import org.apache.xerces.parsers.*;
import org.w3c.dom.*;
import org.xml.sax.*;
import java.io.IOException;
import java.util.StringTokenizer;

/**
 * SAX - example that counts the words of an xml input file
 * Call: % java SAXWordCount inputFile.xml
 */
public class SAXWordCount implements ContentHandler {

  private int numWords;
    
  public void startDocument() throws SAXException {
    this.numWords = 0; 
  }

  public void endDocument() throws SAXException {
    System.out.println(numWords + " words");
    System.out.flush();
  }
  
  private StringBuffer sb = new StringBuffer();
  
  public void characters(char[] text, int start, int length) 
   throws SAXException {
    
    sb.append(text, start, length);
    
  }
  
  private void flush() {
    numWords += countWords(sb.toString());
    sb = new StringBuffer();    
  }
  
  // methods that signify a word break
  public void startElement(String namespaceURI, String localName,
	 String rawName, Attributes atts) throws SAXException {
    this.flush(); 
  }
  
  public void endElement(String namespaceURI, String localName,
	 String rawName) throws SAXException {
    this.flush(); 
  }
  
  public void processingInstruction(String target, String data)
   throws SAXException {
    this.flush(); 
  }

  // methods that aren't necessary in this example
  public void startPrefixMapping(String prefix, String uri) 
   throws SAXException {
    // ignore; 
  }

  public void ignorableWhitespace(char[] text, int start, int length)
   throws SAXException {
    // ignore; 
  }
  
  public void endPrefixMapping(String prefix) throws SAXException {
    // ignore; 
  }

  public void skippedEntity(String name) throws SAXException {
    // ignore; 
  }   
  
  public void setDocumentLocator(Locator locator) {}

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

  public static void main(String[] args) {
     
    SAXParser parser = new SAXParser();
    SAXWordCount counter = new SAXWordCount();
    parser.setContentHandler(counter);
    
    for (int i = 0; i < args.length; i++) {
      try {
        parser.parse(args[i]); 
      }
      catch (SAXException e) {
        System.err.println(e); 
      }
      catch (IOException e) {
        System.err.println(e); 
      }
      
    }
  
  } // end main

}