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

import json

def extract_position_levels():
    """从大健康岗位简历.json中提取岗位等级映射"""
    
    # 读取大健康岗位简历数据
    with open('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:
        resume_data = json.load(f)
    
    # 提取岗位名称和等级的映射
    position_level_map = {}
    
    for item in resume_data:
        position_name = item.get('岗位名称', '')
        level = item.get('岗位等级标签', '')
        
        if position_name and level:
            position_level_map[position_name] = level
    
    # 打印映射关系
    print("大健康产业岗位等级映射：")
    print("=" * 50)
    
    # 按等级分组显示
    levels = {}
    for position, level in position_level_map.items():
        if level not in levels:
            levels[level] = []
        levels[level].append(position)
    
    for level in ['基础岗', '技术骨干岗', '储备干部岗']:
        if level in levels:
            print(f"\n{level}（{len(levels[level])}个岗位）：")
            for position in sorted(levels[level]):
                print(f"  - {position}")
    
    # 保存映射为JSON文件
    with open('position_level_mapping.json', 'w', encoding='utf-8') as f:
        json.dump(position_level_map, f, ensure_ascii=False, indent=2)
    
    print("\n\n岗位等级映射已保存到 position_level_mapping.json")
    print(f"总计 {len(position_level_map)} 个岗位")
    
    return position_level_map

if __name__ == "__main__":
    mapping = extract_position_levels()