|
1 /* |
|
2 * Copyright (c) 1999, 2006, 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 /* @test |
|
25 * @bug 4085160 4139951 5005831 |
|
26 * @summary Test that required character encodings are supported |
|
27 */ |
|
28 |
|
29 import java.io.InputStreamReader; |
|
30 import java.io.OutputStreamWriter; |
|
31 import java.io.ByteArrayInputStream; |
|
32 import java.io.ByteArrayOutputStream; |
|
33 import java.nio.charset.Charset; |
|
34 import java.nio.charset.UnsupportedCharsetException; |
|
35 |
|
36 |
|
37 public class Encodings { |
|
38 |
|
39 |
|
40 static boolean equals(byte[] a, byte[] b) { |
|
41 if (a.length != b.length) return false; |
|
42 for (int i = 0; i < a.length; i++) |
|
43 if (a[i] != b[i]) return false; |
|
44 return true; |
|
45 } |
|
46 |
|
47 |
|
48 static void go(String enc, String str, final byte[] bytes, boolean bidir) |
|
49 throws Exception |
|
50 { |
|
51 final Charset charset = Charset.forName(enc); |
|
52 |
|
53 /* String(byte[] bs, String enc) */ |
|
54 if (!(new String(bytes, enc).equals(str))) |
|
55 throw new Exception(enc + ": String constructor failed"); |
|
56 |
|
57 /* String(byte[] bs, Charset charset) */ |
|
58 if (!(new String(bytes, charset).equals(str))) |
|
59 throw new Exception(charset + ": String constructor failed"); |
|
60 |
|
61 /* String(byte[] bs, int off, int len, Charset charset) */ |
|
62 String start = str.substring(0, 2); |
|
63 String end = str.substring(2); |
|
64 if (enc.equals("UTF-16BE") || enc.equals("UTF-16LE")) { |
|
65 if (!(new String(bytes, 0, 4, charset).equals(start))) |
|
66 throw new Exception(charset + ": String constructor failed"); |
|
67 if (!(new String(bytes, 4, bytes.length - 4, charset).equals(end))) |
|
68 throw new Exception(charset + ": String constructor failed"); |
|
69 } else if (enc.equals("UTF-16")) { |
|
70 if (!(new String(bytes, 0, 6, charset).equals(start))) |
|
71 throw new Exception(charset + ": String constructor failed"); |
|
72 } else { |
|
73 if (!(new String(bytes, 0, 2, charset).equals(start))) |
|
74 throw new Exception(charset + ": String constructor failed"); |
|
75 if (!(new String(bytes, 2, bytes.length - 2, charset).equals(end))) |
|
76 throw new Exception(charset + ": String constructor failed"); |
|
77 } |
|
78 |
|
79 /* InputStreamReader */ |
|
80 ByteArrayInputStream bi = new ByteArrayInputStream(bytes); |
|
81 InputStreamReader r = new InputStreamReader(bi, enc); |
|
82 String inEnc = r.getEncoding(); |
|
83 int n = str.length(); |
|
84 char[] cs = new char[n]; |
|
85 for (int i = 0; i < n;) { |
|
86 int m; |
|
87 if ((m = r.read(cs, i, n - i)) < 0) |
|
88 throw new Exception(enc + ": EOF on InputStreamReader"); |
|
89 i += m; |
|
90 } |
|
91 if (!(new String(cs).equals(str))) |
|
92 throw new Exception(enc + ": InputStreamReader failed"); |
|
93 |
|
94 if (!bidir) { |
|
95 System.err.println(enc + " --> " + inEnc); |
|
96 return; |
|
97 } |
|
98 |
|
99 /* String.getBytes(String enc) */ |
|
