diff --git a/uppsrc/Core/lib/lz4.c b/uppsrc/Core/lib/lz4.c index 08cf6b5cd..179408da4 100644 --- a/uppsrc/Core/lib/lz4.c +++ b/uppsrc/Core/lib/lz4.c @@ -1,6 +1,6 @@ /* LZ4 - Fast LZ compression algorithm - Copyright (C) 2011-2015, Yann Collet. + Copyright (C) 2011-2017, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -28,20 +28,22 @@ 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 + - LZ4 homepage : http://www.lz4.org + - LZ4 source repository : https://github.com/lz4/lz4 */ -/************************************** +/*-************************************ * Tuning parameters **************************************/ /* - * HEAPMODE : + * LZ4_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 malloc()). */ -#define HEAPMODE 0 +#ifndef LZ4_HEAPMODE +# define LZ4_HEAPMODE 0 +#endif /* * ACCELERATION_DEFAULT : @@ -50,9 +52,30 @@ #define ACCELERATION_DEFAULT 1 -/************************************** +/*-************************************ * CPU Feature Detection **************************************/ +/* LZ4_FORCE_MEMORY_ACCESS + * By default, access to unaligned memory is controlled by `memcpy()`, which is safe and portable. + * Unfortunately, on some target/compiler combinations, the generated assembly is sub-optimal. + * The below switch allow to select different access method for improved performance. + * Method 0 (default) : use `memcpy()`. Safe and portable. + * Method 1 : `__packed` statement. It depends on compiler extension (ie, not portable). + * This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`. + * Method 2 : direct access. This method is portable but violate C standard. + * It can generate buggy code on targets which assembly generation depends on alignment. + * But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6) + * See https://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details. + * Prefer these methods in priority order (0 > 1 > 2) + */ +#ifndef LZ4_FORCE_MEMORY_ACCESS /* can be defined externally */ +# if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) ) +# define LZ4_FORCE_MEMORY_ACCESS 2 +# elif defined(__INTEL_COMPILER) || defined(__GNUC__) +# define LZ4_FORCE_MEMORY_ACCESS 1 +# endif +#endif + /* * LZ4_FORCE_SW_BITCOUNT * Define this parameter if your target system or compiler does not support hardware bit count @@ -62,34 +85,61 @@ #endif -/************************************** -* Includes +/*-************************************ +* Dependency **************************************/ #include "lz4.h" +/* see also "memory routines" below */ -/************************************** +/*-************************************ * Compiler Options **************************************/ #ifdef _MSC_VER /* Visual Studio */ -# define FORCE_INLINE static __forceinline # include # pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ # pragma warning(disable : 4293) /* disable: C4293: too large shift (32-bits) */ -#else -# 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 -# endif /* __STDC_VERSION__ */ #endif /* _MSC_VER */ -/* LZ4_GCC_VERSION is defined into lz4.h */ -#if (LZ4_GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__) +#ifndef LZ4_FORCE_INLINE +# ifdef _MSC_VER /* Visual Studio */ +# define LZ4_FORCE_INLINE static __forceinline +# else +# if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */ +# ifdef __GNUC__ +# define LZ4_FORCE_INLINE static inline __attribute__((always_inline)) +# else +# define LZ4_FORCE_INLINE static inline +# endif +# else +# define LZ4_FORCE_INLINE static +# endif /* __STDC_VERSION__ */ +# endif /* _MSC_VER */ +#endif /* LZ4_FORCE_INLINE */ + +/* LZ4_FORCE_O2_GCC_PPC64LE and LZ4_FORCE_O2_INLINE_GCC_PPC64LE + * Gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy, + * together with a simple 8-byte copy loop as a fall-back path. + * However, this optimization hurts the decompression speed by >30%, + * because the execution does not go to the optimized loop + * for typical compressible data, and all of the preamble checks + * before going to the fall-back path become useless overhead. + * This optimization happens only with the -O3 flag, and -O2 generates + * a simple 8-byte copy loop. + * With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy + * functions are annotated with __attribute__((optimize("O2"))), + * and also LZ4_wildCopy is forcibly inlined, so that the O2 attribute + * of LZ4_wildCopy does not affect the compression speed. + */ +#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__) +# define LZ4_FORCE_O2_GCC_PPC64LE __attribute__((optimize("O2"))) +# define LZ4_FORCE_O2_INLINE_GCC_PPC64LE __attribute__((optimize("O2"))) LZ4_FORCE_INLINE +#else +# define LZ4_FORCE_O2_GCC_PPC64LE +# define LZ4_FORCE_O2_INLINE_GCC_PPC64LE static +#endif + +#if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__) # define expect(expr,value) (__builtin_expect ((expr),(value)) ) #else # define expect(expr,value) (expr) @@ -99,7 +149,7 @@ #define unlikely(expr) expect((expr) != 0, 0) -/************************************** +/*-************************************ * Memory routines **************************************/ #include /* malloc, calloc, free */ @@ -109,54 +159,100 @@ #define MEM_INIT memset -/************************************** +/*-************************************ * Basic Types **************************************/ -#if defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */ +#if defined(__cplusplus) || (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; + typedef uintptr_t uptrval; #else typedef unsigned char BYTE; typedef unsigned short U16; typedef unsigned int U32; typedef signed int S32; typedef unsigned long long U64; + typedef size_t uptrval; /* generally true, except OpenVMS-64 */ #endif +#if defined(__x86_64__) + typedef U64 reg_t; /* 64-bits in x32 mode */ +#else + typedef size_t reg_t; /* 32-bits in x32 mode */ +#endif -/************************************** +/*-************************************ * Reading and writing into memory **************************************/ -#define STEPSIZE sizeof(size_t) - -static unsigned LZ4_64bits(void) { return sizeof(void*)==8; } - static unsigned LZ4_isLittleEndian(void) { - const union { U32 i; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */ + const union { U32 u; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */ return one.c[0]; } +#if defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==2) +/* lie to the compiler about data alignment; use with caution */ + +static U16 LZ4_read16(const void* memPtr) { return *(const U16*) memPtr; } +static U32 LZ4_read32(const void* memPtr) { return *(const U32*) memPtr; } +static reg_t LZ4_read_ARCH(const void* memPtr) { return *(const reg_t*) memPtr; } + +static void LZ4_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; } +static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; } + +#elif defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==1) + +/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */ +/* currently only defined for gcc and icc */ +typedef union { U16 u16; U32 u32; reg_t uArch; } __attribute__((packed)) unalign; + +static U16 LZ4_read16(const void* ptr) { return ((const unalign*)ptr)->u16; } +static U32 LZ4_read32(const void* ptr) { return ((const unalign*)ptr)->u32; } +static reg_t LZ4_read_ARCH(const void* ptr) { return ((const unalign*)ptr)->uArch; } + +static void LZ4_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; } +static void LZ4_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; } + +#else /* safe and portable access through memcpy() */ + static U16 LZ4_read16(const void* memPtr) { - U16 val16; - memcpy(&val16, memPtr, 2); - return val16; + U16 val; memcpy(&val, memPtr, sizeof(val)); return val; } +static U32 LZ4_read32(const void* memPtr) +{ + U32 val; memcpy(&val, memPtr, sizeof(val)); return val; +} + +static reg_t LZ4_read_ARCH(const void* memPtr) +{ + reg_t val; memcpy(&val, memPtr, sizeof(val)); return val; +} + +static void LZ4_write16(void* memPtr, U16 value) +{ + memcpy(memPtr, &value, sizeof(value)); +} + +static void LZ4_write32(void* memPtr, U32 value) +{ + memcpy(memPtr, &value, sizeof(value)); +} + +#endif /* LZ4_FORCE_MEMORY_ACCESS */ + + static U16 LZ4_readLE16(const void* memPtr) { - if (LZ4_isLittleEndian()) - { + if (LZ4_isLittleEndian()) { return LZ4_read16(memPtr); - } - else - { + } else { const BYTE* p = (const BYTE*)memPtr; return (U16)((U16)p[0] + (p[1]<<8)); } @@ -164,63 +260,40 @@ static U16 LZ4_readLE16(const void* memPtr) static void LZ4_writeLE16(void* memPtr, U16 value) { - if (LZ4_isLittleEndian()) - { - memcpy(memPtr, &value, 2); - } - else - { + if (LZ4_isLittleEndian()) { + LZ4_write16(memPtr, value); + } else { BYTE* p = (BYTE*)memPtr; p[0] = (BYTE) value; p[1] = (BYTE)(value>>8); } } -static U32 LZ4_read32(const void* memPtr) +static void LZ4_copy8(void* dst, const void* src) { - U32 val32; - memcpy(&val32, memPtr, 4); - return val32; + memcpy(dst,src,8); } -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) +/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */ +LZ4_FORCE_O2_INLINE_GCC_PPC64LE +void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd) { BYTE* d = (BYTE*)dstPtr; const BYTE* s = (const BYTE*)srcPtr; - BYTE* e = (BYTE*)dstEnd; + BYTE* const e = (BYTE*)dstEnd; + do { LZ4_copy8(d,s); d+=8; s+=8; } while (d=2) +# include +# define DEBUGLOG(l, ...) { \ + if (l<=LZ4_DEBUG) { \ + fprintf(stderr, __FILE__ ": "); \ + fprintf(stderr, __VA_ARGS__); \ + fprintf(stderr, " \n"); \ + } } +#else +# define DEBUGLOG(l, ...) {} /* disabled */ +#endif -/************************************** +/*-************************************ * Common functions **************************************/ -static unsigned LZ4_NbCommonBytes (register size_t val) +static unsigned LZ4_NbCommonBytes (register reg_t val) { - if (LZ4_isLittleEndian()) - { - if (LZ4_64bits()) - { + if (LZ4_isLittleEndian()) { + if (sizeof(val)==8) { # if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) unsigned long r = 0; _BitScanForward64( &r, (U64)val ); return (int)(r>>3); -# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT) +# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !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 */ - { + } 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) +# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !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()) - { + } else /* Big Endian CPU */ { + if (sizeof(val)==8) { /* 64-bits */ # 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) +# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) return (__builtin_clzll((U64)val) >> 3); # else + static const U32 by32 = sizeof(val)*4; /* 32 on 64 bits (goal), 16 on 32 bits. + Just to avoid some static analyzer complaining about shift by 32 on 32-bits target. + Note that this code path is never triggered in 32-bits mode. */ unsigned r; - if (!(val>>32)) { r=4; } else { r=0; val>>=32; } + if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; } if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } r += (!val); return r; # endif - } - else /* 32 bits */ - { + } 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) +# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) return (__builtin_clz((U32)val) >> 3); # else unsigned r; @@ -312,19 +391,19 @@ static unsigned LZ4_NbCommonBytes (register size_t val) } } +#define STEPSIZE sizeof(reg_t) 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 */ -/************************************** +/*-************************************ * Local Structures and types **************************************/ -typedef struct { - U32 hashTable[HASH_SIZE_U32]; - U32 currentOffset; - U32 initCheck; - const BYTE* dictionary; - BYTE* bufferStart; /* obsolete, used for slideInputBuffer */ - U32 dictSize; -} LZ4_stream_t_internal; - typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive; typedef enum { byPtr, byU32, byU16 } tableType_t; @@ -365,44 +431,43 @@ typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; typedef enum { full = 0, partial = 1 } earlyEnd_directive; -/************************************** +/*-************************************ * Local Utils **************************************/ int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; } +const char* LZ4_versionString(void) { return LZ4_VERSION_STRING; } int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } int LZ4_sizeofState() { return LZ4_STREAMSIZE; } - -/******************************** +/*-****************************** * Compression functions ********************************/ - -static U32 LZ4_hashSequence(U32 sequence, tableType_t const tableType) +static U32 LZ4_hash4(U32 sequence, tableType_t const tableType) { if (tableType == byU16) - return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1))); + return ((sequence * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1))); else - return (((sequence) * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG)); + return ((sequence * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG)); } -static const U64 prime5bytes = 889523592379ULL; -static U32 LZ4_hashSequence64(size_t sequence, tableType_t const tableType) +static U32 LZ4_hash5(U64 sequence, tableType_t const tableType) { + static const U64 prime5bytes = 889523592379ULL; + static const U64 prime8bytes = 11400714785074694791ULL; const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG; - const U32 hashMask = (1<> (40 - hashLog)) & hashMask; + if (LZ4_isLittleEndian()) + return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog)); + else + return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog)); } -static U32 LZ4_hashSequenceT(size_t sequence, tableType_t const tableType) +LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType) { - if (LZ4_64bits()) - return LZ4_hashSequence64(sequence, tableType); - return LZ4_hashSequence((U32)sequence, tableType); + if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType); + return LZ4_hash4(LZ4_read32(p), 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 const tableType, const BYTE* srcBase) { switch (tableType) @@ -413,27 +478,30 @@ static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableTy } } -static void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) +LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) { - U32 h = LZ4_hashPosition(p, tableType); + U32 const h = LZ4_hashPosition(p, tableType); LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase); } static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) { if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; } - if (tableType == byU32) { U32* hashTable = (U32*) tableBase; return hashTable[h] + srcBase; } - { U16* hashTable = (U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */ + if (tableType == byU32) { const U32* const hashTable = (U32*) tableBase; return hashTable[h] + srcBase; } + { const U16* const hashTable = (U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */ } -static const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) +LZ4_FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) { - U32 h = LZ4_hashPosition(p, tableType); + U32 const h = LZ4_hashPosition(p, tableType); return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase); } -FORCE_INLINE int LZ4_compress_generic( - void* const ctx, + +/** LZ4_compress_generic() : + inlined, to ensure branches are decided at compilation time */ +LZ4_FORCE_INLINE int LZ4_compress_generic( + LZ4_stream_t_internal* const cctx, const char* const source, char* const dest, const int inputSize, @@ -444,15 +512,13 @@ FORCE_INLINE int LZ4_compress_generic( const dictIssue_directive dictIssue, const U32 acceleration) { - LZ4_stream_t_internal* const dictPtr = (LZ4_stream_t_internal*)ctx; - const BYTE* ip = (const BYTE*) source; const BYTE* base; const BYTE* lowLimit; - const BYTE* const lowRefLimit = ip - dictPtr->dictSize; - const BYTE* const dictionary = dictPtr->dictionary; - const BYTE* const dictEnd = dictionary + dictPtr->dictSize; - const size_t dictDelta = dictEnd - (const BYTE*)source; + const BYTE* const lowRefLimit = ip - cctx->dictSize; + const BYTE* const dictionary = cctx->dictionary; + const BYTE* const dictEnd = dictionary + cctx->dictSize; + const ptrdiff_t dictDelta = dictEnd - (const BYTE*)source; const BYTE* anchor = (const BYTE*) source; const BYTE* const