bolognese 2.5.0 → 2.7.0

data/lib/bolognese/citeproc_extensions.rb

@@ -0,0 +1,48 @@
+# frozen_string_literal: true
+
+# Minimal patch for csl-ruby and citeproc-ruby compatibility
+# Root cause: 'contributor' is not recognized as a names variable in citeproc gem
+# https://github.com/inukshuk/citeproc/blob/121fa4a950b9bd71960e42d20db96bcea1165201/lib/citeproc/variable.rb#L20-L24
+
+module CiteProc
+  class Variable
+    # Unfreeze, modify, and refreeze the fields to add 'contributor' and 'accepted-date'
+    if @fields
+      # Unfreeze the fields hash temporarily
+      fields_dup = @fields.dup
+      
+      # Add contributor to names (make a new unfrozen array)
+      fields_dup[:names] = (@fields[:names] + [:contributor]).uniq
+      
+      # Add accepted-date to dates (make a new unfrozen array)
+      fields_dup[:date] = (@fields[:date] + [:'accepted-date']).uniq
+      
+      # Rebuild the types mapping - only use actual type keys, not aliases like :all, :any, etc.
+      types_hash = Hash[*[:date, :names, :number, :text].map { |k| fields_dup[k].map { |n| [n, k] } }.flatten]
+      
+      # Update the class instance variables
+      @fields = fields_dup
+      @types = Hash.new { |h,k| h.fetch(k.to_sym, nil) }.merge(types_hash).freeze
+      
+      # Rebuild @factories from the new @types
+      # This maps each field name to its Variable subclass (Names, Date, Text, Number)
+      @factories = Hash.new { |h,k| h.fetch(k.to_s.intern, CiteProc::Variable) }.merge(
+        Hash[*@types.map { |field_name, type|
+          [field_name, CiteProc.const_get(type.to_s.capitalize)]
+        }.flatten]
+      ).freeze
+      
+      # Recreate the aliases
+      @fields[:name] = @fields[:names]
+      @fields[:dates] = @fields[:date]
+      @fields[:numbers] = @fields[:number]
+      
+      # Recreate :all and :any
+      @fields[:all] = @fields[:any] =
+        [:date, :names, :text, :number].reduce([]) { |s,a| s.concat(@fields[a]) }.sort
+      
+      # Refreeze fields
+      @fields.freeze
+    end
+  end
+end

data/lib/bolognese/datacite_utils.rb

@@ -209,7 +209,9 @@ module Bolognese
           attributes = {
             'relatedIdentifierType' => related_identifier["relatedIdentifierType"],
             'relationType' => related_identifier["relationType"],
-            'resourceTypeGeneral' => related_identifier["resourceTypeGeneral"] }.compact
+            'relationTypeInformation' => related_identifier["relationTypeInformation"],
+            'resourceTypeGeneral' => related_identifier["resourceTypeGeneral",
+            ] }.compact
 
           attributes.merge({ 'relatedMetadataScheme' => related_identifier["relatedMetadataSchema"],
             'schemeURI' => related_identifier["schemeUri"],
@@ -228,6 +230,7 @@ module Bolognese
           attributes = {
             'relatedItemType' => related_item["relatedItemType"],
             'relationType' => related_item["relationType"],
+            'relationTypeInformation' => related_item["relationTypeInformation"],
           }.compact
 
           xml.relatedItem(related_item["relatedItem"], attributes) do

data/lib/bolognese/doi_utils.rb

@@ -13,11 +13,12 @@ module Bolognese
     end
 
     def validate_funder_doi(doi)
-      doi = Array(/\A(?:(http|https):\/(\/)?(dx\.)?(doi.org|handle.stage.datacite.org|handle.test.datacite.org)\/)?(doi:)?(10\.13039\/)?([1-9]\d+)\z/.match(doi)).last
+      match = Array(/\A(?:(http|https):\/(\/)?(dx\.)?(doi.org|handle.stage.datacite.org|handle.test.datacite.org)\/)?(doi:)?(10\.13039\/)?([1-9]\d+)\z/.match(doi)).last
+      return doi unless match
 
