Created
June 10, 2012 19:32
-
-
Save maxpert/2907047 to your computer and use it in GitHub Desktop.
TokyoCabinet + LZ4 speedups
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
processor : 0 | |
vendor_id : GenuineIntel | |
cpu family : 6 | |
model : 37 | |
model name : Intel(R) Core(TM) i3 CPU 540 @ 3.07GHz | |
stepping : 5 | |
cpu MHz : 1200.000 | |
cache size : 4096 KB | |
physical id : 0 | |
siblings : 4 | |
core id : 0 | |
cpu cores : 2 | |
apicid : 0 | |
initial apicid : 0 | |
fdiv_bug : no | |
hlt_bug : no | |
f00f_bug : no | |
coma_bug : no | |
fpu : yes | |
fpu_exception : yes | |
cpuid level : 11 | |
wp : yes | |
flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx rdtscp lm constant_tsc arch_perfmon pebs bts xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm sse4_1 sse4_2 popcnt lahf_lm arat dts tpr_shadow vnmi flexpriority ept vpid | |
bogomips : 6133.45 | |
clflush size : 64 | |
cache_alignment : 64 | |
address sizes : 36 bits physical, 48 bits virtual | |
power management: | |
processor : 1 | |
vendor_id : GenuineIntel | |
cpu family : 6 | |
model : 37 | |
model name : Intel(R) Core(TM) i3 CPU 540 @ 3.07GHz | |
stepping : 5 | |
cpu MHz : 1200.000 | |
cache size : 4096 KB | |
physical id : 0 | |
siblings : 4 | |
core id : 2 | |
cpu cores : 2 | |
apicid : 4 | |
initial apicid : 4 | |
fdiv_bug : no | |
hlt_bug : no | |
f00f_bug : no | |
coma_bug : no | |
fpu : yes | |
fpu_exception : yes | |
cpuid level : 11 | |
wp : yes | |
flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx rdtscp lm constant_tsc arch_perfmon pebs bts xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm sse4_1 sse4_2 popcnt lahf_lm arat dts tpr_shadow vnmi flexpriority ept vpid | |
bogomips : 6133.30 | |
clflush size : 64 | |
cache_alignment : 64 | |
address sizes : 36 bits physical, 48 bits virtual | |
power management: | |
processor : 2 | |
vendor_id : GenuineIntel | |
cpu family : 6 | |
model : 37 | |
model name : Intel(R) Core(TM) i3 CPU 540 @ 3.07GHz | |
stepping : 5 | |
cpu MHz : 1200.000 | |
cache size : 4096 KB | |
physical id : 0 | |
siblings : 4 | |
core id : 0 | |
cpu cores : 2 | |
apicid : 1 | |
initial apicid : 1 | |
fdiv_bug : no | |
hlt_bug : no | |
f00f_bug : no | |
coma_bug : no | |
fpu : yes | |
fpu_exception : yes | |
cpuid level : 11 | |
wp : yes | |
flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx rdtscp lm constant_tsc arch_perfmon pebs bts xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm sse4_1 sse4_2 popcnt lahf_lm arat dts tpr_shadow vnmi flexpriority ept vpid | |
bogomips : 6133.31 | |
clflush size : 64 | |
cache_alignment : 64 | |
address sizes : 36 bits physical, 48 bits virtual | |
power management: | |
processor : 3 | |
vendor_id : GenuineIntel | |
cpu family : 6 | |
model : 37 | |
model name : Intel(R) Core(TM) i3 CPU 540 @ 3.07GHz | |
stepping : 5 | |
cpu MHz : 1200.000 | |
cache size : 4096 KB | |
physical id : 0 | |
siblings : 4 | |
core id : 2 | |
cpu cores : 2 | |
apicid : 5 | |
initial apicid : 5 | |
fdiv_bug : no | |
hlt_bug : no | |
f00f_bug : no | |
coma_bug : no | |
fpu : yes | |
fpu_exception : yes | |
cpuid level : 11 | |
wp : yes | |
flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx rdtscp lm constant_tsc arch_perfmon pebs bts xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm sse4_1 sse4_2 popcnt lahf_lm arat dts tpr_shadow vnmi flexpriority ept vpid | |
bogomips : 6133.31 | |
clflush size : 64 | |
cache_alignment : 64 | |
address sizes : 36 bits physical, 48 bits virtual | |
power management: |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/dev/sda: | |
ATA device, with non-removable media | |
Model Number: ST3250312AS | |
Serial Number: Z2A1KYYX | |
