commonmeta-ruby 3.0.0

data/spec/cli_spec.rb

@@ -0,0 +1,309 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+require 'commonmeta/cli'
+
+describe Commonmeta::CLI do
+  let(:subject) do
+    described_class.new
+  end
+
+  describe "convert from id", vcr: true do
+    SCHEMA_ORG_REGEX = /"@context": "http:\/\/schema.org"/
+    CROSSREF_XML_REGEX = /<doi_batch/
+    DATACITE_REGEX = /"types": {/
+    BIBTEX_REGEX = /@article{https:\/\/doi.org\/10.7554\/elife.01567/
+    BIBTEX_DATA_REGEX = /@misc{https:\/\/doi.org\/10.5061\/dryad.8515/
+    RIS_REGEX = /TY  - JOUR/
+    CSL_REGEX = 'type: "article-journal'
+    CITATION_REGEX = /Sankar M, Nieminen K, Ragni L, Xenarios I/
+    CITATION_DATA_REGEX = /Ollomo B, Durand P, Prugnolle F/
+    JATS_REGEX = /article-title/
+
+    context "crossref" do
+      let(:input) { "10.7554/eLife.01567" }
+
+      it 'default' do
+        expect { subject.convert input }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to schema_org' do
+        subject.options = { from: "crossref", to: "schema_org" }
+        expect { subject.convert input }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to crossref_xml' do
+        subject.options = { from: "crossref", to: "crossref_xml" }
+        expect { subject.convert input }.to output(CROSSREF_XML_REGEX).to_stdout
+      end
+
+      it 'to datacite' do
+        subject.options = { from: "crossref", to: "datacite" }
+        expect { subject.convert input }.to output(DATACITE_REGEX).to_stdout
+      end
+
+      it 'to bibtex' do
+        subject.options = { from: "crossref", to: "bibtex" }
+        expect { subject.convert input }.to output(BIBTEX_REGEX).to_stdout
+      end
+
+      it 'to citation' do
+        subject.options = { from: "crossref", to: "citation", style: "vancouver" }
+        expect { subject.convert input }.to output(CITATION_REGEX).to_stdout
+      end
+    end
+
+    context "crossref" do
+      let(:input) { "10.7554/eLife.01567" }
+
+      it 'default' do
+        expect { subject.convert input }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to schema_org' do
+        subject.options = { to: "schema_org" }
+        expect { subject.convert input }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to crossref_xml' do
+        subject.options = { to: "crossref_xml" }
+        expect { subject.convert input }.to output(CROSSREF_XML_REGEX).to_stdout
+      end
+
+      it 'to datacite' do
+        subject.options = { to: "datacite" }
+        expect { subject.convert input }.to output(DATACITE_REGEX).to_stdout
+      end
+
+      it 'to bibtex' do
+        subject.options = { to: "bibtex" }
+        expect { subject.convert input }.to output(BIBTEX_REGEX).to_stdout
+      end
+
+      it 'to citation' do
+        subject.options = { to: "citation", style: "vancouver" }
+        expect { subject.convert input }.to output(CITATION_REGEX).to_stdout
+      end
+
+      it 'to jats' do
+        subject.options = { to: "jats" }
+        expect { subject.convert input }.to output(JATS_REGEX).to_stdout
+      end
+    end
+
+    context "datacite" do
+      let(:input) { "10.5061/dryad.8515" }
+
+      it 'default' do
+        expect { subject.convert input }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to schema_org' do
+        subject.options = { to: "schema_org" }
+        expect { subject.convert input }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to bibtex' do
+        subject.options = { to: "bibtex" }
+        expect { subject.convert input }.to output(BIBTEX_DATA_REGEX).to_stdout
+      end
+
+      it 'to datacite' do
+        subject.options = { to: "datacite" }
+        expect { subject.convert input }.to output(DATACITE_REGEX).to_stdout
+      end
+
+      it 'to citation' do
+        subject.options = { to: "citation", style: "vancouver" }
+        expect { subject.convert input }.to output(CITATION_DATA_REGEX).to_stdout
+      end
+
+      it 'to jats' do
+        subject.options = { to: "jats" }
+        expect { subject.convert input }.to output(/data-title/).to_stdout
+      end
+    end
+
