bolognese 0.6.4 → 0.6.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 2690851dd5c74b7e9a5b6e0d896b9fdddf0ee447
-  data.tar.gz: 787144fee4b4a236924f6eccd5b70817aec1ae04
+  metadata.gz: 52deb6793101a56d9a824b036aff219ba58327eb
+  data.tar.gz: 9f96c1a7a6920e9395f92969822bc44064fdf179
 SHA512:
-  metadata.gz: b96de50af5318a576b5d2a5f8d17da09bb4bc407137ece77d64f724c6766211360ef50879212c51f36d665766e5d99976344a573237b8fb48f6789d23cfb137c
-  data.tar.gz: bca8c0904a38f753d78ddd214dcadb15f065d823eaba55d3004fea8c20d563b3cb752cdc8cdac25a6881b7a5c5cef89edf448992f2768ffbf45813ab54efa0e1
+  metadata.gz: 893420085b143cff1dd78cbbc5ed96f34cc0497a9a998249076ba2372957bc87c0b0d48873572b10cf628e9b01df8ec0adb6d2580440afcf8c3e8037be6f49bf
+  data.tar.gz: 32378cb92d547a7ecb33f4a69a8e794ca0649a82865552b35794e8f7bb6af14a047fc84a6512cf6dea6df2195664977784a67e263eed1c4fde55d6d6b8b61702

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    bolognese (0.6.4)
+    bolognese (0.6.5)
       activesupport (~> 4.2, >= 4.2.5)
       bibtex-ruby (~> 4.1)
       builder (~> 3.2, >= 3.2.2)

data/lib/bolognese/crossref.rb

@@ -132,14 +132,14 @@ module Bolognese
     end
 
     def name
-      parse_attribute(bibliographic_metadata.dig("titles", "title"))
+      parse_attributes(bibliographic_metadata.dig("titles", "title"))
     end
 
     def alternate_name
       if bibliographic_metadata.fetch("publisher_item", nil).present?
-        parse_attribute(bibliographic_metadata.dig("publisher_item", "item_number"))
+        parse_attributes(bibliographic_metadata.dig("publisher_item", "item_number"))
       else
-        parse_attribute(bibliographic_metadata.fetch("item_number", nil))
+        parse_attributes(bibliographic_metadata.fetch("item_number", nil))
       end
     end
 
@@ -155,7 +155,7 @@ module Bolognese
     def license
       access_indicator = Array.wrap(program_metadata).find { |m| m["name"] == "AccessIndicators" }
       if access_indicator.present?
-        parse_attribute(access_indicator["license_ref"])
+        parse_attributes(access_indicator["license_ref"])
       else
         nil
       end
@@ -173,7 +173,7 @@ module Bolognese
       person = bibliographic_metadata.dig("contributors", "person_name")
       Array.wrap(person).select { |a| a["contributor_role"] == contributor_role }.map do |a|
         { "@type" => "Person",
-          "@id" => parse_attribute(a["ORCID"]),
+          "@id" => parse_attributes(a["ORCID"]),
           "givenName" => a["given_name"],
           "familyName" => a["surname"] }.compact
       end.presence
@@ -214,7 +214,7 @@ module Bolognese
       if journal_metadata.present?
         { "@type" => "Periodical",
           "name" => journal_metadata["full_title"],
-          "issn" => parse_attribute(journal_metadata.fetch("issn", nil)) }.compact
+          "issn" => parse_attributes(journal_metadata.fetch("issn", nil)) }.compact
       else
         nil
       end

data/lib/bolognese/datacite.rb

@@ -86,7 +86,7 @@ module Bolognese
     end
 
     def alternate_name
-      metadata.dig("alternateIdentifiers", "alternateIdentifier", "__content__")
+      parse_attributes(metadata.dig("alternateIdentifiers", "alternateIdentifier"))
     end
 
