feat: Analyze vocabularies

jest.config.js

@@ -1,7 +1,7 @@
 export default {
   preset: 'ts-jest/presets/default-esm',
   extensionsToTreatAsEsm: ['.ts'],
-  testTimeout: 10000,
+  testTimeout: 20000,
   collectCoverage: true,
   collectCoverageFrom: [
     '**/src/**/*.ts', // Include files that are not covered by tests.
@@ -10,10 +10,10 @@ export default {
   coverageReporters: ['json-summary', 'text'],
   coverageThreshold: {
     global: {
-      lines: 20.19,
-      statements: 20.19,
-      branches: 15.23,
-      functions: 17.39,
+      lines: 18.89,
+      statements: 18.89,
+      branches: 14.54,
+      functions: 16.32,
     },
   },
   transform: {

src/analyzer/vocabulary.ts

@@ -0,0 +1,54 @@
+import {Analyzer} from '../analyzer.js';
+import {Dataset} from '../dataset.js';
+import {DataFactory} from 'n3';
+import {Failure, NotSupported, Success} from '../pipeline.js';
+import namedNode = DataFactory.namedNode;
+
+const vocabularyPrefixes = new Map([
+  ['http://schema.org/', 'http://schema.org'],
+  ['https://schema.org/', 'http://schema.org'],
+  [
+    'https://www.ica.org/standards/RiC/ontology#',
+    'https://www.ica.org/standards/RiC/ontology',
+  ],
+  ['http://www.cidoc-crm.org/cidoc-crm/', 'http://www.cidoc-crm.org/cidoc-crm'],
+  ['http://purl.org/ontology/bibo/', 'http://purl.org/ontology/bibo/'],
+  ['http://purl.org/dc/elements/1.1/', 'http://purl.org/dc/elements/1.1/'],
+  ['http://purl.org/dc/terms/', 'http://purl.org/dc/terms/'],
+  ['http://purl.org/dc/dcmitype/', 'http://purl.org/dc/dcmitype/'],
+  [
+    'http://www.w3.org/2004/02/skos/core#',
+    'http://www.w3.org/2004/02/skos/core#',
+  ],
+]);
+
+export class VocabularyAnalyzer implements Analyzer {
+  constructor(private readonly decorated: Analyzer) {}
+
+  async execute(dataset: Dataset): Promise<Success | NotSupported | Failure> {
+    const result = await this.decorated.execute(dataset);
+    if (result instanceof NotSupported || result instanceof Failure) {
+      return result;
+    }
+
+    for (const quad of result.data) {
+      if ('http://rdfs.org/ns/void#property' === quad.predicate.value) {
+        const match = [...vocabularyPrefixes].find(([prefix]) =>
+          quad.object.value.startsWith(prefix)
+        );
+        if (match) {
+          const [, vocabulary] = match;
+          result.data.add(
+            DataFactory.quad(
+              namedNode(dataset.iri),
+              namedNode('http://rdfs.org/ns/void#vocabulary'),
+              namedNode(vocabulary)
+            )
+          );
+        }
+      }
+    }
+
+    return new Success(result.data);
+  }
+}

src/main.ts

@@ -11,6 +11,7 @@ import {SparqlWriter} from './writer/sparql.js';
 import {config} from './config.js';
 import {RdfDumpImporter} from './importer.js';
 import {GraphDBClient} from './graphdb.js';
+import {VocabularyAnalyzer} from './analyzer/vocabulary.js';
 
 const queryEngine = new QueryEngine();
 new Pipeline({
@@ -37,7 +38,6 @@ new Pipeline({
       })
     ),
     await SparqlQueryAnalyzer.fromFile(queryEngine, 'class-partition.rq'),
-    await SparqlQueryAnalyzer.fromFile(queryEngine, 'entity-properties.rq'),
     await SparqlQueryAnalyzer.fromFile(queryEngine, 'object-literals.rq'),
     await SparqlQueryAnalyzer.fromFile(queryEngine, 'object-uris.rq'),
     await SparqlQueryAnalyzer.fromFile(queryEngine, 'properties.rq'),
@@ -47,6 +47,9 @@ new Pipeline({
     new UriSpaceAnalyzer(
       await SparqlQueryAnalyzer.fromFile(queryEngine, 'object-uri-space.rq')
     ),
+    new VocabularyAnalyzer(
+      await SparqlQueryAnalyzer.fromFile(queryEngine, 'entity-properties.rq')
+    ),
   ],
   writers: [
     new FileWriter(),