commonmeta-ruby 3.0.0

data/spec/writers/jats_writer_spec.rb

@@ -0,0 +1,210 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe Commonmeta::Metadata, vcr: true do
+  context 'write metadata as jats xml' do
+    it 'with data citation' do
+      input = '10.7554/eLife.01567'
+      subject = described_class.new(input: input, from: 'crossref')
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to eq('journal')
+      expect(jats['article_title']).to eq('Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth')
+      expect(jats['source']).to eq('eLife')
+      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['year']).to eq('iso_8601_date' => '2014-02-11', '__content__' => '2014')
+      expect(jats['month']).to eq('02')
+      expect(jats['day']).to eq('11')
+    end
+
+    it 'with ORCID ID' do
+      input = 'https://doi.org/10.1155/2012/291294'
+      subject = described_class.new(input: input, from: 'crossref')
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to eq('journal')
+      expect(jats['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['source']).to eq('Pulmonary Medicine')
+      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['year']).to eq('iso_8601_date' => '2012', '__content__' => '2012')
+    end
+
+    it 'with editor' do
+      input = 'https://doi.org/10.1371/journal.pone.0000030'
+      subject = described_class.new(input: input, from: 'crossref')
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to eq('journal')
+      expect(jats['article_title']).to eq('Triose Phosphate Isomerase Deficiency Is Caused by Altered Dimerization–Not Catalytic Inactivity–of the Mutant Enzymes')
+      expect(jats['source']).to eq('PLoS ONE')
+      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')
+      expect(jats['year']).to eq('iso_8601_date' => '2006-12-20', '__content__' => '2006')
+      expect(jats['month']).to eq('12')
+      expect(jats['day']).to eq('20')
+      expect(jats['fpage']).to eq('e30')
+      expect(jats['pub_id']).to eq('pub_id_type' => 'doi',
+                                   '__content__' => '10.1371/journal.pone.0000030')
+    end
+
+    it 'book chapter' do
+      input = 'https://doi.org/10.5005/jp/books/12414_3'
+      subject = described_class.new(input: input, from: 'crossref')
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to eq('chapter')
+      expect(jats['chapter_title']).to eq('Physical Examinations')
+      expect(jats['source']).to eq('Jaypee Brothers Medical Publishing')
+      expect(jats.dig('person_group', 'name')).to eq('surname' => 'Saha', 'given_names' => 'Ashis')
+      expect(jats['year']).to eq('iso_8601_date' => '2015', '__content__' => '2015')
+      expect(jats['fpage']).to eq('27')
+      expect(jats['lpage']).to eq('27')
+      expect(jats['pub_id']).to eq('pub_id_type' => 'doi',
+                                   '__content__' => '10.5005/jp/books/12414_3')
+    end
+
+    it 'Crossref DOI' do
+      input = "#{fixture_path}crossref.bib"
+      subject = described_class.new(input: input, from: 'bibtex')
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to eq('journal')
+      expect(jats['article_title']).to eq('Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth')
+      expect(jats['source']).to eq('eLife')
+      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['year']).to eq('iso_8601_date' => '2014', '__content__' => '2014')
+      expect(jats['month'].nil?).to be(true)
+      expect(jats['pub_id']).to eq('pub_id_type' => 'doi', '__content__' => '10.7554/elife.01567')
+    end
+
+    it 'BlogPosting Citeproc JSON' do
+      input = "#{fixture_path}citeproc.json"
+      subject = described_class.new(input: input, from: 'csl')
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to eq('journal')
+      expect(jats['source']).to eq('DataCite Blog')
+      expect(jats['publisher_name']).to eq('DataCite')
+      expect(jats.dig('person_group',
+                      'name')).to eq('surname' => 'Fenner', 'given_names' => 'Martin')
+      expect(jats['year']).to eq('iso_8601_date' => '2016-12-20', '__content__' => '2016')
+      expect(jats['month']).to eq('12')
+      expect(jats['day']).to eq('20')
+      expect(jats['pub_id']).to eq('pub_id_type' => 'doi', '__content__' => '10.5438/4k3m-nyvg')
