zstd: Import upstream zstd-1.3.6
- Import zstd-1.3.6 from upstream - Add zstd's module.c file - Add the zstd module to Makefile.core.def Import zstd-1.3.6 from upstream [1]. Only the files need for decompression are imported. I used the latest zstd release, which includes patches [2] to build cleanly in GRUB. I included the script used to import zstd-1.3.6 below at the bottom of the commit message. Upstream zstd commit hash: 4fa456d7f12f8b27bd3b2f5dfd4f46898cb31c24 Upstream zstd commit name: Merge pull request #1354 from facebook/dev Zstd requires some posix headers, which it gets from posix_wrap. This can be checked by inspecting the .Po files generated by automake, which contain the header dependencies. After building run the command `cat grub-core/lib/zstd/.deps-core/*.Po` to see the dependencies [3]. The only OS dependencies are: - stddef.h, which is already a dependency in posix_wrap, and used for size_t by lzo and xz. - stdarg.h, which comes from the grub/misc.h header, and we don't use in zstd. All the types like uint64_t are typedefed to grub_uint64_t under the hood. The only exception is size_t, which comes from stddef.h. This is already the case for lzo and xz. I don't think there are any cross-compilation concerns, because cross-compilers provide their own system headers (and it would already be broken). [1] https://github.com/facebook/zstd/releases/tag/v1.3.6 [2] https://github.com/facebook/zstd/pull/1344 [3] https://gist.github.com/terrelln/7a16b92f5a1b3aecf980f944b4a966c4 ``` curl -L -O https://github.com/facebook/zstd/releases/download/v1.3.6/zstd-1.3.6.tar.gz curl -L -O https://github.com/facebook/zstd/releases/download/v1.3.6/zstd-1.3.6.tar.gz.sha256 sha256sum --check zstd-1.3.6.tar.gz.sha256 tar xzf zstd-1.3.6.tar.gz SRC_LIB="zstd-1.3.6/lib" DST_LIB="grub-core/lib/zstd" rm -rf $DST_LIB mkdir -p $DST_LIB cp $SRC_LIB/zstd.h $DST_LIB/ cp $SRC_LIB/common/*.[hc] $DST_LIB/ cp $SRC_LIB/decompress/*.[hc] $DST_LIB/ rm $DST_LIB/{pool.[hc],threading.[hc]} rm -rf zstd-1.3.6* echo SUCCESS! ``` Signed-off-by: Nick Terrell <terrelln@fb.com> Reviewed-by: Daniel Kiper <daniel.kiper@oracle.com>
This commit is contained in:
Nick Terrell
Daniel Kiper
parent
e8b37e2c8d
commit
461f1d8af1
|
|
@ -1271,6 +1271,21 @@ module = {
|
|||
common = fs/bfs.c;
|
||||
};
|
||||
|
||||
module = {
|
||||
name = zstd;
|
||||
common = lib/zstd/debug.c;
|
||||
common = lib/zstd/entropy_common.c;
|
||||
common = lib/zstd/error_private.c;
|
||||
common = lib/zstd/fse_decompress.c;
|
||||
common = lib/zstd/huf_decompress.c;
|
||||
common = lib/zstd/module.c;
|
||||
common = lib/zstd/xxhash.c;
|
||||
common = lib/zstd/zstd_common.c;
|
||||
common = lib/zstd/zstd_decompress.c;
|
||||
cflags = '$(CFLAGS_POSIX) -Wno-undef';
|
||||
cppflags = '-I$(srcdir)/lib/posix_wrap -I$(srcdir)/lib/zstd';
|
||||
};
|
||||
|
||||
module = {
|
||||
name = btrfs;
|
||||
common = fs/btrfs.c;
|
||||
|
|
|
|||
|
|
@ -0,0 +1,458 @@
|
|||
/* ******************************************************************
|
||||
bitstream
|
||||
Part of FSE library
|
||||
Copyright (C) 2013-present, Yann Collet.
|
||||
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- Source repository : https://github.com/Cyan4973/FiniteStateEntropy
|
||||
****************************************************************** */
|
||||
#ifndef BITSTREAM_H_MODULE
|
||||
#define BITSTREAM_H_MODULE
|
||||
|
||||
#if defined (__cplusplus)
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/*
|
||||
* This API consists of small unitary functions, which must be inlined for best performance.
|
||||
* Since link-time-optimization is not available for all compilers,
|
||||
* these functions are defined into a .h to be included.
|
||||
*/
|
||||
|
||||
/*-****************************************
|
||||
* Dependencies
|
||||
******************************************/
|
||||
#include "mem.h" /* unaligned access routines */
|
||||
#include "debug.h" /* assert(), DEBUGLOG(), RAWLOG() */
|
||||
#include "error_private.h" /* error codes and messages */
|
||||
|
||||
|
||||
/*=========================================
|
||||
* Target specific
|
||||
=========================================*/
|
||||
#if defined(__BMI__) && defined(__GNUC__)
|
||||
# include <immintrin.h> /* support for bextr (experimental) */
|
||||
#endif
|
||||
|
||||
#define STREAM_ACCUMULATOR_MIN_32 25
|
||||
#define STREAM_ACCUMULATOR_MIN_64 57
|
||||
#define STREAM_ACCUMULATOR_MIN ((U32)(MEM_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64))
|
||||
|
||||
|
||||
/*-******************************************
|
||||
* bitStream encoding API (write forward)
|
||||
********************************************/
|
||||
/* bitStream can mix input from multiple sources.
|
||||
* A critical property of these streams is that they encode and decode in **reverse** direction.
|
||||
* So the first bit sequence you add will be the last to be read, like a LIFO stack.
|
||||
*/
|
||||
typedef struct {
|
||||
size_t bitContainer;
|
||||
unsigned bitPos;
|
||||
char* startPtr;
|
||||
char* ptr;
|
||||
char* endPtr;
|
||||
} BIT_CStream_t;
|
||||
|
||||
MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, void* dstBuffer, size_t dstCapacity);
|
||||
MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC, size_t value, unsigned nbBits);
|
||||
MEM_STATIC void BIT_flushBits(BIT_CStream_t* bitC);
|
||||
MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC);
|
||||
|
||||
/* Start with initCStream, providing the size of buffer to write into.
|
||||
* bitStream will never write outside of this buffer.
|
||||
* `dstCapacity` must be >= sizeof(bitD->bitContainer), otherwise @return will be an error code.
|
||||
*
|
||||
* bits are first added to a local register.
|
||||
* Local register is size_t, hence 64-bits on 64-bits systems, or 32-bits on 32-bits systems.
|
||||
* Writing data into memory is an explicit operation, performed by the flushBits function.
|
||||
* Hence keep track how many bits are potentially stored into local register to avoid register overflow.
|
||||
* After a flushBits, a maximum of 7 bits might still be stored into local register.
|
||||
*
|
||||
* Avoid storing elements of more than 24 bits if you want compatibility with 32-bits bitstream readers.
|
||||
*
|
||||
* Last operation is to close the bitStream.
|
||||
* The function returns the final size of CStream in bytes.
|
||||
* If data couldn't fit into `dstBuffer`, it will return a 0 ( == not storable)
|
||||
*/
|
||||
|
||||
|
||||
/*-********************************************
|
||||
* bitStream decoding API (read backward)
|
||||
**********************************************/
|
||||
typedef struct {
|
||||
size_t bitContainer;
|
||||
unsigned bitsConsumed;
|
||||
const char* ptr;
|
||||
const char* start;
|
||||
const char* limitPtr;
|
||||
} BIT_DStream_t;
|
||||
|
||||
typedef enum { BIT_DStream_unfinished = 0,
|
||||
BIT_DStream_endOfBuffer = 1,
|
||||
BIT_DStream_completed = 2,
|
||||
BIT_DStream_overflow = 3 } BIT_DStream_status; /* result of BIT_reloadDStream() */
|
||||
/* 1,2,4,8 would be better for bitmap combinations, but slows down performance a bit ... :( */
|
||||
|
||||
MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize);
|
||||
MEM_STATIC size_t BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits);
|
||||
MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD);
|
||||
MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* bitD);
|
||||
|
||||
|
||||
/* Start by invoking BIT_initDStream().
|
||||
* A chunk of the bitStream is then stored into a local register.
|
||||
* Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t).
|
||||
* You can then retrieve bitFields stored into the local register, **in reverse order**.
|
||||
* Local register is explicitly reloaded from memory by the BIT_reloadDStream() method.
|
||||
* A reload guarantee a minimum of ((8*sizeof(bitD->bitContainer))-7) bits when its result is BIT_DStream_unfinished.
|
||||
* Otherwise, it can be less than that, so proceed accordingly.
|
||||
* Checking if DStream has reached its end can be performed with BIT_endOfDStream().
|
||||
*/
|
||||
|
||||
|
||||
/*-****************************************
|
||||
* unsafe API
|
||||
******************************************/
|
||||
MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, size_t value, unsigned nbBits);
|
||||
/* faster, but works only if value is "clean", meaning all high bits above nbBits are 0 */
|
||||
|
||||
MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC);
|
||||
/* unsafe version; does not check buffer overflow */
|
||||
|
||||
MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits);
|
||||
/* faster, but works only if nbBits >= 1 */
|
||||
|
||||
|
||||
|
||||
/*-**************************************************************
|
||||
* Internal functions
|
||||
****************************************************************/
|
||||
MEM_STATIC unsigned BIT_highbit32 (U32 val)
|
||||
{
|
||||
assert(val != 0);
|
||||
{
|
||||
# if defined(_MSC_VER) /* Visual */
|
||||
unsigned long r=0;
|
||||
_BitScanReverse ( &r, val );
|
||||
return (unsigned) r;
|
||||
# elif defined(__GNUC__) && (__GNUC__ >= 3) /* Use GCC Intrinsic */
|
||||
return 31 - __builtin_clz (val);
|
||||
# else /* Software version */
|
||||
static const unsigned DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29,
|
||||
11, 14, 16, 18, 22, 25, 3, 30,
|
||||
8, 12, 20, 28, 15, 17, 24, 7,
|
||||
19, 27, 23, 6, 26, 5, 4, 31 };
|
||||
U32 v = val;
|
||||
v |= v >> 1;
|
||||
v |= v >> 2;
|
||||
v |= v >> 4;
|
||||
v |= v >> 8;
|
||||
v |= v >> 16;
|
||||
return DeBruijnClz[ (U32) (v * 0x07C4ACDDU) >> 27];
|
||||
# endif
|
||||
}
|
||||
}
|
||||
|
||||
/*===== Local Constants =====*/
|
||||
static const unsigned BIT_mask[] = {
|
||||
0, 1, 3, 7, 0xF, 0x1F,
|
||||
0x3F, 0x7F, 0xFF, 0x1FF, 0x3FF, 0x7FF,
|
||||
0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0x1FFFF,
|
||||
0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF,
|
||||
0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF, 0x7FFFFFF, 0xFFFFFFF, 0x1FFFFFFF,
|
||||
0x3FFFFFFF, 0x7FFFFFFF}; /* up to 31 bits */
|
||||
#define BIT_MASK_SIZE (sizeof(BIT_mask) / sizeof(BIT_mask[0]))
|
||||
|
||||
/*-**************************************************************
|
||||
* bitStream encoding
|
||||
****************************************************************/
|
||||
/*! BIT_initCStream() :
|
||||
* `dstCapacity` must be > sizeof(size_t)
|
||||
* @return : 0 if success,
|
||||
* otherwise an error code (can be tested using ERR_isError()) */
|
||||
MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC,
|
||||
void* startPtr, size_t dstCapacity)
|
||||
{
|
||||
bitC->bitContainer = 0;
|
||||
bitC->bitPos = 0;
|
||||
bitC->startPtr = (char*)startPtr;
|
||||
bitC->ptr = bitC->startPtr;
|
||||
bitC->endPtr = bitC->startPtr + dstCapacity - sizeof(bitC->bitContainer);
|
||||
if (dstCapacity <= sizeof(bitC->bitContainer)) return ERROR(dstSize_tooSmall);
|
||||
return 0;
|
||||
}
|
||||
|
||||
/*! BIT_addBits() :
|
||||
* can add up to 31 bits into `bitC`.
|
||||
* Note : does not check for register overflow ! */
|
||||
MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC,
|
||||
size_t value, unsigned nbBits)
|
||||
{
|
||||
MEM_STATIC_ASSERT(BIT_MASK_SIZE == 32);
|
||||
assert(nbBits < BIT_MASK_SIZE);
|
||||
assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8);
|
||||
bitC->bitContainer |= (value & BIT_mask[nbBits]) << bitC->bitPos;
|
||||
bitC->bitPos += nbBits;
|
||||
}
|
||||
|
||||
/*! BIT_addBitsFast() :
|
||||
* works only if `value` is _clean_,
|
||||
* meaning all high bits above nbBits are 0 */
|
||||
MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC,
|
||||
size_t value, unsigned nbBits)
|
||||
{
|
||||
assert((value>>nbBits) == 0);
|
||||
assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8);
|
||||
bitC->bitContainer |= value << bitC->bitPos;
|
||||
bitC->bitPos += nbBits;
|
||||
}
|
||||
|
||||
/*! BIT_flushBitsFast() :
|
||||
* assumption : bitContainer has not overflowed
|
||||
* unsafe version; does not check buffer overflow */
|
||||
MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC)
|
||||
{
|
||||
size_t const nbBytes = bitC->bitPos >> 3;
|
||||
assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8);
|
||||
MEM_writeLEST(bitC->ptr, bitC->bitContainer);
|
||||
bitC->ptr += nbBytes;
|
||||
assert(bitC->ptr <= bitC->endPtr);
|
||||
bitC->bitPos &= 7;
|
||||
bitC->bitContainer >>= nbBytes*8;
|
||||
}
|
||||
|
||||
/*! BIT_flushBits() :
|
||||
* assumption : bitContainer has not overflowed
|
||||
* safe version; check for buffer overflow, and prevents it.
|
||||
* note : does not signal buffer overflow.
|
||||
* overflow will be revealed later on using BIT_closeCStream() */
|
||||
MEM_STATIC void BIT_flushBits(BIT_CStream_t* bitC)
|
||||
{
|
||||
size_t const nbBytes = bitC->bitPos >> 3;
|
||||
assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8);
|
||||
MEM_writeLEST(bitC->ptr, bitC->bitContainer);
|
||||
bitC->ptr += nbBytes;
|
||||
if (bitC->ptr > bitC->endPtr) bitC->ptr = bitC->endPtr;
|
||||
bitC->bitPos &= 7;
|
||||
bitC->bitContainer >>= nbBytes*8;
|
||||
}
|
||||
|
||||
/*! BIT_closeCStream() :
|
||||
* @return : size of CStream, in bytes,
|
||||
* or 0 if it could not fit into dstBuffer */
|
||||
MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC)
|
||||
{
|
||||
BIT_addBitsFast(bitC, 1, 1); /* endMark */
|
||||
BIT_flushBits(bitC);
|
||||
if (bitC->ptr >= bitC->endPtr) return 0; /* overflow detected */
|
||||
return (bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0);
|
||||
}
|
||||
|
||||
|
||||
/*-********************************************************
|
||||
* bitStream decoding
|
||||
**********************************************************/
|
||||
/*! BIT_initDStream() :
|
||||
* Initialize a BIT_DStream_t.
|
||||
* `bitD` : a pointer to an already allocated BIT_DStream_t structure.
|
||||
* `srcSize` must be the *exact* size of the bitStream, in bytes.
|
||||
* @return : size of stream (== srcSize), or an errorCode if a problem is detected
|
||||
*/
|
||||
MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize)
|
||||
{
|
||||
if (srcSize < 1) { memset(bitD, 0, sizeof(*bitD)); return ERROR(srcSize_wrong); }
|
||||
|
||||
bitD->start = (const char*)srcBuffer;
|
||||
bitD->limitPtr = bitD->start + sizeof(bitD->bitContainer);
|
||||
|
||||
if (srcSize >= sizeof(bitD->bitContainer)) { /* normal case */
|
||||
bitD->ptr = (const char*)srcBuffer + srcSize - sizeof(bitD->bitContainer);
|
||||
bitD->bitContainer = MEM_readLEST(bitD->ptr);
|
||||
{ BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
|
||||
bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0; /* ensures bitsConsumed is always set */
|
||||
if (lastByte == 0) return ERROR(GENERIC); /* endMark not present */ }
|
||||
} else {
|
||||
bitD->ptr = bitD->start;
|
||||
bitD->bitContainer = *(const BYTE*)(bitD->start);
|
||||
switch(srcSize)
|
||||
{
|
||||
case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
|
||||
/* fall-through */
|
||||
|
||||
case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
|
||||
/* fall-through */
|
||||
|
||||
case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
|
||||
/* fall-through */
|
||||
|
||||
case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
|
||||
/* fall-through */
|
||||
|
||||
case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
|
||||
/* fall-through */
|
||||
|
||||
case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8;
|
||||
/* fall-through */
|
||||
|
||||
default: break;
|
||||
}
|
||||
{ BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
|
||||
bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0;
|
||||
if (lastByte == 0) return ERROR(corruption_detected); /* endMark not present */
|
||||
}
|
||||
bitD->bitsConsumed += (U32)(sizeof(bitD->bitContainer) - srcSize)*8;
|
||||
}
|
||||
|
||||
return srcSize;
|
||||
}
|
||||
|
||||
MEM_STATIC size_t BIT_getUpperBits(size_t bitContainer, U32 const start)
|
||||
{
|
||||
return bitContainer >> start;
|
||||
}
|
||||
|
||||
MEM_STATIC size_t BIT_getMiddleBits(size_t bitContainer, U32 const start, U32 const nbBits)
|
||||
{
|
||||
#if defined(__BMI__) && defined(__GNUC__) && __GNUC__*1000+__GNUC_MINOR__ >= 4008 /* experimental */
|
||||
# if defined(__x86_64__)
|
||||
if (sizeof(bitContainer)==8)
|
||||
return _bextr_u64(bitContainer, start, nbBits);
|
||||
else
|
||||
# endif
|
||||
return _bextr_u32(bitContainer, start, nbBits);
|
||||
#else
|
||||
assert(nbBits < BIT_MASK_SIZE);
|
||||
return (bitContainer >> start) & BIT_mask[nbBits];
|
||||
#endif
|
||||
}
|
||||
|
||||
MEM_STATIC size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits)
|
||||
{
|
||||
assert(nbBits < BIT_MASK_SIZE);
|
||||
return bitContainer & BIT_mask[nbBits];
|
||||
}
|
||||
|
||||
/*! BIT_lookBits() :
|
||||
* Provides next n bits from local register.
|
||||
* local register is not modified.
|
||||
* On 32-bits, maxNbBits==24.
|
||||
* On 64-bits, maxNbBits==56.
|
||||
* @return : value extracted */
|
||||
MEM_STATIC size_t BIT_lookBits(const BIT_DStream_t* bitD, U32 nbBits)
|
||||
{
|
||||
#if defined(__BMI__) && defined(__GNUC__) /* experimental; fails if bitD->bitsConsumed + nbBits > sizeof(bitD->bitContainer)*8 */
|
||||
return BIT_getMiddleBits(bitD->bitContainer, (sizeof(bitD->bitContainer)*8) - bitD->bitsConsumed - nbBits, nbBits);
|
||||
#else
|
||||
U32 const regMask = sizeof(bitD->bitContainer)*8 - 1;
|
||||
return ((bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> 1) >> ((regMask-nbBits) & regMask);
|
||||
#endif
|
||||
}
|
||||
|
||||
/*! BIT_lookBitsFast() :
|
||||
* unsafe version; only works if nbBits >= 1 */
|
||||
MEM_STATIC size_t BIT_lookBitsFast(const BIT_DStream_t* bitD, U32 nbBits)
|
||||
{
|
||||
U32 const regMask = sizeof(bitD->bitContainer)*8 - 1;
|
||||
assert(nbBits >= 1);
|
||||
return (bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> (((regMask+1)-nbBits) & regMask);
|
||||
}
|
||||
|
||||
MEM_STATIC void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits)
|
||||
{
|
||||
bitD->bitsConsumed += nbBits;
|
||||
}
|
||||
|
||||
/*! BIT_readBits() :
|
||||
* Read (consume) next n bits from local register and update.
|
||||
* Pay attention to not read more than nbBits contained into local register.
|
||||
* @return : extracted value. */
|
||||
MEM_STATIC size_t BIT_readBits(BIT_DStream_t* bitD, U32 nbBits)
|
||||
{
|
||||
size_t const value = BIT_lookBits(bitD, nbBits);
|
||||
BIT_skipBits(bitD, nbBits);
|
||||
return value;
|
||||
}
|
||||
|
||||
/*! BIT_readBitsFast() :
|
||||
* unsafe version; only works only if nbBits >= 1 */
|
||||
MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, U32 nbBits)
|
||||
{
|
||||
size_t const value = BIT_lookBitsFast(bitD, nbBits);
|
||||
assert(nbBits >= 1);
|
||||
BIT_skipBits(bitD, nbBits);
|
||||
return value;
|
||||
}
|
||||
|
||||
/*! BIT_reloadDStream() :
|
||||
* Refill `bitD` from buffer previously set in BIT_initDStream() .
|
||||
* This function is safe, it guarantees it will not read beyond src buffer.
|
||||
* @return : status of `BIT_DStream_t` internal register.
|
||||
* when status == BIT_DStream_unfinished, internal register is filled with at least 25 or 57 bits */
|
||||
MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD)
|
||||
{
|
||||
if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* overflow detected, like end of stream */
|
||||
return BIT_DStream_overflow;
|
||||
|
||||
if (bitD->ptr >= bitD->limitPtr) {
|
||||
bitD->ptr -= bitD->bitsConsumed >> 3;
|
||||
bitD->bitsConsumed &= 7;
|
||||
bitD->bitContainer = MEM_readLEST(bitD->ptr);
|
||||
return BIT_DStream_unfinished;
|
||||
}
|
||||
if (bitD->ptr == bitD->start) {
|
||||
if (bitD->bitsConsumed < sizeof(bitD->bitContainer)*8) return BIT_DStream_endOfBuffer;
|
||||
return BIT_DStream_completed;
|
||||
}
|
||||
/* start < ptr < limitPtr */
|
||||
{ U32 nbBytes = bitD->bitsConsumed >> 3;
|
||||
BIT_DStream_status result = BIT_DStream_unfinished;
|
||||
if (bitD->ptr - nbBytes < bitD->start) {
|
||||
nbBytes = (U32)(bitD->ptr - bitD->start); /* ptr > start */
|
||||
result = BIT_DStream_endOfBuffer;
|
||||
}
|
||||
bitD->ptr -= nbBytes;
|
||||
bitD->bitsConsumed -= nbBytes*8;
|
||||
bitD->bitContainer = MEM_readLEST(bitD->ptr); /* reminder : srcSize > sizeof(bitD->bitContainer), otherwise bitD->ptr == bitD->start */
|
||||
return result;
|
||||
}
|
||||
}
|
||||
|
||||
/*! BIT_endOfDStream() :
|
||||
* @return : 1 if DStream has _exactly_ reached its end (all bits consumed).
|
||||
*/
|
||||
MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* DStream)
|
||||
{
|
||||
return ((DStream->ptr == DStream->start) && (DStream->bitsConsumed == sizeof(DStream->bitContainer)*8));
|
||||
}
|
||||
|
||||
#if defined (__cplusplus)
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif /* BITSTREAM_H_MODULE */
|
||||
|
|
@ -0,0 +1,133 @@
|
|||
/*
|
||||
* Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
|
||||
* All rights reserved.
|
||||
*
|
||||
* This source code is licensed under both the BSD-style license (found in the
|
||||
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
|
||||
* in the COPYING file in the root directory of this source tree).
|
||||
* You may select, at your option, one of the above-listed licenses.
|
||||
*/
|
||||
|
||||
#ifndef ZSTD_COMPILER_H
|
||||
#define ZSTD_COMPILER_H
|
||||
|
||||
/*-*******************************************************
|
||||
* Compiler specifics
|
||||
*********************************************************/
|
||||
/* force inlining */
|
||||
#if defined (__GNUC__) || defined(__cplusplus) || defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */
|
||||
# define INLINE_KEYWORD inline
|
||||
#else
|
||||
# define INLINE_KEYWORD
|
||||
#endif
|
||||
|
||||
#if defined(__GNUC__)
|
||||
# define FORCE_INLINE_ATTR __attribute__((always_inline))
|
||||
#elif defined(_MSC_VER)
|
||||
# define FORCE_INLINE_ATTR __forceinline
|
||||
#else
|
||||
# define FORCE_INLINE_ATTR
|
||||
#endif
|
||||
|
||||
/**
|
||||
* FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant
|
||||
* parameters. They must be inlined for the compiler to elimininate the constant
|
||||
* branches.
|
||||
*/
|
||||
#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR
|
||||
/**
|
||||
* HINT_INLINE is used to help the compiler generate better code. It is *not*
|
||||
* used for "templates", so it can be tweaked based on the compilers
|
||||
* performance.
|
||||
*
|
||||
* gcc-4.8 and gcc-4.9 have been shown to benefit from leaving off the
|
||||
* always_inline attribute.
|
||||
*
|
||||
* clang up to 5.0.0 (trunk) benefit tremendously from the always_inline
|
||||
* attribute.
|
||||
*/
|
||||
#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 4 && __GNUC_MINOR__ >= 8 && __GNUC__ < 5
|
||||
# define HINT_INLINE static INLINE_KEYWORD
|
||||
#else
|
||||
# define HINT_INLINE static INLINE_KEYWORD FORCE_INLINE_ATTR
|
||||
#endif
|
||||
|
||||
/* force no inlining */
|
||||
#ifdef _MSC_VER
|
||||
# define FORCE_NOINLINE static __declspec(noinline)
|
||||
#else
|
||||
# ifdef __GNUC__
|
||||
# define FORCE_NOINLINE static __attribute__((__noinline__))
|
||||
# else
|
||||
# define FORCE_NOINLINE static
|
||||
# endif
|
||||
#endif
|
||||
|
||||
/* target attribute */
|
||||
#ifndef __has_attribute
|
||||
#define __has_attribute(x) 0 /* Compatibility with non-clang compilers. */
|
||||
#endif
|
||||
#if defined(__GNUC__)
|
||||
# define TARGET_ATTRIBUTE(target) __attribute__((__target__(target)))
|
||||
#else
|
||||
# define TARGET_ATTRIBUTE(target)
|
||||
#endif
|
||||
|
||||
/* Enable runtime BMI2 dispatch based on the CPU.
|
||||
* Enabled for clang & gcc >=4.8 on x86 when BMI2 isn't enabled by default.
|
||||
*/
|
||||
#ifndef DYNAMIC_BMI2
|
||||
#if ((defined(__clang__) && __has_attribute(__target__)) \
|
||||
|| (defined(__GNUC__) \
|
||||
&& (__GNUC__ >= 5 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 8)))) \
|
||||
&& (defined(__x86_64__) || defined(_M_X86)) \
|
||||
&& !defined(__BMI2__)
|
||||
# define DYNAMIC_BMI2 1
|
||||
#else
|
||||
# define DYNAMIC_BMI2 0
|
||||
#endif
|
||||
#endif
|
||||
|
||||
/* prefetch
|
||||
* can be disabled, by declaring NO_PREFETCH macro
|
||||
* All prefetch invocations use a single default locality 2,
|
||||
* generating instruction prefetcht1,
|
||||
* which, according to Intel, means "load data into L2 cache".
