commit 5a1d26f1d3033e019442c1d66373e2f70788f8e1 parent 37d7497b121a2d66164f5a116d06c429ed15ffef Author: Michael Savage <mikejsavage@gmail.com> Date: Wed Nov 23 19:09:03 +0200 Update LZ4 Diffstat:
| lz4.cc | | | 814 | +++++++++++++++++++++++++++++++++++++------------------------------------------ |
| lz4.h | | | 381 | ++++++++++++++++++++++++++++++++++++++++++++++++++----------------------------- |
| lz4hc.cc | | | 333 | ++++++++++++++++++++++++++++++++++--------------------------------------------- |
| lz4hc.h | | | 254 | +++++++++++++++++++++++++++++++++++++++++++++---------------------------------- |
diff --git a/lz4.cc b/lz4.cc @@ -1,6 +1,6 @@ /* LZ4 - Fast LZ compression algorithm - Copyright (C) 2011-2015, Yann Collet. + Copyright (C) 2011-2016, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -28,12 +28,12 @@ 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 **************************************/ /* @@ -41,7 +41,9 @@ * 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 HEAPMODE +# define HEAPMODE 0 +#endif /* * ACCELERATION_DEFAULT : @@ -50,9 +52,31 @@ #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 generate assembly depending 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, on command line for example */ +# if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) ) +# define LZ4_FORCE_MEMORY_ACCESS 2 +# elif defined(__INTEL_COMPILER) || \ + (defined(__GNUC__) && ( defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) || defined(__ARM_ARCH_7S__) )) +# 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 @@ -62,13 +86,14 @@ #endif -/************************************** -* Includes +/*-************************************ +* Dependency **************************************/ #include "lz4.h" +/* see also "memory routines" below */ -/************************************** +/*-************************************ * Compiler Options **************************************/ #ifdef _MSC_VER /* Visual Studio */ @@ -77,19 +102,16 @@ # 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 +# if defined(__GNUC__) || defined(__clang__) +# define FORCE_INLINE static inline __attribute__((always_inline)) +# elif defined(__cplusplus) || (defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) +# define FORCE_INLINE static inline # else # define FORCE_INLINE static -# endif /* __STDC_VERSION__ */ +# endif #endif /* _MSC_VER */ -/* LZ4_GCC_VERSION is defined into lz4.h */ -#if (LZ4_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) @@ -99,7 +121,7 @@ #define unlikely(expr) expect((expr) != 0, 0) -/************************************** +/*-************************************ * Memory routines **************************************/ #include <stdlib.h> /* malloc, calloc, free */ @@ -109,54 +131,100 @@ #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 <stdint.h> 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 +232,39 @@ 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 */ +/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */ static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd) { BYTE* d = (BYTE*)dstPtr; const BYTE* s = (const BYTE*)srcPtr; - BYTE* e = (BYTE*)dstEnd; + BYTE* const e = (BYTE*)dstEnd; + do { LZ4_copy8(d,s); d+=8; s+=8; } while (d<e); } -/************************************** +/*-************************************ * Common Constants **************************************/ #define MINMATCH 4 -#define COPYLENGTH 8 +#define WILDCOPYLENGTH 8 #define LASTLITERALS 5 -#define MFLIMIT (COPYLENGTH+MINMATCH) +#define MFLIMIT (WILDCOPYLENGTH+MINMATCH) static const int LZ4_minLength = (MFLIMIT+1); #define KB *(1 <<10) @@ -236,55 +280,48 @@ static const int LZ4_minLength = (MFLIMIT+1); #define RUN_MASK ((1U<<RUN_BITS)-1) -/************************************** +/*-************************************ * Common Utils **************************************/ #define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(int)(!!(c)) }; } /* use only *after* variable declarations */ -/************************************** +/*-************************************ * 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) { # 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 unsigned r; @@ -293,14 +330,12 @@ static unsigned LZ4_NbCommonBytes (register size_t val) 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 +347,19 @@ 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<pInLimit-(STEPSIZE-1))) - { - size_t diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn); + while (likely(pIn<pInLimit-(STEPSIZE-1))) { + reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn); if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; } pIn += LZ4_NbCommonBytes(diff); return (unsigned)(pIn - pStart); } - if (LZ4_64bits()) if ((pIn<(pInLimit-3)) && (LZ4_read32(pMatch) == LZ4_read32(pIn))) { pIn+=4; pMatch+=4; } + if ((STEPSIZE==8) && (pIn<(pInLimit-3)) && (LZ4_read32(pMatch) == LZ4_read32(pIn))) { pIn+=4; pMatch+=4; } if ((pIn<(pInLimit-1)) && (LZ4_read16(pMatch) == LZ4_read16(pIn))) { pIn+=2; pMatch+=2; } if ((pIn<pInLimit) && (*pMatch == *pIn)) pIn++; return (unsigned)(pIn - pStart); @@ -332,29 +367,16 @@ static unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLi #ifndef LZ4_COMMONDEFS_ONLY -/************************************** +/*-************************************ * Local Constants **************************************/ -#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2) -#define HASHTABLESIZE (1 << LZ4_MEMORY_USAGE) -#define HASH_SIZE_U32 (1 << LZ4_HASHLOG) /* required as macro for static allocation */ - static const int LZ4_64Klimit = ((64 KB) + (MFLIMIT-1)); static const U32 LZ4_skipTrigger = 6; /* Increase this value ==> 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; @@ -365,7 +387,7 @@ 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; } @@ -373,36 +395,34 @@ 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<<hashLog) - 1; - return ((sequence * prime5bytes) >> (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) +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 +433,30 @@ 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) +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) +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); } + +/** LZ4_compress_generic() : + inlined, to ensure branches are decided at compilation time */ FORCE_INLINE int LZ4_compress_generic( - void* const ctx, + LZ4_stream_t_internal* const cctx, const char* const source, char* const dest, const int inputSize, @@ -444,15 +467,13 @@ 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 +483,9 @@ 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 +494,11 @@ 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 +506,38 @@ FORCE_INLINE int LZ4_compress_generic( if (inputSize<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ /* First Byte */ - LZ4_putPosition(ip, ctx, tableType, base); + LZ4_putPosition(ip, cctx->hashTable, 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 +545,17 @@ 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<<ML_BITS); + *token = (RUN_MASK<<ML_BITS); for(; len >= 255 ; len-=255) *op++ = 255; *op++ = (BYTE)len; } @@ -558,41 +571,37 @@ _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 +610,19 @@ _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 +634,16 @@ _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<<ML_BITS); } memcpy(op, anchor, lastRun); @@ -656,22 +657,20 @@ _last_literals: int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) { + LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->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); } } @@ -682,10 +681,10 @@ int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutp 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) FREEMEM(ctxPtr); @@ -705,22 +704,21 @@ 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 +750,30 @@ 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 +782,15 @@ 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<<ML_BITS); for(; len >= 255 ; len-=255) *op++ = 255; @@ -815,21 +808,15 @@ _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 +832,11 @@ _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 +847,20 @@ _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<<ML_BITS); } memcpy(op, anchor, lastRunSize); @@ -891,20 +873,17 @@ _last_literals: } -static int LZ4_compress_destSize_extState (void* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize) +static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize) { - LZ4_resetStream((LZ4_stream_t*)state); + LZ4_resetStream(state); - if (targetDstSize >= 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); } } @@ -912,10 +891,10 @@ static int LZ4_compress_destSize_extState (void* state, const char* src, char* d 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 */ + 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); @@ -928,7 +907,7 @@ int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targe -/******************************** +/*-****************************** * Streaming functions ********************************/ @@ -952,10 +931,10 @@ int LZ4_freeStream (LZ4_stream_t* LZ4_stream) } -#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 +942,7 @@ 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 +955,7 @@ 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 +967,12 @@ 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; i<HASH_SIZE_U32; i++) - { + for (i=0; i<LZ4_HASH_SIZE_U32; i++) { if (LZ4_dict->hashTable[i] < delta) LZ4_dict->hashTable[i]=0; else LZ4_dict->hashTable[i] -= delta; } @@ -1010,7 +985,7 @@ 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 +995,8 @@ 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 +1005,23 @@ 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 +1033,15 @@ 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 +1051,17 @@ 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; @@ -1098,14 +1076,14 @@ 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 cover all use cases. + * It shall be instantiated several times, using different sets of directives + * Note that it is important this generic function is really inlined, + * in order to remove useless branches during compilation optimization. */ FORCE_INLINE int LZ4_decompress_generic( const char* const source, @@ -1117,7 +1095,7 @@ FORCE_INLINE int LZ4_decompress_generic( 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, /* == dest when no prefix */ const BYTE* const dictStart, /* only if dict==usingExtDict */ const size_t dictSize /* note : = 0 if noDict */ ) @@ -1133,53 +1111,45 @@ FORCE_INLINE int LZ4_decompress_generic( 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 ((partialDecoding) && (oexit > oend-MFLIMIT)) oexit = oend-MFLIMIT; /* targetOutputSize too high => decode everything */ if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */ if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1); - - /* 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<iend-RUN_MASK:1) && (s==255)); - if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)(op))) goto _output_error; /* overflow detection */ - if ((safeDecode) && unlikely((size_t)(ip+length)<(size_t)(ip))) goto _output_error; /* overflow detection */ + } while ( likely(endOnInput ? ip<iend-RUN_MASK : 1) & (s==255) ); + if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) goto _output_error; /* overflow detection */ + if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) goto _output_error; /* overflow detection */ } /* copy literals */ cpy = op+length; - if (((endOnInput) && ((cpy>(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 */ } @@ -1192,84 +1162,76 @@ 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 < lowLimit))) 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; } - - 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; + match += dec32table[offset]; + memcpy(op+4, match, 4); + match -= dec64; + } else { LZ4_copy8(op, match); match+=8; } + op += 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 (op<cpy) *op++ = *match++; + } else { + LZ4_copy8(op, match); + if (length>16) LZ4_wildCopy(op+8, match+8, cpy); } - else - LZ4_wildCopy(op, match, cpy); op=cpy; /* correction */ } @@ -1301,15 +1263,7 @@ int LZ4_decompress_fast(const char* source, char* dest, int originalSize) } -/* streaming decompression functions */ - -typedef struct -{ - const BYTE* externalDict; - size_t extDictSize; - const BYTE* prefixEnd; - size_t prefixSize; -} LZ4_streamDecode_t_internal; +/*===== streaming decompression functions =====*/ /* * If you prefer dynamic allocation methods, @@ -1328,16 +1282,16 @@ int LZ4_freeStreamDecode (LZ4_streamDecode_t* 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; @@ -1354,20 +1308,17 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti */ 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, @@ -1383,22 +1334,19 @@ int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const ch 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); @@ -1422,8 +1370,7 @@ FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest { 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); @@ -1448,7 +1395,7 @@ int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compres } -/*************************************************** +/*=************************************************* * Obsolete Functions ***************************************************/ /* obsolete compression functions */ @@ -1473,29 +1420,29 @@ 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 +1460,3 @@ int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int origin } #endif /* LZ4_COMMONDEFS_ONLY */ - diff --git a/lz4.h b/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) 2011-2016, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -29,34 +29,79 @@ 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 +#ifndef LZ4_H_2983827168210 +#define LZ4_H_2983827168210 #if defined (__cplusplus) extern "C" { #endif +/* --- Dependency --- */ +#include <stddef.h> /* 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. +*/ + +/*^*************************************************************** +* Export parameters +*****************************************************************/ /* - * 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. +* LZ4_DLL_EXPORT : +* Enable exporting of functions when building a Windows DLL */ +#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.