wortkraft/server/index.js

import express from 'express';
import cors from 'cors';
import path from 'path';
import fs from 'fs';
import crypto from 'crypto';
import { fileURLToPath } from 'url';

const __filename = fileURLToPath(import.meta.url);
const __dirname = path.dirname(__filename);

const app = express();
const PORT = process.env.PORT || 80;
const DATA_DIR = process.env.DATA_DIR || path.resolve(__dirname, '../data_store');
const STATE_FILE = path.join(DATA_DIR, 'wortkraft_state.json');
const TRANSLATE_CACHE_FILE = path.join(DATA_DIR, 'translations_cache.json');
const TTS_CACHE_DIR = path.join(DATA_DIR, 'tts_cache');

if (!fs.existsSync(DATA_DIR)) {
  fs.mkdirSync(DATA_DIR, { recursive: true });
}
if (!fs.existsSync(TTS_CACHE_DIR)) {
  fs.mkdirSync(TTS_CACHE_DIR, { recursive: true });
}

function readJson(filePath, fallback) {
  try {
    if (fs.existsSync(filePath)) {
      const raw = fs.readFileSync(filePath, 'utf8');
      return JSON.parse(raw);
    }
  } catch (err) {
    console.error(`[WORTKRAFT] Error reading ${filePath}:`, err);
  }
  return fallback;
}

function writeJson(filePath, obj) {
  try {
    fs.writeFileSync(filePath, JSON.stringify(obj, null, 2), 'utf8');
    return true;
  } catch (err) {
    console.error(`[WORTKRAFT] Error writing ${filePath}:`, err);
    return false;
  }
}

// Split longer German text into sentence/phrase chunks <= 180 chars for TTS
function splitTextForTts(text, maxLen = 180) {
  const cleaned = text.replace(/\s+/g, ' ').trim();
  if (cleaned.length <= maxLen) return [cleaned];

  const sentences = cleaned.split(/(?<=[.!?…;:])\s+/);
  const chunks = [];
  let current = '';

  for (const sentence of sentences) {
    if ((current + ' ' + sentence).trim().length <= maxLen) {
      current = (current + ' ' + sentence).trim();
    } else {
      if (current) chunks.push(current);
      if (sentence.length <= maxLen) {
        current = sentence;
      } else {
        // Split very long sentence by commas or words
        const words = sentence.split(' ');
        current = '';
        for (const w of words) {
          if ((current + ' ' + w).trim().length <= maxLen) {
            current = (current + ' ' + w).trim();
          } else {
            if (current) chunks.push(current);
            current = w;
          }
        }
      }
    }
  }
  if (current) chunks.push(current);
  return chunks;
}

app.use(cors());
app.use(express.json({ limit: '10mb' }));

// Healthcheck endpoint for Docker & Homepage
app.get('/api/health', (_req, res) => {
  res.json({
    status: 'ok',
    app: 'wortkraft',
    timestamp: new Date().toISOString(),
    uptimeSeconds: Math.floor(process.uptime())
  });
});

// Native German (de-DE) TTS Audio Endpoint with disk caching
app.get('/api/tts', async (req, res) => {
  const text = String(req.query.text || '').trim();
  if (!text) {
    return res.status(400).json({ error: 'Missing text parameter' });
  }

  const hash = crypto.createHash('sha1').update(text).digest('hex');
  const cachedFile = path.join(TTS_CACHE_DIR, `${hash}.mp3`);

  if (fs.existsSync(cachedFile)) {
    res.setHeader('Content-Type', 'audio/mpeg');
    res.setHeader('Cache-Control', 'public, max-age=604800');
    return fs.createReadStream(cachedFile).pipe(res);
  }

  try {
    const chunks = splitTextForTts(text, 180);
    const buffers = [];

