#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
清理修改版简历中的删除线内容和加粗符号
- 删除~~删除线内容~~（包括符号和内容）
- 保留**加粗内容**（删除符号，保留内容）
"""

import re
import shutil
from datetime import datetime

def clean_resume_formatting():
    """清理修改版简历格式"""
    
    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_clean_formatting_{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()
        
        print("🚀 开始清理修改版简历格式...")
        
        # 统计原始符号数量
        strikethrough_count = content.count('~~')
        bold_count = content.count('**')
        print(f"📊 发现删除线符号: {strikethrough_count//2} 对")
        print(f"📊 发现加粗符号: {bold_count//2} 对")
        
        # 定义清理函数
        def clean_content_field(match):
            """清理content字段中的modified内容"""
            full_match = match.group(0)
            modified_content = match.group(1)
            
            # 1. 删除删除线内容（包括~~符号和其中的内容~~）
            cleaned = re.sub(r'~~[^~]*~~', '', modified_content)
            
            # 2. 删除加粗符号（保留**中的内容**）
            cleaned = re.sub(r'\*\*([^*]*)\*\*', r'\1', cleaned)
            
            # 3. 清理多余的空格和标点符号
            # 处理可能产生的多余逗号、分号等
            cleaned = re.sub(r'[，、；]\s*[，、；]', '，', cleaned)
            cleaned = re.sub(r'[，、；]\s*$', '', cleaned, flags=re.MULTILINE)
            cleaned = re.sub(r'^\s*[，、；]', '', cleaned, flags=re.MULTILINE)
            
            # 4. 清理多余的空白行
            cleaned = re.sub(r'\n\s*\n\s*\n', '\n\n', cleaned)
            
            return f'"modified": "{cleaned}"'
        
        # 使用正则表达式找到所有modified字段并清理
        modified_pattern = r'"modified":\s*"([^"]*(?:\\.[^"]*)*)"'
        processed_content = re.sub(modified_pattern, clean_content_field, content, flags=re.DOTALL)
        
        # 统计处理后的符号数量
        final_strikethrough = processed_content.count('~~')
        final_bold = processed_content.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"   - 删除线符号: {strikethrough_count//2} → {final_strikethrough//2}")
        print(f"   - 加粗符号: {bold_count//2} → {final_bold//2}")
        print(f"✅ 已更新 {file_path}")
        
        # 验证JS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("🚀 开始清理修改版简历格式...")
    clean_resume_formatting()
    print("🎉 处理完成！")