diff --git a/MANIFEST.in b/MANIFEST.in index 6be9b8f..07e5070 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,2 +1,4 @@ include README.rst include src/*.h +include tests/*.py +exclude tests/*.pyc diff --git a/setup.py b/setup.py index 328f7e1..d7e5aa8 100644 --- a/setup.py +++ b/setup.py @@ -2,10 +2,57 @@ from setuptools import setup, find_packages, Extension +import subprocess +import os VERSION = (0, 7, 0) VERSION_STR = ".".join([str(x) for x in VERSION]) +# Check to see if we have a lz4 library installed on the system and +# use it if so. If not, we'll use the bundled library. If lz4 is +# installed it will have a pkg-config file, so we'll use pkg-config to +# check for existence of the library. +pkg_config_exe = os.environ.get('PKG_CONFIG', None) or 'pkg-config' +cmd = '{0} --exists liblz4'.format(pkg_config_exe).split() +liblz4_found = subprocess.call(cmd) == 0 + +if liblz4_found: + # Use system lz4, and don't set optimization and warning flags for + # the compiler. Specifically we don't define LZ4_VERSION since the + # system lz4 library could be updated (that's the point of a + # shared library). + lz4mod = Extension('lz4', + [ + 'src/python-lz4.c' + ], + extra_compile_args=[ + "-std=c99", + "-DVERSION=\"%s\"" % VERSION_STR, + ], + libraries=['lz4'], + ) +else: + # Use the bundled lz4 libs, and set the compiler flags as they + # historically have been set. We do set LZ4_VERSION here, since it + # won't change after compilation. + lz4mod = Extension('lz4', + [ + 'src/lz4.c', + 'src/lz4hc.c', + 'src/python-lz4.c' + ], + extra_compile_args=[ + "-std=c99", + "-O3", + "-Wall", + "-W", + "-Wundef", + "-DVERSION=\"%s\"" % VERSION_STR, + "-DLZ4_VERSION=\"r130\"", + ] + ) + + setup( name='lz4', version=VERSION_STR, @@ -16,22 +63,8 @@ url='https://github.com/steeve/python-lz4', packages=find_packages('src'), package_dir={'': 'src'}, - ext_modules=[ - Extension('lz4', [ - 'src/lz4.c', - 'src/lz4hc.c', - 'src/python-lz4.c' - ], extra_compile_args=[ - "-std=c99", - "-O3", - "-Wall", - "-W", - "-Wundef", - "-DVERSION=\"%s\"" % VERSION_STR, - "-DLZ4_VERSION=\"r119\"", - ]) - ], - setup_requires=["nose>=1.0"], + ext_modules=[lz4mod,], + tests_require=["nose>=1.0"], test_suite = "nose.collector", classifiers=[ 'Development Status :: 5 - Production/Stable', diff --git a/src/lz4.c b/src/lz4.c index 482a8ed..08cf6b5 100644 --- a/src/lz4.c +++ b/src/lz4.c @@ -1,6 +1,7 @@ /* LZ4 - Fast LZ compression algorithm - Copyright (C) 2011-2014, Yann Collet. + Copyright (C) 2011-2015, 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 @@ -27,117 +28,68 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. You can contact the author at : - - LZ4 source repository : http://code.google.com/p/lz4/ + - LZ4 source repository : https://github.com/Cyan4973/lz4 - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c */ + /************************************** - Tuning parameters +* Tuning parameters **************************************/ /* * HEAPMODE : * Select how default compression functions will allocate memory for their hash table, - * in memory stack (0:default, fastest), or in memory heap (1:requires memory allocation (malloc)). + * in memory stack (0:default, fastest), or in memory heap (1:requires malloc()). */ #define HEAPMODE 0 - -/************************************** - CPU Feature Detection -**************************************/ -/* 32 or 64 bits ? */ -#if (defined(__x86_64__) || defined(_M_X64) || defined(_WIN64) \ - || defined(__powerpc64__) || defined(__powerpc64le__) \ - || defined(__ppc64__) || defined(__ppc64le__) \ - || defined(__PPC64__) || defined(__PPC64LE__) \ - || defined(__ia64) || defined(__itanium__) || defined(_M_IA64) ) /* Detects 64 bits mode */ -# define LZ4_ARCH64 1 -#else -# define LZ4_ARCH64 0 -#endif - /* - * Little Endian or Big Endian ? - * Overwrite the #define below if you know your architecture endianess + * ACCELERATION_DEFAULT : + * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0 */ -#include /* Apparently required to detect endianess */ -#if defined (__GLIBC__) -# include -# if (__BYTE_ORDER == __BIG_ENDIAN) -# define LZ4_BIG_ENDIAN 1 -# endif -#elif (defined(__BIG_ENDIAN__) || defined(__BIG_ENDIAN) || defined(_BIG_ENDIAN)) && !(defined(__LITTLE_ENDIAN__) || defined(__LITTLE_ENDIAN) || defined(_LITTLE_ENDIAN)) -# define LZ4_BIG_ENDIAN 1 -#elif defined(__sparc) || defined(__sparc__) \ - || defined(__powerpc__) || defined(__ppc__) || defined(__PPC__) \ - || defined(__hpux) || defined(__hppa) \ - || defined(_MIPSEB) || defined(__s390__) -# define LZ4_BIG_ENDIAN 1 -#else -/* Little Endian assumed. PDP Endian and other very rare endian format are unsupported. */ -#endif +#define ACCELERATION_DEFAULT 1 + +/************************************** +* CPU Feature Detection +**************************************/ /* - * Unaligned memory access is automatically enabled for "common" CPU, such as x86. - * For others CPU, such as ARM, the compiler may be more cautious, inserting unnecessary extra code to ensure aligned access property - * If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance + * LZ4_FORCE_SW_BITCOUNT + * Define this parameter if your target system or compiler does not support hardware bit count */ -#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 -/* - * BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE : - * This option may provide a small boost to performance for some big endian cpu, although probably modest. - * You may set this option to 1 if data will remain within closed environment. - * This option is useless on Little_Endian CPU (such as x86) - */ -/* #define BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE 1 */ +/************************************** +* Includes +**************************************/ +#include "lz4.h" /************************************** - Compiler Options +* Compiler Options **************************************/ -#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */ -/* "restrict" is a known keyword */ -#else -# define restrict /* Disable restrict */ -#endif - #ifdef _MSC_VER /* Visual Studio */ # define FORCE_INLINE static __forceinline -# include /* For Visual 2005 */ -# if LZ4_ARCH64 /* 64-bits */ -# pragma intrinsic(_BitScanForward64) /* For Visual 2005 */ -# pragma intrinsic(_BitScanReverse64) /* For Visual 2005 */ -# else /* 32-bits */ -# pragma intrinsic(_BitScanForward) /* For Visual 2005 */ -# pragma intrinsic(_BitScanReverse) /* For Visual 2005 */ -# endif +# include # pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ +# pragma warning(disable : 4293) /* disable: C4293: too large shift (32-bits) */ #else -# ifdef __GNUC__ -# define FORCE_INLINE static inline __attribute__((always_inline)) +# if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */ +# if defined(__GNUC__) || defined(__clang__) +# define FORCE_INLINE static inline __attribute__((always_inline)) +# else +# define FORCE_INLINE static inline +# endif # else -# define FORCE_INLINE static inline -# endif -#endif +# define FORCE_INLINE static +# endif /* __STDC_VERSION__ */ +#endif /* _MSC_VER */ -#ifdef _MSC_VER /* Visual Studio */ -# define lz4_bswap16(x) _byteswap_ushort(x) -#else -# define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8))) -#endif - -#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) - -#if (GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__) +/* LZ4_GCC_VERSION is defined into lz4.h */ +#if (LZ4_GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__) # define expect(expr,value) (__builtin_expect ((expr),(value)) ) #else # define expect(expr,value) (expr) @@ -148,7 +100,7 @@ /************************************** - Memory routines +* Memory routines **************************************/ #include /* malloc, calloc, free */ #define ALLOCATOR(n,s) calloc(n,s) @@ -158,13 +110,7 @@ /************************************** - Includes -**************************************/ -#include "lz4.h" - - -/************************************** - Basic Types +* Basic Types **************************************/ #if defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */ # include @@ -181,46 +127,95 @@ typedef unsigned long long U64; #endif -#if defined(__GNUC__) && !defined(LZ4_FORCE_UNALIGNED_ACCESS) -# define _PACKED __attribute__ ((packed)) -#else -# define _PACKED -#endif -#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__) -# if defined(__IBMC__) || defined(__SUNPRO_C) || defined(__SUNPRO_CC) -# pragma pack(1) -# else -# pragma pack(push, 1) -# endif -#endif +/************************************** +* Reading and writing into memory +**************************************/ +#define STEPSIZE sizeof(size_t) -typedef struct { U16 v; } _PACKED U16_S; -typedef struct { U32 v; } _PACKED U32_S; -typedef struct { U64 v; } _PACKED U64_S; -typedef struct {size_t v;} _PACKED size_t_S; +static unsigned LZ4_64bits(void) { return sizeof(void*)==8; } -#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__) -# if defined(__SUNPRO_C) || defined(__SUNPRO_CC) -# pragma pack(0) -# else -# pragma pack(pop) -# endif -#endif +static unsigned LZ4_isLittleEndian(void) +{ + const union { U32 i; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */ + return one.c[0]; +} + + +static U16 LZ4_read16(const void* memPtr) +{ + U16 val16; + memcpy(&val16, memPtr, 2); + return val16; +} -#define A16(x) (((U16_S *)(x))->v) -#define A32(x) (((U32_S *)(x))->v) -#define A64(x) (((U64_S *)(x))->v) -#define AARCH(x) (((size_t_S *)(x))->v) +static U16 LZ4_readLE16(const void* memPtr) +{ + if (LZ4_isLittleEndian()) + { + return LZ4_read16(memPtr); + } + else + { + const BYTE* p = (const BYTE*)memPtr; + return (U16)((U16)p[0] + (p[1]<<8)); + } +} + +static void LZ4_writeLE16(void* memPtr, U16 value) +{ + if (LZ4_isLittleEndian()) + { + memcpy(memPtr, &value, 2); + } + else + { + BYTE* p = (BYTE*)memPtr; + p[0] = (BYTE) value; + p[1] = (BYTE)(value>>8); + } +} + +static U32 LZ4_read32(const void* memPtr) +{ + U32 val32; + memcpy(&val32, memPtr, 4); + return val32; +} + +static U64 LZ4_read64(const void* memPtr) +{ + U64 val64; + memcpy(&val64, memPtr, 8); + return val64; +} + +static size_t LZ4_read_ARCH(const void* p) +{ + if (LZ4_64bits()) + return (size_t)LZ4_read64(p); + else + return (size_t)LZ4_read32(p); +} + + +static void LZ4_copy4(void* dstPtr, const void* srcPtr) { memcpy(dstPtr, srcPtr, 4); } + +static void LZ4_copy8(void* dstPtr, const void* srcPtr) { memcpy(dstPtr, srcPtr, 8); } + +/* customized version of memcpy, which may overwrite up to 7 bytes beyond dstEnd */ +static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd) +{ + BYTE* d = (BYTE*)dstPtr; + const BYTE* s = (const BYTE*)srcPtr; + BYTE* e = (BYTE*)dstEnd; + do { LZ4_copy8(d,s); d+=8; s+=8; } while (d>3); +# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_ctzll((U64)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 & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58]; +# endif + } + else /* 32 bits */ + { +# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r; + _BitScanForward( &r, (U32)val ); + return (int)(r>>3); +# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_ctz((U32)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 + } + } + else /* Big Endian CPU */ + { + if (LZ4_64bits()) + { +# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r = 0; + _BitScanReverse64( &r, val ); + return (unsigned)(r>>3); +# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_clzll((U64)val) >> 3); +# else + unsigned 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 /* 32 bits */ + { +# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r = 0; + _BitScanReverse( &r, (unsigned long)val ); + return (unsigned)(r>>3); +# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_clz((U32)val) >> 3); +# else + unsigned r; + if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } + r += (!val); + return r; +# endif + } + } +} -typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; -typedef enum { full = 0, partial = 1 } earlyEnd_directive; +static unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit) +{ + const BYTE* const pStart = pIn; + + while (likely(pIn compression run slower on incompressible data */ /************************************** - Macros +* Local Structures and types **************************************/ -#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(!!