glossarist 2.6.2 → 2.6.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a4a05468d25c9ac0d13c748454dc98d7dc031718fe98d298c3db89d6874963a7
-  data.tar.gz: 203b26205a85b9593942d7d6095dab85faa93ed1e99b9f474f20c67a77e61c5d
+  metadata.gz: 1f3a8ec372c1c3e7a93ed7c2bad8ed2837f8f5bcd5ce4ae340bbb9f3b5ddaa75
+  data.tar.gz: e7c0672fc648ea748cff12bfc00a1ea62665aeaa20e4cf8a86dde1419a6094df
 SHA512:
-  metadata.gz: dc177b1d927f7b309cb47fac5158c151001202ba0332b35f0eaf87a8e1e2d9eda400dd077145b10d4acc5ee968676f39dd95172a32ad16e6078ff3357c299317
-  data.tar.gz: eb60cfa90dd26008e2287cbafb35aaeb4e48bb60c120cc254fba024d945f4a6cdb41e9b51a2b8c68a30ac6e31e7e40f38243ec44437a5995126eba47f47110dd
+  metadata.gz: 5a3654b99b5137104e26830fe77b1b6bad3eb2e0ce4ffa45d479b909399c469c41edbd7460ede72dc4f10bf94cc2f40649e78ce8510113ea9d97f0715750af15
+  data.tar.gz: eec5c75fd4a6a434999830038642ce387d74c2b7df976343d4b342aa919d1aaf7c4beccff4f92fbb18a0f0a4acf762885bf837edad7f16dd9889a93b33ed5613

data/.gitignore

@@ -16,8 +16,9 @@
 .rubocop-http---*
 .rubocop-https---*
 
-# Relaton local cache directory
+# Relaton cache directories
 localcache
+spec/fixtures/relaton_cache/
 
 .vscode
 

data/.rubocop_todo.yml

@@ -1,59 +1,93 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2026-05-07 13:57:54 UTC using RuboCop version 1.86.1.
+# on 2026-05-12 04:13:45 UTC using RuboCop version 1.86.1.
 # The point is for the user to remove these configuration records
 # one by one as the offenses are removed from the code base.
 # Note that changes in the inspected code, or installation of new
 # versions of RuboCop, may require this file to be generated again.
 
+# Offense count: 7
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: TreatCommentsAsGroupSeparators, ConsiderPunctuation.
+Bundler/OrderedGems:
+  Exclude:
+    - 'Gemfile'
+
 # Offense count: 1
 Gemspec/RequiredRubyVersion:
   Exclude:
     - 'glossarist.gemspec'
 
-# Offense count: 1
+# Offense count: 4
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyle, IndentationWidth.
 # SupportedStyles: with_first_argument, with_fixed_indentation
 Layout/ArgumentAlignment:
   Exclude:
-    - 'spec/unit/gcr_package_spec.rb'
+    - 'lib/glossarist/sts/import_result.rb'
+    - 'lib/glossarist/sts/importer.rb'
+    - 'lib/glossarist/sts/term_mapper.rb'
 
-# Offense count: 2
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: IndentationWidth.
+Layout/AssignmentIndentation:
+  Exclude:
+    - 'lib/glossarist/sts/term_mapper.rb'
+
+# Offense count: 6
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyleAlignWith.
 # SupportedStylesAlignWith: either, start_of_block, start_of_line
 Layout/BlockAlignment:
   Exclude:
-    - 'lib/glossarist/gcr_validator.rb'
+    - 'lib/glossarist/sts/term_extractor.rb'
+    - 'spec/unit/sts/term_extractor_spec.rb'
+    - 'spec/unit/sts/term_mapper_spec.rb'
 
-# Offense count: 2
+# Offense count: 6
 # This cop supports safe autocorrection (--autocorrect).
 Layout/BlockEndNewline:
   Exclude:
-    - 'lib/glossarist/gcr_validator.rb'
+    - 'lib/glossarist/sts/term_extractor.rb'
+    - 'spec/unit/sts/term_extractor_spec.rb'
+    - 'spec/unit/sts/term_mapper_spec.rb'
 
-# Offense count: 4
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: AllowMultipleStyles, EnforcedHashRocketStyle, EnforcedColonStyle, EnforcedLastArgumentHashStyle.
+# SupportedHashRocketStyles: key, separator, table
+# SupportedColonStyles: key, separator, table
+# SupportedLastArgumentHashStyles: always_inspect, always_ignore, ignore_implicit, ignore_explicit
+Layout/HashAlignment:
+  Exclude:
+    - 'lib/glossarist/sts/importer.rb'
+
+# Offense count: 12
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: Width, EnforcedStyleAlignWith, AllowedPatterns.
 # SupportedStylesAlignWith: start_of_line, relative_to_receiver
 Layout/IndentationWidth:
   Exclude:
-    - 'lib/glossarist/gcr_validator.rb'
+    - 'lib/glossarist/sts/term_extractor.rb'
+    - 'spec/unit/sts/term_extractor_spec.rb'
+    - 'spec/unit/sts/term_mapper_spec.rb'
 
-# Offense count: 214
+# Offense count: 236
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: Max, AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, AllowRBSInlineAnnotation, AllowCopDirectives, AllowedPatterns, SplitStrings.
 # URISchemes: http, https
 Layout/LineLength:
   Enabled: false
 
-# Offense count: 1
+# Offense count: 7
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: AllowInHeredoc.
 Layout/TrailingWhitespace:
   Exclude:
-    - 'spec/unit/gcr_package_spec.rb'
+    - 'lib/glossarist/sts/import_result.rb'
+    - 'lib/glossarist/sts/importer.rb'
+    - 'lib/glossarist/sts/term_mapper.rb'
 
 # Offense count: 1
 # Configuration parameters: AllowedMethods.
@@ -106,12 +140,12 @@ Metrics/CyclomaticComplexity:
     - 'lib/glossarist/transforms/concept_to_skos_transform.rb'
     - 'lib/glossarist/transforms/concept_to_tbx_transform.rb'
 
