bolognese 2.0.0 → 2.3.5

data/spec/author_utils_spec.rb

@@ -89,7 +89,7 @@ describe Bolognese::Metadata, vcr: true do
       subject = Bolognese::Metadata.new(input: input, from: "datacite")
       meta = Maremma.from_xml(subject.raw).fetch("resource", {})
       response = subject.get_authors(meta.dig("creators", "creator"))
-      expect(response).to eq([{"name" => "Enos, Ryan (Harvard University); Fowler, Anthony (University Of Chicago); Vavreck, Lynn (UCLA)", "nameIdentifiers" => [], "affiliation" => []}])
+      expect(response).to eq([{"name" => "Enos, Ryan (Harvard University); Fowler, Anthony (University of Chicago); Vavreck, Lynn (UCLA)", "nameIdentifiers" => [], "affiliation" => []}])
     end
 
     it "hyper-authorship" do
@@ -104,7 +104,7 @@ describe Bolognese::Metadata, vcr: true do
     it "is organization" do
       author = {"email"=>"info@ucop.edu", "creatorName"=> { "__content__" => "University of California, Santa Barbara", "nameType" => "Organizational" }, "role"=>{"namespace"=>"http://www.ngdc.noaa.gov/metadata/published/xsd/schema/resources/Codelist/gmxCodelists.xml#CI_RoleCode", "roleCode"=>"copyrightHolder"} }
       response = subject.get_one_author(author)
-      expect(response).to eq("nameType"=>"Organizational", "name"=>"University Of California, Santa Barbara", "nameIdentifiers" => [], "affiliation" => [])
+      expect(response).to eq("nameType"=>"Organizational", "name"=>"University of California, Santa Barbara", "nameIdentifiers" => [], "affiliation" => [])
     end
 
     it "name with affiliation" do
@@ -164,15 +164,16 @@ describe Bolognese::Metadata, vcr: true do
     input = fixture_path + 'datacite-example-ROR-nameIdentifiers.xml'
     subject = Bolognese::Metadata.new(input: input, from: "datacite")
     expect(subject.creators[2]).to eq("nameType"=>"Organizational", "name"=>"Gump South Pacific Research Station", "nameIdentifiers"=> [{"nameIdentifier"=>"https://ror.org/04sk0et52", "schemeUri"=>"https://ror.org", "nameIdentifierScheme"=>"ROR"}], "affiliation"=>[])
-    expect(subject.creators[3]).to eq("nameType"=>"Organizational", "name"=>"University Of Vic", "nameIdentifiers"=> [{"nameIdentifier"=>"https://ror.org/006zjws59", "schemeUri"=>"https://ror.org", "nameIdentifierScheme"=>"ROR"}], "affiliation"=>[])
-    expect(subject.creators[4]).to eq("nameType"=>"Organizational", "name"=>"University Of Kivu", "nameIdentifiers"=> [{"nameIdentifier"=>"https://ror.org/01qfhxr31", "schemeUri"=>"https://ror.org", "nameIdentifierScheme"=>"ROR"}], "affiliation"=>[])
+    expect(subject.creators[3]).to eq("nameType"=>"Organizational", "name"=>"University of Vic", "nameIdentifiers"=> [{"nameIdentifier"=>"https://ror.org/006zjws59", "schemeUri"=>"https://ror.org", "nameIdentifierScheme"=>"ROR"}], "affiliation"=>[])
+    expect(subject.creators[4]).to eq("nameType"=>"Organizational", "name"=>"University of Kivu", "nameIdentifiers"=> [{"nameIdentifier"=>"https://ror.org/01qfhxr31", "schemeUri"=>"https://ror.org", "nameIdentifierScheme"=>"ROR"}], "affiliation"=>[])
     expect(subject.creators[5]).to eq("nameType"=>"Organizational", "name"=>"សាកលវិទ្យាល័យកម្ពុជា", "nameIdentifiers"=> [{"nameIdentifier"=>"http://ror.org/025e3rc84", "nameIdentifierScheme"=>"RORS"}], "affiliation"=>[])
     expect(subject.creators[6]).to eq("nameType"=>"Organizational", "name"=>"جامعة زاخۆ", "nameIdentifiers"=> [{"nameIdentifier"=>"05sd1pz50", "schemeUri"=>"https://ror.org", "nameIdentifierScheme"=>"RORS"}], "affiliation"=>[])
+    expect(subject.creators[9]).to eq("nameType"=>"Organizational", "name"=>"Gump South Pacific Research Station", "nameIdentifiers"=> [{"nameIdentifier"=>"https://ror.org/04sk0et52", "schemeUri"=>"https://ror.org", "nameIdentifierScheme"=>"ROR"}], "affiliation"=>[])
     expect(subject.contributors.first).to eq("nameType"=>"Organizational", "name"=>" Nawroz University ", "nameIdentifiers"=> [{"nameIdentifier"=>"https://ror.org/04gp75d48", "schemeUri"=>"https://ror.org", "nameIdentifierScheme"=>"ROR"}], "affiliation"=>[], "contributorType"=>"Producer")
-    expect(subject.contributors.last).to eq("nameType"=>"Organizational", "name"=>"University Of Greenland (Https://Www.Uni.Gl/)", "nameIdentifiers"=> [{"nameIdentifier"=>"https://ror.org/00t5j6b61", "schemeUri"=>"https://ror.org", "nameIdentifierScheme"=>"ROR"}],"affiliation"=>[], "contributorType"=>"Sponsor")
+    expect(subject.contributors.last).to eq("nameType"=>"Organizational", "name"=>"University of Greenland (https://www.uni.gl/)", "nameIdentifiers"=> [{"nameIdentifier"=>"https://ror.org/00t5j6b61", "schemeUri"=>"https://ror.org", "nameIdentifierScheme"=>"ROR"}],"affiliation"=>[], "contributorType"=>"Sponsor")
   end
 
