“中文”.length in javascript will return 2 which is not the result I want, here is the replacement:
|
1 2 3 4 5 6 7 8 9 10 11 |
function byteLength(str) { // returns the byte length of an utf8 string var s = str.length; for (var i=str.length-1; i>=0; i--) { var code = str.charCodeAt(i); if (code > 0x7f && code <= 0x7ff) s++; else if (code > 0x7ff && code <= 0xffff) s+=2; if (code >= 0xDC00 && code <= 0xDFFF) i--; //trail surrogate } return s; } |
byteLength(‘中文’); will return 6.
Reference: