Utf8 string encode/decode using regular expressions

utf8-regex.js

/**
 * Encodes multi-byte Unicode string into utf-8 multiple single-byte characters
 * (BMP / basic multilingual plane only).
 *
 * Chars in range U+0080 - U+07FF are encoded in 2 chars, U+0800 - U+FFFF in 3 chars.
 *
 * Can be achieved in JavaScript by unescape(encodeURIComponent(str)),
 * but this approach may be useful in other languages.
 *
 * @param   {string} unicodeString - Unicode string to be encoded as UTF-8.
 * @returns {string} UTF8-encoded string.
 */
function utf8Encode(unicodeString) {
    if (typeof unicodeString != 'string') throw new TypeError('parameter ‘unicodeString’ is not a string');
    const utf8String = unicodeString.replace(
        /[\u0080-\u07ff]/g,  // U+0080 - U+07FF => 2 bytes 110yyyyy, 10zzzzzz
        function(c) {
            var cc = c.charCodeAt(0);
            return String.fromCharCode(0xc0 | cc>>6, 0x80 | cc&0x3f); }
    ).replace(
        /[\u0800-\uffff]/g,  // U+0800 - U+FFFF => 3 bytes 1110xxxx, 10yyyyyy, 10zzzzzz
        function(c) {
            var cc = c.charCodeAt(0);
            return String.fromCharCode(0xe0 | cc>>12, 0x80 | cc>>6&0x3F, 0x80 | cc&0x3f); }
    );
    return utf8String;
}

/**
 * Decodes utf-8 encoded string back into multi-byte Unicode characters.
 *
 * Can be achieved JavaScript by decodeURIComponent(escape(str)),
 * but this approach may be useful in other languages.
 *
 * @param   {string} utf8String - UTF-8 string to be decoded back to Unicode.
 * @returns {string} Decoded Unicode string.
 */
function utf8Decode(utf8String) {
    if (typeof utf8String != 'string') throw new TypeError('parameter ‘utf8String’ is not a string');
    // note: decode 3-byte chars first as decoded 2-byte strings could appear to be 3-byte char!
    const unicodeString = utf8String.replace(
        /[\u00e0-\u00ef][\u0080-\u00bf][\u0080-\u00bf]/g,  // 3-byte chars
        function(c) {  // (note parentheses for precedence)
            var cc = ((c.charCodeAt(0)&0x0f)<<12) | ((c.charCodeAt(1)&0x3f)<<6) | ( c.charCodeAt(2)&0x3f);
            return String.fromCharCode(cc); }
    ).replace(
        /[\u00c0-\u00df][\u0080-\u00bf]/g,                 // 2-byte chars
        function(c) {  // (note parentheses for precedence)
            var cc = (c.charCodeAt(0)&0x1f)<<6 | c.charCodeAt(1)&0x3f;
            return String.fromCharCode(cc); }
    );
    return unicodeString;
}

Hi, This is a brilliant piece of code. I have a string of octal representation of the utf8string like("\320\223...") that I want to decode to unicode String.. How do I do that..?

Hi, nice work, but you don't handle Codepoints above 'U+FFFF' correctly, see https://github.com/TSlivede/utf8-regex-encode-decode-js/

@DhamoR If your String only contains ASCII and octal UTF-8 sequences you can do this:

str="\\320\\223...";
Utf8Decode(str.replace(/\\[0-9][0-9][0-9]/g,function(s){return String.fromCharCode(parseInt(s.substr(1),8));}))

If your string can already contain UTF-16 chars you need to first encode those into UTF-8:

str="\\320\\223"+String.fromCodePoint(0x1F60E)+"...";
Utf8Decode(Utf8Encode(str).replace(/\\[0-9][0-9][0-9]/g,function(s){return String.fromCharCode(parseInt(s.substr(1),8));}))

this does not support emoji :(

Excellent work !

Sorry, touch of a newbie question here. When I try to use the code, I get errors on lines 22/43 with the function(c); call. Can someone tell me where to get this piece of code? Thanks!

I need to make it url by adding -

muito bom.