iend = ip + inputSize; const BYTE* const mflimit = iend - MFLIMIT; @@ -462,10 +528,9 @@ FORCE_INLINE int LZ4_compress_generic( BYTE* const olimit = op + maxOutputSize; U32 forwardH; - size_t refDelta=0; /* Init conditions */ - if ((U32)inputSize > (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 inputSize, too large (or negative) */ switch(dict) { case noDict: @@ -474,11 +539,11 @@ FORCE_INLINE int LZ4_compress_generic( lowLimit = (const BYTE*)source; break; case withPrefix64k: - base = (const BYTE*)source - dictPtr->currentOffset; - lowLimit = (const BYTE*)source - dictPtr->dictSize; + base = (const BYTE*)source - cctx->currentOffset; + lowLimit = (const BYTE*)source - cctx->dictSize; break; case usingExtDict: - base = (const BYTE*)source - dictPtr->currentOffset; + base = (const BYTE*)source - cctx->currentOffset; lowLimit = (const BYTE*)source; break; } @@ -486,44 +551,38 @@ FORCE_INLINE int LZ4_compress_generic( if (inputSizehashTable, tableType, base); ip++; forwardH = LZ4_hashPosition(ip, tableType); /* Main Loop */ - for ( ; ; ) - { + for ( ; ; ) { + ptrdiff_t refDelta = 0; const BYTE* match; BYTE* token; - { - const BYTE* forwardIp = ip; + + /* Find a match */ + { const BYTE* forwardIp = ip; unsigned step = 1; unsigned searchMatchNb = acceleration << LZ4_skipTrigger; - - /* Find a match */ do { - U32 h = forwardH; + U32 const h = forwardH; ip = forwardIp; forwardIp += step; step = (searchMatchNb++ >> LZ4_skipTrigger); if (unlikely(forwardIp > mflimit)) goto _last_literals; - match = LZ4_getPositionOnHash(h, ctx, tableType, base); - if (dict==usingExtDict) - { - if (match<(const BYTE*)source) - { + match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base); + if (dict==usingExtDict) { + if (match < (const BYTE*)source) { refDelta = dictDelta; lowLimit = dictionary; - } - else - { + } else { refDelta = 0; lowLimit = (const BYTE*)source; - } - } + } } forwardH = LZ4_hashPosition(forwardIp, tableType); - LZ4_putPositionOnHash(ip, h, ctx, tableType, base); + LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base); } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0) || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip)) @@ -531,18 +590,17 @@ FORCE_INLINE int LZ4_compress_generic( } /* Catch up */ - while ((ip>anchor) && (match+refDelta > lowLimit) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; } + while (((ip>anchor) & (match+refDelta > lowLimit)) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; } - { - /* Encode Literal length */ - unsigned litLength = (unsigned)(ip - anchor); + /* Encode Literals */ + { unsigned const litLength = (unsigned)(ip - anchor); token = op++; - if ((outputLimited) && (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit))) - return 0; /* Check output limit */ - if (litLength>=RUN_MASK) - { + if ((outputLimited) && /* Check output buffer overflow */ + (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit))) + return 0; + if (litLength >= RUN_MASK) { int len = (int)litLength-RUN_MASK; - *token=(RUN_MASK<= 255 ; len-=255) *op++ = 255; *op++ = (BYTE)len; } @@ -558,41 +616,41 @@ _next_match: LZ4_writeLE16(op, (U16)(ip-match)); op+=2; /* Encode MatchLength */ - { - unsigned matchLength; + { unsigned matchCode; - if ((dict==usingExtDict) && (lowLimit==dictionary)) - { + if ((dict==usingExtDict) && (lowLimit==dictionary)) { const BYTE* limit; match += refDelta; limit = ip + (dictEnd-match); if (limit > matchlimit) limit = matchlimit; - matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, limit); - ip += MINMATCH + matchLength; - if (ip==limit) - { - unsigned more = LZ4_count(ip, (const BYTE*)source, matchlimit); - matchLength += more; + matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit); + ip += MINMATCH + matchCode; + if (ip==limit) { + unsigned const more = LZ4_count(ip, (const BYTE*)source, matchlimit); + matchCode += more; ip += more; } - } - else - { - matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit); - ip += MINMATCH + matchLength; + } else { + matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit); + ip += MINMATCH + matchCode; } - if ((outputLimited) && (unlikely(op + (1 + LASTLITERALS) + (matchLength>>8) > olimit))) - return 0; /* Check output limit */ - if (matchLength>=ML_MASK) - { + if ( outputLimited && /* Check output buffer overflow */ + (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) ) + return 0; + if (matchCode >= ML_MASK) { *token += ML_MASK; - matchLength -= ML_MASK; - for (; matchLength >= 510 ; matchLength-=510) { *op++ = 255; *op++ = 255; } - if (matchLength >= 255) { matchLength-=255; *op++ = 255; } - *op++ = (BYTE)matchLength; - } - else *token += (BYTE)(matchLength); + matchCode -= ML_MASK; + LZ4_write32(op, 0xFFFFFFFF); + while (matchCode >= 4*255) { + op+=4; + LZ4_write32(op, 0xFFFFFFFF); + matchCode -= 4*255; + } + op += matchCode / 255; + *op++ = (BYTE)(matchCode % 255); + } else + *token += (BYTE)(matchCode); } anchor = ip; @@ -601,24 +659,19 @@ _next_match: if (ip > mflimit) break; /* Fill table */ - LZ4_putPosition(ip-2, ctx, tableType, base); + LZ4_putPosition(ip-2, cctx->hashTable, tableType, base); /* Test next position */ - match = LZ4_getPosition(ip, ctx, tableType, base); - if (dict==usingExtDict) - { - if (match<(const BYTE*)source) - { + match = LZ4_getPosition(ip, cctx->hashTable, tableType, base); + if (dict==usingExtDict) { + if (match < (const BYTE*)source) { refDelta = dictDelta; lowLimit = dictionary; - } - else - { + } else { refDelta = 0; lowLimit = (const BYTE*)source; - } - } - LZ4_putPosition(ip, ctx, tableType, base); + } } + LZ4_putPosition(ip, cctx->hashTable, tableType, base); if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1) && (match+MAX_DISTANCE>=ip) && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) ) @@ -630,19 +683,16 @@ _next_match: _last_literals: /* Encode Last Literals */ - { - 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 >= RUN_MASK) - { + { size_t const lastRun = (size_t)(iend - anchor); + if ( (outputLimited) && /* Check output buffer overflow */ + ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) ) + return 0; + if (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 - { + } else { *op++ = (BYTE)(lastRun<internal_donotuse; LZ4_resetStream((LZ4_stream_t*)state); if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; - if (maxOutputSize >= LZ4_compressBound(inputSize)) - { + if (maxOutputSize >= LZ4_compressBound(inputSize)) { if (inputSize < LZ4_64Klimit) - return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue, acceleration); + return LZ4_compress_generic(ctx, 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 - { + return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration); + } else { if (inputSize < LZ4_64Klimit) - return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); + return LZ4_compress_generic(ctx, 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); + return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration); } } int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) { -#if (HEAPMODE) +#if (LZ4_HEAPMODE) void* ctxPtr = ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ #else LZ4_stream_t ctx; - void* ctxPtr = &ctx; + void* const ctxPtr = &ctx; #endif - int result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration); + int const result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration); -#if (HEAPMODE) +#if (LZ4_HEAPMODE) FREEMEM(ctxPtr); #endif return result; @@ -705,22 +753,21 @@ int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxO 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); + return LZ4_compress_generic(&ctx.internal_donotuse, 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); + return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, sizeof(void*)==8 ? byU32 : byPtr, noDict, noDictIssue, acceleration); } -/******************************** -* destSize variant +/*-****************************** +* *_destSize() variant ********************************/ static int LZ4_compress_destSize_generic( - void* const ctx, + LZ4_stream_t_internal* const ctx, const char* const src, char* const dst, int* const srcSizePtr, @@ -752,32 +799,30 @@ static int LZ4_compress_destSize_generic( /* First Byte */ *srcSizePtr = 0; - LZ4_putPosition(ip, ctx, tableType, base); + LZ4_putPosition(ip, ctx->hashTable, tableType, base); ip++; forwardH = LZ4_hashPosition(ip, tableType); /* Main Loop */ - for ( ; ; ) - { + for ( ; ; ) { const BYTE* match; BYTE* token; - { - const BYTE* forwardIp = ip; + + /* Find a match */ + { const BYTE* forwardIp = ip; unsigned step = 1; unsigned searchMatchNb = 1 << LZ4_skipTrigger; - /* Find a match */ do { U32 h = forwardH; ip = forwardIp; forwardIp += step; step = (searchMatchNb++ >> LZ4_skipTrigger); - if (unlikely(forwardIp > mflimit)) - goto _last_literals; + if (unlikely(forwardIp > mflimit)) goto _last_literals; - match = LZ4_getPositionOnHash(h, ctx, tableType, base); + match = LZ4_getPositionOnHash(h, ctx->hashTable, tableType, base); forwardH = LZ4_hashPosition(forwardIp, tableType); - LZ4_putPositionOnHash(ip, h, ctx, tableType, base); + LZ4_putPositionOnHash(ip, h, ctx->hashTable, tableType, base); } while ( ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip)) || (LZ4_read32(match) != LZ4_read32(ip)) ); @@ -786,18 +831,15 @@ static int LZ4_compress_destSize_generic( /* Catch up */ while ((ip>anchor) && (match > lowLimit) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; } - { - /* Encode Literal length */ - unsigned litLength = (unsigned)(ip - anchor); + /* Encode Literal length */ + { unsigned litLength = (unsigned)(ip - anchor); token = op++; - if (op + ((litLength+240)/255) + litLength > oMaxLit) - { + if (op + ((litLength+240)/255) + litLength > oMaxLit) { /* Not enough space for a last match */ op--; goto _last_literals; } - if (litLength>=RUN_MASK) - { + if (litLength>=RUN_MASK) { unsigned len = litLength - RUN_MASK; *token=(RUN_MASK<= 255 ; len-=255) *op++ = 255; @@ -815,21 +857,15 @@ _next_match: LZ4_writeLE16(op, (U16)(ip-match)); op+=2; /* Encode MatchLength */ - { - size_t matchLength; + { size_t matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit); - matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit); - - if (op + ((matchLength+240)/255) > oMaxMatch) - { + if (op + ((matchLength+240)/255) > 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) - { + if (matchLength>=ML_MASK) { *token += ML_MASK; matchLength -= ML_MASK; while (matchLength >= 255) { matchLength-=255; *op++ = 255; } @@ -845,11 +881,11 @@ _next_match: if (op > oMaxSeq) break; /* Fill table */ - LZ4_putPosition(ip-2, ctx, tableType, base); + LZ4_putPosition(ip-2, ctx->hashTable, tableType, base); /* Test next position */ - match = LZ4_getPosition(ip, ctx, tableType, base); - LZ4_putPosition(ip, ctx, tableType, base); + match = LZ4_getPosition(ip, ctx->hashTable, tableType, base); + LZ4_putPosition(ip, ctx->hashTable, tableType, base); if ( (match+MAX_DISTANCE>=ip) && (LZ4_read32(match)==LZ4_read32(ip)) ) { token=op++; *token=0; goto _next_match; } @@ -860,25 +896,20 @@ _next_match: _last_literals: /* Encode Last Literals */ - { - size_t lastRunSize = (size_t)(iend - anchor); - if (op + 1 /* token */ + ((lastRunSize+240)/255) /* litLength */ + lastRunSize /* literals */ > oend) - { + { 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) - { + 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 - { + } else { *op++ = (BYTE)(lastRunSize<= LZ4_compressBound(*srcSizePtr)) /* compression success is guaranteed */ - { + if (targetDstSize >= LZ4_compressBound(*srcSizePtr)) { /* compression success is guaranteed */ return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1); - } - else - { + } else { if (*srcSizePtr < LZ4_64Klimit) - return LZ4_compress_destSize_generic(state, src, dst, srcSizePtr, targetDstSize, byU16); + return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, byU16); else - return LZ4_compress_destSize_generic(state, src, dst, srcSizePtr, targetDstSize, LZ4_64bits() ? byU32 : byPtr); + return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, sizeof(void*)==8 ? byU32 : byPtr); } } int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize) { -#if (HEAPMODE) - void* ctx = ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ +#if (LZ4_HEAPMODE) + LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ #else LZ4_stream_t ctxBody; - void* ctx = &ctxBody; + LZ4_stream_t* ctx = &ctxBody; #endif int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize); -#if (HEAPMODE) +#if (LZ4_HEAPMODE) FREEMEM(ctx); #endif return result; @@ -928,7 +956,7 @@ int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targe -/******************************** +/*-****************************** * Streaming functions ********************************/ @@ -947,15 +975,16 @@ void LZ4_resetStream (LZ4_stream_t* LZ4_stream) int LZ4_freeStream (LZ4_stream_t* LZ4_stream) { + if (!LZ4_stream) return 0; /* support free on NULL */ FREEMEM(LZ4_stream); return (0); } -#define HASH_UNIT sizeof(size_t) +#define HASH_UNIT sizeof(reg_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; + LZ4_stream_t_internal* dict = &LZ4_dict->internal_donotuse; const BYTE* p = (const BYTE*)dictionary; const BYTE* const dictEnd = p + dictSize; const BYTE* base; @@ -963,8 +992,7 @@ int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) if ((dict->initCheck) || (dict->currentOffset > 1 GB)) /* Uninitialized structure, or reuse overflow */ LZ4_resetStream(LZ4_dict); - if (dictSize < (int)HASH_UNIT) - { + if (dictSize < (int)HASH_UNIT) { dict->dictionary = NULL; dict->dictSize = 0; return 0; @@ -977,8 +1005,7 @@ int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) dict->dictSize = (U32)(dictEnd - p); dict->currentOffset += dict->dictSize; - while (p <= dictEnd-HASH_UNIT) - { + while (p <= dictEnd-HASH_UNIT) { LZ4_putPosition(p, dict->hashTable, byU32, base); p+=3; } @@ -990,14 +1017,12 @@ int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) 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 */ - { + ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) { /* address space overflow */ /* rescale hash table */ - U32 delta = LZ4_dict->currentOffset - 64 KB; + U32 const delta = LZ4_dict->currentOffset - 64 KB; const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize; int i; - for (i=0; ihashTable[i] < delta) LZ4_dict->hashTable[i]=0; else LZ4_dict->hashTable[i] -= delta; } @@ -1010,7 +1035,7 @@ static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src) 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; + LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse; const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; const BYTE* smallest = (const BYTE*) source; @@ -1020,10 +1045,8 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, ch if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; /* Check overlapping input/dictionary space */ - { - const BYTE* sourceEnd = (const BYTE*) source + inputSize; - if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) - { + { const BYTE* sourceEnd = (const BYTE*) source + inputSize; + if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) { streamPtr->dictSize = (U32)(dictEnd - sourceEnd); if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB; if (streamPtr->dictSize < 4) streamPtr->dictSize = 0; @@ -1032,25 +1055,23 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, ch } /* prefix mode : source data follows dictionary */ - if (dictEnd == (const BYTE*)source) - { + if (dictEnd == (const BYTE*)source) { int result; if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) - result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration); + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration); else - result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration); + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration); streamPtr->dictSize += (U32)inputSize; streamPtr->currentOffset += (U32)inputSize; return result; } /* external dictionary mode */ - { - int result; + { int result; if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) - result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration); + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration); else - result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration); + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration); streamPtr->dictionary = (const BYTE*)source; streamPtr->dictSize = (U32)inputSize; streamPtr->currentOffset += (U32)inputSize; @@ -1062,15 +1083,15 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, ch /* 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; + LZ4_stream_t_internal* streamPtr = &LZ4_dict->internal_donotuse; int result; const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; const BYTE* smallest = dictEnd; if (smallest > (const BYTE*) source) smallest = (const BYTE*) source; - LZ4_renormDictT((LZ4_stream_t_internal*)LZ4_dict, smallest); + LZ4_renormDictT(streamPtr, smallest); - result = LZ4_compress_generic(LZ4_dict, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1); + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1); streamPtr->dictionary = (const BYTE*)source; streamPtr->dictSize = (U32)inputSize; @@ -1080,10 +1101,17 @@ int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* } +/*! LZ4_saveDict() : + * 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 LZ4_compress_fast_continue(). + * Return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error. + */ 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; + LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse; + const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize; if ((U32)dictSize > 64 KB) dictSize = 64 KB; /* useless to define a dictionary > 64 KB */ if ((U32)dictSize > dict->dictSize) dictSize = dict->dictSize; @@ -1098,88 +1126,79 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize) -/******************************* +/*-***************************** * Decompression functions *******************************/ -/* - * This generic decompression function cover all use cases. - * 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 optimization. +/*! LZ4_decompress_generic() : + * This generic decompression function covers all use cases. + * It shall be instantiated several times, using different sets of directives. + * Note that it is important for performance that this function really get inlined, + * in order to remove useless branches during compilation optimization. */ -FORCE_INLINE int LZ4_decompress_generic( - const char* const source, - char* const dest, - int inputSize, - int outputSize, /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */ +LZ4_FORCE_O2_GCC_PPC64LE +LZ4_FORCE_INLINE int LZ4_decompress_generic( + const char* const src, + char* const dst, + int srcSize, + int outputSize, /* If endOnInput==endOnInputSize, this value is `dstCapacity` */ int endOnInput, /* endOnOutputSize, endOnInputSize */ int partialDecoding, /* full, partial */ int targetOutputSize, /* only used if partialDecoding==partial */ int dict, /* noDict, withPrefix64k, usingExtDict */ - const BYTE* const lowPrefix, /* == dest if dict == noDict */ + const BYTE* const lowPrefix, /* == dst when no prefix */ const BYTE* const dictStart, /* only if dict==usingExtDict */ const size_t dictSize /* note : = 0 if noDict */ ) { - /* Local Variables */ - const BYTE* ip = (const BYTE*) source; - const BYTE* const iend = ip + inputSize; + const BYTE* ip = (const BYTE*) src; + const BYTE* const iend = ip + srcSize; - BYTE* op = (BYTE*) dest; + BYTE* op = (BYTE*) dst; BYTE* const oend = op + outputSize; BYTE* cpy; BYTE* oexit = op + targetOutputSize; - const BYTE* const lowLimit = lowPrefix - dictSize; const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize; - 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 unsigned dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; + const int dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3}; 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 ((srcSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */ if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1); - - /* Main Loop */ - while (1) - { - unsigned token; + /* Main Loop : decode sequences */ + while (1) { size_t length; const BYTE* match; + size_t offset; /* get literal length */ - token = *ip++; - if ((length=(token>>ML_BITS)) == RUN_MASK) - { + unsigned const token = *ip++; + if ((length=(token>>ML_BITS)) == RUN_MASK) { unsigned s; - do - { + do { s = *ip++; length += s; - } - while (likely((endOnInput)?ip(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) ) - || ((!endOnInput) && (cpy>oend-COPYLENGTH))) + if ( ((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) ) + || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) ) { - if (partialDecoding) - { + if (partialDecoding) { if (cpy > oend) goto _output_error; /* Error : write attempt beyond end of output buffer */ if ((endOnInput) && (ip+length > iend)) goto _output_error; /* Error : read attempt beyond end of input buffer */ - } - else - { + } else { if ((!endOnInput) && (cpy != oend)) goto _output_error; /* Error : block decoding must stop exactly there */ if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error; /* Error : input must be consumed */ } @@ -1192,130 +1211,112 @@ FORCE_INLINE int LZ4_decompress_generic( ip += length; op = cpy; /* get offset */ - match = cpy - LZ4_readLE16(ip); ip+=2; - if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error; /* Error : offset outside destination buffer */ + offset = LZ4_readLE16(ip); ip+=2; + match = op - offset; + if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */ + LZ4_write32(op, (U32)offset); /* costs ~1%; silence an msan warning when offset==0 */ /* get matchlength */ length = token & ML_MASK; - if (length == ML_MASK) - { + if (length == ML_MASK) { unsigned s; - do - { - if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error; + do { s = *ip++; + if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error; length += s; } while (s==255); - if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)op)) goto _output_error; /* overflow detection */ + if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */ } length += MINMATCH; /* check external dictionary */ - if ((dict==usingExtDict) && (match < lowPrefix)) - { + if ((dict==usingExtDict) && (match < lowPrefix)) { if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error; /* doesn't respect parsing restriction */ - if (length <= (size_t)(lowPrefix-match)) - { + if (length <= (size_t)(lowPrefix-match)) { /* match can be copied as a single segment from external dictionary */ - match = dictEnd - (lowPrefix-match); - memmove(op, match, length); op += length; - } - else - { - /* match encompass external dictionary and current segment */ - size_t copySize = (size_t)(lowPrefix-match); + memmove(op, dictEnd - (lowPrefix-match), length); + op += length; + } else { + /* match encompass external dictionary and current block */ + size_t const copySize = (size_t)(lowPrefix-match); + size_t const restSize = length - copySize; memcpy(op, dictEnd - copySize, copySize); op += copySize; - copySize = length - copySize; - if (copySize > (size_t)(op-lowPrefix)) /* overlap within current segment */ - { - BYTE* const endOfMatch = op + copySize; + if (restSize > (size_t)(op-lowPrefix)) { /* overlap copy */ + BYTE* const endOfMatch = op + restSize; const BYTE* copyFrom = lowPrefix; while (op < endOfMatch) *op++ = *copyFrom++; - } - else - { - memcpy(op, lowPrefix, copySize); - op += copySize; - } - } + } else { + memcpy(op, lowPrefix, restSize); + op += restSize; + } } continue; } - /* copy repeated sequence */ + /* copy match within block */ cpy = op + length; - if (unlikely((op-match)<8)) - { - const size_t dec64 = dec64table[op-match]; + if (unlikely(offset<8)) { + const int dec64 = dec64table[offset]; 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; } + match += dec32table[offset]; + memcpy(op+4, match, 4); + match -= dec64; + } else { LZ4_copy8(op, match); match+=8; } + op += 8; - if (unlikely(cpy>oend-12)) - { - if (cpy > 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; + if (unlikely(cpy>oend-12)) { + BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1); + if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last LASTLITERALS bytes must be literals (uncompressed) */ + if (op < oCopyLimit) { + LZ4_wildCopy(op, match, oCopyLimit); + match += oCopyLimit - op; + op = oCopyLimit; } while (op16) LZ4_wildCopy(op+8, match+8, cpy); } - else - LZ4_wildCopy(op, match, cpy); op=cpy; /* correction */ } /* end of decoding */ if (endOnInput) - return (int) (((char*)op)-dest); /* Nb of output bytes decoded */ + return (int) (((char*)op)-dst); /* Nb of output bytes decoded */ else - return (int) (((const char*)ip)-source); /* Nb of input bytes read */ + return (int) (((const char*)ip)-src); /* Nb of input bytes read */ /* Overflow error detected */ _output_error: - return (int) (-(((const char*)ip)-source))-1; + return (int) (-(((const char*)ip)-src))-1; } +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, NULL, 0); } +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, NULL, 0); } +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_fast(const char* source, char* dest, int originalSize) { return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)(dest - 64 KB), NULL, 64 KB); } -/* streaming decompression functions */ +/*===== streaming decompression functions =====*/ -typedef struct -{ - const BYTE* externalDict; - size_t extDictSize; - const BYTE* prefixEnd; - size_t prefixSize; -} LZ4_streamDecode_t_internal; - -/* - * If you prefer dynamic allocation methods, - * LZ4_createStreamDecode() - * provides a pointer (void*) towards an initialized LZ4_streamDecode_t structure. - */ LZ4_streamDecode_t* LZ4_createStreamDecode(void) { LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(1, sizeof(LZ4_streamDecode_t)); @@ -1324,20 +1325,21 @@ LZ4_streamDecode_t* LZ4_createStreamDecode(void) int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream) { + if (!LZ4_stream) return 0; /* support free on NULL */ FREEMEM(LZ4_stream); return 0; } -/* - * LZ4_setStreamDecode - * Use this function to instruct where to find the dictionary +/*! + * LZ4_setStreamDecode() : + * Use this function to instruct where to find the dictionary. * This function is not necessary if previous data is still available where it was decoded. * Loading a size of 0 is allowed (same effect as no dictionary). * Return : 1 if OK, 0 if error */ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize) { - LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode; + LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; lz4sd->prefixSize = (size_t) dictSize; lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize; lz4sd->externalDict = NULL; @@ -1352,22 +1354,20 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti If it's not possible, save the relevant part of decoded data into a safe buffer, and indicate where it stands using LZ4_setStreamDecode() */ +LZ4_FORCE_O2_GCC_PPC64LE 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; + LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; int result; - if (lz4sd->prefixEnd == (BYTE*)dest) - { + if (lz4sd->prefixEnd == (BYTE*)dest) { 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 - { + } else { lz4sd->extDictSize = lz4sd->prefixSize; lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, @@ -1381,24 +1381,22 @@ int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const ch return result; } +LZ4_FORCE_O2_GCC_PPC64LE 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; + LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; int result; - if (lz4sd->prefixEnd == (BYTE*)dest) - { + if (lz4sd->prefixEnd == (BYTE*)dest) { 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 - { + } else { lz4sd->extDictSize = lz4sd->prefixSize; - lz4sd->externalDict = (BYTE*)dest - lz4sd->extDictSize; + lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; result = LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize); @@ -1418,12 +1416,12 @@ 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) +LZ4_FORCE_O2_GCC_PPC64LE +LZ4_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 (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); @@ -1431,24 +1429,27 @@ FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize); } +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize) { return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize); } +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize) { return LZ4_decompress_usingDict_generic(source, dest, 0, originalSize, 0, dictStart, dictSize); } /* debug function */ +LZ4_FORCE_O2_GCC_PPC64LE 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 compression functions */ @@ -1473,29 +1474,29 @@ int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; } -static void LZ4_init(LZ4_stream_t_internal* lz4ds, BYTE* base) +static void LZ4_init(LZ4_stream_t* lz4ds, BYTE* base) { - MEM_INIT(lz4ds, 0, LZ4_STREAMSIZE); - lz4ds->bufferStart = base; + MEM_INIT(lz4ds, 0, sizeof(LZ4_stream_t)); + lz4ds->internal_donotuse.bufferStart = base; } 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, (BYTE*)inputBuffer); + if ((((uptrval)state) & 3) != 0) return 1; /* Error : pointer is not aligned on 4-bytes boundary */ + LZ4_init((LZ4_stream_t*)state, (BYTE*)inputBuffer); return 0; } void* LZ4_create (char* inputBuffer) { - void* lz4ds = ALLOCATOR(8, LZ4_STREAMSIZE_U64); - LZ4_init ((LZ4_stream_t_internal*)lz4ds, (BYTE*)inputBuffer); + LZ4_stream_t* lz4ds = (LZ4_stream_t*)ALLOCATOR(8, sizeof(LZ4_stream_t)); + LZ4_init (lz4ds, (BYTE*)inputBuffer); return lz4ds; } char* LZ4_slideInputBuffer (void* LZ4_Data) { - LZ4_stream_t_internal* ctx = (LZ4_stream_t_internal*)LZ4_Data; + LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)LZ4_Data)->internal_donotuse; int dictSize = LZ4_saveDict((LZ4_stream_t*)LZ4_Data, (char*)ctx->bufferStart, 64 KB); return (char*)(ctx->bufferStart + dictSize); } @@ -1513,4 +1514,3 @@ int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int origin } #endif /* LZ4_COMMONDEFS_ONLY */ - diff --git a/uppsrc/Core/lib/lz4.h b/uppsrc/Core/lib/lz4.h index 3e7400225..d284d6300 100644 --- a/uppsrc/Core/lib/lz4.h +++ b/uppsrc/Core/lib/lz4.h @@ -1,7 +1,7 @@ /* - LZ4 - Fast LZ compression algorithm - Header File - Copyright (C) 2011-2015, Yann Collet. + * LZ4 - Fast LZ compression algorithm + * Header File + * Copyright (C) 2011-2017, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -29,52 +29,97 @@ 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 + - LZ4 homepage : http://www.lz4.org + - LZ4 source repository : https://github.com/lz4/lz4 */ -#pragma once - #if defined (__cplusplus) 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. +#ifndef LZ4_H_2983827168210 +#define LZ4_H_2983827168210 + +/* --- Dependency --- */ +#include /* size_t */ + + +/** + Introduction + + LZ4 is lossless compression algorithm, providing compression speed at 400 MB/s per core, + scalable with multi-cores CPU. It features an extremely fast decoder, with speed in + multiple GB/s per core, typically reaching RAM speed limits on multi-core systems. + + The LZ4 compression library provides in-memory compression and decompression functions. + Compression can be done in: + - a single step (described as Simple Functions) + - a single step, reusing a context (described in Advanced Functions) + - unbounded multiple steps (described as Streaming compression) + + lz4.h provides block compression functions. It gives full buffer control to user. + Decompressing an lz4-compressed block also requires metadata (such as compressed size). + Each application is free to encode such metadata in whichever way it wants. + + An additional format, called LZ4 frame specification (doc/lz4_Frame_format.md), + take care of encoding standard metadata alongside LZ4-compressed blocks. + If your application requires interoperability, it's recommended to use it. + A library is provided to take care of it, see lz4frame.h. */ -/************************************** -* Version -**************************************/ -#define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */ -#define LZ4_VERSION_MINOR 7 /* for new (non-breaking) interface capabilities */ -#define LZ4_VERSION_RELEASE 1 /* 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); +/*^*************************************************************** +* Export parameters +*****************************************************************/ +/* +* LZ4_DLL_EXPORT : +* Enable exporting of functions when building a Windows DLL +* LZ4LIB_API : +* Control library symbols visibility. +*/ +#if defined(LZ4_DLL_EXPORT) && (LZ4_DLL_EXPORT==1) +# define LZ4LIB_API __declspec(dllexport) +#elif defined(LZ4_DLL_IMPORT) && (LZ4_DLL_IMPORT==1) +# define LZ4LIB_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ +#elif defined(__GNUC__) && (__GNUC__ >= 4) +# define LZ4LIB_API __attribute__ ((__visibility__ ("default"))) +#else +# define LZ4LIB_API +#endif -/************************************** + +/*------ Version ------*/ +#define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */ +#define LZ4_VERSION_MINOR 8 /* 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) + +#define LZ4_LIB_VERSION LZ4_VERSION_MAJOR.LZ4_VERSION_MINOR.LZ4_VERSION_RELEASE +#define LZ4_QUOTE(str) #str +#define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str) +#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION) + +LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; to be used when checking dll version */ +LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; to be used when checking dll version */ + + +/*-************************************ * Tuning parameter **************************************/ -/* +/*! * LZ4_MEMORY_USAGE : * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.) * Increasing memory usage improves compression ratio * Reduced memory usage can improve speed, due to cache effect * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */ -#define LZ4_MEMORY_USAGE 14 +#ifndef LZ4_MEMORY_USAGE +# define LZ4_MEMORY_USAGE 14 +#endif - -/************************************** +/*-************************************ * Simple Functions **************************************/ - -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_default() : +/*! 