termium 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 9f242a07fdedab976941acc1580ca44d301ab96e3b3c5f70bf17704fabf39f0e
+  data.tar.gz: 9b650e4b6d9786014c09ada236f5d369c5a9138616d77083b14f121b881cb2eb
+SHA512:
+  metadata.gz: 98d930ad1aab03405b14561d17cd14b76531d3a65381362b3a2822e1c8f4244bb49a9f4074a3d189fc8049a6bccbd43d40d02f9766ec00bfe78070c1950c0c5c
+  data.tar.gz: 904748c40e59b69efeb8d2c9355ac9523b005f39b89ca03f2fac18384780e2bba4e87d2b5a441b9c725ed2c9aff426a4c588ef4cb72956199fa92aa371e099c0

data/.github/workflows/main.yml

@@ -0,0 +1,27 @@
+name: Ruby
+
+on:
+  push:
+    branches:
+      - main
+
+  pull_request:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    name: Ruby ${{ matrix.ruby }}
+    strategy:
+      matrix:
+        ruby:
+          - '3.1.2'
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Ruby
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby }}
+        bundler-cache: true
+    - name: Run the default task
+      run: bundle exec rake

data/.gitignore

@@ -0,0 +1,11 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status

data/.rspec

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

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,84 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming, diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive, or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, and will communicate reasons for moderation decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when an individual is officially representing the community in public spaces. Examples of representing our community include using an official e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at ronald.tse@ribose.com. All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing clarity around the nature of the violation and an explanation of why the behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, for a specified period of time. This includes avoiding interactions in community spaces as well as external channels like social media. Violating these terms may lead to a temporary or permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public communication with the community for a specified period of time. No public or private interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, is allowed during this period. Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community standards, including sustained inappropriate behavior,  harassment of an individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.0,
+available at https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at https://www.contributor-covenant.org/translations.

data/Gemfile

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+gemspec

data/README.adoc

@@ -0,0 +1,66 @@
+= Termium Ruby gem
+
+== Purpose
+
+The Termium Ruby gem parses export data formats from the
+https://www.btb.termiumplus.gc.ca[TERMIUM Plus]
+terminology database service from the Government of Canada.
+
+
+== Commands
+
+`termium convert`:: Convert a TERMIUM Plus export XML file to a Glossarist dataset
+
+
+=== Usage
+
+[source,sh]
+----
+$ termium convert -i INPUT_XML_FILE [-o OUTPUT_PATH]
+----
+
+=== Options
+
+[cols="a,a",options="header"]
+|===
+| Flag | Description
+
+|`-i`, `--input-path`
+|
+Source path to TERMIUM Plus XML export file.
+The file needs to start with the `<extract>` tag.
+
+|`-o`, `--output-path`
+|
+Destination path to Glossarist dataset directory.
+If the directory doesn't exist it will be created.
+If not provided, defaults to the basename of the input file, e.g. `foo/bar.xml` will export to `foo/bar/`.
+
+|===
+
+
+== Library
+
+=== Usage
+
+This gem makes heavy use of the `Shale` classes for XML serialization.
+
+The following code converts the Termium extract into a Glossarist dataset.
+
+[source,ruby]
+----
+termium_extract = Termium::Extract.from_xml(IO.read(termium_extract_file))
+glossarist_col = termium_extract.to_concept
+FileUtils.mkdir_p(glossarist_output_file)
+glossarist_col.save_to_files(glossarist_output_file)
+----
+
+== 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 +1,11 @@
+# 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/exe/termium

@@ -0,0 +1,6 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require_relative "../lib/termium/cli"
+
+Termium::Cli.start(ARGV)

