bolognese 1.10.0 → 2.6.1

data/lib/bolognese/readers/datacite_reader.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require 'base64'
+
 module Bolognese
   module Readers
     module DataciteReader
@@ -94,13 +96,29 @@ 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__"].present? ? r["__content__"].strip : nil,
+              "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|
@@ -190,7 +208,8 @@ module Bolognese
             "resourceTypeGeneral" => ri["resourceTypeGeneral"],
             "relatedMetadataScheme" => ri["relatedMetadataScheme"],
             "schemeUri" => ri["schemeURI"],
-            "schemeType" => ri["schemeType"]
+            "schemeType" => ri["schemeType"],
+            "relationTypeInformation" => ri["relationTypeInformation"]
           }.compact
         end
 
@@ -210,7 +229,7 @@ module Bolognese
               "relatedItemIdentifierType" => rii["relatedItemIdentifierType"],
               "relatedMetadataScheme" => rii["relatedMetadataScheme"],
               "schemeURI" => rii["schemeURI"],
-              "schemeType" => rii["schemeType"]
+              "schemeType" => rii["schemeType"],
             }.compact
           end
 
@@ -225,19 +244,20 @@ module Bolognese
 
           a = {
             "relationType" => ri["relationType"],
+            "relationTypeInformation" => ri["relationTypeInformation"],
             "relatedItemType" => ri["relatedItemType"],
             "relatedItemIdentifier" => relatedItemIdentifier,
             "creators" => get_authors(Array.wrap(ri.dig("creators", "creator"))),
             "titles" => get_titles(ri),
             "publicationYear" => ri["publicationYear"],
-            "volume" => ri["volume"],
-            "issue" => ri["issue"],
+            "volume" => parse_attributes(ri["volume"]),
+            "issue" => parse_attributes(ri["issue"]),
             "number" => number,
             "numberType" => numberType,
-            "firstPage" => ri["firstPage"],
-            "lastPage" => ri["lastPage"],
-            "publisher" => ri["publisher"],
-            "edition" => ri["edition"],
+            "firstPage" => parse_attributes(ri["firstPage"]),
+            "lastPage" => parse_attributes(ri["lastPage"]),
+            "publisher" => parse_attributes(ri["publisher"]),
+            "edition" => parse_attributes(ri["edition"]),
             "contributors" => get_authors(Array.wrap(ri.dig("contributors", "contributor"))),
           }.compact
         end
@@ -246,17 +266,13 @@ module Bolognese
           if !gl.is_a?(Hash) || gl["geoLocationPoint"].is_a?(String) || gl["geoLocationBox"].is_a?(String) || gl["geoLocationPolygon"].is_a?(String)
             nil
           else
-
-            # Handle scenario where multiple geoLocationPolygons are allowed within a single geoLocation
-            # we want to return an array if it's already an array (i.e. multiple geoLocationPolygons)
-            # vs if it's singular just return the object
-            # This is for backwards compatability to allow both scenarios.
+            ## Array of geoLocationPolygons within a geoLocation is Unsupported in JSON.
             if gl.dig("geoLocationPolygon").kind_of?(Array)
-              geoLocationPolygon = gl.dig("geoLocationPolygon").map do |glp|
-                Array.wrap(glp.dig("polygonPoint")).map { |glpp| { "polygonPoint" => glpp } }.compact.presence
-              end.compact.presence
+              geoLocationPolygon = nil
             else
-              geoLocationPolygon = Array.wrap(gl.dig("geoLocationPolygon", "polygonPoint")).map { |glp| { "polygonPoint" => glp } }.compact.presence
+              geoLocationPolygon = Array.wrap(gl.dig("geoLocationPolygon", "polygonPoint")).map { |glp| { "polygonPoint" => glp } }
+                .push(Array.wrap(gl.dig("geoLocationPolygon", "inPolygonPoint")).map { |glp| { "inPolygonPoint" => glp } }.first)
+                .compact.presence             
             end
 
             {
@@ -286,8 +302,7 @@ module Bolognese
           "titles" => titles,
           "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,
@@ -307,28 +322,6 @@ module Bolognese
         }.merge(read_options)
       end
 
