bolognese 1.9.9 → 2.6.1

data/lib/bolognese/utils.rb

@@ -2,6 +2,10 @@
 
 module Bolognese
   module Utils
+    class << self
+      include Utils
+    end
+
     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",
@@ -28,7 +32,7 @@ module Bolognese
       "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-nd/4.0" => "https://creativecommons.org/licenses/by-nd/4.0/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",
@@ -63,7 +67,9 @@ module Bolognese
       "OutputManagementPlan" => nil,
       "PeerReview" => "Review",
       "PhysicalObject" => nil,
+      "Poster" => "Poster",
       "Preprint" => nil,
+      "Presentation" => "PresentationDigitalDocument",
       "Report" => "Report",
       "Service" => "Service",
       "Software" => "SoftwareSourceCode",
@@ -74,7 +80,9 @@ module Bolognese
       "Other" => "CreativeWork",
       # not part of DataCite schema, but used internally
       "Periodical" => "Periodical",
-      "DataCatalog" => "DataCatalog"
+      "DataCatalog" => "DataCatalog",
+      "Award" => "Grant",
+      "Project" => "Project"
     }
 
     DC_TO_CP_TRANSLATIONS = {
@@ -97,7 +105,9 @@ module Bolognese
       "OutputManagementPlan" => nil,
       "PeerReview" => "review",
       "PhysicalObject" => nil,
+      "Poster" => "document",
       "Preprint" => nil,
+      "Presentation" => "presentation",
       "Report" => "report",
       "Service" => nil,
       "Sound" => "song",
@@ -274,6 +284,8 @@ module Bolognese
       "Event" => "Event",
       "ImageObject" => "Image",
       "Movie" => "Audiovisual",
+      "Poster" => "Poster",
+      "PresentationDigitalDocument" => "Presentation",
       "PublicationIssue" => "Text",
       "Report" => "Report",
       "ScholarlyArticle" => "Text",
@@ -320,6 +332,8 @@ module Bolognese
       "Event" => nil,
       "ImageObject" => "graphic",
       "Movie" => "motion_picture",
+      "Poster" => "document",
+      "PresentationDigitalDocument" => "presentation",
       "PublicationIssue" => nil,
       "Report" => "report",
       "ScholarlyArticle" => "article-journal",
@@ -342,8 +356,10 @@ module Bolognese
       "Event" => nil,
       "ImageObject" => "FIGURE",
       "Movie" => "MPCT",
-      "Report" => "RPRT",
+      "Poster" => "GEN",
+      "PresentationDigitalDocument" => "SLIDE",
       "PublicationIssue" => nil,
+      "Report" => "RPRT",
       "ScholarlyArticle" => "JOUR",
       "Service" => nil,
       "SoftwareSourceCode" => "COMP",
@@ -386,8 +402,8 @@ module Bolognese
       "BookChapter" => "CHAP",
       "Collection" => nil,
       "ComputationalNotebook" => "COMP",
-      "ConferencePaper" => nil,
-      "ConferenceProceeding" => nil,
+      "ConferencePaper" => "CPAPER",
+      "ConferenceProceeding" => "CONF",
       "DataPaper" => nil,
       "Dataset" => "DATA",
       "Dissertation" => "THES",
@@ -400,7 +416,9 @@ module Bolognese
       "OutputManagementPlan" => nil,
       "PeerReview" => nil,
       "PhysicalObject" => nil,
+      "Poster" => "GEN",
       "Preprint" => nil,
+      "Presentation" => "SLIDE",
       "Report" => "RRPT",
       "Service" => nil,
       "Software" => "COMP",
@@ -413,7 +431,7 @@ module Bolognese
 
     RIS_TO_DC_TRANSLATIONS = {
       "BLOG" => "Text",
-      "GEN" => "Text",
+      "GEN" => "Poster",
       "CTLG" => "Collection",
       "DATA" => "Dataset",
       "FIGURE" => "Image",
@@ -422,7 +440,8 @@ module Bolognese
       "JOUR" => "JournalArticle",
       "COMP" => "Software",
       "VIDEO" => "Audiovisual",
-      "ELEC" => "Text"
+      "ELEC" => "Text",
+      "SLIDE" => "Presentation"
     }
 
