commonmeta-ruby 3.2.12 → 3.2.14

data/spec/readers/cff_reader_spec.rb

@@ -20,14 +20,14 @@ describe Commonmeta::Metadata, vcr: true do
                                         'type' => 'Organization' }])
       expect(subject.titles).to eq([{ 'title' => 'Ruby CFF Library' }])
       expect(subject.descriptions.first['description']).to start_with('This library provides a Ruby interface to manipulate Citation File Format files')
-      expect(subject.subjects).to eq([{ 'subject' => 'ruby' },
-                                      { 'subject' => 'credit' },
-                                      { 'subject' => 'software citation' },
-                                      { 'subject' => 'research software' },
-                                      { 'subject' => 'software sustainability' },
-                                      { 'subject' => 'metadata' },
-                                      { 'subject' => 'citation file format' },
-                                      { 'subject' => 'cff' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Ruby' },
+                                      { 'subject' => 'Credit' },
+                                      { 'subject' => 'Software citation' },
+                                      { 'subject' => 'Research software' },
+                                      { 'subject' => 'Software sustainability' },
+                                      { 'subject' => 'Metadata' },
+                                      { 'subject' => 'Citation file format' },
+                                      { 'subject' => 'Cff' }])
       expect(subject.version).to eq('1.0.1')
       expect(subject.date).to eq('published' => '2022-11-05')
       expect(subject.publisher).to eq('name' => 'GitHub')
@@ -69,15 +69,15 @@ describe Commonmeta::Metadata, vcr: true do
                                         'type' => 'Person' }])
       expect(subject.titles).to eq([{ 'title' => 'cffconvert' }])
       expect(subject.descriptions.first['description']).to start_with('Command line program to validate and convert CITATION.cff files')
-      expect(subject.subjects).to eq([{ 'subject' => 'bibliography' },
-                                      { 'subject' => 'bibtex' },
-                                      { 'subject' => 'cff' },
-                                      { 'subject' => 'citation' },
-                                      { 'subject' => 'citation.cff' },
-                                      { 'subject' => 'codemeta' },
-                                      { 'subject' => 'endnote' },
-                                      { 'subject' => 'ris' },
-                                      { 'subject' => 'citation file format' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Bibliography' },
+                                      { 'subject' => 'Bibtex' },
+                                      { 'subject' => 'Cff' },
+                                      { 'subject' => 'Citation' },
+                                      { 'subject' => 'Citation.cff' },
+                                      { 'subject' => 'Codemeta' },
+                                      { 'subject' => 'Endnote' },
+                                      { 'subject' => 'Ris' },
+                                      { 'subject' => 'Citation file format' }])
       expect(subject.version).to eq('2.0.0')
       expect(subject.date).to eq('published' => '2021-09-22')
       expect(subject.publisher).to eq('name' => 'GitHub')
@@ -98,14 +98,14 @@ describe Commonmeta::Metadata, vcr: true do
                                         'id' => 'https://orcid.org/0000-0002-9538-7919', 'type' => 'Person' }, { 'name' => 'The Ruby Citation File Format Developers', 'type' => 'Organization' }])
       expect(subject.titles).to eq([{ 'title' => 'Ruby CFF Library' }])
       expect(subject.descriptions.first['description']).to start_with('This library provides a Ruby interface to manipulate Citation File Format files')
-      expect(subject.subjects).to eq([{ 'subject' => 'ruby' },
-                                      { 'subject' => 'credit' },
-                                      { 'subject' => 'software citation' },
-                                      { 'subject' => 'research software' },
-                                      { 'subject' => 'software sustainability' },
-                                      { 'subject' => 'metadata' },
-                                      { 'subject' => 'citation file format' },
-                                      { 'subject' => 'cff' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Ruby' },
+                                      { 'subject' => 'Credit' },
+                                      { 'subject' => 'Software citation' },
+                                      { 'subject' => 'Research software' },
+                                      { 'subject' => 'Software sustainability' },
+                                      { 'subject' => 'Metadata' },
+                                      { 'subject' => 'Citation file format' },
+                                      { 'subject' => 'Cff' }])
       expect(subject.version).to eq('1.0.1')
       expect(subject.date).to eq('published' => '2022-11-05')
       expect(subject.publisher).to eq('name' => 'GitHub')
@@ -127,14 +127,14 @@ describe Commonmeta::Metadata, vcr: true do
                                         'id' => 'https://orcid.org/0000-0002-9538-7919', 'type' => 'Person' }, { 'name' => 'The Ruby Citation File Format Developers', 'type' => 'Organization' }])
       expect(subject.titles).to eq([{ 'title' => 'Ruby CFF Library' }])
       expect(subject.descriptions.first['description']).to start_with('This library provides a Ruby interface to manipulate Citation File Format files')
-      expect(subject.subjects).to eq([{ 'subject' => 'ruby' },
-                                      { 'subject' => 'credit' },
-                                      { 'subject' => 'software citation' },
-                                      { 'subject' => 'research software' },
-                                      { 'subject' => 'software sustainability' },
-                                      { 'subject' => 'metadata' },
-                                      { 'subject' => 'citation file format' },
-                                      { 'subject' => 'cff' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Ruby' },
+                                      { 'subject' => 'Credit' },
+                                      { 'subject' => 'Software citation' },
+                                      { 'subject' => 'Research software' },
+                                      { 'subject' => 'Software sustainability' },
+                                      { 'subject' => 'Metadata' },
+                                      { 'subject' => 'Citation file format' },
+                                      { 'subject' => 'Cff' }])
       expect(subject.version).to eq('1.0.1')
       expect(subject.date).to eq('published' => '2022-11-05')
       expect(subject.publisher).to eq('name' => 'GitHub')

