briard 2.0

data/spec/readers/npm_reader_spec.rb

@@ -0,0 +1,66 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe Briard::Metadata, vcr: true do
+  let(:input) { fixture_path + "cgimp_package.json" }
+
+  subject { Briard::Metadata.new(input: input, from: "npm") }
+
+  context "get npm raw" do
+    it "software" do
+      expect(subject.raw).to eq(IO.read(input).strip)
+    end
+  end
+
+  context "get npm metadata" do
+    it "minimal" do
+      expect(subject.valid?).to be false
+      expect(subject.errors.first).to start_with("3:0: ERROR: Element '{http://datacite.org/schema/kernel-4}identifier'")
+      #expect(subject.identifiers).to eq([{"identifier"=>"https://doi.org/10.5438/4k3m-nyvg", "identifierType"=>"DOI"}])
+      #expect(subject.url).to eq("https://blog.datacite.org/eating-your-own-dog-food")
+      expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"article", "reourceType"=>"NPM Package", "resourceTypeGeneral"=>"Software", "ris"=>"GEN", "schemaOrg"=>"SoftwareSourceCode")
+      expect(subject.creators).to eq([{"name"=>":(unav)", "nameType"=>"Organizational"}])
+      expect(subject.titles).to eq([{"title"=>"fullstack_app"}])
+      expect(subject.descriptions).to be_empty
+      expect(subject.rights_list).to eq([{"rights"=>"ISC"}])
+      expect(subject.version_info).to eq("1.0.0")
+      #expect(subject.dates).to eq([{"date"=>"2016-12-20", "dateType"=>"Issued"}])
+      #expect(subject.publication_year).to eq("2016")
+    end
+
+    it "minimal with description" do
+      input = fixture_path + "cit_package.json"
+      subject = Briard::Metadata.new(input: input, from: "npm") 
+      expect(subject.valid?).to be false
+      expect(subject.errors.first).to start_with("3:0: ERROR: Element '{http://datacite.org/schema/kernel-4}identifier'")
+      #expect(subject.identifiers).to eq([{"identifier"=>"https://doi.org/10.5438/4k3m-nyvg", "identifierType"=>"DOI"}])
+      #expect(subject.url).to eq("https://blog.datacite.org/eating-your-own-dog-food")
+      expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"article", "reourceType"=>"NPM Package", "resourceTypeGeneral"=>"Software", "ris"=>"GEN", "schemaOrg"=>"SoftwareSourceCode")
+      expect(subject.creators).to eq([{"name"=>":(unav)", "nameType"=>"Organizational"}])
+      expect(subject.titles).to eq([{"title"=>"CITapp"}])
+      expect(subject.descriptions).to eq([{"description"=>"Concealed Information Test app", "descriptionType"=>"Abstract"}])
+      expect(subject.version_info).to eq("1.1.0")
+      #expect(subject.dates).to eq([{"date"=>"2016-12-20", "dateType"=>"Issued"}])
+      #expect(subject.publication_year).to eq("2016")
+    end
+
+    it "minimal with description" do
+      input = fixture_path + "edam_package.json"
+      subject = Briard::Metadata.new(input: input, from: "npm") 
+      expect(subject.valid?).to be false
+      expect(subject.errors.first).to start_with("3:0: ERROR: Element '{http://datacite.org/schema/kernel-4}identifier'")
+      #expect(subject.identifiers).to eq([{"identifier"=>"https://doi.org/10.5438/4k3m-nyvg", "identifierType"=>"DOI"}])
+      #expect(subject.url).to eq("https://blog.datacite.org/eating-your-own-dog-food")
+      expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"article", "reourceType"=>"NPM Package", "resourceTypeGeneral"=>"Software", "ris"=>"GEN", "schemaOrg"=>"SoftwareSourceCode")
+      expect(subject.creators).to eq([{"affiliation"=>[], "familyName"=>"Brancotte", "givenName"=>"Bryan", "name"=>"Brancotte, Bryan", "nameIdentifiers"=>[], "nameType"=>"Personal"}])
+      expect(subject.titles).to eq([{"title"=>"edam-browser"}])
+      expect(subject.descriptions).to eq([{"description"=>
+        +   "The EDAM Browser is a client-side web-based visualization javascript widget. Its goals are to help describing bio-related resources and service with EDAM, and to facilitate and foster community contributions to EDAM.",
+           "descriptionType"=>"Abstract"}])
+      expect(subject.version_info).to eq("1.0.0")
+      #expect(subject.dates).to eq([{"date"=>"2016-12-20", "dateType"=>"Issued"}])
+      #expect(subject.publication_year).to eq("2016")
+    end
+  end
+end

data/spec/readers/ris_reader_spec.rb

@@ -0,0 +1,75 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe Briard::Metadata, vcr: true do
+  let(:input) { fixture_path + "crossref.ris" }
+
+  subject { Briard::Metadata.new(input: input) }
+
+  context "detect format" do
+    it "extension" do
+      expect(subject.valid?).to be true
+    end
+
+    it "string" do
+      Briard::Metadata.new(input: IO.read(input).strip)
+      expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.7554/elife.01567")
+    end
+  end
+
+  context "get ris raw" do
+    it "Crossref DOI" do
+      expect(subject.raw).to eq(IO.read(input).strip)
+    end
+  end
+
+  context "get ris metadata" do
+    it "Crossref DOI" do
+      expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.7554/elife.01567")
+      expect(subject.types).to eq("citeproc"=>"misc", "resourceTypeGeneral"=>"JournalArticle", "ris"=>"JOUR", "schemaOrg"=>"ScholarlyArticle")
+      expect(subject.url).to eq("http://elifesciences.org/lookup/doi/10.7554/eLife.01567")
+      expect(subject.creators.length).to eq(5)
+      expect(subject.creators.first).to eq("nameType"=>"Personal",
+                                         "name"=>"Sankar, Martial",
+                                         "givenName"=>"Martial",
+                                         "familyName"=>"Sankar",
+                                         "nameIdentifiers" => [],
+                                         "affiliation" => [])
+      expect(subject.titles).to eq([{"title"=>"Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth"}])
+      expect(subject.descriptions.first["description"]).to start_with("Among various advantages, their small size makes model organisms preferred subjects of investigation.")