     BIB_TO_DC_TRANSLATIONS = {
@@ -446,7 +465,9 @@ module Bolognese
       "motion_picture" => "Audiovisual",
       "article-journal" => "JournalArticle",
       "broadcast" => "Audiovisual",
-      "webpage" => "Text"
+      "webpage" => "Text",
+      "document" => "Poster",
+      "presentation" => "Presentation"
     }
 
     SO_TO_BIB_TRANSLATIONS = {
@@ -462,6 +483,8 @@ module Bolognese
       "Event" => "misc",
       "ImageObject" => "misc",
       "Movie" => "misc",
+      "Poster" => "misc",
+      "PresentationDigitalDocument" => "misc",
       "PublicationIssue" => "misc",
       "ScholarlyArticle" => "article",
       "Service" => "misc",
@@ -484,6 +507,28 @@ module Bolognese
       ":etal" => "too numerous to list (et alia)"
     }
 
+    RESOURCE_PATHS = {
+      spdx: 'spdx/licenses.json',
+      fos: 'oecd/fos-mappings.json',
+      for: 'oecd/for-mappings.json',
+      dfg: 'oecd/dfg-mappings.json'
+    }
+
+    def resources_dir_path
+      File.expand_path('../../../resources', __FILE__) + '/'
+    end
+
+    def resource_file( extra_path )
+      File.read(resources_dir_path + extra_path)
+    end
+
+    def resource_json( resource_symbol )
+      if RESOURCE_PATHS.keys().include?(resource_symbol)
+        JSON.load(resource_file(RESOURCE_PATHS[resource_symbol]))
+      end
+    end
+
+
     def find_from_format(id: nil, string: nil, ext: nil, filename: nil)
       if id.present?
         find_from_format_by_id(id)
@@ -574,10 +619,14 @@ module Bolognese
     end
 
     def validate_orcid(orcid)
-      orcid = Array(/\A(?:(http|https):\/\/(www\.)?orcid\.org\/)?(\d{4}[[:space:]-]\d{4}[[:space:]-]\d{4}[[:space:]-]\d{3}[0-9X]+)\z/.match(orcid)).last
+      orcid = Array(/\A(?:(?:http|https):\/\/(?:(?:www|sandbox)?\.)?orcid\.org\/)?(\d{4}[[:space:]-]\d{4}[[:space:]-]\d{4}[[:space:]-]\d{3}[0-9X]+)\/{0,1}\z/.match(orcid)).last
       orcid.gsub(/[[:space:]]/, "-") if orcid.present?
     end
 
+    def validate_ror(ror)
+      Array(/^(?:(?:(?:http|https):\/\/)?ror\.org\/)?(0\w{6}\d{2})\/{0,1}$/.match(ror)).last
+    end
+
     def validate_orcid_scheme(orcid_scheme)
       Array(/\A(http|https):\/\/(www\.)?(orcid\.org)/.match(orcid_scheme)).last
     end
@@ -611,7 +660,7 @@ module Bolognese
       return nil unless id.present?
 
       # check for valid DOI
-      doi = normalize_doi(id, options)
+      doi = DoiUtils::normalize_doi(id, options)
       return doi if doi.present?
 
       # check for valid HTTP uri
@@ -619,7 +668,7 @@ module Bolognese
       return nil unless uri && uri.host && %w(http https).include?(uri.scheme)
 
       # clean up URL
-      PostRank::URI.clean(id)
+      normalize_uri_with_path_cleanup(uri)
     rescue Addressable::URI::InvalidURIError
       nil
     end
@@ -639,9 +688,7 @@ module Bolognese
       uri.scheme = "https" if options[:https]
 
       # clean up URL
-      uri.path = PostRank::URI.clean(uri.path)
-
-      uri.to_s
+      normalize_uri_with_path_cleanup(uri)
     rescue Addressable::URI::InvalidURIError
       nil
     end
@@ -659,11 +706,19 @@ module Bolognese
       "https://orcid.org/" + Addressable::URI.encode(orcid)
     end
 