*/ +#else +# define LZ4LIB_API +#endif -/************************************** -* Version -**************************************/ + +/*========== 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_RELEASE 4 /* 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); -/************************************** +#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); +LZ4LIB_API const char* LZ4_versionString (void); + + +/*-************************************ * 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 @@ -66,15 +111,10 @@ int LZ4_versionNumber (void); #define LZ4_MEMORY_USAGE 14 -/************************************** +/*-************************************ * 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 +126,10 @@ 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 +138,16 @@ 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 +157,9 @@ 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 +167,21 @@ 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 +192,10 @@ 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 +206,9 @@ 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'. @@ -178,98 +220,73 @@ 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 struct { long long table[LZ4_STREAMSIZE_U64]; } LZ4_stream_t; +typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */ -/* - * LZ4_resetStream - * Use this function to init an allocated LZ4_stream_t structure +/*! LZ4_createStream() and LZ4_freeStream() : + * LZ4_createStream() will allocate and initialize an `LZ4_stream_t` structure. + * LZ4_freeStream() releases its memory. */ -void LZ4_resetStream (LZ4_stream_t* streamPtr); +LZ4LIB_API LZ4_stream_t* LZ4_createStream(void); +LZ4LIB_API int LZ4_freeStream (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_resetStream() : + * An LZ4_stream_t structure can be allocated once and re-used multiple times. + * Use this function to init an allocated `LZ4_stream_t` structure and start a new compression. */ -LZ4_stream_t* LZ4_createStream(void); -int LZ4_freeStream (LZ4_stream_t* streamPtr); +LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr); -/* - * LZ4_loadDict - * Use this function to load a static dictionary into LZ4_stream. - * Any previous data will be forgotten, only 'dictionary' will remain in memory. - * Loading a size of 0 is allowed. - * Return : dictionary size, in bytes (necessarily <= 64 KB) +/*! 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) */ -int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize); - -/* - * 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. +LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize); + +/*! LZ4_compress_fast_continue() : + * Compress buffer content 'src', using data from previously compressed blocks as dictionary to improve compression ratio. + * Important : Previous data blocks are assumed to still be present and unmodified ! + * 'dst' buffer must be already allocated. + * If maxDstSize >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster. + * If not, and if compressed data cannot fit into 'dst' buffer size, compression stops, and function returns a zero. */ -int LZ4_compress_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 +LZ4LIB_API 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) */ -#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); +/* creation / destruction of streaming decompression tracking structure */ +LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void); +LZ4LIB_API 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 +/*! 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); +LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize); -/* -*_continue() : +/*! +LZ4_decompress_*_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 : @@ -285,35 +302,120 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti 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); +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); -/* -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); +/*! 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 <stdint.h> + +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, + * and 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)) +union LZ4_streamDecode_u { + unsigned long long table[LZ4_STREAMDECODESIZE_U64]; + LZ4_streamDecode_t_internal internal_donotuse; +} ; /* previously typedef'd to LZ4_streamDecode_t */ -/************************************** +/*=************************************ * Obsolete Functions **************************************/ -/* Deprecate Warnings */ -/* Should these warnings messages be a problem, +/* Deprecation warnings */ +/* Should these 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 (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */ +# define LZ4_DEPRECATED(message) [[deprecated(message)]] +# elif (LZ4_GCC_VERSION >= 405) || defined(__clang__) # define LZ4_DEPRECATED(message) __attribute__((deprecated(message))) # elif (LZ4_GCC_VERSION >= 301) # define LZ4_DEPRECATED(message) __attribute__((deprecated)) @@ -323,20 +425,19 @@ 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); +LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress (const char* source, char* dest, int sourceSize); +LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize); +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. + They are only provided in lz4.c 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. @@ -358,3 +459,5 @@ LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") int LZ4_decompress #if defined (__cplusplus) } #endif + +#endif /* LZ4_H_2983827168210 */ diff --git a/lz4hc.cc b/lz4hc.cc @@ -1,6 +1,6 @@ /* LZ4 HC - High Compression Mode of LZ4 - Copyright (C) 2011-2015, Yann Collet. + Copyright (C) 2011-2016, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -28,27 +28,36 @@ 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 source repository : https://github.com/lz4/lz4 - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c */ +/* note : lz4hc is not an independent module, it requires lz4.h/lz4.c for proper compilation */ - -/************************************** +/* ************************************* * Tuning Parameter -**************************************/ -static const int LZ4HC_compressionLevel_default = 9; +***************************************/ + +/*! + * HEAPMODE : + * Select how default compression function will allocate workplace memory, + * in stack (0:fastest), or in heap (1:requires malloc()). + * Since workplace is rather large, heap mode is recommended. + */ +#ifndef LZ4HC_HEAPMODE +# define LZ4HC_HEAPMODE 1 +#endif -/************************************** -* Includes -**************************************/ +/* ************************************* +* Dependency +***************************************/ #include "lz4hc.h" -/************************************** +/* ************************************* * Local Compiler Options -**************************************/ +***************************************/ #if defined(__GNUC__) # pragma GCC diagnostic ignored "-Wunused-function" #endif @@ -58,52 +67,24 @@ static const int LZ4HC_compressionLevel_default = 9; #endif -/************************************** +/* ************************************* * Common LZ4 definition -**************************************/ +***************************************/ #define LZ4_COMMONDEFS_ONLY #include "lz4.cc" -/************************************** +/* ************************************* * Local Constants -**************************************/ -#define DICTIONARY_LOGSIZE 16 -#define MAXD (1<<DICTIONARY_LOGSIZE) -#define MAXD_MASK (MAXD - 1) - -#define HASH_LOG (DICTIONARY_LOGSIZE-1) -#define HASHTABLESIZE (1 << HASH_LOG) -#define HASH_MASK (HASHTABLESIZE - 1) - +***************************************/ #define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH) -static