1 /*

     2  * Copyright (c) 2016, 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.  Oracle designates this

     8  * particular file as subject to the "Classpath" exception as provided

     9  * by Oracle in the LICENSE file that accompanied this code.

    10  *

    11  * This code is distributed in the hope that it will be useful, but WITHOUT

    12  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or

    13  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License

    14  * version 2 for more details (a copy is included in the LICENSE file that

    15  * accompanied this code).

    16  *

    17  * You should have received a copy of the GNU General Public License version

    18  * 2 along with this work; if not, write to the Free Software Foundation,

    19  * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.

    20  *

    21  * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA

    22  * or visit www.oracle.com if you need additional information or have any

    23  */

    24 package java.net.http;

    25 

    26 import java.nio.ByteBuffer;

    27 import java.nio.CharBuffer;

    28 import java.nio.charset.CharacterCodingException;

    29 import java.nio.charset.CharsetDecoder;

    30 import java.nio.charset.CharsetEncoder;

    31 import java.nio.charset.CoderResult;

    32 import java.nio.charset.CodingErrorAction;

    33 import java.nio.charset.StandardCharsets;

    34 

    35 import static java.lang.System.Logger.Level.WARNING;

    36 import static java.net.http.WSUtils.EMPTY_BYTE_BUFFER;

    37 import static java.net.http.WSUtils.logger;

    38 import static java.nio.charset.StandardCharsets.UTF_8;

    39 

    40 /*

    41  * A collection of tools for UTF-8 coding.

    42  */

    43 final class WSCharsetToolkit {

    44 

    45     private WSCharsetToolkit() { }

    46 

    47     static final class Encoder {

    48 

    49         private final CharsetEncoder encoder = UTF_8.newEncoder();

    50 

    51         ByteBuffer encode(CharBuffer in) throws CharacterCodingException {

    52             return encoder.encode(in);

    53         }

    54 

    55         // TODO:

    56         // ByteBuffer[] encode(CharBuffer in) throws CharacterCodingException {

    57         //     return encoder.encode(in);

    58         // }

    59     }

    60 

    61     static CharBuffer decode(ByteBuffer in) throws CharacterCodingException {

    62         return UTF_8.newDecoder().decode(in);

    63     }

    64 

    65     static final class Decoder {

    66 

    67         private final CharsetDecoder decoder = StandardCharsets.UTF_8.newDecoder();

    68 

    69         {

    70             decoder.onMalformedInput(CodingErrorAction.REPORT);

    71             decoder.onUnmappableCharacter(CodingErrorAction.REPORT);

    72         }

    73 

    74         private ByteBuffer leftovers = EMPTY_BYTE_BUFFER;

    75 

    76         WSShared<CharBuffer> decode(WSShared<ByteBuffer> in, boolean endOfInput)

    77                 throws CharacterCodingException {

    78             ByteBuffer b;

    79             int rem = leftovers.remaining();

    80             if (rem != 0) {

    81                 // TODO: We won't need this wasteful allocation & copying when

    82                 // JDK-8155222 has been resolved

    83                 b = ByteBuffer.allocate(rem + in.remaining());

    84                 b.put(leftovers).put(in.buffer()).flip();

    85             } else {

    86                 b = in.buffer();

    87             }

    88             CharBuffer out = CharBuffer.allocate(b.remaining());

    89             CoderResult r = decoder.decode(b, out, endOfInput);

    90             if (r.isError()) {

    91                 r.throwException();

    92             }

    93             if (b.hasRemaining()) {

    94                 leftovers = ByteBuffer.allocate(b.remaining()).put(b).flip();

    95             } else {

    96                 leftovers = EMPTY_BYTE_BUFFER;

    97             }

    98             // Since it's UTF-8, the assumption is leftovers.remaining() < 4

    99             // (i.e. small). Otherwise a shared buffer should be used

   100             if (!(leftovers.remaining() < 4)) {

   101                 logger.log(WARNING,

   102                         "The size of decoding leftovers is greater than expected: {0}",

   103                         leftovers.remaining());

   104             }

   105             b.position(b.limit()); // As if we always read to the end

   106             in.dispose();

   107             // Decoder promises that in the case of endOfInput == true:

   108             // "...any remaining undecoded input will be treated as being

   109             // malformed"

   110             assert !(endOfInput && leftovers.hasRemaining()) : endOfInput + ", " + leftovers;

   111             if (endOfInput) {

   112                 r = decoder.flush(out);

   113                 decoder.reset();

   114                 if (r.isOverflow()) {

   115                     // FIXME: for now I know flush() does nothing. But the

   116                     // implementation of UTF8 decoder might change. And if now

   117                     // flush() is a no-op, it is not guaranteed to remain so in

   118                     // the future

   119                     throw new InternalError("Not yet implemented");

   120                 }

   121             }

   122             out.flip();

   123             return WSShared.wrap(out);

   124         }

   125     }

   126 }