MangaCircus/discovery/engine.js

'use strict';

const fs = require('node:fs');
const path = require('node:path');
const { normalize } = require('../greatest');
const { anchorsFor } = require('./anchors');
const { MAX_FEED, SLOTS, round2, seedIndexFor, seedNotes, groupFor, partRank, mixSlots } = require('./scoring');

const MAX_CANDIDATES = 2000;
const SEED_KINDS = ['recs', 'creator', 'tagTop', 'fresh'];
const MATURE_TAG_RANK = 60;
const VALID_FORMATS = new Set(['MANGA', 'ONE_SHOT']);
const safeUrl = value => /^https:\/\/[^\s]+$/i.test(String(value || '')) ? String(value) : null;
const unique = values => [...new Set(values.filter(Boolean))];
// manga.json and cached metadata are hand-editable files: a field that is not a list counts as empty.
const listOf = value => Array.isArray(value) ? value : [];
const stringsOf = value => unique(listOf(value).filter(item => typeof item === 'string'));

function cachedMetadata(dir, id) {
  if (!Number.isSafeInteger(Number(id)) || Number(id) < 1) return null;
  try {
    const value = JSON.parse(fs.readFileSync(path.join(dir, `id-${Number(id)}.json`), 'utf8'));
    return value._cacheVersion === 4 && value.metadata?.['x-anilist']?.id === Number(id) ? value.metadata : null;
  } catch { return null; }
}
function candidateFromGreatest(entry, cacheDir) {
  const id = Number(entry.metadata?.id);
  const cached = id ? cachedMetadata(cacheDir, id) : null;
  return {
    id: id ? `anilist:${id}` : `greatest:${entry.id}`,
    title: cached?.title || entry.title, year: cached?.year || entry.year || null,
    type: cached?.['x-anilist']?.format || 'MANGA', status: cached?.status || entry.status || 'unknown',
    cover: safeUrl(cached?.['x-anilist']?.coverUrl) || safeUrl(entry.cover),
    metadataUrl: safeUrl(cached?.['x-anilist']?.url) || safeUrl(entry.metadata?.url) || null,
    tags: stringsOf(cached?.tags), authors: stringsOf(cached?.authors),
    period: entry.period, editorialRank: entry.rank, greatestId: entry.id,
    evidence: [{ id: `greatest:${entry.id}`, kind: 'curation', label: 'Greatest of All Time selection',
      note: String(entry.note || '').slice(0, 600), url: safeUrl(entry.source?.url) || safeUrl(entry.metadata?.url) }],
    relations: cached?.['x-anilist']?.relations || [],
  };
}
function addRelations(map, anchor, cacheDir) {
  for (const relation of listOf(anchor.relations)) {
    if (!relation || typeof relation !== 'object') continue;
    if (!VALID_FORMATS.has(relation.format) || !Number.isSafeInteger(Number(relation.id))) continue;
    const id = `anilist:${Number(relation.id)}`;
    if (map.has(id)) continue;
    const cached = cachedMetadata(cacheDir, relation.id);
    map.set(id, {
      id, title: cached?.title || relation.title || `AniList ${relation.id}`,
      year: cached?.year || null, type: relation.format, status: cached?.status || 'unknown',
      cover: safeUrl(cached?.['x-anilist']?.coverUrl),
      metadataUrl: safeUrl(cached?.['x-anilist']?.url) || safeUrl(relation.url) || `https://anilist.co/manga/${relation.id}`,
      tags: stringsOf(cached?.tags), authors: stringsOf(cached?.authors), period: null,
      editorialRank: null, greatestId: null,
      evidence: [{ id: `relation:${anchor.id}:${id}`, kind: 'relation', label: `${relation.type || 'RELATED'} to ${anchor.title}`,
        note: '', url: safeUrl(relation.url) || `https://anilist.co/manga/${relation.id}` }],
      relatedTo: { id: anchor.id, title: anchor.title, type: String(relation.type || 'RELATED') },
      relations: cached?.['x-anilist']?.relations || [],
    });
  }
}
const textList = values => unique(Array.isArray(values) ? values.map(value => value?.name).filter(name => typeof name === 'string') : []);
const recordList = values => Array.isArray(values) ? values.filter(value => value && typeof value === 'object') : [];
function candidateFromRecord(record, id, seed, fetchedAt) {
  return {
    id: `anilist:${id}`, title: String(record.title || `AniList ${id}`), year: Number(record.year) || null,
    type: record.format || 'MANGA', status: record.status || 'unknown', cover: safeUrl(record.coverUrl),
    metadataUrl: safeUrl(record.siteUrl) || `https://anilist.co/manga/${id}`,
    tags: textList(record.tags), authors: textList(record.authors), period: null, editorialRank: null, greatestId: null,
    evidence: [], relations: [], isAdult: record.isAdult === true,
    averageScore: Number.isFinite(record.averageScore) ? record.averageScore : null,
    tagRecords: recordList(record.tags), authorRecords: recordList(record.authors), fetchedAt, seed,
  };
}
// Greatest and relation candidates keep their own fields; AniList only fills what they lack.
