1 /*
2 * Copyright (c) 2000, 2017, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 #warn This file is preprocessed before being compiled
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 import java.util.Arrays;
38
39
40 /**
41 * An engine that can transform a sequence of $itypesPhrase$ into a sequence of
42 * $otypesPhrase$.
43 *
44 * <a id="steps"></a>
45 *
46 * <p> The input $itype$ sequence is provided in a $itype$ buffer or a series
47 * of such buffers. The output $otype$ sequence is written to a $otype$ buffer
48 * or a series of such buffers. $A$ $coder$ should always be used by making
49 * the following sequence of method invocations, hereinafter referred to as $a$
50 * <i>$coding$ operation</i>:
51 *
52 * <ol>
53 *
54 * <li><p> Reset the $coder$ via the {@link #reset reset} method, unless it
55 * has not been used before; </p></li>
56 *
57 * <li><p> Invoke the {@link #$code$ $code$} method zero or more times, as
58 * long as additional input may be available, passing {@code false} for the
59 * {@code endOfInput} argument and filling the input buffer and flushing the
60 * output buffer between invocations; </p></li>
61 *
62 * <li><p> Invoke the {@link #$code$ $code$} method one final time, passing
63 * {@code true} for the {@code endOfInput} argument; and then </p></li>
64 *
65 * <li><p> Invoke the {@link #flush flush} method so that the $coder$ can
66 * flush any internal state to the output buffer. </p></li>
67 *
68 * </ol>
69 *
70 * Each invocation of the {@link #$code$ $code$} method will $code$ as many
71 * $itype$s as possible from the input buffer, writing the resulting $otype$s
72 * to the output buffer. The {@link #$code$ $code$} method returns when more
73 * input is required, when there is not enough room in the output buffer, or
74 * when $a$ $coding$ error has occurred. In each case a {@link CoderResult}
75 * object is returned to describe the reason for termination. An invoker can
76 * examine this object and fill the input buffer, flush the output buffer, or
77 * attempt to recover from $a$ $coding$ error, as appropriate, and try again.
78 *
79 * <a id="ce"></a>
80 *
81 * <p> There are two general types of $coding$ errors. If the input $itype$
82 * sequence is $notLegal$ then the input is considered <i>malformed</i>. If
83 * the input $itype$ sequence is legal but cannot be mapped to a valid
84 * $outSequence$ then an <i>unmappable character</i> has been encountered.
85 *
86 * <a id="cae"></a>
87 *
88 * <p> How $a$ $coding$ error is handled depends upon the action requested for
89 * that type of error, which is described by an instance of the {@link
90 * CodingErrorAction} class. The possible error actions are to {@linkplain
91 * CodingErrorAction#IGNORE ignore} the erroneous input, {@linkplain
92 * CodingErrorAction#REPORT report} the error to the invoker via
93 * the returned {@link CoderResult} object, or {@linkplain CodingErrorAction#REPLACE
94 * replace} the erroneous input with the current value of the
95 * replacement $replTypeName$. The replacement
96 *
97 #if[encoder]
98 * is initially set to the $coder$'s default replacement, which often
99 * (but not always) has the initial value $defaultReplName$;
100 #end[encoder]
101 #if[decoder]
102 * has the initial value $defaultReplName$;
103 #end[decoder]
104 *
105 * its value may be changed via the {@link #replaceWith($replFQType$)
106 * replaceWith} method.
107 *
108 * <p> The default action for malformed-input and unmappable-character errors
109 * is to {@linkplain CodingErrorAction#REPORT report} them. The
110 * malformed-input error action may be changed via the {@link
111 * #onMalformedInput(CodingErrorAction) onMalformedInput} method; the
112 * unmappable-character action may be changed via the {@link
113 * #onUnmappableCharacter(CodingErrorAction) onUnmappableCharacter} method.
114 *
115 * <p> This class is designed to handle many of the details of the $coding$
116 * process, including the implementation of error actions. $A$ $coder$ for a
117 * specific charset, which is a concrete subclass of this class, need only
118 * implement the abstract {@link #$code$Loop $code$Loop} method, which
119 * encapsulates the basic $coding$ loop. A subclass that maintains internal
120 * state should, additionally, override the {@link #implFlush implFlush} and
121 * {@link #implReset implReset} methods.