-  context "affiliationIdentifier" do
+  context "affiliationIdentifier/nameIdentifier" do
     let(:input) { fixture_path + 'datacite-example-ROR-nameIdentifiers.xml' }
     subject { Bolognese::Metadata.new(input: input, from: "datacite") }
 
@@ -207,6 +208,11 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.creators[8]["nameIdentifiers"]).to eq([{"nameIdentifier"=>"https://orcid.org/0000-0001-9998-0118", "schemeUri"=>"https://orcid.org", "nameIdentifierScheme"=>"ORCID"}])
     end
 
+    it "should normalize valid ORCID nameIdentifier with trailing slash" do
+      #"  0000-0001-9998-0118  ",  # Valid ORCID with leading/trailing spaces
+      expect(subject.creators[10]["nameIdentifiers"]).to eq([{"nameIdentifier"=>"https://orcid.org/0000-0001-9998-0117", "schemeUri"=>"https://orcid.org", "nameIdentifierScheme"=>"ORCID"}])
+    end
+
     it "should parse non ROR schema's without normalizing them" do
       input = fixture_path + 'datacite-example-ROR-nameIdentifiers.xml'
       subject = Bolognese::Metadata.new(input: input, from: "datacite")
@@ -250,4 +256,4 @@ describe Bolognese::Metadata, vcr: true do
       expect(response).to eq("Matt Jones and Peter Slaughter and {University of California, Santa Barbara}")
     end
   end
-end
+end