const int g_maxCompressionLevel = 16; - - -/************************************** -* Local Types -**************************************/ -typedef struct -{ - U32 hashTable[HASHTABLESIZE]; - U16 chainTable[MAXD]; - const BYTE* end; /* next block here to continue on current prefix */ - const BYTE* base; /* All index relative to this position */ - const BYTE* dictBase; /* alternate base for extDict */ - BYTE* inputBuffer; /* deprecated */ - U32 dictLimit; /* below that point, need extDict */ - U32 lowLimit; /* below that point, no more dict */ - U32 nextToUpdate; /* index from which to continue dictionary update */ - U32 compressionLevel; -} LZ4HC_Data_Structure; - /************************************** * Local Macros **************************************/ -#define HASH_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH*8)-HASH_LOG)) -//#define DELTANEXTU16(p) chainTable[(p) & MAXD_MASK] /* flexible, MAXD dependent */ +#define HASH_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH*8)-LZ4HC_HASH_LOG)) +/* #define DELTANEXTU16(p) chainTable[(p) & LZ4HC_MAXD_MASK] */ /* flexible, LZ4HC_MAXD dependent */ #define DELTANEXTU16(p) chainTable[(U16)(p)] /* faster */ static U32 LZ4HC_hashPtr(const void* ptr) { return HASH_FUNCTION(LZ4_read32(ptr)); } @@ -113,7 +94,7 @@ static U32 LZ4HC_hashPtr(const void* ptr) { return HASH_FUNCTION(LZ4_read32(ptr) /************************************** * HC Compression **************************************/ -static void LZ4HC_init (LZ4HC_Data_Structure* hc4, const BYTE* start) +static void LZ4HC_init (LZ4HC_CCtx_internal* hc4, const BYTE* start) { MEM_INIT((void*)hc4->hashTable, 0, sizeof(hc4->hashTable)); MEM_INIT(hc4->chainTable, 0xFF, sizeof(hc4->chainTable)); @@ -127,21 +108,20 @@ static void LZ4HC_init (LZ4HC_Data_Structure* hc4, const BYTE* start) /* Update chains up to ip (excluded) */ -FORCE_INLINE void LZ4HC_Insert (LZ4HC_Data_Structure* hc4, const BYTE* ip) +FORCE_INLINE void LZ4HC_Insert (LZ4HC_CCtx_internal* hc4, const BYTE* ip) { - U16* chainTable = hc4->chainTable; - U32* HashTable = hc4->hashTable; + U16* const chainTable = hc4->chainTable; + U32* const hashTable = hc4->hashTable; const BYTE* const base = hc4->base; - const U32 target = (U32)(ip - base); + U32 const target = (U32)(ip - base); U32 idx = hc4->nextToUpdate; - while(idx < target) - { - U32 h = LZ4HC_hashPtr(base+idx); - size_t delta = idx - HashTable[h]; + while (idx < target) { + U32 const h = LZ4HC_hashPtr(base+idx); + size_t delta = idx - hashTable[h]; if (delta>MAX_DISTANCE) delta = MAX_DISTANCE; DELTANEXTU16(idx) = (U16)delta; - HashTable[h] = idx; + hashTable[h] = idx; idx++; } @@ -149,7 +129,7 @@ FORCE_INLINE void LZ4HC_Insert (LZ4HC_Data_Structure* hc4, const BYTE* ip) } -FORCE_INLINE int LZ4HC_InsertAndFindBestMatch (LZ4HC_Data_Structure* hc4, /* Index table will be updated */ +FORCE_INLINE int LZ4HC_InsertAndFindBestMatch (LZ4HC_CCtx_internal* hc4, /* Index table will be updated */ const BYTE* ip, const BYTE* const iLimit, const BYTE** matchpos, const int maxNbAttempts) @@ -161,7 +141,6 @@ FORCE_INLINE int LZ4HC_InsertAndFindBestMatch (LZ4HC_Data_Structure* hc4, /* I const U32 dictLimit = hc4->dictLimit; const U32 lowLimit = (hc4->lowLimit + 64 KB > (U32)(ip-base)) ? hc4->lowLimit : (U32)(ip - base) - (64 KB - 1); U32 matchIndex; - const BYTE* match; int nbAttempts=maxNbAttempts; size_t ml=0; @@ -169,24 +148,19 @@ FORCE_INLINE int LZ4HC_InsertAndFindBestMatch (LZ4HC_Data_Structure* hc4, /* I LZ4HC_Insert(hc4, ip); matchIndex = HashTable[LZ4HC_hashPtr(ip)]; - while ((matchIndex>=lowLimit) && (nbAttempts)) - { + while ((matchIndex>=lowLimit) && (nbAttempts)) { nbAttempts--; - if (matchIndex >= dictLimit) - { - match = base + matchIndex; + if (matchIndex >= dictLimit) { + const BYTE* const match = base + matchIndex; if (*(match+ml) == *(ip+ml) && (LZ4_read32(match) == LZ4_read32(ip))) { - size_t mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, iLimit) + MINMATCH; + size_t const mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, iLimit) + MINMATCH; if (mlt > ml) { ml = mlt; *matchpos = match; } } - } - else - { - match = dictBase + matchIndex; - if (LZ4_read32(match) == LZ4_read32(ip)) - { + } else { + const BYTE* const match = dictBase + matchIndex; + if (LZ4_read32(match) == LZ4_read32(ip)) { size_t mlt; const BYTE* vLimit = ip + (dictLimit - matchIndex); if (vLimit > iLimit) vLimit = iLimit; @@ -204,7 +178,7 @@ FORCE_INLINE int LZ4HC_InsertAndFindBestMatch (LZ4HC_Data_Structure* hc4, /* I FORCE_INLINE int LZ4HC_InsertAndGetWiderMatch ( - LZ4HC_Data_Structure* hc4, + LZ4HC_CCtx_internal* hc4, const BYTE* const ip, const BYTE* const iLowLimit, const BYTE* const iHighLimit, @@ -229,38 +203,32 @@ FORCE_INLINE int LZ4HC_InsertAndGetWiderMatch ( LZ4HC_Insert(hc4, ip); matchIndex = HashTable[LZ4HC_hashPtr(ip)]; - while ((matchIndex>=lowLimit) && (nbAttempts)) - { + while ((matchIndex>=lowLimit) && (nbAttempts)) { nbAttempts--; - if (matchIndex >= dictLimit) - { + if (matchIndex >= dictLimit) { const BYTE* matchPtr = base + matchIndex; - if (*(iLowLimit + longest) == *(matchPtr - delta + longest)) - if (LZ4_read32(matchPtr) == LZ4_read32(ip)) - { + if (*(iLowLimit + longest) == *(matchPtr - delta + longest)) { + if (LZ4_read32(matchPtr) == LZ4_read32(ip)) { int mlt = MINMATCH + LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, iHighLimit); int back = 0; - while ((ip+back>iLowLimit) + while ((ip+back > iLowLimit) && (matchPtr+back > lowPrefixPtr) && (ip[back-1] == matchPtr[back-1])) back--; mlt -= back; - if (mlt > longest) - { + if (mlt > longest) { longest = (int)mlt; *matchpos = matchPtr+back; *startpos = ip+back; } } - } - else - { - const BYTE* matchPtr = dictBase + matchIndex; - if (LZ4_read32(matchPtr) == LZ4_read32(ip)) - { + } + } else { + const BYTE* const matchPtr = dictBase + matchIndex; + if (LZ4_read32(matchPtr) == LZ4_read32(ip)) { size_t mlt; int back=0; const BYTE* vLimit = ip + (dictLimit - matchIndex); @@ -320,8 +288,15 @@ FORCE_INLINE int LZ4HC_encodeSequence ( /* Encode MatchLength */ length = (int)(matchLength-MINMATCH); if ((limitedOutputBuffer) && (*op + (length>>8) + (1 + LASTLITERALS) > oend)) return 1; /* Check output limit */ - if (length>=(int)ML_MASK) { *token+=ML_MASK; length-=ML_MASK; for(; length > 509 ; length-=510) { *(*op)++ = 255; *(*op)++ = 255; } if (length > 254) { length-=255; *(*op)++ = 255; } *(*op)++ = (BYTE)length; } - else *token += (BYTE)(length); + if (length>=(int)ML_MASK) { + *token += ML_MASK; + length -= ML_MASK; + for(; length > 509 ; length-=510) { *(*op)++ = 255; *(*op)++ = 255; } + if (length > 254) { length-=255; *(*op)++ = 255; } + *(*op)++ = (BYTE)length; + } else { + *token += (BYTE)(length); + } /* Prepare next loop */ *ip += matchLength; @@ -332,16 +307,15 @@ FORCE_INLINE int LZ4HC_encodeSequence ( static int LZ4HC_compress_generic ( - void* ctxvoid, - const char* source, - char* dest, - int inputSize, - int maxOutputSize, + LZ4HC_CCtx_internal* const ctx, + const char* const source, + char* const dest, + int const inputSize, + int const maxOutputSize, int compressionLevel, limitedOutput_directive limit ) { - LZ4HC_Data_Structure* ctx = (LZ4HC_Data_Structure*) ctxvoid; const BYTE* ip = (const BYTE*) source; const BYTE* anchor = ip; const BYTE* const iend = ip + inputSize; @@ -353,26 +327,24 @@ static int LZ4HC_compress_generic ( unsigned maxNbAttempts; int ml, ml2, ml3, ml0; - const