bolognese 1.10.0 → 2.2.0

data/spec/readers/schema_org_reader_spec.rb

@@ -31,7 +31,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.publication_year).to eq("2016")
       expect(subject.related_identifiers.length).to eq(3)
       expect(subject.related_identifiers.last).to eq("relatedIdentifier"=>"10.5438/55e5-t5c0", "relatedIdentifierType"=>"DOI", "relationType"=>"References")
-      expect(subject.publisher).to eq("DataCite")
+      expect(subject.publisher).to eq({"name"=>"DataCite"})
     end
 
     it "BlogPosting with new DOI" do
@@ -59,7 +59,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.publication_year).to eq("2016")
       expect(subject.related_identifiers.length).to eq(3)
       expect(subject.related_identifiers.last).to eq("relatedIdentifier"=>"10.5438/55e5-t5c0", "relatedIdentifierType"=>"DOI", "relationType"=>"References")
-      expect(subject.publisher).to eq("DataCite")
+      expect(subject.publisher).to eq({"name"=>"DataCite"})
     end
 
     it "zenodo" do
@@ -104,7 +104,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.titles).to eq([{"title"=>"Hydrological and meteorological investigations in a lake near Kangerlussuaq, west Greenland"}])
       expect(subject.creators.size).to eq(8)
       expect(subject.creators.first).to eq("nameType" => "Personal", "name"=>"Johansson, Emma", "givenName"=>"Emma", "familyName"=>"Johansson")
-      expect(subject.publisher).to eq("PANGAEA")
+      expect(subject.publisher).to eq({"name"=>"PANGAEA"})
       expect(subject.publication_year).to eq("2014")
     end
 
@@ -169,7 +169,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.publication_year).to eq("2016")
       expect(subject.related_identifiers.length).to eq(3)
       expect(subject.related_identifiers.last).to eq("relatedIdentifier"=>"10.5438/55e5-t5c0", "relatedIdentifierType"=>"DOI", "relationType"=>"References")
-      expect(subject.publisher).to eq("DataCite")
+      expect(subject.publisher).to eq({"name"=>"DataCite", "publisherIdentifier"=>"https://ror.org/04wxnsj81"})
     end
 
     it "GTEx dataset" do
@@ -189,7 +189,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.dates).to eq([{"date"=>"2017", "dateType"=>"Issued"}])
       expect(subject.publication_year).to eq("2017")
       expect(subject.container).to eq("title"=>"GTEx", "type"=>"DataRepository")
-      expect(subject.publisher).to eq("GTEx")
+      expect(subject.publisher).to eq({"name"=>"GTEx"})
       expect(subject.funding_references.length).to eq(7)
       expect(subject.funding_references.first).to eq("funderIdentifier"=>"https://doi.org/10.13039/100000052", "funderIdentifierType"=>"Crossref Funder ID", "funderName"=>"Common Fund of the Office of the Director of the NIH")
     end
@@ -209,7 +209,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.subjects).to eq([{"subject"=>"topmed"}, {"subject"=>"whole genome sequencing"}])
       expect(subject.dates).to eq([{"date"=>"2017-11-30", "dateType"=>"Issued"}])
       expect(subject.publication_year).to eq("2017")
-      expect(subject.publisher).to eq("TOPMed")
+      expect(subject.publisher).to eq({"name"=>"TOPMed"})
       expect(subject.related_identifiers).to eq([{"relatedIdentifier"=>"10.23725/2g4s-qv04", "relatedIdentifierType"=>"DOI", "relationType"=>"References", "resourceTypeGeneral"=>"Dataset"}])
       expect(subject.funding_references).to eq([{"funderIdentifier"=>"https://doi.org/10.13039/100000050", "funderIdentifierType"=>"Crossref Funder ID", "funderName"=>"National Heart, Lung, and Blood Institute (NHLBI)"}])
     end
@@ -240,7 +240,7 @@ describe Bolognese::Metadata, vcr: true do
         {"subject"=>"Sierra (mountain range)"}])
       expect(subject.dates).to eq([{"date"=>"2013", "dateType"=>"Issued"}, {"date"=>"2014-10-17", "dateType"=>"Updated"}])
       expect(subject.publication_year).to eq("2013")
-      expect(subject.publisher).to eq("UC Merced")
+      expect(subject.publisher).to eq({"name"=>"UC Merced"})
       expect(subject.funding_references).to eq([{"funderName"=>"National Science Foundation, Division of Earth Sciences, Critical Zone Observatories"}])
       expect(subject.geo_locations).to eq([{"geoLocationPlace"=>"Providence Creek (Lower, Upper and P301)", "geoLocationPoint"=>{"pointLatitude"=>"37.047756", "pointLongitude"=>"-119.221094"}}])
     end
@@ -258,7 +258,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.titles).to eq([{"title"=>"Registry of all stations from the Tara Oceans Expedition (2009-2013)"}])
       expect(subject.dates).to eq([{"date"=>"2015-02-03", "dateType"=>"Issued"}])
       expect(subject.publication_year).to eq("2015")
-      expect(subject.publisher).to eq("PANGAEA")
+      expect(subject.publisher).to eq({"name"=>"PANGAEA"})
       expect(subject.geo_locations).to eq([{"geoLocationBox"=>{"eastBoundLongitude"=>"174.9006", "northBoundLatitude"=>"79.6753", "southBoundLatitude"=>"-64.3088", "westBoundLongitude"=>"-168.5182"}}])
     end
 
