public static String getCharset(File file) {
String charset = "GBK";
byte[] first3Bytes = new byte[3];
try {
boolean checked = false;
BufferedInputStream bis = new BufferedInputStream(
new FileInputStream(file));
bis.mark(0);
int read = bis.read(first3Bytes, 0, 3);
if (read == -1)
return charset;
if (first3Bytes[0] == (byte) 0xFF && first3Bytes[1] == (byte) 0xFE) {
charset = "UTF-16LE";
checked = true;
} else if (first3Bytes[0] == (byte) 0xFE && first3Bytes[1]
== (byte) 0xFF) {
charset = "UTF-16BE";
checked = true;
} else if (first3Bytes[0] == (byte) 0xEF && first3Bytes[1]
== (byte) 0xBB
&& first3Bytes[2] == (byte) 0xBF) {
charset = "UTF-8";
checked = true;
}
bis.reset();
if (!checked) {
int loc = 0;
while ((read = bis.read()) != -1) {
loc++;
if (read >= 0xF0)
break;
//Separately appear below BF, also be GBK
if (0x80 <= read && read <= 0xBF)
break;
if (0xC0 <= read && read <= 0xDF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF)//Double byte (0xC0-0xDF)
// (0x80 -
//0xBF), also possible within GB encoding
continue;
else
break;
//Mistakes are possible, but less likely
} else if (0xE0 <= read && read <= 0xEF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
charset = "UTF-8";
break;
} else
break;
} else
break;
}
}
System.out.println(loc + " " + Integer.toHexString(read));
}
bis.close();
} catch (Exception e) {
e.printStackTrace();
}
return charset;
}