bolognese 0.4.2 → 0.4.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: bf10f195bc1be468c9dddb8fa414f071b9389752
-  data.tar.gz: 0adbaa0ec469a01e4f68c59c21dacc5e2d4440e9
+  metadata.gz: 6f368d772caba68f6a931b069036edd1fac3e15b
+  data.tar.gz: 85312771808c2971a7b10004f5b77cf6f6276952
 SHA512:
-  metadata.gz: 0b29dc6ca64a5fd2f5c2cbfe4ac393a5eddbaac1334d0f6d07c9462a5471f81103855faa70f923d29de19fe184c50bbc19acc26863e0585c8549c4b7b694f6b1
-  data.tar.gz: 8cf3694170ba6a2ecdb80ee3507bdafbcbaff9e05f5cd3e3ce439f29d42c07b5501298850e9f05f9bc9ce0ba09bc95368a20f784a20a55ad58a5e27324531a7c
+  metadata.gz: ed95b4b96238556e09a234defd26b402d72055204f31f4b9a0411774a5cca13079a91aeb80cccf3f812599a48b94c37fcffa1181ad324d730799894aafd37256
+  data.tar.gz: 2f33f803a3a5ef8b1e957db914225f55fc460a60f5706406f9b43ce3ec5a9542c99fd393267723aed7d5c400b2213f6fb48c334a23d8d8ab1044b1e158b712ca

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    bolognese (0.4.2)
+    bolognese (0.4.3)
       activesupport (~> 4.2, >= 4.2.5)
       builder (~> 3.2, >= 3.2.2)
       dotenv (~> 2.1, >= 2.1.1)
@@ -115,4 +115,4 @@ DEPENDENCIES
   webmock (~> 1.22, >= 1.22.3)
 
 BUNDLED WITH
-   1.14.4
+   1.12.5

data/README.md

@@ -1,3 +1,5 @@
+[![Build Status](https://travis-ci.org/datacite/bolognese.svg?branch=master)](https://travis-ci.org/datacite/bolognese)
+
 # bolognese
 
 Command-line utility for conversion of DOI metadata from and to [schema.org](https://schema.org) in JSON-LD.

data/lib/bolognese/cli.rb

@@ -30,8 +30,12 @@ module Bolognese
         puts Crossref.new(id: pid).as_schema_org
       when provider == "datacite" && options[:as] == "datacite"
         puts Datacite.new(id: pid).raw
-      when "datacite"
+      when provider == "datacite"
         puts Datacite.new(id: pid).as_schema_org
+      when provider == "schema_org" && options[:as] == "datacite"
+        puts SchemaOrg.new(id: pid).as_datacite
+      when provider == "schema_org"
+        puts SchemaOrg.new(id: pid).as_schema_org
       else
         puts "not implemented"
       end

data/lib/bolognese/crossref.rb

@@ -184,21 +184,25 @@ module Bolognese
       end
     end
 
+    def container_title
+      is_part_of.fetch("name", nil)
+    end
+
+    def has_part
+
+    end
+
     def citation
        citations = bibliographic_metadata.dig("citation_list", "citation")
-       Array(citations).map do |c|
+       Array.wrap(citations).map do |c|
          { "@type" => "CreativeWork",
-           "@id" => normalize_doi(c["doi"]),
+           "@id" => normalize_url(c["doi"]),
            "position" => c["key"],
            "name" => c["article_title"],
            "datePublished" => c["cYear"] }.compact
        end.presence
     end
 
-    def related_identifiers
-
-    end
-
     def provider
       { "@type" => "Organization",
         "name" => "Crossref" }
@@ -220,6 +224,7 @@ module Bolognese
         "pageStart" => page_start,
         "pageEnd" => page_end,
         "isPartOf" => is_part_of,
+        "hasPart" => has_part,
         "citation" => citation,
         "provider" => provider
       }.compact

data/lib/bolognese/datacite.rb

@@ -88,6 +88,10 @@ module Bolognese
       get_authors(authors)
     end
 
+    def editor
+
+    end
+
     def version
       metadata.fetch("version", nil)
     end
@@ -134,7 +138,12 @@ module Bolognese
     end
 
     def publisher
-      metadata.fetch("publisher")
+      { "@type" => "Organization",
+        "name" => metadata.fetch("publisher") }
+    end
+
+    def container_title
+      publisher.fetch("name", nil)
     end
 
     def provider

data/lib/bolognese/datacite_utils.rb

@@ -1,11 +1,5 @@
 module Bolognese
   module DataciteUtils
-    #   @resource_type = metadata.fetch("resource_type", nil)
-    #   @rights_list = metadata.fetch("rights_list", nil)
-    #   @descriptions = metadata.fetch("descriptions", nil)
-    #   @contributors = metadata.fetch("contributors", nil)
-    #   @alternate_identifier = metadata.fetch("alternate_identifier", nil)
-    #   @media = metadata.fetch("media", nil)
 
