mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-26 01:22:04 +00:00
Updated LZ4 http://lz4.googlecode.com/svn/trunk/ rev. 62 [#CONV-4593].
This commit is contained in:
Alexey Milovidov
parent
5a36e4bce3
commit
65b1caa9d7
@ -27,6 +27,7 @@
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
*/
|
||||
#pragma once
|
||||
|
||||
#if defined (__cplusplus)
|
||||
extern "C" {
|
||||
@ -37,22 +38,24 @@ extern "C" {
|
||||
// Simple Functions
|
||||
//****************************
|
||||
|
||||
int LZ4_compress (char* source, char* dest, int isize);
|
||||
int LZ4_uncompress (char* source, char* dest, int osize);
|
||||
int LZ4_compress (const char* source, char* dest, int isize);
|
||||
int LZ4_uncompress (const char* source, char* dest, int osize);
|
||||
|
||||
/*
|
||||
LZ4_compress :
|
||||
return : the number of bytes in compressed buffer dest
|
||||
LZ4_compress() :
|
||||
isize : is the input size. Max supported value is ~1.9GB
|
||||
return : the number of bytes written in buffer dest
|
||||
or 0 if the compression fails (if LZ4_COMPRESSMIN is set)
|
||||
note : destination buffer must be already allocated.
|
||||
To avoid any problem, size it to handle worst cases situations (input data not compressible)
|
||||
Worst case size is : "inputsize + 0.4%", with "0.4%" being at least 8 bytes.
|
||||
destination buffer must be sized to handle worst cases situations (input data not compressible)
|
||||
worst case size evaluation is provided by function LZ4_compressBound()
|
||||
|
||||
LZ4_uncompress :
|
||||
LZ4_uncompress() :
|
||||
osize : is the output size, therefore the original size
|
||||
return : the number of bytes read in the source buffer
|
||||
If the source stream is malformed, the function will stop decoding and return a negative result, indicating the byte position of the faulty instruction
|
||||
This version never writes beyond dest + osize, and is therefore protected against malicious data packets
|
||||
note 2 : destination buffer must be already allocated
|
||||
This function never writes beyond dest + osize, and is therefore protected against malicious data packets
|
||||
note : destination buffer must be already allocated
|
||||
*/
|
||||
|
||||
|
||||
@ -60,33 +63,50 @@ LZ4_uncompress :
|
||||
// Advanced Functions
|
||||
//****************************
|
||||
|
||||
int LZ4_uncompress_unknownOutputSize (char* source, char* dest, int isize, int maxOutputSize);
|
||||
int LZ4_compressBound(int isize);
|
||||
|
||||
/*
|
||||
LZ4_uncompress_unknownOutputSize :
|
||||
LZ4_compressBound() :
|
||||
Provides the maximum size that LZ4 may output in a "worst case" scenario (input data not compressible)
|
||||
primarily useful for memory allocation of output buffer.
|
||||
|
||||
isize : is the input size. Max supported value is ~1.9GB
|
||||
return : maximum output size in a "worst case" scenario
|
||||
note : this function is limited by "int" range (2^31-1)
|
||||
*/
|
||||
|
||||
|
||||
int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize);
|
||||
|
||||
/*
|
||||
LZ4_uncompress_unknownOutputSize() :
|
||||
isize : is the input size, therefore the compressed size
|
||||
maxOutputSize : is the size of the destination buffer (which must be already allocated)
|
||||
return : the number of bytes decoded in the destination buffer (necessarily <= maxOutputSize)
|
||||
If the source stream is malformed, the function will stop decoding and return a negative result, indicating the byte position of the faulty instruction
|
||||
This version never writes beyond dest + maxOutputSize, and is therefore protected against malicious data packets
|
||||
note : This version is slower than LZ4_uncompress, and is therefore not recommended for general use
|
||||
This function never writes beyond dest + maxOutputSize, and is therefore protected against malicious data packets
|
||||
note : This version is slightly slower than LZ4_uncompress()
|
||||
*/
|
||||
|
||||
|
||||
int LZ4_compressCtx(void** ctx, char* source, char* dest, int isize);
|
||||
int LZ4_compressCtx(void** ctx, const char* source, char* dest, int isize);
|
||||
int LZ4_compress64kCtx(void** ctx, const char* source, char* dest, int isize);
|
||||
|
||||
/*
|
||||
LZ4_compressCtx :
|
||||
LZ4_compressCtx() :
|
||||
This function explicitly handles the CTX memory structure.
|
||||
It avoids allocating/deallocating memory between each call, improving performance when malloc is time-consuming.
|
||||
Note : when memory is allocated into the stack (default mode), there is no "malloc" penalty.
|
||||
Therefore, this function is mostly useful when memory is allocated into the heap (it requires increasing HASH_LOG value beyond STACK_LIMIT)
|
||||
It avoids allocating/deallocating memory between each call, improving performance when malloc is heavily invoked.
|
||||
This function is only useful when memory is allocated into the heap (HASH_LOG value beyond STACK_LIMIT)
|
||||
Performance difference will be noticeable only when repetitively calling the compression function over many small segments.
|
||||
Note : by default, memory is allocated into the stack, therefore "malloc" is not invoked.
|
||||
LZ4_compress64kCtx() :
|
||||
Same as LZ4_compressCtx(), but specific to small inputs (<64KB).
|
||||
isize *Must* be <64KB, otherwise the output will be corrupted.
|
||||
|
||||
On first call : provide a *ctx=NULL; It will be automatically allocated.
