1 /*
2  * Copyright (C) 2014 The Android Open Source Project
3  * Copyright (c) 2000, 2013, Oracle and/or its affiliates. All rights reserved.
4  * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
5  *
6  * This code is free software; you can redistribute it and/or modify it
7  * under the terms of the GNU General Public License version 2 only, as
8  * published by the Free Software Foundation.  Oracle designates this
9  * particular file as subject to the "Classpath" exception as provided
10  * by Oracle in the LICENSE file that accompanied this code.
11  *
12  * This code is distributed in the hope that it will be useful, but WITHOUT
13  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
14  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
15  * version 2 for more details (a copy is included in the LICENSE file that
16  * accompanied this code).
17  *
18  * You should have received a copy of the GNU General Public License version
19  * 2 along with this work; if not, write to the Free Software Foundation,
20  * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
21  *
22  * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
23  * or visit www.oracle.com if you need additional information or have any
24  * questions.
25  */
26 
27 // -- This file was mechanically generated: Do not edit! -- //
28 
29 package java.nio.charset;
30 
31 import java.nio.Buffer;
32 import java.nio.ByteBuffer;
33 import java.nio.CharBuffer;
34 import java.nio.BufferOverflowException;
35 import java.nio.BufferUnderflowException;
36 import java.lang.ref.WeakReference;
37 import java.nio.charset.CoderMalfunctionError;                  // javadoc
38 import java.util.Arrays;
39 
40 
41 /**
42  * An engine that can transform a sequence of sixteen-bit Unicode characters into a sequence of
43  * bytes in a specific charset.
44  *
45  * <a name="steps"></a>
46  *
47  * <p> The input character sequence is provided in a character buffer or a series
48  * of such buffers.  The output byte sequence is written to a byte buffer
49  * or a series of such buffers.  An encoder should always be used by making
50  * the following sequence of method invocations, hereinafter referred to as an
51  * <i>encoding operation</i>:
52  *
53  * <ol>
54  *
55  *   <li><p> Reset the encoder via the {@link #reset reset} method, unless it
56  *   has not been used before; </p></li>
57  *
58  *   <li><p> Invoke the {@link #encode encode} method zero or more times, as
59  *   long as additional input may be available, passing <tt>false</tt> for the
60  *   <tt>endOfInput</tt> argument and filling the input buffer and flushing the
61  *   output buffer between invocations; </p></li>
62  *
63  *   <li><p> Invoke the {@link #encode encode} method one final time, passing
64  *   <tt>true</tt> for the <tt>endOfInput</tt> argument; and then </p></li>
65  *
66  *   <li><p> Invoke the {@link #flush flush} method so that the encoder can
67  *   flush any internal state to the output buffer. </p></li>
68  *
69  * </ol>
70  *
71  * Each invocation of the {@link #encode encode} method will encode as many
72  * characters as possible from the input buffer, writing the resulting bytes
73  * to the output buffer.  The {@link #encode encode} method returns when more
74  * input is required, when there is not enough room in the output buffer, or
75  * when an encoding error has occurred.  In each case a {@link CoderResult}
76  * object is returned to describe the reason for termination.  An invoker can
77  * examine this object and fill the input buffer, flush the output buffer, or
78  * attempt to recover from an encoding error, as appropriate, and try again.
79  *
80  * <a name="ce"></a>
81  *
82  * <p> There are two general types of encoding errors.  If the input character
83  * sequence is not a legal sixteen-bit Unicode sequence then the input is considered <i>malformed</i>.  If
84  * the input character sequence is legal but cannot be mapped to a valid
85  * byte sequence in the given charset then an <i>unmappable character</i> has been encountered.
86  *
87  * <a name="cae"></a>
88  *
89  * <p> How an encoding error is handled depends upon the action requested for
90  * that type of error, which is described by an instance of the {@link
91  * CodingErrorAction} class.  The possible error actions are to {@linkplain
92  * CodingErrorAction#IGNORE ignore} the erroneous input, {@linkplain
93  * CodingErrorAction#REPORT report} the error to the invoker via
94  * the returned {@link CoderResult} object, or {@linkplain CodingErrorAction#REPLACE
95  * replace} the erroneous input with the current value of the
96  * replacement byte array.  The replacement
97  *
98 
99  * is initially set to the encoder's default replacement, which often
100  * (but not always) has the initial value&nbsp;<tt>{</tt>&nbsp;<tt>(byte)'?'</tt>&nbsp;<tt>}</tt>;
101 
102 
103 
104 
105  *
106  * its value may be changed via the {@link #replaceWith(byte[])
107  * replaceWith} method.
