bolognese 2.6.1 → 2.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: af6403c24df2779189b8883a6ac2a649856eefc21021f2a93e5e6ebeee91592a
-  data.tar.gz: 4fab74f8c6e1044c48a3d66fb64ff90ff134cf868b881dcbfc6a91e410fb3fa8
+  metadata.gz: 835ab3fe44434e73ae854befe4f6acb61ea005c5fdd95833103c7a692b19378c
+  data.tar.gz: 5b5085360ceae14323ae37e82d517dade2e87cc0c8b631a2a1dd8ea95eb5e7be
 SHA512:
-  metadata.gz: edb53a6a6644b9184fec632cb1b6a128d630c403499d19df8ce3e0febbac3a51d3d85d86b3f8a124a5b4fa3f3573022b0d0b633c5b9ced8a9bc416638cd7dfd4
-  data.tar.gz: a3f0b04d4ed508858ea7e7ec896f2182bdd9d7d5773e58e4e97faa8e52bd362cd0688a305b2efec9c614a51564b0927d8270b597ce976322e8650182cab5bc4a
+  metadata.gz: 50d00d40e262c6175bee47c5443f8673dc2af21dce0bd97ee6e31abe62d0631073aa89bac32cd78610706e04662d6501aa1f4059466d2ba1f574353dc832de82
+  data.tar.gz: faa9c4ee7e4c5f1f9c4cd36139701dac10d6a4ec5f4a2bb13213618fff45bb32f14e7aebdee6d27cd27eac8524b731964d953ff45d3f95007e9f98abc3fbf39f

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    bolognese (2.6.1)
+    bolognese (2.7.0)
       activesupport (~> 8.1, >= 8.1.2)
       bibtex-ruby (~> 6.2)
       builder (~> 3.3)

data/lib/bolognese/author_utils.rb

@@ -21,7 +21,6 @@ module Bolognese
       given_name = parse_attributes(author.fetch("givenName", nil))
       family_name = parse_attributes(author.fetch("familyName", nil))
       name = cleanup_author(name)
-      name = [family_name, given_name].join(", ") if family_name.present? && given_name.present?
       contributor_type = parse_attributes(author.fetch("contributorType", nil))
 
       name_type = parse_attributes(author.fetch("creatorName", nil), content: "nameType", first: true) || parse_attributes(author.fetch("contributorName", nil), content: "nameType", first: true)
@@ -46,55 +45,18 @@ module Bolognese
         end
       end.presence
 
-      author = { "nameType" => name_type,
+      { "nameType" => name_type,
                  "name" => name,
                  "givenName" => given_name,
                  "familyName" => family_name,
                  "nameIdentifiers" => name_identifiers,
                  "affiliation" => get_affiliations(author.fetch("affiliation", nil)),
                  "contributorType" => contributor_type }.compact
-
-      return author if family_name.present?
-
-      if is_personal_name?(author)
-        Namae.options[:include_particle_in_family] = true
-        names = Namae.parse(name)
-        parsed_name = names.first
-
-        if parsed_name.present?
-          given_name = parsed_name.given
-          family_name = parsed_name.family
-          name = [family_name, given_name].join(", ")
-        else
-          given_name = nil
-          family_name = nil
-        end
-
-        { "nameType" => "Personal",
-          "name" => name,
-          "givenName" => given_name,
-          "familyName" => family_name,
-          "nameIdentifiers" => Array.wrap(name_identifiers),
-          "affiliation" => Array.wrap(author.fetch("affiliation", nil)),
-          "contributorType" => contributor_type }.compact
-      else
-        { "nameType" => name_type,
-          "name" => name,
-          "nameIdentifiers" => Array.wrap(name_identifiers),
-          "affiliation" => Array.wrap(author.fetch("affiliation", nil)),
-          "contributorType" => contributor_type }.compact
-      end
     end
 
     def cleanup_author(author)
       return nil unless author.present?
 
-      # detect pattern "Smith J.", but not "Smith, John K."
-      author = author.gsub(/[[:space:]]([A-Z]\.)?(-?[A-Z]\.)$/, ', \1\2') unless author.include?(",")
-
-      # remove spaces around hyphens
-      author = author.gsub(" - ", "-")
-
       # titleize strings
       # remove non-standard space characters
       author.gsub(/[[:space:]]/, ' ')
@@ -155,7 +117,6 @@ module Bolognese
             # when `normalize_id` method could not normalize, it returns nil, hence we have following condition
             if affiliation_identifier.nil?
               if a["affiliationIdentifierScheme"] == "ROR"
-                scheme_uri = "https://ror.org"
                 affiliation_identifier = normalize_ror(a["affiliationIdentifier"])
               else
                 affiliation_identifier = a["affiliationIdentifier"]

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/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/datacite_reader.rb

@@ -133,9 +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
@@ -143,15 +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
@@ -179,8 +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
@@ -196,7 +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
@@ -219,7 +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
@@ -236,7 +234,6 @@ module Bolognese
           number = ri["number"]
           if number.is_a?(String)
             number = number
-            numberType = nil
           else
             number = ri.dig("number", "__content__")
             numberType = ri.dig("number", "numberType")

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

@@ -699,19 +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)
@@ -1331,103 +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)

data/lib/bolognese/version.rb

@@ -1,3 +1,3 @@
 module Bolognese
-  VERSION = "2.6.1"
+  VERSION = "2.7.0"
 end

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

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: bolognese
 version: !ruby/object:Gem::Version
-  version: 2.6.1
+  version: 2.7.0
 platform: ruby
 authors:
 - Martin Fenner
 bindir: bin
 cert_chain: []
-date: 2026-04-29 00:00:00.000000000 Z
+date: 2026-05-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: maremma