__tests__/scraper/scraperRoutes.test.js

@@ -1,7 +1,8 @@
 /**
- * Tests for POST /api/admin/scraper/run endpoint
+ * Tests for scraper admin route endpoints
  *
  * Covers:
+ * - POST /api/admin/scraper/run
  *   - Authentication and authorization (401, 403)
  *   - Successful scrape trigger (202 with jobId)
  *   - Conflict when scraper already running (409)
@@ -10,10 +11,17 @@
  *   - dryRun option support
  *   - htmlContent option support
  *   - Response structure validation
+ * - GET /api/admin/scraper/status
+ *   - Authentication and authorization (401/403)
+ *   - Correct status response structure
+ *   - Idle vs running state
+ *   - lastRun details from database
+ *   - nextScheduledRun and schedule fields
+ *   - 503 on database errors
  */
 
 const request = require('supertest');
-const { MongoClient } = require('mongodb');
+const { MongoClient, ObjectId } = require('mongodb');
 const {
   createTestApp,
   generateTestToken,
@@ -23,38 +31,52 @@ const {
   cleanupTestData
 } = require('../helpers/testHelpers');
 
-// We need to mock scraperJob functions to control mutex behavior
+// Mock the scraperJob module to control mutex state and schedule functions
 jest.mock('../../jobs/scraperJob', () => {
-  const actual = {
-    _isRunning: false,
-    _currentJobId: null
-  };
+  let _isRunning = false;
+  let _currentJobId = null;
+  let _scheduleExpression = '0 6 * * *';
+  let _nextScheduledRun = '2026-02-07T06:00:00.000Z';
+
   return {
-    isScraperRunning: jest.fn(() => actual._isRunning),
+    isScraperRunning: jest.fn(() => _isRunning),
     acquireLock: jest.fn((jobId) => {
-      if (actual._isRunning) return false;
-      actual._isRunning = true;
-      actual._currentJobId = jobId;
+      if (_isRunning) return false;
+      _isRunning = true;
+      _currentJobId = jobId;
       return true;
     }),
     releaseLock: jest.fn(() => {
-      actual._isRunning = false;
-      actual._currentJobId = null;
+      _isRunning = false;
+      _currentJobId = null;
     }),
-    getCurrentJobId: jest.fn(() => actual._currentJobId),
-    getScheduleExpression: jest.fn(() => '0 6 * * *'),
-    getNextScheduledRun: jest.fn(() => null),
+    getCurrentJobId: jest.fn(() => _currentJobId),
+    getScheduleExpression: jest.fn(() => _scheduleExpression),
+    getNextScheduledRun: jest.fn(() => _nextScheduledRun),
     initializeScheduler: jest.fn(),
     stopScheduler: jest.fn(),
     isShuttingDown: jest.fn(() => false),
     gracefulShutdown: jest.fn(),
     registerSignalHandlers: jest.fn(),
-    // Expose internal state for test manipulation
+    // Test helpers to control mock state
     _setState: (running, jobId) => {
-      actual._isRunning = running;
-      actual._currentJobId = jobId;
+      _isRunning = running;
+      _currentJobId = jobId || null;
     },
-    _getState: () => actual
+    __setRunning: (running, jobId) => {
+      _isRunning = running;
+      _currentJobId = jobId || null;
+    },
+    __setSchedule: (expression, nextRun) => {
+      _scheduleExpression = expression;
+      _nextScheduledRun = nextRun;
+    },
+    __reset: () => {
+      _isRunning = false;
+      _currentJobId = null;
+      _scheduleExpression = '0 6 * * *';
+      _nextScheduledRun = '2026-02-07T06:00:00.000Z';
+    }
   };
 });
 
@@ -72,11 +94,29 @@ jest.mock('../../services/activityLogger', () => {
   };
 });
 
+// Mock the scraper config for collection names
+jest.mock('../../config/scraper', () => ({
+  TARGET_URL: 'https://example.com/test',
+  SCRAPER_SCHEDULE: '0 6 * * *',
+  SCRAPER_TIMEZONE: 'UTC',
+  SCRAPER_ENABLED: true,
+  SCRAPER_TIMEOUT: 30000,
+  USER_AGENT: 'TestBot/1.0',
+  RETRY_CONFIG: { maxRetries: 3, baseDelay: 1000, timeout: 30000 },
+  SHUTDOWN_TIMEOUT: 30000,
+  COLLECTIONS: {
+    UNITS: 'units_migration_test',
+    PRICES: 'unit_prices_migration_test',
+    DAILY_SUMMARIES: 'daily_summaries',
+    SCRAPER_RUNS: 'scraper_runs'
+  }
+}));
+
 const scraperJob = require('../../jobs/scraperJob');
 const { runScrape } = require('../../services/scraperService');
 const { logActivity } = require('../../services/activityLogger');
 
