rt/emul/compact/src/main/java/java/nio/charset/CharsetEncoder.java
author Jaroslav Tulach <jtulach@netbeans.org>
Thu, 03 Oct 2013 15:40:35 +0200
branchjdk7-b147
changeset 1334 588d5bf7a560
child 1337 c794024954b5
permissions -rw-r--r--
Set of JDK classes needed to run javac
     1 /*
     2  * Copyright (c) 2000, 2008, Oracle and/or its affiliates. All rights reserved.
     3  * ORACLE PROPRIETARY/CONFIDENTIAL. Use is subject to license terms.
     4  *
     5  *
     6  *
     7  *
     8  *
     9  *
    10  *
    11  *
    12  *
    13  *
    14  *
    15  *
    16  *
    17  *
    18  *
    19  *
    20  *
    21  *
    22  *
    23  *
    24  */
    25 
    26 // -- This file was mechanically generated: Do not edit! -- //
    27 
    28 package java.nio.charset;
    29 
    30 import java.nio.Buffer;
    31 import java.nio.ByteBuffer;
    32 import java.nio.CharBuffer;
    33 import java.nio.BufferOverflowException;
    34 import java.nio.BufferUnderflowException;
    35 import java.lang.ref.WeakReference;
    36 import java.nio.charset.CoderMalfunctionError;                  // javadoc
    37 
    38 
    39 /**
    40  * An engine that can transform a sequence of sixteen-bit Unicode characters into a sequence of
    41  * bytes in a specific charset.
    42  *
    43  * <a name="steps">
    44  *
    45  * <p> The input character sequence is provided in a character buffer or a series
    46  * of such buffers.  The output byte sequence is written to a byte buffer
    47  * or a series of such buffers.  An encoder should always be used by making
    48  * the following sequence of method invocations, hereinafter referred to as an
    49  * <i>encoding operation</i>:
    50  *
    51  * <ol>
    52  *
    53  *   <li><p> Reset the encoder via the {@link #reset reset} method, unless it
    54  *   has not been used before; </p></li>
    55  *
    56  *   <li><p> Invoke the {@link #encode encode} method zero or more times, as
    57  *   long as additional input may be available, passing <tt>false</tt> for the
    58  *   <tt>endOfInput</tt> argument and filling the input buffer and flushing the
    59  *   output buffer between invocations; </p></li>
    60  *
    61  *   <li><p> Invoke the {@link #encode encode} method one final time, passing
    62  *   <tt>true</tt> for the <tt>endOfInput</tt> argument; and then </p></li>
    63  *
    64  *   <li><p> Invoke the {@link #flush flush} method so that the encoder can
    65  *   flush any internal state to the output buffer. </p></li>
    66  *
    67  * </ol>
    68  *
    69  * Each invocation of the {@link #encode encode} method will encode as many
    70  * characters as possible from the input buffer, writing the resulting bytes
    71  * to the output buffer.  The {@link #encode encode} method returns when more
    72  * input is required, when there is not enough room in the output buffer, or
    73  * when an encoding error has occurred.  In each case a {@link CoderResult}
    74  * object is returned to describe the reason for termination.  An invoker can
    75  * examine this object and fill the input buffer, flush the output buffer, or
    76  * attempt to recover from an encoding error, as appropriate, and try again.
    77  *
    78  * <a name="ce">
    79  *
    80  * <p> There are two general types of encoding errors.  If the input character
    81  * sequence is not a legal sixteen-bit Unicode sequence then the input is considered <i>malformed</i>.  If
    82  * the input character sequence is legal but cannot be mapped to a valid
    83  * byte sequence in the given charset then an <i>unmappable character</i> has been encountered.
    84  *
    85  * <a name="cae">
    86  *
    87  * <p> How an encoding error is handled depends upon the action requested for
    88  * that type of error, which is described by an instance of the {@link
    89  * CodingErrorAction} class.  The possible error actions are to {@link
    90  * CodingErrorAction#IGNORE </code>ignore<code>} the erroneous input, {@link
    91  * CodingErrorAction#REPORT </code>report<code>} the error to the invoker via
    92  * the returned {@link CoderResult} object, or {@link CodingErrorAction#REPLACE
    93  * </code>replace<code>} the erroneous input with the current value of the
    94  * replacement byte array.  The replacement
    95  *
    96 
    97  * is initially set to the encoder's default replacement, which often
    98  * (but not always) has the initial value&nbsp;<tt>{</tt>&nbsp;<tt>(byte)'?'</tt>&nbsp;<tt>}</tt>;
    99 
   100 
   101 
   102 
   103  *
   104  * its value may be changed via the {@link #replaceWith(byte[])
   105  * replaceWith} method.