+    end
+
+    it 'rdataone' do
+      input = "#{fixture_path}codemeta.json"
+      subject = described_class.new(input: input, from: 'codemeta')
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to eq('software')
+      expect(jats['source']).to eq('R Interface to the DataONE REST API')
+      expect(jats['publisher_name']).to eq('https://cran.r-project.org')
+      expect(jats.dig('person_group', 'name').length).to eq(3)
+      expect(jats.dig('person_group',
+                      'name').first).to eq('surname' => 'Jones', 'given_names' => 'Matt')
+      expect(jats['year']).to eq('iso_8601_date' => '2016-05-27', '__content__' => '2016')
+      expect(jats['month']).to eq('05')
+      expect(jats['day']).to eq('27')
+      expect(jats['version']).to eq('2.0.0')
+      expect(jats['pub_id']).to eq('pub_id_type' => 'doi', '__content__' => '10.5063/f1m61h5x')
+    end
+
+    it 'maremma' do
+      input = 'https://github.com/datacite/maremma'
+      subject = described_class.new(input: input, from: 'codemeta')
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to eq('software')
+      expect(jats['source']).to eq('Maremma: a Ruby library for simplified network calls')
+      expect(jats['publisher_name']).to eq('DataCite')
+      expect(jats.dig('person_group',
+                      'name')).to eq('surname' => 'Fenner', 'given_names' => 'Martin')
+      expect(jats['year']).to eq('iso_8601_date' => '2017-02-24', '__content__' => '2017')
+      expect(jats['month']).to eq('02')
+      expect(jats['day']).to eq('24')
+      expect(jats['pub_id']).to eq('pub_id_type' => 'doi', '__content__' => '10.5438/qeg0-3gm3')
+    end
+
+    it 'Text pass-thru' do
+      input = 'https://doi.org/10.23640/07243.5153971'
+      subject = described_class.new(input: input, from: 'datacite')
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to eq('journal')
+      expect(jats['article_title']).to eq('Recommendation of: ORCID Works Metadata Working Group')
+      expect(jats['source']).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['year']).to eq('iso_8601_date' => '2017', '__content__' => '2017')
+      expect(jats['pub_id']).to eq('pub_id_type' => 'doi',
+                                   '__content__' => '10.23640/07243.5153971')
+    end
+
+    it 'Dataset in schema 4.0' do
+      input = 'https://doi.org/10.5061/DRYAD.8515'
+      subject = described_class.new(input: input, from: 'datacite', regenerate: true)
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to eq('data')
+      expect(jats['data_title']).to eq('Data from: A new malaria agent in African hominids.')
+      expect(jats['source']).to eq('Dryad')
+      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['year']).to eq('iso_8601_date' => '2011', '__content__' => '2011')
+      expect(jats['pub_id']).to eq('pub_id_type' => 'doi', '__content__' => '10.5061/dryad.8515')
+    end
+
+    it 'from schema_org' do
+      input = 'https://blog.front-matter.io/posts/eating-your-own-dog-food/'
+      subject = described_class.new(input: input, from: 'schema_org')
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to eq('journal')
+      expect(jats['article_title']).to eq('Eating your own Dog Food')
+      expect(jats['source']).to eq('Front Matter')
+      expect(jats['publisher_name']).to eq('Front Matter')
+      expect(jats.dig('person_group',
+                      'name')).to eq('surname' => 'Fenner', 'given_names' => 'Martin')
+      expect(jats['year']).to eq('iso_8601_date' => '2016-12-20T00:00:00Z', '__content__' => '2016')
+      expect(jats['month']).to eq('12')
+      expect(jats['day']).to eq('20')
+      expect(jats['pub_id']).to eq('pub_id_type' => 'doi',
+                                   '__content__' => '10.53731/r79vxn1-97aq74v-ag58n')
+    end
+
+    it 'interactive resource without dates' do
+      input = 'https://doi.org/10.34747/g6yb-3412'
+      subject = described_class.new(input: input, from: 'datacite')
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to be_blank
+      expect(jats['source']).to eq('Exploring the "Many analysts, one dataset" project from COS')
+      expect(jats['publisher_name']).to eq('Gigantum, Inc.')