@@ -280,7 +280,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.subjects).to eq([{"subject"=>"topmed"}, {"subject"=>"whole genome sequencing"}])
       expect(subject.dates).to eq([{"date"=>"2017-11-30", "dateType"=>"Issued"}])
       expect(subject.publication_year).to eq("2017")
-      expect(subject.publisher).to eq("TOPMed")
+      expect(subject.publisher).to eq({"name"=>"TOPMed"})
       expect(subject.funding_references).to eq([{"funderIdentifier"=>"https://doi.org/10.13039/100000050", "funderIdentifierType"=>"Crossref Funder ID", "funderName"=>"National Heart, Lung, and Blood Institute (NHLBI)"}])
     end
 
@@ -299,7 +299,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.dates).to eq([{"date"=>"2019-01-09", "dateType"=>"Issued"}, {"date"=>"2019-01-09", "dateType"=>"Created"}, {"date"=>"2019-01-09", "dateType"=>"Updated"}])
       expect(subject.publication_year).to eq("2019")
       expect(subject.id).to eq("https://doi.org/10.23698/aida/drov")
-      expect(subject.publisher).to eq("AIDA")
+      expect(subject.publisher).to eq({"name"=>"AIDA"})
       expect(subject.rights_list).to eq([{"rights"=>"Restricted access", "rightsUri"=>"https://datasets.aida.medtech4health.se/10.23698/aida/drov#license"}])
       expect(subject.id).to eq("https://doi.org/10.23698/aida/drov")
     end
@@ -332,7 +332,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.descriptions.first["description"]).to start_with("The dataset contains a sample of metadata describing papers")
       expect(subject.dates).to eq([{"date"=>"2013-04-03", "dateType"=>"Issued"}])
       expect(subject.publication_year).to eq("2013")
-      expect(subject.publisher).to eq("Zenodo")
+      expect(subject.publisher).to eq({"name"=>"Zenodo"})
       expect(subject.funding_references).to eq([{"awardNumber"=>"246686",
         "awardTitle"=>"Open Access Infrastructure for Research in Europe",
         "awardUri"=>"info:eu-repo/grantAgreement/EC/FP7/246686/",

data/spec/spec_helper.rb

@@ -14,6 +14,7 @@ require 'webmock/rspec'
 require 'rspec/xsd'
 require 'nokogiri'
 require 'vcr'
+require 'byebug'
 
 RSpec.configure do |config|
   config.order = :random

data/spec/writers/citation_writer_spec.rb

@@ -48,5 +48,14 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.locale).to eq("en-US")
       expect(subject.citation).to eq("Clark, D. (2019). <i>Exploring the \"Many analysts, one dataset\" project from COS</i>. Gigantum, Inc. https://doi.org/10.34747/g6yb-3412")
     end
+
+    it "journal article with container title" do
+      input = fixture_path + "datacite_journal_article.xml"
+      subject = Bolognese::Metadata.new(input: input, from: "datacite")
+      expect(subject.types["citeproc"]).to eq("article-journal")
+      expect(subject.style).to eq("apa")
+      expect(subject.locale).to eq("en-US")
+      expect(subject.citation).to eq('Feldman, H. L. (1995). Science and Uncertainty in Mass Exposure Litigation. <i>Texas Law Review</i>. https://doi.org/10.60843/5egy-vc42')
+    end
   end
 end

data/spec/writers/crosscite_writer_spec.rb

@@ -46,6 +46,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(crosscite.dig("descriptions", 0, "description")).to start_with("Among various advantages, their small size makes model organisms preferred subjects of investigation.")
       expect(crosscite.fetch("creators").count).to eq(5)
       expect(crosscite.fetch("creators").first).to eq("nameType"=>"Personal", "name"=>"Sankar, Martial", "givenName"=>"Martial", "familyName"=>"Sankar")
+      expect(crosscite.fetch("publisher")).to eq({"name"=>"{eLife} Sciences Organisation, Ltd."})
     end
 
     it "BlogPosting Citeproc JSON" do
@@ -57,6 +58,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(crosscite.fetch("titles")).to eq([{"title"=>"Eating your own Dog Food"}])
       expect(crosscite.dig("descriptions", 0, "description")).to start_with("Eating your own dog food")
       expect(crosscite.fetch("creators")).to eq([{"familyName"=>"Fenner", "givenName"=>"Martin", "name"=>"Fenner, Martin"}])
+      expect(crosscite.fetch("publisher")).to eq({"name"=>"DataCite"})
     end
 