(c)) }; } /* use only *after* variable declarations */ -#if LZ4_ARCH64 || !defined(__GNUC__) -# define LZ4_WILDCOPY(d,s,e) { do { LZ4_COPY8(d,s) } while (d=e; */ -#else -# define LZ4_WILDCOPY(d,s,e) { if (likely(e-d <= 8)) LZ4_COPY8(d,s) else do { LZ4_COPY8(d,s) } while (d>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 & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58]; -# endif -# endif -} +typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; +typedef enum { full = 0, partial = 1 } earlyEnd_directive; -#else -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; - _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 -} +/************************************** +* Local Utils +**************************************/ +int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; } +int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } +int LZ4_sizeofState() { return LZ4_STREAMSIZE; } -#endif /******************************** - Compression functions +* Compression functions ********************************/ -int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } -static int LZ4_hashSequence(U32 sequence, tableType_t tableType) +static U32 LZ4_hashSequence(U32 sequence, tableType_t const tableType) { if (tableType == byU16) return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1))); @@ -375,15 +386,30 @@ static int LZ4_hashSequence(U32 sequence, tableType_t tableType) return (((sequence) * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG)); } -static int LZ4_hashPosition(const BYTE* p, tableType_t tableType) { return LZ4_hashSequence(A32(p), tableType); } +static const U64 prime5bytes = 889523592379ULL; +static U32 LZ4_hashSequence64(size_t sequence, tableType_t const tableType) +{ + const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG; + const U32 hashMask = (1<> (40 - hashLog)) & hashMask; +} + +static U32 LZ4_hashSequenceT(size_t sequence, tableType_t const tableType) +{ + if (LZ4_64bits()) + return LZ4_hashSequence64(sequence, tableType); + return LZ4_hashSequence((U32)sequence, tableType); +} + +static U32 LZ4_hashPosition(const void* p, tableType_t tableType) { return LZ4_hashSequenceT(LZ4_read_ARCH(p), tableType); } -static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) +static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase) { switch (tableType) { - case byPtr: { const BYTE** hashTable = (const BYTE**) tableBase; hashTable[h] = p; break; } - case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); break; } - case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); break; } + case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = p; return; } + case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); return; } + case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); return; } } } @@ -406,36 +432,17 @@ static const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t t return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase); } -static unsigned LZ4_count(const BYTE* pIn, const BYTE* pRef, const BYTE* pInLimit) -{ - const BYTE* const pStart = pIn; - - while (likely(pIn (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size, too large (or negative) */ + if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size, too large (or negative) */ switch(dict) { case noDict: @@ -476,8 +482,8 @@ static int LZ4_compress_generic( lowLimit = (const BYTE*)source; break; } - if ((tableType == byU16) && (inputSize>=(int)LZ4_64KLIMIT)) return 0; /* Size too large (not within 64K limit) */ - if (inputSize=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */ + if (inputSize> skipStrength; - //if (step>8) step=8; // required for valid forwardIp ; slows down uncompressible data a bit + step = (searchMatchNb++ >> LZ4_skipTrigger); if (unlikely(forwardIp > mflimit)) goto _last_literals; - ref = LZ4_getPositionOnHash(h, ctx, tableType, base); + match = LZ4_getPositionOnHash(h, ctx, tableType, base); if (dict==usingExtDict) { - if (ref<(const BYTE*)source) + if (match<(const BYTE*)source) { refDelta = dictDelta; lowLimit = dictionary; @@ -520,13 +525,13 @@ static int LZ4_compress_generic( forwardH = LZ4_hashPosition(forwardIp, tableType); LZ4_putPositionOnHash(ip, h, ctx, tableType, base); - } while ( ((dictIssue==dictSmall) ? (ref < lowRefLimit) : 0) - || ((tableType==byU16) ? 0 : (ref + MAX_DISTANCE < ip)) - || (A32(ref+refDelta) != A32(ip)) ); + } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0) + || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip)) + || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) ); } /* Catch up */ - while ((ip>anchor) && (ref+refDelta > lowLimit) && (unlikely(ip[-1]==ref[refDelta-1]))) { ip--; ref--; } + while ((ip>anchor) && (match+refDelta > lowLimit) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; } { /* Encode Literal length */ @@ -544,12 +549,13 @@ static int LZ4_compress_generic( else *token = (BYTE)(litLength< matchlimit) limit = matchlimit; - matchLength = LZ4_count(ip+MINMATCH, ref+MINMATCH, limit); + matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, limit); ip += MINMATCH + matchLength; if (ip==limit) { @@ -572,14 +578,14 @@ static int LZ4_compress_generic( } else { - matchLength = LZ4_count(ip+MINMATCH, ref+MINMATCH, matchlimit); + matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit); ip += MINMATCH + matchLength; } + if ((outputLimited) && (unlikely(op + (1 + LASTLITERALS) + (matchLength>>8) > olimit))) + return 0; /* Check output limit */ if (matchLength>=ML_MASK) { - if ((outputLimited) && (unlikely(op + (1 + LASTLITERALS) + (matchLength>>8) > olimit))) - return 0; /* Check output limit */ *token += ML_MASK; matchLength -= ML_MASK; for (; matchLength >= 510 ; matchLength-=510) { *op++ = 255; *op++ = 255; } @@ -598,10 +604,10 @@ static int LZ4_compress_generic( LZ4_putPosition(ip-2, ctx, tableType, base); /* Test next position */ - ref = LZ4_getPosition(ip, ctx, tableType, base); + match = LZ4_getPosition(ip, ctx, tableType, base); if (dict==usingExtDict) { - if (ref<(const BYTE*)source) + if (match<(const BYTE*)source) { refDelta = dictDelta; lowLimit = dictionary; @@ -613,9 +619,9 @@ static int LZ4_compress_generic( } } LZ4_putPosition(ip, ctx, tableType, base); - if ( ((dictIssue==dictSmall) ? (ref>=lowRefLimit) : 1) - && (ref+MAX_DISTANCE>=ip) - && (A32(ref+refDelta)==A32(ip)) ) + if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1) + && (match+MAX_DISTANCE>=ip) + && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) ) { token=op++; *token=0; goto _next_match; } /* Prepare next loop */ @@ -625,13 +631,22 @@ static int LZ4_compress_generic( _last_literals: /* Encode Last Literals */ { - int lastRun = (int)(iend - anchor); - if ((outputLimited) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize)) + const size_t lastRun = (size_t)(iend - anchor); + if ((outputLimited) && ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize)) return 0; /* Check output limit */ - if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<= 255 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; } - else *op++ = (BYTE)(lastRun<= RUN_MASK) + { + size_t accumulator = lastRun - RUN_MASK; + *op++ = RUN_MASK << ML_BITS; + for(; accumulator >= 255 ; accumulator-=255) *op++ = 255; + *op++ = (BYTE) accumulator; + } + else + { + *op++ = (BYTE)(lastRun<= LZ4_compressBound(inputSize)) + { + if (inputSize < LZ4_64Klimit) + return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue, acceleration); + else + return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration); + } + else + { + if (inputSize < LZ4_64Klimit) + return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); + else + return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration); + } +} + + +int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) { #if (HEAPMODE) - void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U32, 4); /* Aligned on 4-bytes boundaries */ + void* ctxPtr = ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ #else - U32 ctx[LZ4_STREAMSIZE_U32] = {0}; /* Ensure data is aligned on 4-bytes boundaries */ + LZ4_stream_t ctx; + void* ctxPtr = &ctx; #endif - int result; - if (inputSize < (int)LZ4_64KLIMIT) - result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue); - else - result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue); + int result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration); #if (HEAPMODE) - FREEMEM(ctx); + FREEMEM(ctxPtr); #endif return result; } -int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) + +int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxOutputSize) +{ + return LZ4_compress_fast(source, dest, inputSize, maxOutputSize, 1); +} + + +/* hidden debug function */ +/* strangely enough, gcc generates faster code when this function is uncommented, even if unused */ +int LZ4_compress_fast_force(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) +{ + LZ4_stream_t ctx; + + LZ4_resetStream(&ctx); + + if (inputSize < LZ4_64Klimit) + return LZ4_compress_generic(&ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); + else + return LZ4_compress_generic(&ctx, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration); +} + + +/******************************** +* destSize variant +********************************/ + +static int LZ4_compress_destSize_generic( + void* const ctx, + const char* const src, + char* const dst, + int* const srcSizePtr, + const int targetDstSize, + const tableType_t tableType) +{ + const BYTE* ip = (const BYTE*) src; + const BYTE* base = (const BYTE*) src; + const BYTE* lowLimit = (const BYTE*) src; + const BYTE* anchor = ip; + const BYTE* const iend = ip + *srcSizePtr; + const BYTE* const mflimit = iend - MFLIMIT; + const BYTE* const matchlimit = iend - LASTLITERALS; + + BYTE* op = (BYTE*) dst; + BYTE* const oend = op + targetDstSize; + BYTE* const oMaxLit = op + targetDstSize - 2 /* offset */ - 8 /* because 8+MINMATCH==MFLIMIT */ - 1 /* token */; + BYTE* const oMaxMatch = op + targetDstSize - (LASTLITERALS + 1 /* token */); + BYTE* const oMaxSeq = oMaxLit - 1 /* token */; + + U32 forwardH; + + + /* Init conditions */ + if (targetDstSize < 1) return 0; /* Impossible to store anything */ + if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size, too large (or negative) */ + if ((tableType == byU16) && (*srcSizePtr>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */ + if (*srcSizePtr> LZ4_skipTrigger); + + if (unlikely(forwardIp > mflimit)) + goto _last_literals; + + match = LZ4_getPositionOnHash(h, ctx, tableType, base); + forwardH = LZ4_hashPosition(forwardIp, tableType); + LZ4_putPositionOnHash(ip, h, ctx, tableType, base); + + } while ( ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip)) + || (LZ4_read32(match) != LZ4_read32(ip)) ); + } + + /* Catch up */ + while ((ip>anchor) && (match > lowLimit) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; } + + { + /* Encode Literal length */ + unsigned litLength = (unsigned)(ip - anchor); + token = op++; + if (op + ((litLength+240)/255) + litLength > oMaxLit) + { + /* Not enough space for a last match */ + op--; + goto _last_literals; + } + if (litLength>=RUN_MASK) + { + unsigned len = litLength - RUN_MASK; + *token=(RUN_MASK<= 255 ; len-=255) *op++ = 255; + *op++ = (BYTE)len; + } + else *token = (BYTE)(litLength< oMaxMatch) + { + /* Match description too long : reduce it */ + matchLength = (15-1) + (oMaxMatch-op) * 255; + } + //printf("offset %5i, matchLength%5i \n", (int)(ip-match), matchLength + MINMATCH); + ip += MINMATCH + matchLength; + + if (matchLength>=ML_MASK) + { + *token += ML_MASK; + matchLength -= ML_MASK; + while (matchLength >= 255) { matchLength-=255; *op++ = 255; } + *op++ = (BYTE)matchLength; + } + else *token += (BYTE)(matchLength); + } + + anchor = ip; + + /* Test end of block */ + if (ip > mflimit) break; + if (op > oMaxSeq) break; + + /* Fill table */ + LZ4_putPosition(ip-2, ctx, tableType, base); + + /* Test next position */ + match = LZ4_getPosition(ip, ctx, tableType, base); + LZ4_putPosition(ip, ctx, tableType, base); + if ( (match+MAX_DISTANCE>=ip) + && (LZ4_read32(match)==LZ4_read32(ip)) ) + { token=op++; *token=0; goto _next_match; } + + /* Prepare next loop */ + forwardH = LZ4_hashPosition(++ip, tableType); + } + +_last_literals: + /* Encode Last Literals */ + { + size_t lastRunSize = (size_t)(iend - anchor); + if (op + 1 /* token */ + ((lastRunSize+240)/255) /* litLength */ + lastRunSize /* literals */ > oend) + { + /* adapt lastRunSize to fill 'dst' */ + lastRunSize = (oend-op) - 1; + lastRunSize -= (lastRunSize+240)/255; + } + ip = anchor + lastRunSize; + + if (lastRunSize >= RUN_MASK) + { + size_t accumulator = lastRunSize - RUN_MASK; + *op++ = RUN_MASK << ML_BITS; + for(; accumulator >= 255 ; accumulator-=255) *op++ = 255; + *op++ = (BYTE) accumulator; + } + else + { + *op++ = (BYTE)(lastRunSize<= LZ4_compressBound(*srcSizePtr)) /* compression success is guaranteed */ + { + return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1); + } + else + { + if (*srcSizePtr < LZ4_64Klimit) + return LZ4_compress_destSize_generic(state, src, dst, srcSizePtr, targetDstSize, byU16); + else + return LZ4_compress_destSize_generic(state, src, dst, srcSizePtr, targetDstSize, LZ4_64bits() ? byU32 : byPtr); + } +} + + +int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize) { #if (HEAPMODE) - void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U32, 4); /* Aligned on 4-bytes boundaries */ + void* ctx = ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ #else - U32 ctx[LZ4_STREAMSIZE_U32] = {0}; /* Ensure data is aligned on 4-bytes boundaries */ + LZ4_stream_t ctxBody; + void* ctx = &ctxBody; #endif - int result; - if (inputSize < (int)LZ4_64KLIMIT) - result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue); - else - result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limitedOutput, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue); + int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize); #if (HEAPMODE) FREEMEM(ctx); @@ -680,58 +927,67 @@ int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, in } -/***************************************** - Experimental : Streaming functions -*****************************************/ -void* LZ4_createStream() +/******************************** +* Streaming functions +********************************/ + +LZ4_stream_t* LZ4_createStream(void) { - void* lz4s = ALLOCATOR(4, LZ4_STREAMSIZE_U32); - MEM_INIT(lz4s, 0, LZ4_STREAMSIZE); + LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(8, LZ4_STREAMSIZE_U64); + LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal)); /* A compilation error here means LZ4_STREAMSIZE is not large enough */ + LZ4_resetStream(lz4s); return lz4s; } -int LZ4_free (void* LZ4_stream) +void LZ4_resetStream (LZ4_stream_t* LZ4_stream) +{ + MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t)); +} + +int LZ4_freeStream (LZ4_stream_t* LZ4_stream) { FREEMEM(LZ4_stream); return (0); } -int LZ4_loadDict (void* LZ4_dict, const char* dictionary, int dictSize) +#define HASH_UNIT sizeof(size_t) +int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) { LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict; const BYTE* p = (const BYTE*)dictionary; const BYTE* const dictEnd = p + dictSize; const BYTE* base; - LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal)); /* A compilation error here means LZ4_STREAMSIZE is not large enough */ - if (dict->initCheck) MEM_INIT(dict, 0, sizeof(LZ4_stream_t_internal)); /* Uninitialized structure detected */ + if ((dict->initCheck) || (dict->currentOffset > 1 GB)) /* Uninitialized structure, or reuse overflow */ + LZ4_resetStream(LZ4_dict); - if (dictSize < MINMATCH) + if (dictSize < (int)HASH_UNIT) { dict->dictionary = NULL; dict->dictSize = 0; - return 1; + return 0; } - if (p <= dictEnd - 64 KB) p = dictEnd - 64 KB; + if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB; + dict->currentOffset += 64 KB; base = p - dict->currentOffset; dict->dictionary = p; dict->dictSize = (U32)(dictEnd - p); dict->currentOffset += dict->dictSize; - while (p <= dictEnd-MINMATCH) + while (p <= dictEnd-HASH_UNIT) { - LZ4_putPosition(p, dict, byU32, base); + LZ4_putPosition(p, dict->hashTable, byU32, base); p+=3; } - return 1; + return