glossarist 2.6.5 → 2.6.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0e3cd8f02f83acf4b2c43139fe2ec0afd8b635860e02e31e530827297648168b
-  data.tar.gz: 755e65d489c0d889ae3d9f4652703d55055aa0b0f0b669b588380070746fc63a
+  metadata.gz: d0e6019628f010211b1f05fbc2297a9c20b53b85ac23e57ac71d8d09ac933dcc
+  data.tar.gz: 65bc93a2714354d47261e21d6ee34c0b46f6d967688188c2af04dcf04ed3aaca
 SHA512:
-  metadata.gz: 5794f170646fa14bae1f7e9d3bf82499c4298f3976804d6cf1b0d33dea90cd26715c5c394cfd6335f8616c4a55d05d78b9cdeb0f653b7a86d629a7b3d0bfe799
-  data.tar.gz: 7681ef4afc518c7cf5bc4fe99a62dc3b41a44c66778257fc5f1e81004867ed86b98ef4c9e4026b8c5a11791d3d618849cf4bf809f11e07d4d87dfef56ffbec5c
+  metadata.gz: 86d9478fdc0bdecdfdce06dd607bd6254c04a9be4e261f41131571c60c043af5b84a2dbef7904c721e0c2646c9436fc734038c4ccd5da3a7a8c31b3fb6fc5429
+  data.tar.gz: 0d9c205d5733dcc767f2f1922eb43fcfdc8e2b445f7c144667bdb508cc285a24e2b50fef9326d085642f1269177f0044401d92fb2128d22466afb91ef25faa34

data/.github/workflows/release.yml

@@ -1,11 +1,8 @@
-# Auto-generated by Cimas: Do not edit it manually!
-# See https://github.com/metanorma/cimas
 name: release
 
 permissions:
   contents: write
   id-token: write
-  pull-requests: write
 
 on:
   workflow_dispatch:
@@ -21,7 +18,7 @@ on:
 
 jobs:
   release:
-    uses: relaton/support/.github/workflows/release.yml@main
+    uses: metanorma/ci/.github/workflows/rubygems-release.yml@main
     with:
       next_version: ${{ github.event.inputs.next_version }}
     secrets:

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2026-05-12 10:41:50 UTC using RuboCop version 1.86.1.
+# on 2026-05-13 07:45:58 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
@@ -11,13 +11,64 @@ Gemspec/RequiredRubyVersion:
   Exclude:
     - 'glossarist.gemspec'
 
-# Offense count: 254
+# Offense count: 3
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle, IndentationWidth.
+# SupportedStyles: with_first_argument, with_fixed_indentation
+Layout/ArgumentAlignment:
+  Exclude:
+    - 'lib/glossarist/designation/expression.rb'
+    - 'spec/unit/designations_spec.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyleAlignWith.
+# SupportedStylesAlignWith: either, start_of_block, start_of_line
+Layout/BlockAlignment:
+  Exclude:
+    - 'spec/unit/designations_spec.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+Layout/BlockEndNewline:
+  Exclude:
+    - 'spec/unit/designations_spec.rb'
+
+# Offense count: 7
+# 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:
+    - 'spec/unit/concept_data_spec.rb'
+    - 'spec/unit/designations_spec.rb'
+
+# Offense count: 2
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: Width, EnforcedStyleAlignWith, AllowedPatterns.
+# SupportedStylesAlignWith: start_of_line, relative_to_receiver
+Layout/IndentationWidth:
+  Exclude:
+    - 'spec/unit/designations_spec.rb'
+
+# Offense count: 267
 # 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/designation/expression.rb'
+    - 'spec/unit/concept_data_spec.rb'
+    - 'spec/unit/designations_spec.rb'
+
 # Offense count: 1
 # Configuration parameters: AllowedMethods.
 # AllowedMethods: enums

data/CLAUDE.md

@@ -23,8 +23,23 @@ All model classes use `Lutaml::Model::Serializable` for serialization.
 - **`ManagedConcept`** (`managed_concept.rb`) — a managed concept with `ManagedConceptData` (groups, localized_concepts map, sources), related concepts, dates, and status. Delegates localization via `add_l10n`/`localization(lang)`.
 - **`Concept`** (`concept.rb`) — base concept with `ConceptData` (definition, terms/designations, notes, examples, sources, dates, language_code). Parent of `LocalizedConcept`.
 - **`LocalizedConcept`** (`localized_concept.rb`) — extends `Concept` with `classification`, `entry_status`, `review_type`.
-- **`ConceptData`** (`concept_data.rb`) — the data payload inside `Concept`: definition, terms, examples, notes, sources, language_code. Uses `DetailedDefinition` collections for definition/examples/notes.
-- **`ManagedConceptData`** (`managed_concept_data.rb`) — the data payload inside `ManagedConcept`: id, localized_concepts hash (lang_code => uuid), groups, sources.
+- **`ConceptData`** (`concept_data.rb`) — the data payload inside `Concept`: definition, terms, examples, notes, sources, non_verb_rep (collection of `NonVerbRep` resource references), language_code (ISO 639), script (ISO 15924), system (ISO 24229 conversion system code). Uses `DetailedDefinition` collections for definition/examples/notes.
+- **`ManagedConceptData`** (`managed_concept_data.rb`) — the data payload inside `ManagedConcept`: id, localized_concepts hash (lang_code => uuid), domains (ConceptReference collection — upper concept references replacing the old `groups` string array), sources.
+
+### NonVerbRep (Resource Reference)
+
+`NonVerbRep` (`non_verb_rep.rb`) models non-verbal representations as URI references to external resources (images, tables, formulas), not embedded content. Attributes: `type` (image/table/formula), `ref` (URI — relative path, URN, or URL), `text` (alt text), `sources` (ConceptSource collection).
+
+### ConceptReference & RelatedConcept
+
+- **`ConceptReference`** (`concept_reference.rb`) — a typed reference to another concept. Local refs use `concept_id` alone; external refs use `source` (URN prefix) + `concept_id` or a direct `urn` field. Has `local?`/`external?` predicates. No `to_gcr_hash` or `from_urn` — model-driven architecture uses lutaml-model for serialization; URN construction/parsing belongs in `UrnResolver`.
+- **`RelatedConcept`** (`related_concept.rb`) — a concept with a typed relationship. Relationship types cover ISO 10241-1 (deprecates/supersedes/superseded_by/compare/contrast/see), ISO 25964/SKOS (broader/narrower/broader_generic/narrower_generic/broader_partitive/narrower_partitive/broader_instantial/narrower_instantial/equivalent/close_match/broad_match/narrow_match/related_match), ISO 12620/TBX (homograph/false_friend/related_concept/related_concept_broader/related_concept_narrower/sequentially_related_concept/spatially_related_concept/temporally_related_concept), and designation-level (abbreviated_form_for/short_form_for). Types are defined in `config.yml` under `related_concept.type`.
+
+### Reference Resolution
+
+- **`ReferenceExtractor`** (`reference_extractor.rb`) — extracts `ConceptReference` and `AssetReference` objects from `{{...}}` mentions and `image::...[]` references in concept text fields.
+- **`ReferenceResolver`** (`reference_resolver.rb`) — resolves references via adapter chain (local → package → remote). Supports route overrides for URI remapping.
+- **`UrnResolver`** (`urn_resolver.rb`) — converts URNs to canonical HTTP URLs (IEC Electropedia, ISO OBP). Extensible via `register_scheme`. All URN construction/parsing logic lives here, not in the model.
 