+    context "schema_org" do
+      let(:id) { "https://blog.datacite.org/eating-your-own-dog-food" }
+
+      it 'default' do
+        expect { subject.convert id }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to schema_org' do
+        subject.options = { to: "schema_org" }
+        expect { subject.convert id }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to datacite' do
+        subject.options = { to: "datacite" }
+        expect { subject.convert id }.to output(DATACITE_REGEX).to_stdout
+      end
+
+      # TODO
+      # it 'to bibtex' do
+      #   subject.options = { to: "bibtex" }
+      #   expect { subject.convert id }.to output(/@article{https:\/\/doi.org\/10.5438\/4k3m-nyvg/).to_stdout
+      # end
+    end
+  end
+
+  describe "convert file" do
+    context "bibtex" do
+      let(:file) { fixture_path + "crossref.bib" }
+
+      it 'default' do
+        expect { subject.convert file }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to schema_org' do
+        subject.options = { to: "schema_org" }
+        expect { subject.convert file }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to datacite' do
+        subject.options = { to: "datacite" }
+        expect { subject.convert file }.to output(DATACITE_REGEX).to_stdout
+      end
+    end
+
+    context "crossref_xml", vcr: true do
+      let(:file) { fixture_path + "crossref.xml" }
+
+      it 'default' do
+        expect { subject.convert file }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to schema_org' do
+        subject.options = { to: "schema_org" }
+        expect { subject.convert file }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to crossref_xml' do
+        subject.options = { to: "crossref_xml" }
+        expect { subject.convert file }.to output(CROSSREF_XML_REGEX).to_stdout
+      end
+
+      it 'to datacite' do
+        subject.options = { to: "datacite" }
+        expect { subject.convert file }.to output(DATACITE_REGEX).to_stdout
+      end
+
+      it 'to bibtex' do
+        subject.options = { to: "bibtex" }
+        expect { subject.convert file }.to output(BIBTEX_REGEX).to_stdout
+      end
+    end
+
+    context "crossref", vcr: true do
+      let(:file) { fixture_path + "crossref.json" }
+
+      it 'default' do
+        expect { subject.convert file }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to schema_org' do
+        subject.options = { to: "schema_org" }
+        expect { subject.convert file }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to crossref_xml' do
+        subject.options = { to: "crossref_xml" }
+        expect { subject.convert file }.to output(CROSSREF_XML_REGEX).to_stdout
+      end
+
+      it 'to datacite' do
+        subject.options = { to: "datacite" }
+        expect { subject.convert file }.to output(DATACITE_REGEX).to_stdout
+      end
+
+      it 'to bibtex' do
+        subject.options = { to: "bibtex" }
+        expect { subject.convert file }.to output(BIBTEX_REGEX).to_stdout
+      end
+    end
+
+    context "datacite", vcr: true do
+      let(:file) { fixture_path + "datacite.json" }
+
+      it 'default' do
+        expect { subject.convert file }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to schema_org' do
+        subject.options = { to: "schema_org" }
+        expect { subject.convert file }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to datacite' do
+        subject.options = { to: "datacite" }
+        expect { subject.convert file }.to output(DATACITE_REGEX).to_stdout
+      end
+
+      it 'to bibtex' do
+        subject.options = { to: "bibtex" }
+        expect { subject.convert file }.to output(/@article{https:\/\/doi.org\/10.5438\/4k3m-nyvg/).to_stdout
+      end
+
+      it 'to datacite invalid' do
+        file = fixture_path + "datacite_missing_creator.xml"
+        subject.options = { to: "datacite", show_errors: "true" }
+        expect { subject.convert file }.to output(/root is missing required keys: id, type, url, creators, titles, publisher, date/).to_stderr
+      end
+
+      it 'to datacite invalid ignore errors' do