+    def normalize_ror(ror)
+      ror = validate_ror(ror)
+      return nil unless ror.present?
+
+      # turn ROR into URL
+      "https://ror.org/" + Addressable::URI.encode(ror)
+    end
+
     def normalize_ids(ids: nil, relation_type: nil)
       Array.wrap(ids).select { |idx| idx["@id"].present? }.map do |idx|
         id = normalize_id(idx["@id"])
-        related_identifier_type = doi_from_url(id).present? ? "DOI" : "URL"
-        id = doi_from_url(id) || id
+        related_identifier_type = DoiUtils::doi_from_url(id).present? ? "DOI" : "URL"
+        id = DoiUtils::doi_from_url(id) || id
 
         { "relatedIdentifier" => id,
           "relationType" => relation_type,
@@ -735,6 +790,14 @@ module Bolognese
       nil
     end
 
+    def normalize_publisher(publisher)
+      if publisher.respond_to?(:to_hash)
+        publisher
+      elsif publisher.respond_to?(:to_str)
+        { "name" => publisher }
+      end
+    end
+
     def to_datacite_json(element, options={})
       a = Array.wrap(element).map do |e|
         e.inject({}) {|h, (k,v)| h[k.dasherize] = v; h }
@@ -779,7 +842,8 @@ module Bolognese
 
     def to_schema_org_contributors(element)
       element = Array.wrap(element).map do |c|
-        c["affiliation"] = Array.wrap(c["affiliation"]).map do |a|
+        transformed_c = c.dup
+        transformed_c["affiliation"] = Array.wrap(c["affiliation"]).map do |a|
           if a.is_a?(String)
             name = a
             affiliation_identifier = nil
@@ -793,10 +857,10 @@ module Bolognese
             "@id" => affiliation_identifier,
             "name" => name }.compact
         end.unwrap
-        c["@type"] = c["nameType"].present? ? c["nameType"][0..-3] : nil
-        c["@id"] = Array.wrap(c["nameIdentifiers"]).first.to_h.fetch("nameIdentifier", nil)
-        c["name"] = c["familyName"].present? ? [c["givenName"], c["familyName"]].join(" ") : c["name"]
-        c.except("nameIdentifiers", "nameType").compact
+        transformed_c["@type"] = c["nameType"].present? ? c["nameType"][0..-3] : nil
+        transformed_c["@id"] = Array.wrap(c["nameIdentifiers"]).first.to_h.fetch("nameIdentifier", nil)
+        transformed_c["name"] = c["familyName"].present? ? [c["givenName"], c["familyName"]].join(" ") : c["name"]
+        transformed_c.except("nameIdentifiers", "nameType").compact
       end.unwrap
     end
 
@@ -883,8 +947,10 @@ module Bolognese
               "address" => gl["geoLocationPlace"],
               "polygon" => Array.wrap(gl.dig("geoLocationPolygon")).map do |glp|
                 Array.wrap(glp).map do |glpp|
-                  [glpp.dig("polygonPoint", "pointLongitude"), glpp.dig("polygonPoint", "pointLatitude")].compact
-                end.compact
+                  if glpp.dig("polygonPoint")
+                    [glpp.dig("polygonPoint", "pointLongitude"), glpp.dig("polygonPoint", "pointLatitude")].compact
+                  end
+                end.compact.presence
               end.compact.presence,
               }
           }
@@ -983,7 +1049,7 @@ module Bolognese
       Array.wrap(element).map do |a|
         if a["literal"].present?
           a["@type"] = "Organization"
-          a["name"] = a["literal"]
+          a["creatorName"] = a["literal"]
         else
           a["@type"] = "Person"
           a["name"] = [a["given"], a["family"]].compact.join(" ")
@@ -1019,12 +1085,16 @@ module Bolognese
       custom_scrubber = Bolognese::WhitelistScrubber.new(options)
 
