• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
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      */
CharsetEncoder(Charset cs, float averageBytesPerChar, float maxBytesPerChar, byte[] replacement, boolean trusted)201     CharsetEncoder(Charset cs, float averageBytesPerChar, float maxBytesPerChar, byte[] replacement,
202             boolean trusted)
203     {
204         // END Android-added: A hidden constructor for the CharsetEncoderICU subclass.
205         this.charset = cs;
206         if (averageBytesPerChar <= 0.0f)
207             throw new IllegalArgumentException("Non-positive "
208                                                + "averageBytesPerChar");
209         if (maxBytesPerChar <= 0.0f)
210             throw new IllegalArgumentException("Non-positive "
211                                                + "maxBytesPerChar");
212         if (!Charset.atBugLevel("1.4")) {
213             if (averageBytesPerChar > maxBytesPerChar)
214                 throw new IllegalArgumentException("averageBytesPerChar"
215                                                    + " exceeds "
216                                                    + "maxBytesPerChar");
217         }
218         this.replacement = replacement;
219         this.averageBytesPerChar = averageBytesPerChar;
220         this.maxBytesPerChar = maxBytesPerChar;
221         // BEGIN Android-changed: Avoid calling replaceWith() for trusted subclasses.
222         // replaceWith(replacement);
223         if (!trusted) {
224             replaceWith(replacement);
225         }
226         // END Android-changed: Avoid calling replaceWith() for trusted subclasses.
227     }
228 
229     /**
230      * Initializes a new encoder.  The new encoder will have the given
231      * bytes-per-char values and its replacement will be the
232      * byte array <tt>{</tt>&nbsp;<tt>(byte)'?'</tt>&nbsp;<tt>}</tt>.
233      *
234      * @param  cs
235      *         The charset that created this encoder
236      *
237      * @param  averageBytesPerChar
238      *         A positive float value indicating the expected number of
239      *         bytes that will be produced for each input character
240      *
241      * @param  maxBytesPerChar
242      *         A positive float value indicating the maximum number of
243      *         bytes that will be produced for each input character
244      *
245      * @throws  IllegalArgumentException
246      *          If the preconditions on the parameters do not hold
247      */
CharsetEncoder(Charset cs, float averageBytesPerChar, float maxBytesPerChar)248     protected CharsetEncoder(Charset cs,
249                              float averageBytesPerChar,
250                              float maxBytesPerChar)
251     {
252         this(cs,
253              averageBytesPerChar, maxBytesPerChar,
254              new byte[] { (byte)'?' });
255     }
256 
257     /**
258      * Returns the charset that created this encoder.
259      *
260      * @return  This encoder's charset
261      */
charset()262     public final Charset charset() {
263         return charset;
264     }
265 
266     /**
267      * Returns this encoder's replacement value.
268      *
269      * @return  This encoder's current replacement,
270      *          which is never <tt>null</tt> and is never empty
271      */
replacement()272     public final byte[] replacement() {
273 
274 
275 
276 
277         return Arrays.copyOf(replacement, replacement.length);
278 
279     }
280 
281     /**
282      * Changes this encoder's replacement value.
283      *
284      * <p> This method invokes the {@link #implReplaceWith implReplaceWith}
285      * method, passing the new replacement, after checking that the new
286      * replacement is acceptable.  </p>
287      *
288      * @param  newReplacement  The replacement value
289      *
290 
291 
292 
293 
294 
295      *         The new replacement; must not be <tt>null</tt>, must have
296      *         non-zero length, must not be longer than the value returned by
297      *         the {@link #maxBytesPerChar() maxBytesPerChar} method, and
298      *         must be {@link #isLegalReplacement legal}
299 
300      *
301      * @return  This encoder
302      *
303      * @throws  IllegalArgumentException
304      *          If the preconditions on the parameter do not hold
305      */
replaceWith(byte[] newReplacement)306     public final CharsetEncoder replaceWith(byte[] newReplacement) {
307         if (newReplacement == null)
308             throw new IllegalArgumentException("Null replacement");
309         int len = newReplacement.length;
310         if (len == 0)
311             throw new IllegalArgumentException("Empty replacement");
312         if (len > maxBytesPerChar)
313             throw new IllegalArgumentException("Replacement too long");
314 
315 
316 
317 
318         if (!isLegalReplacement(newReplacement))
319             throw new IllegalArgumentException("Illegal replacement");
320         this.replacement = Arrays.copyOf(newReplacement, newReplacement.length);
321 
322         implReplaceWith(this.replacement);
323         return this;
324     }
325 
326     /**
327      * Reports a change to this encoder's replacement value.
