'use strict';

// First-party parser; inputs are fetched by the paced source broker, not here.
const decode = value => String(value).replace(/&/g, '&').replace(/'|'/gi, "'")
  .replace(/&quot;/g, '"').replace(/<[^>]+>/g, '').trim();

function catalog({ html, url }) {
  const sourceId = new URL(url).pathname.split('/')[2];
  const title = decode(html.match(/<h1\b[^>]*>([\s\S]*?)<\/h1>/i)?.[1] || 'Untitled');
  const chapters = [];
  const re = /<a\b[^>]*href="(\/chapters\/(\d+-\d+)\/[^"?#]+)"[^>]*>([\s\S]*?)<\/a>/gi;
  for (const match of html.matchAll(re)) {
    if (match[2].split('-')[0] !== sourceId) continue;
    const label = decode(match[3]);
    const number = label.match(/^Chapter\s+([0-9]+(?:\.[0-9]+)?)(?:\b|$)/i)?.[1];
    if (!number) continue;
    chapters.push({ id: match[2], number, title: '', url: new URL(match[1], url).href, raw: label });
  }
  return { title, chapters: [...new Map(chapters.map(ref => [ref.id, ref])).values()],
    chapterLinks: [...html.matchAll(/href="\/chapters\/\d+-\d+\//gi)].length };
}

function pages({ html }) {
  const images = [];
  for (const match of html.matchAll(/<img\b[^>]*class="[^"]*\bjs-page\b[^"]*"[^>]*>/gi)) {
    const url = match[0].match(/\bdata-src="([^"]+)"/i)?.[1];
    if (url) images.push(url.replace(/&amp;/g, '&'));
  }
  return { pages: [...new Set(images)] };
}

module.exports = { catalog, pages };