ALL-teach_sys/frontend_能源/update_modified_resumes.py

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

import json
import os
import datetime
import shutil

def read_modified_resumes():
    """读取所有修改版简历文件"""
    modified_resumes = {}
    folder_path = "网页未导入数据/能源产业/能源修改版简历"
    
    # 获取所有.md文件
    for filename in os.listdir(folder_path):
        if filename.endswith('.md'):
            position_name = filename.replace('.md', '')
            file_path = os.path.join(folder_path, filename)
            
            with open(file_path, 'r', encoding='utf-8') as f:
                content = f.read()
                modified_resumes[position_name] = content
    
    return modified_resumes

def update_mock_file_with_modified():
    """更新Mock文件，添加修改版简历内容"""
    
    mock_file = "src/mocks/resumeInterviewMock.js"
    
    # 备份文件
    backup_path = f"{mock_file}.backup_{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}"
    shutil.copy(mock_file, backup_path)
    print(f"✅ 已备份文件到：{backup_path}")
    
    # 读取修改版简历
    modified_resumes = read_modified_resumes()
    print(f"📚 找到 {len(modified_resumes)} 个修改版简历文件")
    
    # 读取当前mock文件
    with open(mock_file, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # 更新resumeTemplates中对应岗位的modified字段
    import re
    
    updated_count = 0
    for position_name, resume_content in modified_resumes.items():
        print(f"  处理岗位: {position_name}")
        
        # 转义特殊字符用于正则表达式
        escaped_position = re.escape(position_name)
        
        # 查找该岗位在resumeTemplates中的位置
        # 模式：查找 "position": "岗位名称" 后的 content 对象
        pattern = rf'("position":\s*"{escaped_position}"[^{{]*?"content":\s*{{[^}}]*?"original":[^,]*?,)(\s*"modified":\s*)"[^"]*"'
        
        # 准备替换的内容（转义JSON字符串）
        escaped_content = json.dumps(resume_content, ensure_ascii=False)
        
        # 执行替换
        new_content, count = re.subn(
            pattern,
            rf'\1\2{escaped_content}',
            content
        )
        
        if count > 0:
            content = new_content
            updated_count += 1
            print(f"    ✅ 已更新")
        else:
            # 如果第一种模式失败，尝试另一种模式（没有modified字段的情况）
            pattern2 = rf'("position":\s*"{escaped_position}"[^{{]*?"content":\s*{{[^}}]*?"original":[^}}]*?)(}})'
            
            # 添加modified字段
            replacement = rf'\1,\n        "modified": {escaped_content}\2'
            new_content, count = re.subn(pattern2, replacement, content)
            
            if count > 0:
                content = new_content
                updated_count += 1
                print(f"    ✅ 已添加modified字段")
            else:
                print(f"    ⚠️  未找到匹配位置")
    
    # 写回文件
    with open(mock_file, 'w', encoding='utf-8') as f:
        f.write(content)
    
    print(f"\n✅ 成功更新 {updated_count}/{len(modified_resumes)} 个岗位的修改版简历")
    
    # 验证更新
    verify_updates(mock_file, modified_resumes.keys())

def verify_updates(mock_file, position_names):
    """验证更新是否成功"""
    with open(mock_file, 'r', encoding='utf-8') as f:
        content = f.read()
    
    print("\n📊 验证结果：")
    for position_name in position_names:
        # 检查是否包含该岗位的modified内容
        pattern = f'"position": "{position_name}"'
        if pattern in content:
            # 进一步检查是否有modified字段
            # 查找该岗位后面的modified字段
            start_idx = content.find(pattern)
            if start_idx > 0:
                # 查找该岗位content对象的范围（简化检查）
                end_idx = content.find('"position":', start_idx + len(pattern))
                if end_idx < 0:
                    end_idx = start_idx + 2000  # 如果是最后一个，取后面2000字符
                
                section = content[start_idx:end_idx]
                if '"modified":' in section and position_name in section:
                    print(f"  ✅ {position_name}: 已包含修改版")
                else:
                    print(f"  ❌ {position_name}: 未包含修改版")
        else:
            print(f"  ⚠️  {position_name}: 未找到该岗位")

if __name__ == "__main__":
    update_mock_file_with_modified()