+      expect(subject.dates).to eq([{"date"=>"2014", "dateType"=>"Issued"}])
+      expect(subject.publication_year).to eq("2014")
+      expect(subject.related_identifiers).to eq([{"id"=>"2050084X", "relatedIdentifierType"=>"ISSN", "relationType"=>"IsPartOf", "title"=>"eLife", "type"=>"Periodical"}])
+      expect(subject.container).to eq("identifier"=>"2050084X", "title"=>"eLife", "type"=>"Journal", "volume"=>"3")
+    end
+
+    it "DOI does not exist" do
+      input = fixture_path + "pure.ris"
+      doi = "10.7554/elife.01567"
+      subject = Briard::Metadata.new(input: input, doi: doi)
+      expect(subject.valid?).to be false
+      expect(subject.state).to eq("not_found")
+      expect(subject.id).to eq("https://doi.org/10.7554/elife.01567")
+      expect(subject.types).to eq("citeproc"=>"misc", "resourceTypeGeneral"=>"Dissertation", "ris"=>"THES", "schemaOrg"=>"Thesis")
+      expect(subject.creators).to eq([{"nameType"=>"Personal", "name"=>"Toparlar, Y.", "givenName"=>"Y.", "familyName"=>"Toparlar", "nameIdentifiers" => [], "affiliation" => []}])
+      expect(subject.titles).to eq([{"title"=>"A multiscale analysis of the urban heat island effect"}])
+      expect(subject.descriptions.first["description"]).to start_with("Designing the climates of cities")
+      expect(subject.dates).to eq([{"date"=>"2018-04-25", "dateType"=>"Issued"}, {"date"=>"2018-04-25", "dateType"=>"Created"}])
+      expect(subject.publication_year).to eq("2018")
+    end
+
+    it "RIS with Dashes" do
+      input = fixture_path + "ris_bug.ris"
+      abs = "3D image based subject specific models of the ankle complex can be extremely significant in a wide variety of clinical and biomechanical applications such as evaluating the effect of ligament ruptures, diagnosing and comparing surgical procedures. However, there are very few computational models that can accurately capture the full 3D biomechanical properties of the ankle complex. One such computational model was introduced by our group in 2004 [1], and this model was partially validated with a very limited set of parameters for comparison. In the current study, we have developed an improvised version of this model and validated it on a subject to subject basis for a number of specimens. This is achieved by comparing a wide range of biomechanical parameters between the experiments and the simulation. Once, the model is validated, it can be used for a wide variety of clinical and surgical applications .Some applications include comparing the effects of surface morphology on the kinematics of the ankle joint, diagnosing and evaluation of ankle disorders like ligament tears and reconstruction surgeries. Previous experimental studies conducted to understand and validate the effect of morphological variations to kinematics involved invasive surgical procedures and hence could only be conducted in cadaveric foot. Hence a need for a dynamic model which could predict and recreate the kinematics of an ankle using only CT and, or MRI data was realized. Such a model could help in development and non-invasive testing of subject specific TAR. This thesis focusses on the subject specific validation of rigid body models of four specimens and an one-to-one validation based on Load-displacement curves, Range of Motion, Surface-to-surface interaction and Ligament straining patterns. Post validation of the MBS model in MSC ADAMS, the model is used to investigate the effect of axial loads, total ankle arthrodesis and the effect of varying surface morphologies on the behavior of the ankle joint complex. An in-depth comparative analysis on the use of a numerical model for the development and performance evaluation of an implant derived from the morphological parameters of the ankle joint is also presented."
