TestUTF8BOM.java revision 395:bc9a0bba6e72 
1/*
2 * Copyright 2008 Sun Microsystems, 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 Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
20 * CA 95054 USA or visit www.sun.com if you need additional information or
21 * have any questions.
22 */
23
24/* @test
25   @bug 4508058 6378911
26   @summary Check if UTF8 decoder handles BOM correctly
27 */
28
29import java.io.IOException;
30import java.nio.BufferOverflowException;
31import java.nio.*;
32import java.nio.charset.*;
33
34/* The fix for 6378911 is to backout the change we made for 4508058,
35   so this regtest is modified accordingly to leave the beginning
36   BOM untouched during decoding.
37 */
38public class TestUTF8BOM {
39    private static ByteBuffer bf = ByteBuffer.allocateDirect(1000);
40    private static void testDecode(String expected, byte[] input)
41        throws Exception
42    {
43        String out = new String(input, "utf8");
44        if (!out.equals(expected)) {
45            failureReport (out, expected);
46            throw new Exception("UTF_8 Decoding test failed");
47        }
48
49        //try directBuffer.
50        bf.clear();
51        bf.put(input).flip();
52        out = Charset.forName("UTF-8")
53                     .decode(bf)
54                     .toString();
55        if (!out.equals(expected)) {
56            failureReport (out, expected);
57            throw new Exception("UTF_8 Decoding test failed(directbuffer)");
58        }
59    }
60
61    private static void failureReport(String testStr,
62                                      String expected) {
63
64        System.err.println ("Expected Characters:");
65        for (int i = 0; i < expected.length() ; i++) {
66            System.out.println("expected char[" + i + "] : " +
67                              Integer.toHexString((int)expected.charAt(i)) +
68                              "  obtained char[" + i + "] : " +
69                              Integer.toHexString((int)testStr.charAt(i)));
70        }
71    }
72
73    public static void main (String[] args) throws Exception {
74            // Test 1: with BOM at beginning
75            testDecode("\ufeff\u0092\u0093",
76                        new byte[] { (byte) 0xef, (byte) 0xbb, (byte) 0xbf,
77                                     (byte) 0xc2, (byte) 0x92,
78                                     (byte) 0xc2, (byte) 0x93 });
79            // Test 2: with BOM at middle
80            testDecode("\u9200\ufeff\u9300",
81                        new byte[] { (byte) 0xe9, (byte) 0x88, (byte) 0x80,
82                                     (byte) 0xef, (byte) 0xbb, (byte) 0xbf,
83                                     (byte) 0xe9, (byte) 0x8c, (byte) 0x80 });
84
85            // Test 3: with BOM at end
86            testDecode("\u9200\u9300\ufeff",
87                        new byte[] { (byte) 0xe9, (byte) 0x88, (byte) 0x80,
88                                     (byte) 0xe9, (byte) 0x8c, (byte) 0x80,
89                                     (byte) 0xef, (byte) 0xbb, (byte) 0xbf });
90            System.err.println ("\nPASSED UTF-8 decode BOM test");
91   }
92}
93