data/lib/termium/abbreviation.rb

@@ -0,0 +1,56 @@
+# frozen_string_literal: true
+
+require_relative "source_ref"
+require_relative "parameter"
+require_relative "designation_operations"
+
+module Termium
+  # For <abbreviation>
+  class Abbreviation < Shale::Mapper
+    attribute :order, Shale::Type::Integer
+    attribute :value, Shale::Type::String
+    attribute :source_ref, SourceRef
+    attribute :parameter, Parameter, collection: true
+    include DesignationOperations
+
+    # <abbreviation order="1" value="PCI">
+    # <sourceRef order="1" />
+    # <parameter abbreviation="COR" />
+    # <parameter abbreviation="F" />
+    # <parameter abbreviation="NORM" />
+
+    xml do
+      root "abbreviation"
+      map_attribute "order", to: :order
+      map_attribute "value", to: :value
+      map_element "sourceRef", to: :source_ref
+      map_element "parameter", to: :parameter
+    end
+
+    def deprecated
+      parameter.map(&:abbreviation).include?("AE")
+    end
+
+    def to_h
+      set = {
+        "designation" => value,
+        "type" => "abbreviation",
+        "normative_status" => deprecated ? "deprecated" : "preferred"
+      }
+
+      # if geographical_area
+      #   set["geographical_area"] = geographical_area
+      # end
+
+      # if plurality
+      #   set["plurality"] = plurality
+      # end
+
+      set["gender"] = gender if gender
+
+      set["part_of_speech"] = part_of_speech if part_of_speech
+
+      set
+    end
+  end
+end

data/lib/termium/cli.rb

@@ -0,0 +1,71 @@
+# frozen_string_literal: true
+
+require_relative "../termium"
+
+module Termium
+  # Command-line interface
+  class Cli < Thor
+    desc "convert", "Convert Termium entries into a Glossarist dataset"
+
+    option :input_file, aliases: :i, required: true, desc: "Path to TERMIUM Plus XML extract"
+    option :output_file, aliases: :o, desc: "Output file path"
+
+    def input_file_as_path
+      input_path = Pathname.new(Dir.pwd).join(Pathname.new(options[:input_file]))
+
+      unless input_path.exist?
+        error "Input file `#{options[:input_file]}` does not exist."
+        exit 1
+      end
+
+      input_path
+    end
+
+    def output_path_ready
+      output_path = options[:output_file]
+      output_path ||= input_path.dirname.join(input_path.basename(input_path.extname))
+
+      output_path = Pathname.new(Dir.pwd).join(Pathname.new(output_path))
+
+      if output_path.exist?
+        puts "Using existing directory: #{output_path.relative_path_from(Dir.pwd)}"
+      else # and is directory
+        puts "Created directory: #{output_path.relative_path_from(Dir.pwd)}"
+        output_path.mkdir
+      end
+
+      output_path
+    end
+
+    def convert
+      input_path = input_file_as_path
+      puts "Reading input file: #{input_path.relative_path_from(Dir.pwd)}"
+      termium_extract = Termium::Extract.from_xml(IO.read(input_path.expand_path))
+
+      puts "Size of dataset: #{termium_extract.core.size}"
+
+      puts "Converting to Glossarist..."
+      glossarist_col = termium_extract.to_concept
+      # pp glossarist_col.first
+
+      output_path = output_path_ready
+      puts "Writing Glossarist dataset..."
+      glossarist_col.save_to_files(output_path.expand_path)
+      puts "Written Glossarist dataset to: #{output_path.relative_path_from(Dir.pwd)}"
+    end
+
+    def method_missing(*args)
+      warn "No method found named: #{args[0]}"
+      warn "Run with `--help` or `-h` to see available options"
+      exit 1
+    end
+
+    def respond_to_missing?
+      true
+    end
+
+    def self.exit_on_failure?
+      true
+    end
+  end
+end

data/lib/termium/core.rb

@@ -0,0 +1,53 @@
+# frozen_string_literal: true
+
+require_relative "language_module"
+require_relative "subject"
+require_relative "universal_entry"
+require_relative "source"
+
+module Termium
+  # For <core>
+  class Core < Shale::Mapper
+    attribute :identification_number, Shale::Type::String
+    attribute :dissemination_level, Shale::Type::String
+
+    attribute :language_module, LanguageModule, collection: true
+    attribute :subject, Subject
+    attribute :universal_entry, UniversalEntry
+    attribute :source, Source, collection: true
+
+    xml do
+      root "core"
+      map_attribute "disseminationLevel", to: :dissemination_level
+      map_attribute "identificationNumber", to: :identification_number
+      map_element "languageModule", to: :language_module
+      map_element "subject", to: :subject
+      map_element "universalEntry", to: :universal_entry
+      map_element "source", to: :source
+    end
+
+    # TODO: In Termium XML, each definition per lang or note can be linked to a
+    # particular source via the sourceRef number.
+    def concept_sources
+      source.map(&:to_concept_source)
+    end
+
+    def to_concept
+      concept = Glossarist::ManagedConcept.new(id: identification_number)
+
+      language_module.map(&:to_concept).each do |localized_concept|
+        # TODO: This is needed to skip the empty french entries of 10031781 and 10031778
+        next if localized_concept.nil?
+
+        localized_concept.id = identification_number
+        # TODO: this should just be localized_concept.notes << universal_entry.value
+        # TODO: Depends on https://github.com/glossarist/glossarist-ruby/issues/82
+        localized_concept.notes << Glossarist::DetailedDefinition.new(universal_entry.value)
+        localized_concept.sources = concept_sources
+        concept.add_localization(localized_concept)
+      end
+
+      concept
+    end
+  end
+end