+      doi = "10.7554/elife.01567"
+      subject = Briard::Metadata.new(input: input, doi: doi)
+      expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.7554/elife.01567")
+      expect(subject.titles).to eq([{"title"=>"Validation of an Image-based Subject-Specific Dynamic Model of the Ankle Joint Complex and its Applications to the Study of the Effect of Articular Surface Morphology on Ankle Joint Mechanics"}])
+      expect(subject.descriptions.first["description"]).to eq(abs)
+    end
+  end
+end

data/spec/readers/schema_org_reader_spec.rb

@@ -0,0 +1,376 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe Briard::Metadata, vcr: true do
+  let(:fixture_path) { "spec/fixtures/" }
+
+  context "get schema_org raw" do
+    it "BlogPosting" do
+      input = fixture_path + 'schema_org.json'
+      subject = Briard::Metadata.new(input: input)
+      expect(subject.raw).to eq(IO.read(input).strip)
+    end
+  end
+
+  context "get schema_org metadata" do
+    it "BlogPosting" do
+      input = "https://blog.datacite.org/eating-your-own-dog-food/"
+      subject = Briard::Metadata.new(input: input, from: "schema_org")
+      expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.5438/4k3m-nyvg")
+      expect(subject.url).to eq("https://blog.datacite.org/eating-your-own-dog-food")
+      expect(subject.types).to eq("bibtex"=>"article", "citeproc"=>"post-weblog", "resourceTypeGeneral"=>"Preprint", "ris"=>"GEN", "schemaOrg"=>"BlogPosting")
+      expect(subject.creators).to eq([{"affiliation"=>[{"affiliationIdentifier"=>"https://ror.org/04wxnsj81",
+        "affiliationIdentifierScheme"=>"ROR",
+        "name"=>"DataCite"}],"familyName"=>"Fenner", "givenName"=>"Martin", "name"=>"Fenner, Martin", "nameIdentifiers"=> [{"nameIdentifier"=>"https://orcid.org/0000-0003-1419-2405", "nameIdentifierScheme"=>"ORCID", "schemeUri"=>"https://orcid.org"}], "nameType"=>"Personal"}])
+      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.dates).to eq([{"date"=>"2016-12-20", "dateType"=>"Issued"},
+        {"date"=>"2016-12-20", "dateType"=>"Created"},
+        {"date"=>"2016-12-20", "dateType"=>"Updated"}])
+      expect(subject.publication_year).to eq("2016")
+      expect(subject.related_identifiers.length).to eq(3)
+      expect(subject.related_identifiers.last).to eq("relatedIdentifier"=>"10.5438/55e5-t5c0", "relatedIdentifierType"=>"DOI", "relationType"=>"References")
+      expect(subject.publisher).to eq("DataCite")
+    end
+
+    it "BlogPosting with new DOI" do
+      input = "https://blog.datacite.org/eating-your-own-dog-food/"
+      subject = Briard::Metadata.new(input: input, doi: "10.5438/0000-00ss")
+      expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.5438/0000-00ss")
+      expect(subject.doi).to eq("10.5438/0000-00ss")
+      expect(subject.url).to eq("https://blog.datacite.org/eating-your-own-dog-food")
+      expect(subject.types).to eq("bibtex"=>"article", "citeproc"=>"post-weblog", "resourceTypeGeneral"=>"Preprint", "ris"=>"GEN", "schemaOrg"=>"BlogPosting")
+    end
+
+    it "BlogPosting with type as array" do
+      input = fixture_path + 'schema_org_type_as_array.json'
+      subject = Briard::Metadata.new(input: input)
+      expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.5438/4k3m-nyvg")
+      expect(subject.url).to eq("https://blog.datacite.org/eating-your-own-dog-food")
+      expect(subject.types).to eq("bibtex"=>"article", "citeproc"=>"post-weblog", "resourceTypeGeneral"=>"Preprint", "ris"=>"GEN", "schemaOrg"=>"BlogPosting")
+      expect(subject.creators).to eq([{"affiliation"=>[{"name"=>"DataCite"}],"familyName"=>"Fenner", "givenName"=>"Martin", "name"=>"Fenner, Martin", "nameIdentifiers"=> [{"nameIdentifier"=>"https://orcid.org/0000-0003-1419-2405", "nameIdentifierScheme"=>"ORCID", "schemeUri"=>"https://orcid.org"}], "nameType"=>"Personal"}])
+      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.dates).to eq([{"date"=>"2016-12-20", "dateType"=>"Issued"},
+        {"date"=>"2016-12-20", "dateType"=>"Created"},
+        {"date"=>"2016-12-20", "dateType"=>"Updated"}])
+      expect(subject.publication_year).to eq("2016")
+      expect(subject.related_identifiers.length).to eq(3)
+      expect(subject.related_identifiers.last).to eq("relatedIdentifier"=>"10.5438/55e5-t5c0", "relatedIdentifierType"=>"DOI", "relationType"=>"References")
+      expect(subject.publisher).to eq("DataCite")
+    end
+
+    context "get schema_org metadata front matter" do
