remove_diacritics

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# Filename: remove_diacritics.py
# Author: Jeoi Reqi

"""
This Python script removes diacritics (Eg; é, è, ê, ñ, ü, ç, ả, ă & å) from a specified text file and saves the results.

Requirements:
- Python 3
- unidecode library (install using 'pip install unidecode')
"""

import os
from unidecode import unidecode

def remove_diacritics(input_file, output_file):
    try:
        with open(input_file, 'r', encoding='utf-8') as file:
            text = file.read()
            text_without_diacritics = unidecode(text)

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

        print(f"Diacritics removed successfully. Output saved to '{output_file}'.")

    except Exception as e:
        print(f"Error: {str(e)}")

if __name__ == "__main__":
    input_filename = "input.txt"  # Change 'input.txt' to the name of your input file
    output_filename = "output.txt"  # Change 'output.txt' to the desired name for the output file

    input_path = os.path.join(os.getcwd(), input_filename)
    output_path = os.path.join(os.getcwd(), output_filename)

    remove_diacritics(input_path, output_path)