Index: unk/src/org/tukaani/xz/ARMOptions.java =================================================================== --- /trunk/src/org/tukaani/xz/ARMOptions.java (revision 13352) +++ (revision ) @@ -1,37 +1,0 @@ -/* - * ARMOptions - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.io.InputStream; -import org.tukaani.xz.simple.ARM; - -/** - * BCJ filter for little endian ARM instructions. - */ -public class ARMOptions extends BCJOptions { - private static final int ALIGNMENT = 4; - - public ARMOptions() { - super(ALIGNMENT); - } - - public FinishableOutputStream getOutputStream(FinishableOutputStream out, - ArrayCache arrayCache) { - return new SimpleOutputStream(out, new ARM(true, startOffset)); - } - - public InputStream getInputStream(InputStream in, ArrayCache arrayCache) { - return new SimpleInputStream(in, new ARM(false, startOffset)); - } - - FilterEncoder getFilterEncoder() { - return new BCJEncoder(this, BCJCoder.ARM_FILTER_ID); - } -} Index: unk/src/org/tukaani/xz/ARMThumbOptions.java =================================================================== --- /trunk/src/org/tukaani/xz/ARMThumbOptions.java (revision 13352) +++ (revision ) @@ -1,37 +1,0 @@ -/* - * ARMThumbOptions - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.io.InputStream; -import org.tukaani.xz.simple.ARMThumb; - -/** - * BCJ filter for little endian ARM-Thumb instructions. - */ -public class ARMThumbOptions extends BCJOptions { - private static final int ALIGNMENT = 2; - - public ARMThumbOptions() { - super(ALIGNMENT); - } - - public FinishableOutputStream getOutputStream(FinishableOutputStream out, - ArrayCache arrayCache) { - return new SimpleOutputStream(out, new ARMThumb(true, startOffset)); - } - - public InputStream getInputStream(InputStream in, ArrayCache arrayCache) { - return new SimpleInputStream(in, new ARMThumb(false, startOffset)); - } - - FilterEncoder getFilterEncoder() { - return new BCJEncoder(this, BCJCoder.ARMTHUMB_FILTER_ID); - } -} Index: unk/src/org/tukaani/xz/BCJEncoder.java =================================================================== --- /trunk/src/org/tukaani/xz/BCJEncoder.java (revision 13352) +++ (revision ) @@ -1,49 +1,0 @@ -/* - * BCJEncoder - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -class BCJEncoder extends BCJCoder implements FilterEncoder { - private final BCJOptions options; - private final long filterID; - private final byte[] props; - - BCJEncoder(BCJOptions options, long filterID) { - assert isBCJFilterID(filterID); - int startOffset = options.getStartOffset(); - - if (startOffset == 0) { - props = new byte[0]; - } else { - props = new byte[4]; - for (int i = 0; i < 4; ++i) - props[i] = (byte)(startOffset >>> (i * 8)); - } - - this.filterID = filterID; - this.options = (BCJOptions)options.clone(); - } - - public long getFilterID() { - return filterID; - } - - public byte[] getFilterProps() { - return props; - } - - public boolean supportsFlushing() { - return false; - } - - public FinishableOutputStream getOutputStream(FinishableOutputStream out, - ArrayCache arrayCache) { - return options.getOutputStream(out, arrayCache); - } -} Index: unk/src/org/tukaani/xz/BCJOptions.java =================================================================== --- /trunk/src/org/tukaani/xz/BCJOptions.java (revision 13352) +++ (revision ) @@ -1,57 +1,0 @@ -/* - * BCJOptions - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -abstract class BCJOptions extends FilterOptions { - private final int alignment; - int startOffset = 0; - - BCJOptions(int alignment) { - this.alignment = alignment; - } - - /** - * Sets the start offset for the address conversions. - * Normally this is useless so you shouldn't use this function. - * The default value is 0. - */ - public void setStartOffset(int startOffset) - throws UnsupportedOptionsException { - if ((startOffset & (alignment - 1)) != 0) - throw new UnsupportedOptionsException( - "Start offset must be a multiple of " + alignment); - - this.startOffset = startOffset; - } - - /** - * Gets the start offset. - */ - public int getStartOffset() { - return startOffset; - } - - public int getEncoderMemoryUsage() { - return SimpleOutputStream.getMemoryUsage(); - } - - public int getDecoderMemoryUsage() { - return SimpleInputStream.getMemoryUsage(); - } - - public Object clone() { - try { - return super.clone(); - } catch (CloneNotSupportedException e) { - assert false; - throw new RuntimeException(); - } - } -} Index: unk/src/org/tukaani/xz/FinishableWrapperOutputStream.java =================================================================== --- /trunk/src/org/tukaani/xz/FinishableWrapperOutputStream.java (revision 13352) +++ (revision ) @@ -1,70 +1,0 @@ -/* - * FinishableWrapperOutputStream - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.io.OutputStream; -import java.io.IOException; - -/** - * Wraps an output stream to a finishable output stream for use with - * raw encoders. This is not needed for XZ compression and thus most - * people will never need this. - */ -public class FinishableWrapperOutputStream extends FinishableOutputStream { - /** - * The {@link java.io.OutputStream OutputStream} that has been - * wrapped into a FinishableWrapperOutputStream. - */ - protected OutputStream out; - - /** - * Creates a new output stream which support finishing. - * The finish() method will do nothing. - */ - public FinishableWrapperOutputStream(OutputStream out) { - this.out = out; - } - - /** - * Calls {@link java.io.OutputStream#write(int) out.write(b)}. - */ - public void write(int b) throws IOException { - out.write(b); - } - - /** - * Calls {@link java.io.OutputStream#write(byte[]) out.write(buf)}. - */ - public void write(byte[] buf) throws IOException { - out.write(buf); - } - - /** - * Calls {@link java.io.OutputStream#write(byte[],int,int) - out.write(buf, off, len)}. - */ - public void write(byte[] buf, int off, int len) throws IOException { - out.write(buf, off, len); - } - - /** - * Calls {@link java.io.OutputStream#flush() out.flush()}. - */ - public void flush() throws IOException { - out.flush(); - } - - /** - * Calls {@link java.io.OutputStream#close() out.close()}. - */ - public void close() throws IOException { - out.close(); - } -} Index: unk/src/org/tukaani/xz/IA64Options.java =================================================================== --- /trunk/src/org/tukaani/xz/IA64Options.java (revision 13352) +++ (revision ) @@ -1,37 +1,0 @@ -/* - * IA64Options - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.io.InputStream; -import org.tukaani.xz.simple.IA64; - -/** - * BCJ filter for Itanium (IA-64) instructions. - */ -public class IA64Options extends BCJOptions { - private static final int ALIGNMENT = 16; - - public IA64Options() { - super(ALIGNMENT); - } - - public FinishableOutputStream getOutputStream(FinishableOutputStream out, - ArrayCache arrayCache) { - return new SimpleOutputStream(out, new IA64(true, startOffset)); - } - - public InputStream getInputStream(InputStream in, ArrayCache arrayCache) { - return new SimpleInputStream(in, new IA64(false, startOffset)); - } - - FilterEncoder getFilterEncoder() { - return new BCJEncoder(this, BCJCoder.IA64_FILTER_ID); - } -} Index: unk/src/org/tukaani/xz/LZMAInputStream.java =================================================================== --- /trunk/src/org/tukaani/xz/LZMAInputStream.java (revision 13352) +++ (revision ) @@ -1,763 +1,0 @@ -/* - * LZMAInputStream - * - * Authors: Lasse Collin - * Igor Pavlov - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.io.InputStream; -import java.io.DataInputStream; -import java.io.IOException; -import org.tukaani.xz.lz.LZDecoder; -import org.tukaani.xz.rangecoder.RangeDecoderFromStream; -import org.tukaani.xz.lzma.LZMADecoder; - -/** - * Decompresses legacy .lzma files and raw LZMA streams (no .lzma header). - *

- * IMPORTANT: In contrast to other classes in this package, this class - * reads data from its input stream one byte at a time. If the input stream - * is for example {@link java.io.FileInputStream}, wrapping it into - * {@link java.io.BufferedInputStream} tends to improve performance a lot. - * This is not automatically done by this class because there may be use - * cases where it is desired that this class won't read any bytes past - * the end of the LZMA stream. - *

- * Even when using BufferedInputStream, the performance tends - * to be worse (maybe 10-20 % slower) than with {@link LZMA2InputStream} - * or {@link XZInputStream} (when the .xz file contains LZMA2-compressed data). - * - * @since 1.4 - */ -public class LZMAInputStream extends InputStream { - /** - * Largest dictionary size supported by this implementation. - *

