java 读取文件设定字符集_java读取文件字符集示例方法

代码如下:

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;

//单独出现BF以下的，也算是GBK

if (0x80