1 /*

     2  * Copyright (c) 2015, 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  * questions.

    24  */

    25 

    26 package java.net.http;

    27 

    28 import java.nio.ByteBuffer;

    29 import java.nio.CharBuffer;

    30 import java.nio.charset.CharacterCodingException;

    31 import java.nio.charset.CharsetDecoder;

    32 import java.nio.charset.CharsetEncoder;

    33 import java.nio.charset.CoderResult;

    34 import java.nio.charset.CodingErrorAction;

    35 import java.nio.charset.StandardCharsets;

    36 

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

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

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

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

    41 

    42 /*

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

    44  */

    45 final class WSCharsetToolkit {

    46 

    47     private WSCharsetToolkit() { }

    48 

    49     static final class Encoder {

    50 

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

    52 

    53         ByteBuffer encode(CharBuffer in) throws CharacterCodingException {

    54             return encoder.encode(in);

    55         }

    56 

    57         // TODO:

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

    59         //     return encoder.encode(in);

    60         // }

    61     }

    62 

    63     static CharBuffer decode(ByteBuffer in) throws CharacterCodingException {

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

    65     }

    66 

    67     static final class Decoder {

    68 

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

    70 

    71         {

    72             decoder.onMalformedInput(CodingErrorAction.REPORT);

    73             decoder.onUnmappableCharacter(CodingErrorAction.REPORT);

    74         }

    75 

    76         private ByteBuffer leftovers = EMPTY_BYTE_BUFFER;

    77 

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

    79                 throws CharacterCodingException {

    80             ByteBuffer b;

    81             int rem = leftovers.remaining();

    82             if (rem != 0) {

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

    84                 // JDK-8155222 has been resolved

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

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

    87             } else {

    88                 b = in.buffer();

    89             }

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

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

    92             if (r.isError()) {

    93                 r.throwException();

    94             }

    95             if (b.hasRemaining()) {

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

    97             } else {

    98                 leftovers = EMPTY_BYTE_BUFFER;

    99             }

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

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

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

   103                 logger.log(WARNING,

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

   105                         leftovers.remaining());

   106             }

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

   108             in.dispose();

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

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

   111             // malformed"

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

   113             if (endOfInput) {

   114                 r = decoder.flush(out);

   115                 decoder.reset();

   116                 if (r.isOverflow()) {

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

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

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

   120                     // the future

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

   122                 }

   123             }

   124             out.flip();

   125             return WSShared.wrap(out);

   126         }

   127     }

   128 }