glossarist 2.8.7 → 2.8.11

data/lib/glossarist/sts/term_extractor.rb

@@ -7,6 +7,7 @@ module Glossarist
         raw = File.read(xml_path)
         @standard = ::Sts::IsoSts::Standard.from_xml(raw)
         @source_ref = extract_source_ref
+        @std_prefix = extract_std_prefix(@source_ref)
       end
 
       def extract
@@ -90,27 +91,104 @@ module Glossarist
         )
       end
 
+      ELEMENT_NAME_TO_ATTR = {
+        "entailedTerm" => :entailed_term,
+        "xref" => :xref,
+        "italic" => :italic,
+        "bold" => :bold,
+        "sup" => :sup,
+        "sub" => :sub,
+        "monospace" => :monospace,
+        "std" => :std,
+        "math" => :math,
+        "inline-formula" => :inline_formula,
+        "list" => :list,
+        "styled-content" => :styled_content,
+        "ext-link" => :ext_link,
+      }.freeze
+
       def extract_definition_text(lang_set)
         definitions = lang_set.definition
         return "" unless definitions&.any?
 
-        definitions.first.value&.join.to_s.strip
+        extract_mixed_text(definitions.first)
       end
 
       def extract_note_texts(lang_set)
         lang_set.note.filter_map do |n|
-          text = n.value&.join.to_s.strip
+          text = extract_mixed_text(n)
           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 = extract_mixed_text(e)
           text unless text.empty?
         end
       end
 
+      def extract_mixed_text(mixed_element)
+        indices = Hash.new(0)
+        parts = []
+
+        mixed_element.element_order.each do |elem|
+          if elem.node_type == :text
+            parts << elem.text_content.to_s
+          else
+            attr_name = ELEMENT_NAME_TO_ATTR[elem.name]
+            next unless attr_name
+
+            collection = mixed_element.class.attributes.key?(attr_name) &&
+              mixed_element.public_send(attr_name)
+            next unless collection
+
+            child = collection[indices[elem.name]]
+            if child
+              if elem.name == "entailedTerm"
+                parts << format_entailed_term(child)
+              else
+                text = child_value_text(child)
+                parts << text if text
+              end
+            end
+            indices[elem.name] += 1
+          end
+        end
+
+        normalize_whitespace(parts.join)
+      end
+
+      # entailedTerm → "{{19135:2026:3.5.1,concept}}"
+      # format: {{concept_id, render_text}}
+      def format_entailed_term(entailed)
+        raw_text = entailed.value.to_s
+        designation = raw_text.gsub(/\s+\(\d[\d.]*\)\s*\z/, "").strip
+        section = extract_section_from_target(entailed.target)
+
+        if @std_prefix && section
+          "{{#{@std_prefix}:#{section},#{designation}}}"
+        else
+          raw_text.strip
+        end
+      end
+
+      # "term_3.5.1" → "3.5.1", "term_3.8.2-1" → "3.8.2"
+      def extract_section_from_target(target)
+        return nil unless target
+
+        match = target.match(/term_(\d+(?:\.\d+)*)/)
+        match ? match[1] : nil
+      end
+
+      def child_value_text(child)
+        val = child.value
+        case val
+        when Array then val.join.to_s
+        when String then val
+        end
+      end
+
       def extract_source_texts(lang_set)
         lang_set.source.filter_map do |s|
           text = s.value&.join.to_s.strip
@@ -175,12 +253,33 @@ module Glossarist
       end
 
       def extract_ref_text(ref)
-        if ref.value.is_a?(String)
-          ref.value.to_s.strip
+        case ref
+        when ::Sts::IsoSts::StdRef
+          normalize_whitespace(ref.content.join.to_s)
+        when ::Sts::NisoSts::StandardRef
+          normalize_whitespace(ref.value.to_s)
         else
-          ref.content&.join.to_s.strip
+          ""
         end
       end
+
+      def normalize_whitespace(text)
+        text.gsub(/[\s\u00a0]+/, " ").strip
+      end
+
+      # "ISO 19101-1:2014" → "19101-1:2014", "ISO/TS 19130-2:2014" → "TS-19130-2:2014"
+      def extract_std_prefix(source_ref)
+        return nil unless source_ref
+
+        match = source_ref.match(/\AISO(?:\/(\p{Upper}+))? (\d+(?:-\d+)?):(\d+)\z/)
+        return nil unless match
+
+        type_part = match[1]
+        number = match[2]
+        year = match[3]
+
+        type_part ? "#{type_part}-#{number}:#{year}" : "#{number}:#{year}"
+      end
     end
   end
 end