|
||||
On next calls : reuse the same ctx pointer.
|
||||
Use different pointers for different threads when doing multi-threading.
|
||||
|
||||
note : performance difference is small, mostly noticeable when repetitively calling the compression algorithm on many small segments.
|
||||
*/
|
||||
|
||||
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
/*
|
||||
LZ4 - Fast LZ compression algorithm
|
||||
Copyright (C) 2011, Yann Collet.
|
||||
BSD License
|
||||
Copyright (C) 2011-2012, 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
|
||||
@ -27,6 +27,100 @@
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
*/
|
||||
|
||||
//**************************************
|
||||
// Tuning parameters
|
||||
//**************************************
|
||||
// COMPRESSIONLEVEL :
|
||||
// Increasing this value improves compression ratio
|
||||
// Lowering this value reduces memory usage
|
||||
// Reduced memory usage typically improves speed, due to cache effect (ex : L1 32KB for Intel, L1 64KB for AMD)
|
||||
// Memory usage formula : N->2^(N+2) Bytes (examples : 12 -> 16KB ; 17 -> 512KB)
|
||||
#define COMPRESSIONLEVEL 12
|
||||
|
||||
// NOTCOMPRESSIBLE_CONFIRMATION :
|
||||
// Decreasing this value will make the algorithm skip faster data segments considered "incompressible"
|
||||
// This may decrease compression ratio dramatically, but will be faster on incompressible data
|
||||
// Increasing this value will make the algorithm search more before declaring a segment "incompressible"
|
||||
// This could improve compression a bit, but will be slower on incompressible data
|
||||
// The default value (6) is recommended
|
||||
#define NOTCOMPRESSIBLE_CONFIRMATION 6
|
||||
|
||||
// LZ4_COMPRESSMIN :
|
||||
// Compression function will *fail* if it is not successful at compressing input by at least LZ4_COMPRESSMIN bytes
|
||||
// Since the compression function stops working prematurely, it results in a speed gain
|
||||
// The output however is unusable. Compression function result will be zero.
|
||||
// Default : 0 = disabled
|
||||
#define LZ4_COMPRESSMIN 0
|
||||
|
||||
// BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE :
|
||||
// This will provide a boost to performance for big endian cpu, but the resulting compressed stream will be incompatible with little-endian CPU.
|
||||
// You can set this option to 1 in situations where data will stay within closed environment
|
||||
// This option is useless on Little_Endian CPU (such as x86)
|
||||
//#define BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE 1
|
||||
|
||||
|
||||
|
||||
//**************************************
|
||||
// CPU Feature Detection
|
||||
//**************************************
|
||||
// 32 or 64 bits ?
|
||||
#if (defined(__x86_64__) || defined(__x86_64) || defined(__amd64__) || defined(__amd64) || defined(__ppc64__) || defined(_WIN64) || defined(__LP64__) || defined(_LP64) ) // Detects 64 bits mode
|
||||
#define LZ4_ARCH64 1
|
||||
#else
|
||||
#define LZ4_ARCH64 0
|
||||
#endif
|
||||
|
||||
// Little Endian or Big Endian ?
|
||||
#if (defined(__BIG_ENDIAN__) || defined(__BIG_ENDIAN) || defined(_BIG_ENDIAN) || defined(_ARCH_PPC) || defined(__PPC__) || defined(__PPC) || defined(PPC) || defined(__powerpc__) || defined(__powerpc) || defined(powerpc) || ((defined(__BYTE_ORDER__)&&(__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__))) )
|
||||
#define LZ4_BIG_ENDIAN 1
|
||||
#else
|
||||
// Little Endian assumed. PDP Endian and other very rare endian format are unsupported.
|
||||
#endif
|
||||
|
||||
// Unaligned memory access is automatically enabled for "common" CPU, such as x86.
|
||||
// For others CPU, the compiler will be more cautious, and insert extra code to ensure aligned access is respected
|
||||
// If you know your target CPU supports unaligned memory access, you may want to force this option manually to improve performance
|
||||
#if defined(__ARM_FEATURE_UNALIGNED)
|
||||
#define LZ4_FORCE_UNALIGNED_ACCESS 1
|
||||
#endif
|
||||
|
||||
// Uncomment this parameter if your target system or compiler does not support hardware bit count
|
||||
//#define LZ4_FORCE_SW_BITCOUNT
|
||||
|
||||
|
||||
|
||||
//**************************************
|
||||
// Compiler Options
|
||||
//**************************************
|
||||
