判断文件的编码格式

package com.qing.qing.test;

import org.apache.commons.io.FileUtils;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;

import org.apache.commons.io.FileUtils;

public class TestBM {
    public static void main(String[] args) {
        String path = "D:\ytzz\ddd.txt";
        path = "D:\ytzz\ddd - 副本.txt";
        File file = new File(path);
        if(!file.exists()){
            System.out.println("not found");
            return;
        }
        try {

            String type = getFilecharset(new ByteArrayInputStream(FileUtils.readFileToByteArray(file)));

            System.out.println(type);
            byte[] bytes = FileUtils.readFileToByteArray(new File(path));
            System.out.println(new String(bytes,type));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

//判断编码格式方法
public static  String getFilecharset(ByteArrayInputStream byteArrayInputStream) {
    if (byteArrayInputStream == null) return null;
    String charset = "GBK";
    byte[] first3Bytes = new byte[3];
    try {
        boolean checked = false;
        BufferedInputStream bis = new BufferedInputStream(byteArrayInputStream);
        bis.mark(0);
        int read = bis.read(first3Bytes, 0, 3);
        if (read == -1) {
            return charset; //文件编码为 ANSI
        } else if (first3Bytes[0] == (byte) 0xFF
                && first3Bytes[1] == (byte) 0xFE) {
            charset = "UTF-16LE"; //文件编码为 Unicode
            checked = true;
        } else if (first3Bytes[0] == (byte) 0xFE
                && first3Bytes[1] == (byte) 0xFF) {
            charset = "UTF-16BE"; //文件编码为 Unicode big endian
            checked = true;
        } else if (first3Bytes[0] == (byte) 0xEF
                && first3Bytes[1] == (byte) 0xBB
                && first3Bytes[2] == (byte) 0xBF) {
            charset = "UTF-8"; //文件编码为 UTF-8
            checked = true;
        }
        bis.reset();
        if (!checked) {
            int loc = 0;
            while ((read = bis.read()) != -1) {
                loc++;
                if (read >= 0xF0)
                    break;
                if (0x80 <= read && read <= 0xBF) // 单独出现BF以下的，也算是GBK
                    break;
                if (0xC0 <= read && read <= 0xDF) {
                    read = bis.read();
                    if (0x80 <= read && read <= 0xBF) // 双字节 (0xC0 - 0xDF)
                        // (0x80
                        // - 0xBF),也可能在GB编码内
                        continue;
                    else
                        break;
                } else if (0xE0 <= read && read <= 0xEF) {// 也有可能出错，但是几率较小
                    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();
    }
    finally {
        try {
            byteArrayInputStream.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    return charset;
}

}