dict->dictSize; } -void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src) +static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src) { if ((LZ4_dict->currentOffset > 0x80000000) || ((size_t)LZ4_dict->currentOffset > (size_t)src)) /* address space overflow */ @@ -752,8 +1008,7 @@ void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src) } -FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* source, char* dest, int inputSize, - int maxOutputSize, limitedOutput_directive limit) +int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) { LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_stream; const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; @@ -762,6 +1017,7 @@ FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* so if (streamPtr->initCheck) return 0; /* Uninitialized structure detected */ if ((streamPtr->dictSize>0) && (smallest>dictEnd)) smallest = dictEnd; LZ4_renormDictT(streamPtr, smallest); + if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; /* Check overlapping input/dictionary space */ { @@ -780,9 +1036,9 @@ FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* so { int result; if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) - result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, withPrefix64k, dictSmall); + result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration); else - result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, withPrefix64k, noDictIssue); + result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration); streamPtr->dictSize += (U32)inputSize; streamPtr->currentOffset += (U32)inputSize; return result; @@ -792,9 +1048,9 @@ FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* so { int result; if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) - result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, usingExtDict, dictSmall); + result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration); else - result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, usingExtDict, noDictIssue); + result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration); streamPtr->dictionary = (const BYTE*)source; streamPtr->dictSize = (U32)inputSize; streamPtr->currentOffset += (U32)inputSize; @@ -803,18 +1059,7 @@ FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* so } -int LZ4_compress_continue (void* LZ4_stream, const char* source, char* dest, int inputSize) -{ - return LZ4_compress_continue_generic(LZ4_stream, source, dest, inputSize, 0, notLimited); -} - -int LZ4_compress_limitedOutput_continue (void* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize) -{ - return LZ4_compress_continue_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput); -} - - -// Hidden debug function, to force separate dictionary mode +/* Hidden debug function, to force external dictionary mode */ int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize) { LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_dict; @@ -825,7 +1070,7 @@ int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* if (smallest > (const BYTE*) source) smallest = (const BYTE*) source; LZ4_renormDictT((LZ4_stream_t_internal*)LZ4_dict, smallest); - result = LZ4_compress_generic(LZ4_dict, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue); + result = LZ4_compress_generic(LZ4_dict, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1); streamPtr->dictionary = (const BYTE*)source; streamPtr->dictSize = (U32)inputSize; @@ -835,7 +1080,7 @@ int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* } -int LZ4_saveDict (void* LZ4_dict, char* safeBuffer, int dictSize) +int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize) { LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict; const BYTE* previousDictEnd = dict->dictionary + dict->dictSize; @@ -843,28 +1088,28 @@ int LZ4_saveDict (void* LZ4_dict, char* safeBuffer, int dictSize) if ((U32)dictSize > 64 KB) dictSize = 64 KB; /* useless to define a dictionary > 64 KB */ if ((U32)dictSize > dict->dictSize) dictSize = dict->dictSize; - memcpy(safeBuffer, previousDictEnd - dictSize, dictSize); + memmove(safeBuffer, previousDictEnd - dictSize, dictSize); dict->dictionary = (const BYTE*)safeBuffer; dict->dictSize = (U32)dictSize; - return 1; + return dictSize; } -/**************************** - Decompression functions -****************************/ +/******************************* +* Decompression functions +*******************************/ /* * This generic decompression function cover all use cases. - * It shall be instanciated several times, using different sets of directives + * It shall be instantiated several times, using different sets of directives * Note that it is essential this generic function is really inlined, - * in order to remove useless branches during compilation optimisation. + * in order to remove useless branches during compilation optimization. */ FORCE_INLINE int LZ4_decompress_generic( - const char* source, - char* dest, + const char* const source, + char* const dest, int inputSize, int outputSize, /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */ @@ -872,36 +1117,32 @@ FORCE_INLINE int LZ4_decompress_generic( int partialDecoding, /* full, partial */ int targetOutputSize, /* only used if partialDecoding==partial */ int dict, /* noDict, withPrefix64k, usingExtDict */ - const char* dictStart, /* only if dict==usingExtDict */ - int dictSize /* note : = 0 if noDict */ + const BYTE* const lowPrefix, /* == dest if dict == noDict */ + const BYTE* const dictStart, /* only if dict==usingExtDict */ + const size_t dictSize /* note : = 0 if noDict */ ) { /* Local Variables */ - const BYTE* restrict ip = (const BYTE*) source; - const BYTE* ref; + const BYTE* ip = (const BYTE*) source; const BYTE* const iend = ip + inputSize; BYTE* op = (BYTE*) dest; BYTE* const oend = op + outputSize; BYTE* cpy; BYTE* oexit = op + targetOutputSize; - const BYTE* const lowLimit = (const BYTE*)dest - dictSize; + const BYTE* const lowLimit = lowPrefix - dictSize; const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize; -//#define OLD -#ifdef OLD - const size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0}; /* static reduces speed for LZ4_decompress_safe() on GCC64 */ -#else - const size_t dec32table[] = {4-0, 4-3, 4-2, 4-3, 4-0, 4-0, 4-0, 4-0}; /* static reduces speed for LZ4_decompress_safe() on GCC64 */ -#endif - static const size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3}; + const size_t dec32table[] = {4, 1, 2, 1, 4, 4, 4, 4}; + const size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3}; - const int checkOffset = (endOnInput) && (dictSize < (int)(64 KB)); + const int safeDecode = (endOnInput==endOnInputSize); + const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB))); /* Special cases */ - if ((partialDecoding) && (oexit> oend-MFLIMIT)) oexit = oend-MFLIMIT; /* targetOutputSize too high => decode everything */ - if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */ + if ((partialDecoding) && (oexit> oend-MFLIMIT)) oexit = oend-MFLIMIT; /* targetOutputSize too high => decode everything */ + if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */ if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1); @@ -910,8 +1151,9 @@ FORCE_INLINE int LZ4_decompress_generic( { unsigned token; size_t length; + const BYTE* match; - /* get runlength */ + /* get literal length */ token = *ip++; if ((length=(token>>ML_BITS)) == RUN_MASK) { @@ -922,9 +1164,8 @@ FORCE_INLINE int LZ4_decompress_generic( length += s; } while (likely((endOnInput)?ipLZ4_MAX_INPUT_SIZE)) goto _output_error; /* overflow detection */ - if ((sizeof(void*)==4) && unlikely((size_t)(op+length)<(size_t)(op))) goto _output_error; /* quickfix issue 134 */ - if ((endOnInput) && (sizeof(void*)==4) && unlikely((size_t)(ip+length)<(size_t)(ip))) goto _output_error; /* quickfix issue 134 */ + if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)(op))) goto _output_error; /* overflow detection */ + if ((safeDecode) && unlikely((size_t)(ip+length)<(size_t)(ip))) goto _output_error; /* overflow detection */ } /* copy literals */ @@ -945,16 +1186,18 @@ FORCE_INLINE int LZ4_decompress_generic( memcpy(op, ip, length); ip += length; op += length; - break; /* Necessarily EOF, due to parsing restrictions */ + break; /* Necessarily EOF, due to parsing restrictions */ } - LZ4_WILDCOPY(op, ip, cpy); ip -= (op-cpy); op = cpy; + LZ4_wildCopy(op, ip, cpy); + ip += length; op = cpy; /* get offset */ - LZ4_READ_LITTLEENDIAN_16(ref,cpy,ip); ip+=2; - if ((checkOffset) && (unlikely(ref < lowLimit))) goto _output_error; /* Error : offset outside destination buffer */ + match = cpy - LZ4_readLE16(ip); ip+=2; + if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error; /* Error : offset outside destination buffer */ /* get matchlength */ - if ((length=(token&ML_MASK)) == ML_MASK) + length = token & ML_MASK; + if (length == ML_MASK) { unsigned s; do @@ -963,36 +1206,37 @@ FORCE_INLINE int LZ4_decompress_generic( s = *ip++; length += s; } while (s==255); - //if ((sizeof(void*)==4) && unlikely(length>LZ4_MAX_INPUT_SIZE)) goto _output_error; /* overflow detection */ - if ((sizeof(void*)==4) && unlikely((size_t)(op+length)<(size_t)op)) goto _output_error; /* quickfix issue 134 */ + if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)op)) goto _output_error; /* overflow detection */ } + length += MINMATCH; /* check external dictionary */ - if ((dict==usingExtDict) && (ref < (BYTE* const)dest)) + if ((dict==usingExtDict) && (match < lowPrefix)) { - if (unlikely(op+length+MINMATCH > oend-LASTLITERALS)) goto _output_error; + if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error; /* doesn't respect parsing restriction */ - if (length+MINMATCH <= (size_t)(dest-(char*)ref)) + if (length <= (size_t)(lowPrefix-match)) { - ref = dictEnd - (dest-(char*)ref); - memcpy(op, ref, length+MINMATCH); - op += length+MINMATCH; + /* match can be copied as a single segment from external dictionary */ + match = dictEnd - (lowPrefix-match); + memmove(op, match, length); op += length; } else { - size_t copySize = (size_t)(dest-(char*)ref); + /* match encompass external dictionary and current segment */ + size_t copySize = (size_t)(lowPrefix-match); memcpy(op, dictEnd - copySize, copySize); op += copySize; - copySize = length+MINMATCH - copySize; - if (copySize > (size_t)((char*)op-dest)) /* overlap */ + copySize = length - copySize; + if (copySize > (size_t)(op-lowPrefix)) /* overlap within current segment */ { - BYTE* const cpy = op + copySize; - const BYTE* ref = (BYTE*)dest; - while (op < cpy) *op++ = *ref++; + BYTE* const endOfMatch = op + copySize; + const BYTE* copyFrom = lowPrefix; + while (op < endOfMatch) *op++ = *copyFrom++; } else { - memcpy(op, dest, copySize); + memcpy(op, lowPrefix, copySize); op += copySize; } } @@ -1000,34 +1244,32 @@ FORCE_INLINE int LZ4_decompress_generic( } /* copy repeated sequence */ - if (unlikely((op-ref)<(int)STEPSIZE)) + cpy = op + length; + if (unlikely((op-match)<8)) { - const size_t dec64 = dec64table[(sizeof(void*)==4) ? 0 : op-ref]; - op[0] = ref[0]; - op[1] = ref[1]; - op[2] = ref[2]; - op[3] = ref[3]; -#ifdef OLD - op += 4, ref += 4; ref -= dec32table[op-ref]; - A32(op) = A32(ref); - op += STEPSIZE-4; ref -= dec64; -#else - ref += dec32table[op-ref]; - A32(op+4) = A32(ref); - op += STEPSIZE; ref -= dec64; -#endif - } else { LZ4_COPYSTEP(op,ref); } - cpy = op + length - (STEPSIZE-4); - - if (unlikely(cpy>oend-COPYLENGTH-(STEPSIZE-4))) + const size_t dec64 = dec64table[op-match]; + op[0] = match[0]; + op[1] = match[1]; + op[2] = match[2]; + op[3] = match[3]; + match += dec32table[op-match]; + LZ4_copy4(op+4, match); + op += 8; match -= dec64; + } else { LZ4_copy8(op, match); op+=8; match+=8; } + + if (unlikely(cpy>oend-12)) { - if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last 5 bytes must be literals */ - if (op oend-LASTLITERALS) goto _output_error; /* Error : last LASTLITERALS bytes must be literals */ + if (op < oend-8) + { + LZ4_wildCopy(op, match, oend-8); + match += (oend-8) - op; + op = oend-8; + } + while (opdictionary = dictionary; - lz4sd->dictSize = dictSize; + lz4sd->prefixSize = (size_t) dictSize; + lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize; + lz4sd->externalDict = NULL; + lz4sd->extDictSize = 0; return 1; } @@ -1101,43 +1350,61 @@ int LZ4_setDictDecode (void* LZ4_streamDecode, const char* dictionary, int dictS These decoding functions allow decompression of multiple blocks in "streaming" mode. Previously decoded blocks must still be available at the memory position where they were decoded. If it's not possible, save the relevant part of decoded data into a safe buffer, - and indicate where it stands using LZ4_setDictDecode() + and indicate where it stands using LZ4_setStreamDecode() */ -int LZ4_decompress_safe_continue (void* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize) +int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize) { LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode; int result; - result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, lz4sd->dictionary, lz4sd->dictSize); - if (result <= 0) return result; - if (lz4sd->dictionary + lz4sd->dictSize == dest) + if (lz4sd->prefixEnd == (BYTE*)dest) { - lz4sd->dictSize += result; + result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + endOnInputSize, full, 0, + usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize += result; + lz4sd->prefixEnd += result; } else { - lz4sd->dictionary = dest; - lz4sd->dictSize = result; + lz4sd->extDictSize = lz4sd->prefixSize; + lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; + result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + endOnInputSize, full, 0, + usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize = result; + lz4sd->prefixEnd = (BYTE*)dest + result; } return result; } -int LZ4_decompress_fast_continue (void* LZ4_streamDecode, const char* source, char* dest, int originalSize) +int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize) { LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode; int result; - result = LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, usingExtDict, lz4sd->dictionary, lz4sd->dictSize); - if (result <= 0) return result; - if (lz4sd->dictionary + lz4sd->dictSize == dest) + if (lz4sd->prefixEnd == (BYTE*)dest) { - lz4sd->dictSize += result; + result = LZ4_decompress_generic(source, dest, 0, originalSize, + endOnOutputSize, full, 0, + usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize += originalSize; + lz4sd->prefixEnd += originalSize; } else { - lz4sd->dictionary = dest; - lz4sd->dictSize = result; + lz4sd->extDictSize = lz4sd->prefixSize; + lz4sd->externalDict = (BYTE*)dest - lz4sd->extDictSize; + result = LZ4_decompress_generic(source, dest, 0, originalSize, + endOnOutputSize, full, 0, + usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize = originalSize; + lz4sd->prefixEnd = (BYTE*)dest + originalSize; } return result; @@ -1151,20 +1418,47 @@ Advanced decoding functions : the dictionary must be explicitly provided within parameters */ +FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest, int compressedSize, int maxOutputSize, int safe, const char* dictStart, int dictSize) +{ + if (dictSize==0) + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest, NULL, 0); + if (dictStart+dictSize == dest) + { + if (dictSize >= (int)(64 KB - 1)) + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, withPrefix64k, (BYTE*)dest-64 KB, NULL, 0); + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest-dictSize, NULL, 0); + } + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize); +} + int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize) { - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, dictStart, dictSize); + return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize); } int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize) { - return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, usingExtDict, dictStart, dictSize); + return LZ4_decompress_usingDict_generic(source, dest, 0, originalSize, 0, dictStart, dictSize); +} + +/* debug function */ +int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize) +{ + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize); } /*************************************************** - Obsolete Functions +* Obsolete Functions ***************************************************/ +/* obsolete compression functions */ +int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) { return LZ4_compress_default(source, dest, inputSize, maxOutputSize); } +int LZ4_compress(const char* source, char* dest, int inputSize) { return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize)); } +int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1); } +int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1); } +int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, maxDstSize, 1); } +int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) { return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); } + /* These function names are deprecated and should no longer be used. They are only provided here for compatibility with older user programs. @@ -1179,69 +1473,44 @@ int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; } -void LZ4_init(LZ4_stream_t_internal* lz4ds, const BYTE* base) +static void LZ4_init(LZ4_stream_t_internal* lz4ds, BYTE* base) { MEM_INIT(lz4ds, 0, LZ4_STREAMSIZE); lz4ds->bufferStart = base; } -int LZ4_resetStreamState(void* state, const char* inputBuffer) +int LZ4_resetStreamState(void* state, char* inputBuffer) { if ((((size_t)state) & 3) != 0) return 1; /* Error : pointer is not aligned on 4-bytes boundary */ - LZ4_init((LZ4_stream_t_internal*)state, (const BYTE*)inputBuffer); + LZ4_init((LZ4_stream_t_internal*)state, (BYTE*)inputBuffer); return 0; } -void* LZ4_create (const char* inputBuffer) +void* LZ4_create (char* inputBuffer) { - void* lz4ds = ALLOCATOR(4, LZ4_STREAMSIZE_U32); - LZ4_init ((LZ4_stream_t_internal*)lz4ds, (const BYTE*)inputBuffer); + void* lz4ds = ALLOCATOR(8, LZ4_STREAMSIZE_U64); + LZ4_init ((LZ4_stream_t_internal*)lz4ds, (BYTE*)inputBuffer); return lz4ds; } char* LZ4_slideInputBuffer (void* LZ4_Data) { - LZ4_stream_t_internal* lz4ds = (LZ4_stream_t_internal*)LZ4_Data; - - LZ4_saveDict((LZ4_stream_t*)LZ4_Data, (char*)lz4ds->bufferStart, 64 KB); - - return (char*)(lz4ds->bufferStart + 64 KB); -} - -/* Obsolete compresson functions using User-allocated state */ - -int LZ4_sizeofState() { return LZ4_STREAMSIZE; } - -int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize) -{ - if (((size_t)(state)&3) != 0) return 0; /* Error : state is not aligned on 4-bytes boundary */ - MEM_INIT(state, 0, LZ4_STREAMSIZE); - - if (inputSize < (int)LZ4_64KLIMIT) - return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue); - else - return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue); -} - -int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize) -{ - if (((size_t)(state)&3) != 0) return 0; /* Error : state is not aligned on 4-bytes boundary */ - MEM_INIT(state, 0, LZ4_STREAMSIZE); - - if (inputSize < (int)LZ4_64KLIMIT) - return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue); - else - return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue); + LZ4_stream_t_internal* ctx = (LZ4_stream_t_internal*)LZ4_Data; + int dictSize = LZ4_saveDict((LZ4_stream_t*)LZ4_Data, (char*)ctx->bufferStart, 64 KB); + return (char*)(ctx->bufferStart + dictSize); } /* Obsolete streaming decompression functions */ int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize) { - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, withPrefix64k, NULL, 64 KB); + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB); } int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize) { - return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, NULL, 64 KB); + return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB); } + +#endif /* LZ4_COMMONDEFS_ONLY */ + diff --git a/src/lz4.h b/src/lz4.h index 1064fa1..99c6ebb 100644 --- a/src/lz4.h +++ b/src/lz4.h @@ -1,7 +1,8 @@ /* LZ4 - Fast LZ compression algorithm Header File - Copyright (C) 2011-2014, Yann Collet. + Copyright (C) 2011-2015, 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 @@ -28,7 +29,7 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. You can contact the author at : - - LZ4 source repository : http://code.google.com/p/lz4/ + - LZ4 source repository : https://github.com/Cyan4973/lz4 - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c */ #pragma once @@ -37,17 +38,23 @@ extern "C" { #endif +/* + * lz4.h provides block compression functions, and gives full buffer control to programmer. + * If you need to generate inter-operable compressed data (respecting LZ4 frame specification), + * and can let the library handle its own memory, please use lz4frame.h instead. +*/ /************************************** - Version +* Version **************************************/ -#define LZ4_VERSION_MAJOR 1 /* for major interface/format changes */ -#define LZ4_VERSION_MINOR 2 /* for minor interface/format changes */ +#define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */ +#define LZ4_VERSION_MINOR 7 /* for new (non-breaking) interface capabilities */ #define LZ4_VERSION_RELEASE 0 /* for tweaks, bug-fixes, or development */ - +#define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE) +int LZ4_versionNumber (void); /************************************** - Tuning parameter +* Tuning parameter **************************************/ /* * LZ4_MEMORY_USAGE : @@ -60,245 +67,292 @@ extern "C" { /************************************** - Simple Functions +* Simple Functions **************************************/ -int LZ4_compress (const char* source, char* dest, int inputSize); -int LZ4_decompress_safe (const char* source, char* dest, int compressedSize, int maxOutputSize); +int LZ4_compress_default(const char* source, char* dest, int sourceSize, int maxDestSize); +int LZ4_decompress_safe (const char* source, char* dest, int compressedSize, int maxDecompressedSize); /* -LZ4_compress() : - Compresses 'inputSize' bytes from 'source' into 'dest'. - Destination buffer must be already allocated, - and must be sized to handle worst cases situations (input data not compressible) - Worst case size evaluation is provided by function LZ4_compressBound() - inputSize : Max supported value is LZ4_MAX_INPUT_VALUE - return : the number of bytes written in buffer dest - or 0 if the compression fails +LZ4_compress_default() : + Compresses 'sourceSize' bytes from buffer 'source' + into already allocated 'dest' buffer of size 'maxDestSize'. + Compression is guaranteed to succeed if 'maxDestSize' >= LZ4_compressBound(sourceSize). + It also runs faster, so it's a recommended setting. + If the function cannot compress 'source' into a more limited 'dest' budget, + compression stops *immediately*, and the function result is zero. + As a consequence, 'dest' content is not valid. + This function never writes outside 'dest' buffer, nor read outside 'source' buffer. + sourceSize : Max supported value is LZ4_MAX_INPUT_VALUE + maxDestSize : full or partial size of buffer 'dest' (which must be already allocated) + return : the number of bytes written into buffer 'dest' (necessarily <= maxOutputSize) + or 0 if compression fails LZ4_decompress_safe() : - compressedSize : is obviously the source 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 destination buffer is not large enough, decoding will stop and output an error code (<0). + compressedSize : is the precise full size of the compressed block. + maxDecompressedSize : is the size of destination buffer, which must be already allocated. + return : the number of bytes decompressed into destination buffer (necessarily <= maxDecompressedSize) + If destination buffer is not large enough, decoding will stop and output an error code (<0). If the source stream is detected malformed, the function will stop decoding and return a negative result. - This function is protected against buffer overflow exploits : - it never writes outside of output buffer, and never reads outside of input buffer. - Therefore, it is protected against malicious data packets. -*/ - - -/* -Note : - Should you prefer to explicitly allocate compression-table memory using your own allocation method, - use the streaming functions provided below, simply reset the memory area between each call to LZ4_compress_continue() + This function is protected against buffer overflow exploits, including malicious data packets. + It never writes outside output buffer, nor reads outside input buffer. */ /************************************** - Advanced Functions +* Advanced Functions **************************************/ #define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */ -#define LZ4_COMPRESSBOUND(isize) ((unsigned int)(isize) > (unsigned int)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16) +#define LZ4_COMPRESSBOUND(isize) ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16) /* 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. - macro is also provided when result needs to be evaluated at compilation (such as stack memory allocation). + Provides the maximum size that LZ4 compression may output in a "worst case" scenario (input data not compressible) + This function is primarily useful for memory allocation purposes (destination buffer size). + Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example). + Note that LZ4_compress_default() compress faster when dest buffer size is >= LZ4_compressBound(srcSize) + inputSize : max supported value is LZ4_MAX_INPUT_SIZE + return : maximum output size in a "worst case" scenario + or 0, if input size is too large ( > LZ4_MAX_INPUT_SIZE) +*/ +int LZ4_compressBound(int inputSize); - isize : is the input size. Max supported value is LZ4_MAX_INPUT_SIZE - return : maximum output size in a "worst case" scenario - or 0, if input size is too large ( > LZ4_MAX_INPUT_SIZE) +/* +LZ4_compress_fast() : + Same as LZ4_compress_default(), but allows to select an "acceleration" factor. + The larger the acceleration value, the faster the algorithm, but also the lesser the compression. + It's a trade-off. It can be fine tuned, with each successive value providing roughly +~3% to speed. + An acceleration value of "1" is the same as regular LZ4_compress_default() + Values <= 0 will be replaced by ACCELERATION_DEFAULT (see lz4.c), which is 1. */ -int LZ4_compressBound(int isize); +int LZ4_compress_fast (const char* source, char* dest, int sourceSize, int maxDestSize, int acceleration); /* -LZ4_compress_limitedOutput() : - Compress 'inputSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'. - If it cannot achieve it, compression will stop, and result of the function will be zero. - This function never writes outside of provided output buffer. - - inputSize : Max supported value is LZ4_MAX_INPUT_VALUE - maxOutputSize : is the size of the destination buffer (which must be already allocated) - return : the number of bytes written in buffer 'dest' - or 0 if the compression fails +LZ4_compress_fast_extState() : + Same compression function, just using an externally allocated memory space to store compression state. + Use LZ4_sizeofState() to know how much memory must be allocated, + and allocate it on 8-bytes boundaries (using malloc() typically). + Then, provide it as 'void* state' to compression function. */ -int LZ4_compress_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize); +int LZ4_sizeofState(void); +int LZ4_compress_fast_extState (void* state, const char* source, char* dest, int inputSize, int maxDestSize, int acceleration); + + +/* +LZ4_compress_destSize() : + Reverse the logic, by compressing as much data as possible from 'source' buffer + into already allocated buffer 'dest' of size 'targetDestSize'. + This function either compresses the entire 'source' content into 'dest' if it's large enough, + or fill 'dest' buffer completely with as much data as possible from 'source'. + *sourceSizePtr : will be modified to indicate how many bytes where read from 'source' to fill 'dest'. + New value is necessarily <= old value. + return : Nb bytes written into 'dest' (necessarily <= targetDestSize) + or 0 if compression fails +*/ +int LZ4_compress_destSize (const char* source, char* dest, int* sourceSizePtr, int targetDestSize); /* LZ4_decompress_fast() : originalSize : is the original and therefore uncompressed size return : the number of bytes read from the source buffer (in other words, the compressed size) - If the source