+        file = fixture_path + "datacite_missing_creator.xml"
+        subject.options = { to: "datacite" }
+        expect { subject.convert file }.to output(DATACITE_REGEX).to_stdout
+      end
+    end
+
+    context "codemeta" do
+      let(:file) { fixture_path + "codemeta.json" }
+
+      it 'default' do
+        expect { subject.convert file }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to schema_org' do
+        subject.options = { to: "schema_org" }
+        expect { subject.convert file }.to output(SCHEMA_ORG_REGEX).to_stdout
+      end
+
+      it 'to datacite' do
+        subject.options = { to: "datacite" }
+        expect { subject.convert file }.to output(DATACITE_REGEX).to_stdout
+      end
+
+      it 'to bibtex' do
+        subject.options = { to: "bibtex" }
+        expect { subject.convert file }.to output(/@misc{https:\/\/doi.org\/10.5063\/f1m61h5x/).to_stdout
+      end
+    end
+
+    # context "unsupported format" do
+    #   let(:file) { fixture_path + "crossref.xxx" }
+    #
+    #   it 'error' do
+    #     expect { subject.convert file }.to output(/datePublished/).to_stderr
+    #   end
+    # end
+  end
+
+  describe "encode" do
+    let(:input) { "10.53731" }
+
+    it "blog prefix" do
+      expect { subject.encode input }.to output(/https:\/\/doi.org\/10.53731/).to_stdout
+    end
+  end
+
+  describe "decode" do
+    let(:input) { "10.53731/cjx855h-hn5jtq8" }
+
+    it "blog post" do
+      expect { subject.decode input }.to output(/464528469187255429864\n/).to_stdout
+    end
+  end
+end

data/spec/doi_utils_spec.rb

@@ -0,0 +1,318 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe Commonmeta::Metadata, vcr: true do
+  let(:subject) do
+    described_class.new
+  end
+
+  context 'doi resolver' do
+    it 'doi' do
+      doi = '10.5061/DRYAD.8515'
+      response = subject.doi_resolver(doi)
+      expect(response).to eq('https://doi.org/')
+    end
+
+    it 'doi with protocol' do
+      doi = 'doi:10.5061/DRYAD.8515'
+      response = subject.doi_resolver(doi)
+      expect(response).to eq('https://doi.org/')
+    end
+
+    it 'https url' do
+      doi = 'https://doi.org/10.5061/dryad.8515'
+      response = subject.doi_resolver(doi)
+      expect(response).to eq('https://doi.org/')
+    end
+
+    it 'dx.doi.org url' do
+      doi = 'http://dx.doi.org/10.5061/dryad.8515'
+      response = subject.doi_resolver(doi)
+      expect(response).to eq('https://doi.org/')
+    end
+
+    it 'stage resolver' do
+      doi = 'https://handle.stage.datacite.org/10.5061/dryad.8515'
+      response = subject.doi_resolver(doi)
+      expect(response).to eq('https://handle.stage.datacite.org/')
+    end
+
+    it 'stage resolver http' do
+      doi = 'http://handle.stage.datacite.org/10.5061/dryad.8515'
+      response = subject.doi_resolver(doi)
+      expect(response).to eq('https://handle.stage.datacite.org/')
+    end
+
+    it 'force stage resolver' do
+      doi = 'https://doi.org/10.5061/dryad.8515'
+      response = subject.doi_resolver(doi, sandbox: true)
+      expect(response).to eq('https://handle.stage.datacite.org/')
+    end
+  end
+
+  context 'datacite_api_url' do
+    it 'doi' do
+      doi = '10.5061/DRYAD.8515'
+      response = subject.datacite_api_url(doi)
+      expect(response).to eq('https://api.datacite.org/dois/10.5061/dryad.8515?include=media,client')
+    end
+
+    it 'doi with protocol' do
+      doi = 'doi:10.5061/DRYAD.8515'
+      response = subject.datacite_api_url(doi)
+      expect(response).to eq('https://api.datacite.org/dois/10.5061/dryad.8515?include=media,client')
+    end
+
+    it 'https url' do
+      doi = 'https://doi.org/10.5061/dryad.8515'
+      response = subject.datacite_api_url(doi)
+      expect(response).to eq('https://api.datacite.org/dois/10.5061/dryad.8515?include=media,client')
+    end
+
+    it 'dx.doi.org url' do
+      doi = 'http://dx.doi.org/10.5061/dryad.8515'
+      response = subject.datacite_api_url(doi)
+      expect(response).to eq('https://api.datacite.org/dois/10.5061/dryad.8515?include=media,client')
+    end
+
+    it 'test resolver' do