data/lib/termium/designation_operations.rb

@@ -0,0 +1,32 @@
+# frozen_string_literal: true
+
+module Termium
+  # Mixin for designation operations
+  module DesignationOperations
+    PART_OF_SPEECH_CODE_MAPPING = {
+      "ADJ" => "adj",
+      "N" => "noun",
+      "V" => "verb"
+    }.freeze
+    def part_of_speech
+      value = parameter.detect do |x|
+        PART_OF_SPEECH_CODE_MAPPING[x.abbreviation]
+      end
+
+      value ? PART_OF_SPEECH_CODE_MAPPING[value.abbreviation] : nil
+    end
+
+    GENDER_CODE_MAPPING = {
+      "F" => "f",
+      "M" => "m",
+      "EPI" => "c" # this means "Epicine"
+    }.freeze
+    def gender
+      value = parameter.detect do |x|
+        GENDER_CODE_MAPPING[x.abbreviation]
+      end
+
+      value ? GENDER_CODE_MAPPING[value.abbreviation] : nil
+    end
+  end
+end

data/lib/termium/entry_term.rb

@@ -0,0 +1,83 @@
+# frozen_string_literal: true
+
+require_relative "source_ref"
+require_relative "abbreviation"
+require_relative "parameter"
+require_relative "designation_operations"
+
+module Termium
+  # For <entryTerm>
+  class EntryTerm < Shale::Mapper
+    attribute :order, Shale::Type::Integer
+    attribute :value, Shale::Type::String
+    attribute :source_ref, SourceRef
+    attribute :abbreviation, Abbreviation, collection: true
+    attribute :parameter, Parameter, collection: true
+    include DesignationOperations
+
+    xml do
+      root "entryTerm"
+      map_attribute "order", to: :order
+      map_attribute "value", to: :value
+      map_element "abbreviation", to: :abbreviation
+      map_element "sourceRef", to: :source_ref
+      map_element "parameter", to: :parameter
+    end
+
+    # attr_accessor :geographical_area,
+    #   :deprecated,
+    #   :plurality,
+    #   :part_of_speech,
+    #   :gender
+
+    GEOGRAPHICAL_CODE_MAPPING = {
+      "USA" => "US",
+      "CAN" => "CA",
+      "GB" => "GB",
+      "AUS" => "AU",
+      "EUR" => "EU"
+    }.freeze
+    def geographical_area
+      keys = GEOGRAPHICAL_CODE_MAPPING.keys
+      usage = parameter.select do |x|
+        keys.include?(x.abbreviation)
+      end
+
+      return nil if usage.empty?
+
+      usage.map do |x|
+        GEOGRAPHICAL_CODE_MAPPING[x.abbreviation]
+      end.join("; ")
+    end
+
+    def deprecated
+      parameter.map(&:abbreviation).include?("AE")
+    end
+
+    def plurality
+      if parameter.map(&:abbreviation).include?("PL")
+        "plural"
+      else
+        "singular"
+      end
+    end
+
+    def to_h
+      set = {
+        "designation" => value,
+        "type" => "expression",
+        "normative_status" => deprecated ? "deprecated" : "preferred"
+      }
+
+      set["geographical_area"] = geographical_area if geographical_area
+
+      set["plurality"] = plurality if plurality
+
+      set["gender"] = gender if gender
+
+      set["part_of_speech"] = part_of_speech if part_of_speech
+
+      set
+    end
+  end
+end

