glossarist 2.6.1 → 2.6.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b4e48f1d237829b78cd052e39afdd7c952c468be894e25856f79f93471ea2dc6
-  data.tar.gz: f6502f7012e30138193c4c28eee2ab551020edf27ff0c6e08cc39939e5d0c0c3
+  metadata.gz: 1f3a8ec372c1c3e7a93ed7c2bad8ed2837f8f5bcd5ce4ae340bbb9f3b5ddaa75
+  data.tar.gz: e7c0672fc648ea748cff12bfc00a1ea62665aeaa20e4cf8a86dde1419a6094df
 SHA512:
-  metadata.gz: bcfb39fe52138d23d489cfbff45f62b0f00161d3183ef66dbb5718fcbc30694ef5e426bc9f7797329480dddb01a7c96b8f6e1dfc43e392032441bb62487c723a
-  data.tar.gz: 289911c5a5851389cb5e37fbc07bd45825b00cdd51fa8cac5679168af3ec9e2b7313f6afbd7093fb93b35384bfc7318dcb97a22d72869f78a321883f4ab299a4
+  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

@@ -1,12 +1,12 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2026-05-06 18:35:41 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: 5
+# Offense count: 7
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: TreatCommentsAsGroupSeparators, ConsiderPunctuation.
 Bundler/OrderedGems:
@@ -18,27 +18,77 @@ Gemspec/RequiredRubyVersion:
   Exclude:
     - 'glossarist.gemspec'
 
+# Offense count: 4
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle, IndentationWidth.
+# SupportedStyles: with_first_argument, with_fixed_indentation
+Layout/ArgumentAlignment:
+  Exclude:
+    - 'lib/glossarist/sts/import_result.rb'
+    - 'lib/glossarist/sts/importer.rb'
+    - 'lib/glossarist/sts/term_mapper.rb'
+
 # Offense count: 1
 # This cop supports safe autocorrection (--autocorrect).
-Layout/ClosingParenthesisIndentation:
+# Configuration parameters: IndentationWidth.
+Layout/AssignmentIndentation:
   Exclude:
-    - 'spec/unit/concept_set_spec.rb'
+    - '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/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).
+Layout/BlockEndNewline:
+  Exclude:
+    - 'lib/glossarist/sts/term_extractor.rb'
+    - 'spec/unit/sts/term_extractor_spec.rb'
+    - 'spec/unit/sts/term_mapper_spec.rb'
 
 # Offense count: 1
 # This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyle, IndentationWidth.
-# SupportedStyles: consistent, consistent_relative_to_receiver, special_for_inner_method_call, special_for_inner_method_call_in_parentheses
-Layout/FirstArgumentIndentation:
+# 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:
-    - 'spec/unit/concept_set_spec.rb'
+    - 'lib/glossarist/sts/importer.rb'
 
-# Offense count: 202
+# 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/sts/term_extractor.rb'
+    - 'spec/unit/sts/term_extractor_spec.rb'
+    - 'spec/unit/sts/term_mapper_spec.rb'
+
+# 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: 7
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: AllowInHeredoc.
+Layout/TrailingWhitespace:
+  Exclude:
+    - 'lib/glossarist/sts/import_result.rb'
+    - 'lib/glossarist/sts/importer.rb'
+    - 'lib/glossarist/sts/term_mapper.rb'
+
 # Offense count: 1
 # Configuration parameters: AllowedMethods.
 # AllowedMethods: enums
@@ -54,7 +104,7 @@ Lint/UnusedMethodArgument:
   Exclude:
     - 'lib/glossarist/dataset_validator.rb'
 
-# Offense count: 23
+# Offense count: 24
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes, Max.
 Metrics/AbcSize:
   Exclude:
@@ -73,12 +123,6 @@ Metrics/AbcSize:
     - 'lib/glossarist/utilities/uuid.rb'
     - 'spec/unit/concept_collector_spec.rb'
 