data/lib/glossarist/transforms/concept_to_gloss_transform.rb

@@ -122,7 +122,7 @@ module Glossarist
 
         dd_attrs = if data
                      data.class.detailed_definition_fields.to_h do |field|
-                       [field, build_gloss_definitions(data.send(field))]
+                       [field, build_gloss_definitions(data.public_send(field))]
                      end
                    else
                      { definition: [], notes: [], examples: [] }

data/lib/glossarist/v2/managed_concept.rb

@@ -9,15 +9,13 @@ module Glossarist
 
       key_value do
         map :data, to: :data
-        map :id, with: { to: :identifier_to_yaml, from: :identifier_from_yaml }
-        map :identifier,
-            with: { to: :identifier_to_yaml, from: :identifier_from_yaml }
         map :related, to: :related
         map :dates, to: :dates
         map %i[date_accepted dateAccepted],
             with: { from: :date_accepted_from_yaml, to: :date_accepted_to_yaml }
         map :status, to: :status
-        map :uuid, to: :uuid, with: { from: :uuid_from_yaml, to: :uuid_to_yaml }
+        map %i[id uuid], to: :uuid,
+                         with: { from: :uuid_from_yaml, to: :uuid_to_yaml }
         map :sources, to: :sources
       end
     end

data/lib/glossarist/v3/managed_concept.rb

@@ -9,15 +9,13 @@ module Glossarist
 
       key_value do
         map :data, to: :data
-        map :id, with: { to: :identifier_to_yaml, from: :identifier_from_yaml }
-        map :identifier,
-            with: { to: :identifier_to_yaml, from: :identifier_from_yaml }
         map :related, to: :related
         map :dates, to: :dates
         map %i[date_accepted dateAccepted],
             with: { from: :date_accepted_from_yaml, to: :date_accepted_to_yaml }
         map :status, to: :status
-        map :uuid, to: :uuid, with: { from: :uuid_from_yaml, to: :uuid_to_yaml }
+        map %i[id uuid], to: :uuid,
+                         with: { from: :uuid_from_yaml, to: :uuid_to_yaml }
         map :schema_version, to: :schema_version
         map :sources, to: :sources
       end

data/lib/glossarist/validation/asset_index.rb

@@ -28,7 +28,7 @@ module Glossarist
       end
 
       def self.build_from_directory(dataset_path)
-        concepts = ConceptCollector.collect(dataset_path)
+        concepts = GlossaryStore.new.tap { |s| s.load(dataset_path) }.concepts
         build_from_concepts(concepts, dataset_path)
       end
 

data/lib/glossarist/validation/rules/asciidoc_xref_rule.rb

@@ -14,30 +14,20 @@ module Glossarist
         end
 
         def check(context)
-          concept = context.concept
           fname = context.file_name
-          extractor = ReferenceExtractor.new
           issues = []
 
-          concept.localizations.each do |l10n|
-            lang = l10n.language_code || "unknown"
-
-            l10n.text_content.each do |text|
-              next unless text
-
-              extractor.extract_from_text(text).each do |ref|
-                next unless ref.is_a?(BibliographicReference)
-                next if context.bibliography_index.resolve?(ref.anchor)
-
-                issues << issue(
-                  "unresolved bibliography reference <<#{ref.anchor}>>",
-                  code: code, severity: severity,
-                  location: "#{fname}/#{lang}",
-                  suggestion: "add '#{ref.anchor}' as a source, " \
-                              "or verify it exists in bibliography.yaml"
-                )
-              end
-            end
+          context.references.each do |ref|
+            next unless ref.is_a?(BibliographicReference)
+            next if context.bibliography_index.resolve?(ref.anchor)
+
+            issues << issue(
+              "unresolved bibliography reference <<#{ref.anchor}>>",
+              code: code, severity: severity,
+              location: fname,
+              suggestion: "add '#{ref.anchor}' as a source, " \
+                          "or verify it exists in bibliography.yaml"
+            )
           end
 
