Merge branch 'master' into support-rightsidentifier

Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    bolognese (1.6.1)
+    bolognese (1.6.3)
       activesupport (>= 4.2.5)
       benchmark_methods (~> 0.7)
       bibtex-ruby (>= 5.1.0)
@@ -123,25 +123,28 @@ GEM
     rack-test (0.8.3)
       rack (>= 1.0, < 3)
     rake (12.3.3)
-    rdf (3.1.1)
+    rdf (3.1.2)
       hamster (~> 3.0)
       link_header (~> 0.0, >= 0.0.8)
     rdf-aggregate-repo (3.1.0)
       rdf (~> 3.1)
-    rdf-rdfa (3.1.0)
+    rdf-rdfa (3.1.1)
       haml (~> 5.1)
       htmlentities (~> 4.3)
-      rdf (~> 3.1)
+      rdf (~> 3.1, >= 3.1.2)
       rdf-aggregate-repo (~> 3.1)
+      rdf-vocab (~> 3.1, >= 3.1.5)
       rdf-xsd (~> 3.1)
     rdf-rdfxml (3.1.0)
       htmlentities (~> 4.3)
       rdf (~> 3.1)
       rdf-rdfa (~> 3.1)
       rdf-xsd (~> 3.1)
-    rdf-turtle (3.1.0)
+    rdf-turtle (3.1.1)
       ebnf (~> 1.2)
-      rdf (~> 3.1)
+      rdf (~> 3.1, >= 3.1.2)
+    rdf-vocab (3.1.5)
+      rdf (~> 3.1, >= 3.1.2)
     rdf-xsd (3.1.0)
       rdf (~> 3.1)
     rspec (3.9.0)

lib/bolognese/datacite_utils.rb

@@ -172,9 +172,9 @@ def insert_subjects(xml)
     end
 
     def insert_version(xml)
-      return xml unless version.present?
+      return xml unless version_info.present?
 
-      xml.version(version)
+      xml.version(version_info)
     end
 
 

lib/bolognese/metadata.rb

@@ -9,7 +9,7 @@ class Metadata
     attr_accessor :string, :from, :sandbox, :meta, :regenerate, :issue, :show_errors
     attr_reader :doc, :page_start, :page_end
     attr_writer :id, :provider_id, :client_id, :doi, :identifiers, :creators, :contributors, :titles, :publisher, 
-                :rights_list, :dates, :publication_year, :volume, :url, :version,
+                :rights_list, :dates, :publication_year, :volume, :url, :version_info,
                 :subjects, :contributor, :descriptions, :language, :sizes,
                 :formats, :schema_version, :meta, :container, :agency,
                 :format, :funding_references, :state, :geo_locations,
@@ -106,7 +106,7 @@ def initialize(input: nil, from: nil, **options)
         :publication_year,
         :descriptions,
         :rights_list,
-        :version,
+        :version_info,
         :subjects,
         :language,
         :geo_locations,
@@ -189,13 +189,10 @@ def url
       @url ||= meta.fetch("url", nil)
     end
 
-    def version
-      @version ||= meta.fetch("version", nil)
+    def version_info
+      @version_info ||= meta.fetch("version_info", nil) || meta.fetch("version", nil)
     end
 
-    # for backwards compatibility
-    alias_attribute :version_info, :version
-
     def publication_year
       @publication_year ||= meta.fetch("publication_year", nil)
     end

lib/bolognese/metadata_utils.rb

@@ -159,7 +159,7 @@ def citeproc_hsh
         "title" => parse_attributes(titles, content: "title", first: true),
         "URL" => url,
         "copyright" => Array.wrap(rights_list).map { |l| l["rights"] }.first,
-        "version" => version,
+        "version" => version_info
       }.compact.symbolize_keys
     end
 
@@ -181,7 +181,7 @@ def crosscite_hsh
         "identifiers" => identifiers,
         "sizes" => sizes,
         "formats" => formats,
-        "version" => version,
+        "version" => version_info,
         "rights_list" => rights_list,
         "descriptions" => descriptions,
         "geo_locations" => geo_locations,

lib/bolognese/readers/citeproc_reader.rb

@@ -100,8 +100,10 @@ def read_citeproc(string: nil, **options)
         doi = Array.wrap(identifiers).find { |r| r["identifierType"] == "DOI" }.to_h.fetch("identifier", nil)
 
         state = id.present? || read_options.present? ? "findable" : "not_found"
-        subjects = Array.wrap(meta.fetch("categories", nil)).map do |s|
-          { "subject" => s }
+        subjects = Array.wrap(meta.fetch("categories", nil)).reduce([]) do |sum, subject|
+          sum += name_to_fos(subject)
+
+          sum
         end
 