328      *
329      * <p> The default implementation of this method does nothing.  This method
330      * should be overridden by encoders that require notification of changes to
331      * the replacement.  </p>
332      *
333      * @param  newReplacement    The replacement value
334      */
implReplaceWith(byte[] newReplacement)335     protected void implReplaceWith(byte[] newReplacement) {
336     }
337 
338 
339 
340     private WeakReference<CharsetDecoder> cachedDecoder = null;
341 
342     /**
343      * Tells whether or not the given byte array is a legal replacement value
344      * for this encoder.
345      *
346      * <p> A replacement is legal if, and only if, it is a legal sequence of
347      * bytes in this encoder's charset; that is, it must be possible to decode
348      * the replacement into one or more sixteen-bit Unicode characters.
349      *
350      * <p> The default implementation of this method is not very efficient; it
351      * should generally be overridden to improve performance.  </p>
352      *
353      * @param  repl  The byte array to be tested
354      *
355      * @return  <tt>true</tt> if, and only if, the given byte array
356      *          is a legal replacement value for this encoder
357      */
isLegalReplacement(byte[] repl)358     public boolean isLegalReplacement(byte[] repl) {
359         WeakReference<CharsetDecoder> wr = cachedDecoder;
360         CharsetDecoder dec = null;
361         if ((wr == null) || ((dec = wr.get()) == null)) {
362             dec = charset().newDecoder();
363             dec.onMalformedInput(CodingErrorAction.REPORT);
364             dec.onUnmappableCharacter(CodingErrorAction.REPORT);
365             cachedDecoder = new WeakReference<CharsetDecoder>(dec);
366         } else {
367             dec.reset();
368         }
369         ByteBuffer bb = ByteBuffer.wrap(repl);
370         CharBuffer cb = CharBuffer.allocate((int)(bb.remaining()
371                                                   * dec.maxCharsPerByte()));
372         CoderResult cr = dec.decode(bb, cb, true);
373         return !cr.isError();
374     }
375 
376 
377 
378     /**
379      * Returns this encoder's current action for malformed-input errors.
380      *
381      * @return The current malformed-input action, which is never <tt>null</tt>
382      */
malformedInputAction()383     public CodingErrorAction malformedInputAction() {
384         return malformedInputAction;
385     }
386 
387     /**
388      * Changes this encoder's action for malformed-input errors.
389      *
390      * <p> This method invokes the {@link #implOnMalformedInput
391      * implOnMalformedInput} method, passing the new action.  </p>
392      *
393      * @param  newAction  The new action; must not be <tt>null</tt>
394      *
395      * @return  This encoder
396      *
397      * @throws IllegalArgumentException
398      *         If the precondition on the parameter does not hold
399      */
onMalformedInput(CodingErrorAction newAction)400     public final CharsetEncoder onMalformedInput(CodingErrorAction newAction) {
401         if (newAction == null)
402             throw new IllegalArgumentException("Null action");
403         malformedInputAction = newAction;
404         implOnMalformedInput(newAction);
405         return this;
406     }
407 
408     /**
409      * Reports a change to this encoder's malformed-input action.
410      *
411      * <p> The default implementation of this method does nothing.  This method
412      * should be overridden by encoders that require notification of changes to
413      * the malformed-input action.  </p>
414      *
415      * @param  newAction  The new action
416      */
implOnMalformedInput(CodingErrorAction newAction)417     protected void implOnMalformedInput(CodingErrorAction newAction) { }
418 
419     /**
420      * Returns this encoder's current action for unmappable-character errors.