108  *
109  * <p> The default action for malformed-input and unmappable-character errors
110  * is to {@linkplain CodingErrorAction#REPORT report} them.  The
111  * malformed-input error action may be changed via the {@link
112  * #onMalformedInput(CodingErrorAction) onMalformedInput} method; the
113  * unmappable-character action may be changed via the {@link
114  * #onUnmappableCharacter(CodingErrorAction) onUnmappableCharacter} method.
115  *
116  * <p> This class is designed to handle many of the details of the encoding
117  * process, including the implementation of error actions.  An encoder for a
118  * specific charset, which is a concrete subclass of this class, need only
119  * implement the abstract {@link #encodeLoop encodeLoop} method, which
120  * encapsulates the basic encoding loop.  A subclass that maintains internal
121  * state should, additionally, override the {@link #implFlush implFlush} and
122  * {@link #implReset implReset} methods.
123  *
124  * <p> Instances of this class are not safe for use by multiple concurrent
125  * threads.  </p>
126  *
127  *
128  * @author Mark Reinhold
129  * @author JSR-51 Expert Group
130  * @since 1.4
131  *
132  * @see ByteBuffer
133  * @see CharBuffer
134  * @see Charset
135  * @see CharsetDecoder
136  */
137 
138 public abstract class CharsetEncoder {
139 
140     private final Charset charset;
141     private final float averageBytesPerChar;
142     private final float maxBytesPerChar;
143 
144     private byte[] replacement;
145     private CodingErrorAction malformedInputAction
146         = CodingErrorAction.REPORT;
147     private CodingErrorAction unmappableCharacterAction
148         = CodingErrorAction.REPORT;
149 
150     // Internal states
151     //
152     private static final int ST_RESET   = 0;
153     private static final int ST_CODING  = 1;
154     private static final int ST_END     = 2;
155     private static final int ST_FLUSHED = 3;
156 
157     private int state = ST_RESET;
158 
159     private static String stateNames[]
160         = { "RESET", "CODING", "CODING_END", "FLUSHED" };
161 
162 
163     /**
164      * Initializes a new encoder.  The new encoder will have the given
165      * bytes-per-char and replacement values.
166      *
167      * @param  cs
168      *         The charset that created this encoder
169      *
170      * @param  averageBytesPerChar
171      *         A positive float value indicating the expected number of
172      *         bytes that will be produced for each input character
173      *
174      * @param  maxBytesPerChar
175      *         A positive float value indicating the maximum number of
176      *         bytes that will be produced for each input character
177      *
178      * @param  replacement
179      *         The initial replacement; must not be <tt>null</tt>, must have
180      *         non-zero length, must not be longer than maxBytesPerChar,
181      *         and must be {@linkplain #isLegalReplacement legal}
182      *
183      * @throws  IllegalArgumentException
184      *          If the preconditions on the parameters do not hold
185      */
186     protected
CharsetEncoder(Charset cs, float averageBytesPerChar, float maxBytesPerChar, byte[] replacement)187     CharsetEncoder(Charset cs,
188                    float averageBytesPerChar,
189                    float maxBytesPerChar,
190                    byte[] replacement)
191     {
192         // BEGIN Android-added: A hidden constructor for the CharsetEncoderICU subclass.
193         this(cs, averageBytesPerChar, maxBytesPerChar, replacement, false);
194     }
195 
196     /**
197      * This constructor is for subclasses to specify whether {@code replacement} can be used as it
198      * is ("trusted"). If it is trusted, {@link #replaceWith(byte[])} and
199      * {@link #implReplaceWith(byte[])} will not be called.
200      * @hide
201      */
CharsetEncoder(Charset cs, float averageBytesPerChar, float maxBytesPerChar, byte[] replacement, boolean trusted)202     protected CharsetEncoder(Charset cs, float averageBytesPerChar, float maxBytesPerChar, byte[] replacement,
203             boolean trusted)
204     {
205         // END Android-added: A hidden constructor for the CharsetEncoderICU subclass.
206         this.charset = cs;
207         if (averageBytesPerChar <= 0.0f)
208             throw new IllegalArgumentException("Non-positive "
209                                                + "averageBytesPerChar");
210         if (maxBytesPerChar <= 0.0f)
211             throw new IllegalArgumentException("Non-positive "
212                                                + "maxBytesPerChar");
213         if (!Charset.atBugLevel("1.4")) {
214             if (averageBytesPerChar > maxBytesPerChar)
215                 throw new IllegalArgumentException("averageBytesPerChar"
216                                                    + " exceeds "
217                                                    + "maxBytesPerChar");
218         }
219         this.replacement = replacement;
220         this.averageBytesPerChar = averageBytesPerChar;
221         this.maxBytesPerChar = maxBytesPerChar;
222         // BEGIN Android-changed: Avoid calling replaceWith() for trusted subclasses.