     def description
@@ -99,7 +99,7 @@ module Bolognese
     end
 
     def license
-      metadata.dig("rightsList", "rights", "rightsURI")
+      parse_attributes(Array.wrap(metadata.dig("rightsList", "rights")), content: "rightsURI")
     end
 
     def keywords
@@ -113,8 +113,8 @@ module Bolognese
     end
 
     def editor
-      editors = metadata.dig("contributors", "contributor")
-      editors = [editors] if editors.is_a?(Hash)
+      editors = Array.wrap(metadata.dig("contributors", "contributor"))
+                     .select { |r| r["contributorType"] == "Editor" }
       get_authors(editors).presence
     end
 
@@ -135,7 +135,7 @@ module Bolognese
 
     def funding_reference
       Array.wrap(metadata.dig("fundingReferences", "fundingReference")).map do |f|
-        funder_id = parse_attribute(f["funderIdentifier"])
+        funder_id = parse_attributes(f["funderIdentifier"])
         { "@type" => "Organization",
           "@id" => normalize_id(funder_id),
           "name" => f["funderName"] }.compact

data/lib/bolognese/datacite_utils.rb

@@ -46,13 +46,14 @@ module Bolognese
     end
 
     def as_datacite
-      if schema.validate(Nokogiri::XML(datacite_xml))
+      if validation_errors.blank?
         datacite_xml
       end
     end
 
     def validation_errors
       @validation_errors ||= schema.validate(Nokogiri::XML(datacite_xml))
+                                   .map { |error| error.to_s }
     end
 
     def insert_work(xml)
@@ -219,7 +220,9 @@ module Bolognese
       return xml unless license.present?
 
       xml.rightsList do
-        xml.rights(LICENSE_NAMES[license], 'rightsURI' => license)
+        Array.wrap(license).each do |lic|
+          xml.rights(LICENSE_NAMES[lic], 'rightsURI' => lic)
+        end
       end
     end
 

data/lib/bolognese/utils.rb

@@ -66,25 +66,16 @@ module Bolognese
       end
     end
 
-    def parse_attributes(element)
-      if element.is_a?(String)
-        element
-      elsif element.is_a?(Hash)
-        element.fetch("__content__", nil)
-      elsif element.is_a?(Array)
-        element.map { |e| e.fetch("__content__", nil) }
-      else
-        nil
-      end
-    end
+    def parse_attributes(element, options={})
+      content = options[:content] || "__content__"
 
-    def parse_attribute(element)
       if element.is_a?(String)
         element
       elsif element.is_a?(Hash)
-        element.fetch("__content__", nil)
+        element.fetch(content, nil)
       elsif element.is_a?(Array)
-        element.first.fetch("__content__", nil)
+        a = element.map { |e| e.fetch(content, nil) }.uniq
+        a.length == 1 ? a.first : a
       else
         nil
       end

data/lib/bolognese/version.rb

@@ -1,3 +1,3 @@
 module Bolognese
-  VERSION = "0.6.4"
+  VERSION = "0.6.5"
 end

data/spec/cli_spec.rb

@@ -150,6 +150,12 @@ describe Bolognese::CLI 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" }
+        expect { subject.convert file }.to output(/http:\/\/datacite.org\/schema\/kernel-4/).to_stdout
+      end
     end
 
     # context "unsupported format" do

data/spec/crossref_spec.rb

@@ -122,7 +122,7 @@ describe Bolognese::Crossref, vcr: true do
       expect(subject.date_modified).to eq("2016-08-02T12:42:41Z")
       expect(subject.page_start).to eq("1")
       expect(subject.page_end).to eq("7")
-      expect(subject.is_part_of).to eq("@type"=>"Periodical", "name"=>"Pulmonary Medicine", "issn"=>"2090-1836")
+      expect(subject.is_part_of).to eq("@type"=>"Periodical", "name"=>"Pulmonary Medicine", "issn"=>["2090-1836", "2090-1844"])
       expect(subject.provider).to eq("@type"=>"Organization", "name"=>"Crossref")
     end
 

data/spec/datacite_spec.rb

@@ -52,7 +52,7 @@ describe Bolognese::Datacite, vcr: true do
       expect(subject.schema_version).to eq("http://datacite.org/schema/kernel-4")
     end
 