+      doi = 'https://handle.stage.datacite.org/10.5061/dryad.8515'
+      response = subject.datacite_api_url(doi)
+      expect(response).to eq('https://api.stage.datacite.org/dois/10.5061/dryad.8515?include=media,client')
+    end
+
+    it 'test resolver http' do
+      doi = 'http://handle.stage.datacite.org/10.5061/dryad.8515'
+      response = subject.datacite_api_url(doi)
+      expect(response).to eq('https://api.stage.datacite.org/dois/10.5061/dryad.8515?include=media,client')
+    end
+
+    it 'force test resolver' do
+      doi = 'https://doi.org/10.5061/dryad.8515'
+      response = subject.datacite_api_url(doi, sandbox: true)
+      expect(response).to eq('https://api.stage.datacite.org/dois/10.5061/dryad.8515?include=media,client')
+    end
+  end
+
+  context 'normalize doi' do
+    it 'doi' do
+      doi = '10.5061/DRYAD.8515'
+      response = subject.normalize_doi(doi)
+      expect(response).to eq('https://doi.org/10.5061/dryad.8515')
+    end
+
+    it 'doi with protocol' do
+      doi = 'doi:10.5061/DRYAD.8515'
+      response = subject.normalize_doi(doi)
+      expect(response).to eq('https://doi.org/10.5061/dryad.8515')
+    end
+
+    it 'SICI doi' do
+      doi = '10.1890/0012-9658(2006)87[2832:tiopma]2.0.co;2'
+      response = subject.normalize_doi(doi)
+      expect(response).to eq('https://doi.org/10.1890/0012-9658(2006)87%5B2832:tiopma%5D2.0.co;2')
+    end
+
+    it 'https url' do
+      doi = 'https://doi.org/10.5061/dryad.8515'
+      response = subject.normalize_doi(doi)
+      expect(response).to eq('https://doi.org/10.5061/dryad.8515')
+    end
+
+    it 'dx.doi.org url' do
+      doi = 'http://dx.doi.org/10.5061/dryad.8515'
+      response = subject.normalize_doi(doi)
+      expect(response).to eq('https://doi.org/10.5061/dryad.8515')
+    end
+
+    it 'not valid doi prefix' do
+      doi = 'https://doi.org/20.5061/dryad.8515'
+      response = subject.normalize_doi(doi)
+      expect(response.nil?).to be(true)
+    end
+
+    it 'doi prefix with string' do
+      doi = 'https://doi.org/10.506X/dryad.8515'
+      response = subject.normalize_doi(doi)
+      expect(response.nil?).to be(true)
+    end
+
+    it 'doi prefix too long' do
+      doi = 'https://doi.org/10.506123/dryad.8515'
+      response = subject.normalize_doi(doi)
+      expect(response.nil?).to be(true)
+    end
+
+    it 'doi from url without doi proxy' do
+      doi = 'https://handle.net/10.5061/dryad.8515'
+      response = subject.normalize_doi(doi)
+      expect(response.nil?).to be(true)
+    end
+
+    it 'url with one slash' do
+      doi = 'https:/doi.org/10.5061/dryad.8515'
+      response = subject.normalize_doi(doi)
+      expect(response).to eq('https://doi.org/10.5061/dryad.8515')
+    end
+
+    it 'doi from datacite sandbox' do
+      doi = 'https://handle.stage.datacite.org/10.5438/55e5-t5c0'
+      response = subject.normalize_doi(doi)
+      expect(response).to eq('https://handle.stage.datacite.org/10.5438/55e5-t5c0')
+    end
+
+    it 'doi force datacite sandbox' do
+      doi = '10.5438/55e5-t5c0'
+      response = subject.normalize_doi(doi, sandbox: true)
+      expect(response).to eq('https://handle.stage.datacite.org/10.5438/55e5-t5c0')
+    end
+  end
+
+  context 'doi_from_url' do
+    it 'url' do
+      doi = subject.doi_from_url('https://doi.org/10.5061/dryad.8515')
+      expect(doi).to eq('10.5061/dryad.8515')
+    end
+
+    it 'doi' do
+      doi = subject.doi_from_url('10.5061/dryad.8515')
+      expect(doi).to eq('10.5061/dryad.8515')
+    end
+
+    it 'doi with special characters' do
+      doi = subject.doi_from_url('10.5067/terra+aqua/ceres/cldtyphist_l3.004')
+      expect(doi).to eq('10.5067/terra+aqua/ceres/cldtyphist_l3.004')
+    end
+
+    it 'not a doi' do
+      doi = subject.doi_from_url('https://doi.org/10.5061')
+      expect(doi.nil?).to be(true)
+    end
+
+    it 'sandbox url' do
+      doi = subject.doi_from_url('https://handle.stage.datacite.org/10.5438/55e5-t5c0')
+      expect(doi).to eq('10.5438/55e5-t5c0')
+    end
+  end
+
+  context 'doi registration agency' do
+    it 'datacite' do
