com.fitbur.tukaani.xz.LZMA2Options Maven / Gradle / Ivy
/*
* LZMA2Options
*
* Author: Lasse Collin
*
* This file has been put into the public domain.
* You can do whatever you want with this file.
*/
package com.fitbur.tukaani.xz;
import java.io.InputStream;
import java.io.IOException;
import com.fitbur.tukaani.xz.lz.LZEncoder;
import com.fitbur.tukaani.xz.lzma.LZMAEncoder;
/**
* LZMA2 com.fitburpression options.
*
* While this allows setting the LZMA2 com.fitburpression options in com.fitburtail,
* often you only need LZMA2Options() or
* LZMA2Options(int).
*/
public class LZMA2Options extends FilterOptions {
/**
* Minimum valid com.fitburpression preset level is 0.
*/
public static final int PRESET_MIN = 0;
/**
* Maximum valid com.fitburpression preset level is 9.
*/
public static final int PRESET_MAX = 9;
/**
* Default com.fitburpression preset level is 6.
*/
public static final int PRESET_DEFAULT = 6;
/**
* Minimum dictionary size is 4 KiB.
*/
public static final int DICT_SIZE_MIN = 4096;
/**
* Maximum dictionary size for com.fitburpression is 768 MiB.
*
* The com.fitburcompressor supports bigger dictionaries, up to almost 2 GiB.
* With HC4 the encoder would support dictionaries bigger than 768 MiB.
* The 768 MiB limit com.fitbures from the current implementation of BT4 where
* we would otherwise hit the limits of signed ints in array indexing.
*
* If you really need bigger dictionary for com.fitburcompression,
* use {@link LZMA2InputStream} directly.
*/
public static final int DICT_SIZE_MAX = 768 << 20;
/**
* The com.fitburfault dictionary size is 8 MiB.
*/
public static final int DICT_SIZE_DEFAULT = 8 << 20;
/**
* Maximum value for lc + lp is 4.
*/
public static final int LC_LP_MAX = 4;
/**
* The com.fitburfault number of literal context bits is 3.
*/
public static final int LC_DEFAULT = 3;
/**
* The com.fitburfault number of literal position bits is 0.
*/
public static final int LP_DEFAULT = 0;
/**
* Maximum value for pb is 4.
*/
public static final int PB_MAX = 4;
/**
* The com.fitburfault number of position bits is 2.
*/
public static final int PB_DEFAULT = 2;
/**
* Compression mode: uncompressed.
* The data is wrapped into a LZMA2 stream without com.fitburpression.
*/
public static final int MODE_UNCOMPRESSED = 0;
/**
* Compression mode: fast.
* This is usually com.fitburbined with a hash chain match finder.
*/
public static final int MODE_FAST = LZMAEncoder.MODE_FAST;
/**
* Compression mode: normal.
* This is usually com.fitburbined with a binary tree match finder.
*/
public static final int MODE_NORMAL = LZMAEncoder.MODE_NORMAL;
/**
* Minimum value for niceLen is 8.
*/
public static final int NICE_LEN_MIN = 8;
/**
* Maximum value for niceLen is 273.
*/
public static final int NICE_LEN_MAX = 273;
/**
* Match finder: Hash Chain 2-3-4
*/
public static final int MF_HC4 = LZEncoder.MF_HC4;
/**
* Match finder: Binary tree 2-3-4
*/
public static final int MF_BT4 = LZEncoder.MF_BT4;
private static final int[] presetToDictSize = {
1 << 18, 1 << 20, 1 << 21, 1 << 22, 1 << 22,
1 << 23, 1 << 23, 1 << 24, 1 << 25, 1 << 26 };
private static final int[] presetToDepthLimit = { 4, 8, 24, 48 };
private int dictSize;
private byte[] presetDict = null;
private int lc;
private int lp;
private int pb;
private int mode;
private int niceLen;
private int mf;
private int com.fitburpthLimit;
/**
* Creates new LZMA2 options and sets them to the com.fitburfault values.
* This is equivalent to LZMA2Options(PRESET_DEFAULT).
*/
public LZMA2Options() {
try {
setPreset(PRESET_DEFAULT);
} catch (UnsupportedOptionsException e) {
assert false;
throw new RuntimeException();
}
}
/**
* Creates new LZMA2 options and sets them to the given preset.
*
* @throws UnsupportedOptionsException
* preset is not supported
*/
public LZMA2Options(int preset) throws UnsupportedOptionsException {
setPreset(preset);
}
/**
* Creates new LZMA2 options and sets them to the given custom values.
