diff --git a/uppsrc/plugin/lz4/lz4.c b/uppsrc/plugin/lz4/lz4.c deleted file mode 100644 index cecfa528b..000000000 --- a/uppsrc/plugin/lz4/lz4.c +++ /dev/null @@ -1,2239 +0,0 @@ -/* - LZ4 - Fast LZ compression algorithm - Copyright (C) 2011-present, Yann Collet. - - BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) - - Redistribution and use in source and binary forms, with or without - modification, are permitted provided that the following conditions are - met: - - * Redistributions of source code must retain the above copyright - notice, this list of conditions and the following disclaimer. - * Redistributions in binary form must reproduce the above - copyright notice, this list of conditions and the following disclaimer - in the documentation and/or other materials provided with the - distribution. - - THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - - You can contact the author at : - - LZ4 homepage : http://www.lz4.org - - LZ4 source repository : https://github.com/lz4/lz4 -*/ - -/* - * LZ4_SRC_INCLUDED: - * Amalgamation flag, whether lz4.c is included - */ -#ifndef LZ4_SRC_INCLUDED -# define LZ4_SRC_INCLUDED 1 -#endif - -/*-************************************ -* Tuning parameters -**************************************/ -/* - * LZ4_HEAPMODE : - * Select how default compression functions will allocate memory for their hash table, - * in memory stack (0:default, fastest), or in memory heap (1:requires malloc()). - */ -#ifndef LZ4_HEAPMODE -# define LZ4_HEAPMODE 0 -#endif - -/* - * ACCELERATION_DEFAULT : - * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0 - */ -#define ACCELERATION_DEFAULT 1 - - -/*-************************************ -* CPU Feature Detection -**************************************/ -/* LZ4_FORCE_MEMORY_ACCESS - * By default, access to unaligned memory is controlled by `memcpy()`, which is safe and portable. - * Unfortunately, on some target/compiler combinations, the generated assembly is sub-optimal. - * The below switch allow to select different access method for improved performance. - * Method 0 (default) : use `memcpy()`. Safe and portable. - * Method 1 : `__packed` statement. It depends on compiler extension (ie, not portable). - * This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`. - * Method 2 : direct access. This method is portable but violate C standard. - * It can generate buggy code on targets which assembly generation depends on alignment. - * But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6) - * See https://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details. - * Prefer these methods in priority order (0 > 1 > 2) - */ -#ifndef LZ4_FORCE_MEMORY_ACCESS /* can be defined externally */ -# if defined(__GNUC__) && \ - ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) \ - || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) ) -# define LZ4_FORCE_MEMORY_ACCESS 2 -# elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__) -# define LZ4_FORCE_MEMORY_ACCESS 1 -# endif -#endif - -/* - * LZ4_FORCE_SW_BITCOUNT - * Define this parameter if your target system or compiler does not support hardware bit count - */ -#if defined(_MSC_VER) && defined(_WIN32_WCE) /* Visual Studio for WinCE doesn't support Hardware bit count */ -# define LZ4_FORCE_SW_BITCOUNT -#endif - - - -/*-************************************ -* Dependency -**************************************/ -#define LZ4_STATIC_LINKING_ONLY -#define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */ -#include "lz4.h" -/* see also "memory routines" below */ - - -/*-************************************ -* Compiler Options -**************************************/ -#ifdef _MSC_VER /* Visual Studio */ -# include -# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ -# pragma warning(disable : 4293) /* disable: C4293: too large shift (32-bits) */ -#endif /* _MSC_VER */ - -#ifndef LZ4_FORCE_INLINE -# ifdef _MSC_VER /* Visual Studio */ -# define LZ4_FORCE_INLINE static __forceinline -# else -# if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */ -# ifdef __GNUC__ -# define LZ4_FORCE_INLINE static inline __attribute__((always_inline)) -# else -# define LZ4_FORCE_INLINE static inline -# endif -# else -# define LZ4_FORCE_INLINE static -# endif /* __STDC_VERSION__ */ -# endif /* _MSC_VER */ -#endif /* LZ4_FORCE_INLINE */ - -/* LZ4_FORCE_O2_GCC_PPC64LE and LZ4_FORCE_O2_INLINE_GCC_PPC64LE - * Gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy, - * together with a simple 8-byte copy loop as a fall-back path. - * However, this optimization hurts the decompression speed by >30%, - * because the execution does not go to the optimized loop - * for typical compressible data, and all of the preamble checks - * before going to the fall-back path become useless overhead. - * This optimization happens only with the -O3 flag, and -O2 generates - * a simple 8-byte copy loop. - * With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy - * functions are annotated with __attribute__((optimize("O2"))), - * and also LZ4_wildCopy is forcibly inlined, so that the O2 attribute - * of LZ4_wildCopy does not affect the compression speed. - */ -#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__) && !defined(__clang__) -# define LZ4_FORCE_O2_GCC_PPC64LE __attribute__((optimize("O2"))) -# define LZ4_FORCE_O2_INLINE_GCC_PPC64LE __attribute__((optimize("O2"))) LZ4_FORCE_INLINE -#else -# define LZ4_FORCE_O2_GCC_PPC64LE -# define LZ4_FORCE_O2_INLINE_GCC_PPC64LE static -#endif - -#if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__) -# define expect(expr,value) (__builtin_expect ((expr),(value)) ) -#else -# define expect(expr,value) (expr) -#endif - -#ifndef likely -#define likely(expr) expect((expr) != 0, 1) -#endif -#ifndef unlikely -#define unlikely(expr) expect((expr) != 0, 0) -#endif - - -/*-************************************ -* Memory routines -**************************************/ -#include /* malloc, calloc, free */ -#define ALLOC(s) malloc(s) -#define ALLOC_AND_ZERO(s) calloc(1,s) -#define FREEMEM(p) free(p) -#include /* memset, memcpy */ -#define MEM_INIT(p,v,s) memset((p),(v),(s)) - - -/*-************************************ -* Basic Types -**************************************/ -#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) -# include - typedef uint8_t BYTE; - typedef uint16_t U16; - typedef uint32_t U32; - typedef int32_t S32; - typedef uint64_t U64; - typedef uintptr_t uptrval; -#else - typedef unsigned char BYTE; - typedef unsigned short U16; - typedef unsigned int U32; - typedef signed int S32; - typedef unsigned long long U64; - typedef