           issues

data/lib/glossarist/validation/rules/cite_ref_integrity_rule.rb

@@ -0,0 +1,74 @@
+# frozen_string_literal: true
+
+module Glossarist
+  module Validation
+    module Rules
+      class CiteRefIntegrityRule < Base
+        def code = "GLS-110"
+        def category = :references
+        def severity = "warning"
+        def scope = :concept
+
+        def applicable?(context)
+          context.concept.localizations&.any?
+        end
+
+        def check(context)
+          concept = context.concept
+          fname = context.file_name
+          issues = []
+
+          check_unique_source_ids(concept, fname, issues)
+          check_unresolved_mentions(context, concept, fname, issues)
+
+          issues
+        end
+
+        private
+
+        def check_unique_source_ids(concept, fname, issues)
+          seen = Hash.new { |h, k| h[k] = [] }
+          concept.all_sources.each do |source|
+            next unless source.id
+
+            seen[source.id] << source
+          end
+
+          seen.each do |id, sources|
+            next if sources.length <= 1
+
+            issues << issue(
+              "duplicate source id '#{id}' appears #{sources.length} times",
+              code: "GLS-110", severity: severity,
+              location: fname,
+              suggestion: "source ids must be unique within a concept"
+            )
+          end
+        end
+
+        def check_unresolved_mentions(context, concept, fname, issues)
+          keys = cite_mention_keys(context)
+          return if keys.empty?
+
+          known_ids = concept.all_sources.filter_map(&:id).to_set
+          keys.each do |key|
+            next if known_ids.include?(key)
+
+            issues << issue(
+              "inline {{cite:#{key}}} does not resolve to any source",
+              code: "GLS-110", severity: severity,
+              location: fname,
+              suggestion: "add a source with id '#{key}' or fix the reference"
+            )
+          end
+        end
+
+        def cite_mention_keys(context)
+          context.references
+            .select(&:cite?)
+            .filter_map(&:concept_id)
+        end
+      end
+    end
+  end
+end

data/lib/glossarist/validation/rules/concept_context.rb

@@ -3,6 +3,12 @@
 module Glossarist
   module Validation
     module Rules
+      # Shared context for concept-scoped validation rules.
+      #
+      # Provides lazy-memoized access to extracted references so that multiple
+      # rules examining the same concept share one extraction pass (DRY,
+      # single source of truth). Rules ask the context for references rather
+      # than instantiating their own ReferenceExtractor.
       class ConceptContext
         attr_reader :concept, :file_name, :collection_context
 
@@ -16,6 +22,24 @@ module Glossarist
           @concept.data&.id&.to_s
         end
 
+        # All references extracted from the concept's text fields
+        # (definitions, notes, examples) via {{...}} mentions, <<xrefs>>,
+        # and image::...[] references. Includes ConceptReference,
+        # BibliographicReference, and AssetReference objects.
+        # Memoized — extracted once per concept, shared across all rules.
+        def references
+          @references ||= ReferenceExtractor.new
+            .extract_from_managed_concept(@concept)
+        end
+
+        # All asset references (NonVerbRep, GraphicalSymbol) extracted
+        # from the concept's model attributes.
+        # Memoized — extracted once per concept, shared across all rules.
+        def asset_references
+          @asset_references ||= ReferenceExtractor.new
+            .extract_asset_refs_from_concept(@concept)
+        end
+
         def bibliography_index
           @collection_context.bibliography_index
         end

data/lib/glossarist/validation/rules/concept_mention_rule.rb

@@ -14,12 +14,10 @@ module Glossarist
         end
 
         def check(context)
-          concept = context.concept
           fname = context.file_name
-          extractor = ReferenceExtractor.new
           issues = []
 