data/lib/termium/extract.rb

@@ -0,0 +1,28 @@
+# frozen_string_literal: true
+
+require_relative "extract_language"
+require_relative "core"
+
+module Termium
+  # For <extract>
+  class Extract < Shale::Mapper
+    attribute :language, Shale::Type::String
+    attribute :extract_language, ExtractLanguage, collection: true
+    attribute :core, Core, collection: true
+
+    xml do
+      root "termium_extract"
+      # namespace 'http://termium.tpsgc-pwgsc.gc.ca/schemas/2012/06/Termium', 'ns2'
+
+      map_attribute "language", to: :language
+      map_element "extractLanguage", to: :extract_language
+      map_element "core", to: :core
+    end
+
+    def to_concept
+      coll = Glossarist::ManagedConceptCollection.new
+      coll.managed_concepts = core.map(&:to_concept)
+      coll
+    end
+  end
+end

data/lib/termium/extract_language.rb

@@ -0,0 +1,14 @@
+# frozen_string_literal: true
+
+module Termium
+  # For <extractLanguage>
+  class ExtractLanguage < Shale::Mapper
+    attribute :language, Shale::Type::String
+    attribute :order, Shale::Type::Integer
+    xml do
+      root "extractLanguage"
+      map_attribute "language", to: :language
+      map_attribute "order", to: :order
+    end
+  end
+end

data/lib/termium/language_module.rb

@@ -0,0 +1,77 @@
+# frozen_string_literal: true
+
+require_relative "entry_term"
+require_relative "textual_support"
+
+module Termium
+  # For <languageModule>
+  class LanguageModule < Shale::Mapper
+    attribute :language, Shale::Type::String
+    attribute :entry_term, EntryTerm, collection: true
+    attribute :textual_support, TextualSupport, collection: true
+    xml do
+      root "languageModule"
+      map_attribute "language", to: :language
+      map_element "entryTerm", to: :entry_term
+      map_element "textualSupport", to: :textual_support
+    end
+
+    def definition_raw
+      textual_support.detect(&:is_definition?)
+    end
+
+    def definition
+      definition_raw&.value_typed
+    end
+
+    def domain
+      definition_raw&.domain
+    end
+
+    def notes
+      textual_support.select(&:is_note?).map(&:value_typed)
+    end
+
+    def examples
+      textual_support.select(&:is_example?).map(&:value_typed)
+    end
+
+    def abbreviations
+      entry_term.map(&:abbreviation).flatten
+    end
+
+    LANGUAGE_CODE_MAPPING = {
+      "en" => "eng",
+      "fr" => "fre"
+    }.freeze
+
+    def designations
+      # NOTE: entry_term is a collection
+      entry_term + abbreviations
+    end
+
+    def to_h
+      # TODO: This is needed to skip the empty french entries of 10031781 and 10031778
+      return nil unless definition
+
+      src = {
+        "language_code" => LANGUAGE_CODE_MAPPING[language.downcase],
+        "terms" => designations.map(&:to_h),
+        "definition" => [{ content: definition }],
+        "notes" => notes,
+        "examples" => examples
+      }
+
+      src["domain"] = domain if domain
+
+      src
+    end
+
+    def to_concept
+      x = to_h
+      return nil unless x
+
+      Glossarist::LocalizedConcept.new(x)
+    end
+  end
+end

data/lib/termium/parameter.rb

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+module Termium
+  # For <parameter>
+  class Parameter < Shale::Mapper
+    # <parameter abbreviation="NORM"/>
+    attribute :abbreviation, Shale::Type::String
+    xml do
+      root "parameter"
+      map_attribute "abbreviation", to: :abbreviation
+    end
+  end
+end

data/lib/termium/source.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+module Termium
+  # For <source>
+  class Source < Shale::Mapper
+    ISO_BIB_REGEX = /\AISO-([\d-]+)\s+\*\s+(\d{4})\s+.*/.freeze
+    ISOIEC_BIB_REGEX = /\AISO-IEC-([\d-]+)\s+\*\s+(\d{4})\s+.*/.freeze
+
+    attribute :order, Shale::Type::Integer
+    attribute :details, Shale::Type::String
+    xml do
+      root "source"
+      map_attribute "order", to: :order
+      map_attribute "details", to: :details
+    end
+
+    def content
+      if (matches = details.match(ISOIEC_BIB_REGEX))
+        "ISO/IEC #{matches[1]}:#{matches[2]}"
+      elsif (matches = details.match(ISO_BIB_REGEX))
+        "ISO #{matches[1]}:#{matches[2]}"
+      else
+        details
+      end
+    end
+
+    def to_concept_source
+      Glossarist::ConceptSource.new({
+                                      "type" => "lineage",
+                                      "ref" => content,
+                                      "status" => "identical"
+                                    })
+    end
+  end
+end