function fillFromRecord(candidate, record, fetchedAt) {
  if (candidate.isAdult === undefined) candidate.isAdult = record.isAdult === true;
  if (!candidate.tagRecords) candidate.tagRecords = recordList(record.tags);
  if (!candidate.authorRecords) candidate.authorRecords = recordList(record.authors);
  if (candidate.averageScore == null && Number.isFinite(record.averageScore)) candidate.averageScore = record.averageScore;
  if (!candidate.fetchedAt) candidate.fetchedAt = fetchedAt;
}
function addHarvested(map, harvestCache) {
  for (const kind of SEED_KINDS) {
    const entries = harvestCache.list(kind).sort((a, b) => String(a.key).localeCompare(String(b.key)));
    for (const entry of entries) for (const item of Array.isArray(entry.data) ? entry.data : []) {
      const record = item?.record;
      const id = Number(item?.anilistId);
      if (!record || typeof record !== 'object' || !Number.isSafeInteger(id) || id < 1) continue;
      if (record.format && !VALID_FORMATS.has(record.format)) continue;
      const existing = map.get(`anilist:${id}`);
      if (existing) fillFromRecord(existing, record, entry.fetchedAt);
      else map.set(`anilist:${id}`, candidateFromRecord(record, id, kind, entry.fetchedAt));
    }
  }
}
function buildCandidates({ greatest, library, cacheDir, harvestCache = null }) {
  const map = new Map();
  for (const entry of greatest.entries) {
    const candidate = candidateFromGreatest(entry, cacheDir);
    if (candidate.type === 'MANGA' || candidate.type === 'ONE_SHOT') map.set(candidate.id, candidate);
  }
  for (const manga of library) {
    const identity = manga.meta?.['x-anilist'];
    if (!identity?.id) continue;
    addRelations(map, { id: `anilist:${identity.id}`, title: manga.title, relations: identity.relations }, cacheDir);
  }
  for (const candidate of [...map.values()]) if (candidate.greatestId) addRelations(map, candidate, cacheDir);
  if (harvestCache) addHarvested(map, harvestCache);
  return [...map.values()];
}
// Title-level isAdult or a strong adult tag; the Phase A regex only where AniList gave no isAdult.
function isMature(candidate) {
  if (candidate.isAdult === undefined) return candidate.tags.some(tag => /adult|hentai|erotica/i.test(tag));
  return candidate.isAdult === true
    || (candidate.tagRecords || []).some(tag => tag?.isAdult && Number(tag.rank) >= MATURE_TAG_RANK);
}
function ownedKeySet(library) {
  const ids = new Set(), names = new Set();
  for (const manga of library) {
    const id = Number(manga.meta?.['x-anilist']?.id);
    if (id) ids.add(`anilist:${id}`);
    names.add(`${normalize(manga.title)}:${Number(manga.meta?.year) || '?'}`);
  }
  return { ids, names };
}
function labelForVote(greatest, id) { return greatest.entries.find(entry => entry.id === id)?.title || null; }
function feedForUser({ user, db, candidates, greatest, library, queuedTitles = [], harvestCache = null, now = () => new Date() }) {
  const settings = user.settings || {};
  const today = now();
  if (!settings.discoveryEnabled) return { generatedAt: today.toISOString(), items: [], disabled: true };
  const votes = db.greatestRatings?.[user.name] || {};
  const feedback = db.discoveryFeedback?.[user.name] || {};
  const owned = ownedKeySet(library);
  const queued = new Set(queuedTitles.map(normalize));
  const positive = Object.entries(votes).filter(([, vote]) => vote === 'flame' || vote === 'good')
    .map(([id, vote]) => ({ id, vote, title: labelForVote(greatest, id), entry: greatest.entries.find(e => e.id === id) })).filter(x => x.entry);
  const likedTags = new Map(), likedPeriods = new Map();
  for (const anchor of positive) {
    likedPeriods.set(anchor.entry.period, anchor);
    const candidate = candidates.find(c => c.greatestId === anchor.id);
    for (const tag of candidate?.tags || []) likedTags.set(tag.toLowerCase(), anchor);
  }
  const ownedTags = new Map();
  for (const manga of library) for (const tag of stringsOf(manga.meta?.tags)) ownedTags.set(tag.toLowerCase(), manga.title);
  const readTags = new Map();
  if (settings.discoveryReadingActivity) for (const manga of library) {
    const progress = db.progress?.[user.name]?.[manga.id] || {};
    if (!Object.values(progress).some(chapter => chapter?.done)) continue;
    for (const tag of stringsOf(manga.meta?.tags)) readTags.set(tag.toLowerCase(), manga.title);
  }