data/spec/datacite_utils_spec.rb

@@ -204,4 +204,154 @@ describe Bolognese::Metadata, vcr: true do
       )
     end
   end
-end
+
+  ### New DataCite 4.6 Features Tests ###
+
+  context "insert_resource_type with Project" do
+    it "supports Project as resourceTypeGeneral" do
+      # Mock the `types` hash to include Project
+      subject.instance_variable_set(:@types, {
+        "resourceTypeGeneral" => "Project",
+        "resourceType" => "Research Project"
+      })
+
+      # Generate XML using the insert_resource_type method
+      xml = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') { |xml| subject.insert_resource_type(xml) }.to_xml
+
+      response = Maremma.from_xml(xml)
+
+      # Expect `Project` in resourceTypeGeneral and `Research Project` as the content
+      expect(response["resourceType"]).to eq(
+        "resourceTypeGeneral" => "Project",
+        "__content__" => "Research Project"
+      )
+    end
+  end
+
+  context "insert_resource_type with Award" do
+    it "supports Award as resourceTypeGeneral" do
+      # Mock the `types` hash to include Award
+      subject.instance_variable_set(:@types, {
+        "resourceTypeGeneral" => "Award",
+        "resourceType" => "Nobel Prize"
+      })
+
+      # Generate XML using the insert_resource_type method
+      xml = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') { |xml| subject.insert_resource_type(xml) }.to_xml
+
+      response = Maremma.from_xml(xml)
+
+      # Expect `Award` in resourceTypeGeneral and `Nobel Prize` as the content
+      expect(response["resourceType"]).to eq(
+        "resourceTypeGeneral" => "Award",
+        "__content__" => "Nobel Prize"
+      )
+    end
+  end
+
+  context "insert_resource_type when resourceType is available, but using schemaOrg (via SO_TO_DC_TRANSLATIONS) when resourceTypeGeneral is unavailable" do
+    it "supports schemaOrg value as resourceTypeGeneral" do
+      # Mock the `types` hash to include the necessary values
+      subject.instance_variable_set(:@types, {
+        "schemaOrg" => "BlogPosting",
+        "resourceType" => "This dataset contains all projects funded by the European Union under the fifth framework programme for research and technological development (FP5) from 1998 to 2002."
+      })
+
+      # Generate XML using the insert_resource_type method
+      xml = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') { |xml| subject.insert_resource_type(xml) }.to_xml
+
+      response = Maremma.from_xml(xml)
+
+      # Expect `Text` in resourceTypeGeneral (via SO_TP_DC_TRANSLATIONS) and `This dataset contains all projects funded...` as the content
+      expect(response["resourceType"]).to eq(
+        "resourceTypeGeneral" => "Text",
+        "__content__" => "This dataset contains all projects funded by the European Union under the fifth framework programme for research and technological development (FP5) from 1998 to 2002."
+      )
+    end
+  end
+
+  context "insert_resource_type when resourceType is available, 'OTHER' when schemaOrg has no valid translations, and 'resourceTypeGeneral is unavailable" do
+    it "supports Other as resourceTypeGeneral" do
+      # Mock the `types` hash to include the necessary values
+      subject.instance_variable_set(:@types, {
+        "schemaOrg" => "Invalid_SO_Value",
+        "resourceType" => "This dataset contains all projects funded by the European Union under the fifth framework programme for research and technological development (FP5) from 1998 to 2002."
+      })
+
+      # Generate XML using the insert_resource_type method
+      xml = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') { |xml| subject.insert_resource_type(xml) }.to_xml
+
+      response = Maremma.from_xml(xml)
+
+      # Expect `Text` in resourceTypeGeneral (via SO_TP_DC_TRANSLATIONS) and `This dataset contains all projects funded...` as the content
+      expect(response["resourceType"]).to eq(
+        "resourceTypeGeneral" => "Other",
+        "__content__" => "This dataset contains all projects funded by the European Union under the fifth framework programme for research and technological development (FP5) from 1998 to 2002."
+      )
+    end
+  end
+
+  # Test case to insert Coverage DateType (new dateType in DataCite 4.6).
+  context "insert_dates with Coverage" do
+    it "inserts date with dateType Coverage" do
+      subject.dates = [{ "date" => "2021-01-01", "dateType" => "Coverage" }]
+
+      xml = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') { |xml| subject.insert_dates(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      dates = response.dig("dates", "date")
+      expect(dates).to eq("__content__" => "2021-01-01", "dateType" => "Coverage")
+    end
+  end
+
+  # Test case to insert Translator contributor (new contributorType in DataCite 4.6)
+  context "insert_contributors Translator" do
+    it "supports Translator contributorType" do
+      subject.contributors = [
+        { "contributorName" => "John Translator", "contributorType" => "Translator" }
+      ]
+
+      xml = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') { |xml| subject.insert_contributors(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.dig("contributors", "contributor", "contributorType")).to eq("Translator")
+    end
+  end
+
+  # Test case for RRID (new relatedIdentifierType in DataCite 4.6)
+  context "insert_related_identifiers RRID" do
+    it "supports RRID relatedIdentifierType" do
+      subject.related_identifiers = [
+        { "relatedIdentifier" => "RRID:AB_90755", "relatedIdentifierType" => "RRID", "relationType" => "References" }
+      ]
+
+      xml = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') { |xml| subject.insert_related_identifiers(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.dig("relatedIdentifiers", "relatedIdentifier")).to eq("__content__" => "RRID:AB_90755", "relatedIdentifierType" => "RRID", "relationType" => "References")
+    end
+  end
+
+  ### Test case #2 for adding CSTR ###
+  context "insert_related_identifiers CSTR" do
+    it "supports CSTR relatedIdentifierType" do
+      subject.related_identifiers = [
+        { "relatedIdentifier" => "CSTR:AB_12345", "relatedIdentifierType" => "CSTR", "relationType" => "References" }
+      ]
+
+      xml = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') { |xml| subject.insert_related_identifiers(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.dig("relatedIdentifiers", "relatedIdentifier")).to eq("__content__" => "CSTR:AB_12345", "relatedIdentifierType" => "CSTR", "relationType" => "References")
+    end
+  end
+
+  # Test case for HasTranslation (new relationType in DataCite 4.6)
+  context "insert_related_identifiers HasTranslation" do
+    it "supports HasTranslation relationType" do
+      subject.related_identifiers = [
+        { "relatedIdentifier" => "10.1234/translated-version", "relatedIdentifierType" => "DOI", "relationType" => "HasTranslation" }
+      ]
+
+      xml = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') { |xml| subject.insert_related_identifiers(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.dig("relatedIdentifiers", "relatedIdentifier")).to eq("__content__" => "10.1234/translated-version", "relatedIdentifierType" => "DOI", "relationType" => "HasTranslation")
+    end
+  end
+end

