glossarist 2.4.0 → 2.5.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a7c1f2292807bd8b1809b25ac5c818d1720ecded58b715a137e6f98fe87cb58b
-  data.tar.gz: 10eaf733aa2cc0802128eaa37ee2435659b75bdd48731a7bb5f4147d571c3488
+  metadata.gz: 37d088868a3cacb2d02ec05fb6498cc3b053e8663e3e23e20f8b5ac0f5687dd2
+  data.tar.gz: bb1a08101aaaa0400332b9d4bb4c10383386a30e2b5624a612c5abbc1d23ca12
 SHA512:
-  metadata.gz: 38ade24f616a3a303eb2ecf3723010b2876fbb7820bd010812abf7d2801abc28d4ddcb07f8c607f4958886ceb99b86ceea6710776c9aa6431c89513cecb6599a
-  data.tar.gz: fa76a77134597177540b24ae7070521d32efd5ea0f17451373c60b975ef62695dc677cb5f627380e6c85c239029920208f6fe1c1ebd4f9a76bec210e0a30bd9c
+  metadata.gz: df4af9ceee95f45084e27d38d4430040f1f9620b7a71f6a669c1db508b6bb99a14440238289c81dc273d2de792fed42fb3615960b1f831c9bae0722245d5ef03
+  data.tar.gz: edf63cb34ed349a15870412f078bf576326cdb62614d730650779f782452fa24c6de682b156e0ad1a9b7fce5a9a76b6fd803c41a5f092af0e8c84a430c78d10f

data/.gitignore

@@ -21,3 +21,4 @@ localcache
 
 .vscode
 
+TODO*

data/.rubocop_todo.yml

@@ -1,125 +1,23 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2026-03-24 03:31:43 UTC using RuboCop version 1.86.0.
+# on 2026-05-04 09:39:17 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: 1
-# This cop supports safe autocorrection (--autocorrect).
-Gemspec/RequireMFA:
-  Exclude:
-    - 'glossarist.gemspec'
-
 # Offense count: 1
 Gemspec/RequiredRubyVersion:
   Exclude:
     - 'glossarist.gemspec'
 
-# Offense count: 13
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyle, IndentationWidth.
-# SupportedStyles: with_first_argument, with_fixed_indentation
-Layout/ArgumentAlignment:
-  Exclude:
-    - 'lib/glossarist/concept.rb'
-    - 'lib/glossarist/concept_data.rb'
-    - 'lib/glossarist/concept_manager.rb'
-    - 'lib/glossarist/designation/grammar_info.rb'
-    - 'lib/glossarist/managed_concept.rb'
-    - 'spec/features/v2_serialization_spec.rb'
-    - 'spec/unit/locality_spec.rb'
-
-# Offense count: 2
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyleAlignWith.
-# SupportedStylesAlignWith: either, start_of_block, start_of_line
-Layout/BlockAlignment:
-  Exclude:
-    - 'spec/features/v2_serialization_spec.rb'
-
-# Offense count: 2
-# This cop supports safe autocorrection (--autocorrect).
-Layout/BlockEndNewline:
-  Exclude:
-    - 'spec/features/v2_serialization_spec.rb'
-
-# Offense count: 2
-# This cop supports safe autocorrection (--autocorrect).
-Layout/ClosingParenthesisIndentation:
-  Exclude:
-    - 'spec/features/multi_content_yaml_serialization_spec.rb'
-    - 'spec/features/v2_serialization_spec.rb'
-
-# Offense count: 2
-# 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:
-  Exclude:
-    - 'spec/features/multi_content_yaml_serialization_spec.rb'
-    - 'spec/features/v2_serialization_spec.rb'
-
-# Offense count: 10
-# 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:
-    - 'exe/glossarist'
-    - 'lib/glossarist/concept_data.rb'
-    - 'lib/glossarist/designation/grammar_info.rb'
-    - 'spec/unit/locality_spec.rb'
-
-# Offense count: 1
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyle.
-# SupportedStyles: normal, indented_internal_methods
-Layout/IndentationConsistency:
-  Exclude:
-    - 'glossarist.gemspec'
-
-# Offense count: 4
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: Width, EnforcedStyleAlignWith, AllowedPatterns.
-# SupportedStylesAlignWith: start_of_line, relative_to_receiver
-Layout/IndentationWidth:
-  Exclude:
-    - 'spec/features/v2_serialization_spec.rb'
-
-# Offense count: 90
+# Offense count: 196
 # 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: 2
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyle.
-# SupportedStyles: symmetrical, new_line, same_line
-Layout/MultilineMethodCallBraceLayout:
-  Exclude:
-    - 'spec/features/multi_content_yaml_serialization_spec.rb'
-    - 'spec/features/v2_serialization_spec.rb'
-
-# Offense count: 20
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: AllowInHeredoc.
-Layout/TrailingWhitespace:
-  Exclude:
-    - 'exe/glossarist'
-    - 'lib/glossarist/concept.rb'
-    - 'lib/glossarist/concept_data.rb'
-    - 'lib/glossarist/concept_manager.rb'
-    - 'lib/glossarist/designation/grammar_info.rb'
-    - 'lib/glossarist/managed_concept.rb'
-    - 'spec/features/v2_serialization_spec.rb'
-    - 'spec/unit/locality_spec.rb'
-
 # Offense count: 1
 # Configuration parameters: AllowedMethods.
 # AllowedMethods: enums
@@ -132,53 +30,72 @@ Lint/DuplicateMethods:
   Exclude:
     - 'lib/glossarist/managed_concept.rb'
 
