Debian Codegraph @

netx/net/sourceforge/jnlp/runtime/html/AppletExtractor.java

raw
1 /*
2 Copyright (C) 2013 Red Hat, Inc.
3
4 This file is part of IcedTea.
5
6 IcedTea is free software; you can redistribute it and/or
7 modify it under the terms of the GNU General Public License as published by
8 the Free Software Foundation, version 2.
9
10 IcedTea 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 GNU
13 General Public License for more details.
14
15 You should have received a copy of the GNU General Public License
16 along with IcedTea; see the file COPYING. If not, write to
17 the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
18 02110-1301 USA.
19
20 Linking this library statically or dynamically with other modules is
21 making a combined work based on this library. Thus, the terms and
22 conditions of the GNU General Public License cover the whole
23 combination.
24
25 As a special exception, the copyright holders of this library give you
26 permission to link this library with independent modules to produce an
27 executable, regardless of the license terms of these independent
28 modules, and to copy and distribute the resulting executable under
29 terms of your choice, provided that you also meet, for each linked
30 independent module, the terms and conditions of the license of that
31 module. An independent module is a module which is not derived from
32 or based on this library. If you modify this library, you may extend
33 this exception to your version of the library, but you are not
34 obligated to do so. If you do not wish to do so, delete this
35 exception statement from your version.
36 */
37 package net.sourceforge.jnlp.runtime.html;
38
39 import java.io.IOException;
40 import java.io.InputStream;
41 import java.lang.reflect.Method;
42 import java.net.URL;
43 import java.util.LinkedList;
44 import java.util.List;
45 import javax.xml.parsers.DocumentBuilderFactory;
46 import javax.xml.parsers.ParserConfigurationException;
47 import net.sourceforge.jnlp.JNLPFile;
48 import net.sourceforge.jnlp.OptionsDefinitions;
49 import net.sourceforge.jnlp.ParseException;
50 import net.sourceforge.jnlp.Parser;
51 import net.sourceforge.jnlp.ParserSettings;
52 import net.sourceforge.jnlp.cache.UpdatePolicy;
53 import net.sourceforge.jnlp.runtime.JNLPRuntime;
54 import net.sourceforge.jnlp.runtime.Translator;
55 import net.sourceforge.jnlp.util.logging.OutputController;
56 import org.w3c.dom.Document;
57 import org.w3c.dom.Element;
58 import org.w3c.dom.Node;
59 import org.w3c.dom.NodeList;
60 import org.xml.sax.SAXException;
61
62 /**
63 * This class is taking HTML document url as input, try to sanitize with
64 * tagsoup, if availale - and then finds and applet declarations here. Then it
65 * returns first, selected or last one as PluginBridge instance. See parse
66 * method.
67 */
68 public class AppletExtractor {
69
70 private final URL html;
71 private static final String[] APPLETS = new String[]{
72 "applet", "APPLET", "Applet",
73 "object", "OBJECT", "Object",
74 "embed", "EMBED", "Embed"};
75 private final ParserSettings ps;
76
77 public AppletExtractor(URL html) {
78 this(html, null);
79 }
80 public AppletExtractor(URL html, ParserSettings ps) {
81 JNLPRuntime.saveHistory(html.toExternalForm());
82 this.html = html;
83 this.ps = ps;
84 }
85
86 public URL getHtml() {
87 return html;
88 }
89
90 private InputStream cleanStreamIfPossible(InputStream is) {
91 try {
92 if (ps != null && ps.isMalformedXmlAllowed()){
93 Object parser = Parser.getParserInstance(ps);
94 Method m = parser.getClass().getMethod("xmlizeInputStream", InputStream.class);
95 return (InputStream) m.invoke(null, is);
96 } else {
97 OutputController.getLogger().log(OutputController.Level.WARNING_ALL, Translator.R("TAGSOUPhtmlNotUsed", OptionsDefinitions.OPTIONS.XML.option));
98 }
99 } catch (Exception ex) {
100 OutputController.getLogger().log(OutputController.Level.WARNING_ALL, Translator.R("TAGSOUPhtmlBroken"));
101 OutputController.getLogger().log(ex);
102 }
103 return is;
104 }
105
106 public List<Element> findAppletsOnPage() {
107 try{
108 return findAppletsOnPageImpl(openDocument(cleanStreamIfPossible(JNLPFile.openURL(html, null, UpdatePolicy.ALWAYS))));
109 } catch (SAXException sex) {
110 throw new RuntimeException(new ParseException(sex));
111 } catch (IOException | ParserConfigurationException ex) {
112 throw new RuntimeException(ex);
113 }
114 }
115
116 private List<Element> findAppletsOnPageImpl(Document doc) throws ParserConfigurationException, SAXException, IOException {
117 OutputController.getLogger().log("Root element :" + doc.getDocumentElement().getNodeName());
118 //search for applets
119 //search for embed/object
120 //<embed type="application/x-java-applet"
121 //<object type="application/x-java-applet"
122 //warning all searches are case sensitive
123 return findElements(APPLETS, doc.getDocumentElement(), new ElementValidator() {
124
125 @Override
126 public boolean isElementValid(Element e) {
127 return isApplet(e);
128 }
129 });
130 }
131
132 private Document openDocument(InputStream is) throws SAXException, ParserConfigurationException, IOException {
133 OutputController.getLogger().log("Reading " + html.toExternalForm());
134 Document doc = DocumentBuilderFactory.newInstance().newDocumentBuilder().parse(is);
135 doc.getDocumentElement().normalize();
136 return doc;
137 }
138
139 //warning, even application/x-java-applet;jpi-version=1.5.0_07 and more blah blah can be in type, so of embed/object start with
140 //search for
141 //OBJECT classid="clsid:8AD9C840-044E-11D1-B3E9-00805F499D93"
142 //<object codetype="application/x-java-applet" height="120" width="81"
143 private static boolean isApplet(Element eElement) {
144 if (eElement.getNodeName().toLowerCase().equals("applet")) {
145 return true;
146 } else {
147 String type = eElement.getAttribute("type");
148 String codeType = eElement.getAttribute("codetype");
149 String classid = eElement.getAttribute("classid");
150 if ((type != null && type.toLowerCase().contains("application/x-java-applet"))
151 || (codeType != null && codeType.toLowerCase().contains("application/x-java-applet"))
152 || (classid != null && classid.equalsIgnoreCase("clsid:8AD9C840-044E-11D1-B3E9-00805F499D93"))) {
153 return true;
154 }
155 }
156 return false;
157 }
158
159 static List<Element> findElements(String[] elements, Element doc, ElementValidator elementValidator) {
160 List<Element> found = new LinkedList();
161 for (String key : elements) {
162 NodeList nList = doc.getElementsByTagName(key);
163 for (int temp = 0; temp < nList.getLength(); temp++) {
164
165 Node nNode = nList.item(temp);
166 OutputController.getLogger().log("Found in html: " + nNode.getNodeName());
167 if (nNode.getNodeType() == Node.ELEMENT_NODE) {
168 Element eElement = (Element) nNode;
169 if (elementValidator.isElementValid(eElement)) {
170 found.add(eElement);
171 }
172 }
173 }
174 }
175 return found;
176 }
177
178 }