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

import json
import re

def parse_interview_questions(content):
    """解析面试题内容为结构化数据"""
    questions = []

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

    question_id = 1
    for i in range(1, len(sections), 2):
        if i >= len(sections):
            break

        section_title = sections[i].strip()
        section_content = sections[i + 1] if i + 1 < len(sections) else ""

        # 提取每个问题
        question_blocks = re.split(r'\n\d+\.\s+', section_content)

        for j, block in enumerate(question_blocks[1:], 1):  # 跳过第一个空块
            lines = block.strip().split('\n')
            if not lines:
                continue

            question_text = lines[0].strip()

            # 查找答案
            answer_text = ""
            for k, line in enumerate(lines):
                if '示例答案' in line or '答案' in line:
                    # 获取答案内容
                    answer_lines = []
                    for answer_line in lines[k+1:]:
                        answer_line = answer_line.strip()
                        if answer_line and not answer_line.startswith('示例答案'):
                            if re.match(r'^\d+\.', answer_line):
                                break
                            answer_lines.append(answer_line)
                    answer_text = ' '.join(answer_lines)
                    break

            if question_text and answer_text:
                questions.append({
                    "id": f"q{question_id}",
                    "question": question_text,
                    "answer": answer_text
                })
                question_id += 1

    return questions

def main():
    # 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)

    # 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()

    # 创建岗位群到面试题的映射
    industry_questions = {}
    for item in health_data:
        industry = item.get('简历岗位群', '')
        interview_content = item.get('面试题内容', '')

        if industry and interview_content and industry not in industry_questions:
            questions = parse_interview_questions(interview_content)
            if questions:
                # 按类别分组
                category_questions = {}
                current_category = "综合面试题"

                for q in questions:
                    if '岗位理解' in q['question']:
                        current_category = "岗位理解类问题"
                    elif '实践经验' in q['question'] or '案例' in q['question']:
                        current_category = "实践经验类问题"
                    elif '客户服务' in q['question'] or '客户' in q['question']:
                        current_category = "客户服务类问题"
                    elif '市场' in q['question'] or '趋势' in q['question']:
                        current_category = "市场与未来趋势类问题"

                    if current_category not in category_questions:
                        category_questions[current_category] = []
                    category_questions[current_category].append(q)

                # 构建questions数组
                questions_array = []
                cat_id = 1
                for category, cat_questions in category_questions.items():
                    questions_array.append({
                        "id": f"group_q{cat_id}",
                        "question": category,
                        "subQuestions": cat_questions
                    })
                    cat_id += 1

                industry_questions[industry] = questions_array

    # 映射岗位群名称到ID
    industry_mapping = {
        '健康管理': 'health_1',
        '健康检查': 'health_2',
        '康复治疗': 'health_3',
        '慢性病管理': 'health_4',
        '轻医美': 'health_5',
        '心理健康': 'health_6',
        '社群运营': 'health_7',
        '药品供应链管理': 'health_8',
        '药品生产': 'health_9',
        '药品质量检测': 'health_10',
        '药物研发': 'health_11'
    }

    # 为每个岗位群添加questions字段
    updates = 0
    for orig_name, industry_id in industry_mapping.items():
        if orig_name in industry_questions:
            questions = industry_questions[orig_name]

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

            # 查找对应的岗位群并添加questions字段
            # 使用更精确的模式：在positions数组结束后添加questions
            pattern = rf'("id":\s*"{industry_id}"[^{{]*?"positions":\s*\[[^\]]*?\])\s*(\}})'

            # 添加questions字段
            replacement = rf'\1,\n    "questions": {questions_json}\n  \2'

            new_content, count = re.subn(pattern, replacement, content, flags=re.DOTALL)
            if count > 0:
                content = new_content
                updates += 1
                print(f"✓ 为 {orig_name} ({industry_id}) 添加了 {len(questions)} 个问题分类")

    # 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(content)

    print(f"\n完成！更新了 {updates} 个岗位群的面试题")

if __name__ == "__main__":
    main()