Firmware Revision: JC45 | |
Transport: Serial | |
Standards: | |
Used: unknown (minor revision code 0x0029) | |
Supported: 8 7 6 5 | |
Likely used: 8 | |
Configuration: | |
Logical max current | |
cylinders 16383 16383 | |
heads 16 16 | |
sectors/track 63 63 | |
-- | |
CHS current addressable sectors: 16514064 | |
LBA user addressable sectors: 268435455 | |
LBA48 user addressable sectors: 488397168 | |
Logical/Physical Sector size: 512 bytes | |
device size with M = 1024*1024: 238475 MBytes | |
device size with M = 1000*1000: 250059 MBytes (250 GB) | |
cache/buffer size = 8192 KBytes | |
Nominal Media Rotation Rate: 7200 | |
Capabilities: | |
LBA, IORDY(can be disabled) | |
Queue depth: 32 | |
Standby timer values: spec'd by Standard, no device specific minimum | |
R/W multiple sector transfer: Max = 16 Current = 16 | |
Recommended acoustic management value: 208, current value: 208 | |
DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 udma5 *udma6 | |
Cycle time: min=120ns recommended=120ns | |
PIO: pio0 pio1 pio2 pio3 pio4 | |
Cycle time: no flow control=120ns IORDY flow control=120ns | |
Commands/features: | |
Enabled Supported: | |
* SMART feature set | |
Security Mode feature set | |
* Power Management feature set | |
* Write cache | |
* Look-ahead | |
* Host Protected Area feature set | |
* WRITE_BUFFER command | |
* READ_BUFFER command | |
* DOWNLOAD_MICROCODE | |
SET_MAX security extension | |
* Automatic Acoustic Management feature set | |
* 48-bit Address feature set | |
* Device Configuration Overlay feature set | |
* Mandatory FLUSH_CACHE | |
* FLUSH_CACHE_EXT | |
* SMART error logging | |
* SMART self-test | |
* General Purpose Logging feature set | |
* WRITE_{DMA|MULTIPLE}_FUA_EXT | |
* 64-bit World wide name | |
Write-Read-Verify feature set | |
* WRITE_UNCORRECTABLE_EXT command | |
* {READ,WRITE}_DMA_EXT_GPL commands | |
* Segmented DOWNLOAD_MICROCODE | |
* Gen1 signaling speed (1.5Gb/s) | |
* Gen2 signaling speed (3.0Gb/s) | |
* Gen3 signaling speed (6.0Gb/s) | |
* Native Command Queueing (NCQ) | |
* Phy event counters | |
Device-initiated interface power management | |
* Software settings preservation | |
* SMART Command Transport (SCT) feature set | |
* SCT Long Sector Access (AC1) | |
* SCT LBA Segment Access (AC2) | |
* SCT Error Recovery Control (AC3) | |
* SCT Features Control (AC4) | |
* SCT Data Tables (AC5) | |
unknown 206[12] (vendor specific) | |
Security: | |
Master password revision code = 65534 | |
supported | |
not enabled | |
not locked | |
frozen | |
not expired: security count | |
supported: enhanced erase | |
40min for SECURITY ERASE UNIT. 40min for ENHANCED SECURITY ERASE UNIT. | |
Logical Unit WWN Device Identifier: 5000c5002e0d006e | |
NAA : 5 | |
IEEE OUI : 000c50 | |
Unique ID : 02e0d006e | |
Checksum: correct |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
00:00.0 Host bridge: Intel Corporation Core Processor DRAM Controller (rev 18) | |
00:02.0 VGA compatible controller: Intel Corporation Core Processor Integrated Graphics Controller (rev 18) | |
00:16.0 Communication controller: Intel Corporation 5 Series/3400 Series Chipset HECI Controller (rev 06) | |
00:1a.0 USB Controller: Intel Corporation 5 Series/3400 Series Chipset USB2 Enhanced Host Controller (rev 06) | |
00:1b.0 Audio device: Intel Corporation 5 Series/3400 Series Chipset High Definition Audio (rev 06) | |
00:1c.0 PCI bridge: Intel Corporation 5 Series/3400 Series Chipset PCI Express Root Port 1 (rev 06) | |
00:1c.2 PCI bridge: Intel Corporation 5 Series/3400 Series Chipset PCI Express Root Port 3 (rev 06) | |
00:1c.5 PCI bridge: Intel Corporation 5 Series/3400 Series Chipset PCI Express Root Port 6 (rev 06) | |
