1 /*
2  * Copyright (c) 2001, Oracle and/or its affiliates. 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 
24 /*
25  * @test
26  * @bug 4396708
27  * @summary Test URL encoder and decoder on a string that contains
28  * surrogate pairs.
29  *
30  */
31 package test.java.net.URLEncoder;
32 
33 import java.io.*;
34 import java.net.*;
35 import org.testng.annotations.Test;
36 import org.testng.Assert;
37 
38 /*
39  * Surrogate pairs are two character Unicode sequences where the first
40  * character lies in the range [d800, dbff] and the second character lies
41  * in the range [dc00, dfff]. They are used as an escaping mechanism to add
42  * 1M more characters to Unicode.
43  */
44 public class SurrogatePairs {
45 
46     static String[] testStrings = {"\uD800\uDC00",
47             "\uD800\uDFFF",
48             "\uDBFF\uDC00",
49             "\uDBFF\uDFFF",
50             "1\uDBFF\uDC00",
51             "@\uDBFF\uDC00",
52             "\uDBFF\uDC001",
53             "\uDBFF\uDC00@",
54             "\u0101\uDBFF\uDC00",
55             "\uDBFF\uDC00\u0101"
56     };
57 
58     static String[] correctEncodings = {"%F0%90%80%80",
59             "%F0%90%8F%BF",
60             "%F4%8F%B0%80",
61             "%F4%8F%BF%BF",
62             "1%F4%8F%B0%80",
63             "%40%F4%8F%B0%80",
64             "%F4%8F%B0%801",
65             "%F4%8F%B0%80%40",
66             "%C4%81%F4%8F%B0%80",
67             "%F4%8F%B0%80%C4%81"
68     };
69 
70     @Test
testSurrogatePairs()71     public void testSurrogatePairs() throws Exception {
72         for (int i=0; i < testStrings.length; i++) {
73             test(testStrings[i], correctEncodings[i]);
74         }
75     }
76 
test(String str, String correctEncoding)77     private static void test(String str, String correctEncoding)
78             throws Exception {
79         String encoded = URLEncoder.encode(str, "UTF-8");
80 
81         Assert.assertEquals(encoded, correctEncoding);
82 
83         String decoded = URLDecoder.decode(encoded, "UTF-8");
84 
85         Assert.assertEquals(str, decoded);
86     }
87 
88 }