-# Offense count: 35
+# Offense count: 47
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
   Max: 42
 
-# Offense count: 3
+# Offense count: 4
 # Configuration parameters: CountKeywordArgs, MaxOptionalParameters.
 Metrics/ParameterLists:
   Max: 6
@@ -145,7 +179,7 @@ Naming/VariableNumber:
   Exclude:
     - 'spec/unit/rdf/skos_vocabulary_spec.rb'
 
-# Offense count: 3
+# Offense count: 9
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyle, ProceduralMethods, FunctionalMethods, AllowedMethods, AllowedPatterns, AllowBracesOnProceduralOneLiners, BracesRequiredMethods.
 # SupportedStyles: line_count_based, semantic, braces_for_chaining, always_braces
@@ -154,7 +188,9 @@ Naming/VariableNumber:
 # AllowedMethods: lambda, proc, it
 Style/BlockDelimiters:
   Exclude:
-    - 'lib/glossarist/gcr_validator.rb'
+    - 'lib/glossarist/sts/term_extractor.rb'
+    - 'spec/unit/sts/term_extractor_spec.rb'
+    - 'spec/unit/sts/term_mapper_spec.rb'
 
 # Offense count: 6
 # This cop supports safe autocorrection (--autocorrect).
@@ -163,6 +199,12 @@ Style/BlockDelimiters:
 Style/FormatStringToken:
   EnforcedStyle: unannotated
 
+# Offense count: 2
+# This cop supports safe autocorrection (--autocorrect).
+Style/MultilineIfModifier:
+  Exclude:
+    - 'lib/glossarist/sts/importer.rb'
+
 # Offense count: 1
 # Configuration parameters: AllowedClasses.
 Style/OneClassPerFile:

data/Gemfile

@@ -6,29 +6,13 @@ gemspec
 
 gem "canon"
 gem "lutaml-model", "~> 0.8.0"
+gem "nokogiri"
 gem "rake", "~> 13.0"
+gem "relaton", "~> 2.1.0"
 gem "rspec", "~> 3.0"
 gem "rubocop"
 gem "rubocop-performance"
 gem "rubocop-rake"
 gem "rubocop-rspec"
+gem "sts", "~> 0.5.6"
 gem "tbx", "~> 0.1"
-
-# Override relaton gems with lutaml-model 0.8 compatible versions.
-# Released 2.0.0 gems have untyped lutaml-model attributes that fail with 0.8+.
-# lutaml-integration branches have typed attributes and relaton-bib ~> 2.1.0.
-# TODO: Remove once relaton gems release versions with lutaml-model 0.8 support.
-gem "relaton-3gpp", github: "relaton/relaton-3gpp",
-                    branch: "lutaml-integration"
-gem "relaton-bib", github: "relaton/relaton-bib", branch: "lutaml-integration"
-gem "relaton-bipm", github: "relaton/relaton-bipm",
-                    branch: "lutaml-integration"
-gem "relaton-bsi", github: "relaton/relaton-bsi", branch: "lutaml-integration"
-gem "relaton-calconnect", github: "relaton/relaton-calconnect",
-                          branch: "lutaml-integration"
-gem "relaton-ccsds", github: "relaton/relaton-ccsds",
-                     branch: "lutaml-integration"
-gem "relaton-cen", github: "relaton/relaton-cen", branch: "lutaml-integration"
-gem "relaton-iec", github: "relaton/relaton-iec", branch: "lutaml-integration"
-gem "relaton-iso", github: "relaton/relaton-iso", branch: "lutaml-integration"
-gem "relaton-itu", github: "relaton/relaton-itu", branch: "lutaml-integration"

data/README.adoc

@@ -507,6 +507,123 @@ puts skos.to_jsonld
 puts skos.to_turtle
 ----
 
+=== import
+
+Import terminology concepts from STS XML files into a new or existing dataset.
+
+[,bash]
+----
+# Import one or more STS XML files into a new dataset directory
+glossarist import iso-8373.xml -o output_dir
+
+# Import into a new GCR package (--shortname and --version required)
+glossarist import iso-8373.xml -o iso-8373.gcr \
+  --shortname iso-8373 --version 1.0.0 --title "ISO 8373 Robotics"
+
+# Import multiple files into a new dataset
+glossarist import iso-8373.xml iso-9000.xml -o combined_dataset
+
+# Import into an existing dataset (dedup by designation + domain)
+glossarist import iso-8373.xml --into existing_dataset/
+
+# Import into an existing GCR (re-packages automatically)
+glossarist import iso-8373.xml --into existing.gcr
+
+# Control duplicate handling
+glossarist import iso-8373.xml --into existing_dataset/ --on-duplicate replace
+----
+
+Deduplication is based on **designation + domain** (case-insensitive). When
+duplicates are found, the `--on-duplicate` strategy determines the behavior:
+
+[cols="1,2"]
+|===
+|`skip` (default)
+|Keep the existing concept, skip the new one
+
+|`replace`
+|Replace the existing concept with the new one
+
+|`merge`
+|Add new localizations to the existing concept (e.g. add French to an English-only concept)
+|===
+
+Options:
+[cols="1,1"]
+|===
+|o, --output
+|Output directory or `.gcr` file path (new dataset)
+
+|--into
+|Path to existing dataset directory or `.gcr` file to merge into
+
+|--shortname
+|Dataset shortname (required for GCR output)
+
+|--version
+|Dataset version (required for GCR output)
+
+|--title
+|Dataset title
+
+|--description
+|Dataset description
+
+|--owner
+|Dataset owner
+
+|--uri-prefix
+|URI prefix for the dataset
+
+|--on-duplicate
+|How to handle duplicates: `skip`, `replace`, or `merge`
+|===
+
+Ruby API:
+[,ruby]
+----
+require "glossarist/sts"
+
+importer = Glossarist::Sts::Importer.new
+
+# Import into a new dataset directory
+result = importer.import_new(
+  ["iso-8373.xml", "iso-9000.xml"],
+  output: "output_dir",
+)
+puts result.concepts.length    # total concepts imported
+puts result.conflicts.length   # duplicates detected
+puts result.skipped_count      # skipped (strategy: skip)
+
+# Import into a new GCR package
+result = importer.import_new(
+  ["iso-8373.xml"],
+  output: "iso-8373.gcr",
+  shortname: "iso-8373",
+  version: "1.0.0",
+  title: "ISO 8373 Robotics Vocabulary",
+)
+
+# Import into an existing dataset with merge strategy
+importer = Glossarist::Sts::Importer.new(duplicate_strategy: :merge)
+result = importer.import_into_existing(
+  ["french_supplement.xml"],
+  "existing_dataset/",
+)
+result.concepts.each do |mc|
+  puts "#{mc.data.id}: #{mc.localizations.keys.join(', ')}"
+end
+----
+
+==== Import result
+
+`import_new` and `import_into_existing` return an `ImportResult` with:
+
+concepts:: `Array<ManagedConcept>` — the imported concepts
+conflicts:: `Array<DuplicateConflict>` — duplicate pairs detected by designation + domain
+source_files:: `Array<String>` — the input file paths
+skipped_count:: `Integer` — concepts skipped due to duplicates (strategy: skip)
+
 === validate
 