223         // replaceWith(replacement);
224         if (!trusted) {
225             replaceWith(replacement);
226         }
227         // END Android-changed: Avoid calling replaceWith() for trusted subclasses.
228     }
229 
230     /**
231      * Initializes a new encoder.  The new encoder will have the given
232      * bytes-per-char values and its replacement will be the
233      * byte array <tt>{</tt>&nbsp;<tt>(byte)'?'</tt>&nbsp;<tt>}</tt>.
234      *
235      * @param  cs
236      *         The charset that created this encoder
237      *
238      * @param  averageBytesPerChar
239      *         A positive float value indicating the expected number of
240      *         bytes that will be produced for each input character
241      *
242      * @param  maxBytesPerChar
243      *         A positive float value indicating the maximum number of
244      *         bytes that will be produced for each input character
245      *
246      * @throws  IllegalArgumentException
247      *          If the preconditions on the parameters do not hold
248      */
CharsetEncoder(Charset cs, float averageBytesPerChar, float maxBytesPerChar)249     protected CharsetEncoder(Charset cs,
250                              float averageBytesPerChar,
251                              float maxBytesPerChar)
252     {
253         this(cs,
254              averageBytesPerChar, maxBytesPerChar,
255              new byte[] { (byte)'?' });
256     }
257 
258     /**
259      * Returns the charset that created this encoder.
260      *
261      * @return  This encoder's charset
262      */
charset()263     public final Charset charset() {
264         return charset;
265     }
266 
267     /**
268      * Returns this encoder's replacement value.
269      *
270      * @return  This encoder's current replacement,
271      *          which is never <tt>null</tt> and is never empty
272      */
replacement()273     public final byte[] replacement() {
274 
275 
276 
277 
278         return Arrays.copyOf(replacement, replacement.length);
279 
280     }
281 
282     /**
283      * Changes this encoder's replacement value.
284      *
285      * <p> This method invokes the {@link #implReplaceWith implReplaceWith}
286      * method, passing the new replacement, after checking that the new
287      * replacement is acceptable.  </p>
288      *
289      * @param  newReplacement  The replacement value
290      *
291 
292 
293 
294 
295 
296      *         The new replacement; must not be <tt>null</tt>, must have
297      *         non-zero length, must not be longer than the value returned by
298      *         the {@link #maxBytesPerChar() maxBytesPerChar} method, and
299      *         must be {@link #isLegalReplacement legal}
300 
301      *
302      * @return  This encoder
303      *
304      * @throws  IllegalArgumentException
305      *          If the preconditions on the parameter do not hold
306      */
replaceWith(byte[] newReplacement)307     public final CharsetEncoder replaceWith(byte[] newReplacement) {
308         if (newReplacement == null)
309             throw new IllegalArgumentException("Null replacement");
310         int len = newReplacement.length;
311         if (len == 0)
312             throw new IllegalArgumentException("Empty replacement");
313         if (len > maxBytesPerChar)
314             throw new IllegalArgumentException("Replacement too long");
315 
316 
317 
318 
319         if (!isLegalReplacement(newReplacement))
320             throw new IllegalArgumentException("Illegal replacement");
321         this.replacement = Arrays.copyOf(newReplacement, newReplacement.length);
322 
323         implReplaceWith(this.replacement);
324         return this;
325     }
326 
327     /**
328      * Reports a change to this encoder's replacement value.
329      *
330      * <p> The default implementation of this method does nothing.  This method
331      * should be overridden by encoders that require notification of changes to
332      * the replacement.  </p>
333      *
334      * @param  newReplacement    The replacement value
335      */
implReplaceWith(byte[] newReplacement)336     protected void implReplaceWith(byte[] newReplacement) {
337     }
338 
339 
340 
341     private WeakReference<CharsetDecoder> cachedDecoder = null;
342 
343     /**
344      * Tells whether or not the given byte array is a legal replacement value
345      * for this encoder.
346      *
347      * <p> A replacement is legal if, and only if, it is a legal sequence of
348      * bytes in this encoder's charset; that is, it must be possible to decode
349      * the replacement into one or more sixteen-bit Unicode characters.