-describe('POST /api/admin/scraper/run', () => {
+describe('Scraper Routes', () => {
   let connection;
   let db;
   let app;
@@ -97,10 +137,12 @@ describe('POST /api/admin/scraper/run', () => {
 
   beforeEach(async () => {
     await cleanupTestData(db);
+    // Also clean scraper_runs collection
+    await db.collection('scraper_runs').deleteMany({});
     app = await createTestApp(db);
 
-    // Reset scraper state to not running
-    scraperJob._setState(false, null);
+    // Reset scraper state
+    scraperJob.__reset();
 
     // Clear mock call history (but keep implementations intact)
     scraperJob.isScraperRunning.mockClear();
@@ -113,6 +155,11 @@ describe('POST /api/admin/scraper/run', () => {
     runScrape.mockImplementation(() => Promise.resolve({ status: 'success', jobId: 'test-job-id' }));
   });
 
+  // ============================================================
+  // POST /api/admin/scraper/run
+  // ============================================================
+  describe('POST /api/admin/scraper/run', () => {
+
     // ============================================================
     // Authentication Tests
     // ============================================================
@@ -213,7 +260,7 @@ describe('POST /api/admin/scraper/run', () => {
       });
 
       it('should return 409 when scraper is already running', async () => {
-      // Set scraper as running (the mock reads from actual._isRunning)
+        // Set scraper as running
         scraperJob._setState(true, 'existing-job-id');
 