122 *
123 * <p> Instances of this class are not safe for use by multiple concurrent
124 * threads. </p>
125 *
126 *
127 * @author Mark Reinhold
128 * @author JSR-51 Expert Group
129 * @since 1.4
130 *
131 * @see ByteBuffer
132 * @see CharBuffer
133 * @see Charset
134 * @see Charset$OtherCoder$
135 */
136
137 public abstract class Charset$Coder$ {
138
139 private final Charset charset;
140 private final float average$ItypesPerOtype$;
141 private final float max$ItypesPerOtype$;
142
143 private $replType$ replacement;
144 private CodingErrorAction malformedInputAction
145 = CodingErrorAction.REPORT;
146 private CodingErrorAction unmappableCharacterAction
147 = CodingErrorAction.REPORT;
148
149 // Internal states
150 //
151 private static final int ST_RESET = 0;
152 private static final int ST_CODING = 1;
153 private static final int ST_END = 2;
154 private static final int ST_FLUSHED = 3;
155
156 private int state = ST_RESET;
157
158 private static String stateNames[]
159 = { "RESET", "CODING", "CODING_END", "FLUSHED" };
160
161
162 /**
163 * Initializes a new $coder$. The new $coder$ will have the given
164 * $otypes-per-itype$ and replacement values.
165 *
166 * @param cs
167 * The charset that created this $coder$
168 *
169 * @param average$ItypesPerOtype$
170 * A positive float value indicating the expected number of
171 * $otype$s that will be produced for each input $itype$
172 *
173 * @param max$ItypesPerOtype$
174 * A positive float value indicating the maximum number of
175 * $otype$s that will be produced for each input $itype$
176 *
177 * @param replacement
178 * The initial replacement; must not be {@code null}, must have
179 * non-zero length, must not be longer than max$ItypesPerOtype$,
180 * and must be {@linkplain #isLegalReplacement legal}
181 *
182 * @throws IllegalArgumentException
183 * If the preconditions on the parameters do not hold
184 */
185 {#if[encoder]?protected:private}
186 Charset$Coder$(Charset cs,
187 float average$ItypesPerOtype$,
188 float max$ItypesPerOtype$,
189 $replType$ replacement)
190 {
191 this.charset = cs;
192 if (average$ItypesPerOtype$ <= 0.0f)
193 throw new IllegalArgumentException("Non-positive "
194 + "average$ItypesPerOtype$");
195 if (max$ItypesPerOtype$ <= 0.0f)
196 throw new IllegalArgumentException("Non-positive "
197 + "max$ItypesPerOtype$");
198 if (average$ItypesPerOtype$ > max$ItypesPerOtype$)
199 throw new IllegalArgumentException("average$ItypesPerOtype$"
200 + " exceeds "
201 + "max$ItypesPerOtype$");
202 this.replacement = replacement;
203 this.average$ItypesPerOtype$ = average$ItypesPerOtype$;
204 this.max$ItypesPerOtype$ = max$ItypesPerOtype$;
205 replaceWith(replacement);
206 }
207
208 /**
209 * Initializes a new $coder$. The new $coder$ will have the given
210 * $otypes-per-itype$ values and its replacement will be the
211 * $replTypeName$ $defaultReplName$.
212 *
213 * @param cs
214 * The charset that created this $coder$
215 *
216 * @param average$ItypesPerOtype$
217 * A positive float value indicating the expected number of
218 * $otype$s that will be produced for each input $itype$
219 *
220 * @param max$ItypesPerOtype$
221 * A positive float value indicating the maximum number of
222 * $otype$s that will be produced for each input $itype$
223 *
224 * @throws IllegalArgumentException
225 * If the preconditions on the parameters do not hold
226 */
227 protected Charset$Coder$(Charset cs,
228 float average$ItypesPerOtype$,
229 float max$ItypesPerOtype$)
230 {
231 this(cs,
232 average$ItypesPerOtype$, max$ItypesPerOtype$,
233 $defaultRepl$);
234 }
235
236 /**
237 * Returns the charset that created this $coder$.
238 *
239 * @return This $coder$'s charset
240 */
241 public final Charset charset() {
242 return charset;
243 }
244
245 /**
246 * Returns this $coder$'s replacement value.
247 *
248 * @return This $coder$'s current replacement,
249 * which is never {@code null} and is never empty
250 */
251 public final $replType$ replacement() {
252 #if[decoder]
253 return replacement;
254 #end[decoder]
255 #if[encoder]
256 return Arrays.copyOf(replacement, replacement.$replLength$);
257 #end[encoder]
258 }
259
260 /**
261 * Changes this $coder$'s replacement value.