size_t uptrval; /* generally true, except OpenVMS-64 */ -#endif - -#if defined(__x86_64__) - typedef U64 reg_t; /* 64-bits in x32 mode */ -#else - typedef size_t reg_t; /* 32-bits in x32 mode */ -#endif - -/*-************************************ -* Reading and writing into memory -**************************************/ -static unsigned LZ4_isLittleEndian(void) -{ - const union { U32 u; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */ - return one.c[0]; -} - - -#if defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==2) -/* lie to the compiler about data alignment; use with caution */ - -static U16 LZ4_read16(const void* memPtr) { return *(const U16*) memPtr; } -static U32 LZ4_read32(const void* memPtr) { return *(const U32*) memPtr; } -static reg_t LZ4_read_ARCH(const void* memPtr) { return *(const reg_t*) memPtr; } - -static void LZ4_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; } -static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; } - -#elif defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==1) - -/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */ -/* currently only defined for gcc and icc */ -typedef union { U16 u16; U32 u32; reg_t uArch; } __attribute__((packed)) unalign; - -static U16 LZ4_read16(const void* ptr) { return ((const unalign*)ptr)->u16; } -static U32 LZ4_read32(const void* ptr) { return ((const unalign*)ptr)->u32; } -static reg_t LZ4_read_ARCH(const void* ptr) { return ((const unalign*)ptr)->uArch; } - -static void LZ4_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; } -static void LZ4_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; } - -#else /* safe and portable access through memcpy() */ - -static U16 LZ4_read16(const void* memPtr) -{ - U16 val; memcpy(&val, memPtr, sizeof(val)); return val; -} - -static U32 LZ4_read32(const void* memPtr) -{ - U32 val; memcpy(&val, memPtr, sizeof(val)); return val; -} - -static reg_t LZ4_read_ARCH(const void* memPtr) -{ - reg_t val; memcpy(&val, memPtr, sizeof(val)); return val; -} - -static void LZ4_write16(void* memPtr, U16 value) -{ - memcpy(memPtr, &value, sizeof(value)); -} - -static void LZ4_write32(void* memPtr, U32 value) -{ - memcpy(memPtr, &value, sizeof(value)); -} - -#endif /* LZ4_FORCE_MEMORY_ACCESS */ - - -static U16 LZ4_readLE16(const void* memPtr) -{ - if (LZ4_isLittleEndian()) { - return LZ4_read16(memPtr); - } else { - const BYTE* p = (const BYTE*)memPtr; - return (U16)((U16)p[0] + (p[1]<<8)); - } -} - -static void LZ4_writeLE16(void* memPtr, U16 value) -{ - if (LZ4_isLittleEndian()) { - LZ4_write16(memPtr, value); - } else { - BYTE* p = (BYTE*)memPtr; - p[0] = (BYTE) value; - p[1] = (BYTE)(value>>8); - } -} - -/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */ -LZ4_FORCE_O2_INLINE_GCC_PPC64LE -void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd) -{ - BYTE* d = (BYTE*)dstPtr; - const BYTE* s = (const BYTE*)srcPtr; - BYTE* const e = (BYTE*)dstEnd; - - do { memcpy(d,s,8); d+=8; s+=8; } while (d=1) -# include -#else -# ifndef assert -# define assert(condition) ((void)0) -# endif -#endif - -#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(int)(!!(c)) }; } /* use after variable declarations */ - -#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2) -# include -static int g_debuglog_enable = 1; -# define DEBUGLOG(l, ...) { \ - if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) { \ - fprintf(stderr, __FILE__ ": "); \ - fprintf(stderr, __VA_ARGS__); \ - fprintf(stderr, " \n"); \ - } } -#else -# define DEBUGLOG(l, ...) {} /* disabled */ -#endif - - -/*-************************************ -* Common functions -**************************************/ -static unsigned LZ4_NbCommonBytes (reg_t val) -{ - if (LZ4_isLittleEndian()) { - if (sizeof(val)==8) { -# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r = 0; - _BitScanForward64( &r, (U64)val ); - return (int)(r>>3); -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_ctzll((U64)val) >> 3); -# else - static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, - 0, 3, 1, 3, 1, 4, 2, 7, - 0, 2, 3, 6, 1, 5, 3, 5, - 1, 3, 4, 4, 2, 5, 6, 7, - 7, 0, 1, 2, 3, 3, 4, 6, - 2, 6, 5, 5, 3, 4, 5, 6, - 7, 1, 2, 4, 6, 4, 4, 5, - 7, 2, 6, 5, 7, 6, 7, 7 }; - return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58]; -# endif - } else /* 32 bits */ { -# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r; - _BitScanForward( &r, (U32)val ); - return (int)(r>>3); -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_ctz((U32)val) >> 3); -# else - static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, - 3, 2, 2, 1, 3, 2, 0, 1, - 3, 3, 1, 2, 2, 2, 2, 0, - 3, 1, 2, 0, 1, 0, 1, 1 }; - return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27]; -# endif - } - } else /* Big Endian CPU */ { - if (sizeof(val)==8) { /* 64-bits */ -# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r = 0; - _BitScanReverse64( &r, val ); - return (unsigned)(r>>3); -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_clzll((U64)val) >> 3); -# else - static const U32 by32 = sizeof(val)*4; /* 32 on 64 bits (goal), 16 on 32 bits. - Just to avoid some static analyzer complaining about shift by 32 on 32-bits target. - Note that this code path is never triggered in 32-bits mode. */ - unsigned r; - if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; } - if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } - r += (!val); - return r; -# endif - } else /* 32 bits */ { -# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r = 0; - _BitScanReverse( &r, (unsigned long)val ); - return (unsigned)(r>>3); -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_clz((U32)val) >> 3); -# else - unsigned r; - if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } - r += (!val); - return r; -# endif - } - } -} - -#define STEPSIZE sizeof(reg_t) -LZ4_FORCE_INLINE -unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit) -{ - const BYTE* const pStart = pIn; - - if (likely(pIn < pInLimit-(STEPSIZE-1))) { - reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn); - if (!diff) { - pIn+=STEPSIZE; pMatch+=STEPSIZE; - } else { - return LZ4_NbCommonBytes(diff); - } } - - 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 ((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 compression run slower on incompressible data */ - - -/*-************************************ -* Local Structures and types -**************************************/ -typedef enum { - noLimit = 0, - notLimited = 1, - limitedOutput = 2, - fillOutput = 3, - limitedDestSize = 4 -} limitedOutput_directive; -typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t; - -/** - * This