十六、檢測txt檔案的編碼格式
阿新 • • 發佈:2019-01-03
private static String detectCodeFormate(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) {
//檔案編碼為 ANSI
return charset;
} else if (first3Bytes[0] == (byte) 0xFF && first3Bytes[1] == (byte) 0xFE) {
//檔案編碼為 Unicode
charset = "UTF-16LE";
checked = true;
} else if (first3Bytes[0] == (byte) 0xFE && first3Bytes[1] == (byte) 0xFF) {
//檔案編碼為 Unicode big endian
charset = "UTF-16BE";
checked = true;
} else if (first3Bytes[0] == (byte) 0xEF && first3Bytes[1] == (byte) 0xBB
&& first3Bytes[2] == (byte) 0xBF) {
//檔案編碼為 UTF-8
charset = "UTF-8";
checked = true;
}
bis.reset();
if (!checked) {
int loc = 0;
while ((read = bis.read()) != -1) {
loc++;
if (read >= 0xF0){
break;
}
// 單獨出現BF以下的,也算是GBK
if (0x80 <= read && read <= 0xBF)
{break;}
if (0xC0 <= read && read <= 0xDF) {
read = bis.read();
// 雙位元組 (0xC0 - 0xDF)
if (0x80 <= read && read <= 0xBF) {
// (0x80 - 0xBF),也可能在GB編碼內
continue;
}
else {
break;
}
} else if (0xE0 <= read && read <= 0xEF) {// 也有可能出錯,但是機率較小
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
charset = "UTF-8";
break;
} else {
break;
}
} else {
break;
}
}
}
}
bis.close();
} catch (Exception e) {
e.printStackTrace();
}
return charset;
}