commonmeta-ruby 3.2.13 → 3.2.15

data/spec/readers/schema_org_reader_spec.rb

@@ -27,7 +27,7 @@ describe Commonmeta::Metadata, vcr: true do
                                         'type' => 'Person' }])
       expect(subject.titles).to eq([{ 'title' => 'Eating your own Dog Food' }])
       expect(subject.descriptions.first['description']).to start_with('Eating your own dog food')
-      expect(subject.subjects).to eq([{ 'subject' => 'feature' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Feature' }])
       expect(subject.date).to eq('published' => '2016-12-20T00:00:00Z',
                                  'updated' => '2022-08-15T09:06:22Z')
       expect(subject.references.length).to eq(0)
@@ -56,8 +56,8 @@ describe Commonmeta::Metadata, vcr: true do
                                         'type' => 'Person' }])
       expect(subject.titles).to eq([{ 'title' => 'Eating your own Dog Food' }])
       expect(subject.descriptions.first['description']).to start_with('Eating your own dog food')
-      expect(subject.subjects).to eq([{ 'subject' => 'datacite' }, { 'subject' => 'doi' },
-                                      { 'subject' => 'metadata' }, { 'subject' => 'featured' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Datacite' }, { 'subject' => 'Doi' },
+                                      { 'subject' => 'Metadata' }, { 'subject' => 'Featured' }])
       expect(subject.date).to eq('created' => '2016-12-20',
                                  'published' => '2016-12-20',
                                  'updated' => '2016-12-20')
@@ -81,7 +81,7 @@ describe Commonmeta::Metadata, vcr: true do
                                           'type' => 'Person' }])
         expect(subject.titles).to eq([{ 'title' => 'A step forward for software citation: GitHub's enhanced software citation support' }])
         expect(subject.descriptions.first['description']).to start_with('On August 19, GitHub announced software citation')
-        expect(subject.subjects).to eq([{ 'subject' => 'news' }])
+        expect(subject.subjects).to eq([{ 'subject' => 'News' }])
         expect(subject.date).to eq('published' => '2021-08-24T16:57:24Z',
                                    'updated' => '2022-08-15T19:05:14Z')
         expect(subject.references.length).to eq(0)
@@ -104,18 +104,18 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.creators.first).to eq('type' => 'Person', 'givenName' => 'Matthias',
                                            'familyName' => 'Staib', 'id' => 'https://orcid.org/0000-0001-9688-838X', 'affiliation' => [{ 'name' => 'University of Zurich, Zurich, Switzerland' }])
       expect(subject.publisher).to eq('name' => 'Zenodo')
-      expect(subject.subjects).to eq([{ 'subject' => 'pupil size response' },
-                                      { 'subject' => 'skin conductance response' },
-                                      { 'subject' => 'electrocardiogram' },
-                                      { 'subject' => 'electromyogram' },
-                                      { 'subject' => 'electrodermal activity' },
-                                      { 'subject' => 'galvanic skin response' },
-                                      { 'subject' => 'psr' },
-                                      { 'subject' => 'scr' },
-                                      { 'subject' => 'ecg' },
-                                      { 'subject' => 'emg' },
-                                      { 'subject' => 'eda' },
-                                      { 'subject' => 'gsr' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Pupil size response' },
+                                      { 'subject' => 'Skin conductance response' },
+                                      { 'subject' => 'Electrocardiogram' },
+                                      { 'subject' => 'Electromyogram' },
+                                      { 'subject' => 'Electrodermal activity' },
+                                      { 'subject' => 'Galvanic skin response' },
+                                      { 'subject' => 'Psr' },
+                                      { 'subject' => 'Scr' },
+                                      { 'subject' => 'Ecg' },
+                                      { 'subject' => 'Emg' },
+                                      { 'subject' => 'Eda' },
+                                      { 'subject' => 'Gsr' }])
     end
 