 Validate a dataset directory or `.gcr` file for schema compliance.

data/lib/glossarist/cli/import_command.rb

@@ -0,0 +1,54 @@
+# frozen_string_literal: true
+
+module Glossarist
+  class CLI
+    class ImportCommand
+      def initialize(files, options)
+        @files = files
+        @options = options
+      end
+
+      def run
+        importer = Sts::Importer.new(
+          duplicate_strategy: @options[:on_duplicate]&.to_sym || :skip,
+        )
+
+        result = if @options[:into]
+                   importer.import_into_existing(@files, @options[:into])
+                 else
+                   importer.import_new(@files, **import_new_args)
+                 end
+
+        print_summary(result)
+      rescue ArgumentError => e
+        warn "Error: #{e.message}"
+        exit 1
+      end
+
+      private
+
+      def import_new_args
+        {
+          output: @options[:output],
+          shortname: @options[:shortname],
+          version: @options[:version],
+          title: @options[:title],
+          description: @options[:description],
+          owner: @options[:owner],
+          uri_prefix: @options[:uri_prefix],
+        }
+      end
+
+      def print_summary(result) # rubocop:disable Metrics/AbcSize
+        dest = @options[:into] || @options[:output]
+        puts "Imported #{result.concepts.length} concepts to #{dest}"
+        puts "  Source files: #{@files.join(', ')}" if @files.any?
+        return unless result.conflict?
+
+        puts "  #{result.conflicts.length} duplicate(s) detected " \
+             "(strategy: #{@options[:on_duplicate] || 'skip'})"
+        puts "  #{result.skipped_count} concept(s) skipped" if result.skipped_count.positive?
+      end
+    end
+  end
+end

data/lib/glossarist/cli.rb

@@ -4,6 +4,11 @@ require "thor"
 
 module Glossarist
   class CLI < Thor
+    autoload :UpgradeCommand, "#{__dir__}/cli/upgrade_command"
+    autoload :PackageCommand,  "#{__dir__}/cli/package_command"
+    autoload :ValidateCommand, "#{__dir__}/cli/validate_command"
+    autoload :ImportCommand,   "#{__dir__}/cli/import_command"
+    autoload :ExportCommand,   "#{__dir__}/cli/export_command"
     desc "generate_latex", "Convert Concepts to Latex format"
 
     option :concepts_path, aliases: :p, required: true,
@@ -38,8 +43,7 @@ module Glossarist
     option :dry_run, type: :boolean, default: false,
                      desc: "Show what would change without writing"
     def upgrade(source_dir)
-      require_relative "cli/upgrade_command"
-      Glossarist::CLI::UpgradeCommand.new(source_dir, options).run
+      CLI::UpgradeCommand.new(source_dir, options).run
     end
 
     desc "package DIR", "Create a .gcr ZIP archive from a schema v1 dataset"
@@ -62,8 +66,7 @@ module Glossarist
     option :concept_uri_template, type: :string,
                                   desc: "URI template for concept URIs"
     def package(dir)
-      require_relative "cli/package_command"
-      Glossarist::CLI::PackageCommand.new(dir, options).run
+      CLI::PackageCommand.new(dir, options).run
     end
 
     desc "validate PATH",
@@ -76,8 +79,27 @@ module Glossarist
     option :reference_path, type: :string,
                             desc: "Path to directory of .gcr files for cross-dataset reference validation"
     def validate(path)
-      require_relative "cli/validate_command"
-      Glossarist::CLI::ValidateCommand.new(path, options).run
+      CLI::ValidateCommand.new(path, options).run
+    end
+
+    desc "import FILES...", "Import terms from STS XML files"
+    option :output, aliases: :o, type: :string,
+                    desc: "Output directory or .gcr file path (new dataset)"
+    option :into, type: :string,
+                  desc: "Path to existing dataset directory or .gcr file to merge into"
+    option :shortname, type: :string,
+                       desc: "Dataset shortname (required for GCR output)"
+    option :version, type: :string,
+                     desc: "Dataset version (required for GCR output)"
+    option :title, type: :string, desc: "Dataset title"
+    option :description, type: :string, desc: "Dataset description"
+    option :owner, type: :string, desc: "Dataset owner"
+    option :uri_prefix, type: :string, desc: "URI prefix for the dataset"
+    option :on_duplicate, type: :string, default: "skip",
+                          enum: %w[skip replace merge],
+                          desc: "How to handle duplicate concepts (designation + domain)"
+    def import(*files)
+      CLI::ImportCommand.new(files, options).run
     end
 
