DataOutputStream
static int writeUTF(String str, DataOutput out) throws IOException {
int strlen = str.length();
int utflen = 0;
int c, count = 0;
/* use charAt instead of copying String to char array */
for (int i = 0; i < strlen; i++) {
c = str.charAt(i);
if ((c >= 0x0001) && (c <= 0x007F)) {
utflen++;
} else if (c > 0x07FF) {
utflen += 3;
} else {
utflen += 2;
}
}
if (utflen > 65535)
throw new UTFDataFormatException(
"encoded string too long: " + utflen + " bytes");
byte[] bytearr = null;
if (out instanceof DataOutputStream) {
DataOutputStream dos = (DataOutputStream)out;
if(dos.bytearr == null || (dos.bytearr.length < (utflen+2)))
dos.bytearr = new byte[(utflen*2) + 2];
bytearr = dos.bytearr;
} else {
bytearr = new byte[utflen+2];
}
// 将字符串的字节长度写入流中
bytearr[count++] = (byte) ((utflen >>> 8) & 0xFF);
bytearr[count++] = (byte) ((utflen >>> 0) & 0xFF);
int i=0;
for (i=0; i
c = str.charAt(i);
if (!((c >= 0x0001) && (c <= 0x007F))) break;
bytearr[count++] = (byte) c;
}
for (;i < strlen; i++){
c = str.charAt(i);
if ((c >= 0x0001) && (c <= 0x007F)) {
bytearr[count++] = (byte) c;
} else if (c > 0x07FF) {
bytearr[count++] = (byte) (0xE0 | ((c >> 12) & 0x0F));
bytearr[count++] = (byte) (0x80 | ((c >> 6) & 0x3F));
bytearr[count++] = (byte) (0x80 | ((c >> 0) & 0x3F));
} else {
bytearr[count++] = (byte) (0xC0 | ((c >> 6) & 0x1F));
bytearr[count++] = (byte) (0x80 | ((c >> 0) & 0x3F));
}
}
out.write(bytearr, 0, utflen+2);
// 写入的长度在字符串中增加了2,即字节长度标识所占用的资源
return utflen + 2;
}
DataInputStream
public final static String readUTF(DataInput in) throws IOException {
// 读取字符串字节长度
int utflen = in.readUnsignedShort();
//...
}
实际上在调用writeUTF写入时jdk内部有将字符串的字节数写入流中,读取时先读取到字节长度,按照指定的字节长度读取出相应的字符串。