+      doi = 'https://doi.org/10.5061/dryad.8515'
+      response = subject.get_doi_ra(doi)
+      expect(response).to eq('DataCite')
+    end
+
+    it 'crossref' do
+      doi = '10.1371/journal.pone.0000030'
+      response = subject.get_doi_ra(doi)
+      expect(response).to eq('Crossref')
+    end
+
+    it 'medra' do
+      doi = 'https://doi.org/10.1392/roma081203'
+      response = subject.get_doi_ra(doi)
+      expect(response).to eq('mEDRA')
+    end
+
+    it 'kisti' do
+      doi = 'https://doi.org/10.5012/bkcs.2013.34.10.2889'
+      response = subject.get_doi_ra(doi)
+      expect(response).to eq('KISTI')
+    end
+
+    it 'jalc' do
+      doi = 'https://doi.org/10.11367/grsj1979.12.283'
+      response = subject.get_doi_ra(doi)
+      expect(response).to eq('JaLC')
+    end
+
+    it 'op' do
+      doi = 'https://doi.org/10.2791/81962'
+      response = subject.get_doi_ra(doi)
+      expect(response).to eq('OP')
+    end
+
+    it 'not a valid prefix' do
+      doi = 'https://doi.org/10.a/dryad.8515x'
+      response = subject.get_doi_ra(doi)
+      expect(response.nil?).to be(true)
+    end
+
+    it 'not found' do
+      doi = 'https://doi.org/10.99999/dryad.8515x'
+      response = subject.get_doi_ra(doi)
+      expect(response.nil?).to be(true)
+    end
+  end
+
+  context 'validate doi' do
+    it 'doi' do
+      doi = '10.5061/dryad.8515'
+      response = subject.validate_doi(doi)
+      expect(response).to eq('10.5061/dryad.8515')
+    end
+  end
+
+  context 'validate funder doi' do
+    it 'funder doi' do
+      doi = '10.13039/501100001711'
+      response = subject.validate_funder_doi(doi)
+      expect(response).to eq('https://doi.org/10.13039/501100001711')
+    end
+
+    it 'funder doi without prefix' do
+      doi = '501100001711'
+      response = subject.validate_funder_doi(doi)
+      expect(response).to eq('https://doi.org/10.13039/501100001711')
+    end
+
+    it 'non-funder doi' do
+      doi = '10.5061/dryad.8515'
+      response = subject.validate_funder_doi(doi)
+      expect(response.nil?).to be(true)
+    end
+
+    it { expect(subject.validate_funder_doi('10.13039/100000050')).to eq 'https://doi.org/10.13039/100000050' }
+    it { expect(subject.validate_funder_doi('10.13039/100006492')).to eq 'https://doi.org/10.13039/100006492' }
+
+    it {
+      expect(subject.validate_funder_doi('http://handle.test.datacite.org/10.13039/100000080')).to eq 'https://doi.org/10.13039/100000080'
+    }
+
+    it { expect(subject.validate_funder_doi('https://doi.org/10.13039/100000001')).to eq 'https://doi.org/10.13039/100000001' }
+    it { expect(subject.validate_funder_doi('http://doi.org/10.13039/501100001711')).to eq 'https://doi.org/10.13039/501100001711' }
+    it { expect(subject.validate_funder_doi('https://dx.doi.org/10.13039/501100001711')).to eq 'https://doi.org/10.13039/501100001711' }
+    it { expect(subject.validate_funder_doi('doi:10.13039/501100001711')).to eq 'https://doi.org/10.13039/501100001711' }
+    it { expect(subject.validate_funder_doi('10.13039/501100001711')).to eq 'https://doi.org/10.13039/501100001711' }
+    it { expect(subject.validate_funder_doi('501100001711')).to eq 'https://doi.org/10.13039/501100001711' }
+    it { expect(subject.validate_funder_doi('https://doi.org/10.13039/5monkeymonkey').nil?).to be(true) }
+    it { expect(subject.validate_funder_doi('10.13039/5monkeymonkey').nil?).to be(true) }
+  end
+
+  context 'validate prefix' do
+    it 'doi' do
+      doi = '10.5061/dryad.8515'
+      response = subject.validate_prefix(doi)
+      expect(response).to eq('10.5061')
+    end
+
+    it 'doi with protocol' do
+      doi = 'doi:10.5061/dryad.8515'
+      response = subject.validate_prefix(doi)
+      expect(response).to eq('10.5061')
+    end
+
+    it 'doi as url' do
+      doi = 'https://doi.org/10.5061/dryad.8515'
+      response = subject.validate_prefix(doi)
+      expect(response).to eq('10.5061')
+    end
+
+    it 'only prefix' do
+      doi = '10.5061'
+      response = subject.validate_prefix(doi)
+      expect(response).to eq('10.5061')
+    end
+  end
+end