- * LZMA allows dictionaries up to one byte less than 4 GiB. This - * implementation supports only 16 bytes less than 2 GiB. This - * limitation is due to Java using signed 32-bit integers for array - * indexing. The limitation shouldn't matter much in practice since so - * huge dictionaries are not normally used. - */ - public static final int DICT_SIZE_MAX = Integer.MAX_VALUE & ~15; - - private InputStream in; - private ArrayCache arrayCache; - private LZDecoder lz; - private RangeDecoderFromStream rc; - private LZMADecoder lzma; - - private boolean endReached = false; - - private final byte[] tempBuf = new byte[1]; - - /** - * Number of uncompressed bytes left to be decompressed, or -1 if - * the end marker is used. - */ - private long remainingSize; - - private IOException exception = null; - - /** - * Gets approximate decompressor memory requirements as kibibytes for - * the given dictionary size and LZMA properties byte (lc, lp, and pb). - * - * @param dictSize LZMA dictionary size as bytes, should be - * in the range [0, - * DICT_SIZE_MAX] - * - * @param propsByte LZMA properties byte that encodes the values - * of lc, lp, and pb - * - * @return approximate memory requirements as kibibytes (KiB) - * - * @throws UnsupportedOptionsException - * if dictSize is outside - * the range [0, - * DICT_SIZE_MAX] - * - * @throws CorruptedInputException - * if propsByte is invalid - */ - public static int getMemoryUsage(int dictSize, byte propsByte) - throws UnsupportedOptionsException, CorruptedInputException { - if (dictSize < 0 || dictSize > DICT_SIZE_MAX) - throw new UnsupportedOptionsException( - "LZMA dictionary is too big for this implementation"); - - int props = propsByte & 0xFF; - if (props > (4 * 5 + 4) * 9 + 8) - throw new CorruptedInputException("Invalid LZMA properties byte"); - - props %= 9 * 5; - int lp = props / 9; - int lc = props - lp * 9; - - return getMemoryUsage(dictSize, lc, lp); - } - - /** - * Gets approximate decompressor memory requirements as kibibytes for - * the given dictionary size, lc, and lp. Note that pb isn't needed. - * - * @param dictSize LZMA dictionary size as bytes, must be - * in the range [0, - * DICT_SIZE_MAX] - * - * @param lc number of literal context bits, must be - * in the range [0, 8] - * - * @param lp number of literal position bits, must be - * in the range [0, 4] - * - * @return approximate memory requirements as kibibytes (KiB) - */ - public static int getMemoryUsage(int dictSize, int lc, int lp) { - if (lc < 0 || lc > 8 || lp < 0 || lp > 4) - throw new IllegalArgumentException("Invalid lc or lp"); - - // Probability variables have the type "short". There are - // 0x300 (768) probability variables in each literal subcoder. - // The number of literal subcoders is 2^(lc + lp). - // - // Roughly 10 KiB for the base state + LZ decoder's dictionary buffer - // + sizeof(short) * number probability variables per literal subcoder - // * number of literal subcoders - return 10 + getDictSize(dictSize) / 1024 - + ((2 * 0x300) << (lc + lp)) / 1024; - } - - private static int getDictSize(int dictSize) { - if (dictSize < 0 || dictSize > DICT_SIZE_MAX) - throw new IllegalArgumentException( - "LZMA dictionary is too big for this implementation"); - - // For performance reasons, use a 4 KiB dictionary if something - // smaller was requested. It's a rare situation and the performance - // difference isn't huge, and it starts to matter mostly when the - // dictionary is just a few bytes. But we need to handle the special - // case of dictSize == 0 anyway, which is an allowed value but in - // practice means one-byte dictionary. - // - // Note that using a dictionary bigger than specified in the headers - // can hide errors if there is a reference to data beyond the original - // dictionary size but is still within 4 KiB. - if (dictSize < 4096) - dictSize = 4096; - - // Round dictionary size upward to a multiple of 16. This way LZMA - // can use LZDecoder.getPos() for calculating LZMA's posMask. - return (dictSize + 15) & ~15; - } - - /** - * Creates a new .lzma file format decompressor without - * a memory usage limit. - * - * @param in input stream from which .lzma data is read; - * it might be a good idea to wrap it in - * BufferedInputStream, see the - * note at the top of this page - * - * @throws CorruptedInputException - * file is corrupt or perhaps not in - * the .lzma format at all - * - * @throws UnsupportedOptionsException - * dictionary size or uncompressed size is too - * big for this implementation - * - * @throws EOFException - * file is truncated or perhaps not in - * the .lzma format at all - * - * @throws IOException may be thrown by in - */ - public LZMAInputStream(InputStream in) throws IOException { - this(in, -1); - } - - /** - * Creates a new .lzma file format decompressor without - * a memory usage limit. - *

- * This is identical to LZMAInputStream(InputStream) - * except that this also takes the arrayCache argument. - * - * @param in input stream from which .lzma data is read; - * it might be a good idea to wrap it in - * BufferedInputStream, see the - * note at the top of this page - * - * - * @param arrayCache cache to be used for allocating large arrays - * - * @throws CorruptedInputException - * file is corrupt or perhaps not in - * the .lzma format at all - * - * @throws UnsupportedOptionsException - * dictionary size or uncompressed size is too - * big for this implementation - * - * @throws EOFException - * file is truncated or perhaps not in - * the .lzma format at all - * - * @throws IOException may be thrown by in - * - * @since 1.7 - */ - public LZMAInputStream(InputStream in, ArrayCache arrayCache) - throws IOException { - this(in, -1, arrayCache); - } - - /** - * Creates a new .lzma file format decompressor with an optional - * memory usage limit. - * - * @param in input stream from which .lzma data is read; - * it might be a good idea to wrap it in - * BufferedInputStream, see the - * note at the top of this page - * - * @param memoryLimit memory usage limit in kibibytes (KiB) - * or -1 to impose no - * memory usage limit - * - * @throws CorruptedInputException - * file is corrupt or perhaps not in - * the .lzma format at all - * - * @throws UnsupportedOptionsException - * dictionary size or uncompressed size is too - * big for this implementation - * - * @throws MemoryLimitException - * memory usage limit was exceeded - * - * @throws EOFException - * file is truncated or perhaps not in - * the .lzma format at all - * - * @throws IOException may be thrown by in - */ - public LZMAInputStream(InputStream in, int memoryLimit) - throws IOException { - this(in, memoryLimit, ArrayCache.getDefaultCache()); - } - - /** - * Creates a new .lzma file format decompressor with an optional - * memory usage limit. - *

- * This is identical to LZMAInputStream(InputStream, int) - * except that this also takes the arrayCache argument. - * - * @param in input stream from which .lzma data is read; - * it might be a good idea to wrap it in - * BufferedInputStream, see the - * note at the top of this page - * - * @param memoryLimit memory usage limit in kibibytes (KiB) - * or -1 to impose no - * memory usage limit - * - * @param arrayCache cache to be used for allocating large arrays - * - * @throws CorruptedInputException - * file is corrupt or perhaps not in - * the .lzma format at all - * - * @throws UnsupportedOptionsException - * dictionary size or uncompressed size is too - * big for this implementation - * - * @throws MemoryLimitException - * memory usage limit was exceeded - * - * @throws EOFException - * file is truncated or perhaps not in - * the .lzma format at all - * - * @throws IOException may be thrown by in - * - * @since 1.7 - */ - public LZMAInputStream(InputStream in, int memoryLimit, - ArrayCache arrayCache) throws IOException { - DataInputStream inData = new DataInputStream(in); - - // Properties byte (lc, lp, and pb) - byte propsByte = inData.readByte(); - - // Dictionary size is an unsigned 32-bit little endian integer. - int dictSize = 0; - for (int i = 0; i < 4; ++i) - dictSize |= inData.readUnsignedByte() << (8 * i); - - // Uncompressed size is an unsigned 64-bit little endian integer. - // The maximum 64-bit value is a special case (becomes -1 here) - // which indicates that the end marker is used instead of knowing - // the uncompressed size beforehand. - long uncompSize = 0; - for (int i = 0; i < 8; ++i) - uncompSize |= (long)inData.readUnsignedByte() << (8 * i); - - // Check the memory usage limit. - int memoryNeeded = getMemoryUsage(dictSize, propsByte); - if (memoryLimit != -1 && memoryNeeded > memoryLimit) - throw new MemoryLimitException(memoryNeeded, memoryLimit); - - initialize(in, uncompSize, propsByte, dictSize, null, arrayCache); - } - - /** - * Creates a new input stream that decompresses raw LZMA data (no .lzma - * header) from in. - *

- * The caller needs to know if the "end of payload marker (EOPM)" alias - * "end of stream marker (EOS marker)" alias "end marker" present. - * If the end marker isn't used, the caller must know the exact - * uncompressed size of the stream. - *

- * The caller also needs to provide the LZMA properties byte that encodes - * the number of literal context bits (lc), literal position bits (lp), - * and position bits (pb). - *

- * The dictionary size used when compressing is also needed. Specifying - * a too small dictionary size will prevent decompressing the stream. - * Specifying a too big dictionary is waste of memory but decompression - * will work. - *

- * There is no need to specify a dictionary bigger than - * the uncompressed size of the data even if a bigger dictionary - * was used when compressing. If you know the uncompressed size - * of the data, this might allow saving some memory. - * - * @param in input stream from which compressed - * data is read - * - * @param uncompSize uncompressed size of the LZMA stream or -1 - * if the end marker is used in the LZMA stream - * - * @param propsByte LZMA properties byte that has the encoded - * values for literal context bits (lc), literal - * position bits (lp), and position bits (pb) - * - * @param dictSize dictionary size as bytes, must be in the range - * [0, DICT_SIZE_MAX] - * - * @throws CorruptedInputException - * if propsByte is invalid or - * the first input byte is not 0x00 - * - * @throws UnsupportedOptionsException - * dictionary size or uncompressed size is too - * big for this implementation - * - * - */ - public LZMAInputStream(InputStream in, long uncompSize, byte propsByte, - int dictSize) throws IOException { - initialize(in, uncompSize, propsByte, dictSize, null, - ArrayCache.getDefaultCache()); - } - - /** - * Creates a new input stream that decompresses raw LZMA data (no .lzma - * header) from in optionally with a preset dictionary. - * - * @param in input stream from which LZMA-compressed - * data is read - * - * @param uncompSize uncompressed size of the LZMA stream or -1 - * if the end marker is used in the LZMA stream - * - * @param propsByte LZMA properties byte that has the encoded - * values for literal context bits (lc), literal - * position bits (lp), and position bits (pb) - * - * @param dictSize dictionary size as bytes, must be in the range - * [0, DICT_SIZE_MAX] - * - * @param presetDict preset dictionary or null - * to use no preset dictionary - * - * @throws CorruptedInputException - * if propsByte is invalid or - * the first input byte is not 0x00 - * - * @throws UnsupportedOptionsException - * dictionary size or uncompressed size is too - * big for this implementation - * - * @throws EOFException file is truncated or corrupt - * - * @throws IOException may be thrown by in - */ - public LZMAInputStream(InputStream in, long uncompSize, byte propsByte, - int dictSize, byte[] presetDict) - throws IOException { - initialize(in, uncompSize, propsByte, dictSize, presetDict, - ArrayCache.getDefaultCache()); - } - - /** - * Creates a new input stream that decompresses raw LZMA data (no .lzma - * header) from in optionally with a preset dictionary. - *

