import json
import os

def extract_questions():
    # Attempt to find the correct input file.
    # The user specifically asked for 'financial_kb_200.json', but 
    # 'financial_kb_2000.json' was found in the project.
    
    # We will prioritize 'financial_kb_2000.json' as it exists.
    input_file_path = os.path.join(os.path.dirname(__file__), 'financial_kb_2000.json')
    output_file_path = os.path.join(os.path.dirname(__file__), 'kb_questions.txt')

    if not os.path.exists(input_file_path):
        print(f"File {input_file_path} not found. Trying local path...")
        input_file_path = 'src/data/financial_kb_2000.json'
        output_file_path = 'src/data/kb_questions.txt'

    if not os.path.exists(input_file_path):
        print(f"Error: {input_file_path} not found.")
        return

    try:
        with open(input_file_path, 'r', encoding='utf-8') as f:
            data = json.load(f)

        # Handle both list of dicts or a single dict (if the structure varies)
        if isinstance(data, list):
            questions = [item.get('question') for item in data if isinstance(item, dict) and 'question' in item]
        elif isinstance(data, dict):
            # If the JSON is a single object with a questions list or something similar
            questions = [data.get('question')] if 'question' in data else []
        else:
            questions = []

        # Remove None values
        questions = [q for q in questions if q]

        with open(output_file_path, 'w', encoding='utf-8') as f:
            for q in questions:
                f.write(f"{q}\n")

        print(f"Successfully extracted {len(questions)} questions to {output_file_path}")

    except Exception as e:
        print(f"An error occurred: {e}")

if __name__ == "__main__":
    extract_questions()