-    it "Date" do
+    it "date" do
       id = "https://doi.org/10.4230/lipics.tqc.2013.93"
       subject = Bolognese::Datacite.new(id: id)
       expect(subject.id).to eq("https://doi.org/10.4230/lipics.tqc.2013.93")
@@ -68,7 +68,24 @@ describe Bolognese::Datacite, vcr: true do
       expect(subject.schema_version).to eq("http://datacite.org/schema/kernel-2.1")
     end
 
-    it "Funding schema version 3" do
+    it "multiple licenses" do
+      id = "https://doi.org/10.5281/ZENODO.48440"
+      subject = Bolognese::Datacite.new(id: id)
+      expect(subject.id).to eq("https://doi.org/10.5281/zenodo.48440")
+      expect(subject.type).to eq("SoftwareSourceCode")
+      expect(subject.additional_type).to eq("Software")
+      expect(subject.resource_type_general).to eq("Software")
+      expect(subject.author).to eq([{"@type"=>"Agent", "Name"=>"Kristian Garza"}])
+      expect(subject.name).to eq("Analysis Tools for Crossover Experiment of UI using Choice Architecture")
+      expect(subject.description).to start_with("<p>&nbsp;</p>\n\n<p>This tools are used to analyse the data produced by the Crosssover Experiment")
+      expect(subject.license).to eq(["info:eu-repo/semantics/openAccess", "https://creativecommons.org/licenses/by-nc-sa/4.0/"])
+      expect(subject.date_published).to eq("2016-03-27")
+      expect(subject.publisher).to eq("@type"=>"Organization", "name"=>"Zenodo")
+      expect(subject.provider).to eq("@type"=>"Organization", "name"=>"DataCite")
+      expect(subject.schema_version).to eq("http://datacite.org/schema/kernel-3")
+    end
+
+    it "funding schema version 3" do
       id = "https://doi.org/10.5281/ZENODO.1239"
       subject = Bolognese::Datacite.new(id: id)
       expect(subject.id).to eq("https://doi.org/10.5281/zenodo.1239")
@@ -139,6 +156,13 @@ describe Bolognese::Datacite, vcr: true do
       expect(subject.citation).to eq([{"@type"=>"CreativeWork", "@id"=>"https://doi.org/10.1371/journal.ppat.1000446"}])
       expect(subject.provider).to eq("@type"=>"Organization", "name"=>"DataCite")
     end
+
+    it "missing creator" do
+      string = IO.read(fixture_path + "datacite_missing_creator.xml")
+      subject = Bolognese::Datacite.new(string: string)
+      expect(subject.id).to eq("https://doi.org/10.5438/4k3m-nyvg")
+      expect(subject.validation_errors).to eq(["Element '{http://datacite.org/schema/kernel-4}creators': Missing child element(s). Expected is ( {http://datacite.org/schema/kernel-4}creator )."])
+    end
   end
 
   context "get metadata as datacite xml 4.0" do
@@ -176,7 +200,7 @@ describe Bolognese::Datacite, vcr: true do
       id = "https://doi.org/10.5438/6423"
       subject = Bolognese::Datacite.new(id: id, schema_version: "http://datacite.org/schema/kernel-4")
       expect(subject.id).to eq("https://doi.org/10.5438/6423")
-
+      expect(subject.validation_errors).to be_empty
       datacite = Maremma.from_xml(subject.as_datacite).fetch("resource", {})
       expect(datacite.fetch("xsi:schemaLocation", "").split(" ").first).to eq("http://datacite.org/schema/kernel-4")
       expect(datacite.fetch("fundingReferences")).to eq("fundingReference"=>{"funderName"=>"European Commission", "funderIdentifier"=>{"funderIdentifierType"=>"Crossref Funder ID", "__content__"=>"https://doi.org/10.13039/501100000780"}})

