import os
import re
from pathlib import Path

def search_in_file(file_path):
    try:
        with open(file_path, 'r', encoding='utf-8') as f:
            content = f.read()
            s3_matches = re.finditer(r'["\']s3_[^"\']*["\']', content)
            dataset_matches = re.finditer(r'dataset-cached|dataset_cached', content)
            
            results = []
            for match in s3_matches:
                results.append(f"S3 config: {match.group()}")
            for match in dataset_matches:
                results.append(f"Dataset cached: {match.group()}")
                
            if results:
                print(f"\nIn {file_path}:")
                for result in results:
                    print(f"  {result}")
    except Exception as e:
        print(f"Error reading file {file_path}: {e}")

def search_files():
    root_dir = Path(__file__).parent.parent
    for path in root_dir.rglob('*.py'):
        if 'venv' not in str(path) and '.git' not in str(path):
            search_in_file(path)

if __name__ == '__main__':
    search_files()