briard 2.0

data/resources/xml.xsd

@@ -0,0 +1,286 @@
+<?xml version='1.0'?>
+<?xml-stylesheet href="../../2008/09/xsd.xsl" type="text/xsl"?>
+<xs:schema targetNamespace="http://www.w3.org/XML/1998/namespace" 
+  xmlns:xs="http://www.w3.org/2001/XMLSchema" 
+  xmlns   ="http://www.w3.org/1999/xhtml"
+  xml:lang="en">
+
+ <xs:annotation>
+  <xs:documentation>
+   <div>
+    <h1>About the XML namespace</h1>
+
+    <div class="bodytext">
+     <p>
+      This schema document describes the XML namespace, in a form
+      suitable for import by other schema documents.
+     </p>
+     <p>
+      See <a href="http://www.w3.org/XML/1998/namespace.html">
+      http://www.w3.org/XML/1998/namespace.html</a> and
+      <a href="http://www.w3.org/TR/REC-xml">
+      http://www.w3.org/TR/REC-xml</a> for information 
+      about this namespace.
+     </p>
+     <p>
+      Note that local names in this namespace are intended to be
+      defined only by the World Wide Web Consortium or its subgroups.
+      The names currently defined in this namespace are listed below.
+      They should not be used with conflicting semantics by any Working
+      Group, specification, or document instance.
+     </p>
+     <p>   
+      See further below in this document for more information about <a
+      href="#usage">how to refer to this schema document from your own
+      XSD schema documents</a> and about <a href="#nsversioning">the
+      namespace-versioning policy governing this schema document</a>.
+     </p>
+    </div>
+   </div>
+  </xs:documentation>
+ </xs:annotation>
+
+ <xs:attribute name="lang">
+  <xs:annotation>
+   <xs:documentation>
+    <div>
+     
+      <h3>lang (as an attribute name)</h3>
+      <p>
+       denotes an attribute whose value
+       is a language code for the natural language of the content of
+       any element; its value is inherited.  This name is reserved
+       by virtue of its definition in the XML specification.</p>
+     
+    </div>
+    <div>
+     <h4>Notes</h4>
+     <p>
+      Attempting to install the relevant ISO 2- and 3-letter
+      codes as the enumerated possible values is probably never
+      going to be a realistic possibility.  
+     </p>
+     <p>
+      See BCP 47 at <a href="http://www.rfc-editor.org/rfc/bcp/bcp47.txt">
+       http://www.rfc-editor.org/rfc/bcp/bcp47.txt</a>
+      and the IANA language subtag registry at
+      <a href="http://www.iana.org/assignments/language-subtag-registry">
+       http://www.iana.org/assignments/language-subtag-registry</a>
+      for further information.
+     </p>
+     <p>
+      The union allows for the 'un-declaration' of xml:lang with
+      the empty string.
+     </p>
+    </div>
+   </xs:documentation>
+  </xs:annotation>
+  <xs:simpleType>
+   <xs:union memberTypes="xs:language">
+    <xs:simpleType>    
+     <xs:restriction base="xs:string">
+      <xs:enumeration value=""/>
+     </xs:restriction>
+    </xs:simpleType>
+   </xs:union>
+  </xs:simpleType>
+ </xs:attribute>
+
+ <xs:attribute name="space">
+  <xs:annotation>
+   <xs:documentation>
+    <div>
+     
+      <h3>space (as an attribute name)</h3>
+      <p>
+       denotes an attribute whose
+       value is a keyword indicating what whitespace processing
+       discipline is intended for the content of the element; its
+       value is inherited.  This name is reserved by virtue of its
+       definition in the XML specification.</p>
+     
+    </div>
+   </xs:documentation>
+  </xs:annotation>
+  <xs:simpleType>
+   <xs:restriction base="xs:NCName">
+    <xs:enumeration value="default"/>
+    <xs:enumeration value="preserve"/>
+   </xs:restriction>
+  </xs:simpleType>
+ </xs:attribute>
+ 
+ <xs:attribute name="base" type="xs:anyURI"> <xs:annotation>
+   <xs:documentation>
+    <div>
+     
+      <h3>base (as an attribute name)</h3>
+      <p>
+       denotes an attribute whose value
+       provides a URI to be used as the base for interpreting any
+       relative URIs in the scope of the element on which it
+       appears; its value is inherited.  This name is reserved
+       by virtue of its definition in the XML Base specification.</p>
+     
+     <p>
+      See <a
+      href="http://www.w3.org/TR/xmlbase/">http://www.w3.org/TR/xmlbase/</a>
+      for information about this attribute.