     desc "export PATH", "Export concepts in machine-readable formats"
@@ -95,8 +117,7 @@ module Glossarist
     option :title, type: :string,
                    desc: "Dataset title for document header"
     def export(path)
-      require_relative "cli/export_command"
-      Glossarist::CLI::ExportCommand.new(path, options).run
+      CLI::ExportCommand.new(path, options).run
     end
 
     def method_missing(*args)

data/lib/glossarist/designation/expression.rb

@@ -1,5 +1,4 @@
-require_relative "base"
-require_relative "grammar_info"
+# frozen_string_literal: true
 
 module Glossarist
   module Designation

data/lib/glossarist/designation/graphical_symbol.rb

@@ -1,4 +1,4 @@
-require_relative "symbol"
+# frozen_string_literal: true
 
 module Glossarist
   module Designation

data/lib/glossarist/managed_concept.rb

@@ -1,4 +1,4 @@
-require_relative "localized_concept"
+# frozen_string_literal: true
 
 module Glossarist
   class ManagedConcept < Lutaml::Model::Serializable

data/lib/glossarist/rdf/skos_concept.rb

@@ -2,7 +2,6 @@
 
 require "lutaml/turtle"
 require "lutaml/jsonld"
-require_relative "../rdf"
 
 module Glossarist
   module Rdf

data/lib/glossarist/rdf/skos_vocabulary.rb

@@ -2,7 +2,6 @@
 
 require "lutaml/turtle"
 require "lutaml/jsonld"
-require_relative "../rdf"
 
 module Glossarist
   module Rdf

data/lib/glossarist/sts/extracted_designation.rb

@@ -0,0 +1,14 @@
+# frozen_string_literal: true
+
+module Glossarist
+  module Sts
+    ExtractedDesignation = Struct.new(
+      :term,
+      :type,
+      :normative_status,
+      :part_of_speech,
+      :abbreviation_type,
+      keyword_init: true,
+    )
+  end
+end

data/lib/glossarist/sts/extracted_lang_set.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+module Glossarist
+  module Sts
+    ExtractedLangSet = Struct.new(
+      :language_code,
+      :definition_text,
+      :note_texts,
+      :example_texts,
+      :source_texts,
+      :domain,
+      :designations,
+      keyword_init: true,
+    )
+  end
+end

data/lib/glossarist/sts/extracted_term.rb

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+module Glossarist
+  module Sts
+    ExtractedTerm = Struct.new(
+      :id,
+      :label,
+      :source_ref,
+      :lang_sets,
+      keyword_init: true,
+    )
+  end
+end

data/lib/glossarist/sts/import_result.rb

@@ -0,0 +1,24 @@
+# frozen_string_literal: true
+
+module Glossarist
+  module Sts
+    DuplicateConflict = Struct.new(:new_concept, :existing_concept, :key,
+                                   keyword_init: true)
+
+    class ImportResult
+      attr_reader :concepts, :conflicts, :source_files, :skipped_count
+
+      def initialize(concepts:, conflicts: [], source_files: [],
+skipped_count: 0)
+        @concepts = concepts
+        @conflicts = conflicts
+        @source_files = source_files
+        @skipped_count = skipped_count
+      end
+
+      def conflict?
+        !conflicts.empty?
+      end
+    end
+  end
+end

