XHTMLValidator

import org.w3c.dom.*;
import javax.xml.parsers.*;
import java.io.*;
import org.xml.sax.*;


public class XHTMLValidator {

  public static void main(String[] args) {
    
    if (args.length == 0) {
       System.err.println("Usage: java XHTMLValidator URL");
       return;   
    }

    try {
      DocumentBuilderFactory builderFactory 
       = DocumentBuilderFactory.newInstance();
      builderFactory.setNamespaceAware(true);
      builderFactory.setValidating(true);
      DocumentBuilder parser 
       = builderFactory.newDocumentBuilder();
      parser.setErrorHandler(new ValidityErrorReporter());

      Document document;
      try {
        document = parser.parse(args[0]); 
        // ValidityErrorReporter prints any validity errors detected
      }
      catch (SAXException e) {  
        System.out.println(args[0] + " is not valid."); 
        return; 
      }
      
      // If we get this far, then the document is valid XML.
      // Check to see whether the document is actually XHTML    
      DocumentType doctype = document.getDoctype();
  
      if (doctype == null) {
        System.out.println("No DOCTYPE"); 
        return;
      }
  
      String name     = doctype.getName();
      String systemID = doctype.getSystemId();
      String publicID = doctype.getPublicId();
    
      if (!name.equals("html")) {
        System.out.println("Incorrect root element name " + name); 
      }
  
      if (publicID == null
       || (!publicID.equals("-//W3C//DTD XHTML 1.0 Strict//EN")
           && !publicID.equals(
                "-//W3C//DTD XHTML 1.0 Transitional//EN")
           && !publicID.equals(
                "-//W3C//DTD XHTML 1.0 Frameset//EN"))) {
        System.out.println(args[0] 
         + " does not seem to use an XHTML 1.0 DTD");
      }
  
      // Check the namespace on the root element
      Element root = document.getDocumentElement();
      String xmlnsValue = root.getAttribute("xmlns");
      if (!xmlnsValue.equals("http://www.w3.org/1999/xhtml")) {
        System.out.println(args[0] 
         + " does not properly declare the"
         + " http://www.w3.org/1999/xhtml"
         + " namespace on the root element");        
      }
      
      System.out.println(args[0] + " is valid XHTML.");
      
    }
    catch (IOException e) {
      System.err.println("Could not read " + args[0]);
    }
    catch (Exception e) {
      System.err.println(e);
      e.printStackTrace();
    }
    
  }

}