bolognese 1.5.19 → 1.6.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9f12f43e3a56ef075609d39fab403da351db40d2517ce8af31d945275a98f785
-  data.tar.gz: d8f7e1240112ab75a299b5d750dd6218e2f03eb67d4ea14d5c978696d85984ec
+  metadata.gz: 42cbc43f26aa6dd2044b02555d97077aa592b2ad298a3a4381cd1a8ca8100f2b
+  data.tar.gz: a61172b20d5318dfb921429d5946fe807d71d9951bebc5a7397fe705105d1df9
 SHA512:
-  metadata.gz: 35d704991da3b2b84b4d30d02d206adff835e45d5dc887ea5cb85fcab5568c5b0a95a214f2a23de770d47f8f731773286ae81ae33a9bd43fcd04ae403301789b
-  data.tar.gz: ef9fbd252cbe2b1e7c868c574ea8518b75b38063f9d47e629cda4e119d8174dfaa39c1b08c7ab43ae43b83dbd1262d6ec91a5b7dae087005ca60ff995c410f70
+  metadata.gz: b378e7868ce5d7be3f304cf68016cd0c274a972941813973047d0e03f98a4efd5e4fafd660f576a42505fcad1c660a2c8cd8b51d88d9920d112a699e46f9882c
+  data.tar.gz: d29615c3446981b5f63da5c9aea4529ca40042fe89f723dddd27c4a46e3fa077075cb3113ee74d330c11dc01c7ae76122da37e7250f8da7a07e732e19d3144d0

data/.gitignore

@@ -55,3 +55,5 @@ coverage/
 .env.*
 !.env.example
 !.env.travis
+
+.vscode

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    bolognese (1.5.19)
+    bolognese (1.6.3)
       activesupport (>= 4.2.5)
       benchmark_methods (~> 0.7)
       bibtex-ruby (>= 5.1.0)
@@ -30,12 +30,12 @@ PATH
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (6.0.2.2)
+    activesupport (6.0.3.1)
       concurrent-ruby (~> 1.0, >= 1.0.2)
       i18n (>= 0.7, < 2)
       minitest (~> 5.1)
       tzinfo (~> 1.1)
-      zeitwerk (~> 2.2)
+      zeitwerk (~> 2.2, >= 2.2.2)
     addressable (2.7.0)
       public_suffix (>= 2.0.2, < 5.0)
     benchmark_methods (0.7)
@@ -105,7 +105,7 @@ GEM
       oj (>= 2.8.3)
       oj_mimic_json (~> 1.0, >= 1.0.1)
     mini_portile2 (2.4.0)
-    minitest (5.14.0)
+    minitest (5.14.1)
     multi_json (1.14.1)
     multipart-post (2.1.1)
     namae (1.0.1)
@@ -123,40 +123,43 @@ 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)
       rspec-core (~> 3.9.0)
       rspec-expectations (~> 3.9.0)
       rspec-mocks (~> 3.9.0)
-    rspec-core (3.9.1)
-      rspec-support (~> 3.9.1)
-    rspec-expectations (3.9.1)
+    rspec-core (3.9.2)
+      rspec-support (~> 3.9.3)
+    rspec-expectations (3.9.2)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.9.0)
     rspec-mocks (3.9.1)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.9.0)
-    rspec-support (3.9.2)
+    rspec-support (3.9.3)
     rspec-xsd (0.1.0)
       nokogiri (~> 1.6)
       rspec (~> 3)

data/lib/bolognese/datacite_utils.rb

@@ -28,12 +28,14 @@ module Bolognese
       insert_publisher(xml)
       insert_publication_year(xml)
       insert_resource_type(xml)
-      insert_alternate_identifiers(xml)
       insert_subjects(xml)
-      insert_language(xml)
       insert_contributors(xml)
       insert_dates(xml)
+      insert_language(xml)
+      insert_alternate_identifiers(xml)
       insert_related_identifiers(xml)
+      insert_sizes(xml)
+      insert_formats(xml)
       insert_version(xml)
       insert_rights_list(xml)
       insert_descriptions(xml)
@@ -201,6 +203,22 @@ module Bolognese
       end
     end
 
+    def insert_sizes(xml)
+      xml.sizes do
+        Array.wrap(sizes).each do |s|
+          xml.size(s)
+        end
+      end
+    end
+
+    def insert_formats(xml)
+      xml.formats do
+        Array.wrap(formats).each do |f|
+          xml.format(f)
+        end
+      end
+    end
+
     def insert_rights_list(xml)
       return xml unless rights_list.present?
 
