Converting standard Vietnamese Characters to non-accent ones (Chuyển đổi ký tự tiếng Việt sang không dấu). Example: hải -> hai

nonAccentVietnamese.js

// This function converts the string to lowercase, then perform the conversion
function toLowerCaseNonAccentVietnamese(str) {
    str = str.toLowerCase();
//     We can also use this instead of from line 11 to line 17
//     str = str.replace(/\u00E0|\u00E1|\u1EA1|\u1EA3|\u00E3|\u00E2|\u1EA7|\u1EA5|\u1EAD|\u1EA9|\u1EAB|\u0103|\u1EB1|\u1EAF|\u1EB7|\u1EB3|\u1EB5/g, "a");
//     str = str.replace(/\u00E8|\u00E9|\u1EB9|\u1EBB|\u1EBD|\u00EA|\u1EC1|\u1EBF|\u1EC7|\u1EC3|\u1EC5/g, "e");
//     str = str.replace(/\u00EC|\u00ED|\u1ECB|\u1EC9|\u0129/g, "i");
//     str = str.replace(/\u00F2|\u00F3|\u1ECD|\u1ECF|\u00F5|\u00F4|\u1ED3|\u1ED1|\u1ED9|\u1ED5|\u1ED7|\u01A1|\u1EDD|\u1EDB|\u1EE3|\u1EDF|\u1EE1/g, "o");
//     str = str.replace(/\u00F9|\u00FA|\u1EE5|\u1EE7|\u0169|\u01B0|\u1EEB|\u1EE9|\u1EF1|\u1EED|\u1EEF/g, "u");
//     str = str.replace(/\u1EF3|\u00FD|\u1EF5|\u1EF7|\u1EF9/g, "y");
//     str = str.replace(/\u0111/g, "d");
    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");
    // Some system encode vietnamese combining accent as individual utf-8 characters
    str = str.replace(/\u0300|\u0301|\u0303|\u0309|\u0323/g, ""); // Huyền sắc hỏi ngã nặng 
    str = str.replace(/\u02C6|\u0306|\u031B/g, ""); // Â, Ê, Ă, Ơ, Ư
    return str;
}

// This function keeps the casing unchanged for str, then perform the conversion
function toNonAccentVietnamese(str) {
      str = str.replace(/A|Á|À|Ã|Ạ|Â|Ấ|Ầ|Ẫ|Ậ|Ă|Ắ|Ằ|Ẵ|Ặ/g, "A");
      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(/E|É|È|Ẽ|Ẹ|Ê|Ế|Ề|Ễ|Ệ/, "E");
      str = str.replace(/è|é|ẹ|ẻ|ẽ|ê|ề|ế|ệ|ể|ễ/g, "e");
      str = str.replace(/I|Í|Ì|Ĩ|Ị/g, "I");
      str = str.replace(/ì|í|ị|ỉ|ĩ/g, "i");
      str = str.replace(/O|Ó|Ò|Õ|Ọ|Ô|Ố|Ồ|Ỗ|Ộ|Ơ|Ớ|Ờ|Ỡ|Ợ/g, "O");
      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(/U|Ú|Ù|Ũ|Ụ|Ư|Ứ|Ừ|Ữ|Ự/g, "U");
      str = str.replace(/ù|ú|ụ|ủ|ũ|ư|ừ|ứ|ự|ử|ữ/g, "u");
      str = str.replace(/Y|Ý|Ỳ|Ỹ|Ỵ/g, "Y");
      str = str.replace(/ỳ|ý|ỵ|ỷ|ỹ/g, "y");
      str = str.replace(/Đ/g, "D");
      str = str.replace(/đ/g, "d");
      // Some system encode vietnamese combining accent as individual utf-8 characters
      str = str.replace(/\u0300|\u0301|\u0303|\u0309|\u0323/g, ""); // Huyền sắc hỏi ngã nặng 
      str = str.replace(/\u02C6|\u0306|\u031B/g, ""); // Â, Ê, Ă, Ơ, Ư
      return str;
}

Nice !!!

thanks

Cảm ơn anh nhiều lắm <3

1 saoo cho anh . thankzzzzzzz

Hi, you can try
str.normalize("NFD").replace(/[\u0300-\u036f]/g, "")
for more detail, please refer
https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/normalize

Hi, you can try
str.normalize("NFD").replace(/[\u0300-\u036f]/g, "")
for more detail, please refer
https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/normalize

Doesn't work with 'đ'

Thanks!

nice

👍

love it!

