Keep source plugins in single scraper process

scraper/adapters/index.js

@@ -1,92 +1,13 @@
 'use strict';
 
-const { runArchive } = require('../jobs/weebcentral-archive');
-const { runMangaDexArchive } = require('../jobs/mangadex-archive');
-const { SlowHttp } = require('../lib/http');
-const { createWeebHttp } = require('../plugins/broker');
-const { discoverWeebCatalog } = require('./weebcentral');
-const { mangaDexInfo, discoverMangaDexCatalog } = require('./mangadex');
-const { ArchiveControlError } = require('../lib/control');
+// First-party registration only; never load executable source code from a
+// remote catalog or scan a writable directory for modules.
+const adapters = Object.freeze([
+  require('../sources/weebcentral'),
+  require('../sources/mangadex'),
+]);
 const { adapterForPeer } = require('../../peering/adapter');
 
-function controlledHttp(http, shouldStop) {
-  return { async get(...args) {
-    const check = () => { const reason = shouldStop?.(); if (reason) throw new ArchiveControlError(reason === true ? 'paused' : String(reason)); };
-    check(); const response = await http.get(...args); check(); return response;
-  } };
-}
-
-function weebCentralInfo(value) {
-  let url;
-  try { url = new URL(String(value)); } catch { return null; }
-  if (url.protocol !== 'https:' || url.hostname !== 'weebcentral.com') return null;
-  const match = /^\/series\/([A-Z0-9]+)(?:\/([^/?#]+))?\/?$/i.exec(url.pathname);
-  if (!match) return null;
-  const title = decodeURIComponent(match[2] || match[1]).replace(/[-_]+/g, ' ').trim();
-  return { source: 'weebcentral', id: match[1].toUpperCase(), title, url: `https://weebcentral.com/series/${match[1]}${match[2] ? `/${match[2]}` : ''}` };
-}
-
-const adapters = [{
-  id: 'weebcentral',
-  label: 'WeebCentral',
-  match: weebCentralInfo,
-  async discover(item, options) {
-    const httpOptions = {
-      minMs: options.settings.minMs, maxMs: options.settings.maxMs, maxRetries: 2,
-      onEvent: options.onEvent,
-    };
-    const http = process.env.SOURCE_PLUGIN_URL ? createWeebHttp(httpOptions) : new SlowHttp(httpOptions);
-    return discoverWeebCatalog(item.url, controlledHttp(http, options.shouldStop));
-  },
-  run(item, options) {
-    return runArchive({
-      seriesUrl: item.url,
-      libraryRoot: options.libraryRoot,
-      metadataSearch: item.metadataSearch || item.title,
-      minMs: options.settings.minMs,
-      maxMs: options.settings.maxMs,
-      chapterMinMs: options.settings.chapterMinMs,
-      chapterMaxMs: options.settings.chapterMaxMs,
-      shouldStop: options.shouldStop,
-      scope: item.scope,
-      existingPolicy: item.existingPolicy,
-      libraryMangaId: item.libraryMangaId,
-      onPublished: options.onPublished,
-      onCatalog: options.onCatalog,
-    });
-  },
-}, {
-  id: 'mangadex',
-  label: 'MangaDex',
-  match: mangaDexInfo,
-  async discover(item, options) {
-    const http = new SlowHttp({
-      minMs: options.settings.minMs, maxMs: options.settings.maxMs, maxRetries: 2,
-      userAgent: 'MangaCircus-Scraper/1.0 (personal archival; sequential MangaDex requests)',
-      onEvent: options.onEvent,
-    });
-    return discoverMangaDexCatalog(item.url, controlledHttp(http, options.shouldStop));
-  },
-  run(item, options) {
-    return runMangaDexArchive({
-      seriesUrl: item.url,
-      title: item.title,
-      libraryRoot: options.libraryRoot,
-      metadataSearch: item.metadataSearch || item.title,
-      minMs: options.settings.minMs,
-      maxMs: options.settings.maxMs,
-      chapterMinMs: options.settings.chapterMinMs,
-      chapterMaxMs: options.settings.chapterMaxMs,
-      shouldStop: options.shouldStop,
-      scope: item.scope,
-      existingPolicy: item.existingPolicy,
-      libraryMangaId: item.libraryMangaId,
-      onPublished: options.onPublished,
-      onCatalog: options.onCatalog,
-    });
-  },
-}];
-
 function adapterFor(url) {
   const peer = adapterForPeer(url);
   if (peer) return peer;
@@ -97,4 +18,6 @@ function adapterFor(url) {
   return null;
 }
 
