iev 0.4.5 → 0.4.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a539da108086dd1fb862d1d99d6763a3d32015a921ef580018ac9671660b0b68
-  data.tar.gz: af0e1813cae179dd69da3a9e8fde6e8d275e34d59949bd43a0642a171988f311
+  metadata.gz: a965bb1653227f1b4ba8ebc27e9f3a67950d359cec2f809b46d4e0edebec18e9
+  data.tar.gz: 5414e80f45caf460970d75052dc7bd7ec931d697f267de0ea2df6abd6a2209ba
 SHA512:
-  metadata.gz: c93e2479cccfbe56b37b1d1cd604a3b327258abd8c50f9b99e2091abe7e4e714aa8e44c49f9e886d11483ec80e8e2325ce78f0598e8b34fdeb4fe7442b0e0d32
-  data.tar.gz: 28c5084f7a75106feee144201b75b642217674438f14a48c216a1069ed1b5d0abe822d137afb6671303bc1a407689ec236c4b2ff5abe2c0626e3a34f1ec35b34
+  metadata.gz: 805143019d38cf0ed15e6526b8b727e681e8e3361b25d3c58ea71f6b2b4cf66eb3dda9882bcb8f038317bc4f1bd84554f6abdd14e4575774c2572a08b45c8865
+  data.tar.gz: 204a790f8cc565859a3abb9f64b137b235a559bbb411f52fee15989b467c5860ff2fe3073c65495f5c28e1e01a251375c533139cac07eaefb7341b5016669d1a

data/.rubocop.yml

@@ -1,6 +1,7 @@
 # Auto-generated by Cimas: Do not edit it manually!
 # See https://github.com/metanorma/cimas
 inherit_from:
+  - .rubocop_todo.yml
   - https://raw.githubusercontent.com/riboseinc/oss-guides/main/ci/rubocop.yml
 
 # local repo-specific modifications

data/.rubocop_todo.yml

@@ -1,65 +1,100 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2025-11-14 11:14:05 UTC using RuboCop version 1.81.7.
+# on 2026-06-18 12:23:48 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: 43
+# Offense count: 1
+Gemspec/RequiredRubyVersion:
+  Exclude:
+    - 'iev.gemspec'
+
+# Offense count: 64
 # This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: Max, AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, IgnoreCopDirectives, AllowedPatterns, SplitStrings.
+# Configuration parameters: Max, AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, AllowRBSInlineAnnotation, AllowCopDirectives, AllowedPatterns, SplitStrings.
 # URISchemes: http, https
 Layout/LineLength:
-  Exclude:
-    - 'iev.gemspec'
-    - 'lib/iev/cli/command.rb'
-    - 'lib/iev/cli/command_helper.rb'
-    - 'lib/iev/db_cache.rb'
-    - 'lib/iev/source_parser.rb'
-    - 'spec/acceptance/db2yaml_spec.rb'
-    - 'spec/acceptance/xlsx2yaml_spec.rb'
-    - 'spec/iev_spec.rb'
+  Enabled: false
 
-# Offense count: 7
+# Offense count: 19
 # Configuration parameters: IgnoreLiteralBranches, IgnoreConstantBranches, IgnoreDuplicateElseBranch.
 Lint/DuplicateBranch:
   Exclude:
     - 'lib/iev/source_parser.rb'
-    - 'lib/iev/term_builder.rb'
+    - 'lib/iev/utilities.rb'
 
 # Offense count: 1
 Lint/MixedRegexpCaptureTypes:
   Exclude:
     - 'lib/iev/term_builder.rb'
 
-# Offense count: 10
+# Offense count: 2
+Lint/ShadowedException:
+  Exclude:
+    - 'lib/iev/source_parser.rb'
+
+# Offense count: 27
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes, Max.
 Metrics/AbcSize:
   Exclude:
+    - 'lib/iev/cli/command.rb'
+    - 'lib/iev/cli/command_helper.rb'
     - 'lib/iev/converter/mathml_to_asciimath.rb'
     - 'lib/iev/db_writer.rb'
+    - 'lib/iev/exporter.rb'
+    - 'lib/iev/scraper/page_parser.rb'
     - 'lib/iev/source_parser.rb'
+    - 'lib/iev/subject_area_concepts.rb'
+    - 'lib/iev/subject_areas.rb'
     - 'lib/iev/term_builder.rb'
+    - 'lib/iev/utilities.rb'
+    - 'spec/iev/supersession_parser_spec.rb'
 
