bnunicodenormalizer_bengali_text_unicode_normalization_quickstart.py

1from bnunicodenormalizer import Normalizer 
2
3# Initialize the normalizer
4bnorm = Normalizer()
5
6# Example Bengali text with potential unicode issues
7text = "আকাশেতে অনেক তারা"
8
9# Normalize the text
10# The normalize method returns a 'NormalizationResult' object
11# which contains: 'normalized', 'standardized' and 'is_changed'
12normalized_obj = bnorm(text)
13
14# Accessing the normalized string
15print(f"Original: {text}")
16print(f"Normalized: {normalized_obj.normalized}")