262 *
263 * <p> This method invokes the {@link #implReplaceWith implReplaceWith}
264 * method, passing the new replacement, after checking that the new
265 * replacement is acceptable. </p>
266 *
267 * @param newReplacement The new replacement; must not be
268 * {@code null}, must have non-zero length,
269 #if[decoder]
270 * and must not be longer than the value returned by the
271 * {@link #max$ItypesPerOtype$() max$ItypesPerOtype$} method
272 #end[decoder]
273 #if[encoder]
274 * must not be longer than the value returned by the
275 * {@link #max$ItypesPerOtype$() max$ItypesPerOtype$} method, and
276 * must be {@link #isLegalReplacement legal}
277 #end[encoder]
278 *
279 * @return This $coder$
280 *
281 * @throws IllegalArgumentException
282 * If the preconditions on the parameter do not hold
283 */
284 public final Charset$Coder$ replaceWith($replType$ newReplacement) {
285 if (newReplacement == null)
286 throw new IllegalArgumentException("Null replacement");
287 int len = newReplacement.$replLength$;
288 if (len == 0)
289 throw new IllegalArgumentException("Empty replacement");
290 if (len > max$ItypesPerOtype$)
291 throw new IllegalArgumentException("Replacement too long");
292 #if[decoder]
293 this.replacement = newReplacement;
294 #end[decoder]
295 #if[encoder]
296 if (!isLegalReplacement(newReplacement))
297 throw new IllegalArgumentException("Illegal replacement");
298 this.replacement = Arrays.copyOf(newReplacement, newReplacement.$replLength$);
299 #end[encoder]
300 implReplaceWith(this.replacement);
301 return this;
302 }
303
304 /**
305 * Reports a change to this $coder$'s replacement value.
306 *
307 * <p> The default implementation of this method does nothing. This method
308 * should be overridden by $coder$s that require notification of changes to
309 * the replacement. </p>
310 *
311 * @param newReplacement The replacement value
312 */
313 protected void implReplaceWith($replType$ newReplacement) {
314 }
315
316 #if[encoder]
317
318 private WeakReference<CharsetDecoder> cachedDecoder = null;
319
320 /**
321 * Tells whether or not the given byte array is a legal replacement value
322 * for this encoder.
323 *
324 * <p> A replacement is legal if, and only if, it is a legal sequence of
325 * bytes in this encoder's charset; that is, it must be possible to decode
326 * the replacement into one or more sixteen-bit Unicode characters.
327 *
328 * <p> The default implementation of this method is not very efficient; it
329 * should generally be overridden to improve performance. </p>
330 *
331 * @param repl The byte array to be tested
332 *
333 * @return {@code true} if, and only if, the given byte array
334 * is a legal replacement value for this encoder
335 */
336 public boolean isLegalReplacement(byte[] repl) {
337 WeakReference<CharsetDecoder> wr = cachedDecoder;
338 CharsetDecoder dec = null;
339 if ((wr == null) || ((dec = wr.get()) == null)) {
340 dec = charset().newDecoder();
341 dec.onMalformedInput(CodingErrorAction.REPORT);
342 dec.onUnmappableCharacter(CodingErrorAction.REPORT);
343 cachedDecoder = new WeakReference<CharsetDecoder>(dec);
344 } else {
345 dec.reset();
346 }
347 ByteBuffer bb = ByteBuffer.wrap(repl);
348 CharBuffer cb = CharBuffer.allocate((int)(bb.remaining()
349 * dec.maxCharsPerByte()));
350 CoderResult cr = dec.decode(bb, cb, true);
351 return !cr.isError();
352 }
353
354 #end[encoder]
355
356 /**
357 * Returns this $coder$'s current action for malformed-input errors.
358 *
359 * @return The current malformed-input action, which is never {@code null}
360 */
361 public CodingErrorAction malformedInputAction() {
362 return malformedInputAction;
363 }
364
365 /**
366 * Changes this $coder$'s action for malformed-input errors.
367 *
368 * <p> This method invokes the {@link #implOnMalformedInput
369 * implOnMalformedInput} method, passing the new action. </p>
370 *
371 * @param newAction The new action; must not be {@code null}
372 *
373 * @return This $coder$
374 *
375 * @throws IllegalArgumentException
376 * If the precondition on the parameter does not hold
377 */
378 public final Charset$Coder$ onMalformedInput(CodingErrorAction newAction) {
379 if (newAction == null)
380 throw new IllegalArgumentException("Null action");
381 malformedInputAction = newAction;
382 implOnMalformedInput(newAction);
383 return this;
384 }
385
386 /**
387 * Reports a change to this $coder$'s malformed-input action.