+      it "BlogPosting" do
+        input = "https://blog.front-matter.io/posts/step-forward-for-software-citation"
+        subject = Briard::Metadata.new(input: input, from: "schema_org")
+        expect(subject.valid?).to be true
+        expect(subject.id).to eq("https://doi.org/10.53731/r9531p1-97aq74v-ag78v")
+        expect(subject.url).to eq("https://blog.front-matter.io/posts/step-forward-for-software-citation")
+        expect(subject.types).to eq("bibtex"=>"article", "citeproc"=>"post-weblog", "resourceTypeGeneral"=>"Preprint", "ris"=>"GEN", "schemaOrg"=>"BlogPosting")
+        expect(subject.creators).to eq([{"affiliation"=>[],
+          "familyName"=>"Fenner", "givenName"=>"Martin", "name"=>"Fenner, Martin", "nameIdentifiers"=> [{"nameIdentifier"=>"https://orcid.org/0000-0003-1419-2405", "nameIdentifierScheme"=>"ORCID", "schemeUri"=>"https://orcid.org"}], "nameType"=>"Personal"}])
+        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.dates).to eq([{"date"=>"2021-08-24T16:57:24Z", "dateType"=>"Issued"},
+          {"date"=>"2021-08-24T16:03:56Z", "dateType"=>"Created"},
+          {"date"=>"2021-11-01T19:01:15Z", "dateType"=>"Updated"}])
+        expect(subject.publication_year).to eq("2021")
+        expect(subject.related_identifiers.length).to eq(0)
+        expect(subject.container).to eq("identifier"=>"2749-9952", "identifierType"=>"ISSN", "title"=>"Front Matter", "type"=>"Blog")
+        expect(subject.publisher).to eq("Front Matter")
+      end
+    end
+
+    it "zenodo" do
+      input = "https://www.zenodo.org/record/1196821"
+      subject = Briard::Metadata.new(input: input, from: "schema_org")
+      expect(subject.valid?).to be false
+      expect(subject.language).to eq("eng")
+      expect(subject.errors).to eq("49:0: ERROR: Element '{http://datacite.org/schema/kernel-4}publisher': [facet 'minLength'] The value has a length of '0'; this underruns the allowed minimum length of '1'.")
+      expect(subject.id).to eq("https://doi.org/10.5281/zenodo.1196821")
+      expect(subject.doi).to eq("10.5281/zenodo.1196821")
+      expect(subject.url).to eq("https://zenodo.org/record/1196821")
+      expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"dataset", "resourceTypeGeneral"=>"Dataset", "ris"=>"DATA", "schemaOrg"=>"Dataset")
+      expect(subject.titles).to eq([{"title"=>"PsPM-SC4B: SCR, ECG, EMG, PSR and respiration measurements in a delay fear conditioning task with auditory CS and electrical US"}])
+      expect(subject.creators.size).to eq(6)
+      expect(subject.creators.first).to eq("name" => "Staib, Matthias",
+        "nameIdentifiers" => [{"nameIdentifier"=>"https://orcid.org/0000-0001-9688-838X", "nameIdentifierScheme"=>"ORCID", "schemeUri"=>"https://orcid.org"}],
+        "nameType" => "Personal", "givenName"=>"Matthias", "familyName"=>"Staib", "affiliation" => [{"name"=>"University of Zurich, Zurich, Switzerland"}])
+      expect(subject.publisher).to be_nil
+      expect(subject.publication_year).to eq("2018")
+      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
+      input = "https://doi.pangaea.de/10.1594/PANGAEA.836178"
+      subject = Briard::Metadata.new(input: input, from: "schema_org")
+      expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.1594/pangaea.836178")
+      expect(subject.doi).to eq("10.1594/pangaea.836178")
+      expect(subject.url).to eq("https://doi.pangaea.de/10.1594/PANGAEA.836178")
+      expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"dataset", "resourceTypeGeneral"=>"Dataset", "ris"=>"DATA", "schemaOrg"=>"Dataset")
+      expect(subject.titles).to eq([{"title"=>"Hydrological and meteorological investigations in a lake near Kangerlussuaq, west Greenland"}])
+      expect(subject.creators.size).to eq(8)
+      expect(subject.creators.first).to eq("nameType" => "Personal", "name"=>"Johansson, Emma", "givenName"=>"Emma", "familyName"=>"Johansson")
+      expect(subject.publisher).to eq("PANGAEA")
+      expect(subject.publication_year).to eq("2014")
+    end
+
+    # TODO: check redirections
+    # it "ornl" do
+    #   input = "https://doi.org/10.3334/ornldaac/1339"
+    #   subject = Briard::Metadata.new(input: input, from: "schema_org")
+    #   expect(subject.valid?).to be true
+    #   expect(subject.id).to eq("https://doi.org/10.3334/ornldaac/1339")
+    #   expect(subject.doi).to eq("10.3334/ornldaac/1339")
+    #   expect(subject.url).to eq("https://doi.org/10.3334/ornldaac/1339")
