tbx 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: c3a53cd7d9e2bdb108893a0320b4ede11f7b7cdd4d7e2ae3b7727ebe78359286
+  data.tar.gz: 0ca4e4c95c6d837a9583b50e76a31727f3130757a80e706ff1f848d00f6075e7
+SHA512:
+  metadata.gz: bf955090ad2cb8e77516ab3e466cf9637eac9e8537b2f69ff8ec2553d71aef5cb35bc56cb7ce25b2c10cee2441b1a9c22e2cad64ca4d672a4186f34cdbea19d4
+  data.tar.gz: d3ac55aabfbc8ea882098eaa1a0a69d7b0028bf39aba78f7c77dfe749182b9e926164638e7b6a57381318826f9845fc85216b5e4cd343a4ba4e4c4bfdbd935ca

data/.github/workflows/rake.yml

@@ -0,0 +1,15 @@
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
+name: rake
+
+on:
+  push:
+    branches: [ master, main ]
+    tags: [ v* ]
+  pull_request:
+
+jobs:
+  rake:
+    uses: metanorma/ci/.github/workflows/generic-rake.yml@main
+    secrets:
+      pat_token: ${{ secrets.METANORMA_CI_PAT_TOKEN }}

data/.github/workflows/release.yml

@@ -0,0 +1,29 @@
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
+name: release
+
+permissions:
+  contents: write
+  packages: write
+  id-token: write
+
+on:
+  workflow_dispatch:
+    inputs:
+      next_version:
+        description: |
+          Next release version. Possible values: x.y.z, major, minor, patch (or pre|rc|etc).
+          Also, you can pass 'skip' to skip 'git tag' and do 'gem push' for the current version
+        required: true
+        default: 'skip'
+  repository_dispatch:
+    types: [ do-release ]
+
+jobs:
+  release:
+    uses: metanorma/ci/.github/workflows/rubygems-release.yml@main
+    with:
+      next_version: ${{ github.event.inputs.next_version }}
+    secrets:
+      rubygems-api-key: ${{ secrets.METANORMA_CI_RUBYGEMS_API_KEY }}
+      pat_token: ${{ secrets.METANORMA_CI_PAT_TOKEN }}

data/.gitignore

@@ -0,0 +1,16 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status
+
+Gemfile.lock
+.claude
+TODO*
+

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.rubocop.yml

@@ -0,0 +1,17 @@
+inherit_from:
+  - .rubocop_todo.yml
+  - https://raw.githubusercontent.com/riboseinc/oss-guides/master/ci/rubocop.yml
+
+# local repo-specific modifications
+
+AllCops:
+  TargetRubyVersion: 3.2
+  NewCops: enable
+  SuggestExtensions: false
+
+Style/Documentation:
+  Enabled: false
+
+Metrics/BlockLength:
+  Exclude:
+    - "spec/**/*"

data/.rubocop_todo.yml

@@ -0,0 +1,16 @@
+# This configuration was generated by
+# `rubocop --auto-gen-config`
+# on 2026-05-05 13:10:07 UTC using RuboCop version 1.86.1.
+# The point is for the user to remove these configuration records
+# one by one as the offenses are removed from the code base.
+# Note that changes in the inspected code, or installation of new
+# versions of RuboCop, may require this file to be generated again.
+
+# Offense count: 7
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: Max, AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, AllowRBSInlineAnnotation, AllowCopDirectives, AllowedPatterns, SplitStrings.
+# URISchemes: http, https
+Layout/LineLength:
+  Exclude:
+    - 'spec/tbx/document_spec.rb'
+    - 'tbx.gemspec'

