server.js

// server.js — Anichin Scraper REST API + Scheduler

require("dotenv").config();
const express = require("express");
const cors = require("cors");
const cron = require("node-cron");
const { getDB } = require("./firebase");
const {
  scrapeAnimeList,
  scrapeAnimeDetails,
  scrapeIncrementalUpdates,
  scrapeSearch,
  parseAnimeDetail,
  parseEpisodePage,
  fetchPage,
  extractSlug,
} = require("./scraper");

const app = express();
// HF Spaces wajib PORT 7860
const PORT = process.env.PORT || 7860;
const BASE_URL = process.env.BASE_URL || "https://anichin.cafe";

app.use(cors());
app.use(express.json());
app.use(express.static("public")); // serve frontend

// ─── SCRAPE STATE ─────────────────────────────────────────────────────────────

const scrapeState = {
  isRunning: false,
  lastRun: null,
  progress: { current: 0, total: 0, stage: "idle" },
  log: [],
};

function addLog(msg) {
  const entry = { time: new Date().toISOString(), msg };
  scrapeState.log.unshift(entry);
  scrapeState.log = scrapeState.log.slice(0, 100); // keep last 100
  console.log(msg);
}

// ─── API ROUTES ───────────────────────────────────────────────────────────────

// Status
app.get("/api/status", (req, res) => {
  res.json({
    status: "ok",
    scrapeRunning: scrapeState.isRunning,
    lastRun: scrapeState.lastRun,
    progress: scrapeState.progress,
  });
});

// Scrape logs
app.get("/api/logs", (req, res) => {
  res.json(scrapeState.log);
});

// ── Trigger full scrape ───────────────────────────────────────────────────────
app.post("/api/scrape/full", async (req, res) => {
  if (scrapeState.isRunning) {
    return res.status(409).json({ error: "Scrape lagi jalan, tunggu dulu!" });
  }

  const { pages = 10 } = req.body;

  res.json({ message: `Full scrape dimulai — ${pages} halaman`, ok: true });

  // Jalankan di background
  scrapeState.isRunning = true;
  scrapeState.progress = { current: 0, total: pages, stage: "list" };

  (async () => {
    try {
      addLog(`🚀 Full scrape dimulai — ${pages} halaman`);
      const animes = await scrapeAnimeList(`${BASE_URL}/anime/`, pages);
      addLog(`📋 Dapet ${animes.length} anime dari list`);

      scrapeState.progress.stage = "detail";
      scrapeState.progress.total = animes.length;

      await scrapeAnimeDetails(animes);
      addLog(`✅ Full scrape selesai!`);
      scrapeState.lastRun = new Date().toISOString();
    } catch (err) {
      addLog(`❌ Error: ${err.message}`);
    } finally {
      scrapeState.isRunning = false;
      scrapeState.progress.stage = "idle";
    }
  })();
});

// ── Trigger incremental update ────────────────────────────────────────────────
app.post("/api/scrape/update", async (req, res) => {
  if (scrapeState.isRunning) {
    return res.status(409).json({ error: "Scrape lagi jalan!" });
  }

  res.json({ message: "Incremental update dimulai", ok: true });

  scrapeState.isRunning = true;
  scrapeState.progress.stage = "update";

  (async () => {
    try {
      addLog("🔄 Incremental update dimulai");
      await scrapeIncrementalUpdates();
      addLog("✅ Update selesai!");
      scrapeState.lastRun = new Date().toISOString();
    } catch (err) {
      addLog(`❌ Error: ${err.message}`);
    } finally {
      scrapeState.isRunning = false;
      scrapeState.progress.stage = "idle";
    }
  })();
});

// ── Scrape single anime ───────────────────────────────────────────────────────
app.post("/api/scrape/single", async (req, res) => {
  const { url } = req.body;
  if (!url) return res.status(400).json({ error: "URL diperlukan" });

  try {
    addLog(`🎯 Scrape single: ${url}`);
    const html = await fetchPage(url);
    const detail = parseAnimeDetail(html, url);
    const db = getDB();
    const slug = extractSlug(url);

    const { episodes, ...animeData } = detail;
    await db
      .collection("animes")
      .doc(slug)
      .set({ ...animeData, slug, updatedAt: new Date().toISOString() }, { merge: true });

    // Save episodes
    if (episodes.length > 0) {
      const batch = db.batch();
      episodes.forEach((ep) => {
        const epId = `ep-${String(ep.number || 0).padStart(4, "0")}`;
        batch.set(
          db.collection("animes").doc(slug).collection("episodes").doc(epId),
          ep,
          { merge: true }
        );
      });
      await batch.commit();
    }

    addLog(`✅ ${detail.title} berhasil discrape (${episodes.length} eps)`);
    res.json({ success: true, data: detail });
  } catch (err) {
    addLog(`❌ ${err.message}`);
    res.status(500).json({ error: err.message });
  }
});