-      def set_container(meta)
-        series_information = Array.wrap(meta.dig("descriptions", "description")).find { |r| r["descriptionType"] == "SeriesInformation" }.to_h.fetch("__content__", nil)
-        si = get_series_information(series_information)
-
-        is_part_of = Array.wrap(meta.dig("relatedIdentifiers", "relatedIdentifier")).find { |ri| ri["relationType"] == "IsPartOf" }.to_h
-
-        if si["title"].present? || is_part_of.present?
-          {
-            "type" => meta.dig("resourceType", "resourceTypeGeneral") == "Dataset" ? "DataRepository" : "Series",
-            "identifier" => is_part_of["__content__"],
-            "identifierType" => is_part_of["relatedIdentifierType"],
-            "title" => si["title"],
-            "volume" => si["volume"],
-            "issue" => si["issue"],
-            "firstPage" => si["firstPage"],
-            "lastPage" => si["lastPage"]
-          }.compact
-        else
-          {}
-        end
-      end
-
       def get_titles(meta)
         titles = Array.wrap(meta.dig("titles", "title")).map do |r|
           if r.blank?

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

@@ -10,7 +10,9 @@ module Bolognese
         "isPartOf" => "IsPartOf",
         "hasPart" => "HasPart",
         "isPredecessor" => "IsPreviousVersionOf",
-        "isSuccessor" => "IsNewVersionOf"
+        "isSuccessor" => "IsNewVersionOf",
+        "workTranslation" => "HasTranslation",
+        "translationOfWork" => "IsTranslationOf"
       }
 
       SO_TO_DC_REVERSE_RELATION_TYPES = {
@@ -74,7 +76,17 @@ 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)
+        translators = get_authors(from_schema_org_contributors(Array.wrap(meta.fetch("translator", nil))))
+        translators.map! do |translator|
+          translator["contributorType"] = "Translator"
+          translator
+        end
+        contributors += translators
+
+        publisher = {
+          "name" => parse_attributes(meta.fetch("publisher", nil), content: "name", first: true),
+          "publisherIdentifier" => parse_attributes(meta.fetch("publisher", nil), content: "@id", first: true),
+        }.compact if meta.fetch("publisher", nil).present?
 
         ct = (schema_org == "Dataset") ? "includedInDataCatalog" : "Periodical"
         container = if meta.fetch(ct, nil).present?
@@ -102,7 +114,9 @@ module Bolognese
           Array.wrap(schema_org_references(meta)) +
           Array.wrap(schema_org_is_referenced_by(meta)) +
           Array.wrap(schema_org_is_supplement_to(meta)) +
-          Array.wrap(schema_org_is_supplemented_by(meta))
+          Array.wrap(schema_org_is_supplemented_by(meta)) +
+          Array.wrap(schema_org_has_translation(meta)) +
+          Array.wrap(schema_org_is_translation_of(meta))
 
         rights_list = Array.wrap(meta.fetch("license", nil)).compact.map do |rl|
           hsh_to_spdx("__content__" => rl["name"], "rightsURI" => rl["id"])
@@ -123,6 +137,7 @@ module Bolognese
         dates << { "date" => meta.fetch("datePublished"), "dateType" => "Issued" } if Date.edtf(meta.fetch("datePublished", nil)).present?
         dates << { "date" => meta.fetch("dateCreated"), "dateType" => "Created" } if Date.edtf(meta.fetch("dateCreated", nil)).present?
         dates << { "date" => meta.fetch("dateModified"), "dateType" => "Updated" } if Date.edtf(meta.fetch("dateModified", nil)).present?
+        dates << { "date" => meta.fetch("temporalCoverage"), "dateType" => "Coverage" } if Date.edtf(meta.fetch("temporalCoverage", nil)).present?
         publication_year = meta.fetch("datePublished")[0..3] if meta.fetch("datePublished", nil).present?
 
         if meta.fetch("inLanguage", nil).is_a?(String)
@@ -180,7 +195,7 @@ 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,
@@ -236,6 +251,14 @@ module Bolognese
         schema_org_related_identifier(meta, relation_type: "isBasedOn")
       end
 
