diff options
author | tromey <tromey@138bc75d-0d04-0410-961f-82ee72b054a4> | 2006-01-03 22:58:31 +0000 |
---|---|---|
committer | tromey <tromey@138bc75d-0d04-0410-961f-82ee72b054a4> | 2006-01-03 22:58:31 +0000 |
commit | 8a0383655d7d869ef9d344202c78ce3659927052 (patch) | |
tree | 82dbb00c69057da2d374d746d77eb40854b23164 /libjava/gnu | |
parent | bd63b9439095ee94c8dd44ea2225d9db2a2db2c2 (diff) | |
download | gcc-8a0383655d7d869ef9d344202c78ce3659927052.tar.gz |
PR libgcj/9715, PR libgcj/19132:
* java/nio/charset/Charset.java (charsetForName): Try default
provider first.
(availableCharsets): Re-merged.
(providers2): Likewise.
(defaultCharset): Likewise.
* sources.am, Makefile.in: Rebuilt.
* gnu/java/nio/charset/Provider.java: Removed.
* java/io/OutputStreamWriter.java
(OutputStreamWriter(OutputStream,Charset)): New constructor.
(OutputStreamWriter(OutputStream,CharsetEncoder)): Likewise.
* java/io/InputStreamReader.java
(InputStreamReader(InputStream,CharsetDecoder)): New constructor.
(InputStreamReader(InputStream,Charset)): Likewise.
* gnu/gcj/convert/BytesToUnicode.java (getDecoder): Try a
BytesToCharsetAdaptor.
* gnu/gcj/convert/UnicodeToBytes.java (getEncoder): Try a
CharsetToBytesAdaptor.
* gnu/gcj/convert/CharsetToBytesAdaptor.java: New file.
* gnu/gcj/convert/BytesToCharsetAdaptor.java: New file.
* mauve-libgcj: Remove getEncoding exclusion.
git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@109294 138bc75d-0d04-0410-961f-82ee72b054a4
Diffstat (limited to 'libjava/gnu')
-rw-r--r-- | libjava/gnu/gcj/convert/BytesToCharsetAdaptor.java | 90 | ||||
-rw-r--r-- | libjava/gnu/gcj/convert/BytesToUnicode.java | 15 | ||||
-rw-r--r-- | libjava/gnu/gcj/convert/CharsetToBytesAdaptor.java | 150 | ||||
-rw-r--r-- | libjava/gnu/gcj/convert/UnicodeToBytes.java | 20 | ||||
-rw-r--r-- | libjava/gnu/java/nio/charset/Provider.java | 154 |
5 files changed, 270 insertions, 159 deletions
diff --git a/libjava/gnu/gcj/convert/BytesToCharsetAdaptor.java b/libjava/gnu/gcj/convert/BytesToCharsetAdaptor.java new file mode 100644 index 00000000000..78ba848e118 --- /dev/null +++ b/libjava/gnu/gcj/convert/BytesToCharsetAdaptor.java @@ -0,0 +1,90 @@ +/* Copyright (C) 2005 Free Software Foundation + +This file is part of libgcj. + +This software is copyrighted work licensed under the terms of the +Libgcj License. Please consult the file "LIBGCJ_LICENSE" for +details. */ + +package gnu.gcj.convert; + +import java.nio.ByteBuffer; +import java.nio.CharBuffer; +import java.nio.charset.Charset; +import java.nio.charset.CharsetDecoder; +import java.nio.charset.CodingErrorAction; +import java.nio.charset.CoderResult; +import gnu.java.nio.charset.EncodingHelper; + +/** + * Adaptor class that allow any {@link Charset} to be used + * as a BytesToUnicode converter. + */ +public class BytesToCharsetAdaptor extends BytesToUnicode +{ + /** + * The CharsetDecoder that does all the work. + */ + private final CharsetDecoder decoder; + + /** + * ByteBuffer wrapper for this.buf. + */ + private ByteBuffer inBuf; + + /** + * Create a new BytesToCharsetAdaptor for the given Charset. + * + * @param cs the Charset. + */ + public BytesToCharsetAdaptor(Charset cs) + { + this(cs.newDecoder()); + } + + /** + * Create a new BytesToCharsetAdaptor for the given CharsetDecoder. + * + * @param dec the CharsetDecoder. + */ + public BytesToCharsetAdaptor(CharsetDecoder dec) + { + decoder = dec; + // Use default replacments on bad input so that we don't have to + // deal with errors. + decoder.onMalformedInput(CodingErrorAction.REPLACE); + decoder.onUnmappableCharacter(CodingErrorAction.REPLACE); + } + + /** + * Return the decoder's name. The backing Charset's name is + * returned. + * + * @return The name. + */ + public String getName() + { + return EncodingHelper.getOldCanonical(decoder.charset().name()); + } + + public int