#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
面试题数据换行符清理脚本 - 最终版本
直接处理JS文件中的字符串，清理\\n换行符
"""

import re
import shutil
from datetime import datetime

def clean_escaped_newlines_in_js():
    """
    清理JS文件中的转义换行符\\n
    """
    file_path = "src/mocks/resumeInterviewMock.js"
    
    # 创建备份
    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
    backup_path = f"{file_path}.backup_final_newlines_{timestamp}"
    shutil.copy2(file_path, backup_path)
    print(f"📦 已创建备份: {backup_path}")
    
    try:
        # 读取文件
        with open(file_path, 'r', encoding='utf-8') as f:
            content = f.read()
        
        # 统计原始\\n数量
        original_count = content.count('\\\\n')
        print(f"📊 发现 {original_count} 个转义换行符(\\\\n)")
        
        # 处理转义的换行符：\\n -> 实际换行符
        # 但要保持在JSON字符串中的格式正确
        processed_content = content
        
        # 查找并处理answer字段中的\\n
        def replace_newlines_in_answers(match):
            full_match = match.group(0)
            answer_content = match.group(1)
            
            # 将\\n替换为实际换行符，然后重新转义为JSON格式
            cleaned = answer_content.replace('\\\\n', '\n')
            # 移除多余连续换行
            cleaned = re.sub(r'\n{3,}', '\n\n', cleaned)
            # 清理首尾空白
            cleaned = cleaned.strip()
            # 重新转义为JSON格式的换行符
            cleaned = cleaned.replace('\n', '\\n')
            
            return f'"answer": "{cleaned}"'
        
        # 使用正则表达式找到所有answer字段并处理
        answer_pattern = r'"answer":\s*"([^"]*(?:\\.[^"]*)*)"'
        processed_content = re.sub(answer_pattern, replace_newlines_in_answers, processed_content, flags=re.DOTALL)
        
        # 统计处理后的\\n数量
        final_count = processed_content.count('\\\\n')
        processed_fields = original_count - final_count
        
        # 写入文件
        with open(file_path, 'w', encoding='utf-8') as f:
            f.write(processed_content)
        
        print(f"📊 处理统计:")
        print(f"   - 原始\\\\n数量: {original_count}")
        print(f"   - 处理后\\\\n数量: {final_count}")
        print(f"   - 已处理字段数: {processed_fields}")
        print(f"✅ 已更新 {file_path}")
        
        # 验证文件语法
        import subprocess
        try:
            result = subprocess.run(['node', '-c', file_path], capture_output=True, text=True)
            if result.returncode == 0:
                print("✅ JavaScript语法验证通过")
            else:
                print(f"❌ JavaScript语法验证失败: {result.stderr}")
                # 恢复备份
                shutil.copy2(backup_path, file_path)
                print("🔄 已恢复原始文件")
        except Exception as e:
            print(f"⚠️ 无法验证JavaScript语法: {e}")
            
    except Exception as e:
        print(f"❌ 处理失败: {e}")
        # 恢复备份
        shutil.copy2(backup_path, file_path)
        print("🔄 已恢复原始文件")

if __name__ == "__main__":
    print("🚀 开始清理面试题中的换行符...")
    clean_escaped_newlines_in_js()
    print("🎉 处理完成！")