#if __STDC_VERSION__ >= 199901L // C99
|
||||
/* "restrict" is a known keyword */
|
||||
#else
|
||||
#define restrict // Disable restrict
|
||||
#endif
|
||||
|
||||
#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
|
||||
|
||||
#ifdef _MSC_VER // Visual Studio
|
||||
#define inline __forceinline // Visual is not C99, but supports some kind of inline
|
||||
#include <intrin.h> // _BitScanForward
|
||||
#endif
|
||||
|
||||
#ifdef _MSC_VER
|
||||
#define lz4_bswap16(x) _byteswap_ushort(x)
|
||||
#else
|
||||
#define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8)))
|
||||
#endif
|
||||
|
||||
#if (GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__)
|
||||
# define expect(expr,value) (__builtin_expect ((expr),(value)) )
|
||||
#else
|
||||
# define expect(expr,value) (expr)
|
||||
#endif
|
||||
|
||||
#define likely(expr) expect((expr) != 0, 1)
|
||||
#define unlikely(expr) expect((expr) != 0, 0)
|
||||
|
||||
|
||||
//**************************************
|
||||
// Includes
|
||||
//**************************************
|
||||
@ -35,41 +129,53 @@
|
||||
#include <lz4/lz4.h>
|
||||
|
||||
|
||||
//**************************************
|
||||
// Performance parameter
|
||||
//**************************************
|
||||
// Increasing this value improves compression ratio
|
||||
// Lowering this value reduces memory usage
|
||||
// Lowering may also improve speed, typically on reaching cache size limits (L1 32KB for Intel, 64KB for AMD)
|
||||
// Memory usage formula for 32 bits systems : N->2^(N+2) Bytes (examples : 17 -> 512KB ; 12 -> 16KB)
|
||||
#define HASH_LOG 12
|
||||
|
||||
|
||||
//**************************************
|
||||
// Basic Types
|
||||
//**************************************
|
||||
#if defined(_MSC_VER)
|
||||
#if defined(_MSC_VER) // Visual Studio does not support 'stdint' natively
|
||||
#define BYTE unsigned __int8
|
||||
#define U16 unsigned __int16
|
||||
#define U32 unsigned __int32
|
||||
#define S32 __int32
|
||||
#define U64 unsigned __int64
|
||||
#else
|
||||
#include <stdint.h>
|
||||
#define BYTE uint8_t
|
||||
#define U16 uint16_t
|
||||
#define U32 uint32_t
|
||||
#define S32 int32_t
|
||||
#define U64 uint64_t
|
||||
#endif
|
||||
|
||||
#ifndef LZ4_FORCE_UNALIGNED_ACCESS
|
||||
#pragma pack(push, 1)
|
||||
#endif
|
||||
|
||||
typedef struct _U16_S { U16 v; } U16_S;
|
||||
typedef struct _U32_S { U32 v; } U32_S;
|
||||
typedef struct _U64_S { U64 v; } U64_S;
|
||||
|
||||
#ifndef LZ4_FORCE_UNALIGNED_ACCESS
|
||||
#pragma pack(pop)
|
||||
#endif
|
||||
|
||||
#define A64(x) (((U64_S *)(x))->v)
|
||||
#define A32(x) (((U32_S *)(x))->v)
|
||||
#define A16(x) (((U16_S *)(x))->v)
|
||||
|
||||
|
||||
//**************************************
|
||||
// Constants
|
||||
//**************************************
|
||||
#define MINMATCH 4
|
||||
#define SKIPSTRENGTH 6
|
||||
|
||||
#define HASH_LOG COMPRESSIONLEVEL
|
||||
#define HASHTABLESIZE (1 << HASH_LOG)
|
||||
#define HASH_MASK (HASHTABLESIZE - 1)
|
||||
|
||||
#define SKIPSTRENGTH (NOTCOMPRESSIBLE_CONFIRMATION>2?NOTCOMPRESSIBLE_CONFIRMATION:2)
|
||||
#define STACKLIMIT 13
|
||||
#define HEAPMODE (HASH_LOG>STACKLIMIT) // Defines if memory is allocated into the stack (local variable), or into the heap (malloc()).
|
||||
#define COPYTOKEN 4
|
||||
#define COPYLENGTH 8
|
||||
#define LASTLITERALS 5
|
||||
#define MFLIMIT (COPYLENGTH+MINMATCH)
|
||||
@ -78,71 +184,160 @@
|
||||
#define MAXD_LOG 16
|
||||
#define MAX_DISTANCE ((1 << MAXD_LOG) - 1)
|
||||
|
||||
#define HASHTABLESIZE (1 << HASH_LOG)
|
||||
#define HASH_MASK (HASHTABLESIZE - 1)
|
||||
|
||||
#define ML_BITS 4
|
||||
#define ML_MASK ((1U<<ML_BITS)-1)
|
||||
#define RUN_BITS (8-ML_BITS)
|
||||
#define RUN_MASK ((1U<<RUN_BITS)-1)
|
||||
|
||||
|
||||
//**************************************
|
||||
// Architecture-specific macros
|
||||
//**************************************
|
||||
#if LZ4_ARCH64 // 64-bit
|
||||
#define STEPSIZE 8
|
||||
#define UARCH U64
|
||||
#define AARCH A64
|
||||
#define LZ4_COPYSTEP(s,d) A64(d) = A64(s); d+=8; s+=8;
|
||||
#define LZ4_COPYPACKET(s,d) LZ4_COPYSTEP(s,d)
|
||||
#define LZ4_SECURECOPY(s,d,e) if (d<e) LZ4_WILDCOPY(s,d,e)
|
||||
#define HTYPE U32
|
||||
#define INITBASE(base) const BYTE* const base = ip
|
||||
#else // 32-bit
|
||||
#define STEPSIZE 4
|
||||