    for (const chunk of chunks) {
      const ttsUrl = `https://translate.google.com/translate_tts?ie=UTF-8&client=tw-ob&tl=de&q=${encodeURIComponent(chunk)}`;
      const response = await fetch(ttsUrl, {
        headers: {
          'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
        }
      });
      if (!response.ok) {
        throw new Error(`TTS upstream returned ${response.status}`);
      }
      const arrBuf = await response.arrayBuffer();
      buffers.push(Buffer.from(arrBuf));
    }

    const combined = Buffer.concat(buffers);
    fs.writeFileSync(cachedFile, combined);

    res.setHeader('Content-Type', 'audio/mpeg');
    res.setHeader('Cache-Control', 'public, max-age=604800');
    return res.send(combined);
  } catch (err) {
    console.error('[WORTKRAFT] TTS error:', err.message);
    return res.status(502).json({ error: 'TTS generation failed' });
  }
});

// Get persisted learning state (SRS deck, streak, custom words & stories)
app.get('/api/state', (_req, res) => {
  const state = readJson(STATE_FILE, null);
  res.json({ exists: Boolean(state), state });
});

// Save learning state
app.post('/api/state', (req, res) => {
  const payload = req.body;
  if (!payload || typeof payload !== 'object') {
    return res.status(400).json({ error: 'Invalid state payload' });
  }
  payload.updatedAt = new Date().toISOString();
  const ok = writeJson(STATE_FILE, payload);
  res.json({ success: ok, updatedAt: payload.updatedAt });
});

// On-the-fly German -> English word translation fallback for custom texts
app.get('/api/translate', async (req, res) => {
  const word = String(req.query.word || '').trim();
  if (!word) {
    return res.status(400).json({ error: 'Missing word parameter' });
  }
  const key = word.toLowerCase();
  const cache = readJson(TRANSLATE_CACHE_FILE, {});
  if (cache[key]) {
    return res.json({ word, english: cache[key], cached: true });
  }

  try {
    const url = `https://api.mymemory.translated.net/get?q=${encodeURIComponent(word)}&langpair=de|en`;
    const response = await fetch(url);
    if (response.ok) {
      const data = await response.json();
      const translated = data?.responseData?.translatedText;
      if (translated && translated.toLowerCase() !== key) {
        cache[key] = translated;
        writeJson(TRANSLATE_CACHE_FILE, cache);
        return res.json({ word, english: translated, cached: false });
      }
    }
  } catch (err) {
    console.warn('[WORTKRAFT] Translation fallback error:', err.message);
  }
  res.json({ word, english: null });
});

// Serve static frontend files from project root with no-cache headers so updates apply immediately
const PUBLIC_DIR = path.resolve(__dirname, '..');
app.use((req, res, next) => {
  if (!req.path.startsWith('/api/tts')) {
    res.setHeader('Cache-Control', 'no-cache, no-store, must-revalidate');
    res.setHeader('Pragma', 'no-cache');
    res.setHeader('Expires', '0');
  }
  next();
});
app.use('/data', express.static(path.join(PUBLIC_DIR, 'data')));
app.get('/icon.svg', (_req, res) => res.sendFile(path.join(PUBLIC_DIR, 'icon.svg')));
app.get('/styles.css', (_req, res) => res.sendFile(path.join(PUBLIC_DIR, 'styles.css')));
app.get('/app.js', (_req, res) => res.sendFile(path.join(PUBLIC_DIR, 'app.js')));
app.get('/', (_req, res) => res.sendFile(path.join(PUBLIC_DIR, 'index.html')));

app.use((req, res, next) => {
  if (req.method === 'GET' && !req.path.startsWith('/api')) {
    return res.sendFile(path.join(PUBLIC_DIR, 'index.html'));
  }
  next();
});

app.listen(PORT, '0.0.0.0', () => {
  console.log(`[WORTKRAFT] Server listening on port ${PORT}`);
  console.log(`[WORTKRAFT] Persistent data directory: ${DATA_DIR}`);
});