388 *
389 * <p> The default implementation of this method does nothing. This method
390 * should be overridden by $coder$s that require notification of changes to
391 * the malformed-input action. </p>
392 *
393 * @param newAction The new action
394 */
395 protected void implOnMalformedInput(CodingErrorAction newAction) { }
396
397 /**
398 * Returns this $coder$'s current action for unmappable-character errors.
399 *
400 * @return The current unmappable-character action, which is never
401 * {@code null}
402 */
403 public CodingErrorAction unmappableCharacterAction() {
404 return unmappableCharacterAction;
405 }
406
407 /**
408 * Changes this $coder$'s action for unmappable-character errors.
409 *
410 * <p> This method invokes the {@link #implOnUnmappableCharacter
411 * implOnUnmappableCharacter} method, passing the new action. </p>
412 *
413 * @param newAction The new action; must not be {@code null}
414 *
415 * @return This $coder$
416 *
417 * @throws IllegalArgumentException
418 * If the precondition on the parameter does not hold
419 */
420 public final Charset$Coder$ onUnmappableCharacter(CodingErrorAction
421 newAction)
422 {
423 if (newAction == null)
424 throw new IllegalArgumentException("Null action");
425 unmappableCharacterAction = newAction;
426 implOnUnmappableCharacter(newAction);
427 return this;
428 }
429
430 /**
431 * Reports a change to this $coder$'s unmappable-character action.
432 *
433 * <p> The default implementation of this method does nothing. This method
434 * should be overridden by $coder$s that require notification of changes to
435 * the unmappable-character action. </p>
436 *
437 * @param newAction The new action
438 */
439 protected void implOnUnmappableCharacter(CodingErrorAction newAction) { }
440
441 /**
442 * Returns the average number of $otype$s that will be produced for each
443 * $itype$ of input. This heuristic value may be used to estimate the size
444 * of the output buffer required for a given input sequence.
445 *
446 * @return The average number of $otype$s produced
447 * per $itype$ of input
448 */
449 public final float average$ItypesPerOtype$() {
450 return average$ItypesPerOtype$;
451 }
452
453 /**
454 * Returns the maximum number of $otype$s that will be produced for each
455 * $itype$ of input. This value may be used to compute the worst-case size
456 * of the output buffer required for a given input sequence.
457 *
458 * @return The maximum number of $otype$s that will be produced per
459 * $itype$ of input
460 */
461 public final float max$ItypesPerOtype$() {
462 return max$ItypesPerOtype$;
463 }
464
465 /**
466 * $Code$s as many $itype$s as possible from the given input buffer,
467 * writing the results to the given output buffer.
468 *
469 * <p> The buffers are read from, and written to, starting at their current
470 * positions. At most {@link Buffer#remaining in.remaining()} $itype$s
471 * will be read and at most {@link Buffer#remaining out.remaining()}
472 * $otype$s will be written. The buffers' positions will be advanced to
473 * reflect the $itype$s read and the $otype$s written, but their marks and
474 * limits will not be modified.
475 *
476 * <p> In addition to reading $itype$s from the input buffer and writing
477 * $otype$s to the output buffer, this method returns a {@link CoderResult}
478 * object to describe its reason for termination:
479 *
480 * <ul>
481 *
482 * <li><p> {@link CoderResult#UNDERFLOW} indicates that as much of the
483 * input buffer as possible has been $code$d. If there is no further
484 * input then the invoker can proceed to the next step of the
485 * <a href="#steps">$coding$ operation</a>. Otherwise this method
486 * should be invoked again with further input. </p></li>
487 *
488 * <li><p> {@link CoderResult#OVERFLOW} indicates that there is
489 * insufficient space in the output buffer to $code$ any more $itype$s.