       if text.is_a?(String)
-        # remove excessive internal whitespace with squish
-        Loofah.scrub_fragment(text, custom_scrubber).to_s.squish
+        if options[:new_line]
+          # Remove multiple spaces, tabs, and other whitespace characters while preserving single spaces and new lines
+          Loofah.scrub_fragment(text, custom_scrubber).to_s.gsub(/[ \t]+/, ' ').strip
+        else
+          Loofah.scrub_fragment(text, custom_scrubber).to_s.squish
+        end
       elsif text.is_a?(Hash)
-        sanitize(text.fetch(content, nil))
+        sanitize(text.fetch(content, nil), new_line: options[:new_line])
       elsif text.is_a?(Array)
-        a = text.map { |e| e.is_a?(Hash) ? sanitize(e.fetch(content, nil)) : sanitize(e) }.uniq
+        a = text.map { |e| e.is_a?(Hash) ? sanitize(e.fetch(content, nil), new_line: options[:new_line]) : sanitize(e, new_line: options[:new_line]) }.uniq
         a = options[:first] ? a.first : a.unwrap
       else
         nil
@@ -1184,7 +1254,9 @@ module Bolognese
         "urn" => "URN",
         "md5" => "md5",
         "minid" => "minid",
-        "dataguid" => "dataguid"
+        "dataguid" => "dataguid",
+        "cstr" => "CSTR",
+        "rrid" => "RRID"
       }
 
       identifierTypes[identifier_type.downcase] || identifier_type
@@ -1221,7 +1293,7 @@ module Bolognese
     end
 
     def name_to_spdx(name)
-      spdx = JSON.load(File.read(File.expand_path('../../../resources/spdx/licenses.json', __FILE__))).fetch("licenses")
+      spdx = resource_json(:spdx).fetch("licenses")
       license = spdx.find { |l| l["name"] == name || l["licenseId"] == name || l["seeAlso"].first == normalize_cc_url(name) }
 
       if license
@@ -1237,7 +1309,7 @@ module Bolognese
     end
 
     def hsh_to_spdx(hsh)
-      spdx = JSON.load(File.read(File.expand_path('../../../resources/spdx/licenses.json', __FILE__))).fetch("licenses")
+      spdx = resource_json(:spdx).fetch("licenses")
       license = spdx.find { |l| l["licenseId"].casecmp?(hsh["rightsIdentifier"]) || l["seeAlso"].first == normalize_cc_url(hsh["rightsURI"]) || l["name"] == hsh["rights"] || l["seeAlso"].first == normalize_cc_url(hsh["rights"]) }
 
       if license
@@ -1261,7 +1333,7 @@ module Bolognese
 
     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")
+      fos = resource_json(:fos).fetch("fosFields")
 
       subject = fos.find { |l| l["fosLabel"] == name || "FOS: " + l["fosLabel"] == name }
 
@@ -1277,7 +1349,7 @@ module Bolognese
 
       # 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__)))
+      fores = resource_json(:for)
       for_fields = fores.fetch("forFields")
       for_disciplines = fores.fetch("forDisciplines")
 
@@ -1299,7 +1371,7 @@ module Bolognese
 
     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")
+      fos = resource_json(:fos).fetch("fosFields")
       subject = fos.find { |l| l["fosLabel"] == hsh["__content__"] || "FOS: " + l["fosLabel"] == hsh["__content__"] || l["fosLabel"] == hsh["subject"]}
 
       if subject
@@ -1318,7 +1390,7 @@ module Bolognese
 
       # 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__)))
+      fores = resource_json(:for)
       for_fields = fores.fetch("forFields")
       for_disciplines = fores.fetch("forDisciplines")
 
