使用JTidy将html转化成xhtml

 

在做中间件平台的时候，其中有一步就是将html转化成xhtml，这部分由lj负责，于是乎，跑去问了问lj，得知她采用的是JTidy的一个jar文件，于是在网上搜了一下，稍作修改，完成功能是，输入文件为html，输出文件为xhtml.

具体实现如下：

（1）构建路径，引入相应的jar文件jtidy-r938.jar

（2）代码如下：

 

package beans;  import java.io.*;  import java.text.*;  import java.util.*;  import java.net.*;  import org.w3c.tidy.Configuration; import org.w3c.tidy.Tidy;  public class test  {      public static void main(String args[])     {                     testt = newtest();                         t.doTidy("c:\\hopetest\\b.html");//转化开始                 }      public void doTidy(Stringf_in)     {                 BufferedInputStream sourceIn; //输入流         ByteArrayOutputStream tidyOutStream; //输出流         try         {                       Reader reader;                            FileInputStream  fis  =  new   FileInputStream(f_in);//读文件             ByteArrayOutputStream  bos  =  new  ByteArrayOutputStream();               int  ch;               while((ch=fis.read())!=-1)               {                       bos.write(ch);               }               fis.close();               byte[]  bs  =  bos.toByteArray();               bos.close();               String hope_gb2312=new String(bs,"GB2312");//注意，默认是GB2312，所以这里先转化成GB2312然后再转化成其他的。                         byte[] hope_b=hope_gb2312.getBytes();             String basil=new String(hope_b,"utf-8");//将GB2312转化成UTF-8                          byte[]basil_b=basil.getBytes();                        ByteArrayInputStream stream = newByteArrayInputStream(basil.getBytes());             tidyOutStream = new ByteArrayOutputStream();             Tidy tidy = new Tidy();             tidy.setInputEncoding("UTF-8");             tidy.setQuiet(true);                                tidy.setOutputEncoding("UTF-8");                       tidy.setShowWarnings(false); //不显示警告信息             tidy.setIndentContent(true);//             tidy.setSmartIndent(true);             tidy.setIndentAttributes(false);             tidy.setWraplen(1024); //多长换行             //输出为xhtml             tidy.setXHTML(true);              tidy.setErrout(newPrintWriter(System.out));             tidy.parse(stream, tidyOutStream);             DataOutputStream  to=new  DataOutputStream(new  FileOutputStream("C:\\hopetest\\bb.xhtml"));  //将生成的xhtml写入              tidyOutStream.writeTo(to);             System.out.println(tidyOutStream.toString());         }         catch ( Exception ex )         {             System.out.println( ex.toString());             ex.printStackTrace();         }     }   }