source: trunk/gli/src/org/greenstone/gatherer/util/XMLTools.java@ 8014

package org.greenstone.gatherer.util;


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


/** This class is a static class containing useful XML functions */
public class XMLTools
{
    static public ArrayList getChildElementsByTagName(Element parent_element, String element_name)
    {
    ArrayList child_elements = new ArrayList();

    NodeList children_nodelist = parent_element.getChildNodes();
    for (int i = 0; i < children_nodelist.getLength(); i++) {
        Node child_node = children_nodelist.item(i);
        if (child_node.getNodeType() == Node.ELEMENT_NODE && child_node.getNodeName().equals(element_name)) {
        child_elements.add(child_node);
        }
    }

    return child_elements;
    }


    static public String getElementTextValue(Element element)
    {
    // Find the first text node child
    NodeList children_nodelist = element.getChildNodes();
    for (int i = 0; i < children_nodelist.getLength(); i++) {
        Node child_node = children_nodelist.item(i);
        if (child_node.getNodeType() == Node.TEXT_NODE) {
        return child_node.getNodeValue();
        }
    }

    // None found
    return null;
    }


    /** Method to retrieve the value of a given node.
     * @param element The <strong>Element</strong> whose value we wish to find.
     * Soon to be deprecated!
     */
    static final public String getValue(Node element) {
    // If we've been given a subject node first retrieve its value node.
    if(element.getNodeName().equals("Subject")) {
        element = getNodeFromNamed(element, "Value");
    }
    // If we've got a value node, then reconstruct the text. Remember that DOM will split text over 256 characters into several text nodes
    if(element != null && element.hasChildNodes()) {
        StringBuffer text_buffer = new StringBuffer();
        NodeList text_nodes = element.getChildNodes();
        for(int i = 0; i < text_nodes.getLength(); i++) {
        Node possible_text = text_nodes.item(i);
        if(possible_text.getNodeName().equals(StaticStrings.TEXT_NODE)) {
            text_buffer.append(possible_text.getNodeValue());
        }
        }
        return text_buffer.toString();
    }
    return "";
    }


    /** Method to retrieve from the node given, a certain child node with the specified name.
     * @param parent The <strong>Node</strong> whose children should be searched.
     * @param name The required nodes name as a <strong>String</strong>.
     * @return The requested <strong>Node</strong> if it is found, <i>null</i> otherwise.
     * Soon to be deprecated!
     */ 
    static final public Node getNodeFromNamed(Node parent, String name) {
    Node child = null;
    for(Node i = parent.getFirstChild(); i != null && child == null; 
        i = i.getNextSibling()) {
        if(i.getNodeName().equals(name)) {
        child = i;
        }
    }
    return child;
    }


    /** Parse an XML document from a given file */
    static public Document parseXMLFile(File xml_file)
    {
    Document document = null;

    try {
        FileInputStream fis   = new FileInputStream(xml_file);
        InputStreamReader isr = new InputStreamReader(fis, "UTF-8");
        Reader r              = new BufferedReader(isr);
        InputSource isc       = new InputSource(r);
        DOMParser parser      = new DOMParser();
        parser.setFeature("http://xml.org/sax/features/validation", false);
        parser.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
        // May or may not be ignored, the documentation for Xerces is contradictory. If it works then parsing -should- be faster.
        parser.setFeature("http://apache.org/xml/features/dom/defer-node-expansion", true);
        parser.setFeature("http://apache.org/xml/features/dom/include-ignorable-whitespace", false);
        parser.parse(isc);
        document = parser.getDocument();
        isr.close();
        fis.close();
    }
    catch (Exception exception) {
        exception.printStackTrace();
    }

    return document;
    }


    /** Write an XML document to a given file */
    static public void writeXMLFile(File xml_file, Document document)
    {
    try {
        OutputStream os = new FileOutputStream(xml_file);
        // Create an output format for our document.
        OutputFormat f = new OutputFormat(document);
        f.setEncoding("UTF-8");
        f.setIndenting(true);
        f.setLineWidth(0); // Why isn't this working!
        f.setPreserveSpace(false);
        // Create the necessary writer stream for serialization.
        OutputStreamWriter osw = new OutputStreamWriter(os, "UTF-8");
        Writer w               = new BufferedWriter(osw);
        // Generate a new serializer from the above.
        XMLSerializer s        = new XMLSerializer(w, f);
        s.asDOMSerializer();
        // Finally serialize the document to file.
        s.serialize(document);
        // And close.
        os.close();
    }
    catch (Exception exception) {
        exception.printStackTrace();
    }
    }
}