@@ -1357,5 +1429,75 @@ module Bolognese
           "lang" => hsh["lang"] }.compact]
       end
     end
+
+    def dfg_ids_to_fos(dfg_ids)
+      dfgs = resource_json(:dfg).fetch("dfgFields")
+      ids = Array.wrap(dfg_ids)
+
+      subjects = dfgs.select { |l| ids.include?(l["dfgId"])}
+      subjects.map do |subject|
+        {
+          "classificationCode" => subject["fosId"],
+          "subject" =>  subject["fosLabel"],
+          "subjectScheme" => "Fields of Science and Technology (FOS)",
+          "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf"
+        }
+      end
+    end
+
+    def abstract_description
+      # Fetch the first description with descriptionType "Abstract"
+      Array.wrap(descriptions)&.find { |d| d["descriptionType"] == "Abstract" }
+    end
+
+    def generate_container(types, related_items, related_identifiers, descriptions)
+      container_type = (types.respond_to?(:dig) && types&.dig("resourceTypeGeneral")) == "Dataset" ? "DataRepository" : "Series"
+
+      # relatedItem container
+      related_item = Array.wrap(related_items).find { |ri| ri["relationType"] == "IsPublishedIn" }.to_h
+
+      if related_item.present?
+        return {
+          "type" => container_type,
+          "identifier" => related_item.dig("relatedItemIdentifier", "relatedItemIdentifier"),
+          "identifierType" => related_item.dig("relatedItemIdentifier", "relatedItemIdentifierType"),
+          "title" => related_item.dig("titles", 0).then { |t| t ? parse_attributes(t, content: "title", first: true) : nil },
+          "volume" => related_item["volume"],
+          "issue" => related_item["issue"],
+          "edition" => related_item["edition"],
+          "number" => related_item["number"],
+          "chapterNumber" => related_item["numberType"] == "Chapter" ? related_item["number"] : nil,
+          "firstPage" => related_item["firstPage"],
+          "lastPage" => related_item["lastPage"]
+        }.compact
+      end
+
+      # Legacy SeriesInformation/relatedIdentifier container fallback 
+      series_information = Array.wrap(descriptions).find { |r| r["descriptionType"] == "SeriesInformation" }.to_h.fetch("description", nil)
+      si = get_series_information(series_information)
+
+      is_part_of = Array.wrap(related_identifiers).find { |ri| ri["relationType"] == "IsPartOf" }.to_h
+
+      if si["title"].present?
+        return {
+          "type" => container_type,
+          "identifier" => is_part_of["relatedIdentifier"],
+          "identifierType" => is_part_of["relatedIdentifierType"],
+          "title" => si["title"],
+          "volume" => si["volume"],
+          "issue" => si["issue"],
+          "firstPage" => si["firstPage"],
+          "lastPage" => si["lastPage"]
+        }.compact
+      end
+    end
+
+    private
+
+    def normalize_uri_with_path_cleanup(uri)
+      normalized_uri = uri.normalize
+      normalized_uri.path = normalized_uri.path.sub(%r{/\z}, "") if normalized_uri.path.present?
+      normalized_uri.to_s
+    end
   end
 end

data/lib/bolognese/version.rb

@@ -1,3 +1,3 @@
 module Bolognese
-  VERSION = "1.9.9"
+  VERSION = "2.6.1"
 end

data/lib/bolognese/writers/bibtex_writer.rb

@@ -21,7 +21,7 @@ module Bolognese
           volume: container.to_h["volume"],
           issue: container.to_h["issue"],
           pages: pages,
-          publisher: publisher,
+          publisher: publisher["name"],
           year: publication_year,
           copyright: Array.wrap(rights_list).map { |l| l["rights"] }.first,
         }.compact

data/lib/bolognese/writers/codemeta_writer.rb

@@ -19,7 +19,7 @@ module Bolognese
           "tags" => subjects.present? ? Array.wrap(subjects).map { |k| parse_attributes(k, content: "subject", first: true) } : nil,
           "datePublished" => get_date(dates, "Issued") || publication_year,
           "dateModified" => get_date(dates, "Updated"),
-          "publisher" => publisher,
+          "publisher" => publisher["name"],
           "license" => Array.wrap(rights_list).map { |l| l["rightsUri"] }.compact.unwrap,
         }.compact
         JSON.pretty_generate hsh.presence

data/lib/bolognese/writers/csv_writer.rb

@@ -4,18 +4,16 @@ module Bolognese
       require "csv"
 
       def csv
-        return nil unless valid?
-
         bib = {
           doi: doi,
           url: url,
           registered: get_iso8601_date(date_registered),
           state: state,
-          resource_type_general: types["resourceTypeGeneral"],
-          resource_type: types["resourceType"],
+          resource_type_general: types.respond_to?(:to_h) ? types.to_h["resourceTypeGeneral"] : nil,
+          resource_type: types.respond_to?(:to_h) ? types.to_h["resourceType"] : nil,
           title: parse_attributes(titles, content: "title", first: true),
           author: authors_as_string(creators),
-          publisher: publisher,
+          publisher: publisher.respond_to?(:to_h) ? publisher.to_h["name"] : nil,
           publication_year: publication_year
         }.values
 

