1/*
2 * Copyright 2014 Google, Inc.  All Rights Reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation.
8 *
9 * This code is distributed in the hope that it will be useful, but WITHOUT
10 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
11 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
12 * version 2 for more details (a copy is included in the LICENSE file that
13 * accompanied this code).
14 *
15 * You should have received a copy of the GNU General Public License version
16 * 2 along with this work; if not, write to the Free Software Foundation,
17 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
18 *
19 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
20 * or visit www.oracle.com if you need additional information or have any
21 * questions.
22 */
23
24package parse.jdk7156085;
25
26import java.io.ByteArrayInputStream;
27import java.io.IOException;
28import javax.xml.parsers.SAXParser;
29import javax.xml.parsers.SAXParserFactory;
30import org.xml.sax.InputSource;
31import org.xml.sax.helpers.DefaultHandler;
32import org.testng.annotations.Test;
33
34/**
35 * JDK-7156085: ArrayIndexOutOfBoundsException throws in UTF8Reader of SAXParser
36 * https://bugs.openjdk.java.net/browse/JDK-7156085
37 *
38 * XERCESJ-1257: buffer overflow in UTF8Reader for characters out of BMP
39 * https://issues.apache.org/jira/browse/XERCESJ-1257
40 */
41public class UTF8ReaderBug {
42    @Test
43    public void shouldAcceptSupplementaryCharacters() throws Throwable {
44        StringBuilder b = new StringBuilder("<xml>");
45        for(int i = 5; i < 8223; i++) {
46            b.append(' ');
47        }
48        // Add surrogate characters which overflow the buffer. This shows the need to place an
49        // overflow check at --
50        // com.sun.org.apache.xerces.internal.impl.io.UTF8Reader.read(UTF8Reader.java:544)
51        b.append("\uD835\uDC37");
52        b.append("</xml>");
53        sendToParser(b.toString());
54    }
55
56    private static void sendToParser(String b) throws Throwable {
57        byte[] input = b.getBytes("UTF-8");
58        ByteArrayInputStream in = new ByteArrayInputStream(input);
59
60        SAXParserFactory  spf = SAXParserFactory.newInstance();
61        SAXParser p = spf.newSAXParser();
62        p.parse(new InputSource(in), new DefaultHandler());
63    }
64}
65