bolognese 1.11.5 → 2.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 56e889d65ba92e22edbe2dfa559d112281809b5bc3c6828c745af4b2f412e98d
-  data.tar.gz: 5b487af779c0c50a9e87e9e50427fe4575efa68945204659380c7da056333545
+  metadata.gz: df7445354dfea2520078a43cc8eec9128c91c67759e4d4ffe0378223eba52750
+  data.tar.gz: 6673463c01a3a114bdeff5e8ed2f6af7c25f565d0d1e39c35c6e1d1a5b7c5d57
 SHA512:
-  metadata.gz: 613d6c58f9cb704d430012e4640d69e4abce8ed7e411b9d4ce8263c2688f9ee26a8c94039ef1803e5c3af8072682716a752f09bf54888c3215f9c0b74f897d96
-  data.tar.gz: f6ac57bbbc80d5091b72799bba17c8cbcd301e872198a82e705d2642d878a15fe0c2447a2ace3da8d4bcca5eb14ec14bebb7462b9cecf0739a1e2a7e1af9cf27
+  metadata.gz: e7ea1cab22c2a8e6e26979547c6a8a87f83c2e6bb346bad254154087d70534735b53d4fa89798db7688ddecf3945cf11e23ddcedda295154304c3f7ff55ca24a
+  data.tar.gz: 29aee296393f1338d5ab048a10abd4ad760a82dff8abe3a2b5d9a006149b34e1251ab8b883a7205b1eb25f0ded55fb1b476830d6214cff904b26cec81fd8a469

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    bolognese (1.11.5)
+    bolognese (2.0.1)
       activesupport (>= 4.2.5)
       benchmark_methods (~> 0.7)
       bibtex-ruby (>= 5.1.0)
@@ -95,10 +95,10 @@ GEM
       concurrent-ruby (~> 1.0)
     iso8601 (0.9.1)
     json (2.6.2)
-    json-canonicalization (0.3.2)
-    json-ld (3.2.5)
+    json-canonicalization (0.3.1)
+    json-ld (3.2.4)
       htmlentities (~> 4.3)
-      json-canonicalization (~> 0.3, >= 0.3.2)
+      json-canonicalization (~> 0.3)
       link_header (~> 0.0, >= 0.0.8)
       multi_json (~> 1.15)
       rack (>= 2.2, < 4)
@@ -225,6 +225,7 @@ DEPENDENCIES
   bundler (>= 1.0)
   byebug
   hashdiff (>= 1.0.0.beta1, < 2.0.0)
+  json-canonicalization (= 0.3.1)
   rack-test (~> 0)
   rake (~> 12.0)
   rspec (~> 3.4)

data/bolognese.gemspec

@@ -50,6 +50,7 @@ Gem::Specification.new do |s|
   s.add_development_dependency 'simplecov', '0.17.1'
   s.add_development_dependency 'hashdiff', ['>= 1.0.0.beta1', '< 2.0.0']
   s.add_development_dependency 'byebug'
+  s.add_development_dependency 'json-canonicalization', '0.3.1'
 
   s.require_paths = ["lib"]
   s.files       = `git ls-files`.split($/)

data/lib/bolognese/datacite_utils.rb

@@ -106,9 +106,19 @@ module Bolognese
         end
       end
     end
-
+    
     def insert_publisher(xml)
-      xml.publisher(publisher || container && container["title"])
+      if publisher.is_a?(Hash)
+        attributes = {
+          'publisherIdentifier' => publisher["publisherIdentifier"],
+          'publisherIdentifierScheme' => publisher["publisherIdentifierScheme"],
+          'schemeURI' => publisher["schemeUri"],
+          "xml:lang" => publisher["lang"]
+        }.compact
+        xml.publisher(publisher["name"] || container && container["title"], attributes)
+      else
+        xml.publisher(publisher || container && container["title"])
+      end
     end
 