350      *
351      * <p> The default implementation of this method is not very efficient; it
352      * should generally be overridden to improve performance.  </p>
353      *
354      * @param  repl  The byte array to be tested
355      *
356      * @return  <tt>true</tt> if, and only if, the given byte array
357      *          is a legal replacement value for this encoder
358      */
isLegalReplacement(byte[] repl)359     public boolean isLegalReplacement(byte[] repl) {
360         WeakReference<CharsetDecoder> wr = cachedDecoder;
361         CharsetDecoder dec = null;
362         if ((wr == null) || ((dec = wr.get()) == null)) {
363             dec = charset().newDecoder();
364             dec.onMalformedInput(CodingErrorAction.REPORT);
365             dec.onUnmappableCharacter(CodingErrorAction.REPORT);
366             cachedDecoder = new WeakReference<CharsetDecoder>(dec);
367         } else {
368             dec.reset();
369         }
370         ByteBuffer bb = ByteBuffer.wrap(repl);
371         CharBuffer cb = CharBuffer.allocate((int)(bb.remaining()
372                                                   * dec.maxCharsPerByte()));
373         CoderResult cr = dec.decode(bb, cb, true);
374         return !cr.isError();
375     }
376 
377 
378 
379     /**
380      * Returns this encoder's current action for malformed-input errors.
381      *
382      * @return The current malformed-input action, which is never <tt>null</tt>
383      */
malformedInputAction()384     public CodingErrorAction malformedInputAction() {
385         return malformedInputAction;
386     }
387 
388     /**
389      * Changes this encoder's action for malformed-input errors.
390      *
391      * <p> This method invokes the {@link #implOnMalformedInput
392      * implOnMalformedInput} method, passing the new action.  </p>
393      *
394      * @param  newAction  The new action; must not be <tt>null</tt>
395      *
396      * @return  This encoder
397      *
398      * @throws IllegalArgumentException
399      *         If the precondition on the parameter does not hold
400      */
onMalformedInput(CodingErrorAction newAction)401     public final CharsetEncoder onMalformedInput(CodingErrorAction newAction) {
402         if (newAction == null)
403             throw new IllegalArgumentException("Null action");
404         malformedInputAction = newAction;
405         implOnMalformedInput(newAction);
406         return this;
407     }
408 
409     /**
410      * Reports a change to this encoder's malformed-input action.
411      *
412      * <p> The default implementation of this method does nothing.  This method
413      * should be overridden by encoders that require notification of changes to
414      * the malformed-input action.  </p>
415      *
416      * @param  newAction  The new action
417      */
implOnMalformedInput(CodingErrorAction newAction)418     protected void implOnMalformedInput(CodingErrorAction newAction) { }
419 
420     /**
421      * Returns this encoder's current action for unmappable-character errors.
422      *
423      * @return The current unmappable-character action, which is never
424      *         <tt>null</tt>
425      */
unmappableCharacterAction()426     public CodingErrorAction unmappableCharacterAction() {
427         return unmappableCharacterAction;
428     }
429 
430     /**
431      * Changes this encoder's action for unmappable-character errors.
432      *
433      * <p> This method invokes the {@link #implOnUnmappableCharacter
434      * implOnUnmappableCharacter} method, passing the new action.  </p>
435      *
436      * @param  newAction  The new action; must not be <tt>null</tt>
437      *
438      * @return  This encoder
439      *
440      * @throws IllegalArgumentException
441      *         If the precondition on the parameter does not hold
442      */
onUnmappableCharacter(CodingErrorAction newAction)443     public final CharsetEncoder onUnmappableCharacter(CodingErrorAction
444                                                       newAction)
445     {
446         if (newAction == null)
447             throw new IllegalArgumentException("Null action");
448         unmappableCharacterAction = newAction;
449         implOnUnmappableCharacter(newAction);
450         return this;
451     }
452 
453     /**
454      * Reports a change to this encoder's unmappable-character action.
455      *
456      * <p> The default implementation of this method does nothing.  This method
457      * should be overridden by encoders that require notification of changes to
458      * the unmappable-character action.  </p>
459      *
460      * @param  newAction  The new action
461      */
implOnUnmappableCharacter(CodingErrorAction newAction)462     protected void implOnUnmappableCharacter(CodingErrorAction newAction) { }
463 
464     /**
465      * Returns the average number of bytes that will be produced for each
466      * character of input.  This heuristic value may be used to estimate the size
467      * of the output buffer required for a given input sequence.
468      *
469      * @return  The average number of bytes produced
470      *          per character of input
471      */
averageBytesPerChar()472     public final float averageBytesPerChar() {
473         return averageBytesPerChar;
474     }
475 
476     /**
477      * Returns the maximum number of bytes that will be produced for each
478      * character of input.  This value may be used to compute the worst-case size
479      * of the output buffer required for a given input sequence.
