File size: 1,042 Bytes
ed4d993
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
from __future__ import annotations

from typing import Any, List

from langchain_text_splitters.base import TextSplitter


class NLTKTextSplitter(TextSplitter):
    """Splitting text using NLTK package."""

    def __init__(
        self, separator: str = "\n\n", language: str = "english", **kwargs: Any
    ) -> None:
        """Initialize the NLTK splitter."""
        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]:
        """Split incoming text and return chunks."""
        # 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)