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). @@ -86,9 +131,10 @@ LZ4_compress_default() : 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 + or 0 if compression fails */ +LZ4LIB_API int LZ4_compress_default(const char* source, char* dest, int sourceSize, int maxDestSize); -LZ4_decompress_safe() : +/*! LZ4_decompress_safe() : 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) @@ -97,15 +143,16 @@ LZ4_decompress_safe() : This function is protected against buffer overflow exploits, including malicious data packets. It never writes outside output buffer, nor reads outside input buffer. */ +LZ4LIB_API int LZ4_decompress_safe (const char* source, char* dest, int compressedSize, int maxDecompressedSize); -/************************************** +/*-************************************ * Advanced Functions **************************************/ #define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */ #define LZ4_COMPRESSBOUND(isize) ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16) -/* +/*! LZ4_compressBound() : 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). @@ -115,9 +162,9 @@ LZ4_compressBound() : 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); +LZ4LIB_API int LZ4_compressBound(int inputSize); -/* +/*! 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. @@ -125,21 +172,21 @@ LZ4_compress_fast() : 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_compress_fast (const char* source, char* dest, int sourceSize, int maxDestSize, int acceleration); +LZ4LIB_API int LZ4_compress_fast (const char* source, char* dest, int sourceSize, int maxDestSize, int acceleration); -/* +/*! 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_sizeofState(void); -int LZ4_compress_fast_extState (void* state, const char* source, char* dest, int inputSize, int maxDestSize, int acceleration); +LZ4LIB_API int LZ4_sizeofState(void); +LZ4LIB_API 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'. @@ -150,10 +197,10 @@ LZ4_compress_destSize() : 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); +LZ4LIB_API 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) @@ -164,9 +211,9 @@ LZ4_decompress_fast() : 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); +LZ4LIB_API 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 destination buffer 'dest' of size 'maxDecompressedSize'. @@ -178,142 +225,215 @@ LZ4_decompress_safe_partial() : 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 maxDecompressedSize); +LZ4LIB_API int LZ4_decompress_safe_partial (const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize); -/*********************************************** +/*-********************************************* * Streaming Compression Functions ***********************************************/ -#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 : 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 union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */ + +/*! LZ4_createStream() and LZ4_freeStream() : + * LZ4_createStream() will allocate and initialize an `LZ4_stream_t` structure. + * LZ4_freeStream() releases its memory. */ -typedef struct { long long table[LZ4_STREAMSIZE_U64]; } LZ4_stream_t; +LZ4LIB_API LZ4_stream_t* LZ4_createStream(void); +LZ4LIB_API int LZ4_freeStream (LZ4_stream_t* streamPtr); -/* - * LZ4_resetStream - * Use this function to init an allocated LZ4_stream_t structure +/*! LZ4_resetStream() : + * An LZ4_stream_t structure can be allocated once and re-used multiple times. + * Use this function to start compressing a new stream. */ -void LZ4_resetStream (LZ4_stream_t* streamPtr); +LZ4LIB_API 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_loadDict() : + * Use this function to load a static dictionary into LZ4_stream_t. + * Any previous data will be forgotten, only 'dictionary' will remain in memory. + * Loading a size of 0 is allowed, and is the same as reset. + * @return : dictionary size, in bytes (necessarily <= 64 KB) */ -LZ4_stream_t* LZ4_createStream(void); -int LZ4_freeStream (LZ4_stream_t* streamPtr); +LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize); -/* - * 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. - * Return : dictionary size, in bytes (necessarily <= 64 KB) +/*! LZ4_compress_fast_continue() : + * Compress content into 'src' using data from previously compressed blocks, improving compression ratio. + * 'dst' buffer must be already allocated. + * If dstCapacity >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster. + * + * Important : Up to 64KB of previously compressed data is assumed to remain present and unmodified in memory ! + * Special 1 : If input buffer is a double-buffer, it can have any size, including < 64 KB. + * Special 2 : If input buffer is a ring-buffer, it can have any size, including < 64 KB. + * + * @return : size of compressed block + * or 0 if there is an error (typically, compressed data cannot fit into 'dst') + * After an error, the stream status is invalid, it can only be reset or freed. */ -int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize); +LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); -/* - * 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. +/*! LZ4_saveDict() : + * If previously compressed data block is not guaranteed to remain available at its current memory location, + * save it into a safer place (char* safeBuffer). + * Note : it's not necessary to call LZ4_loadDict() after LZ4_saveDict(), dictionary is immediately usable. + * @return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error. */ -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 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 LZ4_compress_fast_continue() - * Return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error - */ -int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int dictSize); +LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int dictSize); -/************************************************ +/*-********************************************** * Streaming Decompression Functions +* Bufferless synchronous API ************************************************/ +typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* incomplete type (defined later) */ +/*! LZ4_createStreamDecode() and LZ4_freeStreamDecode() : + * creation / destruction of streaming decompression tracking structure. + * A tracking structure can be re-used multiple times sequentially. */ +LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void); +LZ4LIB_API int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream); + +/*! LZ4_setStreamDecode() : + * An LZ4_streamDecode_t structure can be allocated once and re-used multiple times. + * Use this function to start decompression of a new stream of blocks. + * A dictionary can optionnally be set. Use NULL or size 0 for a simple reset order. + * @return : 1 if OK, 0 if error + */ +LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize); + +/*! LZ4_decompress_*_continue() : + * These decoding functions allow decompression of consecutive blocks in "streaming" mode. + * A block is an unsplittable entity, it must be presented entirely to a decompression function. + * Decompression functions only accept one block at a time. + * Previously decoded blocks *must* remain available at the memory position where they were decoded (up to 64 KB). + * + * Special : if application sets a ring buffer for decompression, it must respect one of the following conditions : + * - 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 of any 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() before decompressing next block. +*/ +LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxDecompressedSize); +LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize); + + +/*! LZ4_decompress_*_usingDict() : + * These decoding functions work the same as + * a combination of LZ4_setStreamDecode() followed by LZ4_decompress_*_continue() + * They are stand-alone, and don't need an LZ4_streamDecode_t structure. + */ +LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* source, char* dest, int compressedSize, int maxDecompressedSize, const char* dictStart, int dictSize); +LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* source, char* dest, int originalSize, const char* dictStart, int dictSize); + + +/*^********************************************** + * !!!!!! STATIC LINKING ONLY !!!!!! + ***********************************************/ +/*-************************************ + * Private definitions + ************************************** + * Do not use these definitions. + * They are exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`. + * Using these definitions will expose code to API and/or ABI break in future versions of the library. + **************************************/ +#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2) +#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE) +#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG) /* required as macro for static allocation */ + +#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) +#include + +typedef struct { + uint32_t hashTable[LZ4_HASH_SIZE_U32]; + uint32_t currentOffset; + uint32_t initCheck; + const uint8_t* dictionary; + uint8_t* bufferStart; /* obsolete, used for slideInputBuffer */ + uint32_t dictSize; +} LZ4_stream_t_internal; + +typedef struct { + const uint8_t* externalDict; + size_t extDictSize; + const uint8_t* prefixEnd; + size_t prefixSize; +} LZ4_streamDecode_t_internal; + +#else + +typedef struct { + unsigned int hashTable[LZ4_HASH_SIZE_U32]; + unsigned int currentOffset; + unsigned int initCheck; + const unsigned char* dictionary; + unsigned char* bufferStart; /* obsolete, used for slideInputBuffer */ + unsigned int dictSize; +} LZ4_stream_t_internal; + +typedef struct { + const unsigned char* externalDict; + size_t extDictSize; + const unsigned char* prefixEnd; + size_t prefixSize; +} LZ4_streamDecode_t_internal; + +#endif + +/*! + * LZ4_stream_t : + * information structure to track an LZ4 stream. + * init this structure before first use. + * note : only use in association with static linking ! + * this definition is not API/ABI safe, + * it may change in a future version ! + */ +#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4) +#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long)) +union LZ4_stream_u { + unsigned long long table[LZ4_STREAMSIZE_U64]; + LZ4_stream_t_internal internal_donotuse; +} ; /* previously typedef'd to LZ4_stream_t */ + + +/*! + * LZ4_streamDecode_t : + * information structure to track an LZ4 stream during decompression. + * init this structure using LZ4_setStreamDecode (or memset()) before first use + * note : only use in association with static linking ! + * this definition is not API/ABI safe, + * and may change in a future version ! + */ #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. - * 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. - */ -LZ4_streamDecode_t* LZ4_createStreamDecode(void); -int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream); - -/* - * 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 - */ -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* 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 (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); +union LZ4_streamDecode_u { + unsigned long long table[LZ4_STREAMDECODESIZE_U64]; + LZ4_streamDecode_t_internal internal_donotuse; +} ; /* previously typedef'd to LZ4_streamDecode_t */ -/* -Advanced decoding functions : -*_usingDict() : - These decoding functions work the same as - 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 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 **************************************/ -/* Deprecate Warnings */ -/* Should these warnings messages be a problem, + +/*! Deprecation warnings + Should deprecation warnings 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 + typically with -Wno-deprecated-declarations for gcc + or _CRT_SECURE_NO_WARNINGS in Visual. + Otherwise, it's also possible to define LZ4_DISABLE_DEPRECATE_WARNINGS */ +#ifdef LZ4_DISABLE_DEPRECATE_WARNINGS +# define LZ4_DEPRECATED(message) /* disable deprecation warnings */ +#else # define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) -# if (LZ4_GCC_VERSION >= 405) || defined(__clang__) +# if defined(__clang__) /* clang doesn't handle mixed C++11 and CNU attributes */ +# define LZ4_DEPRECATED(message) __attribute__((deprecated(message))) +# elif defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */ +# define LZ4_DEPRECATED(message) [[deprecated(message)]] +# elif (LZ4_GCC_VERSION >= 405) # define LZ4_DEPRECATED(message) __attribute__((deprecated(message))) # elif (LZ4_GCC_VERSION >= 301) # define LZ4_DEPRECATED(message) __attribute__((deprecated)) @@ -323,36 +443,31 @@ int LZ4_decompress_fast_usingDict (const char* source, char* dest, int originalS # pragma message("WARNING: You need to implement LZ4_DEPRECATED for this compiler") # define LZ4_DEPRECATED(message) # endif -#endif /* LZ4_DEPRECATE_WARNING_DEFBLOCK */ +#endif /* LZ4_DISABLE_DEPRECATE_WARNINGS */ /* 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); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress (const char* source, char* dest, int sourceSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") 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); */ +LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_fast() instead") int LZ4_uncompress (const char* source, char* dest, int outputSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_safe() instead") int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize); /* Obsolete streaming functions; use new streaming interface whenever possible */ -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); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_createStream() instead") void* LZ4_create (char* inputBuffer); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_createStream() instead") int LZ4_sizeofStreamState(void); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_resetStream() instead") int LZ4_resetStreamState(void* state, char* inputBuffer); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_saveDict() instead") char* LZ4_slideInputBuffer (void* state); /* Obsolete streaming decoding functions */ -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); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize); + +#endif /* LZ4_H_2983827168210 */ #if defined (__cplusplus) diff --git a/uppsrc/plugin/lz4/lib/lz4.c b/uppsrc/plugin/lz4/lib/lz4.c index 8dbc7df49..179408da4 100644 --- a/uppsrc/plugin/lz4/lib/lz4.c +++ b/uppsrc/plugin/lz4/lib/lz4.c @@ -1,6 +1,7 @@ /* LZ4 - Fast LZ compression algorithm - Copyright (C) 2011-2014, Yann Collet. + Copyright (C) 2011-2017, 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 @@ -27,120 +28,118 @@ 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 public forum : https://groups.google.com/forum/#!forum/lz4c + - LZ4 homepage : http://www.lz4.org + - LZ4 source repository : https://github.com/lz4/lz4 */ -/************************************** - Tuning parameters + +/*-************************************ +* Tuning parameters **************************************/ /* - * HEAPMODE : + * LZ4_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 +#ifndef LZ4_HEAPMODE +# define LZ4_HEAPMODE 0 +#endif -/************************************** - CPU Feature Detection +/* + * ACCELERATION_DEFAULT : + * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0 + */ +#define ACCELERATION_DEFAULT 1 + + +/*-************************************ +* CPU Feature Detection **************************************/ -/* 32 or 64 bits ? */ -#if (defined(__x86_64__) || defined(_M_X64) || defined(_WIN64) \ - || defined(__64BIT__) || defined(__mips64) \ - || defined(__powerpc64__) || defined(__powerpc64le__) \ - || defined(__ppc64__) || defined(__ppc64le__) \ - || defined(__PPC64__) || defined(__PPC64LE__) \ - || defined(__ia64) || defined(__itanium__) || defined(_M_IA64) \ - || defined(__s390x__) ) /* Detects 64 bits mode */ -# define LZ4_ARCH64 1 -#else -# define LZ4_ARCH64 0 -#endif -#define LZ4_32BITS (sizeof(void*)==4) -#define LZ4_64BITS (sizeof(void*)==8) - -/* - * Little Endian or Big Endian ? - * Overwrite the #define below if you know your architecture endianess +/* LZ4_FORCE_MEMORY_ACCESS + * By default, access to unaligned memory is controlled by `memcpy()`, which is safe and portable. + * Unfortunately, on some target/compiler combinations, the generated assembly is sub-optimal. + * The below switch allow to select different access method for improved performance. + * Method 0 (default) : use `memcpy()`. Safe and portable. + * Method 1 : `__packed` statement. It depends on compiler extension (ie, not portable). + * This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`. + * Method 2 : direct access. This method is portable but violate C standard. + * It can generate buggy code on targets which assembly generation depends on alignment. + * But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6) + * See https://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details. + * Prefer these methods in priority order (0 > 1 > 2) */ -#include /* Apparently required to detect endianess */ -#if defined (__GLIBC__) -# include -# if (__BYTE_ORDER == __BIG_ENDIAN) -# define LZ4_BIG_ENDIAN 1 +#ifndef LZ4_FORCE_MEMORY_ACCESS /* can be defined externally */ +# if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) ) +# define LZ4_FORCE_MEMORY_ACCESS 2 +# elif defined(__INTEL_COMPILER) || defined(__GNUC__) +# define LZ4_FORCE_MEMORY_ACCESS 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, 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 */ - - -/************************************** - Compiler Options +/*-************************************ +* Dependency **************************************/ -#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */ -/* "restrict" is a known keyword */ -#else -# define restrict /* Disable restrict */ -#endif +#include "lz4.h" +/* see also "memory routines" below */ + +/*-************************************ +* Compiler Options +**************************************/ #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 */ -#else -# ifdef __GNUC__ -# define FORCE_INLINE static inline __attribute__((always_inline)) +# pragma warning(disable : 4293) /* disable: C4293: too large shift (32-bits) */ +#endif /* _MSC_VER */ + +#ifndef LZ4_FORCE_INLINE +# ifdef _MSC_VER /* Visual Studio */ +# define LZ4_FORCE_INLINE static __forceinline # else -# define FORCE_INLINE static inline -# endif -#endif +# if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */ +# ifdef __GNUC__ +# define LZ4_FORCE_INLINE static inline __attribute__((always_inline)) +# else +# define LZ4_FORCE_INLINE static inline +# endif +# else +# define LZ4_FORCE_INLINE static +# endif /* __STDC_VERSION__ */ +# endif /* _MSC_VER */ +#endif /* LZ4_FORCE_INLINE */ -#ifdef _MSC_VER /* Visual Studio */ -# define lz4_bswap16(x) _byteswap_ushort(x) +/* LZ4_FORCE_O2_GCC_PPC64LE and LZ4_FORCE_O2_INLINE_GCC_PPC64LE + * Gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy, + * together with a simple 8-byte copy loop as a fall-back path. + * However, this optimization hurts the decompression speed by >30%, + * because the execution does not go to the optimized loop + * for typical compressible data, and all of the preamble checks + * before going to the fall-back path become useless overhead. + * This optimization happens only with the -O3 flag, and -O2 generates + * a simple 8-byte copy loop. + * With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy + * functions are annotated with __attribute__((optimize("O2"))), + * and also LZ4_wildCopy is forcibly inlined, so that the O2 attribute + * of LZ4_wildCopy does not affect the compression speed. + */ +#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__) +# define LZ4_FORCE_O2_GCC_PPC64LE __attribute__((optimize("O2"))) +# define LZ4_FORCE_O2_INLINE_GCC_PPC64LE __attribute__((optimize("O2"))) LZ4_FORCE_INLINE #else -# define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8))) +# define LZ4_FORCE_O2_GCC_PPC64LE +# define LZ4_FORCE_O2_INLINE_GCC_PPC64LE static #endif -#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) - -#if (GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__) +#if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__) # define expect(expr,value) (__builtin_expect ((expr),(value)) ) #else # define expect(expr,value) (expr) @@ -150,8 +149,8 @@ #define unlikely(expr) expect((expr) != 0, 0) -/************************************** - Memory routines +/*-************************************ +* Memory routines **************************************/ #include /* malloc, calloc, free */ #define ALLOCATOR(n,s) calloc(n,s) @@ -160,84 +159,147 @@ #define MEM_INIT memset -/************************************** - Includes +/*-************************************ +* Basic Types **************************************/ -#include "lz4.h" - - -/************************************** - Basic Types -**************************************/ -#if defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */ +#if defined(__cplusplus) || (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; + typedef uintptr_t uptrval; #else typedef unsigned char BYTE; typedef unsigned short U16; typedef unsigned int U32; typedef signed int S32; typedef unsigned long long U64; + typedef size_t uptrval; /* generally true, except OpenVMS-64 */ #endif -#if defined(__GNUC__) && !defined(LZ4_FORCE_UNALIGNED_ACCESS) -# define _PACKED __attribute__ ((packed)) +#if defined(__x86_64__) + typedef U64 reg_t; /* 64-bits in x32 mode */ #else -# define _PACKED + typedef size_t reg_t; /* 32-bits in x32 mode */ #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 - -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; - -#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__) -# if defined(__SUNPRO_C) || defined(__SUNPRO_CC) -# pragma pack(0) -# else -# pragma pack(pop) -# endif -#endif - -#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) - - -/************************************** - Constants +/*-************************************ +* Reading and writing into memory **************************************/ -#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2) -#define HASHTABLESIZE (1 << LZ4_MEMORY_USAGE) -#define HASH_SIZE_U32 (1 << LZ4_HASHLOG) +static unsigned LZ4_isLittleEndian(void) +{ + const union { U32 u; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */ + return one.c[0]; +} + +#if defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==2) +/* lie to the compiler about data alignment; use with caution */ + +static U16 LZ4_read16(const void* memPtr) { return *(const U16*) memPtr; } +static U32 LZ4_read32(const void* memPtr) { return *(const U32*) memPtr; } +static reg_t LZ4_read_ARCH(const void* memPtr) { return *(const reg_t*) memPtr; } + +static void LZ4_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; } +static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; } + +#elif defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==1) + +/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */ +/* currently only defined for gcc and icc */ +typedef union { U16 u16; U32 u32; reg_t uArch; } __attribute__((packed)) unalign; + +static U16 LZ4_read16(const void* ptr) { return ((const unalign*)ptr)->u16; } +static U32 LZ4_read32(const void* ptr) { return ((const unalign*)ptr)->u32; } +static reg_t LZ4_read_ARCH(const void* ptr) { return ((const unalign*)ptr)->uArch; } + +static void LZ4_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; } +static void LZ4_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; } + +#else /* safe and portable access through memcpy() */ + +static U16 LZ4_read16(const void* memPtr) +{ + U16 val; memcpy(&val, memPtr, sizeof(val)); return val; +} + +static U32 LZ4_read32(const void* memPtr) +{ + U32 val; memcpy(&val, memPtr, sizeof(val)); return val; +} + +static reg_t LZ4_read_ARCH(const void* memPtr) +{ + reg_t val; memcpy(&val, memPtr, sizeof(val)); return val; +} + +static void LZ4_write16(void* memPtr, U16 value) +{ + memcpy(memPtr, &value, sizeof(value)); +} + +static void LZ4_write32(void* memPtr, U32 value) +{ + memcpy(memPtr, &value, sizeof(value)); +} + +#endif /* LZ4_FORCE_MEMORY_ACCESS */ + + +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()) { + LZ4_write16(memPtr, value); + } else { + BYTE* p = (BYTE*)memPtr; + p[0] = (BYTE) value; + p[1] = (BYTE)(value>>8); + } +} + +static void LZ4_copy8(void* dst, const void* src) +{ + memcpy(dst,src,8); +} + +/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */ +LZ4_FORCE_O2_INLINE_GCC_PPC64LE +void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd) +{ + BYTE* d = (BYTE*)dstPtr; + const BYTE* s = (const BYTE*)srcPtr; + BYTE* const e = (BYTE*)dstEnd; + + do { LZ4_copy8(d,s); d+=8; s+=8; } while (d=2) +# include +# define DEBUGLOG(l, ...) { \ + if (l<=LZ4_DEBUG) { \ + fprintf(stderr, __FILE__ ": "); \ + fprintf(stderr, __VA_ARGS__); \ + fprintf(stderr, " \n"); \ + } } +#else +# define DEBUGLOG(l, ...) {} /* disabled */ +#endif + + +/*-************************************ +* Common functions +**************************************/ +static unsigned LZ4_NbCommonBytes (register reg_t val) +{ + if (LZ4_isLittleEndian()) { + if (sizeof(val)==8) { +# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r = 0; + _BitScanForward64( &r, (U64)val ); + return (int)(r>>3); +# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !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__) || (defined(__GNUC__) && (__GNUC__>=3))) && !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 (sizeof(val)==8) { /* 64-bits */ +# 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__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_clzll((U64)val) >> 3); +# else + static const U32 by32 = sizeof(val)*4; /* 32 on 64 bits (goal), 16 on 32 bits. + Just to avoid some static analyzer complaining about shift by 32 on 32-bits target. + Note that this code path is never triggered in 32-bits mode. */ + unsigned r; + if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; } + 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__) || (defined(__GNUC__) && (__GNUC__>=3))) && !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 + } + } +} + +#define STEPSIZE sizeof(reg_t) +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 */ + + +/*-************************************ +* Local Structures and types +**************************************/ typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive; typedef enum { byPtr, byU32, byU16 } tableType_t; @@ -269,202 +431,94 @@ typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; typedef enum { full = 0, partial = 1 } earlyEnd_directive; -/************************************** - Architecture-specific macros +/*-************************************ +* Local Utils **************************************/ -#define STEPSIZE sizeof(size_t) -#define LZ4_COPYSTEP(d,s) { AARCH(d) = AARCH(s); d+=STEPSIZE; s+=STEPSIZE; } -#define LZ4_COPY8(d,s) { LZ4_COPYSTEP(d,s); if (STEPSIZE<8) LZ4_COPYSTEP(d,s); } - -#if (defined(LZ4_BIG_ENDIAN) && !defined(BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE)) -# define LZ4_READ_LITTLEENDIAN_16(d,s,p) { U16 v = A16(p); v = lz4_bswap16(v); d = (s) - v; } -# define LZ4_WRITE_LITTLEENDIAN_16(p,i) { U16 v = (U16)(i); v = lz4_bswap16(v); A16(p) = v; p+=2; } -#else /* Little Endian */ -# define LZ4_READ_LITTLEENDIAN_16(d,s,p) { d = (s) - A16(p); } -# define LZ4_WRITE_LITTLEENDIAN_16(p,v) { A16(p) = v; p+=2; } -#endif - - -/************************************** - Macros -**************************************/ -#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 -} - -#else - -static int LZ4_NbCommonBytes (register U32 val) -{ -# if defined(LZ4_BIG_ENDIAN) -# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r = 0; - _BitScanReverse( &r, val ); - return (int)(r>>3); -# elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_clz(val) >> 3); -# else - int r; - if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } - r += (!val); - return r; -# endif -# else -# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r; - _BitScanForward( &r, val ); - return (int)(r>>3); -# elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_ctz(val) >> 3); -# else - static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 }; - return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27]; -# endif -# endif -} - -#endif - - -/******************************** - Compression functions -********************************/ int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; } +const char* LZ4_versionString(void) { return LZ4_VERSION_STRING; } int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } +int LZ4_sizeofState() { return LZ4_STREAMSIZE; } -static int LZ4_hashSequence(U32 sequence, tableType_t tableType) + +/*-****************************** +* Compression functions +********************************/ +static U32 LZ4_hash4(U32 sequence, tableType_t const tableType) { if (tableType == byU16) - return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1))); + return ((sequence * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1))); else - return (((sequence) * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG)); + return ((sequence * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG)); } -static int LZ4_hashPosition(const BYTE* p, tableType_t tableType) { return LZ4_hashSequence(A32(p), tableType); } +static U32 LZ4_hash5(U64 sequence, tableType_t const tableType) +{ + static const U64 prime5bytes = 889523592379ULL; + static const U64 prime8bytes = 11400714785074694791ULL; + const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG; + if (LZ4_isLittleEndian()) + return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog)); + else + return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog)); +} -static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) +LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType) +{ + if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType); + return LZ4_hash4(LZ4_read32(p), tableType); +} + +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; } } } -static void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) +LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) { - U32 h = LZ4_hashPosition(p, tableType); + U32 const h = LZ4_hashPosition(p, tableType); LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase); } static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) { if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; } - if (tableType == byU32) { U32* hashTable = (U32*) tableBase; return hashTable[h] + srcBase; } - { U16* hashTable = (U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */ + if (tableType == byU32) { const U32* const hashTable = (U32*) tableBase; return hashTable[h] + srcBase; } + { const