         const res = await request(app)
@@ -525,4 +572,275 @@ describe('POST /api/admin/scraper/run', () => {
         await new Promise(resolve => setTimeout(resolve, 100));
       });
     });
+  });
+
+  // ============================================================
+  // GET /api/admin/scraper/status
+  // ============================================================
+  describe('GET /api/admin/scraper/status', () => {
+
+    describe('Authentication and Authorization', () => {
+      it('should return 401 without authentication', async () => {
+        const res = await request(app)
+          .get('/api/admin/scraper/status')
+          .expect(401);
+
+        expect(res.body).toHaveProperty('error');
+      });
+
+      it('should return 403 for non-admin user', async () => {
+        const regularUser = createTestUser({ role: 'user' });
+        await insertTestUser(db, regularUser);
+        const token = generateTestToken(regularUser._id);
+
+        const res = await request(app)
+          .get('/api/admin/scraper/status')
+          .set('Cookie', [`auth_token=${token}`])
+          .expect(403);
+
+        expect(res.body).toHaveProperty('error');
+        expect(res.body.error).toBe('Admin access required');
+      });
+    });
+
+    describe('Successful status response (admin)', () => {
+      let admin;
+      let token;
+
+      beforeEach(async () => {
+        admin = createTestAdmin();
+        await insertTestUser(db, admin);
+        token = generateTestToken(admin._id);
+      });
+
+      it('should return 200 with status for admin', async () => {
+        const res = await request(app)
+          .get('/api/admin/scraper/status')
+          .set('Cookie', [`auth_token=${token}`])
+          .expect(200);
+
+        expect(res.body).toHaveProperty('data');
+        expect(res.body.data).toHaveProperty('currentStatus');
+        expect(res.body.data).toHaveProperty('runningJobId');
+        expect(res.body.data).toHaveProperty('lastRun');
+        expect(res.body.data).toHaveProperty('nextScheduledRun');
+        expect(res.body.data).toHaveProperty('schedule');
+      });
+
+      it('should return currentStatus "idle" when scraper is not running', async () => {
+        scraperJob.__setRunning(false);
+
+        const res = await request(app)
+          .get('/api/admin/scraper/status')
+          .set('Cookie', [`auth_token=${token}`])
+          .expect(200);
+
+        expect(res.body.data.currentStatus).toBe('idle');
+        expect(res.body.data.runningJobId).toBeNull();
+      });
+
+      it('should return currentStatus "running" with runningJobId when scraper is running', async () => {
+        const jobId = 'test-job-id-abc-123';
+        scraperJob.__setRunning(true, jobId);
+
+        const res = await request(app)
+          .get('/api/admin/scraper/status')
+          .set('Cookie', [`auth_token=${token}`])
+          .expect(200);
+
+        expect(res.body.data.currentStatus).toBe('running');
+        expect(res.body.data.runningJobId).toBe(jobId);
+      });
+
+      it('should return lastRun as null when no runs exist', async () => {
+        const res = await request(app)
+          .get('/api/admin/scraper/status')
+          .set('Cookie', [`auth_token=${token}`])
+          .expect(200);
+
+        expect(res.body.data.lastRun).toBeNull();
+      });
+
+      it('should return lastRun object with correct fields when a run exists', async () => {
+        // Insert a scraper run record
+        await db.collection('scraper_runs').insertOne({
+          jobId: 'previous-job-001',
+          trigger: 'scheduled',
+          status: 'success',
+          startedAt: '2026-02-05T06:00:00.000Z',
+          completedAt: '2026-02-05T06:00:12.345Z',
+          duration: 12345,
+          unitsProcessed: 50,
+          pricesInserted: 48,
+          newUnitsCount: 2,
+          rentedUnitsCount: 1,
+          staleUnitsCount: 0,
+          errors: [],
+          recordedAt: new Date('2026-02-05T06:00:12.345Z')
+        });
+
+        const res = await request(app)
+          .get('/api/admin/scraper/status')
+          .set('Cookie', [`auth_token=${token}`])
+          .expect(200);
+
+        const lastRun = res.body.data.lastRun;
+        expect(lastRun).not.toBeNull();
+        expect(lastRun.jobId).toBe('previous-job-001');
+        expect(lastRun.timestamp).toBe('2026-02-05T06:00:00.000Z');
+        expect(lastRun.status).toBe('success');
+        expect(lastRun.duration).toBe(12345);
+        expect(lastRun.trigger).toBe('scheduled');
+        expect(lastRun.unitsProcessed).toBe(50);
+        expect(lastRun.pricesInserted).toBe(48);
+        expect(lastRun.errors).toBeNull();
+      });
+
+      it('should return lastRun with errors array when last run had errors', async () => {
+        await db.collection('scraper_runs').insertOne({
+          jobId: 'failed-job-002',
+          trigger: 'manual',
+          status: 'failed',
+          startedAt: '2026-02-05T10:00:00.000Z',
+          completedAt: '2026-02-05T10:00:32.000Z',
+          duration: 32000,
+          unitsProcessed: 0,
+          pricesInserted: 0,
+          newUnitsCount: 0,
+          rentedUnitsCount: 0,
+          staleUnitsCount: 0,
+          errors: ['HTTP request failed after 3 retries'],
+          recordedAt: new Date('2026-02-05T10:00:32.000Z')
+        });
+
+        const res = await request(app)
+          .get('/api/admin/scraper/status')
+          .set('Cookie', [`auth_token=${token}`])
+          .expect(200);
+
+        const lastRun = res.body.data.lastRun;
+        expect(lastRun.status).toBe('failed');
+        expect(lastRun.errors).toEqual(['HTTP request failed after 3 retries']);
+      });
+
+      it('should return the most recent run when multiple runs exist', async () => {
+        // Insert older run
+        await db.collection('scraper_runs').insertOne({
+          jobId: 'older-job-001',
+          trigger: 'scheduled',
+          status: 'success',
+          startedAt: '2026-02-04T06:00:00.000Z',
+          completedAt: '2026-02-04T06:00:10.000Z',
+          duration: 10000,
+          unitsProcessed: 45,
+          pricesInserted: 45,
+          errors: [],
+          recordedAt: new Date('2026-02-04T06:00:10.000Z')
+        });
+
+        // Insert newer run
+        await db.collection('scraper_runs').insertOne({
+          jobId: 'newer-job-002',
+          trigger: 'manual',
+          status: 'success',
+          startedAt: '2026-02-05T14:00:00.000Z',
+          completedAt: '2026-02-05T14:00:08.000Z',
+          duration: 8000,
+          unitsProcessed: 52,
+          pricesInserted: 50,
+          errors: [],
+          recordedAt: new Date('2026-02-05T14:00:08.000Z')
+        });
+
+        const res = await request(app)
+          .get('/api/admin/scraper/status')
+          .set('Cookie', [`auth_token=${token}`])
+          .expect(200);
+
+        expect(res.body.data.lastRun.jobId).toBe('newer-job-002');
+        expect(res.body.data.lastRun.trigger).toBe('manual');
+      });
+
+      it('should return nextScheduledRun as ISO timestamp', async () => {
+        scraperJob.__setSchedule('0 6 * * *', '2026-02-07T06:00:00.000Z');
+
+        const res = await request(app)
+          .get('/api/admin/scraper/status')
+          .set('Cookie', [`auth_token=${token}`])
+          .expect(200);
+
+        expect(res.body.data.nextScheduledRun).toBe('2026-02-07T06:00:00.000Z');
+      });
+
+      it('should return nextScheduledRun as null when scheduler is disabled', async () => {
+        scraperJob.__setSchedule('disabled', null);
+
+        const res = await request(app)
+          .get('/api/admin/scraper/status')
+          .set('Cookie', [`auth_token=${token}`])
+          .expect(200);
+
+        expect(res.body.data.nextScheduledRun).toBeNull();
+        expect(res.body.data.schedule).toBe('disabled');
+      });
+
+      it('should return schedule cron expression', async () => {
+        scraperJob.__setSchedule('0 6 * * *', '2026-02-07T06:00:00.000Z');
+
+        const res = await request(app)
+          .get('/api/admin/scraper/status')
+          .set('Cookie', [`auth_token=${token}`])
+          .expect(200);
+
+        expect(res.body.data.schedule).toBe('0 6 * * *');
+      });
+    });
+
+    describe('Error handling', () => {
+      let admin;
+      let token;
+
+      beforeEach(async () => {
+        admin = createTestAdmin();
+        await insertTestUser(db, admin);
+        token = generateTestToken(admin._id);
+      });
+
+      it('should return 503 on database error', async () => {
+        // Create a proxy db that works for auth (users collection)
+        // but throws errors for scraper_runs collection
+        const express = require('express');
+        const cookieParser = require('cookie-parser');
+
+        const brokenApp = express();
+        brokenApp.use(express.json());
+        brokenApp.use(cookieParser());
+
+        // Proxy db: real db for users, broken for scraper_runs
+        const proxyDb = {
+          collection: jest.fn((name) => {
+            if (name === 'scraper_runs') {
+              return {
+                findOne: jest.fn().mockRejectedValue(new Error('Database connection lost'))
+              };
+            }
+            // Delegate to real db for all other collections (users, etc.)
+            return db.collection(name);
+          })
+        };
+        brokenApp.locals.db = proxyDb;
+
+        const adminRoutes = require('../../routes/admin');
+        brokenApp.use('/api/admin', adminRoutes);
+
+        const res = await request(brokenApp)
+          .get('/api/admin/scraper/status')
+          .set('Cookie', [`auth_token=${token}`])
+          .expect(503);
+
+        expect(res.body).toHaveProperty('error');
+        expect(res.body.error).toBe('Service temporarily unavailable');
+      });
+    });
+  });
 });