+    #   expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"article-journal", "ris"=>"GEN", "schemaOrg"=>"DataSet")
+    #   expect(subject.titles).to eq([{"title"=>"Soil Moisture Profiles and Temperature Data from SoilSCAPE Sites, USA"}])
+    #   expect(subject.creators.size).to eq(12)
+    #   expect(subject.creators.first).to eq("familyName"=>"MOGHADDAM", "givenName"=>"M.", "name"=>"MOGHADDAM, M.", "nameType"=>"Personal", "nameIdentifiers"=>[], "affiliation" => [])
+    # end
+
+    it "harvard dataverse" do
+      input = "https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/NJ7XSO"
+      subject = Briard::Metadata.new(input: input, from: "schema_org")
+      expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.7910/dvn/nj7xso")
+      expect(subject.doi).to eq("10.7910/dvn/nj7xso")
+      expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"dataset", "resourceTypeGeneral"=>"Dataset", "ris"=>"DATA", "schemaOrg"=>"Dataset")
+      expect(subject.titles).to eq([{"title"=>"Summary data ankylosing spondylitis GWAS"}])
+      expect(subject.container).to eq("identifier"=>"https://dataverse.harvard.edu", "identifierType"=>"URL", "title"=>"Harvard Dataverse", "type"=>"DataRepository")
+      expect(subject.creators).to eq([{"name" => "International Genetics Of Ankylosing Spondylitis Consortium (IGAS)", "nameIdentifiers"=>[], "affiliation" => []}])
+      expect(subject.subjects).to eq([{"subject"=>"Medicine, Health and Life Sciences"},
+        {"subject"=>"Genome-Wide Association Studies"},
+        {"subject"=>"Ankylosing spondylitis"}])
+    end
+
+    # TODO check 403 status in DOI resolver
+    # it "harvard dataverse via identifiers.org" do
+    #   input = "https://identifiers.org/doi/10.7910/DVN/NJ7XSO"
+    #   subject = Briard::Metadata.new(input: input, from: "schema_org")
+    #   expect(subject.valid?).to be true
+    #   expect(subject.id).to eq("https://doi.org/10.7910/dvn/nj7xso")
+    #   expect(subject.doi).to eq("10.7910/dvn/nj7xso")
+    #   expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"dataset", "resourceTypeGeneral"=>"Dataset", "ris"=>"DATA", "schemaOrg"=>"Dataset")
+    #   expect(subject.titles).to eq([{"title"=>"Summary data ankylosing spondylitis GWAS"}])
+    #   expect(subject.container).to eq("identifier"=>"https://dataverse.harvard.edu", "identifierType"=>"URL", "title"=>"Harvard Dataverse", "type"=>"DataRepository")
+    #   expect(subject.creators).to eq([{"name" => "International Genetics Of Ankylosing Spondylitis Consortium (IGAS)", "nameIdentifiers"=>[], "affiliation" => []}])
+    # end
+  end
+
+  context "get schema_org metadata as string" do
+    it "BlogPosting" do
+      input = fixture_path + 'schema_org.json'
+      subject = Briard::Metadata.new(input: input)
+      expect(subject.valid?).to be true
+      expect(subject.language).to eq("en")
+      expect(subject.id).to eq("https://doi.org/10.5438/4k3m-nyvg")
+      expect(subject.url).to eq("https://blog.datacite.org/eating-your-own-dog-food")
+      expect(subject.types).to eq("bibtex"=>"article", "citeproc"=>"post-weblog", "resourceTypeGeneral"=>"Preprint", "ris"=>"GEN", "schemaOrg"=>"BlogPosting")
+      expect(subject.creators).to eq([{"familyName"=>"Fenner", "givenName"=>"Martin", "name"=>"Fenner, Martin", "nameIdentifiers"=> [{"nameIdentifier"=>"https://orcid.org/0000-0003-1419-2405", "nameIdentifierScheme"=>"ORCID",
+        +     "schemeUri"=>"https://orcid.org"}], "nameType"=>"Personal"}])
+      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.dates).to eq([{"date"=>"2016-12-20", "dateType"=>"Issued"},
+        {"date"=>"2016-12-20", "dateType"=>"Created"},
+        {"date"=>"2016-12-20", "dateType"=>"Updated"}])
+      expect(subject.publication_year).to eq("2016")
+      expect(subject.related_identifiers.length).to eq(3)
+      expect(subject.related_identifiers.last).to eq("relatedIdentifier"=>"10.5438/55e5-t5c0", "relatedIdentifierType"=>"DOI", "relationType"=>"References")
+      expect(subject.publisher).to eq("DataCite")
+    end
+
+    it "GTEx dataset" do
+      input = fixture_path + 'schema_org_gtex.json'
+      subject = Briard::Metadata.new(input: input)
+
+      expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.25491/d50j-3083")
+      expect(subject.identifiers).to eq([{"identifier"=>"687610993", "identifierType"=>"md5"}])
+      expect(subject.url).to eq("https://ors.datacite.org/doi:/10.25491/d50j-3083")