data/CHANGELOG.md

@@ -0,0 +1,5 @@
+## [Unreleased]
+
+## [0.1.0] - 2026-05-05
+
+- Initial release

data/CLAUDE.md

@@ -0,0 +1,124 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Build, Test, and Development Commands
+
+```bash
+# Install dependencies
+bundle install
+
+# Run tests
+bundle exec rspec
+
+# Run a single test file
+bundle exec rspec spec/tbx/document_spec.rb
+
+# Run linting
+bundle exec rubocop
+
+# Run both (default task)
+bundle exec rake
+```
+
+## Architecture
+
+This is a Ruby gem for parsing and serializing TBX (Termbase Exchange) documents per ISO 30042:2019. It uses `lutaml-model` for XML serialization/deserialization.
+
+### Namespace Structure
+
+```
+Tbx
+├── Document         # Root element (<tbx>)
+├── TbxHeader        # <tbxHeader>
+├── FileDesc         # <fileDesc>
+├── PublicationStmt  # <publicationStmt>
+├── TitleStmt        # <titleStmt>
+├── SourceDesc       # <sourceDesc>
+├── EncodingDesc     # <encodingDesc>
+├── RevisionDesc     # <revisionDesc>
+├── Change           # <change>
+├── TextElement      # <text>
+├── Body             # <body>
+├── Back             # <back>
+├── ConceptEntry     # <conceptEntry>
+├── LangSec          # <langSec>
+├── TermSec          # <termSec>
+├── Term             # <term>
+├── TermNote         # <termNote>
+├── TermNoteGrp      # <termNoteGrp>
+├── Descrip          # <descrip>
+├── DescripGrp       # <descripGrp>
+├── DescripNote      # <descripNote>
+├── Admin            # <admin>
+├── AdminGrp         # <adminGrp>
+├── AdminNote        # <adminNote>
+├── Note             # <note>
+├── P                # <p>
+├── Ref              # <ref>
+├── Xref             # <xref>
+├── Transac          # <transac>
+├── TransacGrp       # <transacGrp>
+├── TransacNote      # <transacNote>
+├── DateElement      # <date>
+├── RefObjectSec     # <refObjectSec>
+├── RefObject        # <refObject>
+├── ItemSet          # <itemSet>
+├── ItemGrp          # <itemGrp>
+├── Item             # <item>
+├── Hi               # <hi>
+├── Foreign          # <foreign>
+├── Ec               # <ec>
+├── Sc               # <sc>
+├── Ph               # <ph>
+├── Title            # <title>
+├── Namespaces       # XML namespace definitions
+└── Ruby             # Gem namespace (Tbx::Ruby::VERSION)
+```
+
+### Key Implementation Patterns
+
+**Element Classes** (in `lib/tbx/`):
+- Inherit from `Lutaml::Model::Serializable`
+- Define attributes and XML mapping in `xml do ... end` block
+- Use `map_element` to map child elements, `map_content` for text content
+- Use `mixed_content` for elements that contain both text and child elements
+- Use `w3c_attributes` for `xml:lang` and other W3C attributes
+
+**Example element structure:**
+```ruby
+module Tbx
+  class ConceptEntry < Lutaml::Model::Serializable
+    attribute :id, :string
+    attribute :lang_sec, ::Tbx::LangSec, collection: true
+
+    xml do
+      root "conceptEntry"
+      mixed_content
+      namespace ::Tbx::Namespaces::TbxNamespace
+
+      map_attribute "id", to: :id
+      map_element "langSec", to: :lang_sec
+    end
+  end
+end
+```
+
+**Autoload Pattern**: Elements are autoloaded via `lib/tbx.rb`. When adding new elements, add autoloads in alphabetical order.
+
+### XML Namespace
+
+The TBX namespace is `urn:iso:std:iso:30042:ed-2` defined in `Tbx::Namespaces::TbxNamespace`.
+
+### TBX Styles
+
+- **DCA** (Data Category Archive): Uses standard element names like `<transac type="transactionType">`, `<descrip type="definition">`
+- **DCT** (Data Category Tagging): Uses module-namespaced elements like `<basic:transactionType>`, `<basic:definition>`
+
+Currently DCA style is fully supported. DCT support will be added.
+
+### Reference Data
+
+- RNG/XSD schemas: `reference-docs/schemas/`
+- TBX-Basic dialect examples: `reference-docs/schemas/TBX-Basic_dialect_v1/`
+- Test fixtures: `spec/fixtures/TBX_test_files/` (from https://github.com/LTAC-Global/TBX_test_files)

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,10 @@
+# Code of Conduct
+
+"tbx-ruby" follows [The Ruby Community Conduct Guideline](https://www.ruby-lang.org/en/conduct) in all "collaborative space", which is defined as community communications channels (such as mailing lists, submitted patches, commit comments, etc.):
+
+* Participants will be tolerant of opposing views.
+* Participants must ensure that their language and actions are free of personal attacks and disparaging personal remarks.
+* When interpreting the words and actions of others, participants should always assume good intentions.
+* Behaviour which can be reasonably considered harassment will not be tolerated.
+
+If you have any concerns about behaviour within this project, please contact us at ["ronald.tse@ribose.com"](mailto:"ronald.tse@ribose.com").

