Merge pull request #92 from datacite/support-rightsidentifier

Adding support for spdx rightsidentifier

lib/bolognese/datacite_utils.rb

@@ -232,7 +232,13 @@ def insert_rights_list(xml)
             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

lib/bolognese/metadata_utils.rb

@@ -158,6 +158,7 @@ def citeproc_hsh
         "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

lib/bolognese/readers/bibtex_reader.rb

@@ -76,6 +76,7 @@ def read_bibtex(string: nil, **options)
                     "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 @@ def read_bibtex(string: nil, **options)
           "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

lib/bolognese/readers/citeproc_reader.rb

@@ -60,7 +60,7 @@ def read_citeproc(string: nil, **options)
                 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",

lib/bolognese/readers/codemeta_reader.rb

@@ -64,8 +64,8 @@ def read_codemeta(string: nil, **options)
         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,
@@ -80,7 +80,7 @@ def read_codemeta(string: nil, **options)
           "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

lib/bolognese/readers/crossref_reader.rb

@@ -211,7 +211,7 @@ def crossref_license(program_metadata)
         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
           []

lib/bolognese/readers/datacite_reader.rb

@@ -117,9 +117,9 @@ def read_datacite(string: nil, **options)
           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
 

lib/bolognese/readers/schema_org_reader.rb

@@ -107,10 +107,9 @@ def read_schema_org(string: nil, **options)
           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?

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 @@ def normalize_id(id, options={})
       nil
     end
 
-    def normalize_url(id)
+    def normalize_url(id, options={})
       return nil unless id.present?
 
       # handle info URIs
@@ -485,13 +516,23 @@ def normalize_url(id)
       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?
@@ -1056,6 +1097,45 @@ def jsonlint(json)
       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")

lib/bolognese/version.rb

@@ -1,3 +1,3 @@
 module Bolognese
-  VERSION = "1.6.3"
+  VERSION = "1.6.4"
 end

lib/bolognese/writers/bibtex_writer.rb

@@ -22,7 +22,8 @@ def bibtex
           issue: container.to_h["issue"],
           pages: pages,
           publisher: publisher,
-          year: publication_year
+          year: publication_year,
+          copyright: Array.wrap(rights_list).map { |l| l["rights"] }.first,
         }.compact
         BibTeX::Entry.new(bib).to_s
       end

lib/bolognese/writers/codemeta_writer.rb

@@ -19,7 +19,8 @@ def codemeta
           "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"),
-          "publisher" => publisher
+          "publisher" => publisher,
+          "license" => Array.wrap(rights_list).map { |l| l["rightsUri"] }.compact.unwrap,
         }.compact
         JSON.pretty_generate hsh.presence
       end