     it 'pangaea' do
@@ -157,15 +157,15 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.creators).to eq([{
                                        'name' => 'International Genetics of Ankylosing Spondylitis Consortium (IGAS)'
                                      }])
-      expect(subject.subjects).to eq([{ 'subject' => 'medicine, health and life sciences' },
+      expect(subject.subjects).to eq([{ 'subject' => 'Medicine, health and life sciences' },
                                       { 'subject' => 'genome-wide association studies' },
-                                      { 'subject' => 'ankylosing spondylitis' }])
+                                      { 'subject' => 'Ankylosing spondylitis' }])
     end
 
     it 'upstream blog' do
       input = 'https://upstream.force11.org/elife-reviewed-preprints-interview-with-fiona-hutton'
       subject = described_class.new(input: input, from: 'schema_org')
-      # expect(subject.valid?).to be true
+      expect(subject.valid?).to be true
       expect(subject.id).to eq('https://doi.org/10.54900/8d7emer-rm2pg72')
       expect(subject.type).to eq('Article')
       expect(subject.titles).to eq([{ 'title' => 'eLife Reviewed Preprints: Interview with Fiona Hutton' }])
@@ -175,7 +175,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.creators.first).to eq('familyName' => 'Hutton',
                                            'givenName' => 'Fiona',
                                            'type' => 'Person')
-      expect(subject.subjects).to eq([{ 'subject' => 'interviews' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Interviews' }])
       expect(subject.publisher).to eq('name' => 'Upstream')
       expect(subject.date).to eq('published' => '2022-11-15T10:29:38Z',
                                  'updated' => '2023-01-11T22:58:48Z')
@@ -210,8 +210,8 @@ describe Commonmeta::Metadata, vcr: true do
                                         'type' => 'Person' }])
       expect(subject.titles).to eq([{ 'title' => 'Eating your own Dog Food' }])
       expect(subject.descriptions.first['description']).to start_with('Eating your own dog food')
-      expect(subject.subjects).to eq([{ 'subject' => 'datacite' }, { 'subject' => 'doi' },
-                                      { 'subject' => 'metadata' }, { 'subject' => 'featured' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Datacite' }, { 'subject' => 'Doi' },
+                                      { 'subject' => 'Metadata' }, { 'subject' => 'Featured' }])
       expect(subject.date).to eq('created' => '2016-12-20',
                                  'published' => '2016-12-20',
                                  'updated' => '2016-12-20')
@@ -235,8 +235,8 @@ describe Commonmeta::Metadata, vcr: true do
                                         'type' => 'Organization' }])
       expect(subject.titles).to eq([{ 'title' => 'Fully processed, filtered and normalized gene expression matrices (in BED format) for each tissue, which were used as input into FastQTL for eQTL discovery' }])
       expect(subject.version).to eq('v7')
-      expect(subject.subjects).to eq([{ 'subject' => 'gtex' }, { 'subject' => 'annotation' },
-                                      { 'subject' => 'phenotype' }, { 'subject' => 'gene regulation' }, { 'subject' => 'transcriptomics' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Gtex' }, { 'subject' => 'Annotation' },
+                                      { 'subject' => 'Phenotype' }, { 'subject' => 'Gene regulation' }, { 'subject' => 'Transcriptomics' }])
       expect(subject.date).to eq('published' => '2017')
       expect(subject.container).to eq('title' => 'GTEx', 'type' => 'DataRepository')
       expect(subject.publisher).to eq('name' => 'GTEx')
@@ -263,8 +263,8 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.type).to eq('Dataset')
       expect(subject.creators).to eq([{ 'name' => 'TOPMed IRC', 'type' => 'Organization' }])
       expect(subject.titles).to eq([{ 'title' => 'NWD165827.recab.cram' }])
-      expect(subject.subjects).to eq([{ 'subject' => 'topmed' },
-                                      { 'subject' => 'whole genome sequencing' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Topmed' },
+                                      { 'subject' => 'Whole genome sequencing' }])
       expect(subject.date).to eq('published' => '2017-11-30')
       expect(subject.publisher).to eq('name' => 'TOPMed')
       expect(subject.references).to eq([{ 'doi' => '10.23725/2g4s-qv04',
@@ -292,14 +292,14 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.creators.first).to eq('familyName' => 'Bales', 'givenName' => 'Roger',
                                            'type' => 'Person')
       expect(subject.titles).to eq([{ 'title' => 'Southern Sierra Critical Zone Observatory (SSCZO), Providence Creek meteorological data, soil moisture and temperature, snow depth and air temperature' }])
-      expect(subject.subjects).to eq([{ 'subject' => 'earth sciences' },
-                                      { 'subject' => 'soil moisture' },
-                                      { 'subject' => 'soil temperature' },
-                                      { 'subject' => 'snow depth' },
-                                      { 'subject' => 'air temperature' },
-                                      { 'subject' => 'water balance' },
-                                      { 'subject' => 'nevada' },
-                                      { 'subject' => 'sierra (mountain range)' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Earth sciences' },
+                                      { 'subject' => 'Soil moisture' },
+                                      { 'subject' => 'Soil temperature' },
+                                      { 'subject' => 'Snow depth' },
+                                      { 'subject' => 'Air temperature' },
+                                      { 'subject' => 'Water balance' },
+                                      { 'subject' => 'Nevada' },
+                                      { 'subject' => 'Sierra (mountain range)' }])
       expect(subject.date).to eq('published' => '2013', 'updated' => '2014-10-17')
       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' }])
@@ -347,8 +347,8 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.type).to eq('Dataset')
       expect(subject.creators).to eq([{ 'name' => 'TOPMed', 'type' => 'Organization' }])
       expect(subject.titles).to eq([{ 'title' => 'NWD100953.recab.cram' }])
-      expect(subject.subjects).to eq([{ 'subject' => 'topmed' },
-                                      { 'subject' => 'whole genome sequencing' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Topmed' },
+                                      { 'subject' => 'Whole genome sequencing' }])
       expect(subject.date).to eq('published' => '2017-11-30')
       expect(subject.publisher).to eq('name' => 'TOPMed')
       expect(subject.funding_references).to eq([{
@@ -367,8 +367,8 @@ describe Commonmeta::Metadata, vcr: true do
       # expect(subject.creators).to eq([{"familyName"=>"Lindman", "givenName"=>"Karin", "name"=>"Lindman, Karin", "nameIdentifiers"=>[{"nameIdentifier"=> "https://orcid.org/0000-0003-1298-517X", "nameIdentifierScheme"=>"ORCID", "schemeUri"=>"https://orcid.org"}], "type"=>"Person"}])
       expect(subject.titles).to eq([{ 'title' => 'Ovary data from the Visual Sweden project DROID' }])
       expect(subject.version).to eq('1.0')
-      expect(subject.subjects).to eq([{ 'subject' => 'pathology' }, { 'subject' => 'whole slide imaging' },
-                                      { 'subject' => 'annotated' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Pathology' }, { 'subject' => 'Whole slide imaging' },
+                                      { 'subject' => 'Annotated' }])
       expect(subject.date).to eq('created' => '2019-01-09',
                                  'published' => '2019-01-09',
                                  'updated' => '2019-01-09')