data/spec/fixtures/datacite_missing_creator.xml

@@ -0,0 +1,32 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4/metadata.xsd">
+  <identifier identifierType="DOI">10.5438/4K3M-NYVG</identifier>
+  <titles>
+    <title>Eating your own Dog Food</title>
+  </titles>
+  <publisher>DataCite</publisher>
+  <publicationYear>2016</publicationYear>
+  <resourceType resourceTypeGeneral="Text">BlogPosting</resourceType>
+  <alternateIdentifiers>
+    <alternateIdentifier alternateIdentifierType="Local accession number">MS-49-3632-5083</alternateIdentifier>
+  </alternateIdentifiers>
+  <subjects>
+    <subject>datacite</subject>
+    <subject>doi</subject>
+    <subject>metadata</subject>
+  </subjects>
+  <dates>
+    <date dateType="Created">2016-12-20</date>
+    <date dateType="Issued">2016-12-20</date>
+    <date dateType="Updated">2016-12-20</date>
+  </dates>
+  <relatedIdentifiers>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="References">10.5438/0012</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="References">10.5438/55E5-T5C0</relatedIdentifier>
+    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsPartOf">10.5438/0000-00SS</relatedIdentifier>
+  </relatedIdentifiers>
+  <version>1.0</version>
+  <descriptions>
+    <description descriptionType="Abstract">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...</description>
+  </descriptions>
+</resource>

data/spec/fixtures/vcr_cassettes/Bolognese_Datacite/get_metadata/multiple_licenses.yml