routes/admin.js

@@ -1150,9 +1150,13 @@ const crypto = require('crypto');
 const {
   isScraperRunning,
   acquireLock,
-  releaseLock
+  releaseLock,
+  getCurrentJobId,
+  getScheduleExpression,
+  getNextScheduledRun
 } = require('../jobs/scraperJob');
 const { runScrape } = require('../services/scraperService');
+const scraperConfig = require('../config/scraper');
 
 /**
  * POST /api/admin/scraper/run
@@ -1206,5 +1210,45 @@ router.post('/scraper/run', async (req, res) => {
   }
 });
 
+/**
+ * GET /api/admin/scraper/status
+ * Get current scraper status including running state, last run details,
+ * next scheduled run, and schedule expression.
+ */
+router.get('/scraper/status', async (req, res) => {
+  try {
+    const db = req.app.locals.db;
+
+    // Get last run from history
+    const lastRunDoc = await db.collection(scraperConfig.COLLECTIONS.SCRAPER_RUNS)
+      .findOne({}, { sort: { startedAt: -1 } });
+
+    const lastRun = lastRunDoc ? {
+      jobId: lastRunDoc.jobId,
+      timestamp: lastRunDoc.startedAt,
+      status: lastRunDoc.status,
+      duration: lastRunDoc.duration,
+      trigger: lastRunDoc.trigger,
+      unitsProcessed: lastRunDoc.unitsProcessed,
+      pricesInserted: lastRunDoc.pricesInserted,
+      errors: lastRunDoc.errors?.length > 0 ? lastRunDoc.errors : null
+    } : null;
+
+    res.json({
+      data: {
+        currentStatus: isScraperRunning() ? 'running' : 'idle',
+        runningJobId: isScraperRunning() ? getCurrentJobId() : null,
+        lastRun,
+        nextScheduledRun: getNextScheduledRun(),
+        schedule: getScheduleExpression()
+      }
+    });
+
+  } catch (error) {
+    console.error('Error fetching scraper status:', error);
+    res.status(503).json({ error: 'Service temporarily unavailable' });
+  }
+});
+
 module.exports = router;
 module.exports.clearStatsCache = clearStatsCache;