The input $itype$ sequence is provided in a $itype$ buffer or a series - * of such buffers. The output $otype$ sequence is written to a $otype$ buffer - * or a series of such buffers. $A$ $coder$ should always be used by making - * the following sequence of method invocations, hereinafter referred to as $a$ - * $coding$ operation: - * - *
Reset the $coder$ via the {@link #reset reset} method, unless it - * has not been used before;
Invoke the {@link #$code$ $code$} method zero or more times, as - * long as additional input may be available, passing false for the - * endOfInput argument and filling the input buffer and flushing the - * output buffer between invocations;
Invoke the {@link #$code$ $code$} method one final time, passing - * true for the endOfInput argument; and then
Invoke the {@link #flush flush} method so that the $coder$ can - * flush any internal state to the output buffer.
This method invokes the {@link #implReplaceWith implReplaceWith} - * method, passing the new replacement, after checking that the new - * replacement is acceptable.
- * - * @param newReplacement - * -#if[decoder] - * The new replacement; must not be null - * and must have non-zero length -#end[decoder] -#if[encoder] - * The new replacement; must not be null, must have - * non-zero length, must not be longer than the value returned by - * the {@link #max$ItypesPerOtype$() max$ItypesPerOtype$} method, and - * must be {@link #isLegalReplacement legal}
-#end[encoder]
- *
- * @return This $coder$
- *
- * @throws IllegalArgumentException
- * If the preconditions on the parameter do not hold
- */
- public final Charset$Coder$ replaceWith($replType$ newReplacement) {
- if (newReplacement == null)
- throw new IllegalArgumentException("Null replacement");
- int len = newReplacement.$replLength$;
- if (len == 0)
- throw new IllegalArgumentException("Empty replacement");
- if (len > max$ItypesPerOtype$)
- throw new IllegalArgumentException("Replacement too long");
-#if[encoder]
- if (!isLegalReplacement(newReplacement))
- throw new IllegalArgumentException("Illegal replacement");
-#end[encoder]
- this.replacement = newReplacement;
- implReplaceWith(newReplacement);
- return this;
- }
-
- /**
- * Reports a change to this $coder$'s replacement value.
- *
- * The default implementation of this method does nothing. This method
- * should be overridden by $coder$s that require notification of changes to
- * the replacement.
- *
- * @param newReplacement
- */
- protected void implReplaceWith($replType$ newReplacement) {
- }
-
-#if[encoder]
-
- private WeakReference cachedDecoder = null;
-
- /**
- * Tells whether or not the given byte array is a legal replacement value
- * for this encoder.
- *
- * A replacement is legal if, and only if, it is a legal sequence of
- * bytes in this encoder's charset; that is, it must be possible to decode
- * the replacement into one or more sixteen-bit Unicode characters.
- *
- *
The default implementation of this method is not very efficient; it
- * should generally be overridden to improve performance.
- *
- * @param repl The byte array to be tested
- *
- * @return true if, and only if, the given byte array
- * is a legal replacement value for this encoder
- */
- public boolean isLegalReplacement(byte[] repl) {
- WeakReference wr = cachedDecoder;
- CharsetDecoder dec = null;
- if ((wr == null) || ((dec = wr.get()) == null)) {
- dec = charset().newDecoder();
- dec.onMalformedInput(CodingErrorAction.REPORT);
- dec.onUnmappableCharacter(CodingErrorAction.REPORT);
- cachedDecoder = new WeakReference(dec);
- } else {
- dec.reset();
- }
- ByteBuffer bb = ByteBuffer.wrap(repl);
- CharBuffer cb = CharBuffer.allocate((int)(bb.remaining()
- * dec.maxCharsPerByte()));
- CoderResult cr = dec.decode(bb, cb, true);
- return !cr.isError();
- }
-
-#end[encoder]
-
- /**
- * Returns this $coder$'s current action for malformed-input errors.
- *
- * @return The current malformed-input action, which is never null
- */
- public CodingErrorAction malformedInputAction() {
- return malformedInputAction;
- }
-
- /**
- * Changes this $coder$'s action for malformed-input errors.