+     </p>
+    </div>
+   </xs:documentation>
+  </xs:annotation>
+ </xs:attribute>
+ 
+ <xs:attribute name="id" type="xs:ID">
+  <xs:annotation>
+   <xs:documentation>
+    <div>
+     
+      <h3>id (as an attribute name)</h3> 
+      <p>
+       denotes an attribute whose value
+       should be interpreted as if declared to be of type ID.
+       This name is reserved by virtue of its definition in the
+       xml:id specification.</p>
+     
+     <p>
+      See <a
+      href="http://www.w3.org/TR/xml-id/">http://www.w3.org/TR/xml-id/</a>
+      for information about this attribute.
+     </p>
+    </div>
+   </xs:documentation>
+  </xs:annotation>
+ </xs:attribute>
+
+ <xs:attributeGroup name="specialAttrs">
+  <xs:attribute ref="xml:base"/>
+  <xs:attribute ref="xml:lang"/>
+  <xs:attribute ref="xml:space"/>
+  <xs:attribute ref="xml:id"/>
+ </xs:attributeGroup>
+
+ <xs:annotation>
+  <xs:documentation>
+   <div>
+   
+    <h3>Father (in any context at all)</h3> 
+
+    <div class="bodytext">
+     <p>
+      denotes Jon Bosak, the chair of 
+      the original XML Working Group.  This name is reserved by 
+      the following decision of the W3C XML Plenary and 
+      XML Coordination groups:
+     </p>
+     <blockquote>
+       <p>
+	In appreciation for his vision, leadership and
+	dedication the W3C XML Plenary on this 10th day of
+	February, 2000, reserves for Jon Bosak in perpetuity
+	the XML name "xml:Father".
+       </p>
+     </blockquote>
+    </div>
+   </div>
+  </xs:documentation>
+ </xs:annotation>
+
+ <xs:annotation>
+  <xs:documentation>
+   <div xml:id="usage" id="usage">
+    <h2><a name="usage">About this schema document</a></h2>
+
+    <div class="bodytext">
+     <p>
+      This schema defines attributes and an attribute group suitable
+      for use by schemas wishing to allow <code>xml:base</code>,
+      <code>xml:lang</code>, <code>xml:space</code> or
+      <code>xml:id</code> attributes on elements they define.
+     </p>
+     <p>
+      To enable this, such a schema must import this schema for
+      the XML namespace, e.g. as follows:
+     </p>
+     <pre>
+          &lt;schema . . .>
+           . . .
+           &lt;import namespace="http://www.w3.org/XML/1998/namespace"
+                      schemaLocation="http://www.w3.org/2001/xml.xsd"/>
+     </pre>
+     <p>
+      or
+     </p>
+     <pre>
+           &lt;import namespace="http://www.w3.org/XML/1998/namespace"
+                      schemaLocation="http://www.w3.org/2009/01/xml.xsd"/>
+     </pre>
+     <p>
+      Subsequently, qualified reference to any of the attributes or the
+      group defined below will have the desired effect, e.g.
+     </p>
+     <pre>
+          &lt;type . . .>
+           . . .
+           &lt;attributeGroup ref="xml:specialAttrs"/>
+     </pre>
+     <p>
+      will define a type which will schema-validate an instance element
+      with any of those attributes.
+     </p>
+    </div>
+   </div>
+  </xs:documentation>
+ </xs:annotation>
+
+ <xs:annotation>
+  <xs:documentation>
+   <div id="nsversioning" xml:id="nsversioning">
+    <h2><a name="nsversioning">Versioning policy for this schema document</a></h2>
+    <div class="bodytext">
+     <p>
+      In keeping with the XML Schema WG's standard versioning
+      policy, this schema document will persist at
+      <a href="http://www.w3.org/2009/01/xml.xsd">
+       http://www.w3.org/2009/01/xml.xsd</a>.
+     </p>
+     <p>
+      At the date of issue it can also be found at
+      <a href="http://www.w3.org/2001/xml.xsd">
+       http://www.w3.org/2001/xml.xsd</a>.
+     </p>
+     <p>
+      The schema document at that URI may however change in the future,
+      in order to remain compatible with the latest version of XML
+      Schema itself, or with the XML namespace itself.  In other words,
+      if the XML Schema or XML namespaces change, the version of this
+      document at <a href="http://www.w3.org/2001/xml.xsd">
+       http://www.w3.org/2001/xml.xsd 
+      </a> 
+      will change accordingly; the version at 
+      <a href="http://www.w3.org/2009/01/xml.xsd">
+       http://www.w3.org/2009/01/xml.xsd 
+      </a> 
+      will not change.