data/lib/bolognese/writers/datacite_json_writer.rb

@@ -4,7 +4,9 @@ module Bolognese
   module Writers
     module DataciteJsonWriter
       def datacite_json
-        JSON.pretty_generate crosscite_hsh.transform_keys! { |key| key.camelcase(uppercase_first_letter = :lower) } if crosscite_hsh.present?
+        if crosscite_hsh.present?
+          JSON.pretty_generate crosscite_hsh.transform_keys! { |key| key.camelcase(uppercase_first_letter = :lower) }
+        end
       end
     end
   end

data/lib/bolognese/writers/jats_writer.rb

@@ -77,16 +77,19 @@ module Bolognese
 
       def insert_source(xml)
         if is_chapter?
-          xml.source(publisher)
+          xml.source(publisher["name"])
         elsif is_article? || is_data?
-          xml.source(container && container["title"] || publisher)
+          xml.source(container && container["title"] || publisher["name"])
         else
           xml.source(parse_attributes(titles, content: "title", first: true))
         end
       end
 
       def insert_publisher_name(xml)
-        xml.send("publisher-name", publisher)
+        attributes = {
+          "xml:lang" => publisher["lang"]
+        }.compact
+        xml.send("publisher-name", attributes, publisher["name"])
       end
 
       def insert_publication_date(xml)

data/lib/bolognese/writers/ris_writer.rb

@@ -11,10 +11,10 @@ module Bolognese
           "AU" => to_ris(creators),
           "DO" => doi,
           "UR" => url,
-          "AB" => parse_attributes(descriptions, content: "description", first: true),
+          "AB" => parse_attributes(abstract_description, content: "description", first: true),
           "KW" => Array.wrap(subjects).map { |k| parse_attributes(k, content: "subject", first: true) }.presence,
           "PY" => publication_year,
-          "PB" => publisher,
+          "PB" => publisher["name"],
           "LA" => language,
           "VL" => container.to_h["volume"],
           "IS" => container.to_h["issue"],

data/lib/bolognese/writers/schema_org_writer.rb

@@ -13,7 +13,8 @@ module Bolognese
           "name" => parse_attributes(titles, content: "title", first: true),
           "author" => to_schema_org_creators(creators),
           "editor" => to_schema_org_contributors(contributors),
-          "description" => parse_attributes(descriptions, content: "description", first: true),
+          "translator" => contributors ? to_schema_org_contributors(contributors.select { |c| c["contributorType"] == "Translator" }) : nil,
+          "description" => parse_attributes(abstract_description, content: "description", first: true),
           "license" => Array.wrap(rights_list).map { |l| l["rightsUri"] }.compact.unwrap,
           "version" => version_info,
           "keywords" => subjects.present? ? Array.wrap(subjects).map { |k| parse_attributes(k, content: "subject", first: true) }.join(", ") : nil,
@@ -23,6 +24,7 @@ module Bolognese
           "dateCreated" => get_date(dates, "Created"),
           "datePublished" => get_date(dates, "Issued") || publication_year,
           "dateModified" => get_date(dates, "Updated"),
+          "temporalCoverage" => get_date(dates, "Coverage"),
           "pageStart" => container.to_h["firstPage"],
           "pageEnd" => container.to_h["lastPage"],
           "spatialCoverage" => to_schema_org_spatial_coverage(geo_locations),
@@ -32,12 +34,14 @@ module Bolognese
           "predecessor_of" => to_schema_org_relation(related_identifiers: related_identifiers, relation_type: "IsPreviousVersionOf"),
           "successor_of" => to_schema_org_relation(related_identifiers: related_identifiers, relation_type: "IsNewVersionOf"),
           "citation" => to_schema_org_relation(related_identifiers: related_identifiers, relation_type: "References"),
+          "workTranslation" => to_schema_org_relation(related_identifiers: related_identifiers, relation_type: "HasTranslation"),
+          "translationOfWork" => to_schema_org_relation(related_identifiers: related_identifiers, relation_type: "IsTranslationOf"),
           "@reverse" => reverse.presence,
           "contentUrl" => Array.wrap(content_url).unwrap,
           "schemaVersion" => schema_version,
           "periodical" => types.present? ? ((types["schemaOrg"] != "Dataset") && container.present? ? to_schema_org(container) : nil) : nil,
           "includedInDataCatalog" => types.present? ? ((types["schemaOrg"] == "Dataset") && container.present? ? to_schema_org_container(container, type: "Dataset") : nil) : nil,
-          "publisher" => publisher.present? ? { "@type" => "Organization", "name" => publisher } : nil,
+          "publisher" => publisher.present? ? { "@type" => "Organization", "@id" => publisher["publisherIdentifier"], "name" => publisher["name"] }.compact : nil,
           "funder" => to_schema_org_funder(funding_references),
           "provider" => agency.present? ? { "@type" => "Organization", "name" => agency } : nil
         }.compact.presence