|
||||
* This is a good enough "middle ground" for the time being,
|
||||
* though in theory, it would be better to specialize locality depending on data being prefetched.
|
||||
* Tests could not determine any sensible difference based on locality value. */
|
||||
#if defined(NO_PREFETCH)
|
||||
# define PREFETCH(ptr) (void)(ptr) /* disabled */
|
||||
#else
|
||||
# if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_I86)) /* _mm_prefetch() is not defined outside of x86/x64 */
|
||||
# include <mmintrin.h> /* https://msdn.microsoft.com/fr-fr/library/84szxsww(v=vs.90).aspx */
|
||||
# define PREFETCH(ptr) _mm_prefetch((const char*)(ptr), _MM_HINT_T1)
|
||||
# elif defined(__GNUC__) && ( (__GNUC__ >= 4) || ( (__GNUC__ == 3) && (__GNUC_MINOR__ >= 1) ) )
|
||||
# define PREFETCH(ptr) __builtin_prefetch((ptr), 0 /* rw==read */, 2 /* locality */)
|
||||
# else
|
||||
# define PREFETCH(ptr) (void)(ptr) /* disabled */
|
||||
# endif
|
||||
#endif /* NO_PREFETCH */
|
||||
|
||||
#define CACHELINE_SIZE 64
|
||||
|
||||
#define PREFETCH_AREA(p, s) { \
|
||||
const char* const _ptr = (const char*)(p); \
|
||||
size_t const _size = (size_t)(s); \
|
||||
size_t _pos; \
|
||||
for (_pos=0; _pos<_size; _pos+=CACHELINE_SIZE) { \
|
||||
PREFETCH(_ptr + _pos); \
|
||||
} \
|
||||
}
|
||||
|
||||
/* disable warnings */
|
||||
#ifdef _MSC_VER /* Visual Studio */
|
||||
# include <intrin.h> /* For Visual 2005 */
|
||||
# pragma warning(disable : 4100) /* disable: C4100: unreferenced formal parameter */
|
||||
# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
|
||||
# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */
|
||||
# pragma warning(disable : 4214) /* disable: C4214: non-int bitfields */
|
||||
# pragma warning(disable : 4324) /* disable: C4324: padded structure */
|
||||
#endif
|
||||
|
||||
#endif /* ZSTD_COMPILER_H */
|
||||
|
|
@ -0,0 +1,215 @@
|
|||
/*
|
||||
* Copyright (c) 2018-present, Facebook, Inc.
|
||||
* All rights reserved.
|
||||
*
|
||||
* This source code is licensed under both the BSD-style license (found in the
|
||||
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
|
||||
* in the COPYING file in the root directory of this source tree).
|
||||
* You may select, at your option, one of the above-listed licenses.
|
||||
*/
|
||||
|
||||
#ifndef ZSTD_COMMON_CPU_H
|
||||
#define ZSTD_COMMON_CPU_H
|
||||
|
||||
/**
|
||||
* Implementation taken from folly/CpuId.h
|
||||
* https://github.com/facebook/folly/blob/master/folly/CpuId.h
|
||||
*/
|
||||
|
||||
#include <string.h>
|
||||
|
||||
#include "mem.h"
|
||||
|
||||
#ifdef _MSC_VER
|
||||
#include <intrin.h>
|
||||
#endif
|
||||
|
||||
typedef struct {
|
||||
U32 f1c;
|
||||
U32 f1d;
|
||||
U32 f7b;
|
||||
U32 f7c;
|
||||
} ZSTD_cpuid_t;
|
||||
|
||||
MEM_STATIC ZSTD_cpuid_t ZSTD_cpuid(void) {
|
||||
U32 f1c = 0;
|
||||
U32 f1d = 0;
|
||||
U32 f7b = 0;
|
||||
U32 f7c = 0;
|
||||
#if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_IX86))
|
||||
int reg[4];
|
||||
__cpuid((int*)reg, 0);
|
||||
{
|
||||
int const n = reg[0];
|
||||
if (n >= 1) {
|
||||
__cpuid((int*)reg, 1);
|
||||
f1c = (U32)reg[2];
|
||||
f1d = (U32)reg[3];
|
||||
}
|
||||
if (n >= 7) {
|
||||
__cpuidex((int*)reg, 7, 0);
|
||||
f7b = (U32)reg[1];
|
||||
f7c = (U32)reg[2];
|
||||
}
|
||||
}
|
||||
#elif defined(__i386__) && defined(__PIC__) && !defined(__clang__) && defined(__GNUC__)
|
||||
/* The following block like the normal cpuid branch below, but gcc
|
||||
* reserves ebx for use of its pic register so we must specially
|
||||
* handle the save and restore to avoid clobbering the register
|
||||
*/
|
||||
U32 n;
|
||||
__asm__(
|
||||
"pushl %%ebx\n\t"
|
||||
"cpuid\n\t"
|
||||
"popl %%ebx\n\t"
|
||||
: "=a"(n)
|
||||
: "a"(0)
|
||||
: "ecx", "edx");
|
||||
if (n >= 1) {
|
||||
U32 f1a;
|
||||
__asm__(
|
||||
"pushl %%ebx\n\t"
|
||||
"cpuid\n\t"
|
||||
"popl %%ebx\n\t"
|
||||
: "=a"(f1a), "=c"(f1c), "=d"(f1d)
|
||||
: "a"(1));
|
||||
}
|
||||
if (n >= 7) {
|
||||
__asm__(
|
||||
"pushl %%ebx\n\t"
|
||||
"cpuid\n\t"
|
||||
"movl %%ebx, %%eax\n\r"
|
||||
"popl %%ebx"
|
||||
: "=a"(f7b), "=c"(f7c)
|
||||
: "a"(7), "c"(0)
|
||||
: "edx");
|
||||
}
|
||||
#elif defined(__x86_64__) || defined(_M_X64) || defined(__i386__)
|
||||
U32 n;
|
||||
__asm__("cpuid" : "=a"(n) : "a"(0) : "ebx", "ecx", "edx");
|
||||
if (n >= 1) {
|
||||
U32 f1a;
|
||||
__asm__("cpuid" : "=a"(f1a), "=c"(f1c), "=d"(f1d) : "a"(1) : "ebx");
|
||||
}
|
||||
if (n >= 7) {
|
||||
U32 f7a;
|
||||
__asm__("cpuid"
|
||||
: "=a"(f7a), "=b"(f7b), "=c"(f7c)
|
||||
: "a"(7), "c"(0)
|
||||
: "edx");
|
||||
}
|
||||
#endif
|
||||
{
|
||||
ZSTD_cpuid_t cpuid;
|
||||
cpuid.f1c = f1c;
|
||||
cpuid.f1d = f1d;
|
||||
cpuid.f7b = f7b;
|
||||
cpuid.f7c = f7c;
|
||||
return cpuid;
|
||||
}
|
||||
}
|
||||
|
||||
#define X(name, r, bit) \
|
||||
MEM_STATIC int ZSTD_cpuid_##name(ZSTD_cpuid_t const cpuid) { \
|
||||
return ((cpuid.r) & (1U << bit)) != 0; \
|
||||
}
|
||||
|
||||
/* cpuid(1): Processor Info and Feature Bits. */
|
||||
#define C(name, bit) X(name, f1c, bit)
|
||||
C(sse3, 0)
|
||||
C(pclmuldq, 1)
|
||||
C(dtes64, 2)
|
||||
C(monitor, 3)
|
||||
C(dscpl, 4)
|
||||
C(vmx, 5)
|
||||
C(smx, 6)
|
||||
C(eist, 7)
|
||||
C(tm2, 8)
|
||||
C(ssse3, 9)
|
||||
C(cnxtid, 10)
|
||||
C(fma, 12)
|
||||
C(cx16, 13)
|
||||
C(xtpr, 14)
|
||||
C(pdcm, 15)
|
||||
C(pcid, 17)
|
||||
C(dca, 18)
|
||||
C(sse41, 19)
|
||||
C(sse42, 20)
|
||||
C(x2apic, 21)
|
||||
C(movbe, 22)
|
||||
C(popcnt, 23)
|
||||
C(tscdeadline, 24)
|
||||
C(aes, 25)
|
||||
C(xsave, 26)
|
||||
C(osxsave, 27)
|
||||
C(avx, 28)
|
||||
C(f16c, 29)
|
||||
C(rdrand, 30)
|
||||
#undef C
|
||||
#define D(name, bit) X(name, f1d, bit)
|
||||
D(fpu, 0)
|
||||
D(vme, 1)
|
||||
D(de, 2)
|
||||
D(pse, 3)
|
||||
D(tsc, 4)
|
||||
D(msr, 5)
|
||||
D(pae, 6)
|
||||
D(mce, 7)
|
||||
D(cx8, 8)
|
||||
D(apic, 9)
|
||||
D(sep, 11)
|
||||
D(mtrr, 12)
|
||||
D(pge, 13)
|
||||
D(mca, 14)
|
||||
D(cmov, 15)
|
||||
D(pat, 16)
|
||||
D(pse36, 17)
|
||||
D(psn, 18)
|
||||
D(clfsh, 19)
|
||||
D(ds, 21)
|
||||
D(acpi, 22)
|
||||
D(mmx, 23)
|
||||
D(fxsr, 24)
|
||||
D(sse, 25)
|
||||
D(sse2, 26)
|
||||
D(ss, 27)
|
||||
D(htt, 28)
|
||||
D(tm, 29)
|
||||
D(pbe, 31)
|
||||
#undef D
|
||||
|
||||
/* cpuid(7): Extended Features. */
|
||||
#define B(name, bit) X(name, f7b, bit)
|
||||
B(bmi1, 3)
|
||||
B(hle, 4)
|
||||
B(avx2, 5)
|
||||
B(smep, 7)
|
||||
B(bmi2, 8)
|
||||
B(erms, 9)
|
||||
B(invpcid, 10)
|
||||
B(rtm, 11)
|
||||
B(mpx, 14)
|
||||
B(avx512f, 16)
|
||||
B(avx512dq, 17)
|
||||
B(rdseed, 18)
|
||||
B(adx, 19)
|
||||
B(smap, 20)
|
||||
B(avx512ifma, 21)
|
||||
B(pcommit, 22)
|
||||
B(clflushopt, 23)
|
||||
B(clwb, 24)
|
||||
B(avx512pf, 26)
|
||||
B(avx512er, 27)
|
||||
B(avx512cd, 28)
|
||||
B(sha, 29)
|
||||
B(avx512bw, 30)
|
||||
B(avx512vl, 31)
|
||||
#undef B
|
||||
#define C(name, bit) X(name, f7c, bit)
|
||||
C(prefetchwt1, 0)
|
||||
C(avx512vbmi, 1)
|
||||
#undef C
|
||||
|
||||
#undef X
|
||||
|
||||
#endif /* ZSTD_COMMON_CPU_H */
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
/* ******************************************************************
|
||||
debug
|
||||
Part of FSE library
|
||||
Copyright (C) 2013-present, Yann Collet.
|
||||
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- Source repository : https://github.com/Cyan4973/FiniteStateEntropy
|
||||
****************************************************************** */
|
||||
|
||||
|
||||
/*
|
||||
* This module only hosts one global variable
|
||||
* which can be used to dynamically influence the verbosity of traces,
|
||||
* such as DEBUGLOG and RAWLOG
|
||||
*/
|
||||
|
||||
#include "debug.h"
|
||||
|
||||
int g_debuglevel = DEBUGLEVEL;
|
||||
|
|
@ -0,0 +1,123 @@
|
|||
/* ******************************************************************
|
||||
debug
|
||||
Part of FSE library
|
||||
Copyright (C) 2013-present, Yann Collet.
|
||||
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- Source repository : https://github.com/Cyan4973/FiniteStateEntropy
|
||||
****************************************************************** */
|
||||
|
||||
|
||||
/*
|
||||
* The purpose of this header is to enable debug functions.
|
||||
* They regroup assert(), DEBUGLOG() and RAWLOG() for run-time,
|
||||
* and DEBUG_STATIC_ASSERT() for compile-time.
|
||||
*
|
||||
* By default, DEBUGLEVEL==0, which means run-time debug is disabled.
|
||||
*
|
||||
* Level 1 enables assert() only.
|
||||
* Starting level 2, traces can be generated and pushed to stderr.
|
||||
* The higher the level, the more verbose the traces.
|
||||
*
|
||||
* It's possible to dynamically adjust level using variable g_debug_level,
|
||||
* which is only declared if DEBUGLEVEL>=2,
|
||||
* and is a global variable, not multi-thread protected (use with care)
|
||||
*/
|
||||
|
||||
#ifndef DEBUG_H_12987983217
|
||||
#define DEBUG_H_12987983217
|
||||
|
||||
#if defined (__cplusplus)
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
|
||||
/* static assert is triggered at compile time, leaving no runtime artefact,
|
||||
* but can only work with compile-time constants.
|
||||
* This variant can only be used inside a function. */
|
||||
#define DEBUG_STATIC_ASSERT(c) (void)sizeof(char[(c) ? 1 : -1])
|
||||
|
||||
|
||||
/* DEBUGLEVEL is expected to be defined externally,
|
||||
* typically through compiler command line.
|
||||
* Value must be a number. */
|
||||
#ifndef DEBUGLEVEL
|
||||
# define DEBUGLEVEL 0
|
||||
#endif
|
||||
|
||||
/* recommended values for DEBUGLEVEL :
|
||||
* 0 : no debug, all run-time functions disabled
|
||||
* 1 : no display, enables assert() only
|
||||
* 2 : reserved, for currently active debug path
|
||||
* 3 : events once per object lifetime (CCtx, CDict, etc.)
|
||||
* 4 : events once per frame
|
||||
* 5 : events once per block
|
||||
* 6 : events once per sequence (verbose)
|
||||
* 7+: events at every position (*very* verbose)
|
||||
*
|
||||
* It's generally inconvenient to output traces > 5.
|
||||
* In which case, it's possible to selectively enable higher verbosity levels
|
||||
* by modifying g_debug_level.
|
||||
*/
|
||||
|
||||
#if (DEBUGLEVEL>=1)
|
||||
# include <assert.h>
|
||||
#else
|
||||
# ifndef assert /* assert may be already defined, due to prior #include <assert.h> */
|
||||
# define assert(condition) ((void)0) /* disable assert (default) */
|
||||
# endif
|
||||
#endif
|
||||
|
||||
#if (DEBUGLEVEL>=2)
|
||||
# include <stdio.h>
|
||||
extern int g_debuglevel; /* here, this variable is only declared,
|
||||
it actually lives in debug.c,
|
||||
and is shared by the whole process.
|
||||
It's typically used to enable very verbose levels
|
||||
on selective conditions (such as position in src) */
|
||||
|
||||
# define RAWLOG(l, ...) { \
|
||||
if (l<=g_debuglevel) { \
|
||||
fprintf(stderr, __VA_ARGS__); \
|
||||
} }
|
||||
# define DEBUGLOG(l, ...) { \
|
||||
if (l<=g_debuglevel) { \
|
||||
fprintf(stderr, __FILE__ ": " __VA_ARGS__); \
|
||||
fprintf(stderr, " \n"); \
|
||||
} }
|
||||
#else
|
||||
# define RAWLOG(l, ...) {} /* disabled */
|
||||
# define DEBUGLOG(l, ...) {} /* disabled */
|
||||
#endif
|
||||
|
||||
|
||||
#if defined (__cplusplus)
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif /* DEBUG_H_12987983217 */
|
||||
|
|
@ -0,0 +1,236 @@
|
|||
/*
|
||||
Common functions of New Generation Entropy library
|
||||
Copyright (C) 2016, Yann Collet.
|
||||
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- FSE+HUF source repository : https://github.com/Cyan4973/FiniteStateEntropy
|
||||
- Public forum : https://groups.google.com/forum/#!forum/lz4c
|
||||
*************************************************************************** */
|
||||
|
||||
/* *************************************
|
||||
* Dependencies
|
||||
***************************************/
|
||||
#include "mem.h"
|
||||
#include "error_private.h" /* ERR_*, ERROR */
|
||||
#define FSE_STATIC_LINKING_ONLY /* FSE_MIN_TABLELOG */
|
||||
#include "fse.h"
|
||||
#define HUF_STATIC_LINKING_ONLY /* HUF_TABLELOG_ABSOLUTEMAX */
|
||||
#include "huf.h"
|
||||
|
||||
|
||||
/*=== Version ===*/
|
||||
unsigned FSE_versionNumber(void) { return FSE_VERSION_NUMBER; }
|
||||
|
||||
|
||||
/*=== Error Management ===*/
|
||||
unsigned FSE_isError(size_t code) { return ERR_isError(code); }
|
||||
const char* FSE_getErrorName(size_t code) { return ERR_getErrorName(code); }
|
||||
|
||||
unsigned HUF_isError(size_t code) { return ERR_isError(code); }
|
||||
const char* HUF_getErrorName(size_t code) { return ERR_getErrorName(code); }
|
||||
|
||||
|
||||
/*-**************************************************************
|
||||
* FSE NCount encoding-decoding
|
||||
****************************************************************/
|
||||
size_t FSE_readNCount (short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr,
|
||||
const void* headerBuffer, size_t hbSize)
|
||||
{
|
||||
const BYTE* const istart = (const BYTE*) headerBuffer;
|
||||
const BYTE* const iend = istart + hbSize;
|
||||
const BYTE* ip = istart;
|
||||
int nbBits;
|
||||
int remaining;
|
||||
int threshold;
|
||||
U32 bitStream;
|
||||
int bitCount;
|
||||
unsigned charnum = 0;
|
||||
int previous0 = 0;
|
||||
|
||||
if (hbSize < 4) {
|
||||
/* This function only works when hbSize >= 4 */
|
||||
char buffer[4];
|
||||
memset(buffer, 0, sizeof(buffer));
|
||||
memcpy(buffer, headerBuffer, hbSize);
|
||||
{ size_t const countSize = FSE_readNCount(normalizedCounter, maxSVPtr, tableLogPtr,
|
||||
buffer, sizeof(buffer));
|
||||
if (FSE_isError(countSize)) return countSize;
|
||||
if (countSize > hbSize) return ERROR(corruption_detected);
|
||||
return countSize;
|
||||
} }
|
||||
assert(hbSize >= 4);
|
||||
|
||||
/* init */
|
||||
memset(normalizedCounter, 0, (*maxSVPtr+1) * sizeof(normalizedCounter[0])); /* all symbols not present in NCount have a frequency of 0 */
|
||||
bitStream = MEM_readLE32(ip);
|
||||
nbBits = (bitStream & 0xF) + FSE_MIN_TABLELOG; /* extract tableLog */
|
||||
if (nbBits > FSE_TABLELOG_ABSOLUTE_MAX) return ERROR(tableLog_tooLarge);
|
||||
bitStream >>= 4;
|
||||
bitCount = 4;
|
||||
*tableLogPtr = nbBits;
|
||||
remaining = (1<<nbBits)+1;
|
||||
threshold = 1<<nbBits;
|
||||
nbBits++;
|
||||
|
||||
while ((remaining>1) & (charnum<=*maxSVPtr)) {
|
||||
if (previous0) {
|
||||
unsigned n0 = charnum;
|
||||
while ((bitStream & 0xFFFF) == 0xFFFF) {
|
||||
n0 += 24;
|
||||
if (ip < iend-5) {
|
||||
ip += 2;
|
||||
bitStream = MEM_readLE32(ip) >> bitCount;
|
||||
} else {
|
||||
bitStream >>= 16;
|
||||
bitCount += 16;
|
||||
} }
|
||||
while ((bitStream & 3) == 3) {
|
||||
n0 += 3;
|
||||
bitStream >>= 2;
|
||||
bitCount += 2;
|
||||
}
|
||||
n0 += bitStream & 3;
|
||||
bitCount += 2;
|
||||
if (n0 > *maxSVPtr) return ERROR(maxSymbolValue_tooSmall);
|
||||
while (charnum < n0) normalizedCounter[charnum++] = 0;
|
||||
if ((ip <= iend-7) || (ip + (bitCount>>3) <= iend-4)) {
|
||||
assert((bitCount >> 3) <= 3); /* For first condition to work */
|
||||
ip += bitCount>>3;
|
||||
bitCount &= 7;
|
||||
bitStream = MEM_readLE32(ip) >> bitCount;
|
||||
} else {
|
||||
bitStream >>= 2;
|
||||
} }
|
||||
{ int const max = (2*threshold-1) - remaining;
|
||||
int count;
|
||||
|
||||
if ((bitStream & (threshold-1)) < (U32)max) {
|
||||
count = bitStream & (threshold-1);
|
||||
bitCount += nbBits-1;
|
||||
} else {
|
||||
count = bitStream & (2*threshold-1);
|
||||
if (count >= threshold) count -= max;
|
||||
bitCount += nbBits;
|
||||
}
|
||||
|
||||
count--; /* extra accuracy */
|
||||
remaining -= count < 0 ? -count : count; /* -1 means +1 */
|
||||
normalizedCounter[charnum++] = (short)count;
|
||||
previous0 = !count;
|
||||
while (remaining < threshold) {
|
||||
nbBits--;
|
||||
threshold >>= 1;
|
||||
}
|
||||
|
||||
if ((ip <= iend-7) || (ip + (bitCount>>3) <= iend-4)) {
|
||||
ip += bitCount>>3;
|
||||
bitCount &= 7;
|
||||
} else {
|
||||
bitCount -= (int)(8 * (iend - 4 - ip));
|
||||
ip = iend - 4;
|
||||
}
|
||||
bitStream = MEM_readLE32(ip) >> (bitCount & 31);
|
||||
} } /* while ((remaining>1) & (charnum<=*maxSVPtr)) */
|
||||
if (remaining != 1) return ERROR(corruption_detected);
|
||||
if (bitCount > 32) return ERROR(corruption_detected);
|
||||
*maxSVPtr = charnum-1;
|
||||
|
||||
ip += (bitCount+7)>>3;
|
||||
return ip-istart;
|
||||
}
|
||||
|
||||
|
||||
/*! HUF_readStats() :
|
||||
Read compact Huffman tree, saved by HUF_writeCTable().
|
||||
`huffWeight` is destination buffer.
|
||||
`rankStats` is assumed to be a table of at least HUF_TABLELOG_MAX U32.
|
||||
@return : size read from `src` , or an error Code .
|
||||
Note : Needed by HUF_readCTable() and HUF_readDTableX?() .
|
||||
*/
|
||||
size_t HUF_readStats(BYTE* huffWeight, size_t hwSize, U32* rankStats,
|
||||
U32* nbSymbolsPtr, U32* tableLogPtr,
|
||||
const void* src, size_t srcSize)
|
||||
{
|
||||
U32 weightTotal;
|
||||
const BYTE* ip = (const BYTE*) src;
|
||||
size_t iSize;
|
||||
size_t oSize;
|
||||
|
||||
if (!srcSize) return ERROR(srcSize_wrong);
|
||||
iSize = ip[0];
|
||||
/* memset(huffWeight, 0, hwSize); *//* is not necessary, even though some analyzer complain ... */
|
||||
|
||||
if (iSize >= 128) { /* special header */
|
||||
oSize = iSize - 127;
|
||||
iSize = ((oSize+1)/2);
|
||||
if (iSize+1 > srcSize) return ERROR(srcSize_wrong);
|
||||
if (oSize >= hwSize) return ERROR(corruption_detected);
|
||||
ip += 1;
|
||||
{ U32 n;
|
||||
for (n=0; n<oSize; n+=2) {
|
||||
huffWeight[n] = ip[n/2] >> 4;
|
||||
huffWeight[n+1] = ip[n/2] & 15;
|
||||
} } }
|
||||
else { /* header compressed with FSE (normal case) */
|
||||
FSE_DTable fseWorkspace[FSE_DTABLE_SIZE_U32(6)]; /* 6 is max possible tableLog for HUF header (maybe even 5, to be tested) */
|
||||
if (iSize+1 > srcSize) return ERROR(srcSize_wrong);
|
||||
oSize = FSE_decompress_wksp(huffWeight, hwSize-1, ip+1, iSize, fseWorkspace, 6); /* max (hwSize-1) values decoded, as last one is implied */
|
||||
if (FSE_isError(oSize)) return oSize;
|
||||
}
|
||||
|
||||
/* collect weight stats */
|
||||
memset(rankStats, 0, (HUF_TABLELOG_MAX + 1) * sizeof(U32));
|
||||
weightTotal = 0;
|
||||
{ U32 n; for (n=0; n<oSize; n++) {
|
||||
if (huffWeight[n] >= HUF_TABLELOG_MAX) return ERROR(corruption_detected);
|
||||
rankStats[huffWeight[n]]++;
|
||||
weightTotal += (1 << huffWeight[n]) >> 1;
|
||||
} }
|
||||
if (weightTotal == 0) return ERROR(corruption_detected);
|
||||
|
||||
/* get last non-null symbol weight (implied, total must be 2^n) */
|
||||
{ U32 const tableLog = BIT_highbit32(weightTotal) + 1;
|
||||
if (tableLog > HUF_TABLELOG_MAX) return ERROR(corruption_detected);
|
||||
*tableLogPtr = tableLog;
|
||||
/* determine last weight */
|
||||
{ U32 const total = 1 << tableLog;
|
||||
U32 const rest = total - weightTotal;
|
||||
U32 const verif = 1 << BIT_highbit32(rest);
|
||||
U32 const lastWeight = BIT_highbit32(rest) + 1;
|
||||
if (verif != rest) return ERROR(corruption_detected); /* last value must be a clean power of 2 */
|
||||
huffWeight[oSize] = (BYTE)lastWeight;
|
||||
rankStats[lastWeight]++;
|
||||
} }
|
||||
|
||||
/* check tree construction validity */
|
||||
if ((rankStats[1] < 2) || (rankStats[1] & 1)) return ERROR(corruption_detected); /* by construction : at least 2 elts of rank 1, must be even */
|
||||
|
||||
/* results */
|
||||
*nbSymbolsPtr = (U32)(oSize+1);
|
||||
return iSize+1;
|
||||
}
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
/*
|
||||
* Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
|
||||
* All rights reserved.
|
||||
*
|
||||
* This source code is licensed under both the BSD-style license (found in the
|
||||
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
|
||||
* in the COPYING file in the root directory of this source tree).
|
||||
* You may select, at your option, one of the above-listed licenses.