+     </p>
+     <p>
+      Previous dated (and unchanging) versions of this schema 
+      document are at:
+     </p>
+     <ul>
+      <li><a href="http://www.w3.org/2009/01/xml.xsd">
+	http://www.w3.org/2009/01/xml.xsd</a></li>
+      <li><a href="http://www.w3.org/2007/08/xml.xsd">
+	http://www.w3.org/2007/08/xml.xsd</a></li>
+      <li><a href="http://www.w3.org/2004/10/xml.xsd">
+	http://www.w3.org/2004/10/xml.xsd</a></li>
+      <li><a href="http://www.w3.org/2001/03/xml.xsd">
+	http://www.w3.org/2001/03/xml.xsd</a></li>
+     </ul>
+    </div>
+   </div>
+  </xs:documentation>
+ </xs:annotation>
+
+</xs:schema>

data/spec/array_spec.rb

@@ -0,0 +1,22 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe Array do
+  describe "unwrap" do
+    it "to array" do
+      arr = [1, 2, 3]
+      expect(arr.unwrap).to eq(arr)
+    end
+
+    it "to integer" do
+      arr = [1]
+      expect(arr.unwrap).to eq(1)
+    end
+
+    it "to nil" do
+      arr = []
+      expect(arr.unwrap).to be_nil
+    end
+  end
+end

data/spec/author_utils_spec.rb

@@ -0,0 +1,193 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe Briard::Metadata, vcr: true do
+  let(:input) { "https://doi.org/10.1101/097196" }
+
+  subject { Briard::Metadata.new(input: input, from: "crossref") }
+
+  context "is_personal_name?" do
+    it "has type organization" do
+      author = {"email"=>"info@ucop.edu", "name"=>"University of California, Santa Barbara", "role"=>{"namespace"=>"http://www.ngdc.noaa.gov/metadata/published/xsd/schema/resources/Codelist/gmxCodelists.xml#CI_RoleCode", "roleCode"=>"copyrightHolder"}, "nameType"=>"Organizational" }
+      expect(subject.is_personal_name?(author)).to be false
+    end
+
+    it "has id" do
+      author = {"id"=>"http://orcid.org/0000-0003-1419-2405", "givenName"=>"Martin", "familyName"=>"Fenner", "name"=>"Martin Fenner" }
+      expect(subject.is_personal_name?(author)).to be true
+    end
+
+    it "has orcid id" do
+      author = { "creatorName"=>"Fenner, Martin", "givenName"=>"Martin", "familyName"=>"Fenner", "nameIdentifier"=>{"schemeURI"=>"http://orcid.org/", "nameIdentifierScheme"=>"ORCID", "__content__"=>"0000-0003-1419-2405"}}
+      expect(subject.is_personal_name?(author)).to be true
+    end
+    it "has family name" do
+      author = {"givenName"=>"Martin", "familyName"=>"Fenner", "name"=>"Martin Fenner" }
+      expect(subject.is_personal_name?(author)).to be true
+    end
+
+    it "has comma" do
+      author = {"name"=>"Fenner, Martin" }
+      expect(subject.is_personal_name?(author)).to be true
+    end
+
+    it "has known given name" do
+      author = {"name"=>"Martin Fenner" }
+      expect(subject.is_personal_name?(author)).to be true
+    end
+
+    it "has no info" do
+      author = {"name"=>"M Fenner" }
+      expect(subject.is_personal_name?(author)).to be false
+    end
+  end
+
+  context "get_one_author" do
+    it "has familyName" do
+      input = "https://doi.org/10.5438/4K3M-NYVG"
+      subject = Briard::Metadata.new(input: input, from: "datacite")
+      meta = Maremma.from_xml(subject.raw).fetch("resource", {})
+      response = subject.get_one_author(meta.dig("creators", "creator"))
+      expect(response).to eq("nameIdentifiers" => [{"nameIdentifier"=>"https://orcid.org/0000-0003-1419-2405", "nameIdentifierScheme"=>"ORCID", "schemeUri"=>"https://orcid.org"}], "name"=>"Fenner, Martin", "givenName"=>"Martin", "familyName"=>"Fenner")
+    end
+
+    it "has name in sort-order" do
+      input = "https://doi.org/10.5061/dryad.8515"
+      subject = Briard::Metadata.new(input: input, from: "datacite")
+      meta = Maremma.from_xml(subject.raw).fetch("resource", {})
+      response = subject.get_one_author(meta.dig("creators", "creator").first)
