bolognese 1.11.3 → 2.2.0

data/spec/author_utils_spec.rb

@@ -168,14 +168,16 @@ describe Bolognese::Metadata, vcr: true do
     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")
   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") }
+
     it "should normalize ROR affiliationIdentifier with and without URL" do
-      input = fixture_path + 'datacite-example-ROR-nameIdentifiers.xml'
-      subject = Bolognese::Metadata.new(input: input, from: "datacite")
       # without URL inside affiliationIdentifier="05bp8ka77"
       ror_affiliater0 = subject.creators[0]["affiliation"].select { |r| r["affiliationIdentifierScheme"] == "ROR" }
       expect(ror_affiliater0[0]["affiliationIdentifier"]).to eq("https://ror.org/05bp8ka77")
@@ -184,6 +186,33 @@ describe Bolognese::Metadata, vcr: true do
       expect(ror_affiliater1[0]["affiliationIdentifier"]).to eq("https://ror.org/05bp8ka05")
     end
 
+    it "should normalize the valid ORCID nameIdentifier to URL with schemeURI" do
+      # with "schemeURI"
+      # ORICD normalization  0000-0001-9998-0117 => https://orcid.org/0000-0001-9998-0117
+      expect(subject.creators[0]["nameIdentifiers"]).to eq([{"nameIdentifier"=>"https://orcid.org/0000-0001-9998-0117", "schemeUri"=>"https://orcid.org", "nameIdentifierScheme"=>"ORCID"}])
+    end
+
+    it "should normalize the valid ORCID nameIdentifier to URL without schemeURI" do
+      # without "schemeURI"
+      # ORICD normalization  0000-0001-9998-0117 => https://orcid.org/0000-0001-9998-0117
+      expect(subject.creators[7]["nameIdentifiers"]).to eq([{"nameIdentifier"=>"https://orcid.org/0000-0001-9998-0117", "schemeUri"=>"https://orcid.org", "nameIdentifierScheme"=>"ORCID"}])
+    end
+
+    it "should keep nameIdentifier URL after normalization" do
+      # ORICD normalization  https://orcid.org/0000-0001-9998-0114 => https://orcid.org/0000-0001-9998-0114
+      expect(subject.creators[1]["nameIdentifiers"]).to eq([{"nameIdentifier"=>"https://orcid.org/0000-0001-9998-0114", "schemeUri"=>"https://orcid.org", "nameIdentifierScheme"=>"ORCID"}])
+    end
+
+    it "should sanitize valid ORCID id/URL before normalization" do
+      #"  0000-0001-9998-0118  ",  # Valid ORCID with leading/trailing spaces
+      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")
@@ -227,4 +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

@@ -99,9 +99,13 @@ describe Bolognese::Metadata, vcr: true do
 
   context "insert_subjects" do
     it "insert" do
+      input = "https://doi.org/10.5878/xyad-9f70"
+      subject = Bolognese::Metadata.new(input: input, from: "datacite")
       xml = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') { |xml| subject.insert_subjects(xml) }.to_xml
       response = Maremma.from_xml(xml)
-      expect(response.dig("subjects", "subject")).to eq(["Plasmodium", "malaria", "taxonomy", "mitochondrial genome", "Parasites"])
+      # It should preserve the classificationCode
+      expect(response.dig("subjects", "subject")[0]["classificationCode"]).to eq("a046a1ec-a4d1-4777-8705-3a17548f1969")
+      expect(response.dig("subjects", "subject")[0]).to eq({"subjectScheme"=>"ELSST", "valueURI"=>"https://elsst.cessda.eu/id/a046a1ec-a4d1-4777-8705-3a17548f1969", "classificationCode"=>"a046a1ec-a4d1-4777-8705-3a17548f1969", "xml:lang"=>"en", "__content__"=>"decision making"})
     end
   end
 