|
||||
*/
|
||||
|
||||
/* The purpose of this file is to have a single list of error strings embedded in binary */
|
||||
|
||||
#include "error_private.h"
|
||||
|
||||
const char* ERR_getErrorString(ERR_enum code)
|
||||
{
|
||||
static const char* const notErrorCode = "Unspecified error code";
|
||||
switch( code )
|
||||
{
|
||||
case PREFIX(no_error): return "No error detected";
|
||||
case PREFIX(GENERIC): return "Error (generic)";
|
||||
case PREFIX(prefix_unknown): return "Unknown frame descriptor";
|
||||
case PREFIX(version_unsupported): return "Version not supported";
|
||||
case PREFIX(frameParameter_unsupported): return "Unsupported frame parameter";
|
||||
case PREFIX(frameParameter_windowTooLarge): return "Frame requires too much memory for decoding";
|
||||
case PREFIX(corruption_detected): return "Corrupted block detected";
|
||||
case PREFIX(checksum_wrong): return "Restored data doesn't match checksum";
|
||||
case PREFIX(parameter_unsupported): return "Unsupported parameter";
|
||||
case PREFIX(parameter_outOfBound): return "Parameter is out of bound";
|
||||
case PREFIX(init_missing): return "Context should be init first";
|
||||
case PREFIX(memory_allocation): return "Allocation error : not enough memory";
|
||||
case PREFIX(workSpace_tooSmall): return "workSpace buffer is not large enough";
|
||||
case PREFIX(stage_wrong): return "Operation not authorized at current processing stage";
|
||||
case PREFIX(tableLog_tooLarge): return "tableLog requires too much memory : unsupported";
|
||||
case PREFIX(maxSymbolValue_tooLarge): return "Unsupported max Symbol Value : too large";
|
||||
case PREFIX(maxSymbolValue_tooSmall): return "Specified maxSymbolValue is too small";
|
||||
case PREFIX(dictionary_corrupted): return "Dictionary is corrupted";
|
||||
case PREFIX(dictionary_wrong): return "Dictionary mismatch";
|
||||
case PREFIX(dictionaryCreation_failed): return "Cannot create Dictionary from provided samples";
|
||||
case PREFIX(dstSize_tooSmall): return "Destination buffer is too small";
|
||||
case PREFIX(srcSize_wrong): return "Src size is incorrect";
|
||||
/* following error codes are not stable and may be removed or changed in a future version */
|
||||
case PREFIX(frameIndex_tooLarge): return "Frame index is too large";
|
||||
case PREFIX(seekableIO): return "An I/O error occurred when reading/seeking";
|
||||
case PREFIX(maxCode):
|
||||
default: return notErrorCode;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,76 @@
|
|||
/*
|
||||
* Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
|
||||
* All rights reserved.
|
||||
*
|
||||
* This source code is licensed under both the BSD-style license (found in the
|
||||
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
|
||||
* in the COPYING file in the root directory of this source tree).
|
||||
* You may select, at your option, one of the above-listed licenses.
|
||||
*/
|
||||
|
||||
/* Note : this module is expected to remain private, do not expose it */
|
||||
|
||||
#ifndef ERROR_H_MODULE
|
||||
#define ERROR_H_MODULE
|
||||
|
||||
#if defined (__cplusplus)
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
|
||||
/* ****************************************
|
||||
* Dependencies
|
||||
******************************************/
|
||||
#include <stddef.h> /* size_t */
|
||||
#include "zstd_errors.h" /* enum list */
|
||||
|
||||
|
||||
/* ****************************************
|
||||
* Compiler-specific
|
||||
******************************************/
|
||||
#if defined(__GNUC__)
|
||||
# define ERR_STATIC static __attribute__((unused))
|
||||
#elif defined (__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
|
||||
# define ERR_STATIC static inline
|
||||
#elif defined(_MSC_VER)
|
||||
# define ERR_STATIC static __inline
|
||||
#else
|
||||
# define ERR_STATIC static /* this version may generate warnings for unused static functions; disable the relevant warning */
|
||||
#endif
|
||||
|
||||
|
||||
/*-****************************************
|
||||
* Customization (error_public.h)
|
||||
******************************************/
|
||||
typedef ZSTD_ErrorCode ERR_enum;
|
||||
#define PREFIX(name) ZSTD_error_##name
|
||||
|
||||
|
||||
/*-****************************************
|
||||
* Error codes handling
|
||||
******************************************/
|
||||
#undef ERROR /* reported already defined on VS 2015 (Rich Geldreich) */
|
||||
#define ERROR(name) ZSTD_ERROR(name)
|
||||
#define ZSTD_ERROR(name) ((size_t)-PREFIX(name))
|
||||
|
||||
ERR_STATIC unsigned ERR_isError(size_t code) { return (code > ERROR(maxCode)); }
|
||||
|
||||
ERR_STATIC ERR_enum ERR_getErrorCode(size_t code) { if (!ERR_isError(code)) return (ERR_enum)0; return (ERR_enum) (0-code); }
|
||||
|
||||
|
||||
/*-****************************************
|
||||
* Error Strings
|
||||
******************************************/
|
||||
|
||||
const char* ERR_getErrorString(ERR_enum code); /* error_private.c */
|
||||
|
||||
ERR_STATIC const char* ERR_getErrorName(size_t code)
|
||||
{
|
||||
return ERR_getErrorString(ERR_getErrorCode(code));
|
||||
}
|
||||
|
||||
#if defined (__cplusplus)
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif /* ERROR_H_MODULE */
|
||||
|
|
@ -0,0 +1,708 @@
|
|||
/* ******************************************************************
|
||||
FSE : Finite State Entropy codec
|
||||
Public Prototypes declaration
|
||||
Copyright (C) 2013-2016, Yann Collet.
|
||||
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- Source repository : https://github.com/Cyan4973/FiniteStateEntropy
|
||||
****************************************************************** */
|
||||
|
||||
#if defined (__cplusplus)
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#ifndef FSE_H
|
||||
#define FSE_H
|
||||
|
||||
|
||||
/*-*****************************************
|
||||
* Dependencies
|
||||
******************************************/
|
||||
#include <stddef.h> /* size_t, ptrdiff_t */
|
||||
|
||||
|
||||
/*-*****************************************
|
||||
* FSE_PUBLIC_API : control library symbols visibility
|
||||
******************************************/
|
||||
#if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4)
|
||||
# define FSE_PUBLIC_API __attribute__ ((visibility ("default")))
|
||||
#elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) /* Visual expected */
|
||||
# define FSE_PUBLIC_API __declspec(dllexport)
|
||||
#elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1)
|
||||
# define FSE_PUBLIC_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
|
||||
#else
|
||||
# define FSE_PUBLIC_API
|
||||
#endif
|
||||
|
||||
/*------ Version ------*/
|
||||
#define FSE_VERSION_MAJOR 0
|
||||
#define FSE_VERSION_MINOR 9
|
||||
#define FSE_VERSION_RELEASE 0
|
||||
|
||||
#define FSE_LIB_VERSION FSE_VERSION_MAJOR.FSE_VERSION_MINOR.FSE_VERSION_RELEASE
|
||||
#define FSE_QUOTE(str) #str
|
||||
#define FSE_EXPAND_AND_QUOTE(str) FSE_QUOTE(str)
|
||||
#define FSE_VERSION_STRING FSE_EXPAND_AND_QUOTE(FSE_LIB_VERSION)
|
||||
|
||||
#define FSE_VERSION_NUMBER (FSE_VERSION_MAJOR *100*100 + FSE_VERSION_MINOR *100 + FSE_VERSION_RELEASE)
|
||||
FSE_PUBLIC_API unsigned FSE_versionNumber(void); /**< library version number; to be used when checking dll version */
|
||||
|
||||
|
||||
/*-****************************************
|
||||
* FSE simple functions
|
||||
******************************************/
|
||||
/*! FSE_compress() :
|
||||
Compress content of buffer 'src', of size 'srcSize', into destination buffer 'dst'.
|
||||
'dst' buffer must be already allocated. Compression runs faster is dstCapacity >= FSE_compressBound(srcSize).
|
||||
@return : size of compressed data (<= dstCapacity).
|
||||
Special values : if return == 0, srcData is not compressible => Nothing is stored within dst !!!
|
||||
if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression instead.
|
||||
if FSE_isError(return), compression failed (more details using FSE_getErrorName())
|
||||
*/
|
||||
FSE_PUBLIC_API size_t FSE_compress(void* dst, size_t dstCapacity,
|
||||
const void* src, size_t srcSize);
|
||||
|
||||
/*! FSE_decompress():
|
||||
Decompress FSE data from buffer 'cSrc', of size 'cSrcSize',
|
||||
into already allocated destination buffer 'dst', of size 'dstCapacity'.
|
||||
@return : size of regenerated data (<= maxDstSize),
|
||||
or an error code, which can be tested using FSE_isError() .
|
||||
|
||||
** Important ** : FSE_decompress() does not decompress non-compressible nor RLE data !!!
|
||||
Why ? : making this distinction requires a header.
|
||||
Header management is intentionally delegated to the user layer, which can better manage special cases.
|
||||
*/
|
||||
FSE_PUBLIC_API size_t FSE_decompress(void* dst, size_t dstCapacity,
|
||||
const void* cSrc, size_t cSrcSize);
|
||||
|
||||
|
||||
/*-*****************************************
|
||||
* Tool functions
|
||||
******************************************/
|
||||
FSE_PUBLIC_API size_t FSE_compressBound(size_t size); /* maximum compressed size */
|
||||
|
||||
/* Error Management */
|
||||
FSE_PUBLIC_API unsigned FSE_isError(size_t code); /* tells if a return value is an error code */
|
||||
FSE_PUBLIC_API const char* FSE_getErrorName(size_t code); /* provides error code string (useful for debugging) */
|
||||
|
||||
|
||||
/*-*****************************************
|
||||
* FSE advanced functions
|
||||
******************************************/
|
||||
/*! FSE_compress2() :
|
||||
Same as FSE_compress(), but allows the selection of 'maxSymbolValue' and 'tableLog'
|
||||
Both parameters can be defined as '0' to mean : use default value
|
||||
@return : size of compressed data
|
||||
Special values : if return == 0, srcData is not compressible => Nothing is stored within cSrc !!!
|
||||
if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression.
|
||||
if FSE_isError(return), it's an error code.
|
||||
*/
|
||||
FSE_PUBLIC_API size_t FSE_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
|
||||
|
||||
|
||||
/*-*****************************************
|
||||
* FSE detailed API
|
||||
******************************************/
|
||||
/*!
|
||||
FSE_compress() does the following:
|
||||
1. count symbol occurrence from source[] into table count[] (see hist.h)
|
||||
2. normalize counters so that sum(count[]) == Power_of_2 (2^tableLog)
|
||||
3. save normalized counters to memory buffer using writeNCount()
|
||||
4. build encoding table 'CTable' from normalized counters
|
||||
5. encode the data stream using encoding table 'CTable'
|
||||
|
||||
FSE_decompress() does the following:
|
||||
1. read normalized counters with readNCount()
|
||||
2. build decoding table 'DTable' from normalized counters
|
||||
3. decode the data stream using decoding table 'DTable'
|
||||
|
||||
The following API allows targeting specific sub-functions for advanced tasks.
|
||||
For example, it's possible to compress several blocks using the same 'CTable',
|
||||
or to save and provide normalized distribution using external method.
|
||||
*/
|
||||
|
||||
/* *** COMPRESSION *** */
|
||||
|
||||
/*! FSE_optimalTableLog():
|
||||
dynamically downsize 'tableLog' when conditions are met.
|
||||
It saves CPU time, by using smaller tables, while preserving or even improving compression ratio.
|
||||
@return : recommended tableLog (necessarily <= 'maxTableLog') */
|
||||
FSE_PUBLIC_API unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
|
||||
|
||||
/*! FSE_normalizeCount():
|
||||
normalize counts so that sum(count[]) == Power_of_2 (2^tableLog)
|
||||
'normalizedCounter' is a table of short, of minimum size (maxSymbolValue+1).
|
||||
@return : tableLog,
|
||||
or an errorCode, which can be tested using FSE_isError() */
|
||||
FSE_PUBLIC_API size_t FSE_normalizeCount(short* normalizedCounter, unsigned tableLog,
|
||||
const unsigned* count, size_t srcSize, unsigned maxSymbolValue);
|
||||
|
||||
/*! FSE_NCountWriteBound():
|
||||
Provides the maximum possible size of an FSE normalized table, given 'maxSymbolValue' and 'tableLog'.
|
||||
Typically useful for allocation purpose. */
|
||||
FSE_PUBLIC_API size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog);
|
||||
|
||||
/*! FSE_writeNCount():
|
||||
Compactly save 'normalizedCounter' into 'buffer'.
|
||||
@return : size of the compressed table,
|
||||
or an errorCode, which can be tested using FSE_isError(). */
|
||||
FSE_PUBLIC_API size_t FSE_writeNCount (void* buffer, size_t bufferSize,
|
||||
const short* normalizedCounter,
|
||||
unsigned maxSymbolValue, unsigned tableLog);
|
||||
|
||||
/*! Constructor and Destructor of FSE_CTable.
|
||||
Note that FSE_CTable size depends on 'tableLog' and 'maxSymbolValue' */
|
||||
typedef unsigned FSE_CTable; /* don't allocate that. It's only meant to be more restrictive than void* */
|
||||
FSE_PUBLIC_API FSE_CTable* FSE_createCTable (unsigned maxSymbolValue, unsigned tableLog);
|
||||
FSE_PUBLIC_API void FSE_freeCTable (FSE_CTable* ct);
|
||||
|
||||
/*! FSE_buildCTable():
|
||||
Builds `ct`, which must be already allocated, using FSE_createCTable().
|
||||
@return : 0, or an errorCode, which can be tested using FSE_isError() */
|
||||
FSE_PUBLIC_API size_t FSE_buildCTable(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
|
||||
|
||||
/*! FSE_compress_usingCTable():
|
||||
Compress `src` using `ct` into `dst` which must be already allocated.
|
||||
@return : size of compressed data (<= `dstCapacity`),
|
||||
or 0 if compressed data could not fit into `dst`,
|
||||
or an errorCode, which can be tested using FSE_isError() */
|
||||
FSE_PUBLIC_API size_t FSE_compress_usingCTable (void* dst, size_t dstCapacity, const void* src, size_t srcSize, const FSE_CTable* ct);
|
||||
|
||||
/*!
|
||||
Tutorial :
|
||||
----------
|
||||
The first step is to count all symbols. FSE_count() does this job very fast.
|
||||
Result will be saved into 'count', a table of unsigned int, which must be already allocated, and have 'maxSymbolValuePtr[0]+1' cells.
|
||||
'src' is a table of bytes of size 'srcSize'. All values within 'src' MUST be <= maxSymbolValuePtr[0]
|
||||
maxSymbolValuePtr[0] will be updated, with its real value (necessarily <= original value)
|
||||
FSE_count() will return the number of occurrence of the most frequent symbol.
|
||||
This can be used to know if there is a single symbol within 'src', and to quickly evaluate its compressibility.
|
||||
If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()).
|
||||
|
||||
The next step is to normalize the frequencies.
|
||||
FSE_normalizeCount() will ensure that sum of frequencies is == 2 ^'tableLog'.
|
||||
It also guarantees a minimum of 1 to any Symbol with frequency >= 1.
|
||||
You can use 'tableLog'==0 to mean "use default tableLog value".
|
||||
If you are unsure of which tableLog value to use, you can ask FSE_optimalTableLog(),
|
||||
which will provide the optimal valid tableLog given sourceSize, maxSymbolValue, and a user-defined maximum (0 means "default").
|
||||
|
||||
The result of FSE_normalizeCount() will be saved into a table,
|
||||
called 'normalizedCounter', which is a table of signed short.
|
||||
'normalizedCounter' must be already allocated, and have at least 'maxSymbolValue+1' cells.
|
||||
The return value is tableLog if everything proceeded as expected.
|
||||
It is 0 if there is a single symbol within distribution.
|
||||
If there is an error (ex: invalid tableLog value), the function will return an ErrorCode (which can be tested using FSE_isError()).
|
||||
|
||||
'normalizedCounter' can be saved in a compact manner to a memory area using FSE_writeNCount().
|
||||
'buffer' must be already allocated.
|
||||
For guaranteed success, buffer size must be at least FSE_headerBound().
|
||||
The result of the function is the number of bytes written into 'buffer'.
|
||||
If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError(); ex : buffer size too small).
|
||||
|
||||
'normalizedCounter' can then be used to create the compression table 'CTable'.
|
||||
The space required by 'CTable' must be already allocated, using FSE_createCTable().
|
||||
You can then use FSE_buildCTable() to fill 'CTable'.
|
||||
If there is an error, both functions will return an ErrorCode (which can be tested using FSE_isError()).
|
||||
|
||||
'CTable' can then be used to compress 'src', with FSE_compress_usingCTable().
|
||||
Similar to FSE_count(), the convention is that 'src' is assumed to be a table of char of size 'srcSize'
|
||||
The function returns the size of compressed data (without header), necessarily <= `dstCapacity`.
|
||||
If it returns '0', compressed data could not fit into 'dst'.
|
||||
If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()).
|
||||
*/
|
||||
|
||||
|
||||
/* *** DECOMPRESSION *** */
|
||||
|
||||
/*! FSE_readNCount():
|
||||
Read compactly saved 'normalizedCounter' from 'rBuffer'.
|
||||
@return : size read from 'rBuffer',
|
||||
or an errorCode, which can be tested using FSE_isError().
|
||||
maxSymbolValuePtr[0] and tableLogPtr[0] will also be updated with their respective values */
|
||||
FSE_PUBLIC_API size_t FSE_readNCount (short* normalizedCounter,
|
||||
unsigned* maxSymbolValuePtr, unsigned* tableLogPtr,
|
||||
const void* rBuffer, size_t rBuffSize);
|
||||
|
||||
/*! Constructor and Destructor of FSE_DTable.
|
||||
Note that its size depends on 'tableLog' */
|
||||
typedef unsigned FSE_DTable; /* don't allocate that. It's just a way to be more restrictive than void* */
|
||||
FSE_PUBLIC_API FSE_DTable* FSE_createDTable(unsigned tableLog);
|
||||
FSE_PUBLIC_API void FSE_freeDTable(FSE_DTable* dt);
|
||||
|
||||
/*! FSE_buildDTable():
|
||||
Builds 'dt', which must be already allocated, using FSE_createDTable().
|
||||
return : 0, or an errorCode, which can be tested using FSE_isError() */
|
||||
FSE_PUBLIC_API size_t FSE_buildDTable (FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
|
||||
|
||||
/*! FSE_decompress_usingDTable():
|
||||
Decompress compressed source `cSrc` of size `cSrcSize` using `dt`
|
||||
into `dst` which must be already allocated.
|
||||
@return : size of regenerated data (necessarily <= `dstCapacity`),
|
||||
or an errorCode, which can be tested using FSE_isError() */
|
||||
FSE_PUBLIC_API size_t FSE_decompress_usingDTable(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt);
|
||||
|
||||
/*!
|
||||
Tutorial :
|
||||
----------
|
||||
(Note : these functions only decompress FSE-compressed blocks.
|
||||
If block is uncompressed, use memcpy() instead
|
||||
If block is a single repeated byte, use memset() instead )
|
||||
|
||||
The first step is to obtain the normalized frequencies of symbols.
|
||||
This can be performed by FSE_readNCount() if it was saved using FSE_writeNCount().
|
||||
'normalizedCounter' must be already allocated, and have at least 'maxSymbolValuePtr[0]+1' cells of signed short.
|
||||
In practice, that means it's necessary to know 'maxSymbolValue' beforehand,
|
||||
or size the table to handle worst case situations (typically 256).
|
||||
FSE_readNCount() will provide 'tableLog' and 'maxSymbolValue'.
|
||||
The result of FSE_readNCount() is the number of bytes read from 'rBuffer'.
|
||||
Note that 'rBufferSize' must be at least 4 bytes, even if useful information is less than that.
|
||||
If there is an error, the function will return an error code, which can be tested using FSE_isError().
|
||||
|
||||
The next step is to build the decompression tables 'FSE_DTable' from 'normalizedCounter'.
|
||||
This is performed by the function FSE_buildDTable().
|
||||
The space required by 'FSE_DTable' must be already allocated using FSE_createDTable().
|
||||
If there is an error, the function will return an error code, which can be tested using FSE_isError().
|
||||
|
||||
`FSE_DTable` can then be used to decompress `cSrc`, with FSE_decompress_usingDTable().
|
||||
`cSrcSize` must be strictly correct, otherwise decompression will fail.
|
||||
FSE_decompress_usingDTable() result will tell how many bytes were regenerated (<=`dstCapacity`).
|
||||
If there is an error, the function will return an error code, which can be tested using FSE_isError(). (ex: dst buffer too small)
|
||||
*/
|
||||
|
||||
#endif /* FSE_H */
|
||||
|
||||
#if defined(FSE_STATIC_LINKING_ONLY) && !defined(FSE_H_FSE_STATIC_LINKING_ONLY)
|
||||
#define FSE_H_FSE_STATIC_LINKING_ONLY
|
||||
|
||||
/* *** Dependency *** */
|
||||
#include "bitstream.h"
|
||||
|
||||
|
||||
/* *****************************************
|
||||
* Static allocation
|
||||
*******************************************/
|
||||
/* FSE buffer bounds */
|
||||
#define FSE_NCOUNTBOUND 512
|
||||
#define FSE_BLOCKBOUND(size) (size + (size>>7))
|
||||
#define FSE_COMPRESSBOUND(size) (FSE_NCOUNTBOUND + FSE_BLOCKBOUND(size)) /* Macro version, useful for static allocation */
|
||||
|
||||
/* It is possible to statically allocate FSE CTable/DTable as a table of FSE_CTable/FSE_DTable using below macros */
|
||||
#define FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) (1 + (1<<(maxTableLog-1)) + ((maxSymbolValue+1)*2))
|
||||
#define FSE_DTABLE_SIZE_U32(maxTableLog) (1 + (1<<maxTableLog))
|
||||
|
||||
/* or use the size to malloc() space directly. Pay attention to alignment restrictions though */
|
||||
#define FSE_CTABLE_SIZE(maxTableLog, maxSymbolValue) (FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) * sizeof(FSE_CTable))
|
||||
#define FSE_DTABLE_SIZE(maxTableLog) (FSE_DTABLE_SIZE_U32(maxTableLog) * sizeof(FSE_DTable))
|
||||
|
||||
|
||||
/* *****************************************
|
||||
* FSE advanced API
|
||||
***************************************** */
|
||||
|
||||
unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus);
|
||||
/**< same as FSE_optimalTableLog(), which used `minus==2` */
|
||||
|
||||
/* FSE_compress_wksp() :
|
||||
* Same as FSE_compress2(), but using an externally allocated scratch buffer (`workSpace`).
|
||||
* FSE_WKSP_SIZE_U32() provides the minimum size required for `workSpace` as a table of FSE_CTable.
|
||||
*/
|
||||
#define FSE_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) ( FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) + ((maxTableLog > 12) ? (1 << (maxTableLog - 2)) : 1024) )
|
||||
size_t FSE_compress_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
|
||||
|
||||
size_t FSE_buildCTable_raw (FSE_CTable* ct, unsigned nbBits);
|
||||
/**< build a fake FSE_CTable, designed for a flat distribution, where each symbol uses nbBits */
|
||||
|
||||
size_t FSE_buildCTable_rle (FSE_CTable* ct, unsigned char symbolValue);
|
||||
/**< build a fake FSE_CTable, designed to compress always the same symbolValue */
|
||||
|
||||
/* FSE_buildCTable_wksp() :
|
||||
* Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`).
|
||||
* `wkspSize` must be >= `(1<<tableLog)`.
|
||||
*/
|
||||
size_t FSE_buildCTable_wksp(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
|
||||
|
||||
size_t FSE_buildDTable_raw (FSE_DTable* dt, unsigned nbBits);
|
||||
/**< build a fake FSE_DTable, designed to read a flat distribution where each symbol uses nbBits */
|
||||
|
||||
size_t FSE_buildDTable_rle (FSE_DTable* dt, unsigned char symbolValue);
|
||||
/**< build a fake FSE_DTable, designed to always generate the same symbolValue */
|
||||
|
||||
size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, FSE_DTable* workSpace, unsigned maxLog);
|
||||
/**< same as FSE_decompress(), using an externally allocated `workSpace` produced with `FSE_DTABLE_SIZE_U32(maxLog)` */
|
||||
|
||||
typedef enum {
|
||||
FSE_repeat_none, /**< Cannot use the previous table */
|
||||
FSE_repeat_check, /**< Can use the previous table but it must be checked */
|
||||
FSE_repeat_valid /**< Can use the previous table and it is asumed to be valid */
|
||||
} FSE_repeat;
|
||||
|
||||
/* *****************************************
|
||||
* FSE symbol compression API
|
||||
*******************************************/
|
||||
/*!
|
||||
This API consists of small unitary functions, which highly benefit from being inlined.
|
||||
Hence their body are included in next section.
|
||||
*/
|
||||
typedef struct {
|
||||
ptrdiff_t value;
|
||||
const void* stateTable;
|
||||
const void* symbolTT;
|
||||
unsigned stateLog;
|
||||
} FSE_CState_t;
|
||||
|
||||
static void FSE_initCState(FSE_CState_t* CStatePtr, const FSE_CTable* ct);
|
||||
|
||||
static void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* CStatePtr, unsigned symbol);
|
||||
|
||||
static void FSE_flushCState(BIT_CStream_t* bitC, const FSE_CState_t* CStatePtr);
|
||||
|
||||
/**<
|
||||
These functions are inner components of FSE_compress_usingCTable().
|
||||
They allow the creation of custom streams, mixing multiple tables and bit sources.
|
||||
|
||||
A key property to keep in mind is that encoding and decoding are done **in reverse direction**.
|
||||
So the first symbol you will encode is the last you will decode, like a LIFO stack.
|
||||
|
||||
You will need a few variables to track your CStream. They are :
|
||||
|
||||
FSE_CTable ct; // Provided by FSE_buildCTable()
|
||||
BIT_CStream_t bitStream; // bitStream tracking structure
|
||||
FSE_CState_t state; // State tracking structure (can have several)
|
||||
|
||||
|
||||
The first thing to do is to init bitStream and state.
|
||||
size_t errorCode = BIT_initCStream(&bitStream, dstBuffer, maxDstSize);
|
||||
FSE_initCState(&state, ct);
|
||||
|
||||
Note that BIT_initCStream() can produce an error code, so its result should be tested, using FSE_isError();
|
||||
You can then encode your input data, byte after byte.
|
||||
FSE_encodeSymbol() outputs a maximum of 'tableLog' bits at a time.
|
||||
Remember decoding will be done in reverse direction.
|
||||
FSE_encodeByte(&bitStream, &state, symbol);
|
||||
|
||||
At any time, you can also add any bit sequence.
|
||||
Note : maximum allowed nbBits is 25, for compatibility with 32-bits decoders
|
||||
BIT_addBits(&bitStream, bitField, nbBits);
|
||||
|
||||
The above methods don't commit data to memory, they just store it into local register, for speed.
|
||||
Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t).
|
||||
Writing data to memory is a manual operation, performed by the flushBits function.
|
||||
BIT_flushBits(&bitStream);
|
||||
|
||||
Your last FSE encoding operation shall be to flush your last state value(s).
|
||||
FSE_flushState(&bitStream, &state);
|
||||
|
||||
Finally, you must close the bitStream.
|
||||
The function returns the size of CStream in bytes.
|
||||
If data couldn't fit into dstBuffer, it will return a 0 ( == not compressible)
|
||||
If there is an error, it returns an errorCode (which can be tested using FSE_isError()).
|
||||
size_t size = BIT_closeCStream(&bitStream);
|
||||
*/
|
||||
|
||||
|
||||
/* *****************************************
|
||||
* FSE symbol decompression API
|
||||
*******************************************/
|
||||
typedef struct {
|
||||
size_t state;
|
||||
const void* table; /* precise table may vary, depending on U16 */
|
||||
} FSE_DState_t;
|
||||
|
||||
|
||||
static void FSE_initDState(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD, const FSE_DTable* dt);
|
||||
|
||||
static unsigned char FSE_decodeSymbol(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD);
|
||||
|
||||
static unsigned FSE_endOfDState(const FSE_DState_t* DStatePtr);
|
||||
|
||||
/**<
|
||||
Let's now decompose FSE_decompress_usingDTable() into its unitary components.
|
||||
You will decode FSE-encoded symbols from the bitStream,
|
||||
and also any other bitFields you put in, **in reverse order**.
