Splits a paragraph string into smaller paragraph strings based on the 'max_lines' number passed in

split_paragraph.py

from typing import List

def split_para(para_string: str, max_lines: int = 3) -> List[str]:
    if not max_lines > 0:
        print(f"Error: Please pass a 'max_lines' arg greater than 0")
        return [para_string]

    # Get 1st 'max chunk' of para_string and add to result
    para_lines = para_string.split('\n')
    para_1st_string = '\n'.join(para_lines[:max_lines])
    result = [para_1st_string]
    
    # Get 2nd chunk of para_string and potentially process further recursively
    para_rest_string = '\n'.join(para_lines[max_lines:])
    if para_rest_string:
        result += split_para(para_rest_string, max_lines)

    return result
  

split_paragraph_regex.py

import re
from typing import List

def split_para_regex(para_string: str, max_lines: int = 3) -> List[str]:
    unchanged_result = [para_string]
    if not max_lines > 0:
        print(f"Error: Please pass a 'max_lines' arg greater than 0")
        return unchanged_result


    # Fetch all max-lines-sized chunks
    regex = r".*\n"*max_lines + r"?"
    result = re.findall(regex, para_string)

    # Clean null chunks and trim extra '\n' chars
    result = list(filter(None, result))
    result = [para.strip('\n') for para in result]

    # Return original para when max_size is greater than number of lines
    result = result or unchanged_result

    # Append any remaining chunks smaller than the max_lines size
    result_string = '\n'.join(result)
    rest = para_string.split(result_string)
    rest = filter(None, rest)
    if rest:
        rest = [para.strip('\n') for para in rest]
        result += rest

    return result