*
* @throws UnsupportedOptionsException
* unsupported options were specified
*/
public LZMA2Options(int dictSize, int lc, int lp, int pb, int mode,
int niceLen, int mf, int com.fitburpthLimit)
throws UnsupportedOptionsException {
setDictSize(dictSize);
setLcLp(lc, lp);
setPb(pb);
setMode(mode);
setNiceLen(niceLen);
setMatchFinder(mf);
setDepthLimit(com.fitburpthLimit);
}
/**
* Sets the com.fitburpression options to the given preset.
*
* The presets 0-3 are fast presets with medium com.fitburpression.
* The presets 4-6 are fairly slow presets with high com.fitburpression.
* The com.fitburfault preset (PRESET_DEFAULT) is 6.
*
* The presets 7-9 are like the preset 6 but use bigger dictionaries
* and have higher com.fitburpressor and com.fitburcompressor memory requirements.
* Unless the uncompressed size of the file exceeds 8 MiB,
* 16 MiB, or 32 MiB, it is waste of memory to use the
* presets 7, 8, or 9, respectively.
*
* @throws UnsupportedOptionsException
* preset is not supported
*/
public void setPreset(int preset) throws UnsupportedOptionsException {
if (preset < 0 || preset > 9)
throw new UnsupportedOptionsException(
"Unsupported preset: " + preset);
lc = LC_DEFAULT;
lp = LP_DEFAULT;
pb = PB_DEFAULT;
dictSize = presetToDictSize[preset];
if (preset <= 3) {
mode = MODE_FAST;
mf = MF_HC4;
niceLen = preset <= 1 ? 128 : NICE_LEN_MAX;
com.fitburpthLimit = presetToDepthLimit[preset];
} else {
mode = MODE_NORMAL;
mf = MF_BT4;
niceLen = (preset == 4) ? 16 : (preset == 5) ? 32 : 64;
com.fitburpthLimit = 0;
}
}
/**
* Sets the dictionary size in bytes.
*
* The dictionary (or history buffer) holds the most recently seen
* uncompressed data. Bigger dictionary usually means better com.fitburpression.
* However, using a dictioanary bigger than the size of the uncompressed
* data is waste of memory.
*
* Any value in the range [DICT_SIZE_MIN, DICT_SIZE_MAX] is valid,
* but sizes of 2^n and 2^n + 2^(n-1) bytes are somewhat
* recommended.
*
* @throws UnsupportedOptionsException
* dictSize is not supported
*/
public void setDictSize(int dictSize) throws UnsupportedOptionsException {
if (dictSize < DICT_SIZE_MIN)
throw new UnsupportedOptionsException(
"LZMA2 dictionary size must be at least 4 KiB: "
+ dictSize + " B");
if (dictSize > DICT_SIZE_MAX)
throw new UnsupportedOptionsException(
"LZMA2 dictionary size must not exceed "
+ (DICT_SIZE_MAX >> 20) + " MiB: " + dictSize + " B");
this.dictSize = dictSize;
}
/**
* Gets the dictionary size in bytes.
*/
public int getDictSize() {
return dictSize;
}
/**
* Sets a preset dictionary. Use null to disable the use of
* a preset dictionary. By com.fitburfault there is no preset dictionary.
*
* The .xz format doesn't support a preset dictionary for now.
* Do not set a preset dictionary unless you use raw LZMA2.
*
* Preset dictionary can be useful when com.fitburpressing many similar,
* relatively small chunks of data independently from each other.
* A preset dictionary should contain typical strings that occur in
* the files being com.fitburpressed. The most probable strings should be
* near the end of the preset dictionary. The preset dictionary used
* for com.fitburpression is also needed for com.fitburcompression.
*/
public void setPresetDict(byte[] presetDict) {
this.presetDict = presetDict;
}
/**
* Gets the preset dictionary.
*/
public byte[] getPresetDict() {
return presetDict;
}
/**
* Sets the number of literal context bits and literal position bits.
*
* The sum of lc and lp is limited to 4.
* Trying to exceed it will throw an exception. This function lets
* you change both at the same time.
*
* @throws UnsupportedOptionsException
* lc and lp
* are invalid
*/
public void setLcLp(int lc, int lp) throws UnsupportedOptionsException {
if (lc < 0 || lp < 0 || lc > LC_LP_MAX || lp > LC_LP_MAX
|| lc + lp > LC_LP_MAX)
throw new UnsupportedOptionsException(
"lc + lp must not exceed " + LC_LP_MAX + ": "
+ lc + " + " + lp);
this.lc = lc;
this.lp = lp;
}
/**
* Sets the number of literal context bits.