stream is malformed, the function will stop decoding and return a negative result. + If the source stream is detected malformed, the function will stop decoding and return a negative result. Destination buffer must be already allocated. Its size must be a minimum of 'originalSize' bytes. - note : This function is a bit faster than LZ4_decompress_safe() - It provides fast decompression and fully respect memory boundaries for properly formed compressed data. - It does not provide full protection against intentionnally modified data stream. - Use this function in a trusted environment (data to decode comes from a trusted source). + note : This function fully respect memory boundaries for properly formed compressed data. + It is a bit faster than LZ4_decompress_safe(). + However, it does not provide any protection against intentionally modified data stream (malicious input). + Use this function in trusted environment only (data to decode comes from a trusted source). */ int LZ4_decompress_fast (const char* source, char* dest, int originalSize); - /* LZ4_decompress_safe_partial() : This function decompress a compressed block of size 'compressedSize' at position 'source' - into output buffer 'dest' of size 'maxOutputSize'. + into destination buffer 'dest' of size 'maxDecompressedSize'. The function tries to stop decompressing operation as soon as 'targetOutputSize' has been reached, reducing decompression time. - return : the number of bytes decoded in the destination buffer (necessarily <= maxOutputSize) + return : the number of bytes decoded in the destination buffer (necessarily <= maxDecompressedSize) Note : this number can be < 'targetOutputSize' should the compressed block to decode be smaller. Always control how many bytes were decoded. If the source stream is detected malformed, the function will stop decoding and return a negative result. This function never writes outside of output buffer, and never reads outside of input buffer. It is therefore protected against malicious data packets */ -int LZ4_decompress_safe_partial (const char* source, char* dest, int compressedSize, int targetOutputSize, int maxOutputSize); +int LZ4_decompress_safe_partial (const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize); /*********************************************** - Experimental Streaming Compression Functions +* Streaming Compression Functions ***********************************************/ - -#define LZ4_STREAMSIZE_U32 ((1 << (LZ4_MEMORY_USAGE-2)) + 8) -#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U32 * sizeof(unsigned int)) +#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4) +#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U64 * sizeof(long long)) /* * LZ4_stream_t * information structure to track an LZ4 stream. - * important : set this structure content to zero before first use ! + * important : init this structure content before first use ! + * note : only allocated directly the structure if you are statically linking LZ4 + * If you are using liblz4 as a DLL, please use below construction methods instead. */ -typedef struct { unsigned int table[LZ4_STREAMSIZE_U32]; } LZ4_stream_t; +typedef struct { long long table[LZ4_STREAMSIZE_U64]; } LZ4_stream_t; /* - * If you prefer dynamic allocation methods, - * LZ4_createStream - * provides a pointer (void*) towards an initialized LZ4_stream_t structure. - * LZ4_free just frees it. + * LZ4_resetStream + * Use this function to init an allocated LZ4_stream_t structure */ -void* LZ4_createStream(); -int LZ4_free (void* LZ4_stream); +void LZ4_resetStream (LZ4_stream_t* streamPtr); +/* + * LZ4_createStream will allocate and initialize an LZ4_stream_t structure + * LZ4_freeStream releases its memory. + * In the context of a DLL (liblz4), please use these methods rather than the static struct. + * They are more future proof, in case of a change of LZ4_stream_t size. + */ +LZ4_stream_t* LZ4_createStream(void); +int LZ4_freeStream (LZ4_stream_t* streamPtr); /* * LZ4_loadDict * Use this function to load a static dictionary into LZ4_stream. * Any previous data will be forgotten, only 'dictionary' will remain in memory. - * Loading a size of 0 is allowed (same effect as init). - * Return : 1 if OK, 0 if error - */ -int LZ4_loadDict (void* LZ4_stream, const char* dictionary, int dictSize); - -/* - * LZ4_compress_continue - * Compress data block 'source', using blocks compressed before as dictionary to improve compression ratio - * Previous data blocks are assumed to still be present at their previous location. + * Loading a size of 0 is allowed. + * Return : dictionary size, in bytes (necessarily <= 64 KB) */ -int LZ4_compress_continue (void* LZ4_stream, const char* source, char* dest, int inputSize); +int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize); /* - * LZ4_compress_limitedOutput_continue - * Same as before, but also specify a maximum target compressed size (maxOutputSize) - * If objective cannot be met, compression exits, and returns a zero. + * LZ4_compress_fast_continue + * Compress buffer content 'src', using data from previously compressed blocks as dictionary to improve compression ratio. + * Important : Previous data blocks are assumed to still be present and unmodified ! + * 'dst' buffer must be already allocated. + * If maxDstSize >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster. + * If not, and if compressed data cannot fit into 'dst' buffer size, compression stops, and function returns a zero. */ -int LZ4_compress_limitedOutput_continue (void* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize); +int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int maxDstSize, int acceleration); /* * LZ4_saveDict - * If previously compressed data block is not guaranteed to remain at its previous memory location - * save it into a safe place (char* safeBuffer) + * If previously compressed data block is not guaranteed to remain available at its memory location + * save it into a safer place (char* safeBuffer) * Note : you don't need to call LZ4_loadDict() afterwards, - * dictionary is immediately usable, you can therefore call again LZ4_compress_continue() - * Return : 1 if OK, 0 if error - * Note : any dictSize > 64 KB will be interpreted as 64KB. + * dictionary is immediately usable, you can therefore call LZ4_compress_fast_continue() + * Return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error */ -int LZ4_saveDict (void* LZ4_stream, char* safeBuffer, int dictSize); +int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int dictSize); /************************************************ - Experimental Streaming Decompression Functions +* Streaming Decompression Functions ************************************************/ -#define LZ4_STREAMDECODESIZE_U32 4 -#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U32 * sizeof(unsigned int)) +#define LZ4_STREAMDECODESIZE_U64 4 +#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U64 * sizeof(unsigned long long)) +typedef struct { unsigned long long table[LZ4_STREAMDECODESIZE_U64]; } LZ4_streamDecode_t; /* * LZ4_streamDecode_t * information structure to track an LZ4 stream. - * important : set this structure content to zero before first use ! + * init this structure content using LZ4_setStreamDecode or memset() before first use ! + * + * In the context of a DLL (liblz4) please prefer usage of construction methods below. + * They are more future proof, in case of a change of LZ4_streamDecode_t size in the future. + * LZ4_createStreamDecode will allocate and initialize an LZ4_streamDecode_t structure + * LZ4_freeStreamDecode releases its memory. */ -typedef struct { unsigned int table[LZ4_STREAMDECODESIZE_U32]; } LZ4_streamDecode_t; +LZ4_streamDecode_t* LZ4_createStreamDecode(void); +int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream); /* - * If you prefer dynamic allocation methods, - * LZ4_createStreamDecode() - * provides a pointer (void*) towards an initialized LZ4_streamDecode_t structure. - * LZ4_free just frees it. + * LZ4_setStreamDecode + * Use this function to instruct where to find the dictionary. + * Setting a size of 0 is allowed (same effect as reset). + * Return : 1 if OK, 0 if error */ -void* LZ4_createStreamDecode(); -int LZ4_free (void* LZ4_stream); /* yes, it's the same one as for compression */ +int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize); /* *_continue() : These decoding functions allow decompression of multiple blocks in "streaming" mode. - Previously decoded blocks must still be available at the memory position where they were decoded. - If it's not possible, save the relevant part of decoded data into a safe buffer, - and indicate where it stands using LZ4_setDictDecode() + Previously decoded blocks *must* remain available at the memory position where they were decoded (up to 64 KB) + In the case of a ring buffers, decoding buffer must be either : + - Exactly same size as encoding buffer, with same update rule (block boundaries at same positions) + In which case, the decoding & encoding ring buffer can have any size, including very small ones ( < 64 KB). + - Larger than encoding buffer, by a minimum of maxBlockSize more bytes. + maxBlockSize is implementation dependent. It's the maximum size you intend to compress into a single block. + In which case, encoding and decoding buffers do not need to be synchronized, + and encoding ring buffer can have any size, including small ones ( < 64 KB). + - _At least_ 64 KB + 8 bytes + maxBlockSize. + In which case, encoding and decoding buffers do not need to be synchronized, + and encoding ring buffer can have any size, including larger than decoding buffer. + Whenever these conditions are not possible, save the last 64KB of decoded data into a safe buffer, + and indicate where it is saved using LZ4_setStreamDecode() */ -int LZ4_decompress_safe_continue (void* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize); -int LZ4_decompress_fast_continue (void* LZ4_streamDecode, const char* source, char* dest, int originalSize); - -/* - * LZ4_setDictDecode - * Use this function to instruct where to find the dictionary. - * This function can be used to specify a static dictionary, - * or to instruct where to find some previously decoded data saved into a different memory space. - * Setting a size of 0 is allowed (same effect as no dictionary). - * Return : 1 if OK, 0 if error - */ -int LZ4_setDictDecode (void* LZ4_streamDecode, const char* dictionary, int dictSize); +int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxDecompressedSize); +int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize); /* Advanced decoding functions : *_usingDict() : These decoding functions work the same as - a combination of LZ4_setDictDecode() followed by LZ4_decompress_x_continue() - all together into a single function call. - It doesn't use nor update an LZ4_streamDecode_t structure. + a combination of LZ4_setStreamDecode() followed by LZ4_decompress_x_continue() + They are stand-alone. They don't need nor update an LZ4_streamDecode_t structure. */ -int LZ4_decompress_safe_usingDict (const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize); +int LZ4_decompress_safe_usingDict (const char* source, char* dest, int compressedSize, int maxDecompressedSize, const char* dictStart, int dictSize); int LZ4_decompress_fast_usingDict (const char* source, char* dest, int originalSize, const char* dictStart, int dictSize); - /************************************** - Obsolete Functions +* Obsolete Functions **************************************/ -/* -Obsolete decompression functions -These function names are deprecated and should no longer be used. -They are only provided here for compatibility with older user programs. -- LZ4_uncompress is the same as LZ4_decompress_fast -- LZ4_uncompress_unknownOutputSize is the same as LZ4_decompress_safe -*/ -int LZ4_uncompress (const char* source, char* dest, int outputSize); -int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize); - -/* Obsolete functions for externally allocated state; use streaming interface instead */ -int LZ4_sizeofState(void); +/* Deprecate Warnings */ +/* Should these warnings messages be a problem, + it is generally possible to disable them, + with -Wno-deprecated-declarations for gcc + or _CRT_SECURE_NO_WARNINGS in Visual for example. + You can also define LZ4_DEPRECATE_WARNING_DEFBLOCK. */ +#ifndef LZ4_DEPRECATE_WARNING_DEFBLOCK +# define LZ4_DEPRECATE_WARNING_DEFBLOCK +# define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) +# if (LZ4_GCC_VERSION >= 405) || defined(__clang__) +# define LZ4_DEPRECATED(message) __attribute__((deprecated(message))) +# elif (LZ4_GCC_VERSION >= 301) +# define LZ4_DEPRECATED(message) __attribute__((deprecated)) +# elif defined(_MSC_VER) +# define LZ4_DEPRECATED(message) __declspec(deprecated(message)) +# else +# pragma message("WARNING: You need to implement LZ4_DEPRECATED for this compiler") +# define LZ4_DEPRECATED(message) +# endif +#endif /* LZ4_DEPRECATE_WARNING_DEFBLOCK */ + +/* Obsolete compression functions */ +/* These functions are planned to start generate warnings by r131 approximately */ +int LZ4_compress (const char* source, char* dest, int sourceSize); +int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize); int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize); int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); +int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize); +int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize); + +/* Obsolete decompression functions */ +/* These function names are completely deprecated and must no longer be used. + They are only provided here for compatibility with older programs. + - LZ4_uncompress is the same as LZ4_decompress_fast + - LZ4_uncompress_unknownOutputSize is the same as LZ4_decompress_safe + These function prototypes are now disabled; uncomment them only if you really need them. + It is highly recommended to stop using these prototypes and migrate to maintained ones */ +/* int LZ4_uncompress (const char* source, char* dest, int outputSize); */ +/* int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize); */ /* Obsolete streaming functions; use new streaming interface whenever possible */ -void* LZ4_create (const char* inputBuffer); -int