00:1d.0 USB Controller: Intel Corporation 5 Series/3400 Series Chipset USB2 Enhanced Host Controller (rev 06) | |
00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev a6) | |
00:1f.0 ISA bridge: Intel Corporation 5 Series Chipset LPC Interface Controller (rev 06) | |
00:1f.2 IDE interface: Intel Corporation 5 Series/3400 Series Chipset 4 port SATA IDE Controller (rev 06) | |
00:1f.3 SMBus: Intel Corporation 5 Series/3400 Series Chipset SMBus Controller (rev 06) | |
00:1f.5 IDE interface: Intel Corporation 5 Series/3400 Series Chipset 2 port SATA IDE Controller (rev 06) | |
01:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168B PCI Express Gigabit Ethernet controller (rev 03) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/* | |
LZ4 - Fast LZ compression algorithm | |
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 | |
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 : | |
- LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html | |
- LZ4 source repository : http://code.google.com/p/lz4/ | |
*/ | |
//************************************** | |
// 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 ? | |
// Note : overwrite the below #define if you know your architecture endianess | |
#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 | |
// Define this parameter if your target system or compiler does not support hardware bit count | |
#if defined(_MSC_VER) && defined(_WIN32_WCE) // Visual Studio for Windows CE does not support Hardware bit count | |
# define LZ4_FORCE_SW_BITCOUNT | |
#endif | |
//************************************** | |
// 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 | |
# if LZ4_ARCH64 // 64-bit | |
# pragma intrinsic(_BitScanForward64) // For Visual 2005 | |
# pragma intrinsic(_BitScanReverse64) // For Visual 2005 | |
# else | |
# pragma intrinsic(_BitScanForward) // For Visual 2005 | |
# pragma intrinsic(_BitScanReverse) // For Visual 2005 | |
# endif | |
#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 | |
//************************************** | |
#include <stdlib.h> // for malloc | |
#include <string.h> // for memset | |
#include "lz4.h" | |
//************************************** | |
// Basic Types | |
//************************************** | |
#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 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 COPYLENGTH 8 | |
#define LASTLITERALS 5 | |
#define MFLIMIT (COPYLENGTH+MINMATCH) | |
#define MINLENGTH (MFLIMIT+1) | |
#define MAXD_LOG 16 | |
#define MAX_DISTANCE ((1 << MAXD_LOG) - 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 | |
{ | |
HTYPE hashTable[HASHTABLESIZE]; | |
}; | |
//************************************** | |
// Macros | |
//************************************** | |
#define LZ4_HASH_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH*8)-HASH_LOG)) | |
#define LZ4_HASH_VALUE(p) LZ4_HASH_FUNCTION(A32(p)) | |
#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; } | |
//**************************** | |
// 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, | |
const char* source, | |
char* dest, | |
int isize) | |
{ | |
#if HEAPMODE | |
struct refTables *srt = (struct refTables *) (*ctx); | |
HTYPE* HashTable; | |
#else | |
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; | |
#define matchlimit (iend - LASTLITERALS) | |
BYTE* op = (BYTE*) dest; | |
int len, length; | |
const int skipStrength = SKIPSTRENGTH; | |
U32 forwardH; | |
// Init | |
if (isize<MINLENGTH) goto _last_literals; | |
#if HEAPMODE | |
if (*ctx == NULL) | |
{ | |
srt = (struct refTables *) malloc ( sizeof(struct refTables) ); | |
*ctx = (void*) srt; | |
} | |
HashTable = (HTYPE*)(srt->hashTable); | |
