#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import json
import re
import datetime
import shutil

def clean_interview_questions():
    """
    清理面试题数据，删除difficulty和tags字段
    """
    mock_file = "src/mocks/resumeInterviewMock.js"

    # 备份文件
    backup_path = f"{mock_file}.backup_{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}"
    shutil.copy(mock_file, backup_path)
    print(f"✅ 已备份文件到：{backup_path}")

    # 读取文件内容
    with open(mock_file, 'r', encoding='utf-8') as f:
        content = f.read()

    # 使用正则表达式删除difficulty和tags字段
    # 删除difficulty行
    content = re.sub(r',?\s*"difficulty":\s*"[^"]*"', '', content)

    # 删除tags字段（包括数组内容）
    content = re.sub(r',?\s*"tags":\s*\[[^\]]*\]', '', content)

    # 清理多余的逗号（如果answer后面有逗号但后面没有其他字段）
    content = re.sub(r'("answer":\s*"[^"]*"),\s*\n\s*}', r'\1\n                }', content)

    # 清理多余的空行
    content = re.sub(r'\n\s*\n\s*\n', '\n', content)

    # 写回文件
    with open(mock_file, 'w', encoding='utf-8') as f:
        f.write(content)

    print("✅ 成功清理面试题数据")

    # 验证清理结果
    with open(mock_file, 'r', encoding='utf-8') as f:
        check_content = f.read()

    difficulty_count = len(re.findall(r'"difficulty"', check_content))
    tags_count = len(re.findall(r'"tags"', check_content))

    if difficulty_count == 0 and tags_count == 0:
        print("✅ 验证成功：已完全删除difficulty和tags字段")
    else:
        print(f"⚠️ 仍有残留：difficulty出现{difficulty_count}次，tags出现{tags_count}次")

if __name__ == "__main__":
    clean_interview_questions()