read(char[] outbuffer, int outpos, int count) + { + if (inBuf == null || ! inBuf.hasArray() || inBuf.array() != inbuffer) + inBuf = ByteBuffer.wrap(inbuffer); + inBuf.limit(inpos + inlength); + inBuf.position(inpos); + + CharBuffer outBuf = CharBuffer.wrap(outbuffer, outpos, count); + decoder.decode(inBuf, outBuf, false); + + // Update this.inpos to reflect the bytes consumed. + inpos = inBuf.position(); + // Return the number of characters that were written to outbuffer. + return outBuf.position() - outpos; + } + + // These aren't cached. + public void done() + { + } +} diff --git a/libjava/gnu/gcj/convert/BytesToUnicode.java b/libjava/gnu/gcj/convert/BytesToUnicode.java index f33720aa227..e3afe3ee97b 100644 --- a/libjava/gnu/gcj/convert/BytesToUnicode.java +++ b/libjava/gnu/gcj/convert/BytesToUnicode.java @@ -1,4 +1,4 @@ -/* Copyright (C) 1999, 2000, 2001 Free Software Foundation +/* Copyright (C) 1999, 2000, 2001, 2005 Free Software Foundation This file is part of libgcj. @@ -8,6 +8,8 @@ details. */ package gnu.gcj.convert; +import java.nio.charset.Charset; + public abstract class BytesToUnicode extends IOConverter { /** Buffer to read bytes from. @@ -104,11 +106,20 @@ public abstract class BytesToUnicode extends IOConverter try { // We pass the original name to iconv and let it handle - // its own aliasing. + // its own aliasing. Note that we intentionally prefer + // iconv over nio. return new Input_iconv (encoding); } catch (Throwable _) { + // Ignore, and try the next method. + } + try + { + return new BytesToCharsetAdaptor(Charset.forName(encoding)); + } + catch (Throwable _) + { throw new java.io.UnsupportedEncodingException(encoding + " (" + ex + ')'); } diff --git a/libjava/gnu/gcj/convert/CharsetToBytesAdaptor.java b/libjava/gnu/gcj/convert/CharsetToBytesAdaptor.java new file mode 100644 index 00000000000..4e9bcd5b461 --- /dev/null +++ b/libjava/gnu/gcj/convert/CharsetToBytesAdaptor.java @@ -0,0 +1,150 @@ +/* Copyright (C) 2005, 2006 Free Software Foundation + +This file is part of libgcj. + +This software is copyrighted work licensed under the terms of the +Libgcj License. Please consult the file "LIBGCJ_LICENSE" for +details. */ + +package gnu.gcj.convert; + +import java.nio.ByteBuffer; +import java.nio.CharBuffer; +import java.nio.charset.Charset; +import java.nio.charset.CharsetEncoder; +import java.nio.charset.CodingErrorAction; +import java.nio.charset.CoderResult; +import gnu.java.nio.charset.EncodingHelper; + +/** + * Adaptor class that allow any {@link Charset} to be used + * as a UnicodeToBytes converter. + */ +public class CharsetToBytesAdaptor extends UnicodeToBytes +{ + /** + * The CharsetEncoder that does all the work. + */ + private final CharsetEncoder encoder; + + /** + * ByteBuffer wrapper for this.buf. + */ + private ByteBuffer outBuf; + + /** + * True if we've told the CharsetEncoder that there are no more + * characters available. + */ + private boolean closedEncoder; + + /** + * True if we're finished. + */ + private boolean finished; + + /** + * Create a new CharsetToBytesAdaptor for the given Charset. + * + * @param cs The Charset. + */ + public CharsetToBytesAdaptor(Charset cs) + { + this(cs.newEncoder()); + } + + /** + * Create a new CharsetToBytesAdaptor for the given CharsetEncoder. + * + * @param enc The CharsetEncoder. + */ + public CharsetToBytesAdaptor(CharsetEncoder enc) + { + encoder = enc; + // Use default replacments on bad input so that we don't have to + // deal with errors. + encoder.onMalformedInput(CodingErrorAction.REPLACE); + encoder.onUnmappableCharacter(CodingErrorAction.REPLACE); + } + + /** + * Return the encoder's name. The backing Charset's name is + * returned. + * + * @return The name. + */ + public String getName() + { + return EncodingHelper.getOldCanonical(encoder.charset().name()); + } + + public int write (char[] inbuffer, int