       # remove non-printing whitespace and downcase
-      if doi.present?
-        doi.delete("\u200B").downcase
+      if match.present?
+        doi = match.delete("\u200B").downcase
         "https://doi.org/10.13039/#{doi}"
       end
     end

data/lib/bolognese/metadata.rb

@@ -1,4 +1,4 @@
-# frozen_string_literal: true
+# frozen_string_literal: false
 
 require_relative 'metadata_utils'
 
@@ -76,8 +76,8 @@ module Bolognese
       end
 
       # make sure input is encoded as utf8
-      string = string.force_encoding("UTF-8") if string.present?
-      @string = string
+      string1 = string.dup.force_encoding("UTF-8") if string.present?
+      @string = string1
 
       # input options for citation formatting
       @style = options[:style]
@@ -120,7 +120,7 @@ module Bolognese
 
       @regenerate = options[:regenerate] || read_options.present?
       # generate name for method to call dynamically
-      opts = { string: string, sandbox: options[:sandbox], doi: options[:doi], id: id, ra: ra }.merge(read_options)
+      opts = { string: string1, sandbox: options[:sandbox], doi: options[:doi], id: id, ra: ra }.merge(read_options)
       @meta = @from.present? ? send("read_" + @from, **opts) : {}
     end
 

data/lib/bolognese/metadata_utils.rb

@@ -33,7 +33,6 @@ require_relative 'writers/turtle_writer'
 
 module Bolognese
   module MetadataUtils
-    # include BenchmarkMethods
     include Bolognese::DoiUtils
     include Bolognese::AuthorUtils
     include Bolognese::DataciteUtils
@@ -140,19 +139,28 @@ module Bolognese
         author = to_citeproc(creators)
       end
 
-      if types["resourceTypeGeneral"] == "Software" && version_info.present?
-        type = "book"
+      if types["resourceTypeGeneral"] == "Software"
+        type = "software"
       else
         type = types["citeproc"]
       end
 
+      # Filter out contributors who are already creators, editors, or translators to avoid duplication
+      creator_names = Array.wrap(creators).map { |c| c["name"] || [c["givenName"], c["familyName"]].compact.join(" ") }.compact
+      unique_contributors = Array.wrap(contributors).reject do |c|
+        contributor_name = c["name"] || [c["givenName"], c["familyName"]].compact.join(" ")
+        creator_names.include?(contributor_name) ||
+        c["contributorType"] == "Editor" ||
+        c["contributorType"] == "Translator"
+      end
+
       {
         "type" => type,
         "id" => normalize_doi(doi),
         "categories" => Array.wrap(subjects).map { |k| parse_attributes(k, content: "subject", first: true) }.presence,
         "language" => language,
         "author" => author,
-        "contributor" => to_citeproc(contributors),
+        "contributor" => unique_contributors.presence ? to_citeproc(unique_contributors) : nil,
         "editor" => contributors ? to_citeproc(contributors.select { |c| c["contributorType"] == "Editor" }) : nil,
         "translator" => contributors ? to_citeproc(contributors.select { |c| c["contributorType"] == "Translator" }) : nil,
         "issued" => get_date(dates, "Issued") ? get_date_parts(get_date(dates, "Issued")) : get_date_parts(publication_year.to_s),

data/lib/bolognese/readers/citeproc_reader.rb

@@ -96,7 +96,7 @@ module Bolognese
 
         state = id.present? || read_options.present? ? "findable" : "not_found"
         subjects = Array.wrap(meta.fetch("categories", nil)).reduce([]) do |sum, subject|
-          sum += name_to_fos(subject)
+          sum += name_to_subject(subject)
 
           sum
         end

data/lib/bolognese/readers/codemeta_reader.rb

@@ -55,7 +55,7 @@ module Bolognese
           "ris" => Bolognese::Utils::SO_TO_RIS_TRANSLATIONS[schema_org] || "GEN"
         }.compact
         subjects = Array.wrap(meta.fetch("tags", nil)).reduce([]) do |sum, subject|
-          sum += name_to_fos(subject)
+          sum += name_to_subject(subject)
 
           sum
         end

data/lib/bolognese/readers/crossref_reader.rb

@@ -144,7 +144,7 @@ module Bolognese
 
         state = meta.present? || read_options.present? ? "findable" : "not_found"
 
