pss work: replace \r\n or \n in paragraph only, in a file, paragraph as single line worked. colab code;

 (?<![.,!?])\r?\n\r?\n   it ignore , commas,? ! , but not full stop ; such lines will be highlighted.

find lines without full stop, need to merge with next paragraph. (?<!\.)\r?\n\r?\n

import os

def process_paragraphs(input_file, output_file):

    with open(input_file, 'r', encoding='utf-8') as file:

        content = file.read()

   

    # Splitting content into paragraphs using double newlines as delimiter

    paragraphs = content.split('\n\n')  # This handles paragraphs separated by blank lines

   

    processed_paragraphs = []

    for paragraph in paragraphs:

        # Removing unnecessary line breaks within a paragraph

        cleaned_paragraph = ' '.join(paragraph.splitlines()).strip()

        processed_paragraphs.append(cleaned_paragraph)

   

    # Joining paragraphs back with double newlines to maintain separation

    processed_text = '\n\n'.join(processed_paragraphs)

   

    # Writing processed text to output file

    with open(output_file, 'w', encoding='utf-8') as file:

        file.write(processed_text)

   

    print(f"Processed file saved as: {output_file}")

# Define file paths

input_file_path = "/content/CLOUD_సామెతల జ్ఞానము_25March2025.txt"  # Change filename accordingly

output_file_path = "/content/CLOUD_సామెతల జ్ఞానము_25March2025_output.txt"

# Process file

process_paragraphs(input_file_path, output_file_path)