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

@@ -5,13 +5,13 @@
     <creators>
         <creator>
             <creatorName nameType="Personal">Ashwini Sukale</creatorName>
-            <nameIdentifier schemeURI="https://orcid.org/" nameIdentifierScheme="ORCID"> https://orcid.org/0000-0001-9998-0117 </nameIdentifier>
+            <nameIdentifier schemeURI="https://orcid.org/" nameIdentifierScheme="ORCID">0000-0001-9998-0117</nameIdentifier>
             <affiliation affiliationIdentifier="05bp8ka77" affiliationIdentifierScheme="ROR"> Metadata Game Changers </affiliation>
             <affiliation affiliationIdentifier="grid.268117.b" affiliationIdentifierScheme="GRID">Wesleyan University</affiliation>
         </creator>
         <creator>
             <creatorName nameType="Personal">Erin Robinson</creatorName>
-            <nameIdentifier schemeURI="https://orcid.org/" nameIdentifierScheme="ORCID"> https://orcid.org/0000-0001-9998-0114 </nameIdentifier>
+            <nameIdentifier schemeURI="https://orcid.org/" nameIdentifierScheme="ORCID">https://orcid.org/0000-0001-9998-0114</nameIdentifier>
             <affiliation schemeURI="https://ror.org" affiliationIdentifier="https://ror.org/05bp8ka05" affiliationIdentifierScheme="ROR"> Metadata Game Changers </affiliation>
             <affiliation affiliationIdentifier="grid.268117.b" affiliationIdentifierScheme="GRID" schemeURI="https://grid.ac/institutes/">Wesleyan University</affiliation>
         </creator>
@@ -35,6 +35,22 @@
             <creatorName nameType="Organizational">جامعة زاخۆ</creatorName>
             <nameIdentifier nameIdentifierScheme="RORS" schemeURI="https://ror.org">05sd1pz50</nameIdentifier>
         </creator>
+        <creator>
+            <creatorName nameType="Personal">Ashwini S</creatorName>
+            <nameIdentifier nameIdentifierScheme="ORCID">0000-0001-9998-0117</nameIdentifier>
+        </creator>
+         <creator>
+            <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-v4.5.xml