data/lib/glossarist/sts/importer.rb

@@ -0,0 +1,253 @@
+# frozen_string_literal: true
+
+require "tmpdir"
+require_relative "import_result"
+
+module Glossarist
+  module Sts
+    class Importer
+      STRATEGIES = %i[skip replace merge].freeze
+
+      attr_reader :duplicate_strategy
+
+      def initialize(duplicate_strategy: :skip)
+        unless STRATEGIES.include?(duplicate_strategy)
+          raise ArgumentError,
+                "duplicate_strategy must be one of #{STRATEGIES.join(', ')}, got #{duplicate_strategy}"
+        end
+
+        @duplicate_strategy = duplicate_strategy
+        @mapper = TermMapper.new
+      end
+
+      def import_new(xml_files, output:, shortname: nil, version: nil, **opts)
+        raw_concepts = extract_all_concepts(xml_files)
+        concepts, conflicts, skipped = dedup_concepts(raw_concepts)
+
+        if output.end_with?(".gcr")
+          unless shortname
+            raise ArgumentError,
+                  "--shortname is required for GCR output"
+          end
+          unless version
+            raise ArgumentError,
+                  "--version is required for GCR output"
+          end
+
+          create_gcr(concepts, output, shortname: shortname, version: version,
+                                       **opts)
+        else
+          save_dataset(concepts, output)
+        end
+
+        ImportResult.new(
+          concepts: concepts,
+          conflicts: conflicts,
+          source_files: xml_files,
+          skipped_count: skipped,
+        )
+      end
+
+      def import_into_existing(xml_files, dataset_path)
+        existing = load_existing(dataset_path)
+        new_concepts = extract_all_concepts(xml_files)
+        index = build_concept_index(existing)
+
+        result_state = apply_with_dedup(new_concepts, existing, index)
+
+        save_to_path(existing, dataset_path)
+
+        ImportResult.new(
+          concepts: existing.managed_concepts,
+          conflicts: result_state.conflicts,
+          source_files: xml_files,
+          skipped_count: result_state.skipped,
+        )
+      end
+
+      DedupState = Struct.new(:conflicts, :skipped, keyword_init: true)
+
+      private
+
+      def apply_with_dedup(new_concepts, existing, index)
+        state = DedupState.new(conflicts: [], skipped: 0)
+
+        new_concepts.each do |mc|
+          key = concept_key(mc)
+          existing_mc = index[key]
+
+          if existing_mc.nil?
+            existing.store(mc)
+            index[key] = mc
+          else
+            state.conflicts << DuplicateConflict.new(
+              new_concept: mc, existing_concept: existing_mc, key: key,
+            )
+            handle_duplicate(existing, existing_mc, mc, index, key, state)
+          end
+        end
+
+        state
+      end
+
+      def handle_duplicate(existing, old_mc, new_mc, index, key, state)
+        case duplicate_strategy
+        when :skip
+          state.skipped += 1
+        when :replace
+          replace_in_collection(existing, old_mc, new_mc)
+          index[key] = new_mc
+        when :merge
+          merge_concept(old_mc, new_mc)
+        end
+      end
+
+      def extract_all_concepts(xml_files)
+        xml_files.flat_map do |path|
+          extractor = TermExtractor.new(path)
+          terms = extractor.extract
+          terms.map { |t| @mapper.map(t) }
+        end
+      end
+
+      def dedup_concepts(concepts) # rubocop:disable Metrics/AbcSize, Metrics/CyclomaticComplexity
+        seen = {}
+        conflicts = []
+        skipped = 0
+        unique = []
+
+        concepts.each do |mc|
+          key = concept_key(mc)
+          if key.first.empty? || seen[key].nil?
+            unique << mc
+            seen[key] = mc unless key.first.empty?
+          else
+            conflicts << DuplicateConflict.new(
+              new_concept: mc, existing_concept: seen[key], key: key,
+            )
+            skipped += apply_dedup_to_unique(unique, seen, mc, key)
+          end
+        end
+
+        [unique, conflicts, skipped]
+      end
+
+      def apply_dedup_to_unique(unique, seen, new_mc, key)
+        case duplicate_strategy
+        when :skip
+          1
+        when :replace
+          unique.delete(seen[key])
+          unique << new_mc
+          seen[key] = new_mc
+          0
+        when :merge
+          merge_concept(seen[key], new_mc)
+          0
+        end
+      end
+
+      def concept_key(managed_concept)
+        designation = managed_concept.default_designation.to_s.downcase.strip
+        domain = begin
+          l10n = managed_concept.default_lang
+          l10n&.data&.domain.to_s.downcase.strip
+        end
+        [designation, domain]
+      end
+
+      def build_concept_index(collection)
+        index = {}
+        collection.each do |mc|
+          key = concept_key(mc)
+          index[key] = mc unless key.first.empty?
+        end
+        index
+      end
+
+      def merge_concept(existing_mc, new_mc)
+        new_mc.localizations.each do |l10n|
+          lang = l10n.language_code
+          if existing_mc.localization(lang).nil?
+            existing_mc.add_localization(l10n)
+          end
+        end
+      end
+
+      def replace_in_collection(collection, old_mc, new_mc)
+        collection.managed_concepts.delete(old_mc)
+        collection.store(new_mc)
+      end
+
+      def load_existing(path)
+        collection = ManagedConceptCollection.new
+        if path.end_with?(".gcr")
+          package = GcrPackage.load(path)
+          package.concepts.each { |mc| collection.store(mc) }
+        else
+          concepts = ConceptCollector.collect(path)
+          concepts.each { |mc| collection.store(mc) }
+        end
+        collection
+      end
+
+      def save_to_path(collection, path)
+        if path.end_with?(".gcr")
+          tmpdir = build_temp_dataset(collection.managed_concepts)
+          begin
+            GC.start
+            tmp_gcr = "#{path}.tmp.#{Process.pid}"
+            GcrPackage.create_from_directory(
+              tmpdir,
+              output: tmp_gcr,
+              shortname: File.basename(path, ".gcr"),
+              version: "1.0.0",
+            )
+            FileUtils.rm_f(path)
+            FileUtils.mv(tmp_gcr, path)
+          ensure
+            FileUtils.rm_rf(tmpdir)
+            FileUtils.rm_f(tmp_gcr)
+          end
+        else
+          save_dataset(collection.managed_concepts, path)
+        end
+      end
+
+      def save_dataset(concepts, dir)
+        concepts_dir = File.join(dir, "concepts")
+        FileUtils.mkdir_p(concepts_dir)
+        collection = ManagedConceptCollection.new
+        concepts.each { |mc| collection.store(mc) }
+        collection.save_grouped_concepts_to_files(concepts_dir)
+      end
+
+      def create_gcr(concepts, output, shortname:, version:, **opts)
+        tmpdir = build_temp_dataset(concepts)
+        begin
+          GcrPackage.create_from_directory(
+            tmpdir,
+            output: output,
+            shortname: shortname,
+            version: version,
+            **opts,
+          )
+        ensure
+          FileUtils.rm_rf(tmpdir)
+        end
+      end
+
+      def build_temp_dataset(concepts)
+        tmpdir = Dir.mktmpdir("glossarist-sts-import")
+        concepts_dir = File.join(tmpdir, "concepts")
+        FileUtils.mkdir_p(concepts_dir)
+
+        collection = ManagedConceptCollection.new
+        concepts.each { |mc| collection.store(mc) }
+        collection.save_grouped_concepts_to_files(concepts_dir)
+
+        tmpdir
+      end
+    end
+  end
+end