  const seeds = seedIndexFor({ anchors: anchorsFor({ user, db, library, greatest }), harvestCache, mature: !!settings.discoveryMature });
  const rows = [];
  for (const candidate of candidates) {
    if (candidate.greatestId && votes[candidate.greatestId]) continue;
    if (['dismissed', 'hidden'].includes(feedback[candidate.id])) continue;
    if (owned.ids.has(candidate.id) || owned.names.has(`${normalize(candidate.title)}:${candidate.year || '?'}`)) continue;
    if (queued.has(normalize(candidate.title))) continue;
    if (!settings.discoveryMature && isMature(candidate)) continue;
    const matchingLikedTag = candidate.tags.find(tag => likedTags.has(tag.toLowerCase()));
    const matchingOwnedTag = candidate.tags.find(tag => ownedTags.has(tag.toLowerCase()));
    const matchingReadTag = candidate.tags.find(tag => readTags.has(tag.toLowerCase()));
    const era = likedPeriods.get(candidate.period);
    const relation = candidate.relatedTo;
    const scoreParts = { editorial: candidate.greatestId ? Math.max(0, 6 - Math.min(6, Number(candidate.editorialRank) || 6)) : 0,
      relation: relation ? 3 : 0, sharedTaste: matchingLikedTag ? 4 : 0, sharedLibrary: matchingOwnedTag ? 1 : 0,
      era: era ? 2 : 0, reading: matchingReadTag ? 2 : 0,
      interest: feedback[candidate.id] === 'interested' ? 5 : feedback[candidate.id] === 'maybe' ? 2 : 0,
      communityRec: 0, sameCreator: 0, tagTop: 0, fresh: 0 };
    // Every applicable part brings its reason and, for taste parts, its personal evidence.
    const notes = [];
    if (scoreParts.editorial && candidate.evidence[0]?.note) notes.push({ part: 'editorial', text: candidate.evidence[0].note });
    if (relation) notes.push({ part: 'relation', text: `${candidate.title} is listed as ${relation.type.toLowerCase().replaceAll('_', ' ')} to ${relation.title}. Check the edition and reading order first.` });
    if (matchingLikedTag) {
      const anchor = likedTags.get(matchingLikedTag.toLowerCase());
      notes.push({ part: 'sharedTaste', text: `You liked ${anchor.title}; this also carries the ${matchingLikedTag} tag.`,
        evidence: { id: `taste:greatest:${anchor.id}`, kind: 'personal', label: `Your Greatest vote for ${anchor.title}`, note: `Shared tag: ${matchingLikedTag}`, url: null } });
    }
    if (era) notes.push({ part: 'era', text: `You liked ${era.title}; this is another curated work from ${candidate.period}.`,
      evidence: { id: `taste:greatest:${era.id}`, kind: 'personal', label: `Your Greatest vote for ${era.title}`, note: `Shared period: ${candidate.period}`, url: null } });
    if (matchingReadTag) {
      const title = readTags.get(matchingReadTag.toLowerCase());
      notes.push({ part: 'reading', text: `You have read ${title}; this also carries the ${matchingReadTag} tag.`,
        evidence: { id: `taste:read:${normalize(title)}`, kind: 'personal', label: `Your completed reading in ${title}`, note: `Shared tag: ${matchingReadTag}`, url: null } });
    }
    if (matchingOwnedTag) {
      const title = ownedTags.get(matchingOwnedTag.toLowerCase());
      notes.push({ part: 'sharedLibrary', text: `This shares the ${matchingOwnedTag} tag with ${title} in your library.`,
        evidence: { id: `taste:library:${normalize(title)}`, kind: 'personal', label: `${title} in your library`, note: `Shared tag: ${matchingOwnedTag}`, url: null } });
    }
    for (const note of seedNotes(candidate, seeds, today.getFullYear())) { scoreParts[note.part] = note.value; notes.push(note); }
    notes.sort((a, b) => scoreParts[b.part] - scoreParts[a.part] || partRank(a.part) - partRank(b.part));
    const reasons = notes.map(note => String(note.text).slice(0, 280));
    const fallback = candidate.evidence[0]?.note || (candidate.greatestId || relation ? 'A curated manga worth a closer look.' : 'A manga from AniList worth a closer look.');
    const evidence = [...candidate.evidence];
    for (const note of notes) if (note.evidence && !evidence.some(e => e.id === note.evidence.id)) evidence.push(note.evidence);
    rows.push({ candidateId: candidate.id, reason: (reasons[0] || fallback).slice(0, 280), reasons, evidence,
      evidenceIds: evidence.map(e => e.id), scoreParts, score: round2(Object.values(scoreParts).reduce((a, b) => a + b, 0)),
      period: candidate.period || 'Related works', group: groupFor(scoreParts, candidate.period), tags: candidate.tags });
  }
  // Tags only steer the slot mix; the published row does not repeat them.