@@ -214,7 +232,13 @@ module Bolognese
             r["rightsUri"] = normalize_id(rights)
           end
 
-          attributes = { 'rightsURI' => r["rightsUri"], 'xml:lang' => r["lang"] }.compact
+          attributes = { 
+            "rightsURI" => r["rightsUri"],
+            "rightsIdentifier" => r["rightsIdentifier"],
+            "rightsIdentifierScheme" => r["rightsIdentifierScheme"],
+            "schemeURI" => r["schemeUri"],
+            "xml:lang" => r["lang"] 
+          }.compact
 
           xml.rights(r["rights"], attributes)
         end

data/lib/bolognese/metadata_utils.rb

@@ -158,6 +158,7 @@ module Bolognese
         "publisher" => publisher,
         "title" => parse_attributes(titles, content: "title", first: true),
         "URL" => url,
+        "copyright" => Array.wrap(rights_list).map { |l| l["rights"] }.first,
         "version" => version_info
       }.compact.symbolize_keys
     end

data/lib/bolognese/readers/bibtex_reader.rb

@@ -76,6 +76,7 @@ module Bolognese
                     "dateType" => "Issued" }]
                 end
         publication_year =  meta.try(:date).present? ? meta.date.to_s[0..3] : nil
+        rights_list = meta.try(:copyright).present? ? [hsh_to_spdx("rightsURI" => meta[:copyright])] : []
 
         { "id" => normalize_doi(doi),
           "types" => types,
@@ -90,7 +91,7 @@ module Bolognese
           "dates" => dates,
           "publication_year" => publication_year,
           "descriptions" => meta.try(:abstract).present? ? [{ "description" => meta.try(:abstract) && sanitize(meta.abstract.to_s).presence, "descriptionType" => "Abstract" }] : [],
-          "rights_list" =>  meta.try(:copyright).present? ? [{ "rightsUri" => meta.try(:copyright).to_s.presence }.compact] : [],
+          "rights_list" => rights_list,
           "state" => state
         }.merge(read_options)
       end

data/lib/bolognese/readers/citeproc_reader.rb

@@ -60,7 +60,7 @@ module Bolognese
                 end
         publication_year = get_date_from_date_parts(meta.fetch("issued", nil)).to_s[0..3]
         rights_list = if meta.fetch("copyright", nil)
-                        [{ "rightsUri" => normalize_url(meta.fetch("copyright")) }.compact]
+                        [hsh_to_spdx("rightsURI" => meta.fetch("copyright"))]
                       end
         related_identifiers = if meta.fetch("container-title", nil).present? && meta.fetch("ISSN", nil).present?
                                 [{ "type" => "Periodical",
@@ -100,8 +100,10 @@ module Bolognese
         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,

data/lib/bolognese/readers/codemeta_reader.rb

@@ -57,13 +57,15 @@ module Bolognese
           "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)
-
         titles =  has_title.nil? ?  [{ "title" => meta.fetch("name", nil) }] : [{ "title" => has_title }]  
+        rights_list = meta.fetch("licenseId", nil).present? ? [hsh_to_spdx("rightsIdentifier" => meta.fetch("licenseId"))] : nil
 
         { "id" => id,
           "types" => types,
@@ -78,7 +80,7 @@ module Bolognese
           "dates" => dates,
           "publication_year" => publication_year,
           "descriptions" => meta.fetch("description", nil).present? ? [{ "description" => sanitize(meta.fetch("description")), "descriptionType" => "Abstract" }] : nil,
-          "rights_list" => [{ "rightsUri" => meta.fetch("license", nil) }.compact],
+          "rights_list" => rights_list,
           "version_info" => meta.fetch("version", nil),
           "subjects" => subjects,
           "state" => state