 ### UUID Generation
 
@@ -34,6 +49,16 @@ Concepts use deterministic UUID v5 (SHA-1) derived from their serialized YAML co
 
 `Designation::Base` (`designation/base.rb`) uses a self-referencing factory pattern (`of_yaml`) that dispatches to subclasses based on `type` field: `Expression`, `Symbol`, `Abbreviation`, `GraphicalSymbol`, `LetterSymbol`. The bi-directional mapping is in `SERIALIZED_TYPES` (`designation.rb`).
 
+Designation inheritance hierarchy (MECE):
+- **Base** — `designation`, `normative_status` (preferred/admitted/deprecated/superseded), `geographical_area`, `type`, `language`/ISO 639, `script`/ISO 15924, `system`/ISO 24229, `international`, `absent`, `pronunciation` (collection of `Pronunciation` objects), `sources` (collection of `ConceptSource` — per-designation sources per ISO 10241-1 §6.8), `term_type` (ISO 12620 term type classification — 24 values from `config.yml`), `related` (collection of `RelatedConcept` — designation-level intra-entry relationships: `abbreviated_form_for`, `short_form_for`)
+- **Expression < Base** — `prefix`, `usage_info`, `field_of_application` (IEC "specific use"), `grammar_info`
+- **Abbreviation < Expression** — abbreviation type booleans (`acronym`, `initialism`, `truncation`) from `config.yml`
+- **Symbol < Base** — (no additional attributes)
+- **LetterSymbol < Symbol** — `text`
+- **GraphicalSymbol < Symbol** — `text`, `image`
+
+`ConceptData#domain` stores URI references (relative like `section-103-01`, URN like `urn:iec:std:iec:60050-103-01`, or URL like `https://...`) to subject area concepts.
+
 ### YAML Serialization
 
 - **`ConceptManager`** (`concept_manager.rb`) — handles file I/O. Supports two storage formats:

data/README.adoc

@@ -101,7 +101,7 @@ related:: Array of <<related-concept,RelatedConcept>>
 status:: Enum for the normative status of the term.
 dates:: Array of <<concept-date,ConceptDate>>
 localized_concepts:: Hash of all localizations where keys are language codes and values are uuid of the localized concept.
-groups:: Array of groups in string format
+domains:: Array of <<concept-reference,ConceptReference>> — upper concepts (subject areas, concept schemes, organizing concepts) that this concept belongs to across all languages. Each domain is a typed reference (e.g. `{ concept_id: "103", ref_type: "domain" }`).
 localizations:: Hash of all localizations for this concept where keys are language codes and values are instances of <<localized-concept,LocalizedConcept>>.
 
 There are two ways to initialize and populate a managed concept
@@ -118,9 +118,8 @@ concept = Glossarist::ManagedConcept.new({
       "eng" => "<uuid>"
     },
     "localizations" => <Array of localized concepts or localized concept hashes>,
-    "groups" => [
-      "foo",
-      "bar",
+    "domains" => [
+      { "concept_id" => "103", "ref_type" => "domain" },
     ],
   },
 })
@@ -132,7 +131,9 @@ concept = Glossarist::ManagedConcept.new({
 ----
 concept = Glossarist::ManagedConcept.new
 concept.id = "123"
-concept.groups = ["foo", "bar"]
+concept.data.domains = [
+  Glossarist::ConceptReference.new(concept_id: "103", ref_type: "domain"),
+]
 concept.localizations = <Array of localized concepts or localized concept hashes>
 ----
 
