Java XML Element Text getContent(Element e)

Description

Return the content of the given element.

License

Open Source License

Declaration

public static String getContent(Element e) 

Method Source Code

//package com.java2s;
/*//from www  .j  a  v  a 2 s .  co  m
 * ====================
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER.
 *
 * Copyright 2008-2009 Sun Microsystems, Inc. All rights reserved.
 *
 * The contents of this file are subject to the terms of the Common Development
 * and Distribution License("CDDL") (the "License").  You may not use this file
 * except in compliance with the License.
 *
 * You can obtain a copy of the License at
 * http://opensource.org/licenses/cddl1.php
 * See the License for the specific language governing permissions and limitations
 * under the License.
 *
 * When distributing the Covered Code, include this CDDL Header Notice in each file
 * and include the License file at http://opensource.org/licenses/cddl1.php.
 * If applicable, add the following below this CDDL Header, with the fields
 * enclosed by brackets [] replaced by your own identifying information:
 * "Portions Copyrighted [year] [name of copyright owner]"
 * ====================
 */

import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.Text;

public class Main {
    /**
     * Return the content of the given element.
     * <p/>
     * We will descend to an arbitrary depth looking for the first text node.
     * <p/>
     * Note that the parser may break what was originally a single string of
     * pcdata into multiple adjacent text nodes. Xerces appears to do this when
     * it encounters a '$' in the text, not sure if there is specified behavior,
     * or if its parser specific.
     * <p/>
     * Here, we will congeal adjacent text nodes.
     * <p/>
     * We will NOT ignore text nodes that have only whitespace.
     */
    public static String getContent(Element e) {

        String content = null;

        if (e != null) {

            // find the first inner text node,
            Text t = findText(e, false);
            if (t != null) {
                // we have at least some text
                StringBuilder b = new StringBuilder();
                while (t != null) {
                    b.append(t.getData());
                    Node n = t.getNextSibling();

                    t = null;
                    if (n != null && ((n.getNodeType() == Node.TEXT_NODE)
                            || (n.getNodeType() == Node.CDATA_SECTION_NODE))) {
                        t = (Text) n;
                    }
                }
                content = b.toString();
            }
        }

        return content;
    }

    /**
     * Locate the first text node at any level below the given node. If the
     * ignoreEmpty flag is true, we will ignore text nodes that contain only
     * whitespace characteres.
     * <p/>
     * Note that if you're trying to extract element content, you probably don't
     * want this since parser's can break up pcdata into multiple adjacent text
     * nodes. See getContent() for a more useful method.
     */
    private static Text findText(Node node, boolean ignoreEmpty) {

        Text found = null;

        if (node != null) {

            if (node.getNodeType() == Node.TEXT_NODE || node.getNodeType() == Node.CDATA_SECTION_NODE) {

                Text t = (Text) node;
                if (!ignoreEmpty) {
                    found = t;
                } else {
                    String s = t.getData().trim();
                    if (s.length() > 0) {
                        found = t;
                    }
                }
            }

            if (found == null) {

                for (Node child = node.getFirstChild(); child != null
                        && found == null; child = child.getNextSibling()) {

                    found = findText(child, ignoreEmpty);
                }
            }
        }

        return found;
    }
}

Related

1. getContent(Element element)
2. getContent(Element element)
3. getContent(Element element)
4. getContentFromElement(Element element, String namespaceURI, String localName)