- *
- * This method invokes the {@link #implOnMalformedInput
- * implOnMalformedInput} method, passing the new action.
- *
- * @param newAction The new action; must not be null
- *
- * @return This $coder$
- *
- * @throws IllegalArgumentException
- * If the precondition on the parameter does not hold
- */
- public final Charset$Coder$ onMalformedInput(CodingErrorAction newAction) {
- if (newAction == null)
- throw new IllegalArgumentException("Null action");
- malformedInputAction = newAction;
- implOnMalformedInput(newAction);
- return this;
- }
-
- /**
- * Reports a change to this $coder$'s malformed-input action.
- *
- * The default implementation of this method does nothing. This method
- * should be overridden by $coder$s that require notification of changes to
- * the malformed-input action.
- */
- protected void implOnMalformedInput(CodingErrorAction newAction) { }
-
- /**
- * Returns this $coder$'s current action for unmappable-character errors.
- *
- *
- * @return The current unmappable-character action, which is never
- * null
- */
- public CodingErrorAction unmappableCharacterAction() {
- return unmappableCharacterAction;
- }
-
- /**
- * Changes this $coder$'s action for unmappable-character errors.
- *
- * This method invokes the {@link #implOnUnmappableCharacter
- * implOnUnmappableCharacter} method, passing the new action.
- *
- * @param newAction The new action; must not be null
- *
- * @return This $coder$
- *
- * @throws IllegalArgumentException
- * If the precondition on the parameter does not hold
- */
- public final Charset$Coder$ onUnmappableCharacter(CodingErrorAction
- newAction)
- {
- if (newAction == null)
- throw new IllegalArgumentException("Null action");
- unmappableCharacterAction = newAction;
- implOnUnmappableCharacter(newAction);
- return this;
- }
-
- /**
- * Reports a change to this $coder$'s unmappable-character action.
- *
- * The default implementation of this method does nothing. This method
- * should be overridden by $coder$s that require notification of changes to
- * the unmappable-character action.
- */
- protected void implOnUnmappableCharacter(CodingErrorAction newAction) { }
-
- /**
- * Returns the average number of $otype$s that will be produced for each
- * $itype$ of input. This heuristic value may be used to estimate the size
- * of the output buffer required for a given input sequence.
- *
- * @return The average number of $otype$s produced
- * per $itype$ of input
- */
- public final float average$ItypesPerOtype$() {
- return average$ItypesPerOtype$;
- }
-
- /**
- * Returns the maximum number of $otype$s that will be produced for each
- * $itype$ of input. This value may be used to compute the worst-case size
- * of the output buffer required for a given input sequence.
- *
- * @return The maximum number of $otype$s that will be produced per
- * $itype$ of input
- */
- public final float max$ItypesPerOtype$() {
- return max$ItypesPerOtype$;
- }
-
- /**
- * $Code$s as many $itype$s as possible from the given input buffer,
- * writing the results to the given output buffer.
- *
- * The buffers are read from, and written to, starting at their current
- * positions. At most {@link Buffer#remaining in.remaining()} $itype$s
- * will be read and at most {@link Buffer#remaining out.remaining()}
- * $otype$s will be written. The buffers' positions will be advanced to
- * reflect the $itype$s read and the $otype$s written, but their marks and
- * limits will not be modified.
- *
- *
In addition to reading $itype$s from the input buffer and writing
- * $otype$s to the output buffer, this method returns a {@link CoderResult}
- * object to describe its reason for termination:
- *
- *
- *
- * {@link CoderResult#UNDERFLOW} indicates that as much of the
- * input buffer as possible has been $code$d. If there is no further
- * input then the invoker can proceed to the next step of the
- * $coding$ operation. Otherwise this method
- * should be invoked again with further input.
{@link CoderResult#OVERFLOW} indicates that there is
- * insufficient space in the output buffer to $code$ any more $itype$s.
- * This method should be invoked again with an output buffer that has
- * more {@linkplain Buffer#remaining remaining} $otype$s. This is
- * typically done by draining any $code$d $otype$s from the output
- * buffer.