421      *
422      * @return The current unmappable-character action, which is never
423      *         <tt>null</tt>
424      */
unmappableCharacterAction()425     public CodingErrorAction unmappableCharacterAction() {
426         return unmappableCharacterAction;
427     }
428 
429     /**
430      * Changes this encoder's action for unmappable-character errors.
431      *
432      * <p> This method invokes the {@link #implOnUnmappableCharacter
433      * implOnUnmappableCharacter} method, passing the new action.  </p>
434      *
435      * @param  newAction  The new action; must not be <tt>null</tt>
436      *
437      * @return  This encoder
438      *
439      * @throws IllegalArgumentException
440      *         If the precondition on the parameter does not hold
441      */
onUnmappableCharacter(CodingErrorAction newAction)442     public final CharsetEncoder onUnmappableCharacter(CodingErrorAction
443                                                       newAction)
444     {
445         if (newAction == null)
446             throw new IllegalArgumentException("Null action");
447         unmappableCharacterAction = newAction;
448         implOnUnmappableCharacter(newAction);
449         return this;
450     }
451 
452     /**
453      * Reports a change to this encoder's unmappable-character action.
454      *
455      * <p> The default implementation of this method does nothing.  This method
456      * should be overridden by encoders that require notification of changes to
457      * the unmappable-character action.  </p>
458      *
459      * @param  newAction  The new action
460      */
implOnUnmappableCharacter(CodingErrorAction newAction)461     protected void implOnUnmappableCharacter(CodingErrorAction newAction) { }
462 
463     /**
464      * Returns the average number of bytes that will be produced for each
465      * character of input.  This heuristic value may be used to estimate the size
466      * of the output buffer required for a given input sequence.
467      *
468      * @return  The average number of bytes produced
469      *          per character of input
470      */
averageBytesPerChar()471     public final float averageBytesPerChar() {
472         return averageBytesPerChar;
473     }
474 
475     /**
476      * Returns the maximum number of bytes that will be produced for each
477      * character of input.  This value may be used to compute the worst-case size
478      * of the output buffer required for a given input sequence.
479      *
480      * @return  The maximum number of bytes that will be produced per
481      *          character of input
482      */
maxBytesPerChar()483     public final float maxBytesPerChar() {
484         return maxBytesPerChar;
485     }
486 
487     /**
488      * Encodes as many characters as possible from the given input buffer,
489      * writing the results to the given output buffer.
490      *
491      * <p> The buffers are read from, and written to, starting at their current
492      * positions.  At most {@link Buffer#remaining in.remaining()} characters
493      * will be read and at most {@link Buffer#remaining out.remaining()}
494      * bytes will be written.  The buffers' positions will be advanced to
495      * reflect the characters read and the bytes written, but their marks and
496      * limits will not be modified.
497      *
498      * <p> In addition to reading characters from the input buffer and writing
499      * bytes to the output buffer, this method returns a {@link CoderResult}
500      * object to describe its reason for termination:
501      *
502      * <ul>
503      *
504      *   <li><p> {@link CoderResult#UNDERFLOW} indicates that as much of the
505      *   input buffer as possible has been encoded.  If there is no further
506      *   input then the invoker can proceed to the next step of the
507      *   <a href="#steps">encoding operation</a>.  Otherwise this method
508      *   should be invoked again with further input.  </p></li>
509      *
510      *   <li><p> {@link CoderResult#OVERFLOW} indicates that there is
511      *   insufficient space in the output buffer to encode any more characters.