|
||||
|
||||
You will need a few variables to track your bitStream. They are :
|
||||
|
||||
BIT_DStream_t DStream; // Stream context
|
||||
FSE_DState_t DState; // State context. Multiple ones are possible
|
||||
FSE_DTable* DTablePtr; // Decoding table, provided by FSE_buildDTable()
|
||||
|
||||
The first thing to do is to init the bitStream.
|
||||
errorCode = BIT_initDStream(&DStream, srcBuffer, srcSize);
|
||||
|
||||
You should then retrieve your initial state(s)
|
||||
(in reverse flushing order if you have several ones) :
|
||||
errorCode = FSE_initDState(&DState, &DStream, DTablePtr);
|
||||
|
||||
You can then decode your data, symbol after symbol.
|
||||
For information the maximum number of bits read by FSE_decodeSymbol() is 'tableLog'.
|
||||
Keep in mind that symbols are decoded in reverse order, like a LIFO stack (last in, first out).
|
||||
unsigned char symbol = FSE_decodeSymbol(&DState, &DStream);
|
||||
|
||||
You can retrieve any bitfield you eventually stored into the bitStream (in reverse order)
|
||||
Note : maximum allowed nbBits is 25, for 32-bits compatibility
|
||||
size_t bitField = BIT_readBits(&DStream, nbBits);
|
||||
|
||||
All above operations only read from local register (which size depends on size_t).
|
||||
Refueling the register from memory is manually performed by the reload method.
|
||||
endSignal = FSE_reloadDStream(&DStream);
|
||||
|
||||
BIT_reloadDStream() result tells if there is still some more data to read from DStream.
|
||||
BIT_DStream_unfinished : there is still some data left into the DStream.
|
||||
BIT_DStream_endOfBuffer : Dstream reached end of buffer. Its container may no longer be completely filled.
|
||||
BIT_DStream_completed : Dstream reached its exact end, corresponding in general to decompression completed.
|
||||
BIT_DStream_tooFar : Dstream went too far. Decompression result is corrupted.
|
||||
|
||||
When reaching end of buffer (BIT_DStream_endOfBuffer), progress slowly, notably if you decode multiple symbols per loop,
|
||||
to properly detect the exact end of stream.
|
||||
After each decoded symbol, check if DStream is fully consumed using this simple test :
|
||||
BIT_reloadDStream(&DStream) >= BIT_DStream_completed
|
||||
|
||||
When it's done, verify decompression is fully completed, by checking both DStream and the relevant states.
|
||||
Checking if DStream has reached its end is performed by :
|
||||
BIT_endOfDStream(&DStream);
|
||||
Check also the states. There might be some symbols left there, if some high probability ones (>50%) are possible.
|
||||
FSE_endOfDState(&DState);
|
||||
*/
|
||||
|
||||
|
||||
/* *****************************************
|
||||
* FSE unsafe API
|
||||
*******************************************/
|
||||
static unsigned char FSE_decodeSymbolFast(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD);
|
||||
/* faster, but works only if nbBits is always >= 1 (otherwise, result will be corrupted) */
|
||||
|
||||
|
||||
/* *****************************************
|
||||
* Implementation of inlined functions
|
||||
*******************************************/
|
||||
typedef struct {
|
||||
int deltaFindState;
|
||||
U32 deltaNbBits;
|
||||
} FSE_symbolCompressionTransform; /* total 8 bytes */
|
||||
|
||||
MEM_STATIC void FSE_initCState(FSE_CState_t* statePtr, const FSE_CTable* ct)
|
||||
{
|
||||
const void* ptr = ct;
|
||||
const U16* u16ptr = (const U16*) ptr;
|
||||
const U32 tableLog = MEM_read16(ptr);
|
||||
statePtr->value = (ptrdiff_t)1<<tableLog;
|
||||
statePtr->stateTable = u16ptr+2;
|
||||
statePtr->symbolTT = ((const U32*)ct + 1 + (tableLog ? (1<<(tableLog-1)) : 1));
|
||||
statePtr->stateLog = tableLog;
|
||||
}
|
||||
|
||||
|
||||
/*! FSE_initCState2() :
|
||||
* Same as FSE_initCState(), but the first symbol to include (which will be the last to be read)
|
||||
* uses the smallest state value possible, saving the cost of this symbol */
|
||||
MEM_STATIC void FSE_initCState2(FSE_CState_t* statePtr, const FSE_CTable* ct, U32 symbol)
|
||||
{
|
||||
FSE_initCState(statePtr, ct);
|
||||
{ const FSE_symbolCompressionTransform symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol];
|
||||
const U16* stateTable = (const U16*)(statePtr->stateTable);
|
||||
U32 nbBitsOut = (U32)((symbolTT.deltaNbBits + (1<<15)) >> 16);
|
||||
statePtr->value = (nbBitsOut << 16) - symbolTT.deltaNbBits;
|
||||
statePtr->value = stateTable[(statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
|
||||
}
|
||||
}
|
||||
|
||||
MEM_STATIC void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* statePtr, U32 symbol)
|
||||
{
|
||||
FSE_symbolCompressionTransform const symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol];
|
||||
const U16* const stateTable = (const U16*)(statePtr->stateTable);
|
||||
U32 const nbBitsOut = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16);
|
||||
BIT_addBits(bitC, statePtr->value, nbBitsOut);
|
||||
statePtr->value = stateTable[ (statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
|
||||
}
|
||||
|
||||
MEM_STATIC void FSE_flushCState(BIT_CStream_t* bitC, const FSE_CState_t* statePtr)
|
||||
{
|
||||
BIT_addBits(bitC, statePtr->value, statePtr->stateLog);
|
||||
BIT_flushBits(bitC);
|
||||
}
|
||||
|
||||
|
||||
/* FSE_getMaxNbBits() :
|
||||
* Approximate maximum cost of a symbol, in bits.
|
||||
* Fractional get rounded up (i.e : a symbol with a normalized frequency of 3 gives the same result as a frequency of 2)
|
||||
* note 1 : assume symbolValue is valid (<= maxSymbolValue)
|
||||
* note 2 : if freq[symbolValue]==0, @return a fake cost of tableLog+1 bits */
|
||||
MEM_STATIC U32 FSE_getMaxNbBits(const void* symbolTTPtr, U32 symbolValue)
|
||||
{
|
||||
const FSE_symbolCompressionTransform* symbolTT = (const FSE_symbolCompressionTransform*) symbolTTPtr;
|
||||
return (symbolTT[symbolValue].deltaNbBits + ((1<<16)-1)) >> 16;
|
||||
}
|
||||
|
||||
/* FSE_bitCost() :
|
||||
* Approximate symbol cost, as fractional value, using fixed-point format (accuracyLog fractional bits)
|
||||
* note 1 : assume symbolValue is valid (<= maxSymbolValue)
|
||||
* note 2 : if freq[symbolValue]==0, @return a fake cost of tableLog+1 bits */
|
||||
MEM_STATIC U32 FSE_bitCost(const void* symbolTTPtr, U32 tableLog, U32 symbolValue, U32 accuracyLog)
|
||||
{
|
||||
const FSE_symbolCompressionTransform* symbolTT = (const FSE_symbolCompressionTransform*) symbolTTPtr;
|
||||
U32 const minNbBits = symbolTT[symbolValue].deltaNbBits >> 16;
|
||||
U32 const threshold = (minNbBits+1) << 16;
|
||||
assert(tableLog < 16);
|
||||
assert(accuracyLog < 31-tableLog); /* ensure enough room for renormalization double shift */
|
||||
{ U32 const tableSize = 1 << tableLog;
|
||||
U32 const deltaFromThreshold = threshold - (symbolTT[symbolValue].deltaNbBits + tableSize);
|
||||
U32 const normalizedDeltaFromThreshold = (deltaFromThreshold << accuracyLog) >> tableLog; /* linear interpolation (very approximate) */
|
||||
U32 const bitMultiplier = 1 << accuracyLog;
|
||||
assert(symbolTT[symbolValue].deltaNbBits + tableSize <= threshold);
|
||||
assert(normalizedDeltaFromThreshold <= bitMultiplier);
|
||||
return (minNbBits+1)*bitMultiplier - normalizedDeltaFromThreshold;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/* ====== Decompression ====== */
|
||||
|
||||
typedef struct {
|
||||
U16 tableLog;
|
||||
U16 fastMode;
|
||||
} FSE_DTableHeader; /* sizeof U32 */
|
||||
|
||||
typedef struct
|
||||
{
|
||||
unsigned short newState;
|
||||
unsigned char symbol;
|
||||
unsigned char nbBits;
|
||||
} FSE_decode_t; /* size == U32 */
|
||||
|
||||
MEM_STATIC void FSE_initDState(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD, const FSE_DTable* dt)
|
||||
{
|
||||
const void* ptr = dt;
|
||||
const FSE_DTableHeader* const DTableH = (const FSE_DTableHeader*)ptr;
|
||||
DStatePtr->state = BIT_readBits(bitD, DTableH->tableLog);
|
||||
BIT_reloadDStream(bitD);
|
||||
DStatePtr->table = dt + 1;
|
||||
}
|
||||
|
||||
MEM_STATIC BYTE FSE_peekSymbol(const FSE_DState_t* DStatePtr)
|
||||
{
|
||||
FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state];
|
||||
return DInfo.symbol;
|
||||
}
|
||||
|
||||
MEM_STATIC void FSE_updateState(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD)
|
||||
{
|
||||
FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state];
|
||||
U32 const nbBits = DInfo.nbBits;
|
||||
size_t const lowBits = BIT_readBits(bitD, nbBits);
|
||||
DStatePtr->state = DInfo.newState + lowBits;
|
||||
}
|
||||
|
||||
MEM_STATIC BYTE FSE_decodeSymbol(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD)
|
||||
{
|
||||
FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state];
|
||||
U32 const nbBits = DInfo.nbBits;
|
||||
BYTE const symbol = DInfo.symbol;
|
||||
size_t const lowBits = BIT_readBits(bitD, nbBits);
|
||||
|
||||
DStatePtr->state = DInfo.newState + lowBits;
|
||||
return symbol;
|
||||
}
|
||||
|
||||
/*! FSE_decodeSymbolFast() :
|
||||
unsafe, only works if no symbol has a probability > 50% */
|
||||
MEM_STATIC BYTE FSE_decodeSymbolFast(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD)
|
||||
{
|
||||
FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state];
|
||||
U32 const nbBits = DInfo.nbBits;
|
||||
BYTE const symbol = DInfo.symbol;
|
||||
size_t const lowBits = BIT_readBitsFast(bitD, nbBits);
|
||||
|
||||
DStatePtr->state = DInfo.newState + lowBits;
|
||||
return symbol;
|
||||
}
|
||||
|
||||
MEM_STATIC unsigned FSE_endOfDState(const FSE_DState_t* DStatePtr)
|
||||
{
|
||||
return DStatePtr->state == 0;
|
||||
}
|
||||
|
||||
|
||||
|
||||
#ifndef FSE_COMMONDEFS_ONLY
|
||||
|
||||
/* **************************************************************
|
||||
* Tuning parameters
|
||||
****************************************************************/
|
||||
/*!MEMORY_USAGE :
|
||||
* Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
|
||||
* Increasing memory usage improves compression ratio
|
||||
* Reduced memory usage can improve speed, due to cache effect
|
||||
* Recommended max value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */
|
||||
#ifndef FSE_MAX_MEMORY_USAGE
|
||||
# define FSE_MAX_MEMORY_USAGE 14
|
||||
#endif
|
||||
#ifndef FSE_DEFAULT_MEMORY_USAGE
|
||||
# define FSE_DEFAULT_MEMORY_USAGE 13
|
||||
#endif
|
||||
|
||||
/*!FSE_MAX_SYMBOL_VALUE :
|
||||
* Maximum symbol value authorized.
|
||||
* Required for proper stack allocation */
|
||||
#ifndef FSE_MAX_SYMBOL_VALUE
|
||||
# define FSE_MAX_SYMBOL_VALUE 255
|
||||
#endif
|
||||
|
||||
/* **************************************************************
|
||||
* template functions type & suffix
|
||||
****************************************************************/
|
||||
#define FSE_FUNCTION_TYPE BYTE
|
||||
#define FSE_FUNCTION_EXTENSION
|
||||
#define FSE_DECODE_TYPE FSE_decode_t
|
||||
|
||||
|
||||
#endif /* !FSE_COMMONDEFS_ONLY */
|
||||
|
||||
|
||||
/* ***************************************************************
|
||||
* Constants
|
||||
*****************************************************************/
|
||||
#define FSE_MAX_TABLELOG (FSE_MAX_MEMORY_USAGE-2)
|
||||
#define FSE_MAX_TABLESIZE (1U<<FSE_MAX_TABLELOG)
|
||||
#define FSE_MAXTABLESIZE_MASK (FSE_MAX_TABLESIZE-1)
|
||||
#define FSE_DEFAULT_TABLELOG (FSE_DEFAULT_MEMORY_USAGE-2)
|
||||
#define FSE_MIN_TABLELOG 5
|
||||
|
||||
#define FSE_TABLELOG_ABSOLUTE_MAX 15
|
||||
#if FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX
|
||||
# error "FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX is not supported"
|
||||
#endif
|
||||
|
||||
#define FSE_TABLESTEP(tableSize) ((tableSize>>1) + (tableSize>>3) + 3)
|
||||
|
||||
|
||||
#endif /* FSE_STATIC_LINKING_ONLY */
|
||||
|
||||
|
||||
#if defined (__cplusplus)
|
||||
}
|
||||
#endif
|
||||
|
|
@ -0,0 +1,309 @@
|
|||
/* ******************************************************************
|
||||
FSE : Finite State Entropy decoder
|
||||
Copyright (C) 2013-2015, Yann Collet.
|
||||
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy
|
||||
- Public forum : https://groups.google.com/forum/#!forum/lz4c
|
||||
****************************************************************** */
|
||||
|
||||
|
||||
/* **************************************************************
|
||||
* Includes
|
||||
****************************************************************/
|
||||
#include <stdlib.h> /* malloc, free, qsort */
|
||||
#include <string.h> /* memcpy, memset */
|
||||
#include "bitstream.h"
|
||||
#include "compiler.h"
|
||||
#define FSE_STATIC_LINKING_ONLY
|
||||
#include "fse.h"
|
||||
#include "error_private.h"
|
||||
|
||||
|
||||
/* **************************************************************
|
||||
* Error Management
|
||||
****************************************************************/
|
||||
#define FSE_isError ERR_isError
|
||||
#define FSE_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c) /* use only *after* variable declarations */
|
||||
|
||||
/* check and forward error code */
|
||||
#define CHECK_F(f) { size_t const e = f; if (FSE_isError(e)) return e; }
|
||||
|
||||
|
||||
/* **************************************************************
|
||||
* Templates
|
||||
****************************************************************/
|
||||
/*
|
||||
designed to be included
|
||||
for type-specific functions (template emulation in C)
|
||||
Objective is to write these functions only once, for improved maintenance
|
||||
*/
|
||||
|
||||
/* safety checks */
|
||||
#ifndef FSE_FUNCTION_EXTENSION
|
||||
# error "FSE_FUNCTION_EXTENSION must be defined"
|
||||
#endif
|
||||
#ifndef FSE_FUNCTION_TYPE
|
||||
# error "FSE_FUNCTION_TYPE must be defined"
|
||||
#endif
|
||||
|
||||
/* Function names */
|
||||
#define FSE_CAT(X,Y) X##Y
|
||||
#define FSE_FUNCTION_NAME(X,Y) FSE_CAT(X,Y)
|
||||
#define FSE_TYPE_NAME(X,Y) FSE_CAT(X,Y)
|
||||
|
||||
|
||||
/* Function templates */
|
||||
FSE_DTable* FSE_createDTable (unsigned tableLog)
|
||||
{
|
||||
if (tableLog > FSE_TABLELOG_ABSOLUTE_MAX) tableLog = FSE_TABLELOG_ABSOLUTE_MAX;
|
||||
return (FSE_DTable*)malloc( FSE_DTABLE_SIZE_U32(tableLog) * sizeof (U32) );
|
||||
}
|
||||
|
||||
void FSE_freeDTable (FSE_DTable* dt)
|
||||
{
|
||||
free(dt);
|
||||
}
|
||||
|
||||
size_t FSE_buildDTable(FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog)
|
||||
{
|
||||
void* const tdPtr = dt+1; /* because *dt is unsigned, 32-bits aligned on 32-bits */
|
||||
FSE_DECODE_TYPE* const tableDecode = (FSE_DECODE_TYPE*) (tdPtr);
|
||||
U16 symbolNext[FSE_MAX_SYMBOL_VALUE+1];
|
||||
|
||||
U32 const maxSV1 = maxSymbolValue + 1;
|
||||
U32 const tableSize = 1 << tableLog;
|
||||
U32 highThreshold = tableSize-1;
|
||||
|
||||
/* Sanity Checks */
|
||||
if (maxSymbolValue > FSE_MAX_SYMBOL_VALUE) return ERROR(maxSymbolValue_tooLarge);
|
||||
if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge);
|
||||
|
||||
/* Init, lay down lowprob symbols */
|
||||
{ FSE_DTableHeader DTableH;
|
||||
DTableH.tableLog = (U16)tableLog;
|
||||
DTableH.fastMode = 1;
|
||||
{ S16 const largeLimit= (S16)(1 << (tableLog-1));
|
||||
U32 s;
|
||||
for (s=0; s<maxSV1; s++) {
|
||||
if (normalizedCounter[s]==-1) {
|
||||
tableDecode[highThreshold--].symbol = (FSE_FUNCTION_TYPE)s;
|
||||
symbolNext[s] = 1;
|
||||
} else {
|
||||
if (normalizedCounter[s] >= largeLimit) DTableH.fastMode=0;
|
||||
symbolNext[s] = normalizedCounter[s];
|
||||
} } }
|
||||
memcpy(dt, &DTableH, sizeof(DTableH));
|
||||
}
|
||||
|
||||
/* Spread symbols */
|
||||
{ U32 const tableMask = tableSize-1;
|
||||
U32 const step = FSE_TABLESTEP(tableSize);
|
||||
U32 s, position = 0;
|
||||
for (s=0; s<maxSV1; s++) {
|
||||
int i;
|
||||
for (i=0; i<normalizedCounter[s]; i++) {
|
||||
tableDecode[position].symbol = (FSE_FUNCTION_TYPE)s;
|
||||
position = (position + step) & tableMask;
|
||||
while (position > highThreshold) position = (position + step) & tableMask; /* lowprob area */
|
||||
} }
|
||||
if (position!=0) return ERROR(GENERIC); /* position must reach all cells once, otherwise normalizedCounter is incorrect */
|
||||
}
|
||||
|
||||
/* Build Decoding table */
|
||||
{ U32 u;
|
||||
for (u=0; u<tableSize; u++) {
|
||||
FSE_FUNCTION_TYPE const symbol = (FSE_FUNCTION_TYPE)(tableDecode[u].symbol);
|
||||
U32 const nextState = symbolNext[symbol]++;
|
||||
tableDecode[u].nbBits = (BYTE) (tableLog - BIT_highbit32(nextState) );
|
||||
tableDecode[u].newState = (U16) ( (nextState << tableDecode[u].nbBits) - tableSize);
|
||||
} }
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
||||
#ifndef FSE_COMMONDEFS_ONLY
|
||||
|
||||
/*-*******************************************************
|
||||
* Decompression (Byte symbols)
|
||||
*********************************************************/
|
||||
size_t FSE_buildDTable_rle (FSE_DTable* dt, BYTE symbolValue)
|
||||
{
|
||||
void* ptr = dt;
|
||||
FSE_DTableHeader* const DTableH = (FSE_DTableHeader*)ptr;
|
||||
void* dPtr = dt + 1;
|
||||
FSE_decode_t* const cell = (FSE_decode_t*)dPtr;
|
||||
|
||||
DTableH->tableLog = 0;
|
||||
DTableH->fastMode = 0;
|
||||
|
||||
cell->newState = 0;
|
||||
cell->symbol = symbolValue;
|
||||
cell->nbBits = 0;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
||||
size_t FSE_buildDTable_raw (FSE_DTable* dt, unsigned nbBits)
|
||||
{
|
||||
void* ptr = dt;
|
||||
FSE_DTableHeader* const DTableH = (FSE_DTableHeader*)ptr;
|
||||
void* dPtr = dt + 1;
|
||||
FSE_decode_t* const dinfo = (FSE_decode_t*)dPtr;
|
||||
const unsigned tableSize = 1 << nbBits;
|
||||
const unsigned tableMask = tableSize - 1;
|
||||
const unsigned maxSV1 = tableMask+1;
|
||||
unsigned s;
|
||||
|
||||
/* Sanity checks */
|
||||
if (nbBits < 1) return ERROR(GENERIC); /* min size */
|
||||
|
||||
/* Build Decoding Table */
|
||||
DTableH->tableLog = (U16)nbBits;
|
||||
DTableH->fastMode = 1;
|
||||
for (s=0; s<maxSV1; s++) {
|
||||
dinfo[s].newState = 0;
|
||||
dinfo[s].symbol = (BYTE)s;
|
||||
dinfo[s].nbBits = (BYTE)nbBits;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
FORCE_INLINE_TEMPLATE size_t FSE_decompress_usingDTable_generic(
|
||||
void* dst, size_t maxDstSize,
|
||||
const void* cSrc, size_t cSrcSize,
|
||||
const FSE_DTable* dt, const unsigned fast)
|
||||
{
|
||||
BYTE* const ostart = (BYTE*) dst;
|
||||
BYTE* op = ostart;
|
||||
BYTE* const omax = op + maxDstSize;
|
||||
BYTE* const olimit = omax-3;
|
||||
|
||||
BIT_DStream_t bitD;
|
||||
FSE_DState_t state1;
|
||||
FSE_DState_t state2;
|
||||
|
||||
/* Init */
|
||||
CHECK_F(BIT_initDStream(&bitD, cSrc, cSrcSize));
|
||||
|
||||
FSE_initDState(&state1, &bitD, dt);
|
||||
FSE_initDState(&state2, &bitD, dt);
|
||||
|
||||
#define FSE_GETSYMBOL(statePtr) fast ? FSE_decodeSymbolFast(statePtr, &bitD) : FSE_decodeSymbol(statePtr, &bitD)
|
||||
|
||||
/* 4 symbols per loop */
|
||||
for ( ; (BIT_reloadDStream(&bitD)==BIT_DStream_unfinished) & (op<olimit) ; op+=4) {
|
||||
op[0] = FSE_GETSYMBOL(&state1);
|
||||
|
||||
if (FSE_MAX_TABLELOG*2+7 > sizeof(bitD.bitContainer)*8) /* This test must be static */
|
||||
BIT_reloadDStream(&bitD);
|
||||
|
||||
op[1] = FSE_GETSYMBOL(&state2);
|
||||
|
||||
if (FSE_MAX_TABLELOG*4+7 > sizeof(bitD.bitContainer)*8) /* This test must be static */
|
||||
{ if (BIT_reloadDStream(&bitD) > BIT_DStream_unfinished) { op+=2; break; } }
|
||||
|
||||
op[2] = FSE_GETSYMBOL(&state1);
|
||||
|
||||
if (FSE_MAX_TABLELOG*2+7 > sizeof(bitD.bitContainer)*8) /* This test must be static */
|
||||
BIT_reloadDStream(&bitD);
|
||||
|
||||
op[3] = FSE_GETSYMBOL(&state2);
|
||||
}
|
||||
|
||||
/* tail */
|
||||
/* note : BIT_reloadDStream(&bitD) >= FSE_DStream_partiallyFilled; Ends at exactly BIT_DStream_completed */
|
||||
while (1) {
|
||||
if (op>(omax-2)) return ERROR(dstSize_tooSmall);
|
||||
*op++ = FSE_GETSYMBOL(&state1);
|
||||
if (BIT_reloadDStream(&bitD)==BIT_DStream_overflow) {
|
||||
*op++ = FSE_GETSYMBOL(&state2);
|
||||
break;
|
||||
}
|
||||
|
||||
if (op>(omax-2)) return ERROR(dstSize_tooSmall);
|
||||
*op++ = FSE_GETSYMBOL(&state2);
|
||||
if (BIT_reloadDStream(&bitD)==BIT_DStream_overflow) {
|
||||
*op++ = FSE_GETSYMBOL(&state1);
|
||||
break;
|
||||
} }
|
||||
|
||||
return op-ostart;
|
||||
}
|
||||
|
||||
|
||||
size_t FSE_decompress_usingDTable(void* dst, size_t originalSize,
|
||||
const void* cSrc, size_t cSrcSize,
|
||||
const FSE_DTable* dt)
|
||||
{
|
||||
const void* ptr = dt;
|
||||
const FSE_DTableHeader* DTableH = (const FSE_DTableHeader*)ptr;
|
||||
const U32 fastMode = DTableH->fastMode;
|
||||
|
||||
/* select fast mode (static) */
|
||||
if (fastMode) return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 1);
|
||||
return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 0);
|
||||
}
|
||||
|
||||
|
||||
size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, FSE_DTable* workSpace, unsigned maxLog)
|
||||
{
|
||||
const BYTE* const istart = (const BYTE*)cSrc;
|
||||
const BYTE* ip = istart;
|
||||
short counting[FSE_MAX_SYMBOL_VALUE+1];
|
||||
unsigned tableLog;
|
||||
unsigned maxSymbolValue = FSE_MAX_SYMBOL_VALUE;
|
||||
|
||||
/* normal FSE decoding mode */
|
||||
size_t const NCountLength = FSE_readNCount (counting, &maxSymbolValue, &tableLog, istart, cSrcSize);
|
||||
if (FSE_isError(NCountLength)) return NCountLength;
|
||||
//if (NCountLength >= cSrcSize) return ERROR(srcSize_wrong); /* too small input size; supposed to be already checked in NCountLength, only remaining case : NCountLength==cSrcSize */
|
||||
if (tableLog > maxLog) return ERROR(tableLog_tooLarge);
|
||||
ip += NCountLength;
|
||||
cSrcSize -= NCountLength;
|
||||
|
||||
CHECK_F( FSE_buildDTable (workSpace, counting, maxSymbolValue, tableLog) );
|
||||
|
||||
return FSE_decompress_usingDTable (dst, dstCapacity, ip, cSrcSize, workSpace); /* always return, even if it is an error code */
|
||||
}
|
||||
|
||||
|
||||
typedef FSE_DTable DTable_max_t[FSE_DTABLE_SIZE_U32(FSE_MAX_TABLELOG)];
|
||||
|
||||
size_t FSE_decompress(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize)
|
||||
{
|
||||
DTable_max_t dt; /* Static analyzer seems unable to understand this table will be properly initialized later */
|
||||
return FSE_decompress_wksp(dst, dstCapacity, cSrc, cSrcSize, dt, FSE_MAX_TABLELOG);
|
||||
}
|
||||
|
||||
|
||||
|
||||
#endif /* FSE_COMMONDEFS_ONLY */
|
||||
|
|
@ -0,0 +1,334 @@
|
|||
/* ******************************************************************
|
||||
huff0 huffman codec,
|
||||
part of Finite State Entropy library
|
||||
Copyright (C) 2013-present, Yann Collet.
|
||||
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- Source repository : https://github.com/Cyan4973/FiniteStateEntropy
|
||||
****************************************************************** */
|
||||
|
||||
#if defined (__cplusplus)
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#ifndef HUF_H_298734234
|
||||
#define HUF_H_298734234
|
||||
|
||||
/* *** Dependencies *** */
|
||||
#include <stddef.h> /* size_t */
|
||||
|
||||
|
||||
/* *** library symbols visibility *** */
|
||||
/* Note : when linking with -fvisibility=hidden on gcc, or by default on Visual,
|
||||
* HUF symbols remain "private" (internal symbols for library only).
