与这里的解决方案不同，我需要从UTF-8数据转换到UTF-8数据。为此，我使用(un)escape/(en)decodeURIComponent技巧编写了以下两个函数。它们非常浪费内存，分配的长度是编码后utf8-string的9倍，尽管这些应该由gc恢复。只是不要在100mb的文本中使用它们。

function utf8AbFromStr(str) {
    var strUtf8 = unescape(encodeURIComponent(str));
    var ab = new Uint8Array(strUtf8.length);
    for (var i = 0; i < strUtf8.length; i++) {
        ab[i] = strUtf8.charCodeAt(i);
    }
    return ab;
}

function strFromUtf8Ab(ab) {
    return decodeURIComponent(escape(String.fromCharCode.apply(null, ab)));
}

检查它是否工作:

strFromUtf8Ab(utf8AbFromStr('latinкирилицаαβγδεζηあいうえお'))
-> "latinкирилицаαβγδεζηあいうえお"

var decoder = new TextDecoder ();
var string = decoder.decode (arrayBuffer);

参见https://developer.mozilla.org/en-US/docs/Web/API/TextDecoder/decode

如果你使用的是巨型数组，例如arr.length=1000000 您可以使用此代码来避免堆栈回调问题

function ab2str(buf) {
var bufView = new Uint16Array(buf);
var unis =""
for (var i = 0; i < bufView.length; i++) {
    unis=unis+String.fromCharCode(bufView[i]);
}
return unis
}

逆函数 Mangini从上面回答

function str2ab(str) {
    var buf = new ArrayBuffer(str.length*2); // 2 bytes for each char
    var bufView = new Uint16Array(buf);
    for (var i=0, strLen=str.length; i<strLen; i++) {
        bufView[i] = str.charCodeAt(i);
    }
    return buf;
}

从emscripten:

function stringToUTF8Array(str, outU8Array, outIdx, maxBytesToWrite) {
  if (!(maxBytesToWrite > 0)) return 0;
  var startIdx = outIdx;
  var endIdx = outIdx + maxBytesToWrite - 1;
  for (var i = 0; i < str.length; ++i) {
    var u = str.charCodeAt(i);
    if (u >= 55296 && u <= 57343) {
      var u1 = str.charCodeAt(++i);
      u = 65536 + ((u & 1023) << 10) | u1 & 1023
    }
    if (u <= 127) {
      if (outIdx >= endIdx) break;
      outU8Array[outIdx++] = u
    } else if (u <= 2047) {
      if (outIdx + 1 >= endIdx) break;
      outU8Array[outIdx++] = 192 | u >> 6;
      outU8Array[outIdx++] = 128 | u & 63
    } else if (u <= 65535) {
      if (outIdx + 2 >= endIdx) break;
      outU8Array[outIdx++] = 224 | u >> 12;
      outU8Array[outIdx++] = 128 | u >> 6 & 63;
      outU8Array[outIdx++] = 128 | u & 63
    } else {
      if (outIdx + 3 >= endIdx) break;
      outU8Array[outIdx++] = 240 | u >> 18;
      outU8Array[outIdx++] = 128 | u >> 12 & 63;
      outU8Array[outIdx++] = 128 | u >> 6 & 63;
      outU8Array[outIdx++] = 128 | u & 63
    }
  }
  outU8Array[outIdx] = 0;
  return outIdx - startIdx
}

使用:

stringToUTF8Array('abs', new Uint8Array(3), 0, 4);

Just

const buffer = thisReturnsBuffers();

const blob = new Blob([buffer], {type: 'text/plain; charset=utf-8'});

blob.text().then(text => console.log(text));

Or

const stringVal = "string here";

const blob = new Blob([stringVal], {type: 'text/plain; charset=utf-8'});

blob.arrayBuffer().then(buffer => console.log(buffer));

你们为什么要把事情搞得这么复杂?

我发现这种方法有问题，主要是因为我试图将输出写入一个文件，而它没有正确编码。由于JS似乎使用UCS-2编码(源，源)，我们需要进一步扩展这个解决方案，这是我的增强解决方案，对我来说是有效的。

我对一般文本没有任何困难，但当它变成阿拉伯语或韩语时，输出文件没有所有字符，而是显示错误字符

文件输出: ”、“单位”:“10 K”:“O©iuY喜爱”、“遵循% % {screen_name} {screen_name}”:“U”“O©iu“推特:“¤问题”、“推%{标签}”:“%{标签}’一个¤uEY喜爱”,“推特%{名称}”:“%{名称}U”xA¤uEY喜爱”},柯:{“% {followers_count}的追随者”:“% {followers_count}…X \”,“100 K +”:“100我助教”,“10 K单位”:“我e”,遵循:“\°”,“跟着% {screen_name}”:“% {screen_name}Ø\°X0”,凯西:“œ”,男:“我”,推特:“¸”,“推特%{标签}”:“%{标签}

original: ", " 10 k unit ": "万",follow: "关注"," follow百分之百分之;screen _ name} ": " {screen _ name}先生圆场,tweet: "推特"," tweet百分之百分之{hashtag} ": " {hashtag},推特的"," tweet to百分之百分之{name} ": " {name}先生推到百分之":{},ko " {followers _ count}百分之followers ": " {followers _ count}명의팔로워100 k + ": " 100 ", "만이상"," 10 k unit ": "만단위",follow: "팔로우"," follow百分之百分之{screen _ name} ": " {screen _ name}님팔로우하기",k: "천",米:"백만",tweet: "트윗"," tweet百分之百分之{hashtag} ": " {hashtag}

我从dennis的解决方案和我发现的这个帖子中获取了信息。

这是我的代码:

function encode_utf8(s) {
  return unescape(encodeURIComponent(s));
}

function decode_utf8(s) {
  return decodeURIComponent(escape(s));
}

 function ab2str(buf) {
   var s = String.fromCharCode.apply(null, new Uint8Array(buf));
   return decode_utf8(decode_utf8(s))
 }

function str2ab(str) {
   var s = encode_utf8(str)
   var buf = new ArrayBuffer(s.length); 
   var bufView = new Uint8Array(buf);
   for (var i=0, strLen=s.length; i<strLen; i++) {
     bufView[i] = s.charCodeAt(i);
   }
   return bufView;
 }

这允许我将内容保存到一个文件，而没有编码问题。

How it works: It basically takes the single 8-byte chunks composing a UTF-8 character and saves them as single characters (therefore an UTF-8 character built in this way, could be composed by 1-4 of these characters). UTF-8 encodes characters in a format that variates from 1 to 4 bytes in length. What we do here is encoding the sting in an URI component and then take this component and translate it in the corresponding 8 byte character. In this way we don't lose the information given by UTF8 characters that are more than 1 byte long.