512      *   This method should be invoked again with an output buffer that has
513      *   more {@linkplain Buffer#remaining remaining} bytes. This is
514      *   typically done by draining any encoded bytes from the output
515      *   buffer.  </p></li>
516      *
517      *   <li><p> A {@linkplain CoderResult#malformedForLength
518      *   malformed-input} result indicates that a malformed-input
519      *   error has been detected.  The malformed characters begin at the input
520      *   buffer's (possibly incremented) position; the number of malformed
521      *   characters may be determined by invoking the result object's {@link
522      *   CoderResult#length() length} method.  This case applies only if the
523      *   {@linkplain #onMalformedInput malformed action} of this encoder
524      *   is {@link CodingErrorAction#REPORT}; otherwise the malformed input
525      *   will be ignored or replaced, as requested.  </p></li>
526      *
527      *   <li><p> An {@linkplain CoderResult#unmappableForLength
528      *   unmappable-character} result indicates that an
529      *   unmappable-character error has been detected.  The characters that
530      *   encode the unmappable character begin at the input buffer's (possibly
531      *   incremented) position; the number of such characters may be determined
532      *   by invoking the result object's {@link CoderResult#length() length}
533      *   method.  This case applies only if the {@linkplain #onUnmappableCharacter
534      *   unmappable action} of this encoder is {@link
535      *   CodingErrorAction#REPORT}; otherwise the unmappable character will be
536      *   ignored or replaced, as requested.  </p></li>
537      *
538      * </ul>
539      *
540      * In any case, if this method is to be reinvoked in the same encoding
541      * operation then care should be taken to preserve any characters remaining
542      * in the input buffer so that they are available to the next invocation.
543      *
544      * <p> The <tt>endOfInput</tt> parameter advises this method as to whether
545      * the invoker can provide further input beyond that contained in the given
546      * input buffer.  If there is a possibility of providing additional input
547      * then the invoker should pass <tt>false</tt> for this parameter; if there
548      * is no possibility of providing further input then the invoker should
549      * pass <tt>true</tt>.  It is not erroneous, and in fact it is quite
550      * common, to pass <tt>false</tt> in one invocation and later discover that
551      * no further input was actually available.  It is critical, however, that
552      * the final invocation of this method in a sequence of invocations always
553      * pass <tt>true</tt> so that any remaining unencoded input will be treated
554      * as being malformed.
555      *
556      * <p> This method works by invoking the {@link #encodeLoop encodeLoop}
557      * method, interpreting its results, handling error conditions, and
558      * reinvoking it as necessary.  </p>
559      *
560      *
561      * @param  in
562      *         The input character buffer
563      *
564      * @param  out
565      *         The output byte buffer
566      *
567      * @param  endOfInput
568      *         <tt>true</tt> if, and only if, the invoker can provide no
569      *         additional input characters beyond those in the given buffer
570      *
571      * @return  A coder-result object describing the reason for termination
572      *
573      * @throws  IllegalStateException
574      *          If an encoding operation is already in progress and the previous
575      *          step was an invocation neither of the {@link #reset reset}
576      *          method, nor of this method with a value of <tt>false</tt> for
577      *          the <tt>endOfInput</tt> parameter, nor of this method with a
578      *          value of <tt>true</tt> for the <tt>endOfInput</tt> parameter
579      *          but a return value indicating an incomplete encoding operation
580      *
581      * @throws  CoderMalfunctionError
582      *          If an invocation of the encodeLoop method threw
583      *          an unexpected exception
584      */
encode(CharBuffer in, ByteBuffer out, boolean endOfInput)585     public final CoderResult encode(CharBuffer in, ByteBuffer out,
586                                     boolean endOfInput)
587     {
588         int newState = endOfInput ? ST_END : ST_CODING;
589         if ((state != ST_RESET) && (state != ST_CODING)
590             && !(endOfInput && (state == ST_END)))
591             throwIllegalStateException(state, newState);
592         state = newState;
593 
594         for (;;) {
595 
596             CoderResult cr;
597             try {
598                 cr = encodeLoop(in, out);
599             } catch (BufferUnderflowException x) {
600                 throw new CoderMalfunctionError(x);
601             } catch (BufferOverflowException x) {
602                 throw new CoderMalfunctionError(x);
603             }
604 
605             if (cr.isOverflow())
606                 return cr;
607 
608             if (cr.isUnderflow()) {
609                 if (endOfInput && in.hasRemaining()) {
610                     cr = CoderResult.malformedForLength(in.remaining());
611                     // Fall through to malformed-input case
612                 } else {
613                     return cr;
614                 }
615             }
616 
617             CodingErrorAction action = null;
618             if (cr.isMalformed())
619                 action = malformedInputAction;
620             else if (cr.isUnmappable())
621                 action = unmappableCharacterAction;
622             else
623                 assert false : cr.toString();
624 
625             if (action == CodingErrorAction.REPORT)
626                 return cr;
627 
628             if (action == CodingErrorAction.REPLACE) {
629                 if (out.remaining() < replacement.length)
630                     return CoderResult.OVERFLOW;
631                 out.put(replacement);
632             }
633 
634             if ((action == CodingErrorAction.IGNORE)
635                 || (action == CodingErrorAction.REPLACE)) {
636                 // Skip erroneous input either way
637                 in.position(in.position() + cr.length());
638                 continue;
639             }
640 
641             assert false;
642         }
643 
644     }
645 
646     /**
647      * Flushes this encoder.