data/lib/termium/source_ref.rb

@@ -0,0 +1,12 @@
+# frozen_string_literal: true
+
+module Termium
+  # For <sourceRef>
+  class SourceRef < Shale::Mapper
+    attribute :order, Shale::Type::Integer
+    xml do
+      root "sourceRef"
+      map_attribute "order", to: :order
+    end
+  end
+end

data/lib/termium/subject.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+module Termium
+  # For <subject>
+  class Subject < Shale::Mapper
+    attribute :abbreviation, Shale::Type::String
+    attribute :details, Shale::Type::String
+
+    # <subject abbreviation="YBB" details="Compartment - ISO/IEC JTC 1 Information Technology Vocabulary"/>
+    xml do
+      root "subject"
+      map_attribute "abbreviation", to: :abbreviation
+      map_attribute "details", to: :details
+    end
+  end
+end

data/lib/termium/textual_support.rb

@@ -0,0 +1,89 @@
+# frozen_string_literal: true
+
+require_relative "source_ref"
+
+module Termium
+  # For <textualSupport>
+  class TextualSupport < Shale::Mapper
+    attribute :order, Shale::Type::Integer
+    attribute :type, Shale::Type::String
+    attribute :value, Shale::Type::String
+    attribute :source_ref, SourceRef
+    xml do
+      root "textualSupport"
+      map_attribute "order", to: :order
+      map_attribute "type", to: :type
+      map_element "value", to: :value
+      map_element "sourceRef", to: :source_ref
+    end
+
+    def value_cleaned
+      value.gsub(/\n\s+/, " ")
+    end
+
+    def value_typed
+      if is_example?
+        value_example
+      elsif is_definition?
+        value_definition
+      else
+        value_cleaned
+      end
+    end
+
+    EXAMPLE_REGEX = /\AEx[ea]mples?\s*:\s*/.freeze
+    def is_example?
+      value_cleaned.match(EXAMPLE_REGEX)
+    end
+
+    def is_definition?
+      type == "DEF"
+    end
+
+    def is_note?
+      !is_definition? && !is_example?
+    end
+
+    def is_observation?
+      type == "OBS"
+    end
+
+    def value_example
+      value_cleaned.gsub(EXAMPLE_REGEX, "")
+    end
+
+    DEFINITION_REGEX = /\A<(.+?)>\s*/.freeze
+    def value_definition
+      value_cleaned.gsub(DEFINITION_REGEX, "")
+    end
+
+    def has_domain?
+      !value_cleaned.match(DEFINITION_REGEX).nil?
+    end
+
+    def domain
+      return unless has_domain?
+
+      value_cleaned.match(DEFINITION_REGEX)[1]
+    end
+
+    # This is an attempt to extract the textual reference within the note.
+    # TODO: Use this to correlate the actual term with the source reference, i.e
+    # from the following note, the terms "abduction; inférence abductive" come from
+    # "ISO-IEC-2382-28-1995".
+    # NOTE:  abduction; inférence abductive : termes et définition normalisés par l'ISO/CEI [<<ISO-IEC-2382-28-1995>>].
+    def source_from_note
+      x = note.match(/\[.*\]/)
+      return nil if x.nil?
+
+      ref = x.match(/\[.*\]/).to_s.gsub(/[\[\]]/, "")
+
+      # "[ISO/IEC 2382-13:1996; ISO/IEC 2382-24:1995]"
+      if ref.include?(";")
+        ref.split("; ")
+      else
+        [ref]
+      end
+    end
+  end
+end

data/lib/termium/universal_entry.rb

@@ -0,0 +1,28 @@
+# frozen_string_literal: true
+
+require_relative "source_ref"
+require_relative "parameter"
+
+module Termium
+  # For <universalEntry>
+  class UniversalEntry < Shale::Mapper
+    attribute :order, Shale::Type::Integer
+    attribute :value, Shale::Type::String
+    attribute :source_ref, SourceRef
+    attribute :parameter, Parameter
+
+    # <universalEntry order="1">
+    #   <value>09.08.09 (2382)</value>
+    #   <sourceRef order="1"/>
+    #   <parameter abbreviation="CONUM"/>
+    # </universalEntry>
+
+    xml do
+      root "universalEntry"
+      map_attribute "order", to: :order
+      map_element "value", to: :value
+      map_element "sourceRef", to: :source_ref
+      map_element "parameter", to: :parameter
+    end
+  end
+end