data/spec/utils_spec.rb

@@ -582,7 +582,7 @@ describe Commonmeta::Metadata, vcr: true do
     it "name_to_fos match" do
       name = "Biological sciences"
       response = subject.name_to_fos(name)
-      expect(response).to eq([{ "subject" => "biological sciences" },
+      expect(response).to eq([{ "subject" => "Biological sciences" },
                               { "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf",
                                 "subject" => "FOS: Biological sciences",
                                 "subjectScheme" => "Fields of Science and Technology (FOS)" }])
@@ -591,7 +591,7 @@ describe Commonmeta::Metadata, vcr: true do
     it "name_to_fos for match" do
       name = "Statistics"
       response = subject.name_to_fos(name)
-      expect(response).to eq([{ "subject" => "statistics" },
+      expect(response).to eq([{ "subject" => "Statistics" },
                               { "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf",
                                 "subject" => "FOS: Mathematics",
                                 "subjectScheme" => "Fields of Science and Technology (FOS)" }])
@@ -600,7 +600,7 @@ describe Commonmeta::Metadata, vcr: true do
     it "name_to_fos no match" do
       name = "Random tag"
       response = subject.name_to_fos(name)
-      expect(response).to eq([{ "subject" => "random tag" }])
+      expect(response).to eq([{ "subject" => "Random tag" }])
     end
 