memset((void*)HashTable, 0, sizeof(srt->hashTable)); | |
#else | |
(void) ctx; | |
#endif | |
// First Byte | |
HashTable[LZ4_HASH_VALUE(ip)] = ip - base; | |
ip++; forwardH = LZ4_HASH_VALUE(ip); | |
// Main Loop | |
for ( ; ; ) | |
{ | |
int findMatchAttempts = (1U << skipStrength) + 3; | |
const BYTE* forwardIp = ip; | |
const BYTE* ref; | |
BYTE* token; | |
// Find a match | |
do { | |
U32 h = forwardH; | |
int step = findMatchAttempts++ >> skipStrength; | |
ip = forwardIp; | |
forwardIp = ip + step; | |
if unlikely(forwardIp > mflimit) { goto _last_literals; } | |
forwardH = LZ4_HASH_VALUE(forwardIp); | |
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) && unlikely(ip[-1]==ref[-1])) { ip--; ref--; } | |
// Encode Literal length | |
length = ip - anchor; | |
token = op++; | |
if (length>=(int)RUN_MASK) { *token=(RUN_MASK<<ML_BITS); len = length-RUN_MASK; for(; len > 254 ; len-=255) *op++ = 255; *op++ = (BYTE)len; } | |
else *token = (length<<ML_BITS); | |
// Copy Literals | |
LZ4_BLINDCOPY(anchor, op, length); | |
_next_match: | |
// Encode Offset | |
LZ4_WRITE_LITTLEENDIAN_16(op,ip-ref); | |
// Start Counting | |
ip+=MINMATCH; ref+=MINMATCH; // MinMatch verified | |
anchor = ip; | |
while likely(ip<matchlimit-(STEPSIZE-1)) | |
{ | |
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: | |
// 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_HASH_VALUE(ip-2)] = ip - 2 - base; | |
// Test next position | |
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 | |
anchor = ip++; | |
forwardH = LZ4_HASH_VALUE(ip); | |
} | |
_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); | |
op += iend-anchor; | |
} | |
// End | |
return (int) (((char*)op)-dest); | |
} | |
// Note : this function is valid only if isize < LZ4_64KLIMIT | |
#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, | |
const char* source, | |
char* dest, | |
int isize) | |
{ | |
#if HEAPMODE | |
struct refTables *srt = (struct refTables *) (*ctx); | |
U16* HashTable; | |
#else | |
U16 HashTable[HASH64KTABLESIZE] = {0}; | |
#endif | |
const BYTE* ip = (BYTE*) source; | |
const BYTE* anchor = ip; | |
const BYTE* const base = ip; | |
const BYTE* const iend = ip + isize; | |
const BYTE* const mflimit = iend - MFLIMIT; | |
#define matchlimit (iend - LASTLITERALS) | |
BYTE* op = (BYTE*) dest; | |
int len, length; | |
const int skipStrength = SKIPSTRENGTH; | |
U32 forwardH; | |
// Init | |
if (isize<MINLENGTH) goto _last_literals; | |
#if HEAPMODE | |
if (*ctx == NULL) | |
{ | |
srt = (struct refTables *) malloc ( sizeof(struct refTables) ); | |
*ctx = (void*) srt; | |
} | |
HashTable = (U16*)(srt->hashTable); | |
memset((void*)HashTable, 0, sizeof(srt->hashTable)); | |
#else | |
(void) ctx; | |
#endif | |
// First Byte | |
ip++; forwardH = LZ4_HASH64K_VALUE(ip); | |
// Main Loop | |
for ( ; ; ) | |
{ | |
int findMatchAttempts = (1U << skipStrength) + 3; | |
const BYTE* forwardIp = ip; | |
const BYTE* ref; | |
BYTE* token; | |
// Find a match | |
do { | |
U32 h = forwardH; | |
int step = findMatchAttempts++ >> skipStrength; | |
ip = forwardIp; | |
forwardIp = ip + step; | |
if (forwardIp > mflimit) { goto _last_literals; } | |
forwardH = LZ4_HASH64K_VALUE(forwardIp); | |
ref = base + HashTable[h]; | |
HashTable[h] = ip - base; | |
} while (A32(ref) != A32(ip)); | |
// Catch up | |
while ((ip>anchor) && (ref>(BYTE*)source) && (ip[-1]==ref[-1])) { ip--; ref--; } | |
// Encode Literal length | |
length = ip - anchor; | |
token = op++; | |
if (length>=(int)RUN_MASK) { *token=(RUN_MASK<<ML_BITS); len = length-RUN_MASK; for(; len > 254 ; len-=255) *op++ = 255; *op++ = (BYTE)len; } | |
else *token = (length<<ML_BITS); | |
// Copy Literals | |
