路遇&#x,研究一下发现就是Unicode不同之处在于%u换成了&#x,还有就是后面多了个分号。
给出转换方法,自己留着备用:
public static StringBuffer decodeUnicode(String dataStr) {
dataStr=dataStr.replace("&#x", "\\u");
final StringBuffer buffer = new StringBuffer();
String tempStr = "";
String operStr = dataStr;
if (operStr != null && operStr.indexOf("\\u") == -1)
return buffer.append(operStr);
if (operStr != null && !operStr.equals("")
&& !operStr.startsWith("\\u")) {
tempStr = operStr.substring(0, operStr.indexOf("\\u"));
operStr = operStr.substring(operStr.indexOf("\\u"), operStr
.length());
}
buffer.append(tempStr);
while (operStr != null && !operStr.equals("")
&& operStr.startsWith("\\u")) {
tempStr = operStr.substring(0, 6);
operStr = operStr.substring(7, operStr.length());
String charStr = "";
charStr = tempStr.substring(2, tempStr.length());
char letter = (char) Integer.parseInt(charStr, 16);
buffer.append(new Character(letter).toString());
if (operStr.indexOf("\\u") == -1) {
buffer.append(operStr);
} else {
tempStr = operStr.substring(0, operStr.indexOf("\\u"));
operStr = operStr.substring(operStr.indexOf("\\u"), operStr
.length());
buffer.append(tempStr);
}
}
return buffer;
}