lutaml-model 0.8.0 → 0.8.2

data/spec/lutaml/model/yamls_sequence_spec.rb

@@ -0,0 +1,245 @@
+require "spec_helper"
+require_relative "../../fixtures/geolexica_v2_concept"
+
+RSpec.describe "YAMLS sequence (heterogeneous YAML stream)" do
+  let(:v2_yaml) do
+    <<~YAMLS
+      ---
+      data:
+        identifier: 3.5.8.8
+        localized_concepts:
+          eng: fbe1444a-7c11-555e-bb1b-680a4e6f2502
+      id: 0171b198-d068-53d9-8741-fb87e6755d62
+
+      ---
+      data:
+        definition:
+        - content: characteristic of a financial model that requires users to enter into an agreement prior to receiving services
+        examples: []
+        notes:
+        - content: The agreement can be associated with fees.
+        - content: The agreement can be minimal.
+        sources:
+        - origin:
+            ref: ISO/TS 14812:2022
+            locality:
+              type: clause
+              reference_from: 3.5.8.8
+            link: https://www.iso.org/standard/79779.html
+          type: authoritative
+        terms:
+        - type: expression
+          normative_status: preferred
+          designation: membership-based
+        language_code: eng
+        entry_status: valid
+      id: fbe1444a-7c11-555e-bb1b-680a4e6f2502
+    YAMLS
+  end
+
+  describe "parsing heterogeneous YAML stream" do
+    subject(:managed) { GeolexicaV2::ManagedConcept.from_yamls(v2_yaml) }
+
+    it "parses document 0 as ConceptIndex" do
+      expect(managed.index).to be_a(GeolexicaV2::ConceptIndex)
+      expect(managed.index.id).to eq("0171b198-d068-53d9-8741-fb87e6755d62")
+    end
+
+    it "parses ConceptIndex data fields" do
+      expect(managed.index.data.identifier).to eq("3.5.8.8")
+      expect(managed.index.data.localized_concepts).to eq(
+        "eng" => "fbe1444a-7c11-555e-bb1b-680a4e6f2502",
+      )
+    end
+
+    it "parses document 1+ as LocalizedConcept collection" do
+      expect(managed.localized).to be_an(Array)
+      expect(managed.localized.length).to eq(1)
+    end
+
+    it "parses LocalizedConcept fields" do
+      lc = managed.localized.first
+      expect(lc).to be_a(GeolexicaV2::LocalizedConcept)
+      expect(lc.id).to eq("fbe1444a-7c11-555e-bb1b-680a4e6f2502")
+      expect(lc.data.language_code).to eq("eng")
+      expect(lc.data.entry_status).to eq("valid")
+    end
+
+    it "parses LocalizedConcept definition sequence" do
+      lc = managed.localized.first
+      expect(lc.data.definition).to be_an(Array)
+      expect(lc.data.definition.first.content).to include("characteristic of a financial model")
+    end
+
+    it "parses LocalizedConcept terms sequence" do
+      lc = managed.localized.first
+      expect(lc.data.terms.first.designation).to eq("membership-based")
+      expect(lc.data.terms.first.type).to eq("expression")
+    end
+
+    it "parses LocalizedConcept notes sequence" do
+      lc = managed.localized.first
+      expect(lc.data.notes.length).to eq(2)
+      expect(lc.data.notes.first.content).to eq("The agreement can be associated with fees.")
+    end
+
+    it "parses LocalizedConcept sources with nested origin" do
+      lc = managed.localized.first
+      source = lc.data.sources.first
+      expect(source.type).to eq("authoritative")
+      expect(source.origin.ref).to eq("ISO/TS 14812:2022")
+      expect(source.origin.locality.type).to eq("clause")
+      expect(source.origin.locality.reference_from).to eq("3.5.8.8")
+    end
+
+    it "parses empty examples array" do
+      lc = managed.localized.first
+      expect(lc.data.examples).to eq([])
+    end
+  end
+
+  describe "serialization" do
+    subject(:managed) { GeolexicaV2::ManagedConcept.from_yamls(v2_yaml) }
+
+    it "serializes back to a YAML stream with 2 documents" do
+      output = managed.to_yamls
+      docs = output.split(/^---\s*$/).reject do |d|
+        d.strip.empty?