     def insert_publication_year(xml)
@@ -375,13 +385,11 @@ module Bolognese
               end
             end
             if geo_location["geoLocationPolygon"]
-              geo_location["geoLocationPolygon"].each do |geo_location_polygon|
-                xml.geoLocationPolygon do
-                  geo_location_polygon.each do |polygon_point|
-                    xml.polygonPoint do
-                      xml.pointLatitude(polygon_point.dig("polygonPoint", "pointLatitude"))
-                      xml.pointLongitude(polygon_point.dig("polygonPoint", "pointLongitude"))
-                    end
+              xml.geoLocationPolygon do
+                Array.wrap(geo_location["geoLocationPolygon"]).each do |polygon_point|
+                  xml.polygonPoint do
+                    xml.pointLatitude(polygon_point.dig("polygonPoint", "pointLatitude"))
+                    xml.pointLongitude(polygon_point.dig("polygonPoint", "pointLongitude"))
                   end
                 end
               end

data/lib/bolognese/metadata.rb

@@ -217,7 +217,7 @@ module Bolognese
     end
 
     def publisher
-      @publisher ||= meta.fetch("publisher", nil)
+      @publisher ||= normalize_publisher(meta["publisher"]) if meta.fetch("publisher", nil).present?
     end
 
     def identifiers

data/lib/bolognese/metadata_utils.rb

@@ -161,7 +161,7 @@ module Bolognese
         "volume" => container.to_h["volume"],
         "issue" => container.to_h["issue"],
         "page" => page,
-        "publisher" => publisher,
+        "publisher" => publisher["name"],
         "title" => parse_attributes(titles, content: "title", first: true),
         "URL" => url,
         "copyright" => Array.wrap(rights_list).map { |l| l["rights"] }.first,

data/lib/bolognese/readers/bibtex_reader.rb

@@ -86,11 +86,11 @@ module Bolognese
           "titles" => meta.try(:title).present? ? [{ "title" => meta.try(:title).to_s }] : [],
           "creators" => creators,
           "container" => container,
-          "publisher" => meta.try(:publisher).to_s.presence,
+          "publisher" => meta.try(:publisher).present? ? { "name" => meta.publisher.to_s } : nil,
           "related_identifiers" => related_identifiers,
           "dates" => dates,
           "publication_year" => publication_year,
-          "descriptions" => meta.try(:abstract).present? ? [{ "description" => meta.try(:abstract) && sanitize(meta.abstract.to_s).presence, "descriptionType" => "Abstract" }] : [],
+          "descriptions" => meta.try(:abstract).present? ? [{ "description" => meta.try(:abstract) && sanitize(meta.abstract.to_s, new_line: true).presence, "descriptionType" => "Abstract" }] : [],
           "rights_list" => rights_list,
           "state" => state
         }.merge(read_options)

data/lib/bolognese/readers/citeproc_reader.rb

@@ -107,7 +107,7 @@ module Bolognese
           "related_identifiers" => related_identifiers,
           "dates" => dates,
           "publication_year" => publication_year,
-          "descriptions" => meta.fetch("abstract", nil).present? ? [{ "description" => sanitize(meta.fetch("abstract")), "descriptionType" => "Abstract" }] : [],
+          "descriptions" => meta.fetch("abstract", nil).present? ? [{ "description" => sanitize(meta.fetch("abstract"), new_line: true), "descriptionType" => "Abstract" }] : [],
           "rights_list" => rights_list,
           "version_info" => meta.fetch("version", nil),
           "subjects" => subjects,

data/lib/bolognese/readers/codemeta_reader.rb

@@ -43,7 +43,7 @@ module Bolognese
         dates << { "date" => meta.fetch("dateCreated"), "dateType" => "Created" } if meta.fetch("dateCreated", nil).present?
         dates << { "date" => meta.fetch("dateModified"), "dateType" => "Updated" } if meta.fetch("dateModified", nil).present?
         publication_year = meta.fetch("datePublished")[0..3] if meta.fetch("datePublished", nil).present?
-        publisher = meta.fetch("publisher", nil)
+        publisher = { "name" => meta.fetch("publisher", nil) } if meta.fetch("publisher", nil).present?
         state = meta.present? || read_options.present? ? "findable" : "not_found"
         schema_org = meta.fetch("@type", nil)
         types = {
@@ -76,7 +76,7 @@ module Bolognese
           #{}"is_part_of" => is_part_of,
           "dates" => dates,
           "publication_year" => publication_year,
-          "descriptions" => meta.fetch("description", nil).present? ? [{ "description" => sanitize(meta.fetch("description")), "descriptionType" => "Abstract" }] : nil,
+          "descriptions" => meta.fetch("description", nil).present? ? [{ "description" => sanitize(meta.fetch("description"), new_line: true), "descriptionType" => "Abstract" }] : nil,
           "rights_list" => rights_list,
           "version_info" => meta.fetch("version", nil),
           "subjects" => subjects,

data/lib/bolognese/readers/crosscite_reader.rb

@@ -7,7 +7,10 @@ module Bolognese
         errors = jsonlint(string)
         return { "errors" => errors } if errors.present?
 