-# Offense count: 5
+# Offense count: 15
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/CyclomaticComplexity:
   Exclude:
-    - 'lib/iev.rb'
     - 'lib/iev/converter/mathml_to_asciimath.rb'
+    - 'lib/iev/exporter.rb'
+    - 'lib/iev/scraper/page_parser.rb'
     - 'lib/iev/source_parser.rb'
+    - 'lib/iev/subject_areas.rb'
     - 'lib/iev/term_builder.rb'
+    - 'lib/iev/utilities.rb'
 
-# Offense count: 20
+# Offense count: 36
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
-  Max: 74
+  Max: 73
+
+# Offense count: 1
+# Configuration parameters: CountKeywordArgs, MaxOptionalParameters.
+Metrics/ParameterLists:
+  Max: 7
 
-# Offense count: 3
+# Offense count: 8
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/PerceivedComplexity:
   Exclude:
-    - 'lib/iev.rb'
     - 'lib/iev/converter/mathml_to_asciimath.rb'
+    - 'lib/iev/exporter.rb'
+    - 'lib/iev/scraper/page_parser.rb'
+    - 'lib/iev/subject_areas.rb'
     - 'lib/iev/term_builder.rb'
+
+# Offense count: 1
+# 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:
+    - 'lib/iev/subject_areas.rb'
+
+# Offense count: 2
+# Configuration parameters: EnforcedStyle, CheckMethodNames, CheckSymbols, AllowedIdentifiers, AllowedPatterns.
+# SupportedStyles: snake_case, normalcase, non_integer
+# AllowedIdentifiers: TLS1_1, TLS1_2, capture3, iso8601, rfc1123_date, rfc822, rfc2822, rfc3339, x86_64
+Naming/VariableNumber:
+  Exclude:
+    - 'spec/iev/exporter_spec.rb'

data/CLAUDE.md

@@ -27,15 +27,33 @@ This is a Ruby gem (`iev`) for working with the International Electrotechnical V
 
 ### Key Modules
 
-- `TermBuilder` — the core converter that turns a spreadsheet row into a `Glossarist::LocalizedConcept`. Handles definition splitting (notes/examples extraction), term designation parsing, and source parsing.
+- `TermBuilder` — the core converter that turns a spreadsheet row into a `Glossarist::LocalizedConcept`. Handles definition splitting (notes/examples extraction), term designation parsing, and source parsing. Sets `ConceptData#domain` to section/area title text (not URI).
 - `SourceParser` — parses the SOURCE column from IEV exports, normalizing references (CEI→IEC, UIT→ITU, etc.) and extracting ref/clause/relationship using extensive regex matching.
-- `TermAttrsParser` — parses the TERMATTRIBUTE field (gender, plurality, part of speech, geographical area, abbreviations).
+- `TermAttrsParser` — parses the TERMATTRIBUTE field (gender, plurality, part of speech, geographical area, usage_info).
 - `SupersessionParser` — parses the REPLACES field for deprecated term relationships.
 - `SubjectAreas` — manages the IEV subject area/section hierarchy. Bundled `data/subject_areas.yaml` contains the area/section tree. URI scheme: `area-{code}` and `section-{code}`.
-- `SubjectAreaConcepts` — builds area and section hierarchy concepts with `ConceptReference.domain()` objects in `ManagedConceptData#domains`, `broader`/`narrower` relations, and `ConceptData#domain` references.
-- `Exporter` — full export pipeline (Excel/SQLite → Glossarist YAML). Assigns domain `ConceptReference` objects via `domain_references_for`.
+- `SubjectAreaConcepts` — builds area and section hierarchy concepts. Uses `ConceptReference` with proper `ref_type` per `ConceptReferenceType`: `"domain"` for thematic area classification, `"section"` for structural section membership. Sets `ConceptData#domain` to area title text.
+- `Exporter` — full export pipeline (Excel/SQLite → Glossarist YAML). Assigns domain and section `ConceptReference` objects via `domain_references_for`. Uses `Glossarist::DatasetRegister` model for `register.yaml`. Sets `schema_version: "3"` on all exported concepts. Pipeline order: build → subject areas → section relations → figure extraction → reference enrichment → save concepts → save figures → save bibliography → save register.
+- `FigureBuilder` — destructive extraction pass that hoists AsciiDoc image macros (emitted from SIMG tags by `Utilities`) into dataset-shared `Glossarist::Figure` entities. Rewrites inline text to `{{fig:id, display}}` mentions and adds `FigureReference` entries to `ManagedConceptData#figures`. One Figure entity per unique image file; captions merge across languages.
+- `BibliographyBuilder` — collects unique `(source, id)` pairs from every concept's sources (localized and managed) into a `Glossarist::BibliographyData`. Entry ids are normalized with the same rules as `Glossarist::Validation::BibliographyIndex` so consumers can resolve anchors.
 - `Converter::MathmlToAsciimath` — converts MathML markup to AsciiMath using Plurimath.
-- `Utilities` — HTML processing: converts IEV cross-references (`<a href=IEV...>`) to `{{term, IEV:code}}` format, handles figures, images, bold tags, and newline normalization.
+- `Utilities` — HTML processing: converts IEV cross-references (`<a href=IEV...>`) to `{{URN, term}}` format (ID first, display text last), handles figures, images, bold tags, and newline normalization.
+
+### Domain/Section Model
+
+Per the concept model's `ConceptReferenceType`:
+- `"domain"` — thematic/subject-area classification (area level, e.g. "103")
+- `"section"` — structural section membership (section level, e.g. "103-01")
+
+Each concept's `ManagedConceptData#domains` contains both refs. `ConceptData#domain` (a `LocalizedString`) holds the section/area title text. The `ManagedConcept#related` array holds `broader`/`narrower` relationships for the hierarchy tree.
+
+### V3 Output Artifacts
+
+An export produces these files alongside the concepts/ directory:
+- `register.yaml` — `Glossarist::DatasetRegister` with section tree, languages, owner, URN.
+- `bibliography.yaml` — single `bibliography:` key wrapping an array of `BibliographyEntry` objects. Entry `id` is the normalized anchor that `Glossarist::Validation::BibliographyIndex` will resolve against.
+- `figures/{fig-id}.yaml` — one `Glossarist::Figure` per unique image. Each concept carries a `FigureReference` on `ManagedConceptData#figures` and an inline `{{fig:id, display}}` mention in the text where the figure appeared.
+- References on localized concepts are populated by `Glossarist::ConceptEnricher#inject_references`, which scans text for `{{urn:...}}`, `<<xref>>`, and `image::` patterns.
 
