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
@@ -1,55 +1,55 @@
|
||||
#!/user/bin/python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
Description:
|
||||
本插件实现将文档中乱码去除功能
|
||||
实现逻辑：
|
||||
1. 正则判断该字符的unicode编码是否在乱码范围内。若在范围内，则去除，不在范围内，则保留。
|
||||
2. 运行前，加载乱码字符范围的配置文件，即charset.json。该json文件中，key为字符集名称，value为unicode编码范围的集合。
|
||||
|
||||
Create: 2025/01/13
|
||||
"""
|
||||
import json
|
||||
import re
|
||||
import time
|
||||
from pathlib import Path
|
||||
from typing import Dict, Any
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from deepdata.core.base_op import Mapper
|
||||
|
||||
|
||||
class GrableCharactersCleaner(Mapper):
|
||||
def __init__(self, *args, **kwargs):
|
||||
super().__init__(*args, **kwargs)
|
||||
self._file_path = str(Path(__file__).parent / 'resources' / 'charset.json')
|
||||
self.unicode_grable_code_list = self.get_unicode_grable_code_list() # 乱码unicode编码的十进制范围的集合
|
||||
self.grable_re_compile = re.compile("[" + self.unicode_grable_code_list + "]")
|
||||
|
||||
def get_unicode_grable_code_list(self):
|
||||
"""获取乱码unicode编码范围"""
|
||||
res = ""
|
||||
with open(self._file_path, 'r', encoding='utf-8') as f:
|
||||
charset_number_list = json.load(f)
|
||||
for number_ranges in charset_number_list.values():
|
||||
for number_range in number_ranges:
|
||||
number_range_list = number_range.split(",")
|
||||
if len(number_range_list) < 2:
|
||||
logger.error(f"number_range_list size is {len(number_range_list)}, formatting error")
|
||||
continue
|
||||
res += number_range_list[0] + "-" + number_range_list[1]
|
||||
return res
|
||||
|
||||
def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]:
|
||||
start = time.time()
|
||||
self.read_file_first(sample)
|
||||
sample[self.text_key] = self._grable_characters_filter(sample[self.text_key])
|
||||
logger.info(
|
||||
f"fileName: {sample[self.filename_key]}, method: GrableCharactersCleaner costs {time.time() - start:6f} s")
|
||||
return sample
|
||||
|
||||
def _grable_characters_filter(self, input_data: str):
|
||||
"""去除文档中的乱码"""
|
||||
return self.grable_re_compile.sub("", input_data)
|
||||
#!/user/bin/python␍
|
||||
# -*- coding: utf-8 -*-␍
|
||||
␍
|
||||
"""␍
|
||||
Description:␍
|
||||
本插件实现将文档中乱码去除功能␍
|
||||
实现逻辑：␍
|
||||
1. 正则判断该字符的unicode编码是否在乱码范围内。若在范围内，则去除，不在范围内，则保留。␍
|
||||
2. 运行前，加载乱码字符范围的配置文件，即charset.json。该json文件中，key为字符集名称，value为unicode编码范围的集合。␍
|
||||
␍
|
||||
Create: 2025/01/13␍
|
||||
"""␍
|
||||
import json␍
|
||||
import re␍
|
||||
import time␍
|
||||
from pathlib import Path␍
|
||||
from typing import Dict, Any␍
|
||||
␍
|
||||
from loguru import logger␍
|
||||
␍
|
||||
from deepdata.core.base_op import Mapper␍
|
||||
␍
|
||||
␍
|
||||
class GrableCharactersCleaner(Mapper):␍
|
||||
def __init__(self, *args, **kwargs):␍
|
||||
super().__init__(*args, **kwargs)␍
|
||||
self._file_path = str(Path(__file__).parent / 'resources' / 'charset.json')␍
|
||||
self.unicode_grable_code_list = self.get_unicode_grable_code_list() # 乱码unicode编码的十进制范围的集合␍
|
||||
self.grable_re_compile = re.compile("[" + self.unicode_grable_code_list + "]")␍
|
||||
␍
|
||||
def get_unicode_grable_code_list(self):␍
|
||||
"""获取乱码unicode编码范围"""␍
|
||||
res = ""␍
|
||||
with open(self._file_path, 'r', encoding='utf-8') as f:␍
|
||||
charset_number_list = json.load(f)␍
|
||||
for number_ranges in charset_number_list.values():␍
|
||||
for number_range in number_ranges:␍
|
||||
number_range_list = number_range.split(",")␍
|
||||
if len(number_range_list) < 2:␍
|
||||
logger.error(f"number_range_list size is {len(number_range_list)}, formatting error")␍
|
||||
continue␍
|
||||
res += number_range_list[0] + "-" + number_range_list[1]␍
|
||||
return res␍
|
||||
␍
|
||||
def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]:␍
|
||||
start = time.time()␍
|
||||
self.read_file_first(sample)␍
|
||||
sample[self.text_key] = self._grable_characters_filter(sample[self.text_key])␍
|
||||
logger.info(␍
|
||||
f"fileName: {sample[self.filename_key]}, method: GrableCharactersCleaner costs {time.time() - start:.6f} s")␍
|
||||
return sample␍
|
||||
␍
|
||||
def _grable_characters_filter(self, input_data: str):␍
|
||||
"""去除文档中的乱码"""␍
|
||||
return self.grable_re_compile.sub("", input_data)␍
|
||||
|
||||
Reference in New Issue
Block a user