490 * This method should be invoked again with an output buffer that has
491 * more {@linkplain Buffer#remaining remaining} $otype$s. This is
492 * typically done by draining any $code$d $otype$s from the output
493 * buffer. </p></li>
494 *
495 * <li><p> A {@linkplain CoderResult#malformedForLength
496 * malformed-input} result indicates that a malformed-input
497 * error has been detected. The malformed $itype$s begin at the input
498 * buffer's (possibly incremented) position; the number of malformed
499 * $itype$s may be determined by invoking the result object's {@link
500 * CoderResult#length() length} method. This case applies only if the
501 * {@linkplain #onMalformedInput malformed action} of this $coder$
502 * is {@link CodingErrorAction#REPORT}; otherwise the malformed input
503 * will be ignored or replaced, as requested. </p></li>
504 *
505 * <li><p> An {@linkplain CoderResult#unmappableForLength
506 * unmappable-character} result indicates that an
507 * unmappable-character error has been detected. The $itype$s that
508 * $code$ the unmappable character begin at the input buffer's (possibly
509 * incremented) position; the number of such $itype$s may be determined
510 * by invoking the result object's {@link CoderResult#length() length}
511 * method. This case applies only if the {@linkplain #onUnmappableCharacter
512 * unmappable action} of this $coder$ is {@link
513 * CodingErrorAction#REPORT}; otherwise the unmappable character will be
514 * ignored or replaced, as requested. </p></li>
515 *
516 * </ul>
517 *
518 * In any case, if this method is to be reinvoked in the same $coding$
519 * operation then care should be taken to preserve any $itype$s remaining
520 * in the input buffer so that they are available to the next invocation.
521 *
522 * <p> The {@code endOfInput} parameter advises this method as to whether
523 * the invoker can provide further input beyond that contained in the given
524 * input buffer. If there is a possibility of providing additional input
525 * then the invoker should pass {@code false} for this parameter; if there
526 * is no possibility of providing further input then the invoker should
527 * pass {@code true}. It is not erroneous, and in fact it is quite
528 * common, to pass {@code false} in one invocation and later discover that
529 * no further input was actually available. It is critical, however, that
530 * the final invocation of this method in a sequence of invocations always
531 * pass {@code true} so that any remaining un$code$d input will be treated
532 * as being malformed.
533 *
534 * <p> This method works by invoking the {@link #$code$Loop $code$Loop}
535 * method, interpreting its results, handling error conditions, and
536 * reinvoking it as necessary. </p>
537 *
538 *
539 * @param in
540 * The input $itype$ buffer
541 *
542 * @param out
543 * The output $otype$ buffer
544 *
545 * @param endOfInput
546 * {@code true} if, and only if, the invoker can provide no
547 * additional input $itype$s beyond those in the given buffer
548 *
549 * @return A coder-result object describing the reason for termination
550 *
551 * @throws IllegalStateException
552 * If $a$ $coding$ operation is already in progress and the previous
553 * step was an invocation neither of the {@link #reset reset}
554 * method, nor of this method with a value of {@code false} for
555 * the {@code endOfInput} parameter, nor of this method with a
556 * value of {@code true} for the {@code endOfInput} parameter
557 * but a return value indicating an incomplete $coding$ operation
558 *
559 * @throws CoderMalfunctionError
560 * If an invocation of the $code$Loop method threw
561 * an unexpected exception
562 */
563 public final CoderResult $code$($Itype$Buffer in, $Otype$Buffer out,
564 boolean endOfInput)
565 {
566 int newState = endOfInput ? ST_END : ST_CODING;
567 if ((state != ST_RESET) && (state != ST_CODING)
568 && !(endOfInput && (state == ST_END)))
569 throwIllegalStateException(state, newState);
570 state = newState;
571
572 for (;;) {
573
574 CoderResult cr;
575 try {
576 cr = $code$Loop(in, out);
577 } catch (BufferUnderflowException x) {
578 throw new CoderMalfunctionError(x);
579 } catch (BufferOverflowException x) {
580 throw new CoderMalfunctionError(x);
581 }
582
583 if (cr.isOverflow())
584 return cr;
585
586 if (cr.isUnderflow()) {
587 if (endOfInput && in.hasRemaining()) {
588 cr = CoderResult.malformedForLength(in.remaining());
589 // Fall through to malformed-input case
590 } else {
591 return cr;
592 }
593 }
594
595 CodingErrorAction action = null;
596 if (cr.isMalformed())
597 action = malformedInputAction;
598 else if (cr.isUnmappable())
599 action = unmappableCharacterAction;
600 else
601 assert false : cr.toString();
602
603 if (action == CodingErrorAction.REPORT)
604 return cr;
605
606 if (action == CodingErrorAction.REPLACE) {
607 if (out.remaining() < replacement.$replLength$)
608 return CoderResult.OVERFLOW;
609 out.put(replacement);
610 }
611
612 if ((action == CodingErrorAction.IGNORE)
613 || (action == CodingErrorAction.REPLACE)) {
614 // Skip erroneous input either way
615 in.position(in.position() + cr.length());
616 continue;
617 }
618
619 assert false;
620 }
621
622 }
623
624 /**
625 * Flushes this $coder$.