+      expect(jats.dig('person_group', 'name')).to eq('given_names' => 'Dav', 'surname' => 'Clark')
+      expect(jats['year']).to eq('__content__' => '2019', 'iso_8601_date' => '2019')
+      expect(jats['month'].nil?).to be(true)
+      expect(jats['day'].nil?).to be(true)
+      expect(jats['pub_id']).to eq('pub_id_type' => 'doi', '__content__' => '10.34747/g6yb-3412')
+    end
+  end
+
+  context 'change metadata as datacite xml' do
+    it 'with data citation' do
+      input = '10.7554/eLife.01567'
+      subject = described_class.new(input: input, from: 'crossref')
+      jats = Hash.from_xml(subject.jats).fetch('element_citation', {})
+      expect(jats['publication_type']).to eq('journal')
+      expect(jats['article_title']).to eq('Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth')
+      expect(jats['source']).to eq('eLife')
+      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['year']).to eq('iso_8601_date' => '2014-02-11', '__content__' => '2014')
+      expect(jats['month']).to eq('02')
+      expect(jats['day']).to eq('11')
+      expect(jats['pub_id']).to eq('pub_id_type' => 'doi', '__content__' => '10.7554/elife.01567')
+    end
+  end
+end

data/spec/writers/rdf_xml_writer_spec.rb

@@ -0,0 +1,91 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe Commonmeta::Metadata, vcr: true do
+  context 'write metadata as rdf xml' do
+    # it 'journal article' do
+    #   input = '10.7554/eLife.01567'
+    #   subject = described_class.new(input: input, from: 'crossref')
+    #   expect(subject.valid?).to be true
+    #   rdf_xml = Hash.from_xml(subject.rdf_xml).fetch('RDF', {})
+    #   expect(rdf_xml.dig('ScholarlyArticle', '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')
+    # end
+
+    # it 'with pages' do
+    #   input = 'https://doi.org/10.1155/2012/291294'
+    #   subject = described_class.new(input: input, from: 'crossref')
+    #   expect(subject.valid?).to be true
+    #   rdf_xml = Hash.from_xml(subject.rdf_xml).fetch('RDF', {})
+    #   expect(rdf_xml.dig('ScholarlyArticle', 'about')).to eq('https://doi.org/10.1155/2012/291294')
+    #   expect(rdf_xml.dig('ScholarlyArticle',
+    #                      'name')).to eq('Delineating a Retesting Zone Using Receiver Operating Characteristic Analysis on Serial QuantiFERON Tuberculosis Test Results in US Healthcare Workers')
+    #   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')
+    # end
+
+    # it 'Crossref DOI' do
+    #   input = "#{fixture_path}crossref.bib"
+    #   subject = described_class.new(input: input, from: 'bibtex')
+    #   expect(subject.valid?).to be true
+    #   rdf_xml = Hash.from_xml(subject.rdf_xml).fetch('RDF', {})
+
+    #   expect(rdf_xml.dig('ScholarlyArticle', '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')
+    #   expect(rdf_xml.dig('ScholarlyArticle', 'periodical', 'Journal', 'name')).to eq('eLife')
+    # end
+
+    # it 'BlogPosting' do
+    #   input = 'https://doi.org/10.5438/4K3M-NYVG'
+    #   subject = described_class.new(input: input, from: 'datacite')
+    #   expect(subject.valid?).to be true
+    #   rdf_xml = Hash.from_xml(subject.rdf_xml).fetch('RDF', {})
+    #   expect(rdf_xml.dig('ScholarlyArticle', 'about')).to eq('https://doi.org/10.5438/4k3m-nyvg')
+    #   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')
+    #   expect(rdf_xml.dig('ScholarlyArticle', 'datePublished', '__content__')).to eq('2016-12-20')
+    # end
+
+    # it 'BlogPosting Citeproc JSON' do
+    #   input = "#{fixture_path}citeproc.json"
+    #   subject = described_class.new(input: input, from: 'csl')
+    #   rdf_xml = Hash.from_xml(subject.rdf_xml).fetch('RDF', {})
+    #   expect(rdf_xml.dig('BlogPosting', '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')
+    # end
+
+    # it 'maremma' do
+    #   input = 'https://github.com/datacite/maremma'
+    #   subject = described_class.new(input: input, from: 'codemeta')
+    #   rdf_xml = Hash.from_xml(subject.rdf_xml).fetch('RDF', {})
+    #   expect(rdf_xml.dig('SoftwareSourceCode', 'about')).to eq('https://doi.org/10.5438/qeg0-3gm3')
+    #   expect(rdf_xml.dig('SoftwareSourceCode', 'author', 'Person', 'about')).to eq('https://orcid.org/0000-0003-0077-4738')
+    #   expect(rdf_xml.dig('SoftwareSourceCode', 'author', 'Person', 'name')).to eq('Martin Fenner')
+    #   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')
+    # end
+
+    # it 'BlogPosting schema.org' do
+    #   input = 'https://blog.front-matter.io/posts/eating-your-own-dog-food/'
+    #   subject = described_class.new(input: input, from: 'schema_org')
+    #   expect(subject.valid?).to be true
+    #   rdf_xml = Hash.from_xml(subject.rdf_xml).fetch('RDF', {})
+    #   expect(rdf_xml.dig('Article', 'about')).to eq('https://doi.org/10.53731/r79vxn1-97aq74v-ag58n')
+    #   expect(rdf_xml.dig('Article', 'author', 'Person', 'about')).to eq('https://orcid.org/0000-0003-1419-2405')
+    #   expect(rdf_xml.dig('Article', 'author', 'Person', 'name')).to eq('Martin Fenner')
+    #   expect(rdf_xml.dig('Article', 'name')).to eq('Eating your own Dog Food')
+    #   expect(rdf_xml.dig('Article', 'keywords')).to eq('feature')
+    #   expect(rdf_xml.dig('Article', 'datePublished', '__content__')).to eq('2016-12-20T00:00:00Z')
+    # end
+  end
+end

data/spec/writers/ris_writer_spec.rb

@@ -0,0 +1,206 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe Commonmeta::Metadata, vcr: true do
+  context 'write metadata as ris' do
+    it 'journal article' do
+      input = '10.7554/eLife.01567'
+      subject = described_class.new(input: input, from: 'crossref_xml')
+      ris = subject.ris.split("\r\n")
+      expect(ris[0]).to eq('TY  - JOUR')
+      expect(ris[1]).to eq('T1  - Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth')
+      expect(ris[2]).to eq('T2  - eLife')
+      expect(ris[3]).to eq('AU  - Sankar, Martial')
+      expect(ris[8]).to eq('DO  - 10.7554/elife.01567')
+      expect(ris[9]).to eq('UR  - https://elifesciences.org/articles/01567')
+      expect(ris[10]).to start_with('AB  - Among various advantages')
+      expect(ris[11]).to eq('PY  - 2014')
+      expect(ris[12]).to eq('PB  - eLife Sciences Publications, Ltd')
+      expect(ris[13]).to eq('VL  - 3')
+      expect(ris[14]).to eq('SP  - e01567')
+      expect(ris[15]).to eq('SN  - 2050-084X')
+      expect(ris[16]).to eq('ER  - ')
+    end
+
+    it 'with pages' do
+      input = 'https://doi.org/10.1155/2012/291294'
+      subject = described_class.new(input: input, from: 'crossref_xml')
+      # expect(subject.valid?).to be true
+      ris = subject.ris.split("\r\n")
+      expect(ris[0]).to eq('TY  - JOUR')
+      expect(ris[1]).to eq('T1  - Delineating a Retesting Zone Using Receiver Operating Characteristic Analysis on Serial QuantiFERON Tuberculosis Test Results in US Healthcare Workers')
+      expect(ris[2]).to eq('T2  - Pulmonary Medicine')
+      expect(ris[3]).to eq('AU  - Thanassi, Wendy')