data/lib/glossarist/sts/term_extractor.rb

@@ -0,0 +1,186 @@
+# frozen_string_literal: true
+
+module Glossarist
+  module Sts
+    class TermExtractor
+      def initialize(xml_path)
+        raw = File.read(xml_path)
+        @standard = ::Sts::IsoSts::Standard.from_xml(raw)
+        @source_ref = extract_source_ref
+      end
+
+      def extract
+        term_secs = collect_term_secs
+        term_secs.filter_map do |ts|
+          next unless ts.term_entry
+
+          build_extracted_term(ts)
+        end
+      end
+
+      private
+
+      def collect_term_secs
+        secs = []
+        walk_sections(@standard.body, secs) if @standard.body
+        secs
+      end
+
+      def walk_sections(container, collected)
+        collect_term_secs_from(container, collected)
+        walk_child_secs(container, collected)
+      end
+
+      def collect_term_secs_from(container, collected)
+        secs = container.term_sec
+        secs&.each do |ts|
+          collected << ts
+          walk_sections(ts, collected) if ts.term_sec&.any?
+        end
+      end
+
+      def walk_child_secs(container, collected)
+        secs = container_child_secs(container)
+        secs&.each { |s| walk_sections(s, collected) }
+      end
+
+      def container_child_secs(container)
+        case container
+        when ::Sts::IsoSts::Body, ::Sts::IsoSts::Sec
+          container.sec
+        end
+      end
+
+      def build_extracted_term(term_sec)
+        entry = term_sec.term_entry
+        label_text = extract_label(term_sec)
+
+        lang_sets = entry.lang_set.filter_map do |ls|
+          build_lang_set(ls)
+        end
+
+        Sts::ExtractedTerm.new(
+          id: entry.id,
+          label: label_text,
+          source_ref: @source_ref,
+          lang_sets: lang_sets,
+        )
+      end
+
+      def extract_label(term_sec)
+        label = term_sec.label
+        return nil unless label
+
+        label.content&.join.to_s.strip
+      end
+
+      def build_lang_set(lang_set) # rubocop:disable Metrics/AbcSize
+        lang_code = Sts.convert_language_code(lang_set.lang.to_s)
+
+        Sts::ExtractedLangSet.new(
+          language_code: lang_code,
+          definition_text: extract_definition_text(lang_set),
+          note_texts: extract_note_texts(lang_set),
+          example_texts: extract_example_texts(lang_set),
+          source_texts: extract_source_texts(lang_set),
+          domain: extract_subject_field(lang_set),
+          designations: lang_set.tig.filter_map do |tig|
+            build_designation(tig)
+          end,
+        )
+      end
+
+      def extract_definition_text(lang_set)
+        definitions = lang_set.definition
+        return "" unless definitions&.any?
+
+        definitions.first.value&.join.to_s.strip
+      end
+
+      def extract_note_texts(lang_set)
+        lang_set.note.filter_map do |n|
+          text = n.value&.join.to_s.strip
+          text unless text.empty?
+        end
+      end
+
+      def extract_example_texts(lang_set)
+        lang_set.example.filter_map do |e|
+          text = e.value&.join.to_s.strip
+          text unless text.empty?
+        end
+      end
+
+      def extract_source_texts(lang_set)
+        lang_set.source.filter_map do |s|
+          text = s.value&.join.to_s.strip
+          text unless text.empty?
+        end
+      end
+
+      def extract_subject_field(lang_set)
+        fields = lang_set.subject_field
+        return nil unless fields&.any?
+
+        text = fields.first.value&.join.to_s.strip
+        text unless text.empty?
+      end
+
+      def build_designation(tig)
+        Sts::ExtractedDesignation.new(
+          term: resolve_term_text(tig),
+          type: map_term_type(tig),
+          normative_status: map_normative_status(tig),
+          part_of_speech: tig.pos&.value,
+          abbreviation_type: map_abbreviation_type(tig),
+        )
+      end
+
+      def resolve_term_text(tig)
+        tig.term&.value&.join.to_s.strip
+      end
+
+      def map_term_type(tig)
+        raw = tig.term_type&.value.to_s
+        mapped = TERM_TYPE_MAP[raw]
+        mapped.nil? || raw.empty? ? "expression" : mapped
+      end
+
+      def map_abbreviation_type(tig)
+        raw = tig.term_type&.value.to_s
+        return nil unless TERM_TYPE_MAP[raw] == "abbreviation"
+
+        raw == "acronym" ? "acronym" : "truncation"
+      end
+
+      def map_normative_status(tig)
+        NORMATIVE_STATUS_MAP[tig.normative_authorization&.value.to_s]
+      end
+
+      def extract_source_ref # rubocop:disable Metrics/AbcSize, Metrics/CyclomaticComplexity, Metrics/PerceivedComplexity
+        front = @standard.front
+        return nil unless front
+
+        meta = front.iso_meta || front.std_meta
+        return nil unless meta
+
+        refs = meta.std_ref
+        return nil unless refs&.any?
+
+        best_ref = refs.find { |r| r.type == "dated" } ||
+          refs.find { |r| r.type == "undated" } ||
+          refs.first
+
+        extract_ref_text(best_ref)
+      end
+
+      def extract_ref_text(ref)
+        if ref.value.is_a?(String)
+          ref.value.to_s.strip
+        else
+          ref.content&.join.to_s.strip
+        end
+      end
+    end
+  end
+end

data/lib/glossarist/sts/term_mapper.rb

@@ -0,0 +1,118 @@
+# frozen_string_literal: true
+
+module Glossarist
+  module Sts
+    class TermMapper
+      def map(extracted_term)
+        concept_id = extracted_term.label || extracted_term.id
+
+        mc = Glossarist::ManagedConcept.new(data: { id: concept_id })
+
+        extracted_term.lang_sets.each do |ls|
+          mc.add_localization(build_localized_concept(ls,
+                                                      extracted_term.source_ref))
+        end
+
+        mc
+      end
+
+      private
+
+      def build_localized_concept(lang_set, source_ref)
+        terms = lang_set.designations.map { |d| build_designation(d) }
+
+        Glossarist::LocalizedConcept.of_yaml(
+          "data" => {
+            "language_code" => lang_set.language_code,
+            "terms" => terms,
+            "definition" => build_definitions(lang_set.definition_text),
+            "notes" => build_detailed_definitions(lang_set.note_texts),
+            "examples" => build_detailed_definitions(lang_set.example_texts),
+            "sources" => build_sources(lang_set.source_texts, source_ref),
+            "domain" => lang_set.domain,
+            "entry_status" => "valid",
+          },
+        )
+      end
+
+      def build_definitions(text)
+        return [] unless text && !text.empty?
+
+        [{ "content" => text }]
+      end
+
+      def build_detailed_definitions(texts)
+        texts.filter_map do |text|
+          next if text.empty?
+
+          { "content" => text }
+        end
+      end
+
+      def build_designation(ext_desig)
+        case ext_desig.type
+        when "abbreviation"
+          build_abbreviation_designation(ext_desig)
+        when "symbol"
+          build_symbol_designation(ext_desig)
+        else
+          build_expression_designation(ext_desig)
+        end
+      end
+
+      def build_expression_designation(ext_desig)
+        hash = {
+          "type" => "expression",
+          "designation" => ext_desig.term,
+          "normative_status" => ext_desig.normative_status,
+        }.compact
+
+        if ext_desig.part_of_speech
+          hash["grammar_info"] =
+            [{ "part_of_speech" => ext_desig.part_of_speech }]
+        end
+
+        hash
+      end
+
+      def build_abbreviation_designation(ext_desig)
+        {
+          "type" => "abbreviation",
+          "designation" => ext_desig.term,
+          "normative_status" => ext_desig.normative_status,
+          "abbreviation_type" => ext_desig.abbreviation_type,
+        }.compact
+      end
+
+      def build_symbol_designation(ext_desig)
+        {
+          "type" => "symbol",
+          "designation" => ext_desig.term,
+          "normative_status" => ext_desig.normative_status,
+        }.compact
+      end
+
+      def build_sources(source_texts, source_ref)
+        sources = []
+        if source_ref
+          sources << {
+            "status" => "identical",
+            "type" => "authoritative",
+            "origin" => { "text" => source_ref },
+          }
+        end
+
+        source_texts.each do |text|
+          next if text.empty?
+
+          sources << {
+            "type" => "authoritative",
+            "origin" => { "text" => text },
+          }
+        end
+
+        sources
+      end
+    end
+  end
+end

