src/application/text/preprocessing.py

from nltk.tokenize import sent_tokenize


def split_into_paragraphs(input_text):
    """
    Splits input text into sentences by newlines.

    Args:
        input_text: The input text as a string.

    Returns:
        A list of sentences. Returns an empty list if input is not valid.
    """
    if not isinstance(input_text, str):
        return []

    paragraphs = input_text.splitlines(keepends=True)
    sentences = []
    for paragraph in paragraphs:
        paragraph = paragraph.strip()
        if paragraph and paragraph != "\n":
            sentences.extend(sent_tokenize(paragraph))
    return sentences