iev 0.4.4 → 0.4.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 54693df7923bcf4dc686eac69daf1f4e3f981db12a0c3f7f672e2c7c656a53b2
-  data.tar.gz: 5404339eaad56057bccd9880b324194c73a9d82f8e86224429df4d651b361b67
+  metadata.gz: f5d3397238922342cdb3fb6b5adcf8fa969d2b3d6510742485d7d2a20b1d1a12
+  data.tar.gz: 6a82e64e1201a9a2f04cff66d024de1b23643030ce6e37f26ef09bb2ad334b10
 SHA512:
-  metadata.gz: 474e483fbab5ad2b3450a617d51a67ea1a6217bdfcfa46d99a469234e5fbffc2da4e89e20d7f5049303212086d0edebcb1712b2334829be2daed5d55816ad2b9
-  data.tar.gz: 34595c499fb3855449f92059629fad4da01a5d24b77409e8eab7cd7abf3b6a1eb4b6770e83baca6d0d2df46f22f69d9635eb282d7200e2ac364dd0eef8dea983
+  metadata.gz: be3b984bd46c791580a73644e88dccca4b98b708ce0e28c50f72e822abb609573455201b633d0e4d791b9271cdecb20a555b11cc674dda46bde90fcf7eaccb74
+  data.tar.gz: e56796a853c58aae578dd5c4fe3fbaf3e18115e1a08e22feb7d5f876d9521dee4d27fb734fb05baa12e297b1dc9ac89b67197cad0b51695b2224c3fdb622f3a5

data/.github/workflows/rake.yml

@@ -1,15 +1,18 @@
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
 name: rake
 
-permissions:
-  contents: write
-
 on:
   push:
     branches: [ master, main ]
     tags: [ v* ]
   pull_request:
-  workflow_dispatch:
+
+permissions:
+  contents: write
 
 jobs:
   rake:
     uses: metanorma/ci/.github/workflows/generic-rake.yml@main
+    secrets:
+      pat_token: ${{ secrets.GLOSSARIST_CI_PAT_TOKEN }}

data/.github/workflows/release.yml

@@ -1,3 +1,5 @@
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
 name: release
 
 permissions:

data/.gitignore

@@ -15,5 +15,7 @@
 .vscode/
 
 /concepts/
+/output/
 Gemfile.lock
 TODO*
+spec/fixtures/*.sqlite3

data/.rubocop.yml

@@ -2,7 +2,10 @@
 # See https://github.com/metanorma/cimas
 inherit_from:
   - .rubocop_todo.yml
-  - https://raw.githubusercontent.com/riboseinc/oss-guides/master/ci/rubocop.yml
+  - https://raw.githubusercontent.com/riboseinc/oss-guides/main/ci/rubocop.yml
 
 # local repo-specific modifications
 # ...
+
+AllCops:
+  TargetRubyVersion: 3.4

data/.rubocop_todo.yml

@@ -1,65 +1,142 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2025-11-14 11:14:05 UTC using RuboCop version 1.81.7.
+# on 2026-06-13 04:18:23 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: 2
 # This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: Max, AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, IgnoreCopDirectives, AllowedPatterns, SplitStrings.
+# Configuration parameters: EnforcedStyle, IndentationWidth.
+# SupportedStyles: with_first_argument, with_fixed_indentation
+Layout/ArgumentAlignment:
+  Exclude:
+    - 'spec/iev/exporter_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/iev/exporter_spec.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+Layout/BlockEndNewline:
+  Exclude:
+    - 'spec/iev/exporter_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/iev/exporter_spec.rb'
+
+# Offense count: 65
+# This cop supports safe autocorrection (--autocorrect).
+# 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: 26
 # 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'
+
+# Offense count: 5
+# 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:
+  Exclude:
+    - 'lib/iev/exporter.rb'
+    - 'spec/iev/exporter_spec.rb'

data/CLAUDE.md

@@ -27,15 +27,23 @@ 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.
 - `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.
 
 ### Configuration
 
@@ -47,7 +55,11 @@ 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 +2,14 @@
 
 source "https://rubygems.org"
 
+# Use local glossarist-ruby when available for development.
+# Otherwise falls back to released gem (requires >= 2.8.2 for tags support).
+if File.directory?(File.expand_path("../glossarist-ruby", __dir__))
+  gem "glossarist", path: "../glossarist-ruby"
+else
+  gem "glossarist", ">= 2.8.2"
+end
+
 gem "benchmark"
 gem "canon"
 gem "openssl"
@@ -14,7 +22,3 @@ gem "rubocop-rspec"
 gem "simplecov"
 
 gemspec
-
-# TODO: remove once glossarist 2.7.0 is released with domains migration
-gem "glossarist", git: "https://github.com/glossarist/glossarist-ruby.git",
-                 branch: "feat/metanorma-parity-designation-model"