data/spec/fixtures/citeproc.json

@@ -27,6 +27,10 @@
         "family": "Fenner",
         "given": "Martin",
         "literal": "Fenner, Martin"
-    }
-]
+    }],
+    "translator": [{
+        "family": "Ross",
+        "given": "Cody",
+        "literal": "Ross, Cody"
+    }]
 }

data/spec/fixtures/crossref_schema_4.6_values.xml

@@ -0,0 +1,183 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<crossref_result xmlns="http://www.crossref.org/qrschema/3.0" version="3.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.crossref.org/qrschema/3.0 http://www.crossref.org/schemas/crossref_query_output3.0.xsd">
+  <query_result>
+    <head>
+      <doi_batch_id>none</doi_batch_id>
+    </head>
+    <body>
+      <query status="resolved">
+        <doi type="journal_article">10.7554/eLife.01567</doi>
+        <crm-item name="publisher-name" type="string">eLife Sciences Publications, Ltd</crm-item>
+        <crm-item name="prefix-name" type="string">eLife Sciences Publications, Ltd.</crm-item>
+        <crm-item name="member-id" type="number">4374</crm-item>
+        <crm-item name="citation-id" type="number">67124617</crm-item>
+        <crm-item name="journal-id" type="number">189365</crm-item>
+        <crm-item name="deposit-timestamp" type="number">20180823133646</crm-item>
+        <crm-item name="owner-prefix" type="string">10.7554</crm-item>
+        <crm-item name="last-update" type="date">2018-08-23T13:41:49Z</crm-item>
+        <crm-item name="created" type="date">2014-02-11T16:29:04Z</crm-item>
+        <crm-item name="citedby-count" type="number">13</crm-item>
+        <doi_record>
+          <crossref xmlns="http://www.crossref.org/xschema/1.1" xsi:schemaLocation="http://www.crossref.org/xschema/1.1 http://doi.crossref.org/schemas/unixref1.1.xsd">
+            <journal>
+              <journal_metadata language="en">
+                  <full_title>Journal of Metadata Perfection</full_title>
+                  <abbrev_title>JOMPer</abbrev_title>
+                  <doi_data>
+                      <doi>10.32013/487529</doi>
+                      <resource>https://www.crossref.org/jomper</resource>
+                  </doi_data>
+              </journal_metadata>
+              <journal_issue>
+                  <publication_date media_type="online">
+                      <month>08</month>
+                      <day>13</day>
+                      <year>2008</year>
+                  </publication_date>
+                  <publication_date media_type="print">
+                      <month>08</month>
+                      <day>14</day>
+                      <year>2008</year>
+                  </publication_date>
+                  <journal_volume>
+                      <volume>5</volume>
+                  </journal_volume>
+                  <issue>11</issue>
+              </journal_issue>
+              <journal_article publication_type="full_text">
+                  <titles>
+                      <title>Quand vos meilleures métadonnées ne suffisent pas: travailler avec une spécification imparfaite</title>
+                      <original_language_title language="en">When your best metadata isn't good enough: working with an imperfect specification </original_language_title>
+                  </titles>
+                  <contributors>
+                      <person_name sequence="first" contributor_role="author">
+                          <given_name>Minerva</given_name>
+                          <surname>Housecat</surname>
+                          <affiliation>Crossref University</affiliation>
+                          <ORCID authenticated="true">https://orcid.org/0000-0002-4011-3590</ORCID>
+                      </person_name>
+                      <person_name sequence="additional" contributor_role="author">
+                          <given_name>Josiah</given_name>
+                          <surname>Carberry</surname>
+                          <affiliation>Brown University</affiliation>
+                          <ORCID authenticated="true">https://orcid.org/0000-0002-1825-0097</ORCID>
+                      </person_name>
+                      <person_name contributor_role="editor" sequence="additional">
+                        <given_name>Ashwini</given_name>
+                        <surname>Sukale</surname>
+                        <affiliation>DataCite</affiliation>
+                      </person_name>
+                      <person_name contributor_role="translator" sequence="additional">
+                        <given_name>Cody</given_name>
+                        <surname>Ross</surname>
+                        <affiliation>DataCite</affiliation>
+                      </person_name>
+                  </contributors>
+                  <publication_date media_type="online">
+                      <month>08</month>
+                      <day>13</day>
+                      <year>2018</year>
+                  </publication_date>
+                  <publication_date media_type="print">
+                      <month>08</month>
+                      <day>14</day>
+                      <year>2018</year>
+                  </publication_date>
+                  <acceptance_date>
+                      <month>05</month>
+                      <day>21</day>