enum distinguishes several different modes of accessing previous - * content in the stream. - * - * - noDict : There is no preceding content. - * - withPrefix64k : Table entries up to ctx->dictSize before the current blob - * blob being compressed are valid and refer to the preceding - * content (of length ctx->dictSize), which is available - * contiguously preceding in memory the content currently - * being compressed. - * - usingExtDict : Like withPrefix64k, but the preceding content is somewhere - * else in memory, starting at ctx->dictionary with length - * ctx->dictSize. - * - usingDictCtx : Like usingExtDict, but everything concerning the preceding - * content is in a separate context, pointed to by - * ctx->dictCtx. ctx->dictionary, ctx->dictSize, and table - * entries in the current context that refer to positions - * preceding the beginning of the current compression are - * ignored. Instead, ctx->dictCtx->dictionary and ctx->dictCtx - * ->dictSize describe the location and size of the preceding - * content, and matches are found by looking in the ctx - * ->dictCtx->hashTable. - */ -typedef enum { noDict = 0, withPrefix64k, usingExtDict, usingDictCtx } dict_directive; -typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive; - - -/*-************************************ -* Local Utils -**************************************/ -int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; } -const char* LZ4_versionString(void) { return LZ4_VERSION_STRING; } -int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } -int LZ4_sizeofState() { return LZ4_STREAMSIZE; } - - -/*-************************************ -* Internal Definitions used in Tests -**************************************/ -#if defined (__cplusplus) -extern "C" { -#endif - -int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize); - -int LZ4_decompress_safe_forceExtDict(const char* in, char* out, int inSize, int outSize, const void* dict, size_t dictSize); - -#if defined (__cplusplus) -} -#endif - -/*-****************************** -* Compression functions -********************************/ -static U32 LZ4_hash4(U32 sequence, tableType_t const tableType) -{ - if (tableType == byU16) - return ((sequence * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1))); - else - return ((sequence * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG)); -} - -static U32 LZ4_hash5(U64 sequence, tableType_t const tableType) -{ - const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG; - if (LZ4_isLittleEndian()) { - const U64 prime5bytes = 889523592379ULL; - return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog)); - } else { - const U64 prime8bytes = 11400714785074694791ULL; - return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog)); - } -} - -LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType) -{ - if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType); - return LZ4_hash4(LZ4_read32(p), tableType); -} - -static void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType) -{ - switch (tableType) - { - default: /* fallthrough */ - case clearedTable: /* fallthrough */ - case byPtr: { /* illegal! */ assert(0); return; } - case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; } - case byU16: { U16* hashTable = (U16*) tableBase; assert(idx < 65536); hashTable[h] = (U16)idx; return; } - } -} - -static void LZ4_putPositionOnHash(const BYTE* p, U32 h, - void* tableBase, tableType_t const tableType, - const BYTE* srcBase) -{ - switch (tableType) - { - case clearedTable: { /* illegal! */ assert(0); return; } - case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = p; return; } - case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); return; } - case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); return; } - } -} - -LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) -{ - U32 const h = LZ4_hashPosition(p, tableType); - LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase); -} - -/* LZ4_getIndexOnHash() : - * Index of match position registered in hash table. - * hash position must be calculated by using base+index, or dictBase+index. - * Assumption 1 : only valid if tableType == byU32 or byU16. - * Assumption 2 : h is presumed valid (within limits of hash table) - */ -static U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType) -{ - LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2); - if (tableType == byU32) { - const U32* const hashTable = (const U32*) tableBase; - assert(h < (1U << (LZ4_MEMORY_USAGE-2))); - return hashTable[h]; - } - if (tableType == byU16) { - const U16* const hashTable = (const U16*) tableBase; - assert(h < (1U << (LZ4_MEMORY_USAGE-1))); - return hashTable[h]; - } - assert(0); return 0; /* forbidden case */ -} - -static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType_t tableType, const BYTE* srcBase) -{ - if (tableType == byPtr) { const BYTE* const* hashTable = (const BYTE* const*) tableBase; return hashTable[h]; } - if (tableType == byU32) { const U32* const hashTable = (const U32*) tableBase; return hashTable[h] + srcBase; } - { const U16* const hashTable = (const U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */ -} - -LZ4_FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, - const void* tableBase, tableType_t tableType, - const BYTE* srcBase) -{ - U32 const h = LZ4_hashPosition(p, tableType); - return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase); -} - -LZ4_FORCE_INLINE void LZ4_prepareTable( - LZ4_stream_t_internal* const cctx, - const int inputSize, - const tableType_t tableType) { - /* If compression failed during the previous step, then the context - * is marked as dirty, therefore, it has to be fully reset. - */ - if (cctx->dirty) { - DEBUGLOG(5, "LZ4_prepareTable: Full reset for %p", cctx); - MEM_INIT(cctx, 0, sizeof(LZ4_stream_t_internal)); - return; - } - - /* If the table hasn't been used, it's guaranteed to be zeroed out, and is - * therefore safe to use no matter what mode we're in. Otherwise, we figure - * out if it's safe to leave as is or whether it needs to be reset. - */ - if (cctx->tableType != clearedTable) { - if (cctx->tableType != tableType - || (tableType == byU16 && cctx->currentOffset + inputSize >= 0xFFFFU) - || (tableType == byU32 && cctx->currentOffset > 1 GB) - || tableType == byPtr - || inputSize >= 4 KB) - { - DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", cctx); - MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE); - cctx->currentOffset = 0; - cctx->tableType = clearedTable; - } else { - DEBUGLOG(4, "LZ4_prepareTable: Re-use hash