railseek6/test_server_ocr_fix.py

#!/usr/bin/env python3
"""
Test script to verify the OCR fix is working with the server
"""

import asyncio
import requests
import json
import sys
from pathlib import Path

# Test configuration
SERVER_URL = "http://localhost:3015"
TEST_PDF = "ocr.pdf"

async def test_server_ocr():
    """Test OCR PDF upload to the running server"""
    
    print("🧪 Testing Server OCR Fix")
    print("=" * 50)
    
    # Check if server is running
    try:
        health_response = requests.get(f"{SERVER_URL}/docs")
        if health_response.status_code != 200:
            print("❌ Server is not responding properly")
            return False
        print("✅ Server is running")
    except Exception as e:
        print(f"❌ Cannot connect to server: {e}")
        return False
    
    # Check if PDF file exists
    if not Path(TEST_PDF).exists():
        print(f"❌ Test PDF file not found: {TEST_PDF}")
        return False
    print(f"✅ Test PDF found: {TEST_PDF}")
    
    # Test document upload
    try:
        print(f"📤 Uploading {TEST_PDF} to server...")
        
        with open(TEST_PDF, 'rb') as f:
            files = {'file': (TEST_PDF, f, 'application/pdf')}
            response = requests.post(f"{SERVER_URL}/documents/upload", files=files)
        
        if response.status_code == 200:
            result = response.json()
            print(f"✅ Upload successful: {result}")
            
            # Check processing status
            track_id = result.get('track_id')
            if track_id:
                print(f"📊 Checking processing status for track_id: {track_id}")
                
                # Wait a bit for processing
                await asyncio.sleep(2)
                
                status_response = requests.get(f"{SERVER_URL}/documents/track_status/{track_id}")
                if status_response.status_code == 200:
                    status_data = status_response.json()
                    print(f"📈 Processing status: {status_data}")
                    
                    # Check if any documents were processed successfully
                    documents = status_data.get('documents', [])
                    if documents:
                        for doc in documents:
                            print(f"📄 Document: {doc.get('id')}")
                            print(f"   Status: {doc.get('status')}")
                            print(f"   Content Length: {doc.get('content_length')}")
                            print(f"   Error: {doc.get('error_msg', 'None')}")
                            
                            if doc.get('status') == 'PROCESSED':
                                print("🎉 OCR processing successful!")
                                return True
                            elif doc.get('status') == 'FAILED':
                                print(f"❌ OCR processing failed: {doc.get('error_msg')}")
                                return False
                    else:
                        print("❌ No documents found in processing status")
                        return False
                else:
                    print(f"❌ Failed to get processing status: {status_response.status_code}")
                    return False
            else:
                print("❌ No track_id returned from upload")
                return False
        else:
            print(f"❌ Upload failed: {response.status_code} - {response.text}")
            return False
            
    except Exception as e:
        print(f"❌ Error during upload test: {e}")
        return False

async def test_direct_processor():
    """Test the document processor directly"""
    print("\n🔧 Testing Document Processor Directly")
    print("=" * 50)
    
    try:
        sys.path.append('LightRAG-main')
        from lightrag.document_processor import get_document_processor
        
        processor = get_document_processor()
        print("✅ Document processor loaded successfully")
        
        # Test OCR initialization
        if processor.ocr_processor.ocr_available:
            print("✅ OCR processor is available")
            print(f"   GPU enabled: {processor.ocr_processor.use_gpu}")
        else:
            print("❌ OCR processor not available")
            return False
        
        # Test processing the PDF
        print(f"📄 Processing {TEST_PDF} directly...")
        result = await processor.process_document(TEST_PDF)
        
        print(f"✅ Direct processing result:")
        print(f"   Success: {result.success}")
        print(f"   Content length: {len(result.content)}")
        print(f"   Error: {result.error}")
        print(f"   Metadata: {result.metadata}")
        
        if result.success and len(result.content) > 0:
            print("🎉 Direct OCR processing successful!")
            return True
        else:
            print("❌ Direct OCR processing failed")
            return False
            
    except Exception as e:
        print(f"❌ Error in direct processor test: {e}")
        import traceback
        traceback.print_exc()
        return False

async def main():
    """Run all tests"""
    print("🚀 Starting OCR Fix Verification Tests")
    print("=" * 50)
    
    # Test 1: Direct processor test
    direct_result = await test_direct_processor()
    
    # Test 2: Server upload test
    server_result = await test_server_ocr()
    
    print("\n" + "=" * 50)
    print("📊 TEST RESULTS SUMMARY")
    print("=" * 50)
    print(f"Direct Processor Test: {'✅ PASS' if direct_result else '❌ FAIL'}")
    print(f"Server Upload Test: {'✅ PASS' if server_result else '❌ FAIL'}")
    
    if direct_result and server_result:
        print("\n🎉 ALL TESTS PASSED - OCR fix is working!")
        return True
    else:
        print("\n💥 SOME TESTS FAILED - OCR fix needs more work")
        return False

if __name__ == "__main__":
    success = asyncio.run(main())
    sys.exit(0 if success else 1)