     it "rdataone" do
@@ -67,6 +69,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(crosscite["creators"].length).to eq(3)
       expect(crosscite["creators"].last).to eq("nameType" => "Organizational", "name"=>"University Of California, Santa Barbara", "nameIdentifiers" => [], "affiliation" => [])
       expect(crosscite["version"]).to eq("2.0.0")
+      expect(crosscite["publisher"]).to eq({"name"=>"https://cran.r-project.org"})
     end
 
     it "rdataone codemeta v2" do
@@ -77,6 +80,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(crosscite["creators"].length).to eq(3)
       expect(crosscite["creators"].last).to eq("nameType" => "Organizational", "name"=>"University Of California, Santa Barbara", "nameIdentifiers" => [], "affiliation" => [])
       expect(crosscite["version"]).to eq("2.0.0")
+      expect(crosscite["publisher"]).to eq({"name"=>"https://cran.r-project.org"})
     end
 
     it "datacite database attributes" do
@@ -91,6 +95,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(crosscite.fetch("publication_year")).to eq("2011")
       expect(crosscite.fetch("provider_id")).to eq("dryad")
       expect(crosscite.fetch("client_id")).to eq("dryad.dryad")
+      expect(crosscite.fetch("publisher")).to eq({"name"=>"Dryad"})
     end
 
     it "maremma" do
@@ -106,6 +111,7 @@ describe Bolognese::Metadata, vcr: true do
           [{"nameIdentifier"=>"https://orcid.org/0000-0003-0077-4738",
             "nameIdentifierScheme"=>"ORCID", "schemeUri"=>"https://orcid.org"}],
         "nameType"=>"Personal"}])
+      expect(crosscite.fetch("publisher")).to eq({"name"=>"DataCite"})
     end
 
     it "with data citation schema.org" do
@@ -117,6 +123,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(crosscite.fetch("related_identifiers").count).to eq(3)
       expect(crosscite.fetch("related_identifiers").first).to eq("relatedIdentifier"=>"10.5438/0000-00ss", "relatedIdentifierType"=>"DOI", "relationType"=>"IsPartOf", "resourceTypeGeneral"=>"Text")
       expect(crosscite.fetch("related_identifiers").last).to eq("relatedIdentifier"=>"10.5438/55e5-t5c0", "relatedIdentifierType"=>"DOI", "relationType"=>"References")
+      expect(crosscite.fetch("publisher")).to eq({"name"=>"DataCite"})
     end
   end
 end

data/spec/writers/datacite_json_writer_spec.rb

@@ -18,6 +18,7 @@ describe Bolognese::Metadata, vcr: true do
         "rightsIdentifierScheme"=>"SPDX",
         "rightsUri"=>"https://creativecommons.org/licenses/by/3.0/legalcode",
         "schemeUri"=>"https://spdx.org/licenses/"}])
+      expect(datacite.fetch("publisher")).to eq({"name"=>"eLife Sciences Publications, Ltd"})
     end
 
     it "with ORCID ID" do
@@ -28,6 +29,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(datacite.fetch("types")).to eq("bibtex"=>"article", "citeproc"=>"article-journal", "resourceType"=>"JournalArticle", "resourceTypeGeneral"=>"JournalArticle", "ris"=>"JOUR", "schemaOrg"=>"ScholarlyArticle")
       expect(datacite.fetch("creators").length).to eq(7)
       expect(datacite.fetch("creators").first).to eq("nameType"=>"Personal", "name"=>"Thanassi, Wendy", "givenName"=>"Wendy", "familyName"=>"Thanassi", "affiliation" => [{"name"=>"Department of Medicine, Veterans Affairs Palo Alto Health Care System, 3801 Miranda Avenue MC-, Palo Alto, CA 94304-1207, USA"}, {"name"=>"Occupational Health Strategic Health Care Group, Office of Public Health, Veterans Health Administration, Washington, DC 20006, USA"}, {"name"=>"Division of Emergency Medicine, Stanford University School of Medicine, Stanford, CA 94304, USA"}, {"name"=>"War Related Illness and Injury Study Center (WRIISC) and Mental Illness Research Education and Clinical Center (MIRECC), Department of Veterans Affairs, Palo Alto, CA 94304, USA"}])
+      expect(datacite.fetch("publisher")).to eq({"name"=>"Hindawi Limited"})
     end
 
     it "Crossref DOI" do
@@ -39,6 +41,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(datacite.dig("descriptions", 0, "description")).to start_with("Among various advantages, their small size makes model organisms preferred subjects of investigation.")
       expect(datacite.fetch("creators").length).to eq(5)
       expect(datacite.fetch("creators").first).to eq("nameType"=>"Personal", "name"=>"Sankar, Martial", "givenName"=>"Martial", "familyName"=>"Sankar")
+      expect(datacite.fetch("publisher")).to eq({"name"=>"{eLife} Sciences Organisation, Ltd."})
     end
 
     it "BlogPosting Citeproc JSON" do
@@ -49,6 +52,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(datacite.fetch("titles")).to eq([{"title"=>"Eating your own Dog Food"}])
       expect(datacite.dig("descriptions", 0, "description")).to start_with("Eating your own dog food")
       expect(datacite.fetch("creators")).to eq([{"familyName"=>"Fenner", "givenName"=>"Martin", "name"=>"Fenner, Martin"}])
+      expect(datacite.fetch("publisher")).to eq({"name"=>"DataCite"})
     end
 