480      *
481      * @return  The maximum number of bytes that will be produced per
482      *          character of input
483      */
maxBytesPerChar()484     public final float maxBytesPerChar() {
485         return maxBytesPerChar;
486     }
487 
488     /**
489      * Encodes as many characters as possible from the given input buffer,
490      * writing the results to the given output buffer.
491      *
492      * <p> The buffers are read from, and written to, starting at their current
493      * positions.  At most {@link Buffer#remaining in.remaining()} characters
494      * will be read and at most {@link Buffer#remaining out.remaining()}
495      * bytes will be written.  The buffers' positions will be advanced to
496      * reflect the characters read and the bytes written, but their marks and
497      * limits will not be modified.
498      *
499      * <p> In addition to reading characters from the input buffer and writing
500      * bytes to the output buffer, this method returns a {@link CoderResult}
501      * object to describe its reason for termination:
502      *
503      * <ul>
504      *
505      *   <li><p> {@link CoderResult#UNDERFLOW} indicates that as much of the
506      *   input buffer as possible has been encoded.  If there is no further
507      *   input then the invoker can proceed to the next step of the
508      *   <a href="#steps">encoding operation</a>.  Otherwise this method
509      *   should be invoked again with further input.  </p></li>
510      *
511      *   <li><p> {@link CoderResult#OVERFLOW} indicates that there is
512      *   insufficient space in the output buffer to encode any more characters.
513      *   This method should be invoked again with an output buffer that has
514      *   more {@linkplain Buffer#remaining remaining} bytes. This is
515      *   typically done by draining any encoded bytes from the output
516      *   buffer.  </p></li>
517      *
518      *   <li><p> A {@linkplain CoderResult#malformedForLength
519      *   malformed-input} result indicates that a malformed-input
520      *   error has been detected.  The malformed characters begin at the input
521      *   buffer's (possibly incremented) position; the number of malformed
522      *   characters may be determined by invoking the result object's {@link
523      *   CoderResult#length() length} method.  This case applies only if the
524      *   {@linkplain #onMalformedInput malformed action} of this encoder
525      *   is {@link CodingErrorAction#REPORT}; otherwise the malformed input
526      *   will be ignored or replaced, as requested.  </p></li>
527      *
528      *   <li><p> An {@linkplain CoderResult#unmappableForLength
529      *   unmappable-character} result indicates that an
530      *   unmappable-character error has been detected.  The characters that
531      *   encode the unmappable character begin at the input buffer's (possibly
532      *   incremented) position; the number of such characters may be determined
533      *   by invoking the result object's {@link CoderResult#length() length}
534      *   method.  This case applies only if the {@linkplain #onUnmappableCharacter
535      *   unmappable action} of this encoder is {@link
536      *   CodingErrorAction#REPORT}; otherwise the unmappable character will be
537      *   ignored or replaced, as requested.  </p></li>
538      *
539      * </ul>
540      *
541      * In any case, if this method is to be reinvoked in the same encoding
542      * operation then care should be taken to preserve any characters remaining
543      * in the input buffer so that they are available to the next invocation.
544      *
545      * <p> The <tt>endOfInput</tt> parameter advises this method as to whether
546      * the invoker can provide further input beyond that contained in the given
547      * input buffer.  If there is a possibility of providing additional input
548      * then the invoker should pass <tt>false</tt> for this parameter; if there
549      * is no possibility of providing further input then the invoker should
550      * pass <tt>true</tt>.  It is not erroneous, and in fact it is quite
551      * common, to pass <tt>false</tt> in one invocation and later discover that
552      * no further input was actually available.  It is critical, however, that
553      * the final invocation of this method in a sequence of invocations always
554      * pass <tt>true</tt> so that any remaining unencoded input will be treated
555      * as being malformed.
