Source code for langchain_text_splitters.nltk

from __future__ import annotations

from typing import Any, List

from langchain_text_splitters.base import TextSplitter


class NLTKTextSplitter(TextSplitter):
    """使用NLTK包分割文本。"""

    def __init__(
        self, separator: str = "\n\n", language: str = "english", **kwargs: Any
    ) -> None:
        """初始化NLTK分词器。"""
        super().__init__(**kwargs)
        try:
            from nltk.tokenize import sent_tokenize

            self._tokenizer = sent_tokenize
        except ImportError:
            raise ImportError(
                "NLTK is not installed, please install it with `pip install nltk`."
            )
        self._separator = separator
        self._language = language

    def split_text(self, text: str) -> List[str]:
        """分割传入的文本并返回各个部分。"""
        # First we naively split the large input into a bunch of smaller ones.
        splits = self._tokenizer(text, language=self._language)
        return self._merge_splits(splits, self._separator)