MangaCircus/discovery/cache.js

'use strict';

const fs = require('node:fs');
const path = require('node:path');
const crypto = require('node:crypto');

const DAY = 86400000;
const KINDS = ['title', 'recs', 'creator', 'tagTop', 'fresh'];
const TTL_MS = { title: 30 * DAY, recs: 30 * DAY, creator: 30 * DAY, tagTop: 7 * DAY, fresh: 7 * DAY };

function checkKind(kind) {
  if (!KINDS.includes(kind)) throw new TypeError(`Unknown discovery cache kind: ${kind}`);
}

class DiscoveryCache {
  constructor(dir, { maxFiles = 5000, now = Date.now } = {}) {
    this.dir = path.resolve(dir);
    this.maxFiles = maxFiles;
    this.now = now;
  }
  // base64url keeps any key (slashes, dots, spaces) inside the kind folder.
  fileFor(kind, key) {
    checkKind(kind);
    return path.join(this.dir, kind, `${Buffer.from(String(key)).toString('base64url')}.json`);
  }
  readFile(file, kind) {
    let entry;
    try { entry = JSON.parse(fs.readFileSync(file, 'utf8')); }
    catch (error) {
      if (error.code === 'ENOENT') return null;
      entry = null;
    }
    const valid = entry && entry.schema === 1 && entry.kind === kind && typeof entry.fetchedAt === 'string'
      && Number.isFinite(Date.parse(entry.fetchedAt)) && 'data' in entry;
    if (valid) return entry;
    // A bad file would otherwise be re-read on every lookup; drop it so the caller refetches.
    try { fs.rmSync(file, { force: true }); } catch {}
    return null;
  }
  get(kind, key) { return this.readFile(this.fileFor(kind, key), kind); }
  isFresh(kind, key) {
    const entry = this.get(kind, key);
    return !!entry && this.now() - Date.parse(entry.fetchedAt) < TTL_MS[kind];
  }
  put(kind, key, data) {
    const file = this.fileFor(kind, key);
    const entry = { schema: 1, kind, key, fetchedAt: new Date(this.now()).toISOString(), data };
    fs.mkdirSync(path.dirname(file), { recursive: true });
    const temp = `${file}.${crypto.randomBytes(6).toString('hex')}.tmp`;
    try {
      fs.writeFileSync(temp, JSON.stringify(entry), { mode: 0o600 });
      fs.renameSync(temp, file);
    } finally { try { fs.rmSync(temp, { force: true }); } catch {} }
    this.prune();
    return entry;
  }
  files(kind) {
    try {
      return fs.readdirSync(path.join(this.dir, kind)).filter((name) => name.endsWith('.json'))
        .map((name) => path.join(this.dir, kind, name));
    } catch { return []; }
  }
  list(kind) {
    checkKind(kind);
    return this.files(kind).map((file) => this.readFile(file, kind)).filter(Boolean);
  }
  stats() {
    let files = 0, bytes = 0;
    for (const kind of KINDS) for (const file of this.files(kind)) {
      try { bytes += fs.statSync(file).size; files++; } catch {}
    }
    return { files, bytes };
  }
  // Oldest entries go first so the cache never grows past maxFiles. Every put() calls this, so
  // under the cap it only counts directory entries; files are read only when something must go.
  prune() {
    const byKind = KINDS.map(kind => [kind, this.files(kind)]);
    if (byKind.reduce((sum, [, files]) => sum + files.length, 0) <= this.maxFiles) return;
    const all = [];
    for (const [kind, files] of byKind) for (const file of files) {
      // readFile drops corrupt and schema-mismatched files itself.
      const entry = this.readFile(file, kind);
      if (entry) all.push({ file, at: Date.parse(entry.fetchedAt) });
    }
    if (all.length <= this.maxFiles) return;
    all.sort((a, b) => a.at - b.at);
    for (const { file } of all.slice(0, all.length - this.maxFiles)) {
      try { fs.rmSync(file, { force: true }); } catch {}
    }
  }
}

module.exports = { KINDS, TTL_MS, DiscoveryCache };