#define UARCH U32
|
||||
#define AARCH A32
|
||||
#define LZ4_COPYSTEP(s,d) A32(d) = A32(s); d+=4; s+=4;
|
||||
#define LZ4_COPYPACKET(s,d) LZ4_COPYSTEP(s,d); LZ4_COPYSTEP(s,d);
|
||||
#define LZ4_SECURECOPY LZ4_WILDCOPY
|
||||
#define HTYPE const BYTE*
|
||||
#define INITBASE(base) const int base = 0
|
||||
#endif
|
||||
|
||||
#if (defined(LZ4_BIG_ENDIAN) && !defined(BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE))
|
||||
#define LZ4_READ_LITTLEENDIAN_16(d,s,p) { U16 v = A16(p); v = lz4_bswap16(v); d = (s) - v; }
|
||||
#define LZ4_WRITE_LITTLEENDIAN_16(p,i) { U16 v = (U16)(i); v = lz4_bswap16(v); A16(p) = v; p+=2; }
|
||||
#else // Little Endian
|
||||
#define LZ4_READ_LITTLEENDIAN_16(d,s,p) { d = (s) - A16(p); }
|
||||
#define LZ4_WRITE_LITTLEENDIAN_16(p,v) { A16(p) = v; p+=2; }
|
||||
#endif
|
||||
|
||||
|
||||
//**************************************
|
||||
// Local structures
|
||||
//**************************************
|
||||
struct refTables
|
||||
{
|
||||
const BYTE* hashTable[HASHTABLESIZE];
|
||||
HTYPE hashTable[HASHTABLESIZE];
|
||||
};
|
||||
|
||||
#ifdef __GNUC__
|
||||
# define _PACKED __attribute__ ((packed))
|
||||
#else
|
||||
# define _PACKED
|
||||
#endif
|
||||
|
||||
typedef struct _U32_S
|
||||
{
|
||||
U32 v;
|
||||
} _PACKED U32_S;
|
||||
|
||||
typedef struct _U16_S
|
||||
{
|
||||
U16 v;
|
||||
} _PACKED U16_S;
|
||||
|
||||
#define A32(x) (((U32_S *)(x))->v)
|
||||
#define A16(x) (((U16_S *)(x))->v)
|
||||
|
||||
|
||||
//**************************************
|
||||
// Macros
|
||||
//**************************************
|
||||
#define LZ4_HASH_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH*8)-HASH_LOG))
|
||||
#define LZ4_HASH_VALUE(p) LZ4_HASH_FUNCTION(A32(p))
|
||||
#define LZ4_COPYPACKET(s,d) A32(d) = A32(s); d+=4; s+=4; A32(d) = A32(s); d+=4; s+=4;
|
||||
#define LZ4_WILDCOPY(s,d,e) do { LZ4_COPYPACKET(s,d) } while (d<e);
|
||||
#define LZ4_BLINDCOPY(s,d,l) { BYTE* e=d+l; LZ4_WILDCOPY(s,d,e); d=e; }
|
||||
|
||||
#define LZ4_BLINDCOPY(s,d,l) { BYTE* e=(d)+l; LZ4_WILDCOPY(s,d,e); d=e; }
|
||||
|
||||
|
||||
//****************************
|
||||
// Compression CODE
|
||||
// Private functions
|
||||
//****************************
|
||||
#if LZ4_ARCH64
|
||||
|
||||
inline static int LZ4_NbCommonBytes (register U64 val)
|
||||
{
|
||||
#if defined(LZ4_BIG_ENDIAN)
|
||||
#if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
unsigned long r = 0;
|
||||
_BitScanReverse64( &r, val );
|
||||
return (int)(r>>3);
|
||||
#elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
return (__builtin_clzll(val) >> 3);
|
||||
#else
|
||||
int r;
|
||||
if (!(val>>32)) { r=4; } else { r=0; val>>=32; }
|
||||
if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
|
||||
r += (!val);
|
||||
return r;
|
||||
#endif
|
||||
#else
|
||||
#if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
unsigned long r = 0;
|
||||
_BitScanForward64( &r, val );
|
||||
return (int)(r>>3);
|
||||
#elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
return (__builtin_ctzll(val) >> 3);
|
||||
#else
|
||||
static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 };
|
||||
return DeBruijnBytePos[((U64)((val & -val) * 0x0218A392CDABBD3F)) >> 58];
|
||||
#endif
|
||||
#endif
|
||||
}
|
||||
|
||||
#else
|
||||
|
||||
inline static int LZ4_NbCommonBytes (register U32 val)
|
||||
{
|
||||
#if defined(LZ4_BIG_ENDIAN)
|
||||
#if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
unsigned long r = 0;
|
||||
_BitScanReverse( &r, val );
|
||||
return (int)(r>>3);
|
||||
#elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
return (__builtin_clz(val) >> 3);
|
||||
#else
|
||||
int r;
|
||||
if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
|
||||
r += (!val);
|
||||
return r;
|
||||
#endif
|
||||
#else
|
||||
#if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
unsigned long r = 0;
|
||||
_BitScanForward( &r, val );
|
||||
return (int)(r>>3);
|
||||
#elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
|
||||
return (__builtin_ctz(val) >> 3);
|
||||
#else
|
||||
static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 };
|
||||
return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
|
||||
#endif
|
||||
#endif
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
|
||||
//****************************
|