@@ -0,0 +1,255 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- Example with all properties -->
+<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 ../metadata.xsd">
+    <identifier identifierType="DOI">10.82433/B09Z-4K37</identifier>
+    <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>
+        <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 xml:lang="en" publisherIdentifier="https://ror.org/04z8jg394" publisherIdentifierScheme="ROR" schemeURI="https://ror.org/">Example Publisher</publisher>
+    <publicationYear>2023</publicationYear>
+    <resourceType resourceTypeGeneral="Dataset">Example ResourceType</resourceType>
+    <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>
+    <contributors>
+        <contributor contributorType="ContactPerson">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+            <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>
+        </contributor>
+        <contributor contributorType="DataCollector">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+        <contributor contributorType="DataCurator">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+        <contributor contributorType="DataManager">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+        <contributor contributorType="Distributor">
+            <contributorName nameType="Organizational">ExampleOrganization</contributorName>
+        </contributor>
+        <contributor contributorType="Editor">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+        <contributor contributorType="HostingInstitution">
+            <contributorName nameType="Organizational">ExampleOrganization</contributorName>
+        </contributor>
+        <contributor contributorType="Producer">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+        <contributor contributorType="ProjectLeader">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+        <contributor contributorType="ProjectManager">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+        <contributor contributorType="ProjectMember">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+        <contributor contributorType="RegistrationAgency">
+            <contributorName nameType="Organizational">DataCite</contributorName>
+        </contributor>
+        <contributor contributorType="RegistrationAuthority">
+            <contributorName nameType="Organizational">International DOI Foundation</contributorName>
+        </contributor>
+        <contributor contributorType="RelatedPerson">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+        <contributor contributorType="Researcher">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+        <contributor contributorType="ResearchGroup">
+            <contributorName>ExampleContributor</contributorName>
+        </contributor>
+        <contributor contributorType="RightsHolder">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+        <contributor contributorType="Sponsor">
+            <contributorName>ExampleContributor</contributorName>
+        </contributor>
+        <contributor contributorType="Supervisor">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+        <contributor contributorType="WorkPackageLeader">
+            <contributorName nameType="Organizational">ExampleOrganization</contributorName>
+        </contributor>
+        <contributor contributorType="Other">
+            <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+        </contributor>
+    </contributors>
+    <dates>
+        <date dateType="Accepted">2023-01-01</date>
+        <date dateType="Available">2023-01-01</date>
+        <date dateType="Copyrighted">2023-01-01</date>
+        <date dateType="Collected">2022-01-01/2022-12-31</date>
+        <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>
+        <date dateType="Valid">2023-01-01</date>
+        <date dateType="Withdrawn">2023-01-01</date>
+        <date dateType="Other" dateInformation="ExampleDateInformation">2023-01-01</date>
+    </dates>
+    <language>en</language>
+    <alternateIdentifiers>
+        <alternateIdentifier alternateIdentifierType="Local accession number">12345</alternateIdentifier>
+    </alternateIdentifiers>
+    <relatedIdentifiers>
+        <relatedIdentifier relatedIdentifierType="ARK" relationType="IsCitedBy" resourceTypeGeneral="Audiovisual">ark:/13030/tqb3kh97gh8w</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="arXiv" relationType="Cites" resourceTypeGeneral="Book">arXiv:0706.0001</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="bibcode" relationType="IsSupplementTo" resourceTypeGeneral="BookChapter">2018AGUFM.A24K..07S</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsSupplementedBy" resourceTypeGeneral="Collection">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="EAN13" relationType="IsContinuedBy" resourceTypeGeneral="ComputationalNotebook">9783468111242</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="EISSN" relationType="Continues" resourceTypeGeneral="ConferencePaper">1562-6865</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="Handle" relationType="Describes" resourceTypeGeneral="ConferenceProceeding">10013/epic.10033</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="IGSN" relationType="IsDescribedBy" resourceTypeGeneral="DataPaper">IECUR0097</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="ISBN" relationType="HasMetadata" resourceTypeGeneral="Dataset">978-3-905673-82-1</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="ISSN" relationType="IsMetadataFor" resourceTypeGeneral="Dissertation">0077-5606</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="ISTC" relationType="HasVersion" resourceTypeGeneral="Event">0A9 2002 12B4A105 