@@ -146,55 +147,252 @@ Localized concept has the following fields
 id:: An optional identifier for the term, to be used in cross-references.
 uuid:: UUID for the concept
 designations:: Array of <<designation,Designations>> under which the term being defined is known. This method will also accept an array of hashes for designation and will convert them to their respective classes.
-domain:: An optional semantic domain for the term being defined, in case the term is ambiguous between several semantic domains.
+domain:: URI reference to the subject area or section concept. Can be a relative URI (e.g. `section-103-01`), a URN (e.g. `urn:iec:std:iec:60050-103-01`), or a URL (e.g. `https://www.electropedia.org/iev/iev.nsf/display?openform&ievref=103-01`). This is the per-language upper concept reference — the subject area for this specific localization. Different languages may assign the same abstract concept to different domains.
+related:: Array of <<related-concept,RelatedConcept>> — per-language concept relationships. Concept hierarchies can differ across languages (e.g. Russian distinguishes голубой/siniy as coordinate basic colors, while English unifies them under "blue"). Language-specific broader/narrower/equivalent relationships go here.
 subject:: Subject of the term.
 definition:: Array of <<detailed-definition,Detailed Definition>> of the term.
 non_verb_rep:: Array of <<non-verbal,non-verbal>> representations used to help define the term.
 notes:: Zero or more notes about the term. A note is in <<detailed-definition,Detailed Definition>> format.
 examples:: Zero or more examples of how the term is to be used in <<detailed-definition,Detailed Definition>> format.
 language_code:: The language of the localization, as an ISO-639 3-letter code.
+script:: The script of the localization, as an ISO 15924 4-letter code (e.g. `Hans` for Simplified Chinese, `Latn` for Latin, `Cyrl` for Cyrillic). Optional — when omitted, the default script for the language is assumed.
+system:: The ISO 24229 conversion system code used to produce this localization (e.g. `Var:jpn-Hrkt:Latn:Hepburn-1886` for Hepburn-romanized Japanese). Optional — only set when the localization is a romanization or transliteration.
 entry_status:: Entry status of the concept. Must be one of the following: +notValid+, +valid+, +superseded+, +retired+.
 classification:: Classification of the concept. Must be one of the following: +preferred+, +admitted+, +deprecated+.
 
 [[id,designation]]
-=== Designation::Base
+=== Designation
+
+A name under which a managed term is known. Designations follow an
+inheritance hierarchy based on ISO 10241-1 and the Metanorma concept model.
+
+==== Designation::Base (common to all types)
+
+designation:: String — the term text or symbol.
+normative_status:: Enum — one of `preferred`, `admitted`, `deprecated`, `superseded`.
+geographical_area:: String — geographic usage region (ISO 3166-1 country code).
+language:: String — language of this designation (ISO 639 code). Usually inherited from the LocalizedConcept's `language_code`, but can differ for borrowed terms.
+script:: String — script of the designation text (ISO 15924 code, e.g. `Hani` for Kanji, `Latn` for Latin, `Cyrl` for Cyrillic).
+system:: String — ISO 24229 conversion system code used to produce this designation (e.g. `Var:jpn-Hrkt:Latn:Hepburn-1886` for Hepburn romanization). Optional — only set when the designation is a romanization or transliteration.
+international:: Boolean — whether the designation is used internationally.
+absent:: Boolean — whether the designation is intentionally absent in this language.
+pronunciation:: Collection of `Pronunciation` entries — phonetic or romanized representations of the designation.
+sources:: Collection of `ConceptSource` entries — bibliographic sources for this designation (ISO 10241-1 §6.8).
+term_type:: Enum (ISO 12620) — optional classification of the designation's term type. See <<iso12620-term-types>> below.
+related:: Collection of `RelatedConcept` entries — term-level (designation-to-designation) relationships within the same concept entry. Used for linking abbreviated forms to full forms, short forms to expanded forms, etc. (TBX xref types).
++
+Each `Pronunciation` entry has:
++
+[cols="1,1,2"]
+|===
+|Attribute |Standard |Description
+
+|`content` |— |The pronunciation text
+|`language` |ISO 639 |Language/dialect being pronounced (3-letter code)
+|`script` |ISO 15924 |Script of the pronunciation text (4-letter code)
+|`country` |ISO 3166-1 |Country variant (2-letter code, optional)
+|`system` |ISO 24229 |Conversion system code or identifier (e.g. `IPA`, `Var:jpn-Hrkt:Latn:Hepburn-1886`)
+|===
++
+Example:
++
+[,yaml]
+----
+pronunciation:
+  - content: "toːkjoː"
+    language: jpn
+    script: Latn
+    system: IPA
+  - content: "Tōkyō"
+    language: jpn
+    script: Latn
+    system: "Var:jpn-Hrkt:Latn:Hepburn-1886"
+----
+
+==== Designation::Expression (text-based, inherits Base)
 
-A name under which a managed term is known.
+prefix:: String — text before the designation.
+usage_info:: String — disambiguation text for the designation.
+field_of_application:: String — IEC "specific use", appears in angle brackets after the designation (e.g. "in communication theory").
+grammar_info:: Array of GrammarInfo — gender, number, part of speech.
 
-Methods::
-  `from_h(options)`::: Creates a new designation instance based on the specified type.
+==== Designation::Abbreviation (inherits Expression)
+
+acronym:: Boolean — is this an acronym?
+initialism:: Boolean — is this an initialism?
+truncation:: Boolean — is this a truncation?
+
+==== Designation::Symbol (inherits Base)
+
+No additional attributes beyond Base.
+
+==== Designation::LetterSymbol (inherits Symbol)
+
+text:: String — the letter symbol text.
+
+==== Designation::GraphicalSymbol (inherits Symbol)
+
+text:: String — description of the symbol.
+image:: String — the graphical symbol (emoji, path, or data URL).
+
+==== Factory Method
+
+`Designation::Base.from_h(options)` creates a new designation instance based on the specified type.
 
 Parameters::
   * options (Hash) - The options for creating the designation.
-  * "type" (String) - The type of designation (expression, symbol, abbreviation, graphical_symbol, letter_symbol). Note: type key should be string and not a symbol so { type: "expression" } will not work.
+  * "type" (String) - The type of designation (`expression`, `symbol`, `abbreviation`, `graphical_symbol`, `letter_symbol`). Note: type key should be string and not a symbol so `{ type: "expression" }` will not work.
   * Additional options depend on the specific designation type.
 
 Returns::
-  Designation::{type}::: A new instance of specified type. e.g `Glossarist::Designation::Base.from_h("type" => "expression")` will return `Glossarist::Designation::Expression`
+  Designation::{type}::: A new instance of specified type.
 