     it "rdataone" do
@@ -60,6 +64,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(datacite.fetch("creators").first).to eq("affiliation"=>[{"name"=>"NCEAS"}], "nameType"=>"Personal", "name" => "Jones, Matt",
         "nameIdentifiers" => [{"nameIdentifier"=>"https://orcid.org/0000-0003-0077-4738", "nameIdentifierScheme"=>"ORCID", "schemeUri"=>"https://orcid.org"}], "givenName"=>"Matt", "familyName"=>"Jones")
       expect(datacite.fetch("version")).to eq("2.0.0")
+      expect(datacite.fetch("publisher")).to eq({"name"=>"https://cran.r-project.org"})
     end
 
     it "maremma" do
@@ -75,6 +80,7 @@ describe Bolognese::Metadata, vcr: true do
          [{"nameIdentifier"=>"https://orcid.org/0000-0003-0077-4738",
            "nameIdentifierScheme"=>"ORCID", "schemeUri"=>"https://orcid.org"}],
         "nameType"=>"Personal"}])
+      expect(datacite.fetch("publisher")).to eq({"name"=>"DataCite"})
     end
 
     it "with data citation schema.org" do
@@ -85,6 +91,22 @@ describe Bolognese::Metadata, vcr: true do
       expect(datacite.fetch("titles")).to eq([{"title"=>"Eating your own Dog Food"}])
       expect(datacite.fetch("relatedIdentifiers").count).to eq(3)
       expect(datacite.fetch("relatedIdentifiers").first).to eq("relatedIdentifier"=>"10.5438/0000-00ss", "relatedIdentifierType"=>"DOI", "relationType"=>"IsPartOf", "resourceTypeGeneral"=>"Text")
+      expect(datacite.fetch("publisher")).to eq({"name"=>"DataCite"})
+    end
+
+    it "DataCite DOI with Schema 4.5 publisher attributes" do
+      input = fixture_path + "datacite-example-full-v4.5.xml"
+      subject = Bolognese::Metadata.new(input: input, from: "datacite")
+      datacite = JSON.parse(subject.datacite_json)
+      expect(datacite.fetch("publisher")).to eq(
+        {
+          "name" => "Example Publisher",
+          "publisherIdentifier" => "https://ror.org/04z8jg394",
+          "publisherIdentifierScheme" => "ROR",
+          "schemeUri" => "https://ror.org/",
+          "lang" => "en",
+        },
+      )
     end
   end
 end

data/spec/writers/datacite_writer_spec.rb

@@ -17,6 +17,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(datacite.dig("rightsList", "rights")).to eq("rightsURI"=>"https://creativecommons.org/licenses/by/3.0/legalcode", "rightsIdentifier"=>"cc-by-3.0", "rightsIdentifierScheme"=>"SPDX", "schemeURI"=>"https://spdx.org/licenses/", "__content__"=>"Creative Commons Attribution 3.0 Unported")
       expect(datacite.dig("fundingReferences", "fundingReference").count).to eq(4)
       expect(datacite.dig("fundingReferences", "fundingReference").last).to eq("funderName"=>"University of Lausanne", "funderIdentifier" => {"funderIdentifierType"=>"Crossref Funder ID", "__content__"=>"https://doi.org/10.13039/501100006390"})
+      expect(datacite.dig("publisher")).to eq("eLife Sciences Publications, Ltd")
     end
 
     it "with ORCID ID" do
@@ -31,6 +32,7 @@ describe Bolognese::Metadata, vcr: true do
         "givenName" => "Beatriz",
         "affiliation" => ["War Related Illness and Injury Study Center (WRIISC) and Mental Illness Research Education and Clinical Center (MIRECC), Department of Veterans Affairs, Palo Alto, CA 94304, USA", "Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, CA 94304, USA"],
         "nameIdentifier" => {"nameIdentifierScheme"=>"ORCID", "schemeURI"=>"https://orcid.org", "__content__"=>"https://orcid.org/0000-0003-2043-4925"})
+      expect(datacite.dig("publisher")).to eq("Hindawi Limited")
     end
 
     it "with editor" do
@@ -39,6 +41,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.valid?).to be true
       datacite = Maremma.from_xml(subject.datacite).fetch("resource", {})
       expect(datacite.dig("contributors", "contributor")).to eq("contributorName"=>{"__content__"=>"Janbon, Guilhem", "nameType"=>"Personal"}, "contributorType"=>"Editor", "familyName"=>"Janbon", "givenName"=>"Guilhem")
+      expect(datacite.dig("publisher")).to eq("Public Library of Science (PLoS)")
     end
 
     it "Crossref DOI" do
@@ -52,6 +55,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(datacite.dig("descriptions", "description", 1, "__content__")).to start_with("Among various advantages, their small size makes model organisms preferred subjects of investigation.")
       expect(datacite.dig("creators", "creator").count).to eq(5)
       expect(datacite.dig("creators", "creator").first).to eq("creatorName"=>{"__content__"=>"Sankar, Martial", "nameType"=>"Personal"}, "familyName"=>"Sankar", "givenName"=>"Martial")
+      expect(datacite.dig("publisher")).to eq("{eLife} Sciences Organisation, Ltd.")
     end
 