data/lib/termium/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module Termium
+  VERSION = "0.1.0"
+end

data/lib/termium.rb

@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+require "glossarist"
+require "shale"
+require "shale/adapter/nokogiri"
+Shale.xml_adapter = Shale::Adapter::Nokogiri
+
+module Termium
+  class Error < StandardError; end
+end
+
+require_relative "termium/version"
+require_relative "termium/extract"
+require_relative "termium/extract_language"
+require_relative "termium/core"
+require_relative "termium/abbreviation"
+require_relative "termium/designation_operations"
+require_relative "termium/entry_term"
+require_relative "termium/language_module"
+require_relative "termium/parameter"
+require_relative "termium/source"
+require_relative "termium/source_ref"
+require_relative "termium/subject"
+require_relative "termium/textual_support"
+require_relative "termium/universal_entry"

data/sig/termium.rbs

@@ -0,0 +1,4 @@
+module Termium
+  VERSION: String
+  # See the writing guide of rbs: https://github.com/ruby/rbs#guides
+end

data/termium.gemspec

@@ -0,0 +1,41 @@
+# frozen_string_literal: true
+
+require_relative "lib/termium/version"
+
+all_files_in_git = Dir.chdir(File.expand_path(__dir__)) do
+  `git ls-files -z`.split("\x0")
+end
+
+Gem::Specification.new do |spec|
+  spec.name = "termium"
+  spec.version = Termium::VERSION
+  spec.authors = ["Ribose"]
+  spec.email = ["open.source@ribose.com"]
+
+  spec.summary       =
+    "Parser for the TERMIUM Plus terminology database of the Government of Canada"
+  spec.homepage      = "https://github.com/glossarist/termium"
+  spec.license       = "BSD-2-Clause"
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.6.0")
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = spec.homepage
+  spec.metadata["bug_tracker_uri"] = "#{spec.homepage}/issues"
+
+  # Specify which files should be added to the gem when it is released.
+  spec.files         = all_files_in_git
+                       .reject { |f| f.match(%r{\A(?:test|spec|features|bin|\.)/}) }
+
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "glossarist", "~> 1.0"
+  spec.add_dependency "shale"
+  spec.add_dependency "thor"
+
+  spec.add_development_dependency "pry", "~> 0.14.0"
+  spec.add_development_dependency "rake", "~> 13.0"
+  spec.add_development_dependency "rspec", "~> 3.10"
+  spec.add_development_dependency "rubocop"
+end

metadata

@@ -0,0 +1,171 @@
+--- !ruby/object:Gem::Specification
+name: termium
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Ribose
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2023-11-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: glossarist
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: shale
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: thor
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.14.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.14.0
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.10'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description:
+email:
+- open.source@ribose.com
+executables:
+- termium
+extensions: []
+extra_rdoc_files: []
+files:
+- ".github/workflows/main.yml"
+- ".gitignore"
+- ".rspec"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- README.adoc
+- Rakefile
+- exe/termium
+- lib/termium.rb
+- lib/termium/abbreviation.rb
+- lib/termium/cli.rb
+- lib/termium/core.rb
+- lib/termium/designation_operations.rb
+- lib/termium/entry_term.rb
+- lib/termium/extract.rb
+- lib/termium/extract_language.rb
+- lib/termium/language_module.rb
+- lib/termium/parameter.rb
+- lib/termium/source.rb
+- lib/termium/source_ref.rb
+- lib/termium/subject.rb
+- lib/termium/textual_support.rb
+- lib/termium/universal_entry.rb
+- lib/termium/version.rb
+- sig/termium.rbs
+- termium.gemspec
+homepage: https://github.com/glossarist/termium
+licenses:
+- BSD-2-Clause
+metadata:
+  homepage_uri: https://github.com/glossarist/termium
+  source_code_uri: https://github.com/glossarist/termium
+  bug_tracker_uri: https://github.com/glossarist/termium/issues
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.6.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.7
+signing_key:
+specification_version: 4
+summary: Parser for the TERMIUM Plus terminology database of the Government of Canada
+test_files: []