- * This is identical to LZMAInputStream(InputStream, long, byte, int, - * byte[]) except that this also takes the arrayCache - * argument. - * - * @param in input stream from which LZMA-compressed - * data is read - * - * @param uncompSize uncompressed size of the LZMA stream or -1 - * if the end marker is used in the LZMA stream - * - * @param propsByte LZMA properties byte that has the encoded - * values for literal context bits (lc), literal - * position bits (lp), and position bits (pb) - * - * @param dictSize dictionary size as bytes, must be in the range - * [0, DICT_SIZE_MAX] - * - * @param presetDict preset dictionary or null - * to use no preset dictionary - * - * @param arrayCache cache to be used for allocating large arrays - * - * @throws CorruptedInputException - * if propsByte is invalid or - * the first input byte is not 0x00 - * - * @throws UnsupportedOptionsException - * dictionary size or uncompressed size is too - * big for this implementation - * - * @throws EOFException file is truncated or corrupt - * - * @throws IOException may be thrown by in - * - * @since 1.7 - */ - public LZMAInputStream(InputStream in, long uncompSize, byte propsByte, - int dictSize, byte[] presetDict, - ArrayCache arrayCache) - throws IOException { - initialize(in, uncompSize, propsByte, dictSize, presetDict, - arrayCache); - } - - /** - * Creates a new input stream that decompresses raw LZMA data (no .lzma - * header) from in optionally with a preset dictionary. - * - * @param in input stream from which LZMA-compressed - * data is read - * - * @param uncompSize uncompressed size of the LZMA stream or -1 - * if the end marker is used in the LZMA stream - * - * @param lc number of literal context bits, must be - * in the range [0, 8] - * - * @param lp number of literal position bits, must be - * in the range [0, 4] - * - * @param pb number position bits, must be - * in the range [0, 4] - * - * @param dictSize dictionary size as bytes, must be in the range - * [0, DICT_SIZE_MAX] - * - * @param presetDict preset dictionary or null - * to use no preset dictionary - * - * @throws CorruptedInputException - * if the first input byte is not 0x00 - * - * @throws EOFException file is truncated or corrupt - * - * @throws IOException may be thrown by in - */ - public LZMAInputStream(InputStream in, long uncompSize, - int lc, int lp, int pb, - int dictSize, byte[] presetDict) - throws IOException { - initialize(in, uncompSize, lc, lp, pb, dictSize, presetDict, - ArrayCache.getDefaultCache()); - } - - /** - * Creates a new input stream that decompresses raw LZMA data (no .lzma - * header) from in optionally with a preset dictionary. - *

- * This is identical to LZMAInputStream(InputStream, long, int, int, - * int, int, byte[]) except that this also takes the - * arrayCache argument. - * - * @param in input stream from which LZMA-compressed - * data is read - * - * @param uncompSize uncompressed size of the LZMA stream or -1 - * if the end marker is used in the LZMA stream - * - * @param lc number of literal context bits, must be - * in the range [0, 8] - * - * @param lp number of literal position bits, must be - * in the range [0, 4] - * - * @param pb number position bits, must be - * in the range [0, 4] - * - * @param dictSize dictionary size as bytes, must be in the range - * [0, DICT_SIZE_MAX] - * - * @param presetDict preset dictionary or null - * to use no preset dictionary - * - * @param arrayCache cache to be used for allocating large arrays - * - * @throws CorruptedInputException - * if the first input byte is not 0x00 - * - * @throws EOFException file is truncated or corrupt - * - * @throws IOException may be thrown by in - * - * @since 1.7 - */ - public LZMAInputStream(InputStream in, long uncompSize, - int lc, int lp, int pb, - int dictSize, byte[] presetDict, - ArrayCache arrayCache) - throws IOException { - initialize(in, uncompSize, lc, lp, pb, dictSize, presetDict, - arrayCache); - } - - private void initialize(InputStream in, long uncompSize, byte propsByte, - int dictSize, byte[] presetDict, - ArrayCache arrayCache) - throws IOException { - // Validate the uncompressed size since the other "initialize" throws - // IllegalArgumentException if uncompSize < -1. - if (uncompSize < -1) - throw new UnsupportedOptionsException( - "Uncompressed size is too big"); - - // Decode the properties byte. In contrast to LZMA2, there is no - // limit of lc + lp <= 4. - int props = propsByte & 0xFF; - if (props > (4 * 5 + 4) * 9 + 8) - throw new CorruptedInputException("Invalid LZMA properties byte"); - - int pb = props / (9 * 5); - props -= pb * 9 * 5; - int lp = props / 9; - int lc = props - lp * 9; - - // Validate the dictionary size since the other "initialize" throws - // IllegalArgumentException if dictSize is not supported. - if (dictSize < 0 || dictSize > DICT_SIZE_MAX) - throw new UnsupportedOptionsException( - "LZMA dictionary is too big for this implementation"); - - initialize(in, uncompSize, lc, lp, pb, dictSize, presetDict, - arrayCache); - } - - private void initialize(InputStream in, long uncompSize, - int lc, int lp, int pb, - int dictSize, byte[] presetDict, - ArrayCache arrayCache) - throws IOException { - // getDictSize validates dictSize and gives a message in - // the exception too, so skip validating dictSize here. - if (uncompSize < -1 || lc < 0 || lc > 8 || lp < 0 || lp > 4 - || pb < 0 || pb > 4) - throw new IllegalArgumentException(); - - this.in = in; - this.arrayCache = arrayCache; - - // If uncompressed size is known, use it to avoid wasting memory for - // a uselessly large dictionary buffer. - dictSize = getDictSize(dictSize); - if (uncompSize >= 0 && dictSize > uncompSize) - dictSize = getDictSize((int)uncompSize); - - lz = new LZDecoder(getDictSize(dictSize), presetDict, arrayCache); - rc = new RangeDecoderFromStream(in); - lzma = new LZMADecoder(lz, rc, lc, lp, pb); - - remainingSize = uncompSize; - } - - /** - * Decompresses the next byte from this input stream. - *

- * Reading lots of data with read() from this input stream - * may be inefficient. Wrap it in java.io.BufferedInputStream - * if you need to read lots of data one byte at a time. - * - * @return the next decompressed byte, or -1 - * to indicate the end of the compressed stream - * - * @throws CorruptedInputException - * - * @throws XZIOException if the stream has been closed - * - * @throws EOFException - * compressed input is truncated or corrupt - * - * @throws IOException may be thrown by in - */ - public int read() throws IOException { - return read(tempBuf, 0, 1) == -1 ? -1 : (tempBuf[0] & 0xFF); - } - - /** - * Decompresses into an array of bytes. - *

- * If len is zero, no bytes are read and 0 - * is returned. Otherwise this will block until len - * bytes have been decompressed, the end of the LZMA stream is reached, - * or an exception is thrown. - * - * @param buf target buffer for uncompressed data - * @param off start offset in buf - * @param len maximum number of uncompressed bytes to read - * - * @return number of bytes read, or -1 to indicate - * the end of the compressed stream - * - * @throws CorruptedInputException - * - * @throws XZIOException if the stream has been closed - * - * @throws EOFException compressed input is truncated or corrupt - * - * @throws IOException may be thrown by in - */ - public int read(byte[] buf, int off, int len) throws IOException { - if (off < 0 || len < 0 || off + len < 0 || off + len > buf.length) - throw new IndexOutOfBoundsException(); - - if (len == 0) - return 0; - - if (in == null) - throw new XZIOException("Stream closed"); - - if (exception != null) - throw exception; - - if (endReached) - return -1; - - try { - int size = 0; - - while (len > 0) { - // If uncompressed size is known and thus no end marker will - // be present, set the limit so that the uncompressed size - // won't be exceeded. - int copySizeMax = len; - if (remainingSize >= 0 && remainingSize < len) - copySizeMax = (int)remainingSize; - - lz.setLimit(copySizeMax); - - // Decode into the dictionary buffer. - try { - lzma.decode(); - } catch (CorruptedInputException e) { - // The end marker is encoded with a LZMA symbol that - // indicates maximum match distance. This is larger - // than any supported dictionary and thus causes - // CorruptedInputException from LZDecoder.repeat. - if (remainingSize != -1 || !lzma.endMarkerDetected()) - throw e; - - endReached = true; - - // The exception makes lzma.decode() miss the last range - // decoder normalization, so do it here. This might - // cause an IOException if it needs to read a byte - // from the input stream. - rc.normalize(); - } - - // Copy from the dictionary to buf. - int copiedSize = lz.flush(buf, off); - off += copiedSize; - len -= copiedSize; - size += copiedSize; - - if (remainingSize >= 0) { - // Update the number of bytes left to be decompressed. - remainingSize -= copiedSize; - assert remainingSize >= 0; - - if (remainingSize == 0) - endReached = true; - } - - if (endReached) { - // Checking these helps a lot when catching corrupt - // or truncated .lzma files. LZMA Utils doesn't do - // the first check and thus it accepts many invalid - // files that this implementation and XZ Utils don't. - if (!rc.isFinished() || lz.hasPending()) - throw new CorruptedInputException(); - - putArraysToCache(); - return size == 0 ? -1 : size; - } - } - - return size; - - } catch (IOException e) { - exception = e; - throw e; - } - } - - private void putArraysToCache() { - if (lz != null) { - lz.putArraysToCache(arrayCache); - lz = null; - } - } - - /** - * Closes the stream and calls in.close(). - * If the stream was already closed, this does nothing. - * - * @throws IOException if thrown by in.close() - */ - public void close() throws IOException { - if (in != null) { - putArraysToCache(); - - try { - in.close(); - } finally { - in = null; - } - } - } -} Index: unk/src/org/tukaani/xz/LZMAOutputStream.java =================================================================== --- /trunk/src/org/tukaani/xz/LZMAOutputStream.java (revision 13352) +++ (revision ) @@ -1,331 +1,0 @@ -/* - * LZMAOutputStream - * - * Authors: Lasse Collin - * Igor Pavlov - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.io.OutputStream; -import java.io.IOException; -import org.tukaani.xz.lz.LZEncoder; -import org.tukaani.xz.rangecoder.RangeEncoderToStream; -import org.tukaani.xz.lzma.LZMAEncoder; - -/** - * Compresses into the legacy .lzma file format or into a raw LZMA stream. - * - * @since 1.6 - */ -public class LZMAOutputStream extends FinishableOutputStream { - private OutputStream out; - - private final ArrayCache arrayCache; - - private LZEncoder lz; - private final RangeEncoderToStream rc; - private LZMAEncoder lzma; - - private final int props; - private final boolean useEndMarker; - private final long expectedUncompressedSize; - private long currentUncompressedSize = 0; - - private boolean finished = false; - private IOException exception = null; - - private final byte[] tempBuf = new byte[1]; - - private LZMAOutputStream(OutputStream out, LZMA2Options options, - boolean useHeader, boolean useEndMarker, - long expectedUncompressedSize, - ArrayCache arrayCache) - throws IOException { - if (out == null) - throw new NullPointerException(); - - // -1 indicates unknown and >= 0 are for known sizes. - if (expectedUncompressedSize < -1) - throw new IllegalArgumentException( - "Invalid expected input size (less than -1)"); - - this.useEndMarker = useEndMarker; - this.expectedUncompressedSize = expectedUncompressedSize; - - this.arrayCache = arrayCache; - - this.out = out; - rc = new RangeEncoderToStream(out); - - int dictSize = options.getDictSize(); - lzma = LZMAEncoder.getInstance(rc, - options.getLc(), options.getLp(), options.getPb(), - options.getMode(), - dictSize, 0, options.getNiceLen(), - options.getMatchFinder(), options.getDepthLimit(), - arrayCache); - - lz = lzma.getLZEncoder(); - - byte[] presetDict = options.getPresetDict(); - if (presetDict != null && presetDict.length > 0) { - if (useHeader) - throw new UnsupportedOptionsException( - "Preset dictionary cannot be used in .lzma files " - + "(try a raw LZMA stream instead)"); - - lz.setPresetDict(dictSize, presetDict); - } - - props = (options.getPb() * 5 + options.getLp()) * 9 + options.getLc(); - - if (useHeader) { - // Props byte stores lc, lp, and pb. - out.write(props); - - // Dictionary size is stored as a 32-bit unsigned little endian - // integer. - for (int i = 0; i < 4; ++i) { - out.write(dictSize & 0xFF); - dictSize >>>= 8; - } - - // Uncompressed size is stored as a 64-bit unsigned little endian - // integer. The max value (-1 in two's complement) indicates - // unknown size. - for (int i = 0; i < 8; ++i) - out.write((int)(expectedUncompressedSize >>> (8 * i)) & 0xFF); - } - } - - /** - * Creates a new compressor for the legacy .lzma file format. - *