   106  *
   107  * <p> The default action for malformed-input and unmappable-character errors
   108  * is to {@link CodingErrorAction#REPORT </code>report<code>} them.  The
   109  * malformed-input error action may be changed via the {@link
   110  * #onMalformedInput(CodingErrorAction) onMalformedInput} method; the
   111  * unmappable-character action may be changed via the {@link
   112  * #onUnmappableCharacter(CodingErrorAction) onUnmappableCharacter} method.
   113  *
   114  * <p> This class is designed to handle many of the details of the encoding
   115  * process, including the implementation of error actions.  An encoder for a
   116  * specific charset, which is a concrete subclass of this class, need only
   117  * implement the abstract {@link #encodeLoop encodeLoop} method, which
   118  * encapsulates the basic encoding loop.  A subclass that maintains internal
   119  * state should, additionally, override the {@link #implFlush implFlush} and
   120  * {@link #implReset implReset} methods.
   121  *
   122  * <p> Instances of this class are not safe for use by multiple concurrent
   123  * threads.  </p>
   124  *
   125  *
   126  * @author Mark Reinhold
   127  * @author JSR-51 Expert Group
   128  * @since 1.4
   129  *
   130  * @see ByteBuffer
   131  * @see CharBuffer
   132  * @see Charset
   133  * @see CharsetDecoder
   134  */
   135 
   136 public abstract class CharsetEncoder {
   137 
   138     private final Charset charset;
   139     private final float averageBytesPerChar;
   140     private final float maxBytesPerChar;
   141 
   142     private byte[] replacement;
   143     private CodingErrorAction malformedInputAction
   144         = CodingErrorAction.REPORT;
   145     private CodingErrorAction unmappableCharacterAction
   146         = CodingErrorAction.REPORT;
   147 
   148     // Internal states
   149     //
   150     private static final int ST_RESET   = 0;
   151     private static final int ST_CODING  = 1;
   152     private static final int ST_END     = 2;
   153     private static final int ST_FLUSHED = 3;
   154 
   155     private int state = ST_RESET;
   156 
   157     private static String stateNames[]
   158         = { "RESET", "CODING", "CODING_END", "FLUSHED" };
   159 
   160 
   161     /**
   162      * Initializes a new encoder.  The new encoder will have the given
   163      * bytes-per-char and replacement values. </p>
   164      *
   165      * @param  averageBytesPerChar
   166      *         A positive float value indicating the expected number of
   167      *         bytes that will be produced for each input character
   168      *
   169      * @param  maxBytesPerChar
   170      *         A positive float value indicating the maximum number of
   171      *         bytes that will be produced for each input character
   172      *
   173      * @param  replacement
   174      *         The initial replacement; must not be <tt>null</tt>, must have
   175      *         non-zero length, must not be longer than maxBytesPerChar,
   176      *         and must be {@link #isLegalReplacement </code>legal<code>}
   177      *
   178      * @throws  IllegalArgumentException
   179      *          If the preconditions on the parameters do not hold
   180      */
   181     protected
   182     CharsetEncoder(Charset cs,
   183                    float averageBytesPerChar,
   184                    float maxBytesPerChar,
   185                    byte[] replacement)
   186     {
   187         this.charset = cs;
   188         if (averageBytesPerChar <= 0.0f)
   189             throw new IllegalArgumentException("Non-positive "
   190                                                + "averageBytesPerChar");
   191         if (maxBytesPerChar <= 0.0f)
   192             throw new IllegalArgumentException("Non-positive "
   193                                                + "maxBytesPerChar");
   194         if (!Charset.atBugLevel("1.4")) {
   195             if (averageBytesPerChar > maxBytesPerChar)
   196                 throw new IllegalArgumentException("averageBytesPerChar"
   197                                                    + " exceeds "
   198                                                    + "maxBytesPerChar");
   199         }
   200         this.replacement = replacement;
   201         this.averageBytesPerChar = averageBytesPerChar;
   202         this.maxBytesPerChar = maxBytesPerChar;
   203         replaceWith(replacement);
   204     }
   205 
   206     /**
   207      * Initializes a new encoder.  The new encoder will have the given
   208      * bytes-per-char values and its replacement will be the
   209      * byte array <tt>{</tt>&nbsp;<tt>(byte)'?'</tt>&nbsp;<tt>}</tt>. </p>
   210      *
   211      * @param  averageBytesPerChar
   212      *         A positive float value indicating the expected number of
   213      *         bytes that will be produced for each input character
   214      *
   215      * @param  maxBytesPerChar
   216      *         A positive float value indicating the maximum number of
   217      *         bytes that will be produced for each input character
   218      *
   219      * @throws  IllegalArgumentException
   220      *          If the preconditions on the parameters do not hold
   221      */
   222     protected CharsetEncoder(Charset cs,
   223                              float averageBytesPerChar,
   224                              float maxBytesPerChar)
   225     {
   226         this(cs,
   227              averageBytesPerChar, maxBytesPerChar,
   228              new byte[] { (byte)'?' });
   229     }
   230 
   231     /**
   232      * Returns the charset that created this encoder.  </p>
   233      *
   234      * @return  This encoder's charset
   235      */
   236     public final Charset charset() {
   237         return charset;
   238     }
   239 
   240     /**
   241      * Returns this encoder's replacement value. </p>
   242      *
   243      * @return  This encoder's current replacement,
   244      *          which is never <tt>null</tt> and is never empty
   245      */
   246     public final byte[] replacement() {
   247         return replacement;
   248     }
   249 
   250     /**
   251      * Changes this encoder's replacement value.