data/lib/bolognese.rb

@@ -3,9 +3,7 @@
 require 'active_support/all'
 require 'nokogiri'
 require 'maremma'
-require 'postrank-uri'
 require 'bibtex'
-require 'colorize'
 require 'loofah'
 require 'json/ld'
 require 'rdf/turtle'
@@ -13,13 +11,12 @@ require 'rdf/rdfxml'
 require 'logger'
 require 'iso8601'
 require 'jsonlint'
-require 'benchmark_methods'
 require 'gender_detector'
-require 'citeproc/ruby'
 require 'citeproc'
 require 'csl/styles'
 require 'edtf'
 
+require "bolognese/citeproc_extensions"
 require "bolognese/version"
 require "bolognese/metadata"
 require "bolognese/cli"

data/resources/kernel-4/include/datacite-contributorType-v4.xsd

@@ -2,7 +2,8 @@
 <!-- Version 1.0 - Created 2011-01-13 - FZ, TIB, Germany
    2013-05 v3.0: Addition of ID to simpleType element, added values "ResearchGroup" & "Other"
    2014-08-20 v3.1: Addition of value "DataCurator"
-   2015-05-14 v4.0 dropped value "Funder", use new "funderReference" -->
+   2015-05-14 v4.0 dropped value "Funder", use new "funderReference"
+   2024-12-05 v4.6: Addition of value "Translator" -->
 <xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns="http://datacite.org/schema/kernel-4" targetNamespace="http://datacite.org/schema/kernel-4" elementFormDefault="qualified">
   <xs:simpleType name="contributorType" id="contributorType">
     <xs:annotation>
@@ -29,6 +30,7 @@
       <xs:enumeration value="Researcher" />
       <xs:enumeration value="Sponsor" />
       <xs:enumeration value="Supervisor" />
+      <xs:enumeration value="Translator" />
       <xs:enumeration value="WorkPackageLeader" />
     </xs:restriction>
   </xs:simpleType>

data/resources/kernel-4/include/datacite-dateType-v4.xsd

@@ -2,7 +2,8 @@
 <!-- Version 1.0 - Created 2011-01-13 - FZ, TIB, Germany
      2013-05 v3.0: Addition of ID to simpleType element; addition of value "Collected"; deleted "StartDate" & "EndDate"
      2017-10-23 v4.1: Addition of value "Other"
-     2019-02-14 v4.2: Addition of value "Withdrawn"-->
+     2019-02-14 v4.2: Addition of value "Withdrawn"
+     2024-12-05 v4.6: Addition of value "Coverage"-->
 <xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns="http://datacite.org/schema/kernel-4" targetNamespace="http://datacite.org/schema/kernel-4" elementFormDefault="qualified">
   <xs:simpleType name="dateType" id="dateType">
     <xs:annotation>
@@ -13,6 +14,7 @@
       <xs:enumeration value="Available" />
       <xs:enumeration value="Collected" />
       <xs:enumeration value="Copyrighted" />
+      <xs:enumeration value="Coverage" />
       <xs:enumeration value="Created" />
       <xs:enumeration value="Issued" />
       <xs:enumeration value="Other" />