     it "BlogPosting Citeproc JSON" do
@@ -64,6 +68,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(datacite.dig("descriptions", "description").first).to eq("__content__"=>"DataCite Blog", "descriptionType"=>"SeriesInformation")
       expect(datacite.dig("descriptions", "description", 1, "__content__")).to start_with("Eating your own dog food")
       expect(datacite.dig("creators", "creator")).to eq("creatorName"=>"Fenner, Martin", "familyName"=>"Fenner", "givenName"=>"Martin")
+      expect(datacite.dig("publisher")).to eq("DataCite")
     end
 
     it "rdataone" do
@@ -88,6 +93,7 @@ describe Bolognese::Metadata, vcr: true do
                                                           "__content__"=>"https://orcid.org/0000-0002-2192-403X"}},
                                                          {"creatorName"=>{"__content__"=>"University Of California, Santa Barbara", "nameType"=>"Organizational"}}])
       expect(datacite.fetch("version")).to eq("2.0.0")
+      expect(datacite.dig("publisher")).to eq("https://cran.r-project.org")
     end
 
     it "rdataone and codemeta_v2" do
@@ -112,6 +118,7 @@ describe Bolognese::Metadata, vcr: true do
                                                           "__content__"=>"https://orcid.org/0000-0002-2192-403X"}},
                                                          {"creatorName"=>{"__content__"=>"University Of California, Santa Barbara", "nameType"=>"Organizational"}}])
       expect(datacite.fetch("version")).to eq("2.0.0")
+      expect(datacite.dig("publisher")).to eq("https://cran.r-project.org")
     end
 
     it "maremma" do
@@ -121,6 +128,7 @@ describe Bolognese::Metadata, vcr: true do
       datacite = Maremma.from_xml(subject.datacite).fetch("resource", {})
       expect(datacite.dig("titles", "title")).to eq("Maremma: a Ruby library for simplified network calls")
       expect(datacite.dig("creators", "creator")).to eq("affiliation"=>"DataCite", "creatorName"=> {"__content__"=>"Fenner, Martin", "nameType"=>"Personal"}, "givenName"=>"Martin", "familyName"=>"Fenner", "nameIdentifier"=>{"__content__"=>"https://orcid.org/0000-0003-0077-4738", "nameIdentifierScheme"=>"ORCID", "schemeURI"=>"https://orcid.org"})
+      expect(datacite.dig("publisher")).to eq("DataCite")
     end
 
     it "with version" do
@@ -146,7 +154,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.dates).to eq([{"date"=>"2015-08-19", "dateType"=>"Issued"}])
       expect(subject.publication_year).to eq("2015")
       expect(subject.version_info).to eq("v0.3.2")
-      expect(subject.publisher).to eq("Zenodo")
+      expect(subject.publisher).to eq({"name"=>"Zenodo"})
       expect(subject.agency).to eq("datacite")
       expect(subject.schema_version).to eq("http://datacite.org/schema/kernel-4")
       expect(subject.datacite).to include("<version>v0.3.2</version>")
@@ -168,7 +176,7 @@ describe Bolognese::Metadata, vcr: true do
         "schemeUri"=>"https://spdx.org/licenses/"}])
       expect(subject.dates).to eq([{"date"=>"2017-06-28", "dateType"=>"Created"}, {"date"=>"2017-06-28", "dateType"=>"Updated"}, {"date"=>"2017", "dateType"=>"Issued"}])
       expect(subject.publication_year).to eq("2017")
-      expect(subject.publisher).to eq("Figshare")
+      expect(subject.publisher).to eq({"name"=>"Figshare"})
       expect(subject.subjects).to eq([{"subject"=>"Information Systems"},
        {"schemeUri"=>"http://www.oecd.org/science/inno/38235147.pdf",
         "subject"=>"FOS: Computer and information sciences",
@@ -194,7 +202,7 @@ describe Bolognese::Metadata, vcr: true do
         "schemeUri"=>"https://spdx.org/licenses/"}])
       expect(subject.dates).to eq([{"date"=>"2017-06-28", "dateType"=>"Created"}, {"date"=>"2017-06-28", "dateType"=>"Updated"}, {"date"=>"2017", "dateType"=>"Issued"}])
       expect(subject.publication_year).to eq("2017")
-      expect(subject.publisher).to eq("Figshare")
+      expect(subject.publisher).to eq({"name"=>"Figshare"})
       expect(subject.subjects).to eq([{"subject"=>"Information Systems"},
        {"schemeUri"=>"http://www.oecd.org/science/inno/38235147.pdf",
         "subject"=>"FOS: Computer and information sciences",
@@ -223,12 +231,13 @@ describe Bolognese::Metadata, vcr: true do
       expect(subject.related_identifiers.length).to eq(1)
       expect(subject.related_identifiers.last).to eq("relatedIdentifier" => "10.1371/journal.ppat.1000446",
         "relatedIdentifierType" => "DOI","relationType"=>"Cites")
-      expect(subject.publisher).to eq("Dryad")
+      expect(subject.publisher).to eq({"name"=>"Dryad"})
       expect(subject.agency).to eq("datacite")
       expect(subject.schema_version).to eq("http://datacite.org/schema/kernel-4")
 