-        string.present? ? Maremma.from_json(string) : {}
+        crosscite = string.present? ? Maremma.from_json(string) : {}
+        crosscite["publisher"] = normalize_publisher(crosscite["publisher"]) if crosscite.fetch("publisher", nil).present?
+
+        crosscite
       end
     end
   end

data/lib/bolognese/readers/crossref_reader.rb

@@ -40,8 +40,7 @@ module Bolognese
         journal_metadata = nil
         journal_issue = {}
         journal_metadata = nil
-        publisher = query.dig("crm_item", 0)
-        publisher = nil unless publisher.is_a?(String)
+        publisher = query.dig("crm_item", 0).is_a?(String) ? { "name" => query.dig("crm_item", 0) } : nil
 
         case model
         when "book"
@@ -232,11 +231,11 @@ module Bolognese
 
       def crossref_description(bibliographic_metadata)
         abstract = Array.wrap(bibliographic_metadata.dig("abstract")).map do |r|
-          { "descriptionType" => "Abstract", "description" => sanitize(parse_attributes(r, content: 'p')) }.compact
+          { "descriptionType" => "Abstract", "description" => sanitize(parse_attributes(r, content: 'p'), new_line: true) }.compact
         end
 
         description = Array.wrap(bibliographic_metadata.dig("description")).map do |r|
-          { "descriptionType" => "Other", "description" => sanitize(parse_attributes(r)) }.compact
+          { "descriptionType" => "Other", "description" => sanitize(parse_attributes(r), new_line: true) }.compact
         end
 
         (abstract + description)

data/lib/bolognese/readers/datacite_json_reader.rb

@@ -7,7 +7,10 @@ module Bolognese
         errors = jsonlint(string)
         return { "errors" => errors } if errors.present?
 
-        string.present? ? Maremma.from_json(string).transform_keys! { |key| key.underscore } : {}
+        datacite_json = string.present? ? Maremma.from_json(string).transform_keys! { |key| key.underscore } : {}
+        datacite_json["publisher"] = normalize_publisher(datacite_json["publisher"]) if datacite_json.fetch("publisher", nil).present?
+
+        datacite_json
       end
     end
   end

data/lib/bolognese/readers/datacite_reader.rb

@@ -94,13 +94,29 @@ module Bolognese
 
         titles = get_titles(meta)
 
+        publisher = Array.wrap(meta.dig("publisher")).map do |r|
+          if r.blank?
+            nil
+          elsif r.is_a?(String)
+            { "name" => r.strip }
+          elsif r.is_a?(Hash)
+            {
+              "name" => r["__content__"].strip,
+              "publisherIdentifier" => r["publisherIdentifierScheme"] == "ROR" ? normalize_ror(r["publisherIdentifier"]) : r["publisherIdentifier"],
+              "publisherIdentifierScheme" => r["publisherIdentifierScheme"],
+              "schemeUri" => r["schemeURI"],
+              "lang" => r["lang"],
+            }.compact
+          end
+        end.compact.first
+
         descriptions = Array.wrap(meta.dig("descriptions", "description")).map do |r|
           if r.blank?
             nil
           elsif r.is_a?(String)
-            { "description" => sanitize(r), "descriptionType" => "Abstract" }
+            { "description" => sanitize(r, new_line: true), "descriptionType" => "Abstract" }
           elsif r.is_a?(Hash)
-            { "description" => sanitize(r["__content__"]), "descriptionType" => r["descriptionType"], "lang" => r["lang"] }.compact
+            { "description" => sanitize(r["__content__"], new_line: true), "descriptionType" => r["descriptionType"], "lang" => r["lang"] }.compact
           end
         end.compact
         rights_list = Array.wrap(meta.dig("rightsList", "rights")).map do |r|
@@ -287,7 +303,7 @@ module Bolognese
           "creators" => get_authors(Array.wrap(meta.dig("creators", "creator"))),
           "contributors" => get_authors(Array.wrap(meta.dig("contributors", "contributor"))),
           "container" => set_container(meta),
-          "publisher" => parse_attributes(meta.fetch("publisher", nil), first: true).to_s.strip.presence,
+          "publisher" => publisher,
           "agency" => "datacite",
           "funding_references" => funding_references,
           "dates" => dates,

