#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
清理混合的数据结构，移除所有嵌套的subQuestions结构
只保留扁平的questions结构
"""

import re

def clean_mixed_structures():
    """清理混合结构"""
    try:
        # 读取文件
        with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
            content = f.read()

        print("开始清理混合结构...")

        # 1. 移除所有包含subQuestions的问题组
        # 匹配从 { "id": "group_q..." 开始到对应的 } 结束的完整问题组
        content = re.sub(
            r',?\s*\{\s*"id":\s*"group_q\d+"[\s\S]*?"subQuestions":\s*\[[\s\S]*?\]\s*\}',
            '',
            content,
            flags=re.DOTALL
        )

        # 2. 清理残留的多余逗号和空白
        content = re.sub(r',\s*,', ',', content)
        content = re.sub(r'\[\s*,', '[', content)
        content = re.sub(r',\s*\]', ']', content)

        # 3. 修复空的questions数组
        content = re.sub(r'"questions":\s*\[\s*\]', '"questions": []', content)

        # 4. 清理孤立的逗号和括号
        content = re.sub(r'\s*\]\s*\}\s*\]\s*\},', '\n      }', content)

        # 5. 修复岗位间的连接
        content = re.sub(r'(\s+\}\s*)\n\s+\{\s*("id":\s*"health_)', r'\1,\n      {\n        \2', content)

        print("清理完成，写入文件...")

        # 写回文件
        with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
            f.write(content)

        print("混合结构清理完成！")
        return True

    except Exception as e:
        print(f"清理失败: {e}")
        import traceback
        traceback.print_exc()
        return False

def main():
    clean_mixed_structures()

if __name__ == "__main__":
    main()