BYTE* ref=NULL; - const BYTE* start2=NULL; - const BYTE* ref2=NULL; - const BYTE* start3=NULL; - const BYTE* ref3=NULL; + const BYTE* ref = NULL; + const BYTE* start2 = NULL; + const BYTE* ref2 = NULL; + const BYTE* start3 = NULL; + const BYTE* ref3 = NULL; const BYTE* start0; const BYTE* ref0; - /* init */ - if (compressionLevel > g_maxCompressionLevel) compressionLevel = g_maxCompressionLevel; - if (compressionLevel < 1) compressionLevel = LZ4HC_compressionLevel_default; + if (compressionLevel > LZ4HC_MAX_CLEVEL) compressionLevel = LZ4HC_MAX_CLEVEL; + if (compressionLevel < 1) compressionLevel = LZ4HC_DEFAULT_CLEVEL; maxNbAttempts = 1 << (compressionLevel-1); ctx->end += inputSize; ip++; /* Main Loop */ - while (ip < mflimit) - { + while (ip < mflimit) { ml = LZ4HC_InsertAndFindBestMatch (ctx, ip, matchlimit, (&ref), maxNbAttempts); if (!ml) { ip++; continue; } @@ -383,19 +355,16 @@ static int LZ4HC_compress_generic ( _Search2: if (ip+ml < mflimit) - ml2 = LZ4HC_InsertAndGetWiderMatch(ctx, ip + ml - 2, ip + 1, matchlimit, ml, &ref2, &start2, maxNbAttempts); + ml2 = LZ4HC_InsertAndGetWiderMatch(ctx, ip + ml - 2, ip + 0, matchlimit, ml, &ref2, &start2, maxNbAttempts); else ml2 = ml; - if (ml2 == ml) /* No better match */ - { + if (ml2 == ml) { /* No better match */ if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0; continue; } - if (start0 < ip) - { - if (start2 < ip + ml0) /* empirical */ - { + if (start0 < ip) { + if (start2 < ip + ml0) { /* empirical */ ip = start0; ref = ref0; ml = ml0; @@ -403,8 +372,7 @@ _Search2: } /* Here, start0==ip */ - if ((start2 - ip) < 3) /* First Match too small : removed */ - { + if ((start2 - ip) < 3) { /* First Match too small : removed */ ml = ml2; ip = start2; ref =ref2; @@ -417,15 +385,13 @@ _Search3: * ml2 > ml1, and * ip1+3 <= ip2 (usually < ip1+ml1) */ - if ((start2 - ip) < OPTIMAL_ML) - { + if ((start2 - ip) < OPTIMAL_ML) { int correction; int new_ml = ml; if (new_ml > OPTIMAL_ML) new_ml = OPTIMAL_ML; if (ip+new_ml > start2 + ml2 - MINMATCH) new_ml = (int)(start2 - ip) + ml2 - MINMATCH; correction = new_ml - (int)(start2 - ip); - if (correction > 0) - { + if (correction > 0) { start2 += correction; ref2 += correction; ml2 -= correction; @@ -437,8 +403,7 @@ _Search3: ml3 = LZ4HC_InsertAndGetWiderMatch(ctx, start2 + ml2 - 3, start2, matchlimit, ml2, &ref3, &start3, maxNbAttempts); else ml3 = ml2; - if (ml3 == ml2) /* No better match : 2 sequences to encode */ - { + if (ml3 == ml2) { /* No better match : 2 sequences to encode */ /* ip & ref are known; Now for ml */ if (start2 < ip+ml) ml = (int)(start2 - ip); /* Now, encode 2 sequences */ @@ -448,18 +413,14 @@ _Search3: continue; } - if (start3 < ip+ml+3) /* Not enough space for match 2 : remove it */ - { - if (start3 >= (ip+ml)) /* can write Seq1 immediately ==> Seq2 is removed, so Seq3 becomes Seq1 */ - { - if (start2 < ip+ml) - { + if (start3 < ip+ml+3) { /* Not enough space for match 2 : remove it */ + if (start3 >= (ip+ml)) { /* can write Seq1 immediately ==> Seq2 is removed, so Seq3 becomes Seq1 */ + if (start2 < ip+ml) { int correction = (int)(ip+ml - start2); start2 += correction; ref2 += correction; ml2 -= correction; - if (ml2 < MINMATCH) - { + if (ml2 < MINMATCH) { start2 = start3; ref2 = ref3; ml2 = ml3; @@ -487,23 +448,18 @@ _Search3: * OK, now we have 3 ascending matches; let's write at least the first one * ip & ref are known; Now for ml */ - if (start2 < ip+ml) - { - if ((start2 - ip) < (int)ML_MASK) - { + if (start2 < ip+ml) { + if ((start2 - ip) < (int)ML_MASK) { int correction; if (ml > OPTIMAL_ML) ml = OPTIMAL_ML; if (ip + ml > start2 + ml2 - MINMATCH) ml = (int)(start2 - ip) + ml2 - MINMATCH; correction = ml - (int)(start2 - ip); - if (correction > 0) - { + if (correction > 0) { start2 += correction; ref2 += correction; ml2 -= correction; } - } - else - { + } else { ml = (int)(start2 - ip); } } @@ -521,8 +477,7 @@ _Search3: } /* Encode Last Literals */ - { - int lastRun = (int)(iend - anchor); + { int lastRun = (int)(iend - anchor); if ((limit) && (((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<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun > 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; } else *op++ = (BYTE)(lastRun<<ML_BITS); @@ -535,22 +490,32 @@ _Search3: } -int LZ4_sizeofStateHC(void) { return sizeof(LZ4HC_Data_Structure); } +int LZ4_sizeofStateHC(void) { return sizeof(LZ4_streamHC_t); } int LZ4_compress_HC_extStateHC (void* state, const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel) { + LZ4HC_CCtx_internal* ctx = &((LZ4_streamHC_t*)state)->internal_donotuse; if (((size_t)(state)&(sizeof(void*)-1)) != 0) return 0; /* Error : state is not aligned for pointers (32 or 64 bits) */ - LZ4HC_init ((LZ4HC_Data_Structure*)state, (const BYTE*)src); + LZ4HC_init (ctx, (const BYTE*)src); if (maxDstSize < LZ4_compressBound(srcSize)) - return LZ4HC_compress_generic (state, src, dst, srcSize, maxDstSize, compressionLevel, limitedOutput); + return LZ4HC_compress_generic (ctx, src, dst, srcSize, maxDstSize, compressionLevel, limitedOutput); else - return LZ4HC_compress_generic (state, src, dst, srcSize, maxDstSize, compressionLevel, noLimit); + return LZ4HC_compress_generic (ctx, src, dst, srcSize, maxDstSize, compressionLevel, noLimit); } int LZ4_compress_HC(const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel) { - LZ4HC_Data_Structure state; - return LZ4_compress_HC_extStateHC(&state, src, dst, srcSize, maxDstSize, compressionLevel); +#if defined(LZ4HC_HEAPMODE) && LZ4HC_HEAPMODE==1 + LZ4_streamHC_t* const statePtr = (LZ4_streamHC_t*)malloc(sizeof(LZ4_streamHC_t)); +#else + LZ4_streamHC_t state; + LZ4_streamHC_t* const statePtr = &state; +#endif + int const cSize = LZ4_compress_HC_extStateHC(statePtr, src, dst, srcSize, maxDstSize, compressionLevel); +#if defined(LZ4HC_HEAPMODE) && LZ4HC_HEAPMODE==1 + free(statePtr); +#endif + return cSize; } @@ -566,16 +531,15 @@ int LZ4_freeStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr) { free(LZ4_st /* initialization */ void LZ4_resetStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel) { - LZ4_STATIC_ASSERT(sizeof(LZ4HC_Data_Structure) <= sizeof(LZ4_streamHC_t)); /* if compilation fails here, LZ4_STREAMHCSIZE must be increased */ - ((LZ4HC_Data_Structure*)LZ4_streamHCPtr)->base = NULL; - ((LZ4HC_Data_Structure*)LZ4_streamHCPtr)->compressionLevel = (unsigned)compressionLevel; + LZ4_STATIC_ASSERT(sizeof(LZ4HC_CCtx_internal) <= sizeof(size_t) * LZ4_STREAMHCSIZE_SIZET); /* if compilation fails here, LZ4_STREAMHCSIZE must be increased */ + LZ4_streamHCPtr->internal_donotuse.base = NULL; + LZ4_streamHCPtr->internal_donotuse.compressionLevel = (unsigned)compressionLevel; } int LZ4_loadDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, const char* dictionary, int dictSize) { - LZ4HC_Data_Structure* ctxPtr = (LZ4HC_Data_Structure*) LZ4_streamHCPtr; - if (dictSize > 64 KB) - { + LZ4HC_CCtx_internal* ctxPtr = &LZ4_streamHCPtr->internal_donotuse; + if (dictSize > 64 KB) { dictionary += dictSize - 64 KB; dictSize = 64 KB; } @@ -588,10 +552,9 @@ int LZ4_loadDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, const char* dictionary, int /* compression */ -static void LZ4HC_setExternalDict(LZ4HC_Data_Structure* ctxPtr, const BYTE* newBlock) +static void LZ4HC_setExternalDict(LZ4HC_CCtx_internal* ctxPtr, const BYTE* newBlock) { - if (ctxPtr->end >= ctxPtr->base + 4) - LZ4HC_Insert (ctxPtr, ctxPtr->end-3); /* Referencing remaining dictionary content */ + if (ctxPtr->end >= ctxPtr->base + 4) LZ4HC_Insert (ctxPtr, ctxPtr->end-3); /* Referencing remaining dictionary content */ /* Only one memory segment for extDict, so any previous extDict is lost at this stage */ ctxPtr->lowLimit = ctxPtr->dictLimit; ctxPtr->dictLimit = (U32)(ctxPtr->end - ctxPtr->base); @@ -601,34 +564,29 @@ static void LZ4HC_setExternalDict(LZ4HC_Data_Structure* ctxPtr, const BYTE* newB ctxPtr->nextToUpdate = ctxPtr->dictLimit; /* match referencing will resume from there */ } -static int LZ4_compressHC_continue_generic (LZ4HC_Data_Structure* ctxPtr, +static int LZ4_compressHC_continue_generic (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize, limitedOutput_directive limit) { + LZ4HC_CCtx_internal* ctxPtr = &LZ4_streamHCPtr->internal_donotuse; /* auto-init if forgotten */ - if (ctxPtr->base == NULL) - LZ4HC_init (ctxPtr, (const BYTE*) source); + if (ctxPtr->base == NULL) LZ4HC_init (ctxPtr, (const BYTE*) source); /* Check overflow */ - if ((size_t)(ctxPtr->end - ctxPtr->base) > 2 GB) - { + if ((size_t)(ctxPtr->end - ctxPtr->base) > 2 GB) { size_t dictSize = (size_t)(ctxPtr->end - ctxPtr->base) - ctxPtr->dictLimit; if (dictSize > 64 KB) dictSize = 64 KB; - - LZ4_loadDictHC((LZ4_streamHC_t*)ctxPtr, (const char*)(ctxPtr->end) - dictSize, (int)dictSize); + LZ4_loadDictHC(LZ4_streamHCPtr, (const char*)(ctxPtr->end) - dictSize, (int)dictSize); } /* Check if blocks follow each other */ - if ((const BYTE*)source != ctxPtr->end) - LZ4HC_setExternalDict(ctxPtr, (const BYTE*)source); + if ((const BYTE*)source != ctxPtr->end) LZ4HC_setExternalDict(ctxPtr, (const BYTE*)source); /* Check overlapping input/dictionary space */ - { - const BYTE* sourceEnd = (const BYTE*) source + inputSize; - const BYTE* dictBegin = ctxPtr->dictBase + ctxPtr->lowLimit; - const BYTE* dictEnd = ctxPtr->dictBase + ctxPtr->dictLimit; - if ((sourceEnd > dictBegin) && ((const BYTE*)source < dictEnd)) - { + { const BYTE* sourceEnd = (const BYTE*) source + inputSize; + const BYTE* const dictBegin = ctxPtr->dictBase + ctxPtr->lowLimit; + const BYTE* const dictEnd = ctxPtr->dictBase + ctxPtr->dictLimit; + if ((sourceEnd > dictBegin) && ((const BYTE*)source < dictEnd)) { if (sourceEnd > dictEnd) sourceEnd = dictEnd; ctxPtr->lowLimit = (U32)(sourceEnd - ctxPtr->dictBase); if (ctxPtr->dictLimit - ctxPtr->lowLimit < 4) ctxPtr->lowLimit = ctxPtr->dictLimit; @@ -641,9 +599,9 @@ static int LZ4_compressHC_continue_generic (LZ4HC_Data_Structure* ctxPtr, int LZ4_compress_HC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize) { if (maxOutputSize < LZ4_compressBound(inputSize)) - return LZ4_compressHC_continue_generic ((LZ4HC_Data_Structure*)LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, limitedOutput); + return LZ4_compressHC_continue_generic (LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, limitedOutput); else - return LZ4_compressHC_continue_generic ((LZ4HC_Data_Structure*)LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, noLimit); + return LZ4_compressHC_continue_generic (LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, noLimit); } @@ -651,14 +609,13 @@ int LZ4_compress_HC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* sourc int LZ4_saveDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, char* safeBuffer, int dictSize) { - LZ4HC_Data_Structure* streamPtr = (LZ4HC_Data_Structure*)LZ4_streamHCPtr; - int prefixSize = (int)(streamPtr->end - (streamPtr->base + streamPtr->dictLimit)); + LZ4HC_CCtx_internal* const streamPtr = &LZ4_streamHCPtr->internal_donotuse; + int const prefixSize = (int)(streamPtr->end - (streamPtr->base + streamPtr->dictLimit)); if (dictSize > 64 KB) dictSize = 64 KB; if (dictSize < 4) dictSize = 0; if (dictSize > prefixSize) dictSize = prefixSize; memmove(safeBuffer, streamPtr->end - dictSize, dictSize); - { - U32 endIndex = (U32)(streamPtr->end - streamPtr->base); + { U32 const endIndex = (U32)(streamPtr->end - streamPtr->base); streamPtr->end = (const BYTE*)safeBuffer + dictSize; streamPtr->base = streamPtr->end - endIndex; streamPtr->dictLimit = endIndex - dictSize; @@ -672,8 +629,8 @@ int LZ4_saveDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, char* safeBuffer, int dictS /*********************************** * Deprecated Functions ***********************************/ +/* These functions currently generate deprecation warnings */ /* Deprecated compression functions */ -/* These functions are planned to start generate warnings by r131 approximately */ int LZ4_compressHC(const char* src, char* dst, int srcSize) { return LZ4_compress_HC (src, dst, srcSize, LZ4_compressBound(srcSize), 0); } int LZ4_compressHC_limitedOutput(const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_HC(src, dst, srcSize, maxDstSize, 0); } int LZ4_compressHC2(const char* src, char* dst, int srcSize, int cLevel) { return LZ4_compress_HC (src, dst, srcSize, LZ4_compressBound(srcSize), cLevel); } @@ -687,45 +644,41 @@ int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* ctx, const char* src, /* Deprecated streaming functions */ -/* These functions currently generate deprecation warnings */ int LZ4_sizeofStreamStateHC(void) { return LZ4_STREAMHCSIZE; } int LZ4_resetStreamStateHC(void* state, char* inputBuffer) { + LZ4HC_CCtx_internal *ctx = &((LZ4_streamHC_t*)state)->internal_donotuse; if ((((size_t)state) & (sizeof(void*)-1)) != 0) return 1; /* Error : pointer is not aligned for pointer (32 or 64 bits) */ - LZ4HC_init((LZ4HC_Data_Structure*)state, (const BYTE*)inputBuffer); - ((LZ4HC_Data_Structure*)state)->inputBuffer = (BYTE*)inputBuffer; + LZ4HC_init(ctx, (const BYTE*)inputBuffer); + ctx->inputBuffer = (BYTE*)inputBuffer; return 0; } void* LZ4_createHC (char* inputBuffer) { - void* hc4 = ALLOCATOR(1, sizeof(LZ4HC_Data_Structure)); + LZ4_streamHC_t* hc4 = (LZ4_streamHC_t*)ALLOCATOR(1, sizeof(LZ4_streamHC_t)); if (hc4 == NULL) return NULL; /* not enough memory */ - LZ4HC_init ((LZ4HC_Data_Structure*)hc4, (const BYTE*)inputBuffer); - ((LZ4HC_Data_Structure*)hc4)->inputBuffer = (BYTE*)inputBuffer; + LZ4HC_init (&hc4->internal_donotuse, (const BYTE*)inputBuffer); + hc4->internal_donotuse.inputBuffer = (BYTE*)inputBuffer; return hc4; } -int LZ4_freeHC (void* LZ4HC_Data) -{ - FREEMEM(LZ4HC_Data); - return (0); -} +int LZ4_freeHC (void* LZ4HC_Data) { FREEMEM(LZ4HC_Data); return 0; } int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel) { - return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, 0, compressionLevel, noLimit); + return LZ4HC_compress_generic (&((LZ4_streamHC_t*)LZ4HC_Data)->internal_donotuse, source, dest, inputSize, 0, compressionLevel, noLimit); } int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel) { - return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, maxOutputSize, compressionLevel, limitedOutput); + return LZ4HC_compress_generic (&((LZ4_streamHC_t*)LZ4HC_Data)->internal_donotuse, source, dest, inputSize, maxOutputSize, compressionLevel, limitedOutput); } char* LZ4_slideInputBufferHC(void* LZ4HC_Data) { - LZ4HC_Data_Structure* hc4 = (LZ4HC_Data_Structure*)LZ4HC_Data; - int dictSize = LZ4_saveDictHC((LZ4_streamHC_t*)LZ4HC_Data, (char*)(hc4->inputBuffer), 64 KB); + LZ4HC_CCtx_internal* const hc4 = &((LZ4_streamHC_t*)LZ4HC_Data)->internal_donotuse; + int const dictSize = LZ4_saveDictHC((LZ4_streamHC_t*)LZ4HC_Data, (char*)(hc4->inputBuffer), 64 KB); return (char*)(hc4->inputBuffer + dictSize); } diff --git a/lz4hc.h b/lz4hc.h @@ -1,7 +1,7 @@ /* LZ4 HC - High Compression Mode of LZ4 Header File - Copyright (C) 2011-2015, Yann Collet. + Copyright (C) 2011-2016, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) Redistribution and use in source and binary forms, with or without @@ -28,107 +28,91 @@ 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 source repository : https://github.com/lz4/lz4 - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c */ -#pragma once - +#ifndef LZ4_HC_H_19834876238432 +#define LZ4_HC_H_19834876238432 #if defined (__cplusplus) extern "C" { #endif -/***************************** -* Includes -*****************************/ -#include <stddef.h> /* size_t */ - +/* --- Dependency --- */ +/* note : lz4hc is not an independent module, it requires lz4.h/lz4.c for proper compilation */ +#include "lz4.h" /* stddef, LZ4LIB_API, LZ4_DEPRECATED */ -/************************************** -* Block Compression -**************************************/ -int LZ4_compress_HC (const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel); -/* -LZ4_compress_HC : - Destination buffer 'dst' must be already allocated. - Compression completion is guaranteed if 'dst' buffer is sized to handle worst circumstances (data not compressible) - Worst size evaluation is provided by function LZ4_compressBound() (see "lz4.h") - srcSize : Max supported value is LZ4_MAX_INPUT_SIZE (see "lz4.h") - compressionLevel : Recommended values are between 4 and 9, although any value between 0 and 16 will work. - 0 means "use default value" (see lz4hc.c). - Values >16 behave the same as 16. - return : the number of bytes written into buffer 'dst' - or 0 if compression fails. -*/ +/* --- Useful constants --- */ +#define LZ4HC_MIN_CLEVEL 3 +#define LZ4HC_DEFAULT_CLEVEL 9 +#define LZ4HC_MAX_CLEVEL 16 -/* Note : - Decompression functions are provided within LZ4 source code (see "lz4.h") (BSD license) -*/ +/*-************************************ + * Block Compression + **************************************/ +/*! LZ4_compress_HC() : + * Compress data from `src` into `dst`, using the more powerful but slower "HC" algorithm. + * `dst` must be already allocated. + * Compression is guaranteed to succeed if `dstCapacity >= LZ4_compressBound(srcSize)` (see "lz4.h") + * Max supported `srcSize` value is LZ4_MAX_INPUT_SIZE (see "lz4.h") + * `compressionLevel` : Recommended values are between 4 and 9, although any value between 1 and LZ4HC_MAX_CLEVEL will work. + * Values >LZ4HC_MAX_CLEVEL behave the same as 16. + * @return : the number of bytes written into 'dst' + * or 0 if compression fails. + */ +LZ4LIB_API int LZ4_compress_HC (const char* src, char* dst, int srcSize, int dstCapacity, int compressionLevel); -int LZ4_sizeofStateHC(void); -int LZ4_compress_HC_extStateHC(void* state, const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel); -/* -LZ4_compress_HC_extStateHC() : - Use this function if you prefer to manually allocate memory for compression tables. - To know how much memory must be allocated for the compression tables, use : - int LZ4_sizeofStateHC(); - Allocated memory must be aligned on 8-bytes boundaries (which a normal malloc() will do properly). - - The allocated memory can then be provided to the compression functions using 'void* state' parameter. - LZ4_compress_HC_extStateHC() is equivalent to previously described function. - It just uses externally allocated memory for stateHC. -*/ +/* Note : + * Decompression functions are provided within "lz4.h" (BSD license) + */ -/************************************** -* Streaming Compression -**************************************/ -#define LZ4_STREAMHCSIZE 262192 -#define LZ4_STREAMHCSIZE_SIZET (LZ4_STREAMHCSIZE / sizeof(size_t)) -typedef struct { size_t table[LZ4_STREAMHCSIZE_SIZET]; } LZ4_streamHC_t; -/* - LZ4_streamHC_t - This structure allows static allocation of LZ4 HC streaming state. - State must then be initialized using LZ4_resetStreamHC() before first use. +/*! LZ4_compress_HC_extStateHC() : + * Same as LZ4_compress_HC(), but using an externally allocated memory segment for `state`. + * `state` size is provided by LZ4_sizeofStateHC(). + * Memory segment must be aligned on 8-bytes boundaries (which a normal malloc() will do properly). + */ +LZ4LIB_API int LZ4_compress_HC_extStateHC(void* state, const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel); +LZ4LIB_API int LZ4_sizeofStateHC(void); - Static allocation should only be used in combination with static linking. - If you want to use LZ4 as a DLL, please use construction functions below, which are future-proof. -*/ +/*-************************************ + * Streaming Compression + * Bufferless synchronous API + **************************************/ + typedef union LZ4_streamHC_u LZ4_streamHC_t; /* incomplete type (defined later) */ -LZ4_streamHC_t* LZ4_createStreamHC(void); -int LZ4_freeStreamHC (LZ4_streamHC_t* streamHCPtr); -/* - These functions create and release memory for LZ4 HC streaming state. - Newly created states are already initialized. - Existing state space can be re-used anytime using LZ4_resetStreamHC(). - If you use LZ4 as a DLL, use these functions instead of static structure allocation, - to avoid size mismatch between different versions. -*/ +/*! LZ4_createStreamHC() and LZ4_freeStreamHC() : + * These functions create and release memory for LZ4 HC streaming state. + * Newly created states are automatically initialized. + * Existing states can be re-used several times, using LZ4_resetStreamHC(). + * These methods are API and ABI stable, they can be used in combination with a DLL. + */ +LZ4LIB_API LZ4_streamHC_t* LZ4_createStreamHC(void); +LZ4LIB_API int LZ4_freeStreamHC (LZ4_streamHC_t* streamHCPtr); -void LZ4_resetStreamHC (LZ4_streamHC_t* streamHCPtr, int compressionLevel); -int LZ4_loadDictHC (LZ4_streamHC_t* streamHCPtr, const char* dictionary, int dictSize); +LZ4LIB_API void LZ4_resetStreamHC (LZ4_streamHC_t* streamHCPtr, int compressionLevel); +LZ4LIB_API int LZ4_loadDictHC (LZ4_streamHC_t* streamHCPtr, const char* dictionary, int dictSize); -int LZ4_compress_HC_continue (LZ4_streamHC_t* streamHCPtr, const char* src, char* dst, int srcSize, int maxDstSize); +LZ4LIB_API int LZ4_compress_HC_continue (LZ4_streamHC_t* streamHCPtr, const char* src, char* dst, int srcSize, int maxDstSize); -int LZ4_saveDictHC (LZ4_streamHC_t* streamHCPtr, char* safeBuffer, int maxDictSize); +LZ4LIB_API int LZ4_saveDictHC (LZ4_streamHC_t* streamHCPtr, char* safeBuffer, int maxDictSize); /* These functions compress data in successive blocks of any size, using previous blocks as dictionary. One key assumption is that previous blocks (up to 64 KB) remain read-accessible while compressing next blocks. - There is an exception for ring buffers, which can be smaller 64 KB. - Such case is automatically detected and correctly handled by LZ4_compress_HC_continue(). + There is an exception for ring buffers, which can be smaller than 64 KB. + Ring buffers scenario is automatically detected and handled by LZ4_compress_HC_continue(). Before starting compression, state must be properly initialized, using LZ4_resetStreamHC(). A first "fictional block" can then be designated as initial dictionary, using LZ4_loadDictHC() (Optional). Then, use LZ4_compress_HC_continue() to compress each successive block. - It works like LZ4_compress_HC(), but use previous