data/lib/bolognese/readers/crossref_reader.rb

@@ -211,7 +211,7 @@ module Bolognese
         access_indicator = Array.wrap(program_metadata).find { |m| m["name"] == "AccessIndicators" }
         if access_indicator.present?
           Array.wrap(access_indicator["license_ref"]).map do |license|
-            { "rightsUri" => normalize_url(parse_attributes(license)) }
+            hsh_to_spdx("rightsURI" => parse_attributes(license))
           end.uniq
         else
           []

data/lib/bolognese/readers/datacite_reader.rb

@@ -93,7 +93,7 @@ module Bolognese
           "bibtex" => Bolognese::Utils::CR_TO_BIB_TRANSLATIONS[resource_type.to_s.underscore.camelcase] || Bolognese::Utils::SO_TO_BIB_TRANSLATIONS[schema_org] || "misc",
           "ris" => Bolognese::Utils::CR_TO_RIS_TRANSLATIONS[resource_type.to_s.underscore.camelcase] || Bolognese::Utils::DC_TO_RIS_TRANSLATIONS[resource_type_general.to_s.dasherize] || "GEN"
         }.compact
-        
+
         titles = Array.wrap(meta.dig("titles", "title")).map do |r|
           if r.blank?
             nil
@@ -117,20 +117,22 @@ module Bolognese
           if r.blank?
             nil
           elsif r.is_a?(String)
-            { "rights" => r }
+            name_to_spdx(r)
           elsif r.is_a?(Hash)
-            { "rights" => r["__content__"], "rightsUri" => normalize_url(r["rightsURI"]), "lang" => r["lang"] }.compact
+            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)
@@ -164,12 +166,15 @@ module Bolognese
         funding_references = Array.wrap(meta.dig("fundingReferences", "fundingReference")).compact.map do |fr|
           scheme_uri = parse_attributes(fr["funderIdentifier"], content: "schemeURI")
           funder_identifier = parse_attributes(fr["funderIdentifier"])
-          funder_identifier = !funder_identifier.to_s.start_with?("https://","http://") && scheme_uri.present? ? normalize_id(scheme_uri + funder_identifier) : normalize_id(funder_identifier)
-          
+          funder_identifier_type = parse_attributes(fr["funderIdentifier"], content: "funderIdentifierType")
+          if funder_identifier_type != "Other"
+            funder_identifier = !funder_identifier.to_s.start_with?("https://","http://") && scheme_uri.present? ? normalize_id(scheme_uri + funder_identifier) : normalize_id(funder_identifier)
+          end
+
           {
             "funderName" => fr["funderName"],
             "funderIdentifier" => funder_identifier,
-            "funderIdentifierType" => parse_attributes(fr["funderIdentifier"], content: "funderIdentifierType"),
+            "funderIdentifierType" => funder_identifier_type,
             "awardNumber" => parse_attributes(fr["awardNumber"]),
             "awardUri" => parse_attributes(fr["awardNumber"], content: "awardURI"),
             "awardTitle" => fr["awardTitle"] }.compact
@@ -181,7 +186,7 @@ module Bolognese
             rid = ri["__content__"]
           end
 
-          { 
+          {
             "relatedIdentifier" => rid,
             "relatedIdentifierType" => ri["relatedIdentifierType"],
             "relationType" => ri["relationType"],

data/lib/bolognese/readers/ris_reader.rb

@@ -82,8 +82,10 @@ module Bolognese
           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,

data/lib/bolognese/readers/schema_org_reader.rb

@@ -107,10 +107,9 @@ module Bolognese
           Array.wrap(schema_org_is_supplement_to(meta)) +
           Array.wrap(schema_org_is_supplemented_by(meta))
 
-        rights_list = [{
-          "rightsUri" => parse_attributes(meta.fetch("license", nil), content: "id", first: true),
-          "rights" => parse_attributes(meta.fetch("license", nil), content: "name", first: true)
-        }]
+        rights_list = Array.wrap(meta.fetch("license", nil)).compact.map do |rl|
+          hsh_to_spdx("__content__" => rl["name"], "rightsURI" => rl["id"])
+        end
 
         funding_references = Array.wrap(meta.fetch("funder", nil)).compact.map do |fr|
           if fr["@id"].present?
@@ -150,8 +149,13 @@ module Bolognese
             "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,