U16* const hashTable = (U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */ } -static const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) +LZ4_FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) { - U32 h = LZ4_hashPosition(p, tableType); + U32 const h = LZ4_hashPosition(p, tableType); return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase); } -static unsigned LZ4_count(const BYTE* pIn, const BYTE* pRef, const BYTE* pInLimit) + +/** LZ4_compress_generic() : + inlined, to ensure branches are decided at compilation time */ +LZ4_FORCE_INLINE int LZ4_compress_generic( + LZ4_stream_t_internal* const cctx, + const char* const source, + char* const dest, + const int inputSize, + const int maxOutputSize, + const limitedOutput_directive outputLimited, + const tableType_t tableType, + const dict_directive dict, + const dictIssue_directive dictIssue, + const U32 acceleration) { - const BYTE* const pStart = pIn; - - while (likely(pIndictSize; - const BYTE* const dictionary = dictPtr->dictionary; - const BYTE* const dictEnd = dictionary + dictPtr->dictSize; - const size_t dictDelta = dictEnd - (const BYTE*)source; + const BYTE* const lowRefLimit = ip - cctx->dictSize; + const BYTE* const dictionary = cctx->dictionary; + const BYTE* const dictEnd = dictionary + cctx->dictSize; + const ptrdiff_t dictDelta = dictEnd - (const BYTE*)source; const BYTE* anchor = (const BYTE*) source; const BYTE* const iend = ip + inputSize; const BYTE* const mflimit = iend - MFLIMIT; @@ -473,12 +527,10 @@ static int LZ4_compress_generic( BYTE* op = (BYTE*) dest; BYTE* const olimit = op + maxOutputSize; - const int skipStrength = SKIPSTRENGTH; U32 forwardH; - size_t refDelta=0; /* Init conditions */ - if ((U32)inputSize > (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 inputSize, too large (or negative) */ switch(dict) { case noDict: @@ -487,133 +539,118 @@ static int LZ4_compress_generic( lowLimit = (const BYTE*)source; break; case withPrefix64k: - base = (const BYTE*)source - dictPtr->currentOffset; - lowLimit = (const BYTE*)source - dictPtr->dictSize; + base = (const BYTE*)source - cctx->currentOffset; + lowLimit = (const BYTE*)source - cctx->dictSize; break; case usingExtDict: - base = (const BYTE*)source - dictPtr->currentOffset; + base = (const BYTE*)source - cctx->currentOffset; 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 (inputSizehashTable, tableType, base); ip++; forwardH = LZ4_hashPosition(ip, tableType); /* Main Loop */ - for ( ; ; ) - { - const BYTE* ref; + for ( ; ; ) { + ptrdiff_t refDelta = 0; + const BYTE* match; BYTE* token; - { - const BYTE* forwardIp = ip; - unsigned step=1; - unsigned searchMatchNb = (1U << skipStrength); - /* Find a match */ + /* Find a match */ + { const BYTE* forwardIp = ip; + unsigned step = 1; + unsigned searchMatchNb = acceleration << LZ4_skipTrigger; do { - U32 h = forwardH; + U32 const h = forwardH; ip = forwardIp; forwardIp += step; - step = searchMatchNb++ >> skipStrength; + step = (searchMatchNb++ >> LZ4_skipTrigger); if (unlikely(forwardIp > mflimit)) goto _last_literals; - ref = LZ4_getPositionOnHash(h, ctx, tableType, base); - if (dict==usingExtDict) - { - if (ref<(const BYTE*)source) - { + match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base); + if (dict==usingExtDict) { + if (match < (const BYTE*)source) { refDelta = dictDelta; lowLimit = dictionary; - } - else - { + } else { refDelta = 0; lowLimit = (const BYTE*)source; - } - } + } } forwardH = LZ4_hashPosition(forwardIp, tableType); - LZ4_putPositionOnHash(ip, h, ctx, tableType, base); + LZ4_putPositionOnHash(ip, h, cctx->hashTable, 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 */ - unsigned litLength = (unsigned)(ip - anchor); - STATCODE(lz4stat_LiteralLen += litLength;) - STATCODE(lz4stat_Literals += litLength > 0); + /* Encode Literals */ + { unsigned const litLength = (unsigned)(ip - anchor); token = op++; - if ((outputLimited) && (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit))) - return 0; /* Check output limit */ - if (litLength>=RUN_MASK) - { + if ((outputLimited) && /* Check output buffer overflow */ + (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit))) + return 0; + if (litLength >= RUN_MASK) { int len = (int)litLength-RUN_MASK; - *token=(RUN_MASK<= 255 ; len-=255) { - *op++ = 255; - STATCODE(lz4stat_BigLiteral++); - } + *token = (RUN_MASK<= 255 ; len-=255) *op++ = 255; *op++ = (BYTE)len; - STATCODE(lz4stat_BigLiteral++); } else *token = (BYTE)(litLength< matchlimit) limit = matchlimit; - matchLength = LZ4_count(ip+MINMATCH, ref+MINMATCH, limit); - ip += MINMATCH + matchLength; - if (ip==limit) - { - unsigned more = LZ4_count(ip, (const BYTE*)source, matchlimit); - matchLength += more; + matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit); + ip += MINMATCH + matchCode; + if (ip==limit) { + unsigned const more = LZ4_count(ip, (const BYTE*)source, matchlimit); + matchCode += more; ip += more; } - } - else - { - matchLength = LZ4_count(ip+MINMATCH, ref+MINMATCH, matchlimit); - ip += MINMATCH + matchLength; + } else { + matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit); + ip += MINMATCH + matchCode; } - if (matchLength>=ML_MASK) - { - if ((outputLimited) && (unlikely(op + (1 + LASTLITERALS) + (matchLength>>8) > olimit))) - return 0; /* Check output limit */ + if ( outputLimited && /* Check output buffer overflow */ + (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) ) + return 0; + if (matchCode >= ML_MASK) { *token += ML_MASK; - matchLength -= ML_MASK; - for (; matchLength >= 510 ; matchLength-=510) { *op++ = 255; *op++ = 255; STATCODE(lz4stat_BigMatch+=2); } - if (matchLength >= 255) { matchLength-=255; *op++ = 255; STATCODE(lz4stat_BigMatch++); } - *op++ = (BYTE)matchLength; - STATCODE(lz4stat_BigMatch++); - } - else *token += (BYTE)(matchLength); + matchCode -= ML_MASK; + LZ4_write32(op, 0xFFFFFFFF); + while (matchCode >= 4*255) { + op+=4; + LZ4_write32(op, 0xFFFFFFFF); + matchCode -= 4*255; + } + op += matchCode / 255; + *op++ = (BYTE)(matchCode % 255); + } else + *token += (BYTE)(matchCode); } anchor = ip; @@ -622,29 +659,23 @@ _next_match: if (ip > mflimit) break; /* Fill table */ - LZ4_putPosition(ip-2, ctx, tableType, base); + LZ4_putPosition(ip-2, cctx->hashTable, tableType, base); /* Test next position */ - ref = LZ4_getPosition(ip, ctx, tableType, base); - if (dict==usingExtDict) - { - if (ref<(const BYTE*)source) - { + match = LZ4_getPosition(ip, cctx->hashTable, tableType, base); + if (dict==usingExtDict) { + if (match < (const BYTE*)source) { refDelta = dictDelta; lowLimit = dictionary; - } - else - { + } else { refDelta = 0; lowLimit = (const BYTE*)source; - } - } - LZ4_putPosition(ip, ctx, tableType, base); - if ( ((dictIssue==dictSmall) ? (ref>=lowRefLimit) : 1) - && (ref+MAX_DISTANCE>=ip) - && (A32(ref+refDelta)==A32(ip)) ) - { token=op++; *token=0; - goto _next_match; } + } } + LZ4_putPosition(ip, cctx->hashTable, tableType, base); + 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 */ forwardH = LZ4_hashPosition(++ip, tableType); @@ -652,14 +683,20 @@ _next_match: _last_literals: /* Encode Last Literals */ - { - int lastRun = (int)(iend - anchor); - if ((outputLimited) && (((char*)op - 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< (U32)maxOutputSize) ) + return 0; + if (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<internal_donotuse; + LZ4_resetStream((LZ4_stream_t*)state); + if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; + + if (maxOutputSize >= LZ4_compressBound(inputSize)) { + if (inputSize < LZ4_64Klimit) + return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue, acceleration); + else + return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration); + } else { + 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, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration); + } +} + + +int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) +{ +#if (LZ4_HEAPMODE) + 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* const 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, LZ4_64BITS ? byU32 : byPtr, noDict, noDictIssue); + int const result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration); -#if (HEAPMODE) - FREEMEM(ctx); +#if (LZ4_HEAPMODE) + 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) { -#if (HEAPMODE) - void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U32, 4); /* Aligned on 4-bytes boundaries */ -#else - U32 ctx[LZ4_STREAMSIZE_U32] = {0}; /* Ensure data is aligned on 4-bytes boundaries */ -#endif - int result; + return LZ4_compress_fast(source, dest, inputSize, maxOutputSize, 1); +} - if (inputSize < (int)LZ4_64KLIMIT) - result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue); + +/* 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.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); else - result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64BITS ? byU32 : byPtr, noDict, noDictIssue); + return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, sizeof(void*)==8 ? byU32 : byPtr, noDict, noDictIssue, acceleration); +} -#if (HEAPMODE) + +/*-****************************** +* *_destSize() variant +********************************/ + +static int LZ4_compress_destSize_generic( + LZ4_stream_t_internal* 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 (*srcSizePtrhashTable, tableType, base); + ip++; forwardH = LZ4_hashPosition(ip, tableType); + + /* Main Loop */ + for ( ; ; ) { + const BYTE* match; + BYTE* token; + + /* Find a match */ + { const BYTE* forwardIp = ip; + unsigned step = 1; + unsigned searchMatchNb = 1 << LZ4_skipTrigger; + + do { + U32 h = forwardH; + ip = forwardIp; + forwardIp += step; + step = (searchMatchNb++ >> LZ4_skipTrigger); + + if (unlikely(forwardIp > mflimit)) goto _last_literals; + + match = LZ4_getPositionOnHash(h, ctx->hashTable, tableType, base); + forwardH = LZ4_hashPosition(forwardIp, tableType); + LZ4_putPositionOnHash(ip, h, ctx->hashTable, 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; + } + 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->hashTable, tableType, base); + + /* Test next position */ + match = LZ4_getPosition(ip, ctx->hashTable, tableType, base); + LZ4_putPosition(ip, ctx->hashTable, 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->internal_donotuse, src, dst, srcSizePtr, targetDstSize, byU16); + else + return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, sizeof(void*)==8 ? byU32 : byPtr); + } +} + + +int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize) +{ +#if (LZ4_HEAPMODE) + LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ +#else + LZ4_stream_t ctxBody; + LZ4_stream_t* ctx = &ctxBody; +#endif + + int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize); + +#if (LZ4_HEAPMODE) FREEMEM(ctx); #endif return result; } -/***************************************** - Experimental : Streaming functions -*****************************************/ -/* - * LZ4_initStream - * Use this function once, to init a newly allocated LZ4_stream_t structure - * Return : 1 if OK, 0 if error - */ +/*-****************************** +* Streaming functions +********************************/ + +LZ4_stream_t* LZ4_createStream(void) +{ + 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; +} + void LZ4_resetStream (LZ4_stream_t* LZ4_stream) { MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t)); } -LZ4_stream_t* LZ4_createStream(void) -{ - LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(4, LZ4_STREAMSIZE_U32); - LZ4_resetStream(lz4s); - return lz4s; -} - int LZ4_freeStream (LZ4_stream_t* LZ4_stream) { + if (!LZ4_stream) return 0; /* support free on NULL */ FREEMEM(LZ4_stream); return (0); } +#define HASH_UNIT sizeof(reg_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; + LZ4_stream_t_internal* dict = &LZ4_dict->internal_donotuse; 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) LZ4_resetStream(LZ4_dict); /* 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) - { - LZ4_putPosition(p, dict, byU32, base); + while (p <= dictEnd-HASH_UNIT) { + LZ4_putPosition(p, dict->hashTable, byU32, base); p+=3; } - return 1; + return dict->dictSize; } 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 */ - { + ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) { /* address space overflow */ /* rescale hash table */ - U32 delta = LZ4_dict->currentOffset - 64 KB; + U32 const delta = LZ4_dict->currentOffset - 64 KB; const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize; int i; - for (i=0; ihashTable[i] < delta) LZ4_dict->hashTable[i]=0; else LZ4_dict->hashTable[i] -= delta; } @@ -790,22 +1033,20 @@ static 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; + LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse; const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; const BYTE* smallest = (const BYTE*) source; 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 */ - { - const BYTE* sourceEnd = (const BYTE*) source + inputSize; - if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) - { + { const BYTE* sourceEnd = (const BYTE*) source + inputSize; + if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) { streamPtr->dictSize = (U32)(dictEnd - sourceEnd); if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB; if (streamPtr->dictSize < 4) streamPtr->dictSize = 0; @@ -814,25 +1055,23 @@ FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* so } /* prefix mode : source data follows dictionary */ - if (dictEnd == (const BYTE*)source) - { + if (dictEnd == (const BYTE*)source) { 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(streamPtr, 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(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration); streamPtr->dictSize += (U32)inputSize; streamPtr->currentOffset += (U32)inputSize; return result; } /* external dictionary mode */ - { - int result; + { 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(streamPtr, 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(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration); streamPtr->dictionary = (const BYTE*)source; streamPtr->dictSize = (U32)inputSize; streamPtr->currentOffset += (U32)inputSize; @@ -840,29 +1079,19 @@ FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* so } } -int LZ4_compress_continue (LZ4_stream_t* 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 (LZ4_stream_t* 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; + LZ4_stream_t_internal* streamPtr = &LZ4_dict->internal_donotuse; int result; const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; const BYTE* smallest = dictEnd; if (smallest > (const BYTE*) source) smallest = (const BYTE*) source; - LZ4_renormDictT((LZ4_stream_t_internal*)LZ4_dict, smallest); + LZ4_renormDictT(streamPtr, smallest); - result = LZ4_compress_generic(LZ4_dict, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue); + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1); streamPtr->dictionary = (const BYTE*)source; streamPtr->dictSize = (U32)inputSize; @@ -872,10 +1101,17 @@ int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* } +/*! LZ4_saveDict() : + * 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 LZ4_compress_fast_continue(). + * Return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error. + */ 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; + LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse; + const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize; if ((U32)dictSize > 64 KB) dictSize = 64 KB; /* useless to define a dictionary > 64 KB */ if ((U32)dictSize > dict->dictSize) dictSize = dict->dictSize; @@ -890,87 +1126,79 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize) -/**************************** - Decompression functions -****************************/ -/* - * This generic decompression function cover all use cases. - * 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 optimization. +/*-***************************** +* Decompression functions +*******************************/ +/*! LZ4_decompress_generic() : + * This generic decompression function covers all use cases. + * It shall be instantiated several times, using different sets of directives. + * Note that it is important for performance that this function really get inlined, + * in order to remove useless branches during compilation optimization. */ -FORCE_INLINE int LZ4_decompress_generic( - const char* source, - char* dest, - int inputSize, - int outputSize, /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */ +LZ4_FORCE_O2_GCC_PPC64LE +LZ4_FORCE_INLINE int LZ4_decompress_generic( + const char* const src, + char* const dst, + int srcSize, + int outputSize, /* If endOnInput==endOnInputSize, this value is `dstCapacity` */ int endOnInput, /* endOnOutputSize, endOnInputSize */ 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, /* == dst when no prefix */ + 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* const iend = ip + inputSize; + const BYTE* ip = (const BYTE*) src; + const BYTE* const iend = ip + srcSize; - BYTE* op = (BYTE*) dest; + BYTE* op = (BYTE*) dst; BYTE* const oend = op + outputSize; BYTE* cpy; BYTE* oexit = op + targetOutputSize; - const BYTE* const lowLimit = (const BYTE*)dest - dictSize; const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize; - 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 unsigned dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; + const int dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3}; 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 ((srcSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */ if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1); - - /* Main Loop */ - while (1) - { - unsigned token; + /* Main Loop : decode sequences */ + while (1) { size_t length; + const BYTE* match; + size_t offset; - /* get runlength */ - token = *ip++; - if ((length=(token>>ML_BITS)) == RUN_MASK) - { + /* get literal length */ + unsigned const token = *ip++; + if ((length=(token>>ML_BITS)) == RUN_MASK) { unsigned s; - do - { + do { s = *ip++; length += s; - } - while (likely((endOnInput)?ip(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) ) - || ((!endOnInput) && (cpy>oend-COPYLENGTH))) + if ( ((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) ) + || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) ) { - if (partialDecoding) - { + if (partialDecoding) { if (cpy > oend) goto _output_error; /* Error : write attempt beyond end of output buffer */ if ((endOnInput) && (ip+length > iend)) goto _output_error; /* Error : read attempt beyond end of input buffer */ - } - else - { + } else { if ((!endOnInput) && (cpy != oend)) goto _output_error; /* Error : block decoding must stop exactly there */ if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error; /* Error : input must be consumed */ } @@ -979,147 +1207,143 @@ FORCE_INLINE int LZ4_decompress_generic( op += length; 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 */ + offset = LZ4_readLE16(ip); ip+=2; + match = op - offset; + if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */ + LZ4_write32(op, (U32)offset); /* costs ~1%; silence an msan warning when offset==0 */ /* get matchlength */ - if ((length=(token&ML_MASK)) == ML_MASK) - { + length = token & ML_MASK; + if (length == ML_MASK) { unsigned s; - do - { - if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error; + do { s = *ip++; + if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error; length += s; } while (s==255); - if ((safeDecode) && LZ4_32BITS && unlikely((size_t)(op+length)<(size_t)op)) goto _output_error; /* overflow detection */ + if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */ } length += MINMATCH; /* check external dictionary */ - if ((dict==usingExtDict) && (ref < (BYTE* const)dest)) - { - if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error; + if ((dict==usingExtDict) && (match < lowPrefix)) { + if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error; /* doesn't respect parsing restriction */ - if (length <= (size_t)(dest-(char*)ref)) - { - ref = dictEnd - (dest-(char*)ref); - memcpy(op, ref, length); + if (length <= (size_t)(lowPrefix-match)) { + /* match can be copied as a single segment from external dictionary */ + memmove(op, dictEnd - (lowPrefix-match), length); op += length; - } - else - { - size_t copySize = (size_t)(dest-(char*)ref); + } else { + /* match encompass external dictionary and current block */ + size_t const copySize = (size_t)(lowPrefix-match); + size_t const restSize = length - copySize; memcpy(op, dictEnd - copySize, copySize); op += copySize; - copySize = length - copySize; - if (copySize > (size_t)((char*)op-dest)) /* overlap */ - { - BYTE* const endOfMatch = op + copySize; - const BYTE* copyFrom = (BYTE*)dest; + if (restSize > (size_t)(op-lowPrefix)) { /* overlap copy */ + BYTE* const endOfMatch = op + restSize; + const BYTE* copyFrom = lowPrefix; while (op < endOfMatch) *op++ = *copyFrom++; - } - else - { - memcpy(op, dest, copySize); - op += copySize; - } - } + } else { + memcpy(op, lowPrefix, restSize); + op += restSize; + } } continue; } - /* copy repeated sequence */ + /* copy match within block */ cpy = op + length; - if (unlikely((op-ref)<(int)STEPSIZE)) - { - const size_t dec64 = dec64table[op-ref]; - op[0] = ref[0]; - op[1] = ref[1]; - op[2] = ref[2]; - op[3] = ref[3]; - ref += dec32table[op-ref]; - A32(op+4) = A32(ref); - op += 8; ref -= dec64; - } else { LZ4_COPY8(op,ref); } + if (unlikely(offset<8)) { + const int dec64 = dec64table[offset]; + op[0] = match[0]; + op[1] = match[1]; + op[2] = match[2]; + op[3] = match[3]; + match += dec32table[offset]; + memcpy(op+4, match, 4); + match -= dec64; + } else { LZ4_copy8(op, match); match+=8; } + op += 8; - if (unlikely(cpy>oend-12)) - { - if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last 5 bytes must be literals */ - if (opoend-12)) { + BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1); + if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last LASTLITERALS bytes must be literals (uncompressed) */ + if (op < oCopyLimit) { + LZ4_wildCopy(op, match, oCopyLimit); + match += oCopyLimit - op; + op = oCopyLimit; + } + while (op16) LZ4_wildCopy(op+8, match+8, cpy); } - else LZ4_WILDCOPY(op, ref, cpy); op=cpy; /* correction */ } /* end of decoding */ if (endOnInput) - return (int) (((char*)op)-dest); /* Nb of output bytes decoded */ + return (int) (((char*)op)-dst); /* Nb of output bytes decoded */ else - return (int) (((char*)ip)-source); /* Nb of input bytes read */ + return (int) (((const char*)ip)-src); /* Nb of input bytes read */ /* Overflow error detected */ _output_error: - return (int) (-(((char*)ip)-source))-1; + return (int) (-(((const char*)ip)-src))-1; } +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize) { - return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, NULL, 0); + return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, NULL, 0); } +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize) { - return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, NULL, 0); + return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, NULL, 0); } +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_fast(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); } -/* streaming decompression functions */ -typedef struct -{ - const char* dictionary; - int dictSize; -} LZ4_streamDecode_t_internal; +/*===== streaming decompression functions =====*/ -/* - * If you prefer dynamic allocation methods, - * LZ4_createStreamDecode() - * provides a pointer (void*) towards an initialized LZ4_streamDecode_t structure. - */ LZ4_streamDecode_t* LZ4_createStreamDecode(void) { - LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(sizeof(U32), LZ4_STREAMDECODESIZE_U32); - MEM_INIT(lz4s, 0, LZ4_STREAMDECODESIZE); + LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(1, sizeof(LZ4_streamDecode_t)); return lz4s; } int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream) { + if (!LZ4_stream) return 0; /* support free on NULL */ FREEMEM(LZ4_stream); return 0; } -/* - * LZ4_setStreamDecode - * Use this function to instruct where to find the dictionary +/*! + * LZ4_setStreamDecode() : + * Use this function to instruct where to find the dictionary. * This function is not necessary if previous data is still available where it was decoded. * Loading a size of 0 is allowed (same effect as no dictionary). * Return : 1 if OK, 0 if error */ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize) { - LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode; - lz4sd->dictionary = dictionary; - lz4sd->dictSize = dictSize; + LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; + lz4sd->prefixSize = (size_t) dictSize; + lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize; + lz4sd->externalDict = NULL; + lz4sd->extDictSize = 0; return 1; } @@ -1128,43 +1352,57 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti 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() */ +LZ4_FORCE_O2_GCC_PPC64LE 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; + LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; 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) - { - lz4sd->dictSize += result; - } - else - { - lz4sd->dictionary = dest; - lz4sd->dictSize = result; + if (lz4sd->prefixEnd == (BYTE*)dest) { + 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->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; } +LZ4_FORCE_O2_GCC_PPC64LE 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; + LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; 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) - { - lz4sd->dictSize += result; - } - else - { - lz4sd->dictionary = dest; - lz4sd->dictSize = result; + if (lz4sd->prefixEnd == (BYTE*)dest) { + 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->extDictSize = lz4sd->prefixSize; + lz4sd->externalDict = lz4sd->prefixEnd - 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; @@ -1178,37 +1416,50 @@ 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) +LZ4_FORCE_O2_GCC_PPC64LE +LZ4_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, NULL, 64 KB); - if ((dictStart+dictSize == dest) && (dictSize >= (int)(64 KB - 1))) - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, withPrefix64k, NULL, 64 KB); - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, dictStart, dictSize); + 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); } +LZ4_FORCE_O2_GCC_PPC64LE 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); } +LZ4_FORCE_O2_GCC_PPC64LE 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 */ +LZ4_FORCE_O2_GCC_PPC64LE 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, dictStart, 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. @@ -1223,69 +1474,43 @@ int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; } -static void LZ4_init(LZ4_stream_t_internal* lz4ds, const BYTE* base) +static void LZ4_init(LZ4_stream_t* lz4ds, BYTE* base) { - MEM_INIT(lz4ds, 0, LZ4_STREAMSIZE); - lz4ds->bufferStart = base; + MEM_INIT(lz4ds, 0, sizeof(LZ4_stream_t)); + lz4ds->internal_donotuse.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); + if ((((uptrval)state) & 3) != 0) return 1; /* Error : pointer is not aligned on 4-bytes boundary */ + LZ4_init((LZ4_stream_t*)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); + LZ4_stream_t* lz4ds = (LZ4_stream_t*)ALLOCATOR(8, sizeof(LZ4_stream_t)); + LZ4_init (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, LZ4_64BITS ? 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, LZ4_64BITS ? byU32 : byPtr, noDict, noDictIssue); + LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)LZ4_Data)->internal_donotuse; + 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/uppsrc/plugin/lz4/lib/lz4.h b/uppsrc/plugin/lz4/lib/lz4.h index ef1d1fffc..d284d6300 100644 --- a/uppsrc/plugin/lz4/lib/lz4.h +++ b/uppsrc/plugin/lz4/lib/lz4.h @@ -1,7 +1,8 @@ /* - LZ4 - Fast LZ compression algorithm - Header File - Copyright (C) 2011-2014, Yann Collet. + * LZ4 - Fast LZ compression algorithm + * Header File + * Copyright (C) 2011-2017, 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 @@ -28,118 +29,178 @@ 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 public forum : https://groups.google.com/forum/#!forum/lz4c + - LZ4 homepage : http://www.lz4.org + - LZ4 source repository : https://github.com/lz4/lz4 */ -#pragma once - #if defined (__cplusplus) extern "C" { #endif -/* - * lz4.h provides raw compression format functions, for optimal performance and integration into programs. - * If you need to generate data using an inter-operable format (respecting the framing specification), - * please use lz4frame.h instead. +#ifndef LZ4_H_2983827168210 +#define LZ4_H_2983827168210 + +/* --- Dependency --- */ +#include /* size_t */ + + +/** + Introduction + + LZ4 is lossless compression algorithm, providing compression speed at 400 MB/s per core, + scalable with multi-cores CPU. It features an extremely fast decoder, with speed in + multiple GB/s per core, typically reaching RAM speed limits on multi-core systems. + + The LZ4 compression library provides in-memory compression and decompression functions. + Compression can be done in: + - a single step (described as Simple Functions) + - a single step, reusing a context (described in Advanced Functions) + - unbounded multiple steps (described as Streaming compression) + + lz4.h provides block compression functions. It gives full buffer control to user. + Decompressing an lz4-compressed block also requires metadata (such as compressed size). + Each application is free to encode such metadata in whichever way it wants. + + An additional format, called LZ4 frame specification (doc/lz4_Frame_format.md), + take care of encoding standard metadata alongside LZ4-compressed blocks. + If your application requires interoperability, it's recommended to use it. + A library is provided to take care of it, see lz4frame.h. */ -/************************************** - Version -**************************************/ -#define LZ4_VERSION_MAJOR 1 /* for major interface/format changes */ -#define LZ4_VERSION_MINOR 3 /* for minor interface/format changes */ -#define LZ4_VERSION_RELEASE 1 /* 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 -**************************************/ +/*^*************************************************************** +* Export parameters +*****************************************************************/ /* +* LZ4_DLL_EXPORT : +* Enable exporting of functions when building a Windows DLL +* LZ4LIB_API : +* Control library symbols visibility. +*/ +#if defined(LZ4_DLL_EXPORT) && (LZ4_DLL_EXPORT==1) +# define LZ4LIB_API __declspec(dllexport) +#elif defined(LZ4_DLL_IMPORT) && (LZ4_DLL_IMPORT==1) +# define LZ4LIB_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ +#elif defined(__GNUC__) && (__GNUC__ >= 4) +# define LZ4LIB_API __attribute__ ((__visibility__ ("default"))) +#else +# define LZ4LIB_API +#endif + + +/*------ Version ------*/ +#define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */ +#define LZ4_VERSION_MINOR 8 /* 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) + +#define LZ4_LIB_VERSION LZ4_VERSION_MAJOR.LZ4_VERSION_MINOR.LZ4_VERSION_RELEASE +#define LZ4_QUOTE(str) #str +#define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str) +#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION) + +LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; to be used when checking dll version */ +LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; to be used when checking dll version */ + + +/*-************************************ +* Tuning parameter +**************************************/ +/*! * LZ4_MEMORY_USAGE : * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.) * Increasing memory usage improves compression ratio * Reduced memory usage can improve speed, due to cache effect * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */ -#define LZ4_MEMORY_USAGE 14 +#ifndef LZ4_MEMORY_USAGE +# define LZ4_MEMORY_USAGE 14 +#endif - -/************************************** - Simple Functions +/*-************************************ +* Simple Functions **************************************/ +/*! 