||||
// Public functions
|
||||
//****************************
|
||||
|
||||
int LZ4_compressBound(int isize)
|
||||
{
|
||||
return (isize + (isize/255) + 16);
|
||||
}
|
||||
|
||||
|
||||
|
||||
//******************************
|
||||
// Compression functions
|
||||
//******************************
|
||||
|
||||
int LZ4_compressCtx(void** ctx,
|
||||
char* source,
|
||||
const char* source,
|
||||
char* dest,
|
||||
int isize)
|
||||
{
|
||||
#if HEAPMODE
|
||||
struct refTables *srt = (struct refTables *) (*ctx);
|
||||
const BYTE** HashTable;
|
||||
HTYPE* HashTable;
|
||||
#else
|
||||
const BYTE* HashTable[HASHTABLESIZE] = {0};
|
||||
HTYPE HashTable[HASHTABLESIZE] = {0};
|
||||
#endif
|
||||
|
||||
const BYTE* ip = (BYTE*) source;
|
||||
INITBASE(base);
|
||||
const BYTE* anchor = ip;
|
||||
const BYTE* const iend = ip + isize;
|
||||
const BYTE* const mflimit = iend - MFLIMIT;
|
||||
@ -163,7 +358,7 @@ int LZ4_compressCtx(void** ctx,
|
||||
srt = (struct refTables *) malloc ( sizeof(struct refTables) );
|
||||
*ctx = (void*) srt;
|
||||
}
|
||||
HashTable = srt->hashTable;
|
||||
HashTable = (HTYPE*)(srt->hashTable);
|
||||
memset((void*)HashTable, 0, sizeof(srt->hashTable));
|
||||
#else
|
||||
(void) ctx;
|
||||
@ -171,7 +366,7 @@ int LZ4_compressCtx(void** ctx,
|
||||
|
||||
|
||||
// First Byte
|
||||
HashTable[LZ4_HASH_VALUE(ip)] = ip;
|
||||
HashTable[LZ4_HASH_VALUE(ip)] = ip - base;
|
||||
ip++; forwardH = LZ4_HASH_VALUE(ip);
|
||||
|
||||
// Main Loop
|
||||
@ -189,16 +384,16 @@ int LZ4_compressCtx(void** ctx,
|
||||
ip = forwardIp;
|
||||
forwardIp = ip + step;
|
||||
|
||||
if (forwardIp > mflimit) { goto _last_literals; }
|
||||
if unlikely(forwardIp > mflimit) { goto _last_literals; }
|
||||
|
||||
forwardH = LZ4_HASH_VALUE(forwardIp);
|
||||
ref = HashTable[h];
|
||||
HashTable[h] = ip;
|
||||
ref = base + HashTable[h];
|
||||
HashTable[h] = ip - base;
|
||||
|
||||
} while ((ref < ip - MAX_DISTANCE) || (A32(ref) != A32(ip)));
|
||||
|
||||
// Catch up
|
||||
while ((ip>anchor) && (ref>(BYTE*)source) && (ip[-1]==ref[-1])) { ip--; ref--; }
|
||||
while ((ip>anchor) && (ref>(BYTE*)source) && unlikely(ip[-1]==ref[-1])) { ip--; ref--; }
|
||||
|
||||
// Encode Literal length
|
||||
length = ip - anchor;
|
||||
@ -209,24 +404,27 @@ int LZ4_compressCtx(void** ctx,
|
||||
// Copy Literals
|
||||
LZ4_BLINDCOPY(anchor, op, length);
|
||||
|
||||
|
||||
_next_match:
|
||||
// Encode Offset
|
||||
A16(op) = (ip-ref); op+=2;
|
||||
LZ4_WRITE_LITTLEENDIAN_16(op,ip-ref);
|
||||
|
||||
// Start Counting
|
||||
ip+=MINMATCH; ref+=MINMATCH; // MinMatch verified
|
||||
anchor = ip;
|
||||
while (A32(ref) == A32(ip))
|
||||
while likely(ip<matchlimit-(STEPSIZE-1))
|
||||
{
|
||||
ip+=4; ref+=4;
|
||||
if (ip>matchlimit-4) { ref -= ip - (matchlimit-3); ip = matchlimit-3; break; }
|
||||
UARCH diff = AARCH(ref) ^ AARCH(ip);
|
||||
if (!diff) { ip+=STEPSIZE; ref+=STEPSIZE; continue; }
|
||||
ip += LZ4_NbCommonBytes(diff);
|
||||
goto _endCount;
|
||||
}
|
||||
if (A16(ref) == A16(ip)) { ip+=2; ref+=2; }
|
||||
if (*ref == *ip) ip++;
|
||||
len = (ip - anchor);
|
||||
if (LZ4_ARCH64) if ((ip<(matchlimit-3)) && (A32(ref) == A32(ip))) { ip+=4; ref+=4; }
|
||||
if ((ip<(matchlimit-1)) && (A16(ref) == A16(ip))) { ip+=2; ref+=2; }
|
||||
if ((ip<matchlimit) && (*ref == *ip)) ip++;
|
||||
_endCount:
|
||||
|
||||
// Encode MatchLength
|
||||
len = (ip - anchor);
|
||||
if (len>=(int)ML_MASK) { *token+=ML_MASK; len-=ML_MASK; for(; len > 509 ; len-=510) { *op++ = 255; *op++ = 255; } if (len > 254) { len-=255; *op++ = 255; } *op++ = (BYTE)len; }
|
||||
else *token += len;
|
||||
|
||||
@ -234,11 +432,11 @@ _next_match:
|
||||
if (ip > mflimit) { anchor = ip; break; }
|
||||
|
||||
// Fill table
|
||||
HashTable[LZ4_HASH_VALUE(ip-2)] = ip-2;
|
||||
HashTable[LZ4_HASH_VALUE(ip-2)] = ip - 2 - base;
|
||||
|
||||
// Test next position
|
||||
ref = HashTable[LZ4_HASH_VALUE(ip)];
|
||||
HashTable[LZ4_HASH_VALUE(ip)] = ip;
|
||||
ref = base + HashTable[LZ4_HASH_VALUE(ip)];
|
||||
HashTable[LZ4_HASH_VALUE(ip)] = ip - base;
|
||||
if ((ref > ip - (MAX_DISTANCE + 1)) && (A32(ref) == A32(ip))) { token = op++; *token=0; goto _next_match; }
|
||||
|
||||
// Prepare next loop
|
||||
@ -250,6 +448,7 @@ _last_literals:
|
||||
// Encode Last Literals
|
||||
{
|
||||