+      end.map { |d| YAML.safe_load("---\n#{d}") }
+      expect(docs.length).to eq(2)
+    end
+
+    it "round-trips index data" do
+      output = managed.to_yamls
+      managed2 = GeolexicaV2::ManagedConcept.from_yamls(output)
+
+      expect(managed2.index.id).to eq(managed.index.id)
+      expect(managed2.index.data.identifier).to eq(managed.index.data.identifier)
+      expect(managed2.index.data.localized_concepts).to eq(managed.index.data.localized_concepts)
+    end
+
+    it "round-trips localized concept data" do
+      output = managed.to_yamls
+      managed2 = GeolexicaV2::ManagedConcept.from_yamls(output)
+
+      lc = managed2.localized.first
+      expect(lc.id).to eq(managed.localized.first.id)
+      expect(lc.data.language_code).to eq("eng")
+      expect(lc.data.definition.first.content).to include("characteristic of a financial model")
+      expect(lc.data.terms.first.designation).to eq("membership-based")
+      expect(lc.data.notes.length).to eq(2)
+      expect(lc.data.sources.first.origin.ref).to eq("ISO/TS 14812:2022")
+    end
+
+    it "round-trips empty arrays" do
+      output = managed.to_yamls
+      managed2 = GeolexicaV2::ManagedConcept.from_yamls(output)
+      expect(managed2.localized.first.data.examples).to eq([])
+    end
+  end
+
+  describe "parsing actual geolexica v2 file" do
+    let(:v2_file) do
+      File.read(File.expand_path("../../fixtures/geolexica_v2_sample.yaml",
+                                 __dir__))
+    end
+
+    it "parses the real geolexica v2 file" do
+      managed = GeolexicaV2::ManagedConcept.from_yamls(v2_file)
+      expect(managed.index.data.identifier).to eq("3.5.8.8")
+      expect(managed.localized.first.data.language_code).to eq("eng")
+      expect(managed.localized.first.data.terms.first.designation).to eq("membership-based")
+    end
+  end
+
+  describe "YAMLS sequence with 3 documents" do
+    let(:three_doc_yaml) do
+      <<~YAMLS
+        ---
+        data:
+          identifier: 3.7.1.5
+          localized_concepts:
+            eng: doc1-eng-id
+        id: doc0-id
+
+        ---
+        data:
+          definition:
+          - content: First localized concept
+          examples: []
+          notes: []
+          sources: []
+          terms:
+          - type: expression
+            normative_status: preferred
+            designation: term one
+          language_code: eng
+          entry_status: valid
+        id: doc1-eng-id
+
+        ---
+        data:
+          definition:
+          - content: Second localized concept (French)
+          examples: []
+          notes: []
+          sources: []
+          terms:
+          - type: expression
+            normative_status: preferred
+            designation: terme un
+          language_code: fra
+          entry_status: valid
+        id: doc1-fra-id
+      YAMLS
+    end
+
+    it "parses 1 index + 2 localized concepts" do
+      managed = GeolexicaV2::ManagedConcept.from_yamls(three_doc_yaml)
+      expect(managed.index.data.identifier).to eq("3.7.1.5")
+      expect(managed.localized.length).to eq(2)
+      expect(managed.localized[0].data.language_code).to eq("eng")
+      expect(managed.localized[1].data.language_code).to eq("fra")
+    end
+
+    it "round-trips 3 documents" do
+      managed = GeolexicaV2::ManagedConcept.from_yamls(three_doc_yaml)
+      output = managed.to_yamls
