import java.io.IOException;
import org.apache.xerces.parsers.DOMParser;
import org.w3c.dom.*;
import org.xml.sax.SAXException;
/**
* This class provides static methods to analyse and display a DOM
* structure of an XML Document
* @author Udo Altmann
* @version 1.0
*
*/
public class analyse {
/**
* @param args File to be analysed
* @throws IOException
* @throws SAXException
*/
public static void main(String args[]) throws IOException, SAXException {
DOMParser dp = new DOMParser();
//
// Es gibt keine DOM-Methode zum Anlegen von Documenten
//
dp.parse(args[0]);
//
// Die Verarbeitung startet mit dem Interface Document
//
Document doc = dp.getDocument();
//
// Dokumente sind auch Knoten
//
process(doc);
}
/**
* @param nd Node to be analysed. Child nodes are processed recursively
*/
public static void process(Node nd) {
System.out.println(
"Node type:\t"
+ nd.getNodeType()
+ " - "
+ nodeTypeToString(nd.getNodeType()));
System.out.println("\tname:\t" + nd.getNodeName());
System.out.println("\tvalue:\t\"" + nd.getNodeValue() + "\"");
if (nd.getParentNode() != null) {
System.out.println(
"\tparent:\t"
+ nodeTypeToString(nd.getParentNode().getNodeType())
+ "\t"
+ nd.getParentNode().getNodeName());
} else {
System.out.println("\tno parent\t");
}
System.out.println("\tspecific details:\t");
//nd.
switch (nd.getNodeType()) {
case Node.DOCUMENT_NODE :
Document doc = (Document) nd;
System.out.println(
"\t\tDocumentElement: "
+ doc.getDocumentElement().getNodeName());
break;
case Node.ELEMENT_NODE :
Element el = (Element) nd;
//
// hasAttributes ist nicht in DOM-Level 1!
//
if (el.hasAttributes()) {
System.out.println("\t\tgetTagName: " + el.getTagName());
System.out.println("\t\tAttribute:");
NamedNodeMap nnm = el.getAttributes();
int i;
for (i = 0; i < nnm.getLength(); i++) {
process(nnm.item(i));
}
} else {
System.out.println("\t\tno attributes!");
}
break;
case Node.ATTRIBUTE_NODE :
Attr at = (Attr) nd;
System.out.println("\t\tgetName:" + at.getName());
System.out.println("\t\tspecified: " + at.getSpecified());
System.out.println("\t\tgetValue: " + at.getValue());
break;
case Node.COMMENT_NODE :
Comment cm = (Comment) nd;
System.out.println("\t\tgetData: " + cm.getData());
System.out.println("\t\tgetLength: " + cm.getLength());
break;
case Node.TEXT_NODE :
Text tn = (Text) nd;
System.out.println("\t\tgetData: " + tn.getData());
System.out.println("\t\tgetLength: " + tn.getLength());
break;
case Node.CDATA_SECTION_NODE :
Text cs = (Text) nd;
System.out.println("\t\tgetData: " + cs.getData());
System.out.println("\t\tgetLength: " + cs.getLength());
break;
case Node.DOCUMENT_TYPE_NODE :
int i;
DocumentType dt = (DocumentType) nd;
System.out.println("\t\tgetName: " + dt.getName());
System.out.println("\t\tgetPublicId: " + dt.getPublicId());
System.out.println("\t\tgetSytemId: " + dt.getSystemId());
//
// DOM 2 und parserabhängig
//
System.out.println(
"\t\tgetInternalSubset: " + dt.getInternalSubset());
NamedNodeMap nnm = dt.getEntities();
if (nnm.getLength() <= 0) {
System.out.println("\t\tno Entities");
} else {
for (i = 0; i < nnm.getLength(); i++) {
process(nnm.item(i));
}
}
nnm = dt.getNotations();
if (nnm.getLength() <= 0) {
System.out.println("\t\tno Notations");
} else {
for (i = 0; i < nnm.getLength(); i++) {
process(nnm.item(i));
}
}
break;
case Node.NOTATION_NODE :
Notation no = (Notation) nd;
System.out.println("\t\tgetPublicId: " + no.getPublicId());
System.out.println("\t\tgetSytemId: " + no.getSystemId());
break;
case Node.ENTITY_NODE :
Entity en = (Entity) nd;
System.out.println(
"\t\tgetNotationName: " + en.getNotationName());
System.out.println("\t\tgetPublicId: " + en.getPublicId());
System.out.println("\t\tgetSytemId: " + en.getSystemId());
break;
case Node.PROCESSING_INSTRUCTION_NODE :
ProcessingInstruction pe = (ProcessingInstruction) nd;
System.out.println("\t\tgetTarget: " + pe.getTarget());
System.out.println("\t\tgetData: " + pe.getData());
break;
//
// Für die folgenden Knotentyp gibt es keine speziellen Attribute/Methoden
//
case Node.ENTITY_REFERENCE_NODE :
//
// EntityRefences werden evtl. nicht erkannt, wenn sie beim Parsen ersetzt werden
//
// EntityReference er = (EntityReference) nd;
// break;
case Node.DOCUMENT_FRAGMENT_NODE :
// DocumentFragment df = (DocumentFragment) nd;
// break;
default :
System.out.println("\t\tno details!");
}
if (nd.hasChildNodes()) {
NodeList nl = nd.getChildNodes();
int i;
for (i = 0; i < nl.getLength(); i++) {
process(nl.item(i));
}
}
}
/**
* Static method to convert Nodetypes to Strings
* @param s Type as short
* @return Type as String
*/
public static String nodeTypeToString(short s) {
switch (s) {
case Node.ATTRIBUTE_NODE :
return "ATTRIBUTE_NODE";
case Node.CDATA_SECTION_NODE :
return "CDATA_SECTION_NODE";
case Node.COMMENT_NODE :
return "COMMENT_NODE";
case Node.DOCUMENT_FRAGMENT_NODE :
return "DOCUMENT_FRAGMENT_NODE";
case Node.DOCUMENT_NODE :
return "DOCUMENT_NODE";
case Node.DOCUMENT_TYPE_NODE :
return "DOCUMENT_TYPE_NODE";
case Node.ELEMENT_NODE :
return "ELEMENT_NODE";
case Node.ENTITY_NODE :
return "ENTITY_NODE";
case Node.ENTITY_REFERENCE_NODE :
return "ENTITY_REFERENCE_NODE";
case Node.NOTATION_NODE :
return "NOTATION_NODE";
case Node.PROCESSING_INSTRUCTION_NODE :
return "PROCESSING_INSTRUCTION_NODE";
case Node.TEXT_NODE :
return "TEXT_NODE";
default :
return null;
}
}
}