100 lines
3.8 KiB
Python
100 lines
3.8 KiB
Python
|
#!/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！")
|