 Example
 [,ruby]
 ----
-# Example usage of Designation::Base class
+# Expression with field of application
+expr = Designation::Base.from_h({
+  "type" => "expression",
+  "designation" => "information",
+  "normative_status" => "preferred",
+  "field_of_application" => "in communication theory",
+})
+
+# International abbreviation
+abbr = Designation::Base.from_h({
+  "type" => "abbreviation",
+  "designation" => "ISO",
+  "international" => true,
+  "acronym" => true,
+})
+----
+
+[[iso12620-term-types]]
+==== ISO 12620 Term Types
+
+The `term_type` attribute on `Designation::Base` classifies designations
+according to ISO 12620 (also used as TBX `termType`). This is orthogonal to
+the structural designation `type` (expression/abbreviation/symbol): the
+structural type determines how the designation is serialized, while
+`term_type` provides ISO 12620 semantic classification.
+
+[cols="1,2"]
+|===
+|Term type |Description
+
+|`abbreviation`
+|A shortened form of a word or phrase (general category)
+
+|`acronym`
+|An abbreviation pronounced as a word (e.g. NATO, laser)
+
+|`clipped_term`
+|A term formed by clipping part of a longer term (e.g. "phone" from "telephone")
+
+|`common_name`
+|A name in common use for a concept (e.g. "water" vs H₂O)
+
+|`entry_term`
+|The headword or main term in a terminological entry
+
+|`equation`
+|A mathematical equation used as a designation
+
+|`formula`
+|A chemical or mathematical formula (e.g. H₂O, E=mc²)
+
+|`full_form`
+|The complete, unabbreviated form of a designation (e.g. "World Wide Web")
+
+|`initialism`
+|An abbreviation pronounced letter by letter (e.g. "URL", "FBI")
+
+|`internationalism`
+|A term used with the same meaning across many languages (e.g. "computer", "algorithm")
+
+|`international_scientific_term`
+|A term established by international scientific agreement (e.g. "hydrogen")
+
+|`logical_expression`
+|A logical or Boolean expression used as a designation
+
+|`part_number`
+|A part number or catalog identifier used as a designation
 
-attributes_for_expression = { designation: "foobar", geographical_area: "abc", normative_status: "status" }
-designation_expression = Designation::Base.from_h({ "type" => "expression" }.merge(attributes_for_expression))
+|`phraseological_unit`
+|A multi-word expression or phrase functioning as a term (e.g. "software engineering")
 
-attributes_for_abbreviation = { designation: "foobar", geographical_area: "abc", normative_status: "status", international: true }
-designation_abbreviation = Designation::Base.from_h({ "type" => "abbreviation" }.merge(attributes_for_abbreviation))
+|`transcribed_form`
+|A designation produced by phonetic transcription from another script
 
+|`transliterated_form`
+|A designation produced by transliteration from another script (e.g. "Moskva" from "Москва")
+
+|`short_form`
+|A shortened form of a designation that is not an abbreviation (e.g. "US" for "United States")
+
+|`shortcut`
+|A keyboard shortcut or command sequence (e.g. "Ctrl+V" for paste)
+
+|`sku`
+|A stock keeping unit identifier
+
+|`standard_text`
+|A standardized text passage used as a designation
+
+|`symbol`
+|A non-verbal symbol representing the concept (e.g. Ω for ohm)
+
+|`synonym`
+|A term with the same meaning in the same language, used as an alternative designation
+
+|`synonymous_phrase`
+|A phrase that is synonymous with the preferred designation
+
+|`variant`
+|A spelling, regional, or stylistic variant of another designation
+|===
+
+==== Designation-Level Relationships (TBX xref)
+
+Designations can have intra-entry relationships — links between
+designations of the *same* concept. These correspond to TBX `xref`
+elements on term information groups (`<tig>`).
+
+[cols="1,2"]
+|===
+|Relationship type |Description
+
+|`abbreviated_form_for`
+|This designation is an abbreviated form of the target (e.g. "WWW" → "World Wide Web")
+
+|`short_form_for`
+|This designation is a short form of the target (e.g. "US" → "United States of America")
+|===
+
+Example:
+[,yaml]
+----
+terms:
+  - designation: WWW
+    type: abbreviation
+    term_type: acronym
+    related:
+      - type: abbreviated_form_for
+        content: "World Wide Web"
+  - designation: World Wide Web
+    type: expression
+    term_type: full_form
 ----
 
 [[id,related-concept]]
 === RelatedConcept
 
-A term related to the current term.
-
-Following fields are available for the Related Concept
+A concept related to the current concept with a typed relationship.
 
-type:: An enum to denote the relation of the term to the current term.
-content:: The designation of the related term.
-ref:: A <<citation, citation>> of the related term, in a Termbase.
+type:: Enum — the relationship type (see <<relationship-types,Relationship Types>> below).
+content:: String — free-text content describing the related concept.
+ref:: A <<citation,Citation>> reference to the related concept.
 
 There are two ways to initialize and populate a related concept
 
@@ -219,6 +417,208 @@ related_concept.content = "designation of the related concept"
 related_concept.ref = <Citation object>
 ----
 
