JDOM Example

import org.jdom.*;
import org.jdom.input.SAXBuilder;
import java.util.*;


public class JDOMWordCount {

  public static void main(String[] args) {
  
    if (args.length == 0) {
      System.out.println("Usage: java JDOMWordCount URL1 URL2..."); 
    } 
      
    SAXBuilder builder = new SAXBuilder();
     
    // start parsing... 
    for (int i = 0; i < args.length; i++) {
      
      // command line should offer URIs or file names
      try {
        Document doc = builder.build(args[i]);
        Element root = doc.getRootElement();
        int numWords = countWordsInElement(root);
        System.out.println(numWords + " words");

      }
      catch (JDOMException e) { // indicates a well-formedness or other error
        System.out.println(args[i] + " is not well formed.");
        System.out.println(e.getMessage());
      }
      
    }   
  
  }

  public static int countWordsInElement(Element element) {
    
    int numWords = 0;
    
    List children = element.getContent();
    Iterator iterator = children.iterator();
    while (iterator.hasNext()) {
      Object o = iterator.next();
      if (o instanceof Text) {
        numWords += countWordsInString((Text) o);
      } 
      else if (o instanceof Element) {
        // note use of recursion
        numWords += countWordsInElement((Element) o); 
      } 
    }
    
    return numWords;  
    
  }

  private static int countWordsInString(Text text) {
    
    if (text == null) return 0;
    String s = text.getText();
    s = s.trim();
    if (s.length() == 0) return 0;
    
    StringTokenizer st = new StringTokenizer(s);
    return st.countTokens();
    
  }

}

% java JDOMWordCount hotcop.xml
16 words