inpos, int inlength) + { + // Wrap the char array so it can be used by the encoder. + CharBuffer b = CharBuffer.wrap(inbuffer, inpos, inlength); + write(b); + return b.position() - inpos; // Number of chars consumed. + } + + public int write (String str, int inpos, int inlength, char work) + { + // Wrap the String so it can be used by the encoder. + CharBuffer b = CharBuffer.wrap(str, inpos, inlength); + write(b); + return b.position() - inpos; // Number of chars consumed. + } + + /** + * Encode as much of inBuf as will fit in buf. The number of + * chars consumed is reflected by the new position of inBuf. The + * output is put in buf and count is incremented by the number of + * bytes written. + * + * @param inBuf The input. + */ + private void write(CharBuffer inBuf) + { + // Reuse existing outBuf if it is still wrapping the same array + // it was created with. + if (outBuf == null || !outBuf.hasArray() || outBuf.array() != buf) + outBuf = ByteBuffer.wrap(buf); + + // Set the current position. + outBuf.position(count); + + // If we've already said that there is no more input available, + // then we simply try to flush again. + if (closedEncoder) + { + CoderResult result = encoder.flush(outBuf); + if (result == CoderResult.UNDERFLOW) + finished = true; + } + else + { + // Do the conversion. If there are no characters to write, + // then we are finished. + closedEncoder = ! inBuf.hasRemaining(); + encoder.encode(inBuf, outBuf, closedEncoder); + } + + // Mark the new end of buf. + count = outBuf.position(); + } + + /** + * Check for cached output in the converter. + * + * @return true if there is cached output that has not been + * written to buf. + */ + public boolean havePendingBytes() + { + return ! finished; + } + + // These aren't cached. + public void done() + { + } +} diff --git a/libjava/gnu/gcj/convert/UnicodeToBytes.java b/libjava/gnu/gcj/convert/UnicodeToBytes.java index b1432586ce5..8522bec117a 100644 --- a/libjava/gnu/gcj/convert/UnicodeToBytes.java +++ b/libjava/gnu/gcj/convert/UnicodeToBytes.java @@ -1,4 +1,4 @@ -/* Copyright (C) 1999, 2000, 2001, 2003 Free Software Foundation +/* Copyright (C) 1999, 2000, 2001, 2003, 2005 Free Software Foundation This file is part of libgcj. @@ -8,6 +8,8 @@ details. */ package gnu.gcj.convert; +import java.nio.charset.Charset; + public abstract class UnicodeToBytes extends IOConverter { /** Buffer to emit bytes to. @@ -99,10 +101,22 @@ public abstract class UnicodeToBytes extends IOConverter catch (Throwable ex) { try - { + { // We pass the original name to iconv and let it handle - // its own aliasing. + // its own aliasing. Note that we intentionally prefer + // iconv over nio. return new Output_iconv (encoding); + } + catch (Throwable _) + { + // Ignore, and try the next method. + } + try + { + // Try using finding java.nio.charset.Charset and using + // the adaptor. Use the original name as Charsets have + // their own canonical names. + return new CharsetToBytesAdaptor(Charset.forName(encoding)); } catch (Throwable _) { diff --git a/libjava/gnu/java/nio/charset/Provider.java b/libjava/gnu/java/nio/charset/Provider.java deleted file mode 100644 index 586a09e1a1b..00000000000 --- a/libjava/gnu/java/nio/charset/Provider.java +++ /dev/null @@ -1,154 +0,0 @@ -/* Provider.java -- - Copyright (C) 2002, 2005 Free Software Foundation, Inc. - -This file is part of GNU Classpath. - -GNU Classpath is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 2, or (at your option) -any later version. - -GNU Classpath is distributed in the hope that it will be useful, but -WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -General Public License for more details. - -You should have received a copy of the GNU General Public License -along with GNU Classpath; see the file COPYING. If not, write to the -Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA -02110-1301 USA. - -Linking this library statically or dynamically with other modules is -making a combined work based on this library. Thus, the terms and -conditions of the GNU General Public License cover the whole -combination. - -As a special exception, the copyright holders of this library give you -permission to link this library with independent modules to produce an -executable, regardless of the license terms of these independent -modules, and to copy and distribute the resulting executable under -terms of your choice, provided that you also meet, for each linked -independent module, the terms and conditions of the license of that -module. An independent module is a module which is not derived from -or based on this library. If you modify this library, you may extend -this exception to your version of the library, but you are not -obligated to do so. If you do not wish to do so, delete this -exception statement from your version. */ - -package gnu.java.nio.charset; - -import java.nio.charset.Charset; -import java.nio.charset.spi.CharsetProvider; -import java.util.Collections; -import java.util.HashMap; -import java.util.Iterator; - -/** - * Charset provider for the required charsets. Used by - * {@link Charset#charsetForName} and * {@link Charset#availableCharsets}. - * - * @author Jesse Rosenstock - * @author Robert Schuster (thebohemian@gmx.net) - * @see Charset - */ -public final class Provider extends CharsetProvider -{ - private static Provider singleton; - - static - { - synchronized (Provider.class) - { - singleton = null; - } - } - - /** - * Map from charset name to charset canonical name. The strings - * are all lower-case to allow case-insensitive retrieval of - * Charset instances. - */ - private final HashMap canonicalNames; - - /** - * Map from lower-case canonical name to Charset. - * TODO: We may want to use soft references. We would then need to keep - * track of the class name to regenerate the object. - */ - private final HashMap charsets; - - private Provider () - { - canonicalNames = new HashMap (); - charsets = new HashMap (); - - // US-ASCII aka ISO646-US - addCharset (new US_ASCII ()); - - // ISO-8859-1 aka ISO-LATIN-1 - addCharset (new ISO_8859_1 ()); - - // UTF-8 - addCharset (new UTF_8 ()); - - // UTF-16BE - addCharset (new UTF_16BE ()); - - // UTF-16LE - addCharset (new UTF_16LE ()); - - // UTF-16 - addCharset (new UTF_16 ()); - } - - public Iterator charsets () - { - return Collections.unmodifiableCollection (charsets.values ()) - .iterator (); - } - - /** - * Returns a Charset instance by converting the given - * name to lower-case, looking up the canonical charset - * name and finally looking up the Charset with that name. - * - * <p>The lookup is therefore case-insensitive.</p> - * - * @returns The Charset having <code>charsetName</code> - * as its alias or null if no such Charset exist. - */ - public Charset charsetForName (String charsetName) - { - return (Charset) charsets.get(canonicalNames.get(charsetName.toLowerCase())); - } - - /** - * Puts a Charset under its canonical name into the 'charsets' map. - * Then puts a mapping from all its alias names to the canonical name. - * - * <p>All names are converted to lower-case</p>. - * - * @param cs - */ - private void addCharset (Charset cs) - { - String canonicalName = cs.name().toLowerCase(); - charsets.put (canonicalName, cs); - - /* Adds a mapping between the canonical name - * itself making a lookup using that name - * no special case. - */ - canonicalNames.put(canonicalName, canonicalName); - - for (Iterator i = cs.aliases ().iterator (); i.hasNext (); ) - canonicalNames.put (((String) i.next()).toLowerCase(), canonicalName); - } - - public static synchronized Provider provider () - { - if (singleton == null) - singleton = new Provider (); - return singleton; - } -} |