int lastRun = iend - anchor;
|
||||
if ((LZ4_COMPRESSMIN>0) && (((op - (BYTE*)dest) + lastRun + 1 + ((lastRun-15)/255)) > isize - LZ4_COMPRESSMIN)) return 0;
|
||||
if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun > 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }
|
||||
else *op++ = (lastRun<<ML_BITS);
|
||||
memcpy(op, anchor, iend - anchor);
|
||||
@ -263,12 +462,13 @@ _last_literals:
|
||||
|
||||
|
||||
// Note : this function is valid only if isize < LZ4_64KLIMIT
|
||||
#define LZ4_64KLIMIT ((1U<<16) + (MFLIMIT-1))
|
||||
#define LZ4_64KLIMIT ((1<<16) + (MFLIMIT-1))
|
||||
#define HASHLOG64K (HASH_LOG+1)
|
||||
#define HASH64KTABLESIZE (1U<<HASHLOG64K)
|
||||
#define LZ4_HASH64K_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH*8)-HASHLOG64K))
|
||||
#define LZ4_HASH64K_VALUE(p) LZ4_HASH64K_FUNCTION(A32(p))
|
||||
int LZ4_compress64kCtx(void** ctx,
|
||||
char* source,
|
||||
const char* source,
|
||||
char* dest,
|
||||
int isize)
|
||||
{
|
||||
@ -276,7 +476,7 @@ int LZ4_compress64kCtx(void** ctx,
|
||||
struct refTables *srt = (struct refTables *) (*ctx);
|
||||
U16* HashTable;
|
||||
#else
|
||||
U16 HashTable[HASHTABLESIZE<<1] = {0};
|
||||
U16 HashTable[HASH64KTABLESIZE] = {0};
|
||||
#endif
|
||||
|
||||
const BYTE* ip = (BYTE*) source;
|
||||
@ -346,37 +546,40 @@ int LZ4_compress64kCtx(void** ctx,
|
||||
// Copy Literals
|
||||
LZ4_BLINDCOPY(anchor, op, length);
|
||||
|
||||
|
||||
_next_match:
|
||||
// Encode Offset
|
||||
A16(op) = (ip-ref); op+=2;
|
||||
LZ4_WRITE_LITTLEENDIAN_16(op,ip-ref);
|
||||
|
||||
// Start Counting
|
||||
ip+=MINMATCH; ref+=MINMATCH; // MinMatch verified
|
||||
anchor = ip;
|
||||
while (ip<matchlimit-3)
|
||||
while (ip<matchlimit-(STEPSIZE-1))
|
||||
{
|
||||
if (A32(ref) == A32(ip)) { ip+=4; ref+=4; continue; }
|
||||
if (A16(ref) == A16(ip)) { ip+=2; ref+=2; }
|
||||
if (*ref == *ip) ip++;
|
||||
UARCH diff = AARCH(ref) ^ AARCH(ip);
|
||||
if (!diff) { ip+=STEPSIZE; ref+=STEPSIZE; continue; }
|
||||
ip += LZ4_NbCommonBytes(diff);
|
||||
goto _endCount;
|
||||
}
|
||||
if (LZ4_ARCH64) if ((ip<(matchlimit-3)) && (A32(ref) == A32(ip))) { ip+=4; ref+=4; }
|
||||
if ((ip<(matchlimit-1)) && (A16(ref) == A16(ip))) { ip+=2; ref+=2; }
|
||||
if ((ip<matchlimit) && (*ref == *ip)) ip++;
|
||||
_endCount:
|
||||
len = (ip - anchor);
|
||||
|
||||
// Encode MatchLength
|
||||
len = (ip - anchor);
|
||||
if (len>=(int)ML_MASK) { *token+=ML_MASK; len-=ML_MASK; for(; len > 509 ; len-=510) { *op++ = 255; *op++ = 255; } if (len > 254) { len-=255; *op++ = 255; } *op++ = (BYTE)len; }
|
||||
else *token += len;
|
||||
|
||||
// Test end of chunk
|
||||
if (ip > mflimit) { anchor = ip; break; }
|
||||
|
||||
// Fill table
|
||||
HashTable[LZ4_HASH64K_VALUE(ip-2)] = ip - 2 - base;
|
||||
|
||||
// Test next position
|
||||
ref = base + HashTable[LZ4_HASH64K_VALUE(ip)];
|
||||
HashTable[LZ4_HASH64K_VALUE(ip)] = ip - base;
|
||||
if ((ref > ip - (MAX_DISTANCE + 1)) && (A32(ref) == A32(ip))) { token = op++; *token=0; goto _next_match; }
|
||||
if (A32(ref) == A32(ip)) { token = op++; *token=0; goto _next_match; }
|
||||
|
||||
// Prepare next loop
|
||||
anchor = ip++;
|
||||
@ -387,6 +590,7 @@ _last_literals:
|
||||
// Encode Last Literals
|
||||
{
|
||||
int lastRun = iend - anchor;
|
||||
if ((LZ4_COMPRESSMIN>0) && (((op - (BYTE*)dest) + lastRun + 1 + ((lastRun-15)/255)) > isize - LZ4_COMPRESSMIN)) return 0;
|
||||
if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun > 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }
|
||||
else *op++ = (lastRun<<ML_BITS);
|
||||
memcpy(op, anchor, iend - anchor);
|
||||
@ -399,7 +603,7 @@ _last_literals:
|
||||
|
||||
|
||||
|
||||
int LZ4_compress(char* source,
|
||||
int LZ4_compress(const char* source,
|
||||
char* dest,
|
||||
int isize)
|
||||
{
|
||||
@ -421,31 +625,31 @@ int LZ4_compress(char* source,
|
||||
|
||||
|
||||
//****************************
|
||||
// Decompression CODE
|
||||
// Decompression functions
|
||||
//****************************
|
||||
|
||||
// Note : The decoding functions LZ4_uncompress() and LZ4_uncompress_unknownOutputSize()
|
||||
// are safe against "buffer overflow" attack type
|
||||
// since they will *never* write outside of the provided output buffer :
|
||||
// they both check this condition *before* writing anything.