+[[relationship-types]]
+==== Relationship Types
+
+Relationship types are drawn from ISO 10241-1, ISO 25964/SKOS, and ISO 12620/TBX. The table below shows each type with its provenance and cross-standard equivalents.
+
+[cols="1,1,1,1,1"]
+|===
+|Glossarist type |Category |ISO 10241-1 |ISO 25964 / SKOS |ISO 12620 / TBX
+
+|`deprecates`
+|Lifecycle
+|deprecates
+|—
+|—
+
+|`supersedes`
+|Lifecycle
+|supersedes
+|—
+|—
+
+|`superseded_by`
+|Lifecycle
+|superseded by
+|—
+|—
+
+|`broader`
+|Hierarchical
+|broader concept
+|BT (broaderTerm)
+|broaderTerm
+
+|`narrower`
+|Hierarchical
+|narrower concept
+|NT (narrowerTerm)
+|narrowerTerm
+
+|`broader_generic`
+|Hierarchical (generic)
+|—
+|BTG (broaderGeneric, is-a)
+|broaderTermGeneric
+
+|`narrower_generic`
+|Hierarchical (generic)
+|—
+|NTG (narrowerGeneric)
+|narrowerTermGeneric
+
+|`broader_partitive`
+|Hierarchical (partitive)
+|—
+|BTP (broaderPartitive, part-whole)
+|broaderTermPartitive
+
+|`narrower_partitive`
+|Hierarchical (partitive)
+|—
+|NTP (narrowerPartitive)
+|narrowerTermPartitive
+
+|`broader_instantial`
+|Hierarchical (instantial)
+|—
+|BTI (broaderInstantial, instance-of)
+|broaderTermInstantial
+
+|`narrower_instantial`
+|Hierarchical (instantial)
+|—
+|NTI (narrowerInstantial)
+|narrowerTermInstantial
+
+|`equivalent`
+|Equivalence
+|equivalent
+|exactMatch
+|—
+
+|`close_match`
+|Approx. equiv.
+|—
+|closeMatch
+|—
+
+|`broad_match`
+|Cross-vocab mapping
+|—
+|broadMatch
+|—
+
+|`narrow_match`
+|Cross-vocab mapping
+|—
+|narrowMatch
+|—
+
+|`related_match`
+|Cross-vocab mapping
+|—
+|relatedMatch
+|—
+
+|`compare`
+|Comparative
+|compare
+|—
+|—
+
+|`contrast`
+|Comparative
+|contrast
+|—
+|—
+
+|`see`
+|Associative
+|see also
+|RT (relatedTerm)
+|crossReference
+
+|`related_concept`
+|Associative
+|—
+|—
+|relatedConcept
+
+|`related_concept_broader`
+|Associative (broader)
+|—
+|—
+|relatedConceptBroader
+
+|`related_concept_narrower`
+|Associative (narrower)
+|—
+|—
+|relatedConceptNarrower
+
+|`sequentially_related_concept`
+|Associative (sequential)
+|—
+|—
+|sequentiallyRelatedConcept
+
+|`spatially_related_concept`
+|Associative (spatial)
+|—
+|—
+|spatiallyRelatedConcept
+
+|`temporally_related_concept`
+|Associative (temporal)
+|—
+|—
+|temporallyRelatedConcept
+
+|`homograph`
+|Lexical
+|—
+|—
+|homograph
+
+|`false_friend`
+|Lexical
+|—
+|—
+|falseFriend
+|===
+
+[[id,concept-reference]]
+=== ConceptReference
+
+A typed reference to another concept, either local (within the same glossary) or external (in another concept registry).
+
+term:: String — the display text for the referenced concept.
+concept_id:: String — the identifier of the target concept.
+source:: String — the registry URI prefix for external references (e.g. `urn:iec:std:iec:60050`).
+ref_type:: String — the reference type: `local`, `designation`, or `urn`.
+urn:: String — a direct URN for the target concept (e.g. `urn:iec:std:iec:60050-102-01-01`).
+
+Local references use `concept_id` without `source`. External references use `source` + `concept_id` or a direct `urn`.
+
+[,ruby]
+----
+# Local reference
+ref = Glossarist::ConceptReference.new(term: "latitude", concept_id: "200", ref_type: "local")
+
+# External reference via URN
+ref = Glossarist::ConceptReference.new(
+  term: "equality",
+  concept_id: "102-01-01",
+  source: "urn:iec:std:iec:60050",
+  ref_type: "urn",
+)
+
+ref.local?    # => false
+ref.external? # => true
+----
+
 [[id,concept-date]]
 === Concept Date
 
@@ -324,12 +724,27 @@ citation.clause = "some clause"
 
 === NonVerbRep
 
-Non-verbal Representation have the following fields
+Non-verbal representations are associated resources (images, tables, formulas) used to help define a concept (ISO 10241-1 §6.5). They live outside the concept model and are referenced by URI. Resources can be shared across concepts and belong either to the dataset package (relative path) or are externally referenced (URL/URN).
 
-image:: An image used to help define a term.
-table:: A table used to help define a term.
-formula:: A formula used to help define a term.
-sources:: Bibliographic <<concept-source,concept source>> for the non-verbal representation of the term.
+type:: String — the type of representation: `image`, `table`, or `formula`.
+ref:: String — URI reference to the resource (relative path within the GCR package, URN, or URL).
+text:: String — optional text description or alt text.
+sources:: Collection of <<concept-source,ConceptSource>> entries — bibliographic sources for the representation.
+
+Example:
++
+[,yaml]
+----
+non_verbal_rep:
+  - type: image
+    ref: assets/images/figure-1.svg
+    text: Diagram showing the concept hierarchy
+  - type: formula
+    ref: urn:gcr:assets:formula-eq1
+    sources:
+      - type: authoritative
+        status: identical
+----
 