         { "id" => id,
@@ -119,7 +121,7 @@ def read_citeproc(string: nil, **options)
           "publication_year" => publication_year,
           "descriptions" => meta.fetch("abstract", nil).present? ? [{ "description" => sanitize(meta.fetch("abstract")), "descriptionType" => "Abstract" }] : [],
           "rights_list" => rights_list,
-          "version" => meta.fetch("version", nil),
+          "version_info" => meta.fetch("version", nil),
           "subjects" => subjects,
           "state" => state
         }.merge(read_options)

lib/bolognese/readers/codemeta_reader.rb

@@ -57,8 +57,10 @@ def read_codemeta(string: nil, **options)
           "bibtex" => Bolognese::Utils::SO_TO_BIB_TRANSLATIONS[schema_org] || "misc",
           "ris" => Bolognese::Utils::SO_TO_RIS_TRANSLATIONS[schema_org] || "GEN"
         }.compact
-        subjects = Array.wrap(meta.fetch("tags", nil)).map do |s|
-          { "subject" => s }
+        subjects = Array.wrap(meta.fetch("tags", nil)).reduce([]) do |sum, subject|
+          sum += name_to_fos(subject)
+
+          sum
         end
 
         has_title = meta.fetch("title", nil)
@@ -79,7 +81,7 @@ def read_codemeta(string: nil, **options)
           "publication_year" => publication_year,
           "descriptions" => meta.fetch("description", nil).present? ? [{ "description" => sanitize(meta.fetch("description")), "descriptionType" => "Abstract" }] : nil,
           "rights_list" => rights_list,
-          "version" => meta.fetch("version", nil),
+          "version_info" => meta.fetch("version", nil),
           "subjects" => subjects,
           "state" => state
         }.merge(read_options)

lib/bolognese/readers/crossref_reader.rb

@@ -172,7 +172,7 @@ def read_crossref(string: nil, **options)
           "publication_year" => publication_year,
           "descriptions" => crossref_description(bibliographic_metadata),
           "rights_list" => crossref_license(program_metadata),
-          "version" => nil,
+          "version_info" => nil,
           "subjects" => nil,
           "language" => nil,
           "sizes" => nil,

lib/bolognese/readers/datacite_reader.rb

@@ -122,15 +122,17 @@ def read_datacite(string: nil, **options)
             hsh_to_spdx(r)
           end
         end.compact
-        subjects = Array.wrap(meta.dig("subjects", "subject")).map do |k|
-          if k.blank?
-            nil
-          elsif k.is_a?(String)
-            { "subject" => sanitize(k) }
-          elsif k.is_a?(Hash)
-            { "subject" => sanitize(k["__content__"]), "subjectScheme" => k["subjectScheme"], "schemeUri" => k["schemeURI"], "valueUri" => k["valueURI"], "lang" => k["lang"] }.compact
+
+        subjects = Array.wrap(meta.dig("subjects", "subject")).reduce([]) do |sum, subject|
+          if subject.is_a?(String)
+            sum += name_to_fos(subject)
+          elsif subject.is_a?(Hash)
+            sum += hsh_to_fos(subject)
           end
-        end.compact
+
+          sum
+        end.uniq
+
         dates = Array.wrap(meta.dig("dates", "date")).map do |r|
           if r.is_a?(Hash) && date = sanitize(r["__content__"]).presence
             if Date.edtf(date).present? || Bolognese::Utils::UNKNOWN_INFORMATION.key?(date)
@@ -233,7 +235,7 @@ def read_datacite(string: nil, **options)
           "publication_year" => parse_attributes(meta.fetch("publicationYear", nil), first: true).to_s.strip.presence,
           "descriptions" => descriptions,
           "rights_list" => Array.wrap(rights_list),
-          "version" => meta.fetch("version", nil).to_s.presence,
+          "version_info" => meta.fetch("version", nil).to_s.presence,
           "subjects" => subjects,
           "language" => parse_attributes(meta.fetch("language", nil), first: true).to_s.strip.presence,
           "geo_locations" => geo_locations,