LZ4_sizeofStreamState(void); -int LZ4_resetStreamState(void* state, const char* inputBuffer); -char* LZ4_slideInputBuffer (void* state); +LZ4_DEPRECATED("use LZ4_createStream() instead") void* LZ4_create (char* inputBuffer); +LZ4_DEPRECATED("use LZ4_createStream() instead") int LZ4_sizeofStreamState(void); +LZ4_DEPRECATED("use LZ4_resetStream() instead") int LZ4_resetStreamState(void* state, char* inputBuffer); +LZ4_DEPRECATED("use LZ4_saveDict() instead") char* LZ4_slideInputBuffer (void* state); /* Obsolete streaming decoding functions */ -int LZ4_decompress_safe_withPrefix64k (const char* source, char* dest, int compressedSize, int maxOutputSize); -int LZ4_decompress_fast_withPrefix64k (const char* source, char* dest, int originalSize); +LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize); +LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize); #if defined (__cplusplus) diff --git a/src/lz4hc.c b/src/lz4hc.c index 6086749..a22ab2b 100644 --- a/src/lz4hc.c +++ b/src/lz4hc.c @@ -1,561 +1,279 @@ /* - LZ4 HC - High Compression Mode of LZ4 - Copyright (C) 2011-2014, 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/ + LZ4 HC - High Compression Mode of LZ4 + Copyright (C) 2011-2015, 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 : + - LZ4 source repository : https://github.com/Cyan4973/lz4 + - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c */ /************************************** - Tuning Parameter +* Tuning Parameter **************************************/ -#define LZ4HC_DEFAULT_COMPRESSIONLEVEL 8 +static const int LZ4HC_compressionLevel_default = 9; /************************************** - Memory routines +* Includes **************************************/ -#include /* calloc, free */ -#define ALLOCATOR(s) calloc(1,s) -#define FREEMEM free -#include /* memset, memcpy */ -#define MEM_INIT memset - - -/************************************** - CPU Feature Detection -**************************************/ -/* 32 or 64 bits ? */ -#if (defined(__x86_64__) || defined(_M_X64) || defined(_WIN64) \ - || defined(__powerpc64__) || defined(__powerpc64le__) \ - || defined(__ppc64__) || defined(__ppc64le__) \ - || defined(__PPC64__) || defined(__PPC64LE__) \ - || defined(__ia64) || defined(__itanium__) || defined(_M_IA64) ) /* Detects 64 bits mode */ -# define LZ4_ARCH64 1 -#else -# define LZ4_ARCH64 0 -#endif - -/* - * Little Endian or Big Endian ? - * Overwrite the #define below if you know your architecture endianess - */ -#include /* Apparently required to detect endianess */ -#if defined (__GLIBC__) -# include -# if (__BYTE_ORDER == __BIG_ENDIAN) -# define LZ4_BIG_ENDIAN 1 -# endif -#elif (defined(__BIG_ENDIAN__) || defined(__BIG_ENDIAN) || defined(_BIG_ENDIAN)) && !(defined(__LITTLE_ENDIAN__) || defined(__LITTLE_ENDIAN) || defined(_LITTLE_ENDIAN)) -# define LZ4_BIG_ENDIAN 1 -#elif defined(__sparc) || defined(__sparc__) \ - || defined(__powerpc__) || defined(__ppc__) || defined(__PPC__) \ - || defined(__hpux) || defined(__hppa) \ - || defined(_MIPSEB) || defined(__s390__) -# 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 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 +#include "lz4hc.h" /************************************** - Compiler Options +* Local Compiler Options **************************************/ -#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */ -/* "restrict" is a known keyword */ -#else -# define restrict /* Disable restrict */ -#endif - -#ifdef _MSC_VER /* Visual Studio */ -# define FORCE_INLINE static __forceinline -# include /* For Visual 2005 */ -# if LZ4_ARCH64 /* 64-bits */ -# pragma intrinsic(_BitScanForward64) /* For Visual 2005 */ -# pragma intrinsic(_BitScanReverse64) /* For Visual 2005 */ -# else /* 32-bits */ -# pragma intrinsic(_BitScanForward) /* For Visual 2005 */ -# pragma intrinsic(_BitScanReverse) /* For Visual 2005 */ -# endif -# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ -# pragma warning(disable : 4701) /* disable: C4701: potentially uninitialized local variable used */ -#else -# ifdef __GNUC__ -# define FORCE_INLINE static inline __attribute__((always_inline)) -# else -# define FORCE_INLINE static inline -# endif +#if defined(__GNUC__) +# pragma GCC diagnostic ignored "-Wunused-function" #endif -#ifdef _MSC_VER /* Visual Studio */ -# define lz4_bswap16(x) _byteswap_ushort(x) -#else -# define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8))) +#if defined (__clang__) +# pragma clang diagnostic ignored "-Wunused-function" #endif /************************************** - Includes -**************************************/ -#include "lz4hc.h" -#include "lz4.h" - - -/************************************** - Basic Types +* Common LZ4 definition **************************************/ -#if defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */ -# include - 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; -#endif - -#if defined(__GNUC__) && !defined(LZ4_FORCE_UNALIGNED_ACCESS) -# define _PACKED __attribute__ ((packed)) -#else -# define _PACKED -#endif - -#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__) -# ifdef __IBMC__ -# pragma pack(1) -# else -# pragma pack(push, 1) -# endif -#endif - -typedef struct _U16_S { U16 v; } _PACKED U16_S; -typedef struct _U32_S { U32 v; } _PACKED U32_S; -typedef struct _U64_S { U64 v; } _PACKED U64_S; - -#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__) -# 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) +#define LZ4_COMMONDEFS_ONLY +#include "lz4.c" /************************************** - Constants +* Local Constants **************************************/ -#define MINMATCH 4 - #define DICTIONARY_LOGSIZE 16 #define MAXD (1<> ((MINMATCH*8)-HASH_LOG)) -#define HASH_VALUE(p) HASH_FUNCTION(A32(p)) -#define HASH_POINTER(p) (HashTable[HASH_VALUE(p)] + base) -#define DELTANEXT(p) chainTable[(size_t)(p) & MAXD_MASK] -#define GETNEXT(p) ((p) - (size_t)DELTANEXT(p)) - - -/************************************** - Private functions -**************************************/ -#if LZ4_ARCH64 +//#define DELTANEXTU16(p) chainTable[(p) & MAXD_MASK] /* flexible, MAXD dependent */ +#define DELTANEXTU16(p) chainTable[(U16)(p)] /* faster */ -FORCE_INLINE 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__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 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__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 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 -} +static U32 LZ4HC_hashPtr(const void* ptr) { return HASH_FUNCTION(LZ4_read32(ptr)); } -#else -FORCE_INLINE int LZ4_NbCommonBytes (register U32 val) -{ -#if defined(LZ4_BIG_ENDIAN) -# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r; - _BitScanReverse( &r, val ); - return (int)(r>>3); -# elif defined(__GNUC__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 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; - _BitScanForward( &r, val ); - return (int)(r>>3); -# elif defined(__GNUC__) && ((__GNUC__ * 100 + __GNUC_MINOR__) >= 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 - -int LZ4_sizeofStreamStateHC() -{ - return sizeof(LZ4HC_Data_Structure); -} - -FORCE_INLINE void LZ4_initHC (LZ4HC_Data_Structure* hc4, const BYTE* base) +/************************************** +* HC Compression +**************************************/ +static void LZ4HC_init (LZ4HC_Data_Structure* hc4, const BYTE* start) { MEM_INIT((void*)hc4->hashTable, 0, sizeof(hc4->hashTable)); MEM_INIT(hc4->chainTable, 0xFF, sizeof(hc4->chainTable)); - hc4->nextToUpdate = base + 1; - hc4->base = base; - hc4->inputBuffer = base; - hc4->end = base; -} - -int LZ4_resetStreamStateHC(void* state, const char* inputBuffer) -{ - if ((((size_t)state) & (sizeof(void*)-1)) != 0) return 1; /* Error : pointer is not aligned for pointer (32 or 64 bits) */ - LZ4_initHC((LZ4HC_Data_Structure*)state, (const BYTE*)inputBuffer); - return 0; -} - - -void* LZ4_createHC (const char* inputBuffer) -{ - void* hc4 = ALLOCATOR(sizeof(LZ4HC_Data_Structure)); - LZ4_initHC ((LZ4HC_Data_Structure*)hc4, (const BYTE*)inputBuffer); - return hc4; -} - - -int LZ4_freeHC (void* LZ4HC_Data) -{ - FREEMEM(LZ4HC_Data); - return (0); + hc4->nextToUpdate = 64 KB; + hc4->base = start - 64 KB; + hc4->end = start; + hc4->dictBase = start - 64 KB; + hc4->dictLimit = 64 KB; + hc4->lowLimit = 64 KB; } /* Update chains up to ip (excluded) */ FORCE_INLINE void LZ4HC_Insert (LZ4HC_Data_Structure* hc4, const BYTE* ip) { - U16* chainTable = hc4->chainTable; - HTYPE* HashTable = hc4->hashTable; - INITBASE(base,hc4->base); + U16* chainTable = hc4->chainTable; + U32* HashTable = hc4->hashTable; + const BYTE* const base = hc4->base; + const U32 target = (U32)(ip - base); + U32 idx = hc4->nextToUpdate; - while(hc4->nextToUpdate < ip) + while(idx < target) { - const BYTE* const p = hc4->nextToUpdate; - size_t delta = (p) - HASH_POINTER(p); + U32 h = LZ4HC_hashPtr(base+idx); + size_t delta = idx - HashTable[h]; if (delta>MAX_DISTANCE) delta = MAX_DISTANCE; - DELTANEXT(p) = (U16)delta; - HashTable[HASH_VALUE(p)] = (HTYPE)((p) - base); - hc4->nextToUpdate++; + DELTANEXTU16(idx) = (U16)delta; + HashTable[h] = idx; + idx++; } -} - - -char* LZ4_slideInputBufferHC(void* LZ4HC_Data) -{ - LZ4HC_Data_Structure* hc4 = (LZ4HC_Data_Structure*)LZ4HC_Data; - U32 distance = (U32)(hc4->end - hc4->inputBuffer) - 64 KB; - distance = (distance >> 16) << 16; /* Must be a multiple of 64 KB */ - LZ4HC_Insert(hc4, hc4->end - MINMATCH); - memcpy((void*)(hc4->end - 64 KB - distance), (const void*)(hc4->end - 64 KB), 64 KB); - hc4->nextToUpdate -= distance; - hc4->base -= distance; - if ((U32)(hc4->inputBuffer - hc4->base) > 1 GB + 64 KB) /* Avoid overflow */ - { - int i; - hc4->base += 1 GB; - for (i=0; ihashTable[i] -= 1 GB; - } - hc4->end -= distance; - return (char*)(hc4->end); -} - -FORCE_INLINE size_t LZ4HC_CommonLength (const BYTE* p1, const BYTE* p2, const BYTE* const matchlimit) -{ - const BYTE* p1t = p1; - - while (p1tnextToUpdate = target; } -FORCE_INLINE int LZ4HC_InsertAndFindBestMatch (LZ4HC_Data_Structure* hc4, const BYTE* ip, const BYTE* const matchlimit, const BYTE** matchpos, const int maxNbAttempts) +FORCE_INLINE int LZ4HC_InsertAndFindBestMatch (LZ4HC_Data_Structure* hc4, /* Index table will be updated */ + const BYTE* ip, const BYTE* const iLimit, + const BYTE** matchpos, + const int maxNbAttempts) { U16* const chainTable = hc4->chainTable; - HTYPE* const HashTable = hc4->hashTable; - const BYTE* ref; - INITBASE(base,hc4->base); + U32* const HashTable = hc4->hashTable; + const BYTE* const base = hc4->base; + const BYTE* const dictBase = hc4->dictBase; + const U32 dictLimit = hc4->dictLimit; + const U32 lowLimit = (hc4->lowLimit + 64 KB > (U32)(ip-base)) ? hc4->lowLimit : (U32)(ip - base) - (64 KB - 1); + U32 matchIndex; + const BYTE* match; int nbAttempts=maxNbAttempts; - size_t repl=0, ml=0; - U16 delta=0; /* useless assignment, to remove an uninitialization warning */ + size_t ml=0; /* HC4 match finder */ LZ4HC_Insert(hc4, ip); - ref = HASH_POINTER(ip); + matchIndex = HashTable[LZ4HC_hashPtr(ip)]; -#define REPEAT_OPTIMIZATION -#ifdef REPEAT_OPTIMIZATION - /* Detect repetitive sequences of length <= 4 */ - if ((U32)(ip-ref) <= 4) /* potential repetition */ - { - if (A32(ref) == A32(ip)) /* confirmed */ - { - delta = (U16)(ip-ref); - repl = ml = LZ4HC_CommonLength(ip+MINMATCH, ref+MINMATCH, matchlimit) + MINMATCH; - *matchpos = ref; - } - ref = GETNEXT(ref); - } -#endif - - while (((U32)(ip-ref) <= MAX_DISTANCE) && (nbAttempts)) + while ((matchIndex>=lowLimit) && (nbAttempts)) { nbAttempts--; - if (*(ref+ml) == *(ip+ml)) - if (A32(ref) == A32(ip)) + if (matchIndex >= dictLimit) { - size_t mlt = LZ4HC_CommonLength(ip+MINMATCH, ref+MINMATCH, matchlimit) + MINMATCH; - if (mlt > ml) { ml = mlt; *matchpos = ref; } + match = base + matchIndex; + if (*(match+ml) == *(ip+ml) + && (LZ4_read32(match) == LZ4_read32(ip))) + { + size_t mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, iLimit) + MINMATCH; + if (mlt > ml) { ml = mlt; *matchpos = match; } + } } - ref = GETNEXT(ref); - } - -#ifdef REPEAT_OPTIMIZATION - /* Complete table */ - if (repl) - { - const BYTE* ptr = ip; - const BYTE* end; - - end = ip + repl - (MINMATCH-1); - while(ptr < end-delta) + else { - DELTANEXT(ptr) = delta; /* Pre-Load */ - ptr++; + match = dictBase + matchIndex; + if (LZ4_read32(match) == LZ4_read32(ip)) + { + size_t mlt; + const BYTE* vLimit = ip + (dictLimit - matchIndex); + if (vLimit > iLimit) vLimit = iLimit; + mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, vLimit) + MINMATCH; + if ((ip+mlt == vLimit) && (vLimit < iLimit)) + mlt += LZ4_count(ip+mlt, base+dictLimit, iLimit); + if (mlt > ml) { ml = mlt; *matchpos = base + matchIndex; } /* virtual matchpos */ + } } - do - { - DELTANEXT(ptr) = delta; - HashTable[HASH_VALUE(ptr)] = (HTYPE)((ptr) - base); /* Head of chain */ - ptr++; - } while(ptr < end); - hc4->nextToUpdate = end; + matchIndex -= DELTANEXTU16(matchIndex); } -#endif return (int)ml; } -FORCE_INLINE int LZ4HC_InsertAndGetWiderMatch (LZ4HC_Data_Structure* hc4, const BYTE* ip, const BYTE* startLimit, const BYTE* matchlimit, int longest, const BYTE** matchpos, const BYTE** startpos, const int maxNbAttempts) +FORCE_INLINE int LZ4HC_InsertAndGetWiderMatch ( + LZ4HC_Data_Structure* hc4, + const BYTE* const ip, + const BYTE* const iLowLimit, + const BYTE* const iHighLimit, + int longest, + const BYTE** matchpos, + const BYTE** startpos, + const int maxNbAttempts) { - U16* const chainTable = hc4->chainTable; - HTYPE* const HashTable = hc4->hashTable; - INITBASE(base,hc4->base); - const BYTE* ref; + U16* const chainTable = hc4->chainTable; + U32* const HashTable = hc4->hashTable; + const BYTE* const base = hc4->base; + const U32 dictLimit = hc4->dictLimit; + const BYTE* const lowPrefixPtr = base + dictLimit; + const U32 lowLimit = (hc4->lowLimit + 64 KB > (U32)(ip-base)) ? hc4->lowLimit : (U32)(ip - base) - (64 KB - 1); + const BYTE* const dictBase = hc4->dictBase; + U32 matchIndex; int nbAttempts = maxNbAttempts; - int delta = (int)(ip-startLimit); + int delta = (int)(ip-iLowLimit); + /* First Match */ LZ4HC_Insert(hc4, ip); - ref = HASH_POINTER(ip); + matchIndex = HashTable[LZ4HC_hashPtr(ip)]; - while (((U32)(ip-ref) <= MAX_DISTANCE) && (nbAttempts)) + while ((matchIndex>=lowLimit) && (nbAttempts)) { nbAttempts--; - if (*(startLimit + longest) == *(ref - delta + longest)) - if (A32(ref) == A32(ip)) + if (matchIndex >= dictLimit) { -#if 1 - const BYTE* reft = ref+MINMATCH; - const BYTE* ipt = ip+MINMATCH; - const BYTE* startt = ip; + const BYTE* matchPtr = base + matchIndex; + if (*(iLowLimit + longest) == *(matchPtr - delta + longest)) + if (LZ4_read32(matchPtr) == LZ4_read32(ip)) + { + int mlt = MINMATCH + LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, iHighLimit); + int back = 0; - while (iptiLowLimit) + && (matchPtr+back > lowPrefixPtr) + && (ip[back-1] == matchPtr[back-1])) + back--; - while ((startt>startLimit) && (reft > hc4->inputBuffer) && (startt[-1] == reft[-1])) {startt--; reft--;} + mlt -= back; - if ((ipt-startt) > longest) + if (mlt > longest) + { + longest = (int)mlt; + *matchpos = matchPtr+back; + *startpos = ip+back; + } + } + } + else + { + const BYTE* matchPtr = dictBase + matchIndex; + if (LZ4_read32(matchPtr) == LZ4_read32(ip)) { - longest = (int)(ipt-startt); - *matchpos = reft; - *startpos = startt; + size_t mlt; + int back=0; + const BYTE* vLimit = ip + (dictLimit - matchIndex); + if (vLimit > iHighLimit) vLimit = iHighLimit; + mlt = LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, vLimit) + MINMATCH; + if ((ip+mlt == vLimit) && (vLimit < iHighLimit)) + mlt += LZ4_count(ip+mlt, base+dictLimit, iHighLimit); + while ((ip+back > iLowLimit) && (matchIndex+back > lowLimit) && (ip[back-1] == matchPtr[back-1])) back--; + mlt -= back; + if ((int)mlt > longest) { longest = (int)mlt; *matchpos = base + matchIndex + back; *startpos = ip+back; } } } - ref = GETNEXT(ref); + matchIndex -= DELTANEXTU16(matchIndex); } return longest; @@ -564,34 +282,44 @@ FORCE_INLINE int LZ4HC_InsertAndGetWiderMatch (LZ4HC_Data_Structure* hc4, const typedef enum { noLimit = 0, limitedOutput = 1 } limitedOutput_directive; +#define LZ4HC_DEBUG 0 +#if LZ4HC_DEBUG +static unsigned debug = 0; +#endif + FORCE_INLINE int LZ4HC_encodeSequence ( - const BYTE** ip, - BYTE** op, - const BYTE** anchor, - int matchLength, - const BYTE* ref, - limitedOutput_directive limitedOutputBuffer, - BYTE* oend) + const BYTE** ip, + BYTE** op, + const BYTE** anchor, + int matchLength, + const BYTE* const match, + limitedOutput_directive limitedOutputBuffer, + BYTE* oend) { int length; BYTE* token; +#if LZ4HC_DEBUG + if (debug) printf("literal : %u -- match : %u -- offset : %u\n", (U32)(*ip - *anchor), (U32)matchLength, (U32)(*ip-match)); +#endif + /* Encode Literal length */ length = (int)(*ip - *anchor); token = (*op)++; - if ((limitedOutputBuffer) && ((*op + length + (2 + 1 + LASTLITERALS) + (length>>8)) > oend)) return 1; /* Check output limit */ + if ((limitedOutputBuffer) && ((*op + (length>>8) + length + (2 + 1 + LASTLITERALS)) > oend)) return 1; /* Check output limit */ if (length>=(int)RUN_MASK) { int len; *token=(RUN_MASK< 254 ; len-=255) *(*op)++ = 255; *(*op)++ = (BYTE)len; } else *token = (BYTE)(length<>8) > oend)) return 1; /* Check output limit */ + if ((limitedOutputBuffer) && (*op + (length>>8) + (1 + LASTLITERALS) > oend)) return 1; /* Check output limit */ if (length>=(int)ML_MASK) { *token+=ML_MASK; length-=ML_MASK; for(; length > 509 ; length-=510) { *(*op)++ = 255; *(*op)++ = 255; } if (length > 254) { length-=255; *(*op)++ = 255; } *(*op)++ = (BYTE)length; } else *token += (BYTE)(length); @@ -603,16 +331,15 @@ FORCE_INLINE int LZ4HC_encodeSequence ( } -#define MAX_COMPRESSION_LEVEL 16 static int LZ4HC_compress_generic ( - void* ctxvoid, - const char* source, - char* dest, - int inputSize, - int maxOutputSize, - int compressionLevel, - limitedOutput_directive limit - ) + void* ctxvoid, + const char* source, + char* dest, + int inputSize, + int maxOutputSize, + int compressionLevel, + limitedOutput_directive limit + ) { LZ4HC_Data_Structure* ctx = (LZ4HC_Data_Structure*) ctxvoid; const BYTE* ip = (const BYTE*) source; @@ -624,7 +351,7 @@ static int LZ4HC_compress_generic ( BYTE* op = (BYTE*) dest; BYTE* const oend = op + maxOutputSize; - const int maxNbAttempts = compressionLevel > MAX_COMPRESSION_LEVEL ? 1 << MAX_COMPRESSION_LEVEL : compressionLevel ? 1<<(compressionLevel-1) : 1<end) return 0; + /* init */ + if (compressionLevel > g_maxCompressionLevel) compressionLevel = g_maxCompressionLevel; + if (compressionLevel < 1) compressionLevel = LZ4HC_compressionLevel_default; + maxNbAttempts = 1 << (compressionLevel-1); ctx->end += inputSize; ip++; @@ -684,10 +413,10 @@ static int LZ4HC_compress_generic ( _Search3: /* - * Currently we have : - * ml2 > ml1, and - * ip1+3 <= ip2 (usually < ip1+ml1) - */ + * Currently we have : + * ml2 > ml1, and + * ip1+3 <= ip2 (usually < ip1+ml1) + */ if ((start2 - ip) < OPTIMAL_ML) { int correction; @@ -755,9 +484,9 @@ static int LZ4HC_compress_generic ( } /* - * OK, now we have 3 ascending matches; let's write at least the first one - * ip & ref are known; Now for ml - */ + * OK, now we have 3 ascending matches; let's write at least the first one + * ip & ref are known; Now for ml + */ if (start2 < ip+ml) { if ((start2 - ip) < (int)ML_MASK) @@ -789,7 +518,6 @@ static int LZ4HC_compress_generic ( ml2 = ml3; goto _Search3; - } /* Encode Last Literals */ @@ -807,73 +535,181 @@ static int LZ4HC_compress_generic ( } -int LZ4_compressHC2(const char* source, char* dest, int inputSize, int compressionLevel) -{ - void* ctx = LZ4_createHC(source); - int result; - if (ctx==NULL) return 0; +int LZ4_sizeofStateHC(void) { return sizeof(LZ4HC_Data_Structure); } - result = LZ4HC_compress_generic (ctx, source, dest, inputSize, 0, compressionLevel, noLimit); +int LZ4_compress_HC_extStateHC (void* state, const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel) +{ + if (((size_t)(state)&(sizeof(void*)-1)) != 0) return 0; /* Error : state is not aligned for pointers (32 or 64 bits) */ + LZ4HC_init ((LZ4HC_Data_Structure*)state, (const BYTE*)src); + if (maxDstSize < LZ4_compressBound(srcSize)) + return LZ4HC_compress_generic (state, src, dst, srcSize, maxDstSize, compressionLevel, limitedOutput); + else + return LZ4HC_compress_generic (state, src, dst, srcSize, maxDstSize, compressionLevel, noLimit); +} - LZ4_freeHC(ctx); - return result; +int LZ4_compress_HC(const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel) +{ + LZ4HC_Data_Structure state; + return LZ4_compress_HC_extStateHC(&state, src, dst, srcSize, maxDstSize, compressionLevel); } -int LZ4_compressHC(const char* source, char* dest, int inputSize) { return LZ4_compressHC2(source, dest, inputSize, 0); } -int LZ4_compressHC2_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel) -{ - void* ctx = LZ4_createHC(source); - int result; - if (ctx==NULL) return 0; - result = LZ4HC_compress_generic (ctx, source, dest, inputSize, maxOutputSize, compressionLevel, limitedOutput); +/************************************** +* Streaming Functions +**************************************/ +/* allocation */ +LZ4_streamHC_t* LZ4_createStreamHC(void) { return (LZ4_streamHC_t*)malloc(sizeof(LZ4_streamHC_t)); } +int LZ4_freeStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr) { free(LZ4_streamHCPtr); return 0; } + - LZ4_freeHC(ctx); - return result; +/* initialization */ +void LZ4_resetStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel) +{ + LZ4_STATIC_ASSERT(sizeof(LZ4HC_Data_Structure) <= sizeof(LZ4_streamHC_t)); /* if compilation fails here, LZ4_STREAMHCSIZE must be increased */ + ((LZ4HC_Data_Structure*)LZ4_streamHCPtr)->base = NULL; + ((LZ4HC_Data_Structure*)LZ4_streamHCPtr)->compressionLevel = (unsigned)compressionLevel; } -int LZ4_compressHC_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) +int LZ4_loadDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, const char* dictionary, int dictSize) { - return LZ4_compressHC2_limitedOutput(source, dest, inputSize, maxOutputSize, 0); + LZ4HC_Data_Structure* ctxPtr = (LZ4HC_Data_Structure*) LZ4_streamHCPtr; + if (dictSize > 64 KB) + { + dictionary += dictSize - 64 KB; + dictSize = 64 KB; + } + LZ4HC_init (ctxPtr, (const BYTE*)dictionary); + if (dictSize >= 4) LZ4HC_Insert (ctxPtr, (const BYTE*)dictionary +(dictSize-3)); + ctxPtr->end = (const BYTE*)dictionary + dictSize; + return dictSize; } -/***************************** - Using external allocation -*****************************/ -int LZ4_sizeofStateHC() { return sizeof(LZ4HC_Data_Structure); } +/* compression */ +static void LZ4HC_setExternalDict(LZ4HC_Data_Structure* ctxPtr, const BYTE* newBlock) +{ + if (ctxPtr->end >= ctxPtr->base + 4) + LZ4HC_Insert (ctxPtr, ctxPtr->end-3); /* Referencing remaining dictionary content */ + /* Only one memory segment for extDict, so any previous extDict is lost at this stage */ + ctxPtr->lowLimit = ctxPtr->dictLimit; + ctxPtr->dictLimit = (U32)(ctxPtr->end - ctxPtr->base); + ctxPtr->dictBase = ctxPtr->base; + ctxPtr->base = newBlock - ctxPtr->dictLimit; + ctxPtr->end = newBlock; + ctxPtr->nextToUpdate = ctxPtr->dictLimit; /* match referencing will resume from there */ +} -int LZ4_compressHC2_withStateHC (void* state, const char* source, char* dest, int inputSize, int compressionLevel) +static int LZ4_compressHC_continue_generic (LZ4HC_Data_Structure* ctxPtr, + const char* source, char* dest, + int inputSize, int maxOutputSize, limitedOutput_directive limit) { - if (((size_t)(state)&(sizeof(void*)-1)) != 0) return 0; /* Error : state is not aligned for pointers (32 or 64 bits) */ - LZ4_initHC ((LZ4HC_Data_Structure*)state, (const BYTE*)source); - return LZ4HC_compress_generic (state, source, dest, inputSize, 0, compressionLevel, noLimit); + /* auto-init if forgotten */ + if (ctxPtr->base == NULL) + LZ4HC_init (ctxPtr, (const BYTE*) source); + + /* Check overflow */ + if ((size_t)(ctxPtr->end - ctxPtr->base) > 2 GB) + { + size_t dictSize = (size_t)(ctxPtr->end - ctxPtr->base) - ctxPtr->dictLimit; + if (dictSize > 64 KB) dictSize = 64 KB; + + LZ4_loadDictHC((LZ4_streamHC_t*)ctxPtr, (const char*)(ctxPtr->end) - dictSize, (int)dictSize); + } + + /* Check if blocks follow each other */ + if ((const BYTE*)source != ctxPtr->end) + LZ4HC_setExternalDict(ctxPtr, (const BYTE*)source); + + /* Check overlapping input/dictionary space */ + { + const BYTE* sourceEnd = (const BYTE*) source + inputSize; + const BYTE* dictBegin = ctxPtr->dictBase + ctxPtr->lowLimit; + const BYTE* dictEnd = ctxPtr->dictBase + ctxPtr->dictLimit; + if ((sourceEnd > dictBegin) && ((const BYTE*)source < dictEnd)) + { + if (sourceEnd > dictEnd) sourceEnd = dictEnd; + ctxPtr->lowLimit = (U32)(sourceEnd - ctxPtr->dictBase); + if (ctxPtr->dictLimit - ctxPtr->lowLimit < 4) ctxPtr->lowLimit = ctxPtr->dictLimit; + } + } + + return LZ4HC_compress_generic (ctxPtr, source, dest, inputSize, maxOutputSize, ctxPtr->compressionLevel, limit); +} + +int LZ4_compress_HC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize) +{ + if (maxOutputSize < LZ4_compressBound(inputSize)) + return LZ4_compressHC_continue_generic ((LZ4HC_Data_Structure*)LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, limitedOutput); + else + return LZ4_compressHC_continue_generic ((LZ4HC_Data_Structure*)LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, noLimit); } -int LZ4_compressHC_withStateHC (void* state, const char* source, char* dest, int inputSize) -{ return LZ4_compressHC2_withStateHC (state, source, dest, inputSize, 0); } +/* dictionary saving */ -int LZ4_compressHC2_limitedOutput_withStateHC (void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel) +int LZ4_saveDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, char* safeBuffer, int dictSize) { - if (((size_t)(state)&(sizeof(void*)-1)) != 0) return 0; /* Error : state is not aligned for pointers (32 or 64 bits) */ - LZ4_initHC ((LZ4HC_Data_Structure*)state, (const BYTE*)source); - return LZ4HC_compress_generic (state, source, dest, inputSize, maxOutputSize, compressionLevel, limitedOutput); + LZ4HC_Data_Structure* streamPtr = (LZ4HC_Data_Structure*)LZ4_streamHCPtr; + int prefixSize = (int)(streamPtr->end - (streamPtr->base + streamPtr->dictLimit)); + if (dictSize > 64 KB) dictSize = 64 KB; + if (dictSize < 4) dictSize = 0; + if (dictSize > prefixSize) dictSize = prefixSize; + memmove(safeBuffer, streamPtr->end - dictSize, dictSize); + { + U32 endIndex = (U32)(streamPtr->end - streamPtr->base); + streamPtr->end = (const BYTE*)safeBuffer + dictSize; + streamPtr->base = streamPtr->end - endIndex; + streamPtr->dictLimit = endIndex - dictSize; + streamPtr->lowLimit = endIndex - dictSize; + if (streamPtr->nextToUpdate < streamPtr->dictLimit) streamPtr->nextToUpdate = streamPtr->dictLimit; + } + return dictSize; } -int LZ4_compressHC_limitedOutput_withStateHC (void* state, const char* source, char* dest, int inputSize, int maxOutputSize) -{ return LZ4_compressHC2_limitedOutput_withStateHC (state, source, dest, inputSize, maxOutputSize, 0); } +/*********************************** +* Deprecated Functions +***********************************/ +/* Deprecated compression functions */ +/* These functions are planned to start generate warnings by r131 approximately */ +int LZ4_compressHC(const char* src, char* dst, int srcSize) { return LZ4_compress_HC (src, dst, srcSize, LZ4_compressBound(srcSize), 0); } +int LZ4_compressHC_limitedOutput(const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_HC(src, dst, srcSize, maxDstSize, 0); } +int LZ4_compressHC2(const char* src, char* dst, int srcSize, int cLevel) { return LZ4_compress_HC (src, dst, srcSize, LZ4_compressBound(srcSize), cLevel); } +int LZ4_compressHC2_limitedOutput(const char* src, char* dst, int srcSize, int maxDstSize, int cLevel) { return LZ4_compress_HC(src, dst, srcSize, maxDstSize, cLevel); } +int LZ4_compressHC_withStateHC (void* state, const char* src, char* dst, int srcSize) { return LZ4_compress_HC_extStateHC (state, src, dst, srcSize, LZ4_compressBound(srcSize), 0); } +int LZ4_compressHC_limitedOutput_withStateHC (void* state, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_HC_extStateHC (state, src, dst, srcSize, maxDstSize, 0); } +int LZ4_compressHC2_withStateHC (void* state, const char* src, char* dst, int srcSize, int cLevel) { return LZ4_compress_HC_extStateHC(state, src, dst, srcSize, LZ4_compressBound(srcSize), cLevel); } +int LZ4_compressHC2_limitedOutput_withStateHC (void* state, const char* src, char* dst, int srcSize, int maxDstSize, int cLevel) { return