     it "hsh_to_fos match" do

data/spec/writers/bibtex_writer_spec.rb

@@ -71,7 +71,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(bibtex[:title]).to eq('Maremma: a Ruby library for simplified network calls')
       expect(bibtex[:author]).to eq('Fenner, Martin')
       expect(bibtex[:publisher]).to eq('DataCite')
-      expect(bibtex[:keywords]).to eq('faraday, excon, net/http')
+      expect(bibtex[:keywords]).to eq('Faraday, excon, net/http')
       expect(bibtex[:year]).to eq('2017')
       expect(bibtex[:copyright]).to eq('MIT')
     end
@@ -128,7 +128,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(bibtex[:title]).to eq('Eating your own Dog Food')
       expect(bibtex[:author]).to eq('Fenner, Martin')
       expect(bibtex[:publisher]).to eq('Front Matter')
-      expect(bibtex[:keywords]).to eq('feature')
+      expect(bibtex[:keywords]).to eq('Feature')
       expect(bibtex[:year]).to eq('2016')
     end
 
@@ -152,7 +152,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(bibtex[:bibtex_type].to_s).to eq('misc')
       expect(bibtex[:bibtex_key]).to eq('https://doi.org/10.1594/pangaea.721193')
       expect(bibtex[:doi]).to eq('10.1594/pangaea.721193')
-      expect(bibtex[:keywords]).to start_with('Animalia, Bottles or small containers/Aquaria (<20 L)')
+      expect(bibtex[:keywords]).to start_with('Animalia, bottles or small containers/aquaria (<20 l)')
       expect(bibtex[:year]).to eq('2007')
       expect(bibtex[:copyright]).to eq('CC-BY-3.0')
     end

data/spec/writers/cff_writer_spec.rb

@@ -73,8 +73,8 @@ describe Commonmeta::Metadata, vcr: true do
       expect(json['abstract']).to eq('This library provides a Ruby interface to manipulate Citation File Format files')
       expect(json['date-released']).to eq('2022-11-05')
       expect(json['repository-code']).to eq('https://github.com/citation-file-format/ruby-cff')
-      expect(json['keywords']).to eq(['ruby', 'credit', 'software citation', 'research software',
-                                      'software sustainability', 'metadata', 'citation file format', 'cff'])
+      expect(json['keywords']).to eq(['Ruby', 'Credit', 'Software citation', 'Research software',
+                                      'Software sustainability', 'Metadata', 'Citation file format', 'Cff'])
       expect(json['license']).to eq('Apache-2.0')
       expect(json['references']).to eq('identifiers' => [{ 'type' => 'doi',
                                                            'value' => '10.5281/zenodo.1003149' }])

