001 import java.io.IOException;
002
003 //Hier werden nur Standardklassen und Interfaces importiert
004 import org.w3c.dom.*;
005 import org.w3c.dom.bootstrap.DOMImplementationRegistry;
006 import org.w3c.dom.ls.DOMImplementationLS;
007 import org.w3c.dom.ls.LSParser;
008
009 /**
010 * This class provides static methods to load, analyse and display a DOM
011 * structure of an XML Document
012 *
013 * @author Udo Altmann
014 * @version 2.0 (2005)
015 *
016 */
017
018 public class DOMAnalyse {
019
020 /**
021 * @param args
022 * File to be analysed
023 * @throws IOException
024 * @throws IllegalAccessException
025 * @throws InstantiationException
026 * @throws ClassNotFoundException
027 * @throws ClassCastException
028 */
029 public static void main(String args[]) throws IOException,
030 ClassCastException, ClassNotFoundException, InstantiationException,
031 IllegalAccessException {
032
033 // DOM Level 3 DOMImplementationSourceImpl implements
034 // org.w3c.dom.DOMImplementationSource
035 // An dieser Stelle werden die zur Verfügung stehenden Implementationen
036 // gesetzt
037 System.setProperty(DOMImplementationRegistry.PROPERTY,
038 "org.apache.xerces.dom.DOMImplementationSourceImpl");
039
040 // Class from org.w3c.dom.bootstrap
041 DOMImplementationRegistry registry;
042 registry = DOMImplementationRegistry.newInstance();
043
044 DOMImplementationLS impl = (DOMImplementationLS) registry
045 .getDOMImplementation("LS"); // Load and Save
046
047 LSParser parser = impl.createLSParser(
048 DOMImplementationLS.MODE_SYNCHRONOUS, null);
049
050 DOMConfiguration conf = parser.getDomConfig();
051
052 // Setzen diverser Attribute
053 conf.setParameter("validate-if-schema", new Boolean(true));
054 conf.setParameter("cdata-sections", new Boolean(true));
055 conf.setParameter("entities", new Boolean(true));
056
057 DOMStringList sl = conf.getParameterNames();
058 int i;
059 System.out.println("Parameters for parsing:");
060 for (i = 0; i < sl.getLength(); i++) {
061 System.out.println("\t" + sl.item(i) + ": "
062 + conf.getParameter(sl.item(i)));
063 }
064
065 //
066 // Die Verarbeitung startet mit dem Interface Document
067 //
068 // Dokumente sind auch Knoten
069 //
070 Document doc = parser.parseURI(args[0]);
071 process(doc);
072 }
073
074 /**
075 * @param nd
076 * Node to be analysed. Child nodes are processed recursively
077 */
078 public static void process(Node nd) {
079 System.out.println("Node type:\t" + nd.getNodeType() + " - "
080 + nodeTypeToString(nd.getNodeType()));
081 System.out.println("\tname:\t" + nd.getNodeName());
082 System.out.println("\tvalue:\t\"" + nd.getNodeValue() + "\"");
083 if (nd.getParentNode() != null) {
084 System.out.println("\tparent:\t"
085 + nodeTypeToString(nd.getParentNode().getNodeType()) + "\t"
086 + nd.getParentNode().getNodeName());
087 } else {
088 System.out.println("\tno parent\t");
089 }
090 System.out.println("\tspecific details:\t");
091 // nd.
092 switch (nd.getNodeType()) {
093 case Node.DOCUMENT_NODE:
094 Document doc = (Document) nd;
095 System.out.println("\t\tDocumentElement: "
096 + doc.getDocumentElement().getNodeName());
097 break;
098 case Node.ELEMENT_NODE:
099 Element el = (Element) nd;
100 System.out.println("\t\tgetTagName: " + el.getTagName());
101 System.out.println("\t\tgetLocalName: " + el.getLocalName());
102 System.out.println("\t\tgetNamespaceURI: " + el.getNamespaceURI());
103 //
104 // hasAttributes since DOM-Level 2 (for elements)
105 //
106 if (el.hasAttributes()) {
107 System.out.println("\t\tAttribute:");
108 NamedNodeMap nnm = el.getAttributes();
109 int i;
110 for (i = 0; i < nnm.getLength(); i++) {
111 process(nnm.item(i));
112 }
113 } else {
114 System.out.println("\t\tno attributes!");
115 }
116 break;
117 case Node.ATTRIBUTE_NODE:
118 Attr at = (Attr) nd;
119 System.out.println("\t\tgetName:" + at.getName());
120 System.out.println("\t\tspecified: " + at.getSpecified());
