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

import json
from collections import defaultdict

def extract_job_groups():
    """
    从能源岗位简历.json提取所有岗位群并生成面试题数据结构
    """
    # 读取能源岗位简历数据
    with open("网页未导入数据/能源产业/能源岗位简历.json", 'r', encoding='utf-8') as f:
        energy_jobs = json.load(f)

    # 按岗位群分组
    job_groups = defaultdict(list)
    for job in energy_jobs:
        group_name = job.get("简历岗位群", "")
        if group_name:
            job_groups[group_name].append(job)

    # 生成industries数据结构
    industries = []
    group_id = 1

    for group_name, jobs in job_groups.items():
        industry = {
            "id": f"energy_{group_id}",
            "name": group_name,
            "positions": [],
            "questions": [
                {
                    "id": f"group_q{group_id}",
                    "question": f"# {group_name}面试题",
                    "subQuestions": []
                }
            ]
        }

        # 添加该岗位群下的所有岗位
        pos_id = 1
        for job in jobs:
            position = {
                "id": f"energy_{group_id}_{pos_id}",
                "title": job["岗位名称"],
                "level": job.get("岗位等级标签", "基础岗"),
                "avatar": job.get("岗位头像", ""),
                "department": group_name,
                "type": "全职",
                "experience": "1-3年",
                "education": "大专",
                "salary": "8-15K",
                "location": "北京",
                "updateTime": "2024-01-20",
                "description": f"负责{job['岗位名称']}相关工作",
                "requirements": []
            }
            industry["positions"].append(position)
            pos_id += 1

        industries.append(industry)
        group_id += 1

    # 输出统计信息
    print(f"✅ 找到 {len(job_groups)} 个岗位群")
    print("📋 岗位群列表：")
    for i, (group_name, jobs) in enumerate(job_groups.items(), 1):
        print(f"   {i}. {group_name} ({len(jobs)}个岗位)")

    # 保存到文件
    with open("energy_industries_data.js", 'w', encoding='utf-8') as f:
        f.write("// 能源产业岗位群数据\n")
        f.write("const industries = ")
        f.write(json.dumps(industries, ensure_ascii=False, indent=2))
        f.write(";\n\nexport default industries;")

    print(f"\n✅ 数据已保存到 energy_industries_data.js")

    return industries

if __name__ == "__main__":
    extract_job_groups()