DOM based TagStripper


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


public class DOMTagStripper extends NodeIterator {

  public static void main(String[] args) {
     
    DOMParser parser = new DOMParser();
    NodeIterator iterator = new DOMTagStripper();
    
    for (int i = 0; i < args.length; i++) {
      try {
        // Read the entire document into memory
        parser.parse(args[i]); 
       
        Document d = parser.getDocument();
        iterator.followNode(d);
      }
      catch (SAXException e) {
        System.err.println(e); 
      }
      catch (IOException e) {
        System.err.println(e); 
      }
      
    }
  
  } // end main

  public void processNode(Node node) {
    
    int type = node.getNodeType();
    if (type == Node.TEXT_NODE) {
      System.out.print(node.getNodeValue());
    }
    
  }

}

Previous | Next | Top | Cafe con Leche

Copyright 2000 Elliotte Rusty Harold
elharo@metalab.unc.edu
Last Modified March 15, 2000