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）
80 lines
2.7 KiB
Python
80 lines
2.7 KiB
Python
import time
|
|
from typing import Dict, Any
|
|
|
|
import presidio_analyzer as analyzer
|
|
import presidio_anonymizer as anonymizer
|
|
import spacy
|
|
from loguru import logger
|
|
|
|
from deepdata.core.base_op import Mapper
|
|
|
|
from .custom_entities import id_recognizer, phone_recognizer, zipcode_recognizer, url_recognizer
|
|
|
|
|
|
class PiiDetector(Mapper):
|
|
custom_ops = True
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
super(PiiDetector, self).__init__(*args, **kwargs)
|
|
self.support_language = kwargs.get("support_language", "zh")
|
|
|
|
self.nlp_engine = None
|
|
self.text_analyzer = None
|
|
self.anom = None
|
|
|
|
self.init_model(*args, **kwargs)
|
|
|
|
def init_model(self, *args, **kwargs):
|
|
try:
|
|
spacy.load("zh_core_web_sm")
|
|
except OSError:
|
|
logger.warning(
|
|
"zh_core_web_sm model not found. Please run: python -m spacy download zh_core_web_sm"
|
|
)
|
|
raise
|
|
|
|
provider = analyzer.nlp_engine.NlpEngineProvider(
|
|
nlp_configuration={
|
|
"nlp_engine_name": "spacy",
|
|
"models": [
|
|
{"lang_code": "zh", "model_name": "zh_core_web_sm"}
|
|
]
|
|
}
|
|
)
|
|
|
|
# 创建NLP Engine
|
|
self.nlp_engine = provider.create_engine()
|
|
|
|
# 初始化AnalyzerEngine
|
|
self.text_analyzer = analyzer.AnalyzerEngine(nlp_engine=self.nlp_engine, supported_languages=["zh"])
|
|
self.text_analyzer.registry.load_predefined_recognizers()
|
|
for recognizer in [id_recognizer, phone_recognizer, zipcode_recognizer, url_recognizer]:
|
|
self.text_analyzer.registry.add_recognizer(recognizer)
|
|
|
|
# 初始化AnonymizerEngine
|
|
self.anom = anonymizer.AnonymizerEngine()
|
|
|
|
def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]:
|
|
start = time.time()
|
|
self.read_file_first(sample)
|
|
text = sample.get(self.text_key, "")
|
|
if not text:
|
|
logger.warning(f"fileName: {sample.get(self.filename_key, 'unknown')}, text is empty, skip PII detection.")
|
|
return sample
|
|
|
|
try:
|
|
analyzer_results = self.text_analyzer.analyze(text=text, language=self.support_language)
|
|
res = self.anom.anonymize(text=text, analyzer_results=analyzer_results)
|
|
sample[self.text_key] = res.text
|
|
except Exception as e:
|
|
logger.error(
|
|
f"fileName: {sample.get(self.filename_key, 'unknown')}, "
|
|
f"PII detection failed: {e}. Returning original text."
|
|
)
|
|
|
|
logger.info(
|
|
f"fileName: {sample.get(self.filename_key, 'unknown')}, "
|
|
f"method: PiiDetector costs {time.time() - start:.6f} s"
|
|
)
|
|
return sample
|