+      managed2 = GeolexicaV2::ManagedConcept.from_yamls(output)
+
+      expect(managed2.localized.length).to eq(2)
+      expect(managed2.localized[0].data.terms.first.designation).to eq("term one")
+      expect(managed2.localized[1].data.terms.first.designation).to eq("terme un")
+    end
+  end
+
+  describe "ManagedConceptCollection (directory of v2 files)" do
+    let(:fixture_dir) { File.expand_path("../../fixtures", __dir__) }
+    let(:v2_files) do
+      %w[geolexica_v2_sample.yaml geolexica_v2_sample2.yaml].map do |f|
+        File.join(fixture_dir, f)
+      end
+    end
+
+    it "loads each v2 file as a separate ManagedConcept" do
+      concepts = v2_files.map do |f|
+        GeolexicaV2::ManagedConcept.from_yamls(File.read(f))
+      end
+      expect(concepts.length).to eq(2)
+      concepts.each do |concept|
+        expect(concept.index).to be_a(GeolexicaV2::ConceptIndex)
+        expect(concept.localized).to be_an(Array)
+        expect(concept.localized).not_to be_empty
+      end
+    end
+
+    it "can be assembled into a collection manually" do
+      concepts = v2_files.map do |f|
+        GeolexicaV2::ManagedConcept.from_yamls(File.read(f))
+      end
+      collection = GeolexicaV2::ManagedConceptCollection.new(concepts)
+      expect(collection.size).to eq(2)
+      expect(collection.first.index).to be_a(GeolexicaV2::ConceptIndex)
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -33,6 +33,11 @@ RSpec.configure do |config|
     Lutaml::Model::GlobalRegister.instance.reset if defined?(Lutaml::Model::GlobalRegister)
   end
 
+  # Reset adapter state between adapter-switching tests
+  config.after(:each, :adapter_test) do
+    Lutaml::Model::AdapterScope.reset! if defined?(Lutaml::Model::AdapterScope)
+  end
+
   # After each test, ensure :xsd context exists
   # Some specs call GlobalContext.reset! which removes :xsd context
   # but :xsd register (from lutaml-xsd) needs its context to exist

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: lutaml-model
 version: !ruby/object:Gem::Version
-  version: 0.8.0
+  version: 0.8.2
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-05-01 00:00:00.000000000 Z
+date: 2026-05-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: base64
@@ -189,7 +189,6 @@ files:
 - bench/bench_niso.rb
 - bench/bench_sts.rb
 - bench/bench_unitsml.rb
-- bench/bench_uniword.rb
 - bench/bench_xmi.rb
 - bench/gate_config.rb
 - benchmark/quick_benchmark.rb
@@ -290,6 +289,7 @@ files:
 - docs/model_transforms.adoc
 - docs/namespace-management.adoc
 - docs/xml-schema-qualification.md
+- docs/yamls_sequence.adoc
 - exe/lutaml-model
 - flake.lock
 - flake.nix
@@ -373,6 +373,8 @@ files:
 - lib/lutaml/key_value/transformation/value_serializer.rb
 - lib/lutaml/key_value/transformation_builder.rb
 - lib/lutaml/model.rb
+- lib/lutaml/model/adapter_resolver.rb
+- lib/lutaml/model/adapter_scope.rb
 - lib/lutaml/model/attribute.rb
 - lib/lutaml/model/attribute_validator.rb
 - lib/lutaml/model/cached_type_resolver.rb
@@ -809,6 +811,8 @@ files:
 - lib/lutaml/yamls/adapter/mapping_rule.rb
 - lib/lutaml/yamls/adapter/standard_adapter.rb
 - lib/lutaml/yamls/adapter/transform.rb
+- lib/lutaml/yamls/adapter/yamls_sequence.rb
+- lib/lutaml/yamls/adapter/yamls_sequence_rule.rb
 - lib/tasks/benchmark_runner.rb
 - lib/tasks/memory_profile.rb
 - lib/tasks/performance.rake
@@ -827,6 +831,9 @@ files:
 - spec/ceramic_spec.rb
 - spec/fixtures/address.rb