-# Offense count: 1
-# Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
-# AllowedMethods: refine
-Metrics/BlockLength:
-  Max: 28
-
 # Offense count: 19
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/CyclomaticComplexity:
@@ -96,7 +140,7 @@ 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
@@ -135,6 +179,19 @@ Naming/VariableNumber:
   Exclude:
     - 'spec/unit/rdf/skos_vocabulary_spec.rb'
 
+# 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
+# ProceduralMethods: benchmark, bm, bmbm, create, each_with_object, measure, new, realtime, tap, with_object
+# FunctionalMethods: let, let!, subject, watch
+# AllowedMethods: lambda, proc, it
+Style/BlockDelimiters:
+  Exclude:
+    - '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).
 # Configuration parameters: MaxUnannotatedPlaceholdersAllowed, Mode, AllowedMethods, AllowedPatterns.
@@ -142,6 +199,12 @@ Naming/VariableNumber:
 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/concept_collector.rb

@@ -41,13 +41,35 @@ module Glossarist
       def v1_concepts?(dir)
         concepts_dir = File.join(dir, "concepts")
         File.directory?(concepts_dir) &&
+          !v2_flat_concepts?(dir) &&
+          !managed_concepts?(dir) &&
           Dir.glob(File.join(concepts_dir, "*.yaml")).any? do |f|
             V1::Concept.from_file(f)&.termid?
           end
       end
 
       def v2_concepts?(dir)
-        File.directory?(File.join(dir, "geolexica-v2"))
+        File.directory?(File.join(dir, "geolexica-v2")) ||
+          v2_flat_concepts?(dir)
+      end
+
+      def v2_flat_concepts?(dir)
+        return false if managed_concepts?(dir)
+
+        concepts_dir = File.join(dir, "concepts")
+        return false unless File.directory?(concepts_dir)
+
+        Dir.glob(File.join(concepts_dir, "*.yaml")).first(5).any? do |f|
+          v2_flat_concept_file?(f)
+        end
+      end
+
+      def v2_flat_concept_file?(path)
+        raw = File.read(path, encoding: "utf-8")
+        doc = ConceptDocument.from_yamls(raw)
+        !!doc.concept&.data&.id
+      rescue StandardError
+        false
       end
 
       def managed_concepts?(dir)
@@ -74,24 +96,32 @@ module Glossarist
       end
 
       def collect_v2_concepts(dir)
-        v2_dir = File.join(dir, "geolexica-v2")
-        if File.directory?(File.join(v2_dir, "concepts"))
-          collect_managed_concepts(v2_dir)
+        if v2_flat_concepts?(dir)
+          collect_grouped_v2_concepts(File.join(dir, "concepts"))
         else
-          collect_grouped_v2_concepts(v2_dir)
+          v2_dir = File.join(dir, "geolexica-v2")
+          if File.directory?(File.join(v2_dir, "concepts"))
+            collect_managed_concepts(v2_dir)
+          else
+            collect_grouped_v2_concepts(v2_dir)
+          end
         end
       end
 
       def each_v2_concept(dir, &block)
-        v2_dir = File.join(dir, "geolexica-v2")
-        if File.directory?(File.join(v2_dir, "concepts"))
-          each_managed_concept(v2_dir, &block)
+        if v2_flat_concepts?(dir)
+          each_grouped_v2_concepts(File.join(dir, "concepts"), &block)
         else
-          each_grouped_v2_concept(v2_dir, &block)
+          v2_dir = File.join(dir, "geolexica-v2")
+          if File.directory?(File.join(v2_dir, "concepts"))
+            each_managed_concept(v2_dir, &block)
+          else
+            each_grouped_v2_concepts(v2_dir, &block)
+          end
         end
       end
 
-      def each_grouped_v2_concept(v2_dir, &block)
+      def each_grouped_v2_concepts(v2_dir, &block)
         collection = ManagedConceptCollection.new
         manager = ConceptManager.new(path: v2_dir)
         manager.load_from_files(collection: collection)

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