UTF-8 Chacters Extracting from Java XMLDocument - Revised so example works

Question

I'm working on a string XML document that has utf-8 charcters within the
text nodes, e.g. &;lsquo; &;rsquo; In the original string these are ok, and when represented through to a web page appear correctly as a ‘ ’
quotes.
<p>Example XML Document :- </p>
<p><?xml version=&quot;1.0&quot; encoding=&quot;UTF-8&quot;?><br>
<!DOCTYPE art [<br>
<!ELEMENT art (#PCDATA | b)*><br>
<!ELEMENT b (#PCDATA)><br>
<!ENTITY lsquo &quot;&;#x2018;&quot;><br>
<!ENTITY rsquo &quot;&;#x2019;&quot;><br>
]><br>
<art><br>
This ZZZ&;lsquo;La Sapienza&;rsquo; di Roma <b>some
Text</b><br>
ZZZZ&;lsquo;La Sapienza&;rsquo; 00185 ZZZZ<br>
</art></p>
<p>However if i use the oracle.xml.parser.v2.DOMParser to create a
oracle.xml.parser.v2.XMLDocument from the String, I cannot get the text from the
nodes correctly, using oracle.xml.parser.v2.XMLDocument.print(System.out) or
through the org.w3c.dom.Node.getNodeValue().</p>
<p>I need to Extract the <art> tags data,  the resulting text must be
:-</p>
<p>    <i>This ZZZ&;lsquo;La Sapienza&;rsquo; di Roma <b>some Text</b>ZZZZ&;lsquo;La Sapienza&;rsquo; 00185
ZZZZ</i></p>
<p>AND NOT :-</p>
<p>      This ZZZbLa Sapienzab
di Roma <b>some Text</b>ZZZZbLa
Sapienzab 00185 ZZZZ</p>
<p>AND NOT :-</p>
<p>      <i>This ZZZ&lsquo;La Sapienza&rsquo; di Roma <b>some Text</b>ZZZZ&lsquo;La Sapienza&rsquo; 00185
ZZZZ</i></p>
<p>Example Program,  Just copy &; Paste into Jdeveloper</p>
<p>Project Libraries Required  :- Oracle XML Parser 2.0 ( D:\jdev323\lib\xmlparserv2.jar
)</p>
<p>COPY FROM HERE >></p>
<p> import java.io.IOException;<br>
import org.w3c.dom.Node;<br>
import org.xml.sax.SAXException;<br>
import oracle.xml.parser.v2.XMLDocument;<br>
import oracle.xml.parser.v2.DOMParser;<br>
import oracle.xml.parser.v2.XSLException;<br>
import org.xml.sax.InputSource;<br>
import java.io.StringReader;<br>
<br>
public class Class3 extends Object {<br>
<br>
public Class3 () throws IOException , SAXException, XSLException{<br>
String docText =<br>
"<?xml version=\"1.0\" encoding=\"UTF-8\"?>" +"\n"+<br>
"<!DOCTYPE art [" + "\n"+<br>
"<!ELEMENT art (#PCDATA | b)*>" +"\n"+<br>
"<!ELEMENT b (#PCDATA)>" +"\n"+<br>
"<!ENTITY lsquo \"&;#x2018;\">" +"\n"+<br>
"<!ENTITY rsquo \"&;#x2019;\">" +"\n"+<br>
"]>" +"\n"+<br>
"<art>" +"\n"+<br>
" This ZZZ&;lsquo;La Sapienza&;rsquo; di Roma <b>some Text</b>"+"\n"+<br>
" ZZZZ&;lsquo;La Sapienza&;rsquo; 00185 ZZZZ" +"\n"+<br>
"</art>" + "\n";<br>
System.out.println("----------------------------------------");<br>
System.out.println("Original String Value ");<br>
System.out.println("----------------------------------------");<br>
System.out.println(docText);<br>
System.out.println("----------------------------------------");<br>
System.out.println("Value from XMLDocument.Print(Systen.out)");<br>
System.out.println("----------------------------------------");<br>
InputSource input = new InputSource(new StringReader(docText));<br>
DOMParser xp = new DOMParser();<br>
xp.setValidationMode(false);<br>
xp.setPreserveWhitespace(false);<br>
xp.parse (input);<br>
XMLDocument xMLDocument = (XMLDocument)xp.getDocument();<br>
xMLDocument.print(System.out );<br>
<br>
System.out.println("----------------------------------------");<br>
System.out.println("Value from Node Walk");<br>
System.out.println("----------------------------------------");<br>
Node theNode = xMLDocument.getFirstChild();<br>
this.walkNode(theNode);<br>
}<br>
<br>
public void showNode (Node inNode) {<br>
System.out.println(inNode.getNodeName() + " <--> "<br>
+ inNode.getNodeType() + " <--> "<br>
+ inNode.getNodeValue() + " <--> ");<br>
<br>
Node kid=inNode.getFirstChild();<br>
if(kid==null) {<br>
} else {<br>
walkNode(kid);<br>
}<br>
}<br>
<br>
public void walkNode (Node theFirst) {<br>
while(null!=theFirst){<br>
showNode(theFirst);<br>
theFirst=theFirst.getNextSibling();<br>
}<br>
}<br>
<br>
public static void main(String[] args) throws Exception {<br>
Class3 class3 = new Class3();<br>
<br>
}<br>
}<br>
<<  END HERE</p>
null