+      def schema_org_has_translation(meta)
+        schema_org_related_identifier(meta, relation_type: "workTranslation", )
+      end
+
+      def schema_org_is_translation_of(meta)
+        schema_org_related_identifier(meta, relation_type: "translationOfWork")
+      end
+
     end
   end
 end

data/lib/bolognese/utils.rb

@@ -32,7 +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",
@@ -67,7 +67,9 @@ module Bolognese
       "OutputManagementPlan" => nil,
       "PeerReview" => "Review",
       "PhysicalObject" => nil,
+      "Poster" => "Poster",
       "Preprint" => nil,
+      "Presentation" => "PresentationDigitalDocument",
       "Report" => "Report",
       "Service" => "Service",
       "Software" => "SoftwareSourceCode",
@@ -78,7 +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 = {
@@ -101,7 +105,9 @@ module Bolognese
       "OutputManagementPlan" => nil,
       "PeerReview" => "review",
       "PhysicalObject" => nil,
+      "Poster" => "document",
       "Preprint" => nil,
+      "Presentation" => "presentation",
       "Report" => "report",
       "Service" => nil,
       "Sound" => "song",
@@ -278,6 +284,8 @@ module Bolognese
       "Event" => "Event",
       "ImageObject" => "Image",
       "Movie" => "Audiovisual",
+      "Poster" => "Poster",
+      "PresentationDigitalDocument" => "Presentation",
       "PublicationIssue" => "Text",
       "Report" => "Report",
       "ScholarlyArticle" => "Text",
@@ -324,6 +332,8 @@ module Bolognese
       "Event" => nil,
       "ImageObject" => "graphic",
       "Movie" => "motion_picture",
+      "Poster" => "document",
+      "PresentationDigitalDocument" => "presentation",
       "PublicationIssue" => nil,
       "Report" => "report",
       "ScholarlyArticle" => "article-journal",
@@ -346,8 +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",
@@ -404,7 +416,9 @@ module Bolognese
       "OutputManagementPlan" => nil,
       "PeerReview" => nil,
       "PhysicalObject" => nil,
+      "Poster" => "GEN",
       "Preprint" => nil,
+      "Presentation" => "SLIDE",
       "Report" => "RRPT",
       "Service" => nil,
       "Software" => "COMP",
@@ -417,7 +431,7 @@ module Bolognese
 
     RIS_TO_DC_TRANSLATIONS = {
       "BLOG" => "Text",
-      "GEN" => "Text",
+      "GEN" => "Poster",
       "CTLG" => "Collection",
       "DATA" => "Dataset",
       "FIGURE" => "Image",
@@ -426,7 +440,8 @@ module Bolognese
       "JOUR" => "JournalArticle",
       "COMP" => "Software",
       "VIDEO" => "Audiovisual",
-      "ELEC" => "Text"
+      "ELEC" => "Text",
+      "SLIDE" => "Presentation"
     }
 
     BIB_TO_DC_TRANSLATIONS = {
@@ -450,7 +465,9 @@ module Bolognese
       "motion_picture" => "Audiovisual",
       "article-journal" => "JournalArticle",
       "broadcast" => "Audiovisual",
-      "webpage" => "Text"
+      "webpage" => "Text",
+      "document" => "Poster",
+      "presentation" => "Presentation"
     }
 
     SO_TO_BIB_TRANSLATIONS = {
@@ -466,6 +483,8 @@ module Bolognese
       "Event" => "misc",
       "ImageObject" => "misc",
       "Movie" => "misc",
+      "Poster" => "misc",
+      "PresentationDigitalDocument" => "misc",
       "PublicationIssue" => "misc",
       "ScholarlyArticle" => "article",
       "Service" => "misc",
@@ -600,12 +619,12 @@ module Bolognese
     end
 
     def validate_orcid(orcid)
-      orcid = Array(/\A(?:(?:http|https):\/\/(?:(?:www|sandbox)?\.)?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})$/.match(ror)).last
+      Array(/^(?:(?:(?:http|https):\/\/)?ror\.org\/)?(0\w{6}\d{2})\/{0,1}$/.match(ror)).last
     end
 
     def validate_orcid_scheme(orcid_scheme)
@@ -649,7 +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
@@ -669,9 +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
@@ -773,6 +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 }
@@ -817,7 +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
@@ -831,10 +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
 
@@ -921,8 +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,
               }
           }
@@ -1021,7 +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(" ")
@@ -1057,12 +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
@@ -1222,7 +1254,9 @@ module Bolognese
         "urn" => "URN",
         "md5" => "md5",
         "minid" => "minid",
-        "dataguid" => "dataguid"
+        "dataguid" => "dataguid",
+        "cstr" => "CSTR",
+        "rrid" => "RRID"
       }
 
       identifierTypes[identifier_type.downcase] || identifier_type
@@ -1410,5 +1444,60 @@ module Bolognese
         }
       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 = "1.10.0"
+  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"],