data/lib/glossarist/sts.rb

@@ -0,0 +1,87 @@
+# frozen_string_literal: true
+
+require "sts"
+
+module Glossarist
+  module Sts
+    autoload :ExtractedDesignation, "#{__dir__}/sts/extracted_designation"
+    autoload :ExtractedLangSet,     "#{__dir__}/sts/extracted_lang_set"
+    autoload :ExtractedTerm,        "#{__dir__}/sts/extracted_term"
+    autoload :ImportResult,         "#{__dir__}/sts/import_result"
+    autoload :Importer,             "#{__dir__}/sts/importer"
+    autoload :TermExtractor,        "#{__dir__}/sts/term_extractor"
+    autoload :TermMapper,           "#{__dir__}/sts/term_mapper"
+
+    ISO_639_1_TO_639_2 = {
+      "aa" => "aar", "ab" => "abk", "af" => "afr", "ak" => "aka",
+      "am" => "amh", "an" => "arg", "ar" => "ara", "as" => "asm",
+      "av" => "ava", "ay" => "aym", "az" => "aze", "ba" => "bak",
+      "be" => "bel", "bg" => "bul", "bh" => "bih", "bi" => "bis",
+      "bm" => "bam", "bn" => "ben", "bo" => "bod", "br" => "bre",
+      "bs" => "bos", "ca" => "cat", "ce" => "che", "ch" => "cha",
+      "co" => "cos", "cr" => "cre", "cs" => "ces", "cu" => "chu",
+      "cv" => "chv", "cy" => "cym", "da" => "dan", "de" => "deu",
+      "dv" => "div", "dz" => "dzo", "ee" => "ewe", "el" => "ell",
+      "en" => "eng", "eo" => "epo", "es" => "spa", "et" => "est",
+      "eu" => "eus", "fa" => "fas", "ff" => "ful", "fi" => "fin",
+      "fj" => "fij", "fo" => "fao", "fr" => "fra", "fy" => "fry",
+      "ga" => "gle", "gd" => "gla", "gl" => "glg", "gn" => "grn",
+      "gu" => "guj", "gv" => "glv", "ha" => "hau", "he" => "heb",
+      "hi" => "hin", "ho" => "hmo", "hr" => "hrv", "ht" => "hat",
+      "hu" => "hun", "hy" => "hye", "hz" => "her", "ia" => "ina",
+      "id" => "ind", "ie" => "ile", "ig" => "ibo", "ii" => "iii",
+      "ik" => "ipk", "io" => "ido", "is" => "isl", "it" => "ita",
+      "iu" => "iku", "ja" => "jpn", "jv" => "jav", "ka" => "kat",
+      "kg" => "kon", "ki" => "kik", "kj" => "kua", "kk" => "kaz",
+      "kl" => "kal", "km" => "khm", "kn" => "kan", "ko" => "kor",
+      "kr" => "kau", "ks" => "kas", "ku" => "kur", "kv" => "kom",
+      "kw" => "cor", "ky" => "kir", "la" => "lat", "lb" => "ltz",
+      "lg" => "lug", "li" => "lim", "ln" => "lin", "lo" => "lao",
+      "lt" => "lit", "lu" => "lub", "lv" => "lav", "mg" => "mlg",
+      "mh" => "mah", "mi" => "mri", "mk" => "mkd", "ml" => "mal",
+      "mn" => "mon", "mr" => "mar", "ms" => "msa", "mt" => "mlt",
+      "my" => "mya", "na" => "nau", "nb" => "nob", "nd" => "nde",
+      "ne" => "nep", "ng" => "ndo", "nl" => "nld", "nn" => "nno",
+      "no" => "nor", "nr" => "nbl", "nv" => "nav", "ny" => "nya",
+      "oc" => "oci", "oj" => "oji", "om" => "orm", "or" => "ori",
+      "os" => "oss", "pa" => "pan", "pi" => "pli", "pl" => "pol",
+      "ps" => "pus", "pt" => "por", "qu" => "que", "rm" => "roh",
+      "rn" => "run", "ro" => "ron", "ru" => "rus", "rw" => "kin",
+      "sa" => "san", "sc" => "srd", "sd" => "snd", "se" => "sme",
+      "sg" => "sag", "si" => "sin", "sk" => "slk", "sl" => "slv",
+      "sm" => "smo", "sn" => "sna", "so" => "som", "sq" => "sqi",
+      "sr" => "srp", "ss" => "ssw", "st" => "sot", "su" => "sun",
+      "sv" => "swe", "sw" => "swa", "ta" => "tam", "te" => "tel",
+      "tg" => "tgk", "th" => "tha", "ti" => "tir", "tk" => "tuk",
+      "tl" => "tgl", "tn" => "tsn", "to" => "ton", "tr" => "tur",
+      "ts" => "tso", "tt" => "tat", "tw" => "twi", "ty" => "tah",
+      "ug" => "uig", "uk" => "ukr", "ur" => "urd", "uz" => "uzb",
+      "ve" => "ven", "vi" => "vie", "vo" => "vol", "wa" => "wln",
+      "wo" => "wol", "xh" => "xho", "yi" => "yid", "yo" => "yor",
+      "za" => "zha", "zh" => "zho", "zu" => "zul"
+    }.freeze
+
+    TERM_TYPE_MAP = {
+      "acronym" => "abbreviation",
+      "abbreviation" => "abbreviation",
+      "fullForm" => "expression",
+      "symbol" => "symbol",
+      "variant" => "expression",
+      "equation" => "expression",
+      "formula" => "expression",
+    }.freeze
+
+    NORMATIVE_STATUS_MAP = {
+      "preferredTerm" => "preferred",
+      "admittedTerm" => "admitted",
+      "deprecatedTerm" => "deprecated",
+    }.freeze
+
+    def self.convert_language_code(code)
+      return code if code.nil?
+      return code if code.length == 3
+
+      ISO_639_1_TO_639_2[code] || code
+    end
+  end
+end

