Java

Java内部采用UTF-16(USC2)编码,比如:
"我" 为 98 17,
"a" 为 0 97,
" " 为 0 32,
"1" 为 0 49....

public static String cutString(String s, int length) throws Exception{
      byte[] bytes = s.getBytes("Unicode");
        int n = 0;
        int i = 2;//标志两位 [0]=-2 [1]=-1
        for (; i < bytes.length && n < length; i++) {
            if (i % 2 == 1) {
                n++;
            } else {
                if (bytes[i] != 0) {
                    n++;
                }
            }
        }
        if (i % 2 == 1) {
            if (bytes[i - 1] != 0)
                i = i - 1;
            else
                i = i + 1;
        }
        return new String(bytes, 0, i, "Unicode");
    }
原文地址:https://www.cnblogs.com/kavlez/p/4005454.html