@@ -0,0 +1,186 @@
+---
+http_interactions:
+- request:
+    method: get
+    uri: https://doi.org/10.5281/zenodo.48440
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      User-Agent:
+      - Maremma - https://github.com/datacite/maremma
+      Accept:
+      - application/vnd.datacite.datacite+xml
+  response:
+    status:
+      code: 303
+      message: ''
+    headers:
+      Server:
+      - Apache-Coyote/1.1
+      Vary:
+      - Accept
+      Location:
+      - http://data.datacite.org/10.5281%2Fzenodo.48440
+      Expires:
+      - Wed, 22 Feb 2017 23:30:53 GMT
+      Content-Type:
+      - text/html;charset=utf-8
+      Content-Length:
+      - '179'
+      Date:
+      - Wed, 22 Feb 2017 22:50:12 GMT
+    body:
+      encoding: UTF-8
+      string: |-
+        <html><head><title>Handle Redirect</title></head>
+        <body><a href="http://data.datacite.org/10.5281%2Fzenodo.48440">http://data.datacite.org/10.5281%2Fzenodo.48440</a></body></html>
+    http_version: 
+  recorded_at: Wed, 22 Feb 2017 22:50:13 GMT
+- request:
+    method: get
+    uri: http://data.datacite.org/10.5281%2Fzenodo.48440
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      User-Agent:
+      - Maremma - https://github.com/datacite/maremma
+      Accept:
+      - application/vnd.datacite.datacite+xml
+  response:
+    status:
+      code: 301
+      message: ''
+    headers:
+      Server:
+      - openresty/1.11.2.2
+      Date:
+      - Wed, 22 Feb 2017 22:50:13 GMT
+      Content-Type:
+      - text/html
+      Content-Length:
+      - '191'
+      Connection:
+      - keep-alive
+      Location:
+      - https://data.datacite.org/10.5281%2Fzenodo.48440
+    body:
+      encoding: UTF-8
+      string: "<html>\r\n<head><title>301 Moved Permanently</title></head>\r\n<body
+        bgcolor=\"white\">\r\n<center><h1>301 Moved Permanently</h1></center>\r\n<hr><center>openresty/1.11.2.2</center>\r\n</body>\r\n</html>\r\n"
+    http_version: 
+  recorded_at: Wed, 22 Feb 2017 22:50:13 GMT
+- request:
+    method: get
+    uri: https://data.datacite.org/10.5281%2Fzenodo.48440
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      User-Agent:
+      - Maremma - https://github.com/datacite/maremma
+      Accept:
+      - application/vnd.datacite.datacite+xml
+  response:
+    status:
+      code: 200
+      message: ''
+    headers:
+      Server:
+      - openresty/1.11.2.2
+      Date:
+      - Wed, 22 Feb 2017 22:50:13 GMT
+      Content-Type:
+      - application/vnd.datacite.datacite+xml
+      Content-Length:
+      - '2773'
+      Connection:
+      - keep-alive
+      Cache-Control:
+      - no-transform, max-age=3600
+      Last-Modified:
+      - Mon, 04 Apr 2016 15:04:32 GMT
+      Vary:
+      - Accept
+      Access-Control-Allow-Origin:
+      - "*"
+      Access-Control-Allow-Methods:
+      - GET, POST, OPTIONS
+    body:
+      encoding: UTF-8
+      string: |
+        <resource xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
+          <identifier identifierType="DOI">10.5281/zenodo.48440</identifier>
+          <creators>
+            <creator>
+              <creatorName>Kristian Garza</creatorName>
+            </creator>
+          </creators>
+          <titles>
+            <title>Analysis Tools for Crossover Experiment of UI using Choice Architecture</title>
+          </titles>
+          <publisher>Zenodo</publisher>
+          <publicationYear>2016</publicationYear>
+          <subjects>
+            <subject>choice architecture</subject>
+            <subject>crossover experiment</subject>
+            <subject>hci</subject>
+          </subjects>
+          <dates>
+            <date dateType="Issued">2016-03-27</date>
+          </dates>
+          <resourceType resourceTypeGeneral="Software"/>
+          <alternateIdentifiers>
+            <alternateIdentifier alternateIdentifierType="URL">http://zenodo.org/record/48440</alternateIdentifier>
+          </alternateIdentifiers>
+          <relatedIdentifiers>
+            <relatedIdentifier relationType="IsSupplementTo" relatedIdentifierType="URL">https://github.com/kjgarza/frame_experiment_analysis/tree/v1.0</relatedIdentifier>
+          </relatedIdentifiers>
+          <rightsList>
+            <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
+            <rights rightsURI="https://creativecommons.org/licenses/by-nc-sa/4.0/">Creative Commons Attribution-NonCommercial-ShareAlike</rights>
+          </rightsList>
+          <descriptions>
+            <description descriptionType="Abstract">&lt;p&gt;&amp;nbsp;&lt;/p&gt;
+
+        &lt;p&gt;This tools are used to analyse the data produced by the Crosssover Experiment I designed to test Choice Architecture techniques as UI interventions in a SEEk4Science data catalogue. It contains:&lt;/p&gt;
+
+        &lt;p&gt;- Data structures for the experimental data.&lt;br /&gt;
+        - Visualisation functions&lt;br /&gt;
+        - Analysis functions&lt;/p&gt;
+
+        &lt;p&gt;## Installation&lt;/p&gt;
+
+        &lt;p&gt;- R&lt;br /&gt;
+        - python&lt;br /&gt;
+        - ipython 4&lt;/p&gt;
+
+        &lt;p&gt;Clone and use.&lt;/p&gt;
+
+        &lt;p&gt;## Usage&lt;/p&gt;
+
+        &lt;p&gt;&lt;br /&gt;
+        ```python&lt;br /&gt;
+        source(&amp;#39;parallel_plot.r&amp;#39;)&lt;br /&gt;
+        with(z, parallelset(trt,response, freq=count, alpha=0.2))&lt;br /&gt;
+        ```&lt;/p&gt;
+
+        &lt;p&gt;&lt;br /&gt;
+        ## Contributing&lt;/p&gt;
+
+        &lt;p&gt;1. Fork it!&lt;br /&gt;
+        2. Create your feature branch: `git checkout -b my-new-feature`&lt;br /&gt;
+        3. Commit your changes: `git commit -am &amp;#39;Add some feature&amp;#39;`&lt;br /&gt;
+        4. Push to the branch: `git push origin my-new-feature`&lt;br /&gt;
+        5. Submit a pull request :D&lt;/p&gt;
+
+        &lt;p&gt;&lt;br /&gt;
+        ## License&lt;/p&gt;
+
+        &lt;p&gt;This work supports my PhD Thesis at University of Manchester.&lt;/p&gt;</description>
+          </descriptions>
+        </resource>
+    http_version: 
+  recorded_at: Wed, 22 Feb 2017 22:50:13 GMT
+recorded_with: VCR 3.0.3