data/Gemfile

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+gemspec
+
+gem "canon"
+gem "lutaml-model", path: "../../lutaml/lutaml-model"
+gem "nokogiri"
+gem "rake", "~> 13.0"
+gem "rspec", "~> 3.0"
+gem "rubocop", "~> 1.21"
+gem "rubocop-performance"
+gem "rubocop-rake"
+gem "rubocop-rspec"

data/README.adoc

@@ -0,0 +1,156 @@
+= Ruby library for TBX (ISO 30042:2019)
+
+== Purpose
+
+The `tbx` Ruby gem allows you to parse, manipulate, and serialize TBX
+(TermBase eXchange) documents as defined by ISO 30042:2019.
+
+TBX is an international standard for representing structured terminological
+data in XML. This library provides complete coverage of the TBX core
+structure, including:
+
+* **DCA** (Data Category Archive) style -- standard TBX element names with
+  `type` attributes (e.g., `<descrip type="definition">`)
+* **DCT** (Data Category Tagging) style -- module-namespaced elements
+  (e.g., `<basic:definition>`) *(planned)*
+
+The library is built on https://github.com/lutaml/lutaml-model[`lutaml-model`]
+for declarative XML serialization.
+
+[NOTE]
+This is a work-in-progress.
+
+== Installation
+
+Install the gem and add to the application's Gemfile:
+
+[source,bash]
+----
+bundle add tbx
+----
+
+Or install directly:
+
+[source,bash]
+----
+gem install tbx
+----
+
+== Usage
+
+[source,ruby]
+----
+require 'tbx'
+
+# Parse a TBX file
+doc = IO.read('spec/fixtures/TBX_test_files/min_good.tbx')
+tbx = Tbx::Document.from_xml(doc)
+
+# Access document metadata
+tbx.type          # => "TBX-Min"
+tbx.style         # => "dca"
+tbx.lang          # => "en"
+
+# Access header
+tbx.tbx_header.file_desc.source_desc.p.first.content.join
+# => "TBX file, created via MultiTerm Export"
+
+# Navigate concept entries
+entry = tbx.text.body.concept_entry.first
+entry.id                           # => "c1"
+entry.lang_sec.first.lang          # => "en"
+entry.lang_sec.first.term_sec.first.term.content.join
+# => "open cluster"
+
+# Serialize back to XML
+puts tbx.to_xml(pretty: true)
+# => round-tripped TBX document
+----
+
+=== API
+
+[source,ruby]
+----
+# Parse
+tbx = Tbx::Document.from_xml(xml_string)
+
+# Access elements
+tbx.tbx_header.file_desc.source_desc
+tbx.text.body.concept_entry.each do |entry|
+  entry.lang_sec.each do |lang|
+    lang.term_sec.each do |ts|
+      puts ts.term.content.join
+    end
+  end
+end
+
+# Serialize back
+tbx.to_xml
+tbx.to_xml(pretty: true, declaration: true, encoding: "utf-8")
+----
+
+=== Supported TBX elements
+
+==== Root and structure
+
+`Document` (`<tbx>`), `TbxHeader`, `TextElement`, `Body`, `Back`
+
+==== Terminological entries
+
+`ConceptEntry`, `LangSec`, `TermSec`, `Term`
+
+==== Data categories
+
+`Admin`, `AdminGrp`, `AdminNote`, `Descrip`, `DescripGrp`, `DescripNote`,
+`TermNote`, `TermNoteGrp`, `Ref`, `Xref`
+
+==== Transactions
+
+`Transac`, `TransacGrp`, `TransacNote`, `DateElement`
+
+==== Header
+
+`FileDesc`, `PublicationStmt`, `TitleStmt`, `SourceDesc`, `EncodingDesc`,
+`RevisionDesc`, `Change`
+
+==== Reference objects
+
+`RefObjectSec`, `RefObject`, `ItemSet`, `ItemGrp`, `Item`
+
+==== Inline
+
+`Hi`, `Foreign`, `Ec`, `Sc`, `Ph`, `Note`, `P`, `Title`
+
+== Test data
+
+Test fixtures are sourced from the
+https://github.com/LTAC-Global/TBX_test_files[TBX_test_files] repository
+maintained by https://ltac-global.org[LTAC Global], and from the TBX-Basic
+dialect schemas included in `reference-docs/`.
+
+== Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then,
+run `bundle exec rake` to run the tests and linter.
+
+[source,bash]
+----
+# Run tests
+bundle exec rspec
+
+# Run linter
+bundle exec rubocop
+
+# Run both (default task)
+bundle exec rake
+----
+
+== Credits
+
+This gem is developed, maintained and funded by
+https://www.ribose.com[Ribose Inc.]
+
+== License
+
+The gem is available as open source under the terms of the
+https://opensource.org/licenses/BSD-2-Clause[2-Clause BSD License].