648      *
649      * <p> Some encoders maintain internal state and may need to write some
650      * final bytes to the output buffer once the overall input sequence has
651      * been read.
652      *
653      * <p> Any additional output is written to the output buffer beginning at
654      * its current position.  At most {@link Buffer#remaining out.remaining()}
655      * bytes will be written.  The buffer's position will be advanced
656      * appropriately, but its mark and limit will not be modified.
657      *
658      * <p> If this method completes successfully then it returns {@link
659      * CoderResult#UNDERFLOW}.  If there is insufficient room in the output
660      * buffer then it returns {@link CoderResult#OVERFLOW}.  If this happens
661      * then this method must be invoked again, with an output buffer that has
662      * more room, in order to complete the current <a href="#steps">encoding
663      * operation</a>.
664      *
665      * <p> If this encoder has already been flushed then invoking this method
666      * has no effect.
667      *
668      * <p> This method invokes the {@link #implFlush implFlush} method to
669      * perform the actual flushing operation.  </p>
670      *
671      * @param  out
672      *         The output byte buffer
673      *
674      * @return  A coder-result object, either {@link CoderResult#UNDERFLOW} or
675      *          {@link CoderResult#OVERFLOW}
676      *
677      * @throws  IllegalStateException
678      *          If the previous step of the current encoding operation was an
679      *          invocation neither of the {@link #flush flush} method nor of
680      *          the three-argument {@link
681      *          #encode(CharBuffer,ByteBuffer,boolean) encode} method
682      *          with a value of <tt>true</tt> for the <tt>endOfInput</tt>
683      *          parameter
684      */
flush(ByteBuffer out)685     public final CoderResult flush(ByteBuffer out) {
686         if (state == ST_END) {
687             CoderResult cr = implFlush(out);
688             if (cr.isUnderflow())
689                 state = ST_FLUSHED;
690             return cr;
691         }
692 
693         if (state != ST_FLUSHED)
694             throwIllegalStateException(state, ST_FLUSHED);
695 
696         return CoderResult.UNDERFLOW; // Already flushed
697     }
698 
699     /**
700      * Flushes this encoder.
701      *
702      * <p> The default implementation of this method does nothing, and always
703      * returns {@link CoderResult#UNDERFLOW}.  This method should be overridden
704      * by encoders that may need to write final bytes to the output buffer
705      * once the entire input sequence has been read. </p>
706      *
707      * @param  out
708      *         The output byte buffer
709      *
710      * @return  A coder-result object, either {@link CoderResult#UNDERFLOW} or
711      *          {@link CoderResult#OVERFLOW}
712      */
implFlush(ByteBuffer out)713     protected CoderResult implFlush(ByteBuffer out) {
714         return CoderResult.UNDERFLOW;
715     }
716 
717     /**
718      * Resets this encoder, clearing any internal state.
719      *
720      * <p> This method resets charset-independent state and also invokes the
721      * {@link #implReset() implReset} method in order to perform any
722      * charset-specific reset actions.  </p>
723      *
724      * @return  This encoder
725      *
726      */
reset()727     public final CharsetEncoder reset() {
728         implReset();
729         state = ST_RESET;
730         return this;
731     }
732 
733     /**
734      * Resets this encoder, clearing any charset-specific internal state.