// ── Search scrape ─────────────────────────────────────────────────────────────
app.get("/api/scrape/search", async (req, res) => {
  const { q } = req.query;
  if (!q) return res.status(400).json({ error: "Query diperlukan" });

  try {
    const results = await scrapeSearch(q);
    res.json({ query: q, count: results.length, results });
  } catch (err) {
    res.status(500).json({ error: err.message });
  }
});

// ─── DATABASE ROUTES (baca data dari Firebase) ────────────────────────────────

// Get semua anime (paginated)
app.get("/api/animes", async (req, res) => {
  try {
    const db = getDB();
    const { limit = 20, page = 1, status, genre, type, sort = "title" } = req.query;
    const lim = Math.min(parseInt(limit), 100);

    let query = db.collection("animes").where("hasDetails", "==", true);

    if (status) query = query.where("status", "==", status);
    if (type) query = query.where("type", "==", type);

    const snapshot = await query.limit(lim * parseInt(page)).get();
    const all = [];
    snapshot.forEach((doc) => all.push({ id: doc.id, ...doc.data() }));

    // Client-side pagination
    const start = (parseInt(page) - 1) * lim;
    const data = all.slice(start, start + lim);

    res.json({ total: all.length, page: parseInt(page), limit: lim, data });
  } catch (err) {
    res.status(500).json({ error: err.message });
  }
});

// Get detail anime
app.get("/api/animes/:slug", async (req, res) => {
  try {
    const db = getDB();
    const doc = await db.collection("animes").doc(req.params.slug).get();
    if (!doc.exists) return res.status(404).json({ error: "Anime not found" });

    // Get episodes
    const epsSnap = await db
      .collection("animes")
      .doc(req.params.slug)
      .collection("episodes")
      .orderBy("number", "asc")
      .get();

    const episodes = [];
    epsSnap.forEach((ep) => episodes.push(ep.data()));

    res.json({ id: doc.id, ...doc.data(), episodes });
  } catch (err) {
    res.status(500).json({ error: err.message });
  }
});

// Search dari Firebase
app.get("/api/animes/search/local", async (req, res) => {
  try {
    const { q } = req.query;
    if (!q) return res.status(400).json({ error: "Query diperlukan" });

    const db = getDB();
    // Firestore nggak support full-text search native,
    // kita pake range query buat approximate match
    const snapshot = await db
      .collection("animes")
      .orderBy("title")
      .startAt(q)
      .endAt(q + "\uf8ff")
      .limit(20)
      .get();

    const results = [];
    snapshot.forEach((doc) => results.push({ id: doc.id, ...doc.data() }));
    res.json({ query: q, count: results.length, results });
  } catch (err) {
    res.status(500).json({ error: err.message });
  }
});

// Stats
app.get("/api/stats", async (req, res) => {
  try {
    const db = getDB();
    const totalSnap = await db.collection("animes").count().get();
    const ongoingSnap = await db
      .collection("animes")
      .where("status", "in", ["Ongoing", "ongoing", "Airing"])
      .count()
      .get();

    res.json({
      totalAnimes: totalSnap.data().count,
      ongoingAnimes: ongoingSnap.data().count,
      lastScrape: scrapeState.lastRun,
    });
  } catch (err) {
    res.status(500).json({ error: err.message });
  }
});

// ─── SCHEDULER ────────────────────────────────────────────────────────────────
// Cron: update anime ongoing setiap hari jam 06:00 WIB (23:00 UTC)
cron.schedule("0 23 * * *", async () => {
  if (!scrapeState.isRunning) {
    addLog("⏰ Scheduled incremental update jalan...");
    scrapeState.isRunning = true;
    try {
      await scrapeIncrementalUpdates();
      scrapeState.lastRun = new Date().toISOString();
    } catch (err) {
      addLog(`❌ Scheduled error: ${err.message}`);
    } finally {
      scrapeState.isRunning = false;
    }
  }
});

// ─── START SERVER ─────────────────────────────────────────────────────────────
app.listen(PORT, "0.0.0.0", () => {
  console.log(`
╔═══════════════════════════════════════════════╗
║   🍥 Anichin Scraper — Hugging Face Spaces   ║
╠═══════════════════════════════════════════════╣
║  Port    : ${PORT}                               ║
║  Mode    : ${process.env.NODE_ENV || "development"}                         ║
║  Firebase: ${process.env.FIREBASE_PROJECT_ID || "NOT SET ⚠️"}     ║
╚═══════════════════════════════════════════════╝
  `);
});