       datacite = Maremma.from_xml(subject.datacite).fetch("resource", {})
       expect(datacite.fetch("xsi:schemaLocation", "").split(" ").first).to eq("http://datacite.org/schema/kernel-4")
+      expect(datacite.dig("publisher")).to eq("Dryad")
     end
 
     it "Affiliation" do
@@ -248,13 +257,83 @@ describe Bolognese::Metadata, vcr: true do
         "schemeUri"=>"https://spdx.org/licenses/"}])
       expect(subject.dates).to eq([{"date"=>"2014-10-17", "dateType"=>"Updated"}, {"date"=>"2016-03-14T17:02:02Z", "dateType"=>"Available"}, {"date"=>"2013", "dateType"=>"Issued"}])
       expect(subject.publication_year).to eq("2013")
-      expect(subject.publisher).to eq("UC Merced")
+      expect(subject.publisher).to eq({"name"=>"UC Merced"})
       expect(subject.agency).to eq("datacite")
       expect(subject.schema_version).to eq("http://datacite.org/schema/kernel-4")
 
       datacite = Maremma.from_xml(subject.datacite).fetch("resource", {})
       expect(datacite.fetch("xsi:schemaLocation", "").split(" ").first).to eq("http://datacite.org/schema/kernel-4")
       expect(datacite.dig("creators", "creator", 0, "affiliation")).to eq(["UC Merced", "NSF"])
+      expect(datacite.dig("publisher")).to eq("UC Merced")
+    end
+
+    it "Schema 4.5 publisher with attributes" do
+      input = fixture_path + 'datacite-example-full-v4.5.xml'
+      doi = "10.82433/B09Z-4K37"
+      subject = Bolognese::Metadata.new(input: input, from: "datacite", regenerate: true)
+      expect(subject.valid?).to be true
+
+      datacite = Maremma.from_xml(subject.datacite).fetch("resource", {})
+      expect(datacite.fetch("xsi:schemaLocation", "").split(" ").first).to eq("http://datacite.org/schema/kernel-4")
+      expect(datacite.dig("publisher")).to eq(
+        {
+          "__content__" => "Example Publisher",
+          "publisherIdentifier" => "https://ror.org/04z8jg394",
+          "publisherIdentifierScheme" => "ROR",
+          "schemeURI" => "https://ror.org/",
+          "xml:lang" => "en",
+        }
+      )
+    end
+
+    it "Geolocations" do
+      input = fixture_path + 'datacite-example-full-v4.5.xml'
+      doi = "10.82433/B09Z-4K37"
+      subject = Bolognese::Metadata.new(input: input, from: "datacite", regenerate: true)
+      expect(subject.valid?).to be true
+
+      datacite = Maremma.from_xml(subject.datacite).fetch("resource", {})
+      expect(datacite.dig("geoLocations", "geoLocation", "geoLocationPlace")).to eq("Vancouver, British Columbia, Canada")
+      expect(datacite.dig("geoLocations", "geoLocation", "geoLocationPoint")).to eq(
+        {
+          "pointLatitude" => "49.2827",
+          "pointLongitude" => "-123.1207",
+        }
+      )
+      expect(datacite.dig("geoLocations", "geoLocation", "geoLocationBox")).to eq(
+        {
+          "westBoundLongitude" => "-123.27",
+          "eastBoundLongitude" => "-123.02",
+          "southBoundLatitude" => "49.195",
+          "northBoundLatitude" => "49.315",
+        }
+      )
+      expect(datacite.dig("geoLocations", "geoLocation", "geoLocationPolygon")).to eq(
+        { 
+          "polygonPoint" => [
+            {
+              "pointLatitude" => "41.991",
+              "pointLongitude" => "-71.032",
+            },
+            {
+              "pointLatitude" => "42.893",
+              "pointLongitude" => "-69.622",
+            },
+            {
+              "pointLatitude" => "41.991",
+              "pointLongitude" => "-68.211",
+            },
+            {
+              "pointLatitude" => "41.090",
+              "pointLongitude" => "-69.622",
+            },
+            {
+              "pointLatitude" => "41.991",
+              "pointLongitude" => "-71.032",
+            },
+          ]
+        }
+      )
     end
 