-# Offense count: 3
-# This cop supports unsafe autocorrection (--autocorrect-all).
-Lint/NonAtomicFileOperation:
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: AllowUnusedKeywordArguments, IgnoreEmptyMethods, IgnoreNotImplementedMethods, NotImplementedExceptions.
+# NotImplementedExceptions: NotImplementedError
+Lint/UnusedMethodArgument:
   Exclude:
-    - 'lib/glossarist/concept_manager.rb'
+    - 'lib/glossarist/dataset_validator.rb'
 
-# Offense count: 4
+# Offense count: 18
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes, Max.
 Metrics/AbcSize:
   Exclude:
+    - 'lib/glossarist/cli/package_command.rb'
+    - 'lib/glossarist/cli/validate_command.rb'
     - 'lib/glossarist/concept_manager.rb'
+    - 'lib/glossarist/gcr_metadata.rb'
+    - 'lib/glossarist/gcr_package.rb'
+    - 'lib/glossarist/reference_extractor.rb'
+    - 'lib/glossarist/reference_resolver.rb'
+    - 'lib/glossarist/resolution_adapter/local.rb'
+    - 'lib/glossarist/schema_migration.rb'
     - 'lib/glossarist/utilities/uuid.rb'
+    - 'spec/unit/concept_collector_spec.rb'
 
-# Offense count: 2
+# Offense count: 1
+# Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
+# AllowedMethods: refine
+Metrics/BlockLength:
+  Max: 28
+
+# Offense count: 15
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/CyclomaticComplexity:
   Exclude:
+    - 'lib/glossarist/concept_validator.rb'
     - 'lib/glossarist/designation/expression.rb'
+    - 'lib/glossarist/gcr_metadata.rb'
     - 'lib/glossarist/managed_concept.rb'
+    - 'lib/glossarist/reference_extractor.rb'
+    - 'lib/glossarist/reference_resolver.rb'
+    - 'lib/glossarist/resolution_adapter/local.rb'
+    - 'lib/glossarist/schema_migration.rb'
 
-# Offense count: 9
+# Offense count: 31
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
-  Max: 19
+  Max: 42
 
-# Offense count: 1
+# Offense count: 12
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/PerceivedComplexity:
   Exclude:
+    - 'lib/glossarist/concept_validator.rb'
     - 'lib/glossarist/designation/expression.rb'
+    - 'lib/glossarist/gcr_metadata.rb'
+    - 'lib/glossarist/reference_extractor.rb'
+    - 'lib/glossarist/reference_resolver.rb'
+    - 'lib/glossarist/resolution_adapter/local.rb'
+    - 'lib/glossarist/schema_migration.rb'
 
