Checkpoint first-party source parser pilot

scraper/test/source-plugin.test.js

@@ -0,0 +1,67 @@
+'use strict';
+
+const test = require('node:test');
+const assert = require('node:assert/strict');
+const { createServer } = require('../plugins/worker');
+const { parse } = require('../plugins/registry');
+const { parseSource } = require('../plugins/client');
+const { discoverWeebCatalog, discoverWeebChapter } = require('../adapters/weebcentral');
+
+const seriesUrl = 'https://weebcentral.com/series/ABC/title';
+const chapterUrl = 'https://weebcentral.com/chapters/XYZ';
+const seriesHtml = '<h1>Test Manga</h1><div hx-get="/series/ABC/full-chapter-list"></div>';
+const listHtml = '<a href="/chapters/XYZ">Chapter 1</a><a href="/chapters/LMN">Log. 2</a>';
+const chapterHtml = '<time datetime="2026-01-01"></time>';
+const imagesHtml = '<img src="https://img.example/1.jpg"><img data-src="https://img.example/2.jpg">';
+
+test('first-party registry rejects unknown plugins and malformed input', () => {
+  assert.throws(() => parse('remote-module', 'catalog', { html: listHtml, url: seriesUrl }), /Unknown/);
+  assert.throws(() => parse('weebcentral', 'catalog', { html: listHtml, url: 'file:///tmp/x' }), /Invalid source URL/);
+  assert.throws(() => parse('weebcentral', 'catalog', { html: listHtml, url: 'https://other.example/series/a' }), /does not belong/);
+  assert.equal(parse('weebcentral', 'catalog', { html: listHtml, url: seriesUrl }).chapters.length, 2);
+});
+
+test('isolated parser preserves WeebCentral catalog and page discovery', async () => {
+  const server = createServer();
+  await new Promise(resolve => server.listen(0, '127.0.0.1', resolve));
+  const previous = process.env.SOURCE_PLUGIN_URL;
+  process.env.SOURCE_PLUGIN_URL = `http://127.0.0.1:${server.address().port}`;
+  const requested = [];
+  const http = { async get(url) {
+    requested.push(url);
+    const body = url === seriesUrl ? seriesHtml
+      : url.endsWith('/full-chapter-list') ? listHtml
+        : url === chapterUrl ? chapterHtml
+          : imagesHtml;
+    return { text: async () => body };
+  } };
+  try {
+    const catalog = await discoverWeebCatalog(seriesUrl, http);
+    assert.equal(catalog.title, 'Test Manga');
+    assert.deepEqual(catalog.chapters.map(chapter => chapter.number), ['1', '2']);
+    const chapter = await discoverWeebChapter(catalog.chapters[0], http);
+    assert.equal(chapter.pages.length, 2);
+    assert.equal(chapter.added, '2026-01-01');
+    assert.equal(requested.length, 4);
+    const response = await fetch(`${process.env.SOURCE_PLUGIN_URL}/v1/parse`, {
+      method: 'POST', headers: { 'content-type': 'application/json' },
+      body: JSON.stringify({ plugin: 'unapproved', operation: 'catalog', input: { html: listHtml, url: seriesUrl } }),
+    });
+    assert.equal(response.status, 400);
+  } finally {
+    if (previous === undefined) delete process.env.SOURCE_PLUGIN_URL;
+    else process.env.SOURCE_PLUGIN_URL = previous;
+    await new Promise(resolve => server.close(resolve));
+  }
+});
+
+test('configured worker failure does not fall back to local parsing', async () => {
+  const previous = process.env.SOURCE_PLUGIN_URL;
+  process.env.SOURCE_PLUGIN_URL = 'http://127.0.0.1:1';
+  try {
+    await assert.rejects(parseSource('weebcentral', 'catalog', { html: listHtml, url: seriesUrl }));
+  } finally {
+    if (previous === undefined) delete process.env.SOURCE_PLUGIN_URL;
+    else process.env.SOURCE_PLUGIN_URL = previous;
+  }
+});