   252      *
   253      * <p> This method invokes the {@link #implReplaceWith implReplaceWith}
   254      * method, passing the new replacement, after checking that the new
   255      * replacement is acceptable.  </p>
   256      *
   257      * @param  newReplacement
   258      *
   259 
   260 
   261 
   262 
   263 
   264      *         The new replacement; must not be <tt>null</tt>, must have
   265      *         non-zero length, must not be longer than the value returned by
   266      *         the {@link #maxBytesPerChar() maxBytesPerChar} method, and
   267      *         must be {@link #isLegalReplacement </code>legal<code>}
   268 
   269      *
   270      * @return  This encoder
   271      *
   272      * @throws  IllegalArgumentException
   273      *          If the preconditions on the parameter do not hold
   274      */
   275     public final CharsetEncoder replaceWith(byte[] newReplacement) {
   276         if (newReplacement == null)
   277             throw new IllegalArgumentException("Null replacement");
   278         int len = newReplacement.length;
   279         if (len == 0)
   280             throw new IllegalArgumentException("Empty replacement");
   281         if (len > maxBytesPerChar)
   282             throw new IllegalArgumentException("Replacement too long");
   283 
   284         if (!isLegalReplacement(newReplacement))
   285             throw new IllegalArgumentException("Illegal replacement");
   286 
   287         this.replacement = newReplacement;
   288         implReplaceWith(newReplacement);
   289         return this;
   290     }
   291 
   292     /**
   293      * Reports a change to this encoder's replacement value.
   294      *
   295      * <p> The default implementation of this method does nothing.  This method
   296      * should be overridden by encoders that require notification of changes to
   297      * the replacement.  </p>
   298      *
   299      * @param  newReplacement
   300      */
   301     protected void implReplaceWith(byte[] newReplacement) {
   302     }
   303 
   304 
   305 
   306     private WeakReference<CharsetDecoder> cachedDecoder = null;
   307 
   308     /**
   309      * Tells whether or not the given byte array is a legal replacement value
   310      * for this encoder.
   311      *
   312      * <p> A replacement is legal if, and only if, it is a legal sequence of
   313      * bytes in this encoder's charset; that is, it must be possible to decode
   314      * the replacement into one or more sixteen-bit Unicode characters.