     SO_TO_DC_TRANSLATIONS = {
       "VideoObject" => "Audiovisual",
@@ -23,10 +17,10 @@ module Bolognese
     LICENSE_NAMES = {
       "http://creativecommons.org/publicdomain/zero/1.0/" => "Public Domain (CC0 1.0)",
       "http://creativecommons.org/licenses/by/3.0/" => "Creative Commons Attribution 3.0 (CC-BY 3.0)",
-      "https://creativecommons.org/licenses/by/4.0/" => "Creative Commons Attribution 4.0 (CC-BY 4.0)",
-      "https://creativecommons.org/licenses/by-nc/4.0/" => "Creative Commons Attribution Noncommercial 4.0 (CC-BY-NC 4.0)",
-      "https://creativecommons.org/licenses/by-sa/4.0/" => "Creative Commons Attribution Share Alike 4.0 (CC-BY-SA 4.0)",
-      "https://creativecommons.org/licenses/by-nc-nd/4.0/" => "Creative Commons Attribution Noncommercial No Derivaties 4.0 (CC-BY-NC-ND 4.0)"
+      "http://creativecommons.org/licenses/by/4.0/" => "Creative Commons Attribution 4.0 (CC-BY 4.0)",
+      "http://creativecommons.org/licenses/by-nc/4.0/" => "Creative Commons Attribution Noncommercial 4.0 (CC-BY-NC 4.0)",
+      "http://creativecommons.org/licenses/by-sa/4.0/" => "Creative Commons Attribution Share Alike 4.0 (CC-BY-SA 4.0)",
+      "http://creativecommons.org/licenses/by-nc-nd/4.0/" => "Creative Commons Attribution Noncommercial No Derivaties 4.0 (CC-BY-NC-ND 4.0)"
     }
 
     SCHEMA = File.expand_path("../../../resources/kernel-4.0/metadata.xsd", __FILE__)
@@ -76,7 +70,7 @@ module Bolognese
 
     def insert_creators(xml)
       xml.creators do
-        Array(author).each do |creator|
+        Array.wrap(author).each do |creator|
           xml.creator do
             insert_person(xml, creator, "creator")
           end
@@ -88,7 +82,7 @@ module Bolognese
       return xml unless editor.present?
 
       xml.contributors do
-        Array(editor).each do |contributor|
+        Array.wrap(editor).each do |contributor|
           xml.contributor("contributorType" => "Editor") do
             insert_person(xml, contributor, "contributor")
           end
@@ -97,12 +91,11 @@ module Bolognese
     end
 
     def insert_person(xml, person, type)
-      person_name = [person["familyName"], person["givenName"]].compact.join(", ").presence || person["name"]
+      person_name = person["name"].presence || [person["familyName"], person["givenName"]].compact.join(", ")
 
-      xml.send(:'creatorName', person_name) if type == "creator"
-      xml.send(:'contributorName', person_name) if type == "contributor"
-      xml.send(:'givenName', person["givenName"]) if person["givenName"].present?
-      xml.send(:'familyName', person["familyName"]) if person["familyName"].present?
+      xml.send(type + "Name", person_name)
+      xml.givenName(person["givenName"]) if person["givenName"].present?
+      xml.familyName(person["familyName"]) if person["familyName"].present?
       xml.nameIdentifier(person["@id"], 'schemeURI' => 'http://orcid.org/', 'nameIdentifierScheme' => 'ORCID') if person["@id"].present?
     end
 
@@ -117,7 +110,7 @@ module Bolognese
     end
 
     def insert_publisher(xml)
-      xml.publisher(is_part_of["name"])
+      xml.publisher(container_title)
     end
 
     def insert_publication_year(xml)
@@ -166,20 +159,37 @@ module Bolognese
       xml.version(version)
     end
 