Greate!

Thank you !

Thanks so much!

function này sẽ trả về text là lowercase nên trong trường hợp text đầu ra bạn vẫn muốn giữ nguyên định dạng ban đầu thì cần define thêm chữ in hoa cho từng ký tự

Fork a version with capital letters here https://gist.github.com/doraeminemon/d7b8dba2fd6f32b3c2c47db22d33404e

thank you

Thank you <3

The gist has been updated with a new version that support character casing, with credits to @doraeminemon

thank

Thank you so much!!

nicee

thank you so much!

có cách nào convert không dấu thành có dấu không

Thank you so much!

Thank you so much !
what about from english to vietnamese ?
@doraeminemon

cam on anh rat nhieu

it not working
input: MẪU BIÊN BẢN HỌP XEM LẠI BĂNG HÌNH.doc
output: MAU BIEN BẢN HOP XEM LAI BANG HINH.doc

thanks

MẪU BIÊN BẢN HỌP XEM LẠI BĂNG HÌNH.doc

function toNonAccentVietnamese(str) {
      str = str.replace(/A|Á|À|Ả|Ã|Ạ|Â|Ấ|Ầ|Ẩ|Ẫ|Ậ|Ă|Ắ|Ằ|Ẳ|Ẵ|Ặ/g, "A");
      str = str.replace(/à|á|ạ|ả|ã|â|ầ|ấ|ậ|ẩ|ẫ|ậ|ă|ằ|ắ|ặ|ẳ|ẵ/g, "a");
<same_for_remaining>
...

Thiếu mấy chữ dấu hỏi

function toNonAccentVietnamese(str) {
  return decodeURI(str).normalize('NFC')
      .replace(/Á|À|Ả|Ã|Ạ|Â|Ấ|Ầ|Ẫ|Ẩ|Ậ|Ă|Ắ|Ằ|Ẵ|Ặ|ẳ/g, "A")
      .replace(/á|à|ả|ã|ạ|â|ấ|ầ|ẫ|ẩ|ậ|ă|ắ|ằ|ẵ|ặ|ẳ/g, "a")
      .replace(/É|È|Ẻ|Ẽ|Ẹ|Ê|Ế|Ề|Ể|Ễ|Ệ/g, "E")
      .replace(/é|è|ẻ|ẽ|ẹ|ê|ề|ế|ệ|ể|ễ/g, "e")
      .replace(/Í|Ì|Ỉ|Ĩ|Ị/g, "I")
      .replace(/ì|í|ị|ỉ|ĩ/g, "i")
      .replace(/Ó|Ò|Ỏ|Õ|Ọ|Ô|Ố|Ồ|Ỗ|Ộ|Ổ|Ơ|Ớ|Ờ|Ỡ|Ợ|Ở/g, "O")
      .replace(/ò|ó|ọ|ỏ|õ|ô|ồ|ố|ộ|ổ|ỗ|ơ|ờ|ớ|ợ|ở|ỡ/g, "o")
      .replace(/Ú|Ù|Ủ|Ũ|Ụ|Ư|Ứ|Ừ|Ữ|Ử|Ự/g, "U")
      .replace(/ù|ú|ụ|ủ|ũ|ư|ừ|ứ|ự|ử|ữ/g, "u")
      .replace(/Ý|Ỳ|Ỷ|Ỹ|Ỵ/g, "Y")
      .replace(/ỳ|ý|ỵ|ỷ|ỹ/g, "y")
      .replace(/Đ/g, "D")
      .replace(/đ/g, "d")
}