+                      <year>2018</year>
+                  </acceptance_date>
+                  <pages>
+                      <first_page>1</first_page>
+                      <last_page>3</last_page>
+                  </pages>
+                  <publisher_item>
+                      <item_number item_number_type="article_number">2347854-0</item_number>
+                  </publisher_item>
+                  <program xmlns="http://www.crossref.org/relations.xsd">
+                      <related_item>
+                          <description>English language version</description>
+                          <intra_work_relation relationship-type="hasTranslation" identifier-type="doi"
+                              >10.32013/zLl10OQ</intra_work_relation>
+                      </related_item>
+                      <related_item>
+                        <description>Portuguese translation of an article</description>
+                        <intra_work_relation relationship-type="isTranslationOf" identifier-type="doi">10.5555/original_language</intra_work_relation>
+                      </related_item>
+                  </program>
+                  <archive_locations>
+                      <archive name="CLOCKSS"/>
+                      <archive name="Internet Archive"/>
+                      <archive name="Portico"/>
+                      <archive name="KB"/>
+                  </archive_locations>
+                  <doi_data>
+                      <doi>10.32013/4859104</doi>
+                      <resource>https://www.crossref.org/xml-samples/</resource>
+                      <collection property="crawler-based">
+                          <item crawler="iParadigms">
+                              <resource>https://www.crossref.org/faqs.html</resource>
+                          </item>
+                      </collection>
+                      <collection property="text-mining">
+                          <item>
+                              <resource content_version="vor" mime_type="text/xml"
+                                  >https://www.crossref.org/example.xml</resource>
+                          </item>
+                      </collection>
+                      <collection property="link-header">
+                          <item link_header_relationship="dul">
+                              <resource>http://www.crossref.org/exampleDULendpoint</resource>
+                          </item>
+                      </collection>
+                  </doi_data>
+                  <citation_list>
+                      <citation key="ref1">
+                          <doi>10.1101/144147</doi>
+                          <unstructured_citation>BioSharing: Harnessing Metadata Standards For The
+                              Data Commons. Susanna-Assunta Sansone, Alejandra Gonzalez-Beltran,
+                              Philippe Rocca-Serra, PeterMcQuilton, Massimiliano Izzo, Allyson Lister,
+                              Milo Thurston. bioRxiv 144147</unstructured_citation>
+                      </citation>
+                      <citation key="ref2">
+                          <doi>10.1515/jdis-2017-0012</doi>
+                          <unstructured_citation>Greenberg, J. (2017). Big Metadata, Smart Metadata,
+                              and Metadata Capital: Toward Greater Synergy Between Data Science and
+                              Metadata, Journal of Data and Information Science, 2(3), 19-36.
+                          </unstructured_citation>
+                      </citation>
+                      <citation key="ref3">
+                          <doi>10.32013/s4947892</doi>
+                      </citation>
+                      <citation key="ref4">
+                          <doi>10.1108/LHTN-12-2016-0059</doi>
+                          <unstructured_citation>Jung ran Park, Yuji Tosaka, (2017) “Emerging
+                              information standards and technologies: cataloging and metadata
+                              professionals’ perspectives", Library Hi Tech News, Vol. 34 Issue: 4,
+                              pp.22-26</unstructured_citation>
+                      </citation>
+                      <citation key="ref5">
+                          <journal_title>Information Technology and Libraries</journal_title>
+                          <author>Park</author>
+                          <volume>29</volume>
+                          <issue>3</issue>
+                          <first_page>104</first_page>
+                          <cYear>2010</cYear>
+                          <doi>10.6017/ital.v29i3.3136</doi>
+                          <article_title>Metadata creation practices in digital repositories and collections: Schemata, selection criteria, and interoperability</article_title>
+                      </citation>
+                      <citation key="ref6">
+                          <unstructured_citation>Riley, J. (2017). Understanding metadata.
+                              Bethesda,MD: NISO Press.</unstructured_citation>
+                      </citation>
+                  </citation_list>
+              </journal_article>
+          </journal>
+  
+          </crossref>
+        </doi_record>
+      </query>
+    </body>
+  </query_result>
+</crossref_result>