+      expect(subject.content_url).to eq(["https://storage.googleapis.com/gtex_analysis_v7/single_tissue_eqtl_data/GTEx_Analysis_v7_eQTL_expression_matrices.tar.gz"])
+      expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"dataset", "resourceType"=>"Gene expression matrices", "resourceTypeGeneral"=>"Dataset", "ris"=>"DATA", "schemaOrg"=>"Dataset")
+      expect(subject.creators).to eq([{"name"=>"The GTEx Consortium", "nameType"=>"Organizational", "nameIdentifiers"=>[], "affiliation" => []}])
+      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_info).to eq("v7")
+      expect(subject.subjects).to eq([{"subject"=>"gtex"}, {"subject"=>"annotation"}, {"subject"=>"phenotype"}, {"subject"=>"gene regulation"}, {"subject"=>"transcriptomics"}])
+      expect(subject.dates).to eq([{"date"=>"2017", "dateType"=>"Issued"}])
+      expect(subject.publication_year).to eq("2017")
+      expect(subject.container).to eq("title"=>"GTEx", "type"=>"DataRepository")
+      expect(subject.publisher).to eq("GTEx")
+      expect(subject.funding_references.length).to eq(7)
+      expect(subject.funding_references.first).to eq("funderIdentifier"=>"https://doi.org/10.13039/100000052", "funderIdentifierType"=>"Crossref Funder ID", "funderName"=>"Common Fund of the Office of the Director of the NIH")
+    end
+
+    it "TOPMed dataset" do
+      input = fixture_path + 'schema_org_topmed.json'
+      subject = Briard::Metadata.new(input: input)
+      expect(subject.valid?).to be true
+      expect(subject.identifiers).to eq([{"identifier"=>"3b33f6b9338fccab0901b7d317577ea3", "identifierType"=>"md5"},
+        {"identifier"=>"ark:/99999/fk41CrU4eszeLUDe", "identifierType"=>"minid"},
+        {"identifier"=>"dg.4503/c3d66dc9-58da-411c-83c4-dd656aa3c4b7", "identifierType"=>"dataguid"}])
+      expect(subject.url).to eq("https://ors.datacite.org/doi:/10.23725/8na3-9s47")
+      expect(subject.content_url).to eq(["s3://cgp-commons-public/topmed_open_access/197bc047-e917-55ed-852d-d563cdbc50e4/NWD165827.recab.cram", "gs://topmed-irc-share/public/NWD165827.recab.cram"])
+      expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"dataset", "resourceType"=>"CRAM file", "resourceTypeGeneral"=>"Dataset", "ris"=>"DATA", "schemaOrg"=>"Dataset")
+      expect(subject.creators).to eq([{"name"=>"TOPMed IRC", "nameType"=>"Organizational", "nameIdentifiers"=>[], "affiliation" => []}])
+      expect(subject.titles).to eq([{"title"=>"NWD165827.recab.cram"}])
+      expect(subject.subjects).to eq([{"subject"=>"topmed"}, {"subject"=>"whole genome sequencing"}])
+      expect(subject.dates).to eq([{"date"=>"2017-11-30", "dateType"=>"Issued"}])
+      expect(subject.publication_year).to eq("2017")
+      expect(subject.publisher).to eq("TOPMed")
+      expect(subject.related_identifiers).to eq([{"relatedIdentifier"=>"10.23725/2g4s-qv04", "relatedIdentifierType"=>"DOI", "relationType"=>"References", "resourceTypeGeneral"=>"Dataset"}])
+      expect(subject.funding_references).to eq([{"funderIdentifier"=>"https://doi.org/10.13039/100000050", "funderIdentifierType"=>"Crossref Funder ID", "funderName"=>"National Heart, Lung, and Blood Institute (NHLBI)"}])
+    end
+
+    it "tdl_iodp dataset" do
+      input = fixture_path + 'schema_org_tdl_iodp_invalid_authors.json'
+      subject = Briard::Metadata.new(input: input)
+      expect(subject.valid?).to be false
+    end
+
+    it "geolocation" do
+      input = fixture_path + 'schema_org_geolocation.json'
+      subject = Briard::Metadata.new(input: input)
+
+      expect(subject.valid?).to be true
+      expect(subject.identifiers).to eq([{"identifier"=>"https://doi.org/10.6071/z7wc73", "identifierType"=>"DOI"}])
+      expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"dataset", "resourceType"=>"dataset", "resourceTypeGeneral"=>"Dataset", "ris"=>"DATA", "schemaOrg"=>"Dataset")
+      expect(subject.creators.length).to eq(6)
+      expect(subject.creators.first).to eq("familyName"=>"Bales", "givenName"=>"Roger", "name"=>"Bales, Roger", "nameType"=>"Personal")
+      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.dates).to eq([{"date"=>"2013", "dateType"=>"Issued"},
+        {"date"=>"2014-10-17", "dateType"=>"Updated"}])
+      expect(subject.publication_year).to eq("2013")
+      expect(subject.publisher).to eq("UC Merced")
+      expect(subject.funding_references).to eq([{"funderName"=>"National Science Foundation, Division of Earth Sciences, Critical Zone Observatories"}])
