使用javascript计算textarea中的字节数

Question

我需要计算使用javascript编码UTF8时textarea的字节数.知道怎么做吗？

谢谢!

Answer 1

encodeURIComponent(text).replace(/%[A-F\d]{2}/g, 'U').length

Answer 2

结合各种答案,以下方法应该快速准确,并避免可能导致encodeURIComponent()错误的无效代理对的问题:

function getUTF8Length(s) {
  var len = 0;
  for (var i = 0; i < s.length; i++) {
    var code = s.charCodeAt(i);
    if (code <= 0x7f) {
      len += 1;
    } else if (code <= 0x7ff) {
      len += 2;
    } else if (code >= 0xd800 && code <= 0xdfff) {
      // Surrogate pair: These take 4 bytes in UTF-8 and 2 chars in UCS-2
      // (Assume next char is the other [valid] half and just skip it)
      len += 4; i++;
    } else if (code < 0xffff) {
      len += 3;
    } else {
      len += 4;
    }
  }
  return len;
}

Answer 3

编辑:正如didier-l所指出的,此函数不能正确计算代理字符.

broofa的答案应该正确计算代理人,请参阅/sf/answers/854426261/.

我在这里测试了两个提出的版本以及一个天真的实现:

 getUTF8Length: function(string) {
    var utf8length = 0;
    for (var n = 0; n < string.length; n++) {
        var c = string.charCodeAt(n);
        if (c < 128) {
            utf8length++;
        }
        else if((c > 127) && (c < 2048)) {
            utf8length = utf8length+2;
        }
        else {
            utf8length = utf8length+3;
        }
    }
    return utf8length;
 }

结果是我的版本在firefox中稍微快一点,并且chrome(~30x)比在这里发布的版本快得多.

Answer 4

如果你的字符串中有非bmp字符,那就更复杂了......

因为javascript执行UTF-16编码,而"字符"是2字节堆栈(16位),所有多字节字符(3个或更多字节)将不起作用:

    <script type="text/javascript">
        var nonBmpString = "foo€";
        console.log( nonBmpString.length );
        // will output 5
    </script>

字符"€"的长度为3个字节(24位).Javascript确实将其解释为2个字符,因为在JS中,字符是16位块.

因此,要正确获取混合字符串的字节大小,我们必须编写自己的函数fixedCharCodeAt();

    function fixedCharCodeAt(str, idx) {
        idx = idx || 0;
        var code = str.charCodeAt(idx);
        var hi, low;
        if (0xD800 <= code && code <= 0xDBFF) { // High surrogate (could change last hex to 0xDB7F to treat high private surrogates as single characters)
            hi = code;
            low = str.charCodeAt(idx + 1);
            if (isNaN(low)) {
                throw 'Kein gültiges Schriftzeichen oder Speicherfehler!';
            }
            return ((hi - 0xD800) * 0x400) + (low - 0xDC00) + 0x10000;
        }
        if (0xDC00 <= code && code <= 0xDFFF) { // Low surrogate
            // We return false to allow loops to skip this iteration since should have already handled high surrogate above in the previous iteration
            return false;
            /*hi = str.charCodeAt(idx-1);
            low = code;
            return ((hi - 0xD800) * 0x400) + (low - 0xDC00) + 0x10000;*/
        }
        return code;
    }

现在我们可以计算字节...

    function countUtf8(str) {
        var result = 0;
        for (var n = 0; n < str.length; n++) {
            var charCode = fixedCharCodeAt(str, n);
            if (typeof charCode === "number") {
                if (charCode < 128) {
                    result = result + 1;
                } else if (charCode < 2048) {
                    result = result + 2;
                } else if (charCode < 65536) {
                    result = result + 3;
                } else if (charCode < 2097152) {
                    result = result + 4;
                } else if (charCode < 67108864) {
                    result = result + 5;
                } else {
                    result = result + 6;
                }
            }
        }
        return result;
    }

顺便说一下......你不应该使用encodeURI方法,因为它是一个原生的浏览器功能;)

更多东西:

• GitHub上的代码
• 有关Mozilla Developer Networks的更多信息

干杯

frankneff.ch / @frank_neff