+      expect(ris[10]).to eq('DO  - 10.1155/2012/291294')
+      expect(ris[11]).to eq('UR  - http://www.hindawi.com/journals/pm/2012/291294')
+      expect(ris[12]).to start_with('AB  - . To find a statistically significant separation point for the QuantiFERON')
+      expect(ris[13]).to eq('PY  - 2012')
+      expect(ris[14]).to eq('PB  - Hindawi Limited')
+      expect(ris[15]).to eq('VL  - 2012')
+      expect(ris[16]).to eq('SP  - 1')
+      expect(ris[17]).to eq('EP  - 7')
+      expect(ris[18]).to eq('SN  - 2090-1844')
+      expect(ris[19]).to eq('ER  - ')
+    end
+
+    it 'alternate name' do
+      input = 'https://doi.org/10.3205/ZMA001102'
+      subject = described_class.new(input: input, from: 'datacite')
+      # expect(subject.valid?).to be true
+      ris = subject.ris.split("\r\n")
+      expect(ris[0]).to eq('TY  - GEN')
+      expect(ris[1]).to eq('T1  - Visions and reality: the idea of competence-oriented assessment for German medical students is not yet realised in licensing examinations')
+      expect(ris[2]).to eq('T2  - GMS Journal for Medical Education; 34(2):Doc25')
+      expect(ris[3]).to eq('AU  - Huber-Lang, Markus')
+      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[22]).to eq('PY  - 2017')
+      expect(ris[23]).to eq('PB  - German Medical Science GMS Publishing House')
+      expect(ris[24]).to eq('LA  - en')
+      expect(ris[25]).to eq('SN  - 2366-5017')
+      expect(ris[26]).to eq('ER  - ')
+    end
+
+    it 'Crossref DOI' do
+      input = "#{fixture_path}crossref.bib"
+      subject = described_class.new(input: input, from: 'bibtex')
+
+      ris = subject.ris.split("\r\n")
+      expect(ris[0]).to eq('TY  - JOUR')
+      expect(ris[1]).to eq('T1  - Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth')
+      expect(ris[2]).to eq('T2  - eLife')
+      expect(ris[3]).to eq('AU  - Sankar, Martial')
+      expect(ris[8]).to eq('DO  - 10.7554/elife.01567')
+      expect(ris[9]).to eq('UR  - http://elifesciences.org/lookup/doi/10.7554/eLife.01567')
+      expect(ris[10]).to eq('AB  - Among various advantages, their small size makes model organisms preferred subjects of investigation. Yet, even in model systems detailed analysis of numerous developmental processes at cellular level is severely hampered by their scale.')
+      expect(ris[11]).to eq('PY  - 2014')
+      expect(ris[12]).to eq('PB  - {eLife} Sciences Organisation, Ltd.')
+      expect(ris[13]).to eq('VL  - 3')
+      expect(ris[14]).to eq('SN  - 2050-084X')
+      expect(ris[15]).to eq('ER  - ')
+    end
+
+    it 'BlogPosting' do
+      input = 'https://doi.org/10.5438/4K3M-NYVG'
+      subject = described_class.new(input: input, from: 'datacite')
+      expect(subject.valid?).to be true
+      ris = subject.ris.split("\r\n")
+      expect(ris[0]).to eq('TY  - JOUR')
+      expect(ris[1]).to eq('T1  - Eating your own Dog Food')
+      expect(ris[2]).to eq('AU  - Fenner, Martin')
+      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[10]).to eq('PY  - 2016')
+      expect(ris[11]).to eq('PB  - DataCite')
+      expect(ris[12]).to eq('LA  - en')
+      expect(ris[13]).to eq('SN  - 10.5438/0000-00ss')
+      expect(ris[14]).to eq('ER  - ')
+    end
+
+    it 'BlogPosting Citeproc JSON' do
+      input = "#{fixture_path}citeproc.json"
+      subject = described_class.new(input: input, from: 'csl')
+      ris = subject.ris.split("\r\n")
+      expect(ris[0]).to eq('TY  - JOUR')