   315      *
   316      * <p> The default implementation of this method is not very efficient; it
   317      * should generally be overridden to improve performance.  </p>
   318      *
   319      * @param  repl  The byte array to be tested
   320      *
   321      * @return  <tt>true</tt> if, and only if, the given byte array
   322      *          is a legal replacement value for this encoder
   323      */
   324     public boolean isLegalReplacement(byte[] repl) {
   325         WeakReference<CharsetDecoder> wr = cachedDecoder;
   326         CharsetDecoder dec = null;
   327         if ((wr == null) || ((dec = wr.get()) == null)) {
   328             dec = charset().newDecoder();
   329             dec.onMalformedInput(CodingErrorAction.REPORT);
   330             dec.onUnmappableCharacter(CodingErrorAction.REPORT);
   331             cachedDecoder = new WeakReference<CharsetDecoder>(dec);
   332         } else {
   333             dec.reset();
   334         }
   335         ByteBuffer bb = ByteBuffer.wrap(repl);
   336         CharBuffer cb = CharBuffer.allocate((int)(bb.remaining()
   337                                                   * dec.maxCharsPerByte()));
   338         CoderResult cr = dec.decode(bb, cb, true);
   339         return !cr.isError();
   340     }
   341 
   342 
   343 
   344     /**
   345      * Returns this encoder's current action for malformed-input errors.  </p>
   346      *
   347      * @return The current malformed-input action, which is never <tt>null</tt>
   348      */
   349     public CodingErrorAction malformedInputAction() {
   350         return malformedInputAction;
   351     }
   352 
   353     /**
   354      * Changes this encoder's action for malformed-input errors.  </p>
   355      *
   356      * <p> This method invokes the {@link #implOnMalformedInput
   357      * implOnMalformedInput} method, passing the new action.  </p>
   358      *
   359      * @param  newAction  The new action; must not be <tt>null</tt>
   360      *
   361      * @return  This encoder
   362      *
   363      * @throws IllegalArgumentException
   364      *         If the precondition on the parameter does not hold
   365      */
   366     public final CharsetEncoder onMalformedInput(CodingErrorAction newAction) {
   367         if (newAction == null)
   368             throw new IllegalArgumentException("Null action");
   369         malformedInputAction = newAction;
   370         implOnMalformedInput(newAction);
   371         return this;
   372     }
   373 
   374     /**
   375      * Reports a change to this encoder's malformed-input action.
   376      *
   377      * <p> The default implementation of this method does nothing.  This method
   378      * should be overridden by encoders that require notification of changes to
   379      * the malformed-input action.  </p>
   380      */
   381     protected void implOnMalformedInput(CodingErrorAction newAction) { }
   382 
   383     /**
   384      * Returns this encoder's current action for unmappable-character errors.
   385      * </p>
   386      *
   387      * @return The current unmappable-character action, which is never
   388      *         <tt>null</tt>
   389      */
   390     public CodingErrorAction unmappableCharacterAction() {
   391         return unmappableCharacterAction;
   392     }
   393 
   394     /**
   395      * Changes this encoder's action for unmappable-character errors.
   396      *
   397      * <p> This method invokes the {@link #implOnUnmappableCharacter
   398      * implOnUnmappableCharacter} method, passing the new action.  </p>
   399      *
   400      * @param  newAction  The new action; must not be <tt>null</tt>
   401      *
   402      * @return  This encoder
   403      *
   404      * @throws IllegalArgumentException
   405      *         If the precondition on the parameter does not hold
   406      */
   407     public final CharsetEncoder onUnmappableCharacter(CodingErrorAction
   408                                                       newAction)
   409     {
   410         if (newAction == null)
   411             throw new IllegalArgumentException("Null action");
   412         unmappableCharacterAction = newAction;
   413         implOnUnmappableCharacter(newAction);
   414         return this;
   415     }
   416 
   417     /**
   418      * Reports a change to this encoder's unmappable-character action.
   419      *
   420      * <p> The default implementation of this method does nothing.  This method
   421      * should be overridden by encoders that require notification of changes to
   422      * the unmappable-character action.  </p>
   423      */
   424     protected void implOnUnmappableCharacter(CodingErrorAction newAction) { }
   425 
   426     /**
   427      * Returns the average number of bytes that will be produced for each
   428      * character of input.  This heuristic value may be used to estimate the size
   429      * of the output buffer required for a given input sequence. </p>
   430      *
   431      * @return  The average number of bytes produced
   432      *          per character of input
   433      */
   434     public final float averageBytesPerChar() {
   435         return averageBytesPerChar;
   436     }
   437 
   438     /**
   439      * Returns the maximum number of bytes that will be produced for each
   440      * character of input.  This value may be used to compute the worst-case size
   441      * of the output buffer required for a given input sequence. </p>
   442      *
   443      * @return  The maximum number of bytes that will be produced per
   444      *          character of input
   445      */
   446     public final float maxBytesPerChar() {
   447         return maxBytesPerChar;
   448     }
   449 
   450     /**
   451      * Encodes as many characters as possible from the given input buffer,
   452      * writing the results to the given output buffer.
   453      *
   454      * <p> The buffers are read from, and written to, starting at their current
   455      * positions.  At most {@link Buffer#remaining in.remaining()} characters
   456      * will be read and at most {@link Buffer#remaining out.remaining()}
   457      * bytes will be written.  The buffers' positions will be advanced to
   458      * reflect the characters read and the bytes written, but their marks and
   459      * limits will not be modified.
