langchain_experimental.data_anonymizer.base

from abc import ABC, abstractmethod
from typing import Callable, List, Optional

from langchain_experimental.data_anonymizer.deanonymizer_mapping import MappingDataType
from langchain_experimental.data_anonymizer.deanonymizer_matching_strategies import (
    exact_matching_strategy,
)

DEFAULT_DEANONYMIZER_MATCHING_STRATEGY = exact_matching_strategy


[docs]class AnonymizerBase(ABC):
    """用于匿名化的基础抽象类。

它是公共的和非虚拟的，因为它允许在基类中包装所有方法的行为。"""

[docs]    def anonymize(
        self,
        text: str,
        language: Optional[str] = None,
        allow_list: Optional[List[str]] = None,
    ) -> str:
        """文本匿名化。"""

        return self._anonymize(text, language, allow_list)

    @abstractmethod
    def _anonymize(
        self, text: str, language: Optional[str], allow_list: Optional[List[str]] = None
    ) -> str:
        """用于对文本进行匿名化的抽象方法"""


[docs]class ReversibleAnonymizerBase(AnonymizerBase):
    """
    可逆匿名化器的基础抽象类。
    """

[docs]    def deanonymize(
        self,
        text_to_deanonymize: str,
        deanonymizer_matching_strategy: Callable[
            [str, MappingDataType], str
        ] = DEFAULT_DEANONYMIZER_MATCHING_STRATEGY,
    ) -> str:
        """识别文本"""
        return self._deanonymize(text_to_deanonymize, deanonymizer_matching_strategy)

    @abstractmethod
    def _deanonymize(
        self,
        text_to_deanonymize: str,
        deanonymizer_matching_strategy: Callable[[str, MappingDataType], str],
    ) -> str:
        """抽象方法，用于去匿名化文本"""

[docs]    @abstractmethod
    def reset_deanonymizer_mapping(self) -> None:
        """重置去匿名化映射的抽象方法"""
Source code for langchain_experimental.data_anonymizer.base
