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

import json
import re

# 读取大健康岗位简历数据
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/网页未导入数据/大健康产业/大健康岗位简历.json', 'r', encoding='utf-8') as f:
    health_data = json.load(f)

# 获取药物研发的面试题
drug_questions = []
for item in health_data:
    if item.get('简历岗位群') == '药物研发':
        interview_content = item.get('面试题内容', '')
        if interview_content and not drug_questions:  # 只取第一个
            # 提取问题
            content = interview_content

            # 删除"判断题："前缀
            content = re.sub(r'判断题[：:]?\s*', '', content)

            # 分割成类别
            sections = re.split(r'\n# ([一二三四五六七八九十]+、[^#\n]+)', content)

            questions = []
            if len(sections) > 1:
                for i in range(1, len(sections), 2):
                    if i+1 >= len(sections):
                        break

                    category_title = sections[i].strip()
                    category_content = sections[i+1]

                    # 提取问题和答案
                    sub_questions = []
                    lines = category_content.split('\n')

                    current_question = None
                    current_answer = []
                    in_answer = False

                    for line in lines:
                        line = line.strip()

                        # 检查是否是新问题
                        question_match = re.match(r'^(\d+)\.\s*(.+)$', line)
                        if question_match:
                            # 保存上一个问题
                            if current_question and current_answer:
                                answer_text = ' '.join(current_answer).strip()
                                answer_text = re.sub(r'^(示例)?答案[：:]?\s*', '', answer_text)
                                if answer_text:
                                    sub_questions.append({
                                        "question": current_question,
                                        "answer": answer_text
                                    })

                            # 开始新问题
                            current_question = question_match.group(2).strip()
                            current_answer = []
                            in_answer = False

                        # 检查是否是答案开始
                        elif '答案' in line or '示例答案' in line:
                            in_answer = True
                            answer_part = re.sub(r'^(示例)?答案[：:]?\s*', '', line).strip()
                            if answer_part:
                                current_answer.append(answer_part)

                        # 收集答案内容
                        elif in_answer and line and not re.match(r'^#', line):
                            current_answer.append(line)

                    # 保存最后一个问题
                    if current_question and current_answer:
                        answer_text = ' '.join(current_answer).strip()
                        answer_text = re.sub(r'^(示例)?答案[：:]?\s*', '', answer_text)
                        if answer_text:
                            sub_questions.append({
                                "question": current_question,
                                "answer": answer_text
                            })

                    if sub_questions:
                        questions.append({
                            "category": category_title,
                            "questions": sub_questions
                        })

            drug_questions = questions
            break

# 转换为前端格式
questions_array = []
total_q = 0
for i, cat in enumerate(drug_questions, 1):
    sub_q_array = []
    for j, q in enumerate(cat['questions'], 1):
        total_q += 1
        sub_q_array.append({
            "id": f"q{total_q}",
            "question": q['question'],
            "answer": q['answer']
        })

    questions_array.append({
        "id": f"group_q{i}",
        "question": cat['category'],
        "subQuestions": sub_q_array
    })

# 生成JSON字符串
questions_json = json.dumps(questions_array, ensure_ascii=False, indent=2)

# 读取Mock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()

# 在health_11的positions数组后添加questions
# 找到最后一个position的结束
pattern = r'("id":\s*"health_11_4"[^}]*?"requirements":\s*\[[^\]]*?\]\s*\}\]\s*\})'

match = re.search(pattern, content, re.DOTALL)
if match:
    end_pos = match.end()

    # 在这个位置插入questions
    # 先找到']'的位置（positions数组的结束）
    positions_end = content.rfind(']', 0, end_pos)

    # 构建新的内容
    new_content = content[:positions_end] + '],\n    "questions": ' + questions_json + '\n  ' + content[end_pos:]

    # 写回文件
    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)

    print(f"✓ 已添加药物研发的 {len(questions_array)} 个分类，共 {total_q} 个面试题")
else:
    print("未找到health_11的结构")