table (no reset)"); - } - } - - /* Adding a gap, so all previous entries are > MAX_DISTANCE back, is faster - * than compressing without a gap. However, compressing with - * currentOffset == 0 is faster still, so we preserve that case. - */ - if (cctx->currentOffset != 0 && tableType == byU32) { - DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset"); - cctx->currentOffset += 64 KB; - } - - /* Finally, clear history */ - cctx->dictCtx = NULL; - cctx->dictionary = NULL; - cctx->dictSize = 0; -} - -/** LZ4_compress_generic() : - inlined, to ensure branches are decided at compilation time */ -LZ4_FORCE_INLINE int LZ4_compress_generic( - LZ4_stream_t_internal* const cctx, - const char* const source, - char* const dest, - const int inputSize, - int *inputConsumed, /* only written when outputLimited == fillOutput */ - const int maxOutputSize, - const limitedOutput_directive outputLimited, - const tableType_t tableType, - const dict_directive dictDirective, - const dictIssue_directive dictIssue, - const U32 acceleration) -{ - int result; - const BYTE* ip = (const BYTE*) source; - - U32 const startIndex = cctx->currentOffset; - const BYTE* base = (const BYTE*) source - startIndex; - const BYTE* lowLimit; - - const LZ4_stream_t_internal* dictCtx = (const LZ4_stream_t_internal*) cctx->dictCtx; - const BYTE* const dictionary = - dictDirective == usingDictCtx ? dictCtx->dictionary : cctx->dictionary; - const U32 dictSize = - dictDirective == usingDictCtx ? dictCtx->dictSize : cctx->dictSize; - const U32 dictDelta = (dictDirective == usingDictCtx) ? startIndex - dictCtx->currentOffset : 0; /* make indexes in dictCtx comparable with index in current context */ - - int const maybe_extMem = (dictDirective == usingExtDict) || (dictDirective == usingDictCtx); - U32 const prefixIdxLimit = startIndex - dictSize; /* used when dictDirective == dictSmall */ - const BYTE* const dictEnd = dictionary + dictSize; - const BYTE* anchor = (const BYTE*) source; - const BYTE* const iend = ip + inputSize; - const BYTE* const mflimitPlusOne = iend - MFLIMIT + 1; - const BYTE* const matchlimit = iend - LASTLITERALS; - - /* the dictCtx currentOffset is indexed on the start of the dictionary, - * while a dictionary in the current context precedes the currentOffset */ - const BYTE* dictBase = (dictDirective == usingDictCtx) ? - dictionary + dictSize - dictCtx->currentOffset : - dictionary + dictSize - startIndex; - - BYTE* op = (BYTE*) dest; - BYTE* const olimit = op + maxOutputSize; - - U32 offset = 0; - U32 forwardH; - - DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, tableType=%u", inputSize, tableType); - /* If init conditions are not met, we don't have to mark stream - * as having dirty context, since no action was taken yet */ - if (outputLimited == fillOutput && maxOutputSize < 1) return 0; /* Impossible to store anything */ - if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported inputSize, too large (or negative) */ - if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */ - if (tableType==byPtr) assert(dictDirective==noDict); /* only supported use case with byPtr */ - assert(acceleration >= 1); - - lowLimit = (const BYTE*)source - (dictDirective == withPrefix64k ? dictSize : 0); - - /* Update context state */ - if (dictDirective == usingDictCtx) { - /* Subsequent linked blocks can't use the dictionary. */ - /* Instead, they use the block we just compressed. */ - cctx->dictCtx = NULL; - cctx->dictSize = (U32)inputSize; - } else { - cctx->dictSize += (U32)inputSize; - } - cctx->currentOffset += (U32)inputSize; - cctx->tableType = (U16)tableType; - - if (inputSizehashTable, tableType, base); - ip++; forwardH = LZ4_hashPosition(ip, tableType); - - /* Main Loop */ - for ( ; ; ) { - const BYTE* match; - BYTE* token; - - /* Find a match */ - if (tableType == byPtr) { - const BYTE* forwardIp = ip; - unsigned step = 1; - unsigned searchMatchNb = acceleration << LZ4_skipTrigger; - do { - U32 const h = forwardH; - ip = forwardIp; - forwardIp += step; - step = (searchMatchNb++ >> LZ4_skipTrigger); - - if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals; - assert(ip < mflimitPlusOne); - - match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base); - forwardH = LZ4_hashPosition(forwardIp, tableType); - LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base); - - } while ( (match+MAX_DISTANCE < ip) - || (LZ4_read32(match) != LZ4_read32(ip)) ); - - } else { /* byU32, byU16 */ - - const BYTE* forwardIp = ip; - unsigned step = 1; - unsigned searchMatchNb = acceleration << LZ4_skipTrigger; - do { - U32 const h = forwardH; - U32 const current = (U32)(forwardIp - base); - U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType); - assert(matchIndex <= current); - assert(forwardIp - base < (ptrdiff_t)(2 GB - 1)); - ip = forwardIp; - forwardIp += step; - step = (searchMatchNb++ >> LZ4_skipTrigger); - - if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals; - assert(ip < mflimitPlusOne); - - if (dictDirective == usingDictCtx) { - if (matchIndex < startIndex) { - /* there was no match, try the dictionary */ - assert(tableType == byU32); - matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32); - match = dictBase + matchIndex; - matchIndex += dictDelta; /* make dictCtx index comparable with current context */ - lowLimit = dictionary; - } else { - match = base + matchIndex; - lowLimit = (const BYTE*)source; - } - } else if (dictDirective==usingExtDict) { - if (matchIndex < startIndex) { - DEBUGLOG(7, "extDict candidate: matchIndex=%5u < startIndex=%5u", matchIndex, startIndex); - assert(startIndex - matchIndex >= MINMATCH); - match = dictBase + matchIndex; - lowLimit = dictionary; - } else { - match = base + matchIndex; - lowLimit = (const BYTE*)source; - } - } else { /* single continuous memory segment */ - match = base + matchIndex; - } - forwardH = LZ4_hashPosition(forwardIp, tableType); - LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType); - - if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) continue; /* match outside of valid area */ - assert(matchIndex < current); - if ((tableType != byU16) && (matchIndex+MAX_DISTANCE < current)) continue; /* too far */ - if (tableType == byU16) assert((current - matchIndex) <= MAX_DISTANCE); /* too_far presumed impossible with byU16 */ - - if (LZ4_read32(match) == LZ4_read32(ip)) { - if (maybe_extMem) offset = current - matchIndex; - break; /* match found */ - } - - } while(1); - } - - /* Catch up */ - while (((ip>anchor) & (match > lowLimit)) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; } - - /* Encode Literals */ - { unsigned const litLength = (unsigned)(ip - anchor); - token = op++; - if ((outputLimited == limitedOutput) && /* Check output buffer overflow */ - (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit))) - goto _failure; - - if ((outputLimited == fillOutput) && - (unlikely(op + (litLength+240)/255 /* litlen */ + litLength /* literals */ + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit))) { - op--; - goto _last_literals; - } - if (litLength >= RUN_MASK) { - int len = (int)litLength-RUN_MASK; - *token = (RUN_MASK<= 255 ; len-=255) *op++ = 255; - *op++ = (BYTE)len; - } - else *token = (BYTE)(litLength< olimit)) { - /* the match was too close to the end, rewind and go to last literals */ - op = token; - goto _last_literals; - } - - /* Encode Offset */ - if (maybe_extMem) { /* static test */ - DEBUGLOG(6, " with offset=%u (ext if > %i)", offset, (int)(ip - (const BYTE*)source)); - assert(offset <= MAX_DISTANCE && offset > 0); - LZ4_writeLE16(op, (U16)offset); op+=2; - } else { - DEBUGLOG(6, " with offset=%u (same segment)", (U32)(ip - match)); - assert(ip-match <= MAX_DISTANCE); - LZ4_writeLE16(op, (U16)(ip - match)); op+=2; - } - - /* Encode MatchLength */ - { unsigned matchCode; - - if ( (dictDirective==usingExtDict || dictDirective==usingDictCtx) - && (lowLimit==dictionary) /* match within extDict */ ) { - const BYTE* limit = ip + (dictEnd-match); - assert(dictEnd > match); - if (limit > matchlimit) limit = matchlimit; - matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit); - ip += MINMATCH + matchCode; - if (ip==limit) { - unsigned const more = LZ4_count(limit, (const BYTE*)source, matchlimit); - matchCode += more; - ip += more; - } - DEBUGLOG(6, " with matchLength=%u starting in extDict", matchCode+MINMATCH); - } else { - matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit); - ip += MINMATCH + matchCode; - DEBUGLOG(6, " with matchLength=%u", matchCode+MINMATCH); - } - - if ((outputLimited) && /* Check output buffer overflow */ - (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) ) { - if (outputLimited == limitedOutput) - goto _failure; - if (outputLimited == fillOutput) { - /* Match description too long : reduce it */ - U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 2 - 1 - LASTLITERALS) * 255; - ip -= matchCode - newMatchCode; - matchCode = newMatchCode; - } - } - if (matchCode >= ML_MASK) { - *token += ML_MASK; - 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; - - /* Test end of chunk */ - if (ip >= mflimitPlusOne) break; - - /* Fill table */ - LZ4_putPosition(ip-2, cctx->hashTable, tableType, base); - - /* Test next position */ - if (tableType == byPtr) { - - match = LZ4_getPosition(ip, cctx->hashTable, tableType, base); - LZ4_putPosition(ip, cctx->hashTable, tableType, base); - if ( (match+MAX_DISTANCE >= ip) - && (LZ4_read32(match) == LZ4_read32(ip)) ) - { token=op++; *token=0; goto _next_match; } - - } else { /* byU32, byU16 */ - - U32 const h = LZ4_hashPosition(ip, tableType); - U32 const current = (U32)(ip-base); - U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType); - assert(matchIndex < current); - if (dictDirective == usingDictCtx) { - if (matchIndex < startIndex) { - /* there was no match, try the dictionary */ - matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32); - match = dictBase + matchIndex; - lowLimit = dictionary; /* required for match length counter */ - matchIndex += dictDelta; - } else { - match = base + matchIndex; - lowLimit = (const BYTE*)source; /* required for match length counter */ - } - } else if (dictDirective==usingExtDict) { - if (matchIndex < startIndex) { - match = dictBase + matchIndex; - lowLimit = dictionary; /* required for match length counter */ - } else { - match = base + matchIndex; - lowLimit = (const BYTE*)source; /* required for match length counter */ - } - } else { /* single memory segment */ - match = base + matchIndex; - } - LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType); - assert(matchIndex < current); - if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1) - && ((tableType==byU16) ? 1 : (matchIndex+MAX_DISTANCE >= current)) - && (LZ4_read32(match) == LZ4_read32(ip)) ) { - token=op++; - *token=0; - if (maybe_extMem) offset = current - matchIndex; - DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i", - (int)(anchor-(const BYTE*)source), 0, (int)(ip-(const BYTE*)source)); - goto _next_match; - } - } - - /* Prepare next loop */ - forwardH = LZ4_hashPosition(++ip, tableType); - - } - -_last_literals: - /* Encode Last Literals */ - { size_t lastRun = (size_t)(iend - anchor); - if ( (outputLimited) && /* Check output buffer overflow */ - (op + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > olimit)) { - if (outputLimited == fillOutput) { - /* adapt lastRun to fill 'dst' */ - lastRun = (olimit-op) - 1; - lastRun -= (lastRun+240)/255; - } - if (outputLimited == limitedOutput) - goto _failure; - } - if (lastRun >= RUN_MASK) { - size_t accumulator = lastRun - RUN_MASK; - *op++ = RUN_MASK << ML_BITS; - for(; accumulator >= 255 ; accumulator-=255) *op++ = 255; - *op++ = (BYTE) accumulator; - } else { - *op++ = (BYTE)(lastRun< 0); - return result; - -_failure: - /* Mark stream as having dirty context, so, it has to be fully reset */ - cctx->dirty = 1; - return 0; -} - - -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; - if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; - LZ4_resetStream((LZ4_stream_t*)state); - if (maxOutputSize >= LZ4_compressBound(inputSize)) { - if (inputSize < LZ4_64Klimit) { - return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, byU16, noDict, noDictIssue, acceleration); - } else { - const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > MAX_DISTANCE)) ? byPtr : byU32; - return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); - } - } else { - if (inputSize < LZ4_64Klimit) {; - return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); - } else { - const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > MAX_DISTANCE)) ? byPtr : byU32; - return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration); - } - } -} - -/** - * LZ4_compress_fast_extState_fastReset() : - * A variant of LZ4_compress_fast_extState(). - * - * Using this variant avoids an expensive initialization step. It is only safe - * to call if the state buffer is known to be correctly initialized already - * (see comment in lz4.h on LZ4_resetStream_fast() for a definition of - * "correctly initialized"). - */ -int LZ4_compress_fast_extState_fastReset(void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration) -{ - LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse; - if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; - - if (dstCapacity >= LZ4_compressBound(srcSize)) { - if (srcSize < LZ4_64Klimit) { - const tableType_t tableType = byU16; - LZ4_prepareTable(ctx, srcSize, tableType); - if (ctx->currentOffset) { - return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, dictSmall, acceleration); - } else { - return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); - } - } else { - const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32; - LZ4_prepareTable(ctx, srcSize, tableType); - return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); - } - } else { - if (srcSize < LZ4_64Klimit) { - const tableType_t tableType = byU16; - LZ4_prepareTable(ctx, srcSize, tableType); - if (ctx->currentOffset) { - return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, dictSmall, acceleration); - } else { - return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration); - } - } else { - const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32; - LZ4_prepareTable(ctx, srcSize, tableType); - return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration); - } - } -} - - -int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) -{ - int result; -#if (LZ4_HEAPMODE) - LZ4_stream_t* ctxPtr = ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ - if (ctxPtr == NULL) return 0; -#else - LZ4_stream_t ctx; - LZ4_stream_t* const ctxPtr = &ctx; -#endif - result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration); - -#if (LZ4_HEAPMODE) - FREEMEM(ctxPtr); -#endif - return result; -} - - -int LZ4_compress_default(const char* src, char* dst, int srcSize, int maxOutputSize) -{ - return LZ4_compress_fast(src, dst, srcSize, maxOutputSize, 1); -} - - -/* hidden debug function */ -/* strangely enough, gcc generates faster code when this function is uncommented, even if unused */ -int LZ4_compress_fast_force(const char* src, char* dst, int srcSize, int dstCapacity, int acceleration) -{ - LZ4_stream_t ctx; - LZ4_resetStream(&ctx); - - if (srcSize < LZ4_64Klimit) { - return LZ4_compress_generic(&ctx.internal_donotuse, src, dst, srcSize, NULL, dstCapacity, limitedOutput, byU16, noDict, noDictIssue, acceleration); - } else { - tableType_t const addrMode = (sizeof(void*) > 4) ? byU32 : byPtr; - return LZ4_compress_generic(&ctx.internal_donotuse, src, dst, srcSize, NULL, dstCapacity, limitedOutput, addrMode, noDict, noDictIssue, acceleration); - } -} - - -/* Note!: This function leaves the stream in an unclean/broken state! - * It is not safe to subsequently use the same state with a _fastReset() or - * _continue() call without resetting it. */ -static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize) -{ - LZ4_resetStream(state); - - if (targetDstSize >= LZ4_compressBound(*srcSizePtr)) { /* compression success is guaranteed */ - return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1); - } else { - if (*srcSizePtr < LZ4_64Klimit) { - return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, byU16, noDict, noDictIssue, 1); - } else { - tableType_t const addrMode = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32; - return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, addrMode, noDict, noDictIssue, 1); - } } -} - - -int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize) -{ -#if (LZ4_HEAPMODE) - LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ - if (ctx == NULL) return 0; -#else - LZ4_stream_t ctxBody; - LZ4_stream_t* ctx = &ctxBody; -#endif - - int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize); - -#if (LZ4_HEAPMODE) - FREEMEM(ctx); -#endif - return result; -} - - - -/*-****************************** -* Streaming functions -********************************/ - -LZ4_stream_t* LZ4_createStream(void) -{ - LZ4_stream_t* const lz4s = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); - LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal)); /* A compilation error here means LZ4_STREAMSIZE is not large enough */ - DEBUGLOG(4, "LZ4_createStream %p", lz4s); - if (lz4s == NULL) return NULL; - LZ4_resetStream(lz4s); - return lz4s; -} - -void LZ4_resetStream (LZ4_stream_t* LZ4_stream) -{ - DEBUGLOG(5, "LZ4_resetStream (ctx:%p)", LZ4_stream); - MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t)); -} - -void LZ4_resetStream_fast(LZ4_stream_t* ctx) { - LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32); -} - -int LZ4_freeStream (LZ4_stream_t* LZ4_stream) -{ - if (!LZ4_stream) return 0; /* support free on NULL */ - DEBUGLOG(5, "LZ4_freeStream %p", LZ4_stream); - FREEMEM(LZ4_stream); - return (0); -} - - -#define HASH_UNIT sizeof(reg_t) -int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) -{ - LZ4_stream_t_internal* dict = &LZ4_dict->internal_donotuse; - const tableType_t tableType = byU32; - const BYTE* p = (const BYTE*)dictionary; - const BYTE* const dictEnd = p + dictSize; - const BYTE* base; - - DEBUGLOG(4, "LZ4_loadDict (%i bytes from %p into %p)", dictSize, dictionary, LZ4_dict); - - /* It's necessary to reset the context, - * and not just continue it with prepareTable() - * to avoid any risk of generating overflowing matchIndex - * when compressing using this dictionary */ - LZ4_resetStream(LZ4_dict); - - /* We always increment the offset by 64 KB, since, if the dict is longer, - * we truncate it to the last 64k, and if it's shorter, we still want to - * advance by a whole window length so we can provide the guarantee that - * there are only valid offsets in the window, which allows an optimization - * in LZ4_compress_fast_continue() where it uses noDictIssue even when the - * dictionary isn't a full 64k. */ - - if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB; - base = dictEnd - 64 KB - dict->currentOffset; - dict->dictionary = p; - dict->dictSize = (U32)(dictEnd - p); - dict->currentOffset += 64 KB; - dict->tableType = tableType; - - if (dictSize < (int)HASH_UNIT) { - return 0; - } - - while (p <= dictEnd-HASH_UNIT) { - LZ4_putPosition(p, dict->hashTable, tableType, base); - p+=3; - } - - return dict->dictSize; -} - -void LZ4_attach_dictionary(LZ4_stream_t *working_stream, const LZ4_stream_t *dictionary_stream) { - /* Calling LZ4_resetStream_fast() here makes sure that changes will not be - * erased by subsequent calls to LZ4_resetStream_fast() in case stream was - * marked as having dirty context, e.g. requiring full reset. - */ - LZ4_resetStream_fast(working_stream); - - if (dictionary_stream != NULL) { - /* If the current offset is zero, we will never look in the - * external dictionary context, since there is no value