556      *
557      * <p> This method works by invoking the {@link #encodeLoop encodeLoop}
558      * method, interpreting its results, handling error conditions, and
559      * reinvoking it as necessary.  </p>
560      *
561      *
562      * @param  in
563      *         The input character buffer
564      *
565      * @param  out
566      *         The output byte buffer
567      *
568      * @param  endOfInput
569      *         <tt>true</tt> if, and only if, the invoker can provide no
570      *         additional input characters beyond those in the given buffer
571      *
572      * @return  A coder-result object describing the reason for termination
573      *
574      * @throws  IllegalStateException
575      *          If an encoding operation is already in progress and the previous
576      *          step was an invocation neither of the {@link #reset reset}
577      *          method, nor of this method with a value of <tt>false</tt> for
578      *          the <tt>endOfInput</tt> parameter, nor of this method with a
579      *          value of <tt>true</tt> for the <tt>endOfInput</tt> parameter
580      *          but a return value indicating an incomplete encoding operation
581      *
582      * @throws  CoderMalfunctionError
583      *          If an invocation of the encodeLoop method threw
584      *          an unexpected exception
585      */
encode(CharBuffer in, ByteBuffer out, boolean endOfInput)586     public final CoderResult encode(CharBuffer in, ByteBuffer out,
587                                     boolean endOfInput)
588     {
589         int newState = endOfInput ? ST_END : ST_CODING;
590         if ((state != ST_RESET) && (state != ST_CODING)
591             && !(endOfInput && (state == ST_END)))
592             throwIllegalStateException(state, newState);
593         state = newState;
594 
595         for (;;) {
596 
597             CoderResult cr;
598             try {
599                 cr = encodeLoop(in, out);
600             } catch (BufferUnderflowException x) {
601                 throw new CoderMalfunctionError(x);
602             } catch (BufferOverflowException x) {
603                 throw new CoderMalfunctionError(x);
604             }
605 
606             if (cr.isOverflow())
607                 return cr;
608 
609             if (cr.isUnderflow()) {
610                 if (endOfInput && in.hasRemaining()) {
611                     cr = CoderResult.malformedForLength(in.remaining());
612                     // Fall through to malformed-input case
613                 } else {
614                     return cr;
615                 }
616             }
617 
618             CodingErrorAction action = null;
619             if (cr.isMalformed())
620                 action = malformedInputAction;
621             else if (cr.isUnmappable())
622                 action = unmappableCharacterAction;
623             else
624                 assert false : cr.toString();
625 
626             if (action == CodingErrorAction.REPORT)
627                 return cr;
628 
629             if (action == CodingErrorAction.REPLACE) {
630                 if (out.remaining() < replacement.length)
631                     return CoderResult.OVERFLOW;
632                 out.put(replacement);
633             }
634 
635             if ((action == CodingErrorAction.IGNORE)
636                 || (action == CodingErrorAction.REPLACE)) {
637                 // Skip erroneous input either way
638                 in.position(in.position() + cr.length());
639                 continue;
640             }
641 
642             assert false;
643         }
644 
645     }
646 
647     /**
648      * Flushes this encoder.
649      *
650      * <p> Some encoders maintain internal state and may need to write some
651      * final bytes to the output buffer once the overall input sequence has
652      * been read.
653      *
654      * <p> Any additional output is written to the output buffer beginning at
655      * its current position.  At most {@link Buffer#remaining out.remaining()}
656      * bytes will be written.  The buffer's position will be advanced
657      * appropriately, but its mark and limit will not be modified.
658      *
659      * <p> If this method completes successfully then it returns {@link
660      * CoderResult#UNDERFLOW}.  If there is insufficient room in the output
661      * buffer then it returns {@link CoderResult#OVERFLOW}.  If this happens
662      * then this method must be invoked again, with an output buffer that has
663      * more room, in order to complete the current <a href="#steps">encoding
664      * operation</a>.
665      *
666      * <p> If this encoder has already been flushed then invoking this method
667      * has no effect.
668      *
669      * <p> This method invokes the {@link #implFlush implFlush} method to
670      * perform the actual flushing operation.  </p>
671      *
672      * @param  out
673      *         The output byte buffer
674      *
675      * @return  A coder-result object, either {@link CoderResult#UNDERFLOW} or
676      *          {@link CoderResult#OVERFLOW}
677      *
678      * @throws  IllegalStateException
679      *          If the previous step of the current encoding operation was an
680      *          invocation neither of the {@link #flush flush} method nor of
681      *          the three-argument {@link
682      *          #encode(CharBuffer,ByteBuffer,boolean) encode} method
683      *          with a value of <tt>true</tt> for the <tt>endOfInput</tt>
684      *          parameter
685      */
flush(ByteBuffer out)686     public final CoderResult flush(ByteBuffer out) {
687         if (state == ST_END) {
688             CoderResult cr = implFlush(out);
689             if (cr.isUnderflow())
690                 state = ST_FLUSHED;
691             return cr;
692         }
693 
694         if (state != ST_FLUSHED)
695             throwIllegalStateException(state, ST_FLUSHED);
696 
697         return CoderResult.UNDERFLOW; // Already flushed
698     }
699 
700     /**
701      * Flushes this encoder.