LZ4_BLINDCOPY(anchor, op, length); | |
_next_match: | |
// Encode Offset | |
LZ4_WRITE_LITTLEENDIAN_16(op,ip-ref); | |
// Start Counting | |
ip+=MINMATCH; ref+=MINMATCH; // MinMatch verified | |
anchor = ip; | |
while (ip<matchlimit-(STEPSIZE-1)) | |
{ | |
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: | |
// 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 (A32(ref) == A32(ip)) { token = op++; *token=0; goto _next_match; } | |
// Prepare next loop | |
anchor = ip++; | |
forwardH = LZ4_HASH64K_VALUE(ip); | |
} | |
_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); | |
op += iend-anchor; | |
} | |
// End | |
return (int) (((char*)op)-dest); | |
} | |
int LZ4_compress(const char* source, | |
char* dest, | |
int isize) | |
{ | |
#if HEAPMODE | |
void* ctx = malloc(sizeof(struct refTables)); | |
int result; | |
if (isize < LZ4_64KLIMIT) | |
result = LZ4_compress64kCtx(&ctx, source, dest, isize); | |
else result = LZ4_compressCtx(&ctx, source, dest, isize); | |
free(ctx); | |
return result; | |
#else | |
if (isize < (int)LZ4_64KLIMIT) return LZ4_compress64kCtx(NULL, source, dest, isize); | |
return LZ4_compressCtx(NULL, source, dest, isize); | |
#endif | |
} | |
//**************************** | |
// Decompression functions | |
//**************************** | |
// Note : The decoding functions LZ4_uncompress() and LZ4_uncompress_unknownOutputSize() | |
// 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(const char* source, | |
char* dest, | |
int osize) | |
{ | |
// Local Variables | |
const BYTE* restrict ip = (const BYTE*) source; | |
const BYTE* restrict ref; | |
BYTE* restrict op = (BYTE*) dest; | |
BYTE* const oend = op + osize; | |
BYTE* cpy; | |
BYTE token; | |
int len, length; | |
size_t dec[] ={0, 3, 2, 3, 0, 0, 0, 0}; | |
// Main Loop | |
while (1) | |
{ | |
// get runlength | |
token = *ip++; | |
if ((length=(token>>ML_BITS)) == RUN_MASK) { for (;(len=*ip++)==255;length+=255){} length += len; } | |
// copy literals | |
cpy = op+length; | |
if unlikely(cpy>oend-COPYLENGTH) | |
{ | |
if (cpy > oend) goto _output_error; // Error : request to write beyond destination buffer | |
memcpy(op, ip, length); | |
ip += length; | |
break; // Necessarily EOF | |
} | |
LZ4_WILDCOPY(ip, op, cpy); ip -= (op-cpy); op = cpy; | |
// get offset | |
LZ4_READ_LITTLEENDIAN_16(ref,cpy,ip); ip+=2; | |
if (ref < (BYTE* const)dest) goto _output_error; // Error : offset create reference outside destination buffer | |
// get matchlength | |
if ((length=(token&ML_MASK)) == ML_MASK) { for (;*ip==255;length+=255) {ip++;} length += *ip++; } | |
// copy repeated sequence | |
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); 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; // Error : request to write beyond destination buffer | |
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_SECURECOPY(ref, op, cpy); | |
op=cpy; // correction | |
} | |
// end of decoding | |
return (int) (((char*)ip)-source); | |
// write overflow error detected | |
_output_error: | |
return (int) (-(((char*)ip)-source)); | |
} | |
int LZ4_uncompress_unknownOutputSize( | |
const char* source, | |
char* dest, | |
int isize, | |
int maxOutputSize) | |
{ | |
// Local Variables | |
const BYTE* restrict ip = (const BYTE*) source; | |
const BYTE* const iend = ip + isize; | |
const BYTE* restrict ref; | |
BYTE* restrict op = (BYTE*) dest; | |
BYTE* const oend = op + maxOutputSize; | |
BYTE* cpy; | |
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) { int s=255; while ((ip<iend) && (s==255)) { s=*ip++; length += s; } } | |
// copy literals | |
cpy = op+length; | |
if ((cpy>oend-COPYLENGTH) || (ip+length>iend-COPYLENGTH)) | |
{ | |