data/lib/bolognese/readers/npm_reader.rb

@@ -103,7 +103,7 @@ module Bolognese
           #"related_identifiers" => related_identifiers,
           #"dates" => dates,
           #"publication_year" => publication_year,
-          "descriptions" => meta.fetch("description", nil).present? ? [{ "description" => sanitize(meta.fetch("description")), "descriptionType" => "Abstract" }] : [],
+          "descriptions" => meta.fetch("description", nil).present? ? [{ "description" => sanitize(meta.fetch("description"), new_line: true), "descriptionType" => "Abstract" }] : [],
           "rights_list" => rights_list,
           "version_info" => meta.fetch("version", nil),
           "subjects" => subjects

data/lib/bolognese/readers/ris_reader.rb

@@ -89,12 +89,12 @@ module Bolognese
           "url" => meta.fetch("UR", nil),
           "titles" => meta.fetch("T1", nil).present? ? [{ "title" => meta.fetch("T1", nil) }] : nil,
           "creators" => get_authors(author),
-          "publisher" => meta.fetch("PB", "(:unav)"),
+          "publisher" => { "name" => meta.fetch("PB", "(:unav)") },
           "container" => container,
           "related_identifiers" => related_identifiers,
           "dates" => dates,
           "publication_year" => publication_year,
-          "descriptions" => meta.fetch("AB", nil).present? ? [{ "description" => sanitize(meta.fetch("AB")), "descriptionType" => "Abstract" }] : nil,
+          "descriptions" => meta.fetch("AB", nil).present? ? [{ "description" => sanitize(meta.fetch("AB"), new_line: true), "descriptionType" => "Abstract" }] : nil,
           "subjects" => subjects,
           "language" => meta.fetch("LA", nil),
           "state" => state

data/lib/bolognese/readers/schema_org_reader.rb

@@ -74,7 +74,8 @@ module Bolognese
           creators = get_authors(from_schema_org_creators(Array.wrap(authors)))
         end
         contributors = get_authors(from_schema_org_contributors(Array.wrap(meta.fetch("editor", nil))))
-        publisher = parse_attributes(meta.fetch("publisher", nil), content: "name", first: true)
+        publisher_name = parse_attributes(meta.fetch("publisher", nil), content: "name", first: true)
+        publisher = { "name" => publisher_name } if publisher_name.present?
 
         ct = (schema_org == "Dataset") ? "includedInDataCatalog" : "Periodical"
         container = if meta.fetch(ct, nil).present?
@@ -180,7 +181,7 @@ module Bolognese
           "related_identifiers" => related_identifiers,
           "publication_year" => publication_year,
           "dates" => dates,
-          "descriptions" => meta.fetch("description", nil).present? ? [{ "description" => sanitize(meta.fetch("description")), "descriptionType" => "Abstract" }] : nil,
+          "descriptions" => meta.fetch("description", nil).present? ? [{ "description" => sanitize(meta.fetch("description"), new_line: true), "descriptionType" => "Abstract" }] : nil,
           "rights_list" => rights_list,
           "version_info" => meta.fetch("version", nil).to_s.presence,
           "subjects" => subjects,

data/lib/bolognese/utils.rb

@@ -773,6 +773,14 @@ 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 }
@@ -1057,12 +1065,16 @@ 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

data/lib/bolognese/version.rb

@@ -1,3 +1,3 @@
 module Bolognese
-  VERSION = "1.11.5"
+  VERSION = "2.0.1"
 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