 [[id,concept-source]]
 === ConceptSource

data/config.yml

@@ -26,23 +26,90 @@ designation:
   base:
     normative_status:
       - preferred
-      - deprecated
       - admitted
+      - deprecated
+      - superseded
       - <símbolo> # in iev-data => '<symbol>'
       - 티에스 # in iev-data => translates to 'TS' I think it is a synonym and not status.
       - prąd startowy # in iev-data => 'starting current' I think it is a synonym and not status.
+  relationship_type:
+    # Term-level (designation-to-designation within the same concept entry)
+    - abbreviated_form_for
+    - short_form_for
 
 related_concept:
   type:
+    # Lifecycle (ISO 10241-1)
     - deprecates
     - supersedes
     - superseded_by
+    # Hierarchical (ISO 10241-1 / ISO 25964)
     - narrower
     - broader
+    # Hierarchical sub-types — ISO 25964 generic (BTG/NTG)
+    - broader_generic
+    - narrower_generic
+    # Hierarchical sub-types — ISO 25964 partitive (BTP/NTP)
+    - broader_partitive
+    - narrower_partitive
+    # Hierarchical sub-types — ISO 25964 instantial (BTI/NTI)
+    - broader_instantial
+    - narrower_instantial
+    # Equivalence (ISO 10241-1 / ISO 25964 exactMatch / SKOS)
     - equivalent
+    # Approximate equivalence (ISO 25964 closeMatch / SKOS)
+    - close_match
+    # Cross-vocabulary mapping (SKOS)
+    - broad_match
+    - narrow_match
+    - related_match
+    # Comparative (ISO 10241-1)
     - compare
     - contrast
+    # Associative (ISO 10241-1 / ISO 25964 RT / TBX crossReference)
     - see
+    # Associative sub-types (ISO 25964 / TBX)
+    - related_concept
+    - related_concept_broader
+    - related_concept_narrower
+    # Associative — spatial/temporal (ISO 25964 / TBX)
+    - sequentially_related_concept
+    - spatially_related_concept
+    - temporally_related_concept
+    # Lexical (ISO 12620 / TBX)
+    - homograph
+    - false_friend
+
+iso12620:
+  term_type:
+    # ISO 12620 term type classification for designations.
+    # Orthographic / structural:
+    - abbreviation
+    - acronym
+    - clipped_term
+    - full_form
+    - initialism
+    - short_form
+    - transliterated_form
+    - transcribed_form
+    - variant
+    # Symbolic / formulaic:
+    - equation
+    - formula
+    - logical_expression
+    - symbol
+    # Usage / provenance:
+    - common_name
+    - entry_term
+    - internationalism
+    - international_scientific_term
+    - part_number
+    - phraseological_unit
+    - shortcut
+    - sku
+    - standard_text
+    - synonym
+    - synonymous_phrase
 
 abbreviation:
   type:

data/lib/glossarist/concept.rb

@@ -4,7 +4,7 @@ module Glossarist
     attribute :id, :string
     attribute :uuid, :string
     attribute :subject, :string
-    attribute :non_verb_rep, :string
+    attribute :non_verb_rep, NonVerbRep, collection: true
     attribute :extension_attributes, :string
     attribute :lineage_source, :string
     attribute :localizations, :hash

data/lib/glossarist/concept_data.rb

@@ -30,6 +30,8 @@ module Glossarist
     # Language code should be exactly 3 char long.
     # TODO: use min_length, max_length once added in lutaml-model
     attribute :language_code, :string, pattern: /^.{3}$/
+    attribute :script, :string
+    attribute :system, :string
     attribute :entry_status, :string
 
     key_value do
@@ -48,6 +50,8 @@ module Glossarist
       map :references, to: :references
       map :domain, to: :domain
       map %i[language_code languageCode], to: :language_code
+      map :script, to: :script
+      map :system, to: :system
       map %i[entry_status entryStatus], to: :entry_status
       map %i[review_date reviewDate], to: :review_date
       map %i[review_decision_date reviewDecisionDate], to: :review_decision_date

data/lib/glossarist/concept_reference.rb

@@ -1,17 +1,29 @@
 # frozen_string_literal: true
 
 module Glossarist
+  # A typed reference to another concept, either local (within the same
+  # glossary) or external (in another concept registry).
+  #
+  # Local references use +concept_id+ without +source+. External references
+  # use +source+ (a registry URN prefix) and +concept_id+ to identify the
+  # target concept, or a direct +urn+ field for formal URN references.
   class ConceptReference < Lutaml::Model::Serializable
     attribute :term, :string
     attribute :concept_id, :string
     attribute :source, :string
     attribute :ref_type, :string
+    attribute :urn, :string
 
     key_value do
       map :term, to: :term
       map :concept_id, to: :concept_id
       map :source, to: :source
       map :ref_type, to: :ref_type
+      map :urn, to: :urn
+    end
+
+    def self.domain(concept_id)
+      new(concept_id: concept_id, ref_type: "domain")
     end
 
     def local?
@@ -23,25 +35,6 @@ module Glossarist
       !local?
     end
 
-    def to_urn
-      return nil unless external?
-      return nil unless source && concept_id
-
-      case source
-      when /\Aurn:iec/ then "#{source}-#{concept_id}"
-      when /\Aurn:iso/ then "#{source}:term:#{concept_id}"
-      else "#{source}/#{concept_id}"
-      end
-    end
-
-    def to_gcr_hash
-      h = { "term" => term }
-      h["concept_id"] = concept_id if concept_id
-      h["source"] = source if source
-      h["ref_type"] = ref_type if ref_type
-      h.compact
-    end
-
     def dedup_key
       concept_id ? [source, concept_id] : [source, concept_id, term]
     end

data/lib/glossarist/designation/abbreviation.rb

@@ -1,7 +1,6 @@
 module Glossarist
   module Designation
     class Abbreviation < Expression
-      attribute :international, :boolean
       attribute :type, :string, default: -> { "abbreviation" }
 