- * If the uncompressed size of the input data is known, it will be stored - * in the .lzma header and no end of stream marker will be used. Otherwise - * the header will indicate unknown uncompressed size and the end of stream - * marker will be used. - *

- * Note that a preset dictionary cannot be used in .lzma files but - * it can be used for raw LZMA streams. - * - * @param out output stream to which the compressed data - * will be written - * - * @param options LZMA compression options; the same class - * is used here as is for LZMA2 - * - * @param inputSize uncompressed size of the data to be compressed; - * use -1 when unknown - * - * @throws IOException may be thrown from out - */ - public LZMAOutputStream(OutputStream out, LZMA2Options options, - long inputSize) - throws IOException { - this(out, options, inputSize, ArrayCache.getDefaultCache()); - } - - /** - * Creates a new compressor for the legacy .lzma file format. - *

- * This is identical to - * LZMAOutputStream(OutputStream, LZMA2Options, long) - * except that this also takes the arrayCache argument. - * - * @param out output stream to which the compressed data - * will be written - * - * @param options LZMA compression options; the same class - * is used here as is for LZMA2 - * - * @param inputSize uncompressed size of the data to be compressed; - * use -1 when unknown - * - * @param arrayCache cache to be used for allocating large arrays - * - * @throws IOException may be thrown from out - * - * @since 1.7 - */ - public LZMAOutputStream(OutputStream out, LZMA2Options options, - long inputSize, ArrayCache arrayCache) - throws IOException { - this(out, options, true, inputSize == -1, inputSize, arrayCache); - } - - /** - * Creates a new compressor for raw LZMA (also known as LZMA1) stream. - *

- * Raw LZMA streams can be encoded with or without end of stream marker. - * When decompressing the stream, one must know if the end marker was used - * and tell it to the decompressor. If the end marker wasn't used, the - * decompressor will also need to know the uncompressed size. - * - * @param out output stream to which the compressed data - * will be written - * - * @param options LZMA compression options; the same class - * is used here as is for LZMA2 - * - * @param useEndMarker - * if end of stream marker should be written - * - * @throws IOException may be thrown from out - */ - public LZMAOutputStream(OutputStream out, LZMA2Options options, - boolean useEndMarker) throws IOException { - this(out, options, useEndMarker, ArrayCache.getDefaultCache()); - } - - /** - * Creates a new compressor for raw LZMA (also known as LZMA1) stream. - *

- * This is identical to - * LZMAOutputStream(OutputStream, LZMA2Options, boolean) - * except that this also takes the arrayCache argument. - * - * @param out output stream to which the compressed data - * will be written - * - * @param options LZMA compression options; the same class - * is used here as is for LZMA2 - * - * @param useEndMarker - * if end of stream marker should be written - * - * @param arrayCache cache to be used for allocating large arrays - * - * @throws IOException may be thrown from out - * - * @since 1.7 - */ - public LZMAOutputStream(OutputStream out, LZMA2Options options, - boolean useEndMarker, ArrayCache arrayCache) - throws IOException { - this(out, options, false, useEndMarker, -1, arrayCache); - } - - /** - * Returns the LZMA lc/lp/pb properties encoded into a single byte. - * This might be useful when handling file formats other than .lzma - * that use the same encoding for the LZMA properties as .lzma does. - */ - public int getProps() { - return props; - } - - /** - * Gets the amount of uncompressed data written to the stream. - * This is useful when creating raw LZMA streams without - * the end of stream marker. - */ - public long getUncompressedSize() { - return currentUncompressedSize; - } - - public void write(int b) throws IOException { - tempBuf[0] = (byte)b; - write(tempBuf, 0, 1); - } - - public void write(byte[] buf, int off, int len) throws IOException { - if (off < 0 || len < 0 || off + len < 0 || off + len > buf.length) - throw new IndexOutOfBoundsException(); - - if (exception != null) - throw exception; - - if (finished) - throw new XZIOException("Stream finished or closed"); - - if (expectedUncompressedSize != -1 - && expectedUncompressedSize - currentUncompressedSize < len) - throw new XZIOException("Expected uncompressed input size (" - + expectedUncompressedSize + " bytes) was exceeded"); - - currentUncompressedSize += len; - - try { - while (len > 0) { - int used = lz.fillWindow(buf, off, len); - off += used; - len -= used; - lzma.encodeForLZMA1(); - } - } catch (IOException e) { - exception = e; - throw e; - } - } - - /** - * Flushing isn't supported and will throw XZIOException. - */ - public void flush() throws IOException { - throw new XZIOException("LZMAOutputStream does not support flushing"); - } - - /** - * Finishes the stream without closing the underlying OutputStream. - */ - public void finish() throws IOException { - if (!finished) { - if (exception != null) - throw exception; - - try { - if (expectedUncompressedSize != -1 - && expectedUncompressedSize != currentUncompressedSize) - throw new XZIOException("Expected uncompressed size (" - + expectedUncompressedSize + ") doesn't equal " - + "the number of bytes written to the stream (" - + currentUncompressedSize + ")"); - - lz.setFinishing(); - lzma.encodeForLZMA1(); - - if (useEndMarker) - lzma.encodeLZMA1EndMarker(); - - rc.finish(); - } catch (IOException e) { - exception = e; - throw e; - } - - finished = true; - - lzma.putArraysToCache(arrayCache); - lzma = null; - lz = null; - } - } - - /** - * Finishes the stream and closes the underlying OutputStream. - */ - public void close() throws IOException { - if (out != null) { - try { - finish(); - } catch (IOException e) {} - - try { - out.close(); - } catch (IOException e) { - if (exception == null) - exception = e; - } - - out = null; - } - - if (exception != null) - throw exception; - } -} Index: unk/src/org/tukaani/xz/PowerPCOptions.java =================================================================== --- /trunk/src/org/tukaani/xz/PowerPCOptions.java (revision 13352) +++ (revision ) @@ -1,37 +1,0 @@ -/* - * PowerPCOptions - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.io.InputStream; -import org.tukaani.xz.simple.PowerPC; - -/** - * BCJ filter for big endian PowerPC instructions. - */ -public class PowerPCOptions extends BCJOptions { - private static final int ALIGNMENT = 4; - - public PowerPCOptions() { - super(ALIGNMENT); - } - - public FinishableOutputStream getOutputStream(FinishableOutputStream out, - ArrayCache arrayCache) { - return new SimpleOutputStream(out, new PowerPC(true, startOffset)); - } - - public InputStream getInputStream(InputStream in, ArrayCache arrayCache) { - return new SimpleInputStream(in, new PowerPC(false, startOffset)); - } - - FilterEncoder getFilterEncoder() { - return new BCJEncoder(this, BCJCoder.POWERPC_FILTER_ID); - } -} Index: unk/src/org/tukaani/xz/ResettableArrayCache.java =================================================================== --- /trunk/src/org/tukaani/xz/ResettableArrayCache.java (revision 13352) +++ (revision ) @@ -1,120 +1,0 @@ -/* - * ResettableArrayCache - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.util.ArrayList; -import java.util.List; - -/** - * An ArrayCache wrapper that remembers what has been allocated - * and allows returning all allocations to the underlying cache at once. - * - * @since 1.7 - */ -public class ResettableArrayCache extends ArrayCache { - private final ArrayCache arrayCache; - - // Lists of arrays that have been allocated from the arrayCache. - private final List byteArrays; - private final List intArrays; - - /** - * Creates a new ResettableArrayCache based on the given ArrayCache. - */ - public ResettableArrayCache(ArrayCache arrayCache) { - this.arrayCache = arrayCache; - - // Treat the dummy cache as a special case since it's a common case. - // With it we don't need to put the arrays back to the cache and - // thus we don't need to remember what has been allocated. - if (arrayCache == ArrayCache.getDummyCache()) { - byteArrays = null; - intArrays = null; - } else { - byteArrays = new ArrayList(); - intArrays = new ArrayList(); - } - } - - public byte[] getByteArray(int size, boolean fillWithZeros) { - byte[] array = arrayCache.getByteArray(size, fillWithZeros); - - if (byteArrays != null) { - synchronized(byteArrays) { - byteArrays.add(array); - } - } - - return array; - } - - public void putArray(byte[] array) { - if (byteArrays != null) { - // The array is more likely to be near the end of the list so - // start the search from the end. - synchronized(byteArrays) { - int i = byteArrays.lastIndexOf(array); - if (i != -1) - byteArrays.remove(i); - } - - arrayCache.putArray(array); - } - } - - public int[] getIntArray(int size, boolean fillWithZeros) { - int[] array = arrayCache.getIntArray(size, fillWithZeros); - - if (intArrays != null) { - synchronized(intArrays) { - intArrays.add(array); - } - } - - return array; - } - - public void putArray(int[] array) { - if (intArrays != null) { - synchronized(intArrays) { - int i = intArrays.lastIndexOf(array); - if (i != -1) - intArrays.remove(i); - } - - arrayCache.putArray(array); - } - } - - /** - * Puts all allocated arrays back to the underlying ArrayCache - * that haven't already been put there with a call to - * {@code putArray}. - */ - public void reset() { - if (byteArrays != null) { - // Put the arrays to the cache in reverse order: the array that - // was allocated first is returned last. - synchronized(byteArrays) { - for (int i = byteArrays.size() - 1; i >= 0; --i) - arrayCache.putArray(byteArrays.get(i)); - - byteArrays.clear(); - } - - synchronized(intArrays) { - for (int i = intArrays.size() - 1; i >= 0; --i) - arrayCache.putArray(intArrays.get(i)); - - intArrays.clear(); - } - } - } -} Index: unk/src/org/tukaani/xz/SPARCOptions.java =================================================================== --- /trunk/src/org/tukaani/xz/SPARCOptions.java (revision 13352) +++ (revision ) @@ -1,37 +1,0 @@ -/* - * SPARCOptions - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.io.InputStream; -import org.tukaani.xz.simple.SPARC; - -/** - * BCJ filter for SPARC. - */ -public class SPARCOptions extends BCJOptions { - private static final int ALIGNMENT = 4; - - public SPARCOptions() { - super(ALIGNMENT); - } - - public FinishableOutputStream getOutputStream(FinishableOutputStream out, - ArrayCache arrayCache) { - return new SimpleOutputStream(out, new SPARC(true, startOffset)); - } - - public InputStream getInputStream(InputStream in, ArrayCache arrayCache) { - return new SimpleInputStream(in, new SPARC(false, startOffset)); - } - - FilterEncoder getFilterEncoder() { - return new BCJEncoder(this, BCJCoder.SPARC_FILTER_ID); - } -} Index: unk/src/org/tukaani/xz/SeekableFileInputStream.java =================================================================== --- /trunk/src/org/tukaani/xz/SeekableFileInputStream.java (revision 13352) +++ (revision ) @@ -1,102 +1,0 @@ -/* - * SeekableFileInputStream - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.io.File; -import java.io.RandomAccessFile; -import java.io.IOException; -import java.io.FileNotFoundException; - -/** - * Wraps a {@link java.io.RandomAccessFile RandomAccessFile} - * in a SeekableInputStream. - */ -public class SeekableFileInputStream extends SeekableInputStream { - /** - * The RandomAccessFile that has been wrapped - * into a SeekableFileInputStream. - */ - protected RandomAccessFile randomAccessFile; - - /** - * Creates a new seekable input stream that reads from the specified file. - */ - public SeekableFileInputStream(File file) throws FileNotFoundException { - randomAccessFile = new RandomAccessFile(file, "r"); - } - - /** - * Creates a new seekable input stream that reads from a file with - * the specified name. - */ - public SeekableFileInputStream(String name) throws FileNotFoundException { - randomAccessFile = new RandomAccessFile(name, "r"); - } - - /** - * Creates a new seekable input stream from an existing - * RandomAccessFile object. - */ - public SeekableFileInputStream(RandomAccessFile randomAccessFile) { - this.randomAccessFile = randomAccessFile; - } - - /** - * Calls {@link RandomAccessFile#read() randomAccessFile.read()}. - */ - public int read() throws IOException { - return randomAccessFile.read(); - } - - /** - * Calls {@link RandomAccessFile#read(byte[]) randomAccessFile.read(buf)}. - */ - public int read(byte[] buf) throws IOException { - return randomAccessFile.read(buf); - } - - /** - * Calls - * {@link RandomAccessFile#read(byte[],int,int) - * randomAccessFile.read(buf, off, len)}. - */ - public int read(byte[] buf, int off, int len) throws IOException { - return randomAccessFile.read(buf, off, len); - } - - /** - * Calls {@link RandomAccessFile#close() randomAccessFile.close()}. - */ - public void close() throws IOException { - randomAccessFile.close(); - } - - /** - * Calls {@link RandomAccessFile#length() randomAccessFile.length()}. - */ - public long length() throws IOException { - return randomAccessFile.length(); - } - - /** - * Calls {@link RandomAccessFile#getFilePointer() - randomAccessFile.getFilePointer()}. - */ - public long position() throws IOException { - return randomAccessFile.getFilePointer(); - } - - /** - * Calls {@link RandomAccessFile#seek(long) randomAccessFile.seek(long)}. - */ - public void seek(long pos) throws IOException { - randomAccessFile.seek(pos); - } -} Index: unk/src/org/tukaani/xz/SeekableXZInputStream.java =================================================================== --- /trunk/src/org/tukaani/xz/SeekableXZInputStream.java (revision 13352) +++ (revision ) @@ -1,1152 +1,0 @@ -/* - * SeekableXZInputStream - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.util.Arrays; -import java.util.ArrayList; -import java.io.DataInputStream; -import java.io.IOException; -import java.io.EOFException; -import org.tukaani.xz.common.DecoderUtil; -import org.tukaani.xz.common.StreamFlags; -import org.tukaani.xz.check.Check; -import org.tukaani.xz.index.IndexDecoder; -import org.tukaani.xz.index.BlockInfo; - -/** - * Decompresses a .xz file in random access mode. - * This supports decompressing concatenated .xz files. - *