data/lib/glossarist/transforms/concept_to_skos_transform.rb

@@ -1,7 +1,5 @@
 # frozen_string_literal: true
 
-require_relative "../rdf"
-
 module Glossarist
   module Transforms
     class ConceptToSkosTransform

data/lib/glossarist/version.rb

@@ -4,5 +4,5 @@
 #
 
 module Glossarist
-  VERSION = "2.6.2"
+  VERSION = "2.6.3"
 end

data/lib/glossarist.rb

@@ -7,14 +7,13 @@ require "psych"
 require "thor"
 require "lutaml/model"
 
-require_relative "glossarist/glossary_definition"
-
 module Glossarist
   autoload :Asset,                    "glossarist/asset"
   autoload :Citation,                 "glossarist/citation"
   autoload :CLI,                      "glossarist/cli"
   autoload :CollectionConfig,         "glossarist/collection_config"
   autoload :Collection,               "glossarist/collection"
+  autoload :Collections,              "glossarist/collections"
   autoload :Concept,                  "glossarist/concept"
   autoload :ConceptData,              "glossarist/concept_data"
   autoload :ConceptReference,         "glossarist/concept_reference"
@@ -35,10 +34,10 @@ module Glossarist
   autoload :DetailedDefinition,       "glossarist/detailed_definition"
   autoload :Designation,              "glossarist/designation"
   autoload :Error,                    "glossarist/error"
-  autoload :GcrPackage,              "glossarist/gcr_package"
-  autoload :GcrMetadata,             "glossarist/gcr_metadata"
-  autoload :GcrStatistics,           "glossarist/gcr_statistics"
-  autoload :GcrValidator,            "glossarist/gcr_validator"
+  autoload :GcrPackage,               "glossarist/gcr_package"
+  autoload :GcrMetadata,              "glossarist/gcr_metadata"
+  autoload :GcrStatistics,            "glossarist/gcr_statistics"
+  autoload :GcrValidator,             "glossarist/gcr_validator"
   autoload :InvalidTypeError, "glossarist/error/invalid_type_error"
   autoload :InvalidLanguageCodeError,
            "glossarist/error/invalid_language_code_error"
@@ -52,16 +51,20 @@ module Glossarist
   autoload :ManagedConceptData,       "glossarist/managed_concept_data"
   autoload :NonVerbRep,               "glossarist/non_verb_rep"
   autoload :RelatedConcept,           "glossarist/related_concept"
+  autoload :Rdf,                      "glossarist/rdf"
+  autoload :Sts,                      "glossarist/sts"
+  autoload :Transforms,               "glossarist/transforms"
   autoload :SchemaMigration,          "glossarist/schema_migration"
   autoload :UrnResolver,              "glossarist/urn_resolver"
   autoload :Utilities,                "glossarist/utilities"
-  autoload :RegisterData, "glossarist/register_data"
+  autoload :RegisterData,             "glossarist/register_data"
   autoload :ValidationResult,         "glossarist/validation_result"
   autoload :V1,                       "glossarist/v1"
 end
 
 require_relative "glossarist/version"
 require_relative "glossarist/collections"
+require_relative "glossarist/glossary_definition"
 
 module Glossarist
   LANG_CODES = %w[eng ara deu fra spa ita jpn kor pol por srp swe zho rus fin

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: glossarist
 version: !ruby/object:Gem::Version
-  version: 2.6.2
+  version: 2.6.3
 platform: ruby
 authors:
 - Ribose
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-05-07 00:00:00.000000000 Z
+date: 2026-05-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: lutaml-model
@@ -122,6 +122,7 @@ files:
 - lib/glossarist/citation.rb
 - lib/glossarist/cli.rb
 - lib/glossarist/cli/export_command.rb
+- lib/glossarist/cli/import_command.rb
 - lib/glossarist/cli/package_command.rb
 - lib/glossarist/cli/upgrade_command.rb
 - lib/glossarist/cli/validate_command.rb
@@ -192,6 +193,14 @@ files:
 - lib/glossarist/resolution_adapter/remote.rb
 - lib/glossarist/resolution_adapter/route.rb
 - lib/glossarist/schema_migration.rb
+- lib/glossarist/sts.rb
+- lib/glossarist/sts/extracted_designation.rb
+- lib/glossarist/sts/extracted_lang_set.rb
+- lib/glossarist/sts/extracted_term.rb
+- lib/glossarist/sts/import_result.rb
+- lib/glossarist/sts/importer.rb
+- lib/glossarist/sts/term_extractor.rb
+- lib/glossarist/sts/term_mapper.rb
 - lib/glossarist/transforms.rb
 - lib/glossarist/transforms/concept_to_skos_transform.rb
 - lib/glossarist/transforms/concept_to_tbx_transform.rb