-        related_identifiers = Array.wrap(crossref_is_part_of(journal_metadata)) + Array.wrap(crossref_references(bibliographic_metadata)) + Array.wrap(crossref_has_translation(program_metadata)) + Array.wrap(crossref_is_translation_of(program_metadata))
+        related_identifiers = Array.wrap(crossref_is_part_of(journal_metadata)) + Array.wrap(crossref_references(bibliographic_metadata)) + Array.wrap(crossref_has_translation(program_metadata)) + Array.wrap(crossref_is_translation_of(program_metadata)) + Array.wrap(crossref_is_related_material(program_metadata))
 
         container = if journal_metadata.present?
                       issn = normalize_issn(journal_metadata.to_h.fetch("issn", nil))
@@ -395,6 +395,19 @@ module Bolognese
           end
         end.compact.unwrap
       end
+
+      def crossref_is_related_material(program_metadata)
+        refs = program_metadata.dig("related_item") if program_metadata.is_a?(Hash)
+        Array.wrap(refs).select { |a| a.dig("interwork_relation", "relationship_type") == "isRelatedMaterial" }.map do |c|
+          if c.dig("inter_work_relation", "identifier_type") == "doi"
+            { "relatedIdentifier" => parse_attributes(c["inter_work_relation"]).downcase,
+              "relationType" => "Other",
+              "relatedIdentifierType" => "DOI" }.compact
+          else
+            nil
+          end
+        end.compact.unwrap
+      end
     end
   end
 end

data/lib/bolognese/readers/datacite_reader.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require 'base64'
+
 module Bolognese
   module Readers
     module DataciteReader
@@ -131,9 +133,9 @@ module Bolognese
 
         subjects = Array.wrap(meta.dig("subjects", "subject")).reduce([]) do |sum, subject|
           if subject.is_a?(String)
-            sum += name_to_fos(subject)
+            sum += name_to_subject(subject)
           elsif subject.is_a?(Hash)
-            sum += hsh_to_fos(subject)
+            sum += hsh_to_subject(subject)
           end
 
           sum
@@ -141,15 +143,12 @@ module Bolognese
 
         dates = Array.wrap(meta.dig("dates", "date")).map do |r|
           if r.is_a?(Hash) && date = sanitize(r["__content__"]).presence
-            if Date.edtf(date).present? || Bolognese::Utils::UNKNOWN_INFORMATION.key?(date)
-              { "date" => date,
-                "dateType" => parse_attributes(r, content: "dateType"),
-                "dateInformation" => parse_attributes(r, content: "dateInformation")
-              }.compact
-            end
+            { "date" => date,
+              "dateType" => parse_attributes(r, content: "dateType"),
+              "dateInformation" => parse_attributes(r, content: "dateInformation")
+            }.compact
           end
         end.compact
-        dates << { "date" => meta.fetch("publicationYear", nil), "dateType" => "Issued" } if meta.fetch("publicationYear", nil).present? && get_date(dates, "Issued").blank?
         sizes = Array.wrap(meta.dig("sizes", "size")).map do |k|
           if k.blank?
             nil
@@ -177,8 +176,7 @@ module Bolognese
           if funder_identifier_type == "Crossref Funder ID"
             funder_identifier = validate_funder_doi(funder_identifier)
           elsif funder_identifier_type == "ROR"
-            funder_identifier =  normalize_ror(funder_identifier)
-            scheme_uri = "https://ror.org"
+            funder_identifier = normalize_ror(funder_identifier)
           else
             funder_identifier = normalize_id(funder_identifier) ? normalize_id(funder_identifier) : funder_identifier
           end
@@ -194,7 +192,8 @@ module Bolognese
         end
         related_identifiers = Array.wrap(meta.dig("relatedIdentifiers", "relatedIdentifier")).map do |ri|
           if ri["relatedIdentifierType"] == "DOI"
-            rid = validate_doi(ri["__content__"].to_s.downcase)
+            doi = ri["__content__"].to_s.downcase
+            rid = validate_doi(doi) || doi
           else
             rid = ri["__content__"]
           end
@@ -206,7 +205,8 @@ module Bolognese
             "resourceTypeGeneral" => ri["resourceTypeGeneral"],
             "relatedMetadataScheme" => ri["relatedMetadataScheme"],
             "schemeUri" => ri["schemeURI"],
-            "schemeType" => ri["schemeType"]
+            "schemeType" => ri["schemeType"],
+            "relationTypeInformation" => ri["relationTypeInformation"]
           }.compact
         end
 