if (cpy > oend) goto _output_error; // Error : request to write beyond destination buffer | |
if (ip+length > iend) goto _output_error; // Error : request to read beyond source buffer | |
memcpy(op, ip, length); | |
op += length; | |
ip += length; | |
if (ip<iend) goto _output_error; // Error : LZ4 format violation | |
break; // Necessarily EOF, due to parsing restrictions | |
} | |
LZ4_WILDCOPY(ip, op, cpy); ip -= (op-cpy); op = cpy; | |
// get offset | |
LZ4_READ_LITTLEENDIAN_16(ref,cpy,ip); ip+=2; | |
if (ref < (BYTE* const)dest) goto _output_error; // Error : offset creates reference outside of destination buffer | |
// get matchlength | |
if ((length=(token&ML_MASK)) == ML_MASK) { while (ip<iend) { int s = *ip++; length +=s; if (s==255) continue; break; } } | |
// copy repeated sequence | |
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); 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; // Error : request to write outside of destination buffer | |
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_SECURECOPY(ref, op, cpy); | |
op=cpy; // correction | |
} | |
// end of decoding | |
return (int) (((char*)op)-dest); | |
// write overflow error detected | |
_output_error: | |
return (int) (-(((char*)ip)-source)); | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/* | |
LZ4 - Fast LZ compression algorithm | |
Header File | |
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 | |
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 : | |
- LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html | |
- LZ4 source repository : http://code.google.com/p/lz4/ | |
*/ | |
#pragma once | |
#if defined (__cplusplus) | |
extern "C" { | |
#endif | |
//**************************** | |
// Simple Functions | |
//**************************** | |
int LZ4_compress (const char* source, char* dest, int isize); | |
int LZ4_uncompress (const char* source, char* dest, int osize); | |
/* | |
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. | |
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() : | |
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 function never writes beyond dest + osize, and is therefore protected against malicious data packets | |
note : destination buffer must be already allocated | |
*/ | |
//**************************** | |
// Advanced Functions | |
//**************************** | |
int LZ4_compressBound(int isize); | |
/* | |
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 function never writes beyond dest + maxOutputSize, and is therefore protected against malicious data packets | |
note : Destination buffer must be already allocated. | |
This version is slightly slower than LZ4_uncompress() | |
*/ | |
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() : | |
This function explicitly handles the CTX memory structure. | |
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. | |
*/ | |
#if defined (__cplusplus) | |
} | |
#endif |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/* | |
Tokyocabinet + LZ4 | |
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 | |
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 : | |
- Author homepage : http://maxpert.net.tc/ | |
*/ | |
#include <tcutil.h> | |
#include <tcbdb.h> | |
#include <stdio.h> | |
#include <stdlib.h> | |
#include <string.h> | |
#include <time.h> | |
#include <sys/timeb.h> | |
#include <sys/types.h> | |
#include <sys/stat.h> | |
#include "lz4.h" | |
/** | |
* CRC32 digest function | |
* Code taken from http://www.koders.com/c/fid699AFE0A656F0022C9D6B9D1743E697B69CE5815.aspx | |
*/ | |
u_int32_t crc_tab[256]; | |
void chksum_crc32gentab () | |
{ | |
unsigned long crc, poly; | |
int i, j; | |
poly = 0xEDB88320L; | |
