?(cocina_contributor)
+          end
+        end
+
+        def datacite_creator?(cocina_contributor)
+          !datacite_funder?(cocina_contributor) && !datacite_contributor?(cocina_contributor)
+        end
+
+        def datacite_funder?(cocina_contributor)
+          marc_relator(cocina_contributor) == 'funder'
+        end
+
+        def datacite_contributor?(cocina_contributor)
+          marc_relator(cocina_contributor) == 'publisher' || degree_committee_member?(cocina_contributor)
+        end
+
+        def datacite_creators
+          @datacite_creators ||= cocina_creators.map { |cocina_creator| datacite_creator(cocina_creator) }.uniq
+        end
+
+        def datacite_contributors
+          @datacite_contributors ||= cocina_contributors.map do |cocina_contributor|
+            datacite_contributor(cocina_contributor)
+          end.uniq
+        end
+
+        def datacite_funders
+          @datacite_funders ||= cocina_funders.map { |cocina_funder| { funderName: cocina_funder.name.first.value } }
+        end
+
+        def datacite_creator(cocina_contributor)
+          return personal_name(cocina_contributor) if person?(cocina_contributor)
+
+          organizational_name(cocina_contributor)
+        end
+
+        def person?(cocina_contributor)
+          cocina_contributor.type == 'person'
+        end
+
+        def datacite_contributor(cocina_contributor)
+          datacite_creator(cocina_contributor).merge({ contributorType: contributor_type(cocina_contributor) })
+        end
+
+        def personal_name(cocina_contributor) # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
+          {
+            nameType: 'Personal',
+            nameIdentifiers: name_identifiers(cocina_contributor).presence,
+            affiliation: affiliations(cocina_contributor).presence
+          }.tap do |name_hash|
+            # NOTE: This is needed for ETDs, for which we do not receive structured
+            #       contributor names from Axess for ETD readers
+            if cocina_contributor.name.first.structuredValue.empty?
+              name_hash[:name] = cocina_contributor.name.first.value
+            elsif (name = cocina_contributor.name.first.structuredValue.find { |part| part.type == 'name' }).present?
+              name_hash[:name] = name.value
+            else
+              forename = cocina_contributor.name.first.structuredValue.find { |part| part.type == 'forename' }
+              surname = cocina_contributor.name.first.structuredValue.find { |part| part.type == 'surname' }
+
+              name_hash[:name] = "#{surname.value}, #{forename.value}"
+              name_hash[:givenName] = forename.value
+              name_hash[:familyName] = surname.value
+            end
+          end
+            .compact
+        end
+
+        def organizational_name(cocina_contributor)
+          name = cocina_contributor.name.first.structuredValue.first || cocina_contributor.name.first
+          {
+            name: name.value,
+            nameType: 'Organizational',
+            nameIdentifiers: name_identifiers(name).presence
+          }.compact
+        end
+
+        def name_identifiers(cocina_contributor)
+          Array(cocina_contributor.identifier).map do |identifier|
+            {
+              nameIdentifier: identifier.value || identifier.uri,
+              nameIdentifierScheme: identifier.type,
+              schemeUri: identifier.source.uri
+            }.compact
+          end
+        end
+
+        def affiliations(cocina_contributor) # rubocop:disable Metrics/MethodLength
+          Array(cocina_contributor.affiliation).map do |affiliation|
+            institution = affiliation.structuredValue.find { |descriptive_value| descriptive_value.identifier.present? }
+            institution ||= affiliation # if no structured value with identifier, use the affiliation itself
+            identifier = institution.identifier.find { |id| id.type == 'ROR' }
+            next unless identifier&.uri
+
+            {
+              affiliationIdentifier: identifier.uri,
+              affiliationIdentifierScheme: 'ROR',
+              name: institution.value,
+              schemeUri: 'https://ror.org/'
+            }.compact
+          end
+        end
+
+        def contributor_type(cocina_contributor)
+          if person?(cocina_contributor)
+            return DATACITE_PERSON_CONTRIBUTOR_TYPES.fetch(marc_relator(cocina_contributor),
+                                                           'Other')
+          end
+
+          DATACITE_ORGANIZATION_CONTRIBUTOR_TYPES.fetch(marc_relator(cocina_contributor), 'Other')
+        end
+
+        # NOTE: This is how ETDs map to Cocina by way of MARC21 to MODS, where the
+        #       700$e and 700$4 subfields cannot be interpreted as pertaining to
+        #       the same role, so the Cocina winds up expressing this as two
+        #       roles, e.g.:
+        #
+        #   role: [
+        #     {
+        #       value: "degree committee member",
+        #     },
+        #     {
+        #       code: "ths",
+        #       source: {
+        #         code: "marcrelator",
+        #       },
+        #     }
+        #   ]
+        def degree_committee_member?(cocina_contributor)
+          cocina_contributor.role.any? { |contrib_role| contrib_role.value == 'degree committee member' } &&
+            cocina_contributor.role.any? do |contrib_role|
+              contrib_role.code == 'ths' && contrib_role.source.code == 'marcrelator'
+            end
+        end
+
+        def marc_relator(cocina_contributor)
+          Array(cocina_contributor.role).find do |role|
+            role&.source&.code == 'marcrelator'
+          end&.value
+        end
+      end
+    end
+  end
+end