JAVA讀取不同編碼格式的TXT文件

  最近做一個全文檢索的功能，要求在用戶上傳附件時獲取其內容存入數據庫，CSV,EXCEL,WORD,PPT都搞定了。剩餘一個最簡單的TXT文檔，開始忽略了它還有不同編碼，導致一些編碼格式的文本亂碼。兼容寫法如下，一個判斷文件頭的方法搞定所有。



    

    privateString getCharset(String fileName) throws IOException{
      
          BufferedInputStream bin = new BufferedInputStream(newFileInputStream(fileName));  
          int p = (bin.read() << 8) +bin.read();  
          
          String code = null;  
          
          switch (p) {  
              case 0xefbb:  
                  code = "UTF-8";  
                  break;  
              case 0xfffe:  
                  code = "Unicode";  
                  break;  
              case 0xfeff:  
                  code = "UTF-16BE";  
                  break;  
              default:  
                  code = "GBK";  
          }  
          return code;
    }
    
    
    publicString getTextFromText(String filePath){
      
         try {
            InputStreamReader isr = new InputStreamReader(newFileInputStream(filePath),getCharset(filePath));
            BufferedReader br = newBufferedReader(isr);
            
             StringBuffer sb = new StringBuffer();  
             String temp = null;   
             while((temp = br.readLine()) != null){  
                 sb.append(temp);   
             }   
             br.close();       
             return sb.toString();   
         } catch (FileNotFoundException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
            
         }catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
         }   
         return null;
    }