 - spec/fixtures/ceramic.rb
+- spec/fixtures/geolexica_v2_concept.rb
+- spec/fixtures/geolexica_v2_sample.yaml
+- spec/fixtures/geolexica_v2_sample2.yaml
 - spec/fixtures/liquid_templates/_ceramic.liquid
 - spec/fixtures/liquid_templates/_ceramics.liquid
 - spec/fixtures/liquid_templates/_ceramics_in_one.liquid
@@ -1500,6 +1507,7 @@ files:
 - spec/fixtures/xml/test_schema.xsd
 - spec/fixtures/xml/user.xsd
 - spec/fixtures/xml/valid_math_document.xml
+- spec/fixtures/yamls_range_concept.rb
 - spec/lutaml/key_value/transformation/collection_serializer_spec.rb
 - spec/lutaml/key_value/transformation/rule_compiler_spec.rb
 - spec/lutaml/key_value/transformation/value_serializer_spec.rb
@@ -1622,6 +1630,8 @@ files:
 - spec/lutaml/model/xsd_type_validation_spec.rb
 - spec/lutaml/model/yaml_adapter_spec.rb
 - spec/lutaml/model/yamls/standard_adapter_spec.rb
+- spec/lutaml/model/yamls_range_spec.rb
+- spec/lutaml/model/yamls_sequence_spec.rb
 - spec/lutaml/model/yamls_spec.rb
 - spec/lutaml/model_spec.rb
 - spec/lutaml/xml/adapter/nokogiri_adapter_spec.rb

data/bench/bench_uniword.rb

@@ -1,69 +0,0 @@
-#!/usr/bin/env ruby
-# frozen_string_literal: true
-
-# Benchmark: Uniword (OOXML/DOCX document parsing)
-# Gate: parse time < 30s for ISO-690 (4.8MB document.xml)
-#
-# Usage:
-#   UNIWORD_DIR=/path/to/uniword ITERATIONS=5 bundle exec ruby tmp/bench/bench_uniword.rb
-#   BENCH_JSON=/tmp/results.json bundle exec ruby tmp/bench/bench_uniword.rb
-
-require_relative "bench_common"
-include BenchCommon
-
-print_header("Uniword Benchmark — OOXML/DOCX document parsing")
-
-uniword_root = ENV["UNIWORD_DIR"] || "/Users/mulgogi/src/mn/uniword"
-$LOAD_PATH.unshift("#{uniword_root}/lib")
-require "uniword"
-require "zip"
-
-iso_file = "#{uniword_root}/spec/fixtures/uniword-private/fixtures/iso/ISO_690_2021-Word_document(en).docx"
-
-unless File.exist?(iso_file)
-  puts "  ISO 690 fixture not found: #{iso_file}"
-  puts "  Ensure uniword-private submodule is initialized."
-  exit 1
-end
-
-# Extract document.xml from DOCX
-xml_content = nil
-Zip::File.open(iso_file) do |zip|
-  entry = zip.find_entry("word/document.xml")
-  xml_content = entry.get_input_stream.read if entry
-end
-
-file_size_kb = File.size(iso_file) / 1024.0
-xml_size_kb = xml_content.bytesize / 1024.0
-puts "  File: #{File.basename(iso_file)} (#{file_size_kb.round(0)}KB)"
-puts "  document.xml: #{xml_size_kb.round(0)}KB"
-puts
-
-results = {}
-results[:iso690] = measure("Uniword ISO 690 (#{xml_size_kb.round(0)}KB)") do
-  Uniword::Wordprocessingml::DocumentRoot.from_xml(xml_content)
-end
-
-# Also test with a simpler document if available
-demo_file = "#{uniword_root}/examples/demo_formal_integral_roundtrip_spec.docx"
-if File.exist?(demo_file)
-  demo_xml = nil
-  Zip::File.open(demo_file) do |zip|
-    entry = zip.find_entry("word/document.xml")
-    demo_xml = entry.get_input_stream.read if entry
-  end
-  if demo_xml
-    demo_size_kb = demo_xml.bytesize / 1024.0
-    results[:demo] = measure("Uniword demo_formal (#{demo_size_kb.round(0)}KB)") do
-      Uniword::Wordprocessingml::DocumentRoot.from_xml(demo_xml)
-    end
-  end
-end
-
-puts "\n  Gate checks:"
-if results[:iso690]
-  status = results[:iso690][:avg_time] < 30.0 ? "PASS" : "FAIL"
-  printf "  ISO-690 < 30s: %s (%.3fs)\n", status, results[:iso690][:avg_time]
-end
-
-write_results_json(json_output_path, results) if json_output_path