@@ -15,7 +15,7 @@ module Bolognese
           resource_type: types["resourceType"],
           title: parse_attributes(titles, content: "title", first: true),
           author: authors_as_string(creators),
-          publisher: publisher,
+          publisher: publisher["name"],
           publication_year: publication_year
         }.values
 

data/lib/bolognese/writers/datacite_json_writer.rb

@@ -4,7 +4,12 @@ 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?
+        # Remove the following change for the schema 4.5 release
+        if crosscite_hsh.present?
+          datacite_json_hsh = crosscite_hsh
+          datacite_json_hsh['publisher'] = self.publisher['name'] if self.publisher&.respond_to?(:to_hash) && self.publisher.has_key?('name') && !self.publisher['name'].blank?
+          JSON.pretty_generate datacite_json_hsh.transform_keys! { |key| key.camelcase(uppercase_first_letter = :lower) }
+        end
       end
     end
   end

data/lib/bolognese/writers/jats_writer.rb

@@ -77,16 +77,16 @@ 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)
+        xml.send("publisher-name", publisher["name"])
       end
 
       def insert_publication_date(xml)

data/lib/bolognese/writers/ris_writer.rb

@@ -14,7 +14,7 @@ module Bolognese
           "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

@@ -37,7 +37,7 @@ module Bolognese
           "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", "name" => publisher["name"] } : nil,
           "funder" => to_schema_org_funder(funding_references),
           "provider" => agency.present? ? { "@type" => "Organization", "name" => agency } : nil
         }.compact.presence

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

@@ -46,6 +46,8 @@
       <xs:enumeration value="IsRequiredBy" />
       <xs:enumeration value="Obsoletes" />
       <xs:enumeration value="IsObsoletedBy" />
+      <xs:enumeration value="Collects" />
+      <xs:enumeration value="IsCollectedBy" />
     </xs:restriction>
   </xs:simpleType>
 </xs:schema>

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

@@ -22,6 +22,7 @@
       <xs:enumeration value="Dissertation" />
       <xs:enumeration value="Event" />
       <xs:enumeration value="Image" />
+      <xs:enumeration value="Instrument" />
       <xs:enumeration value="InteractiveResource" />
       <xs:enumeration value="Journal" />
       <xs:enumeration value="JournalArticle" />
@@ -35,6 +36,7 @@
       <xs:enumeration value="Software" />
       <xs:enumeration value="Sound" />
       <xs:enumeration value="Standard" />
+      <xs:enumeration value="StudyRegistration" />
       <xs:enumeration value="Text" />
       <xs:enumeration value="Workflow" />
       <xs:enumeration value="Other" />