- * Each .xz file consist of one or more Streams. Each Stream consist of zero - * or more Blocks. Each Stream contains an Index of Streams' Blocks. - * The Indexes from all Streams are loaded in RAM by a constructor of this - * class. A typical .xz file has only one Stream, and parsing its Index will - * need only three or four seeks. - *

- * To make random access possible, the data in a .xz file must be splitted - * into multiple Blocks of reasonable size. Decompression can only start at - * a Block boundary. When seeking to an uncompressed position that is not at - * a Block boundary, decompression starts at the beginning of the Block and - * throws away data until the target position is reached. Thus, smaller Blocks - * mean faster seeks to arbitrary uncompressed positions. On the other hand, - * smaller Blocks mean worse compression. So one has to make a compromise - * between random access speed and compression ratio. - *

- * Implementation note: This class uses linear search to locate the correct - * Stream from the data structures in RAM. It was the simplest to implement - * and should be fine as long as there aren't too many Streams. The correct - * Block inside a Stream is located using binary search and thus is fast - * even with a huge number of Blocks. - * - *

Memory usage

- *

- * The amount of memory needed for the Indexes is taken into account when - * checking the memory usage limit. Each Stream is calculated to need at - * least 1 KiB of memory and each Block 16 bytes of memory, rounded up - * to the next kibibyte. So unless the file has a huge number of Streams or - * Blocks, these don't take significant amount of memory. - * - *

Creating random-accessible .xz files

- *

- * When using {@link XZOutputStream}, a new Block can be started by calling - * its {@link XZOutputStream#endBlock() endBlock} method. If you know - * that the decompressor will only need to seek to certain uncompressed - * positions, it can be a good idea to start a new Block at (some of) these - * positions (and only at these positions to get better compression ratio). - *

- * liblzma in XZ Utils supports starting a new Block with - * LZMA_FULL_FLUSH. XZ Utils 5.1.1alpha added threaded - * compression which creates multi-Block .xz files. XZ Utils 5.1.1alpha - * also added the option --block-size=SIZE to the xz command - * line tool. XZ Utils 5.1.2alpha added a partial implementation of - * --block-list=SIZES which allows specifying sizes of - * individual Blocks. - * - * @see SeekableFileInputStream - * @see XZInputStream - * @see XZOutputStream - */ -public class SeekableXZInputStream extends SeekableInputStream { - /** - * Cache for big arrays. - */ - private final ArrayCache arrayCache; - - /** - * The input stream containing XZ compressed data. - */ - private SeekableInputStream in; - - /** - * Memory usage limit after the memory usage of the IndexDecoders have - * been substracted. - */ - private final int memoryLimit; - - /** - * Memory usage of the IndexDecoders. - * memoryLimit + indexMemoryUsage equals the original - * memory usage limit that was passed to the constructor. - */ - private int indexMemoryUsage = 0; - - /** - * List of IndexDecoders, one for each Stream in the file. - * The list is in reverse order: The first element is - * the last Stream in the file. - */ - private final ArrayList streams - = new ArrayList(); - - /** - * Bitmask of all Check IDs seen. - */ - private int checkTypes = 0; - - /** - * Uncompressed size of the file (all Streams). - */ - private long uncompressedSize = 0; - - /** - * Uncompressed size of the largest XZ Block in the file. - */ - private long largestBlockSize = 0; - - /** - * Number of XZ Blocks in the file. - */ - private int blockCount = 0; - - /** - * Size and position information about the current Block. - * If there are no Blocks, all values will be -1. - */ - private final BlockInfo curBlockInfo; - - /** - * Temporary (and cached) information about the Block whose information - * is queried via getBlockPos and related functions. - */ - private final BlockInfo queriedBlockInfo; - - /** - * Integrity Check in the current XZ Stream. The constructor leaves - * this to point to the Check of the first Stream. - */ - private Check check; - - /** - * Flag indicating if the integrity checks will be verified. - */ - private final boolean verifyCheck; - - /** - * Decoder of the current XZ Block, if any. - */ - private BlockInputStream blockDecoder = null; - - /** - * Current uncompressed position. - */ - private long curPos = 0; - - /** - * Target position for seeking. - */ - private long seekPos; - - /** - * True when seek(long) has been called but the actual - * seeking hasn't been done yet. - */ - private boolean seekNeeded = false; - - /** - * True when end of the file was reached. This can be cleared by - * calling seek(long). - */ - private boolean endReached = false; - - /** - * Pending exception from an earlier error. - */ - private IOException exception = null; - - /** - * Temporary buffer for read(). This avoids reallocating memory - * on every read() call. - */ - private final byte[] tempBuf = new byte[1]; - - /** - * Creates a new seekable XZ decompressor without a memory usage limit. - * - * @param in seekable input stream containing one or more - * XZ Streams; the whole input stream is used - * - * @throws XZFormatException - * input is not in the XZ format - * - * @throws CorruptedInputException - * XZ data is corrupt or truncated - * - * @throws UnsupportedOptionsException - * XZ headers seem valid but they specify - * options not supported by this implementation - * - * @throws EOFException - * less than 6 bytes of input was available - * from in, or (unlikely) the size - * of the underlying stream got smaller while - * this was reading from it - * - * @throws IOException may be thrown by in - */ - public SeekableXZInputStream(SeekableInputStream in) - throws IOException { - this(in, -1); - } - - /** - * Creates a new seekable XZ decompressor without a memory usage limit. - *

