美文网首页
java读取文本文件第一个字符多出一个问号解决方法

java读取文本文件第一个字符多出一个问号解决方法

作者: Jerry_dong | 来源:发表于2017-10-27 10:20 被阅读0次

转载:http://blog.csdn.net/datangxiajun/article/details/51604565

测试代码如下

package test;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.PushbackInputStream;
import java.io.Reader;
import java.nio.charset.Charset;

public class test
{

    public static void main(String[] args) throws IOException
    {
        File file = new File("D:/222.txt");
        String content=txt2String(file);
    }
    
    public static String txt2String(File file) throws IOException{
       /* InputStreamReader read = new InputStreamReader(
                new FileInputStream(file), "UTF-8");
        BufferedReader br = new BufferedReader(read);*/
        BufferedReader br = new BufferedReader(new UnicodeReader(new FileInputStream(file),Charset.defaultCharset().name()));
        StringBuilder result = new StringBuilder();
        try{
            String s = null;
            while((s = br.readLine())!=null){//使用readLine方法,一次读一行
                System.out.println(s);
                result.append(s);
            }
            br.close();    
        }catch(Exception e){
            e.printStackTrace();
        }
        return result.toString();
    }
    
    static class UnicodeReader extends Reader {  
        PushbackInputStream internalIn;  
        InputStreamReader   internalIn2 = null;  
        String              defaultEnc;  
        
        private static final int BOM_SIZE = 4;  
        
          
        UnicodeReader(InputStream in, String defaultEnc) {  
           internalIn = new PushbackInputStream(in, BOM_SIZE);  
           this.defaultEnc = defaultEnc;  
        }  
        
        UnicodeReader(InputStream in) {  
            internalIn = new PushbackInputStream(in, BOM_SIZE);  
         }
        
        public String getDefaultEncoding() {  
           return defaultEnc;  
        }  
        
          
        public String getEncoding() {  
           if (internalIn2 == null) return null;  
           return internalIn2.getEncoding();  
        }  
        
          
        protected void init() throws IOException {  
           if (internalIn2 != null) return;  
        
           String encoding;  
           byte bom[] = new byte[BOM_SIZE];  
           int n, unread;  
           n = internalIn.read(bom, 0, bom.length);  
        
           if ( (bom[0] == (byte)0x00) && (bom[1] == (byte)0x00) &&  
                       (bom[2] == (byte)0xFE) && (bom[3] == (byte)0xFF) ) {  
              encoding = "UTF-32BE";  
              unread = n - 4;  
           } else if ( (bom[0] == (byte)0xFF) && (bom[1] == (byte)0xFE) &&  
                       (bom[2] == (byte)0x00) && (bom[3] == (byte)0x00) ) {  
              encoding = "UTF-32LE";  
              unread = n - 4;  
           } else if (  (bom[0] == (byte)0xEF) && (bom[1] == (byte)0xBB) &&  
                 (bom[2] == (byte)0xBF) ) {  
              encoding = "UTF-8";  
              unread = n - 3;  
           } else if ( (bom[0] == (byte)0xFE) && (bom[1] == (byte)0xFF) ) {  
              encoding = "UTF-16BE";  
              unread = n - 2;  
           } else if ( (bom[0] == (byte)0xFF) && (bom[1] == (byte)0xFE) ) {  
              encoding = "UTF-16LE";  
              unread = n - 2;  
           } else {  
              // Unicode BOM mark not found, unread all bytes  
              encoding = defaultEnc;  
              unread = n;  
           }      
           //System.out.println("read=" + n + ", unread=" + unread);  
        
           if (unread > 0) internalIn.unread(bom, (n - unread), unread);  
        
           // Use given encoding  
           if (encoding == null) {  
              internalIn2 = new InputStreamReader(internalIn);  
           } else {  
              internalIn2 = new InputStreamReader(internalIn, encoding);  
           }  
        }  
        
        public void close() throws IOException {  
           init();  
           internalIn2.close();  
        }  
        
        public int read(char[] cbuf, int off, int len) throws IOException {  
           init();  
           return internalIn2.read(cbuf, off, len);  
        }  
        
      }  

}

相关文章

网友评论

      本文标题: java读取文本文件第一个字符多出一个问号解决方法

      本文链接:https://www.haomeiwen.com/subject/nzkrpxtx.html