Answer 1

import java.io.IOException;
import org.w3c.dom.Node;
import org.xml.sax.SAXException;
import oracle.xml.parser.v2.XMLDocument;
import oracle.xml.parser.v2.DOMParser;
import oracle.xml.parser.v2.XSLException;
import org.xml.sax.InputSource;
import java.io.StringReader;
public class Class3 extends Object {
public Class3 () throws IOException , SAXException, XSLException{
String docText =
"<?xml version=\"1.0\" encoding=\"UTF-8\"?>" +"\n"+
"<!DOCTYPE art [" + "\n"+
"<!ELEMENT art (#PCDATA | b)*>" +"\n"+
"<!ELEMENT b (#PCDATA)>" +"\n"+
"<!ENTITY lsquo \"&#x2018;\">" +"\n"+
"<!ENTITY rsquo \"&#x2019;\">" +"\n"+
"]>" +"\n"+
"<art>" +"\n"+
" This ZZZ&lsquo;La Sapienza&rsquo; di Roma <b>some Text</b>"+"\n"+
" ZZZZ&lsquo;La Sapienza&rsquo; 00185 ZZZZ" +"\n"+
"</art>" + "\n";
System.out.println("----------------------------------------");
System.out.println("Original String Value ");
System.out.println("----------------------------------------");
System.out.println(docText);
System.out.println("----------------------------------------");
System.out.println("Value from XMLDocument.Print(Systen.out)");
System.out.println("----------------------------------------");
InputSource input = new InputSource(new StringReader(docText));
DOMParser xp = new DOMParser();
xp.setValidationMode(false);
xp.setPreserveWhitespace(false);
xp.parse (input);
XMLDocument xMLDocument = (XMLDocument)xp.getDocument();
xMLDocument.print(System.out);
System.out.println("----------------------------------------");
System.out.println("Value from Node Walk");
System.out.println("----------------------------------------");
Node theNode = xMLDocument.getFirstChild();
this.walkNode(theNode);
public void showNode (Node inNode) {
System.out.println(inNode.getNodeName() + " <--> "
+ inNode.getNodeType() + " <--> "
+ inNode.getNodeValue() + " <--> ");
Node kid=inNode.getFirstChild();
if(kid==null) {
} else {
walkNode(kid);
public void walkNode (Node theFirst) {
while(null!=theFirst){
showNode(theFirst);
theFirst=theFirst.getNextSibling();
public static void main(String[] args) throws Exception {
Class3 class3 = new Class3();
}