- * This is identical to - * SeekableXZInputStream(SeekableInputStream) except that - * this also takes the arrayCache argument. - * - * @param in seekable input stream containing one or more - * XZ Streams; the whole input stream is used - * - * @param arrayCache cache to be used for allocating large arrays - * - * @throws XZFormatException - * input is not in the XZ format - * - * @throws CorruptedInputException - * XZ data is corrupt or truncated - * - * @throws UnsupportedOptionsException - * XZ headers seem valid but they specify - * options not supported by this implementation - * - * @throws EOFException - * less than 6 bytes of input was available - * from in, or (unlikely) the size - * of the underlying stream got smaller while - * this was reading from it - * - * @throws IOException may be thrown by in - * - * @since 1.7 - */ - public SeekableXZInputStream(SeekableInputStream in, ArrayCache arrayCache) - throws IOException { - this(in, -1, arrayCache); - } - - /** - * Creates a new seekable XZ decomporessor with an optional - * memory usage limit. - * - * @param in seekable input stream containing one or more - * XZ Streams; the whole input stream is used - * - * @param memoryLimit memory usage limit in kibibytes (KiB) - * or -1 to impose no - * memory usage limit - * - * @throws XZFormatException - * input is not in the XZ format - * - * @throws CorruptedInputException - * XZ data is corrupt or truncated - * - * @throws UnsupportedOptionsException - * XZ headers seem valid but they specify - * options not supported by this implementation - * - * @throws MemoryLimitException - * decoded XZ Indexes would need more memory - * than allowed by the memory usage limit - * - * @throws EOFException - * less than 6 bytes of input was available - * from in, or (unlikely) the size - * of the underlying stream got smaller while - * this was reading from it - * - * @throws IOException may be thrown by in - */ - public SeekableXZInputStream(SeekableInputStream in, int memoryLimit) - throws IOException { - this(in, memoryLimit, true); - } - - /** - * Creates a new seekable XZ decomporessor with an optional - * memory usage limit. - *

- * This is identical to - * SeekableXZInputStream(SeekableInputStream,int) - * except that this also takes the arrayCache argument. - * - * @param in seekable input stream containing one or more - * XZ Streams; the whole input stream is used - * - * @param memoryLimit memory usage limit in kibibytes (KiB) - * or -1 to impose no - * memory usage limit - * - * @param arrayCache cache to be used for allocating large arrays - * - * @throws XZFormatException - * input is not in the XZ format - * - * @throws CorruptedInputException - * XZ data is corrupt or truncated - * - * @throws UnsupportedOptionsException - * XZ headers seem valid but they specify - * options not supported by this implementation - * - * @throws MemoryLimitException - * decoded XZ Indexes would need more memory - * than allowed by the memory usage limit - * - * @throws EOFException - * less than 6 bytes of input was available - * from in, or (unlikely) the size - * of the underlying stream got smaller while - * this was reading from it - * - * @throws IOException may be thrown by in - * - * @since 1.7 - */ - public SeekableXZInputStream(SeekableInputStream in, int memoryLimit, - ArrayCache arrayCache) - throws IOException { - this(in, memoryLimit, true, arrayCache); - } - - /** - * Creates a new seekable XZ decomporessor with an optional - * memory usage limit and ability to disable verification - * of integrity checks. - *

- * Note that integrity check verification should almost never be disabled. - * Possible reasons to disable integrity check verification: - *

    - *
  • Trying to recover data from a corrupt .xz file.
    • - *
  • Speeding up decompression. This matters mostly with SHA-256 - * or with files that have compressed extremely well. It's recommended - * that integrity checking isn't disabled for performance reasons - * unless the file integrity is verified externally in some other - * way.
    • - *
- *

- * verifyCheck only affects the integrity check of - * the actual compressed data. The CRC32 fields in the headers - * are always verified. - * - * @param in seekable input stream containing one or more - * XZ Streams; the whole input stream is used - * - * @param memoryLimit memory usage limit in kibibytes (KiB) - * or -1 to impose no - * memory usage limit - * - * @param verifyCheck if true, the integrity checks - * will be verified; this should almost never - * be set to false - * - * @throws XZFormatException - * input is not in the XZ format - * - * @throws CorruptedInputException - * XZ data is corrupt or truncated - * - * @throws UnsupportedOptionsException - * XZ headers seem valid but they specify - * options not supported by this implementation - * - * @throws MemoryLimitException - * decoded XZ Indexes would need more memory - * than allowed by the memory usage limit - * - * @throws EOFException - * less than 6 bytes of input was available - * from in, or (unlikely) the size - * of the underlying stream got smaller while - * this was reading from it - * - * @throws IOException may be thrown by in - * - * @since 1.6 - */ - public SeekableXZInputStream(SeekableInputStream in, int memoryLimit, - boolean verifyCheck) - throws IOException { - this(in, memoryLimit, verifyCheck, ArrayCache.getDefaultCache()); - } - - /** - * Creates a new seekable XZ decomporessor with an optional - * memory usage limit and ability to disable verification - * of integrity checks. - *

- * This is identical to - * SeekableXZInputStream(SeekableInputStream,int,boolean) - * except that this also takes the arrayCache argument. - * - * @param in seekable input stream containing one or more - * XZ Streams; the whole input stream is used - * - * @param memoryLimit memory usage limit in kibibytes (KiB) - * or -1 to impose no - * memory usage limit - * - * @param verifyCheck if true, the integrity checks - * will be verified; this should almost never - * be set to false - * - * @param arrayCache cache to be used for allocating large arrays - * - * @throws XZFormatException - * input is not in the XZ format - * - * @throws CorruptedInputException - * XZ data is corrupt or truncated - * - * @throws UnsupportedOptionsException - * XZ headers seem valid but they specify - * options not supported by this implementation - * - * @throws MemoryLimitException - * decoded XZ Indexes would need more memory - * than allowed by the memory usage limit - * - * @throws EOFException - * less than 6 bytes of input was available - * from in, or (unlikely) the size - * of the underlying stream got smaller while - * this was reading from it - * - * @throws IOException may be thrown by in - * - * @since 1.7 - */ - public SeekableXZInputStream(SeekableInputStream in, int memoryLimit, - boolean verifyCheck, ArrayCache arrayCache) - throws IOException { - this.arrayCache = arrayCache; - this.verifyCheck = verifyCheck; - this.in = in; - DataInputStream inData = new DataInputStream(in); - - // Check the magic bytes in the beginning of the file. - { - in.seek(0); - byte[] buf = new byte[XZ.HEADER_MAGIC.length]; - inData.readFully(buf); - if (!Arrays.equals(buf, XZ.HEADER_MAGIC)) - throw new XZFormatException(); - } - - // Get the file size and verify that it is a multiple of 4 bytes. - long pos = in.length(); - if ((pos & 3) != 0) - throw new CorruptedInputException( - "XZ file size is not a multiple of 4 bytes"); - - // Parse the headers starting from the end of the file. - byte[] buf = new byte[DecoderUtil.STREAM_HEADER_SIZE]; - long streamPadding = 0; - - while (pos > 0) { - if (pos < DecoderUtil.STREAM_HEADER_SIZE) - throw new CorruptedInputException(); - - // Read the potential Stream Footer. - in.seek(pos - DecoderUtil.STREAM_HEADER_SIZE); - inData.readFully(buf); - - // Skip Stream Padding four bytes at a time. - // Skipping more at once would be faster, - // but usually there isn't much Stream Padding. - if (buf[8] == 0x00 && buf[9] == 0x00 && buf[10] == 0x00 - && buf[11] == 0x00) { - streamPadding += 4; - pos -= 4; - continue; - } - - // It's not Stream Padding. Update pos. - pos -= DecoderUtil.STREAM_HEADER_SIZE; - - // Decode the Stream Footer and check if Backward Size - // looks reasonable. - StreamFlags streamFooter = DecoderUtil.decodeStreamFooter(buf); - if (streamFooter.backwardSize >= pos) - throw new CorruptedInputException( - "Backward Size in XZ Stream Footer is too big"); - - // Check that the Check ID is supported. Store it in case this - // is the first Stream in the file. - check = Check.getInstance(streamFooter.checkType); - - // Remember which Check IDs have been seen. - checkTypes |= 1 << streamFooter.checkType; - - // Seek to the beginning of the Index. - in.seek(pos - streamFooter.backwardSize); - - // Decode the Index field. - IndexDecoder index; - try { - index = new IndexDecoder(in, streamFooter, streamPadding, - memoryLimit); - } catch (MemoryLimitException e) { - // IndexDecoder doesn't know how much memory we had - // already needed so we need to recreate the exception. - assert memoryLimit >= 0; - throw new MemoryLimitException( - e.getMemoryNeeded() + indexMemoryUsage, - memoryLimit + indexMemoryUsage); - } - - // Update the memory usage and limit counters. - indexMemoryUsage += index.getMemoryUsage(); - if (memoryLimit >= 0) { - memoryLimit -= index.getMemoryUsage(); - assert memoryLimit >= 0; - } - - // Remember the uncompressed size of the largest Block. - if (largestBlockSize < index.getLargestBlockSize()) - largestBlockSize = index.getLargestBlockSize(); - - // Calculate the offset to the beginning of this XZ Stream and - // check that it looks sane. - long off = index.getStreamSize() - DecoderUtil.STREAM_HEADER_SIZE; - if (pos < off) - throw new CorruptedInputException("XZ Index indicates " - + "too big compressed size for the XZ Stream"); - - // Seek to the beginning of this Stream. - pos -= off; - in.seek(pos); - - // Decode the Stream Header. - inData.readFully(buf); - StreamFlags streamHeader = DecoderUtil.decodeStreamHeader(buf); - - // Verify that the Stream Header matches the Stream Footer. - if (!DecoderUtil.areStreamFlagsEqual(streamHeader, streamFooter)) - throw new CorruptedInputException( - "XZ Stream Footer does not match Stream Header"); - - // Update the total uncompressed size of the file and check that - // it doesn't overflow. - uncompressedSize += index.getUncompressedSize(); - if (uncompressedSize < 0) - throw new UnsupportedOptionsException("XZ file is too big"); - - // Update the Block count and check that it fits into an int. - blockCount += index.getRecordCount(); - if (blockCount < 0) - throw new UnsupportedOptionsException( - "XZ file has over " + Integer.MAX_VALUE + " Blocks"); - - // Add this Stream to the list of Streams. - streams.add(index); - - // Reset to be ready to parse the next Stream. - streamPadding = 0; - } - - assert pos == 0; - - // Save it now that indexMemoryUsage has been substracted from it. - this.memoryLimit = memoryLimit; - - // Store the relative offsets of the Streams. This way we don't - // need to recalculate them in this class when seeking; the - // IndexDecoder instances will handle them. - IndexDecoder prev = streams.get(streams.size() - 1); - for (int i = streams.size() - 2; i >= 0; --i) { - IndexDecoder cur = streams.get(i); - cur.setOffsets(prev); - prev = cur; - } - - // Initialize curBlockInfo to point to the first Stream. - // The blockNumber will be left to -1 so that .hasNext() - // and .setNext() work to get the first Block when starting - // to decompress from the beginning of the file. - IndexDecoder first = streams.get(streams.size() - 1); - curBlockInfo = new BlockInfo(first); - - // queriedBlockInfo needs to be allocated too. The Stream used for - // initialization doesn't matter though. - queriedBlockInfo = new BlockInfo(first); - } - - /** - * Gets the types of integrity checks used in the .xz file. - * Multiple checks are possible only if there are multiple - * concatenated XZ Streams. - *