LZ4_compress_HC_extStateHC(state, src, dst, srcSize, maxDstSize, cLevel); } +int LZ4_compressHC_continue (LZ4_streamHC_t* ctx, const char* src, char* dst, int srcSize) { return LZ4_compress_HC_continue (ctx, src, dst, srcSize, LZ4_compressBound(srcSize)); } +int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* ctx, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_HC_continue (ctx, src, dst, srcSize, maxDstSize); } + + +/* Deprecated streaming functions */ +/* These functions currently generate deprecation warnings */ +int LZ4_sizeofStreamStateHC(void) { return LZ4_STREAMHCSIZE; } + +int LZ4_resetStreamStateHC(void* state, char* inputBuffer) +{ + if ((((size_t)state) & (sizeof(void*)-1)) != 0) return 1; /* Error : pointer is not aligned for pointer (32 or 64 bits) */ + LZ4HC_init((LZ4HC_Data_Structure*)state, (const BYTE*)inputBuffer); + ((LZ4HC_Data_Structure*)state)->inputBuffer = (BYTE*)inputBuffer; + return 0; +} -/**************************** - Stream functions -****************************/ +void* LZ4_createHC (char* inputBuffer) +{ + void* hc4 = ALLOCATOR(1, sizeof(LZ4HC_Data_Structure)); + LZ4HC_init ((LZ4HC_Data_Structure*)hc4, (const BYTE*)inputBuffer); + ((LZ4HC_Data_Structure*)hc4)->inputBuffer = (BYTE*)inputBuffer; + return hc4; +} -int LZ4_compressHC_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize) +int LZ4_freeHC (void* LZ4HC_Data) { - return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, 0, 0, noLimit); + FREEMEM(LZ4HC_Data); + return (0); } int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel) @@ -881,12 +717,14 @@ int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, 0, compressionLevel, noLimit); } -int LZ4_compressHC_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize) +int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel) { - return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, maxOutputSize, 0, limitedOutput); + return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, maxOutputSize, compressionLevel, limitedOutput); } -int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel) +char* LZ4_slideInputBufferHC(void* LZ4HC_Data) { - return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, maxOutputSize, compressionLevel, limitedOutput); + LZ4HC_Data_Structure* hc4 = (LZ4HC_Data_Structure*)LZ4HC_Data; + int dictSize = LZ4_saveDictHC((LZ4_streamHC_t*)LZ4HC_Data, (char*)(hc4->inputBuffer), 64 KB); + return (char*)(hc4->inputBuffer + dictSize); } diff --git a/src/lz4hc.h b/src/lz4hc.h index 372f7ba..431f7c8 100644 --- a/src/lz4hc.h +++ b/src/lz4hc.h @@ -1,60 +1,189 @@ -/* - LZ4 HC - High Compression Mode of LZ4 - 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 - - -int LZ4_compressHC (const char* source, char* dest, int isize); - -/* -LZ4_compressHC : - return : the number of bytes in compressed buffer dest - 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 evaluation is provided by function LZ4_compressBound() (see "lz4.h") -*/ - - -/* Note : -Decompression functions are provided within regular LZ4 source code (see "lz4.h") (BSD license) -*/ - - -#if defined (__cplusplus) -} -#endif +/* + LZ4 HC - High Compression Mode of LZ4 + Header File + Copyright (C) 2011-2015, 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 : + - LZ4 source repository : https://github.com/Cyan4973/lz4 + - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c +*/ +#pragma once + + +#if defined (__cplusplus) +extern "C" { +#endif + +/***************************** +* Includes +*****************************/ +#include /* size_t */ + + +/************************************** +* Block Compression +**************************************/ +int LZ4_compress_HC (const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel); +/* +LZ4_compress_HC : + Destination buffer 'dst' must be already allocated. + Compression completion is guaranteed if 'dst' buffer is sized to handle worst circumstances (data not compressible) + Worst size evaluation is provided by function LZ4_compressBound() (see "lz4.h") + srcSize : Max supported value is LZ4_MAX_INPUT_SIZE (see "lz4.h") + compressionLevel : Recommended values are between 4 and 9, although any value between 0 and 16 will work. + 0 means "use default value" (see lz4hc.c). + Values >16 behave the same as 16. + return : the number of bytes written into buffer 'dst' + or 0 if compression fails. +*/ + + +/* Note : + Decompression functions are provided within LZ4 source code (see "lz4.h") (BSD license) +*/ + + +int LZ4_sizeofStateHC(void); +int LZ4_compress_HC_extStateHC(void* state, const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel); +/* +LZ4_compress_HC_extStateHC() : + Use this function if you prefer to manually allocate memory for compression tables. + To know how much memory must be allocated for the compression tables, use : + int LZ4_sizeofStateHC(); + + Allocated memory must be aligned on 8-bytes boundaries (which a normal malloc() will do properly). + + The allocated memory can then be provided to the compression functions using 'void* state' parameter. + LZ4_compress_HC_extStateHC() is equivalent to previously described function. + It just uses externally allocated memory for stateHC. +*/ + + +/************************************** +* Streaming Compression +**************************************/ +#define LZ4_STREAMHCSIZE 262192 +#define LZ4_STREAMHCSIZE_SIZET (LZ4_STREAMHCSIZE / sizeof(size_t)) +typedef struct { size_t table[LZ4_STREAMHCSIZE_SIZET]; } LZ4_streamHC_t; +/* + LZ4_streamHC_t + This structure allows static allocation of LZ4 HC streaming state. + State must then be initialized using LZ4_resetStreamHC() before first use. + + Static allocation should only be used in combination with static linking. + If you want to use LZ4 as a DLL, please use construction functions below, which are future-proof. +*/ + + +LZ4_streamHC_t* LZ4_createStreamHC(void); +int LZ4_freeStreamHC (LZ4_streamHC_t* streamHCPtr); +/* + These functions create and release memory for LZ4 HC streaming state. + Newly created states are already initialized. + Existing state space can be re-used anytime using LZ4_resetStreamHC(). + If you use LZ4 as a DLL, use these functions instead of static structure allocation, + to avoid size mismatch between different versions. +*/ + +void LZ4_resetStreamHC (LZ4_streamHC_t* streamHCPtr, int compressionLevel); +int LZ4_loadDictHC (LZ4_streamHC_t* streamHCPtr, const char* dictionary, int dictSize); + +int LZ4_compress_HC_continue (LZ4_streamHC_t* streamHCPtr, const char* src, char* dst, int srcSize, int maxDstSize); + +int LZ4_saveDictHC (LZ4_streamHC_t* streamHCPtr, char* safeBuffer, int maxDictSize); + +/* + These functions compress data in successive blocks of any size, using previous blocks as dictionary. + One key assumption is that previous blocks (up to 64 KB) remain read-accessible while compressing next blocks. + There is an exception for ring buffers, which can be smaller 64 KB. + Such case is automatically detected and correctly handled by LZ4_compress_HC_continue(). + + Before starting compression, state must be properly initialized, using LZ4_resetStreamHC(). + A first "fictional block" can then be designated as initial dictionary, using LZ4_loadDictHC() (Optional). + + Then, use LZ4_compress_HC_continue() to compress each successive block. + It works like LZ4_compress_HC(), but use previous memory blocks as dictionary to improve compression. + Previous memory blocks (including initial dictionary when present) must remain accessible and unmodified during compression. + As a reminder, size 'dst' buffer to handle worst cases, using LZ4_compressBound(), to ensure success of compression operation. + + If, for any reason, previous data blocks can't be preserved unmodified in memory during next compression block, + you must save it to a safer memory space, using LZ4_saveDictHC(). + Return value of LZ4_saveDictHC() is the size of dictionary effectively saved into 'safeBuffer'. +*/ + + + +/************************************** +* Deprecated Functions +**************************************/ +/* Deprecate Warnings */ +/* Should these warnings messages be a problem, + it is generally possible to disable them, + with -Wno-deprecated-declarations for gcc + or _CRT_SECURE_NO_WARNINGS in Visual for example. + You can also define LZ4_DEPRECATE_WARNING_DEFBLOCK. */ +#ifndef LZ4_DEPRECATE_WARNING_DEFBLOCK +# define LZ4_DEPRECATE_WARNING_DEFBLOCK +# define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) +# if (LZ4_GCC_VERSION >= 405) || defined(__clang__) +# define LZ4_DEPRECATED(message) __attribute__((deprecated(message))) +# elif (LZ4_GCC_VERSION >= 301) +# define LZ4_DEPRECATED(message) __attribute__((deprecated)) +# elif defined(_MSC_VER) +# define LZ4_DEPRECATED(message) __declspec(deprecated(message)) +# else +# pragma message("WARNING: You need to implement LZ4_DEPRECATED for this compiler") +# define LZ4_DEPRECATED(message) +# endif +#endif // LZ4_DEPRECATE_WARNING_DEFBLOCK + +/* compression functions */ +/* these functions are planned to trigger warning messages by r131 approximately */ +int LZ4_compressHC (const char* source, char* dest, int inputSize); +int LZ4_compressHC_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize); +int LZ4_compressHC2 (const char* source, char* dest, int inputSize, int compressionLevel); +int LZ4_compressHC2_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); +int LZ4_compressHC_withStateHC (void* state, const char* source, char* dest, int inputSize); +int LZ4_compressHC_limitedOutput_withStateHC (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); +int LZ4_compressHC2_withStateHC (void* state, const char* source, char* dest, int inputSize, int compressionLevel); +int LZ4_compressHC2_limitedOutput_withStateHC(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); +int LZ4_compressHC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize); +int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize); + +/* Streaming functions following the older model; should no longer be used */ +LZ4_DEPRECATED("use LZ4_createStreamHC() instead") void* LZ4_createHC (char* inputBuffer); +LZ4_DEPRECATED("use LZ4_saveDictHC() instead") char* LZ4_slideInputBufferHC (void* LZ4HC_Data); +LZ4_DEPRECATED("use LZ4_freeStreamHC() instead") int LZ4_freeHC (void* LZ4HC_Data); +LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_createStreamHC() instead") int LZ4_sizeofStreamStateHC(void); +LZ4_DEPRECATED("use LZ4_resetStreamHC() instead") int LZ4_resetStreamStateHC(void* state, char* inputBuffer); + + +#if defined (__cplusplus) +} +#endif diff --git a/src/python-lz4.c b/src/python-lz4.c index 45fe995..b4f8e27 100644 --- a/src/python-lz4.c +++ b/src/python-lz4.c @@ -55,6 +55,40 @@ static inline uint32_t load_le32(const char *c) { static const int hdr_size = sizeof(uint32_t); + +static PyObject *py_lz4_compress_fast(PyObject *self, PyObject *args) { + PyObject *result; + const char *source; + int source_size; + char *dest; + int dest_size; + int acceleration; + + if (!PyArg_ParseTuple(args, "s#I", &source, &source_size, &acceleration)) + return NULL; + + dest_size = hdr_size + LZ4_compressBound(source_size); + result = PyBytes_FromStringAndSize(NULL, dest_size); + if (result == NULL) { + return NULL; + } + dest = PyBytes_AS_STRING(result); + store_le32(dest, source_size); + if (source_size > 0) { + //int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) + int osize = LZ4_compress_fast(source, dest + hdr_size, source_size, LZ4_compressBound(source_size), acceleration); + int actual_size = hdr_size + osize; + /* Resizes are expensive; tolerate some slop to avoid. */ + if (actual_size < (dest_size / 4) * 3) { + _PyBytes_Resize(&result, actual_size); + } else { + Py_SIZE(result) = actual_size; + } + } + return result; +} + + static PyObject *compress_with(compressor compress, PyObject *self, PyObject *args) { PyObject *result; const char *source; @@ -125,15 +159,22 @@ static PyObject *py_lz4_uncompress(PyObject *self, PyObject *args) { return result; } +static PyObject *py_lz4_versionnumber(PyObject *self, PyObject *args) { + return Py_BuildValue("i", LZ4_versionNumber()); +} + static PyMethodDef Lz4Methods[] = { + {"LZ4_compress_fast", py_lz4_compress_fast, METH_VARARGS, COMPRESSFAST_DOCSTRING}, {"LZ4_compress", py_lz4_compress, METH_VARARGS, COMPRESS_DOCSTRING}, {"LZ4_uncompress", py_lz4_uncompress, METH_VARARGS, UNCOMPRESS_DOCSTRING}, {"compress", py_lz4_compress, METH_VARARGS, COMPRESS_DOCSTRING}, + {"compress_fast", py_lz4_compress_fast, METH_VARARGS, COMPRESS_DOCSTRING}, {"compressHC", py_lz4_compressHC, METH_VARARGS, COMPRESSHC_DOCSTRING}, {"uncompress", py_lz4_uncompress, METH_VARARGS, UNCOMPRESS_DOCSTRING}, {"decompress", py_lz4_uncompress, METH_VARARGS, UNCOMPRESS_DOCSTRING}, {"dumps", py_lz4_compress, METH_VARARGS, COMPRESS_DOCSTRING}, {"loads", py_lz4_uncompress, METH_VARARGS, UNCOMPRESS_DOCSTRING}, + {"lz4version", py_lz4_versionnumber, METH_VARARGS, "Returns the version number of the lz4 C library"}, {NULL, NULL, 0, NULL} }; @@ -204,7 +245,9 @@ void initlz4(void) PyModule_AddStringConstant(module, "VERSION", VERSION); PyModule_AddStringConstant(module, "__version__", VERSION); +#ifdef LZ4_VERSION /* Only defined if we're building against bundled lz4 */ PyModule_AddStringConstant(module, "LZ4_VERSION", LZ4_VERSION); +#endif #if PY_MAJOR_VERSION >= 3 return module; diff --git a/src/python-lz4.h b/src/python-lz4.h index 70e81ac..d395397 100644 --- a/src/python-lz4.h +++ b/src/python-lz4.h @@ -32,11 +32,13 @@ #include "Python.h" static PyObject *py_lz4_compress(PyObject *self, PyObject *args); +static PyObject *py_lz4_compress_fast(PyObject *self, PyObject *args); static PyObject *py_lz4_uncompress(PyObject *self, PyObject *args); PyMODINIT_FUNC initlz4(void); #define COMPRESS_DOCSTRING "Compress string, returning the compressed data.\nRaises an exception if any error occurs." +#define COMPRESSFAST_DOCSTRING "Compress string with the given acceleration, returning the compressed data.\nRaises an exception if any error occurs." #define COMPRESSHC_DOCSTRING COMPRESS_DOCSTRING "\n\nCompared to compress, this gives a better compression ratio, but is much slower." #define UNCOMPRESS_DOCSTRING "Decompress string, returning the uncompressed data.\nRaises an exception if any error occurs."