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

import json
import re

def extract_energy_projects():
    """
    从学生完成的项目.json中提取能源产业的项目数据
    """
    with open("网页未导入数据/学生完成的项目.json", 'r', encoding='utf-8') as f:
        all_projects = json.load(f)

    # 筛选能源产业的项目
    energy_projects = [p for p in all_projects if p.get("所属就业管家") == "能源"]

    print(f"📊 找到 {len(energy_projects)} 个能源产业单元的项目")

    # 转换为myProjectsData格式
    my_projects_data = []
    for project in energy_projects:
        unit_name = project.get("单元名称查询", "")
        ai_projects = project.get("AI项目名称", [])

        # 清理项目名称（去除序号前缀）
        cleaned_projects = []
        for proj in ai_projects:
            # 去除"1."或"2."等前缀
            cleaned = re.sub(r'^\d+\.\s*', '', proj)
            if cleaned:
                cleaned_projects.append(cleaned)

        if unit_name and cleaned_projects:
            my_projects_data.append({
                "unitName": unit_name,
                "projects": cleaned_projects
            })

    return my_projects_data

def generate_js_code(my_projects_data):
    """
    生成JavaScript代码
    """
    js_code = "// 我的项目库数据\nconst myProjectsData = [\n"

    for idx, unit in enumerate(my_projects_data):
        js_code += '  {\n'
        js_code += f'    "unitName": "{unit["unitName"]}",\n'
        js_code += '    "projects": [\n'

        for j, proj in enumerate(unit["projects"]):
            # 转义双引号
            proj_escaped = proj.replace('"', '\\"')
            js_code += f'      "{proj_escaped}"'
            if j < len(unit["projects"]) - 1:
                js_code += ','
            js_code += '\n'

        js_code += '    ]\n'
        js_code += '  }'
        if idx < len(my_projects_data) - 1:
            js_code += ','
        js_code += '\n'

    js_code += '];\n'

    return js_code

def update_project_library_page():
    """
    更新项目库页面组件中的myProjectsData
    """
    # 提取能源项目数据
    energy_projects = extract_energy_projects()

    # 生成新的JS代码
    new_js_code = generate_js_code(energy_projects)

    # 读取现有组件文件
    with open("src/pages/ProjectLibraryPage/index.jsx", 'r', encoding='utf-8') as f:
        content = f.read()

    # 查找并替换myProjectsData部分
    pattern = r'// 我的项目库数据\nconst myProjectsData = \[[\s\S]*?\];\n'

    if re.search(pattern, content):
        updated_content = re.sub(pattern, new_js_code, content)

        # 写入更新后的内容
        with open("src/pages/ProjectLibraryPage/index.jsx", 'w', encoding='utf-8') as f:
            f.write(updated_content)

        print("✅ 成功更新myProjectsData数据")

        # 显示统计信息
        print(f"\n📋 更新统计：")
        print(f"  - 单元数量：{len(energy_projects)}")
        total_projects = sum(len(unit['projects']) for unit in energy_projects)
        print(f"  - 项目总数：{total_projects}")

        # 显示前3个单元的信息
        print("\n📚 前3个单元示例：")
        for unit in energy_projects[:3]:
            print(f"  • {unit['unitName']}")
            for proj in unit['projects']:
                print(f"    - {proj}")
    else:
        print("❌ 未找到myProjectsData数据块")

if __name__ == "__main__":
    update_project_library_page()