memory blocks as dictionary to improve compression. Previous memory blocks (including initial dictionary when present) must remain accessible and unmodified during compression. - As a reminder, size 'dst' buffer to handle worst cases, using LZ4_compressBound(), to ensure success of compression operation. + 'dst' buffer should be sized to handle worst case scenarios, using LZ4_compressBound(), to ensure operation success. If, for any reason, previous data blocks can't be preserved unmodified in memory during next compression block, you must save it to a safer memory space, using LZ4_saveDictHC(). @@ -136,50 +120,100 @@ int LZ4_saveDictHC (LZ4_streamHC_t* streamHCPtr, char* safeBuffer, int maxDictSi */ +/*-****************************************** + * !!!!! STATIC LINKING ONLY !!!!! + *******************************************/ + + /*-************************************* + * PRIVATE DEFINITIONS : + * Do not use these definitions. + * They are exposed to allow static allocation of `LZ4_streamHC_t`. + * Using these definitions makes the code vulnerable to potential API break when upgrading LZ4 + **************************************/ +#define LZ4HC_DICTIONARY_LOGSIZE 16 +#define LZ4HC_MAXD (1<<LZ4HC_DICTIONARY_LOGSIZE) +#define LZ4HC_MAXD_MASK (LZ4HC_MAXD - 1) + +#define LZ4HC_HASH_LOG (LZ4HC_DICTIONARY_LOGSIZE-1) +#define LZ4HC_HASHTABLESIZE (1 << LZ4HC_HASH_LOG) +#define LZ4HC_HASH_MASK (LZ4HC_HASHTABLESIZE - 1) + + +#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) +#include <stdint.h> + +typedef struct +{ + uint32_t hashTable[LZ4HC_HASHTABLESIZE]; + uint16_t chainTable[LZ4HC_MAXD]; + const uint8_t* end; /* next block here to continue on current prefix */ + const uint8_t* base; /* All index relative to this position */ + const uint8_t* dictBase; /* alternate base for extDict */ + uint8_t* inputBuffer; /* deprecated */ + uint32_t dictLimit; /* below that point, need extDict */ + uint32_t lowLimit; /* below that point, no more dict */ + uint32_t nextToUpdate; /* index from which to continue dictionary update */ + uint32_t compressionLevel; +} LZ4HC_CCtx_internal; + +#else + +typedef struct +{ + unsigned int hashTable[LZ4HC_HASHTABLESIZE]; + unsigned short chainTable[LZ4HC_MAXD]; + const unsigned char* end; /* next block here to continue on current prefix */ + const unsigned char* base; /* All index relative to this position */ + const unsigned char* dictBase; /* alternate base for extDict */ + unsigned char* inputBuffer; /* deprecated */ + unsigned int dictLimit; /* below that point, need extDict */ + unsigned int lowLimit; /* below that point, no more dict */ + unsigned int nextToUpdate; /* index from which to continue dictionary update */ + unsigned int compressionLevel; +} LZ4HC_CCtx_internal; -/************************************** +#endif + +#define LZ4_STREAMHCSIZE 262192 +#define LZ4_STREAMHCSIZE_SIZET (LZ4_STREAMHCSIZE / sizeof(size_t)) +union LZ4_streamHC_u { + size_t table[LZ4_STREAMHCSIZE_SIZET]; + LZ4HC_CCtx_internal internal_donotuse; +}; /* previously typedef'd to LZ4_streamHC_t */ +/* + LZ4_streamHC_t : + This structure allows static allocation of LZ4 HC streaming state. + State must be initialized using LZ4_resetStreamHC() before first use. + + Static allocation shall only be used in combination with static linking. + When invoking LZ4 from a DLL, use create/free functions instead, which are API and ABI stable. +*/ + + +/*-************************************ * Deprecated Functions **************************************/ -/* Deprecate Warnings */ -/* Should these warnings messages be a problem, - it is generally possible to disable them, - with -Wno-deprecated-declarations for gcc - or _CRT_SECURE_NO_WARNINGS in Visual for example. - You can also define LZ4_DEPRECATE_WARNING_DEFBLOCK. */ -#ifndef LZ4_DEPRECATE_WARNING_DEFBLOCK -# define LZ4_DEPRECATE_WARNING_DEFBLOCK -# define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) -# if (LZ4_GCC_VERSION >= 405) || defined(__clang__) -# define LZ4_DEPRECATED(message) __attribute__((deprecated(message))) -# elif (LZ4_GCC_VERSION >= 301) -# define LZ4_DEPRECATED(message) __attribute__((deprecated)) -# elif defined(_MSC_VER) -# define LZ4_DEPRECATED(message) __declspec(deprecated(message)) -# else -# pragma message("WARNING: You need to implement LZ4_DEPRECATED for this compiler") -# define LZ4_DEPRECATED(message) -# endif -#endif // LZ4_DEPRECATE_WARNING_DEFBLOCK - -/* compression functions */ -/* these functions are planned to trigger warning messages by r131 approximately */ -int LZ4_compressHC (const char* source, char* dest, int inputSize); -int LZ4_compressHC_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize); -int LZ4_compressHC2 (const char* source, char* dest, int inputSize, int compressionLevel); -int LZ4_compressHC2_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); -int LZ4_compressHC_withStateHC (void* state, const char* source, char* dest, int inputSize); -int LZ4_compressHC_limitedOutput_withStateHC (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); -int LZ4_compressHC2_withStateHC (void* state, const char* source, char* dest, int inputSize, int compressionLevel); -int LZ4_compressHC2_limitedOutput_withStateHC(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); -int LZ4_compressHC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize); -int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize); - -/* Streaming functions following the older model; should no longer be used */ +/* see lz4.h LZ4_DISABLE_DEPRECATE_WARNINGS to turn off deprecation warnings */ + +/* deprecated compression functions */ +/* these functions will trigger warning messages in future releases */ +LZ4_DEPRECATED("use LZ4_compress_HC() instead") int LZ4_compressHC (const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_HC() instead") int LZ4_compressHC_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_HC() instead") int LZ4_compressHC2 (const char* source, char* dest, int inputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_compress_HC() instead") int LZ4_compressHC2_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") int LZ4_compressHC_withStateHC (void* state, const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") int LZ4_compressHC_limitedOutput_withStateHC (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") int LZ4_compressHC2_withStateHC (void* state, const char* source, char* dest, int inputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") int LZ4_compressHC2_limitedOutput_withStateHC(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize); + +/* Deprecated Streaming functions using older model; should no longer be used */ LZ4_DEPRECATED("use LZ4_createStreamHC() instead") void* LZ4_createHC (char* inputBuffer); LZ4_DEPRECATED("use LZ4_saveDictHC() instead") char* LZ4_slideInputBufferHC (void* LZ4HC_Data); LZ4_DEPRECATED("use LZ4_freeStreamHC() instead") int LZ4_freeHC (void* LZ4HC_Data); -LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel); -LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); LZ4_DEPRECATED("use LZ4_createStreamHC() instead") int LZ4_sizeofStreamStateHC(void); LZ4_DEPRECATED("use LZ4_resetStreamHC() instead") int LZ4_resetStreamStateHC(void* state, char* inputBuffer); @@ -187,3 +221,5 @@ LZ4_DEPRECATED("use LZ4_resetStreamHC() instead") int LZ4_resetStreamStateHC( #if defined (__cplusplus) } #endif + +#endif /* LZ4_HC_H_19834876238432 */