-module.exports = { adapters, adapterFor, weebCentralInfo, mangaDexInfo };
+module.exports = { adapters, adapterFor,
+  weebCentralInfo: require('./weebcentral').weebCentralInfo,
+  mangaDexInfo: require('./mangadex').mangaDexInfo };

scraper/adapters/mangadex.js

@@ -1,8 +1,8 @@
 'use strict';
 
 const API = 'https://api.mangadex.org';
-const { specialKey } = require('../../chapter-identity');
-const { parseSource } = require('../plugins/client');
+const { parse } = require('../plugins/registry');
+const { localizedTitle, chapterNumber, selectChapterReleases, availabilitySummary, pageUrls } = require('../plugins/mangadex');
 
 function mangaDexInfo(value) {
   let url;
@@ -15,78 +15,6 @@ function mangaDexInfo(value) {
   return { source: 'mangadex', id, title, url: `https://mangadex.org/title/${id}${match[2] ? `/${match[2]}` : ''}` };
 }
 
-function localizedTitle(attributes = {}) {
-  const titles = attributes.title || {};
-  return titles.en || titles['ja-ro'] || titles.ja || Object.values(titles).find(Boolean) || 'Untitled';
-}
-
-function chapterNumber(value) {
-  const raw = String(value ?? '').trim();
-  if (!/^\d+(?:\.\d+)?$/.test(raw)) return null;
-  const [whole, decimal = ''] = raw.split('.');
-  const normalizedWhole = whole.replace(/^0+(?=\d)/, '') || '0';
-  const normalizedDecimal = decimal.replace(/0+$/, '');
-  return normalizedDecimal ? `${normalizedWhole}.${normalizedDecimal}` : normalizedWhole;
-}
-
-function groupFor(resource) {
-  const relation = (resource.relationships || []).find(item => item.type === 'scanlation_group');
-  return relation ? { id: relation.id, name: relation.attributes?.name || 'Unknown group' } : null;
-}
-
-function releaseRank(resource) {
-  const group = groupFor(resource)?.name || '';
-  const credited = /official|license/i.test(group) ? 0 : group ? 1 : 2;
-  const date = Date.parse(resource.attributes?.publishAt || resource.attributes?.readableAt || resource.attributes?.createdAt || '') || Number.MAX_SAFE_INTEGER;
-  return [credited, date, resource.id];
-}
-
-function compareRank(left, right) {
-  const a = releaseRank(left), b = releaseRank(right);
-  return a[0] - b[0] || a[1] - b[1] || String(a[2]).localeCompare(String(b[2]));
-}
-
-function selectChapterReleases(resources = [], specialLabel = 'Special') {
-  const selected = new Map();
-  for (const resource of resources) {
-    if (resource.attributes?.externalUrl || Number(resource.attributes?.pages || 0) < 1) continue;
-    const number = chapterNumber(resource.attributes?.chapter) || specialKey(resource.id);
-    const prior = selected.get(number);
-    if (!prior || compareRank(resource, prior) < 0) selected.set(number, resource);
-  }
-  return [...selected.entries()].map(([number, resource]) => {
-    const group = groupFor(resource);
-    return {
-      id: resource.id, number, title: resource.attributes?.title || '',
-      ...(!chapterNumber(resource.attributes?.chapter) ? { special: true, label: specialLabel, sourceId: resource.id, sourceNumber: resource.attributes?.chapter ?? null } : {}),
-      ...(resource.attributes?.volume ? { volume: chapterNumber(resource.attributes.volume) || String(resource.attributes.volume) } : {}),
-      pages: Number(resource.attributes?.pages || 0),
-      added: resource.attributes?.publishAt || resource.attributes?.readableAt || resource.attributes?.createdAt,
-      group,
-      url: `https://mangadex.org/chapter/${resource.id}`,
-    };