data/Rakefile

@@ -0,0 +1,12 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+require "rubocop/rake_task"
+
+RuboCop::RakeTask.new
+
+task default: %i[spec rubocop]

data/lib/tbx/admin.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+module Tbx
+  class Admin < Lutaml::Model::Serializable
+    attribute :id, :string
+    attribute :lang, Lutaml::Xml::W3c::XmlLangType
+    attribute :target, :string
+    attribute :datatype, :string
+    attribute :type, :string
+    attribute :content, :string, collection: true
+    attribute :hi, ::Tbx::Hi, collection: true
+    attribute :ec, ::Tbx::Ec, collection: true
+    attribute :foreign, ::Tbx::Foreign, collection: true
+    attribute :ph, ::Tbx::Ph, collection: true
+    attribute :sc, ::Tbx::Sc, collection: true
+
+    xml do
+      root "admin"
+      mixed_content
+      namespace ::Tbx::Namespaces::TbxNamespace
+
+      map_attribute "id", to: :id
+      w3c_attributes :lang
+      map_attribute "target", to: :target
+      map_attribute "datatype", to: :datatype
+      map_attribute "type", to: :type
+      map_content to: :content
+      map_element "hi", to: :hi
+      map_element "ec", to: :ec
+      map_element "foreign", to: :foreign
+      map_element "ph", to: :ph
+      map_element "sc", to: :sc
+    end
+  end
+end

data/lib/tbx/admin_grp.rb

@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+module Tbx
+  class AdminGrp < Lutaml::Model::Serializable
+    attribute :id, :string
+    attribute :admin, ::Tbx::Admin
+    attribute :admin_note, ::Tbx::AdminNote, collection: true
+    attribute :note, ::Tbx::Note, collection: true
+    attribute :ref, ::Tbx::Ref, collection: true
+    attribute :xref, ::Tbx::Xref, collection: true
+
+    xml do
+      root "adminGrp"
+      mixed_content
+      namespace ::Tbx::Namespaces::TbxNamespace
+
+      map_attribute "id", to: :id
+      map_element "admin", to: :admin
+      map_element "adminNote", to: :admin_note
+      map_element "note", to: :note
+      map_element "ref", to: :ref
+      map_element "xref", to: :xref
+    end
+  end
+end

data/lib/tbx/admin_note.rb

@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+module Tbx
+  class AdminNote < Lutaml::Model::Serializable
+    attribute :id, :string
+    attribute :lang, Lutaml::Xml::W3c::XmlLangType
+    attribute :target, :string
+    attribute :datatype, :string
+    attribute :type, :string
+    attribute :content, :string, collection: true
+
+    xml do
+      root "adminNote"
+      mixed_content
+      namespace ::Tbx::Namespaces::TbxNamespace
+
+      map_attribute "id", to: :id
+      w3c_attributes :lang
+      map_attribute "target", to: :target
+      map_attribute "datatype", to: :datatype
+      map_attribute "type", to: :type
+      map_content to: :content
+    end
+  end
+end

data/lib/tbx/back.rb

@@ -0,0 +1,17 @@
+# frozen_string_literal: true
+
+module Tbx
+  class Back < Lutaml::Model::Serializable
+    attribute :id, :string
+    attribute :ref_object_sec, ::Tbx::RefObjectSec, collection: true
+
+    xml do
+      root "back"
+      mixed_content
+      namespace ::Tbx::Namespaces::TbxNamespace
+
+      map_attribute "id", to: :id
+      map_element "refObjectSec", to: :ref_object_sec
+    end
+  end
+end