data/lib/bolognese/utils.rb

@@ -2,13 +2,44 @@
 
 module Bolognese
   module Utils
-    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)",
-      "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 Derivatives 4.0 (CC-BY-NC-ND 4.0)"
+    NORMALIZED_LICENSES = {
+      "https://creativecommons.org/licenses/by/1.0" => "https://creativecommons.org/licenses/by/1.0/legalcode",
+      "https://creativecommons.org/licenses/by/2.0" => "https://creativecommons.org/licenses/by/2.0/legalcode",
+      "https://creativecommons.org/licenses/by/2.5" => "https://creativecommons.org/licenses/by/2.5/legalcode",
+      "https://creativecommons.org/licenses/by/3.0" => "https://creativecommons.org/licenses/by/3.0/legalcode",
+      "https://creativecommons.org/licenses/by/4.0" => "https://creativecommons.org/licenses/by/4.0/legalcode",
+      "https://creativecommons.org/licenses/by-nc/1.0" => "https://creativecommons.org/licenses/by-nc/1.0/legalcode",
+      "https://creativecommons.org/licenses/by-nc/2.0" => "https://creativecommons.org/licenses/by-nc/2.0/legalcode",
+      "https://creativecommons.org/licenses/by-nc/2.5" => "https://creativecommons.org/licenses/by-nc/2.5/legalcode",
+      "https://creativecommons.org/licenses/by-nc/3.0" => "https://creativecommons.org/licenses/by-nc/3.0/legalcode",
+      "https://creativecommons.org/licenses/by-nc/4.0" => "https://creativecommons.org/licenses/by-nc/4.0/legalcode",
+      "https://creativecommons.org/licenses/by-nd-nc/1.0" => "https://creativecommons.org/licenses/by-nd-nc/1.0/legalcode",
+      "https://creativecommons.org/licenses/by-nd-nc/2.0" => "https://creativecommons.org/licenses/by-nd-nc/2.0/legalcode",
+      "https://creativecommons.org/licenses/by-nd-nc/2.5" => "https://creativecommons.org/licenses/by-nd-nc/2.5/legalcode",
+      "https://creativecommons.org/licenses/by-nd-nc/3.0" => "https://creativecommons.org/licenses/by-nd-nc/3.0/legalcode",
+      "https://creativecommons.org/licenses/by-nd-nc/4.0" => "https://creativecommons.org/licenses/by-nd-nc/4.0/legalcode",
+      "https://creativecommons.org/licenses/by-nc-sa/1.0" => "https://creativecommons.org/licenses/by-nc-sa/1.0/legalcode",
+      "https://creativecommons.org/licenses/by-nc-sa/2.0" => "https://creativecommons.org/licenses/by-nc-sa/2.0/legalcode",
+      "https://creativecommons.org/licenses/by-nc-sa/2.5" => "https://creativecommons.org/licenses/by-nc-sa/2.5/legalcode",
+      "https://creativecommons.org/licenses/by-nc-sa/3.0" => "https://creativecommons.org/licenses/by-nc-sa/3.0/legalcode",
+      "https://creativecommons.org/licenses/by-nc-sa/4.0" => "https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode",
+      "https://creativecommons.org/licenses/by-nd/1.0" => "https://creativecommons.org/licenses/by-nd/1.0/legalcode",
+      "https://creativecommons.org/licenses/by-nd/2.0" => "https://creativecommons.org/licenses/by-nd/2.0/legalcode",
+      "https://creativecommons.org/licenses/by-nd/2.5" => "https://creativecommons.org/licenses/by-nd/2.5/legalcode",
+      "https://creativecommons.org/licenses/by-nd/3.0" => "https://creativecommons.org/licenses/by-nd/3.0/legalcode",
+      "https://creativecommons.org/licenses/by-nd/4.0" => "https://creativecommons.org/licenses/by-nd/2.0/legalcode",
+      "https://creativecommons.org/licenses/by-sa/1.0" => "https://creativecommons.org/licenses/by-sa/1.0/legalcode",
+      "https://creativecommons.org/licenses/by-sa/2.0" => "https://creativecommons.org/licenses/by-sa/2.0/legalcode",
+      "https://creativecommons.org/licenses/by-sa/2.5" => "https://creativecommons.org/licenses/by-sa/2.5/legalcode",
+      "https://creativecommons.org/licenses/by-sa/3.0" => "https://creativecommons.org/licenses/by-sa/3.0/legalcode",
+      "https://creativecommons.org/licenses/by-sa/4.0" => "https://creativecommons.org/licenses/by-sa/4.0/legalcode",
+      "https://creativecommons.org/licenses/by-nc-nd/1.0" => "https://creativecommons.org/licenses/by-nc-nd/1.0/legalcode",
+      "https://creativecommons.org/licenses/by-nc-nd/2.0" => "https://creativecommons.org/licenses/by-nc-nd/2.0/legalcode",
+      "https://creativecommons.org/licenses/by-nc-nd/2.5" => "https://creativecommons.org/licenses/by-nc-nd/2.5/legalcode",
+      "https://creativecommons.org/licenses/by-nc-nd/3.0" => "https://creativecommons.org/licenses/by-nc-nd/3.0/legalcode",
+      "https://creativecommons.org/licenses/by-nc-nd/4.0" => "https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode",
+      "https://creativecommons.org/licenses/publicdomain" => "https://creativecommons.org/licenses/publicdomain/",
+      "https://creativecommons.org/publicdomain/zero/1.0" => "https://creativecommons.org/publicdomain/zero/1.0/legalcode",
     }
 