-        def is_part_of
-      related_identifiers("IsPartOf").first
-    end
+    def rel_identifiers
+      ipo = Array.wrap(is_part_of).map do |i|
+        {
+          "text" => i["@id"],
+          "related_identifier_type" => validate_url(i["@id"]),
+          "relation_type" => "IsPartOf" }
+      end.select { |i| i["related_identifier_type"].present? }
+
+      hp = Array.wrap(has_part).map do |i|
+        {
+          "text" => i["@id"],
+          "related_identifier_type" => validate_url(i["@id"]),
+          "relation_type" => "HasPart" }
+      end.select { |i| i["related_identifier_type"].present? }
+
+      c = Array.wrap(citation).map do |i|
+        {
+          "text" => i["@id"],
+          "related_identifier_type" => validate_url(i["@id"]),
+          "relation_type" => "References" }
+      end.select { |i| i["related_identifier_type"].present? }
 
-    def related_identifiers
-      Array.wrap(is_part_of) + Array(has_part) + Array(citation)
+      ipo + hp + c
     end
 
     def insert_related_identifiers(xml)
-      return xml unless related_identifiers.present?
+      return xml unless rel_identifiers.present?
 
       xml.relatedIdentifiers do
-        related_identifiers.each do |related_identifier|
-          xml.relatedIdentifier(related_identifier[:value], 'relatedIdentifierType' => related_identifier[:related_identifier_type], 'relationType' => related_identifier[:relation_type])
+        rel_identifiers.each do |related_identifier|
+          xml.relatedIdentifier(related_identifier["text"], 'relatedIdentifierType' => related_identifier["related_identifier_type"], 'relationType' => related_identifier["relation_type"])
         end
       end
     end

data/lib/bolognese/schema_org.rb

@@ -79,6 +79,10 @@ module Bolognese
       Array(metadata.fetch("author", nil)).map { |a| a.except("name") }
     end
 
+    def editor
+      Array(metadata.fetch("editor", nil)).map { |a| a.except("name") }
+    end
+
     def description
       metadata.fetch("description", nil)
     end
@@ -127,6 +131,14 @@ module Bolognese
       metadata.fetch("publisher", nil)
     end
 
+    def container_title
+      if publisher.is_a?(Hash)
+        publisher.fetch("name", nil)
+      elsif publisher.is_a?(String)
+        publisher
+      end
+    end
+
     def provider
       metadata.fetch("provider", nil)
     end
@@ -139,6 +151,7 @@ module Bolognese
         "name" => name,
         "alternateName" => alternate_name,
         "author" => author,
+        "editor" => editor,
         "description" => description,
         "license" => license,
         "version" => version,

data/lib/bolognese/utils.rb

@@ -20,6 +20,14 @@ module Bolognese
       Array(/\A(?:http:\/\/orcid\.org\/)?(\d{4}-\d{4}-\d{4}-\d{3}[0-9X]+)\z/.match(orcid)).last
     end
 
+    def validate_url(str)
+      if /\A(?:(http|https):\/\/(dx\.)?doi.org\/)?(doi:)?(10\.\d{4,5}\/.+)\z/.match(str)
+        "DOI"
+      elsif /\A(http|https):\/\//.match(str)
+        "URL"
+      end
+    end
+
     def parse_attributes(element)
       if element.is_a?(String)
         element

data/lib/bolognese/version.rb

@@ -1,3 +1,3 @@
 module Bolognese
-  VERSION = "0.4.2"
+  VERSION = "0.4.3"
 end

data/spec/cli_spec.rb

@@ -38,5 +38,19 @@ describe Bolognese::CLI do
         expect { subject.read id }.to output(/http:\/\/datacite.org\/schema\/kernel-3/).to_stdout
       end
     end
+
+    context "schema_org" do
+      let(:id) { "https://blog.datacite.org/eating-your-own-dog-food" }
+
+      it 'as schema_org' do
+        subject.options = { as: "schema_org" }
+        expect { subject.read id }.to output(/datacite, doi, metadata, featured/).to_stdout
+      end
+
+      it 'as datacite' do
+        subject.options = { as: "datacite" }
+        expect { subject.read id }.to output(/http:\/\/datacite.org\/schema\/kernel-4/).to_stdout
+      end
+    end
   end
 end

data/spec/crossref_spec.rb

@@ -163,13 +163,14 @@ describe Bolognese::Crossref, vcr: true do
   end
 
   context "get metadata as datacite xml" do
-    it "DOI with data citation" do
+    it "with data citation" do
       expect(subject.validation_errors).to be_empty
       datacite = Maremma.from_xml(subject.as_datacite).fetch("resource", {})
       expect(datacite.dig("titles", "title")).to eq("Automated quantitative histology reveals vascular morphodynamics during Arabidopsis hypocotyl secondary growth")
+      expect(datacite.dig("relatedIdentifiers", "relatedIdentifier").count).to eq(25)
     end
 