data/spec/readers/codemeta_reader_spec.rb

@@ -28,8 +28,8 @@ describe Commonmeta::Metadata, vcr: true do
                                         'type' => 'Person' }])
       expect(subject.titles).to eq([{ 'title' => 'Maremma: a Ruby library for simplified network calls' }])
       expect(subject.descriptions.first['description']).to start_with('Ruby utility library for network requests')
-      expect(subject.subjects).to eq([{ 'subject' => 'faraday' }, { 'subject' => 'excon' },
-                                      { 'subject' => 'net/http' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Faraday' }, { 'subject' => 'Excon' },
+                                      { 'subject' => 'Net/http' }])
       expect(subject.date).to eq('created' => '2015-11-28',
                                  'published' => '2017-02-24',
                                  'updated' => '2017-02-24')
@@ -57,8 +57,8 @@ describe Commonmeta::Metadata, vcr: true do
                                         'type' => 'Organization' }])
       expect(subject.titles).to eq([{ 'title' => 'R Interface to the DataONE REST API' }])
       expect(subject.descriptions.first['description']).to start_with('Provides read and write access to data and metadata')
-      expect(subject.subjects).to eq([{ 'subject' => 'data sharing' }, { 'subject' => 'data repository' },
-                                      { 'subject' => 'dataone' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Data sharing' }, { 'subject' => 'Data repository' },
+                                      { 'subject' => 'Dataone' }])
       expect(subject.version).to eq('2.0.0')
       expect(subject.date).to eq('created' => '2016-05-27',
                                  'published' => '2016-05-27',
@@ -82,8 +82,8 @@ describe Commonmeta::Metadata, vcr: true do
                                         'type' => 'Person' }])
       expect(subject.titles).to eq([{ 'title' => 'Maremma: a Ruby library for simplified network calls' }])
       expect(subject.descriptions.first['description']).to start_with('Simplifies network calls')
-      expect(subject.subjects).to eq([{ 'subject' => 'faraday' }, { 'subject' => 'excon' },
-                                      { 'subject' => 'net/http' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Faraday' }, { 'subject' => 'Excon' },
+                                      { 'subject' => 'Net/http' }])
       expect(subject.date).to eq('created' => '2015-11-28',
                                  'published' => '2017-02-24',
                                  'updated' => '2017-02-24')
@@ -104,8 +104,8 @@ describe Commonmeta::Metadata, vcr: true do
                                           'type' => 'Person')
       expect(subject.titles).to eq([{ 'title' => 'DOI Registrations for Software' }])
       expect(subject.descriptions.first['description']).to start_with('Analysis of DataCite DOIs registered for software')
-      expect(subject.subjects).to eq([{ 'subject' => 'doi' }, { 'subject' => 'software' },
-                                      { 'subject' => 'codemeta' }])
+      expect(subject.subjects).to eq([{ 'subject' => 'Doi' }, { 'subject' => 'Software' },
+                                      { 'subject' => 'Codemeta' }])
       expect(subject.date).to eq('created' => '2018-03-09',
                                  'published' => '2018-05-17',
                                  'updated' => '2018-05-17')