       Glossarist::GlossaryDefinition::ABBREVIATION_TYPES.each do |name|
@@ -9,7 +8,6 @@ module Glossarist
       end
 
       key_value do
-        map :international, to: :international
         map :type, to: :type, render_default: true
         Glossarist::GlossaryDefinition::ABBREVIATION_TYPES.each do |name|
           map name.to_sym, to: name.to_sym

data/lib/glossarist/designation/base.rb

@@ -6,12 +6,30 @@ module Glossarist
       attribute :normative_status, :string,
                 values: Glossarist::GlossaryDefinition::DESIGNATION_BASE_NORMATIVE_STATUSES
       attribute :type, :string
+      attribute :language, :string
+      attribute :script, :string
+      attribute :system, :string
+      attribute :international, :boolean
+      attribute :absent, :boolean
+      attribute :pronunciation, Pronunciation, collection: true
+      attribute :sources, ConceptSource, collection: true
+      attribute :term_type, :string
+      attribute :related, RelatedConcept, collection: true
 
       key_value do
         map :type, to: :type
         map %i[normative_status normativeStatus], to: :normative_status
         map %i[geographical_area geographicalArea], to: :geographical_area
         map :designation, to: :designation
+        map :language, to: :language
+        map :script, to: :script
+        map :system, to: :system
+        map :international, to: :international
+        map :absent, to: :absent
+        map :pronunciation, to: :pronunciation
+        map :sources, to: :sources
+        map %i[term_type termType], to: :term_type
+        map :related, to: :related
       end
 
       def self.of_yaml(hash, options = {})
@@ -34,7 +52,9 @@ module Glossarist
       end
 
       def self.infer_designation_type(hash)
-        if hash["international"] || hash["abbreviation_type"]
+        if hash["abbreviation_type"]
+          "abbreviation"
+        elsif hash["international"]
           "symbol"
         else
           "expression"

data/lib/glossarist/designation/expression.rb

@@ -5,6 +5,7 @@ module Glossarist
     class Expression < Base
       attribute :prefix, :string
       attribute :usage_info, :string
+      attribute :field_of_application, :string
 
       attribute :gender, :string
       attribute :plurality, :string
@@ -16,6 +17,8 @@ module Glossarist
         map :type, to: :type, render_default: true
         map :prefix, to: :prefix
         map %i[usage_info usageInfo], to: :usage_info
+        map %i[field_of_application fieldOfApplication],
+            to: :field_of_application
         map %i[grammar_info grammarInfo], to: :grammar_info
       end
 

data/lib/glossarist/designation/letter_symbol.rb

@@ -2,13 +2,9 @@ module Glossarist
   module Designation
     class LetterSymbol < Symbol
       attribute :text, :string
-      attribute :language, :string
-      attribute :script, :string
 
       key_value do
         map :text, to: :text
-        map :language, to: :language
-        map :script, to: :script
       end
 
       def self.of_yaml(hash, options = {})

data/lib/glossarist/designation/symbol.rb

@@ -1,11 +1,9 @@
 module Glossarist
   module Designation
     class Symbol < Base
-      attribute :international, :boolean
       attribute :type, :string, default: -> { "symbol" }
 
       key_value do
-        map :international, to: :international
         map :type, to: :type, render_default: true
       end
 

data/lib/glossarist/glossary_definition.rb

@@ -28,5 +28,10 @@ module Glossarist
     CONCEPT_DATE_TYPES = config.dig("concept_date", "type").freeze
 
     CONCEPT_STATUSES = config.dig("concept", "status").freeze
+
+    DESIGNATION_RELATIONSHIP_TYPES = config.dig("designation",
+                                                 "relationship_type")&.freeze
+
+    ISO12620_TERM_TYPES = config.dig("iso12620", "term_type").freeze
   end
 end

data/lib/glossarist/managed_concept_data.rb

@@ -5,7 +5,7 @@ module Glossarist
     attribute :id, :string
     attribute :uri, :string
     attribute :localized_concepts, :hash
-    attribute :groups, :string, collection: true
+    attribute :domains, ConceptReference, collection: true
     attribute :sources, ConceptSource, collection: true
     attribute :localizations, LocalizedConcept,
               collection: Collections::LocalizationCollection,
@@ -16,7 +16,8 @@ module Glossarist
                              with: { to: :id_to_yaml, from: :id_from_yaml }
       map :uri, to: :uri
       map %i[localized_concepts localizedConcepts], to: :localized_concepts
-      map :groups, to: :groups
+      map %i[domains groups], to: :domains,
+                             with: { from: :domains_from_yaml, to: :domains_to_yaml }
       map :sources, to: :sources
       map :localizations, to: :localizations,
                           with: { from: :localizations_from_yaml, to: :localizations_to_yaml }
@@ -41,6 +42,24 @@ module Glossarist
 
     def localizations_to_yaml(model, doc); end
 
+    def domains_from_yaml(model, value)
+      return unless value.is_a?(Array)
+
+      model.domains = value.map do |item|
+        if item.is_a?(Hash)
+          ConceptReference.of_yaml(item)
+        else
+          ConceptReference.new(concept_id: item.to_s, ref_type: "domain")
+        end
+      end
+    end
+
+    def domains_to_yaml(model, doc)
+      return if model.domains.nil? || model.domains.empty?
+
+      doc["domains"] = model.domains.map(&:to_hash)
+    end
+
     def authoritative_source
       return [] unless sources
 

data/lib/glossarist/non_verb_rep.rb

@@ -1,14 +1,29 @@
+# frozen_string_literal: true
+
 module Glossarist
+  # A non-verbal representation used to help define a concept, following
+  # ISO 10241-1 §6.5.
+  #
+  # Non-verbal representations are associated resources (images, tables,
+  # formulas) that live outside the concept model. They are referenced by URI
+  # and can be shared across concepts. The resource belongs either to the
+  # dataset package (relative path) or is externally referenced (URL/URN).
+  #
+  # Each non-verbal representation specifies:
+  # - +type+: one of "image", "table", "formula"
+  # - +ref+: URI reference to the resource (relative path, URN, or URL)
+  # - +text+: optional text description or alt text
+  # - +sources+: bibliographic sources for the representation
   class NonVerbRep < Lutaml::Model::Serializable
-    attribute :image, :string
-    attribute :table, :string
-    attribute :formula, :string
+    attribute :type, :string
+    attribute :ref, :string
+    attribute :text, :string
     attribute :sources, ConceptSource, collection: true
 
     key_value do
-      map :image, to: :image
-      map :table, to: :table
-      map :formula, to: :formula
+      map :type, to: :type
+      map :ref, to: :ref
+      map :text, to: :text
       map :sources, to: :sources
     end
   end

