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

import json
from collections import defaultdict

def extract_positions_by_batch():
    # 读取土木水利岗位简历数据
    with open('网页未导入数据/土木水利产业/土木水利岗位简历.json', 'r', encoding='utf-8') as f:
        civil_positions_data = json.load(f)

    # 按批次分类
    batch_positions = {
        "第一批次": [],
        "第二批次": [],
        "第三批次": []
    }

    # 提取岗位名称并按批次分类
    for item in civil_positions_data:
        position_name = item.get("岗位名称", "")
        batch = item.get("批次", "")

        if batch in batch_positions and position_name:
            batch_positions[batch].append(position_name)

    # 输出结果
    print("土木水利岗位按批次分类：\n")

    # 第一批次
    print(f"第一批次 ({len(batch_positions['第一批次'])} 个岗位):")
    for pos in batch_positions['第一批次']:
        print(f"  - {pos}")

    # 第二批次
    print(f"\n第二批次 ({len(batch_positions['第二批次'])} 个岗位):")
    for pos in batch_positions['第二批次']:
        print(f"  - {pos}")

    # 第三批次
    print(f"\n第三批次 ({len(batch_positions['第三批次'])} 个岗位):")
    for pos in batch_positions['第三批次']:
        print(f"  - {pos}")

    # 生成JavaScript格式的输出
    print("\n\n=== JavaScript格式输出 ===\n")

    print("const initialBatchPositions = {")
    print(f'  batch1: {json.dumps(batch_positions["第一批次"], ensure_ascii=False, indent=4).replace("    ", "    ")},')
    print(f'  batch2: {json.dumps(batch_positions["第二批次"], ensure_ascii=False, indent=4).replace("    ", "    ")},')
    print(f'  batch3: {json.dumps(batch_positions["第三批次"], ensure_ascii=False, indent=4).replace("    ", "    ")}')
    print("};")

if __name__ == "__main__":
    extract_positions_by_batch()