 ### Configuration
 
@@ -47,7 +65,11 @@ This is a Ruby gem (`iev`) for working with the International Electrotechnical V
 ## Key Conventions
 
 - Ruby >= 3.1.0 required
+- All constants live under `Iev::` namespace (e.g. `Iev::IEV_SOURCE`, not top-level `IEV_SOURCE`)
+- `Iev.config` / `Iev.configure` / `Iev.reset_config!` are defined directly in `lib/iev.rb` — they must be available at load time without triggering autoload
 - `plurimath` and `unitsml` are optional runtime dependencies — loaded with `rescue LoadError`, so the `DataSource`/`Db` APIs work without them
 - The IEV Excel export format is specific to IEC-internal use; column structure is documented in README.adoc
 - Language codes: the spreadsheet uses ISO 639-1 (2-char like "en"), internally converted to ISO 639-2/3 (3-char like "eng") via `Iso639Code` and `DataConversions`
 - `DataConversions` is a refinement (`using DataConversions`) that adds `.sanitize` and `.decode_html` methods to String
+- `IevCode` is the single source of truth for IEV code decomposition — always use it instead of manual `split("-")` parsing
+- Schema version 3: all exported concepts use `schema_version: "3"`, which supports `annotations`, V3 concept sources, and structured references

data/Gemfile

@@ -2,6 +2,15 @@
 
 source "https://rubygems.org"
 
+# Use local glossarist-ruby when available for development.
+# Otherwise falls back to released gem (requires >= 2.8.15 for
+# BibliographyData, Figure/NonVerbRep, and ConceptEnricher support).
+if File.directory?(File.expand_path("../glossarist-ruby", __dir__))
+  gem "glossarist", path: "../glossarist-ruby"
+else
+  gem "glossarist", ">= 2.8.15"
+end
+
 gem "benchmark"
 gem "canon"
 gem "openssl"

data/README.adoc

@@ -228,7 +228,7 @@ There are these data types inside the term attribute field. Make sure you split
 We need to parse out all NOTEs and EXAMPLEs and normalize them.
 
 For all `This links to <a href=IEV112-01-01>quantity</a>`, we parse them and replace with:
-`This links to {{quantity, IEV:112-01-01}}`.
+`This links to {{IEV:112-01-01, quantity}}`.
 
 e.g.
 