-  }).sort((a, b) => Number(!!a.special) - Number(!!b.special) || (a.special ? a.number.localeCompare(b.number) : Number(a.number) - Number(b.number) || a.number.localeCompare(b.number)));
-}
-
-function availabilitySummary(attributes, releases, chapters, externalReleases = null) {
-  const numbered = chapters.filter(ref => !ref.special);
-  const expected = chapterNumber(attributes.lastChapter);
-  const maximum = numbered.length ? Math.max(...numbered.map(ref => Number(ref.number))) : null;
-  // Reaching the final chapter number is not full coverage when the catalog
-  // contains fewer distinct numbered releases than the expected chapter span.
-  const expectedCount = expected && /^\d+$/.test(expected) ? Number(expected) : null;
-  const sparse = expectedCount && numbered.length < expectedCount;
-  const reason = chapters.length ? null : externalReleases > 0 ? 'external-only'
-    : Array.isArray(attributes.availableTranslatedLanguages) && !attributes.availableTranslatedLanguages.includes('en') ? 'no-english' : 'no-hosted-pages';
-  const message = reason === 'external-only' ? `MangaDex lists ${externalReleases} English external-link releases, but no hosted English pages. External links are not downloaded.`
-    : reason === 'no-english' ? 'This MangaDex edition has no English releases listed.'
-      : reason ? 'This MangaDex edition has no hosted English releases with pages.' : null;
-  return { language: 'en', hostedReleases: releases.filter(r => !r.attributes?.externalUrl && Number(r.attributes?.pages) > 0).length,
-    selectedChapters: chapters.length, numberedChapters: numbered.length, specialReleases: chapters.length - numbered.length,
-    externalReleases, expectedLastChapter: expected, highestHostedChapter: maximum,
-    coverage: expected && (maximum === null || maximum < Number(expected) || sparse) ? 'partial' : 'unknown', reason, message };
-}
-
 async function jsonGet(http, url) {
   const response = await http.get(url, { accept: 'application/json' });
   const body = await response.json();
@@ -99,10 +27,7 @@ async function discoverMangaDexCatalog(seriesUrl, http) {
   if (!info) throw new Error('Invalid MangaDex title URL');
   const manga = (await jsonGet(http, `${API}/manga/${info.id}`)).data;
   if (!manga || manga.type !== 'manga') throw new Error('MangaDex title was not found');
-  const isolated = !!process.env.MANGADEX_PLUGIN_URL;
-  const pluginMetadata = isolated
-    ? await parseSource('mangadex', 'metadata', { html: JSON.stringify(manga), url: `${API}/manga/${info.id}` })
-    : null;
+  const metadata = parse('mangadex', 'metadata', { data: manga, url: `${API}/manga/${info.id}` });
 
   const releases = [];
   let offset = 0;
@@ -112,67 +37,45 @@ async function discoverMangaDexCatalog(seriesUrl, http) {
     params.append('includes[]', 'scanlation_group');
     params.append('order[chapter]', 'asc');
     const page = await jsonGet(http, `${API}/manga/${info.id}/feed?${params}`);
-    if (isolated) {
-      const parsed = await parseSource('mangadex', 'feed', { html: JSON.stringify(page.data || []), url: `${API}/manga/${info.id}/feed` });
-      releases.push(...parsed.releases);
-    } else releases.push(...(page.data || []));
+    releases.push(...parse('mangadex', 'feed', { data: page.data || [], url: `${API}/manga/${info.id}/feed` }).releases);
     offset += page.data?.length || 0;
     if (!page.data?.length || offset >= Number(page.total || 0)) break;
   }
 