626 *
627 * <p> Some $coder$s maintain internal state and may need to write some
628 * final $otype$s to the output buffer once the overall input sequence has
629 * been read.
630 *
631 * <p> Any additional output is written to the output buffer beginning at
632 * its current position. At most {@link Buffer#remaining out.remaining()}
633 * $otype$s will be written. The buffer's position will be advanced
634 * appropriately, but its mark and limit will not be modified.
635 *
636 * <p> If this method completes successfully then it returns {@link
637 * CoderResult#UNDERFLOW}. If there is insufficient room in the output
638 * buffer then it returns {@link CoderResult#OVERFLOW}. If this happens
639 * then this method must be invoked again, with an output buffer that has
640 * more room, in order to complete the current <a href="#steps">$coding$
641 * operation</a>.
642 *
643 * <p> If this $coder$ has already been flushed then invoking this method
644 * has no effect.
645 *
646 * <p> This method invokes the {@link #implFlush implFlush} method to
647 * perform the actual flushing operation. </p>
648 *
649 * @param out
650 * The output $otype$ buffer
651 *
652 * @return A coder-result object, either {@link CoderResult#UNDERFLOW} or
653 * {@link CoderResult#OVERFLOW}
654 *
655 * @throws IllegalStateException
656 * If the previous step of the current $coding$ operation was an
657 * invocation neither of the {@link #flush flush} method nor of
658 * the three-argument {@link
659 * #$code$($Itype$Buffer,$Otype$Buffer,boolean) $code$} method
660 * with a value of {@code true} for the {@code endOfInput}
661 * parameter
662 */
663 public final CoderResult flush($Otype$Buffer out) {
664 if (state == ST_END) {
665 CoderResult cr = implFlush(out);
666 if (cr.isUnderflow())
667 state = ST_FLUSHED;
668 return cr;
669 }
670
671 if (state != ST_FLUSHED)
672 throwIllegalStateException(state, ST_FLUSHED);
673
674 return CoderResult.UNDERFLOW; // Already flushed
675 }
676
677 /**
678 * Flushes this $coder$.
679 *
680 * <p> The default implementation of this method does nothing, and always
681 * returns {@link CoderResult#UNDERFLOW}. This method should be overridden
682 * by $coder$s that may need to write final $otype$s to the output buffer
683 * once the entire input sequence has been read. </p>
684 *
685 * @param out
686 * The output $otype$ buffer
687 *
688 * @return A coder-result object, either {@link CoderResult#UNDERFLOW} or
689 * {@link CoderResult#OVERFLOW}
690 */
691 protected CoderResult implFlush($Otype$Buffer out) {
692 return CoderResult.UNDERFLOW;
693 }
694
695 /**
696 * Resets this $coder$, clearing any internal state.
697 *
698 * <p> This method resets charset-independent state and also invokes the
699 * {@link #implReset() implReset} method in order to perform any
700 * charset-specific reset actions. </p>
701 *
702 * @return This $coder$
703 *
704 */
705 public final Charset$Coder$ reset() {
706 implReset();
707 state = ST_RESET;
708 return this;
709 }
710
711 /**
712 * Resets this $coder$, clearing any charset-specific internal state.
713 *
714 * <p> The default implementation of this method does nothing. This method
715 * should be overridden by $coder$s that maintain internal state. </p>
716 */
717 protected void implReset() { }
718
719 /**
720 * $Code$s one or more $itype$s into one or more $otype$s.
721 *
722 * <p> This method encapsulates the basic $coding$ loop, $coding$ as many
723 * $itype$s as possible until it either runs out of input, runs out of room
724 * in the output buffer, or encounters $a$ $coding$ error. This method is
725 * invoked by the {@link #$code$ $code$} method, which handles result
726 * interpretation and error recovery.
727 *
728 * <p> The buffers are read from, and written to, starting at their current
729 * positions. At most {@link Buffer#remaining in.remaining()} $itype$s
730 * will be read, and at most {@link Buffer#remaining out.remaining()}
731 * $otype$s will be written. The buffers' positions will be advanced to
732 * reflect the $itype$s read and the $otype$s written, but their marks and
733 * limits will not be modified.