data/spec/readers/json_feed_reader_spec.rb

@@ -22,7 +22,10 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.date).to eq('published' => '2023-05-31')
       expect(subject.descriptions.first['description']).to start_with("As trailed on a Twitter thread last week I’ve been working on a manuscript describing the efforts to map taxonomic names to their original descriptions in the taxonomic literature.")
       expect(subject.publisher).to eq('name' => 'iPhylo')
-      expect(subject.subjects).to be_nil
+      expect(subject.subjects).to eq([{"subject"=>"Natural sciences"},
+        {"schemeUri"=>"http://www.oecd.org/science/inno/38235147.pdf",
+         "subject"=>"FOS: Natural sciences",
+         "subjectScheme"=>"Fields of Science and Technology (FOS)"}])
       expect(subject.language).to eq('en')
       expect(subject.container).to eq("identifier"=>"https://iphylo.blogspot.com/", "identifierType"=>"URL", "title"=>"iPhylo", "type"=>"Periodical")
     end
@@ -43,7 +46,10 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.date).to eq('published' => '2023-05-16', 'updated' => '2023-05-16')
       expect(subject.descriptions.first['description']).to start_with("One question I have increasingly asked myself in the past few years. Meaning Can I run this open source software using Docker containers and a Docker Compose file?")
       expect(subject.publisher).to eq('name' => 'Front Matter')
-      expect(subject.subjects).to eq([{"subject"=>"news"}])
+      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('en')
       expect(subject.container).to eq("identifier"=>"https://blog.front-matter.io", "identifierType"=>"URL", "title"=>"Front Matter", "type"=>"Periodical")
     end
@@ -64,7 +70,10 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.date).to eq('published' => '2023-04-08')
       expect(subject.descriptions.first['description']).to start_with("A graphical, user-friendly tool for programs to highlight important data to prospective applicants")
       expect(subject.publisher).to eq('name' => 'I.D.E.A.S.')
-      expect(subject.subjects).to be_nil
+      expect(subject.subjects).to eq([{"subject"=>"Medical and health sciences"},
+        {"schemeUri"=>"http://www.oecd.org/science/inno/38235147.pdf",
+         "subject"=>"FOS: Medical and health sciences",
+         "subjectScheme"=>"Fields of Science and Technology (FOS)"}])
       expect(subject.language).to eq('en')
       expect(subject.container).to eq("identifier"=>"https://www.ideasurg.pub/", "identifierType"=>"URL", "title"=>"I.D.E.A.S.", "type"=>"Periodical")
     end
@@ -85,7 +94,10 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.date).to eq('published' => '2023-06-03')
       expect(subject.descriptions.first['description']).to start_with("A Data Exploration with Public Data from the Academic Surgical Congress")
       expect(subject.publisher).to eq('name' => 'I.D.E.A.S.')
-      expect(subject.subjects).to eq([{"subject"=>"pre-print"}])
+      expect(subject.subjects).to eq([{"subject"=>"Medical and health sciences"},
+        {"schemeUri"=>"http://www.oecd.org/science/inno/38235147.pdf",
+         "subject"=>"FOS: Medical and health sciences",
+         "subjectScheme"=>"Fields of Science and Technology (FOS)"}])
       expect(subject.language).to eq('en')
       expect(subject.container).to eq("identifier"=>"https://www.ideasurg.pub/", "identifierType"=>"URL", "title"=>"I.D.E.A.S.", "type"=>"Periodical")
       expect(subject.references).to be_nil
@@ -107,7 +119,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.date).to eq('published' => '2023-02-01', 'updated' => '2023-04-13')
       expect(subject.descriptions.first['description']).to start_with("Guinea worm disease reaches all-time low: only 13* human cases reported in 2022")
       expect(subject.publisher).to eq('name' => 'Syldavia Gazette')
-      expect(subject.subjects).to be_nil
+      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.container).to eq("identifier"=>"https://syldavia-gazette.org", "identifierType"=>"URL", "title"=>"Syldavia Gazette", "type"=>"Periodical")