- * The returned value has a bit set for every check type that is present. - * For example, if CRC64 and SHA-256 were used, the return value is - * (1 << XZ.CHECK_CRC64) - * | (1 << XZ.CHECK_SHA256). - */ - public int getCheckTypes() { - return checkTypes; - } - - /** - * Gets the amount of memory in kibibytes (KiB) used by - * the data structures needed to locate the XZ Blocks. - * This is usually useless information but since it is calculated - * for memory usage limit anyway, it is nice to make it available to too. - */ - public int getIndexMemoryUsage() { - return indexMemoryUsage; - } - - /** - * Gets the uncompressed size of the largest XZ Block in bytes. - * This can be useful if you want to check that the file doesn't - * have huge XZ Blocks which could make seeking to arbitrary offsets - * very slow. Note that huge Blocks don't automatically mean that - * seeking would be slow, for example, seeking to the beginning of - * any Block is always fast. - */ - public long getLargestBlockSize() { - return largestBlockSize; - } - - /** - * Gets the number of Streams in the .xz file. - * - * @since 1.3 - */ - public int getStreamCount() { - return streams.size(); - } - - /** - * Gets the number of Blocks in the .xz file. - * - * @since 1.3 - */ - public int getBlockCount() { - return blockCount; - } - - /** - * Gets the uncompressed start position of the given Block. - * - * @throws IndexOutOfBoundsException if - * blockNumber < 0 or - * blockNumber >= getBlockCount(). - * - * @since 1.3 - */ - public long getBlockPos(int blockNumber) { - locateBlockByNumber(queriedBlockInfo, blockNumber); - return queriedBlockInfo.uncompressedOffset; - } - - /** - * Gets the uncompressed size of the given Block. - * - * @throws IndexOutOfBoundsException if - * blockNumber < 0 or - * blockNumber >= getBlockCount(). - * - * @since 1.3 - */ - public long getBlockSize(int blockNumber) { - locateBlockByNumber(queriedBlockInfo, blockNumber); - return queriedBlockInfo.uncompressedSize; - } - - /** - * Gets the position where the given compressed Block starts in - * the underlying .xz file. - * This information is rarely useful to the users of this class. - * - * @throws IndexOutOfBoundsException if - * blockNumber < 0 or - * blockNumber >= getBlockCount(). - * - * @since 1.3 - */ - public long getBlockCompPos(int blockNumber) { - locateBlockByNumber(queriedBlockInfo, blockNumber); - return queriedBlockInfo.compressedOffset; - } - - /** - * Gets the compressed size of the given Block. - * This together with the uncompressed size can be used to calculate - * the compression ratio of the specific Block. - * - * @throws IndexOutOfBoundsException if - * blockNumber < 0 or - * blockNumber >= getBlockCount(). - * - * @since 1.3 - */ - public long getBlockCompSize(int blockNumber) { - locateBlockByNumber(queriedBlockInfo, blockNumber); - return (queriedBlockInfo.unpaddedSize + 3) & ~3; - } - - /** - * Gets integrity check type (Check ID) of the given Block. - * - * @throws IndexOutOfBoundsException if - * blockNumber < 0 or - * blockNumber >= getBlockCount(). - * - * @see #getCheckTypes() - * - * @since 1.3 - */ - public int getBlockCheckType(int blockNumber) { - locateBlockByNumber(queriedBlockInfo, blockNumber); - return queriedBlockInfo.getCheckType(); - } - - /** - * Gets the number of the Block that contains the byte at the given - * uncompressed position. - * - * @throws IndexOutOfBoundsException if - * pos < 0 or - * pos >= length(). - * - * @since 1.3 - */ - public int getBlockNumber(long pos) { - locateBlockByPos(queriedBlockInfo, pos); - return queriedBlockInfo.blockNumber; - } - - /** - * Decompresses the next byte from this input stream. - * - * @return the next decompressed byte, or -1 - * to indicate the end of the compressed stream - * - * @throws CorruptedInputException - * @throws UnsupportedOptionsException - * @throws MemoryLimitException - * - * @throws XZIOException if the stream has been closed - * - * @throws IOException may be thrown by in - */ - public int read() throws IOException { - return read(tempBuf, 0, 1) == -1 ? -1 : (tempBuf[0] & 0xFF); - } - - /** - * Decompresses into an array of bytes. - *

- * If len is zero, no bytes are read and 0 - * is returned. Otherwise this will try to decompress len - * bytes of uncompressed data. Less than len bytes may - * be read only in the following situations: - *

    - *
  • The end of the compressed data was reached successfully.
    • - *
  • An error is detected after at least one but less than - * len bytes have already been successfully - * decompressed. The next call with non-zero len - * will immediately throw the pending exception.
    • - *
  • An exception is thrown.
    • - *
- * - * @param buf target buffer for uncompressed data - * @param off start offset in buf - * @param len maximum number of uncompressed bytes to read - * - * @return number of bytes read, or -1 to indicate - * the end of the compressed stream - * - * @throws CorruptedInputException - * @throws UnsupportedOptionsException - * @throws MemoryLimitException - * - * @throws XZIOException if the stream has been closed - * - * @throws IOException may be thrown by in - */ - public int read(byte[] buf, int off, int len) throws IOException { - if (off < 0 || len < 0 || off + len < 0 || off + len > buf.length) - throw new IndexOutOfBoundsException(); - - if (len == 0) - return 0; - - if (in == null) - throw new XZIOException("Stream closed"); - - if (exception != null) - throw exception; - - int size = 0; - - try { - if (seekNeeded) - seek(); - - if (endReached) - return -1; - - while (len > 0) { - if (blockDecoder == null) { - seek(); - if (endReached) - break; - } - - int ret = blockDecoder.read(buf, off, len); - - if (ret > 0) { - curPos += ret; - size += ret; - off += ret; - len -= ret; - } else if (ret == -1) { - blockDecoder = null; - } - } - } catch (IOException e) { - // We know that the file isn't simply truncated because we could - // parse the Indexes in the constructor. So convert EOFException - // to CorruptedInputException. - if (e instanceof EOFException) - e = new CorruptedInputException(); - - exception = e; - if (size == 0) - throw e; - } - - return size; - } - - /** - * Returns the number of uncompressed bytes that can be read - * without blocking. The value is returned with an assumption - * that the compressed input data will be valid. If the compressed - * data is corrupt, CorruptedInputException may get - * thrown before the number of bytes claimed to be available have - * been read from this input stream. - * - * @return the number of uncompressed bytes that can be read - * without blocking - */ - public int available() throws IOException { - if (in == null) - throw new XZIOException("Stream closed"); - - if (exception != null) - throw exception; - - if (endReached || seekNeeded || blockDecoder == null) - return 0; - - return blockDecoder.available(); - } - - /** - * Closes the stream and calls in.close(). - * If the stream was already closed, this does nothing. - *

- * This is equivalent to close(true). - * - * @throws IOException if thrown by in.close() - */ - public void close() throws IOException { - close(true); - } - - /** - * Closes the stream and optionally calls in.close(). - * If the stream was already closed, this does nothing. - * If close(false) has been called, a further - * call of close(true) does nothing (it doesn't call - * in.close()). - *

- * If you don't want to close the underlying InputStream, - * there is usually no need to worry about closing this stream either; - * it's fine to do nothing and let the garbage collector handle it. - * However, if you are using {@link ArrayCache}, close(false) - * can be useful to put the allocated arrays back to the cache without - * closing the underlying InputStream. - *

- * Note that if you successfully reach the end of the stream - * (read returns -1), the arrays are - * automatically put back to the cache by that read call. In - * this situation close(false) is redundant (but harmless). - * - * @throws IOException if thrown by in.close() - * - * @since 1.7 - */ - public void close(boolean closeInput) throws IOException { - if (in != null) { - if (blockDecoder != null) { - blockDecoder.close(); - blockDecoder = null; - } - - try { - if (closeInput) - in.close(); - } finally { - in = null; - } - } - } - - /** - * Gets the uncompressed size of this input stream. If there are multiple - * XZ Streams, the total uncompressed size of all XZ Streams is returned. - */ - public long length() { - return uncompressedSize; - } - - /** - * Gets the current uncompressed position in this input stream. - * - * @throws XZIOException if the stream has been closed - */ - public long position() throws IOException { - if (in == null) - throw new XZIOException("Stream closed"); - - return seekNeeded ? seekPos : curPos; - } - - /** - * Seeks to the specified absolute uncompressed position in the stream. - * This only stores the new position, so this function itself is always - * very fast. The actual seek is done when read is called - * to read at least one byte. - *