@@ -300,9 +300,9 @@ notes:
 
 [source,yaml]
 ----
-definition: {{quantity, IEV:112-01-01}} which keeps the same value under particular circumstances, or which results from theoretical considerations
+definition: {{IEV:112-01-01, quantity}} which keeps the same value under particular circumstances, or which results from theoretical considerations
 examples:
-  - {{time constant, IEV:103-05-26}}, equilibrium constant for a chemical reaction, {{fundamental physical constant, IEV:112-03-09}}.
+  - {{IEV:103-05-26, time constant}}, equilibrium constant for a chemical reaction, {{IEV:112-03-09, fundamental physical constant}}.
 ----
 
 
@@ -582,6 +582,10 @@ of columns during export:
 | Derived from `IEVREF`
 | The IEVREF pattern `AAA-BB-CC` is split. Creates two `ConceptReference` objects with `ref_type: "domain"` and `source: "urn:iec:std:iec:60050"` (IEC URN per IEC URN specification): `area-AAA` and `section-AAA-BB`. For example, `103-01-02` produces `area-103` + `section-103-01`.
 
+| `ManagedConceptData#tags`
+| Derived from `IEVREF`
+| Plain string tags for grouping and filtering. Derived from the IEV subject area hierarchy: includes the area title (e.g. `"Mathematics - Functions"`) and section title (e.g. `"General concepts"`).
+
 | `LocalizedConcept#classification`
 | `SYNONYM1STATUS`
 | Maps localized classification values: Chinese/Russian/Spanish `"admitido"` to `"admitted"`, various forms of `"preferred"` similarly; other values lowercased as-is.
@@ -749,6 +753,9 @@ data:
     - concept_id: section-103-01
       source: urn:iec:std:iec:60050
       ref_type: domain
+  tags:
+    - "Mathematics - Functions"
+    - "General concepts"
 ----
 
 The `ref_type: domain` distinguishes domain references from other

data/iev.gemspec

@@ -22,14 +22,15 @@ Gem::Specification.new do |spec|
   spec.required_ruby_version = Gem::Requirement.new(">= 3.2.0")
 
   spec.add_dependency "creek", "~> 2.6"
-  spec.add_dependency "glossarist", "~> 2.6", ">= 2.6.7"
   spec.add_dependency "ferrum", "~> 0.15"
+  spec.add_dependency "glossarist", ">= 2.8.15"
+  spec.add_dependency "lutaml-model", "~> 0.8.0"
   spec.add_dependency "nokogiri", "~> 1.19"
   spec.add_dependency "plurimath"
-  spec.add_dependency "lutaml-model", "~> 0.8.0"
   spec.add_dependency "relaton", ">= 2.0.0", "< 3"
   spec.add_dependency "sequel", "~> 5.40"
   spec.add_dependency "sqlite3", "~> 1.7"
   spec.add_dependency "thor", "~> 1.0"
   spec.add_dependency "unitsml"
+  spec.metadata["rubygems_mfa_required"] = "true"
 end

data/lib/iev/bibliography_builder.rb

@@ -0,0 +1,87 @@
+# frozen_string_literal: true
+
+module Iev
+  # Builds a `Glossarist::BibliographyData` from the sources cited across a
+  # concept collection.
+  #
+  # Each unique `(source, id)` pair from a concept's `ConceptSource#origin`
+  # becomes one `BibliographyEntry`. The entry's `id` is the normalized
+  # anchor that `Glossarist::Validation::BibliographyIndex` uses for
+  # resolution — so the same normalization rules are applied here.
+  module BibliographyBuilder
+    module_function
+
+    # @param concepts [Enumerable<Glossarist::ManagedConcept>]
+    # @return [Glossarist::BibliographyData]
+    def build(concepts)
+      entries = collect_entries(concepts)
+      Glossarist::BibliographyData.new(entries: entries)
+    end
+
+    def collect_entries(concepts)
+      seen = {}
+      concepts.each do |concept|
+        concept.localizations.each do |l10n|
+          collect_from_l10n(l10n, seen)
+        end
+        Array(concept.sources).each { |src| add_source_entry(src, seen) }
+      end
+      seen.values.sort_by(&:id)
+    end
+    private_class_method :collect_entries
+
+    def collect_from_l10n(l10n, seen)
+      Array(l10n.all_sources).each { |src| add_source_entry(src, seen) }
+    end
+    private_class_method :collect_from_l10n
+
+    def add_source_entry(source, seen)
+      ref = source_origin_ref(source)
+      return unless ref
+
+      seen[entry_label(ref)] ||= build_entry(ref, source&.origin)
+    end
+    private_class_method :add_source_entry
+
+    def source_origin_ref(source)
+      ref = source&.origin&.ref
+      return unless ref&.source && !ref.source.strip.empty?
+
+      ref
+    end
+    private_class_method :source_origin_ref
+
+    def build_entry(ref, origin)
+      label = entry_label(ref)
+      Glossarist::BibliographyEntry.new(
+        id: normalize_anchor(label),
+        reference: label,
+        link: origin&.link,
+        type: type_for(ref.source),
+      )
+    end
+    private_class_method :build_entry
+
+    def entry_label(ref)
+      [ref.source, ref.id].compact.join(" ").strip
+    end
+    private_class_method :entry_label
+
+    # Mirrors `Glossarist::Validation::BibliographyIndex#normalize_anchor`
+    # so the id we write matches what the validator will look up.
+    def normalize_anchor(anchor)
+      anchor.to_s.gsub(/[ \/:]/, "_").gsub(/__+/, "_").downcase
+    end
+    private_class_method :normalize_anchor
+
+    def type_for(source)
+      case source.to_s
+      when /\A(IEV|VIM|JCGM)/ then "vocabulary"
+      when /\AITU/ then "recommendation"
+      when /\A(BIPM|BBIPM)/ then "brochure"
+      else "standard"
+      end
+    end
+    private_class_method :type_for
+  end
+end