-    it "DOI with ORCID ID" do
+    it "with ORCID ID" do
       id = "https://doi.org/10.1155/2012/291294"
       subject = Bolognese::Crossref.new(id: id)
       expect(subject.validation_errors).to be_empty
@@ -177,5 +178,13 @@ describe Bolognese::Crossref, vcr: true do
       expect(datacite.dig("creators", "creator").count).to eq(7)
       expect(datacite.dig("creators", "creator").first).to eq("creatorName"=>"Thanassi, Wendy", "givenName"=>"Wendy", "familyName"=>"Thanassi")
     end
+
+    it "with editor" do
+      id = "https://doi.org/10.1371/journal.pone.0000030"
+      subject = Bolognese::Crossref.new(id: id)
+      expect(subject.validation_errors).to be_empty
+      datacite = Maremma.from_xml(subject.as_datacite).fetch("resource", {})
+      expect(datacite.dig("contributors", "contributor")).to eq("contributorType"=>"Editor", "contributorName"=>"Janbon, Guilhem", "givenName"=>"Guilhem", "familyName"=>"Janbon")
+    end
   end
 end

data/spec/datacite_spec.rb

@@ -25,6 +25,7 @@ describe Bolognese::Datacite, vcr: true do
       expect(subject.has_part).to eq([{"@type"=>"CreativeWork", "@id"=>"https://doi.org/10.5061/dryad.8515/1"},
                                       {"@type"=>"CreativeWork", "@id"=>"https://doi.org/10.5061/dryad.8515/2"}])
       expect(subject.citation).to eq([{"@type"=>"CreativeWork", "@id"=>"https://doi.org/10.1371/journal.ppat.1000446"}])
+      expect(subject.publisher).to eq("@type"=>"Organization", "name"=>"Dryad Digital Repository")
       expect(subject.provider).to eq("@type"=>"Organization", "name"=>"DataCite")
     end
 
@@ -43,6 +44,7 @@ describe Bolognese::Datacite, vcr: true do
       expect(subject.is_part_of).to eq("@type"=>"CreativeWork", "@id"=>"https://doi.org/10.5438/0000-00ss")
       expect(subject.citation).to eq([{"@type"=>"CreativeWork", "@id"=>"https://doi.org/10.5438/0012"},
                                       {"@type"=>"CreativeWork", "@id"=>"https://doi.org/10.5438/55e5-t5c0"}])
+      expect(subject.publisher).to eq("@type"=>"Organization", "name"=>"DataCite")
       expect(subject.provider).to eq("@type"=>"Organization", "name"=>"DataCite")
     end
 
@@ -56,6 +58,7 @@ describe Bolognese::Datacite, vcr: true do
       expect(subject.name).to eq("The Minimum Size of Qubit Unextendible Product Bases")
       expect(subject.description).to start_with("We investigate the problem of constructing unextendible product bases in the qubit case")
       expect(subject.date_published).to eq("2013")
+      expect(subject.publisher).to eq("@type"=>"Organization", "name"=>"Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik GmbH, Wadern/Saarbruecken, Germany")
       expect(subject.provider).to eq("@type"=>"Organization", "name"=>"DataCite")
     end
   end