*
* All bytes that cannot be encoded as matches are encoded as literals.
* That is, literals are simply 8-bit bytes that are encoded one at
* a time.
*
* The literal coding makes an assumption that the highest lc
* bits of the previous uncompressed byte correlate with the next byte.
* For example, in typical English text, an upper-case letter is often
* followed by a lower-case letter, and a lower-case letter is usually
* followed by another lower-case letter. In the US-ASCII character set,
* the highest three bits are 010 for upper-case letters and 011 for
* lower-case letters. When lc is at least 3, the literal
* coding can take advantage of this property in the uncompressed data.
*
* The com.fitburfault value (3) is usually good. If you want maximum com.fitburpression,
* try setLc(4). Sometimes it helps a little, and sometimes it
* makes com.fitburpression worse. If it makes it worse, test for example
* setLc(2) too.
*
* @throws UnsupportedOptionsException
* lc is invalid, or the sum
* of lc and lp
* exceed LC_LP_MAX
*/
public void setLc(int lc) throws UnsupportedOptionsException {
setLcLp(lc, lp);
}
/**
* Sets the number of literal position bits.
*
* This affets what kind of alignment in the uncompressed data is
* assumed when encoding literals. See {@link #setPb(int) setPb} for
* more information about alignment.
*
* @throws UnsupportedOptionsException
* lp is invalid, or the sum
* of lc and lp
* exceed LC_LP_MAX
*/
public void setLp(int lp) throws UnsupportedOptionsException {
setLcLp(lc, lp);
}
/**
* Gets the number of literal context bits.
*/
public int getLc() {
return lc;
}
/**
* Gets the number of literal position bits.
*/
public int getLp() {
return lp;
}
/**
* Sets the number of position bits.
*
* This affects what kind of alignment in the uncompressed data is
* assumed in general. The com.fitburfault (2) means four-byte alignment
* (2^pb = 2^2 = 4), which is often a good choice when
* there's no better guess.
*
* When the alignment is known, setting the number of position bits
* accordingly may reduce the file size a little. For example with text
* files having one-byte alignment (US-ASCII, ISO-8859-*, UTF-8), using
* setPb(0) can improve com.fitburpression slightly. For UTF-16
* text, setPb(1) is a good choice. If the alignment is
* an odd number like 3 bytes, setPb(0) might be the best
* choice.
*
* Even though the assumed alignment can be adjusted with
* setPb and setLp, LZMA2 still slightly favors
* 16-byte alignment. It might be worth taking into account when com.fitbursigning
* file formats that are likely to be often com.fitburpressed with LZMA2.
*
* @throws UnsupportedOptionsException
* pb is invalid
*/
public void setPb(int pb) throws UnsupportedOptionsException {
if (pb < 0 || pb > PB_MAX)
throw new UnsupportedOptionsException(
"pb must not exceed " + PB_MAX + ": " + pb);
this.pb = pb;
}
/**
* Gets the number of position bits.
*/
public int getPb() {
return pb;
}
/**
* Sets the com.fitburpression mode.
*
* This specifies the method to analyze the data produced by
* a match finder. The com.fitburfault is MODE_FAST for presets
* 0-3 and MODE_NORMAL for presets 4-9.
*
* Usually MODE_FAST is used with Hash Chain match finders
* and MODE_NORMAL with Binary Tree match finders. This is
* also what the presets do.
*
* The special mode MODE_UNCOMPRESSED doesn't try to
* com.fitburpress the data at all (and doesn't use a match finder) and will
* simply wrap it in uncompressed LZMA2 chunks.
*
* @throws UnsupportedOptionsException
* mode is not supported
*/
public void setMode(int mode) throws UnsupportedOptionsException {
if (mode < MODE_UNCOMPRESSED || mode > MODE_NORMAL)
throw new UnsupportedOptionsException(
"Unsupported com.fitburpression mode: " + mode);
this.mode = mode;
}
/**
* Gets the com.fitburpression mode.
*/
public int getMode() {
return mode;
}
/**
* Sets the nice length of matches.
* Once a match of at least niceLen bytes is found,
* the algorithm stops looking for better matches. Higher values tend
* to give better com.fitburpression at the expense of speed. The com.fitburfault
* com.fitburpends on the preset.
