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）
69 lines
2.3 KiB
Python
69 lines
2.3 KiB
Python
#!/user/bin/python
|
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
|
|
|
"""
|
|
|
|
Description: 政治文本过滤
|
|
|
|
Create: 2024/12/26 15:43
|
|
|
|
"""
|
|
|
|
import time
|
|
|
|
from pathlib import Path
|
|
|
|
from typing import Dict, Any
|
|
|
|
|
|
|
|
from loguru import logger
|
|
|
|
|
|
|
|
from deepdata.common.utils.aho_corasick import AhoCorasic
|
|
|
|
from deepdata.core.base_op import Mapper
|
|
|
|
|
|
|
|
|
|
|
|
class PoliticalWordCleaner(Mapper):
|
|
|
|
"""外部输入的政治文本过滤插件"""
|
|
|
|
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
|
|
super().__init__(*args, **kwargs)
|
|
|
|
root_path = Path(__file__).parent / 'resources'
|
|
|
|
political_file_path = str(root_path / 'political.txt')
|
|
|
|
special_symbols_path = str(root_path / 'special_symbols.txt')
|
|
|
|
self.special_symbols = self.load_words_list(special_symbols_path)
|
|
|
|
self.political_words = self.load_words_list(political_file_path)
|
|
|
|
self.ac_automaton = AhoCorasic(self.political_words)
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
def load_words_list(path):
|
|
|
|
"""词表加载"""
|
|
|
|
with open(path, 'r', encoding='utf-8') as f:
|
|
|
|
words = set(f.read().splitlines())
|
|
|
|
return words
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
def words_replace(target_strings: list, text: str):
|
|
|
|
"""
|
|
|
|
目标字符串替换。
|
|
|
|
|
|
|
|
Args:
|
|
|
|
target_strings: 前缀树根节点。
|
|
|
|
text: 待清洗文本。
|
|
|
|
returns:
|
|
|
|
清洗后文本。
|
|
|
|
"""
|
|
|
|
target_strings.sort(key=lambda x: -len(x))
|
|
|
|
for s in target_strings:
|
|
|
|
tmp_text = text.replace(s, '*' * len(s))
|
|
|
|
text = tmp_text
|
|
|
|
return text
|
|
|
|
|
|
|
|
def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]:
|
|
|
|
start = time.time()
|
|
|
|
self.read_file_first(sample)
|
|
|
|
sample[self.text_key] = self._political_word_filter(sample[self.text_key])
|
|
|
|
logger.info(
|
|
|
|
f"fileName: {sample[self.filename_key]}, method: PoliticalWordCleaner costs {time.time() - start:.6f} s")
|
|
|
|
return sample
|
|
|
|
|
|
|
|
def _political_word_filter(self, text):
|
|
|
|
"""词语过滤主函数，分行过滤"""
|
|
|
|
filtered_rows = []
|
|
|
|
for row in text.split('\n'):
|
|
|
|
matched_words = self.ac_automaton.search(row, self.special_symbols)
|
|
|
|
filtered_rows.append(self.words_replace(matched_words, row))
|
|
|
|
return '\n'.join(filtered_rows)
|
|
|