for (i = 0; i < 256; i++) | |
{ | |
crc = i; | |
for (j = 8; j > 0; j--) | |
{ | |
if (crc & 1) | |
{ | |
crc = (crc >> 1) ^ poly; | |
} | |
else | |
{ | |
crc >>= 1; | |
} | |
} | |
crc_tab[i] = crc; | |
} | |
} | |
u_int32_t chksum_crc32(unsigned char *block, unsigned int length) | |
{ | |
register unsigned long crc; | |
unsigned long i; | |
crc = 0xFFFFFFFF; | |
for (i = 0; i < length; i++) | |
{ | |
crc = ((crc >> 8) & 0x00FFFFFF) ^ crc_tab[(crc ^ *block++) & 0xFF]; | |
} | |
return (crc ^ 0xFFFFFFFF); | |
} | |
struct compress_buffer_t { | |
void *buffer; | |
int curr_size; | |
int total_size; | |
}; | |
struct compress_buffer_t g_compressor = {NULL, 0, 0}; | |
void fast_compress(struct compress_buffer_t *out, const void *data, int szData) { | |
int expected_size = LZ4_compressBound(szData); | |
if( expected_size > out->total_size || out->buffer == NULL){ | |
if(out->buffer != NULL) free(out->buffer); | |
out->buffer = malloc(expected_size); | |
out->total_size = expected_size; | |
} | |
out->curr_size = LZ4_compress(data, out->buffer, szData); | |
} | |
bool put_in_db(TCBDB *db, const char *key, const void *data, int szData, bool compress){ | |
int szKey = strlen(key); | |
if(compress == true){ | |
fast_compress(&g_compressor, data, szData); | |
if( !g_compressor.curr_size ){ | |
fprintf(stderr, "Error compressing data"); | |
return false; | |
} | |
printf("\t\t\t\t\t\tCompressed size %d/%d\r", g_compressor.curr_size, szData); | |
return tcbdbput(db, key, szKey, g_compressor.buffer, g_compressor.curr_size); | |
} | |
return tcbdbput(db, key, szKey, data, szData); | |
} | |
static int get_millis() | |
{ | |
struct timeb tb; | |
int nCount; | |
ftime( &tb ); | |
nCount = tb.millitm + (tb.time & 0xfffff) * 1000; | |
return nCount; | |
} | |
char **Tweets = NULL; | |
int TotalTweets = 0; | |
void load_tweets(const char *pattern, int total){ | |
char *file_name = (char *) malloc(8*1024); | |
int i; | |
printf("loading...\n"); | |
Tweets = (char **)malloc(total * sizeof(char*)); | |
TotalTweets = total; | |
for(i=0; i<total; i++){ | |
FILE *fp; | |
sprintf(file_name, "%s%d", pattern, i); | |
fp = fopen(file_name, "r"); | |
Tweets[i] = (char *) malloc(8*1024); | |
if( fread(Tweets[i], 1, 8*1024, fp) != 0 ){ | |
printf("Loaded %s... %s \n", file_name, Tweets[i]); | |
} | |
} | |
free(file_name); | |
} | |
char *pick_tweet(){ | |
return Tweets[rand() % TotalTweets]; | |
} | |
int main(){ | |
TCBDB *db; | |
char *key, *val; | |
int ecode, i, total_time = 0, total_entries = 100000; | |
db = tcbdbnew(); | |
chksum_crc32gentab(); | |
srand ( time(NULL) ); | |
load_tweets("tweets/", 11); | |
/* open the database */ | |
if(!tcbdbopen(db, "dump.tcb", BDBOWRITER | BDBOCREAT)){ | |
ecode = tcbdbecode(db); | |
fprintf(stderr, "open error: %s\n", tcbdberrmsg(ecode)); | |
} | |
key = (char *)malloc(1024); | |
for( i=0; i<total_entries; i++){ | |
u_int32_t cs; | |
int rno = rand(); | |
int start_time; | |
sprintf(key, "%d-%08d-key", i, i); | |
cs = chksum_crc32(key, strlen(key)); | |
sprintf(key, "%08X-%08d-key", cs, i); | |
val = pick_tweet(); | |
start_time = get_millis(); | |
put_in_db(db, key, val, strlen(val), true); | |
total_time += get_millis() - start_time; | |
printf("Entries:%08d \t Time: %08d(ms)\r", i, total_time); | |
} | |
printf("Total time consumed for %d entries %d(ms)\t\t\t\t\n", total_entries, total_time); | |
tcbdbdel(db); | |
return 0; | |
} |
Compressed:
Total time consumed for 100000 entries 244250(ms)
File Size (dump.tcb): 197.5 MB (197,468,416 bytes)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uncompressed:
Total time consumed for 100000 entries 503514(ms)
File size (dump.tcb): 382.5 MB (382,522,880 bytes)