     it "with data citation schema.org" do

data/spec/writers/jats_writer_spec.rb

@@ -11,6 +11,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(jats.dig("publication_type")).to eq("journal")
       expect(jats.dig("article_title")).to eq("Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth")
       expect(jats.dig("source")).to eq("eLife")
+      expect(jats.dig("publisher_name")).to eq("eLife Sciences Publications, Ltd")
       expect(jats.dig("person_group", "name").length).to eq(5)
       expect(jats.dig("person_group", "name").first).to eq("surname"=>"Sankar", "given_names"=>"Martial")
       expect(jats.dig("year")).to eq("iso_8601_date"=>"2014-02-11", "__content__"=>"2014")
@@ -25,6 +26,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(jats.dig("publication_type")).to eq("journal")
       expect(jats.dig("article_title")).to eq("Delineating a Retesting Zone Using Receiver Operating Characteristic Analysis on Serial QuantiFERON Tuberculosis Test Results in US Healthcare Workers")
       expect(jats.dig("source")).to eq("Pulmonary Medicine")
+      expect(jats.dig("publisher_name")).to eq("Hindawi Limited")
       expect(jats.dig("person_group", "name").length).to eq(7)
       expect(jats.dig("person_group", "name").first).to eq("surname"=>"Thanassi", "given_names"=>"Wendy")
       expect(jats.dig("year")).to eq("iso_8601_date"=>"2012", "__content__"=>"2012")
@@ -37,6 +39,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(jats.dig("publication_type")).to eq("journal")
       expect(jats.dig("article_title")).to eq("Triose Phosphate Isomerase Deficiency Is Caused by Altered Dimerization???Not Catalytic Inactivity???of the Mutant Enzymes")
       expect(jats.dig("source")).to eq("PLoS ONE")
+      expect(jats.dig("publisher_name")).to eq("Public Library of Science (PLoS)")
       expect(jats.dig("person_group", 0, "name").length).to eq(5)
       expect(jats.dig("person_group", 0, "name").first).to eq("surname"=>"Ralser", "given_names"=>"Markus")
       expect(jats.dig("person_group", 1, "name")).to eq("surname"=>"Janbon", "given_names"=>"Guilhem")
@@ -54,6 +57,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(jats.dig("publication_type")).to eq("chapter")
       expect(jats.dig("chapter_title")).to eq("Physical Examinations")
       expect(jats.dig("source")).to eq("Jaypee Brothers Medical Publishing")
+      expect(jats.dig("publisher_name")).to eq("Jaypee Brothers Medical Publishing")
       expect(jats.dig("person_group", "name")).to eq("surname"=>"Saha", "given_names"=>"Ashis")
       expect(jats.dig("year")).to eq("iso_8601_date"=>"2015", "__content__"=>"2015")
       expect(jats.dig("fpage")).to eq("27")
@@ -68,6 +72,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(jats.dig("publication_type")).to eq("journal")
       expect(jats.dig("article_title")).to eq("Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth")
       expect(jats.dig("source")).to eq("eLife")
+      expect(jats.dig("publisher_name")).to eq("{eLife} Sciences Organisation, Ltd.")
       expect(jats.dig("person_group", "name").length).to eq(5)
       expect(jats.dig("person_group", "name").first).to eq("surname"=>"Sankar", "given_names"=>"Martial")
       expect(jats.dig("year")).to eq("iso_8601_date"=>"2014", "__content__"=>"2014")
@@ -126,6 +131,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(jats.dig("publication_type")).to eq("journal")
       expect(jats.dig("article_title")).to eq("Recommendation of: ORCID Works Metadata Working Group")
       expect(jats.dig("source")).to eq("Figshare")
+      expect(jats.dig("publisher_name")).to eq("Figshare")
       expect(jats.dig("person_group", "name").length).to eq(20)
       expect(jats.dig("person_group", "name").first).to eq("surname"=>"Paglione", "given_names"=>"Laura")
       expect(jats.dig("year")).to eq("iso_8601_date"=>"2017", "__content__"=>"2017")
@@ -139,6 +145,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(jats.dig("publication_type")).to eq("data")
       expect(jats.dig("data_title")).to eq("Data from: A new malaria agent in African hominids.")
       expect(jats.dig("source")).to eq("Dryad")
+      expect(jats.dig("publisher_name")).to eq(nil)
       expect(jats.dig("person_group", "name").length).to eq(8)
       expect(jats.dig("person_group", "name").first).to eq("surname"=>"Ollomo", "given_names"=>"Benjamin")
       expect(jats.dig("year")).to eq("iso_8601_date"=>"2011", "__content__"=>"2011")
@@ -172,6 +179,13 @@ describe Bolognese::Metadata, vcr: true do
       expect(jats.dig("day")).to be_nil
       expect(jats.dig("pub_id")).to eq("pub_id_type"=>"doi", "__content__"=>"10.34747/g6yb-3412")
     end
+
+    it "with publisher with language" do
+      input = fixture_path + 'datacite-xml-lang.xml'
+      subject = Bolognese::Metadata.new(input: input)
+      jats = Maremma.from_xml(subject.jats).fetch("element_citation", {})
+      expect(jats.dig("publisher_name")).to eq({"xml:lang"=>"en", "__content__"=>"OSI SAF"})
+    end
   end
 