lib/bolognese/readers/npm_reader.rb

@@ -105,7 +105,7 @@ def read_npm(string: nil, **options)
           #"publication_year" => publication_year,
           "descriptions" => meta.fetch("description", nil).present? ? [{ "description" => sanitize(meta.fetch("description")), "descriptionType" => "Abstract" }] : [],
           "rights_list" => rights_list,
-          "version" => meta.fetch("version", nil),
+          "version_info" => meta.fetch("version", nil),
           "subjects" => subjects
           #"state" => state
         }.merge(read_options)

lib/bolognese/readers/ris_reader.rb

@@ -82,8 +82,10 @@ def read_ris(string: nil, **options)
           nil
         end
         state = meta.fetch("DO", nil).present? || read_options.present? ? "findable" : "not_found"
-        subjects = Array.wrap(meta.fetch("KW", nil)).map do |s|
-          { "subject" => s }
+        subjects = Array.wrap(meta.fetch("KW", nil)).reduce([]) do |sum, subject|
+          sum += name_to_fos(subject)
+
+          sum
         end
 
         { "id" => id,

lib/bolognese/readers/schema_org_reader.rb

@@ -149,8 +149,13 @@ def read_schema_org(string: nil, **options)
             "geoLocationBox" => geo_location_box
           }.compact
         end
-        subjects = Array.wrap(meta.fetch("keywords", nil).to_s.split(", ")).map do |s|
-          { "subject" => s }
+
+        # handle keywords as array and as comma-separated string
+        subjects = meta.fetch("keywords", nil)
+        subjects = subjects.to_s.split(", ") if subjects.is_a?(String)
+        subjects = Array.wrap(subjects).reduce([]) do |sum, subject|
+          sum += name_to_fos(subject)
+          sum
         end
 
         { "id" => id,
@@ -172,7 +177,7 @@ def read_schema_org(string: nil, **options)
           "dates" => dates,
           "descriptions" => meta.fetch("description", nil).present? ? [{ "description" => sanitize(meta.fetch("description")), "descriptionType" => "Abstract" }] : nil,
           "rights_list" => rights_list,
-          "version" => meta.fetch("version", nil).to_s.presence,
+          "version_info" => meta.fetch("version", nil).to_s.presence,
           "subjects" => subjects,
           "state" => state,
           "schema_version" => meta.fetch("schemaVersion", nil).to_s.presence,

