Files
railseek6/debug_webui_ocr.py

62 lines
2.1 KiB
Python

#!/usr/bin/env python3
"""
Debug script to test Web UI OCR processor
"""
import os
import sys
import logging
# Set up logging to see what's happening
logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)
def test_webui_processor():
"""Test the processor as it would run in Web UI"""
print("🧪 TESTING WEB UI OCR PROCESSOR")
print("=" * 50)
# Simulate Web UI environment
print("1. Adding workspace directory to sys.path...")
workspace_dir = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
print(f" Workspace dir: {workspace_dir}")
if workspace_dir not in sys.path:
sys.path.insert(0, workspace_dir)
print(" ✅ Added workspace to sys.path")
print("2. Importing simple_ocr_processor...")
try:
from simple_ocr_processor import get_simple_ocr_processor
print(" ✅ Import successful")
print("3. Initializing OCR processor...")
processor = get_simple_ocr_processor()
print(f" Processor available: {processor.available}")
print(f" Processor type: {type(processor)}")
if hasattr(processor, 'ocr_engine'):
print(f" OCR Engine type: {type(processor.ocr_engine)}")
else:
print(" ❌ No OCR engine found!")
# Test with an image
test_image = "extracted_images/image1.png"
if os.path.exists(test_image):
print(f"4. Testing OCR on {test_image}...")
result = processor.extract_text_from_image(test_image)
print(f" OCR Result: {len(result['text'])} chars, confidence: {result['confidence']:.3f}")
if result['text']:
print(f" Text: {result['text'][:200]}...")
else:
print(" No text extracted")
else:
print(f"❌ Test image not found: {test_image}")
except Exception as e:
print(f"❌ Error: {e}")
import traceback
traceback.print_exc()
if __name__ == "__main__":
test_webui_processor()