100 byte[] bs = str.getBytes(enc); |
|
101 if (!equals(bs, bytes)) |
|
102 throw new Exception(enc + ": String.getBytes failed"); |
|
103 |
|
104 /* String.getBytes(Charset charset) */ |
|
105 bs = str.getBytes(charset); |
|
106 if (!equals(bs, bytes)) |
|
107 throw new Exception(charset + ": String.getBytes failed"); |
|
108 |
|
109 // Calls to String.getBytes(Charset) shouldn't automatically |
|
110 // use the cached thread-local encoder. |
|
111 if (charset.name().equals("UTF-16BE")) { |
|
112 String s = new String(bytes, charset); |
|
113 // Replace the thread-local encoder with this one. |
|
114 byte[] bb = s.getBytes(Charset.forName("UTF-16LE")); |
|
115 if (bytes.length != bb.length) { |
|
116 // Incidental test. |
|
117 throw new RuntimeException("unequal length: " |
|
118 + bytes.length + " != " |
|
119 + bb.length); |
|
120 } else { |
|
121 boolean diff = false; |
|
122 // Expect different byte[] between UTF-16LE and UTF-16BE |
|
123 // even though encoder was previously cached by last call |
|
124 // to getBytes(). |
|
125 for (int i = 0; i < bytes.length; i++) { |
|
126 if (bytes[i] != bb[i]) |
|
127 diff = true; |
|
128 } |
|
129 if (!diff) |
|
130 throw new RuntimeException("byte arrays equal"); |
|
131 } |
|
132 } |
|
133 |
|
134 /* OutputStreamWriter */ |
|
135 ByteArrayOutputStream bo = new ByteArrayOutputStream(); |
|
136 OutputStreamWriter w = new OutputStreamWriter(bo, enc); |
|
137 String outEnc = w.getEncoding(); |
|
138 w.write(str); |
|
139 w.close(); |
|
140 bs = bo.toByteArray(); |
|
141 if (!equals(bs, bytes)) |
|
142 throw new Exception(enc + ": OutputStreamWriter failed"); |
|
143 |
|
144 System.err.println(enc + " --> " + inEnc + " / " + outEnc); |
|
145 } |
|
146 |
|
147 |
|
148 static void go(String enc, String str, byte[] bytes) throws Exception { |
|
149 go(enc, str, bytes, true); |
|
150 } |
|
151 |
|
152 |
|
153 public static void main(String[] args) throws Exception { |
|
154 |
|
155 go("US-ASCII", "abc", new byte[] { 'a', 'b', 'c' }); |
|
156 go("us-ascii", "abc", new byte[] { 'a', 'b', 'c' }); |
|
157 go("ISO646-US", "abc", new byte[] { 'a', 'b', 'c' }); |
|
158 go("ISO-8859-1", "ab\u00c7", new byte[] { 'a', 'b', (byte)'\u00c7' }); |
|
159 go("UTF-8", "ab\u1e09", |
|
160 new byte[] { 'a', 'b', |
|
161 (byte)(0xe0 | (0x0f & (0x1e09 >> 12))), |
|
162 (byte)(0x80 | (0x3f & (0x1e09 >> 6))), |
|
163 (byte)(0x80 | (0x3f & 0x1e09)) }); |
|
164 go("UTF-16BE", "ab\u1e09", |
|
165 new byte[] { 0, 'a', 0, 'b', 0x1e, 0x09 }); |
|
166 go("UTF-16LE", "ab\u1e09", |
|
167 new byte[] { 'a', 0, 'b', 0, 0x09, 0x1e }); |
|
168 |
|
169 /* UTF-16 accepts both byte orders on input but always uses big-endian |
|
170 * on output, so test all three cases |
|
171 */ |
|
172 go("UTF-16", "ab\u1e09", |
|
173 new byte[] { (byte)0xfe, (byte)0xff, 0, 'a', 0, 'b', 0x1e, 0x09 }); |
|
174 go("UTF-16", "ab\u1e09", |
|
175 new byte[] { (byte)0xff, (byte)0xfe, 'a', 0, 'b', 0, 0x09, 0x1e }, |
|
176 false); |
|
177 } |
|
178 |
|
179 } |