data/spec/datacite_utils_spec.rb

@@ -0,0 +1,159 @@
+require 'spec_helper'
+
+describe Bolognese::Datacite, vcr: true do
+  let(:id) { "https://doi.org/10.5061/DRYAD.8515" }
+
+  subject { Bolognese::Datacite.new(id: id) }
+
+  context "insert_identifier" do
+    it "doi" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_identifier(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response["identifier"]).to eq("identifierType"=>"DOI", "text"=>"10.5061/DRYAD.8515")
+    end
+  end
+
+  context "insert_creators" do
+    it "insert" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_creators(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.dig("creators", "creator").first).to eq("creatorName"=>"Ollomo, Benjamin", "givenName"=>"Benjamin", "familyName"=>"Ollomo")
+    end
+  end
+
+  context "insert_contributors" do
+    it "none" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_contributors(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response).to be_nil
+    end
+  end
+
+  context "insert_person" do
+    it "creator only name" do
+      person = { "name" => "Carberry, Josiah" }
+      type = "creator"
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_person(xml, person, type) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response).to eq("creatorName"=>"Carberry, Josiah")
+    end
+
+    # it "creator given and family name" do
+    #   person = { "givenName" => "Josiah", "familyName" => "Carberry" }
+    #   type = "creator"
+    #   xml = Nokogiri::XML::Builder.new { |xml| subject.insert_person(xml, person, type) }.to_xml
+    #   response = Maremma.from_xml(xml)
+    #   expect(response).to eq("creatorName"=>"Carberry, Josiah")
+    # end
+  end
+
+  context "insert_titles" do
+    it "insert" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_titles(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.dig("titles", "title")).to eq("Data from: A new malaria agent in African hominids.")
+    end
+  end
+
+  context "insert_publisher" do
+    it "insert" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_publisher(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response["publisher"]).to eq("Dryad Digital Repository")
+    end
+  end
+
+  context "insert_publication_year" do
+    it "insert" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_publication_year(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response["publicationYear"]).to eq("2011")
+    end
+  end
+
+  context "insert_resource_type" do
+    it "insert" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_resource_type(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response["resourceType"]).to eq("resourceTypeGeneral"=>"Dataset", "text"=>"DataPackage")
+    end
+  end
+
+  context "insert_alternate_identifiers" do
+    it "insert" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_alternate_identifiers(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.dig("alternateIdentifiers", "alternateIdentifier")).to eq("alternateIdentifierType"=>"Local accession number", "text"=>"Ollomo B, Durand P, Prugnolle F, Douzery EJP, Arnathau C, Nkoghe D, Leroy E, Renaud F (2009) A new malaria agent in African hominids. PLoS Pathogens 5(5): e1000446.")
+    end
+  end
+
+  context "insert_dates" do
+    it "insert" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_dates(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.dig("dates", "date")).to eq("dateType"=>"Issued", "text"=>"2011")
+    end
+  end
+
+  context "insert_subjects" do
+    it "insert" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_subjects(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.dig("subjects", "subject")).to eq(["Phylogeny", "Malaria", "Parasites", "Taxonomy", "Mitochondrial genome", "Africa", "Plasmodium"])
+    end
+  end
+
+  context "insert_version" do
+    it "insert" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_version(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.fetch("version", nil)).to eq("1")
+    end
+  end
+
+  context "insert_related_identifiers" do
+    it "rel_identifiers" do
+      expect(subject.rel_identifiers).to eq([{"text"=>"https://doi.org/10.5061/dryad.8515/1",
+                                              "related_identifier_type"=>"DOI",
+                                              "relation_type"=>"HasPart"},
+                                             {"text"=>"https://doi.org/10.5061/dryad.8515/2",
+                                              "related_identifier_type"=>"DOI",
+                                              "relation_type"=>"HasPart"},
+                                             {"text"=>"https://doi.org/10.1371/journal.ppat.1000446",
+                                              "related_identifier_type"=>"DOI",
+                                              "relation_type"=>"References"}])
+    end
+
+    it "insert" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_related_identifiers(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.dig("relatedIdentifiers", "relatedIdentifier")).to eq([{"relatedIdentifierType"=>"DOI",
+                                                                              "relationType"=>"HasPart",
+                                                                              "text"=>"https://doi.org/10.5061/dryad.8515/1"},
+                                                                             {"relatedIdentifierType"=>"DOI",
+                                                                              "relationType"=>"HasPart",
+                                                                              "text"=>"https://doi.org/10.5061/dryad.8515/2"},
+                                                                             {"relatedIdentifierType"=>"DOI",
+                                                                              "relationType"=>"References",
+                                                                              "text"=>"https://doi.org/10.1371/journal.ppat.1000446"}])
+    end
+  end
+
+  context "insert_rights_list" do
+    it "insert" do
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_rights_list(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.dig("rightsList", "rights")).to eq("rightsURI"=>"http://creativecommons.org/publicdomain/zero/1.0/", "text"=>"Public Domain (CC0 1.0)")
+    end
+  end
+
+  context "insert_descriptions" do
+    it "insert" do
+      id = "https://doi.org/10.5438/4K3M-NYVG"
+      subject = Bolognese::Datacite.new(id: id)
+      xml = Nokogiri::XML::Builder.new { |xml| subject.insert_descriptions(xml) }.to_xml
+      response = Maremma.from_xml(xml)
+      expect(response.dig("descriptions", "description")).to eq("descriptionType" => "Abstract", "text" => "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...")
+    end
+  end
+end