1 /*
   2  * Copyright (c) 2008, 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    @bug 6346419
  26    @summary Check correctness of the UTF-32 and its variant charsets
  27  */
  28 
  29 import java.io.*;
  30 import java.nio.*;
  31 import java.nio.charset.*;
  32 
  33 public class TestUTF_32 {
  34     private static void testDecode(String charset,
  35                                    String expected,
  36                                    byte[] input)
  37         throws Exception
  38     {
  39         String out = new String(input, charset);
  40         if (!out.equals(expected)) {
  41             failureReport (out, expected);
  42             throw new Exception("UTF_32 Decoding test failed: " + charset);
  43         }
  44     }
  45 
  46     private static void testEncode(String charset,
  47                                    String input,
  48                                    byte[] expected)
  49         throws Exception
  50     {
  51         byte[] testBytes = input.getBytes(charset);
  52         for (int i = 0; i< expected.length; i++)
  53             if (testBytes[i] != expected[i])
  54                 throw new Exception("UTF_32 Encoding test failed: [" + i + "]"+ charset);
  55 
  56     }
  57 
  58     private static void warn(String s) {
  59         System.err.println("FAILED Test UTF-32:" +
  60                             s) ;
  61     }
  62 
  63     private static void failureReport(String testStr,
  64                                       String expected) {
  65         System.err.println ("Expected Characters:");
  66         for (int i = 0; i < expected.length() ; i++) {
  67             warn("expected char[" + i + "] : " +
  68                   Integer.toHexString((int)expected.charAt(i)) +
  69                  "obtained char[" + i + "] : " +
  70                   Integer.toHexString((int)testStr.charAt(i)));
  71         }
  72     }
  73 
  74     private static void writeInt(OutputStream os, int i, boolean isBig)
  75         throws Exception
  76     {
  77         if (isBig) {
  78             os.write((i>>24) & 0xff);
  79             os.write((i>>16) & 0xff);
  80             os.write((i>>8) & 0xff);
  81             os.write(i & 0xff);
  82         } else {
  83             os.write(i & 0xff);
  84             os.write((i>>8) & 0xff);
  85             os.write((i>>16) & 0xff);
  86             os.write((i>>24) & 0xff);
  87         }
  88     }
  89 
  90     private static byte[] getBytes(boolean doBOM, boolean isBig)
  91         throws Exception
  92     {
  93         ByteArrayOutputStream baos = new ByteArrayOutputStream(1024*1024);
  94         if (doBOM)
  95            writeInt(baos, 0xfeff, isBig);
  96 
  97         for (int i = 0; i < 0xffff; i++) {
  98             if (i < Character.MIN_SURROGATE ||
  99                 i > Character.MAX_SURROGATE)
 100             writeInt(baos, i, isBig);
 101         }
 102         for (int i = 0x10000; i < 0x1ffff; i++) {
 103             writeInt(baos, i, isBig);
 104         }
 105 
 106         for (int i = 0x100000; i < 0x10ffff; i++) {
 107             writeInt(baos, i, isBig);
 108         }
 109         byte[] bb = baos.toByteArray();
 110         baos.close();
 111         return bb;
 112     }
 113 
 114     public static void main (String[] args) throws Exception {
 115         byte[] bb;
 116         String s;
 117 
 118         // Test 1: UTF_32 BigEndian
 119         bb = getBytes(false, true);
 120         s = new String(bb, "UTF-32");
 121         testDecode("UTF_32", s, bb);
 122         testEncode("UTF_32", s, bb);
 123 
 124         // Test 2: UTF_32 LittleEndian Decoding With BOM and
 125         //         BigEndian Encoding
 126         bb = getBytes(true, false);
 127         s = new String(bb, "UTF-32");
 128         bb = getBytes(false, true);
 129         testDecode("UTF_32", s, bb);
 130         testEncode("UTF_32", s, bb);
 131 
 132 
 133         // Test 3: UTF_32BE
 134         bb = getBytes(false, true);
 135         s = new String(bb, "UTF-32BE");
 136         testDecode("UTF_32BE", s, bb);
 137         testEncode("UTF_32BE", s, bb);
 138 
 139 
 140         // Test 4: UTF_32LE
 141         bb = getBytes(false, false);
 142         s = new String(bb, "UTF-32LE");
 143         testDecode("UTF_32LE", s, bb);
 144         testEncode("UTF_32LE", s, bb);
 145 
 146         // Test 5: UTF_32BE_BOM
 147         bb = getBytes(true, true);
 148         s = new String(bb, "UTF-32BE-BOM");
 149         testDecode("UTF_32BE_BOM", s, bb);
 150         testEncode("UTF_32BE_BOM", s, bb);
 151 
 152 
 153         // Test 6: UTF_32LE_BOM
 154         bb = getBytes(true, false);
 155         s = new String(bb, "UTF-32LE-BOM");
 156         testDecode("UTF_32LE_BOM", s, bb);
 157         testEncode("UTF_32LE_BOM", s, bb);
 158 
 159         s = "\u4e00\ufffd\u4e01";
 160         // Test 7: BigEndian with reverse BOM in middle
 161         bb = new byte[] {
 162             (byte)0x00,(byte)0x00,(byte)0x4e,(byte)0x00,
 163             (byte)0xff,(byte)0xfe,(byte)0x00,(byte)0x00,
 164             (byte)0x00,(byte)0x00,(byte)0x4e,(byte)0x01
 165         };
 166         if (!s.equals(new String(bb, "UTF_32")) ||
 167             !s.equals(new String(bb, "UTF_32BE")) ||
 168             !s.equals(new String(bb, "UTF_32BE_BOM")))
 169             throw new Exception("UTF_32 Decoding test failed: ");
 170 
 171         // Test 7: LittleEndian with reverse BOM in middle
 172         bb = new byte[] {
 173             (byte)0xff,(byte)0xfe,(byte)0x00,(byte)0x00,
 174             (byte)0x00,(byte)0x4e,(byte)0x00,(byte)0x00,
 175             (byte)0x00,(byte)0x00,(byte)0xfe,(byte)0xff,
 176             (byte)0x01,(byte)0x4e,(byte)0x00,(byte)0x00
 177         };
 178         if (!s.equals(new String(bb, "UTF_32")) ||
 179             !s.equals(new String(bb, "UTF_32LE")) ||
 180             !s.equals(new String(bb, "UTF_32LE_BOM")))
 181             throw new Exception("UTF_32 Decoding test failed: ");
 182 
 183         // Test 8: Overflow
 184         if (CoderResult.OVERFLOW !=
 185             Charset.forName("UTF_32")
 186             .newDecoder()
 187             .decode((ByteBuffer.allocate(4)
 188                                  .put(new byte[]
 189                                       {(byte)0,(byte)1, (byte)0,(byte)01})
 190                                  .flip()),
 191                     CharBuffer.allocate(1),
 192                     true)) {
 193             throw new Exception ("Test UTF-32 Overflow test failed");
 194         }
 195         System.err.println ("OVERALL PASS OF UTF-32 Test");
 196     }
 197 }