7</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="LISSN" relationType="IsVersionOf" resourceTypeGeneral="Image">1188-1534</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="LSID" relationType="IsNewVersionOf" resourceTypeGeneral="InteractiveResource">urn:lsid:ubio.org:namebank:11815</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="PMID" relationType="IsPreviousVersionOf" resourceTypeGeneral="Journal">12082125</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="PURL" relationType="IsPartOf" resourceTypeGeneral="JournalArticle">http://purl.oclc.org/foo/bar</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="UPC" relationType="HasPart" resourceTypeGeneral="Model">123456789999</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="URL" relationType="IsPublishedIn" resourceTypeGeneral="OutputManagementPlan">http://www.heatflow.und.edu/index2.html</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="URN" relationType="IsReferencedBy" resourceTypeGeneral="PeerReview">urn:nbn:de:101:1-201102033592</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="w3id" relationType="References" resourceTypeGeneral="PhysicalObject">https://w3id.org/games/spec/coil#Coil_Bomb_Die_Of_Age</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsDocumentedBy" resourceTypeGeneral="Preprint">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="Documents" resourceTypeGeneral="Report">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsCompiledBy" resourceTypeGeneral="Service">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="Compiles" resourceTypeGeneral="Software">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVariantFormOf" resourceTypeGeneral="Sound">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsOriginalFormOf" resourceTypeGeneral="Standard">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo" resourceTypeGeneral="Text">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsReviewedBy" resourceTypeGeneral="Workflow">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="Reviews" resourceTypeGeneral="Other">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsDerivedFrom" resourceTypeGeneral="Other">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsSourceOf" resourceTypeGeneral="Other">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsRequiredBy" resourceTypeGeneral="Other">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="Requires" resourceTypeGeneral="Other">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="Obsoletes" resourceTypeGeneral="Other">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsObsoletedBy" resourceTypeGeneral="Other">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="Collects" resourceTypeGeneral="Other">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+        <relatedIdentifier relatedIdentifierType="DOI" relationType="IsCollectedBy" resourceTypeGeneral="Other">10.1016/j.epsl.2011.11.037</relatedIdentifier>
+    </relatedIdentifiers>
+    <sizes>
+        <size>1 MB</size>
+        <size>90 pages</size>
+    </sizes>
+    <formats>
+        <format>application/xml</format>
+        <format>text/plain</format>
+    </formats>
+    <version>1</version>
+    <rightsList>
+        <rights xml:lang="en" schemeURI="https://spdx.org/licenses/" rightsIdentifierScheme="SPDX" rightsIdentifier="CC-BY-4.0" rightsURI="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International</rights>
+    </rightsList>
+    <descriptions>
+        <description xml:lang="en" descriptionType="Abstract">Example Abstract</description>
+        <description xml:lang="en" descriptionType="Methods">Example Methods</description>
+        <description xml:lang="en" descriptionType="SeriesInformation">Example SeriesInformation</description>
+        <description xml:lang="en" descriptionType="TableOfContents">Example TableOfContents</description>
+        <description xml:lang="en" descriptionType="TechnicalInfo">Example TechnicalInfo</description>
+        <description xml:lang="en" descriptionType="Other">Example Other</description>
+    </descriptions>
+    <geoLocations>
+        <geoLocation>
+            <geoLocationPlace>Vancouver, British Columbia, Canada</geoLocationPlace>
+            <geoLocationPoint>
+                <pointLatitude>49.2827</pointLatitude>
+                <pointLongitude>-123.1207</pointLongitude>
+            </geoLocationPoint>
+            <geoLocationBox>
+                <westBoundLongitude>-123.27</westBoundLongitude>
+                <eastBoundLongitude>-123.02</eastBoundLongitude>
+                <southBoundLatitude>49.195</southBoundLatitude>
+                <northBoundLatitude>49.315</northBoundLatitude>
+            </geoLocationBox>
+            <geoLocationPolygon>
+                <polygonPoint>
+                  <pointLatitude>41.991</pointLatitude>
+                  <pointLongitude>-71.032</pointLongitude>
+                </polygonPoint>
+                <polygonPoint>
+                  <pointLatitude>42.893</pointLatitude>
+                  <pointLongitude>-69.622</pointLongitude>
+                </polygonPoint>
+                <polygonPoint>
+                  <pointLatitude>41.991</pointLatitude>
+                  <pointLongitude>-68.211</pointLongitude>
+                </polygonPoint>
+                <polygonPoint>
+                  <pointLatitude>41.090</pointLatitude>
+                  <pointLongitude>-69.622</pointLongitude>
+                </polygonPoint>
+                <polygonPoint>
+                  <pointLatitude>41.991</pointLatitude>
+                  <pointLongitude>-71.032</pointLongitude>
+                </polygonPoint>
+              </geoLocationPolygon>
+        </geoLocation>
+    </geoLocations>
+    <fundingReferences>
+        <fundingReference>
+            <funderName>Example Funder</funderName>
+            <funderIdentifier funderIdentifierType="Crossref Funder ID">https://doi.org/10.13039/501100000780</funderIdentifier>
+            <awardNumber awardURI="https://example.com/example-award-uri">12345</awardNumber>
+            <awardTitle>Example AwardTitle</awardTitle>
+        </fundingReference>
+    </fundingReferences>
+    <relatedItems>
+        <relatedItem relatedItemType="Text" relationType="Cites">
+            <relatedItemIdentifier relatedItemIdentifierType="ISSN">1234-5678</relatedItemIdentifier>
+            <creators>
+                <creator>
+                    <creatorName nameType="Personal">ExampleFamilyName, ExampleGivenName</creatorName>
+                    <givenName>ExampleGivenName</givenName>
+                    <familyName>ExampleFamilyName</familyName>
+                </creator>
+            </creators>
+            <titles>
+                <title>Example RelatedItem Title</title>
+                <title titleType="TranslatedTitle">Example RelatedItem TranslatedTitle</title>
+            </titles>
+            <publicationYear>1990</publicationYear>
+            <volume>1</volume>
+            <issue>2</issue>
+            <number numberType="Other">1</number>
+            <firstPage>1</firstPage>
+            <lastPage>100</lastPage>
+            <publisher>Example RelatedItem Publisher</publisher>
+            <edition>Example RelatedItem Edition</edition>
+            <contributors>
+                <contributor contributorType="Other">
+                    <contributorName nameType="Personal">ExampleFamilyName, ExampleGivenName</contributorName>
+                    <givenName>ExampleGivenName</givenName>
+                    <familyName>ExampleFamilyName</familyName>
+                </contributor>
+            </contributors>
+        </relatedItem>
+    </relatedItems>
+</resource>
+        