702      *
703      * <p> The default implementation of this method does nothing, and always
704      * returns {@link CoderResult#UNDERFLOW}.  This method should be overridden
705      * by encoders that may need to write final bytes to the output buffer
706      * once the entire input sequence has been read. </p>
707      *
708      * @param  out
709      *         The output byte buffer
710      *
711      * @return  A coder-result object, either {@link CoderResult#UNDERFLOW} or
712      *          {@link CoderResult#OVERFLOW}
713      */
implFlush(ByteBuffer out)714     protected CoderResult implFlush(ByteBuffer out) {
715         return CoderResult.UNDERFLOW;
716     }
717 
718     /**
719      * Resets this encoder, clearing any internal state.
720      *
721      * <p> This method resets charset-independent state and also invokes the
722      * {@link #implReset() implReset} method in order to perform any
723      * charset-specific reset actions.  </p>
724      *
725      * @return  This encoder
726      *
727      */
reset()728     public final CharsetEncoder reset() {
729         implReset();
730         state = ST_RESET;
731         return this;
732     }
733 
734     /**
735      * Resets this encoder, clearing any charset-specific internal state.
736      *
737      * <p> The default implementation of this method does nothing.  This method
738      * should be overridden by encoders that maintain internal state.  </p>
739      */
implReset()740     protected void implReset() { }
741 
742     /**
743      * Encodes one or more characters into one or more bytes.
744      *
745      * <p> This method encapsulates the basic encoding loop, encoding as many
746      * characters as possible until it either runs out of input, runs out of room
747      * in the output buffer, or encounters an encoding error.  This method is
748      * invoked by the {@link #encode encode} method, which handles result
749      * interpretation and error recovery.
750      *
751      * <p> The buffers are read from, and written to, starting at their current
752      * positions.  At most {@link Buffer#remaining in.remaining()} characters
753      * will be read, and at most {@link Buffer#remaining out.remaining()}
754      * bytes will be written.  The buffers' positions will be advanced to
755      * reflect the characters read and the bytes written, but their marks and
756      * limits will not be modified.
757      *
758      * <p> This method returns a {@link CoderResult} object to describe its
759      * reason for termination, in the same manner as the {@link #encode encode}
760      * method.  Most implementations of this method will handle encoding errors
761      * by returning an appropriate result object for interpretation by the
762      * {@link #encode encode} method.  An optimized implementation may instead
763      * examine the relevant error action and implement that action itself.
764      *
765      * <p> An implementation of this method may perform arbitrary lookahead by
766      * returning {@link CoderResult#UNDERFLOW} until it receives sufficient
767      * input.  </p>
768      *
769      * @param  in
770      *         The input character buffer
771      *
772      * @param  out
773      *         The output byte buffer
774      *
775      * @return  A coder-result object describing the reason for termination
776      */
encodeLoop(CharBuffer in, ByteBuffer out)777     protected abstract CoderResult encodeLoop(CharBuffer in,
778                                               ByteBuffer out);
779 
780     /**
781      * Convenience method that encodes the remaining content of a single input
782      * character buffer into a newly-allocated byte buffer.
783      *
784      * <p> This method implements an entire <a href="#steps">encoding
785      * operation</a>; that is, it resets this encoder, then it encodes the
786      * characters in the given character buffer, and finally it flushes this
787      * encoder.  This method should therefore not be invoked if an encoding
788      * operation is already in progress.  </p>
789      *
790      * @param  in
791      *         The input character buffer
792      *
793      * @return A newly-allocated byte buffer containing the result of the
794      *         encoding operation.  The buffer's position will be zero and its
795      *         limit will follow the last byte written.
796      *
797      * @throws  IllegalStateException
798      *          If an encoding operation is already in progress
799      *
800      * @throws  MalformedInputException
801      *          If the character sequence starting at the input buffer's current
802      *          position is not a legal sixteen-bit Unicode sequence and the current malformed-input action
803      *          is {@link CodingErrorAction#REPORT}
804      *
805      * @throws  UnmappableCharacterException
806      *          If the character sequence starting at the input buffer's current
807      *          position cannot be mapped to an equivalent byte sequence and
808      *          the current unmappable-character action is {@link
809      *          CodingErrorAction#REPORT}
810      */
encode(CharBuffer in)811     public final ByteBuffer encode(CharBuffer in)
812         throws CharacterCodingException
813     {
814         int n = (int)(in.remaining() * averageBytesPerChar());
815         ByteBuffer out = ByteBuffer.allocate(n);
816 
817         if ((n == 0) && (in.remaining() == 0))
818             return out;
819         reset();
820         for (;;) {
821             CoderResult cr = in.hasRemaining() ?
822                 encode(in, out, true) : CoderResult.UNDERFLOW;
823             if (cr.isUnderflow())
824                 cr = flush(out);
825 
826             if (cr.isUnderflow())
827                 break;
828             if (cr.isOverflow()) {
829                 n = 2*n + 1;    // Ensure progress; n might be 0!