+      expect(response).to eq("nameType"=>"Personal", "name"=>"Ollomo, Benjamin", "givenName"=>"Benjamin", "familyName"=>"Ollomo", "nameIdentifiers" => [], "affiliation" => [{"affiliationIdentifier"=>"https://ror.org/01wyqb997", "affiliationIdentifierScheme"=>"ROR", "name"=>"Centre International de Recherches Médicales de Franceville"}])
+    end
+
+    it "has name in display-order" do
+      input = "https://doi.org/10.5281/ZENODO.48440"
+      subject = Briard::Metadata.new(input: input, from: "datacite")
+      meta = Maremma.from_xml(subject.raw).fetch("resource", {})
+      response = subject.get_one_author(meta.dig("creators", "creator"))
+      expect(response).to eq("nameType"=>"Personal", "name"=>"Garza, Kristian", "givenName"=>"Kristian", "familyName"=>"Garza", "nameIdentifiers" => [], "affiliation" => [])
+    end
+
+    it "has name in display-order with ORCID" do
+      input = "https://doi.org/10.6084/M9.FIGSHARE.4700788"
+      subject = Briard::Metadata.new(input: input, from: "datacite")
+      meta = Maremma.from_xml(subject.raw).fetch("resource", {})
+      response = subject.get_one_author(meta.dig("creators", "creator"))
+      expect(response).to eq("nameType"=>"Personal", "nameIdentifiers" => [{"nameIdentifier"=>"https://orcid.org/0000-0003-4881-1606", "nameIdentifierScheme"=>"ORCID", "schemeUri"=>"https://orcid.org"}], "name"=>"Bedini, Andrea", "givenName"=>"Andrea", "familyName"=>"Bedini", "affiliation" => [])
+    end
+
+    it "has name in Thai" do
+      input = "https://doi.org/10.14457/KMITL.res.2006.17"
+      subject = Briard::Metadata.new(input: input, from: "datacite")
+      meta = Maremma.from_xml(subject.raw).fetch("resource", {})
+      response = subject.get_one_author(meta.dig("creators", "creator"))
+      expect(response).to eq("name"=>"กัญจนา แซ่เตียว", "nameIdentifiers" => [], "affiliation" => [])
+    end
+
+    it "multiple author names in one field" do
+      input = "https://doi.org/10.7910/dvn/eqtqyo"
+      subject = Briard::Metadata.new(input: input, from: "datacite")
+      meta = Maremma.from_xml(subject.raw).fetch("resource", {})
+      response = subject.get_authors(meta.dig("creators", "creator"))
+      expect(response).to eq([{"name" => "Enos, Ryan (Harvard University); Fowler, Anthony (University Of Chicago); Vavreck, Lynn (UCLA)", "nameIdentifiers" => [], "affiliation" => []}])
+    end
+
+    it "hyper-authorship" do
+      input = "https://doi.org/10.17182/HEPDATA.77274.V1"
+      subject = Briard::Metadata.new(input: input, from: "datacite")
+      meta = Maremma.from_xml(subject.raw).fetch("resource", {})
+      response = subject.get_authors(meta.dig("creators", "creator"))
+      expect(response).to eq( [{"affiliation"=>[], "name"=>"ALICE Collaboration", "nameIdentifiers"=>[], "nameType"=>"Organizational"}])
+    end
+
+    it "is organization" do
+      author = {"email"=>"info@ucop.edu", "creatorName"=> { "__content__" => "University of California, Santa Barbara", "nameType" => "Organizational" }, "role"=>{"namespace"=>"http://www.ngdc.noaa.gov/metadata/published/xsd/schema/resources/Codelist/gmxCodelists.xml#CI_RoleCode", "roleCode"=>"copyrightHolder"} }
+      response = subject.get_one_author(author)
+      expect(response).to eq("nameType"=>"Organizational", "name"=>"University Of California, Santa Barbara", "nameIdentifiers" => [], "affiliation" => [])
+    end
+
+    it "name with affiliation" do
+      input = "10.11588/DIGLIT.6130"
+      subject = Briard::Metadata.new(input: input, from: "datacite")
+      meta = Maremma.from_xml(subject.raw).fetch("resource", {})
+      response = subject.get_one_author(meta.dig("creators", "creator"))
+      expect(response).to eq("nameType"=>"Organizational", "name"=>"Dr. Störi, Kunstsalon", "nameIdentifiers" => [], "affiliation" => [])
+    end
+
+    it "name with affiliation and country" do
+      input = "10.16910/jemr.9.1.2"
+      subject = Briard::Metadata.new(input: input, from: "crossref")
+      response = subject.get_one_author(subject.creators.first)