@@ -216,7 +216,8 @@ module Bolognese
           relatedItemIdentifier = nil
           if rii
             if rii["relatedItemIdentifierType"] == "DOI"
-              rid = validate_doi(rii["__content__"].to_s.downcase)
+              doi = rii["__content__"].to_s.downcase
+              rid = validate_doi(doi) || doi
             else
               rid = rii["__content__"]
             end
@@ -226,14 +227,13 @@ module Bolognese
               "relatedItemIdentifierType" => rii["relatedItemIdentifierType"],
               "relatedMetadataScheme" => rii["relatedMetadataScheme"],
               "schemeURI" => rii["schemeURI"],
-              "schemeType" => rii["schemeType"]
+              "schemeType" => rii["schemeType"],
             }.compact
           end
 
           number = ri["number"]
           if number.is_a?(String)
             number = number
-            numberType = nil
           else
             number = ri.dig("number", "__content__")
             numberType = ri.dig("number", "numberType")
@@ -241,6 +241,7 @@ module Bolognese
 
           a = {
             "relationType" => ri["relationType"],
+            "relationTypeInformation" => ri["relationTypeInformation"],
             "relatedItemType" => ri["relatedItemType"],
             "relatedItemIdentifier" => relatedItemIdentifier,
             "creators" => get_authors(Array.wrap(ri.dig("creators", "creator"))),

data/lib/bolognese/readers/ris_reader.rb

@@ -78,7 +78,7 @@ module Bolognese
         end
         state = meta.fetch("DO", nil).present? || read_options.present? ? "findable" : "not_found"
         subjects = Array.wrap(meta.fetch("KW", nil)).reduce([]) do |sum, subject|
-          sum += name_to_fos(subject)
+          sum += name_to_subject(subject)
 
           sum
         end

data/lib/bolognese/readers/schema_org_reader.rb

@@ -174,7 +174,7 @@ module Bolognese
         subjects = meta.fetch("keywords", nil)
         subjects = subjects.to_s.split(", ") if subjects.is_a?(String)
         subjects = Array.wrap(subjects).reduce([]) do |sum, subject|
-          sum += name_to_fos(subject)
+          sum += name_to_subject(subject)
           sum
         end
 

data/lib/bolognese/utils.rb

@@ -67,7 +67,9 @@ module Bolognese
       "OutputManagementPlan" => nil,
       "PeerReview" => "Review",
       "PhysicalObject" => nil,
+      "Poster" => "Poster",
       "Preprint" => nil,
+      "Presentation" => "PresentationDigitalDocument",
       "Report" => "Report",
       "Service" => "Service",
       "Software" => "SoftwareSourceCode",
@@ -103,7 +105,9 @@ module Bolognese
       "OutputManagementPlan" => nil,
       "PeerReview" => "review",
       "PhysicalObject" => nil,
+      "Poster" => "document",
       "Preprint" => nil,
+      "Presentation" => "presentation",
       "Report" => "report",
       "Service" => nil,
       "Sound" => "song",
@@ -280,6 +284,8 @@ module Bolognese
       "Event" => "Event",
       "ImageObject" => "Image",
       "Movie" => "Audiovisual",
+      "Poster" => "Poster",
+      "PresentationDigitalDocument" => "Presentation",
       "PublicationIssue" => "Text",
       "Report" => "Report",
       "ScholarlyArticle" => "Text",
@@ -326,6 +332,8 @@ module Bolognese
       "Event" => nil,
       "ImageObject" => "graphic",
       "Movie" => "motion_picture",
+      "Poster" => "document",
+      "PresentationDigitalDocument" => "presentation",
       "PublicationIssue" => nil,
       "Report" => "report",
       "ScholarlyArticle" => "article-journal",
@@ -348,8 +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",
@@ -406,7 +416,9 @@ module Bolognese
       "OutputManagementPlan" => nil,
       "PeerReview" => nil,
       "PhysicalObject" => nil,
+      "Poster" => "GEN",
       "Preprint" => nil,
+      "Presentation" => "SLIDE",
       "Report" => "RRPT",
       "Service" => nil,
       "Software" => "COMP",
@@ -419,7 +431,7 @@ module Bolognese
 