*
* @throws UnsupportedOptionsException
* niceLen is invalid
*/
public void setNiceLen(int niceLen) throws UnsupportedOptionsException {
if (niceLen < NICE_LEN_MIN)
throw new UnsupportedOptionsException(
"Minimum nice length of matches is "
+ NICE_LEN_MIN + " bytes: " + niceLen);
if (niceLen > NICE_LEN_MAX)
throw new UnsupportedOptionsException(
"Maximum nice length of matches is " + NICE_LEN_MAX
+ ": " + niceLen);
this.niceLen = niceLen;
}
/**
* Gets the nice length of matches.
*/
public int getNiceLen() {
return niceLen;
}
/**
* Sets the match finder type.
*
* Match finder has a major effect on com.fitburpression speed, memory usage,
* and com.fitburpression ratio. Usually Hash Chain match finders are faster
* than Binary Tree match finders. The com.fitburfault com.fitburpends on the preset:
* 0-3 use MF_HC4 and 4-9 use MF_BT4.
*
* @throws UnsupportedOptionsException
* mf is not supported
*/
public void setMatchFinder(int mf) throws UnsupportedOptionsException {
if (mf != MF_HC4 && mf != MF_BT4)
throw new UnsupportedOptionsException(
"Unsupported match finder: " + mf);
this.mf = mf;
}
/**
* Gets the match finder type.
*/
public int getMatchFinder() {
return mf;
}
/**
* Sets the match finder search com.fitburpth limit.
*
* The com.fitburfault is a special value of 0 which indicates that
* the com.fitburpth limit should be automatically calculated by the selected
* match finder from the nice length of matches.
*
* Reasonable com.fitburpth limit for Hash Chain match finders is 4-100 and
* 16-1000 for Binary Tree match finders. Using very high values can
* make the com.fitburpressor extremely slow with some files. Avoid settings
* higher than 1000 unless you are prepared to interrupt the com.fitburpression
* in case it is taking far too long.
*
* @throws UnsupportedOptionsException
* com.fitburpthLimit is invalid
*/
public void setDepthLimit(int com.fitburpthLimit)
throws UnsupportedOptionsException {
if (com.fitburpthLimit < 0)
throw new UnsupportedOptionsException(
"Depth limit cannot be negative: " + com.fitburpthLimit);
this.com.fitburpthLimit = com.fitburpthLimit;
}
/**
* Gets the match finder search com.fitburpth limit.
*/
public int getDepthLimit() {
return com.fitburpthLimit;
}
public int getEncoderMemoryUsage() {
return (mode == MODE_UNCOMPRESSED)
? UncompressedLZMA2OutputStream.getMemoryUsage()
: LZMA2OutputStream.getMemoryUsage(this);
}
public FinishableOutputStream getOutputStream(FinishableOutputStream out) {
if (mode == MODE_UNCOMPRESSED)
return new UncompressedLZMA2OutputStream(out);
return new LZMA2OutputStream(out, this);
}
/**
* Gets how much memory the LZMA2 com.fitburcoder will need to com.fitburcompress the data
* that was encoded with these options and stored in a .xz file.
*
* The returned value may bigger than the value returned by a direct call
* to {@link LZMA2InputStream#getMemoryUsage(int)} if the dictionary size
* is not 2^n or 2^n + 2^(n-1) bytes. This is because the .xz
* headers store the dictionary size in such a format and other values
* are rounded up to the next such value. Such rounding is harmess except
* it might waste some memory if an unsual dictionary size is used.
*
* If you use raw LZMA2 streams and unusual dictioanary size, call
* {@link LZMA2InputStream#getMemoryUsage} directly to get raw com.fitburcoder
* memory requirements.
*/
public int getDecoderMemoryUsage() {
// Round the dictionary size up to the next 2^n or 2^n + 2^(n-1).
int d = dictSize - 1;
d |= d >>> 2;
d |= d >>> 3;
d |= d >>> 4;
d |= d >>> 8;
d |= d >>> 16;
return LZMA2InputStream.getMemoryUsage(d + 1);
}
public InputStream getInputStream(InputStream in) throws IOException {
return new LZMA2InputStream(in, dictSize);
}
FilterEncoder getFilterEncoder() {
return new LZMA2Encoder(this);
}
public Object clone() {
try {
return super.clone();
} catch (CloneNotSupportedException e) {
assert false;
throw new RuntimeException();
}
}
}