略做修改。
public class Unicode {
// java 读入unicode string,示例: 2013年5月5日
public static void main(String[] args) {
String a = "2013\\u5e745\\u67085\\u65e5";
String b = readUnicodeStr2(a);
System.out.println(b);
}
// java 读入unicode string,示例: \u674e\u661f
public static String readUnicodeStr(String unicodeStr) {
StringBuilder buf = new StringBuilder();
// 因为java转义和正则转义,所以u要这么写
String[] cc = unicodeStr.split("\\\\u");
for (String c : cc) {
if (c.equals(""))
continue;
int cInt = Integer.parseInt(c, 16);
char cChar = (char) cInt;
buf.append(cChar);
}
return buf.toString();
}
// java 读入unicode,增加对unicode串中包含的英文的处理,示例:tb\u674ea\u661fb
public static String readUnicodeStr2(String unicodeStr) {
StringBuilder buf = new StringBuilder();
for (int i = 0; i < unicodeStr.length(); i++) {
char char1 = unicodeStr.charAt(i);
if (char1 == '\\' && isUnicode(unicodeStr, i)) {
String cStr = unicodeStr.substring(i + 2, i + 6);
int cInt = Integer.parseInt(cStr, 16);
buf.append((char) cInt);
// 跨过当前unicode码,因为还有i++,所以这里i加5,而不是6
i = i + 5;
} else {
buf.append(char1);
}
}
return buf.toString();
}
// 判断以index从i开始的串,是不是unicode码
private static boolean isUnicode(String unicodeStr, int i) {
int len = unicodeStr.length();
int remain = len - i;
// unicode码,反斜杠后还有5个字符 uxxxx
if (remain < 5)
return false;
char flag2 = unicodeStr.charAt(i + 1);
if (flag2 != 'u')
return false;
String nextFour = unicodeStr.substring(i + 2, i + 6);
return isHexStr(nextFour);
}
/** hex str 0-9 a-f A-F */
private static boolean isHexStr(String str) {
for (int i = 0; i < str.length(); i++) {
char ch = str.charAt(i);
boolean isHex = (ch >= '0' && ch <= '9' || ch >= 'a' && ch <= 'f' || ch >= 'A'
&& ch <= 'F');
if (!isHex) {
return false;
}
}
return true;
}
}