121 System.out.println("\t\tgetValue: " + at.getValue());
122 System.out.println("\t\tgetLocalName: " + at.getLocalName());
123 System.out.println("\t\tgetNamespaceURI: " + at.getNamespaceURI());
124 break;
125 case Node.COMMENT_NODE:
126 Comment cm = (Comment) nd;
127 System.out.println("\t\tgetData: " + cm.getData());
128 System.out.println("\t\tgetLength: " + cm.getLength());
129 break;
130 case Node.TEXT_NODE:
131 Text tn = (Text) nd;
132 System.out.println("\t\tgetData: " + tn.getData());
133 System.out.println("\t\tgetLength: " + tn.getLength());
134 break;
135 case Node.CDATA_SECTION_NODE:
136 Text cs = (Text) nd;
137 System.out.println("\t\tgetData: " + cs.getData());
138 System.out.println("\t\tgetLength: " + cs.getLength());
139 break;
140 case Node.DOCUMENT_TYPE_NODE:
141 int i;
142 DocumentType dt = (DocumentType) nd;
143 System.out.println("\t\tgetName: " + dt.getName());
144 System.out.println("\t\tgetPublicId: " + dt.getPublicId());
145 System.out.println("\t\tgetSystemId: " + dt.getSystemId());
146 //
147 // DOM 2 und parserabhängig
148 //
149 System.out.println("\t\tgetInternalSubset: "
150 + dt.getInternalSubset());
151 NamedNodeMap nnm = dt.getEntities();
152 if (nnm.getLength() <= 0) {
153 System.out.println("\t\tno Entities");
154 } else {
155 for (i = 0; i < nnm.getLength(); i++) {
156 process(nnm.item(i));
157 }
158 }
159 nnm = dt.getNotations();
160 if (nnm.getLength() <= 0) {
161 System.out.println("\t\tno Notations");
162 } else {
163 for (i = 0; i < nnm.getLength(); i++) {
164 process(nnm.item(i));
165 }
166 }
167 break;
168 case Node.NOTATION_NODE:
169 Notation no = (Notation) nd;
170 System.out.println("\t\tgetPublicId: " + no.getPublicId());
171 System.out.println("\t\tgetSytemId: " + no.getSystemId());
172 break;
173 case Node.ENTITY_NODE:
174 Entity en = (Entity) nd;
175 System.out.println("\t\tgetNotationName: " + en.getNotationName());
176 System.out.println("\t\tgetPublicId: " + en.getPublicId());
177 System.out.println("\t\tgetSytemId: " + en.getSystemId());
178 break;
179 case Node.PROCESSING_INSTRUCTION_NODE:
180 ProcessingInstruction pe = (ProcessingInstruction) nd;
181 System.out.println("\t\tgetTarget: " + pe.getTarget());
182 System.out.println("\t\tgetData: " + pe.getData());
183 break;
184 //
185 // Für die folgenden Knotentyp gibt es keine speziellen
186 // Attribute/Methoden
187 //
188 case Node.ENTITY_REFERENCE_NODE:
189 //
190 // EntityRefences werden evtl. nicht erkannt, wenn sie beim Parsen
191 // ersetzt werden
192 //
193 // EntityReference er = (EntityReference) nd;
194 // break;
195 case Node.DOCUMENT_FRAGMENT_NODE:
196 // DocumentFragment df = (DocumentFragment) nd;
197 // break;
198 default:
199 System.out.println("\t\tno details!");
200 }
201 if (nd.hasChildNodes()) {
202 NodeList nl = nd.getChildNodes();
203 int i;
204 for (i = 0; i < nl.getLength(); i++) {
205 process(nl.item(i));
206 }
207 }
208 }
209
210 /**
211 * Static method to convert Nodetypes to Strings
212 *
213 * @param s
214 * Type as short
215 * @return Type as String
216 */
217 public static String nodeTypeToString(short s) {
218
219 switch (s) {
220 case Node.ATTRIBUTE_NODE:
221 return "ATTRIBUTE_NODE";
222 case Node.CDATA_SECTION_NODE:
223 return "CDATA_SECTION_NODE";
224 case Node.COMMENT_NODE:
225 return "COMMENT_NODE";
226 case Node.DOCUMENT_FRAGMENT_NODE:
227 return "DOCUMENT_FRAGMENT_NODE";
228 case Node.DOCUMENT_NODE:
229 return "DOCUMENT_NODE";
230 case Node.DOCUMENT_TYPE_NODE:
231 return "DOCUMENT_TYPE_NODE";
232 case Node.ELEMENT_NODE:
233 return "ELEMENT_NODE";
234 case Node.ENTITY_NODE:
235 return "ENTITY_NODE";
236 case Node.ENTITY_REFERENCE_NODE:
237 return "ENTITY_REFERENCE_NODE";
238 case Node.NOTATION_NODE:
239 return "NOTATION_NODE";
240 case Node.PROCESSING_INSTRUCTION_NODE:
241 return "PROCESSING_INSTRUCTION_NODE";
242 case Node.TEXT_NODE:
243 return "TEXT_NODE";
244 default:
245
246 return null;
247 }
248 }
249
250 }