ut8数据库无法保存超多3个字节的utf字符，手写了一个过滤器，可指定过滤最大字符长度
UTF-8编码规则 1字节 0xxxxxxx 2字节 110xxxxx 10xxxxxx 3字节 1110xxxx 10xxxxxx 10xxxxxx 4字节 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx 5字节 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 6字节 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
实现
public static String utf8M(String str, int m) {
byte[] bytes = str.getBytes(KtIo.utf8());
int len = bytes.length;
int off = 0;
byte[] buffer = null;
byte b;
int s;
int j, k;
int lst = len - 1;
for (int i = 0; i < len; i++) {
b = bytes[i];
s = b & 0XFF;
if (s < 192) {
if (buffer != null) {
buffer[off++] = b;
}
} else {
if (s < 224) {
j = 1;
} else if (s < 240) {
j = 2;
} else if (s < 248) {
j = 3;
} else if (s < 252) {
j = 4;
} else if (b < 254) {
j = 5;
} else {
i += 6;
continue;
}
if (j < m) {
// 允许字符长度
j += i;
if (buffer != null) {
buffer[off++] = b;
k = j < lst ? j : lst;
for (i++; i <= k; i++) {
buffer[off++] = bytes[i];
}
}
i = j;
} else {
// 过滤字符长度
if (buffer == null) {
buffer = bytes;
off = i;
}
i += j;
}
}
}
return buffer == null ? str : new String(buffer, 0, off, KtIo.charset());
}
测试
public void test() throws IOException {
System.out.println(KtStr.utf8M("sda\uD83D\uDC16♎♏♐♑大啊\uD83D\uDC01\uD83D\uDC02\uD83D\uDC05\uD83D\uDC07\uD83D\uDC09\uD83D\uDC0D\uD83D\uDC0E\uD83D\uDC10\uD83D\uDC12\uD83D\uDC13\uD83D\uDC15\uD83D\uDC16子\uD83C\uDF40木\uD83C\uDF40青\uD83C\uDF40澄\uD83C\uDF40", 3));
}