-  const title = isolated ? pluginMetadata.title : localizedTitle(manga.attributes);
-  const specialLabel = isolated ? pluginMetadata.specialLabel : /pre.serialization|pilot/i.test(title) ? 'Pilot'
-    : (manga.attributes?.tags || []).some(tag => tag.attributes?.name?.en === 'Oneshot') ? 'One-shot' : 'Special';
-  const pluginCatalog = async externalReleases => parseSource('mangadex', 'catalog', {
-    html: JSON.stringify({ attributes: pluginMetadata.availabilityAttributes, releases, specialLabel, externalReleases }),
+  const { title, specialLabel } = metadata;
+  const parseCatalog = externalReleases => parse('mangadex', 'catalog', {
+    data: { attributes: metadata.availabilityAttributes, releases, specialLabel, externalReleases },
     url: `${API}/manga/${info.id}`,
   });
-  let parsed = isolated ? await pluginCatalog(null) : null;
-  const chapters = isolated ? parsed.chapters : selectChapterReleases(releases, specialLabel);
+  let parsed = parseCatalog(null);
+  const chapters = parsed.chapters;
   // External-only is a separate feed mode, not a combined hosted+external catalog.
   let externalReleases = null;
   if (!chapters.length) {
     const params = new URLSearchParams({ limit: '1', includeFutureUpdates: '0', includeExternalUrl: '1' });
     params.append('translatedLanguage[]', 'en');
     externalReleases = Number((await jsonGet(http, `${API}/manga/${info.id}/feed?${params}`)).total || 0);
-    if (isolated) parsed = await pluginCatalog(externalReleases);
+    parsed = parseCatalog(externalReleases);
   }
   return {
     id: info.id,
     title,
-    originalLanguage: isolated ? pluginMetadata.originalLanguage : manga.attributes?.originalLanguage || null,
-    links: isolated ? pluginMetadata.links : manga.attributes?.links || {},
-    availability: isolated ? parsed.availability : availabilitySummary(manga.attributes || {}, releases, chapters, externalReleases),
+    originalLanguage: metadata.originalLanguage,
+    links: metadata.links,
+    availability: parsed.availability,
     chapters,
   };
 }
 
-function pageUrls(atHome, chapterUrl, expectedPages) {
-  const base = new URL(atHome.baseUrl);
-  if (base.protocol !== 'https:' || !(base.hostname === 'uploads.mangadex.org' || base.hostname.endsWith('.mangadex.network'))) {
-    throw new Error(`Unexpected MangaDex@Home host: ${base.hostname}`);
-  }
-  const hash = String(atHome.chapter?.hash || '');
-  const files = atHome.chapter?.data;
-  if (!hash || !Array.isArray(files) || !files.length) throw new Error('MangaDex@Home returned no pages');
-  if (expectedPages && files.length !== expectedPages) throw new Error(`MangaDex page count changed: expected ${expectedPages}, received ${files.length}`);
-  return files.map(file => ({
-    url: new URL(`/data/${encodeURIComponent(hash)}/${encodeURIComponent(file)}`, base).href,
-    headers: { referer: chapterUrl },
-  }));
-}
-
 async function discoverMangaDexChapter(ref, http) {
   const atHome = await jsonGet(http, `${API}/at-home/server/${ref.id}?forcePort443=true`);
   const groupName = ref.group?.name ? ` · ${ref.group.name}` : '';
-  const parsed = process.env.MANGADEX_PLUGIN_URL
-    ? await parseSource('mangadex', 'atHome', { html: JSON.stringify({ response: atHome, chapterUrl: ref.url, expectedPages: ref.pages }), url: `${API}/at-home/server/${ref.id}` })
-    : null;
+  const parsed = parse('mangadex', 'atHome', { data: { response: atHome, chapterUrl: ref.url, expectedPages: ref.pages }, url: `${API}/at-home/server/${ref.id}` });
   return {
     number: ref.number, title: ref.title || '', added: ref.added,
     ...(ref.special ? { special: true, label: ref.label, sourceId: ref.id, sourceNumber: ref.sourceNumber ?? null } : {}),
     source: { name: `MangaDex${groupName}`, url: ref.url },
-    pages: parsed ? parsed.pages : pageUrls(atHome, ref.url, ref.pages),
+    pages: parsed.pages,
   };
 }
 