+      expect(ris[1]).to eq('T1  - Eating your own Dog Food')
+      expect(ris[2]).to eq('T2  - DataCite Blog')
+      expect(ris[3]).to eq('AU  - Fenner, Martin')
+      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[14]).to eq('PY  - 2016')
+      expect(ris[15]).to eq('PB  - DataCite')
+      expect(ris[16]).to eq('ER  - ')
+    end
+
+    it 'BlogPosting DataCite JSON' do
+      input = "#{fixture_path}datacite.json"
+      subject = described_class.new(input: input, from: 'datacite')
+      ris = subject.ris.split("\r\n")
+      expect(ris[0]).to eq('TY  - JOUR')
+      expect(ris[1]).to eq('T1  - Eating your own Dog Food')
+      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[8]).to eq('PY  - 2016')
+      expect(ris[9]).to eq('PB  - DataCite')
+      expect(ris[10]).to eq('ER  - ')
+    end
+
+    it 'BlogPosting schema.org' do
+      input = 'https://blog.front-matter.io/posts/eating-your-own-dog-food/'
+      subject = described_class.new(input: input, from: 'schema_org')
+      ris = subject.ris.split("\r\n")
+      expect(ris[0]).to eq('TY  - JOUR')
+      expect(ris[1]).to eq('T1  - Eating your own Dog Food')
+      expect(ris[2]).to eq('T2  - Front Matter')
+      expect(ris[3]).to eq('AU  - Fenner, Martin')
+      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[8]).to eq('PY  - 2016')
+      expect(ris[9]).to eq('PB  - Front Matter')
+      expect(ris[10]).to eq('LA  - en')
+      expect(ris[11]).to eq('SN  - 2749-9952')
+      expect(ris[12]).to eq('ER  - ')
+    end
+
+    it 'Dataset' do
+      input = '10.5061/DRYAD.8515'
+      subject = described_class.new(input: input, from: 'datacite')
+      expect(subject.valid?).to be true
+      ris = subject.ris.split("\r\n")
+      expect(ris[0]).to eq('TY  - DATA')
+      expect(ris[1]).to eq('T1  - Data from: A new malaria agent in African hominids.')
+      expect(ris[2]).to eq('AU  - Ollomo, Benjamin')
+      expect(ris[10]).to eq('DO  - 10.5061/dryad.8515')
+      expect(ris[11]).to eq('UR  - http://datadryad.org/stash/dataset/doi:10.5061/dryad.8515')
+      expect(ris[13]).to eq('KW  - Plasmodium')
+      expect(ris[18]).to eq('PB  - Dryad')
+      expect(ris[19]).to eq('LA  - en')
+      expect(ris[20]).to eq('ER  - ')
+    end
+
+    it 'maremma' do
+      input = 'https://github.com/datacite/maremma'
+      subject = described_class.new(input: input, from: 'codemeta')
+      ris = subject.ris.split("\r\n")
+      expect(ris[0]).to eq('TY  - COMP')
+      expect(ris[1]).to eq('T1  - Maremma: a Ruby library for simplified network calls')
+      expect(ris[2]).to eq('AU  - Fenner, Martin')
+      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[9]).to eq('PY  - 2017')
+      expect(ris[10]).to eq('PB  - DataCite')
+      expect(ris[11]).to eq('ER  - ')
+    end
+
+    it 'keywords with subject scheme' do
+      input = 'https://doi.org/10.1594/pangaea.721193'
+      subject = described_class.new(input: input, from: 'datacite')
+      ris = subject.ris.split("\r\n")
+      expect(ris[0]).to eq('TY  - DATA')
+      expect(ris[1]).to eq('T1  - Seawater carbonate chemistry and processes during experiments with Crassostrea gigas, 2007')
+      expect(ris[2]).to eq('AU  - Kurihara, Haruko')
+      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[51]).to eq('PY  - 2007')
+      expect(ris[52]).to eq('PB  - PANGAEA')
+      expect(ris[53]).to eq('LA  - en')
+      expect(ris[54]).to eq('ER  - ')
+    end
+  end
+end