boc/quixzoom-capture-pipeline/api/server.js

/**
 * QUIXZOOM Capture Pipeline — API Server
 * 
 * Huvudserver som exponerar:
 * - Upload API
 * - Status API
 * - Dataset API
 * - Admin API
 * 
 * Teknik: Node.js, Express, Redis
 */

const express = require('express');
const cors = require('cors');
const helmet = require('helmet');
const rateLimit = require('express-rate-limit');
const Redis = require('ioredis');

const uploadRouter = require('./upload');

const app = express();
const PORT = process.env.PORT || 3000;

// Redis-anslutning
const redis = new Redis({
  host: process.env.REDIS_HOST || 'localhost',
  port: process.env.REDIS_PORT || 6379,
  password: process.env.REDIS_PASSWORD,
});

// Middleware
app.use(helmet());
app.use(cors({
  origin: process.env.ALLOWED_ORIGINS?.split(',') || ['http://localhost:3000'],
  methods: ['GET', 'POST', 'PUT', 'DELETE'],
  allowedHeaders: ['Content-Type', 'Authorization'],
}));

// Rate limiting
const limiter = rateLimit({
  windowMs: 15 * 60 * 1000, // 15 minuter
  max: 100, // Max 100 requests per window
  message: { error: 'För många förfrågningar, försök igen senare' },
});
app.use('/api/', limiter);

// Body parsing
app.use(express.json({ limit: '10mb' }));
app.use(express.urlencoded({ extended: true, limit: '10mb' }));

// Health check
app.get('/health', (req, res) => {
  res.json({
    status: 'healthy',
    timestamp: new Date().toISOString(),
    version: '1.0.0',
  });
});

// API-routes
app.use('/api', uploadRouter);

// Dataset API — hämta träningsdata
app.get('/api/dataset/:version', async (req, res) => {
  try {
    const { version } = req.params;
    const { format = 'json', limit = 1000, offset = 0 } = req.query;
    
    // Hämta dataset från Redis eller R2
    const datasetKey = `quixzoom:dataset:${version}`;
    const datasetInfo = await redis.hgetall(datasetKey);
    
    if (!datasetInfo || Object.keys(datasetInfo).length === 0) {
      return res.status(404).json({ error: 'Dataset not found' });
    }
    
    res.json({
      version,
      format,
      limit: parseInt(limit),
      offset: parseInt(offset),
      total: parseInt(datasetInfo.total || 0),
      createdAt: datasetInfo.createdAt,
      url: `https://${process.env.R2_BUCKET_NAME}.r2.cloudflarestorage.com/datasets/${version}.jsonl`,
    });
  } catch (error) {
    res.status(500).json({ error: error.message });
  }
});

// Dataset API — lista alla versioner
app.get('/api/datasets', async (req, res) => {
  try {
    const keys = await redis.keys('quizoom:dataset:*');
    const datasets = [];
    
    for (const key of keys) {
      const info = await redis.hgetall(key);
      datasets.push({
        version: key.replace('quixzoom:dataset:', ''),
        ...info,
      });
    }
    
    res.json({ datasets });
  } catch (error) {
    res.status(500).json({ error: error.message });
  }
});

// Admin API — statistik
app.get('/api/stats', async (req, res) => {
  try {
    const stats = {
      uploads: {
        total: parseInt(await redis.get('quixzoom:stats:uploads:total') || 0),
        today: parseInt(await redis.get(`quixzoom:stats:uploads:${new Date().toISOString().split('T')[0]}`) || 0),
      },
      processing: {
        pending: await redis.llen('quixzoom:processing:queue'),
        completed: parseInt(await redis.get('quixzoom:stats:processing:completed') || 0),
        failed: parseInt(await redis.get('quixzoom:stats:processing:failed') || 0),
      },
      taxonomy: {
        tagged: parseInt(await redis.get('quixzoom:stats:taxonomy:tagged') || 0),
        pending: parseInt(await redis.get('quixzoom:stats:taxonomy:pending') || 0),
      },
      contributors: {
        total: parseInt(await redis.get('quixzoom:stats:contributors:total') || 0),
        active: parseInt(await redis.get('quixzoom:stats:contributors:active') || 0),
      },
    };
    
    res.json(stats);
  } catch (error) {
    res.status(500).json({ error: error.message });
  }
});

// Admin API — köstatus
app.get('/api/queue/status', async (req, res) => {
  try {
    const queues = {
      upload: await redis.llen('quixzoom:upload:queue'),
      processing: await redis.llen('quixzoom:processing:queue'),
      ai: await redis.llen('quixzoom:ai:queue'),
      taxonomy: await redis.llen('quixzoom:taxonomy:queue'),
      dataset: await redis.llen('quixzoom:dataset:queue'),
    };
    
    res.json({ queues });
  } catch (error) {
    res.status(500).json({ error: error.message });
  }
});

// Felhantering
app.use((err, req, res, next) => {
  console.error('API Error:', err);
  res.status(err.status || 500).json({
    error: err.message || 'Internal server error',
    stack: process.env.NODE_ENV === 'development' ? err.stack : undefined,
  });
});

// 404
app.use((req, res) => {
  res.status(404).json({ error: 'Endpoint not found' });
});

// Starta server
app.listen(PORT, () => {
  console.log(`[SERVER] QUIXZOOM Capture Pipeline API running on port ${PORT}`);
  console.log(`[SERVER] Environment: ${process.env.NODE_ENV || 'development'}`);
});

module.exports = app;