是否有一种普遍接受的技术可以有效地将JavaScript字符串转换为arraybuffer,反之亦然?具体来说,我希望能够将ArrayBuffer的内容写入localStorage,然后再将其读回来。
当前回答
var decoder = new TextDecoder ();
var string = decoder.decode (arrayBuffer);
参见https://developer.mozilla.org/en-US/docs/Web/API/TextDecoder/decode
其他回答
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"
Blob比String.fromCharCode(null,array)慢得多;
但如果数组缓冲区太大,就会失败。我发现的最佳解决方案是使用String.fromCharCode(null,数组);并将其拆分为不会破坏堆栈的操作,但每次比单个char更快。
大数组缓冲区的最佳解决方案是:
function arrayBufferToString(buffer){
var bufView = new Uint16Array(buffer);
var length = bufView.length;
var result = '';
var addition = Math.pow(2,16)-1;
for(var i = 0;i<length;i+=addition){
if(i + addition > length){
addition = length - i;
}
result += String.fromCharCode.apply(null, bufView.subarray(i,i+addition));
}
return result;
}
我发现这比使用blob快20倍。它也适用于超过100mb的大字符串。
atob()返回的“本机”二进制字符串是一个每个字符1字节的数组。
所以我们不应该在一个字符中存储2个字节。
var arrayBufferToString = function(buffer) {
return String.fromCharCode.apply(null, new Uint8Array(buffer));
}
var stringToArrayBuffer = function(str) {
return (new Uint8Array([].map.call(str,function(x){return x.charCodeAt(0)}))).buffer;
}
尽管Dennis和gengkev使用Blob/FileReader的解决方案有效,但我不建议采用这种方法。这是一种解决简单问题的异步方法,比直接解决方案要慢得多。我在html5rocks上发布了一个更简单(更快)的解决方案: http://updates.html5rocks.com/2012/06/How-to-convert-ArrayBuffer-to-and-from-String
解决方案是:
function ab2str(buf) {
return String.fromCharCode.apply(null, new Uint16Array(buf));
}
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;
}
编辑:
Encoding API帮助解决字符串转换问题。请查看Jeff Posnik在Html5Rocks.com上对上述原创文章的回复。
摘录:
Encoding API使原始字节和原生JavaScript字符串之间的转换变得简单,而不考虑需要使用的许多标准编码中的哪一种。
<pre id="results"></pre>
<script>
if ('TextDecoder' in window) {
// The local files to be fetched, mapped to the encoding that they're using.
var filesToEncoding = {
'utf8.bin': 'utf-8',
'utf16le.bin': 'utf-16le',
'macintosh.bin': 'macintosh'
};
Object.keys(filesToEncoding).forEach(function(file) {
fetchAndDecode(file, filesToEncoding[file]);
});
} else {
document.querySelector('#results').textContent = 'Your browser does not support the Encoding API.'
}
// Use XHR to fetch `file` and interpret its contents as being encoded with `encoding`.
function fetchAndDecode(file, encoding) {
var xhr = new XMLHttpRequest();
xhr.open('GET', file);
// Using 'arraybuffer' as the responseType ensures that the raw data is returned,
// rather than letting XMLHttpRequest decode the data first.
xhr.responseType = 'arraybuffer';
xhr.onload = function() {
if (this.status == 200) {
// The decode() method takes a DataView as a parameter, which is a wrapper on top of the ArrayBuffer.
var dataView = new DataView(this.response);
// The TextDecoder interface is documented at http://encoding.spec.whatwg.org/#interface-textdecoder
var decoder = new TextDecoder(encoding);
var decodedString = decoder.decode(dataView);
// Add the decoded file's text to the <pre> element on the page.
document.querySelector('#results').textContent += decodedString + '\n';
} else {
console.error('Error while requesting', file, this);
}
};
xhr.send();
}
</script>
stringToArrayBuffer(byteString) {
var byteArray = new Uint8Array(byteString.length);
for (var i = 0; i < byteString.length; i++) {
byteArray[i] = byteString.codePointAt(i);
}
return byteArray;
}
arrayBufferToString(buffer) {
var byteArray = new Uint8Array(buffer);
var byteString = '';
for (var i = 0; i < byteArray.byteLength; i++) {
byteString += String.fromCodePoint(byteArray[i]);
}
return byteString;
}