a table - * entry can take that indicate a miss. In that case, we need - * to bump the offset to something non-zero. - */ - if (working_stream->internal_donotuse.currentOffset == 0) { - working_stream->internal_donotuse.currentOffset = 64 KB; - } - working_stream->internal_donotuse.dictCtx = &(dictionary_stream->internal_donotuse); - } else { - working_stream->internal_donotuse.dictCtx = NULL; - } -} - - -static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, int nextSize) -{ - if (LZ4_dict->currentOffset + nextSize > 0x80000000) { /* potential ptrdiff_t overflow (32-bits mode) */ - /* rescale hash table */ - U32 const delta = LZ4_dict->currentOffset - 64 KB; - const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize; - int i; - DEBUGLOG(4, "LZ4_renormDictT"); - for (i=0; ihashTable[i] < delta) LZ4_dict->hashTable[i]=0; - else LZ4_dict->hashTable[i] -= delta; - } - LZ4_dict->currentOffset = 64 KB; - if (LZ4_dict->dictSize > 64 KB) LZ4_dict->dictSize = 64 KB; - LZ4_dict->dictionary = dictEnd - LZ4_dict->dictSize; - } -} - - -int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) -{ - const tableType_t tableType = byU32; - LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse; - const BYTE* dictEnd = streamPtr->dictionary + streamPtr->dictSize; - - DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i)", inputSize); - - if (streamPtr->dirty) return 0; /* Uninitialized structure detected */ - LZ4_renormDictT(streamPtr, inputSize); /* avoid index overflow */ - if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; - - /* invalidate tiny dictionaries */ - if ( (streamPtr->dictSize-1 < 4-1) /* intentional underflow */ - && (dictEnd != (const BYTE*)source) ) { - DEBUGLOG(5, "LZ4_compress_fast_continue: dictSize(%u) at addr:%p is too small", streamPtr->dictSize, streamPtr->dictionary); - streamPtr->dictSize = 0; - streamPtr->dictionary = (const BYTE*)source; - dictEnd = (const BYTE*)source; - } - - /* Check overlapping input/dictionary space */ - { 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; - streamPtr->dictionary = dictEnd - streamPtr->dictSize; - } - } - - /* prefix mode : source data follows dictionary */ - if (dictEnd == (const BYTE*)source) { - if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) - return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration); - else - return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, noDictIssue, acceleration); - } - - /* external dictionary mode */ - { int result; - if (streamPtr->dictCtx) { - /* We depend here on the fact that dictCtx'es (produced by - * LZ4_loadDict) guarantee that their tables contain no references - * to offsets between dictCtx->currentOffset - 64 KB and - * dictCtx->currentOffset - dictCtx->dictSize. This makes it safe - * to use noDictIssue even when the dict isn't a full 64 KB. - */ - if (inputSize > 4 KB) { - /* For compressing large blobs, it is faster to pay the setup - * cost to copy the dictionary's tables into the active context, - * so that the compression loop is only looking into one table. - */ - memcpy(streamPtr, streamPtr->dictCtx, sizeof(LZ4_stream_t)); - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration); - } else { - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration); - } - } else { - if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) { - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration); - } else { - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration); - } - } - streamPtr->dictionary = (const BYTE*)source; - streamPtr->dictSize = (U32)inputSize; - return result; - } -} - - -/* Hidden debug function, to force-test external dictionary mode */ -int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize) -{ - LZ4_stream_t_internal* streamPtr = &LZ4_dict->internal_donotuse; - int result; - - LZ4_renormDictT(streamPtr, srcSize); - - if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) { - result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, dictSmall, 1); - } else { - result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, noDictIssue, 1); - } - - streamPtr->dictionary = (const BYTE*)source; - streamPtr->dictSize = (U32)srcSize; - - return result; -} - - -/*! 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* 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; - - memmove(safeBuffer, previousDictEnd - dictSize, dictSize); - - dict->dictionary = (const BYTE*)safeBuffer; - dict->dictSize = (U32)dictSize; - - return dictSize; -} - - - -/*-******************************* - * Decompression functions - ********************************/ - -typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; -typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive; - -#undef MIN -#define MIN(a,b) ( (a) < (b) ? (a) : (b) ) - -/* Read the variable-length literal or match length. - * - * ip - pointer to use as input. - * lencheck - end ip. Return an error if ip advances >= lencheck. - * loop_check - check ip >= lencheck in body of loop. Returns loop_error if so. - * initial_check - check ip >= lencheck before start of loop. Returns initial_error if so. - * error (output) - error code. Should be set to 0 before call. - */ -typedef enum { loop_error = -2, initial_error = -1, ok = 0} variable_length_error; -LZ4_FORCE_INLINE unsigned read_variable_length(const BYTE**ip, const BYTE* lencheck, int loop_check, int initial_check, variable_length_error* error) { - unsigned length = 0; - unsigned s; - if (initial_check && unlikely((*ip) >= lencheck)) { /* overflow detection */ - *error = initial_error; - return length; - } - do { - s = **ip; - (*ip)++; - length += s; - if (loop_check && unlikely((*ip) >= lencheck)) { /* overflow detection */ - *error = loop_error; - return length; - } - } while (s==255); - - return length; -} - -/*! LZ4_decompress_generic() : - * This generic decompression function covers all use cases. - * It shall be instantiated several times, using different sets of directives. - * Note that it is important for performance that this function really get inlined, - * in order to remove useless branches during compilation optimization. - */ -LZ4_FORCE_INLINE int -LZ4_decompress_generic( - const char* const src, - char* const dst, - int srcSize, - int outputSize, /* If endOnInput==endOnInputSize, this value is `dstCapacity` */ - - endCondition_directive endOnInput, /* endOnOutputSize, endOnInputSize */ - earlyEnd_directive partialDecoding, /* full, partial */ - dict_directive dict, /* noDict, withPrefix64k, usingExtDict */ - const BYTE* const lowPrefix, /* always <= dst, == dst when no prefix */ - const BYTE* const dictStart, /* only if dict==usingExtDict */ - const size_t dictSize /* note : = 0 if noDict */ - ) -{ - if (src == NULL) return -1; - - { const BYTE* ip = (const BYTE*) src; - const BYTE* const iend = ip + srcSize; - - BYTE* op = (BYTE*) dst; - BYTE* const oend = op + outputSize; - BYTE* cpy; - - const BYTE* const dictEnd = (dictStart == NULL) ? NULL : dictStart + dictSize; - - const int safeDecode = (endOnInput==endOnInputSize); - const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB))); - - - /* Set up the "end" pointers for the shortcut. */ - const BYTE* const shortiend = iend - (endOnInput ? 