dovhpmnm31216
dovhpmnm31216
2014-06-24 06:09

UTF-8到UTF-16LE Javascript

I need to convert an utf-8 string to utf-16LE in javascript like the iconv() php function.

Ie:

iconv("UTF-8", "UTF-16LE", $string);

The output should be like this:

49 00 6e 00 64 00 65 00 78 00

I found this func to decode UTF-16LE and it's works fine but i don't know how to do the same to encode.

function decodeUTF16LE( binaryStr ) {
    var cp = [];
    for( var i = 0; i < binaryStr.length; i+=2) {
        cp.push( 
             binaryStr.charCodeAt(i) |
            ( binaryStr.charCodeAt(i+1) << 8 )
        );
    }

    return String.fromCharCode.apply( String, cp );
}

The conclusion is to create a binary file that can be downloaded.

The code:

function download(filename, text) {
    var a = window.document.createElement('a');

    var byteArray = new Uint8Array(text.length);
    for (var i = 0; i < text.length; i++) {
        byteArray[i] = text.charCodeAt(i) & 0xff;
    }
    a.href = window.URL.createObjectURL(new Blob([byteArray.buffer], {'type': 'application/type'}));

    a.download = filename;

    // Append anchor to body.
    document.body.appendChild(a);
    a.click();

    // Remove anchor from body
    document.body.removeChild(a);
}
  • 点赞
  • 写回答
  • 关注问题
  • 收藏
  • 复制链接分享
  • 邀请回答

2条回答

  • dougaicha5258 dougaicha5258 7年前

    This should do it:

    var byteArray = new Uint8Array(text.length * 2);
    for (var i = 0; i < text.length; i++) {
        byteArray[i*2] = text.charCodeAt(i) // & 0xff;
        byteArray[i*2+1] = text.charCodeAt(i) >> 8 // & 0xff;
    }
    

    It's the inverse of your decodeUTF16LE function. Notice that neither works with code points outside of the BMP.

    点赞 评论 复制链接分享
  • douketangyouzh5219 douketangyouzh5219 7年前

    Thanks a lot Bergi, this works perfectly combining to standard utf8 to utf16 encode function:

    function encodeUTF16LE(str) {
        var out, i, len, c;
        var char2, char3;
    
        out = "";
        len = str.length;
        i = 0;
        while(i < len) {
            c = str.charCodeAt(i++);
            switch(c >> 4)
            { 
              case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7:
                // 0xxxxxxx
                out += str.charAt(i-1);
                break;
              case 12: case 13:
                // 110x xxxx   10xx xxxx
                char2 = str.charCodeAt(i++);
                out += String.fromCharCode(((c & 0x1F) << 6) | (char2 & 0x3F));
                out += str.charAt(i-1);
                break;
              case 14:
                // 1110 xxxx  10xx xxxx  10xx xxxx
                char2 = str.charCodeAt(i++);
                char3 = str.charCodeAt(i++);
                out += String.fromCharCode(((c & 0x0F) << 12) | ((char2 & 0x3F) << 6) | ((char3 & 0x3F) << 0));
                break;
            }
        }
    
        var byteArray = new Uint8Array(out.length * 2);
        for (var i = 0; i < out.length; i++) {
            byteArray[i*2] = out.charCodeAt(i); // & 0xff;
            byteArray[i*2+1] = out.charCodeAt(i) >> 8; // & 0xff;
        }
    
        return String.fromCharCode.apply( String, byteArray );
    }
    
    点赞 评论 复制链接分享