|
||||
* Set macro FSE_DLL_EXPORT to 1 if you want HUF symbols visible on DLL interface */
|
||||
#if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4)
|
||||
# define HUF_PUBLIC_API __attribute__ ((visibility ("default")))
|
||||
#elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) /* Visual expected */
|
||||
# define HUF_PUBLIC_API __declspec(dllexport)
|
||||
#elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1)
|
||||
# define HUF_PUBLIC_API __declspec(dllimport) /* not required, just to generate faster code (saves a function pointer load from IAT and an indirect jump) */
|
||||
#else
|
||||
# define HUF_PUBLIC_API
|
||||
#endif
|
||||
|
||||
|
||||
/* ========================== */
|
||||
/* *** simple functions *** */
|
||||
/* ========================== */
|
||||
|
||||
/** HUF_compress() :
|
||||
* Compress content from buffer 'src', of size 'srcSize', into buffer 'dst'.
|
||||
* 'dst' buffer must be already allocated.
|
||||
* Compression runs faster if `dstCapacity` >= HUF_compressBound(srcSize).
|
||||
* `srcSize` must be <= `HUF_BLOCKSIZE_MAX` == 128 KB.
|
||||
* @return : size of compressed data (<= `dstCapacity`).
|
||||
* Special values : if return == 0, srcData is not compressible => Nothing is stored within dst !!!
|
||||
* if HUF_isError(return), compression failed (more details using HUF_getErrorName())
|
||||
*/
|
||||
HUF_PUBLIC_API size_t HUF_compress(void* dst, size_t dstCapacity,
|
||||
const void* src, size_t srcSize);
|
||||
|
||||
/** HUF_decompress() :
|
||||
* Decompress HUF data from buffer 'cSrc', of size 'cSrcSize',
|
||||
* into already allocated buffer 'dst', of minimum size 'dstSize'.
|
||||
* `originalSize` : **must** be the ***exact*** size of original (uncompressed) data.
|
||||
* Note : in contrast with FSE, HUF_decompress can regenerate
|
||||
* RLE (cSrcSize==1) and uncompressed (cSrcSize==dstSize) data,
|
||||
* because it knows size to regenerate (originalSize).
|
||||
* @return : size of regenerated data (== originalSize),
|
||||
* or an error code, which can be tested using HUF_isError()
|
||||
*/
|
||||
HUF_PUBLIC_API size_t HUF_decompress(void* dst, size_t originalSize,
|
||||
const void* cSrc, size_t cSrcSize);
|
||||
|
||||
|
||||
/* *** Tool functions *** */
|
||||
#define HUF_BLOCKSIZE_MAX (128 * 1024) /**< maximum input size for a single block compressed with HUF_compress */
|
||||
HUF_PUBLIC_API size_t HUF_compressBound(size_t size); /**< maximum compressed size (worst case) */
|
||||
|
||||
/* Error Management */
|
||||
HUF_PUBLIC_API unsigned HUF_isError(size_t code); /**< tells if a return value is an error code */
|
||||
HUF_PUBLIC_API const char* HUF_getErrorName(size_t code); /**< provides error code string (useful for debugging) */
|
||||
|
||||
|
||||
/* *** Advanced function *** */
|
||||
|
||||
/** HUF_compress2() :
|
||||
* Same as HUF_compress(), but offers control over `maxSymbolValue` and `tableLog`.
|
||||
* `maxSymbolValue` must be <= HUF_SYMBOLVALUE_MAX .
|
||||
* `tableLog` must be `<= HUF_TABLELOG_MAX` . */
|
||||
HUF_PUBLIC_API size_t HUF_compress2 (void* dst, size_t dstCapacity,
|
||||
const void* src, size_t srcSize,
|
||||
unsigned maxSymbolValue, unsigned tableLog);
|
||||
|
||||
/** HUF_compress4X_wksp() :
|
||||
* Same as HUF_compress2(), but uses externally allocated `workSpace`.
|
||||
* `workspace` must have minimum alignment of 4, and be at least as large as HUF_WORKSPACE_SIZE */
|
||||
#define HUF_WORKSPACE_SIZE (6 << 10)
|
||||
#define HUF_WORKSPACE_SIZE_U32 (HUF_WORKSPACE_SIZE / sizeof(U32))
|
||||
HUF_PUBLIC_API size_t HUF_compress4X_wksp (void* dst, size_t dstCapacity,
|
||||
const void* src, size_t srcSize,
|
||||
unsigned maxSymbolValue, unsigned tableLog,
|
||||
void* workSpace, size_t wkspSize);
|
||||
|
||||
#endif /* HUF_H_298734234 */
|
||||
|
||||
/* ******************************************************************
|
||||
* WARNING !!
|
||||
* The following section contains advanced and experimental definitions
|
||||
* which shall never be used in the context of a dynamic library,
|
||||
* because they are not guaranteed to remain stable in the future.
|
||||
* Only consider them in association with static linking.
|
||||
* *****************************************************************/
|
||||
#if defined(HUF_STATIC_LINKING_ONLY) && !defined(HUF_H_HUF_STATIC_LINKING_ONLY)
|
||||
#define HUF_H_HUF_STATIC_LINKING_ONLY
|
||||
|
||||
/* *** Dependencies *** */
|
||||
#include "mem.h" /* U32 */
|
||||
|
||||
|
||||
/* *** Constants *** */
|
||||
#define HUF_TABLELOG_MAX 12 /* max runtime value of tableLog (due to static allocation); can be modified up to HUF_ABSOLUTEMAX_TABLELOG */
|
||||
#define HUF_TABLELOG_DEFAULT 11 /* default tableLog value when none specified */
|
||||
#define HUF_SYMBOLVALUE_MAX 255
|
||||
|
||||
#define HUF_TABLELOG_ABSOLUTEMAX 15 /* absolute limit of HUF_MAX_TABLELOG. Beyond that value, code does not work */
|
||||
#if (HUF_TABLELOG_MAX > HUF_TABLELOG_ABSOLUTEMAX)
|
||||
# error "HUF_TABLELOG_MAX is too large !"
|
||||
#endif
|
||||
|
||||
|
||||
/* ****************************************
|
||||
* Static allocation
|
||||
******************************************/
|
||||
/* HUF buffer bounds */
|
||||
#define HUF_CTABLEBOUND 129
|
||||
#define HUF_BLOCKBOUND(size) (size + (size>>8) + 8) /* only true when incompressible is pre-filtered with fast heuristic */
|
||||
#define HUF_COMPRESSBOUND(size) (HUF_CTABLEBOUND + HUF_BLOCKBOUND(size)) /* Macro version, useful for static allocation */
|
||||
|
||||
/* static allocation of HUF's Compression Table */
|
||||
#define HUF_CTABLE_SIZE_U32(maxSymbolValue) ((maxSymbolValue)+1) /* Use tables of U32, for proper alignment */
|
||||
#define HUF_CTABLE_SIZE(maxSymbolValue) (HUF_CTABLE_SIZE_U32(maxSymbolValue) * sizeof(U32))
|
||||
#define HUF_CREATE_STATIC_CTABLE(name, maxSymbolValue) \
|
||||
U32 name##hb[HUF_CTABLE_SIZE_U32(maxSymbolValue)]; \
|
||||
void* name##hv = &(name##hb); \
|
||||
HUF_CElt* name = (HUF_CElt*)(name##hv) /* no final ; */
|
||||
|
||||
/* static allocation of HUF's DTable */
|
||||
typedef U32 HUF_DTable;
|
||||
#define HUF_DTABLE_SIZE(maxTableLog) (1 + (1<<(maxTableLog)))
|
||||
#define HUF_CREATE_STATIC_DTABLEX1(DTable, maxTableLog) \
|
||||
HUF_DTable DTable[HUF_DTABLE_SIZE((maxTableLog)-1)] = { ((U32)((maxTableLog)-1) * 0x01000001) }
|
||||
#define HUF_CREATE_STATIC_DTABLEX2(DTable, maxTableLog) \
|
||||
HUF_DTable DTable[HUF_DTABLE_SIZE(maxTableLog)] = { ((U32)(maxTableLog) * 0x01000001) }
|
||||
|
||||
|
||||
/* ****************************************
|
||||
* Advanced decompression functions
|
||||
******************************************/
|
||||
size_t HUF_decompress4X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< single-symbol decoder */
|
||||
size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< double-symbols decoder */
|
||||
|
||||
size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< decodes RLE and uncompressed */
|
||||
size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< considers RLE and uncompressed as errors */
|
||||
size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< considers RLE and uncompressed as errors */
|
||||
size_t HUF_decompress4X1_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< single-symbol decoder */
|
||||
size_t HUF_decompress4X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< single-symbol decoder */
|
||||
size_t HUF_decompress4X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< double-symbols decoder */
|
||||
size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< double-symbols decoder */
|
||||
|
||||
|
||||
/* ****************************************
|
||||
* HUF detailed API
|
||||
* ****************************************/
|
||||
|
||||
/*! HUF_compress() does the following:
|
||||
* 1. count symbol occurrence from source[] into table count[] using FSE_count() (exposed within "fse.h")
|
||||
* 2. (optional) refine tableLog using HUF_optimalTableLog()
|
||||
* 3. build Huffman table from count using HUF_buildCTable()
|
||||
* 4. save Huffman table to memory buffer using HUF_writeCTable()
|
||||
* 5. encode the data stream using HUF_compress4X_usingCTable()
|
||||
*
|
||||
* The following API allows targeting specific sub-functions for advanced tasks.
|
||||
* For example, it's possible to compress several blocks using the same 'CTable',
|
||||
* or to save and regenerate 'CTable' using external methods.
|
||||
*/
|
||||
unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
|
||||
typedef struct HUF_CElt_s HUF_CElt; /* incomplete type */
|
||||
size_t HUF_buildCTable (HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue, unsigned maxNbBits); /* @return : maxNbBits; CTable and count can overlap. In which case, CTable will overwrite count content */
|
||||
size_t HUF_writeCTable (void* dst, size_t maxDstSize, const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog);
|
||||
size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
|
||||
|
||||
typedef enum {
|
||||
HUF_repeat_none, /**< Cannot use the previous table */
|
||||
HUF_repeat_check, /**< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1, 4}X_repeat */
|
||||
HUF_repeat_valid /**< Can use the previous table and it is assumed to be valid */
|
||||
} HUF_repeat;
|
||||
/** HUF_compress4X_repeat() :
|
||||
* Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
|
||||
* If it uses hufTable it does not modify hufTable or repeat.
|
||||
* If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
|
||||
* If preferRepeat then the old table will always be used if valid. */
|
||||
size_t HUF_compress4X_repeat(void* dst, size_t dstSize,
|
||||
const void* src, size_t srcSize,
|
||||
unsigned maxSymbolValue, unsigned tableLog,
|
||||
void* workSpace, size_t wkspSize, /**< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */
|
||||
HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2);
|
||||
|
||||
/** HUF_buildCTable_wksp() :
|
||||
* Same as HUF_buildCTable(), but using externally allocated scratch buffer.
|
||||
* `workSpace` must be aligned on 4-bytes boundaries, and its size must be >= HUF_CTABLE_WORKSPACE_SIZE.
|
||||
*/
|
||||
#define HUF_CTABLE_WORKSPACE_SIZE_U32 (2*HUF_SYMBOLVALUE_MAX +1 +1)
|
||||
#define HUF_CTABLE_WORKSPACE_SIZE (HUF_CTABLE_WORKSPACE_SIZE_U32 * sizeof(unsigned))
|
||||
size_t HUF_buildCTable_wksp (HUF_CElt* tree,
|
||||
const U32* count, U32 maxSymbolValue, U32 maxNbBits,
|
||||
void* workSpace, size_t wkspSize);
|
||||
|
||||
/*! HUF_readStats() :
|
||||
* Read compact Huffman tree, saved by HUF_writeCTable().
|
||||
* `huffWeight` is destination buffer.
|
||||
* @return : size read from `src` , or an error Code .
|
||||
* Note : Needed by HUF_readCTable() and HUF_readDTableXn() . */
|
||||
size_t HUF_readStats(BYTE* huffWeight, size_t hwSize,
|
||||
U32* rankStats, U32* nbSymbolsPtr, U32* tableLogPtr,
|
||||
const void* src, size_t srcSize);
|
||||
|
||||
/** HUF_readCTable() :
|
||||
* Loading a CTable saved with HUF_writeCTable() */
|
||||
size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize);
|
||||
|
||||
/** HUF_getNbBits() :
|
||||
* Read nbBits from CTable symbolTable, for symbol `symbolValue` presumed <= HUF_SYMBOLVALUE_MAX
|
||||
* Note 1 : is not inlined, as HUF_CElt definition is private
|
||||
* Note 2 : const void* used, so that it can provide a statically allocated table as argument (which uses type U32) */
|
||||
U32 HUF_getNbBits(const void* symbolTable, U32 symbolValue);
|
||||
|
||||
/*
|
||||
* HUF_decompress() does the following:
|
||||
* 1. select the decompression algorithm (X1, X2) based on pre-computed heuristics
|
||||
* 2. build Huffman table from save, using HUF_readDTableX?()
|
||||
* 3. decode 1 or 4 segments in parallel using HUF_decompress?X?_usingDTable()
|
||||
*/
|
||||
|
||||
/** HUF_selectDecoder() :
|
||||
* Tells which decoder is likely to decode faster,
|
||||
* based on a set of pre-computed metrics.
|
||||
* @return : 0==HUF_decompress4X1, 1==HUF_decompress4X2 .
|
||||
* Assumption : 0 < dstSize <= 128 KB */
|
||||
U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize);
|
||||
|
||||
/**
|
||||
* The minimum workspace size for the `workSpace` used in
|
||||
* HUF_readDTableX1_wksp() and HUF_readDTableX2_wksp().
|
||||
*
|
||||
* The space used depends on HUF_TABLELOG_MAX, ranging from ~1500 bytes when
|
||||
* HUF_TABLE_LOG_MAX=12 to ~1850 bytes when HUF_TABLE_LOG_MAX=15.
|
||||
* Buffer overflow errors may potentially occur if code modifications result in
|
||||
* a required workspace size greater than that specified in the following
|
||||
* macro.
|
||||
*/
|
||||
#define HUF_DECOMPRESS_WORKSPACE_SIZE (2 << 10)
|
||||
#define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32))
|
||||
|
||||
size_t HUF_readDTableX1 (HUF_DTable* DTable, const void* src, size_t srcSize);
|
||||
size_t HUF_readDTableX1_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
|
||||
size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize);
|
||||
size_t HUF_readDTableX2_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
|
||||
|
||||
size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
|
||||
size_t HUF_decompress4X1_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
|
||||
size_t HUF_decompress4X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
|
||||
|
||||
|
||||
/* ====================== */
|
||||
/* single stream variants */
|
||||
/* ====================== */
|
||||
|
||||
size_t HUF_compress1X (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
|
||||
size_t HUF_compress1X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize); /**< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */
|
||||
size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
|
||||
/** HUF_compress1X_repeat() :
|
||||
* Same as HUF_compress1X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
|
||||
* If it uses hufTable it does not modify hufTable or repeat.
|
||||
* If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
|
||||
* If preferRepeat then the old table will always be used if valid. */
|
||||
size_t HUF_compress1X_repeat(void* dst, size_t dstSize,
|
||||
const void* src, size_t srcSize,
|
||||
unsigned maxSymbolValue, unsigned tableLog,
|
||||
void* workSpace, size_t wkspSize, /**< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */
|
||||
HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2);
|
||||
|
||||
size_t HUF_decompress1X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /* single-symbol decoder */
|
||||
size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /* double-symbol decoder */
|
||||
|
||||
size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);
|
||||
size_t HUF_decompress1X_DCtx_wksp (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);
|
||||
size_t HUF_decompress1X1_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< single-symbol decoder */
|
||||
size_t HUF_decompress1X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< single-symbol decoder */
|
||||
size_t HUF_decompress1X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< double-symbols decoder */
|
||||
size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< double-symbols decoder */
|
||||
|
||||
size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); /**< automatic selection of sing or double symbol decoder, based on DTable */
|
||||
size_t HUF_decompress1X1_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
|
||||
size_t HUF_decompress1X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
|
||||
|
||||
/* BMI2 variants.
|
||||
* If the CPU has BMI2 support, pass bmi2=1, otherwise pass bmi2=0.
|
||||
*/
|
||||
size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2);
|
||||
size_t HUF_decompress1X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2);
|
||||
size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2);
|
||||
size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2);
|
||||
|
||||
#endif /* HUF_STATIC_LINKING_ONLY */
|
||||
|
||||
#if defined (__cplusplus)
|
||||
}
|
||||
#endif
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,374 @@
|
|||
/*
|
||||
* Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
|
||||
* All rights reserved.
|
||||
*
|
||||
* This source code is licensed under both the BSD-style license (found in the
|
||||
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
|
||||
* in the COPYING file in the root directory of this source tree).
|
||||
* You may select, at your option, one of the above-listed licenses.
|
||||
*/
|
||||
|
||||
#ifndef MEM_H_MODULE
|
||||
#define MEM_H_MODULE
|
||||
|
||||
#if defined (__cplusplus)
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/*-****************************************
|
||||
* Dependencies
|
||||
******************************************/
|
||||
#include <stddef.h> /* size_t, ptrdiff_t */
|
||||
#include <string.h> /* memcpy */
|
||||
|
||||
|
||||
/*-****************************************
|
||||
* Compiler specifics
|
||||
******************************************/
|
||||
#if defined(_MSC_VER) /* Visual Studio */
|
||||
# include <stdlib.h> /* _byteswap_ulong */
|
||||
# include <intrin.h> /* _byteswap_* */
|
||||
#endif
|
||||
#if defined(__GNUC__)
|
||||
# define MEM_STATIC static __inline __attribute__((unused))
|
||||
#elif defined (__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
|
||||
# define MEM_STATIC static inline
|
||||
#elif defined(_MSC_VER)
|
||||
# define MEM_STATIC static __inline
|
||||
#else
|
||||
# define MEM_STATIC static /* this version may generate warnings for unused static functions; disable the relevant warning */
|
||||
#endif
|
||||
|
||||
/* code only tested on 32 and 64 bits systems */
|
||||
#define MEM_STATIC_ASSERT(c) { enum { MEM_static_assert = 1/(int)(!!(c)) }; }
|
||||
MEM_STATIC void MEM_check(void) { MEM_STATIC_ASSERT((sizeof(size_t)==4) || (sizeof(size_t)==8)); }
|
||||
|
||||
|
||||
/*-**************************************************************
|
||||
* Basic Types
|
||||
*****************************************************************/
|
||||
#if !defined (__VMS) && (defined (__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) )
|
||||
# include <stdint.h>
|
||||
typedef uint8_t BYTE;
|
||||
typedef uint16_t U16;
|
||||
typedef int16_t S16;
|
||||
typedef uint32_t U32;
|
||||
typedef int32_t S32;
|
||||
typedef uint64_t U64;
|
||||
typedef int64_t S64;
|
||||
#else
|
||||
# include <limits.h>
|
||||
#if CHAR_BIT != 8
|
||||
# error "this implementation requires char to be exactly 8-bit type"
|
||||
#endif
|
||||
typedef unsigned char BYTE;
|
||||
#if USHRT_MAX != 65535
|
||||
# error "this implementation requires short to be exactly 16-bit type"
|
||||
#endif
|
||||
typedef unsigned short U16;
|
||||
typedef signed short S16;
|
||||
#if UINT_MAX != 4294967295
|
||||
# error "this implementation requires int to be exactly 32-bit type"
|
||||
#endif
|
||||
typedef unsigned int U32;
|
||||
typedef signed int S32;
|
||||
/* note : there are no limits defined for long long type in C90.
|
||||
* limits exist in C99, however, in such case, <stdint.h> is preferred */
|
||||
typedef unsigned long long U64;
|
||||
typedef signed long long S64;
|
||||
#endif
|
||||
|
||||
|
||||
/*-**************************************************************
|
||||
* Memory I/O
|
||||
*****************************************************************/
|
||||
/* MEM_FORCE_MEMORY_ACCESS :
|
||||
* By default, access to unaligned memory is controlled by `memcpy()`, which is safe and portable.
|
||||
* Unfortunately, on some target/compiler combinations, the generated assembly is sub-optimal.
|
||||
* The below switch allow to select different access method for improved performance.
|
||||
* Method 0 (default) : use `memcpy()`. Safe and portable.
|
||||
* Method 1 : `__packed` statement. It depends on compiler extension (i.e., not portable).
|
||||
* This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`.
|
||||
* Method 2 : direct access. This method is portable but violate C standard.
|
||||
* It can generate buggy code on targets depending on alignment.
|
||||
* In some circumstances, it's the only known way to get the most performance (i.e. GCC + ARMv6)
|
||||
* See http://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details.
|
||||
* Prefer these methods in priority order (0 > 1 > 2)
|
||||
*/
|
||||
#ifndef MEM_FORCE_MEMORY_ACCESS /* can be defined externally, on command line for example */
|
||||
# if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
|
||||
# define MEM_FORCE_MEMORY_ACCESS 2
|
||||
# elif defined(__INTEL_COMPILER) || defined(__GNUC__)
|
||||
# define MEM_FORCE_MEMORY_ACCESS 1
|
||||
# endif
|
||||
#endif
|
||||
|
||||
MEM_STATIC unsigned MEM_32bits(void) { return sizeof(size_t)==4; }
|
||||
MEM_STATIC unsigned MEM_64bits(void) { return sizeof(size_t)==8; }
|
||||
|
||||
MEM_STATIC unsigned MEM_isLittleEndian(void)
|
||||
{
|
||||
const union { U32 u; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */
|
||||
return one.c[0];
|
||||
}
|
||||
|
||||
#if defined(MEM_FORCE_MEMORY_ACCESS) && (MEM_FORCE_MEMORY_ACCESS==2)
|
||||
|
||||
/* violates C standard, by lying on structure alignment.
|
||||
Only use if no other choice to achieve best performance on target platform */
|
||||
MEM_STATIC U16 MEM_read16(const void* memPtr) { return *(const U16*) memPtr; }
|
||||
MEM_STATIC U32 MEM_read32(const void* memPtr) { return *(const U32*) memPtr; }
|
||||
MEM_STATIC U64 MEM_read64(const void* memPtr) { return *(const U64*) memPtr; }
|
||||
MEM_STATIC size_t MEM_readST(const void* memPtr) { return *(const size_t*) memPtr; }
|
||||
|
||||
MEM_STATIC void MEM_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; }
|
||||
MEM_STATIC void MEM_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; }
|
||||
MEM_STATIC void MEM_write64(void* memPtr, U64 value) { *(U64*)memPtr = value; }
|
||||
|
||||
#elif defined(MEM_FORCE_MEMORY_ACCESS) && (MEM_FORCE_MEMORY_ACCESS==1)
|
||||
|
||||
/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */
|
||||
/* currently only defined for gcc and icc */
|
||||
#if defined(_MSC_VER) || (defined(__INTEL_COMPILER) && defined(WIN32))
|
||||
__pragma( pack(push, 1) )
|
||||
typedef struct { U16 v; } unalign16;
|
||||
typedef struct { U32 v; } unalign32;
|
||||
typedef struct { U64 v; } unalign64;
|
||||
typedef struct { size_t v; } unalignArch;
|
||||
__pragma( pack(pop) )
|
||||
#else
|
||||
typedef struct { U16 v; } __attribute__((packed)) unalign16;
|
||||
typedef struct { U32 v; } __attribute__((packed)) unalign32;
|
||||
typedef struct { U64 v; } __attribute__((packed)) unalign64;
|
||||
typedef struct { size_t v; } __attribute__((packed)) unalignArch;
|
||||
#endif
|
||||
|
||||
MEM_STATIC U16 MEM_read16(const void* ptr) { return ((const unalign16*)ptr)->v; }
|
||||
MEM_STATIC U32 MEM_read32(const void* ptr) { return ((const unalign32*)ptr)->v; }
|
||||
MEM_STATIC U64 MEM_read64(const void* ptr) { return ((const unalign64*)ptr)->v; }
|
||||
MEM_STATIC size_t MEM_readST(const void* ptr) { return ((const unalignArch*)ptr)->v; }
|
||||
|
||||
MEM_STATIC void MEM_write16(void* memPtr, U16 value) { ((unalign16*)memPtr)->v = value; }
|
||||
MEM_STATIC void MEM_write32(void* memPtr, U32 value) { ((unalign32*)memPtr)->v = value; }
|
||||
MEM_STATIC void MEM_write64(void* memPtr, U64 value) { ((unalign64*)memPtr)->v = value; }
|
||||
|
||||
#else
|
||||
|
||||
/* default method, safe and standard.