data/lib/glossarist/pronunciation.rb

@@ -0,0 +1,32 @@
+module Glossarist
+  # A pronunciation or transcription of a designation, following ISO 24229
+  # spelling system conventions.
+  #
+  # Each pronunciation entry specifies the text of the pronunciation and the
+  # context in which it is expressed:
+  # - +language+ (ISO 639) identifies the language or dialect being pronounced
+  # - +script+ (ISO 15924) identifies the script used for the pronunciation text
+  # - +country+ (ISO 3166-1) identifies the country variant
+  # - +system+ identifies the transcription/romanization system used (ISO 24229
+  #   conversion system code or a simple identifier like "IPA")
+  #
+  # A designation can have multiple pronunciations, e.g.:
+  #   - IPA:       { content: "toːkjoː", script: "Latn", language: "jpn", system: "IPA" }
+  #   - Hepburn:   { content: "Tōkyō",   script: "Latn", language: "jpn", system: "Var:jpn-Hrkt:Latn:Hepburn-1886" }
+  #   - Cyrillic:  { content: "Токио",   script: "Cyrl", language: "rus", system: "polivanov" }
+  class Pronunciation < Lutaml::Model::Serializable
+    attribute :content, :string
+    attribute :language, :string
+    attribute :script, :string
+    attribute :country, :string
+    attribute :system, :string
+
+    key_value do
+      map :content, to: :content
+      map :language, to: :language
+      map :script, to: :script
+      map :country, to: :country
+      map :system, to: :system
+    end
+  end
+end

data/lib/glossarist/reference_extractor.rb

@@ -157,11 +157,9 @@ module Glossarist
       refs = []
 
       concept.localizations.each do |l10n|
-        nvr = l10n.non_verb_rep
-        if nvr.is_a?(String) && !nvr.strip.empty?
-          nvr.strip.split.each do |p|
-            refs << AssetReference.new(path: p) unless p.empty?
-          end
+        Array(l10n.non_verb_rep).each do |nvr|
+          next unless nvr.is_a?(NonVerbRep) && nvr.ref && !nvr.ref.strip.empty?
+          refs << AssetReference.new(path: nvr.ref.strip)
         end
 
         (l10n.data&.terms || []).each do |term|

data/lib/glossarist/urn_resolver.rb

@@ -64,7 +64,19 @@ module Glossarist
     def to_urn(urn_or_reference)
       case urn_or_reference
       when String then urn_or_reference
-      when ConceptReference then urn_or_reference.to_urn
+      when ConceptReference then concept_reference_to_urn(urn_or_reference)
+      end
+    end
+
+    def concept_reference_to_urn(ref)
+      return ref.urn if ref.urn && !ref.urn.strip.empty?
+      return nil unless ref.external?
+      return nil unless ref.source && ref.concept_id
+
+      case ref.source
+      when /\Aurn:iec/ then "#{ref.source}-#{ref.concept_id}"
+      when /\Aurn:iso/ then "#{ref.source}:term:#{ref.concept_id}"
+      else "#{ref.source}/#{ref.concept_id}"
       end
     end
   end

data/lib/glossarist/v1/concept.rb

@@ -42,6 +42,7 @@ module Glossarist
           mc.add_localization(LocalizedConcept.of_yaml({ "data" => data }))
         end
 
+        assign_domains(mc) if groups.is_a?(Array) && groups.any?
         assign_references(mc) if references.is_a?(Array) && references.any?
 
         mc
@@ -49,6 +50,12 @@ module Glossarist
 
       private
 
+      def assign_domains(concept)
+        concept.data.domains = groups.map do |g|
+          ConceptReference.new(concept_id: g.to_s, ref_type: "domain")
+        end
+      end
+
       def assign_references(concept)
         l10n = concept.localization("eng") || concept.localizations.values.first
         return unless l10n

data/lib/glossarist/validation/asset_index.rb

@@ -94,10 +94,11 @@ module Glossarist
         end
 
         def register_non_verb_rep(index, l10n)
-          nvr = l10n.non_verb_rep
-          return unless nvr.is_a?(String) && !nvr.strip.empty?
+          Array(l10n.non_verb_rep).each do |nvr|
+            next unless nvr.is_a?(NonVerbRep) && nvr.ref && !nvr.ref.strip.empty?
 
-          nvr.strip.split.each { |p| index.register(p) }
+            index.register(nvr.ref.strip)
+          end
         end
 
         def register_graphical_symbols(index, l10n)

data/lib/glossarist/version.rb

@@ -4,5 +4,5 @@
 #
 
 module Glossarist
-  VERSION = "2.6.5"
+  VERSION = "2.6.6"
 end

data/lib/glossarist.rb

@@ -52,6 +52,7 @@ module Glossarist
   autoload :ManagedConceptCollection, "glossarist/managed_concept_collection"
   autoload :ManagedConceptData,       "glossarist/managed_concept_data"
   autoload :NonVerbRep,               "glossarist/non_verb_rep"
+  autoload :Pronunciation,            "glossarist/pronunciation"
   autoload :RelatedConcept,           "glossarist/related_concept"
   autoload :Rdf,                      "glossarist/rdf"
   autoload :Sts,                      "glossarist/sts"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: glossarist
 version: !ruby/object:Gem::Version
-  version: 2.6.5
+  version: 2.6.6
 platform: ruby
 authors:
 - Ribose
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-05-12 00:00:00.000000000 Z
+date: 2026-05-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: lutaml-model
@@ -192,6 +192,7 @@ files:
 - lib/glossarist/managed_concept_collection.rb
 - lib/glossarist/managed_concept_data.rb
 - lib/glossarist/non_verb_rep.rb
+- lib/glossarist/pronunciation.rb
 - lib/glossarist/rdf.rb
 - lib/glossarist/rdf/localized_literal.rb
 - lib/glossarist/rdf/namespaces.rb