     RIS_TO_DC_TRANSLATIONS = {
       "BLOG" => "Text",
-      "GEN" => "Text",
+      "GEN" => "Poster",
       "CTLG" => "Collection",
       "DATA" => "Dataset",
       "FIGURE" => "Image",
@@ -428,7 +440,8 @@ module Bolognese
       "JOUR" => "JournalArticle",
       "COMP" => "Software",
       "VIDEO" => "Audiovisual",
-      "ELEC" => "Text"
+      "ELEC" => "Text",
+      "SLIDE" => "Presentation"
     }
 
     BIB_TO_DC_TRANSLATIONS = {
@@ -452,7 +465,9 @@ module Bolognese
       "motion_picture" => "Audiovisual",
       "article-journal" => "JournalArticle",
       "broadcast" => "Audiovisual",
-      "webpage" => "Text"
+      "webpage" => "Text",
+      "document" => "Poster",
+      "presentation" => "Presentation"
     }
 
     SO_TO_BIB_TRANSLATIONS = {
@@ -468,6 +483,8 @@ module Bolognese
       "Event" => "misc",
       "ImageObject" => "misc",
       "Movie" => "misc",
+      "Poster" => "misc",
+      "PresentationDigitalDocument" => "misc",
       "PublicationIssue" => "misc",
       "ScholarlyArticle" => "article",
       "Service" => "misc",
@@ -651,7 +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
@@ -671,9 +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
@@ -684,19 +699,19 @@ module Bolognese
     end
 
     def normalize_orcid(orcid)
-      orcid = validate_orcid(orcid)
-      return nil unless orcid.present?
+      validated = validate_orcid(orcid)
+      return orcid unless validated.present?
 
       # turn ORCID ID into URL
-      "https://orcid.org/" + Addressable::URI.encode(orcid)
+      "https://orcid.org/" + Addressable::URI.encode(validated)
     end
 
     def normalize_ror(ror)
-      ror = validate_ror(ror)
-      return nil unless ror.present?
+      validated = validate_ror(ror)
+      return ror unless validated.present?
 
       # turn ROR into URL
-      "https://ror.org/" + Addressable::URI.encode(ror)
+      "https://ror.org/" + Addressable::URI.encode(validated)
     end
 
     def normalize_ids(ids: nil, relation_type: nil)
@@ -1316,103 +1331,18 @@ module Bolognese
       end
     end
 
-    def name_to_fos(name)
-      # first find subject in Fields of Science (OECD)
-      fos = resource_json(:fos).fetch("fosFields")
-
-      subject = fos.find { |l| l["fosLabel"] == name || "FOS: " + l["fosLabel"] == name }
-
-      if subject
-        return [{
-          "subject" => sanitize(name) },
-        {
-          "subject" => "FOS: " + subject["fosLabel"],
-          "subjectScheme" => "Fields of Science and Technology (FOS)",
-          "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf"
-        }]
-      end
-
-      # if not found, look in Fields of Research (Australian and New Zealand Standard Research Classification)
-      # and map to Fields of Science. Add an extra entry for the latter
-      fores = resource_json(:for)
-      for_fields = fores.fetch("forFields")
-      for_disciplines = fores.fetch("forDisciplines")
-
-      subject = for_fields.find { |l| l["forLabel"] == name } ||
-                for_disciplines.find { |l| l["forLabel"] == name }
-
-      if subject
-        [{
-          "subject" => sanitize(name) },
-        {
-          "subject" => "FOS: " + subject["fosLabel"],
-          "subjectScheme" => "Fields of Science and Technology (FOS)",
-          "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf"
-        }]
-      else
-        [{ "subject" => sanitize(name) }]
-      end
+    def name_to_subject(name)
+      [{ "subject" => sanitize(name) }]
     end
 
