2 * Copyright 2005-2010 the original author or authors.
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
8 * http://www.apache.org/licenses/LICENSE-2.0
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
16 package org.wamblee.xml;
18 import java.io.ByteArrayInputStream;
19 import java.io.ByteArrayOutputStream;
20 import java.io.IOException;
21 import java.io.InputStream;
22 import java.io.OutputStream;
23 import java.util.ArrayList;
24 import java.util.List;
26 import java.util.TreeMap;
27 import java.util.logging.Level;
28 import java.util.logging.Logger;
30 import javax.xml.XMLConstants;
31 import javax.xml.parsers.DocumentBuilder;
32 import javax.xml.parsers.DocumentBuilderFactory;
33 import javax.xml.parsers.ParserConfigurationException;
34 import javax.xml.transform.Transformer;
35 import javax.xml.transform.TransformerException;
36 import javax.xml.transform.TransformerFactory;
37 import javax.xml.transform.dom.DOMSource;
38 import javax.xml.transform.stream.StreamResult;
39 import javax.xml.transform.stream.StreamSource;
40 import javax.xml.validation.Schema;
41 import javax.xml.validation.SchemaFactory;
42 import javax.xml.validation.Validator;
44 import org.w3c.dom.Attr;
45 import org.w3c.dom.Document;
46 import org.w3c.dom.Element;
47 import org.w3c.dom.NamedNodeMap;
48 import org.w3c.dom.Node;
49 import org.w3c.dom.NodeList;
50 import org.w3c.dom.bootstrap.DOMImplementationRegistry;
51 import org.w3c.dom.ls.DOMImplementationLS;
52 import org.w3c.dom.ls.LSException;
53 import org.w3c.dom.ls.LSInput;
54 import org.w3c.dom.ls.LSParser;
55 import org.xml.sax.SAXException;
58 * Some basic XML utilities for common reoccuring tasks for DOM documents.
60 * @author Erik Brakkee
62 public final class DomUtils {
63 private static final Logger LOG = Logger
64 .getLogger(DomUtils.class.getName());
67 * Disabled default constructor.
75 * Parses an XML document from a string.
83 public static Document read(String aDocument) throws XMLException {
84 ByteArrayInputStream is = new ByteArrayInputStream(aDocument.getBytes());
90 * Parses an XML document from a stream.
98 public static Document read(InputStream aIs) throws XMLException {
100 DOMImplementationRegistry registry = DOMImplementationRegistry
103 DOMImplementationLS impl = (DOMImplementationLS) registry
104 .getDOMImplementation("LS");
106 LSParser builder = impl.createLSParser(
107 DOMImplementationLS.MODE_SYNCHRONOUS, null);
108 LSInput input = impl.createLSInput();
109 input.setByteStream(aIs);
110 return builder.parse(input);
111 } catch (IllegalAccessException e) {
112 throw new XMLException(e.getMessage(), e);
113 } catch (InstantiationException e) {
114 throw new XMLException(e.getMessage(), e);
115 } catch (ClassNotFoundException e) {
116 throw new XMLException(e.getMessage(), e);
117 } catch (LSException e) {
118 throw new XMLException(e.getMessage(), e);
122 } catch (Exception e) {
123 LOG.log(Level.WARNING, "Error closing XML file", e);
129 * Reads and validates a document against a schema.
136 * @return Parsed and validated document.
139 public static Document readAndValidate(InputStream aIs, InputStream aSchema)
140 throws XMLException {
142 Document doc = read(aIs);
143 final Schema schema = SchemaFactory.newInstance(
144 XMLConstants.W3C_XML_SCHEMA_NS_URI).newSchema(
145 new StreamSource(aSchema));
146 Validator validator = schema.newValidator();
147 validator.validate(new DOMSource(doc));
150 } catch (SAXException e) {
151 throw new XMLException(e.getMessage(), e);
152 } catch (IOException e) {
153 throw new XMLException(e.getMessage(), e);
157 } catch (Exception e) {
158 LOG.log(Level.WARNING, "Error closing schema", e);
163 } catch (Exception e) {
164 LOG.log(Level.WARNING, "Error closing XML file", e);
170 * Serializes an XML document to a stream.
173 * Document to serialize.
178 public static void serialize(Document aDocument, OutputStream aOs)
181 TransformerFactory factory = TransformerFactory.newInstance();
182 Transformer identityTransform = factory.newTransformer();
183 DOMSource source = new DOMSource(aDocument);
184 StreamResult result = new StreamResult(aOs);
185 identityTransform.transform(source, result);
186 } catch (TransformerException e) {
187 throw new IOException(e.getMessage(), e);
192 * Serializes an XML document.
195 * Document to serialize.
197 * @return Serialized document.
200 public static String serialize(Document aDocument) throws IOException {
201 ByteArrayOutputStream os = new ByteArrayOutputStream();
202 serialize(aDocument, os);
204 return os.toString();
208 * Removes duplicate attributes from a DOM tree.This is useful for
209 * postprocessing the output of JTidy as a workaround for a bug in JTidy.
212 * Node to remove duplicate attributes from (recursively).
213 * Attributes of the node itself are not dealt with. Only the
214 * child nodes are dealt with.
216 public static void removeDuplicateAttributes(Node aNode) {
217 NodeList list = aNode.getChildNodes();
219 for (int i = 0; i < list.getLength(); i++) {
220 Node node = list.item(i);
222 if (node instanceof Element) {
223 removeDuplicateAttributes((Element) node);
224 removeDuplicateAttributes(node);
230 * Removes duplicate attributes from an element.
235 private static void removeDuplicateAttributes(Element aElement) {
236 NamedNodeMap attributes = aElement.getAttributes();
237 Map<String, Attr> uniqueAttributes = new TreeMap<String, Attr>();
238 List<Attr> attlist = new ArrayList<Attr>();
240 for (int i = 0; i < attributes.getLength(); i++) {
241 Attr attribute = (Attr) attributes.item(i);
243 if (uniqueAttributes.containsKey(attribute.getNodeName())) {
244 LOG.info("Detected duplicate attribute (will be removed)'" +
245 attribute.getNodeName() + "'");
248 uniqueAttributes.put(attribute.getNodeName(), attribute);
249 attlist.add(attribute);
252 // Remove all attributes from the element.
253 for (Attr att : attlist) {
254 aElement.removeAttributeNode(att);
257 // Add the unique attributes back to the element.
258 for (Attr att : uniqueAttributes.values()) {
259 aElement.setAttributeNode(att);