test: specify pluggable fact ingestion behavior

tests/ingestion.test.ts

@@ -0,0 +1,54 @@
+import { afterEach, beforeEach, describe, expect, it } from 'vitest';
+
+import { IdentityDB } from '../src/core/identity-db';
+import { NaiveExtractor } from '../src/ingestion/naive-extractor';
+import type { FactExtractor } from '../src/ingestion/types';
+
+describe('IdentityDB ingestion', () => {
+  let db: IdentityDB;
+
+  beforeEach(async () => {
+    db = await IdentityDB.connect({ client: 'sqlite', filename: ':memory:' });
+    await db.initialize();
+  });
+
+  afterEach(async () => {
+    await db.close();
+  });
+
+  it('ingests a statement using a provided extractor', async () => {
+    const extractor: FactExtractor = {
+      async extract(input) {
+        return {
+          statement: input,
+          topics: [
+            { name: 'I', category: 'entity', granularity: 'concrete', role: 'subject' },
+            { name: 'TypeScript', category: 'entity', granularity: 'concrete', role: 'object' },
+            { name: '2025', category: 'temporal', granularity: 'concrete', role: 'time' },
+          ],
+        };
+      },
+    };
+
+    const fact = await db.ingestStatement('I have worked with TypeScript since 2025.', {
+      extractor,
+    });
+
+    expect(fact.topics.map((topic) => topic.name)).toEqual(['I', 'TypeScript', '2025']);
+
+    const linkedFacts = await db.getTopicFactsLinkedTo('TypeScript', '2025');
+    expect(linkedFacts).toHaveLength(1);
+    expect(linkedFacts[0]?.statement).toBe('I have worked with TypeScript since 2025.');
+  });
+
+  it('ships a deterministic naive extractor for local usage', async () => {
+    const fact = await db.ingestStatement('I have worked with TypeScript since 2025.', {
+      extractor: new NaiveExtractor(),
+    });
+
+    expect(fact.topics.map((topic) => topic.name)).toEqual(['I', 'TypeScript', '2025']);
+
+    const topic = await db.getTopicByName('TypeScript', { includeFacts: true });
+    expect(topic?.facts).toHaveLength(1);
+  });
+});