-          refs = extractor.extract_from_managed_concept(concept)
+          refs = context.references
             .select { |r| r.is_a?(ConceptReference) && r.local? }
 
           refs.each do |ref|

data/lib/glossarist/validation/rules/image_reference_rule.rb

@@ -14,33 +14,22 @@ module Glossarist
         end
 
         def check(context)
-          concept = context.concept
           fname = context.file_name
-          extractor = ReferenceExtractor.new
           issues = []
 
-          concept.localizations.each do |l10n|
-            lang = l10n.language_code || "unknown"
-
-            l10n.text_content.each do |text|
-              next unless text
-
-              extractor.extract_from_text(text).each do |ref|
-                next unless ref.is_a?(AssetReference)
-                next if context.asset_index.resolve?(ref.path)
+          context.references.each do |ref|
+            next unless ref.is_a?(AssetReference)
+            next if context.asset_index.resolve?(ref.path)
 
-                issues << issue(
-                  "unresolved image reference #{ref.path}",
-                  code: "GLS-103", severity: severity,
-                  location: "#{fname}/#{lang}",
-                  suggestion: "add '#{ref.path}' to the dataset's images/ directory"
-                )
-              end
-            end
+            issues << issue(
+              "unresolved image reference #{ref.path}",
+              code: "GLS-103", severity: severity,
+              location: fname,
+              suggestion: "add '#{ref.path}' to the dataset's images/ directory"
+            )
           end
 
-          asset_refs = extractor.extract_asset_refs_from_concept(concept)
-          asset_refs.each do |ref|
+          context.asset_references.each do |ref|
             next if context.asset_index.resolve?(ref.path)
 
             issues << issue(

data/lib/glossarist/version.rb

@@ -4,5 +4,5 @@
 #
 
 module Glossarist
-  VERSION = "2.8.7"
+  VERSION = "2.8.11"
 end

data/lib/glossarist.rb

@@ -27,35 +27,27 @@ module Glossarist
   autoload :ReferenceResolver,        "glossarist/reference_resolver"
   autoload :ResolutionAdapter,        "glossarist/resolution_adapter"
   autoload :ConceptDate,              "glossarist/concept_date"
-  autoload :ConceptManager,           "glossarist/concept_manager"
   autoload :ConceptSet,               "glossarist/concept_set"
   autoload :ConceptSource,            "glossarist/concept_source"
   autoload :ConceptStore,             "glossarist/concept_store"
   autoload :ConceptValidator,         "glossarist/concept_validator"
-  autoload :ConceptCollector,         "glossarist/concept_collector"
   autoload :ConceptComparator,        "glossarist/concept_comparator"
-  autoload :ContextConfiguration, "glossarist/context_configuration"
+  autoload :ContextConfiguration,     "glossarist/context_configuration"
   autoload :ComparisonResult,         "glossarist/comparison_result"
   autoload :ConceptDiff,              "glossarist/concept_diff"
   autoload :ConceptDocument,          "glossarist/concept_document"
-  autoload :ConceptEnricher,          "glossarist/concept_enricher"
+  autoload :ConceptEnricher, "glossarist/concept_enricher"
   autoload :Config,                   "glossarist/config"
   autoload :DatasetValidator,         "glossarist/dataset_validator"
   autoload :CustomLocality,           "glossarist/custom_locality"
   autoload :DetailedDefinition,       "glossarist/detailed_definition"
   autoload :Designation,              "glossarist/designation"
-  autoload :Error,                    "glossarist/error"
+  autoload :Errors,                   "glossarist/errors"
   autoload :GcrPackage,               "glossarist/gcr_package"
   autoload :GcrPackageDefinition,     "glossarist/gcr_package_definition"
   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"
-  autoload :ParseError, "glossarist/error/parse_error"
-  autoload :CacheVersionMismatchError,
-           "glossarist/error/cache_version_mismatch_error"
   autoload :Locality,                 "glossarist/locality"
   autoload :LocalizedConcept,         "glossarist/localized_concept"
   autoload :ManagedConcept,           "glossarist/managed_concept"
@@ -72,8 +64,8 @@ module Glossarist
   autoload :Utilities,                "glossarist/utilities"
   autoload :Validation,               "glossarist/validation"
   autoload :RegisterData,             "glossarist/register_data"
-  autoload :Section,                 "glossarist/section"
-  autoload :DatasetRegister,         "glossarist/dataset_register"
+  autoload :Section,                  "glossarist/section"
+  autoload :DatasetRegister,          "glossarist/dataset_register"
   autoload :ValidationResult,         "glossarist/validation_result"
   autoload :V1,                       "glossarist/v1"
   autoload :V2,                       "glossarist/v2"

