MangaCircus/scraper/lib/legacy-publication.js

'use strict';

const fs = require('fs').promises;
const path = require('path');
const { imageExtension } = require('./images');
const { assertInside } = require('./names');

const PAGE = /^(\d{4,5})(?:_[a-z0-9]+)*\.(jpe?g|png|webp|gif|avif|bmp)$/i;
const BOOK = /^(?:v|s|x)\d{2,3}(?: |$)/i;
const CHAPTER = /^(?:c\d{4}(?:\.\d*[1-9])?|x\d{2})(?: |$)/i;
const OWN_STAGE = /^\.staging-mcscraper-[a-f0-9]+$/;

async function exists(target) {
  try { await fs.access(target); return true; } catch { return false; }
}

async function renameRetry(from, to, tries = 5) {
  for (let attempt = 0; ; attempt++) {
    try { await fs.rename(from, to); return; } catch (error) {
      if (attempt >= tries || !['EPERM', 'EBUSY', 'EACCES'].includes(error.code)) throw error;
      await new Promise(resolve => setTimeout(resolve, 200 * (attempt + 1)));
    }
  }
}

async function writeJsonAtomic(file, value) {
  const temp = `${file}.migration.tmp`;
  const old = `${file}.migration.old`;
  await fs.writeFile(temp, JSON.stringify(value, null, 2) + '\n', { mode: 0o644 });
  await fs.rm(old, { force: true });
  await renameRetry(file, old);
  try {
    await renameRetry(temp, file);
  } catch (error) {
    await renameRetry(old, file).catch(() => {});
    await fs.rm(temp, { force: true });
    throw error;
  }
  await fs.rm(old, { force: true }).catch(() => {});
}

async function directories(folder) {
  return (await fs.readdir(folder, { withFileTypes: true })).filter(entry => entry.isDirectory());
}

async function validatePage(file, expected) {
  const handle = await fs.open(file, 'r');
  try {
    const prefix = Buffer.alloc(16);
    const { bytesRead } = await handle.read(prefix, 0, prefix.length, 0);
    const actual = imageExtension(prefix.subarray(0, bytesRead));
    if (!actual) throw new Error(`Unsupported image bytes: ${file}`);
    const normalized = expected.toLowerCase() === 'jpeg' ? 'jpg' : expected.toLowerCase();
    if (actual !== normalized) throw new Error(`Image extension does not match bytes: ${file}`);
  } finally {
    await handle.close();
  }
}

async function validateChapter(folder) {
  const entries = await fs.readdir(folder, { withFileTypes: true });
  if (entries.some(entry => entry.isDirectory())) throw new Error(`Chapter contains a subdirectory: ${folder}`);
  const chapterFile = path.join(folder, 'chapter.json');
  const chapter = JSON.parse(await fs.readFile(chapterFile, 'utf8'));
  if (!chapter.source?.name || !chapter.source?.url) throw new Error(`Invalid chapter source: ${chapterFile}`);
  const pages = entries.filter(entry => entry.isFile() && entry.name !== 'chapter.json').map(entry => {
    const match = PAGE.exec(entry.name);
    if (!match) throw new Error(`Invalid chapter file: ${path.join(folder, entry.name)}`);
    return { name: entry.name, number: Number(match[1]), extension: match[2] };
  }).sort((a, b) => a.number - b.number);
  if (!pages.length) throw new Error(`Chapter has no pages: ${folder}`);
  for (let index = 0; index < pages.length; index++) {
    if (pages[index].number !== index + 1) throw new Error(`Non-contiguous pages in ${folder}`);
    await validatePage(path.join(folder, pages[index].name), pages[index].extension);
  }
  return pages.length;
}