|
||||
can sometimes prove slower */
|
||||
|
||||
MEM_STATIC U16 MEM_read16(const void* memPtr)
|
||||
{
|
||||
U16 val; memcpy(&val, memPtr, sizeof(val)); return val;
|
||||
}
|
||||
|
||||
MEM_STATIC U32 MEM_read32(const void* memPtr)
|
||||
{
|
||||
U32 val; memcpy(&val, memPtr, sizeof(val)); return val;
|
||||
}
|
||||
|
||||
MEM_STATIC U64 MEM_read64(const void* memPtr)
|
||||
{
|
||||
U64 val; memcpy(&val, memPtr, sizeof(val)); return val;
|
||||
}
|
||||
|
||||
MEM_STATIC size_t MEM_readST(const void* memPtr)
|
||||
{
|
||||
size_t val; memcpy(&val, memPtr, sizeof(val)); return val;
|
||||
}
|
||||
|
||||
MEM_STATIC void MEM_write16(void* memPtr, U16 value)
|
||||
{
|
||||
memcpy(memPtr, &value, sizeof(value));
|
||||
}
|
||||
|
||||
MEM_STATIC void MEM_write32(void* memPtr, U32 value)
|
||||
{
|
||||
memcpy(memPtr, &value, sizeof(value));
|
||||
}
|
||||
|
||||
MEM_STATIC void MEM_write64(void* memPtr, U64 value)
|
||||
{
|
||||
memcpy(memPtr, &value, sizeof(value));
|
||||
}
|
||||
|
||||
#endif /* MEM_FORCE_MEMORY_ACCESS */
|
||||
|
||||
MEM_STATIC U32 MEM_swap32(U32 in)
|
||||
{
|
||||
#if defined(_MSC_VER) /* Visual Studio */
|
||||
return _byteswap_ulong(in);
|
||||
#elif defined (__GNUC__) && (__GNUC__ * 100 + __GNUC_MINOR__ >= 403)
|
||||
return __builtin_bswap32(in);
|
||||
#else
|
||||
return ((in << 24) & 0xff000000 ) |
|
||||
((in << 8) & 0x00ff0000 ) |
|
||||
((in >> 8) & 0x0000ff00 ) |
|
||||
((in >> 24) & 0x000000ff );
|
||||
#endif
|
||||
}
|
||||
|
||||
MEM_STATIC U64 MEM_swap64(U64 in)
|
||||
{
|
||||
#if defined(_MSC_VER) /* Visual Studio */
|
||||
return _byteswap_uint64(in);
|
||||
#elif defined (__GNUC__) && (__GNUC__ * 100 + __GNUC_MINOR__ >= 403)
|
||||
return __builtin_bswap64(in);
|
||||
#else
|
||||
return ((in << 56) & 0xff00000000000000ULL) |
|
||||
((in << 40) & 0x00ff000000000000ULL) |
|
||||
((in << 24) & 0x0000ff0000000000ULL) |
|
||||
((in << 8) & 0x000000ff00000000ULL) |
|
||||
((in >> 8) & 0x00000000ff000000ULL) |
|
||||
((in >> 24) & 0x0000000000ff0000ULL) |
|
||||
((in >> 40) & 0x000000000000ff00ULL) |
|
||||
((in >> 56) & 0x00000000000000ffULL);
|
||||
#endif
|
||||
}
|
||||
|
||||
MEM_STATIC size_t MEM_swapST(size_t in)
|
||||
{
|
||||
if (MEM_32bits())
|
||||
return (size_t)MEM_swap32((U32)in);
|
||||
else
|
||||
return (size_t)MEM_swap64((U64)in);
|
||||
}
|
||||
|
||||
/*=== Little endian r/w ===*/
|
||||
|
||||
MEM_STATIC U16 MEM_readLE16(const void* memPtr)
|
||||
{
|
||||
if (MEM_isLittleEndian())
|
||||
return MEM_read16(memPtr);
|
||||
else {
|
||||
const BYTE* p = (const BYTE*)memPtr;
|
||||
return (U16)(p[0] + (p[1]<<8));
|
||||
}
|
||||
}
|
||||
|
||||
MEM_STATIC void MEM_writeLE16(void* memPtr, U16 val)
|
||||
{
|
||||
if (MEM_isLittleEndian()) {
|
||||
MEM_write16(memPtr, val);
|
||||
} else {
|
||||
BYTE* p = (BYTE*)memPtr;
|
||||
p[0] = (BYTE)val;
|
||||
p[1] = (BYTE)(val>>8);
|
||||
}
|
||||
}
|
||||
|
||||
MEM_STATIC U32 MEM_readLE24(const void* memPtr)
|
||||
{
|
||||
return MEM_readLE16(memPtr) + (((const BYTE*)memPtr)[2] << 16);
|
||||
}
|
||||
|
||||
MEM_STATIC void MEM_writeLE24(void* memPtr, U32 val)
|
||||
{
|
||||
MEM_writeLE16(memPtr, (U16)val);
|
||||
((BYTE*)memPtr)[2] = (BYTE)(val>>16);
|
||||
}
|
||||
|
||||
MEM_STATIC U32 MEM_readLE32(const void* memPtr)
|
||||
{
|
||||
if (MEM_isLittleEndian())
|
||||
return MEM_read32(memPtr);
|
||||
else
|
||||
return MEM_swap32(MEM_read32(memPtr));
|
||||
}
|
||||
|
||||
MEM_STATIC void MEM_writeLE32(void* memPtr, U32 val32)
|
||||
{
|
||||
if (MEM_isLittleEndian())
|
||||
MEM_write32(memPtr, val32);
|
||||
else
|
||||
MEM_write32(memPtr, MEM_swap32(val32));
|
||||
}
|
||||
|
||||
MEM_STATIC U64 MEM_readLE64(const void* memPtr)
|
||||
{
|
||||
if (MEM_isLittleEndian())
|
||||
return MEM_read64(memPtr);
|
||||
else
|
||||
return MEM_swap64(MEM_read64(memPtr));
|
||||
}
|
||||
|
||||
MEM_STATIC void MEM_writeLE64(void* memPtr, U64 val64)
|
||||
{
|
||||
if (MEM_isLittleEndian())
|
||||
MEM_write64(memPtr, val64);
|
||||
else
|
||||
MEM_write64(memPtr, MEM_swap64(val64));
|
||||
}
|
||||
|
||||
MEM_STATIC size_t MEM_readLEST(const void* memPtr)
|
||||
{
|
||||
if (MEM_32bits())
|
||||
return (size_t)MEM_readLE32(memPtr);
|
||||
else
|
||||
return (size_t)MEM_readLE64(memPtr);
|
||||
}
|
||||
|
||||
MEM_STATIC void MEM_writeLEST(void* memPtr, size_t val)
|
||||
{
|
||||
if (MEM_32bits())
|
||||
MEM_writeLE32(memPtr, (U32)val);
|
||||
else
|
||||
MEM_writeLE64(memPtr, (U64)val);
|
||||
}
|
||||
|
||||
/*=== Big endian r/w ===*/
|
||||
|
||||
MEM_STATIC U32 MEM_readBE32(const void* memPtr)
|
||||
{
|
||||
if (MEM_isLittleEndian())
|
||||
return MEM_swap32(MEM_read32(memPtr));
|
||||
else
|
||||
return MEM_read32(memPtr);
|
||||
}
|
||||
|
||||
MEM_STATIC void MEM_writeBE32(void* memPtr, U32 val32)
|
||||
{
|
||||
if (MEM_isLittleEndian())
|
||||
MEM_write32(memPtr, MEM_swap32(val32));
|
||||
else
|
||||
MEM_write32(memPtr, val32);
|
||||
}
|
||||
|
||||
MEM_STATIC U64 MEM_readBE64(const void* memPtr)
|
||||
{
|
||||
if (MEM_isLittleEndian())
|
||||
return MEM_swap64(MEM_read64(memPtr));
|
||||
else
|
||||
return MEM_read64(memPtr);
|
||||
}
|
||||
|
||||
MEM_STATIC void MEM_writeBE64(void* memPtr, U64 val64)
|
||||
{
|
||||
if (MEM_isLittleEndian())
|
||||
MEM_write64(memPtr, MEM_swap64(val64));
|
||||
else
|
||||
MEM_write64(memPtr, val64);
|
||||
}
|
||||
|
||||
MEM_STATIC size_t MEM_readBEST(const void* memPtr)
|
||||
{
|
||||
if (MEM_32bits())
|
||||
return (size_t)MEM_readBE32(memPtr);
|
||||
else
|
||||
return (size_t)MEM_readBE64(memPtr);
|
||||
}
|
||||
|
||||
MEM_STATIC void MEM_writeBEST(void* memPtr, size_t val)
|
||||
{
|
||||
if (MEM_32bits())
|
||||
MEM_writeBE32(memPtr, (U32)val);
|
||||
else
|
||||
MEM_writeBE64(memPtr, (U64)val);
|
||||
}
|
||||
|
||||
|
||||
#if defined (__cplusplus)
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif /* MEM_H_MODULE */
|
||||
|
|
@ -0,0 +1,21 @@
|
|||
/*
|
||||
* GRUB -- GRand Unified Bootloader
|
||||
* Copyright (C) 2018 Free Software Foundation, Inc.
|
||||
*
|
||||
* GRUB is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
* the Free Software Foundation, either version 3 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* GRUB is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License
|
||||
* along with GRUB. If not, see <http://www.gnu.org/licenses/>.
|
||||
*/
|
||||
|
||||
#include <grub/dl.h>
|
||||
|
||||
GRUB_MOD_LICENSE ("GPLv3");
|
||||
|
|
@ -0,0 +1,876 @@
|
|||
/*
|
||||
* xxHash - Fast Hash algorithm
|
||||
* Copyright (C) 2012-2016, Yann Collet
|
||||
*
|
||||
* BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions are
|
||||
* met:
|
||||
*
|
||||
* * Redistributions of source code must retain the above copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
* * Redistributions in binary form must reproduce the above
|
||||
* copyright notice, this list of conditions and the following disclaimer
|
||||
* in the documentation and/or other materials provided with the
|
||||
* distribution.
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
*
|
||||
* You can contact the author at :
|
||||
* - xxHash homepage: http://www.xxhash.com
|
||||
* - xxHash source repository : https://github.com/Cyan4973/xxHash
|
||||
*/
|
||||
|
||||
|
||||
/* *************************************
|
||||
* Tuning parameters
|
||||
***************************************/
|
||||
/*!XXH_FORCE_MEMORY_ACCESS :
|
||||
* By default, access to unaligned memory is controlled by `memcpy()`, which is safe and portable.
|
||||
* Unfortunately, on some target/compiler combinations, the generated assembly is sub-optimal.
|
||||
* The below switch allow to select different access method for improved performance.
|
||||
* Method 0 (default) : use `memcpy()`. Safe and portable.
|
||||
* Method 1 : `__packed` statement. It depends on compiler extension (ie, not portable).
|
||||
* This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`.
|
||||
* Method 2 : direct access. This method doesn't depend on compiler but violate C standard.
|
||||
* It can generate buggy code on targets which do not support unaligned memory accesses.
|
||||
* But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6)
|
||||
* See http://stackoverflow.com/a/32095106/646947 for details.
|
||||
* Prefer these methods in priority order (0 > 1 > 2)
|
||||
*/
|
||||
#ifndef XXH_FORCE_MEMORY_ACCESS /* can be defined externally, on command line for example */
|
||||
# if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
|
||||
# define XXH_FORCE_MEMORY_ACCESS 2
|
||||
# elif (defined(__INTEL_COMPILER) && !defined(WIN32)) || \
|
||||
(defined(__GNUC__) && ( defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) || defined(__ARM_ARCH_7S__) ))
|
||||
# define XXH_FORCE_MEMORY_ACCESS 1
|
||||
# endif
|
||||
#endif
|
||||
|
||||
/*!XXH_ACCEPT_NULL_INPUT_POINTER :
|
||||
* If the input pointer is a null pointer, xxHash default behavior is to trigger a memory access error, since it is a bad pointer.
|
||||
* When this option is enabled, xxHash output for null input pointers will be the same as a null-length input.
|
||||
* By default, this option is disabled. To enable it, uncomment below define :
|
||||
*/
|
||||
/* #define XXH_ACCEPT_NULL_INPUT_POINTER 1 */
|
||||
|
||||
/*!XXH_FORCE_NATIVE_FORMAT :
|
||||
* By default, xxHash library provides endian-independant Hash values, based on little-endian convention.
|
||||
* Results are therefore identical for little-endian and big-endian CPU.
|
||||
* This comes at a performance cost for big-endian CPU, since some swapping is required to emulate little-endian format.
|
||||
* Should endian-independance be of no importance for your application, you may set the #define below to 1,
|
||||
* to improve speed for Big-endian CPU.
|
||||
* This option has no impact on Little_Endian CPU.
|
||||
*/
|
||||
#ifndef XXH_FORCE_NATIVE_FORMAT /* can be defined externally */
|
||||
# define XXH_FORCE_NATIVE_FORMAT 0
|
||||
#endif
|
||||
|
||||
/*!XXH_FORCE_ALIGN_CHECK :
|
||||
* This is a minor performance trick, only useful with lots of very small keys.
|
||||
* It means : check for aligned/unaligned input.
|
||||
* The check costs one initial branch per hash; set to 0 when the input data
|
||||
* is guaranteed to be aligned.
|
||||
*/
|
||||
#ifndef XXH_FORCE_ALIGN_CHECK /* can be defined externally */
|
||||
# if defined(__i386) || defined(_M_IX86) || defined(__x86_64__) || defined(_M_X64)
|
||||
# define XXH_FORCE_ALIGN_CHECK 0
|
||||
# else
|
||||
# define XXH_FORCE_ALIGN_CHECK 1
|
||||
# endif
|
||||
#endif
|
||||
|
||||
|
||||
/* *************************************
|
||||
* Includes & Memory related functions
|
||||
***************************************/
|
||||
/* Modify the local functions below should you wish to use some other memory routines */
|
||||
/* for malloc(), free() */
|
||||
#include <stdlib.h>
|
||||
#include <stddef.h> /* size_t */
|
||||
static void* XXH_malloc(size_t s) { return malloc(s); }
|
||||
static void XXH_free (void* p) { free(p); }
|
||||
/* for memcpy() */
|
||||
#include <string.h>
|
||||
static void* XXH_memcpy(void* dest, const void* src, size_t size) { return memcpy(dest,src,size); }
|
||||
|
||||
#ifndef XXH_STATIC_LINKING_ONLY
|
||||
# define XXH_STATIC_LINKING_ONLY
|
||||
#endif
|
||||
#include "xxhash.h"
|
||||
|
||||
|
||||
/* *************************************
|
||||
* Compiler Specific Options
|
||||
***************************************/
|
||||
#if defined (__GNUC__) || defined(__cplusplus) || defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */
|
||||
# define INLINE_KEYWORD inline
|
||||
#else
|
||||
# define INLINE_KEYWORD
|
||||
#endif
|
||||
|
||||
#if defined(__GNUC__)
|
||||
# define FORCE_INLINE_ATTR __attribute__((always_inline))
|
||||
#elif defined(_MSC_VER)
|
||||
# define FORCE_INLINE_ATTR __forceinline
|
||||
#else
|
||||
# define FORCE_INLINE_ATTR
|
||||
#endif
|
||||
|
||||
#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR
|
||||
|
||||
|
||||
#ifdef _MSC_VER
|
||||
# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
|
||||
#endif
|
||||
|
||||
|
||||
/* *************************************
|
||||
* Basic Types
|
||||
***************************************/
|
||||
#ifndef MEM_MODULE
|
||||
# define MEM_MODULE
|
||||
# if !defined (__VMS) && (defined (__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) )
|
||||
# include <stdint.h>
|
||||
typedef uint8_t BYTE;
|
||||
typedef uint16_t U16;
|
||||
typedef uint32_t U32;
|
||||
typedef int32_t S32;
|
||||
typedef uint64_t U64;
|
||||
# else
|
||||
typedef unsigned char BYTE;
|
||||
typedef unsigned short U16;
|
||||
typedef unsigned int U32;
|
||||
typedef signed int S32;
|
||||
typedef unsigned long long U64; /* if your compiler doesn't support unsigned long long, replace by another 64-bit type here. Note that xxhash.h will also need to be updated. */
|
||||
# endif
|
||||
#endif
|
||||
|
||||
|
||||
#if (defined(XXH_FORCE_MEMORY_ACCESS) && (XXH_FORCE_MEMORY_ACCESS==2))
|
||||
|
||||
/* Force direct memory access. Only works on CPU which support unaligned memory access in hardware */
|
||||
static U32 XXH_read32(const void* memPtr) { return *(const U32*) memPtr; }
|
||||
static U64 XXH_read64(const void* memPtr) { return *(const U64*) memPtr; }
|
||||
|
||||
#elif (defined(XXH_FORCE_MEMORY_ACCESS) && (XXH_FORCE_MEMORY_ACCESS==1))
|
||||
|
||||
/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */
|
||||
/* currently only defined for gcc and icc */
|
||||
typedef union { U32 u32; U64 u64; } __attribute__((packed)) unalign;
|
||||
|
||||
static U32 XXH_read32(const void* ptr) { return ((const unalign*)ptr)->u32; }
|
||||
static U64 XXH_read64(const void* ptr) { return ((const unalign*)ptr)->u64; }
|
||||
|
||||
#else
|
||||
|
||||
/* portable and safe solution. Generally efficient.
|
||||
* see : http://stackoverflow.com/a/32095106/646947
|
||||
*/
|
||||
|
||||
static U32 XXH_read32(const void* memPtr)
|
||||
{
|
||||
U32 val;
|
||||
memcpy(&val, memPtr, sizeof(val));
|
||||
return val;
|
||||
}
|
||||
|
||||
static U64 XXH_read64(const void* memPtr)
|
||||
{
|
||||
U64 val;
|
||||
memcpy(&val, memPtr, sizeof(val));
|
||||
return val;
|
||||
}
|
||||
|
||||
#endif /* XXH_FORCE_DIRECT_MEMORY_ACCESS */
|
||||
|
||||
|
||||
/* ****************************************
|
||||
* Compiler-specific Functions and Macros
|
||||
******************************************/
|
||||
#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
|
||||
|
||||
/* Note : although _rotl exists for minGW (GCC under windows), performance seems poor */
|
||||
#if defined(_MSC_VER)
|
||||
# define XXH_rotl32(x,r) _rotl(x,r)
|
||||
# define XXH_rotl64(x,r) _rotl64(x,r)
|
||||
#else
|
||||
# define XXH_rotl32(x,r) ((x << r) | (x >> (32 - r)))
|
||||
# define XXH_rotl64(x,r) ((x << r) | (x >> (64 - r)))
|
||||
#endif
|
||||
|
||||
#if defined(_MSC_VER) /* Visual Studio */
|
||||
# define XXH_swap32 _byteswap_ulong
|
||||
# define XXH_swap64 _byteswap_uint64
|
||||
#elif GCC_VERSION >= 403
|
||||
# define XXH_swap32 __builtin_bswap32
|
||||
# define XXH_swap64 __builtin_bswap64
|
||||
#else
|
||||
static U32 XXH_swap32 (U32 x)
|
||||
{
|
||||
return ((x << 24) & 0xff000000 ) |
|
||||
((x << 8) & 0x00ff0000 ) |
|
||||
((x >> 8) & 0x0000ff00 ) |
|
||||
((x >> 24) & 0x000000ff );
|
||||
}
|
||||
static U64 XXH_swap64 (U64 x)
|
||||
{
|
||||
return ((x << 56) & 0xff00000000000000ULL) |
|
||||
((x << 40) & 0x00ff000000000000ULL) |
|
||||
((x << 24) & 0x0000ff0000000000ULL) |
|
||||
((x << 8) & 0x000000ff00000000ULL) |
|
||||
((x >> 8) & 0x00000000ff000000ULL) |
|
||||
((x >> 24) & 0x0000000000ff0000ULL) |
|
||||
((x >> 40) & 0x000000000000ff00ULL) |
|
||||
((x >> 56) & 0x00000000000000ffULL);
|
||||
}
|
||||
#endif
|
||||
|
||||
|
||||
/* *************************************
|
||||
* Architecture Macros
|
||||
***************************************/
|
||||
typedef enum { XXH_bigEndian=0, XXH_littleEndian=1 } XXH_endianess;
|
||||
|
||||
/* XXH_CPU_LITTLE_ENDIAN can be defined externally, for example on the compiler command line */
|
||||
#ifndef XXH_CPU_LITTLE_ENDIAN
|
||||
static const int g_one = 1;
|
||||
# define XXH_CPU_LITTLE_ENDIAN (*(const char*)(&g_one))
|
||||
#endif
|
||||
|
||||
|
||||
/* ***************************
|
||||
* Memory reads
|
||||
*****************************/
|
||||
typedef enum { XXH_aligned, XXH_unaligned } XXH_alignment;
|
||||
|
||||
FORCE_INLINE_TEMPLATE U32 XXH_readLE32_align(const void* ptr, XXH_endianess endian, XXH_alignment align)
|
||||
{
|
||||
if (align==XXH_unaligned)
|
||||
return endian==XXH_littleEndian ? XXH_read32(ptr) : XXH_swap32(XXH_read32(ptr));
|
||||
else
|
||||
return endian==XXH_littleEndian ? *(const U32*)ptr : XXH_swap32(*(const U32*)ptr);
|
||||
}
|
||||
|
||||
FORCE_INLINE_TEMPLATE U32 XXH_readLE32(const void* ptr, XXH_endianess endian)
|
||||
{
|
||||
return XXH_readLE32_align(ptr, endian, XXH_unaligned);
|
||||
}
|
||||
|
||||
static U32 XXH_readBE32(const void* ptr)
|
||||
{
|
||||
return XXH_CPU_LITTLE_ENDIAN ? XXH_swap32(XXH_read32(ptr)) : XXH_read32(ptr);
|
||||
}
|
||||
|
||||
FORCE_INLINE_TEMPLATE U64 XXH_readLE64_align(const void* ptr, XXH_endianess endian, XXH_alignment align)
|
||||
{
|
||||
if (align==XXH_unaligned)
|
||||
return endian==XXH_littleEndian ? XXH_read64(ptr) : XXH_swap64(XXH_read64(ptr));
|
||||
else
|
||||
return endian==XXH_littleEndian ? *(const U64*)ptr : XXH_swap64(*(const U64*)ptr);
|
||||
}
|
||||
|
||||
FORCE_INLINE_TEMPLATE U64 XXH_readLE64(const void* ptr, XXH_endianess endian)
|
||||
{
|
||||
return XXH_readLE64_align(ptr, endian, XXH_unaligned);
|
||||
}
|
||||
|
||||
static U64 XXH_readBE64(const void* ptr)
|
||||
{
|
||||
return XXH_CPU_LITTLE_ENDIAN ? XXH_swap64(XXH_read64(ptr)) : XXH_read64(ptr);
|
||||
}
|
||||
|
||||
|
||||
/* *************************************
|
||||
* Macros
|
||||
***************************************/
|
||||
#define XXH_STATIC_ASSERT(c) { enum { XXH_static_assert = 1/(int)(!!(c)) }; } /* use only *after* variable declarations */
|
||||
|
||||
|
||||
/* *************************************
|
||||
* Constants
|
||||
***************************************/
|
||||
static const U32 PRIME32_1 = 2654435761U;
|
||||
static const U32 PRIME32_2 = 2246822519U;
|
||||
static const U32 PRIME32_3 = 3266489917U;
|
||||
static const U32 PRIME32_4 = 668265263U;
|
||||
static const U32 PRIME32_5 = 374761393U;
|
||||
|
||||
static const U64 PRIME64_1 = 11400714785074694791ULL;
|
||||
static const U64 PRIME64_2 = 14029467366897019727ULL;
|
||||
static const U64 PRIME64_3 = 1609587929392839161ULL;
|
||||
static const U64 PRIME64_4 = 9650029242287828579ULL;
|
||||
static const U64 PRIME64_5 = 2870177450012600261ULL;
|
||||
|
||||
XXH_PUBLIC_API unsigned XXH_versionNumber (void) { return XXH_VERSION_NUMBER; }
|
||||
|
||||
|
||||
/* **************************
|
||||
* Utils
|
||||
****************************/
|
||||
XXH_PUBLIC_API void XXH32_copyState(XXH32_state_t* restrict dstState, const XXH32_state_t* restrict srcState)
|
||||
{
|
||||
memcpy(dstState, srcState, sizeof(*dstState));
|
||||
}
|
||||
|
||||
XXH_PUBLIC_API void XXH64_copyState(XXH64_state_t* restrict dstState, const XXH64_state_t* restrict srcState)
|
||||
{
|
||||
memcpy(dstState, srcState, sizeof(*dstState));
|
||||
}
|
||||
|
||||
|
||||
/* ***************************
|
||||
* Simple Hash Functions
|
||||
*****************************/
|
||||
|
||||
static U32 XXH32_round(U32 seed, U32 input)
|
||||
{
|
||||
seed += input * PRIME32_2;
|
||||
seed = XXH_rotl32(seed, 13);
|
||||
seed *= PRIME32_1;
|
||||
return seed;
|
||||
}
|
||||
|
||||
FORCE_INLINE_TEMPLATE U32 XXH32_endian_align(const void* input, size_t len, U32 seed, XXH_endianess endian, XXH_alignment align)
|
||||
{
|
||||
const BYTE* p = (const BYTE*)input;
|
||||
const BYTE* bEnd = p + len;
|
||||
U32 h32;
|
||||
#define XXH_get32bits(p) XXH_readLE32_align(p, endian, align)
|
||||
|
||||
#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
|
||||
if (p==NULL) {
|
||||
len=0;
|
||||
bEnd=p=(const BYTE*)(size_t)16;
|
||||
}
|
||||
#endif
|
||||
|
||||
if (len>=16) {
|
||||
const BYTE* const limit = bEnd - 16;
|
||||
U32 v1 = seed + PRIME32_1 + PRIME32_2;
|
||||
U32 v2 = seed + PRIME32_2;
|
||||
U32 v3 = seed + 0;
|
||||
U32 v4 = seed - PRIME32_1;
|
||||
|
||||
do {
|
||||
v1 = XXH32_round(v1, XXH_get32bits(p)); p+=4;
|
||||
v2 = XXH32_round(v2, XXH_get32bits(p)); p+=4;
|
||||
v3 = XXH32_round(v3, XXH_get32bits(p)); p+=4;
|
||||
v4 = XXH32_round(v4, XXH_get32bits(p)); p+=4;
|
||||
} while (p<=limit);
|
||||
|
||||
h32 = XXH_rotl32(v1, 1) + XXH_rotl32(v2, 7) + XXH_rotl32(v3, 12) + XXH_rotl32(v4, 18);
|
||||
} else {
|
||||
h32 = seed + PRIME32_5;
|
||||
}
|
||||
|
||||
h32 += (U32) len;
|
||||
|
||||
while (p+4<=bEnd) {
|
||||
h32 += XXH_get32bits(p) * PRIME32_3;
|
||||
h32 = XXH_rotl32(h32, 17) * PRIME32_4 ;
|
||||
p+=4;
|
||||
}
|
||||
|
||||
while (p<bEnd) {
|
||||
h32 += (*p) * PRIME32_5;
|
||||
h32 = XXH_rotl32(h32, 11) * PRIME32_1 ;
|
||||
p++;
|
||||
}
|
||||
|
||||
h32 ^= h32 >> 15;
|
||||
h32 *= PRIME32_2;
|
||||
h32 ^= h32 >> 13;
|
||||
h32 *= PRIME32_3;
|
||||
h32 ^= h32 >> 16;
|
||||
|
||||
return h32;
|
||||
}
|
||||
|
||||
|
||||
XXH_PUBLIC_API unsigned int XXH32 (const void* input, size_t len, unsigned int seed)
|
||||
{
|
||||
#if 0
|
||||
/* Simple version, good for code maintenance, but unfortunately slow for small inputs */
|
||||
XXH32_CREATESTATE_STATIC(state);
|
||||
XXH32_reset(state, seed);
|
||||
XXH32_update(state, input, len);
|
||||
return XXH32_digest(state);
|
||||
#else
|
||||
XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
|
||||
|
||||