734 *
735 * <p> This method returns a {@link CoderResult} object to describe its
736 * reason for termination, in the same manner as the {@link #$code$ $code$}
737 * method. Most implementations of this method will handle $coding$ errors
738 * by returning an appropriate result object for interpretation by the
739 * {@link #$code$ $code$} method. An optimized implementation may instead
740 * examine the relevant error action and implement that action itself.
741 *
742 * <p> An implementation of this method may perform arbitrary lookahead by
743 * returning {@link CoderResult#UNDERFLOW} until it receives sufficient
744 * input. </p>
745 *
746 * @param in
747 * The input $itype$ buffer
748 *
749 * @param out
750 * The output $otype$ buffer
751 *
752 * @return A coder-result object describing the reason for termination
753 */
754 protected abstract CoderResult $code$Loop($Itype$Buffer in,
755 $Otype$Buffer out);
756
757 /**
758 * Convenience method that $code$s the remaining content of a single input
759 * $itype$ buffer into a newly-allocated $otype$ buffer.
760 *
761 * <p> This method implements an entire <a href="#steps">$coding$
762 * operation</a>; that is, it resets this $coder$, then it $code$s the
763 * $itype$s in the given $itype$ buffer, and finally it flushes this
764 * $coder$. This method should therefore not be invoked if $a$ $coding$
765 * operation is already in progress. </p>
766 *
767 * @param in
768 * The input $itype$ buffer
769 *
770 * @return A newly-allocated $otype$ buffer containing the result of the
771 * $coding$ operation. The buffer's position will be zero and its
772 * limit will follow the last $otype$ written.
773 *
774 * @throws IllegalStateException
775 * If $a$ $coding$ operation is already in progress
776 *
777 * @throws MalformedInputException
778 * If the $itype$ sequence starting at the input buffer's current
779 * position is $notLegal$ and the current malformed-input action
780 * is {@link CodingErrorAction#REPORT}
781 *
782 * @throws UnmappableCharacterException
783 * If the $itype$ sequence starting at the input buffer's current
784 * position cannot be mapped to an equivalent $otype$ sequence and
785 * the current unmappable-character action is {@link
786 * CodingErrorAction#REPORT}
787 */
788 public final $Otype$Buffer $code$($Itype$Buffer in)
789 throws CharacterCodingException
790 {
791 int n = (int)(in.remaining() * average$ItypesPerOtype$());
792 $Otype$Buffer out = $Otype$Buffer.allocate(n);
793
794 if ((n == 0) && (in.remaining() == 0))
795 return out;
796 reset();
797 for (;;) {
798 CoderResult cr = in.hasRemaining() ?
799 $code$(in, out, true) : CoderResult.UNDERFLOW;
800 if (cr.isUnderflow())
801 cr = flush(out);
802
803 if (cr.isUnderflow())
804 break;
805 if (cr.isOverflow()) {
806 n = 2*n + 1; // Ensure progress; n might be 0!
807 $Otype$Buffer o = $Otype$Buffer.allocate(n);
808 out.flip();
809 o.put(out);
810 out = o;
811 continue;
812 }
813 cr.throwException();
814 }
815 out.flip();
816 return out;
817 }
818
819 #if[decoder]
820
821 /**
822 * Tells whether or not this decoder implements an auto-detecting charset.
823 *
824 * <p> The default implementation of this method always returns
825 * {@code false}; it should be overridden by auto-detecting decoders to
826 * return {@code true}. </p>
827 *
828 * @return {@code true} if, and only if, this decoder implements an
829 * auto-detecting charset
830 */
831 public boolean isAutoDetecting() {
832 return false;
833 }
834
835 /**
836 * Tells whether or not this decoder has yet detected a
837 * charset <i>(optional operation)</i>.
838 *
839 * <p> If this decoder implements an auto-detecting charset then at a
840 * single point during a decoding operation this method may start returning
841 * {@code true} to indicate that a specific charset has been detected in
842 * the input byte sequence. Once this occurs, the {@link #detectedCharset
843 * detectedCharset} method may be invoked to retrieve the detected charset.
844 *
845 * <p> That this method returns {@code false} does not imply that no bytes
846 * have yet been decoded. Some auto-detecting decoders are capable of
847 * decoding some, or even all, of an input byte sequence without fixing on
848 * a particular charset.