735      *
736      * <p> The default implementation of this method does nothing.  This method
737      * should be overridden by encoders that maintain internal state.  </p>
738      */
implReset()739     protected void implReset() { }
740 
741     /**
742      * Encodes one or more characters into one or more bytes.
743      *
744      * <p> This method encapsulates the basic encoding loop, encoding as many
745      * characters as possible until it either runs out of input, runs out of room
746      * in the output buffer, or encounters an encoding error.  This method is
747      * invoked by the {@link #encode encode} method, which handles result
748      * interpretation and error recovery.
749      *
750      * <p> The buffers are read from, and written to, starting at their current
751      * positions.  At most {@link Buffer#remaining in.remaining()} characters
752      * will be read, and at most {@link Buffer#remaining out.remaining()}
753      * bytes will be written.  The buffers' positions will be advanced to
754      * reflect the characters read and the bytes written, but their marks and
755      * limits will not be modified.
756      *
757      * <p> This method returns a {@link CoderResult} object to describe its
758      * reason for termination, in the same manner as the {@link #encode encode}
759      * method.  Most implementations of this method will handle encoding errors
760      * by returning an appropriate result object for interpretation by the
761      * {@link #encode encode} method.  An optimized implementation may instead
762      * examine the relevant error action and implement that action itself.
763      *
764      * <p> An implementation of this method may perform arbitrary lookahead by
765      * returning {@link CoderResult#UNDERFLOW} until it receives sufficient
766      * input.  </p>
767      *
768      * @param  in
769      *         The input character buffer
770      *
771      * @param  out
772      *         The output byte buffer
773      *
774      * @return  A coder-result object describing the reason for termination
775      */
encodeLoop(CharBuffer in, ByteBuffer out)776     protected abstract CoderResult encodeLoop(CharBuffer in,
777                                               ByteBuffer out);
778 
779     /**
780      * Convenience method that encodes the remaining content of a single input
781      * character buffer into a newly-allocated byte buffer.
782      *
783      * <p> This method implements an entire <a href="#steps">encoding
784      * operation</a>; that is, it resets this encoder, then it encodes the
785      * characters in the given character buffer, and finally it flushes this
786      * encoder.  This method should therefore not be invoked if an encoding
787      * operation is already in progress.  </p>
788      *
789      * @param  in
790      *         The input character buffer
791      *
792      * @return A newly-allocated byte buffer containing the result of the
793      *         encoding operation.  The buffer's position will be zero and its
794      *         limit will follow the last byte written.
795      *
796      * @throws  IllegalStateException
797      *          If an encoding operation is already in progress
798      *
799      * @throws  MalformedInputException
800      *          If the character sequence starting at the input buffer's current
801      *          position is not a legal sixteen-bit Unicode sequence and the current malformed-input action
802      *          is {@link CodingErrorAction#REPORT}
803      *
804      * @throws  UnmappableCharacterException
805      *          If the character sequence starting at the input buffer's current
806      *          position cannot be mapped to an equivalent byte sequence and
807      *          the current unmappable-character action is {@link
808      *          CodingErrorAction#REPORT}
809      */
encode(CharBuffer in)810     public final ByteBuffer encode(CharBuffer in)
811         throws CharacterCodingException
812     {
813         int n = (int)(in.remaining() * averageBytesPerChar());
814         ByteBuffer out = ByteBuffer.allocate(n);
815 
816         if ((n == 0) && (in.remaining() == 0))
817             return out;
818         reset();
819         for (;;) {
820             CoderResult cr = in.hasRemaining() ?
821                 encode(in, out, true) : CoderResult.UNDERFLOW;
822             if (cr.isUnderflow())
823                 cr = flush(out);
824 
825             if (cr.isUnderflow())
826                 break;
827             if (cr.isOverflow()) {
828                 n = 2*n + 1;    // Ensure progress; n might be 0!