data/spec/utils_spec.rb

@@ -41,38 +41,12 @@ describe Bolognese::Crossref, vcr: true do
     it "array" do
       element = [{ "__content__" => "10.5061/DRYAD.8515" }]
       response = subject.parse_attributes(element)
-      expect(response).to eq(["10.5061/DRYAD.8515"])
-    end
-
-    it "nil" do
-      element = nil
-      response = subject.parse_attributes(element)
-      expect(response).to be_nil
-    end
-  end
-
-  context "parse attribute" do
-    it "string" do
-      element = "10.5061/DRYAD.8515"
-      response = subject.parse_attribute(element)
-      expect(response).to eq("10.5061/DRYAD.8515")
-    end
-
-    it "hash" do
-      element = { "__content__" => "10.5061/DRYAD.8515" }
-      response = subject.parse_attribute(element)
-      expect(response).to eq("10.5061/DRYAD.8515")
-    end
-
-    it "array" do
-      element = [{ "__content__" => "10.5061/DRYAD.8515" }]
-      response = subject.parse_attribute(element)
       expect(response).to eq("10.5061/DRYAD.8515")
     end
 
     it "nil" do
       element = nil
-      response = subject.parse_attribute(element)
+      response = subject.parse_attributes(element)
       expect(response).to be_nil
     end
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bolognese
 version: !ruby/object:Gem::Version
-  version: 0.6.4
+  version: 0.6.5
 platform: ruby
 authors:
 - Martin Fenner
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-02-22 00:00:00.000000000 Z
+date: 2017-02-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: maremma
@@ -343,6 +343,7 @@ files:
 - spec/fixtures/crossref.bib
 - spec/fixtures/crossref.xml
 - spec/fixtures/datacite.xml
+- spec/fixtures/datacite_missing_creator.xml
 - spec/fixtures/schema_org.json
 - spec/fixtures/vcr_cassettes/Bolognese_CLI/convert_from_id/crossref/as_bibtex.yml
 - spec/fixtures/vcr_cassettes/Bolognese_CLI/convert_from_id/crossref/as_crossref.yml
@@ -419,6 +420,7 @@ files:
 - spec/fixtures/vcr_cassettes/Bolognese_Datacite/get_metadata/Funding_schema_version_3.yml
 - spec/fixtures/vcr_cassettes/Bolognese_Datacite/get_metadata/Funding_schema_version_4.yml
 - spec/fixtures/vcr_cassettes/Bolognese_Datacite/get_metadata/Schema_org_JSON.yml
+- spec/fixtures/vcr_cassettes/Bolognese_Datacite/get_metadata/multiple_licenses.yml
 - spec/fixtures/vcr_cassettes/Bolognese_Datacite/get_metadata_as_bibtex/BlogPosting.yml
 - spec/fixtures/vcr_cassettes/Bolognese_Datacite/get_metadata_as_bibtex/Dataset.yml
 - spec/fixtures/vcr_cassettes/Bolognese_Datacite/get_metadata_as_datacite_xml_4_0/Dataset.yml