|
||||
// A corrupted packet however can make them *read* within the first 64K before the output buffer.
|
||||
// are safe against "buffer overflow" attack type.
|
||||
// They will never write nor read outside of the provided output buffers.
|
||||
// LZ4_uncompress_unknownOutputSize() also insures that it will never read outside of the input buffer.
|
||||
// A corrupted input will produce an error result, a negative int, indicating the position of the error within input stream.
|
||||
|
||||
int LZ4_uncompress(char* source,
|
||||
int LZ4_uncompress(const char* source,
|
||||
char* dest,
|
||||
int osize)
|
||||
{
|
||||
// Local Variables
|
||||
const BYTE* ip = (const BYTE*) source;
|
||||
BYTE* ref;
|
||||
const BYTE* restrict ip = (const BYTE*) source;
|
||||
const BYTE* restrict ref;
|
||||
|
||||
BYTE* op = (BYTE*) dest;
|
||||
BYTE* restrict op = (BYTE*) dest;
|
||||
BYTE* const oend = op + osize;
|
||||
BYTE* cpy;
|
||||
|
||||
BYTE token;
|
||||
|
||||
U32 dec[4]={0, 3, 2, 3};
|
||||
int len, length;
|
||||
size_t dec[] ={0, 3, 2, 3, 0, 0, 0, 0};
|
||||
|
||||
|
||||
// Main Loop
|
||||
@ -456,44 +660,51 @@ int LZ4_uncompress(char* source,
|
||||
if ((length=(token>>ML_BITS)) == RUN_MASK) { for (;(len=*ip++)==255;length+=255){} length += len; }
|
||||
|
||||
// copy literals
|
||||
ref = op+length;
|
||||
if (ref>oend-COPYLENGTH)
|
||||
cpy = op+length;
|
||||
if unlikely(cpy>oend-COPYLENGTH)
|
||||
{
|
||||
if (ref > oend) goto _output_error;
|
||||
if (cpy > oend) goto _output_error;
|
||||
memcpy(op, ip, length);
|
||||
ip += length;
|
||||
break; // Necessarily EOF
|
||||
}
|
||||
LZ4_WILDCOPY(ip, op, ref); ip -= (op-ref); op = ref;
|
||||
|
||||
LZ4_WILDCOPY(ip, op, cpy); ip -= (op-cpy); op = cpy;
|
||||
|
||||
// get offset
|
||||
ref -= A16(ip); ip+=2;
|
||||
LZ4_READ_LITTLEENDIAN_16(ref,cpy,ip); ip+=2;
|
||||
if (ref < (BYTE* const)dest) goto _output_error;
|
||||
|
||||
// get matchlength
|
||||
if ((length=(token&ML_MASK)) == ML_MASK) { for (;*ip==255;length+=255) {ip++;} length += *ip++; }
|
||||
|
||||
// copy repeated sequence
|
||||
if (op-ref<COPYTOKEN)
|
||||
if unlikely(op-ref<STEPSIZE)
|
||||
{
|
||||
#if LZ4_ARCH64
|
||||
size_t dec2table[]={0, 0, 0, -1, 0, 1, 2, 3};
|
||||
size_t dec2 = dec2table[op-ref];
|
||||
#else
|
||||
const int dec2 = 0;
|
||||
#endif
|
||||
*op++ = *ref++;
|
||||
*op++ = *ref++;
|
||||
*op++ = *ref++;
|
||||
*op++ = *ref++;
|
||||
ref -= dec[op-ref];
|
||||
A32(op)=A32(ref);
|
||||
} else { A32(op)=A32(ref); op+=4; ref+=4; }
|
||||
cpy = op + length;
|
||||
if (cpy > oend-COPYLENGTH)
|
||||
A32(op)=A32(ref); op += STEPSIZE-4;
|
||||
ref -= dec2;
|
||||
} else { LZ4_COPYSTEP(ref,op); }
|
||||
cpy = op + length - (STEPSIZE-4);
|
||||
if (cpy>oend-COPYLENGTH)
|
||||
{
|
||||
if (cpy > oend) goto _output_error;
|
||||
LZ4_WILDCOPY(ref, op, (oend-COPYLENGTH));
|
||||
LZ4_SECURECOPY(ref, op, (oend-COPYLENGTH));
|
||||
while(op<cpy) *op++=*ref++;
|
||||
op=cpy;
|
||||
if (op == oend) break; // Check EOF (should never happen, since last 5 bytes are supposed to be literals)
|
||||
continue;
|
||||
}
|
||||
LZ4_WILDCOPY(ref, op, cpy);
|
||||
LZ4_SECURECOPY(ref, op, cpy);
|
||||
op=cpy; // correction
|
||||
}
|
||||
|
||||
@ -507,73 +718,82 @@ _output_error:
|
||||
|
||||
|
||||
int LZ4_uncompress_unknownOutputSize(
|
||||
char* source,
|
||||
const char* source,
|
||||
char* dest,
