Bỏ dấu tiếng việt python

áàảãạăắằẳẵặâấầẩẫậ

éèẻẽẹêếềểễệ

óòỏõọôốồổỗộơớờởỡợ

íìỉĩị

úùủũụưứừửữự

ýỳỷỹỵ

0

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

def no_accent_vietnamese(s):

    s=re.sub('[áàảãạăắằẳẵặâấầẩẫậ]','a',s)

    s= re.sub('[ÁÀẢÃẠĂẮẰẲẴẶÂẤẦẨẪẬ]','A',s)

    s=re.sub('[éèẻẽẹêếềểễệ]','e',s)

    s =re.sub('[ÉÈẺẼẸÊẾỀỂỄỆ]','E',s)

    s=re.sub('[óòỏõọôốồổỗộơớờởỡợ]','o',s)

    s =re.sub('[ÓÒỎÕỌÔỐỒỔỖỘƠỚỜỞỠỢ]','O',s)

    s=re.sub('[íìỉĩị]','i',s)

    s =re.sub('[ÍÌỈĨỊ]','I',s)

    s=re.sub('[úùủũụưứừửữự]','u',s)

    s =re.sub('[ÚÙỦŨỤƯỨỪỬỮỰ]','U',s)

    s=re.sub('[ýỳỷỹỵ]','y',s)

    s =re.sub('[ÝỲỶỸỴ]','Y',s)

    s=re.sub('đ','d',s)

    s =re.sub('Đ','D',s)

    returns

import unidecode

def remove_accent(text):

    returnunidecode.unidecode(text)

0

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

// https://gist.github.com/hu2di/e80d99051529dbaa7252922baafd40e3

functionchange_alias(alias){

    varstr=alias;

    str= str.toLowerCase();

    str= str.replace(/à|á|ạ|ả|ã|â|ầ|ấ|ậ|ẩ|ẫ|ă|ằ|ắ|ặ|ẳ|ẵ/g,"a");

    str= str.replace(/è|é|ẹ|ẻ|ẽ|ê|ề|ế|ệ|ể|ễ/g,"e");

    str= str.replace(/ì|í|ị|ỉ|ĩ/g,"i");

    str= str.replace(/ò|ó|ọ|ỏ|õ|ô|ồ|ố|ộ|ổ|ỗ|ơ|ờ|ớ|ợ|ở|ỡ/g,"o");

    str= str.replace(/ù|ú|ụ|ủ|ũ|ư|ừ|ứ|ự|ử|ữ/g,"u");

    str= str.replace(/ỳ|ý|ỵ|ỷ|ỹ/g,"y");

    str=str.replace(/đ/g,"d");

    str =str.replace(/!|@|%|\^|\*|\(|\)|\+|\=|\<|\>|\?|\/|,|\.|\:|\;|\'|\"|\&|\#|\[|\]|~|\$|_|`|-|{|}|\||\\/g," ");

    str=str.replace(/+/g," ");

    str=str.trim();

    return str;

}

import java.text.Normalizer;

import java.util.regex.Pattern;

publicclassNlpUtils{

    publicstatic StringremoveAccent(Strings){Stringtemp=Normalizer.normalize(s,Normalizer.Form.NFD); Pattern pattern=Pattern.compile("\\p{InCombiningDiacriticalMarks}+");temp=pattern.matcher(temp).replaceAll("");

    return temp.replaceAll("đ","d");}

     publicstaticvoidmain(String[]args){

        System.out.println(removeAccent("xin chào đồng chí!"));

     }

}