       expect(subject.references.length).to eq(5)
@@ -130,7 +142,10 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.date).to eq('published' => '2023-05-23', 'updated' => '2023-05-23')
       expect(subject.descriptions.first['description']).to start_with("Die EU-Wissenschaftsministerien haben sich auf ihrer heutigen Sitzung in Brüssel unter dem Titel “Council conclusions on high-quality, transparent, open, trustworthy and equitable scholarly publishing”")
       expect(subject.publisher).to eq('name' => 'wisspub.net')
-      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.container).to eq("identifier"=>"https://wisspub.net", "identifierType"=>"URL", "title"=>"wisspub.net", "type"=>"Periodical")
     end
@@ -150,7 +165,10 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.date).to eq('published' => '2023-06-09', 'updated' => '2023-06-09')
       expect(subject.descriptions.first['description']).to start_with("Haplocanthosaurus tibiae and dorsal vertebrae.")
       expect(subject.publisher).to eq('name' => 'Sauropod Vertebra Picture of the Week')
-      expect(subject.subjects).to eq([{"subject"=>"#mte14"}, {"subject"=>"barosaurus"}, {"subject"=>"cervical"}, {"subject"=>"conferences"}, {"subject"=>"diplodocids"}])
+      expect(subject.subjects).to eq([{"subject"=>"Natural sciences"},
+        {"schemeUri"=>"http://www.oecd.org/science/inno/38235147.pdf",
+         "subject"=>"FOS: Natural sciences",
+         "subjectScheme"=>"Fields of Science and Technology (FOS)"}])
       expect(subject.language).to eq('en')
       expect(subject.container).to eq("identifier"=>"https://svpow.com", "identifierType"=>"URL", "title"=>"Sauropod Vertebra Picture of the Week", "type"=>"Periodical")
       expect(subject.references.length).to eq(3)
@@ -173,7 +191,10 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.date).to eq('published' => '2023-04-18', 'updated' => '2023-04-18')
       expect(subject.descriptions.first['description']).to start_with("Research software is a key part of most research today. As University of Manchester Professor Carole Goble has said, \"software is the ubiquitous instrument of science.\"")
       expect(subject.publisher).to eq('name' => 'Upstream')
-      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.container).to eq("identifier"=>"https://upstream.force11.org", "identifierType"=>"URL", "title"=>"Upstream", "type"=>"Periodical")
       expect(subject.references.length).to eq(11)
@@ -196,7 +217,10 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.date).to eq('published' => '2020-07-11', 'updated' => '2020-07-11')
       expect(subject.descriptions.first['description']).to start_with("Over the past few months, Citation Style Language developers have worked to address a backlog of feature requests. This work will be reflected in two upcoming releases.")
       expect(subject.publisher).to eq('name' => 'Citation Style Language')
-      expect(subject.subjects).to be_nil
+      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('en')
       expect(subject.container).to eq("identifier"=>"https://citationstyles.org/", "identifierType"=>"URL", "title"=>"Citation Style Language", "type"=>"Periodical")
     end
@@ -208,10 +232,14 @@ describe Commonmeta::Metadata, vcr: true do
       expect(response).to eq("ca2a7df4-f3b9-487c-82e9-27f54de75ea8")
     end
 
+    it 'not indexed posts' do
+      response = subject.get_json_feed_not_indexed('2023-01-01')
+      expect(response).to eq("ab58e412-06eb-42b7-b81a-d340825b9d48")
+    end
+
     it 'by blog_id' do
-      response = subject.get_json_feed_by_blog('tyfqw20').split('\n')
-      expect(response.length).to eq(25)
-      expect(response.first).to eq("3e1278f6-e7c0-43e1-bb54-6829e1344c0d")
+      response = subject.get_json_feed_by_blog('tyfqw20')
+      expect(response).to eq("3e1278f6-e7c0-43e1-bb54-6829e1344c0d")
     end
   end
 end

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