830                 ByteBuffer o = ByteBuffer.allocate(n);
831                 out.flip();
832                 o.put(out);
833                 out = o;
834                 continue;
835             }
836             cr.throwException();
837         }
838         out.flip();
839         return out;
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 
883 
884 
885 
886 
887 
888 
889 
890 
891 
892 
893 
894 
895 
896 
897 
898 
899 
900 
901 
902 
903 
904 
905 
906 
907 
908 
909 
910 
911 
912 
913 
914 
915 
916 
917 
918 
919 
canEncode(CharBuffer cb)920     private boolean canEncode(CharBuffer cb) {
921         if (state == ST_FLUSHED)
922             reset();
923         else if (state != ST_RESET)
924             throwIllegalStateException(state, ST_CODING);
925 
926         // BEGIN Android-added: Fast path handling for empty buffers.
927         // Empty buffers can always be "encoded".
928         if (!cb.hasRemaining()) {
929             return true;
930         }
931         // END Android-added: Fast path handling for empty buffers.
932 
933         CodingErrorAction ma = malformedInputAction();
934         CodingErrorAction ua = unmappableCharacterAction();
935         try {
936             onMalformedInput(CodingErrorAction.REPORT);
937             onUnmappableCharacter(CodingErrorAction.REPORT);
938             encode(cb);
939         } catch (CharacterCodingException x) {
940             return false;
941         } finally {
942             onMalformedInput(ma);
943             onUnmappableCharacter(ua);
944             reset();
945         }
946         return true;
947     }
948 
949     /**
950      * Tells whether or not this encoder can encode the given character.
951      *
952      * <p> This method returns <tt>false</tt> if the given character is a
953      * surrogate character; such characters can be interpreted only when they
954      * are members of a pair consisting of a high surrogate followed by a low
955      * surrogate.  The {@link #canEncode(java.lang.CharSequence)
956      * canEncode(CharSequence)} method may be used to test whether or not a
957      * character sequence can be encoded.
958      *
959      * <p> This method may modify this encoder's state; it should therefore not
960      * be invoked if an <a href="#steps">encoding operation</a> is already in
961      * progress.
962      *
963      * <p> The default implementation of this method is not very efficient; it
964      * should generally be overridden to improve performance.  </p>
965      *
966      * @param   c
967      *          The given character
968      *
969      * @return  <tt>true</tt> if, and only if, this encoder can encode
970      *          the given character
971      *
972      * @throws  IllegalStateException
973      *          If an encoding operation is already in progress
974      */
canEncode(char c)975     public boolean canEncode(char c) {
976         CharBuffer cb = CharBuffer.allocate(1);
977         cb.put(c);
978         cb.flip();
979         return canEncode(cb);
980     }
981 
982     /**
983      * Tells whether or not this encoder can encode the given character
984      * sequence.
985      *
986      * <p> If this method returns <tt>false</tt> for a particular character
987      * sequence then more information about why the sequence cannot be encoded
988      * may be obtained by performing a full <a href="#steps">encoding
989      * operation</a>.
990      *
991      * <p> This method may modify this encoder's state; it should therefore not
992      * be invoked if an encoding operation is already in progress.
993      *
994      * <p> The default implementation of this method is not very efficient; it
995      * should generally be overridden to improve performance.  </p>
996      *
997      * @param   cs
998      *          The given character sequence
999      *
1000      * @return  <tt>true</tt> if, and only if, this encoder can encode
1001      *          the given character without throwing any exceptions and without
1002      *          performing any replacements
1003      *
1004      * @throws  IllegalStateException
1005      *          If an encoding operation is already in progress
1006      */
canEncode(CharSequence cs)1007     public boolean canEncode(CharSequence cs) {
1008         CharBuffer cb;
1009         if (cs instanceof CharBuffer)
1010             cb = ((CharBuffer)cs).duplicate();
1011         else
1012             // Android-removed: An unnecessary call to toString().
1013             // cb = CharBuffer.wrap(cs.toString());
1014             cb = CharBuffer.wrap(cs);
1015         return canEncode(cb);
1016     }
1017 
1018 
1019 
1020 
throwIllegalStateException(int from, int to)1021     private void throwIllegalStateException(int from, int to) {
1022         throw new IllegalStateException("Current state = " + stateNames[from]
1023                                         + ", new state = " + stateNames[to]);
1024     }
1025 
1026 }
1027