849 *
850 * <p> The default implementation of this method always throws an {@link
851 * UnsupportedOperationException}; it should be overridden by
852 * auto-detecting decoders to return {@code true} once the input charset
853 * has been determined. </p>
854 *
855 * @return {@code true} if, and only if, this decoder has detected a
856 * specific charset
857 *
858 * @throws UnsupportedOperationException
859 * If this decoder does not implement an auto-detecting charset
860 */
861 public boolean isCharsetDetected() {
862 throw new UnsupportedOperationException();
863 }
864
865 /**
866 * Retrieves the charset that was detected by this
867 * decoder <i>(optional operation)</i>.
868 *
869 * <p> If this decoder implements an auto-detecting charset then this
870 * method returns the actual charset once it has been detected. After that
871 * point, this method returns the same value for the duration of the
872 * current decoding operation. If not enough input bytes have yet been
873 * read to determine the actual charset then this method throws an {@link
874 * IllegalStateException}.
875 *
876 * <p> The default implementation of this method always throws an {@link
877 * UnsupportedOperationException}; it should be overridden by
878 * auto-detecting decoders to return the appropriate value. </p>
879 *
880 * @return The charset detected by this auto-detecting decoder,
881 * or {@code null} if the charset has not yet been determined
882 *
883 * @throws IllegalStateException
884 * If insufficient bytes have been read to determine a charset
885 *
886 * @throws UnsupportedOperationException
887 * If this decoder does not implement an auto-detecting charset
888 */
889 public Charset detectedCharset() {
890 throw new UnsupportedOperationException();
891 }
892
893 #end[decoder]
894
895 #if[encoder]
896
897 private boolean canEncode(CharBuffer cb) {
898 if (state == ST_FLUSHED)
899 reset();
900 else if (state != ST_RESET)
901 throwIllegalStateException(state, ST_CODING);
902 CodingErrorAction ma = malformedInputAction();
903 CodingErrorAction ua = unmappableCharacterAction();
904 try {
905 onMalformedInput(CodingErrorAction.REPORT);
906 onUnmappableCharacter(CodingErrorAction.REPORT);
907 encode(cb);
908 } catch (CharacterCodingException x) {
909 return false;
910 } finally {
911 onMalformedInput(ma);
912 onUnmappableCharacter(ua);
913 reset();
914 }
915 return true;
916 }
917
918 /**
919 * Tells whether or not this encoder can encode the given character.
920 *
921 * <p> This method returns {@code false} if the given character is a
922 * surrogate character; such characters can be interpreted only when they
923 * are members of a pair consisting of a high surrogate followed by a low
924 * surrogate. The {@link #canEncode(java.lang.CharSequence)
925 * canEncode(CharSequence)} method may be used to test whether or not a
926 * character sequence can be encoded.
927 *
928 * <p> This method may modify this encoder's state; it should therefore not
929 * be invoked if an <a href="#steps">encoding operation</a> is already in
930 * progress.
931 *
932 * <p> The default implementation of this method is not very efficient; it
933 * should generally be overridden to improve performance. </p>
934 *
935 * @param c
936 * The given character
937 *
938 * @return {@code true} if, and only if, this encoder can encode
939 * the given character
940 *
941 * @throws IllegalStateException
942 * If $a$ $coding$ operation is already in progress
943 */
944 public boolean canEncode(char c) {
945 CharBuffer cb = CharBuffer.allocate(1);
946 cb.put(c);
947 cb.flip();
948 return canEncode(cb);
949 }
950
951 /**
952 * Tells whether or not this encoder can encode the given character
953 * sequence.
954 *
955 * <p> If this method returns {@code false} for a particular character
956 * sequence then more information about why the sequence cannot be encoded
957 * may be obtained by performing a full <a href="#steps">encoding
958 * operation</a>.
959 *
960 * <p> This method may modify this encoder's state; it should therefore not
961 * be invoked if an encoding operation is already in 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 cs
967 * The given character sequence
968 *
969 * @return {@code true} if, and only if, this encoder can encode
970 * the given character without throwing any exceptions and without
971 * performing any replacements
972 *
973 * @throws IllegalStateException
974 * If $a$ $coding$ operation is already in progress
975 */
976 public boolean canEncode(CharSequence cs) {
977 CharBuffer cb;
978 if (cs instanceof CharBuffer)
979 cb = ((CharBuffer)cs).duplicate();
980 else
981 cb = CharBuffer.wrap(cs.toString());
982 return canEncode(cb);
983 }
984
985 #end[encoder]
986
987
988 private void throwIllegalStateException(int from, int to) {
989 throw new IllegalStateException("Current state = " + stateNames[from]
990 + ", new state = " + stateNames[to]);
991 }
992
993 }