-    def hsh_to_fos(hsh)
-      # first find subject in Fields of Science (OECD)
-      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
-        return [{
-          "subject" => sanitize(hsh["__content__"] || hsh["subject"]),
-          "subjectScheme" => hsh["subjectScheme"],
-          "schemeUri" => hsh["schemeURI"] || hsh["schemeUri"],
-          "valueUri" => hsh["valueURI"] || hsh["valueUri"],
-          "classificationCode" => hsh["classificationCode"],
-          "lang" => hsh["lang"] }.compact,
-        {
-          "subject" => "FOS: " + subject["fosLabel"],
-          "subjectScheme" => "Fields of Science and Technology (FOS)",
-          "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf" }.compact]
-      end
-
-      # if not found, look in Fields of Research (Australian and New Zealand Standard Research Classification)
-      # and map to Fields of Science. Add an extra entry for the latter
-      fores = resource_json(:for)
-      for_fields = fores.fetch("forFields")
-      for_disciplines = fores.fetch("forDisciplines")
-
-      # try to extract forId
-      if hsh["subjectScheme"] == "FOR"
-        for_id = hsh["__content__"].to_s.split(" ").first || hsh["subject"].to_s.split(" ").first
-        for_id = for_id.rjust(6, "0")
-
-        subject = for_fields.find { |l| l["forId"] == for_id } ||
-                  for_disciplines.find { |l| l["forId"] == for_id[0..3] }
-      else
-        subject = for_fields.find { |l| l["forLabel"] == hsh["__content__"] || l["forLabel"] == hsh["subject"] } ||
-                  for_disciplines.find { |l| l["forLabel"] == hsh["__content__"] || l["forLabel"] == hsh["subject"] }
-      end
-
-      if subject
-        [{
-          "subject" => sanitize(hsh["__content__"] || hsh["subject"]),
-          "subjectScheme" => hsh["subjectScheme"],
-          "classificationCode" => hsh["classificationCode"],
-          "schemeUri" => hsh["schemeURI"] || hsh["schemeUri"],
-          "valueUri" => hsh["valueURI"] || hsh["valueUri"],
-          "lang" => hsh["lang"] }.compact,
-        {
-          "subject" => "FOS: " + subject["fosLabel"],
-          "subjectScheme" => "Fields of Science and Technology (FOS)",
-          "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf"
-        }]
-      else
-        [{
-          "subject" => sanitize(hsh["__content__"] || hsh["subject"]),
-          "subjectScheme" => hsh["subjectScheme"],
-          "classificationCode" => hsh["classificationCode"],
-          "schemeUri" => hsh["schemeURI"] || hsh["schemeUri"],
-          "valueUri" => hsh["valueURI"] || hsh["valueUri"],
-          "lang" => hsh["lang"] }.compact]
-      end
+    def hsh_to_subject(hsh)
+      [{
+        "subject" => sanitize(hsh["__content__"] || hsh["subject"]),
+        "subjectScheme" => hsh["subjectScheme"],
+        "classificationCode" => hsh["classificationCode"],
+        "schemeUri" => hsh["schemeURI"] || hsh["schemeUri"],
+        "valueUri" => hsh["valueURI"] || hsh["valueUri"],
+        "lang" => hsh["lang"] }.compact]
     end
 
     def dfg_ids_to_fos(dfg_ids)
@@ -1476,5 +1406,13 @@ module Bolognese
         }.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 = "2.5.0"
+  VERSION = "2.7.0"
 end

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["name"],
+          publisher: publisher.respond_to?(:to_h) ? publisher.to_h["name"] : nil,
           publication_year: publication_year
         }.values
 

data/lib/bolognese/writers/jats_writer.rb

@@ -93,9 +93,10 @@ module Bolognese
       end
 
       def insert_publication_date(xml)
-        year, month, day = get_date_parts(get_date(dates, "Issued")).to_h.fetch("date-parts", []).first
+        date = get_date(dates, "Issued") || publication_year
+        year, month, day = get_date_parts(date).to_h.fetch("date-parts", []).first
 
-        xml.year(year, "iso-8601-date" => get_date(dates, "Issued"))
+        xml.year(year, "iso-8601-date" => date)
         xml.month(month.to_s.rjust(2, '0')) if month.present?
         xml.day(day.to_s.rjust(2, '0')) if day.present?
       end

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"