async function inspectLegacyWork({ libraryRoot, seriesId }) {
  const id = String(seriesId || '');
  if (!/^[A-Za-z0-9-]+$/.test(id)) throw new Error(`Unsafe legacy series id: ${id}`);
  const root = path.resolve(libraryRoot);
  const workRoot = assertInside(root, path.join(root, `.mcscraper-work-${id}`));
  const stateFile = path.join(workRoot, 'job.json');
  if (!(await exists(stateFile))) return null;
  const state = JSON.parse(await fs.readFile(stateFile, 'utf8'));
  if (state.publicationMode === 'incremental') return null;
  const mangaDirs = (await directories(workRoot)).filter(entry => !entry.name.startsWith('.'));
  if (!mangaDirs.length) return null;
  if (mangaDirs.length !== 1) throw new Error(`Legacy work ${id} must contain exactly one manga folder`);
  const mangaDir = path.join(workRoot, mangaDirs[0].name);
  const target = assertInside(root, path.join(root, mangaDirs[0].name));
  if (await exists(target)) throw new Error(`Cannot publish legacy work; target already exists: ${target}`);
  const meta = JSON.parse(await fs.readFile(path.join(mangaDir, 'manga.json'), 'utf8'));
  if (!meta.title || !Array.isArray(meta.sources) || !meta.sources.length) throw new Error(`Invalid legacy manga metadata: ${mangaDir}`);

  let chapterCount = 0, pageCount = 0;
  const incompleteStages = [];
  for (const book of await directories(mangaDir)) {
    if (book.name.startsWith('.')) throw new Error(`Unexpected hidden folder remains in ${mangaDir}`);
    if (!BOOK.test(book.name)) throw new Error(`Invalid legacy book folder: ${book.name}`);
    const bookDir = path.join(mangaDir, book.name);
    for (const chapter of await directories(bookDir)) {
      if (chapter.name.startsWith('.')) {
        if (!OWN_STAGE.test(chapter.name)) throw new Error(`Unexpected hidden folder remains in ${bookDir}: ${chapter.name}`);
        incompleteStages.push(path.join(bookDir, chapter.name));
        continue;
      }
      if (!CHAPTER.test(chapter.name)) throw new Error(`Invalid legacy chapter folder: ${chapter.name}`);
      pageCount += await validateChapter(path.join(bookDir, chapter.name));
      chapterCount++;
    }
  }
  const completedCount = new Set(state.completed || []).size;
  if (!chapterCount || chapterCount !== completedCount) {
    throw new Error(`Legacy work ${id} has ${chapterCount} complete folders but ${completedCount} completed checkpoint entries`);
  }
  return {
    id, root, workRoot, stateFile, state, mangaDir, target,
    mangaId: path.basename(target), chapterCount, pageCount, incompleteStages,
  };
}

async function promoteLegacyWork(inspection) {
  const { stateFile, mangaDir, target, state, workRoot } = inspection;
  const quarantineRoot = path.join(workRoot, '.legacy-incomplete');
  const quarantined = [];
  if (inspection.incompleteStages.length) await fs.mkdir(quarantineRoot, { recursive: true, mode: 0o755 });
  for (const stage of inspection.incompleteStages) {
    const relative = path.relative(mangaDir, stage).split(path.sep).join('__');
    const quarantine = path.join(quarantineRoot, relative);
    await renameRetry(stage, quarantine);
    quarantined.push({ stage, quarantine });
  }
  try {
    await renameRetry(mangaDir, target);
  } catch (error) {
    for (const item of quarantined.reverse()) await renameRetry(item.quarantine, item.stage).catch(() => {});
    throw error;
  }
  const migrated = {
    ...state,
    publicationMode: 'incremental',
    status: 'paused',
    current: null,
    jobCompleted: 0,
    total: 0,
    migratedToIncremental: {
      time: new Date().toISOString(),
      mangaId: inspection.mangaId,
      chaptersPublished: inspection.chapterCount,
      pagesPublished: inspection.pageCount,
      incompleteStagesQuarantined: quarantined.length,
    },
  };
  try {
    await writeJsonAtomic(stateFile, migrated);
  } catch (error) {
    await renameRetry(target, mangaDir).catch(() => {});
    for (const item of quarantined.reverse()) await renameRetry(item.quarantine, item.stage).catch(() => {});
    throw error;
  }
  await fs.appendFile(path.join(workRoot, 'job.log'), JSON.stringify({
    time: migrated.migratedToIncremental.time,
    level: 'info',
    message: `Published ${inspection.chapterCount} completed legacy chapters and switched to incremental mode`,
    mangaId: inspection.mangaId,
  }) + '\n').catch(() => {});
  return {
    seriesId: inspection.id,
    mangaId: inspection.mangaId,
    finalPath: target,
    chaptersPublished: inspection.chapterCount,
    pagesPublished: inspection.pageCount,
    incompleteStagesQuarantined: quarantined.length,
  };
}

module.exports = { inspectLegacyWork, promoteLegacyWork };