data/spec/fixtures/datacite-seriesinformation.xml

@@ -36,6 +36,11 @@
   <version>1.0</version>
   <descriptions>
     <description descriptionType="SeriesInformation" xml:lang="en">DataCite Blog, 2(9), 3-4</description>
-    <description descriptionType="Abstract">Eating your own dog food is a slang term to describe that an organization should itself use the products and services it provides. For DataCite this means that we should use DOIs with appropriate metadata and strategies for long-term preservation for...</description>
-  </descriptions>
+    <description descriptionType="Abstract">Eating your own dog food is a slang term to 
+      describe that an organization should itself use the products and services it provides. 
+      For DataCite this means that we should use DOIs with appropriate metadata and strategies for long-term preservation for...
+      &#8226; Unicode Bullet Point: This is an example of a bullet point.\u2605
+      &#9632; Unicode Black Square: This is an example of a black square.
+    </description>
+</descriptions>
 </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>

data/spec/fixtures/datacite_journal_article.xml

@@ -0,0 +1,64 @@
+<?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">10.60843/5EGY-VC42</identifier>
+    <creators>
+        <creator>
+            <creatorName nameType="Personal">Feldman, Heidi Li</creatorName>
+            <givenName>Heidi Li</givenName>
+            <familyName>Feldman</familyName>
+            <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="https://orcid.org">https://orcid.org/0000-0003-1905-2698</nameIdentifier>
+        </creator>
+    </creators>
+    <titles>
+        <title xml:lang="en">Science and Uncertainty in Mass Exposure Litigation</title>
+        <title xml:lang="en">Science and Uncertainty in Mass Exposure Litigation, 74 Tex. L. Rev. 1 (1995)</title>
+    </titles>
+    <publisher>Texas Law Review</publisher>
+    <publicationYear>1995</publicationYear>
+    <resourceType resourceTypeGeneral="JournalArticle">Article</resourceType>
+    <subjects>
+        <subject subjectScheme="Fields of Science and Technology (FOS)" schemeURI="http://www.oecd.org/science/inno/38235147.pdf" classificationCode="5.5">FOS: Law</subject>
+    </subjects>
+    <contributors>
+        <contributor contributorType="HostingInstitution">
+            <contributorName nameType="Organizational">Georgetown Law Library</contributorName>
+            <nameIdentifier nameIdentifierScheme="" schemeURI=""/>
+            <affiliation affiliationIdentifier="https://ror.org/05vzafd60" affiliationIdentifierScheme="ROR" schemeURI="https://ror.org">Georgetown University</affiliation>
+        </contributor>
+    </contributors>
+    <dates>
+        <date dateType="Issued">1995-11</date>
+        <date dateType="Collected">2016-04-25</date>
+    </dates>
+    <language>en</language>
+    <relatedIdentifiers>
+        <relatedIdentifier relatedIdentifierType="ISSN" relationType="IsPublishedIn" resourceTypeGeneral="Journal">0040-4411</relatedIdentifier>
+    </relatedIdentifiers>
+    <relatedItems>
+        <relatedItem relatedItemType="Journal" relationType="IsSourceOf">
+            <relatedItemIdentifier relatedItemIdentifierType="ISSN">0040-4411</relatedItemIdentifier>
+            <creators>
+                <creator>
+                    <creatorName>University of Texas School of Law</creatorName>
+                </creator>
+            </creators>
+            <titles>
+                <title>Texas Law Review</title>
+            </titles>
+            <publicationYear>1995</publicationYear>
+            <volume>74</volume>
+            <issue>1</issue>
+        </relatedItem>
+    </relatedItems>
+    <sizes/>
+    <formats>
+        <format>text/html</format>
+        <format>application/pdf</format>
+    </formats>
+    <version/>
+    <descriptions>
+        <description xml:lang="en" descriptionType="Abstract">Critics of the tort system have condemned courts for their alleged leniency in admitting scientific expert testimony, especially in mass exposure litigation. Claiming that this has resulted in an epidemic of "junk science" in the courtroom, these commentators have urged a more scientific approach to admissibility, intimating that employing more scientific standards would exclude scientific evidence favorable to plaintiffs, thereby demonstrating to factfinders that litigated substances are in fact safe or at least not unsafe.</description>
+    </descriptions>
+</resource>

data/spec/fixtures/schema_org.json

@@ -14,6 +14,7 @@
     }],
     "publisher": {
         "@type": "Organization",
+        "@id": "https://ror.org/04wxnsj81",
         "name": "DataCite"
     },
     "dateCreated": "2016-12-20",