if (XXH_FORCE_ALIGN_CHECK) {
|
||||
if ((((size_t)input) & 3) == 0) { /* Input is 4-bytes aligned, leverage the speed benefit */
|
||||
if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
|
||||
return XXH32_endian_align(input, len, seed, XXH_littleEndian, XXH_aligned);
|
||||
else
|
||||
return XXH32_endian_align(input, len, seed, XXH_bigEndian, XXH_aligned);
|
||||
} }
|
||||
|
||||
if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
|
||||
return XXH32_endian_align(input, len, seed, XXH_littleEndian, XXH_unaligned);
|
||||
else
|
||||
return XXH32_endian_align(input, len, seed, XXH_bigEndian, XXH_unaligned);
|
||||
#endif
|
||||
}
|
||||
|
||||
|
||||
static U64 XXH64_round(U64 acc, U64 input)
|
||||
{
|
||||
acc += input * PRIME64_2;
|
||||
acc = XXH_rotl64(acc, 31);
|
||||
acc *= PRIME64_1;
|
||||
return acc;
|
||||
}
|
||||
|
||||
static U64 XXH64_mergeRound(U64 acc, U64 val)
|
||||
{
|
||||
val = XXH64_round(0, val);
|
||||
acc ^= val;
|
||||
acc = acc * PRIME64_1 + PRIME64_4;
|
||||
return acc;
|
||||
}
|
||||
|
||||
FORCE_INLINE_TEMPLATE U64 XXH64_endian_align(const void* input, size_t len, U64 seed, XXH_endianess endian, XXH_alignment align)
|
||||
{
|
||||
const BYTE* p = (const BYTE*)input;
|
||||
const BYTE* const bEnd = p + len;
|
||||
U64 h64;
|
||||
#define XXH_get64bits(p) XXH_readLE64_align(p, endian, align)
|
||||
|
||||
#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
|
||||
if (p==NULL) {
|
||||
len=0;
|
||||
bEnd=p=(const BYTE*)(size_t)32;
|
||||
}
|
||||
#endif
|
||||
|
||||
if (len>=32) {
|
||||
const BYTE* const limit = bEnd - 32;
|
||||
U64 v1 = seed + PRIME64_1 + PRIME64_2;
|
||||
U64 v2 = seed + PRIME64_2;
|
||||
U64 v3 = seed + 0;
|
||||
U64 v4 = seed - PRIME64_1;
|
||||
|
||||
do {
|
||||
v1 = XXH64_round(v1, XXH_get64bits(p)); p+=8;
|
||||
v2 = XXH64_round(v2, XXH_get64bits(p)); p+=8;
|
||||
v3 = XXH64_round(v3, XXH_get64bits(p)); p+=8;
|
||||
v4 = XXH64_round(v4, XXH_get64bits(p)); p+=8;
|
||||
} while (p<=limit);
|
||||
|
||||
h64 = XXH_rotl64(v1, 1) + XXH_rotl64(v2, 7) + XXH_rotl64(v3, 12) + XXH_rotl64(v4, 18);
|
||||
h64 = XXH64_mergeRound(h64, v1);
|
||||
h64 = XXH64_mergeRound(h64, v2);
|
||||
h64 = XXH64_mergeRound(h64, v3);
|
||||
h64 = XXH64_mergeRound(h64, v4);
|
||||
|
||||
} else {
|
||||
h64 = seed + PRIME64_5;
|
||||
}
|
||||
|
||||
h64 += (U64) len;
|
||||
|
||||
while (p+8<=bEnd) {
|
||||
U64 const k1 = XXH64_round(0, XXH_get64bits(p));
|
||||
h64 ^= k1;
|
||||
h64 = XXH_rotl64(h64,27) * PRIME64_1 + PRIME64_4;
|
||||
p+=8;
|
||||
}
|
||||
|
||||
if (p+4<=bEnd) {
|
||||
h64 ^= (U64)(XXH_get32bits(p)) * PRIME64_1;
|
||||
h64 = XXH_rotl64(h64, 23) * PRIME64_2 + PRIME64_3;
|
||||
p+=4;
|
||||
}
|
||||
|
||||
while (p<bEnd) {
|
||||
h64 ^= (*p) * PRIME64_5;
|
||||
h64 = XXH_rotl64(h64, 11) * PRIME64_1;
|
||||
p++;
|
||||
}
|
||||
|
||||
h64 ^= h64 >> 33;
|
||||
h64 *= PRIME64_2;
|
||||
h64 ^= h64 >> 29;
|
||||
h64 *= PRIME64_3;
|
||||
h64 ^= h64 >> 32;
|
||||
|
||||
return h64;
|
||||
}
|
||||
|
||||
|
||||
XXH_PUBLIC_API unsigned long long XXH64 (const void* input, size_t len, unsigned long long seed)
|
||||
{
|
||||
#if 0
|
||||
/* Simple version, good for code maintenance, but unfortunately slow for small inputs */
|
||||
XXH64_CREATESTATE_STATIC(state);
|
||||
XXH64_reset(state, seed);
|
||||
XXH64_update(state, input, len);
|
||||
return XXH64_digest(state);
|
||||
#else
|
||||
XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
|
||||
|
||||
if (XXH_FORCE_ALIGN_CHECK) {
|
||||
if ((((size_t)input) & 7)==0) { /* Input is aligned, let's leverage the speed advantage */
|
||||
if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
|
||||
return XXH64_endian_align(input, len, seed, XXH_littleEndian, XXH_aligned);
|
||||
else
|
||||
return XXH64_endian_align(input, len, seed, XXH_bigEndian, XXH_aligned);
|
||||
} }
|
||||
|
||||
if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
|
||||
return XXH64_endian_align(input, len, seed, XXH_littleEndian, XXH_unaligned);
|
||||
else
|
||||
return XXH64_endian_align(input, len, seed, XXH_bigEndian, XXH_unaligned);
|
||||
#endif
|
||||
}
|
||||
|
||||
|
||||
/* **************************************************
|
||||
* Advanced Hash Functions
|
||||
****************************************************/
|
||||
|
||||
XXH_PUBLIC_API XXH32_state_t* XXH32_createState(void)
|
||||
{
|
||||
return (XXH32_state_t*)XXH_malloc(sizeof(XXH32_state_t));
|
||||
}
|
||||
XXH_PUBLIC_API XXH_errorcode XXH32_freeState(XXH32_state_t* statePtr)
|
||||
{
|
||||
XXH_free(statePtr);
|
||||
return XXH_OK;
|
||||
}
|
||||
|
||||
XXH_PUBLIC_API XXH64_state_t* XXH64_createState(void)
|
||||
{
|
||||
return (XXH64_state_t*)XXH_malloc(sizeof(XXH64_state_t));
|
||||
}
|
||||
XXH_PUBLIC_API XXH_errorcode XXH64_freeState(XXH64_state_t* statePtr)
|
||||
{
|
||||
XXH_free(statePtr);
|
||||
return XXH_OK;
|
||||
}
|
||||
|
||||
|
||||
/*** Hash feed ***/
|
||||
|
||||
XXH_PUBLIC_API XXH_errorcode XXH32_reset(XXH32_state_t* statePtr, unsigned int seed)
|
||||
{
|
||||
XXH32_state_t state; /* using a local state to memcpy() in order to avoid strict-aliasing warnings */
|
||||
memset(&state, 0, sizeof(state)-4); /* do not write into reserved, for future removal */
|
||||
state.v1 = seed + PRIME32_1 + PRIME32_2;
|
||||
state.v2 = seed + PRIME32_2;
|
||||
state.v3 = seed + 0;
|
||||
state.v4 = seed - PRIME32_1;
|
||||
memcpy(statePtr, &state, sizeof(state));
|
||||
return XXH_OK;
|
||||
}
|
||||
|
||||
|
||||
XXH_PUBLIC_API XXH_errorcode XXH64_reset(XXH64_state_t* statePtr, unsigned long long seed)
|
||||
{
|
||||
XXH64_state_t state; /* using a local state to memcpy() in order to avoid strict-aliasing warnings */
|
||||
memset(&state, 0, sizeof(state)-8); /* do not write into reserved, for future removal */
|
||||
state.v1 = seed + PRIME64_1 + PRIME64_2;
|
||||
state.v2 = seed + PRIME64_2;
|
||||
state.v3 = seed + 0;
|
||||
state.v4 = seed - PRIME64_1;
|
||||
memcpy(statePtr, &state, sizeof(state));
|
||||
return XXH_OK;
|
||||
}
|
||||
|
||||
|
||||
FORCE_INLINE_TEMPLATE XXH_errorcode XXH32_update_endian (XXH32_state_t* state, const void* input, size_t len, XXH_endianess endian)
|
||||
{
|
||||
const BYTE* p = (const BYTE*)input;
|
||||
const BYTE* const bEnd = p + len;
|
||||
|
||||
#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
|
||||
if (input==NULL) return XXH_ERROR;
|
||||
#endif
|
||||
|
||||
state->total_len_32 += (unsigned)len;
|
||||
state->large_len |= (len>=16) | (state->total_len_32>=16);
|
||||
|
||||
if (state->memsize + len < 16) { /* fill in tmp buffer */
|
||||
XXH_memcpy((BYTE*)(state->mem32) + state->memsize, input, len);
|
||||
state->memsize += (unsigned)len;
|
||||
return XXH_OK;
|
||||
}
|
||||
|
||||
if (state->memsize) { /* some data left from previous update */
|
||||
XXH_memcpy((BYTE*)(state->mem32) + state->memsize, input, 16-state->memsize);
|
||||
{ const U32* p32 = state->mem32;
|
||||
state->v1 = XXH32_round(state->v1, XXH_readLE32(p32, endian)); p32++;
|
||||
state->v2 = XXH32_round(state->v2, XXH_readLE32(p32, endian)); p32++;
|
||||
state->v3 = XXH32_round(state->v3, XXH_readLE32(p32, endian)); p32++;
|
||||
state->v4 = XXH32_round(state->v4, XXH_readLE32(p32, endian)); p32++;
|
||||
}
|
||||
p += 16-state->memsize;
|
||||
state->memsize = 0;
|
||||
}
|
||||
|
||||
if (p <= bEnd-16) {
|
||||
const BYTE* const limit = bEnd - 16;
|
||||
U32 v1 = state->v1;
|
||||
U32 v2 = state->v2;
|
||||
U32 v3 = state->v3;
|
||||
U32 v4 = state->v4;
|
||||
|
||||
do {
|
||||
v1 = XXH32_round(v1, XXH_readLE32(p, endian)); p+=4;
|
||||
v2 = XXH32_round(v2, XXH_readLE32(p, endian)); p+=4;
|
||||
v3 = XXH32_round(v3, XXH_readLE32(p, endian)); p+=4;
|
||||
v4 = XXH32_round(v4, XXH_readLE32(p, endian)); p+=4;
|
||||
} while (p<=limit);
|
||||
|
||||
state->v1 = v1;
|
||||
state->v2 = v2;
|
||||
state->v3 = v3;
|
||||
state->v4 = v4;
|
||||
}
|
||||
|
||||
if (p < bEnd) {
|
||||
XXH_memcpy(state->mem32, p, (size_t)(bEnd-p));
|
||||
state->memsize = (unsigned)(bEnd-p);
|
||||
}
|
||||
|
||||
return XXH_OK;
|
||||
}
|
||||
|
||||
XXH_PUBLIC_API XXH_errorcode XXH32_update (XXH32_state_t* state_in, const void* input, size_t len)
|
||||
{
|
||||
XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
|
||||
|
||||
if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
|
||||
return XXH32_update_endian(state_in, input, len, XXH_littleEndian);
|
||||
else
|
||||
return XXH32_update_endian(state_in, input, len, XXH_bigEndian);
|
||||
}
|
||||
|
||||
|
||||
|
||||
FORCE_INLINE_TEMPLATE U32 XXH32_digest_endian (const XXH32_state_t* state, XXH_endianess endian)
|
||||
{
|
||||
const BYTE * p = (const BYTE*)state->mem32;
|
||||
const BYTE* const bEnd = (const BYTE*)(state->mem32) + state->memsize;
|
||||
U32 h32;
|
||||
|
||||
if (state->large_len) {
|
||||
h32 = XXH_rotl32(state->v1, 1) + XXH_rotl32(state->v2, 7) + XXH_rotl32(state->v3, 12) + XXH_rotl32(state->v4, 18);
|
||||
} else {
|
||||
h32 = state->v3 /* == seed */ + PRIME32_5;
|
||||
}
|
||||
|
||||
h32 += state->total_len_32;
|
||||
|
||||
while (p+4<=bEnd) {
|
||||
h32 += XXH_readLE32(p, endian) * PRIME32_3;
|
||||
h32 = XXH_rotl32(h32, 17) * PRIME32_4;
|
||||
p+=4;
|
||||
}
|
||||
|
||||
while (p<bEnd) {
|
||||
h32 += (*p) * PRIME32_5;
|
||||
h32 = XXH_rotl32(h32, 11) * PRIME32_1;
|
||||
p++;
|
||||
}
|
||||
|
||||
h32 ^= h32 >> 15;
|
||||
h32 *= PRIME32_2;
|
||||
h32 ^= h32 >> 13;
|
||||
h32 *= PRIME32_3;
|
||||
h32 ^= h32 >> 16;
|
||||
|
||||
return h32;
|
||||
}
|
||||
|
||||
|
||||
XXH_PUBLIC_API unsigned int XXH32_digest (const XXH32_state_t* state_in)
|
||||
{
|
||||
XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
|
||||
|
||||
if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
|
||||
return XXH32_digest_endian(state_in, XXH_littleEndian);
|
||||
else
|
||||
return XXH32_digest_endian(state_in, XXH_bigEndian);
|
||||
}
|
||||
|
||||
|
||||
|
||||
/* **** XXH64 **** */
|
||||
|
||||
FORCE_INLINE_TEMPLATE XXH_errorcode XXH64_update_endian (XXH64_state_t* state, const void* input, size_t len, XXH_endianess endian)
|
||||
{
|
||||
const BYTE* p = (const BYTE*)input;
|
||||
const BYTE* const bEnd = p + len;
|
||||
|
||||
#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
|
||||
if (input==NULL) return XXH_ERROR;
|
||||
#endif
|
||||
|
||||
state->total_len += len;
|
||||
|
||||
if (state->memsize + len < 32) { /* fill in tmp buffer */
|
||||
XXH_memcpy(((BYTE*)state->mem64) + state->memsize, input, len);
|
||||
state->memsize += (U32)len;
|
||||
return XXH_OK;
|
||||
}
|
||||
|
||||
if (state->memsize) { /* tmp buffer is full */
|
||||
XXH_memcpy(((BYTE*)state->mem64) + state->memsize, input, 32-state->memsize);
|
||||
state->v1 = XXH64_round(state->v1, XXH_readLE64(state->mem64+0, endian));
|
||||
state->v2 = XXH64_round(state->v2, XXH_readLE64(state->mem64+1, endian));
|
||||
state->v3 = XXH64_round(state->v3, XXH_readLE64(state->mem64+2, endian));
|
||||
state->v4 = XXH64_round(state->v4, XXH_readLE64(state->mem64+3, endian));
|
||||
p += 32-state->memsize;
|
||||
state->memsize = 0;
|
||||
}
|
||||
|
||||
if (p+32 <= bEnd) {
|
||||
const BYTE* const limit = bEnd - 32;
|
||||
U64 v1 = state->v1;
|
||||
U64 v2 = state->v2;
|
||||
U64 v3 = state->v3;
|
||||
U64 v4 = state->v4;
|
||||
|
||||
do {
|
||||
v1 = XXH64_round(v1, XXH_readLE64(p, endian)); p+=8;
|
||||
v2 = XXH64_round(v2, XXH_readLE64(p, endian)); p+=8;
|
||||
v3 = XXH64_round(v3, XXH_readLE64(p, endian)); p+=8;
|
||||
v4 = XXH64_round(v4, XXH_readLE64(p, endian)); p+=8;
|
||||
} while (p<=limit);
|
||||
|
||||
state->v1 = v1;
|
||||
state->v2 = v2;
|
||||
state->v3 = v3;
|
||||
state->v4 = v4;
|
||||
}
|
||||
|
||||
if (p < bEnd) {
|
||||
XXH_memcpy(state->mem64, p, (size_t)(bEnd-p));
|
||||
state->memsize = (unsigned)(bEnd-p);
|
||||
}
|
||||
|
||||
return XXH_OK;
|
||||
}
|
||||
|
||||
XXH_PUBLIC_API XXH_errorcode XXH64_update (XXH64_state_t* state_in, const void* input, size_t len)
|
||||
{
|
||||
XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
|
||||
|
||||
if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
|
||||
return XXH64_update_endian(state_in, input, len, XXH_littleEndian);
|
||||
else
|
||||
return XXH64_update_endian(state_in, input, len, XXH_bigEndian);
|
||||
}
|
||||
|
||||
|
||||
|
||||
FORCE_INLINE_TEMPLATE U64 XXH64_digest_endian (const XXH64_state_t* state, XXH_endianess endian)
|
||||
{
|
||||
const BYTE * p = (const BYTE*)state->mem64;
|
||||
const BYTE* const bEnd = (const BYTE*)state->mem64 + state->memsize;
|
||||
U64 h64;
|
||||
|
||||
if (state->total_len >= 32) {
|
||||
U64 const v1 = state->v1;
|
||||
U64 const v2 = state->v2;
|
||||
U64 const v3 = state->v3;
|
||||
U64 const v4 = state->v4;
|
||||
|
||||
h64 = XXH_rotl64(v1, 1) + XXH_rotl64(v2, 7) + XXH_rotl64(v3, 12) + XXH_rotl64(v4, 18);
|
||||
h64 = XXH64_mergeRound(h64, v1);
|
||||
h64 = XXH64_mergeRound(h64, v2);
|
||||
h64 = XXH64_mergeRound(h64, v3);
|
||||
h64 = XXH64_mergeRound(h64, v4);
|
||||
} else {
|
||||
h64 = state->v3 + PRIME64_5;
|
||||
}
|
||||
|
||||
h64 += (U64) state->total_len;
|
||||
|
||||
while (p+8<=bEnd) {
|
||||
U64 const k1 = XXH64_round(0, XXH_readLE64(p, endian));
|
||||
h64 ^= k1;
|
||||
h64 = XXH_rotl64(h64,27) * PRIME64_1 + PRIME64_4;
|
||||
p+=8;
|
||||
}
|
||||
|
||||
if (p+4<=bEnd) {
|
||||
h64 ^= (U64)(XXH_readLE32(p, endian)) * PRIME64_1;
|
||||
h64 = XXH_rotl64(h64, 23) * PRIME64_2 + PRIME64_3;
|
||||
p+=4;
|
||||
}
|
||||
|
||||
while (p<bEnd) {
|
||||
h64 ^= (*p) * PRIME64_5;
|
||||
h64 = XXH_rotl64(h64, 11) * PRIME64_1;
|
||||
p++;
|
||||
}
|
||||
|
||||
h64 ^= h64 >> 33;
|
||||
h64 *= PRIME64_2;
|
||||
h64 ^= h64 >> 29;
|
||||
h64 *= PRIME64_3;
|
||||
h64 ^= h64 >> 32;
|
||||
|
||||
return h64;
|
||||
}
|
||||
|
||||
|
||||
XXH_PUBLIC_API unsigned long long XXH64_digest (const XXH64_state_t* state_in)
|
||||
{
|
||||
XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
|
||||
|
||||
if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
|
||||
return XXH64_digest_endian(state_in, XXH_littleEndian);
|
||||
else
|
||||
return XXH64_digest_endian(state_in, XXH_bigEndian);
|
||||
}
|
||||
|
||||
|
||||
/* **************************
|
||||
* Canonical representation
|
||||
****************************/
|
||||
|
||||
/*! Default XXH result types are basic unsigned 32 and 64 bits.
|
||||
* The canonical representation follows human-readable write convention, aka big-endian (large digits first).
|
||||
* These functions allow transformation of hash result into and from its canonical format.
|
||||
* This way, hash values can be written into a file or buffer, and remain comparable across different systems and programs.
|
||||
*/
|
||||
|
||||
XXH_PUBLIC_API void XXH32_canonicalFromHash(XXH32_canonical_t* dst, XXH32_hash_t hash)
|
||||
{
|
||||
XXH_STATIC_ASSERT(sizeof(XXH32_canonical_t) == sizeof(XXH32_hash_t));
|
||||
if (XXH_CPU_LITTLE_ENDIAN) hash = XXH_swap32(hash);
|
||||
memcpy(dst, &hash, sizeof(*dst));
|
||||
}
|
||||
|
||||
XXH_PUBLIC_API void XXH64_canonicalFromHash(XXH64_canonical_t* dst, XXH64_hash_t hash)
|
||||
{
|
||||
XXH_STATIC_ASSERT(sizeof(XXH64_canonical_t) == sizeof(XXH64_hash_t));
|
||||
if (XXH_CPU_LITTLE_ENDIAN) hash = XXH_swap64(hash);
|
||||
memcpy(dst, &hash, sizeof(*dst));
|
||||
}
|
||||
|
||||
XXH_PUBLIC_API XXH32_hash_t XXH32_hashFromCanonical(const XXH32_canonical_t* src)
|
||||
{
|
||||
return XXH_readBE32(src);
|
||||
}
|
||||
|
||||
XXH_PUBLIC_API XXH64_hash_t XXH64_hashFromCanonical(const XXH64_canonical_t* src)
|
||||
{
|
||||
return XXH_readBE64(src);
|
||||
}
|
||||
|
|
@ -0,0 +1,305 @@
|
|||
/*
|
||||
xxHash - Extremely Fast Hash algorithm
|
||||
Header File
|
||||
Copyright (C) 2012-2016, Yann Collet.
|
||||
|
||||
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
You can contact the author at :
|
||||
- xxHash source repository : https://github.com/Cyan4973/xxHash
|
||||
*/
|
||||
|
||||
/* Notice extracted from xxHash homepage :
|
||||
|
||||
xxHash is an extremely fast Hash algorithm, running at RAM speed limits.
|
||||
It also successfully passes all tests from the SMHasher suite.
|
||||
|
||||
Comparison (single thread, Windows Seven 32 bits, using SMHasher on a Core 2 Duo @3GHz)
|
||||
|
||||
Name Speed Q.Score Author
|
||||
xxHash 5.4 GB/s 10
|
||||
CrapWow 3.2 GB/s 2 Andrew
|
||||
MumurHash 3a 2.7 GB/s 10 Austin Appleby
|
||||
SpookyHash 2.0 GB/s 10 Bob Jenkins
|
||||
SBox 1.4 GB/s 9 Bret Mulvey
|
||||
Lookup3 1.2 GB/s 9 Bob Jenkins
|
||||
SuperFastHash 1.2 GB/s 1 Paul Hsieh
|
||||
CityHash64 1.05 GB/s 10 Pike & Alakuijala
|
||||
FNV 0.55 GB/s 5 Fowler, Noll, Vo
|
||||
CRC32 0.43 GB/s 9
|
||||
MD5-32 0.33 GB/s 10 Ronald L. Rivest
|
||||
SHA1-32 0.28 GB/s 10
|
||||
|
||||
Q.Score is a measure of quality of the hash function.
|
||||
It depends on successfully passing SMHasher test set.
|
||||
10 is a perfect score.
|
||||
|
||||
A 64-bits version, named XXH64, is available since r35.
|
||||
It offers much better speed, but for 64-bits applications only.
|
||||
Name Speed on 64 bits Speed on 32 bits
|
||||
XXH64 13.8 GB/s 1.9 GB/s
|
||||
XXH32 6.8 GB/s 6.0 GB/s
|
||||
*/
|
||||
|
||||
#if defined (__cplusplus)
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#ifndef XXHASH_H_5627135585666179
|
||||
#define XXHASH_H_5627135585666179 1
|
||||
|
||||
|
||||
/* ****************************
|
||||
* Definitions
|
||||
******************************/
|
||||
#include <stddef.h> /* size_t */
|
||||
typedef enum { XXH_OK=0, XXH_ERROR } XXH_errorcode;
|
||||
|
||||
|
||||
/* ****************************
|
||||
* API modifier
|
||||
******************************/
|
||||
/** XXH_PRIVATE_API
|
||||
* This is useful if you want to include xxhash functions in `static` mode
|
||||
* in order to inline them, and remove their symbol from the public list.
|
||||
* Methodology :
|
||||
* #define XXH_PRIVATE_API
|
||||
* #include "xxhash.h"
|
||||
* `xxhash.c` is automatically included.
|
||||
* It's not useful to compile and link it as a separate module anymore.
|
||||
*/
|
||||
#ifdef XXH_PRIVATE_API
|
||||
# ifndef XXH_STATIC_LINKING_ONLY
|
||||
# define XXH_STATIC_LINKING_ONLY
|
||||
# endif
|
||||
# if defined(__GNUC__)
|
||||
# define XXH_PUBLIC_API static __inline __attribute__((unused))
|
||||
# elif defined (__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
|
||||
# define XXH_PUBLIC_API static inline
|
||||
# elif defined(_MSC_VER)
|
||||
# define XXH_PUBLIC_API static __inline
|
||||
# else
|
||||
# define XXH_PUBLIC_API static /* this version may generate warnings for unused static functions; disable the relevant warning */
|
||||
# endif
|
||||
#else
|
||||
# define XXH_PUBLIC_API /* do nothing */
|
||||
#endif /* XXH_PRIVATE_API */
|
||||
|
||||
/*!XXH_NAMESPACE, aka Namespace Emulation :
|
||||
|
||||
If you want to include _and expose_ xxHash functions from within your own library,
|
||||
but also want to avoid symbol collisions with another library which also includes xxHash,
|
||||
|
||||
you can use XXH_NAMESPACE, to automatically prefix any public symbol from xxhash library
|
||||
with the value of XXH_NAMESPACE (so avoid to keep it NULL and avoid numeric values).
|
||||
|
||||
Note that no change is required within the calling program as long as it includes `xxhash.h` :
|
||||
regular symbol name will be automatically translated by this header.
|
||||
*/
|
||||
#ifdef XXH_NAMESPACE
|
||||
# define XXH_CAT(A,B) A##B
|
||||
# define XXH_NAME2(A,B) XXH_CAT(A,B)
|
||||
# define XXH32 XXH_NAME2(XXH_NAMESPACE, XXH32)
|
||||
# define XXH64 XXH_NAME2(XXH_NAMESPACE, XXH64)
|
||||
# define XXH_versionNumber XXH_NAME2(XXH_NAMESPACE, XXH_versionNumber)
|
||||
# define XXH32_createState XXH_NAME2(XXH_NAMESPACE, XXH32_createState)
|
||||
# define XXH64_createState XXH_NAME2(XXH_NAMESPACE, XXH64_createState)
|
||||
# define XXH32_freeState XXH_NAME2(XXH_NAMESPACE, XXH32_freeState)
|
||||
# define XXH64_freeState XXH_NAME2(XXH_NAMESPACE, XXH64_freeState)
|
||||
# define XXH32_reset XXH_NAME2(XXH_NAMESPACE, XXH32_reset)
|
||||
# define XXH64_reset XXH_NAME2(XXH_NAMESPACE, XXH64_reset)
|
||||
# define XXH32_update XXH_NAME2(XXH_NAMESPACE, XXH32_update)
|
||||
# define XXH64_update XXH_NAME2(XXH_NAMESPACE, XXH64_update)
|
||||
# define XXH32_digest XXH_NAME2(XXH_NAMESPACE, XXH32_digest)
|
||||
# define XXH64_digest XXH_NAME2(XXH_NAMESPACE, XXH64_digest)
|
||||
# define XXH32_copyState XXH_NAME2(XXH_NAMESPACE, XXH32_copyState)
|
||||
# define XXH64_copyState XXH_NAME2(XXH_NAMESPACE, XXH64_copyState)
|
||||
# define XXH32_canonicalFromHash XXH_NAME2(XXH_NAMESPACE, XXH32_canonicalFromHash)
|
||||
# define XXH64_canonicalFromHash XXH_NAME2(XXH_NAMESPACE, XXH64_canonicalFromHash)
|
||||
# define XXH32_hashFromCanonical XXH_NAME2(XXH_NAMESPACE, XXH32_hashFromCanonical)
|
||||
# define XXH64_hashFromCanonical XXH_NAME2(XXH_NAMESPACE, XXH64_hashFromCanonical)
|
||||
#endif
|
||||
|
||||
|
||||
/* *************************************
|
||||
* Version
|
||||
***************************************/
|
||||
#define XXH_VERSION_MAJOR 0
|
||||
#define XXH_VERSION_MINOR 6
|
||||
#define XXH_VERSION_RELEASE 2
|
||||
#define XXH_VERSION_NUMBER (XXH_VERSION_MAJOR *100*100 + XXH_VERSION_MINOR *100 + XXH_VERSION_RELEASE)
|
||||
XXH_PUBLIC_API unsigned XXH_versionNumber (void);
|
||||
|
||||
|
||||
/* ****************************
|
||||
* Simple Hash Functions
|
||||
******************************/
|
||||
typedef unsigned int XXH32_hash_t;
|
||||
typedef unsigned long long XXH64_hash_t;
|
||||
|
||||
XXH_PUBLIC_API XXH32_hash_t XXH32 (const void* input, size_t length, unsigned int seed);
|
||||
XXH_PUBLIC_API XXH64_hash_t XXH64 (const void* input, size_t length, unsigned long long seed);
|
||||
|
||||
/*!
