source: trunk/gli/src/org/greenstone/gatherer/util/XMLTools.java@ 8601

Last change on this file since 8601 was 8023, checked in by mdewsnip, 20 years ago

More new metadata code: metadata elements now have definitions and comments.

  • Property svn:keywords set to Author Date Id Revision
File size: 5.4 KB
Line 
1package org.greenstone.gatherer.util;
2
3
4import java.io.*;
5import java.util.*;
6import org.apache.xerces.parsers.*;
7import org.apache.xml.serialize.*;
8import org.w3c.dom.*;
9import org.xml.sax.*;
10
11
12/** This class is a static class containing useful XML functions */
13public class XMLTools
14{
15 /** Remove all of the child nodes from a certain node. */
16 static final public void clear(Node node)
17 {
18 while (node.hasChildNodes()) {
19 node.removeChild(node.getFirstChild());
20 }
21 }
22
23
24 static public ArrayList getChildElementsByTagName(Element parent_element, String element_name)
25 {
26 ArrayList child_elements = new ArrayList();
27
28 NodeList children_nodelist = parent_element.getChildNodes();
29 for (int i = 0; i < children_nodelist.getLength(); i++) {
30 Node child_node = children_nodelist.item(i);
31 if (child_node.getNodeType() == Node.ELEMENT_NODE && child_node.getNodeName().equals(element_name)) {
32 child_elements.add(child_node);
33 }
34 }
35
36 return child_elements;
37 }
38
39
40 static public String getElementTextValue(Element element)
41 {
42 // Find the first text node child
43 NodeList children_nodelist = element.getChildNodes();
44 for (int i = 0; i < children_nodelist.getLength(); i++) {
45 Node child_node = children_nodelist.item(i);
46 if (child_node.getNodeType() == Node.TEXT_NODE) {
47 return child_node.getNodeValue();
48 }
49 }
50
51 // None found
52 return "";
53 }
54
55
56 /** Method to retrieve the value of a given node.
57 * @param element The <strong>Element</strong> whose value we wish to find.
58 * Soon to be deprecated!
59 */
60 static final public String getValue(Node element) {
61 // If we've been given a subject node first retrieve its value node.
62 if(element.getNodeName().equals("Subject")) {
63 element = getNodeFromNamed(element, "Value");
64 }
65 // If we've got a value node, then reconstruct the text. Remember that DOM will split text over 256 characters into several text nodes
66 if(element != null && element.hasChildNodes()) {
67 StringBuffer text_buffer = new StringBuffer();
68 NodeList text_nodes = element.getChildNodes();
69 for(int i = 0; i < text_nodes.getLength(); i++) {
70 Node possible_text = text_nodes.item(i);
71 if(possible_text.getNodeName().equals(StaticStrings.TEXT_NODE)) {
72 text_buffer.append(possible_text.getNodeValue());
73 }
74 }
75 return text_buffer.toString();
76 }
77 return "";
78 }
79
80
81 /** Method to retrieve from the node given, a certain child node with the specified name.
82 * @param parent The <strong>Node</strong> whose children should be searched.
83 * @param name The required nodes name as a <strong>String</strong>.
84 * @return The requested <strong>Node</strong> if it is found, <i>null</i> otherwise.
85 * Soon to be deprecated!
86 */
87 static final public Node getNodeFromNamed(Node parent, String name) {
88 Node child = null;
89 for(Node i = parent.getFirstChild(); i != null && child == null;
90 i = i.getNextSibling()) {
91 if(i.getNodeName().equals(name)) {
92 child = i;
93 }
94 }
95 return child;
96 }
97
98
99 /** Set the #text node value of some element.
100 * @param element the Element whose value we wish to set
101 * @param value the new value for the element as a String
102 * Soon to be deprecated!
103 */
104 static final public void setValue(Element element, String value) {
105 // Remove any existing child node(s)
106 clear(element);
107 // Add new text node.
108 if (value != null) {
109 element.appendChild(element.getOwnerDocument().createTextNode(value));
110 }
111 }
112
113
114 /** Parse an XML document from a given file */
115 static public Document parseXMLFile(File xml_file)
116 {
117 Document document = null;
118
119 try {
120 FileInputStream fis = new FileInputStream(xml_file);
121 InputStreamReader isr = new InputStreamReader(fis, "UTF-8");
122 Reader r = new BufferedReader(isr);
123 InputSource isc = new InputSource(r);
124 DOMParser parser = new DOMParser();
125 parser.setFeature("http://xml.org/sax/features/validation", false);
126 parser.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
127 // May or may not be ignored, the documentation for Xerces is contradictory. If it works then parsing -should- be faster.
128 parser.setFeature("http://apache.org/xml/features/dom/defer-node-expansion", true);
129 parser.setFeature("http://apache.org/xml/features/dom/include-ignorable-whitespace", false);
130 parser.parse(isc);
131 document = parser.getDocument();
132 isr.close();
133 fis.close();
134 }
135 catch (Exception exception) {
136 exception.printStackTrace();
137 }
138
139 return document;
140 }
141
142
143 /** Write an XML document to a given file */
144 static public void writeXMLFile(File xml_file, Document document)
145 {
146 try {
147 OutputStream os = new FileOutputStream(xml_file);
148 // Create an output format for our document.
149 OutputFormat f = new OutputFormat(document);
150 f.setEncoding("UTF-8");
151 f.setIndenting(true);
152 f.setLineWidth(0); // Why isn't this working!
153 f.setPreserveSpace(false);
154 // Create the necessary writer stream for serialization.
155 OutputStreamWriter osw = new OutputStreamWriter(os, "UTF-8");
156 Writer w = new BufferedWriter(osw);
157 // Generate a new serializer from the above.
158 XMLSerializer s = new XMLSerializer(w, f);
159 s.asDOMSerializer();
160 // Finally serialize the document to file.
161 s.serialize(document);
162 // And close.
163 os.close();
164 }
165 catch (Exception exception) {
166 exception.printStackTrace();
167 }
168 }
169}
Note: See TracBrowser for help on using the repository browser.