- * Seeking past the end of the stream is possible. In that case - * read will return -1 to indicate - * the end of the stream. - * - * @param pos new uncompressed read position - * - * @throws XZIOException - * if pos is negative, or - * if stream has been closed - */ - public void seek(long pos) throws IOException { - if (in == null) - throw new XZIOException("Stream closed"); - - if (pos < 0) - throw new XZIOException("Negative seek position: " + pos); - - seekPos = pos; - seekNeeded = true; - } - - /** - * Seeks to the beginning of the given XZ Block. - * - * @throws XZIOException - * if blockNumber < 0 or - * blockNumber >= getBlockCount(), - * or if stream has been closed - * - * @since 1.3 - */ - public void seekToBlock(int blockNumber) throws IOException { - if (in == null) - throw new XZIOException("Stream closed"); - - if (blockNumber < 0 || blockNumber >= blockCount) - throw new XZIOException("Invalid XZ Block number: " + blockNumber); - - // This is a bit silly implementation. Here we locate the uncompressed - // offset of the specified Block, then when doing the actual seek in - // seek(), we need to find the Block number based on seekPos. - seekPos = getBlockPos(blockNumber); - seekNeeded = true; - } - - /** - * Does the actual seeking. This is also called when read - * needs a new Block to decode. - */ - private void seek() throws IOException { - // If seek(long) wasn't called, we simply need to get the next Block - // from the same Stream. If there are no more Blocks in this Stream, - // then we behave as if seek(long) had been called. - if (!seekNeeded) { - if (curBlockInfo.hasNext()) { - curBlockInfo.setNext(); - initBlockDecoder(); - return; - } - - seekPos = curPos; - } - - seekNeeded = false; - - // Check if we are seeking to or past the end of the file. - if (seekPos >= uncompressedSize) { - curPos = seekPos; - - if (blockDecoder != null) { - blockDecoder.close(); - blockDecoder = null; - } - - endReached = true; - return; - } - - endReached = false; - - // Locate the Block that contains the uncompressed target position. - locateBlockByPos(curBlockInfo, seekPos); - - // Seek in the underlying stream and create a new Block decoder - // only if really needed. We can skip it if the current position - // is already in the correct Block and the target position hasn't - // been decompressed yet. - // - // NOTE: If curPos points to the beginning of this Block, it's - // because it was left there after decompressing an earlier Block. - // In that case, decoding of the current Block hasn't been started - // yet. (Decoding of a Block won't be started until at least one - // byte will also be read from it.) - if (!(curPos > curBlockInfo.uncompressedOffset && curPos <= seekPos)) { - // Seek to the beginning of the Block. - in.seek(curBlockInfo.compressedOffset); - - // Since it is possible that this Block is from a different - // Stream than the previous Block, initialize a new Check. - check = Check.getInstance(curBlockInfo.getCheckType()); - - // Create a new Block decoder. - initBlockDecoder(); - curPos = curBlockInfo.uncompressedOffset; - } - - // If the target wasn't at a Block boundary, decompress and throw - // away data to reach the target position. - if (seekPos > curPos) { - // NOTE: The "if" below is there just in case. In this situation, - // blockDecoder.skip will always skip the requested amount - // or throw an exception. - long skipAmount = seekPos - curPos; - if (blockDecoder.skip(skipAmount) != skipAmount) - throw new CorruptedInputException(); - - curPos = seekPos; - } - } - - /** - * Locates the Block that contains the given uncompressed position. - */ - private void locateBlockByPos(BlockInfo info, long pos) { - if (pos < 0 || pos >= uncompressedSize) - throw new IndexOutOfBoundsException( - "Invalid uncompressed position: " + pos); - - // Locate the Stream that contains the target position. - IndexDecoder index; - for (int i = 0; ; ++i) { - index = streams.get(i); - if (index.hasUncompressedOffset(pos)) - break; - } - - // Locate the Block from the Stream that contains the target position. - index.locateBlock(info, pos); - - assert (info.compressedOffset & 3) == 0; - assert info.uncompressedSize > 0; - assert pos >= info.uncompressedOffset; - assert pos < info.uncompressedOffset + info.uncompressedSize; - } - - /** - * Locates the given Block and stores information about it - * to info. - */ - private void locateBlockByNumber(BlockInfo info, int blockNumber) { - // Validate. - if (blockNumber < 0 || blockNumber >= blockCount) - throw new IndexOutOfBoundsException( - "Invalid XZ Block number: " + blockNumber); - - // Skip the search if info already points to the correct Block. - if (info.blockNumber == blockNumber) - return; - - // Search the Stream that contains the given Block and then - // search the Block from that Stream. - for (int i = 0; ; ++i) { - IndexDecoder index = streams.get(i); - if (index.hasRecord(blockNumber)) { - index.setBlockInfo(info, blockNumber); - return; - } - } - } - - /** - * Initializes a new BlockInputStream. This is a helper function for - * seek(). - */ - private void initBlockDecoder() throws IOException { - try { - // Set it to null first so that GC can collect it if memory - // runs tight when initializing a new BlockInputStream. - if (blockDecoder != null) { - blockDecoder.close(); - blockDecoder = null; - } - - blockDecoder = new BlockInputStream( - in, check, verifyCheck, memoryLimit, - curBlockInfo.unpaddedSize, curBlockInfo.uncompressedSize, - arrayCache); - } catch (MemoryLimitException e) { - // BlockInputStream doesn't know how much memory we had - // already needed so we need to recreate the exception. - assert memoryLimit >= 0; - throw new MemoryLimitException( - e.getMemoryNeeded() + indexMemoryUsage, - memoryLimit + indexMemoryUsage); - } catch (IndexIndicatorException e) { - // It cannot be Index so the file must be corrupt. - throw new CorruptedInputException(); - } - } -} Index: unk/src/org/tukaani/xz/SimpleOutputStream.java =================================================================== --- /trunk/src/org/tukaani/xz/SimpleOutputStream.java (revision 13352) +++ (revision ) @@ -1,151 +1,0 @@ -/* - * SimpleOutputStream - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.io.IOException; -import org.tukaani.xz.simple.SimpleFilter; - -class SimpleOutputStream extends FinishableOutputStream { - private static final int FILTER_BUF_SIZE = 4096; - - private FinishableOutputStream out; - private final SimpleFilter simpleFilter; - - private final byte[] filterBuf = new byte[FILTER_BUF_SIZE]; - private int pos = 0; - private int unfiltered = 0; - - private IOException exception = null; - private boolean finished = false; - - private final byte[] tempBuf = new byte[1]; - - static int getMemoryUsage() { - return 1 + FILTER_BUF_SIZE / 1024; - } - - SimpleOutputStream(FinishableOutputStream out, - SimpleFilter simpleFilter) { - if (out == null) - throw new NullPointerException(); - - this.out = out; - this.simpleFilter = simpleFilter; - } - - public void write(int b) throws IOException { - tempBuf[0] = (byte)b; - write(tempBuf, 0, 1); - } - - public void write(byte[] buf, int off, int len) throws IOException { - if (off < 0 || len < 0 || off + len < 0 || off + len > buf.length) - throw new IndexOutOfBoundsException(); - - if (exception != null) - throw exception; - - if (finished) - throw new XZIOException("Stream finished or closed"); - - while (len > 0) { - // Copy more unfiltered data into filterBuf. - int copySize = Math.min(len, FILTER_BUF_SIZE - (pos + unfiltered)); - System.arraycopy(buf, off, filterBuf, pos + unfiltered, copySize); - off += copySize; - len -= copySize; - unfiltered += copySize; - - // Filter the data in filterBuf. - int filtered = simpleFilter.code(filterBuf, pos, unfiltered); - assert filtered <= unfiltered; - unfiltered -= filtered; - - // Write out the filtered data. - try { - out.write(filterBuf, pos, filtered); - } catch (IOException e) { - exception = e; - throw e; - } - - pos += filtered; - - // If end of filterBuf was reached, move the pending unfiltered - // data to the beginning of the buffer so that more data can - // be copied into filterBuf on the next loop iteration. - if (pos + unfiltered == FILTER_BUF_SIZE) { - System.arraycopy(filterBuf, pos, filterBuf, 0, unfiltered); - pos = 0; - } - } - } - - private void writePending() throws IOException { - assert !finished; - - if (exception != null) - throw exception; - - try { - out.write(filterBuf, pos, unfiltered); - } catch (IOException e) { - exception = e; - throw e; - } - - finished = true; - } - - public void flush() throws IOException { - throw new UnsupportedOptionsException("Flushing is not supported"); - } - - public void finish() throws IOException { - if (!finished) { - // If it fails, don't call out.finish(). - writePending(); - - try { - out.finish(); - } catch (IOException e) { - exception = e; - throw e; - } - } - } - - public void close() throws IOException { - if (out != null) { - if (!finished) { - // out.close() must be called even if writePending() fails. - // writePending() saves the possible exception so we can - // ignore exceptions here. - try { - writePending(); - } catch (IOException e) {} - } - - try { - out.close(); - } catch (IOException e) { - // If there is an earlier exception, the exception - // from out.close() is lost. - if (exception == null) - exception = e; - } - - out = null; - } - - if (exception != null) - throw exception; - } -} Index: unk/src/org/tukaani/xz/X86Options.java =================================================================== --- /trunk/src/org/tukaani/xz/X86Options.java (revision 13352) +++ (revision ) @@ -1,37 +1,0 @@ -/* - * X86Options - * - * Author: Lasse Collin - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz; - -import java.io.InputStream; -import org.tukaani.xz.simple.X86; - -/** - * BCJ filter for x86 (32-bit and 64-bit) instructions. - */ -public class X86Options extends BCJOptions { - private static final int ALIGNMENT = 1; - - public X86Options() { - super(ALIGNMENT); - } - - public FinishableOutputStream getOutputStream(FinishableOutputStream out, - ArrayCache arrayCache) { - return new SimpleOutputStream(out, new X86(true, startOffset)); - } - - public InputStream getInputStream(InputStream in, ArrayCache arrayCache) { - return new SimpleInputStream(in, new X86(false, startOffset)); - } - - FilterEncoder getFilterEncoder() { - return new BCJEncoder(this, BCJCoder.X86_FILTER_ID); - } -} Index: unk/src/org/tukaani/xz/rangecoder/RangeDecoderFromStream.java =================================================================== --- /trunk/src/org/tukaani/xz/rangecoder/RangeDecoderFromStream.java (revision 13352) +++ (revision ) @@ -1,41 +1,0 @@ -/* - * RangeDecoderFromStream - * - * Authors: Lasse Collin - * Igor Pavlov - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz.rangecoder; - -import java.io.InputStream; -import java.io.DataInputStream; -import java.io.IOException; -import org.tukaani.xz.CorruptedInputException; - -public final class RangeDecoderFromStream extends RangeDecoder { - private final DataInputStream inData; - - public RangeDecoderFromStream(InputStream in) throws IOException { - inData = new DataInputStream(in); - - if (inData.readUnsignedByte() != 0x00) - throw new CorruptedInputException(); - - code = inData.readInt(); - range = 0xFFFFFFFF; - } - - public boolean isFinished() { - return code == 0; - } - - public void normalize() throws IOException { - if ((range & TOP_MASK) == 0) { - code = (code << SHIFT_BITS) | inData.readUnsignedByte(); - range <<= SHIFT_BITS; - } - } -} Index: unk/src/org/tukaani/xz/rangecoder/RangeEncoderToStream.java =================================================================== --- /trunk/src/org/tukaani/xz/rangecoder/RangeEncoderToStream.java (revision 13352) +++ (revision ) @@ -1,27 +1,0 @@ -/* - * RangeEncoderToStream - * - * Authors: Lasse Collin - * Igor Pavlov - * - * This file has been put into the public domain. - * You can do whatever you want with this file. - */ - -package org.tukaani.xz.rangecoder; - -import java.io.OutputStream; -import java.io.IOException; - -public final class RangeEncoderToStream extends RangeEncoder { - private final OutputStream out; - - public RangeEncoderToStream(OutputStream out) { - this.out = out; - reset(); - } - - void writeByte(int b) throws IOException { - out.write(b); - } -}