   460      *
   461      * <p> In addition to reading characters from the input buffer and writing
   462      * bytes to the output buffer, this method returns a {@link CoderResult}
   463      * object to describe its reason for termination:
   464      *
   465      * <ul>
   466      *
   467      *   <li><p> {@link CoderResult#UNDERFLOW} indicates that as much of the
   468      *   input buffer as possible has been encoded.  If there is no further
   469      *   input then the invoker can proceed to the next step of the
   470      *   <a href="#steps">encoding operation</a>.  Otherwise this method
   471      *   should be invoked again with further input.  </p></li>
   472      *
   473      *   <li><p> {@link CoderResult#OVERFLOW} indicates that there is
   474      *   insufficient space in the output buffer to encode any more characters.
   475      *   This method should be invoked again with an output buffer that has
   476      *   more {@linkplain Buffer#remaining remaining} bytes. This is
   477      *   typically done by draining any encoded bytes from the output
   478      *   buffer.  </p></li>
   479      *
   480      *   <li><p> A {@link CoderResult#malformedForLength
   481      *   </code>malformed-input<code>} result indicates that a malformed-input
   482      *   error has been detected.  The malformed characters begin at the input
   483      *   buffer's (possibly incremented) position; the number of malformed
   484      *   characters may be determined by invoking the result object's {@link
   485      *   CoderResult#length() length} method.  This case applies only if the
   486      *   {@link #onMalformedInput </code>malformed action<code>} of this encoder
   487      *   is {@link CodingErrorAction#REPORT}; otherwise the malformed input
   488      *   will be ignored or replaced, as requested.  </p></li>
   489      *
   490      *   <li><p> An {@link CoderResult#unmappableForLength
   491      *   </code>unmappable-character<code>} result indicates that an
   492      *   unmappable-character error has been detected.  The characters that
   493      *   encode the unmappable character begin at the input buffer's (possibly
   494      *   incremented) position; the number of such characters may be determined
   495      *   by invoking the result object's {@link CoderResult#length() length}
   496      *   method.  This case applies only if the {@link #onUnmappableCharacter
   497      *   </code>unmappable action<code>} of this encoder is {@link
   498      *   CodingErrorAction#REPORT}; otherwise the unmappable character will be
   499      *   ignored or replaced, as requested.  </p></li>
   500      *
   501      * </ul>
   502      *
   503      * In any case, if this method is to be reinvoked in the same encoding
   504      * operation then care should be taken to preserve any characters remaining
   505      * in the input buffer so that they are available to the next invocation.
   506      *
   507      * <p> The <tt>endOfInput</tt> parameter advises this method as to whether
   508      * the invoker can provide further input beyond that contained in the given
   509      * input buffer.  If there is a possibility of providing additional input
   510      * then the invoker should pass <tt>false</tt> for this parameter; if there
   511      * is no possibility of providing further input then the invoker should
   512      * pass <tt>true</tt>.  It is not erroneous, and in fact it is quite
   513      * common, to pass <tt>false</tt> in one invocation and later discover that
   514      * no further input was actually available.  It is critical, however, that
   515      * the final invocation of this method in a sequence of invocations always
   516      * pass <tt>true</tt> so that any remaining unencoded input will be treated
   517      * as being malformed.
   518      *
   519      * <p> This method works by invoking the {@link #encodeLoop encodeLoop}
   520      * method, interpreting its results, handling error conditions, and
   521      * reinvoking it as necessary.  </p>
   522      *
   523      *
   524      * @param  in
   525      *         The input character buffer
   526      *
   527      * @param  out
   528      *         The output byte buffer
   529      *
   530      * @param  endOfInput
   531      *         <tt>true</tt> if, and only if, the invoker can provide no
   532      *         additional input characters beyond those in the given buffer
   533      *
   534      * @return  A coder-result object describing the reason for termination
   535      *
   536      * @throws  IllegalStateException
   537      *          If an encoding operation is already in progress and the previous
   538      *          step was an invocation neither of the {@link #reset reset}
   539      *          method, nor of this method with a value of <tt>false</tt> for
   540      *          the <tt>endOfInput</tt> parameter, nor of this method with a
   541      *          value of <tt>true</tt> for the <tt>endOfInput</tt> parameter
   542      *          but a return value indicating an incomplete encoding operation
   543      *
   544      * @throws  CoderMalfunctionError
   545      *          If an invocation of the encodeLoop method threw
   546      *          an unexpected exception
   547      */
   548     public final CoderResult encode(CharBuffer in, ByteBuffer out,
   549                                     boolean endOfInput)
   550     {
   551         int newState = endOfInput ? ST_END : ST_CODING;
