feat(deepdata): 引入修改密码、文件预览组件与清洗算子增强,deepflow 改名为 deep-flow

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)
This commit is contained in:
沃巴蒂
2026-10-03 22:44:56 +08:00
parent cbb1048e18
commit ff22ed3a8b
1156 changed files with 129912 additions and 21716 deletions
+37 -37
View File
@@ -1,37 +1,37 @@
#!/user/bin/python
# -*- coding: utf-8 -*-
"""
Description: URL网址匿名化
Create: 2024/12/26 15:43
"""
import re
import time
from typing import Dict, Any
from loguru import logger
from deepdata.core.base_op import Mapper
class AnonymizedUrlCleaner(Mapper):
"""将文档中的网址匿名化"""
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.url_pattern = r'((?:(?:https?|ftp|file)://|(?<![a-zA-Z\-\.])www\.)' \
r'[\-A-Za-z0-9\+&@\(\)#/%\?=\^~_|!:\,\.\;]+[\-A-Za-z0-9\+&@#/%=\~_\|])' \
r'(?![\-A-Za-z0-9\+&@#/%=\~_\|])'
self.url_re_compile = re.compile(self.url_pattern, re.MULTILINE)
def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]:
start = time.time()
self.read_file_first(sample)
sample[self.text_key] = self._url_filter(sample[self.text_key])
logger.info(f"fileName: {sample[self.filename_key]}, method: UrlCleaner costs {time.time() - start:6f} s")
return sample
def _url_filter(self, input_data: str):
input_data = ''.join(['【', input_data, '】'])
text = self.url_re_compile.sub("<url>", input_data)
return text[1:-1]
#!/user/bin/python␍
# -*- coding: utf-8 -*-␍
␍
"""␍
Description: URL网址匿名化␍
Create: 2024/12/26 15:43␍
"""␍
import re␍
import time␍
from typing import Dict, Any␍
␍
from loguru import logger␍
␍
from deepdata.core.base_op import Mapper␍
␍
␍
class AnonymizedUrlCleaner(Mapper):␍
"""将文档中的网址匿名化"""␍
␍
def __init__(self, *args, **kwargs):␍
super().__init__(*args, **kwargs)␍
self.url_pattern = r'((?:(?:https?|ftp|file)://|(?<![a-zA-Z\-\.])www\.)' \␍
r'[\-A-Za-z0-9\+&@\(\)#/%\?=\^~_|!:\,\.\;]+[\-A-Za-z0-9\+&@#/%=\~_\|])' \␍
r'(?![\-A-Za-z0-9\+&@#/%=\~_\|])'␍
self.url_re_compile = re.compile(self.url_pattern, re.MULTILINE)␍
␍
def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]:␍
start = time.time()␍
self.read_file_first(sample)␍
sample[self.text_key] = self._url_filter(sample[self.text_key])␍
logger.info(f"fileName: {sample[self.filename_key]}, method: UrlCleaner costs {time.time() - start:.6f} s")␍
return sample␍
␍
def _url_filter(self, input_data: str):␍
input_data = ''.join(['【', input_data, '】'])␍
text = self.url_re_compile.sub("<url>", input_data)␍
return text[1:-1]␍