online_sys/frontend_大健康/merge_and_clean_questions.py

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

import json
import re

print("合并面试题到单个卡片并删除序号...")

# 备份当前文件
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
    content = f.read()

with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/src/mocks/resumeInterviewMock.js.backup_before_final_merge', 'w', encoding='utf-8') as f:
    f.write(content)

# 提取industries数组的内容
industries_pattern = r'const industries = (\[.*?\]);'
industries_match = re.search(industries_pattern, content, re.DOTALL)

if not industries_match:
    print("❌ 无法找到industries数据")
    exit(1)

# 将JavaScript转换为JSON格式
industries_js = industries_match.group(1)
# 处理JavaScript对象到JSON的转换
industries_js = re.sub(r'(\w+):', r'"\1":', industries_js)  # 添加引号到键
industries_js = re.sub(r':\s*"([^"]*)"', lambda m: ': "' + m.group(1).replace('\n', '\\n') + '"', industries_js)

# 解析为Python对象
mock_data = None
try:
    industries = json.loads(industries_js)
except json.JSONDecodeError as e:
    # 如果JSON解析失败，尝试使用eval（注意：实际生产环境应避免使用eval）
    print(f"JSON解析失败: {e}")
    print("尝试使用备用方法...")

    # 从文件中直接提取数据结构
    exec_globals = {}
    exec_locals = {}

    # 创建一个临时的JavaScript到Python转换
    temp_content = content.replace('const industries = ', 'industries = ')
    temp_content = temp_content.replace('const resumeTemplates = ', 'resumeTemplates = ')
    temp_content = temp_content.replace('export ', '# export ')

    # 提取industries部分
    start_idx = temp_content.find('industries = [')
    end_idx = temp_content.find('];', start_idx) + 2
    industries_str = temp_content[start_idx:end_idx]

    # 尝试通过更安全的方式解析
    # 先读取备份文件看看正确的格式
    with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/health_mock_data.json', 'r', encoding='utf-8') as f:
        mock_data = json.load(f)
        industries = mock_data['industries']

print(f"找到 {len(industries)} 个岗位群")

# 处理每个岗位群的面试题
for industry in industries:
    if 'questions' in industry and isinstance(industry['questions'], list) and len(industry['questions']) > 1:
        print(f"处理 {industry['name']} 的面试题...")

        # 收集所有子问题
        all_sub_questions = []
        question_counter = 1

        # 遍历所有面试题卡片
        for question_card in industry['questions']:
            if 'subQuestions' in question_card:
                for sub_q in question_card['subQuestions']:
                    # 删除问题开头的序号
                    question_text = sub_q['question']
                    question_text = re.sub(r'^\d+\.\s*', '', question_text)

                    all_sub_questions.append({
                        'id': f'q{question_counter}',
                        'question': question_text,
                        'answer': sub_q['answer']
                    })
                    question_counter += 1

        # 创建单个合并的卡片
        merged_card = {
            'id': f"{industry['id']}_q1",
            'question': f"{industry['name']}岗位群面试题",
            'subQuestions': all_sub_questions
        }

        # 替换为单个卡片
        industry['questions'] = [merged_card]
        print(f"✓ {industry['name']}: 合并为1个卡片，包含 {len(all_sub_questions)} 个问题")

    elif 'questions' in industry and len(industry['questions']) == 1:
        # 如果已经是单个卡片，只需要删除序号
        if 'subQuestions' in industry['questions'][0]:
            for sub_q in industry['questions'][0]['subQuestions']:
                sub_q['question'] = re.sub(r'^\d+\.\s*', '', sub_q['question'])
            print(f"✓ {industry['name']}: 已是单卡片，删除了序号")

# 提取resumeTemplates
resumeTemplates_pattern = r'const resumeTemplates = (\{.*?\});'
resumeTemplates_match = re.search(resumeTemplates_pattern, content, re.DOTALL)

if resumeTemplates_match:
    resumeTemplates_js = resumeTemplates_match.group(1)
    # 类似处理，这里直接从mock_data获取
    if mock_data:
        resumeTemplates = mock_data['resumeTemplates']
    else:
        # 如果没有mock_data，从health_mock_data.json读取
        with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/health_mock_data.json', 'r', encoding='utf-8') as f:
            temp_data = json.load(f)
            resumeTemplates = temp_data['resumeTemplates']
else:
    resumeTemplates = {}

# 转换为JavaScript格式
industries_js = json.dumps(industries, ensure_ascii=False, indent=2)
resumeTemplates_js = json.dumps(resumeTemplates, ensure_ascii=False, indent=2)

# 创建新的Mock文件内容
new_content = f"""// 简历与面试题Mock数据

// 岗位群列表
const industries = {industries_js};

// 简历模板数据
const resumeTemplates = {resumeTemplates_js};

// 我的简历数据
const myResume = {{
    personalInfo: {{
      name: "张三",
      phone: "138****8888",
      email: "zhangsan@example.com",
      age: 25,
      education: "苏州信息职业技术学院 2020.9-2023.6",
      experience: "2年",
      location: "北京"
    }},
    workExperience: [
      {{
        company: "某健康管理公司",
        position: "健康管理师",
        duration: "2022.03-2024.01",
        description: "负责健康评估和健康管理方案制定工作"
      }}
    ],
    skills: ["健康评估", "健康管理", "数据分析", "客户服务"],
    projects: [
      {{
        name: "企业员工健康管理项目",
        role: "健康管理师",
        duration: "2023.05-2023.12",
        description: "负责企业员工的健康评估和管理方案制定"
      }}
    ]
  }};

// 获取页面mock数据的函数
export function getMockPageData() {{
  return resumeInterviewMockData;
}}

// 导出合并的数据
export const resumeInterviewMockData = {{
  industries,
  resumeTemplates,
  myResume
}};
"""

# 写入新内容
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
    f.write(new_content)

# 同时更新JSON文件以保持一致
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/health_mock_data_full.json', 'w', encoding='utf-8') as f:
    json.dump({'industries': industries, 'resumeTemplates': resumeTemplates}, f, ensure_ascii=False, indent=2)

print("\n✓ 面试题合并完成!")
print("  - 每个岗位群只有一个面试题卡片")
print("  - 删除了所有题目前的序号")
print("  - 原文件已备份为 resumeInterviewMock.js.backup_before_final_merge")
print("  - 同步更新了 health_mock_data_full.json")