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
@@ -1,75 +1,75 @@
|
||||
#!/user/bin/python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
Description: 身份证号码匿名化插件
|
||||
Create: 2024/12/26 15:43
|
||||
"""
|
||||
import ipaddress
|
||||
import re
|
||||
import time
|
||||
from typing import Dict, Any
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from deepdata.core.base_op import Mapper
|
||||
|
||||
|
||||
class AnonymizedIpAddress(Mapper):
|
||||
def __init__(self, *args, **kwargs):
|
||||
# IP地址校验
|
||||
# X.X.X.X与四级目录格式相同，避免误清洗，该格式的IP地址必须匹配 IP/IP地址等字样
|
||||
super().__init__(*args, **kwargs)
|
||||
self.ipv4_1_and_prefix_pattern = r'ip(地址| address|v4)?( |:|：)*(?<![\.\d])'
|
||||
# X.X.X.X
|
||||
self.ipv4_pattern = r'(?<![\.\d])\d\.\d\.\d\.\d(?![\.\d])'
|
||||
self.ipv4_re_compile = re.compile(r"(?<![\d.])(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})(?![.\d])")
|
||||
self.ipv6_re_compile = re.compile(r"(?<![0-9a-fA-F:])(([0-9a-fA-F]{0,4}:)+[0-9a-fA-F]{0,4})(?![0-9a-fA-F:])")
|
||||
|
||||
@staticmethod
|
||||
def verify_ip_address(ip):
|
||||
"""验证字符串是否为合法ip地址"""
|
||||
try:
|
||||
ipaddress.ip_address(ip)
|
||||
except ValueError:
|
||||
return False
|
||||
return True
|
||||
|
||||
def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]:
|
||||
start = time.time()
|
||||
self.read_file_first(sample)
|
||||
sample[self.text_key] = self._ip_address_filter(sample[self.text_key])
|
||||
logger.info(f"fileName: {sample[self.filename_key]}, method: IPAddressCleaner costs {time.time() - start:6f} s")
|
||||
return sample
|
||||
|
||||
def filter_ipv4(self, ipv4, line):
|
||||
"""ipv4地址匿名化"""
|
||||
if not self.verify_ip_address(ipv4):
|
||||
return line
|
||||
ipv4_format = ipv4.replace(".", "\\.")
|
||||
# 非单字节ip地址直接匿名化
|
||||
if not re.search(self.ipv4_pattern, "【" + ipv4 + "】"):
|
||||
line = re.compile(r"(?<![\d.])" + ipv4_format + r"(?![.\d])").sub("<ip>", line)
|
||||
elif re.search(self.ipv4_1_and_prefix_pattern + ipv4_format + r"(?![.\d])", line, re.IGNORECASE):
|
||||
# 单字节ip地址需搜索关键字眼，有关键字眼则段落中单字节ip地址匿名化
|
||||
line = re.compile(self.ipv4_pattern).sub("<ip>", line)
|
||||
return line
|
||||
|
||||
def _ip_address_filter(self, input_data: str):
|
||||
""" IPv4、IPv6地址匿名化"""
|
||||
lines = input_data.split("\n")
|
||||
line_list = []
|
||||
for line in lines:
|
||||
# 为防止IP地址处于段落开头或结尾不能被匹配，需要在字符串首尾加占位符
|
||||
line = ''.join(['【', line, '】'])
|
||||
ipv4_groups = self.ipv4_re_compile.findall(line)
|
||||
for ipv4 in ipv4_groups:
|
||||
line = self.filter_ipv4(ipv4, line)
|
||||
ipv6_groups = self.ipv6_re_compile.findall(line)
|
||||
for group in ipv6_groups:
|
||||
ipv6 = group[0]
|
||||
if ipv6 and self.verify_ip_address(ipv6):
|
||||
line = re.compile(r"(?<![0-9a-fA-F:])" + ipv6 + "(?![0-9a-fA-F:])").sub("<ip>", line)
|
||||
line_list.append(line[1:-1])
|
||||
text = "\n".join([line.strip() for line in line_list])
|
||||
return text
|
||||
#!/user/bin/python␍
|
||||