  const items = mixSlots(rows, { topTags: seeds.topTags }).map(({ tags, ...row }) => row);
  return { generatedAt: today.toISOString(), items };
}
// Sample across eras (and seed kinds) before the work cap; insertion order in the curated
// catalog must not make recent manga invisible.
function candidatePool({ greatest, library, cacheDir, harvestCache }) {
  const all = buildCandidates({ greatest, library, cacheDir, harvestCache });
  const buckets = new Map();
  for (const candidate of all) {
    const key = candidate.period || candidate.seed || 'Related works';
    if (!buckets.has(key)) buckets.set(key, []);
    buckets.get(key).push(candidate);
  }
  const candidates = [];
  while (candidates.length < MAX_CANDIDATES && [...buckets.values()].some(values => values.length)) {
    for (const values of buckets.values()) {
      if (values.length && candidates.length < MAX_CANDIDATES) candidates.push(values.shift());
    }
  }
  return { all, candidates };
}
// Only candidates a feed shows are published; the rest of the pool (up to 2000, with AniList
// records) would bloat discovery.json for nothing. examined/clipped still describe the whole pool.
function runResult(all, candidates, feeds) {
  const shown = new Set();
  for (const feed of Object.values(feeds)) for (const item of feed?.items || []) shown.add(item.candidateId);
  return { candidates: Object.fromEntries(candidates.filter(c => shown.has(c.id)).map(c => [c.id, c])), feeds,
    examined: all.length, clipped: Math.max(0, all.length - candidates.length) };
}
function generate({ db, library, greatest, cacheDir, harvestCache = null, queuedTitles = [], now }) {
  const { all, candidates } = candidatePool({ greatest, library, cacheDir, harvestCache });
  const feeds = {};
  for (const user of Object.values(db.users || {}))
    feeds[user.name] = feedForUser({ user, db, candidates, greatest, library, queuedTitles, harvestCache, now });
  return runResult(all, candidates, feeds);
}
// Same result as generate(), but yields to the event loop between users so the reader stays responsive.
async function generateAsync({ db, library, greatest, cacheDir, harvestCache = null, queuedTitles = [], onlyUser, now }) {
  const { all, candidates } = candidatePool({ greatest, library, cacheDir, harvestCache });
  const feeds = {};
  for (const user of Object.values(db.users || {})) {
    if (onlyUser !== undefined && user.name !== onlyUser) continue;
    await new Promise(setImmediate);
    feeds[user.name] = feedForUser({ user, db, candidates, greatest, library, queuedTitles, harvestCache, now });
  }
  return runResult(all, candidates, feeds);
}
// A per-user rescore replaces one feed; the others and the candidates they show are carried over.
function mergeUserFeed(prior, result, userName) {
  const feeds = { ...(prior?.feeds || {}) };
  if (result.feeds?.[userName]) feeds[userName] = result.feeds[userName];
  else delete feeds[userName];
  const candidates = {};
  for (const [name, feed] of Object.entries(feeds)) {
    if (name === userName) continue;
    for (const item of feed?.items || []) {
      const candidate = prior?.candidates?.[item.candidateId];
      if (candidate) candidates[item.candidateId] = candidate;
    }
  }
  Object.assign(candidates, result.candidates || {});
  return { candidates, feeds };
}

module.exports = { generate, generateAsync, buildCandidates, candidatePool, feedForUser, mixSlots, mergeUserFeed, cachedMetadata,
  isMature, MAX_CANDIDATES, MAX_FEED, SLOTS };