source: trunk/gsdl3/src/java/org/greenstone/gsdl3/util/XMLConverter.java@ 4087

Last change on this file since 4087 was 4087, checked in by kjdon, 21 years ago

added a new getDOM(File, String) that specifies an encoding to read the file with
  • Property svn:keywords set to Author Date Id Revision
File size: 8.0 KB
Line 
1/*
2 * XMLConverter.java
3 * Copyright (C) 2002 New Zealand Digital Library, http://www.nzdl.org
4 *
5 * This program is free software; you can redistribute it and/or modify
6 * it under the terms of the GNU General Public License as published by
7 * the Free Software Foundation; either version 2 of the License, or
8 * (at your option) any later version.
9 *
10 * This program is distributed in the hope that it will be useful,
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 * GNU General Public License for more details.
14 *
15 * You should have received a copy of the GNU General Public License
16 * along with this program; if not, write to the Free Software
17 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
18 */
19package org.greenstone.gsdl3.util;
20
21// XML classes
22import org.w3c.dom.Document;
23import org.w3c.dom.Node;
24import org.w3c.dom.NodeList;
25import org.w3c.dom.NamedNodeMap;
26import org.xml.sax.InputSource;
27import org.apache.xerces.parsers.DOMParser;
28import org.apache.xerces.dom.DocumentImpl; // for new Documents
29
30// other java classes
31import java.io.Reader;
32import java.io.InputStreamReader;
33import java.io.StringReader;
34import java.io.File;
35import java.io.FileInputStream;
36import java.io.FileReader;
37
38/** XMLConverter - utitlity class for greenstone
39 *
40 * parses XML Strings into Documents, converts Nodes to Strings
41 * different parsers have different behaviour - can experiment in here
42 * now we only use xerces
43 *
44 * @author <a href="mailto:[email protected]">Katherine Don</a>
45 * @version $Revision: 4087 $
46 *
47 */
48public class XMLConverter {
49
50 /** xerces parser */
51 protected DOMParser parser_ = null;
52
53 private boolean outputEscaping = true;
54
55
56 /** the no-args constructor */
57 public XMLConverter() {
58 try {
59 parser_ = new DOMParser();
60 } catch (Exception e) {
61 System.err.println("XMLConverter:exception "+e.getMessage());
62 }
63 }
64
65 /** returns a DOM Document */
66 public Document getDOM(String in) {
67
68 try {
69 Reader reader = new StringReader(in);
70 InputSource xml_source = new InputSource(reader);
71
72 parser_.parse(xml_source);
73 Document doc = parser_.getDocument();
74 return doc;
75
76 } catch (Exception e) {
77 System.err.println("XMLConverter.getDOM(String): exception "+e.getMessage());
78 }
79 return null;
80 }
81
82 /** returns a DOM Document */
83 public Document getDOM(File in) {
84 try {
85
86 FileReader reader = new FileReader(in);
87 InputSource xml_source = new InputSource(reader);
88
89 parser_.parse(xml_source);
90 Document doc = parser_.getDocument();
91
92 return doc;
93
94 } catch (Exception e) {
95 System.err.println("XMLConverter.getDOM(File): exception "+e.getMessage());
96 }
97 return null;
98 }
99
100 /** returns a DOM document */
101 public Document getDOM(File in, String encoding) {
102 try {
103
104 InputStreamReader isr = new InputStreamReader(new FileInputStream(in), encoding);
105 InputSource xml_source = new InputSource(isr);
106
107 parser_.parse(xml_source);
108 Document doc = parser_.getDocument();
109
110 return doc;
111
112 } catch (Exception e) {
113 System.err.println("XMLConverter.getDOM(File): exception "+e.getMessage());
114 }
115 return null;
116 }
117
118
119 /** creates a new empty DOM Document */
120 public Document newDOM() {
121 Document doc = new DocumentImpl();
122 return doc;
123 }
124
125 /** returns the Node as a String */
126 public String getString(Node xmlNode)
127 {
128 outputEscaping = true;
129 return getString(xmlNode, 0, false);
130 }
131
132 /** returns the node as a nicely formatted String - this introduces extra
133 * text nodes if the String is read back in as a DOM, so should only be
134 * used for printing */
135 public String getPrettyString(Node xmlNode) {
136
137 outputEscaping = true;
138 return getString(xmlNode, 0, true);
139 }
140
141 private String getString(Node xmlNode, int depth, boolean pretty)
142 {
143 String xmlRepresentation = "";
144
145 if (xmlNode == null)
146 return "<null>";
147
148 short nodeType = xmlNode.getNodeType();
149 String nodeName = xmlNode.getNodeName();
150
151 // Handle Element nodes
152 if (nodeType == Node.ELEMENT_NODE) {
153 if (pretty) {
154 xmlRepresentation += "\n";
155 for (int i = 0; i < depth; i++) {
156 xmlRepresentation += " ";
157 }
158 }
159
160 // Write opening tag
161 xmlRepresentation += "<" + nodeName;
162
163 // Write the node attributes
164 NamedNodeMap nodeAttributes = xmlNode.getAttributes();
165 for (int i = 0; i < nodeAttributes.getLength(); i++) {
166 Node attribute = nodeAttributes.item(i);
167 xmlRepresentation += " " + attribute.getNodeName() + "=";
168 xmlRepresentation += "\"" + attribute.getNodeValue() + "\"";
169 }
170
171 // If the node has no children, close the opening tag and return
172 if (xmlNode.hasChildNodes() == false) {
173 // This produces somewhat ugly output, but it is necessary to compensate
174 // for display bugs in Netscape. Firstly, the space is needed before the
175 // closing bracket otherwise Netscape will ignore some tags (<br/>, for
176 // example). Also, a newline character would be expected after the tag,
177 // but this causes problems with the display of links (the link text
178 // will contain a newline character, which is displayed badly).