   context "change metadata as datacite xml" do
@@ -182,6 +196,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(jats.dig("publication_type")).to eq("journal")
       expect(jats.dig("article_title")).to eq("Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth")
       expect(jats.dig("source")).to eq("eLife")
+      expect(jats.dig("publisher_name")).to eq("eLife Sciences Publications, Ltd")
       expect(jats.dig("person_group", "name").length).to eq(5)
       expect(jats.dig("person_group", "name").first).to eq("surname"=>"Sankar", "given_names"=>"Martial")
       expect(jats.dig("year")).to eq("iso_8601_date"=>"2014-02-11", "__content__"=>"2014")

data/spec/writers/rdf_xml_writer_spec.rb

@@ -12,6 +12,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(rdf_xml.dig("ScholarlyArticle", "rdf:about")).to eq("https://doi.org/10.7554/elife.01567")
       expect(rdf_xml.dig("ScholarlyArticle", "name")).to eq("Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth")
       expect(rdf_xml.dig("ScholarlyArticle", "datePublished", "__content__")).to eq("2014-02-11")
+      expect(rdf_xml.dig("ScholarlyArticle", "publisher", "Organization", "name")).to eq("eLife Sciences Publications, Ltd")
     end
     
     it "with pages" do
@@ -24,6 +25,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(rdf_xml.dig("ScholarlyArticle", "datePublished", "__content__")).to eq("2012")
       expect(rdf_xml.dig("ScholarlyArticle", "pageStart")).to eq("1")
       expect(rdf_xml.dig("ScholarlyArticle", "pageEnd")).to eq("7")
+      expect(rdf_xml.dig("ScholarlyArticle", "publisher", "Organization", "name")).to eq("Hindawi Limited")
     end
 
     it "Crossref DOI" do
@@ -36,6 +38,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(rdf_xml.dig("ScholarlyArticle", "name")).to eq("Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth")
       expect(rdf_xml.dig("ScholarlyArticle", "datePublished", "__content__")).to eq("2014")
       expect(rdf_xml.dig("ScholarlyArticle", "periodical", "Journal", "name")).to eq("eLife")
+      expect(rdf_xml.dig("ScholarlyArticle", "publisher", "Organization", "name")).to eq("{eLife} Sciences Organisation, Ltd.")
     end
 
     it "BlogPosting" do
@@ -47,6 +50,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(rdf_xml.dig("ScholarlyArticle", "name")).to eq("Eating your own Dog Food")
       expect(rdf_xml.dig("ScholarlyArticle", "keywords")).to eq("datacite, doi, metadata, FOS: Computer and information sciences, FOS: Computer and information sciences")
       expect(rdf_xml.dig("ScholarlyArticle", "datePublished", "__content__")).to eq("2016-12-20")
+      expect(rdf_xml.dig("ScholarlyArticle", "publisher", "Organization", "name")).to eq("DataCite")
     end
     
     it "BlogPosting Citeproc JSON" do
@@ -56,6 +60,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(rdf_xml.dig("BlogPosting", "rdf:about")).to eq("https://doi.org/10.5438/4k3m-nyvg")
       expect(rdf_xml.dig("BlogPosting", "name")).to eq("Eating your own Dog Food")
       expect(rdf_xml.dig("BlogPosting", "datePublished", "__content__")).to eq("2016-12-20")
+      expect(rdf_xml.dig("BlogPosting", "publisher", "Organization", "name")).to eq("DataCite")
     end
     
     it "maremma" do
@@ -68,6 +73,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(rdf_xml.dig("SoftwareSourceCode", "name")).to eq("Maremma: a Ruby library for simplified network calls")
       expect(rdf_xml.dig("SoftwareSourceCode", "keywords")).to eq("faraday, excon, net/http")
       expect(rdf_xml.dig("SoftwareSourceCode", "datePublished", "__content__")).to eq("2017-02-24")
+      expect(rdf_xml.dig("SoftwareSourceCode", "publisher", "Organization", "name")).to eq("DataCite")
     end
 
     it "BlogPosting schema.org" do
@@ -81,6 +87,7 @@ describe Bolognese::Metadata, vcr: true do
       expect(rdf_xml.dig("BlogPosting", "name")).to eq("Eating your own Dog Food")
       expect(rdf_xml.dig("BlogPosting", "keywords")).to eq("datacite, doi, metadata, featured")
       expect(rdf_xml.dig("BlogPosting", "datePublished", "__content__")).to eq("2016-12-20")
+      expect(rdf_xml.dig("BlogPosting", "publisher", "Organization", "name")).to eq("DataCite")
     end
   end
 end

data/spec/writers/schema_org_writer_spec.rb

@@ -365,5 +365,18 @@ describe Bolognese::Metadata, vcr: true do
       expect(json["@type"]).to eq("CreativeWork")
       expect(json["datePublished"]).to eq("2019")
     end
+
+    it "from Schema 4.5 with publisher attributes" do
+      input = fixture_path + 'datacite-example-full-v4.5.xml'
+      subject = Bolognese::Metadata.new(input: input)
+      json = JSON.parse(subject.schema_org)
+      expect(json["publisher"]).to eq(
+         {
+          "@type" => "Organization",
+          "@id" => "https://ror.org/04z8jg394",
+          "name" => "Example Publisher"
+         }
+      )
+    end
   end
 end