-# Offense count: 1
-# This cop supports safe autocorrection (--autocorrect).
-Performance/StringIdentifierArgument:
-  Exclude:
-    - 'spec/unit/collection_spec.rb'
-
-# Offense count: 3
-# 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:
+# Offense count: 6
+# Configuration parameters: MinNameLength, AllowNamesEndingInNumbers, AllowedNames, ForbiddenNames.
+# AllowedNames: as, at, by, cc, db, id, if, in, io, ip, of, on, os, pp, to
+Naming/MethodParameterName:
   Exclude:
-    - 'spec/features/v2_serialization_spec.rb'
+    - 'lib/glossarist/schema_migration.rb'
 
 # Offense count: 6
 # This cop supports safe autocorrection (--autocorrect).
@@ -188,28 +105,15 @@ Style/FormatStringToken:
   EnforcedStyle: unannotated
 
 # Offense count: 1
-# This cop supports unsafe autocorrection (--autocorrect-all).
-Style/MapIntoArray:
+# Configuration parameters: AllowedClasses.
+Style/OneClassPerFile:
   Exclude:
-    - 'spec/unit/collection_spec.rb'
+    - 'spec/**/*'
+    - 'test/**/*'
+    - 'lib/glossarist.rb'
 
 # Offense count: 1
 # Configuration parameters: Max.
 Style/SafeNavigationChainLength:
   Exclude:
     - 'lib/glossarist/managed_concept.rb'
-
-# Offense count: 2
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyle, ConsistentQuotesInMultiline.
-# SupportedStyles: single_quotes, double_quotes
-Style/StringLiterals:
-  Exclude:
-    - 'glossarist.gemspec'
-
-# Offense count: 2
-# This cop supports safe autocorrection (--autocorrect).
-Style/SuperArguments:
-  Exclude:
-    - 'lib/glossarist/designation/base.rb'
-    - 'lib/glossarist/designation/expression.rb'