829                 ByteBuffer o = ByteBuffer.allocate(n);
830                 out.flip();
831                 o.put(out);
832                 out = o;
833                 continue;
834             }
835             cr.throwException();
836         }
837         out.flip();
838         return out;
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 
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 
canEncode(CharBuffer cb)919     private boolean canEncode(CharBuffer cb) {
920         if (state == ST_FLUSHED)
921             reset();
922         else if (state != ST_RESET)
923             throwIllegalStateException(state, ST_CODING);
924 
925         // BEGIN Android-added: Fast path handling for empty buffers.
926         // Empty buffers can always be "encoded".
927         if (!cb.hasRemaining()) {
928             return true;
929         }
930         // END Android-added: Fast path handling for empty buffers.
931 
932         CodingErrorAction ma = malformedInputAction();
933         CodingErrorAction ua = unmappableCharacterAction();
934         try {
935             onMalformedInput(CodingErrorAction.REPORT);
936             onUnmappableCharacter(CodingErrorAction.REPORT);
937             encode(cb);
938         } catch (CharacterCodingException x) {
939             return false;
940         } finally {
941             onMalformedInput(ma);
942             onUnmappableCharacter(ua);
943             reset();
944         }
945         return true;
946     }
947 
948     /**
949      * Tells whether or not this encoder can encode the given character.
950      *
951      * <p> This method returns <tt>false</tt> if the given character is a
952      * surrogate character; such characters can be interpreted only when they
953      * are members of a pair consisting of a high surrogate followed by a low
954      * surrogate.  The {@link #canEncode(java.lang.CharSequence)
955      * canEncode(CharSequence)} method may be used to test whether or not a
956      * character sequence can be encoded.
957      *
958      * <p> This method may modify this encoder's state; it should therefore not
959      * be invoked if an <a href="#steps">encoding operation</a> is already in
960      * progress.
961      *
962      * <p> The default implementation of this method is not very efficient; it
963      * should generally be overridden to improve performance.  </p>
964      *
965      * @param   c
966      *          The given character
967      *
968      * @return  <tt>true</tt> if, and only if, this encoder can encode
969      *          the given character
970      *
971      * @throws  IllegalStateException
972      *          If an encoding operation is already in progress
973      */
canEncode(char c)974     public boolean canEncode(char c) {
975         CharBuffer cb = CharBuffer.allocate(1);
976         cb.put(c);
977         cb.flip();
978         return canEncode(cb);
979     }
980 
981     /**
982      * Tells whether or not this encoder can encode the given character
983      * sequence.
984      *
985      * <p> If this method returns <tt>false</tt> for a particular character
986      * sequence then more information about why the sequence cannot be encoded
987      * may be obtained by performing a full <a href="#steps">encoding
988      * operation</a>.
989      *
990      * <p> This method may modify this encoder's state; it should therefore not
991      * be invoked if an encoding operation is already in progress.
992      *
993      * <p> The default implementation of this method is not very efficient; it
994      * should generally be overridden to improve performance.  </p>
995      *
996      * @param   cs
997      *          The given character sequence
998      *
999      * @return  <tt>true</tt> if, and only if, this encoder can encode
1000      *          the given character without throwing any exceptions and without
1001      *          performing any replacements
1002      *
1003      * @throws  IllegalStateException
1004      *          If an encoding operation is already in progress
1005      */
canEncode(CharSequence cs)1006     public boolean canEncode(CharSequence cs) {
1007         CharBuffer cb;
1008         if (cs instanceof CharBuffer)
1009             cb = ((CharBuffer)cs).duplicate();
1010         else
1011             // Android-removed: An unnecessary call to toString().
1012             // cb = CharBuffer.wrap(cs.toString());
1013             cb = CharBuffer.wrap(cs);
1014         return canEncode(cb);
1015     }
1016 
1017 
1018 
1019 
throwIllegalStateException(int from, int to)1020     private void throwIllegalStateException(int from, int to) {
1021         throw new IllegalStateException("Current state = " + stateNames[from]
1022                                         + ", new state = " + stateNames[to]);
1023     }
1024 
1025 }
1026