+      expect(subject.geo_locations).to eq([{"geoLocationPlace"=>"Providence Creek (Lower, Upper and P301)", "geoLocationPoint"=>{"pointLatitude"=>"37.047756", "pointLongitude"=>"-119.221094"}}])
+    end
+
+    it "geolocation geoshape" do
+      input = fixture_path + 'schema_org_geoshape.json'
+      subject = Briard::Metadata.new(input: input)
+
+      expect(subject.valid?).to be true
+      expect(subject.language).to eq("en")
+      expect(subject.id).to eq("https://doi.org/10.1594/pangaea.842237")
+      expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"dataset", "resourceTypeGeneral"=>"Dataset", "ris"=>"DATA", "schemaOrg"=>"Dataset")
+      expect(subject.creators.length).to eq(2)
+      expect(subject.creators.first).to eq("name"=>"Tara Oceans Consortium, Coordinators", "nameType"=>"Organizational", "nameIdentifiers"=>[], "affiliation" => [])
+      expect(subject.titles).to eq([{"title"=>"Registry of all stations from the Tara Oceans Expedition (2009-2013)"}])
+      expect(subject.dates).to eq([{"date"=>"2015-02-03", "dateType"=>"Issued"}])
+      expect(subject.publication_year).to eq("2015")
+      expect(subject.publisher).to eq("PANGAEA")
+      expect(subject.geo_locations).to eq([{"geoLocationBox"=>{"eastBoundLongitude"=>"174.9006", "northBoundLatitude"=>"79.6753", "southBoundLatitude"=>"-64.3088", "westBoundLongitude"=>"-168.5182"}}])
+    end
+
+    it "schema_org list" do
+      data = IO.read(fixture_path + 'schema_org_list.json').strip
+      input = JSON.parse(data).first.to_json
+      subject = Briard::Metadata.new(input: input)
+      expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.23725/7jg3-v803")
+      expect(subject.identifiers).to eq([{"identifier"=>"ark:/99999/fk4E1n6n1YHKxPk", "identifierType"=>"minid"},
+        {"identifier"=>"dg.4503/01b048d0-e128-4cb0-94e9-b2d2cab7563d",
+         "identifierType"=>"dataguid"},
+        {"identifier"=>"f9e72bdf25bf4b4f0e581d9218fec2eb", "identifierType"=>"md5"}])
+      expect(subject.url).to eq("https://ors.datacite.org/doi:/10.23725/7jg3-v803")
+      expect(subject.content_url).to eq(["s3://cgp-commons-public/topmed_open_access/44a8837b-4456-5709-b56b-54e23000f13a/NWD100953.recab.cram","gs://topmed-irc-share/public/NWD100953.recab.cram","dos://dos.commons.ucsc-cgp.org/01b048d0-e128-4cb0-94e9-b2d2cab7563d?version=2018-05-26T133719.491772Z"])
+      expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"dataset", "resourceType"=>"CRAM file", "resourceTypeGeneral"=>"Dataset", "ris"=>"DATA", "schemaOrg"=>"Dataset")
+      expect(subject.creators).to eq([{"name"=>"TOPMed", "nameType"=>"Organizational", "nameIdentifiers"=>[], "affiliation" => []}])
+      expect(subject.titles).to eq([{"title"=>"NWD100953.recab.cram"}])
+      expect(subject.subjects).to eq([{"subject"=>"topmed"}, {"subject"=>"whole genome sequencing"}])
+      expect(subject.dates).to eq([{"date"=>"2017-11-30", "dateType"=>"Issued"}])
+      expect(subject.publication_year).to eq("2017")
+      expect(subject.publisher).to eq("TOPMed")
+      expect(subject.funding_references).to eq([{"funderIdentifier"=>"https://doi.org/10.13039/100000050", "funderIdentifierType"=>"Crossref Funder ID", "funderName"=>"National Heart, Lung, and Blood Institute (NHLBI)"}])
+    end
+
+    it "aida dataset" do
+      input = fixture_path + 'aida.json'
+      subject = Briard::Metadata.new(input: input)
+
+      expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.23698/aida/drov")
+      expect(subject.url).to eq("https://doi.aida.medtech4health.se/10.23698/aida/drov")
+      expect(subject.types).to eq("bibtex"=>"misc", "citeproc"=>"dataset", "resourceTypeGeneral"=>"Dataset", "ris"=>"DATA", "schemaOrg"=>"Dataset")
+      # 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"}], "nameType"=>"Personal"}])
+      expect(subject.titles).to eq([{"title"=>"Ovary data from the Visual Sweden project DROID"}])
+      expect(subject.version_info).to eq("1.0")
+      expect(subject.subjects).to eq([{"subject"=>"pathology"}, {"subject"=>"whole slide imaging"}, {"subject"=>"annotated"}])
+      expect(subject.dates).to eq([{"date"=>"2019-01-09", "dateType"=>"Issued"},
+        {"date"=>"2019-01-09", "dateType"=>"Created"},
+        {"date"=>"2019-01-09", "dateType"=>"Updated"}])
+      expect(subject.publication_year).to eq("2019")
+      expect(subject.id).to eq("https://doi.org/10.23698/aida/drov")
+      expect(subject.publisher).to eq("AIDA")