A {@link CoderResult#malformedForLength
- *
malformed-input} result indicates that a malformed-input
- * error has been detected. The malformed $itype$s begin at the input
- * buffer's (possibly incremented) position; the number of malformed
- * $itype$s may be determined by invoking the result object's {@link
- * CoderResult#length() length} method. This case applies only if the
- * {@link #onMalformedInput malformed action} of this $coder$
- * is {@link CodingErrorAction#REPORT}; otherwise the malformed input
- * will be ignored or replaced, as requested.
- *
- * An {@link CoderResult#unmappableForLength
- *
unmappable-character} result indicates that an
- * unmappable-character error has been detected. The $itype$s that
- * $code$ the unmappable character begin at the input buffer's (possibly
- * incremented) position; the number of such $itype$s may be determined
- * by invoking the result object's {@link CoderResult#length() length}
- * method. This case applies only if the {@link #onUnmappableCharacter
- * unmappable action} of this $coder$ is {@link
- * CodingErrorAction#REPORT}; otherwise the unmappable character will be
- * ignored or replaced, as requested.
- *
- *
- *
- * In any case, if this method is to be reinvoked in the same $coding$
- * operation then care should be taken to preserve any $itype$s remaining
- * in the input buffer so that they are available to the next invocation.
- *
- * The endOfInput parameter advises this method as to whether
- * the invoker can provide further input beyond that contained in the given
- * input buffer. If there is a possibility of providing additional input
- * then the invoker should pass false for this parameter; if there
- * is no possibility of providing further input then the invoker should
- * pass true. It is not erroneous, and in fact it is quite
- * common, to pass false in one invocation and later discover that
- * no further input was actually available. It is critical, however, that
- * the final invocation of this method in a sequence of invocations always
- * pass true so that any remaining un$code$d input will be treated
- * as being malformed.
- *
- *
This method works by invoking the {@link #$code$Loop $code$Loop}
- * method, interpreting its results, handling error conditions, and
- * reinvoking it as necessary.
- *
- *
- * @param in
- * The input $itype$ buffer
- *
- * @param out
- * The output $otype$ buffer
- *
- * @param endOfInput
- * true if, and only if, the invoker can provide no
- * additional input $itype$s beyond those in the given buffer
- *
- * @return A coder-result object describing the reason for termination
- *
- * @throws IllegalStateException
- * If $a$ $coding$ operation is already in progress and the previous
- * step was an invocation neither of the {@link #reset reset}
- * method, nor of this method with a value of false for
- * the endOfInput parameter, nor of this method with a
- * value of true for the endOfInput parameter
- * but a return value indicating an incomplete $coding$ operation
- *
- * @throws CoderMalfunctionError
- * If an invocation of the $code$Loop method threw
- * an unexpected exception
- */
- public final CoderResult $code$($Itype$Buffer in, $Otype$Buffer out,
- boolean endOfInput)
- {
- int newState = endOfInput ? ST_END : ST_CODING;
- if ((state != ST_RESET) && (state != ST_CODING)
- && !(endOfInput && (state == ST_END)))
- throwIllegalStateException(state, newState);
- state = newState;
-
- for (;;) {
-
- CoderResult cr;
- try {
- cr = $code$Loop(in, out);
- } catch (BufferUnderflowException x) {
- throw new CoderMalfunctionError(x);
- } catch (BufferOverflowException x) {
- throw new CoderMalfunctionError(x);
- }
-
- if (cr.isOverflow())
- return cr;
-
- if (cr.isUnderflow()) {
- if (endOfInput && in.hasRemaining()) {
- cr = CoderResult.malformedForLength(in.remaining());
- // Fall through to malformed-input case
- } else {
- return cr;
- }
- }
-
- CodingErrorAction action = null;
- if (cr.isMalformed())
- action = malformedInputAction;
- else if (cr.isUnmappable())
- action = unmappableCharacterAction;
- else
- assert false : cr.toString();
-
- if (action == CodingErrorAction.REPORT)
- return cr;
-
- if (action == CodingErrorAction.REPLACE) {
- if (out.remaining() < replacement.$replLength$)
- return CoderResult.OVERFLOW;
- out.put(replacement);
- }
-
- if ((action == CodingErrorAction.IGNORE)
- || (action == CodingErrorAction.REPLACE)) {
- // Skip erroneous input either way
- in.position(in.position() + cr.length());
- continue;
- }
-
- assert false;
- }
-
- }
-
- /**
- * Flushes this $coder$.
