本次同步 09-12 至 09-28 的代码变更,主要内容: 新增功能 - 修改密码:后端新增 ChangePasswordRequest DTO 与UserController/UserService 对应接口,前端新增 ChangePasswordDialog 并在 Header 接入入口 - 文件预览组件重构:file-preview 目录拆分出 VideoPreview(支持 blobUrl 直传)、 ImagePreview、AudioPreview,index.tsx 统一调度各类型预览器 - 新增 my_ops 算子模块:markitdown_parser、mineru_pdf_parser、text_quality_evaluator - 新增 tools/minio-file-server MinIO 文件服务 功能增强 - 数据清洗:cleaning_task_service/scheduler/routes 重构, data_juicer_executor 与 wrapper 增强,OperatorTable/LogsTable/TaskDetail 同步调整 - 数据标注:annotation sync.py、project.py 接口与schema 更新 - 数据采集、算子市场、首页与菜单路由相关页面调整 - DataJuicer 算子接入(useOperatorOperations、dj_ops_schema) 结构调整 - deepflow/ 更名为 deep-flow/(419 个文件重命名) - 新增 helm 部署编排、GitHub Actions 之外的自建镜像构建脚本 未纳入本次提交 - scripts-backup/、runtime/python-executor-backup/、components_backup/(备份目录) - *.backup*、__pycache__ 产物 - zh_core_web_sm-3.8.0-py3-none-any.whl(46MB 构建产物) - DataX/(内嵌独立仓库,远程亦未收录其源码)
49 lines
2.0 KiB
Python
49 lines
2.0 KiB
Python
#!/user/bin/python
|
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
|
|
|
"""
|
|
|
|
Description: 邮件地址匿名化
|
|
|
|
Create: 2025/01/15
|
|
|
|
"""
|
|
|
|
from loguru import logger
|
|
|
|
import re
|
|
|
|
import time
|
|
|
|
from typing import Dict, Any
|
|
|
|
|
|
|
|
from email_validator import validate_email, EmailNotValidError
|
|
|
|
|
|
|
|
|
|
|
|
from deepdata.core.base_op import Mapper
|
|
|
|
|
|
|
|
|
|
|
|
class EmailNumberCleaner(Mapper):
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
|
|
super().__init__(*args, **kwargs)
|
|
|
|
self.front_email_pattern = r'(?<=[^0-9a-zA-Z\!\#\$\%\&\'\*\+\-\/\=\?\^\_\`\{\|\}\~\-])'
|
|
|
|
self.back_email_pattern = r'(?=[^0-9a-zA-Z\!\#\$\%\&\'\*\+\-\/\=\?\^\_\`\{\|\}\~\-])'
|
|
|
|
self.email_pattern = r'([a-zA-Z\d.\-+_]+\s?@\s?[a-zA-Z\d.\-+_]+\.[a-zA-Z0-9]{2,6})'
|
|
|
|
|
|
|
|
def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]:
|
|
|
|
start = time.time()
|
|
|
|
self.read_file_first(sample)
|
|
|
|
sample[self.text_key] = self._email_number_filter(sample[self.text_key])
|
|
|
|
logger.info(f"fileName: {sample[self.filename_key]}, method: EmailCleaner costs {time.time() - start:.6f} s")
|
|
|
|
return sample
|
|
|
|
|
|
|
|
def _email_number_filter(self, input_data: str):
|
|
|
|
""" 邮箱匿名化"""
|
|
|
|
mixed_data = ''.join(['龥', input_data, '龥'])
|
|
|
|
paired_emails = re.compile(self.front_email_pattern + self.email_pattern + self.back_email_pattern).findall(
|
|
|
|
mixed_data)
|
|
|
|
if paired_emails:
|
|
|
|
for email in paired_emails:
|
|
|
|
try:
|
|
|
|
# 验证电子邮件地址
|
|
|
|
validate_email(email, check_deliverability=False)
|
|
|
|
mixed_data = re.compile(self.front_email_pattern + re.escape(email) + self.back_email_pattern).sub(
|
|
|
|
"<email>", mixed_data, count=1)
|
|
|
|
except EmailNotValidError as err:
|
|
|
|
# 日志打印该电子邮件地址无效(不显示具体电子邮件地址)
|
|
|
|
logger.error(f"email is abnormal email form: {err}")
|
|
|
|
return mixed_data[1:-1]
|
|
|