source: trunk/gsdl3/src/java/org/greenstone/gsdl3/util/XMLConverter.java@ 3849

/*
 *    XMLConverter.java
 *    Copyright (C) 2002 New Zealand Digital Library, http://www.nzdl.org
 *
 *    This program is free software; you can redistribute it and/or modify
 *    it under the terms of the GNU General Public License as published by
 *    the Free Software Foundation; either version 2 of the License, or
 *    (at your option) any later version.
 *
 *    This program is distributed in the hope that it will be useful,
 *    but WITHOUT ANY WARRANTY; without even the implied warranty of
 *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *    GNU General Public License for more details.
 *
 *    You should have received a copy of the GNU General Public License
 *    along with this program; if not, write to the Free Software
 *    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
package org.greenstone.gsdl3.util;

// XML classes
import org.w3c.dom.Document; 
import org.w3c.dom.Node; 
import org.w3c.dom.NodeList;
import org.w3c.dom.NamedNodeMap;
import org.xml.sax.InputSource;
//import javax.xml.parsers.*;
//import org.apache.xerces.dom.TextImpl;
import org.apache.xerces.parsers.DOMParser;
import org.apache.xerces.dom.DocumentImpl; // for new Documents

// other java classes
import java.io.Reader;
import java.io.StringReader;
import java.io.File;
import java.io.FileReader;

/** XMLConverter - utitlity class for greenstone
 *
 * parses XML Strings into Documents, converts Nodes to Strings
 * different parsers have different behaviour - can experiment in here
 *
 * @author <a href="mailto:[email protected]">Katherine Don</a>
 * @version $Revision: 3849 $
 *
 */
public class XMLConverter {

    /** JAXP parser factory */
    //protected DocumentBuilderFactory doc_build_fact_=null;
    /** JAXP parser */
    //  protected DocumentBuilder doc_builder_=null;

    /** xerces parser */
    protected DOMParser parser_ = null;

    private boolean outputEscaping = true;


     /** the no-args constructor */
    public XMLConverter() {
    try {
        //doc_build_fact_ = DocumentBuilderFactory.newInstance();
        
        //doc_builder_ = doc_build_fact_.newDocumentBuilder(); 
        parser_ = new DOMParser();
    } catch (Exception e) {
        System.out.println("XMLConverter:exception "+e.getMessage());
    }
    }

    /** returns a DOM Document */
    public Document getDOM(String in) {
        
    try {
        Reader reader = new StringReader(in);
        InputSource xml_source = new InputSource(reader);
        
        // Document doc = doc_builder_.parse(xml_source);
        parser_.parse(xml_source);
        Document doc = parser_.getDocument();
        return doc;

    } catch (Exception e) {
        System.out.println("XMLConverter.getDOM(String): exception "+e.getMessage());
    }
    return null;
    }
  
    /** returns a DOM Document */
    public Document getDOM(File in) {
    try {
        
        Reader reader = new FileReader(in);
        InputSource xml_source = new InputSource(reader);
        
        //Document doc = doc_builder_.parse(xml_source);
        parser_.parse(xml_source);
        Document doc = parser_.getDocument();
        
        return doc;

    } catch (Exception e) {
        System.out.println("XMLConverter.getDOM(File): exception "+e.getMessage());
    }
    return null;
    }

    /** creates a new empty DOM Document */
    public Document newDOM() {
    // try with xerces
    Document doc = new DocumentImpl(); //doc_builder_.newDocument();
    return doc;
    }

    /** returns the Node as a String */
    public String getString(Node xmlNode)
    {
    outputEscaping = true;
    return getString(xmlNode, 0);
    }


    private String getString(Node xmlNode, int depth)
    {
    String xmlRepresentation = "";

    if (xmlNode == null)
        return "<null>";

    short nodeType = xmlNode.getNodeType();
    String nodeName = xmlNode.getNodeName();

    // Handle Element nodes
    if (nodeType == Node.ELEMENT_NODE) {
        xmlRepresentation += "\n";
        for (int i = 0; i < depth; i++)
        xmlRepresentation += "  ";

        // Write opening tag
        xmlRepresentation += "<" + nodeName;

        // Write the node attributes
        NamedNodeMap nodeAttributes = xmlNode.getAttributes();
        for (int i = 0; i < nodeAttributes.getLength(); i++) {
        Node attribute = nodeAttributes.item(i);
        xmlRepresentation += " " + attribute.getNodeName() + "=";
        xmlRepresentation += "\"" + attribute.getNodeValue() + "\"";
        }

        // If the node has no children, close the opening tag and return
        if (xmlNode.hasChildNodes() == false) {
        // This produces somewhat ugly output, but it is necessary to compensate
        // for display bugs in Netscape. Firstly, the space is needed before the
        // closing bracket otherwise Netscape will ignore some tags (<br/>, for
        // example). Also, a newline character would be expected after the tag,
        // but this causes problems with the display of links (the link text
        // will contain a newline character, which is displayed badly).
        xmlRepresentation += " />";
        return xmlRepresentation;
        }

        // Close the opening tag
        xmlRepresentation += ">";

        // Apply recursively to the children of this node
        NodeList children = xmlNode.getChildNodes();
        for (int i = 0; i < children.getLength(); i++) {
        xmlRepresentation += getString(children.item(i), depth + 1);
        }

        // Write closing tag
        if (xmlRepresentation.endsWith("\n")) {
        for (int i = 0; i < depth; i++)
            xmlRepresentation += "  ";
        }
        xmlRepresentation += "</" + nodeName + ">\n";
    }

    // Handle Text nodes
    else if (nodeType == Node.TEXT_NODE) {
        String text = xmlNode.getNodeValue();

        // Perform output escaping, if required
        if (outputEscaping) {
        text = text.replaceAll("&", "&amp;");  // Must be done first!!
        text = text.replaceAll("<", "&lt;");
        text = text.replaceAll(">", "&gt;");
        text = text.replaceAll("\"", "&quot;");
        text = text.replaceAll("\'", "&apos;");
        }

        // Remove any control-C characters
        text = text.replaceAll("" + (char) 3, "");
        xmlRepresentation += text;
    }

    // Handle Processing Instruction nodes
    else if (nodeType == Node.PROCESSING_INSTRUCTION_NODE) {
        if (nodeName == "javax.xml.transform.disable-output-escaping") {
        outputEscaping = false;
        }
        else if (nodeName == "javax.xml.transform.enable-output-escaping") {
        outputEscaping = true;
        }
        else {
        System.err.println("Warning: Unhandled processing instruction " + nodeName);
        }
    }

    // A type of node that is not handled yet
    else {
        System.err.println("Warning: Unknown node type: " + nodeType);
    }

    return xmlRepresentation;
    }
}