Smuggling/fingerprinting text with Unicode variation selectors

smuggling.js

// Source: https://paulbutler.org/2025/smuggling-arbitrary-data-through-an-emoji/
function byteToVariationSelector(byte) {
    if (byte < 16) {
        return String.fromCodePoint(0xFE00 + byte);
    } else {
        return String.fromCodePoint(0xE0100 + (byte - 16));
    }
}

function encode(base, str) {
    let utf8Encode = new TextEncoder();
    let bytes = utf8Encode.encode(str);
    let result = base;
    for (let byte of bytes) {
        result += byteToVariationSelector(byte);
    }
    return result;
}

function variationSelectorToByte(variationSelector) {
    const codePoint = variationSelector.codePointAt(0);
    if (codePoint >= 0xFE00 && codePoint <= 0xFE0F) {
        return codePoint - 0xFE00;
    } else if (codePoint >= 0xE0100 && codePoint <= 0xE01EF) {
        return codePoint - 0xE0100 + 16;
    } else {
        return null;
    }
}

function decode(variationSelectors) {
    let result = [];
    for (let char of variationSelectors) {
        let byte = variationSelectorToByte(char);
        if (byte !== null) {
            result.push(byte);
        } else if (result.length > 0) {
            return String.fromCharCode(...result);
        }
        // Ignore non-variation selectors until we have encountered the first one.
    }
    return String.fromCharCode(...result);
}

encode('😊', 'hello world');