data/spec/writers/crossref_xml_writer_spec.rb

@@ -68,7 +68,7 @@ describe Commonmeta::Metadata, vcr: true do
                                         "givenName" => "Martin",
                                         "id" => "https://orcid.org/0000-0003-1419-2405",
                                         "type" => "Person" }])
-      expect(subject.subjects).to eq([{ "subject" => "news" }])
+      expect(subject.subjects).to eq([{ "subject" => "News" }])
       expect(subject.language).to eq("en")
       expect(subject.license).to eq("id" => "CC-BY-4.0",
                                     "url" => "https://creativecommons.org/licenses/by/4.0/legalcode")
@@ -89,7 +89,7 @@ describe Commonmeta::Metadata, vcr: true do
                                         "givenName" => "Martin",
                                         "id" => "https://orcid.org/0000-0003-1419-2405",
                                         "type" => "Person" }])
-      expect(subject.subjects).to eq([{ "subject" => "interview" }])
+      expect(subject.subjects).to eq([{ "subject" => "Interview" }])
       expect(subject.container).to eq("identifier" => "https://blog.front-matter.io/", "identifierType" => "URL",
                                       "title" => "Front Matter", "type" => "Periodical")
       expect(subject.language).to eq("en")
@@ -157,7 +157,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.creators.first).to eq("familyName" => "Hosseini",
                                            "givenName" => "Mohammad",
                                            "type" => "Person")
-      expect(subject.subjects).to eq([{ "subject" => "news" }])
+      expect(subject.subjects).to eq([{ "subject" => "News" }])
       expect(subject.language).to eq("en")
       expect(subject.license).to eq("id" => "CC-BY-4.0",
                                     "url" => "https://creativecommons.org/licenses/by/4.0/legalcode")
@@ -181,7 +181,10 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.titles).to eq([{ "title" => "Attempts at automating journal subject classification" }])
       expect(subject.creators.length).to eq(1)
       expect(subject.creators.first).to eq("familyName" => "Datta", "givenName" => "Esha", "id" => "https://orcid.org/0000-0001-9165-2757", "type" => "Person")
-      expect(subject.subjects).to eq([{ "subject" => "original research" }])
+      expect(subject.subjects).to eq([{"subject"=>"Humanities"},
+        {"schemeUri"=>"http://www.oecd.org/science/inno/38235147.pdf",
+         "subject"=>"FOS: Humanities",
+         "subjectScheme"=>"Fields of Science and Technology (FOS)"}])
       expect(subject.language).to eq("en")
       expect(subject.license).to eq("id" => "CC-BY-4.0",
                                     "url" => "https://creativecommons.org/licenses/by/4.0/legalcode")
@@ -191,7 +194,8 @@ describe Commonmeta::Metadata, vcr: true do
                                          "person_name")).first).to eq("ORCID" => "https://orcid.org/0000-0001-9165-2757", "contributor_role" => "author", "given_name" => "Esha", "sequence" => "first", "surname" => "Datta")
       expect(crossref_xml.dig("titles",
                               "title")).to eq("Attempts at automating journal subject classification")
-      expect(crossref_xml.dig('item_number')).to eq("__content__"=>"2x2kzts-edc9rgb-vg6s4j6-z9t0d56", "item_number_type"=>"uuid")
+      expect(crossref_xml.dig('item_number')).to eq("__content__"=>"5d14ffacb9ac4e20bdc0d9248df4e80d", "item_number_type"=>"uuid")
+      expect(crossref_xml.dig('group_title')).to eq('Humanities')
     end
 
     it "json_feed_item with references" do
@@ -206,7 +210,10 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.titles).to eq([{ "title" => "The Research Software Alliance (ReSA)" }])
       expect(subject.creators.length).to eq(2)
       expect(subject.creators.first).to eq("familyName"=>"Katz", "givenName"=>"Daniel S.", "id"=>"https://orcid.org/0000-0001-5934-7525", "type"=>"Person")
-      expect(subject.subjects).to eq([{ "subject" => "news" }])
+      expect(subject.subjects).to eq([{"subject"=>"Humanities"},
+        {"schemeUri"=>"http://www.oecd.org/science/inno/38235147.pdf",
+         "subject"=>"FOS: Humanities",
+         "subjectScheme"=>"Fields of Science and Technology (FOS)"}])
       expect(subject.language).to eq("en")
       expect(subject.license).to eq("id" => "CC-BY-4.0",
                                     "url" => "https://creativecommons.org/licenses/by/4.0/legalcode")
@@ -219,7 +226,8 @@ describe Commonmeta::Metadata, vcr: true do
                               "title")).to eq("The Research Software Alliance (ReSA)")
       expect(crossref_xml.dig("citation_list", "citation").length).to eq(11)
       expect(crossref_xml.dig("citation_list", "citation").last).to eq("doi"=>"10.5281/zenodo.3699950", "key"=>"ref11")
-      expect(crossref_xml.dig('item_number')).to eq("__content__"=>"4n9y0kg-3pd8288-fheey4m-qy53g93", "item_number_type"=>"uuid")
+      expect(crossref_xml.dig('item_number')).to eq("__content__"=>"954f81380ecd409087c5cef1297f1470", "item_number_type"=>"uuid")
+      expect(crossref_xml.dig('group_title')).to eq('Humanities')
     end
 