data/spec/fixtures/datacite-example-ROR-nameIdentifiers.xml

@@ -43,6 +43,14 @@
             <creatorName nameType="Personal">Mike B</creatorName>
             <nameIdentifier nameIdentifierScheme="ORCID"> 0000-0001-9998-0118 </nameIdentifier>
         </creator>
+        <creator>
+            <creatorName nameType="Organizational">Gump South Pacific Research Station</creatorName>
+            <nameIdentifier nameIdentifierScheme="ROR" schemeURI="https://ror.org/">https://ror.org/04sk0et52/</nameIdentifier>
+        </creator>
+        <creator>
+            <creatorName nameType="Personal">Ashwini Sukale</creatorName>
+            <nameIdentifier schemeURI="https://orcid.org/" nameIdentifierScheme="ORCID">https://orcid.org/0000-0001-9998-0117/</nameIdentifier>
+        </creator>
     </creators>
     <titles>
         <title xml:lang="en-US">Genomic Standards Consortium (GSC) Island Sampling Day: Moorea Reef to Ridges Genomic Transect</title>

data/spec/fixtures/datacite-example-full-v4.6.xml

@@ -0,0 +1,114 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<resource
+    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+    xmlns="http://datacite.org/schema/kernel-4"
+    xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.6/metadata.xsd">
+
+    <!-- DOI Identifier -->
+    <identifier identifierType="DOI">10.82433/B09Z-4K37</identifier>
+
+    <!-- Creators -->
+    <creators>
+        <creator>
+            <creatorName nameType="Personal">ExampleFamilyName, ExampleGivenName</creatorName>
+            <givenName>ExampleGivenName</givenName>
+            <familyName>ExampleFamilyName</familyName>
+            <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="https://orcid.org">https://orcid.org/0000-0001-5727-2427</nameIdentifier>
+            <affiliation affiliationIdentifier="https://ror.org/04wxnsj81" affiliationIdentifierScheme="ROR" schemeURI="https://ror.org">ExampleAffiliation</affiliation>
+        </creator>
+        <creator>
+            <creatorName xml:lang="en" nameType="Organizational">ExampleOrganization</creatorName>
+            <nameIdentifier nameIdentifierScheme="ROR" schemeURI="https://ror.org">https://ror.org/04wxnsj81</nameIdentifier>
+        </creator>
+    </creators>
+
+    <!-- Titles -->
+    <titles>
+        <title xml:lang="en">Example Title</title>
+        <title titleType="Subtitle" xml:lang="en">Example Subtitle</title>
+        <title titleType="TranslatedTitle" xml:lang="fr">Example TranslatedTitle</title>
+        <title titleType="AlternativeTitle" xml:lang="en">Example AlternativeTitle</title>
+    </titles>
+
+    <!-- Publisher -->
+    <publisher xml:lang="en" publisherIdentifier="https://ror.org/04z8jg394" publisherIdentifierScheme="ROR" schemeURI="https://ror.org/">Example Publisher</publisher>
+
+    <!-- Publication Year -->
+    <publicationYear>2023</publicationYear>
+
+    <!-- New resourceTypeGeneral: Project -->
+    <resourceType resourceTypeGeneral="Project">Research Project</resourceType>
+
+    <!-- Subjects -->
+    <subjects>
+        <subject subjectScheme="Fields of Science and Technology (FOS)" schemeURI="http://www.oecd.org/science/inno" valueURI="http://www.oecd.org/science/inno/38235147.pdf">FOS: Computer and information sciences</subject>
+        <subject subjectScheme="Australian and New Zealand Standard Research Classification (ANZSRC), 2020" schemeURI="https://www.abs.gov.au/statistics/classifications/australian-and-new-zealand-standard-research-classification-anzsrc" classificationCode="461001">Digital curation and preservation</subject>
