import requests
import os
import json
import time

# Test uploading and processing ocr.pdf to verify it contains actual content
base_url = 'http://localhost:3015'

# Login first
print("🔐 Logging in...")
login_data = {'username': 'jleu3482', 'password': 'jleu1212'}
login_response = requests.post(f'{base_url}/login', data=login_data)

if login_response.status_code == 200:
    token = login_response.json().get('access_token')
    headers = {'Authorization': f'Bearer {token}'}
    print('✅ Login successful')
    
    # First, delete all documents to start fresh
    print("\n🗑️  Deleting all documents...")
    delete_response = requests.delete(f'{base_url}/documents', headers=headers)
    if delete_response.status_code == 200:
        print("✅ All documents deleted successfully")
    else:
        print(f"❌ Delete failed: {delete_response.text}")
    
    # Wait for cleanup
    time.sleep(3)
    
    # Now upload ocr.pdf fresh
    pdf_file = 'ocr.pdf'
    if not os.path.exists(pdf_file):
        print(f"❌ {pdf_file} not found")
        exit(1)
    
    print(f"\n📤 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)
    
    print(f"  Upload Status: {upload_response.status_code}")
    if upload_response.status_code == 200:
        result = upload_response.json()
        print(f"  Response: {json.dumps(result, indent=2)}")
        
        if result.get('status') == 'success':
            print("✅ Upload successful, waiting for processing...")
            # Wait longer for OCR processing
            print("⏳ Waiting 15 seconds for OCR processing...")
            time.sleep(15)
        else:
            print(f"⚠️  Upload status: {result.get('status')}")
    else:
        print(f'❌ Upload failed: {upload_response.text}')
    
    # Check document status after upload
    print("\n🔍 Checking document status...")
    status_response = requests.get(f'{base_url}/documents', headers=headers)
    if status_response.status_code == 200:
        documents = status_response.json()
        print(f"  Documents response: {json.dumps(documents, indent=2)}")
        
        # Extract content summary if available
        if 'statuses' in documents:
            processed = documents['statuses'].get('processed', [])
            failed = documents['statuses'].get('failed', [])
            
            for doc in processed:
                if doc.get('file_path') == 'ocr.pdf':
                    print(f"\n✅ OCR.PDF PROCESSED SUCCESSFULLY!")
                    print(f"  Content Summary: {doc.get('content_summary', 'No summary')}")
                    print(f"  Content Length: {doc.get('content_length', 0)} characters")
                    print(f"  Chunks: {doc.get('chunks_count', 0)}")
            
            for doc in failed:
                if doc.get('file_path') == 'ocr.pdf':
                    print(f"\n❌ OCR.PDF FAILED!")
                    print(f"  Error: {doc.get('error_msg', 'Unknown error')}")
    
    # Test search with specific content that should be in ocr.pdf
    print("\n🔍 Testing search functionality...")
    test_queries = [
        "table data",
        "document content", 
        "scanned text",
        "PDF information",
        "extracted content"
    ]
    
    for query in test_queries:
        print(f"\n🔎 Querying: \"{query}\"")
        query_data = {'query': query, 'top_k': 5}
        search_response = requests.post(f'{base_url}/query', json=query_data, headers=headers)
        
        if search_response.status_code == 200:
            results = search_response.json()
            if isinstance(results, dict):
                response_text = results.get('response', '')
                print(f"  Response length: {len(response_text)} characters")
                print(f"  Preview: {response_text[:200]}...")
                
                # Check for specific indicators
                if 'ocr.pdf' in response_text.lower():
                    print("  ✅ Found reference to ocr.pdf!")
                if 'table' in response_text.lower():
                    print("  ✅ Found table content!")
                if len(response_text) > 50:  # Meaningful response
                    print("  ✅ Got meaningful response!")
            else:
                print(f"  Unexpected result format: {type(results)}")
        else:
            print(f'❌ Search failed: {search_response.text}')
            
else:
    print('❌ Login failed')