     it "json_feed_item from rogue scholar with doi" do
@@ -233,7 +241,10 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.titles).to eq([{ "title" => "EU-Mitgliedstaaten betonen die Rolle von wissenschaftsgeleiteten Open-Access-Modellen jenseits von APCs" }])
       expect(subject.creators.length).to eq(1)
       expect(subject.creators.first).to eq("familyName"=>"Pampel", "givenName"=>"Heinz", "id"=>"https://orcid.org/0000-0003-3334-2771", "type"=>"Person")
-      expect(subject.subjects).to eq([{"subject"=>"open access"}, {"subject"=>"open access transformation"}, {"subject"=>"open science"}, {"subject"=>"eu"}])
+      expect(subject.subjects).to eq([{"subject"=>"Engineering and technology"},
+        {"schemeUri"=>"http://www.oecd.org/science/inno/38235147.pdf",
+         "subject"=>"FOS: Engineering and technology",
+         "subjectScheme"=>"Fields of Science and Technology (FOS)"}])
       expect(subject.language).to eq("de")
       expect(subject.license).to eq("id" => "CC-BY-4.0",
                                     "url" => "https://creativecommons.org/licenses/by/4.0/legalcode")
@@ -243,7 +254,8 @@ describe Commonmeta::Metadata, vcr: true do
                                          "person_name")).first).to eq("ORCID"=>"https://orcid.org/0000-0003-3334-2771", "contributor_role"=>"author", "given_name"=>"Heinz", "sequence"=>"first", "surname"=>"Pampel")
       expect(crossref_xml.dig("titles",
                               "title")).to eq("EU-Mitgliedstaaten betonen die Rolle von wissenschaftsgeleiteten Open-Access-Modellen jenseits von APCs")
-      expect(crossref_xml.dig('item_number')).to eq("__content__"=>"way2ng-4s48j9v-hbw4rjf-aqh9f33", "item_number_type"=>"uuid")
+      expect(crossref_xml.dig('item_number')).to eq("__content__"=>"1c57855813244493b8af84c49eabc52f", "item_number_type"=>"uuid")
+      expect(crossref_xml.dig('group_title')).to eq('Engineering and technology')
     end
   end
 end

