Find the first text descendent node of an element : DOM Node « XML « Java






Find the first text descendent node of an element

      
/*
 * Copyright (C) 2001  Christian Cryder [christianc@granitepeaks.com]
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library 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
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 * $Id: DOMUtil.java 114 2005-12-09 15:51:51Z christianc $
 */

import java.io.IOException;
import java.io.OutputStream;
import java.io.PrintWriter;
import java.util.Iterator;

import org.w3c.dom.Attr;
import org.w3c.dom.CharacterData;
import org.w3c.dom.Comment;
import org.w3c.dom.DOMException;
import org.w3c.dom.Element;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.w3c.dom.Text;

/**
 * DOM related utility functions.
 */
public class DOMUtil {

    private static byte[] sep = System.getProperty("line.separator").getBytes();

    /**
     * Find the first text descendent node of an element.
     * This recursively looks more than one level to search
     * for text in font nodes, etc.
     *
     * @param node The starting node for the search.
     * @return The text node or null if not found.
     */
    public static Text findFirstText(Node node) {
        if (node instanceof Text) return (Text) node;
        for (Node child = node.getFirstChild(); child!=null; child = child.getNextSibling()) {
            Text text = findFirstText(child);
            if (text!=null) return text;
        }
        return null;
    }

    /**
     * Gets the first text descendent node of an element.
     * This recursively looks more than one level to search
     * for text in font nodes, etc. Throws a DOMException
     * if the Text object is not found.
     *
     * @param node The starting node for the search.
     * @return The text node or null if not found.
     * @throws DOMException if the Text object is not found
     */
    public static Text getFirstText(Node node) {
        Text text = findFirstText(node);
        if (text==null) {
            String msg = "No child text mode found for element";
            String id = getID(node);
            throw new DOMException((short) -1, msg+(id!=null ? "; id=\""+id+"\"" : ""));
        }
        return text;
    }



    /**
     * Automatically set text in a Node. Basically we find the first
     * Text node beneath the current node and replace it with a
     * CDATASection for the incoming text. All other Text nodes are
     * removed. Throws a DOMException if it's illegal to add a Text
     * child to the particular node.
     *
     * @param node the starting node for the search.
     * @param text the text to be set
     * @param allowMarkupInText whether to allow markup in text to pass through unparsed
     * @return the updated node
     * @throws DOMException if the Text object is not found
     */
    public static Node setTextInNode(Node node, String text, boolean allowMarkupInText) {
        //start by setting the value in the first text node we find with a comment
        Comment comment = node.getOwnerDocument().createComment("");
        Node newNode = null;
        
        //csc_092701.1 - support both encoded/unencoded text
        if (allowMarkupInText) newNode = node.getOwnerDocument().createCDATASection(text);
        else newNode = node.getOwnerDocument().createTextNode(text);
//System.out.println ("newNode: "+newNode);
        
        Text textComp = DOMUtil.findFirstText((Element) node);
//System.out.println ("textComp:"+textComp);        
        if (textComp==null) {
            node.appendChild(comment);
        } else {
            Node parent = textComp.getParentNode();
            parent.replaceChild(comment, textComp);
        }
        
        //now remove all the rest of the text nodes
        removeAllTextNodes(node);        

        //now replace the comment with the newNode
        Node parent = comment.getParentNode();
        parent.replaceChild(newNode, comment);
//System.out.println ("parent:  "+parent);        
//System.out.println ("result:  "+DOMUtil.findFirstText((Element) parent));        
//DOMUtil.printStackTrace(parent.getOwnerDocument().getDocumentElement());
        return node;
    }
    
    /**
     * Remove all text nodes below this node
     *
     * @param node The starting node for the search.
     */
    public static void removeAllTextNodes(Node node) {
        if (node==null) return;
        if (!node.hasChildNodes()) return;
        NodeList nl = node.getChildNodes();
        for (int i=nl.getLength()-1; i>=0; i--) {
            Node n = (Node) nl.item(i);        
            if (n instanceof Text) node.removeChild(n);
            else removeAllTextNodes(n);
        }
    }
    
    /**
     * Given a Node name, return the "id" attribute if it exists.
     * If it does not exist, return null instead. This is basically
     * just a convenience method to cast the node to element and 
     * return the id from that.
     *
     * @param node the node name in question
     * @return the id value for the given node, if it exists. null if 
     *        doesn't
     */
    public static String getID(Node node) {
        return getID(node, null);
    }

    /**
     * Given a Node, return the "id" attribute if it exists.
     * If it does not exist, return nullResponse instead. This is basically
     * just a convenience method to cast the node to element and 
     * return the id from that.
     *
     * @param node the node in question
     * @param nullResponse the response to be returned if the id attribute
     *        does not exist
     * @return the id value for the given node, if it exists. null if 
     *        doesn't
     */
    public static String getID(Node node, String nullResponse) {
        String nodeName = nullResponse;
        if (node instanceof Element) {
            nodeName = ((Element) node).getAttribute("id");
        }
        return nodeName;
    }



    protected static void print(OutputStream out, String s) {
        if (out!=null) try {
            out.write(s.getBytes());
            out.write(sep);
        } catch (IOException ioe) {}
    }
}

   
    
    
    
    
    
  








Related examples in the same category

1.DOM Node query
2.Getting Elements with DOM
3.Getting Attributes with DOM
4.Getting the Root Element in a DOM Document
5.Getting a Node Relative to Another Node in a DOM Document
6.Verbose DOM Parser
7.Getting the Notations in a DOM Document
8.Getting the Declared Entities in a DOM Document
9.Use DOM parser to deal with XML document with attributes
10.List an XML document with DOM parser
11.Removing All the Attributes in a DOM Element
12.Listing All the Attributes of a DOM Element
13.Adding and Removing an Attribute in a DOM Element
14.Getting and Setting an Attribute in a DOM Element
15.Changing the Name of a DOM Element
16.Visiting All the Elements in a DOM Document
17.Remove all attributes by first making a copy of the attribute names and then using the list to remove the attributes:
18.Removing a Node from a DOM Document
19.Remove All nodes
20.Getting a DOM Element by Id
21.Determining If an Attribute Was Supplied in a DOM Element
22.DOM serializer
23.Add a text node to the element
24.Add a text node to the beginning of the element
25.Add a text node before the last child of the element
26.Add another element after the first child of the root element
27.Add a text node in front of the new item element
28.Adding a CDATA Section to a DOM Document
29.Accessing attributes of an element
30.Get the W3C NodeList instance associated with the XPath selection supplied
31.Get the W3C Node instance associated with the XPath selection supplied
32.Convert Hashtable to a Node
33.Convert NodeList To Node Array
34.Returns a Properties object matching the given node
35.Returns a list of value for the given node
36.Returns the value of the attribute of the given element
37.Returns the value of the child node with the given name
38.Returns the value of the given node
39.Simplified implementation of a Node from a Document Object Model (DOM)
40.Extract all text children of an element
41.Extract the textual content from a Node.
42.Returns a first child DOM Node of type ELEMENT_NODE for the specified Node
43.Remove this node from its parent.
44.Find Node
45.Set or replace the text value
46.Gets the first child element of a node.
47.Gets the last child element of a node.
48.Gets the next sibling of a node that is an element.
49.Gets the first element with the specified qualified name that is descendant of e.
50.NodeList to List
51.Get Text from Node
52.Get text value from Node
53.Get text value by tag name
54.Wrap Node List to Collection