data/CLAUDE.md

@@ -0,0 +1,85 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Build & Test Commands
+
+- `bundle install` — install dependencies
+- `bundle exec rspec` — run all tests
+- `bundle exec rspec spec/unit/citation_spec.rb` — run a single test file
+- `bundle exec rspec spec/unit/citation_spec.rb:12` — run a single test by line number
+- `bundle exec rake` — runs `bundle exec rspec` (default rake task)
+- `bundle exec rubocop` — lint
+
+## Architecture
+
+Glossarist is a Ruby gem implementing the [Glossarist concept model](https://github.com/glossarist/concept-model) (ISO 10241-1). It provides classes for managing terminology glossaries with multi-language support, serialization to/from YAML, and bibliography integration via Relaton.
+
+All model classes use `Lutaml::Model::Serializable` for serialization.
+
+### Core Model Hierarchy
+
+- **`ManagedConceptCollection`** (`managed_concept_collection.rb`) — top-level enumerable collection of ManagedConcepts. Entry point for loading/saving glossaries via `ConceptManager`.
+- **`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.
+
+### UUID Generation
+
+Concepts use deterministic UUID v5 (SHA-1) derived from their serialized YAML content and the OID namespace (`Utilities::UUID`). This means a concept's UUID is stable across sessions as long as its data doesn't change.
+
+### Designation (STI-like pattern)
+
+`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`).
+
+### YAML Serialization
+
+- **`ConceptManager`** (`concept_manager.rb`) — handles file I/O. Supports two storage formats:
+  1. Separate `concept/` and `localized_concept/` directories (or `localized-concept/` with dashes)
+  2. Grouped: concept + localized concepts in a single YAML stream file
+- Supports both camelCase and snake_case keys in YAML (e.g., `localizedConcepts` / `localized_concepts`) using `%i[key1 key2]` mapping syntax.
+- Also supports V1 format (`concept-*.yaml` files at root level).
+
+### Configuration & Extensibility
+
+- **`Config`** (`config.rb`) — singleton that holds registered classes for `:localized_concept` and `:managed_concept`. Allows swapping implementations via `register_class`.
+- **`GlossaryDefinition`** (`glossary_definition.rb`) — loads enum values (concept statuses, source types, etc.) from `config.yml`.
+- A `glossarist.yaml` file in the working directory can register extension attributes.
+
+### Collections
+
+Custom collection classes in `collections/` extend `Lutaml::Model::Collection`:
+- **`LocalizationCollection`** — keyed by `language_code`, used for `ManagedConceptData#localizations`.
+- **`DetailedDefinitionCollection`**, **`ConceptSourceCollection`** — typed collections for ConceptData fields.
+- **`BibliographyCollection`** — extends `Relaton::Db` for bibliography caching with cache version checking.
+- **`AssetCollection`**, **`Collection`** (base enumerable), **`DesignationCollection`**.
+
+### GCR Packaging
+
+Three classes handle glossary concept registry (GCR) ZIP packages:
+- **`GcrPackage`** (`gcr_package.rb`) — creates/loads/validates ZIP archives containing `metadata.yaml`, `register.yaml`, and `concepts/*.yaml` entries.
+- **`GcrMetadata`** (`gcr_metadata.rb`) — package metadata (shortname, version, languages, statistics). Built from concepts via `GcrMetadata.from_concepts`.
+- **`GcrStatistics`** (`gcr_statistics.rb`) — computes stats (total concepts, languages, concepts by status) from concept data.
+- **`SchemaMigration`** (`schema_migration.rb`) — migrates concepts from v0 (legacy IEV format) to v1, normalizing definitions, dates, entry statuses, and extracting inline references.
+- **`ValidationResult`** (`validation_result.rb`) — simple errors/warnings container for package validation.
+
+### CLI
+
+The `exe/glossarist` executable uses Thor. Currently provides `generate_latex` which converts concepts to LaTeX glossary entries via `ConceptSet`.
+
+### Dependencies
+
+- `lutaml-model` (~> 0.8) — serialization framework (YAML/XML)
+- `relaton` (>= 2.0.0, < 3) — bibliography database integration
+- `thor` — CLI commands
+
+## Gemfile Notes
+
+The Gemfile overrides relaton gems from git branches for lutaml-model 0.8 compatibility:
+- 5 repos use `fix/lutaml-model-0.8` branches (relaton-bib, relaton-iso, relaton-3gpp, relaton-bipm, relaton-bsi)
+- 5 repos use `lutaml-integration` branches (relaton-calconnect, relaton-ccsds, relaton-cen, relaton-iec, relaton-itu)
+- Released 2.0.0 gems have untyped lutaml-model attributes that fail with 0.8+
+- relaton-bib 2.1.0 is released but sub-gems pin `~> 2.0.0`, blocking 2.1.0 adoption until upstream updates constraints
+- Remove git overrides once relaton gems release versions with lutaml-model 0.8 support

data/Gemfile

@@ -2,12 +2,33 @@
 
 source "https://rubygems.org"
 
-gem "lutaml-model"
-gem "pry"
-gem "rake"
-gem "rspec"
+gemspec
+
+gem "canon"
+gem "lutaml-model", "~> 0.8.0"
+gem "rake", "~> 13.0"
+gem "rspec", "~> 3.0"
+gem "rubocop"
 gem "rubocop-performance"
 gem "rubocop-rake"
 gem "rubocop-rspec"
 
-gemspec
+# 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+.
+# fix/lutaml-model-0.8 branches keep version 2.0.0 (compatible) + lutaml-model ~> 0.8.
+# lutaml-integration branches also have typed attributes and work with relaton-bib ~> 2.0.0.
+# TODO: Remove once relaton gems release versions with lutaml-model 0.8 support.
+gem "relaton-3gpp", github: "relaton/relaton-3gpp",
+                    branch: "fix/lutaml-model-0.8"
+gem "relaton-bib", github: "relaton/relaton-bib", branch: "fix/lutaml-model-0.8"
+gem "relaton-bipm", github: "relaton/relaton-bipm",
+                    branch: "fix/lutaml-model-0.8"
+gem "relaton-bsi", github: "relaton/relaton-bsi", branch: "fix/lutaml-model-0.8"
+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: "fix/lutaml-model-0.8"
+gem "relaton-itu", github: "relaton/relaton-itu", branch: "lutaml-integration"