+      expect(subject.rights_list).to eq([{"rights"=>"Restricted access", "rightsUri"=>"https://datasets.aida.medtech4health.se/10.23698/aida/drov#license"}])
+      expect(subject.id).to eq("https://doi.org/10.23698/aida/drov")
+    end
+
+    it "from attributes" do
+      subject = Briard::Metadata.new(input: nil,
+        from: "schema_org",
+        doi: "10.5281/zenodo.1239",
+        creators: [{"type"=>"Person", "name"=>"Jahn, Najko", "givenName"=>"Najko", "familyName"=>"Jahn"}],
+        titles: [{ "title" => "Publication Fp7 Funding Acknowledgment - Plos Openaire" }],
+        descriptions: [{ "description" => "The dataset contains a sample of metadata describing papers" }],
+        publisher: "Zenodo",
+        publication_year: "2013",
+        dates: [{"date"=>"2013-04-03", "dateType"=>"Issued"}],
+        funding_references: [{"awardNumber"=>"246686",
+          "awardTitle"=>"Open Access Infrastructure for Research in Europe",
+          "awardUri"=>"info:eu-repo/grantAgreement/EC/FP7/246686/",
+          "funderIdentifier"=>"https://doi.org/10.13039/501100000780",
+          "funderIdentifierType"=>"Crossref Funder ID",
+          "funderName"=>"European Commission"}],
+        types: { "resourceTypeGeneral" => "Dataset", "schemaOrg" => "Dataset" })
+
+      expect(subject.valid?).to be true
+      expect(subject.doi).to eq("10.5281/zenodo.1239")
+      expect(subject.id).to eq("https://doi.org/10.5281/zenodo.1239")
+      expect(subject.types["schemaOrg"]).to eq("Dataset")
+      expect(subject.types["resourceTypeGeneral"]).to eq("Dataset")
+      expect(subject.creators).to eq([{"familyName"=>"Jahn", "givenName"=>"Najko", "name"=>"Jahn, Najko", "type"=>"Person"}])
+      expect(subject.titles).to eq([{"title"=>"Publication Fp7 Funding Acknowledgment - Plos Openaire"}])
+      expect(subject.descriptions.first["description"]).to start_with("The dataset contains a sample of metadata describing papers")
+      expect(subject.dates).to eq([{"date"=>"2013-04-03", "dateType"=>"Issued"}])
+      expect(subject.publication_year).to eq("2013")
+      expect(subject.publisher).to eq("Zenodo")
+      expect(subject.funding_references).to eq([{"awardNumber"=>"246686",
+        "awardTitle"=>"Open Access Infrastructure for Research in Europe",
+        "awardUri"=>"info:eu-repo/grantAgreement/EC/FP7/246686/",
+        "funderIdentifier"=>"https://doi.org/10.13039/501100000780",
+        "funderIdentifierType"=>"Crossref Funder ID",
+        "funderName"=>"European Commission"}])
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,94 @@
+# frozen_string_literal: true
+
+require 'bundler/setup'
+Bundler.setup
+
+require 'simplecov'
+SimpleCov.start
+
+require 'briard'
+require 'maremma'
+require 'rspec'
+require 'rack/test'
+require 'webmock/rspec'
+require 'rspec/xsd'
+require 'nokogiri'
+require 'vcr'
+
+RSpec.configure do |config|
+  config.order = :random
+  config.include RSpec::XSD
+  config.include WebMock::API
+  config.include Rack::Test::Methods
+  config.expect_with :rspec do |c|
+    c.syntax = :expect
+  end
+
+  config.before do
+    ARGV.replace []
+  end
+
+  config.before(:suite) do
+    ::NameDetector = GenderDetector.new
+  end
+end
+
+def fixture_path
+  File.expand_path("../fixtures", __FILE__) + '/'
+end
+
+# This code was adapted from Thor, available under MIT-LICENSE
+# Copyright (c) 2008 Yehuda Katz, Eric Hodel, et al.
+def capture(stream)
+  begin
+    stream = stream.to_s
+    eval "$#{stream} = StringIO.new"
+    yield
+    result = eval("$#{stream}").string
+  ensure
+    eval("$#{stream} = #{stream.upcase}")
+  end
+
+  result
+end
+
+def capture_stdout(&block)
+  original_stdout = $stdout
+  $stdout = fake = StringIO.new
+  begin
+    yield
+  ensure
+    $stdout = original_stdout
+  end
+  fake.string
+end
+
+def capture_stderr(&block)
+  original_stderr = $stderr
+  $stderr = fake = StringIO.new
+  begin
+    yield
+  ensure
+    $stderr = original_stderr
+  end
+  fake.string
+end
+
+# This code was adapted from Ruby on Rails, available under MIT-LICENSE
+# Copyright (c) 2004-2013 David Heinemeier Hansson
+def silence_warnings
+  old_verbose, $VERBOSE = $VERBOSE, nil
+  yield
+ensure
+  $VERBOSE = old_verbose
+end
+
+alias silence capture
+
+VCR.configure do |c|
+  c.cassette_library_dir = "spec/fixtures/vcr_cassettes"
+  c.hook_into :webmock
+  c.ignore_localhost = true
+  c.ignore_hosts 'codeclimate.com'
+  c.configure_rspec_metadata!
+end