94 lines
3.4 KiB
Python
94 lines
3.4 KiB
Python
|
#!/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！")
|