|
||||
int isize,
|
||||
int maxOutputSize)
|
||||
{
|
||||
// Local Variables
|
||||
const BYTE* ip = (const BYTE*) source;
|
||||
const BYTE* restrict ip = (const BYTE*) source;
|
||||
const BYTE* const iend = ip + isize;
|
||||
BYTE* ref;
|
||||
const BYTE* restrict ref;
|
||||
|
||||
BYTE* op = (BYTE*) dest;
|
||||
BYTE* restrict op = (BYTE*) dest;
|
||||
BYTE* const oend = op + maxOutputSize;
|
||||
BYTE* cpy;
|
||||
|
||||
BYTE token;
|
||||
|
||||
U32 dec[COPYTOKEN]={0, 3, 2, 3};
|
||||
int len, length;
|
||||
size_t dec[] ={0, 3, 2, 3, 0, 0, 0, 0};
|
||||
|
||||
|
||||
// Main Loop
|
||||
while (ip<iend)
|
||||
{
|
||||
BYTE token;
|
||||
int length;
|
||||
|
||||
// get runlength
|
||||
token = *ip++;
|
||||
if ((length=(token>>ML_BITS)) == RUN_MASK) { for (;(len=*ip++)==255;length+=255){} length += len; }
|
||||
if ((length=(token>>ML_BITS)) == RUN_MASK) { int s=255; while ((ip<iend) && (s==255)) { s=*ip++; length += s; } }
|
||||
|
||||
// copy literals
|
||||
ref = op+length;
|
||||
if (ref>oend-COPYLENGTH)
|
||||
cpy = op+length;
|
||||
if ((cpy>oend-COPYLENGTH) || (ip+length>iend-COPYLENGTH))
|
||||
{
|
||||
if (ref > oend) goto _output_error;
|
||||
if (cpy > oend) goto _output_error;
|
||||
if (ip+length > iend) goto _output_error;
|
||||
memcpy(op, ip, length);
|
||||
op += length;
|
||||
ip += length;
|
||||
break; // Necessarily EOF
|
||||
if (ip<iend) goto _output_error;
|
||||
break; // Necessarily EOF, due to parsing restrictions
|
||||
}
|
||||
LZ4_WILDCOPY(ip, op, ref); ip -= (op-ref); op = ref;
|
||||
if (ip>=iend) break; // check EOF
|
||||
|
||||
LZ4_WILDCOPY(ip, op, cpy); ip -= (op-cpy); op = cpy;
|
||||
|
||||
// get offset
|
||||
ref -= A16(ip); ip+=2;
|
||||
LZ4_READ_LITTLEENDIAN_16(ref,cpy,ip); ip+=2;
|
||||
if (ref < (BYTE* const)dest) goto _output_error;
|
||||
|
||||
// get matchlength
|
||||
if ((length=(token&ML_MASK)) == ML_MASK) { for (;(len=*ip++)==255;length+=255){} length += len; }
|
||||
if ((length=(token&ML_MASK)) == ML_MASK) { while (ip<iend) { int s = *ip++; length +=s; if (s==255) continue; break; } }
|
||||
|
||||
// copy repeated sequence
|
||||
if (op-ref<COPYTOKEN)
|
||||
if unlikely(op-ref<STEPSIZE)
|
||||
{
|
||||
#if LZ4_ARCH64
|
||||
size_t dec2table[]={0, 0, 0, -1, 0, 1, 2, 3};
|
||||
size_t dec2 = dec2table[op-ref];
|
||||
#else
|
||||
const int dec2 = 0;
|
||||
#endif
|
||||
*op++ = *ref++;
|
||||
*op++ = *ref++;
|
||||
*op++ = *ref++;
|
||||
*op++ = *ref++;
|
||||
ref -= dec[op-ref];
|
||||
A32(op)=A32(ref);
|
||||
} else { A32(op)=A32(ref); op+=4; ref+=4; }
|
||||
cpy = op + length;
|
||||
A32(op)=A32(ref); op += STEPSIZE-4;
|
||||
ref -= dec2;
|
||||
} else { LZ4_COPYSTEP(ref,op); }
|
||||
cpy = op + length - (STEPSIZE-4);
|
||||
if (cpy>oend-COPYLENGTH)
|
||||
{
|
||||
if (cpy > oend) goto _output_error;
|
||||
LZ4_WILDCOPY(ref, op, (oend-COPYLENGTH));
|
||||
LZ4_SECURECOPY(ref, op, (oend-COPYLENGTH));
|
||||
while(op<cpy) *op++=*ref++;
|
||||
op=cpy;
|
||||
if (op == oend) break; // Check EOF (should never happen, since last 5 bytes are supposed to be literals)
|
||||
continue;
|
||||
}
|
||||
LZ4_WILDCOPY(ref, op, cpy);
|
||||
LZ4_SECURECOPY(ref, op, cpy);
|
||||
op=cpy; // correction
|
||||
}
|
||||
|
||||
@ -585,4 +805,3 @@ _output_error:
|
||||
return (int) (-(((char*)ip)-source));
|
||||
}
|
||||
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user