data/spec/writers/ris_writer_spec.rb

@@ -56,7 +56,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(ris[9]).to eq('DO  - 10.3205/zma001102')
       expect(ris[10]).to eq('UR  - http://www.egms.de/en/journals/zma/2017-34/zma001102.shtml')
       expect(ris[11]).to start_with('AB  - Objective: Competence orientation')
-      expect(ris[12]).to eq('KW  - medical competence')
+      expect(ris[12]).to eq('KW  - Medical competence')
       expect(ris[22]).to eq('PY  - 2017')
       expect(ris[23]).to eq('PB  - German Medical Science GMS Publishing House')
       expect(ris[24]).to eq('LA  - en')
@@ -94,8 +94,8 @@ describe Commonmeta::Metadata, vcr: true do
       expect(ris[3]).to eq('DO  - 10.5438/4k3m-nyvg')
       expect(ris[4]).to eq('UR  - https://blog.datacite.org/eating-your-own-dog-food/')
       expect(ris[5]).to eq('AB  - 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...')
-      expect(ris[6]).to eq('KW  - datacite')
-      expect(ris[9]).to eq('KW  - FOS: Computer and information sciences')
+      expect(ris[6]).to eq('KW  - Datacite')
+      expect(ris[9]).to eq('KW  - Fos: computer and information sciences')
       expect(ris[10]).to eq('PY  - 2016')
       expect(ris[11]).to eq('PB  - DataCite')
       expect(ris[12]).to eq('LA  - en')
@@ -114,7 +114,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(ris[4]).to eq('DO  - 10.5438/4k3m-nyvg')
       expect(ris[5]).to eq('UR  - https://blog.datacite.org/eating-your-own-dog-food')
       expect(ris[6]).to eq('AB  - 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...')
-      expect(ris[7]).to eq('KW  - phylogeny')
+      expect(ris[7]).to eq('KW  - Phylogeny')
       expect(ris[14]).to eq('PY  - 2016')
       expect(ris[15]).to eq('PB  - DataCite')
       expect(ris[16]).to eq('ER  - ')
@@ -129,7 +129,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(ris[2]).to eq('AU  - Fenner, Martin')
       expect(ris[3]).to eq('DO  - 10.5438/4k3m-nyvg')
       expect(ris[4]).to eq('AB  - 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...')
-      expect(ris[5]).to eq('KW  - datacite')
+      expect(ris[5]).to eq('KW  - Datacite')
       expect(ris[8]).to eq('PY  - 2016')
       expect(ris[9]).to eq('PB  - DataCite')
       expect(ris[10]).to eq('ER  - ')
@@ -146,7 +146,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(ris[4]).to eq('DO  - 10.53731/r79vxn1-97aq74v-ag58n')
       expect(ris[5]).to eq('UR  - https://blog.front-matter.io/posts/eating-your-own-dog-food')
       expect(ris[6]).to eq('AB  - 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 the scholarly outputs we produce. For the most part this is not research data, but rather technical documents such as the DataCite Schema and its documentation (2016). These outputs also include the posts on this blog, where we discuss topics relev')
-      expect(ris[7]).to eq('KW  - feature')
+      expect(ris[7]).to eq('KW  - Feature')
       expect(ris[8]).to eq('PY  - 2016')
       expect(ris[9]).to eq('PB  - Front Matter')
       expect(ris[10]).to eq('LA  - en')
@@ -180,7 +180,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(ris[3]).to eq('DO  - 10.5438/qeg0-3gm3')
       expect(ris[4]).to eq('UR  - https://github.com/datacite/maremma')
       expect(ris[5]).to eq('AB  - Ruby utility library for network requests. Based on Faraday and Excon, provides a wrapper for XML/JSON parsing and error handling. All successful responses are returned as hash with key data, all errors in a JSONAPI-friendly hash with key errors.')
-      expect(ris[6]).to eq('KW  - faraday')
+      expect(ris[6]).to eq('KW  - Faraday')
       expect(ris[9]).to eq('PY  - 2017')
       expect(ris[10]).to eq('PB  - DataCite')
       expect(ris[11]).to eq('ER  - ')
@@ -196,7 +196,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(ris[5]).to eq('DO  - 10.1594/pangaea.721193')
       expect(ris[6]).to eq('UR  - https://doi.pangaea.de/10.1594/PANGAEA.721193')
       expect(ris[8]).to eq('KW  - Animalia')
-      expect(ris[9]).to eq('KW  - Bottles or small containers/Aquaria (<20 L)')
+      expect(ris[9]).to eq('KW  - Bottles or small containers/aquaria (<20 l)')
       expect(ris[51]).to eq('PY  - 2007')
       expect(ris[52]).to eq('PB  - PANGAEA')
       expect(ris[53]).to eq('LA  - en')

data/spec/writers/schema_org_writer_spec.rb

@@ -64,7 +64,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(json['@id']).to eq('https://doi.org/10.5061/dryad.8515')
       expect(json['@type']).to eq('Dataset')
       expect(json['license']).to eq('https://creativecommons.org/publicdomain/zero/1.0/legalcode')
-      expect(json['keywords']).to eq('Plasmodium, malaria, mitochondrial genome, Parasites')
+      expect(json['keywords']).to eq('Plasmodium, malaria, mitochondrial genome, parasites')
     end
 