lib/bolognese/utils.rb

@@ -1133,6 +1133,100 @@ def hsh_to_spdx(hsh)
           "rightsIdentifierScheme" => hsh["rightsIdentifierScheme"],
           "schemeUri" => hsh["schemeUri"],
           "lang" => hsh["lang"] }.compact
+
+    def name_to_fos(name)
+      # first find subject in Fields of Science (OECD)
+      fos = JSON.load(File.read(File.expand_path('../../../resources/oecd/fos-mappings.json', __FILE__))).fetch("fosFields")
+
+      subject = fos.find { |l| l["fosLabel"] == name || "FOS: " + l["fosLabel"] == name }
+
+      if subject
+        return [{ 
+          "subject" => sanitize(name) },
+        {
+          "subject" => "FOS: " + subject["fosLabel"],
+          "subjectScheme" => "Fields of Science and Technology (FOS)",
+          "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf"
+        }]
+      end
+
+      # if not found, look in Fields of Research (Australian and New Zealand Standard Research Classification)
+      # and map to Fields of Science. Add an extra entry for the latter
+      fores = JSON.load(File.read(File.expand_path('../../../resources/oecd/for-mappings.json', __FILE__)))
+      for_fields = fores.fetch("forFields")
+      for_disciplines = fores.fetch("forDisciplines")
+
+      subject = for_fields.find { |l| l["forLabel"] == name } ||
+                for_disciplines.find { |l| l["forLabel"] == name }
+
+      if subject
+        [{ 
+          "subject" => sanitize(name) },
+        {
+          "subject" => "FOS: " + subject["fosLabel"],
+          "subjectScheme" => "Fields of Science and Technology (FOS)",
+          "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf"
+        }]
+      else
+        [{ "subject" => sanitize(name) }]
+      end
+    end
+
+    def hsh_to_fos(hsh)
+      # first find subject in Fields of Science (OECD)
+      fos = JSON.load(File.read(File.expand_path('../../../resources/oecd/fos-mappings.json', __FILE__))).fetch("fosFields")
+      subject = fos.find { |l| l["fosLabel"] == hsh["__content__"] || "FOS: " + l["fosLabel"] == hsh["__content__"] }
+
+      if subject
+        return [{ 
+          "subject" => sanitize(hsh["__content__"]), 
+          "subjectScheme" => hsh["subjectScheme"],
+          "schemeUri" => hsh["schemeURI"], 
+          "valueUri" => hsh["valueURI"], 
+          "lang" => hsh["lang"] }.compact,
+        {  
+          "subject" => "FOS: " + subject["fosLabel"],
+          "subjectScheme" => "Fields of Science and Technology (FOS)",
+          "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf" }.compact] 
+      end
+
+      # if not found, look in Fields of Research (Australian and New Zealand Standard Research Classification)
+      # and map to Fields of Science. Add an extra entry for the latter
+      fores = JSON.load(File.read(File.expand_path('../../../resources/oecd/for-mappings.json', __FILE__)))
+      for_fields = fores.fetch("forFields")
+      for_disciplines = fores.fetch("forDisciplines")
+
+      # try to extract forId
+      if hsh["subjectScheme"] == "FOR"
+        for_id = hsh["__content__"].split(" ").first
+        for_id = for_id.rjust(6, "0")        
+
+        subject = for_fields.find { |l| l["forId"] == for_id } ||
+                  for_disciplines.find { |l| l["forId"] == for_id[0..3] }
+      else
+        subject = for_fields.find { |l| l["forLabel"] == hsh["__content__"] } ||
+                  for_disciplines.find { |l| l["forLabel"] == hsh["__content__"] }
+      end
+
+      if subject
+        [{ 
+          "subject" => sanitize(hsh["__content__"]), 
+          "subjectScheme" => hsh["subjectScheme"],
+          "schemeUri" => hsh["schemeURI"], 
+          "valueUri" => hsh["valueURI"], 
+          "lang" => hsh["lang"] }.compact,
+        {
+          "subject" => "FOS: " + subject["fosLabel"],
+          "subjectScheme" => "Fields of Science and Technology (FOS)",
+          "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf"
+        }]
+      else
+        [{ 
+          "subject" => sanitize(hsh["__content__"]), 
+          "subjectScheme" => hsh["subjectScheme"],
+          "schemeUri" => hsh["schemeURI"], 
+          "valueUri" => hsh["valueURI"], 
+          "lang" => hsh["lang"] }.compact]  
       end
     end
   end

lib/bolognese/version.rb

@@ -1,3 +1,3 @@
 module Bolognese
-  VERSION = "1.6.1"
+  VERSION = "1.6.3"
 end

lib/bolognese/writers/codemeta_writer.rb

@@ -15,7 +15,7 @@ def codemeta
           "name" => parse_attributes(titles, content: "title", first: true),
           "authors" => creators,
           "description" => parse_attributes(descriptions, content: "description", first: true),
-          "version" => version,
+          "version" => version_info,
           "tags" => subjects.present? ? Array.wrap(subjects).map { |k| parse_attributes(k, content: "subject", first: true) } : nil,
           "datePublished" => get_date(dates, "Issued"),
           "dateModified" => get_date(dates, "Updated"),

lib/bolognese/writers/jats_writer.rb

@@ -22,7 +22,7 @@ def insert_citation(xml)
         insert_issue(xml) if container.to_h["issue"].present?
         insert_fpage(xml) if container.to_h["firstPage"].present?
         insert_lpage(xml) if container.to_h["lastPage"].present?
-        insert_version(xml) if version.present?
+        insert_version(xml) if version_info.present?
         insert_pub_id(xml)
       end
 
@@ -112,7 +112,7 @@ def insert_lpage(xml)
       end
 
       def insert_version(xml)
-        xml.version(version)
+        xml.version(version_info)
       end
 
       def insert_pub_id(xml)

lib/bolognese/writers/schema_org_writer.rb

@@ -15,7 +15,7 @@ def schema_hsh
           "editor" => to_schema_org_contributors(contributors),
           "description" => parse_attributes(descriptions, content: "description", first: true),
           "license" => Array.wrap(rights_list).map { |l| l["rightsUri"] }.compact.unwrap,
-          "version" => version,
+          "version" => version_info,
           "keywords" => subjects.present? ? Array.wrap(subjects).map { |k| parse_attributes(k, content: "subject", first: true) }.join(", ") : nil,
           "inLanguage" => language,
           "contentSize" => Array.wrap(sizes).unwrap,