data/lib/tbx/body.rb

@@ -0,0 +1,17 @@
+# frozen_string_literal: true
+
+module Tbx
+  class Body < Lutaml::Model::Serializable
+    attribute :id, :string
+    attribute :concept_entry, ::Tbx::ConceptEntry, collection: true
+
+    xml do
+      root "body"
+      mixed_content
+      namespace ::Tbx::Namespaces::TbxNamespace
+
+      map_attribute "id", to: :id
+      map_element "conceptEntry", to: :concept_entry
+    end
+  end
+end

data/lib/tbx/change.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+module Tbx
+  class Change < Lutaml::Model::Serializable
+    attribute :id, :string
+    attribute :lang, Lutaml::Xml::W3c::XmlLangType
+    attribute :p, ::Tbx::P, collection: true
+
+    xml do
+      root "change"
+      mixed_content
+      namespace ::Tbx::Namespaces::TbxNamespace
+
+      map_attribute "id", to: :id
+      w3c_attributes :lang
+      map_element "p", to: :p
+    end
+  end
+end

data/lib/tbx/concept_entry.rb

@@ -0,0 +1,33 @@
+# frozen_string_literal: true
+
+module Tbx
+  class ConceptEntry < Lutaml::Model::Serializable
+    attribute :id, :string
+    attribute :admin, ::Tbx::Admin, collection: true
+    attribute :admin_grp, ::Tbx::AdminGrp, collection: true
+    attribute :descrip, ::Tbx::Descrip, collection: true
+    attribute :descrip_grp, ::Tbx::DescripGrp, collection: true
+    attribute :note, ::Tbx::Note, collection: true
+    attribute :ref, ::Tbx::Ref, collection: true
+    attribute :transac_grp, ::Tbx::TransacGrp, collection: true
+    attribute :xref, ::Tbx::Xref, collection: true
+    attribute :lang_sec, ::Tbx::LangSec, collection: true
+
+    xml do
+      root "conceptEntry"
+      mixed_content
+      namespace ::Tbx::Namespaces::TbxNamespace
+
+      map_attribute "id", to: :id
+      map_element "admin", to: :admin
+      map_element "adminGrp", to: :admin_grp
+      map_element "descrip", to: :descrip
+      map_element "descripGrp", to: :descrip_grp
+      map_element "note", to: :note
+      map_element "ref", to: :ref
+      map_element "transacGrp", to: :transac_grp
+      map_element "xref", to: :xref
+      map_element "langSec", to: :lang_sec
+    end
+  end
+end

data/lib/tbx/date.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+module Tbx
+  class DateElement < Lutaml::Model::Serializable
+    attribute :id, :string
+    attribute :content, :string
+
+    xml do
+      root "date"
+      namespace ::Tbx::Namespaces::TbxNamespace
+
+      map_attribute "id", to: :id
+      map_content to: :content
+    end
+  end
+end

data/lib/tbx/descrip.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+module Tbx
+  class Descrip < Lutaml::Model::Serializable
+    attribute :id, :string
+    attribute :lang, Lutaml::Xml::W3c::XmlLangType
+    attribute :target, :string
+    attribute :datatype, :string
+    attribute :type, :string
+    attribute :content, :string, collection: true
+    attribute :hi, ::Tbx::Hi, collection: true
+    attribute :ec, ::Tbx::Ec, collection: true
+    attribute :foreign, ::Tbx::Foreign, collection: true
+    attribute :ph, ::Tbx::Ph, collection: true
+    attribute :sc, ::Tbx::Sc, collection: true
+
+    xml do
+      root "descrip"
+      mixed_content
+      namespace ::Tbx::Namespaces::TbxNamespace
+
+      map_attribute "id", to: :id
+      w3c_attributes :lang
+      map_attribute "target", to: :target
+      map_attribute "datatype", to: :datatype
+      map_attribute "type", to: :type
+      map_content to: :content
+      map_element "hi", to: :hi
+      map_element "ec", to: :ec
+      map_element "foreign", to: :foreign
+      map_element "ph", to: :ph
+      map_element "sc", to: :sc
+    end
+  end
+end