data/lib/iev/cli/command.rb

@@ -142,14 +142,15 @@ module Iev
         summary
       end
 
-      desc "subject_areas", "Fetch IEV subject areas and sections from Electropedia."
+      desc "subject_areas",
+           "Fetch IEV subject areas and sections from Electropedia."
       option :output, desc: "Output YAML file (default: stdout)", aliases: :o
       option :refresh, type: :boolean, default: false,
                        desc: "Force re-fetch even if cached"
       def subject_areas
         if options[:refresh]
           cache_path = File.join(Iev.config.cache_dir, "subject_areas.yaml")
-          FileUtils.rm_f(cache_path) if File.exist?(cache_path)
+          FileUtils.rm_f(cache_path)
         end
 
         result = Iev::SubjectAreas.fetch

data/lib/iev/cli/ui.rb

@@ -12,12 +12,12 @@ module Iev
     module Ui
       module_function
 
-      def debug(*args)
-        Helper.cli_out(:debug, *args)
+      def debug(*)
+        Helper.cli_out(:debug, *)
       end
 
-      def warn(*args)
-        Helper.cli_out(:warn, *args)
+      def warn(*)
+        Helper.cli_out(:warn, *)
       end
 
       # Prints progress message which will be replaced on next call.
@@ -52,7 +52,7 @@ module Iev
 
         def cli_out(level, *args)
           topic = args[0].is_a?(Symbol) ? args.shift : nil
-          message = args.map(&:to_s).join(" ").chomp
+          message = args.join(" ").chomp
           ui_tag = Thread.current[:iev_ui_tag]
 
           return unless should_out?(level, topic)

data/lib/iev/config.rb

@@ -9,23 +9,9 @@ module Iev
     attr_accessor :data_path, :cache_dir, :remote_base_url
 
     def initialize
-      @data_path = ENV["IEV_DATA_PATH"]
+      @data_path = ENV.fetch("IEV_DATA_PATH", nil)
       @cache_dir = ENV["IEV_CACHE_DIR"] || File.join(Dir.tmpdir, "iev-cache")
       @remote_base_url = DEFAULT_REMOTE_BASE_URL
     end
   end
-
-  class << self
-    def config
-      @config ||= Config.new
-    end
-
-    def configure
-      yield(config) if block_given?
-    end
-
-    def reset_config!
-      @config = nil
-    end
-  end
 end

data/lib/iev/data_source.rb

@@ -63,7 +63,8 @@ module Iev
         path = File.join(data_path, "concept-#{code}.yaml")
         return nil unless File.exist?(path)
 
-        YAML.safe_load(File.read(path, encoding: "utf-8"), permitted_classes: [Date, Time])
+        YAML.safe_load(File.read(path, encoding: "utf-8"),
+                       permitted_classes: [Date, Time])
       end
 
       def from_remote(code)
@@ -101,7 +102,8 @@ module Iev
         cache_path = cache_file_path(filename)
         return nil unless File.exist?(cache_path)
 
-        YAML.safe_load(File.read(cache_path, encoding: "utf-8"), permitted_classes: [Date, Time])
+        YAML.safe_load(File.read(cache_path, encoding: "utf-8"),
+                       permitted_classes: [Date, Time])
       end
 
       def write_cache(filename, data)

data/lib/iev/db_writer.rb

@@ -6,6 +6,7 @@
 module Iev
   class DbWriter
     include Cli::Ui
+
     using DataConversions
 
     attr_reader :db