   552         if ((state != ST_RESET) && (state != ST_CODING)
   553             && !(endOfInput && (state == ST_END)))
   554             throwIllegalStateException(state, newState);
   555         state = newState;
   556 
   557         for (;;) {
   558 
   559             CoderResult cr;
   560             try {
   561                 cr = encodeLoop(in, out);
   562             } catch (BufferUnderflowException x) {
   563                 throw new CoderMalfunctionError(x);
   564             } catch (BufferOverflowException x) {
   565                 throw new CoderMalfunctionError(x);
   566             }
   567 
   568             if (cr.isOverflow())
   569                 return cr;
   570 
   571             if (cr.isUnderflow()) {
   572                 if (endOfInput && in.hasRemaining()) {
   573                     cr = CoderResult.malformedForLength(in.remaining());
   574                     // Fall through to malformed-input case
   575                 } else {
   576                     return cr;
   577                 }
   578             }
   579 
   580             CodingErrorAction action = null;
   581             if (cr.isMalformed())
   582                 action = malformedInputAction;
   583             else if (cr.isUnmappable())
   584                 action = unmappableCharacterAction;
   585             else
   586                 assert false : cr.toString();
   587 
   588             if (action == CodingErrorAction.REPORT)
   589                 return cr;
   590 
   591             if (action == CodingErrorAction.REPLACE) {
   592                 if (out.remaining() < replacement.length)
   593                     return CoderResult.OVERFLOW;
   594                 out.put(replacement);
   595             }
   596 
   597             if ((action == CodingErrorAction.IGNORE)
   598                 || (action == CodingErrorAction.REPLACE)) {
   599                 // Skip erroneous input either way
   600                 in.position(in.position() + cr.length());
   601                 continue;
   602             }
   603 
   604             assert false;
   605         }
   606 
   607     }
   608 
   609     /**
   610      * Flushes this encoder.
   611      *
   612      * <p> Some encoders maintain internal state and may need to write some
   613      * final bytes to the output buffer once the overall input sequence has
   614      * been read.
   615      *
   616      * <p> Any additional output is written to the output buffer beginning at
   617      * its current position.  At most {@link Buffer#remaining out.remaining()}
   618      * bytes will be written.  The buffer's position will be advanced
   619      * appropriately, but its mark and limit will not be modified.
   620      *
   621      * <p> If this method completes successfully then it returns {@link
   622      * CoderResult#UNDERFLOW}.  If there is insufficient room in the output
   623      * buffer then it returns {@link CoderResult#OVERFLOW}.  If this happens
   624      * then this method must be invoked again, with an output buffer that has
   625      * more room, in order to complete the current <a href="#steps">encoding
   626      * operation</a>.
   627      *
   628      * <p> If this encoder has already been flushed then invoking this method
   629      * has no effect.
   630      *
   631      * <p> This method invokes the {@link #implFlush implFlush} method to
   632      * perform the actual flushing operation.  </p>
   633      *
   634      * @param  out
   635      *         The output byte buffer
   636      *
   637      * @return  A coder-result object, either {@link CoderResult#UNDERFLOW} or
   638      *          {@link CoderResult#OVERFLOW}
   639      *
   640      * @throws  IllegalStateException
   641      *          If the previous step of the current encoding operation was an
   642      *          invocation neither of the {@link #flush flush} method nor of
   643      *          the three-argument {@link
   644      *          #encode(CharBuffer,ByteBuffer,boolean) encode} method
   645      *          with a value of <tt>true</tt> for the <tt>endOfInput</tt>
   646      *          parameter
   647      */
   648     public final CoderResult flush(ByteBuffer out) {
   649         if (state == ST_END) {
   650             CoderResult cr = implFlush(out);
   651             if (cr.isUnderflow())
   652                 state = ST_FLUSHED;
   653             return cr;
   654         }
   655 
   656         if (state != ST_FLUSHED)
   657             throwIllegalStateException(state, ST_FLUSHED);
   658 
   659         return CoderResult.UNDERFLOW; // Already flushed
   660     }
   661 
   662     /**
   663      * Flushes this encoder.
   664      *
   665      * <p> The default implementation of this method does nothing, and always
   666      * returns {@link CoderResult#UNDERFLOW}.  This method should be overridden
   667      * by encoders that may need to write final bytes to the output buffer
   668      * once the entire input sequence has been read. </p>
   669      *
   670      * @param  out
   671      *         The output byte buffer
   672      *
   673      * @return  A coder-result object, either {@link CoderResult#UNDERFLOW} or
   674      *          {@link CoderResult#OVERFLOW}
   675      */
   676     protected CoderResult implFlush(ByteBuffer out) {
   677         return CoderResult.UNDERFLOW;
   678     }
   679 
   680     /**
   681      * Resets this encoder, clearing any internal state.
