Source code for langchain_text_splitters.konlpy

from __future__ import annotations

from typing import Any, List

from langchain_text_splitters.base import TextSplitter


[docs]class KonlpyTextSplitter(TextSplitter): """使用KonlpyεŒ…ζ₯εˆ†ε‰²ζ–‡ζœ¬γ€‚ ι€‚η”¨δΊŽεˆ†ε‰²ιŸ©ζ–‡ζ–‡ζœ¬γ€‚ """
[docs] def __init__( self, separator: str = "\n\n", **kwargs: Any, ) -> None: """εˆε§‹εŒ–Konlpyζ–‡ζœ¬εˆ†ε‰²ε™¨γ€‚""" super().__init__(**kwargs) self._separator = separator try: from konlpy.tag import Kkma except ImportError: raise ImportError( """ Konlpy is not installed, please install it with `pip install konlpy` """ ) self.kkma = Kkma()
[docs] def split_text(self, text: str) -> List[str]: """εˆ†ε‰²δΌ ε…₯ηš„ζ–‡ζœ¬εΉΆθΏ”ε›žεˆ†ε—γ€‚""" splits = self.kkma.sentences(text) return self._merge_splits(splits, self._separator)