- *
- * Some $coder$s maintain internal state and may need to write some
- * final $otype$s to the output buffer once the overall input sequence has
- * been read.
- *
- *
Any additional output is written to the output buffer beginning at
- * its current position. At most {@link Buffer#remaining out.remaining()}
- * $otype$s will be written. The buffer's position will be advanced
- * appropriately, but its mark and limit will not be modified.
- *
- *
If this method completes successfully then it returns {@link
- * CoderResult#UNDERFLOW}. If there is insufficient room in the output
- * buffer then it returns {@link CoderResult#OVERFLOW}. If this happens
- * then this method must be invoked again, with an output buffer that has
- * more room, in order to complete the current $coding$
- * operation.
- *
- *
If this $coder$ has already been flushed then invoking this method
- * has no effect.
- *
- *
This method invokes the {@link #implFlush implFlush} method to
- * perform the actual flushing operation.
- *
- * @param out
- * The output $otype$ buffer
- *
- * @return A coder-result object, either {@link CoderResult#UNDERFLOW} or
- * {@link CoderResult#OVERFLOW}
- *
- * @throws IllegalStateException
- * If the previous step of the current $coding$ operation was an
- * invocation neither of the {@link #flush flush} method nor of
- * the three-argument {@link
- * #$code$($Itype$Buffer,$Otype$Buffer,boolean) $code$} method
- * with a value of true for the endOfInput
- * parameter
- */
- public final CoderResult flush($Otype$Buffer out) {
- if (state == ST_END) {
- CoderResult cr = implFlush(out);
- if (cr.isUnderflow())
- state = ST_FLUSHED;
- return cr;
- }
-
- if (state != ST_FLUSHED)
- throwIllegalStateException(state, ST_FLUSHED);
-
- return CoderResult.UNDERFLOW; // Already flushed
- }
-
- /**
- * Flushes this $coder$.
- *
- * The default implementation of this method does nothing, and always
- * returns {@link CoderResult#UNDERFLOW}. This method should be overridden
- * by $coder$s that may need to write final $otype$s to the output buffer
- * once the entire input sequence has been read.
- *
- * @param out
- * The output $otype$ buffer
- *
- * @return A coder-result object, either {@link CoderResult#UNDERFLOW} or
- * {@link CoderResult#OVERFLOW}
- */
- protected CoderResult implFlush($Otype$Buffer out) {
- return CoderResult.UNDERFLOW;
- }
-
- /**
- * Resets this $coder$, clearing any internal state.
- *
- * This method resets charset-independent state and also invokes the
- * {@link #implReset() implReset} method in order to perform any
- * charset-specific reset actions.
- *
- * @return This $coder$
- *
- */
- public final Charset$Coder$ reset() {
- implReset();
- state = ST_RESET;
- return this;
- }
-
- /**
- * Resets this $coder$, clearing any charset-specific internal state.
- *
- * The default implementation of this method does nothing. This method
- * should be overridden by $coder$s that maintain internal state.
- */
- protected void implReset() { }
-
- /**
- * $Code$s one or more $itype$s into one or more $otype$s.
- *
- * This method encapsulates the basic $coding$ loop, $coding$ as many
- * $itype$s as possible until it either runs out of input, runs out of room
- * in the output buffer, or encounters $a$ $coding$ error. This method is
- * invoked by the {@link #$code$ $code$} method, which handles result
- * interpretation and error recovery.
- *
- *
The buffers are read from, and written to, starting at their current
- * positions. At most {@link Buffer#remaining in.remaining()} $itype$s
- * will be read, and at most {@link Buffer#remaining out.remaining()}
- * $otype$s will be written. The buffers' positions will be advanced to
- * reflect the $itype$s read and the $otype$s written, but their marks and
- * limits will not be modified.