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 */ +LZ4LIB_API int LZ4_compress_default(const char* source, char* dest, int sourceSize, int maxDestSize); -int LZ4_compress (const char* source, char* dest, int sourceSize); -int LZ4_decompress_safe (const char* source, char* dest, int compressedSize, int maxDecompressedSize); - -/* -LZ4_compress() : - Compresses 'sourceSize' 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_SIZE - return : the number of bytes written in buffer dest - or 0 if the compression fails - -LZ4_decompress_safe() : - compressedSize : is obviously the source size - maxDecompressedSize : is the size of the destination buffer, which must be already allocated. - return : the number of bytes decompressed into the destination buffer (necessarily <= maxDecompressedSize) - If the destination buffer is not large enough, decoding will stop and output an error code (<0). +/*! LZ4_decompress_safe() : + 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, - and never writes outside of output buffer, nor reads outside of input buffer. - It is also protected against malicious data packets. + This function is protected against buffer overflow exploits, including malicious data packets. + It never writes outside output buffer, nor reads outside input buffer. */ +LZ4LIB_API int LZ4_decompress_safe (const char* source, char* dest, int compressedSize, int maxDecompressedSize); -/************************************** - 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 compression may output in a "worst case" scenario (input data not compressible) - This function is primarily useful for memory allocation purposes (output buffer size). + 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). - - 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) + 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 isize); +LZ4LIB_API int LZ4_compressBound(int inputSize); - -/* -LZ4_compress_limitedOutput() : - Compress 'sourceSize' 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 saves time and memory on detecting non-compressible (or barely compressible) data. - This function never writes outside of provided output buffer. - - sourceSize : 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 compression fails +/*! +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_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize); +LZ4LIB_API int LZ4_compress_fast (const char* source, char* dest, int sourceSize, int maxDestSize, int acceleration); -/* -LZ4_compress_withState() : - Same compression functions, but using an externally allocated memory space to store compression state. +/*! +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 then, provide it as 'void* state' to compression functions. + and allocate it on 8-bytes boundaries (using malloc() typically). + Then, provide it as 'void* state' to compression function. */ -int LZ4_sizeofState(void); -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); +LZ4LIB_API int LZ4_sizeofState(void); +LZ4LIB_API 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 +*/ +LZ4LIB_API 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) @@ -150,10 +211,9 @@ LZ4_decompress_fast() : 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); +LZ4LIB_API 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 destination buffer 'dest' of size 'maxDecompressedSize'. @@ -165,169 +225,250 @@ LZ4_decompress_safe_partial() : 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 maxDecompressedSize); +LZ4LIB_API int LZ4_decompress_safe_partial (const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize); -/*********************************************** - Experimental Streaming Compression Functions +/*-********************************************* +* Streaming Compression Functions ***********************************************/ +typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */ -#define LZ4_STREAMSIZE_U32 ((1 << (LZ4_MEMORY_USAGE-2)) + 8) -#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U32 * sizeof(unsigned int)) -/* - * LZ4_stream_t - * information structure to track an LZ4 stream. - * important : init this structure content before first use ! +/*! LZ4_createStream() and LZ4_freeStream() : + * LZ4_createStream() will allocate and initialize an `LZ4_stream_t` structure. + * LZ4_freeStream() releases its memory. */ -typedef struct { unsigned int table[LZ4_STREAMSIZE_U32]; } LZ4_stream_t; +LZ4LIB_API LZ4_stream_t* LZ4_createStream(void); +LZ4LIB_API int LZ4_freeStream (LZ4_stream_t* streamPtr); -/* - * LZ4_resetStream - * Use this function to init an allocated LZ4_stream_t structure +/*! LZ4_resetStream() : + * An LZ4_stream_t structure can be allocated once and re-used multiple times. + * Use this function to start compressing a new stream. */ -void LZ4_resetStream (LZ4_stream_t* LZ4_streamPtr); +LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr); -/* - * If you prefer dynamic allocation methods, - * LZ4_createStream will allocate and initialize an LZ4_stream_t structure - * LZ4_freeStream releases its memory. +/*! LZ4_loadDict() : + * Use this function to load a static dictionary into LZ4_stream_t. + * Any previous data will be forgotten, only 'dictionary' will remain in memory. + * Loading a size of 0 is allowed, and is the same as reset. + * @return : dictionary size, in bytes (necessarily <= 64 KB) */ -LZ4_stream_t* LZ4_createStream(void); -int LZ4_freeStream (LZ4_stream_t* LZ4_stream); +LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize); -/* - * 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. - * Return : 1 if OK, 0 if error +/*! LZ4_compress_fast_continue() : + * Compress content into 'src' using data from previously compressed blocks, improving compression ratio. + * 'dst' buffer must be already allocated. + * If dstCapacity >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster. + * + * Important : Up to 64KB of previously compressed data is assumed to remain present and unmodified in memory ! + * Special 1 : If input buffer is a double-buffer, it can have any size, including < 64 KB. + * Special 2 : If input buffer is a ring-buffer, it can have any size, including < 64 KB. + * + * @return : size of compressed block + * or 0 if there is an error (typically, compressed data cannot fit into 'dst') + * After an error, the stream status is invalid, it can only be reset or freed. */ -int LZ4_loadDict (LZ4_stream_t* LZ4_stream, const char* dictionary, int dictSize); +LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); -/* - * 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. +/*! LZ4_saveDict() : + * If previously compressed data block is not guaranteed to remain available at its current memory location, + * save it into a safer place (char* safeBuffer). + * Note : it's not necessary to call LZ4_loadDict() after LZ4_saveDict(), dictionary is immediately usable. + * @return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error. */ -int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize); - -/* - * 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. - */ -int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize); - -/* - * LZ4_saveDict - * 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 : dictionary size in bytes, or 0 if error - * Note : any dictSize > 64 KB will be interpreted as 64KB. - */ -int LZ4_saveDict (LZ4_stream_t* LZ4_stream, char* safeBuffer, int dictSize); +LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int dictSize); -/************************************************ - Experimental Streaming Decompression Functions +/*-********************************************** +* Streaming Decompression Functions +* Bufferless synchronous API ************************************************/ +typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* incomplete type (defined later) */ -#define LZ4_STREAMDECODESIZE_U32 4 -#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U32 * sizeof(unsigned int)) -/* - * LZ4_streamDecode_t +/*! LZ4_createStreamDecode() and LZ4_freeStreamDecode() : + * creation / destruction of streaming decompression tracking structure. + * A tracking structure can be re-used multiple times sequentially. */ +LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void); +LZ4LIB_API int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream); + +/*! LZ4_setStreamDecode() : + * An LZ4_streamDecode_t structure can be allocated once and re-used multiple times. + * Use this function to start decompression of a new stream of blocks. + * A dictionary can optionnally be set. Use NULL or size 0 for a simple reset order. + * @return : 1 if OK, 0 if error + */ +LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize); + +/*! LZ4_decompress_*_continue() : + * These decoding functions allow decompression of consecutive blocks in "streaming" mode. + * A block is an unsplittable entity, it must be presented entirely to a decompression function. + * Decompression functions only accept one block at a time. + * Previously decoded blocks *must* remain available at the memory position where they were decoded (up to 64 KB). + * + * Special : if application sets a ring buffer for decompression, it must respect one of the following conditions : + * - 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 of any 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() before decompressing next block. +*/ +LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxDecompressedSize); +LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize); + + +/*! LZ4_decompress_*_usingDict() : + * These decoding functions work the same as + * a combination of LZ4_setStreamDecode() followed by LZ4_decompress_*_continue() + * They are stand-alone, and don't need an LZ4_streamDecode_t structure. + */ +LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* source, char* dest, int compressedSize, int maxDecompressedSize, const char* dictStart, int dictSize); +LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* source, char* dest, int originalSize, const char* dictStart, int dictSize); + + +/*^********************************************** + * !!!!!! STATIC LINKING ONLY !!!!!! + ***********************************************/ +/*-************************************ + * Private definitions + ************************************** + * Do not use these definitions. + * They are exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`. + * Using these definitions will expose code to API and/or ABI break in future versions of the library. + **************************************/ +#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2) +#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE) +#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG) /* required as macro for static allocation */ + +#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) +#include + +typedef struct { + uint32_t hashTable[LZ4_HASH_SIZE_U32]; + uint32_t currentOffset; + uint32_t initCheck; + const uint8_t* dictionary; + uint8_t* bufferStart; /* obsolete, used for slideInputBuffer */ + uint32_t dictSize; +} LZ4_stream_t_internal; + +typedef struct { + const uint8_t* externalDict; + size_t extDictSize; + const uint8_t* prefixEnd; + size_t prefixSize; +} LZ4_streamDecode_t_internal; + +#else + +typedef struct { + unsigned int hashTable[LZ4_HASH_SIZE_U32]; + unsigned int currentOffset; + unsigned int initCheck; + const unsigned char* dictionary; + unsigned char* bufferStart; /* obsolete, used for slideInputBuffer */ + unsigned int dictSize; +} LZ4_stream_t_internal; + +typedef struct { + const unsigned char* externalDict; + size_t extDictSize; + const unsigned char* prefixEnd; + size_t prefixSize; +} LZ4_streamDecode_t_internal; + +#endif + +/*! + * LZ4_stream_t : * information structure to track an LZ4 stream. - * important : init this structure content using LZ4_setStreamDecode or memset() before first use ! + * init this structure before first use. + * note : only use in association with static linking ! + * this definition is not API/ABI safe, + * it may change in a future version ! */ -typedef struct { unsigned int table[LZ4_STREAMDECODESIZE_U32]; } LZ4_streamDecode_t; +#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4) +#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long)) +union LZ4_stream_u { + unsigned long long table[LZ4_STREAMSIZE_U64]; + LZ4_stream_t_internal internal_donotuse; +} ; /* previously typedef'd to LZ4_stream_t */ -/* - * LZ4_setStreamDecode - * 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 + +/*! + * LZ4_streamDecode_t : + * information structure to track an LZ4 stream during decompression. + * init this structure using LZ4_setStreamDecode (or memset()) before first use + * note : only use in association with static linking ! + * this definition is not API/ABI safe, + * and may change in a future version ! */ -int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize); - -/* - * If you prefer dynamic allocation methods, - * LZ4_createStreamDecode will allocate and initialize an LZ4_streamDecode_t structure - * LZ4_freeStreamDecode releases its memory. - */ -LZ4_streamDecode_t* LZ4_createStreamDecode(void); -int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream); - -/* -*_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 its new address using LZ4_setStreamDecode() -*/ -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); +#define LZ4_STREAMDECODESIZE_U64 4 +#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U64 * sizeof(unsigned long long)) +union LZ4_streamDecode_u { + unsigned long long table[LZ4_STREAMDECODESIZE_U64]; + LZ4_streamDecode_t_internal internal_donotuse; +} ; /* previously typedef'd to LZ4_streamDecode_t */ -/* -Advanced decoding functions : -*_usingDict() : - These decoding functions work the same as - a combination of LZ4_setDictDecode() followed by LZ4_decompress_x_continue() - They don't use nor update an LZ4_streamDecode_t structure. -*/ -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 -These function prototypes are now disabled; uncomment them if you really need them. -It is highly recommended to stop using these functions and migrated to newer ones */ -/* int LZ4_uncompress (const char* source, char* dest, int outputSize); */ -/* int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize); */ -/* - * If you prefer dynamic allocation methods, - * LZ4_createStreamDecode() - * provides a pointer (void*) towards an initialized LZ4_streamDecode_t structure. - * LZ4_free just frees it. - */ -/* void* LZ4_createStreamDecode(void); */ -/*int LZ4_free (void* LZ4_stream); yes, it's the same one as for compression */ +/*! Deprecation warnings + Should deprecation warnings be a problem, + it is generally possible to disable them, + typically with -Wno-deprecated-declarations for gcc + or _CRT_SECURE_NO_WARNINGS in Visual. + Otherwise, it's also possible to define LZ4_DISABLE_DEPRECATE_WARNINGS */ +#ifdef LZ4_DISABLE_DEPRECATE_WARNINGS +# define LZ4_DEPRECATED(message) /* disable deprecation warnings */ +#else +# define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) +# if defined(__clang__) /* clang doesn't handle mixed C++11 and CNU attributes */ +# define LZ4_DEPRECATED(message) __attribute__((deprecated(message))) +# elif defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */ +# define LZ4_DEPRECATED(message) [[deprecated(message)]] +# elif (LZ4_GCC_VERSION >= 405) +# 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_DISABLE_DEPRECATE_WARNINGS */ + +/* Obsolete compression functions */ +LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress (const char* source, char* dest, int sourceSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize); + +/* Obsolete decompression functions */ +LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_fast() instead") int LZ4_uncompress (const char* source, char* dest, int outputSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_safe() instead") 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); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_createStream() instead") void* LZ4_create (char* inputBuffer); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_createStream() instead") int LZ4_sizeofStreamState(void); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_resetStream() instead") int LZ4_resetStreamState(void* state, char* inputBuffer); +LZ4LIB_API 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); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize); +LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize); -#ifdef flagLZ4STATS -#define LZ4_STATS -#endif +#endif /* LZ4_H_2983827168210 */ -#ifdef LZ4_STATS -extern int lz4stat_Literals; -extern int lz4stat_LiteralLen; -extern int lz4stat_Matches; -extern int lz4stat_BigMatch; -extern int lz4stat_BigLiteral; -#endif #if defined (__cplusplus) }