langchain/libs/text-splitters/langchain_text_splitters/konlpy.py
Christophe Bornet 802d2bf249
text-splitters: Add ruff rule UP (pyupgrade) (#31841)
See https://docs.astral.sh/ruff/rules/#pyupgrade-up
All auto-fixed except `typing.AbstractSet` -> `collections.abc.Set`
2025-07-03 10:11:35 -04:00

37 lines
976 B
Python

from __future__ import annotations
from typing import Any
from langchain_text_splitters.base import TextSplitter
class KonlpyTextSplitter(TextSplitter):
"""Splitting text using Konlpy package.
It is good for splitting Korean text.
"""
def __init__(
self,
separator: str = "\n\n",
**kwargs: Any,
) -> None:
"""Initialize the Konlpy text splitter."""
super().__init__(**kwargs)
self._separator = separator
try:
import konlpy
except ImportError:
raise ImportError(
"""
Konlpy is not installed, please install it with
`pip install konlpy`
"""
)
self.kkma = konlpy.tag.Kkma()
def split_text(self, text: str) -> list[str]:
"""Split incoming text and return chunks."""
splits = self.kkma.sentences(text)
return self._merge_splits(splits, self._separator)