   682      *
   683      * <p> This method resets charset-independent state and also invokes the
   684      * {@link #implReset() implReset} method in order to perform any
   685      * charset-specific reset actions.  </p>
   686      *
   687      * @return  This encoder
   688      *
   689      */
   690     public final CharsetEncoder reset() {
   691         implReset();
   692         state = ST_RESET;
   693         return this;
   694     }
   695 
   696     /**
   697      * Resets this encoder, clearing any charset-specific internal state.
   698      *
   699      * <p> The default implementation of this method does nothing.  This method
   700      * should be overridden by encoders that maintain internal state.  </p>
   701      */
   702     protected void implReset() { }
   703 
   704     /**
   705      * Encodes one or more characters into one or more bytes.
   706      *
   707      * <p> This method encapsulates the basic encoding loop, encoding as many
   708      * characters as possible until it either runs out of input, runs out of room
   709      * in the output buffer, or encounters an encoding error.  This method is
   710      * invoked by the {@link #encode encode} method, which handles result
   711      * interpretation and error recovery.
   712      *
   713      * <p> The buffers are read from, and written to, starting at their current
   714      * positions.  At most {@link Buffer#remaining in.remaining()} characters
   715      * will be read, and at most {@link Buffer#remaining out.remaining()}
   716      * bytes will be written.  The buffers' positions will be advanced to
   717      * reflect the characters read and the bytes written, but their marks and
   718      * limits will not be modified.
   719      *
   720      * <p> This method returns a {@link CoderResult} object to describe its
   721      * reason for termination, in the same manner as the {@link #encode encode}
   722      * method.  Most implementations of this method will handle encoding errors
   723      * by returning an appropriate result object for interpretation by the
   724      * {@link #encode encode} method.  An optimized implementation may instead
   725      * examine the relevant error action and implement that action itself.
   726      *
   727      * <p> An implementation of this method may perform arbitrary lookahead by
   728      * returning {@link CoderResult#UNDERFLOW} until it receives sufficient
   729      * input.  </p>
   730      *
   731      * @param  in
   732      *         The input character buffer
   733      *
   734      * @param  out
   735      *         The output byte buffer
   736      *
   737      * @return  A coder-result object describing the reason for termination
   738      */
   739     protected abstract CoderResult encodeLoop(CharBuffer in,
   740                                               ByteBuffer out);
   741 
   742     /**
   743      * Convenience method that encodes the remaining content of a single input
   744      * character buffer into a newly-allocated byte buffer.
   745      *
   746      * <p> This method implements an entire <a href="#steps">encoding
   747      * operation</a>; that is, it resets this encoder, then it encodes the
   748      * characters in the given character buffer, and finally it flushes this
   749      * encoder.  This method should therefore not be invoked if an encoding
   750      * operation is already in progress.  </p>
   751      *
   752      * @param  in
   753      *         The input character buffer
   754      *
   755      * @return A newly-allocated byte buffer containing the result of the
   756      *         encoding operation.  The buffer's position will be zero and its
   757      *         limit will follow the last byte written.
   758      *
   759      * @throws  IllegalStateException
   760      *          If an encoding operation is already in progress
   761      *
   762      * @throws  MalformedInputException
   763      *          If the character sequence starting at the input buffer's current
   764      *          position is not a legal sixteen-bit Unicode sequence and the current malformed-input action
   765      *          is {@link CodingErrorAction#REPORT}
   766      *
   767      * @throws  UnmappableCharacterException
   768      *          If the character sequence starting at the input buffer's current
   769      *          position cannot be mapped to an equivalent byte sequence and
   770      *          the current unmappable-character action is {@link
   771      *          CodingErrorAction#REPORT}
   772      */
   773     public final ByteBuffer encode(CharBuffer in)
   774         throws CharacterCodingException
   775     {
   776         int n = (int)(in.remaining() * averageBytesPerChar());
   777         ByteBuffer out = ByteBuffer.allocate(n);
   778 
   779         if ((n == 0) && (in.remaining() == 0))
   780             return out;
   781         reset();
   782         for (;;) {
   783             CoderResult cr = in.hasRemaining() ?
   784                 encode(in, out, true) : CoderResult.UNDERFLOW;
   785             if (cr.isUnderflow())
   786                 cr = flush(out);
   787 
   788             if (cr.isUnderflow())
   789                 break;
   790             if (cr.isOverflow()) {
   791                 n = 2*n + 1;    // Ensure progress; n might be 0!