data/resources/kernel-4/metadata.xsd

@@ -2,7 +2,7 @@
 <!-- Revision history
   2010-08-26 Complete revision according to new common specification by the metadata work group after review. AJH, DTIC
   2010-11-17 Revised to current state of kernel review, FZ, TIB
-  2011-01-17 Complete revsion after community review. FZ, TIB
+  2011-01-17 Complete revision after community review. FZ, TIB
   2011-03-17 Release of v2.1: added a namespace; mandatory properties got minLength; changes in the definitions of relationTypes IsDocumentedBy/Documents and isCompiledBy/Compiles; changes type of property "Date" from xs:date to xs:string. FZ, TIB
   2011-06-27 v2.2: namespace: kernel-2.2, additions to controlled lists "resourceType", "contributorType", "relatedIdentifierType", and "descriptionType". Removal of intermediate include-files.
   2013-07-24 v3.0: namespace: kernel-3.0; delete LastMetadataUpdate & MetadateVersionNumber; additions to controlled lists "contributorType", "dateType", "descriptionType", "relationType", "relatedIdentifierType" & "resourceType"; deletion of "StartDate" & "EndDate" from list "dateType" and "Film" from "resourceType";  allow arbitrary order of elements; allow optional wrapper elements to be empty; include xml:lang attribute for title, subject & description; include attribute schemeURI for nameIdentifier of creator, contributor & subject; added new attributes "relatedMetadataScheme", "schemeURI" & "schemeType" to relatedIdentifier; included new property "geoLocation"
@@ -12,7 +12,8 @@
   2018-09-08 v4.1.1 Make schema 4.1 backwards compatible to 4.0 by allowing geolocation elements in any order
   2019-02-14 v4.2: Addition of dateType value "Withdrawn", relationType values "Obsoletes", "isObsoletedBy", addition of new subproperties for Rights: rightsIdentifier, rightsIdentifierScheme, schemeURI, addition of the XML language attribute to the properties Creator, Contributor and Publisher for organizational names, don't check format of DOI
   2019-07-13 v4.3: Addition of new subproperties for Affiliation: "affiliationIdentifier", "affiliationIdentifierScheme", "schemeURI", addition of new sub-property for funderIdentifier: "schemeURI", addition of new funderIdentifierScheme: "ROR", added documentation for nameIdentifier 
-  2021-03-08 v4.4: Addition of new property relatedItem, relationType value "isPublishedIn", subject subproperty "classificationCode", controlled list "numberType", additional 13 properties for controlled list "resourceType" -->
+  2021-03-08 v4.4: Addition of new property relatedItem, relationType value "isPublishedIn", subject subproperty "classificationCode", controlled list "numberType", additional 13 properties for controlled list "resourceType" 
+  2023-??-?? v4.5: Addition of new subproperties for publisher: "publisherIdentifier", "publisherIdentifierScheme", and "schemeURI"; addition of new resourceTypeGeneral values "Instrument" and "StudyRegistration"; addition of new relationType values "Collects" and "IsCollectedBy".-->
 <xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" targetNamespace="http://datacite.org/schema/kernel-4" elementFormDefault="qualified" xml:lang="EN">
   <xs:import namespace="http://www.w3.org/XML/1998/namespace" schemaLocation="include/xml.xsd" />
   <xs:include schemaLocation="include/datacite-titleType-v4.xsd" />
@@ -105,6 +106,9 @@
           <xs:complexType>
             <xs:simpleContent>
               <xs:extension base="nonemptycontentStringType">
+                <xs:attribute name="publisherIdentifier" type="xs:string" use="optional" />
+                <xs:attribute name="publisherIdentifierScheme" type="xs:string" use="optional" />
+                <xs:attribute name="schemeURI" type="xs:anyURI" use="optional" />
                 <xs:attribute ref="xml:lang" />
               </xs:extension>
             </xs:simpleContent>
@@ -161,7 +165,7 @@
             <xs:sequence>
               <xs:element name="contributor" minOccurs="0" maxOccurs="unbounded">
                 <xs:annotation>
-                  <xs:documentation>The institution or person responsible for collecting, creating, or otherwise contributing to the developement of the dataset.</xs:documentation>
+                  <xs:documentation>The institution or person responsible for collecting, creating, or otherwise contributing to the development of the dataset.</xs:documentation>
                   <xs:documentation>The personal name format should be: Family, Given.</xs:documentation>
                 </xs:annotation>
                 <xs:complexType>
@@ -524,7 +528,7 @@ Use the complete title of a license and include version information if applicabl
                     </xs:element>
                     <xs:element name="number" minOccurs="0">
                       <xs:annotation>
-                        <xs:documentation>Issue number or name of the related item.</xs:documentation>
+                        <xs:documentation>Number of the related item e.g. report number of article number.</xs:documentation>
                       </xs:annotation>
                       <xs:complexType>
                         <xs:simpleContent>
@@ -641,19 +645,19 @@ Use the complete title of a license and include version information if applicabl
       <xs:pattern value="\d{2}(\d{2}|\?\?|\d(\d|\?))(-(\d{2}|\?\?))?~?\??" />
       <!--  
       The following pattern is for  yearMonthDay - yyyymmdd,  where 'dd' may be '??'  so '200412??' means "some day during the month of 12/2004". 
-      The whole  string may be followed by '?' or '~'  to mean "questionable" or "approximate".     Hypens are  not allowed for this pattern. 
+      The whole  string may be followed by '?' or '~'  to mean "questionable" or "approximate".     Hyphens are  not allowed for this pattern. 
       -->
       <xs:pattern value="\d{6}(\d{2}|\?\?)~?\??" />
       <!--  
 
       The following pattern is for date and time with T separator:'yyyymmddThhmmss'. 
-      Hypens in date and colons in time not allowed for this pattern.   
+      Hyphens in date and colons in time not allowed for this pattern.   
       -->
       <xs:pattern value="\d{8}T\d{6}" />
       <!--  
 