179 xmlRepresentation += " />";
180 return xmlRepresentation;
181 }
182
183 // Close the opening tag
184 xmlRepresentation += ">";
185
186 // Apply recursively to the children of this node
187 NodeList children = xmlNode.getChildNodes();
188 for (int i = 0; i < children.getLength(); i++) {
189 xmlRepresentation += getString(children.item(i), depth + 1, pretty);
190 }
191
192 // Write closing tag
193 if (pretty) {
194 if (xmlRepresentation.endsWith("\n")) {
195 for (int i = 0; i < depth; i++)
196 xmlRepresentation += " ";
197 }
198 }
199 xmlRepresentation += "</" + nodeName + ">";
200 if (pretty) {
201 xmlRepresentation += "\n";
202 }
203 }
204
205 // Handle Text nodes
206 else if (nodeType == Node.TEXT_NODE) {
207 String text = xmlNode.getNodeValue();
208
209 // Perform output escaping, if required
210 if (outputEscaping) {
211 text = text.replaceAll("&", "&amp;"); // Must be done first!!
212 text = text.replaceAll("<", "&lt;");
213 text = text.replaceAll(">", "&gt;");
214 text = text.replaceAll("\"", "&quot;");
215 text = text.replaceAll("\'", "&apos;");
216 }
217
218 // Remove any control-C characters
219 text = text.replaceAll("" + (char) 3, "");
220 xmlRepresentation += text;
221 }
222
223 // Handle Processing Instruction nodes
224 else if (nodeType == Node.PROCESSING_INSTRUCTION_NODE) {
225 if (nodeName.equals("javax.xml.transform.disable-output-escaping")) {
226 outputEscaping = false;
227 }
228 else if (nodeName.equals("javax.xml.transform.enable-output-escaping")) {
229 outputEscaping = true;
230 }
231 else {
232 System.err.println("XMLConverter.getString(): Warning: Unhandled processing instruction " + nodeName);
233 }
234 }
235
236 // A type of node that is not handled yet
237 else {
238 System.err.println("XMLConverter.getString(): Warning: Unknown node type: " + nodeType+" "+getNodeTypeString(nodeType));
239 }
240
241 return xmlRepresentation;
242 }
243
244 protected static String getNodeTypeString(short node_type) {
245
246 String type = "";
247 switch(node_type) {
248 case Node.ATTRIBUTE_NODE:
249 type="ATTRIBUTE_NODE";
250 break;
251 case Node.CDATA_SECTION_NODE:
252 type="CDATA_SECTION_NODE";
253 break;
254 case Node.COMMENT_NODE:
255 type="COMMENT_NODE";
256 break;
257 case Node.DOCUMENT_FRAGMENT_NODE:
258 type="DOCUMENT_FRAGMENT_NODE";
259 break;
260 case Node.DOCUMENT_NODE:
261 type="DOCUMENT_NODE";
262 break;
263 case Node.DOCUMENT_TYPE_NODE:
264 type="DOCUMENT_TYPE_NODE";
265 break;
266 case Node.ELEMENT_NODE:
267 type="ELEMENT_NODE";
268 break;
269 case Node.ENTITY_NODE:
270 type="ENTITY_NODE";
271 break;
272 case Node.ENTITY_REFERENCE_NODE:
273 type="ENTITY_REFERENCE_NODE";
274 break;
275 case Node.NOTATION_NODE:
276 type="NOTATION_NODE";
277 break;
278 case Node.PROCESSING_INSTRUCTION_NODE:
279 type="PROCESSING_INSTRUCTION_NODE";
280 break;
281 case Node.TEXT_NODE:
282 type="TEXT_NODE";
283 break;
284 default:
285 type="UNKNOWN";
286 }
287
288 return type;
289 }
290}
Note: See TracBrowser for help on using the repository browser.