沃巴蒂
ff22ed3a8b
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）
66 lines
3.0 KiB
Python
66 lines
3.0 KiB
Python
#!/user/bin/python
|
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
|
|
|
"""
|
|
|
|
Description: 文档目录去除
|
|
|
|
Create: 2025/01/13
|
|
|
|
"""
|
|
|
|
import re
|
|
|
|
import time
|
|
|
|
from typing import Dict, Any
|
|
|
|
|
|
|
|
from loguru import logger
|
|
|
|
|
|
|
|
from deepdata.core.base_op import Mapper
|
|
|
|
|
|
|
|
|
|
|
|
class ContentCleaner(Mapper):
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
|
|
super().__init__(*args, **kwargs)
|
|
|
|
self.no_content_count = 3 # 连续不符合目录结构的行数阈值
|
|
|
|
# 目录标题
|
|
|
|
self.content_text_pattern = r"^ *(目 *录|CONTENT(S)?) *$"
|
|
|
|
# 目录行 前缀格式
|
|
|
|
self.content_preface_pattern = r"^ *(前言|About This Document|\d+(\.\d+)*|[a-zA-Z]+(\.\d+)*)"
|
|
|
|
# 目录行 中间格式
|
|
|
|
self.content_middle_pattern = r"\.{7,}"
|
|
|
|
# 目录行 结尾格式
|
|
|
|
self.content_end_pattern = r"(\d|错误!未定义书签。|[IXV]+) *$"
|
|
|
|
self.content_pattern = self.content_preface_pattern + ".*" + self.content_end_pattern
|
|
|
|
|
|
|
|
def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]:
|
|
|
|
start = time.time()
|
|
|
|
self.read_file_first(sample)
|
|
|
|
sample[self.text_key] = self._content_filter(sample[self.text_key])
|
|
|
|
logger.info(f"fileName: {sample[self.filename_key]}, method: ContentCleaner costs {time.time() - start:.6f} s")
|
|
|
|
return sample
|
|
|
|
|
|
|
|
def _content_filter(self, input_data: str):
|
|
|
|
count = 0 # 记录不符合目录结构的次数，连续3行不满足要求，则认为已经进入正文
|
|
|
|
# 目录起始和结束索引
|
|
|
|
content_start_index, content_end_index = -1, -1
|
|
|
|
lines = input_data.split("\n")
|
|
|
|
for i, line in enumerate(lines):
|
|
|
|
if content_start_index >= 0 and count >= self.no_content_count:
|
|
|
|
break
|
|
|
|
# 首先匹配目录或content字眼
|
|
|
|
if content_start_index < 0 and re.match(self.content_text_pattern, line, re.IGNORECASE):
|
|
|
|
content_start_index = i
|
|
|
|
content_end_index = i
|
|
|
|
# 匹配两种形式的目录行
|
|
|
|
# 1. 以指定格式开始、指定格式结尾；2.该行包含点数量超过7个
|
|
|
|
elif content_start_index >= 0 and (re.match(self.content_pattern, line, re.IGNORECASE)
|
|
|
|
or re.search(self.content_middle_pattern, line)):
|
|
|
|
content_end_index = i
|
|
|
|
count = 0
|
|
|
|
elif content_start_index >= 0 and not (re.match(self.content_pattern, line, re.IGNORECASE)
|
|
|
|
or re.search(self.content_middle_pattern, line)):
|
|
|
|
count += 1
|
|
|
|
|
|
|
|
if 0 <= content_start_index < content_end_index:
|
|
|
|
res = "\n".join(lines[:content_start_index] + lines[content_end_index + 1:])
|
|
|
|
else:
|
|
|
|
# 只有目录关键字时，关键字不去除;或不符合目录结构，返回原文
|
|
|
|
res = "\n".join(lines)
|
|
|
|
return res
|
|
|