       The following pattern is for a date range. in years: 'yyyy/yyyy'; or year/month: yyyy-mm/yyyy-mm, or year/month/day: yyyy-mm-dd/yyyy-mm-dd. Beginning or end of range value may be 'unknown'. End of range value may be 'open'.
-      Hypens mandatory when month is present. 
+      Hyphens mandatory when month is present. 
       -->
       <xs:pattern value="((-)?(\d{4}(-\d{2})?(-\d{2})?)|unknown)/((-)?(\d{4}(-\d{2})?(-\d{2})?)|unknown|open)" />
     </xs:restriction>

data/resources/kernel-4.5/include/datacite-contributorType-v4.xsd

@@ -0,0 +1,35 @@
+<?xml version="1.0" encoding="UTF-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" -->
+<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>
+      <xs:documentation>The type of contributor of the resource.</xs:documentation>
+    </xs:annotation>
+    <xs:restriction base="xs:string">
+      <xs:enumeration value="ContactPerson" />
+      <xs:enumeration value="DataCollector" />
+      <xs:enumeration value="DataCurator" />
+      <xs:enumeration value="DataManager" />
+      <xs:enumeration value="Distributor" />
+      <xs:enumeration value="Editor" />
+      <xs:enumeration value="HostingInstitution" />
+      <xs:enumeration value="Other" />
+      <xs:enumeration value="Producer" />
+      <xs:enumeration value="ProjectLeader" />
+      <xs:enumeration value="ProjectManager" />
+      <xs:enumeration value="ProjectMember" />
+      <xs:enumeration value="RegistrationAgency" />
+      <xs:enumeration value="RegistrationAuthority" />
+      <xs:enumeration value="RelatedPerson" />
+      <xs:enumeration value="ResearchGroup" />
+      <xs:enumeration value="RightsHolder" />
+      <xs:enumeration value="Researcher" />
+      <xs:enumeration value="Sponsor" />
+      <xs:enumeration value="Supervisor" />
+      <xs:enumeration value="WorkPackageLeader" />
+    </xs:restriction>
+  </xs:simpleType>
+</xs:schema>

data/resources/kernel-4.5/include/datacite-dateType-v4.xsd

@@ -0,0 +1,25 @@
+<?xml version="1.0" encoding="UTF-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"-->
+<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>
+      <xs:documentation>The type of date. Use RKMS‐ISO8601 standard for depicting date ranges.To indicate the end of an embargo period, use Available. To indicate the start of an embargo period, use Submitted or Accepted, as appropriate.</xs:documentation>
+    </xs:annotation>
+    <xs:restriction base="xs:string">
+      <xs:enumeration value="Accepted" />
+      <xs:enumeration value="Available" />
+      <xs:enumeration value="Collected" />
+      <xs:enumeration value="Copyrighted" />
+      <xs:enumeration value="Created" />
+      <xs:enumeration value="Issued" />
+      <xs:enumeration value="Other" />
+      <xs:enumeration value="Submitted" />
+      <xs:enumeration value="Updated" />
+      <xs:enumeration value="Valid" />
+      <xs:enumeration value="Withdrawn" />
+    </xs:restriction>
+  </xs:simpleType>
+</xs:schema>

data/resources/kernel-4.5/include/datacite-descriptionType-v4.xsd

@@ -0,0 +1,19 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- Version 1.0 - Created 2011-01-13 - FZ, TIB, Germany
+     2013-05 v3.0: Addition of ID to simpleType element, addition of value "Methods"
+     2015-02-12 v4.0: Addition of value "TechnicalInfo"-->
+<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="descriptionType" id="descriptionType">
+    <xs:annotation>
+      <xs:documentation>The type of the description.</xs:documentation>
+    </xs:annotation>
+    <xs:restriction base="xs:string">
+      <xs:enumeration value="Abstract" />
+      <xs:enumeration value="Methods" />
+      <xs:enumeration value="SeriesInformation" />
+      <xs:enumeration value="TableOfContents" />
+      <xs:enumeration value="TechnicalInfo" />
+      <xs:enumeration value="Other" />
+    </xs:restriction>
+  </xs:simpleType>
+</xs:schema>