data/scripts/upgrade_dataset_to_v3.rb

@@ -32,7 +32,7 @@ manager.load_from_files(collection: collection)
 
 count = 0
 collection.each do |concept|
-  Glossarist::SchemaMigration.migrate_concept(concept)
+  Glossarist::SchemaMigration::V2ToV3.migrate_concept(concept)
   count += 1
 end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: glossarist
 version: !ruby/object:Gem::Version
-  version: 2.8.7
+  version: 2.8.11
 platform: ruby
 authors:
 - Ribose
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-06-09 00:00:00.000000000 Z
+date: 2026-06-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: lutaml-model
@@ -199,14 +199,12 @@ files:
 - lib/glossarist/collections/typed_collection.rb
 - lib/glossarist/comparison_result.rb
 - lib/glossarist/concept.rb
-- lib/glossarist/concept_collector.rb
 - lib/glossarist/concept_comparator.rb
 - lib/glossarist/concept_data.rb
 - lib/glossarist/concept_date.rb
 - lib/glossarist/concept_diff.rb
 - lib/glossarist/concept_document.rb
 - lib/glossarist/concept_enricher.rb
-- lib/glossarist/concept_manager.rb
 - lib/glossarist/concept_ref.rb
 - lib/glossarist/concept_reference.rb
 - lib/glossarist/concept_set.rb
@@ -230,11 +228,13 @@ files:
 - lib/glossarist/designation/suffix.rb
 - lib/glossarist/designation/symbol.rb
 - lib/glossarist/detailed_definition.rb
-- lib/glossarist/error.rb
-- lib/glossarist/error/cache_version_mismatch_error.rb
-- lib/glossarist/error/invalid_language_code_error.rb
-- lib/glossarist/error/invalid_type_error.rb
-- lib/glossarist/error/parse_error.rb
+- lib/glossarist/errors.rb
+- lib/glossarist/errors/base.rb
+- lib/glossarist/errors/cache_version_mismatch_error.rb
+- lib/glossarist/errors/invalid_language_code_error.rb
+- lib/glossarist/errors/invalid_type_error.rb
+- lib/glossarist/errors/load_error.rb
+- lib/glossarist/errors/parse_error.rb
 - lib/glossarist/gcr_metadata.rb
 - lib/glossarist/gcr_package.rb
 - lib/glossarist/gcr_package_definition.rb
@@ -281,11 +281,14 @@ files:
 - lib/glossarist/register_data.rb
 - lib/glossarist/related_concept.rb
 - lib/glossarist/resolution_adapter.rb
+- lib/glossarist/resolution_adapter/bibliography.rb
 - lib/glossarist/resolution_adapter/local.rb
 - lib/glossarist/resolution_adapter/package.rb
 - lib/glossarist/resolution_adapter/remote.rb
 - lib/glossarist/resolution_adapter/route.rb
 - lib/glossarist/schema_migration.rb
+- lib/glossarist/schema_migration/v0_to_v1.rb
+- lib/glossarist/schema_migration/v2_to_v3.rb
 - lib/glossarist/section.rb
 - lib/glossarist/sts.rb
 - lib/glossarist/sts/extracted_designation.rb
@@ -343,6 +346,7 @@ files:
 - lib/glossarist/validation/rules/base.rb
 - lib/glossarist/validation/rules/bibliography_yaml_rule.rb
 - lib/glossarist/validation/rules/citation_completeness_rule.rb
+- lib/glossarist/validation/rules/cite_ref_integrity_rule.rb
 - lib/glossarist/validation/rules/concept_context.rb
 - lib/glossarist/validation/rules/concept_count_rule.rb
 - lib/glossarist/validation/rules/concept_id_rule.rb