     it 'Schema.org JSON Cyark' do
@@ -97,7 +97,7 @@ describe Commonmeta::Metadata, vcr: true do
                                     { '@type' => 'Organization',
                                       'name' => 'University of California, Santa Barbara' }])
       expect(json['version']).to eq('2.0.0')
-      expect(json['keywords']).to eq('data sharing, data repository, dataone')
+      expect(json['keywords']).to eq('Data sharing, data repository, dataone')
     end
 
     it 'Funding' do
@@ -129,7 +129,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(json['@id']).to eq('https://doi.org/10.4232/1.2745')
       expect(json['@type']).to eq('Dataset')
       expect(json['name']).to eq('Flash Eurobarometer 54 (Madrid Summit)')
-      expect(json['keywords']).to eq('KAT12 International Institutions, Relations, Conditions, Internationale Politik und Internationale Organisationen, Wirtschaftssysteme und wirtschaftliche Entwicklung, International politics and organisations, Economic systems and development')
+      expect(json['keywords']).to eq('Kat12 international institutions, relations, conditions, internationale politik und internationale organisationen, wirtschaftssysteme und wirtschaftliche entwicklung, international politics and organisations, economic systems and development')
     end
 
     it 'subject scheme multiple keywords' do
@@ -139,7 +139,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(json['@id']).to eq('https://doi.org/10.1594/pangaea.721193')
       expect(json['@type']).to eq('Dataset')
       expect(json['name']).to eq('Seawater carbonate chemistry and processes during experiments with Crassostrea gigas, 2007')
-      expect(json['keywords']).to include('Animalia, Bottles or small containers/Aquaria (<20 L)')
+      expect(json['keywords']).to include('Animalia, bottles or small containers/aquaria (<20 l)')
       expect(json['license']).to eq('https://creativecommons.org/licenses/by/3.0/legalcode')
     end
 
@@ -224,7 +224,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(json['name']).to eq('Fully processed, filtered and normalized gene expression matrices (in BED format) for each tissue, which were used as input into FastQTL for eQTL discovery')
       expect(json['version']).to eq('v7')
       expect(json['author']).to eq('@type' => 'Organization', 'name' => 'The GTEx Consortium')
-      expect(json['keywords']).to eq('gtex, annotation, phenotype, gene regulation, transcriptomics')
+      expect(json['keywords']).to eq('Gtex, annotation, phenotype, gene regulation, transcriptomics')
       expect(json['datePublished']).to eq('2017')
       expect(json['contentUrl']).to eq('https://storage.googleapis.com/gtex_analysis_v7/single_tissue_eqtl_data/GTEx_Analysis_v7_eQTL_expression_matrices.tar.gz')
       expect(json['schemaVersion']).to eq('http://datacite.org/schema/kernel-4')
@@ -275,7 +275,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(json['additionalType']).to eq('CRAM file')
       expect(json['name']).to eq('NWD165827.recab.cram')
       expect(json['author']).to eq('@type' => 'Organization', 'name' => 'TOPMed IRC')
-      expect(json['keywords']).to eq('topmed, whole genome sequencing')
+      expect(json['keywords']).to eq('Topmed, whole genome sequencing')
       expect(json['datePublished']).to eq('2017-11-30')
       expect(json['contentUrl']).to eq([
                                          's3://cgp-commons-public/topmed_open_access/197bc047-e917-55ed-852d-d563cdbc50e4/NWD165827.recab.cram', 'gs://topmed-irc-share/public/NWD165827.recab.cram'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: commonmeta-ruby
 version: !ruby/object:Gem::Version
-  version: 3.2.13
+  version: 3.2.15
 platform: ruby
 authors:
 - Martin Fenner
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-06-16 00:00:00.000000000 Z
+date: 2023-06-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -1185,6 +1185,7 @@ files:
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_with_doi.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_without_doi.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/jekyll_post.yml
+- spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/substack_post_with_broken_reference.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/syldavia_gazette_post_with_references.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/upstream_post_with_references.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/wordpress_post.yml