This question concerns unicode characters that are more than one utf-16 character
string.length returns the number of unicode 16 chars in the string. But what about the case of characters that are more than 1 unicode 16 character? Is it possible to get the actual number of characters as well as "true" values from string.charAt of the actual character, and not the utf-16 pieces?
var test = "🀄";
console.log(test.length)
var regex = /[\u{1F000}-\u{1F0FF}]/g;
var regex2 = /🀄/g
console.log('test: ' + regex.test(test));
console.log('test2: ' + regex2.test(test));Another option is to use RegExp with the unicode flag.
var test = "🀄";
var length = test.match(/./ug).length;
console.log(length);Please note that this and the answer using the spread operator can break under certain circumstances.
var test = "Z͑ͫ̓ͪ̂ͫ̽͏̴̙̤̞͉͚̯̞̠͍A̴̵̜̰͔ͫ͗͢L̠ͨͧͩ͘G̴̻͈͍͔̹̑͗̎̅͛́Ǫ̵̹̻̝̳͂̌̌͘";
var length = test.match(/./ug).length;
console.log(length);To get the char at a specific index you can use the following function.
var test = "🀄👼👺💩";
var charAt = charAt(test);
console.log(charAt);
function charAt(string, index) {
if(!index)
index = 0;
return string.match(/./ug)[index];
}you can use spread operator:
var test = "🀄";
var test2 = [...test];
console.log(test.length);
console.log(test2.length);about your second question, you need to modify regexp:
var test = "🀄";
console.log(test.length)
var regex = /[\u{1F000}-\u{1F0FF}]/ug;
var regex2 = /🀄/g
console.log('test: ' + regex.test(test));
console.log('test2: ' + regex2.test(test));