+        <subject>Example Subject</subject>
+    </subjects>
+
+    <!-- New ContributorType: Translator -->
+    <contributors>
+        <contributor contributorType="Translator">
+            <contributorName nameType="Personal">Doe, Jane</contributorName>
+            <givenName>Jane</givenName>
+            <familyName>Doe</familyName>
+            <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="https://orcid.org">https://orcid.org/0000-0003-1419-2405</nameIdentifier>
+            <affiliation affiliationIdentifier="https://ror.org/04wxnsj81" affiliationIdentifierScheme="ROR" schemeURI="https://ror.org">ExampleAffiliation</affiliation>
+        </contributor>
+        <contributor contributorType="ContactPerson">
+            <contributorName nameType="Personal">Smith, John</contributorName>
+            <givenName>John</givenName>
+            <familyName>Smith</familyName>
+            <affiliation affiliationIdentifier="https://ror.org/04wxnsj81" affiliationIdentifierScheme="ROR" schemeURI="https://ror.org">ExampleAffiliation</affiliation>
+        </contributor>
+    </contributors>
+
+    <!-- Dates (Including New dateType "Coverage") -->
+    <dates>
+        <date dateType="Coverage">2020-01-01</date>  <!-- DataCite 4.6: Coverage DateType -->
+        <date dateType="Created">2023-01-01</date>
+        <date dateType="Issued">2023-01-01</date>
+        <date dateType="Submitted">2023-01-01</date>
+        <date dateType="Updated">2023-01-01</date>
+    </dates>
+
+    <!-- Related Identifiers (Including CSTR, RRID, HasTranslation) -->
+    <relatedIdentifiers>
+        <relatedIdentifier relatedIdentifierType="RRID" relationType="References">RRID:AB_90755</relatedIdentifier>         <!-- DataCite 4.6: New RRID Identifier -->
+        <relatedIdentifier relatedIdentifierType="CSTR" relationType="References">CSTR:AB_12345</relatedIdentifier>       <!-- DataCite 4.6: New CSTR Identifier -->
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="HasTranslation">10.1234/translated-version</relatedIdentifier>     <!-- DataCite 4.6: HasTranslation RelationType -->
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsTranslationOf">10.1234/other-version</relatedIdentifier>     <!-- DataCite 4.6: HasTranslation RelationType -->
+    </relatedIdentifiers>
+
+    <!-- Sizes & Formats -->
+    <sizes>
+        <size>1 MB</size>
+    </sizes>
+    <formats>
+        <format>application/xml</format>
+    </formats>
+
+    <!-- Version -->
+    <version>1</version>
+
+    <!-- Rights (CC BY 4.0) -->
+    <rightsList>
+        <rights xml:lang="en" rightsURI="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International</rights>
+    </rightsList>
+
+    <!-- Descriptions (Abstract) -->
+    <descriptions>
+        <description xml:lang="en" descriptionType="Abstract">This dataset illustrates the use of new DataCite fields, including Project and Award resource types, RRID, CSTR, Translator, and others.</description>
+    </descriptions>
+
+    <!-- GeoLocations Example -->
+    <geoLocations>
+        <geoLocation>
+            <geoLocationPlace>Vancouver, British Columbia, Canada</geoLocationPlace>
+            <geoLocationPoint>
+                <pointLatitude>49.2827</pointLatitude>
+                <pointLongitude>-123.1207</pointLongitude>
+            </geoLocationPoint>
+        </geoLocation>
+    </geoLocations>
+</resource>

