railseek6/test_ocr_workflow_results.py

import requests
import os
import json
import time
import sys

def test_ocr_workflow():
    """Test complete OCR workflow for scanned table PDF"""
    base_url = 'http://localhost:3015'
    pdf_file = 'ocr.pdf'
    
    print("=" * 60)
    print("OCR PDF WORKFLOW TEST - SCANNED TABLE DOCUMENT")
    print("=" * 60)
    
    # Check if ocr.pdf exists
    if not os.path.exists(pdf_file):
        print(f"❌ {pdf_file} not found in current directory")
        return False
    
    print(f"📄 Testing with: {pdf_file}")
    print(f"📊 File size: {os.path.getsize(pdf_file)} bytes")
    
    # Login first
    print("\n1. 🔐 AUTHENTICATION")
    login_data = {'username': 'jleu3482', 'password': 'jleu1212'}
    try:
        login_response = requests.post(f'{base_url}/login', data=login_data, timeout=30)
        if login_response.status_code == 200:
            token = login_response.json().get('access_token')
            headers = {'Authorization': f'Bearer {token}'}
            print('✅ Login successful')
        else:
            print(f'❌ Login failed: {login_response.status_code}')
            return False
    except Exception as e:
        print(f'❌ Login error: {e}')
        return False
    
    # Upload ocr.pdf
    print("\n2. 📤 DOCUMENT UPLOAD")
    try:
        print(f"Uploading {pdf_file}...")
        with open(pdf_file, 'rb') as file:
            files = {'file': (pdf_file, file, 'application/pdf')}
            upload_response = requests.post(f'{base_url}/documents/upload', files=files, headers=headers, timeout=60)
        
        print(f"Upload Status: {upload_response.status_code}")
        if upload_response.status_code == 200:
            upload_result = upload_response.json()
            print('✅ Upload successful')
            print(f"Response: {json.dumps(upload_result, indent=2)}")
            track_id = upload_result.get('track_id', '')
        else:
            print(f'❌ Upload failed: {upload_response.text}')
            return False
    except Exception as e:
        print(f'❌ Upload error: {e}')
        return False
    
    # Wait for processing
    print("\n3. ⏳ WAITING FOR PROCESSING")
    max_wait = 120  # 2 minutes max
    wait_time = 0
    processing_complete = False
    
    while wait_time < max_wait and not processing_complete:
        print(f"Waiting for processing... ({wait_time}s/{max_wait}s)")
        time.sleep(10)
        wait_time += 10
        
        try:
            # Check document status
            status_response = requests.get(f'{base_url}/documents', headers=headers, timeout=30)
            if status_response.status_code == 200:
                documents = status_response.json()
                statuses = documents.get('statuses', {})
                
                # Check for completed documents
                completed = statuses.get('completed', [])
                processing = statuses.get('processing', [])
                failed = statuses.get('failed', [])
                
                print(f"📊 Status - Completed: {len(completed)}, Processing: {len(processing)}, Failed: {len(failed)}")
                
                # Check if our document is completed
                for doc in completed:
                    if doc.get('file_path') == pdf_file:
                        print("✅ Document processing completed!")
                        processing_complete = True
                        print(f"Document details: {json.dumps(doc, indent=2)}")
                        break
                
                # Check if failed
                for doc in failed:
                    if doc.get('file_path') == pdf_file:
                        print(f"❌ Document processing failed: {doc.get('error_msg', 'Unknown error')}")
                        return False
                        
            else:
                print(f"⚠️  Status check failed: {status_response.status_code}")
                
        except Exception as e:
            print(f"⚠️  Status check error: {e}")
    
    if not processing_complete:
        print("❌ Processing timeout - document not processed within expected time")
        return False
    
    # Test search functionality
    print("\n4. 🔍 SEARCH FUNCTIONALITY TEST")
    
    # Test queries based on expected content from scanned table
    test_queries = [
        "table data",
        "document content", 
        "information in the pdf",
        "what does this document contain"
    ]
    
    for query in test_queries:
        print(f"\nTesting query: '{query}'")
        try:
            query_data = {'query': query, 'top_k': 5}
            search_response = requests.post(f'{base_url}/query', json=query_data, headers=headers, timeout=30)
            
            if search_response.status_code == 200:
                results = search_response.json()
                print(f"✅ Search successful")
                
                if isinstance(results, dict):
                    response_text = results.get('response', 'No response field')
                    print(f"Response: {response_text}")
                    
                    # Check for no-context response
                    if '[no-context]' in response_text:
                        print("⚠️  No relevant content found in document")
                    else:
                        print("🎉 Content found and retrieved!")
                        
                else:
                    print(f"Unexpected response format: {type(results)}")
                    print(f"Raw result: {results}")
            else:
                print(f'❌ Search failed: {search_response.text}')
                
        except Exception as e:
            print(f'❌ Search error: {e}')
    
    # Get detailed document information
    print("\n5. 📋 DOCUMENT DETAILS")
    try:
        status_response = requests.get(f'{base_url}/documents', headers=headers, timeout=30)
        if status_response.status_code == 200:
            documents = status_response.json()
            completed_docs = documents.get('statuses', {}).get('completed', [])
            
            for doc in completed_docs:
                if doc.get('file_path') == pdf_file:
                    print("📄 Document Summary:")
                    print(f"  - File: {doc.get('file_path')}")
                    print(f"  - Status: {doc.get('status')}")
                    print(f"  - Content Length: {doc.get('content_length', 'N/A')}")
                    print(f"  - Chunks Count: {doc.get('chunks_count', 'N/A')}")
                    print(f"  - Created: {doc.get('created_at')}")
                    print(f"  - Updated: {doc.get('updated_at')}")
                    break
    except Exception as e:
        print(f"⚠️  Could not get document details: {e}")
    
    print("\n" + "=" * 60)
    print("WORKFLOW TEST COMPLETED")
    print("=" * 60)
    return True

if __name__ == "__main__":
    success = test_ocr_workflow()
    sys.exit(0 if success else 1)