/*--
Copyright (C) 2001 Brett McLaughlin.
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions, and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright
notice, this list of conditions, and the disclaimer that follows
these conditions in the documentation and/or other materials
provided with the distribution.
3. The name "Java and XML" must not be used to endorse or promote products
derived from this software without prior written permission. For
written permission, please contact brett@newInstance.com.
In addition, we request (but do not require) that you include in the
end-user documentation provided with the redistribution and/or in the
software itself an acknowledgement equivalent to the following:
"This product includes software developed for the
'Java and XML' book, by Brett McLaughlin (O'Reilly & Associates)."
THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE JDOM AUTHORS OR THE PROJECT
CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
SUCH DAMAGE.
*/
import java.io.File;
// DOM imports
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.w3c.dom.traversal.DocumentTraversal;
import org.w3c.dom.traversal.NodeFilter;
import org.w3c.dom.traversal.NodeIterator;
// Vendor parser
import org.apache.xerces.parsers.DOMParser;
/**
* ItemSearcher
shows how the DOM Level 2 Traversal
* module can be used for searching through a document.
*/
public class ItemSearcher {
/** The default namespace for the document to search through */
private String docNS = "http://www.oreilly.com/javaxml2";
/**
* This method takes a file, and searches it for specific
* pieces of data using DOM traversal.
*
* @param filename name of XML file to search through.
* @throws Exception
- generic problem handling.
*/
public void search(String filename) throws Exception {
// Parse into a DOM tree
File file = new File(filename);
DOMParser parser = new DOMParser();
parser.parse(file.toURL().toString());
Document doc = parser.getDocument();
// Get node to start iterating with
Element root = doc.getDocumentElement();
NodeList descriptionElements =
root.getElementsByTagNameNS(docNS, "description");
Element description = (Element)descriptionElements.item(0);
// Get a NodeIterator
NodeIterator i = ((DocumentTraversal)doc)
.createNodeIterator(description, NodeFilter.SHOW_ALL,
new FormattingNodeFilter(), true);
Node n;
while ((n = i.nextNode()) != null) {
System.out.println("Search phrase found: '" + n.getNodeValue() + "'");
}
}
/**
* Provide a static entry point.
*/
public static void main(String[] args) {
if (args.length == 0) {
System.out.println("No item files to search through specified.");
return;
}
try {
ItemSearcher searcher = new ItemSearcher();
for (int i=0; i System.out.println("Processing file: " + args[i]);
searcher.search(args[i]);
}
} catch (Exception e) {
e.printStackTrace();
}
}
}
class FormattingNodeFilter implements NodeFilter {
public short acceptNode(Node n) {
if (n.getNodeType() == Node.TEXT_NODE) {
Node parent = n.getParentNode();
if ((parent.getNodeName().equalsIgnoreCase("b")) ||
(parent.getNodeName().equalsIgnoreCase("i"))) {
return FILTER_ACCEPT;
}
}
// If we got here, not interested
return FILTER_SKIP;
}
}