Search code examples
javahtmlservletstomcat7

How to print Hindi text into web page by giving servlet , java and html code

i am using servlet, java and one html code to extract hindi text from following URL : https://hi.wikipedia.org/wiki/%E0%A4%B5%E0%A4%BE%E0%A4%B0%E0%A4%BE%E0%A4%A3%E0%A4%B8%E0%A5%80

i want to display hindi font by servlet code , code is given as :

//Extraction1.java //java file
import java.io.IOException;
import java.net.URL;
import java.util.Scanner;

public class Extraction1 {

 public String toHtmlString(String url) throws IOException 
{
  StringBuilder sb = new StringBuilder();
  for(Scanner sc = new Scanner(new URL(url).openStream()); sc.hasNext(); )
  sb.append(sc.nextLine()).append('\n');
  return sb.toString();
 }
}

MultiParamServlet3.java // servlet file

import java.io.*;
import javax.servlet.*;
import javax.servlet.http.*;

public class MultiParamServlet3 extends HttpServlet
{
  private static final long serialVersionUID = 1L;

  public void doPost(HttpServletRequest req,HttpServletResponse resp) throws          ServletException,IOException
{
  PrintWriter pw=resp.getWriter();

   resp.setContentType("text/html");

   String[] values=req.getParameterValues("habits");

   Extraction1 t=new Extraction1();
   String s=t.toHtmlString(values[0]).replaceAll("\\<.*?>","");
   pw.println("<html><head><meta charset=\"utf-8\"></head><body>"+s+"</body></html>");

  pw.close(); 
 }
}

index.html // html file

  <!DOCTYPE html>
  <html>
  <head>
  <meta charset="utf-8">
  <title>Insert title here</title>
  </head>
  <body>
  <form method="Post" action="MultiParamServlet3">
  <Label> <br><br>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;      &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&n bsp;&nbsp;&nbsp;&nbsp;Enter    the URL : </label>
  <input name='habits' id='t2'>
  <input type="submit" name="submit"> 
 </form>
 </body>
 </html>

servlet program able to print english text after extraction, but hindi text converted as ????? (question mark).

how to print hindi text into web page by servlet program ?

Solution

  • You have to set encoding response.

    change "text/html" to "UTF-8".

    resp.setCharacterEncoding("UTF-8");