cxyz/src/comicland/chapters.js

const {
  CHAPTER_PATHNAME_PATTERN,
  COMICLAND_API_ORIGIN,
  COMICLAND_HOSTS,
  LISTING_PATHNAME_PATTERN,
} = require("./constants.js");
const { fetchComicLandJson, unwrapApiData } = require("./io.js");

/**
 * @typedef {object} ChapterLink
 * @property {string} url - Absolute chapter reader URL.
 * @property {string} title - Chapter label (trimmed).
 */

/**
 * @param {string} pathname - URL pathname.
 * @returns {string} Path without trailing slashes.
 */
function stripTrailingSlash(pathname) {
  return pathname.replace(/\/+$/u, "") || "/";
}

/**
 * @param {string} pathname - URL pathname.
 * @returns {boolean} Whether this path is a ComicLand chapter reader URL.
 */
function isChapterPathname(pathname) {
  return CHAPTER_PATHNAME_PATTERN.test(stripTrailingSlash(pathname));
}

/**
 * @param {string} pathname - URL pathname.
 * @returns {boolean} Whether this path is a ComicLand series listing URL.
 */
function isListingPathname(pathname) {
  return LISTING_PATHNAME_PATTERN.test(stripTrailingSlash(pathname));
}

/**
 * @param {string} url - Any http(s) URL.
 * @returns {boolean} True when hostname is ComicLand (hint only).
 */
function isLikelyComicLandSite(url) {
  try {
    const { hostname } = new URL(url);
    const host = hostname.toLowerCase();
    return COMICLAND_HOSTS.some((h) => h === host) || host.includes("comicland");
  } catch {
    return false;
  }
}

/**
 * Series slug from `/comic/{slug}` or `/comic/{slug}/chapter/{index}`.
 * @param {string} pageUrl - Series or chapter URL.
 * @returns {string} Slug segment, or `"comic"`.
 */
function seriesSlugFromListingUrl(pageUrl) {
  try {
    const { pathname } = new URL(pageUrl);
    const parts = pathname.split("/").filter(Boolean);
    const comicIdx = parts.indexOf("comic");
    if (comicIdx !== -1 && parts[comicIdx + 1] !== undefined) {
      return parts[comicIdx + 1];
    }
  } catch {
    /* invalid URL */
  }
  return "comic";
}

/**
 * @param {string} pageUrl - Series or chapter URL.
 * @returns {{ origin: string, slug: string, chapterIndex: string|null }} Parsed parts.
 */
function parseComicLandUrl(pageUrl) {
  const u = new URL(pageUrl);
  const parts = u.pathname.split("/").filter(Boolean);
  const comicIdx = parts.indexOf("comic");
  const slug =
    comicIdx !== -1 && parts[comicIdx + 1] !== undefined
      ? parts[comicIdx + 1]
      : "comic";
  let chapterIndex = null;
  const chapterIdx = parts.indexOf("chapter");
  if (chapterIdx !== -1 && parts[chapterIdx + 1] !== undefined) {
    chapterIndex = parts[chapterIdx + 1];
  }
  return { origin: u.origin, slug, chapterIndex };
}

/**
 * @param {string} siteOrigin - e.g. `https://comicland.org`.
 * @param {string} slug - Series slug.
 * @param {string|number} chapterIndex - API `chapter_index`.
 * @returns {string} Canonical reader URL (no trailing slash).
 */
function chapterUrlFromParts(siteOrigin, slug, chapterIndex) {
  const origin = siteOrigin.replace(/\/+$/u, "");
  return `${origin}/comic/${slug}/chapter/${String(chapterIndex)}`;
}

/**
 * @param {unknown} rawIndex - API `chapter_index`.
 * @returns {string} Index as used in the reader URL.
 */
function chapterIndexString(rawIndex) {
  if (typeof rawIndex === "number" && Number.isFinite(rawIndex)) {
    return Number.isInteger(rawIndex) ? String(rawIndex) : String(rawIndex);
  }
  if (typeof rawIndex === "string" && rawIndex.trim()) {
    return rawIndex.trim();
  }
  throw new Error("ComicLand chapter is missing chapter_index");
}

/**
 * GET `/api/comic/detail?slug=` and return mapped chapter links (oldest first).
 * @param {string} listingPageUrl - e.g. `https://comicland.org/comic/{slug}`
 * @returns {Promise<{ chapters: ChapterLink[], comicTitle: string }>} Chapter rows and series title.
 */
async function fetchChapterLinks(listingPageUrl) {
  const { origin, slug } = parseComicLandUrl(listingPageUrl);
  const apiUrl = `${COMICLAND_API_ORIGIN}/api/comic/detail?slug=${encodeURIComponent(slug)}`;
  const payload = await fetchComicLandJson(apiUrl);
  const data = unwrapApiData(payload, "comic/detail");

  const comicTitle =
    typeof data.title === "string" && data.title.trim()
      ? data.title.trim()
      : slug;

  const rawChapters = Array.isArray(data.chapters) ? data.chapters : [];
  /** @type {ChapterLink[]} */
  const chapters = [];

  for (const row of rawChapters) {
    if (!row || typeof row !== "object") {
      continue;
    }
    let index;
    try {
      index = chapterIndexString(row.chapter_index);
    } catch {
      continue;
    }
    const title =
      typeof row.title === "string" && row.title.trim()
        ? row.title.trim().replace(/\s+/gu, " ")
        : `Chapter ${index}`;
    chapters.push({
      url: chapterUrlFromParts(origin, slug, index),
      title,
    });
  }

  chapters.sort((a, b) => {
    const na = Number.parseFloat(String(new URL(a.url).pathname.split("/").pop()));
    const nb = Number.parseFloat(String(new URL(b.url).pathname.split("/").pop()));
    if (Number.isFinite(na) && Number.isFinite(nb) && na !== nb) {
      return na - nb;
    }
    return a.url.localeCompare(b.url);
  });

  return { chapters, comicTitle };
}

module.exports = {
  chapterUrlFromParts,
  fetchChapterLinks,
  isChapterPathname,
  isLikelyComicLandSite,
  isListingPathname,
  parseComicLandUrl,
  seriesSlugFromListingUrl,
};