Add first-party MangaPill source and distinct volume releases

scraper/test/mangapill-source.test.js

@@ -0,0 +1,61 @@
+'use strict';
+const test = require('node:test');
+const assert = require('node:assert/strict');
+const fs = require('node:fs/promises');
+const os = require('node:os');
+const path = require('node:path');
+const { adapterFor } = require('../adapters');
+const { parse } = require('../plugins/registry');
+const { discoverMangaPillCatalog, discoverMangaPillChapter } = require('../adapters/mangapill');
+const { validateHostRequest } = require('../plugins/broker');
+const { runArchive } = require('../jobs/weebcentral-archive');
+const { Canvas } = require('../../tools/png');
+const { scanLibrary } = require('../lib/library-inventory');
+
+const seriesUrl = 'https://mangapill.com/manga/552/bleach';
+const chapterUrl = 'https://mangapill.com/chapters/552-10001000/bleach-chapter-1';
+const imageUrl = 'https://cdn.readdetectiveconan.com/file/mangap/552/10001000/1.jpg';
+const catalogHtml = `<h1 class="font-bold">Bleach</h1><div id="chapters"><a href="/chapters/552-10002000/bleach-chapter-2">Chapter 2</a><a href="/chapters/552-10001000/bleach-chapter-1">Chapter 1</a></div>`;
+const chapterHtml = `<picture><img class="js-page" data-src="${imageUrl}"/></picture>`;
+
+test('MangaPill discovery stays in its host and keeps ordered source chapter IDs', async () => {
+  assert.equal(adapterFor(seriesUrl).adapter.id, 'mangapill');
+  assert.equal(adapterFor('http://mangapill.com/manga/552/bleach'), null);
+  const http = { async get(url) {
+    assert.ok([seriesUrl, chapterUrl].includes(url));
+    return { async text() { return url === seriesUrl ? catalogHtml : chapterHtml; } };
+  } };
+  const catalog = await discoverMangaPillCatalog(seriesUrl, http);
+  assert.deepEqual(catalog.chapters.map(chapter => [chapter.id, chapter.number]),
+    [['552-10001000', '1'], ['552-10002000', '2']]);
+  const chapter = await discoverMangaPillChapter(catalog.chapters[0], http);
+  assert.deepEqual(chapter.pages, [{ url: imageUrl, headers: { referer: chapterUrl } }]);
+  assert.throws(() => parse('mangapill', 'pages', {
+    html: '<img class="js-page" data-src="https://other.example/file/mangap/1.jpg">', url: chapterUrl,
+  }), /page host/);
+  assert.throws(() => validateHostRequest('https://other.example/manga/552', 'mangapill.com', { accept: 'text/html' }), /left its source host/);
+});
+
+test('MangaPill uses the shared checkpoint-safe publisher and skips an existing chapter', async t => {
+  const root = await fs.mkdtemp(path.join(os.tmpdir(), 'mc-mangapill-'));
+  t.after(() => fs.rm(root, { recursive: true, force: true }));
+  const png = new Canvas(10, 20, [1, 2, 3]).png();
+  const createHttp = () => ({ async get(url) {
+    if (url === seriesUrl) return { async text() { return catalogHtml.replace(/<a[^>]*>Chapter 2<\/a>/, ''); } };
+    if (url === chapterUrl) return { async text() { return chapterHtml; } };
+    if (url === imageUrl) return { async arrayBuffer() { return png; } };
+    throw new Error(`Unexpected source request: ${url}`);
+  } });
+  const options = { source: 'mangapill', sourceLabel: 'MangaPill', sourceId: '552',
+    discoverCatalog: discoverMangaPillCatalog, discoverChapter: discoverMangaPillChapter, createHttp,
+    seriesUrl, libraryRoot: root, scope: { mode: 'missing' },
+    minMs: 1000, maxMs: 1000, chapterMinMs: 5000, chapterMaxMs: 5000 };
+  const first = await runArchive(options);
+  assert.equal(first.publishedCount, 1);
+  const manga = (await scanLibrary(root)).mangas[0];
+  assert.equal(manga.ids.mangapill, '552');
+  assert.equal(manga.chapters[0].sourceKey, 'mangapill');
+  const second = await runArchive(options);
+  assert.equal(second.publishedCount, 0);
+  assert.equal(second.selectedCount, 0);
+});