|
||||
XXH32() :
|
||||
Calculate the 32-bits hash of sequence "length" bytes stored at memory address "input".
|
||||
The memory between input & input+length must be valid (allocated and read-accessible).
|
||||
"seed" can be used to alter the result predictably.
|
||||
Speed on Core 2 Duo @ 3 GHz (single thread, SMHasher benchmark) : 5.4 GB/s
|
||||
XXH64() :
|
||||
Calculate the 64-bits hash of sequence of length "len" stored at memory address "input".
|
||||
"seed" can be used to alter the result predictably.
|
||||
This function runs 2x faster on 64-bits systems, but slower on 32-bits systems (see benchmark).
|
||||
*/
|
||||
|
||||
|
||||
/* ****************************
|
||||
* Streaming Hash Functions
|
||||
******************************/
|
||||
typedef struct XXH32_state_s XXH32_state_t; /* incomplete type */
|
||||
typedef struct XXH64_state_s XXH64_state_t; /* incomplete type */
|
||||
|
||||
/*! State allocation, compatible with dynamic libraries */
|
||||
|
||||
XXH_PUBLIC_API XXH32_state_t* XXH32_createState(void);
|
||||
XXH_PUBLIC_API XXH_errorcode XXH32_freeState(XXH32_state_t* statePtr);
|
||||
|
||||
XXH_PUBLIC_API XXH64_state_t* XXH64_createState(void);
|
||||
XXH_PUBLIC_API XXH_errorcode XXH64_freeState(XXH64_state_t* statePtr);
|
||||
|
||||
|
||||
/* hash streaming */
|
||||
|
||||
XXH_PUBLIC_API XXH_errorcode XXH32_reset (XXH32_state_t* statePtr, unsigned int seed);
|
||||
XXH_PUBLIC_API XXH_errorcode XXH32_update (XXH32_state_t* statePtr, const void* input, size_t length);
|
||||
XXH_PUBLIC_API XXH32_hash_t XXH32_digest (const XXH32_state_t* statePtr);
|
||||
|
||||
XXH_PUBLIC_API XXH_errorcode XXH64_reset (XXH64_state_t* statePtr, unsigned long long seed);
|
||||
XXH_PUBLIC_API XXH_errorcode XXH64_update (XXH64_state_t* statePtr, const void* input, size_t length);
|
||||
XXH_PUBLIC_API XXH64_hash_t XXH64_digest (const XXH64_state_t* statePtr);
|
||||
|
||||
/*
|
||||
These functions generate the xxHash of an input provided in multiple segments.
|
||||
Note that, for small input, they are slower than single-call functions, due to state management.
|
||||
For small input, prefer `XXH32()` and `XXH64()` .
|
||||
|
||||
XXH state must first be allocated, using XXH*_createState() .
|
||||
|
||||
Start a new hash by initializing state with a seed, using XXH*_reset().
|
||||
|
||||
Then, feed the hash state by calling XXH*_update() as many times as necessary.
|
||||
Obviously, input must be allocated and read accessible.
|
||||
The function returns an error code, with 0 meaning OK, and any other value meaning there is an error.
|
||||
|
||||
Finally, a hash value can be produced anytime, by using XXH*_digest().
|
||||
This function returns the nn-bits hash as an int or long long.
|
||||
|
||||
It's still possible to continue inserting input into the hash state after a digest,
|
||||
and generate some new hashes later on, by calling again XXH*_digest().
|
||||
|
||||
When done, free XXH state space if it was allocated dynamically.
|
||||
*/
|
||||
|
||||
|
||||
/* **************************
|
||||
* Utils
|
||||
****************************/
|
||||
#if !(defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)) /* ! C99 */
|
||||
# define restrict /* disable restrict */
|
||||
#endif
|
||||
|
||||
XXH_PUBLIC_API void XXH32_copyState(XXH32_state_t* restrict dst_state, const XXH32_state_t* restrict src_state);
|
||||
XXH_PUBLIC_API void XXH64_copyState(XXH64_state_t* restrict dst_state, const XXH64_state_t* restrict src_state);
|
||||
|
||||
|
||||
/* **************************
|
||||
* Canonical representation
|
||||
****************************/
|
||||
/* Default result type for XXH functions are primitive unsigned 32 and 64 bits.
|
||||
* The canonical representation uses human-readable write convention, aka big-endian (large digits first).
|
||||
* These functions allow transformation of hash result into and from its canonical format.
|
||||
* This way, hash values can be written into a file / memory, and remain comparable on different systems and programs.
|
||||
*/
|
||||
typedef struct { unsigned char digest[4]; } XXH32_canonical_t;
|
||||
typedef struct { unsigned char digest[8]; } XXH64_canonical_t;
|
||||
|
||||
XXH_PUBLIC_API void XXH32_canonicalFromHash(XXH32_canonical_t* dst, XXH32_hash_t hash);
|
||||
XXH_PUBLIC_API void XXH64_canonicalFromHash(XXH64_canonical_t* dst, XXH64_hash_t hash);
|
||||
|
||||
XXH_PUBLIC_API XXH32_hash_t XXH32_hashFromCanonical(const XXH32_canonical_t* src);
|
||||
XXH_PUBLIC_API XXH64_hash_t XXH64_hashFromCanonical(const XXH64_canonical_t* src);
|
||||
|
||||
#endif /* XXHASH_H_5627135585666179 */
|
||||
|
||||
|
||||
|
||||
/* ================================================================================================
|
||||
This section contains definitions which are not guaranteed to remain stable.
|
||||
They may change in future versions, becoming incompatible with a different version of the library.
|
||||
They shall only be used with static linking.
|
||||
Never use these definitions in association with dynamic linking !
|
||||
=================================================================================================== */
|
||||
#if defined(XXH_STATIC_LINKING_ONLY) && !defined(XXH_STATIC_H_3543687687345)
|
||||
#define XXH_STATIC_H_3543687687345
|
||||
|
||||
/* These definitions are only meant to allow allocation of XXH state
|
||||
statically, on stack, or in a struct for example.
|
||||
Do not use members directly. */
|
||||
|
||||
struct XXH32_state_s {
|
||||
unsigned total_len_32;
|
||||
unsigned large_len;
|
||||
unsigned v1;
|
||||
unsigned v2;
|
||||
unsigned v3;
|
||||
unsigned v4;
|
||||
unsigned mem32[4]; /* buffer defined as U32 for alignment */
|
||||
unsigned memsize;
|
||||
unsigned reserved; /* never read nor write, will be removed in a future version */
|
||||
}; /* typedef'd to XXH32_state_t */
|
||||
|
||||
struct XXH64_state_s {
|
||||
unsigned long long total_len;
|
||||
unsigned long long v1;
|
||||
unsigned long long v2;
|
||||
unsigned long long v3;
|
||||
unsigned long long v4;
|
||||
unsigned long long mem64[4]; /* buffer defined as U64 for alignment */
|
||||
unsigned memsize;
|
||||
unsigned reserved[2]; /* never read nor write, will be removed in a future version */
|
||||
}; /* typedef'd to XXH64_state_t */
|
||||
|
||||
|
||||
# ifdef XXH_PRIVATE_API
|
||||
# include "xxhash.c" /* include xxhash functions as `static`, for inlining */
|
||||
# endif
|
||||
|
||||
#endif /* XXH_STATIC_LINKING_ONLY && XXH_STATIC_H_3543687687345 */
|
||||
|
||||
|
||||
#if defined (__cplusplus)
|
||||
}
|
||||
#endif
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,81 @@
|
|||
/*
|
||||
* Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
|
||||
* All rights reserved.
|
||||
*
|
||||
* This source code is licensed under both the BSD-style license (found in the
|
||||
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
|
||||
* in the COPYING file in the root directory of this source tree).
|
||||
* You may select, at your option, one of the above-listed licenses.
|
||||
*/
|
||||
|
||||
|
||||
|
||||
/*-*************************************
|
||||
* Dependencies
|
||||
***************************************/
|
||||
#include <stdlib.h> /* malloc, calloc, free */
|
||||
#include <string.h> /* memset */
|
||||
#include "error_private.h"
|
||||
#include "zstd_internal.h"
|
||||
|
||||
|
||||
/*-****************************************
|
||||
* Version
|
||||
******************************************/
|
||||
unsigned ZSTD_versionNumber(void) { return ZSTD_VERSION_NUMBER; }
|
||||
|
||||
const char* ZSTD_versionString(void) { return ZSTD_VERSION_STRING; }
|
||||
|
||||
|
||||
/*-****************************************
|
||||
* ZSTD Error Management
|
||||
******************************************/
|
||||
/*! ZSTD_isError() :
|
||||
* tells if a return value is an error code */
|
||||
unsigned ZSTD_isError(size_t code) { return ERR_isError(code); }
|
||||
|
||||
/*! ZSTD_getErrorName() :
|
||||
* provides error code string from function result (useful for debugging) */
|
||||
const char* ZSTD_getErrorName(size_t code) { return ERR_getErrorName(code); }
|
||||
|
||||
/*! ZSTD_getError() :
|
||||
* convert a `size_t` function result into a proper ZSTD_errorCode enum */
|
||||
ZSTD_ErrorCode ZSTD_getErrorCode(size_t code) { return ERR_getErrorCode(code); }
|
||||
|
||||
/*! ZSTD_getErrorString() :
|
||||
* provides error code string from enum */
|
||||
const char* ZSTD_getErrorString(ZSTD_ErrorCode code) { return ERR_getErrorString(code); }
|
||||
|
||||
|
||||
|
||||
/*=**************************************************************
|
||||
* Custom allocator
|
||||
****************************************************************/
|
||||
void* ZSTD_malloc(size_t size, ZSTD_customMem customMem)
|
||||
{
|
||||
if (customMem.customAlloc)
|
||||
return customMem.customAlloc(customMem.opaque, size);
|
||||
return malloc(size);
|
||||
}
|
||||
|
||||
void* ZSTD_calloc(size_t size, ZSTD_customMem customMem)
|
||||
{
|
||||
if (customMem.customAlloc) {
|
||||
/* calloc implemented as malloc+memset;
|
||||
* not as efficient as calloc, but next best guess for custom malloc */
|
||||
void* const ptr = customMem.customAlloc(customMem.opaque, size);
|
||||
memset(ptr, 0, size);
|
||||
return ptr;
|
||||
}
|
||||
return calloc(1, size);
|
||||
}
|
||||
|
||||
void ZSTD_free(void* ptr, ZSTD_customMem customMem)
|
||||
{
|
||||
if (ptr!=NULL) {
|
||||
if (customMem.customFree)
|
||||
customMem.customFree(customMem.opaque, ptr);
|
||||
else
|
||||
free(ptr);
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,92 @@
|
|||
/*
|
||||
* Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
|
||||
* All rights reserved.
|
||||
*
|
||||
* This source code is licensed under both the BSD-style license (found in the
|
||||
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
|
||||
* in the COPYING file in the root directory of this source tree).
|
||||
* You may select, at your option, one of the above-listed licenses.
|
||||
*/
|
||||
|
||||
#ifndef ZSTD_ERRORS_H_398273423
|
||||
#define ZSTD_ERRORS_H_398273423
|
||||
|
||||
#if defined (__cplusplus)
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/*===== dependency =====*/
|
||||
#include <stddef.h> /* size_t */
|
||||
|
||||
|
||||
/* ===== ZSTDERRORLIB_API : control library symbols visibility ===== */
|
||||
#ifndef ZSTDERRORLIB_VISIBILITY
|
||||
# if defined(__GNUC__) && (__GNUC__ >= 4)
|
||||
# define ZSTDERRORLIB_VISIBILITY __attribute__ ((visibility ("default")))
|
||||
# else
|
||||
# define ZSTDERRORLIB_VISIBILITY
|
||||
# endif
|
||||
#endif
|
||||
#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1)
|
||||
# define ZSTDERRORLIB_API __declspec(dllexport) ZSTDERRORLIB_VISIBILITY
|
||||
#elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1)
|
||||
# define ZSTDERRORLIB_API __declspec(dllimport) ZSTDERRORLIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
|
||||
#else
|
||||
# define ZSTDERRORLIB_API ZSTDERRORLIB_VISIBILITY
|
||||
#endif
|
||||
|
||||
/*-*********************************************
|
||||
* Error codes list
|
||||
*-*********************************************
|
||||
* Error codes _values_ are pinned down since v1.3.1 only.
|
||||
* Therefore, don't rely on values if you may link to any version < v1.3.1.
|
||||
*
|
||||
* Only values < 100 are considered stable.
|
||||
*
|
||||
* note 1 : this API shall be used with static linking only.
|
||||
* dynamic linking is not yet officially supported.
|
||||
* note 2 : Prefer relying on the enum than on its value whenever possible
|
||||
* This is the only supported way to use the error list < v1.3.1
|
||||
* note 3 : ZSTD_isError() is always correct, whatever the library version.
|
||||
**********************************************/
|
||||
typedef enum {
|
||||
ZSTD_error_no_error = 0,
|
||||
ZSTD_error_GENERIC = 1,
|
||||
ZSTD_error_prefix_unknown = 10,
|
||||
ZSTD_error_version_unsupported = 12,
|
||||
ZSTD_error_frameParameter_unsupported = 14,
|
||||
ZSTD_error_frameParameter_windowTooLarge = 16,
|
||||
ZSTD_error_corruption_detected = 20,
|
||||
ZSTD_error_checksum_wrong = 22,
|
||||
ZSTD_error_dictionary_corrupted = 30,
|
||||
ZSTD_error_dictionary_wrong = 32,
|
||||
ZSTD_error_dictionaryCreation_failed = 34,
|
||||
ZSTD_error_parameter_unsupported = 40,
|
||||
ZSTD_error_parameter_outOfBound = 42,
|
||||
ZSTD_error_tableLog_tooLarge = 44,
|
||||
ZSTD_error_maxSymbolValue_tooLarge = 46,
|
||||
ZSTD_error_maxSymbolValue_tooSmall = 48,
|
||||
ZSTD_error_stage_wrong = 60,
|
||||
ZSTD_error_init_missing = 62,
|
||||
ZSTD_error_memory_allocation = 64,
|
||||
ZSTD_error_workSpace_tooSmall= 66,
|
||||
ZSTD_error_dstSize_tooSmall = 70,
|
||||
ZSTD_error_srcSize_wrong = 72,
|
||||
/* following error codes are __NOT STABLE__, they can be removed or changed in future versions */
|
||||
ZSTD_error_frameIndex_tooLarge = 100,
|
||||
ZSTD_error_seekableIO = 102,
|
||||
ZSTD_error_maxCode = 120 /* never EVER use this value directly, it can change in future versions! Use ZSTD_isError() instead */
|
||||
} ZSTD_ErrorCode;
|
||||
|
||||
/*! ZSTD_getErrorCode() :
|
||||
convert a `size_t` function result into a `ZSTD_ErrorCode` enum type,
|
||||
which can be used to compare with enum list published above */
|
||||
ZSTDERRORLIB_API ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult);
|
||||
ZSTDERRORLIB_API const char* ZSTD_getErrorString(ZSTD_ErrorCode code); /**< Same as ZSTD_getErrorName, but using a `ZSTD_ErrorCode` enum argument */
|
||||
|
||||
|
||||
#if defined (__cplusplus)
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif /* ZSTD_ERRORS_H_398273423 */
|
||||
|
|
@ -0,0 +1,257 @@
|
|||
/*
|
||||
* Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
|
||||
* All rights reserved.
|
||||
*
|
||||
* This source code is licensed under both the BSD-style license (found in the
|
||||
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
|
||||
* in the COPYING file in the root directory of this source tree).
|
||||
* You may select, at your option, one of the above-listed licenses.
|
||||
*/
|
||||
|
||||
#ifndef ZSTD_CCOMMON_H_MODULE
|
||||
#define ZSTD_CCOMMON_H_MODULE
|
||||
|
||||
/* this module contains definitions which must be identical
|
||||
* across compression, decompression and dictBuilder.
|
||||
* It also contains a few functions useful to at least 2 of them
|
||||
* and which benefit from being inlined */
|
||||
|
||||
/*-*************************************
|
||||
* Dependencies
|
||||
***************************************/
|
||||
#include "compiler.h"
|
||||
#include "mem.h"
|
||||
#include "debug.h" /* assert, DEBUGLOG, RAWLOG, g_debuglevel */
|
||||
#include "error_private.h"
|
||||
#define ZSTD_STATIC_LINKING_ONLY
|
||||
#include "zstd.h"
|
||||
#define FSE_STATIC_LINKING_ONLY
|
||||
#include "fse.h"
|
||||
#define HUF_STATIC_LINKING_ONLY
|
||||
#include "huf.h"
|
||||
#ifndef XXH_STATIC_LINKING_ONLY
|
||||
# define XXH_STATIC_LINKING_ONLY /* XXH64_state_t */
|
||||
#endif
|
||||
#include "xxhash.h" /* XXH_reset, update, digest */
|
||||
|
||||
|
||||
#if defined (__cplusplus)
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/* ---- static assert (debug) --- */
|
||||
#define ZSTD_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c)
|
||||
|
||||
|
||||
/*-*************************************
|
||||
* shared macros
|
||||
***************************************/
|
||||
#undef MIN
|
||||
#undef MAX
|
||||
#define MIN(a,b) ((a)<(b) ? (a) : (b))
|
||||
#define MAX(a,b) ((a)>(b) ? (a) : (b))
|
||||
#define CHECK_F(f) { size_t const errcod = f; if (ERR_isError(errcod)) return errcod; } /* check and Forward error code */
|
||||
#define CHECK_E(f, e) { size_t const errcod = f; if (ERR_isError(errcod)) return ERROR(e); } /* check and send Error code */
|
||||
|
||||
|
||||
/*-*************************************
|
||||
* Common constants
|
||||
***************************************/
|
||||
#define ZSTD_OPT_NUM (1<<12)
|
||||
|
||||
#define ZSTD_REP_NUM 3 /* number of repcodes */
|
||||
#define ZSTD_REP_MOVE (ZSTD_REP_NUM-1)
|
||||
static const U32 repStartValue[ZSTD_REP_NUM] = { 1, 4, 8 };
|
||||
|
||||
#define KB *(1 <<10)
|
||||
#define MB *(1 <<20)
|
||||
#define GB *(1U<<30)
|
||||
|
||||
#define BIT7 128
|
||||
#define BIT6 64
|
||||
#define BIT5 32
|
||||
#define BIT4 16
|
||||
#define BIT1 2
|
||||
#define BIT0 1
|
||||
|
||||
#define ZSTD_WINDOWLOG_ABSOLUTEMIN 10
|
||||
#define ZSTD_WINDOWLOG_DEFAULTMAX 27 /* Default maximum allowed window log */
|
||||
static const size_t ZSTD_fcs_fieldSize[4] = { 0, 2, 4, 8 };
|
||||
static const size_t ZSTD_did_fieldSize[4] = { 0, 1, 2, 4 };
|
||||
|
||||
#define ZSTD_FRAMEIDSIZE 4 /* magic number size */
|
||||
|
||||
#define ZSTD_BLOCKHEADERSIZE 3 /* C standard doesn't allow `static const` variable to be init using another `static const` variable */
|
||||
static const size_t ZSTD_blockHeaderSize = ZSTD_BLOCKHEADERSIZE;
|
||||
typedef enum { bt_raw, bt_rle, bt_compressed, bt_reserved } blockType_e;
|
||||
|
||||
#define MIN_SEQUENCES_SIZE 1 /* nbSeq==0 */
|
||||
#define MIN_CBLOCK_SIZE (1 /*litCSize*/ + 1 /* RLE or RAW */ + MIN_SEQUENCES_SIZE /* nbSeq==0 */) /* for a non-null block */
|
||||
|
||||
#define HufLog 12
|
||||
typedef enum { set_basic, set_rle, set_compressed, set_repeat } symbolEncodingType_e;
|
||||
|
||||
#define LONGNBSEQ 0x7F00
|
||||
|
||||
#define MINMATCH 3
|
||||
|
||||
#define Litbits 8
|
||||
#define MaxLit ((1<<Litbits) - 1)
|
||||
#define MaxML 52
|
||||
#define MaxLL 35
|
||||
#define DefaultMaxOff 28
|
||||
#define MaxOff 31
|
||||
#define MaxSeq MAX(MaxLL, MaxML) /* Assumption : MaxOff < MaxLL,MaxML */
|
||||
#define MLFSELog 9
|
||||
#define LLFSELog 9
|
||||
#define OffFSELog 8
|
||||
#define MaxFSELog MAX(MAX(MLFSELog, LLFSELog), OffFSELog)
|
||||
|
||||
static const U32 LL_bits[MaxLL+1] = { 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0,
|
||||
1, 1, 1, 1, 2, 2, 3, 3,
|
||||
4, 6, 7, 8, 9,10,11,12,
|
||||
13,14,15,16 };
|
||||
static const S16 LL_defaultNorm[MaxLL+1] = { 4, 3, 2, 2, 2, 2, 2, 2,
|
||||
2, 2, 2, 2, 2, 1, 1, 1,
|
||||
2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, 3, 2, 1, 1, 1, 1, 1,
|
||||
-1,-1,-1,-1 };
|
||||
#define LL_DEFAULTNORMLOG 6 /* for static allocation */
|
||||
static const U32 LL_defaultNormLog = LL_DEFAULTNORMLOG;
|
||||
|
||||
static const U32 ML_bits[MaxML+1] = { 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0,
|
||||
1, 1, 1, 1, 2, 2, 3, 3,
|
||||
4, 4, 5, 7, 8, 9,10,11,
|
||||
12,13,14,15,16 };
|
||||
static const S16 ML_defaultNorm[MaxML+1] = { 1, 4, 3, 2, 2, 2, 2, 2,
|
||||
2, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, 1, 1, 1, 1, 1,-1,-1,
|
||||
-1,-1,-1,-1,-1 };
|
||||
#define ML_DEFAULTNORMLOG 6 /* for static allocation */
|
||||
static const U32 ML_defaultNormLog = ML_DEFAULTNORMLOG;
|
||||
|
||||
static const S16 OF_defaultNorm[DefaultMaxOff+1] = { 1, 1, 1, 1, 1, 1, 2, 2,
|
||||
2, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, 1, 1, 1, 1, 1, 1, 1,
|
||||
-1,-1,-1,-1,-1 };
|
||||
#define OF_DEFAULTNORMLOG 5 /* for static allocation */
|
||||
static const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG;
|
||||
|
||||
|
||||
/*-*******************************************
|
||||
* Shared functions to include for inlining
|
||||
*********************************************/
|
||||
static void ZSTD_copy8(void* dst, const void* src) { memcpy(dst, src, 8); }
|
||||
#define COPY8(d,s) { ZSTD_copy8(d,s); d+=8; s+=8; }
|
||||
|
||||
/*! ZSTD_wildcopy() :
|
||||
* custom version of memcpy(), can overwrite up to WILDCOPY_OVERLENGTH bytes (if length==0) */
|
||||
#define WILDCOPY_OVERLENGTH 8
|
||||
MEM_STATIC void ZSTD_wildcopy(void* dst, const void* src, ptrdiff_t length)
|
||||
{
|
||||
const BYTE* ip = (const BYTE*)src;
|
||||
BYTE* op = (BYTE*)dst;
|
||||
BYTE* const oend = op + length;
|
||||
do
|
||||
COPY8(op, ip)
|
||||
while (op < oend);
|
||||
}
|
||||
|
||||
MEM_STATIC void ZSTD_wildcopy_e(void* dst, const void* src, void* dstEnd) /* should be faster for decoding, but strangely, not verified on all platform */
|
||||
{
|
||||
const BYTE* ip = (const BYTE*)src;
|
||||
BYTE* op = (BYTE*)dst;
|
||||
BYTE* const oend = (BYTE*)dstEnd;
|
||||
do
|
||||
COPY8(op, ip)
|
||||
while (op < oend);
|
||||
}
|
||||
|
||||
|
||||
/*-*******************************************
|
||||
* Private declarations
|
||||
*********************************************/
|
||||
typedef struct seqDef_s {
|
||||
U32 offset;
|
||||
U16 litLength;
|
||||
U16 matchLength;
|
||||
} seqDef;
|
||||
|
||||
typedef struct {
|
||||
seqDef* sequencesStart;
|
||||
seqDef* sequences;
|
||||
BYTE* litStart;
|
||||
BYTE* lit;
|
||||
BYTE* llCode;
|
||||
BYTE* mlCode;
|
||||
BYTE* ofCode;
|
||||
size_t maxNbSeq;
|
||||
size_t maxNbLit;
|
||||
U32 longLengthID; /* 0 == no longLength; 1 == Lit.longLength; 2 == Match.longLength; */
|
||||
U32 longLengthPos;
|
||||
} seqStore_t;
|
||||
|
||||
const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx); /* compress & dictBuilder */
|
||||
void ZSTD_seqToCodes(const seqStore_t* seqStorePtr); /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */
|
||||
|
||||
/* custom memory allocation functions */
|
||||
void* ZSTD_malloc(size_t size, ZSTD_customMem customMem);
|
||||
void* ZSTD_calloc(size_t size, ZSTD_customMem customMem);
|
||||
void ZSTD_free(void* ptr, ZSTD_customMem customMem);
|
||||
|
||||
|
||||
MEM_STATIC U32 ZSTD_highbit32(U32 val) /* compress, dictBuilder, decodeCorpus */
|
||||
{
|
||||
assert(val != 0);
|
||||
{
|
||||
# if defined(_MSC_VER) /* Visual */
|
||||
unsigned long r=0;
|
||||
_BitScanReverse(&r, val);
|
||||
return (unsigned)r;
|
||||
# elif defined(__GNUC__) && (__GNUC__ >= 3) /* GCC Intrinsic */
|
||||
return 31 - __builtin_clz(val);
|
||||
# else /* Software version */
|
||||
static const U32 DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, 11, 14, 16, 18, 22, 25, 3, 30, 8, 12, 20, 28, 15, 17, 24, 7, 19, 27, 23, 6, 26, 5, 4, 31 };
|
||||
U32 v = val;
|
||||
v |= v >> 1;
|
||||
v |= v >> 2;
|
||||
v |= v >> 4;
|
||||
v |= v >> 8;
|
||||
v |= v >> 16;
|
||||
return DeBruijnClz[(v * 0x07C4ACDDU) >> 27];
|
||||
# endif
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/* ZSTD_invalidateRepCodes() :
|
||||
* ensures next compression will not use repcodes from previous block.
|
||||
* Note : only works with regular variant;
|
||||
* do not use with extDict variant ! */
|
||||
void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx); /* zstdmt, adaptive_compression (shouldn't get this definition from here) */
|
||||
|
||||
|
||||
typedef struct {
|
||||
blockType_e blockType;
|
||||
U32 lastBlock;
|
||||
U32 origSize;
|
||||
} blockProperties_t;
|
||||
|
||||
/*! ZSTD_getcBlockSize() :
|
||||
* Provides the size of compressed block from block header `src` */
|
||||
/* Used by: decompress, fullbench (does not get its definition from here) */
|
||||
size_t ZSTD_getcBlockSize(const void* src, size_t srcSize,
|
||||
blockProperties_t* bpPtr);
|
||||
|
||||
#if defined (__cplusplus)
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif /* ZSTD_CCOMMON_H_MODULE */
|
||||
Loading…
Reference in New Issue