| import string | |
| def preprocess_bn(txt): | |
| """ | |
| This functions is used for preprocessing Bangla text. | |
| Two major preprocessing is done- | |
| 1. Punctuations removal. | |
| 2. Whitespace removal. | |
| Processed text is returned as a return value. | |
| """ | |
| for punc in string.punctuation: | |
| txt=txt.replace(punc, '') | |
| txt=txt.replace('।', '') | |
| txt=' '.join(txt.split()) | |
| return txt |