读取.dat文件 中文是乱码 该怎么解决

[ADC_VN]

先说一下我的情况。
dat文件700多M，包含很多的网页。我的程序如下：

import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
 

public class Reader {
  
    public static void readTxtFile(String filePath){
        try {
                String encoding="GBK";
                File file=new File(filePath);
                encoding= getFilecharset(file);
                
                if(file.isFile() && file.exists()){ //判断文件是否存在
                    InputStreamReader read = new InputStreamReader(
                    new FileInputStream(file),encoding);//考虑到编码格式
                    BufferedReader bufferedReader = new BufferedReader(read);
                    String lineTxt = null;
                    while((lineTxt = bufferedReader.readLine()) != null){
                        System.out.println(lineTxt);
                    }
                    read.close();
        }else{
            System.out.println("找不到指定的文件");
        }
        } catch (Exception e) {
            System.out.println("读取文件内容出错");
            e.printStackTrace();
        }
     
    }
    private static  String getFilecharset(File sourceFile) {
    	  String charset = "GBK";
    	  byte[] first3Bytes = new byte[3];
    	  try {
    	   boolean checked = false;
    	   BufferedInputStream bis = new BufferedInputStream(new FileInputStream(sourceFile));
    	   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();
    	  }
    	  return charset;
    	 }
    
    
    public static void main(String argv[]){
        String filePath = "E:\\dataset_604494\\604494\\cwt_quark_70thousand.dat";
//      "res/";
        readTxtFile(filePath);
    }
   }

部分运行结果如下：

url: http://yule.sohu.com/20071207/n253862872.shtml
date: Sun, 06 Jan 2008 07:17:40 GMT
ip: 162.105.146.2
unzip-length: 120233
length: 28392

x滌介w堑8鴻:G?姢I葚I婔p嶕灱<IN騸巼??l@癶雹3哝蠣??刷D堚撅獺奣鋆r靫枫尿?uk楫薨壥媑?I牷曛蓐汁[U窞<~黋嘾??
宵缇鎄4姦獜煄噅匱鑄恃濌夓鹵X?$?H^?9較挥楂輓椵??宝茷寀ы乆O璤蕮縊噧лk?v急镠??秀蓍*At	?G?筴%WFS趋齔N湲丳<U?
膫醜拙f9???盚#煪柣B鯍S躻,?J?q(僪q賋>↑筯鳷呅秝?庛荖痌掲??|鞓袡堳銫0&
ぢ県?埬挕}G鋎)刜g84#K?降N&T<?%-0犄:序L篑?禪

[业余草]

你换一种编码，utf-8试一试

[ADC_VN]

引用 1 楼 xmt1139057136 的回复:

你换一种编码，utf-8试一试

中文全是问号