scraper/adapters/weebcentral.js

@@ -3,16 +3,26 @@
 const { SlowHttp } = require('../lib/http');
 const { fallbackDirection } = require('../../reading-direction');
 const parser = require('../plugins/weebcentral');
-const { parseSource } = require('../plugins/client');
+const { parse } = require('../plugins/registry');
+
+function weebCentralInfo(value) {
+  let url;
+  try { url = new URL(String(value)); } catch { return null; }
+  if (url.protocol !== 'https:' || url.hostname !== 'weebcentral.com') return null;
+  const match = /^\/series\/([A-Z0-9]+)(?:\/([^/?#]+))?\/?$/i.exec(url.pathname);
+  if (!match) return null;
+  const title = decodeURIComponent(match[2] || match[1]).replace(/[-_]+/g, ' ').trim();
+  return { source: 'weebcentral', id: match[1].toUpperCase(), title, url: `https://weebcentral.com/series/${match[1]}${match[2] ? `/${match[2]}` : ''}` };
+}
 
 const parseChapters = (html, baseUrl) => parser.catalog({ html, url: baseUrl }).chapters;
 const parsePageUrls = (html, baseUrl) => parser.pages({ html, url: baseUrl }).pages;
 
 async function discoverWeebCatalog(seriesUrl, http) {
   const seriesHtml = await (await http.get(seriesUrl, { accept: 'text/html' })).text();
-  const { title, listUrl } = await parseSource('weebcentral', 'series', { html: seriesHtml, url: seriesUrl });
+  const { title, listUrl } = parse('weebcentral', 'series', { html: seriesHtml, url: seriesUrl });
   const listHtml = listUrl ? await (await http.get(listUrl, { accept: 'text/html' })).text() : seriesHtml;
-  const parsed = await parseSource('weebcentral', 'catalog', { html: listHtml, url: seriesUrl });
+  const parsed = parse('weebcentral', 'catalog', { html: listHtml, url: seriesUrl });
   const chapterLinks = parsed.chapterLinks;
   const chapters = parsed.chapters.sort((a, b) =>
     Number(a.book?.number || 1) - Number(b.book?.number || 1) || Number(a.number) - Number(b.number));
@@ -24,9 +34,9 @@ async function discoverWeebCatalog(seriesUrl, http) {
 
 async function discoverWeebChapter(chapter, http) {
   const pageHtml = await (await http.get(chapter.url, { accept: 'text/html' })).text();
-  const { manifestUrl, added } = await parseSource('weebcentral', 'chapter', { html: pageHtml, url: chapter.url });
+  const { manifestUrl, added } = parse('weebcentral', 'chapter', { html: pageHtml, url: chapter.url });
   const fragment = await (await http.get(`${manifestUrl}&reading_style=long_strip&current_page=1`, { accept: 'text/html' })).text();
-  const parsed = await parseSource('weebcentral', 'pages', { html: fragment, url: manifestUrl });
+  const parsed = parse('weebcentral', 'pages', { html: fragment, url: manifestUrl });
   const pages = parsed.pages.map(url => ({ url, headers: { referer: chapter.url } }));
   if (!pages.length) throw new Error(`No pages found for chapter ${chapter.number}`);
   return {
@@ -55,4 +65,4 @@ async function discoverWeebCentral(seriesUrl, options = {}) {
   };
 }
 
-module.exports = { discoverWeebCentral, discoverWeebCatalog, discoverWeebChapter, parseChapters, parsePageUrls };
+module.exports = { weebCentralInfo, discoverWeebCentral, discoverWeebCatalog, discoverWeebChapter, parseChapters, parsePageUrls };