用 Ajax 抓回來的中文變成亂碼,通常不是伺服器出了問題,而是編碼對不上。這篇示範一個完整可運作的處理流程:IE 走 responseBody 加自寫轉碼,其他瀏覽器走 overrideMimeType 直接指定來源編碼。
var http_request = false;
function makePOSTRequest(url, parameters) {
http_request = false;
if (window.XMLHttpRequest) {
http_request = new XMLHttpRequest();
if (http_request.overrideMimeType) {
http_request.overrideMimeType('text/html');
}
} else if (window.ActiveXObject) {
try {
http_request = new ActiveXObject("Msxml2.XMLHTTP");
} catch (e) {
try {
http_request = new ActiveXObject("Microsoft.XMLHTTP");
} catch (e) {}
}
}
if (!http_request) {
alert('Cannot create XMLHTTP instance');
return false;
}
http_request.onreadystatechange = alertContents;
http_request.open('POST', url, true);
http_request.setRequestHeader("Content-type", "application/x-www-form-urlencoded");
http_request.setRequestHeader("Content-length", parameters.length);
http_request.setRequestHeader("Connection", "close");
// 非 IE 瀏覽器:直接告訴瀏覽器回應的編碼
if (!Sys.ie) {
http_request.overrideMimeType("text/html;charset=gb2312");
}
http_request.send(parameters);
}
function alertContents() {
if (http_request.readyState == 4) {
if (http_request.status == 200) {
var result;
if (Sys.ie) {
result = http_request.responseBody; // 原始位元組
} else {
result = http_request.responseText;
}
document.getElementById('waiting').innerHTML = '';
if (Sys.ie) {
document.getElementById('showresults').innerHTML = gb2utf8(result);
} else {
document.getElementById('showresults').innerHTML = result;
}
} else {
alert('There was a problem with the request.');
}
} else {
document.getElementById('waiting').innerHTML = '<img src="loading.gif">';
}
}
function get(obj) {
makePOSTRequest('y.htm', '');
}
IE 拿不到正確解碼的 responseText,只能拿原始位元組自行處理。這段程式碼的做法是借用 VBScript 的 MidB / Chr 來做位元組層級的切分與重組,並用一個 glbEncode 物件快取已轉換過的字元,避免重複運算:
// IE 專用的混寫函式
function gb2utf8(data){
var glbEncode = [];
gb2utf8_data = data;
execScript("gb2utf8_data = MidB(gb2utf8_data, 1)", "VBScript");
var t = escape(gb2utf8_data)
.replace(/%u/g, "")
.replace(/(.{2})(.{2})/g, "%$2%$1")
.replace(/%([A-Z].)%(.{2})/g, "@$1$2");
t = t.split("@");
var i = 0, j = t.length, k;
while (++i < j) {
k = t[i].substring(0, 4);
if (!glbEncode[k]) {
gb2utf8_char = eval("0x" + k);
execScript("gb2utf8_char = Chr(gb2utf8_char)", "VBScript");
glbEncode[k] = escape(gb2utf8_char).substring(1, 6);
}
t[i] = glbEncode[k] + t[i].substring(4);
}
gb2utf8_data = gb2utf8_char = null;
return unescape(t.join("%"));
}
var Sys = {};
var ua = navigator.userAgent.toLowerCase();
if (window.ActiveXObject)
Sys.ie = ua.match(/msie ([\d.]+)/)[1];
else if (document.getBoxObjectFor)
Sys.firefox = ua.match(/firefox\/([\d.]+)/)[1];
else if (window.MessageEvent && !document.getBoxObjectFor)
Sys.chrome = ua.match(/chrome\/([\d.]+)/)[1];
else if (window.opera)
Sys.opera = ua.match(/opera.([\d.]+)/)[1];
else if (window.openDatabase)
Sys.safari = ua.match(/version\/([\d.]+)/)[1];
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"https://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="https://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="content-type" content="text/html; charset=gb2312" />
<title></title>
<script type="text/javascript" language="javascript" src="rsajax.js"></script>
</head>
<body>
<div align="center">
<input onclick="javascript:get(document.getElementById('acctform'));"
name="acctform" id="acctform" type="button">
<div id="waiting"></div>
<div id="showresults"></div>
</div>
</body>
</html>
整體策略是依瀏覽器能力分流:
overrideMimeType("text/html;charset=gb2312") 在 send() 之前呼叫,瀏覽器就會以 GB2312 解碼回應,responseText 直接可用。responseBody(未解碼的位元組),交給 gb2utf8() 轉成字串。註解中提到的 escape/unescape 替代方案,是早期另一種把 UTF-8 與漢字互轉的思路。readyState 還沒到 4 時顯示 loading 圖片,完成後清空。這點小細節對使用者感知的效能影響其實不小。這整套 machinery 在現在可以縮成:
fetch('y.htm')
.then(res => res.arrayBuffer()) // 先拿原始位元組
.then(buf => new TextDecoder('gb2312').decode(buf))
.then(text => {
document.getElementById('showresults').textContent = text;
});
或用 XMLHttpRequest 加 responseType,效果相同。TextDecoder 遵循 WHATWG 編碼標準,gb2312、gbk、big5 都直接支援,不必再借 VBScript 的手。
順帶一提,範例中最後把結果塞進 innerHTML 其實是有風險的——若來源內容不可信,可能形成 XSS。改用 textContent 更安全,這也是原範例裡 escape 相關註解的用意所在。
而最根本的解法依然是:讓伺服器端輸出 UTF-8,並在回應標頭與頁面 meta 上一致宣告。跨編碼轉換永遠是額外的風險與成本,能消除就消除。