- *
- *
This method returns a {@link CoderResult} object to describe its
- * reason for termination, in the same manner as the {@link #$code$ $code$}
- * method. Most implementations of this method will handle $coding$ errors
- * by returning an appropriate result object for interpretation by the
- * {@link #$code$ $code$} method. An optimized implementation may instead
- * examine the relevant error action and implement that action itself.
- *
- *
An implementation of this method may perform arbitrary lookahead by
- * returning {@link CoderResult#UNDERFLOW} until it receives sufficient
- * input.
- *
- * @param in
- * The input $itype$ buffer
- *
- * @param out
- * The output $otype$ buffer
- *
- * @return A coder-result object describing the reason for termination
- */
- protected abstract CoderResult $code$Loop($Itype$Buffer in,
- $Otype$Buffer out);
-
- /**
- * Convenience method that $code$s the remaining content of a single input
- * $itype$ buffer into a newly-allocated $otype$ buffer.
- *
- * This method implements an entire $coding$
- * operation; that is, it resets this $coder$, then it $code$s the
- * $itype$s in the given $itype$ buffer, and finally it flushes this
- * $coder$. This method should therefore not be invoked if $a$ $coding$
- * operation is already in progress.
- *
- * @param in
- * The input $itype$ buffer
- *
- * @return A newly-allocated $otype$ buffer containing the result of the
- * $coding$ operation. The buffer's position will be zero and its
- * limit will follow the last $otype$ written.
- *
- * @throws IllegalStateException
- * If $a$ $coding$ operation is already in progress
- *
- * @throws MalformedInputException
- * If the $itype$ sequence starting at the input buffer's current
- * position is $notLegal$ and the current malformed-input action
- * is {@link CodingErrorAction#REPORT}
- *
- * @throws UnmappableCharacterException
- * If the $itype$ sequence starting at the input buffer's current
- * position cannot be mapped to an equivalent $otype$ sequence and
- * the current unmappable-character action is {@link
- * CodingErrorAction#REPORT}
- */
- public final $Otype$Buffer $code$($Itype$Buffer in)
- throws CharacterCodingException
- {
- int n = (int)(in.remaining() * average$ItypesPerOtype$());
- $Otype$Buffer out = $Otype$Buffer.allocate(n);
-
- if ((n == 0) && (in.remaining() == 0))
- return out;
- reset();
- for (;;) {
- CoderResult cr = in.hasRemaining() ?
- $code$(in, out, true) : CoderResult.UNDERFLOW;
- if (cr.isUnderflow())
- cr = flush(out);
-
- if (cr.isUnderflow())
- break;
- if (cr.isOverflow()) {
- n = 2*n + 1; // Ensure progress; n might be 0!
- $Otype$Buffer o = $Otype$Buffer.allocate(n);
- out.flip();
- o.put(out);
- out = o;
- continue;
- }
- cr.throwException();
- }
- out.flip();
- return out;
- }
-
-#if[decoder]
-
- /**
- * Tells whether or not this decoder implements an auto-detecting charset.
- *
- * The default implementation of this method always returns
- * false; it should be overridden by auto-detecting decoders to
- * return true.
- *
- * @return true if, and only if, this decoder implements an
- * auto-detecting charset
- */
- public boolean isAutoDetecting() {
- return false;
- }
-
- /**
- * Tells whether or not this decoder has yet detected a
- * charset (optional operation).
- *
- * If this decoder implements an auto-detecting charset then at a
- * single point during a decoding operation this method may start returning
- * true to indicate that a specific charset has been detected in
- * the input byte sequence. Once this occurs, the {@link #detectedCharset
- * detectedCharset} method may be invoked to retrieve the detected charset.
- *
- *
That this method returns false does not imply that no bytes
- * have yet been decoded. Some auto-detecting decoders are capable of
- * decoding some, or even all, of an input byte sequence without fixing on
- * a particular charset.
- *
- *
The default implementation of this method always throws an {@link
- * UnsupportedOperationException}; it should be overridden by
- * auto-detecting decoders to return true once the input charset
- * has been determined.