     DC_TO_SO_TRANSLATIONS = {
@@ -475,7 +506,7 @@ module Bolognese
       nil
     end
 
-    def normalize_url(id)
+    def normalize_url(id, options={})
       return nil unless id.present?
 
       # handle info URIs
@@ -485,13 +516,23 @@ module Bolognese
       uri = Addressable::URI.parse(id)
 
       return nil unless uri && uri.host && %w(http https ftp).include?(uri.scheme)
+  
+      # optionally turn into https URL
+      uri.scheme = "https" if options[:https]
 
       # clean up URL
-      PostRank::URI.clean(id)
+      uri.path = PostRank::URI.clean(uri.path)
+
+      uri.to_s
     rescue Addressable::URI::InvalidURIError
       nil
     end
 
+    def normalize_cc_url(id)
+      id = normalize_url(id, https: true)
+      NORMALIZED_LICENSES.fetch(id, id)
+    end
+
     def normalize_orcid(orcid)
       orcid = validate_orcid(orcid)
       return nil unless orcid.present?
@@ -1056,5 +1097,139 @@ module Bolognese
       error_array
     end
 
+    def name_to_spdx(name)
+      spdx = JSON.load(File.read(File.expand_path('../../../resources/spdx/licenses.json', __FILE__))).fetch("licenses")
+      license = spdx.find { |l| l["name"] == name || l["licenseId"] == name || l["seeAlso"].first == normalize_cc_url(name) }
+
+      if license
+        {
+          "rights" => license["name"],
+          "rightsUri" => license["seeAlso"].first,
+          "rightsIdentifier" => license["licenseId"],
+          "rightsIdentifierScheme" => "SPDX",
+          "schemeUri" => "https://spdx.org/licenses/" }.compact
+      else
+        { "rights" => name }
+      end
+    end
+
+    def hsh_to_spdx(hsh)
+      spdx = JSON.load(File.read(File.expand_path('../../../resources/spdx/licenses.json', __FILE__))).fetch("licenses")
+      license = spdx.find { |l| l["licenseId"] == hsh["rightsIdentifier"] || l["seeAlso"].first == normalize_cc_url(hsh["rightsURI"]) || l["name"] == hsh["rights"] || l["seeAlso"].first == normalize_cc_url(hsh["rights"]) }
+
+      if license
+        {
+          "rights" => license["name"],
+          "rightsUri" => license["seeAlso"].first,
+          "rightsIdentifier" => license["licenseId"],
+          "rightsIdentifierScheme" => "SPDX",
+          "schemeUri" => "https://spdx.org/licenses/",
+          "lang" => hsh["lang"] }.compact
+      else
+        {
+          "rights" => hsh["__content__"],
+          "rightsUri" => hsh["rightsURI"],
+          "rightsIdentifier" => hsh["rightsIdentifier"],
+          "rightsIdentifierScheme" => hsh["rightsIdentifierScheme"],
+          "schemeUri" => hsh["schemeUri"],
+          "lang" => hsh["lang"] }.compact
+      end
+    end
+
+    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
 end