data/spec/fixtures/datacite-xml-lang.xml

@@ -15,7 +15,7 @@
         <title xml:lang="en">DOI Test 2 title content</title>
         <title xml:lang="en">AAPP</title>
     </titles>
-    <publisher>OSI SAF</publisher>
+    <publisher xml:lang="en">OSI SAF</publisher>
     <publicationYear>2004</publicationYear>
     <resourceType resourceTypeGeneral="Collection">Climate Data Record</resourceType>
     <dates>

data/spec/fixtures/datacite_blank_name_identifier.xml

@@ -0,0 +1,22 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://schema.datacite.org/meta/kernel-4.3/metadata.xsd">
+  <identifier identifierType="DOI">10.15148/3b68dac4-7688-4fbb-ba64-5f9b3bbab954</identifier>
+  <creators>
+    <creator>
+      <creatorName>SNO KARST</creatorName>
+      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="https://orcid.org"/>
+    </creator>
+  </creators>
+  <publisher>OSU OREME</publisher>
+  <titles>
+    <title>Time series of type chemistry in Le Tarn basin - PARC NATIONAL CEVENNES observatory - KARST observatory network -  OZCAR Critical Zone network Research Infrastructure</title>
+  </titles>
+  <publicationYear>2023</publicationYear>
+  <contributors>
+    <contributor contributorType="ProjectMember">
+      <contributorName>Manche, Yannick</contributorName>
+      <nameIdentifier schemeURI="http://orcid.org/" nameIdentifierScheme="ORCID"></nameIdentifier>
+    </contributor>
+  </contributors>
+  <resourceType resourceTypeGeneral="Dataset">Dataset</resourceType>
+</resource>

data/spec/fixtures/datacite_blank_publisher.xml

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4/metadata.xsd">
+  <identifier identifierType="DOI">10.81360/4DVP-KR57</identifier>
+  <creators>
+    <creator>
+      <creatorName nameType="Personal">Møller, Jørgen</creatorName>
+      <givenName>Jørgen</givenName>
+      <familyName>Møller</familyName>
+    </creator>
+  </creators>
+  <titles>
+    <title xml:lang="en">Economic Crisis and Democratic Breakdown in the Interwar Years: A Reassessment</title>
+    <title xml:lang="de">Wirtschaftskrise und demokratischer Zusammenbruch in der Zwischenkriegszeit: Eine Neubewertung</title>
+  </titles>
+  <publisher publisherIdentifier="https://ror.org/04wxnsj81"></publisher>
+  <publicationYear>2015</publicationYear>
+  <resourceType resourceTypeGeneral="JournalArticle"/>
+</resource>