# -*- coding: utf-8 -*-␍
|
||||
␍
|
||||
"""␍
|
||||
Description: 身份证号码匿名化插件␍
|
||||
Create: 2024/12/26 15:43␍
|
||||
"""␍
|
||||
import ipaddress␍
|
||||
import re␍
|
||||
import time␍
|
||||
from typing import Dict, Any␍
|
||||
␍
|
||||
from loguru import logger␍
|
||||
␍
|
||||
from deepdata.core.base_op import Mapper␍
|
||||
␍
|
||||
␍
|
||||
class AnonymizedIpAddress(Mapper):␍
|
||||
def __init__(self, *args, **kwargs):␍
|
||||
# IP地址校验␍
|
||||
# X.X.X.X与四级目录格式相同，避免误清洗，该格式的IP地址必须匹配 IP/IP地址等字样␍
|
||||
super().__init__(*args, **kwargs)␍
|
||||
self.ipv4_1_and_prefix_pattern = r'ip(地址| address|v4)?( |:|：)*(?<![\.\d])'␍
|
||||
# X.X.X.X␍
|
||||
self.ipv4_pattern = r'(?<![\.\d])\d\.\d\.\d\.\d(?![\.\d])'␍
|
||||
self.ipv4_re_compile = re.compile(r"(?<![\d.])(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})(?![.\d])")␍
|
||||
self.ipv6_re_compile = re.compile(r"(?<![0-9a-fA-F:])(([0-9a-fA-F]{0,4}:)+[0-9a-fA-F]{0,4})(?![0-9a-fA-F:])")␍
|
||||
␍
|
||||
@staticmethod␍
|
||||
def verify_ip_address(ip):␍
|
||||
"""验证字符串是否为合法ip地址"""␍
|
||||
try:␍
|
||||
ipaddress.ip_address(ip)␍
|
||||
except ValueError:␍
|
||||
return False␍
|
||||
return True␍
|
||||
␍
|
||||
def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]:␍
|
||||
start = time.time()␍
|
||||
self.read_file_first(sample)␍
|
||||
sample[self.text_key] = self._ip_address_filter(sample[self.text_key])␍
|
||||
logger.info(f"fileName: {sample[self.filename_key]}, method: IPAddressCleaner costs {time.time() - start:.6f} s")␍
|
||||
return sample␍
|
||||
␍
|
||||
def filter_ipv4(self, ipv4, line):␍
|
||||
"""ipv4地址匿名化"""␍
|
||||
if not self.verify_ip_address(ipv4):␍
|
||||
return line␍
|
||||
ipv4_format = ipv4.replace(".", "\\.")␍
|
||||
# 非单字节ip地址直接匿名化␍
|
||||
if not re.search(self.ipv4_pattern, "【" + ipv4 + "】"):␍
|
||||
line = re.compile(r"(?<![\d.])" + ipv4_format + r"(?![.\d])").sub("<ip>", line)␍
|
||||
elif re.search(self.ipv4_1_and_prefix_pattern + ipv4_format + r"(?![.\d])", line, re.IGNORECASE):␍
|
||||
# 单字节ip地址需搜索关键字眼，有关键字眼则段落中单字节ip地址匿名化␍
|
||||
line = re.compile(self.ipv4_pattern).sub("<ip>", line)␍
|
||||
return line␍
|
||||
␍
|
||||
def _ip_address_filter(self, input_data: str):␍
|
||||
""" IPv4、IPv6地址匿名化"""␍
|
||||
lines = input_data.split("\n")␍
|
||||
line_list = []␍
|
||||
for line in lines:␍
|
||||
# 为防止IP地址处于段落开头或结尾不能被匹配，需要在字符串首尾加占位符␍
|
||||
line = ''.join(['【', line, '】'])␍
|
||||
ipv4_groups = self.ipv4_re_compile.findall(line)␍
|
||||
for ipv4 in ipv4_groups:␍
|
||||
line = self.filter_ipv4(ipv4, line)␍
|
||||
ipv6_groups = self.ipv6_re_compile.findall(line)␍
|
||||
for group in ipv6_groups:␍
|
||||
ipv6 = group[0]␍
|
||||
if ipv6 and self.verify_ip_address(ipv6):␍
|
||||
line = re.compile(r"(?<![0-9a-fA-F:])" + ipv6 + "(?![0-9a-fA-F:])").sub("<ip>", line)␍
|
||||
line_list.append(line[1:-1])␍
|
||||
text = "\n".join([line.strip() for line in line_list])␍
|
||||
return text␍
|
||||
|
||||
Reference in New Issue
Block a user