- *
- * @return true if, and only if, this decoder has detected a
- * specific charset
- *
- * @throws UnsupportedOperationException
- * If this decoder does not implement an auto-detecting charset
- */
- public boolean isCharsetDetected() {
- throw new UnsupportedOperationException();
- }
-
- /**
- * Retrieves the charset that was detected by this
- * decoder (optional operation).
- *
- * If this decoder implements an auto-detecting charset then this
- * method returns the actual charset once it has been detected. After that
- * point, this method returns the same value for the duration of the
- * current decoding operation. If not enough input bytes have yet been
- * read to determine the actual charset then this method throws an {@link
- * IllegalStateException}.
- *
- *
The default implementation of this method always throws an {@link
- * UnsupportedOperationException}; it should be overridden by
- * auto-detecting decoders to return the appropriate value.
- *
- * @return The charset detected by this auto-detecting decoder,
- * or null if the charset has not yet been determined
- *
- * @throws IllegalStateException
- * If insufficient bytes have been read to determine a charset
- *
- * @throws UnsupportedOperationException
- * If this decoder does not implement an auto-detecting charset
- */
- public Charset detectedCharset() {
- throw new UnsupportedOperationException();
- }
-
-#end[decoder]
-
-#if[encoder]
-
- private boolean canEncode(CharBuffer cb) {
- if (state == ST_FLUSHED)
- reset();
- else if (state != ST_RESET)
- throwIllegalStateException(state, ST_CODING);
- CodingErrorAction ma = malformedInputAction();
- CodingErrorAction ua = unmappableCharacterAction();
- try {
- onMalformedInput(CodingErrorAction.REPORT);
- onUnmappableCharacter(CodingErrorAction.REPORT);
- encode(cb);
- } catch (CharacterCodingException x) {
- return false;
- } finally {
- onMalformedInput(ma);
- onUnmappableCharacter(ua);
- reset();
- }
- return true;
- }
-
- /**
- * Tells whether or not this encoder can encode the given character.
- *
- * This method returns false if the given character is a
- * surrogate character; such characters can be interpreted only when they
- * are members of a pair consisting of a high surrogate followed by a low
- * surrogate. The {@link #canEncode(java.lang.CharSequence)
- * canEncode(CharSequence)} method may be used to test whether or not a
- * character sequence can be encoded.
- *
- *
This method may modify this encoder's state; it should therefore not
- * be invoked if an encoding operation is already in
- * progress.
- *
- *
The default implementation of this method is not very efficient; it
- * should generally be overridden to improve performance.
- *
- * @return true if, and only if, this encoder can encode
- * the given character
- *
- * @throws IllegalStateException
- * If $a$ $coding$ operation is already in progress
- */
- public boolean canEncode(char c) {
- CharBuffer cb = CharBuffer.allocate(1);
- cb.put(c);
- cb.flip();
- return canEncode(cb);
- }
-
- /**
- * Tells whether or not this encoder can encode the given character
- * sequence.
- *
- * If this method returns false for a particular character
- * sequence then more information about why the sequence cannot be encoded
- * may be obtained by performing a full encoding
- * operation.
- *
- *
This method may modify this encoder's state; it should therefore not
- * be invoked if an encoding operation is already in progress.
- *
- *
The default implementation of this method is not very efficient; it
- * should generally be overridden to improve performance.
- *
- * @return true if, and only if, this encoder can encode
- * the given character without throwing any exceptions and without
- * performing any replacements
- *
- * @throws IllegalStateException
- * If $a$ $coding$ operation is already in progress
- */
- public boolean canEncode(CharSequence cs) {
- CharBuffer cb;
- if (cs instanceof CharBuffer)
- cb = ((CharBuffer)cs).duplicate();
- else
- cb = CharBuffer.wrap(cs.toString());
- return canEncode(cb);
- }
-
-#end[encoder]
-
-
- private void throwIllegalStateException(int from, int to) {
- throw new IllegalStateException("Current state = " + stateNames[from]
- + ", new state = " + stateNames[to]);
- }
-
-}