+      expect(response).to eq("familyName" => "Eraslan",
+        "givenName" => "Sukru",
+        "name" => "Eraslan, Sukru")
+    end
+
+    it "name with role" do
+      input = "10.14463/GBV:873056442"
+      subject = Briard::Metadata.new(input: input, from: "datacite")
+      meta = Maremma.from_xml(subject.raw).fetch("resource", {})
+      response = subject.get_one_author(meta.dig("creators", "creator").first)
+      expect(response).to eq("affiliation" => [],
+        "familyName" => "Schumacher",
+        "givenName" => "Heinrich Christian",
+        "name" => "Schumacher, Heinrich Christian",
+        "nameIdentifiers" => [{"nameIdentifier"=>"http://d-nb.info/gnd/118611593", "nameIdentifierScheme"=>"GND", "schemeUri"=>"http://d-nb.info/gnd/"}],
+        "nameType" => "Personal")
+    end
+
+    it "multiple name_identifier" do
+      input = "10.24350/CIRM.V.19028803"
+      subject = Briard::Metadata.new(input: input, from: "datacite")
+      meta = Maremma.from_xml(subject.raw).fetch("resource", {})
+      response = subject.get_one_author(meta.dig("creators", "creator"))
+      expect(response).to eq("nameType"=>"Personal", "name"=>"Dubos, Thomas", "givenName"=>"Thomas", "familyName"=>"Dubos", "affiliation" => [{"name"=>"École Polytechnique Laboratoire de Météorologie Dynamique"}], "nameIdentifiers" => [{"nameIdentifier"=>"http://isni.org/isni/0000 0003 5752 6882", "nameIdentifierScheme"=>"ISNI", "schemeUri"=>"http://isni.org/isni/"}, {"nameIdentifier"=>"https://orcid.org/0000-0003-4514-4211", "nameIdentifierScheme"=>"ORCID", "schemeUri"=>"https://orcid.org"}])
+    end
+
+    it "nameType organizational" do
+      input = fixture_path + 'gtex.xml'
+      subject = Briard::Metadata.new(input: input, from: "datacite")
+      meta = Maremma.from_xml(subject.raw).fetch("resource", {})
+      response = subject.get_one_author(meta.dig("creators", "creator"))
+      expect(response).to eq("nameType"=>"Organizational", "name"=>"The GTEx Consortium", "nameIdentifiers" => [], "affiliation" => [])
+    end
+
+    it "only familyName and givenName" do
+      input = "https://doi.pangaea.de/10.1594/PANGAEA.836178"
+      subject = Briard::Metadata.new(input: input, from: "schema_org")
+      expect(subject.creators.first).to eq("nameType" => "Personal", "name"=>"Johansson, Emma", "givenName"=>"Emma", "familyName"=>"Johansson")
+    end
+  end
+
+  context "authors_as_string" do
+    let(:author_with_organization) { [{"type"=>"Person",
+                                       "id"=>"http://orcid.org/0000-0003-0077-4738",
+                                       "name"=>"Matt Jones"},
+                                      {"type"=>"Person",
+                                       "id"=>"http://orcid.org/0000-0002-2192-403X",
+                                       "name"=>"Peter Slaughter"},
+                                      {"type"=>"Organization",
+                                       "id"=>"http://orcid.org/0000-0002-3957-2474",
+                                       "name"=>"University of California, Santa Barbara"}] }
+
+    it "author" do
+      response = subject.authors_as_string(subject.creators)
+      expect(response).to eq("Fenner, Martin and Crosas, Merc?? and Grethe, Jeffrey and Kennedy, David and Hermjakob, Henning and Rocca-Serra, Philippe and Durand, Gustavo and Berjon, Robin and Karcher, Sebastian and Martone, Maryann and Clark, Timothy")
+    end
+
+    it "single author" do
+      response = subject.authors_as_string(subject.creators.first)
+      expect(response).to eq("Fenner, Martin")
+    end
+
+    it "no author" do
+      response = subject.authors_as_string(nil)
+      expect(response).to be_nil
+    end
+
+    it "with organization" do
+      response = subject.authors_as_string(author_with_organization)
+      expect(response).to eq("Matt Jones and Peter Slaughter and {University of California, Santa Barbara}")
+    end
+  end
+end