   792                 ByteBuffer o = ByteBuffer.allocate(n);
   793                 out.flip();
   794                 o.put(out);
   795                 out = o;
   796                 continue;
   797             }
   798             cr.throwException();
   799         }
   800         out.flip();
   801         return out;
   802     }
   803 
   804 
   805 
   806 
   807 
   808 
   809 
   810 
   811 
   812 
   813 
   814 
   815 
   816 
   817 
   818 
   819 
   820 
   821 
   822 
   823 
   824 
   825 
   826 
   827 
   828 
   829 
   830 
   831 
   832 
   833 
   834 
   835 
   836 
   837 
   838 
   839 
   840 
   841 
   842 
   843 
   844 
   845 
   846 
   847 
   848 
   849 
   850 
   851 
   852 
   853 
   854 
   855 
   856 
   857 
   858 
   859 
   860 
   861 
   862 
   863 
   864 
   865 
   866 
   867 
   868 
   869 
   870 
   871 
   872 
   873 
   874 
   875 
   876 
   877 
   878 
   879 
   880 
   881 
   882     private boolean canEncode(CharBuffer cb) {
   883         if (state == ST_FLUSHED)
   884             reset();
   885         else if (state != ST_RESET)
   886             throwIllegalStateException(state, ST_CODING);
   887         CodingErrorAction ma = malformedInputAction();
   888         CodingErrorAction ua = unmappableCharacterAction();
   889         try {
   890             onMalformedInput(CodingErrorAction.REPORT);
   891             onUnmappableCharacter(CodingErrorAction.REPORT);
   892             encode(cb);
   893         } catch (CharacterCodingException x) {
   894             return false;
   895         } finally {
   896             onMalformedInput(ma);
   897             onUnmappableCharacter(ua);
   898             reset();
   899         }
   900         return true;
   901     }
   902 
   903     /**
   904      * Tells whether or not this encoder can encode the given character.
   905      *
   906      * <p> This method returns <tt>false</tt> if the given character is a
   907      * surrogate character; such characters can be interpreted only when they
   908      * are members of a pair consisting of a high surrogate followed by a low
   909      * surrogate.  The {@link #canEncode(java.lang.CharSequence)
   910      * canEncode(CharSequence)} method may be used to test whether or not a
   911      * character sequence can be encoded.
   912      *
   913      * <p> This method may modify this encoder's state; it should therefore not
   914      * be invoked if an <a href="#steps">encoding operation</a> is already in
   915      * progress.
   916      *
   917      * <p> The default implementation of this method is not very efficient; it
   918      * should generally be overridden to improve performance.  </p>
   919      *
   920      * @return  <tt>true</tt> if, and only if, this encoder can encode
   921      *          the given character
   922      *
   923      * @throws  IllegalStateException
   924      *          If an encoding operation is already in progress
   925      */
   926     public boolean canEncode(char c) {
   927         CharBuffer cb = CharBuffer.allocate(1);
   928         cb.put(c);
   929         cb.flip();
   930         return canEncode(cb);
   931     }
   932 
   933     /**
   934      * Tells whether or not this encoder can encode the given character
   935      * sequence.
   936      *
   937      * <p> If this method returns <tt>false</tt> for a particular character
   938      * sequence then more information about why the sequence cannot be encoded
   939      * may be obtained by performing a full <a href="#steps">encoding
   940      * operation</a>.
   941      *
   942      * <p> This method may modify this encoder's state; it should therefore not
   943      * be invoked if an encoding operation is already in progress.
   944      *
   945      * <p> The default implementation of this method is not very efficient; it
   946      * should generally be overridden to improve performance.  </p>
   947      *
   948      * @return  <tt>true</tt> if, and only if, this encoder can encode
   949      *          the given character without throwing any exceptions and without
   950      *          performing any replacements
   951      *
   952      * @throws  IllegalStateException
   953      *          If an encoding operation is already in progress
   954      */
   955     public boolean canEncode(CharSequence cs) {
   956         CharBuffer cb;
   957         if (cs instanceof CharBuffer)
   958             cb = ((CharBuffer)cs).duplicate();
   959         else
   960             cb = CharBuffer.wrap(cs.toString());
   961         return canEncode(cb);
   962     }
   963 
   964 
   965 
   966 
   967     private void throwIllegalStateException(int from, int to) {
   968         throw new IllegalStateException("Current state = " + stateNames[from]
   969                                         + ", new state = " + stateNames[to]);
   970     }
   971 
   972 }