14 : 8) /*maxLL*/ - 2 /*offset*/; - const BYTE* const shortoend = oend - (endOnInput ? 14 : 8) /*maxLL*/ - 18 /*maxML*/; - - const BYTE* match; - size_t offset; - unsigned token; - size_t length; - - - DEBUGLOG(5, "LZ4_decompress_generic (srcSize:%i, dstSize:%i)", srcSize, outputSize); - - /* Special cases */ - assert(lowPrefix <= op); - if ((endOnInput) && (unlikely(outputSize==0))) return ((srcSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */ - if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0 ? 1 : -1); - if ((endOnInput) && unlikely(srcSize==0)) return -1; - - /* Currently the fast loop shows a regression on qualcomm arm chips. */ -#if defined(__i386__) || defined(__x86_64__) - if ((oend - op) < FASTLOOP_SAFE_DISTANCE) - goto safe_decode; - - /* Fast loop : decode sequences as long as output < iend-FASTLOOP_SAFE_DISTANCE */ - while (1) { - /* Main fastloop assertion: We can always wildcopy FASTLOOP_SAFE_DISTANCE */ - assert(oend - op >= FASTLOOP_SAFE_DISTANCE); - - token = *ip++; - length = token >> ML_BITS; /* literal length */ - - assert(!endOnInput || ip <= iend); /* ip < iend before the increment */ - - /* decode literal length */ - if (length == RUN_MASK) { - variable_length_error error = ok; - length += read_variable_length(&ip, iend-RUN_MASK, endOnInput, endOnInput, &error); - if (error == initial_error) goto _output_error; - 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; - LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH); - if ( ((endOnInput) && ((cpy>oend-FASTLOOP_SAFE_DISTANCE) || (ip+length>iend-(2+1+LASTLITERALS))) ) - || ((!endOnInput) && (cpy>oend-FASTLOOP_SAFE_DISTANCE)) ) - { - goto safe_literal_copy; - } - LZ4_wildCopy32(op, ip, cpy); - ip += length; op = cpy; - } else { - cpy = op+length; - /* We don't need to check oend, since we check it once for each loop below */ - if ( ((endOnInput) && (ip+16>iend-(2+1+LASTLITERALS)))) - { - goto safe_literal_copy; - } - /* Literals can only be 14, but hope compilers optimize if we copy by a register size */ - memcpy(op, ip, 16); - ip += length; op = cpy; - } - - /* get offset */ - offset = LZ4_readLE16(ip); ip+=2; - match = op - offset; - - /* get matchlength */ - length = token & ML_MASK; - - if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */ - - if (length == ML_MASK) { - variable_length_error error = ok; - length += read_variable_length(&ip, iend - LASTLITERALS + 1, endOnInput, 0, &error); - if (error != ok) goto _output_error; - if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */ - length += MINMATCH; - if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) { - goto safe_match_copy; - } - } else { - length += MINMATCH; - if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) { - goto safe_match_copy; - } - - /* Fastpath check: Avoids a branch in LZ4_wildCopy32 if true */ - if (!(dict == usingExtDict) || (match >= lowPrefix)) { - if (offset >= 8) { - memcpy(op, match, 8); - memcpy(op+8, match+8, 8); - memcpy(op+16, match+16, 2); - op += length; - continue; - } - } - } - - /* match starting within external dictionary */ - if ((dict==usingExtDict) && (match < lowPrefix)) { - if (unlikely(op+length > oend-LASTLITERALS)) { - if (partialDecoding) length = MIN(length, (size_t)(oend-op)); - else goto _output_error; /* doesn't respect parsing restriction */ - } - - if (length <= (size_t)(lowPrefix-match)) { - /* match fits entirely within external dictionary : just copy */ - memmove(op, dictEnd - (lowPrefix-match), length); - op += length; - } else { - /* match stretches into both 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; - 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, restSize); - op += restSize; - } } - continue; - } - - /* copy match within block */ - cpy = op + length; - - /* partialDecoding : may not respect endBlock parsing restrictions */ - assert(op<=oend); - if (unlikely(offset<16)) { - LZ4_memcpy_using_offset(op, match, cpy, offset); - } else { - LZ4_wildCopy32(op, match, cpy); - } - - op = cpy; /* wildcopy correction */ - } - safe_decode: -#endif - - /* Main Loop : decode remaining sequences where output < FASTLOOP_SAFE_DISTANCE */ - while (1) { - token = *ip++; - length = token >> ML_BITS; /* literal length */ - - assert(!endOnInput || ip <= iend); /* ip < iend before the increment */ - - /* A two-stage shortcut for the most common case: - * 1) If the literal length is 0..14, and there is enough space, - * enter the shortcut and copy 16 bytes on behalf of the literals - * (in the fast mode, only 8 bytes can be safely copied this way). - * 2) Further if the match length is 4..18, copy 18 bytes in a similar - * manner; but we ensure that there's enough space in the output for - * those 18 bytes earlier, upon entering the shortcut (in other words, - * there is a combined check for both stages). - */ - if ( (endOnInput ? length != RUN_MASK : length <= 8) - /* strictly "less than" on input, to re-enter the loop with at least one byte */ - && likely((endOnInput ? ip < shortiend : 1) & (op <= shortoend)) ) { - /* Copy the literals */ - memcpy(op, ip, endOnInput ? 16 : 8); - op += length; ip += length; - - /* The second stage: prepare for match copying, decode full info. - * If it doesn't work out, the info won't be wasted. */ - length = token & ML_MASK; /* match length */ - offset = LZ4_readLE16(ip); ip += 2; - match = op - offset; - assert(match <= op); /* check overflow */ - - /* Do not deal with overlapping matches. */ - if ( (length != ML_MASK) - && (offset >= 8) - && (dict==withPrefix64k || match >= lowPrefix) ) { - /* Copy the match. */ - memcpy(op + 0, match + 0, 8); - memcpy(op + 8, match + 8, 8); - memcpy(op +16, match +16, 2); - op += length + MINMATCH; - /* Both stages worked, load the next token. */ - continue; - } - - /* The second stage didn't work out, but the info is ready. - * Propel it right to the point of match copying. */ - goto _copy_match; - } - - /* decode literal length */ - if (length == RUN_MASK) { - variable_length_error error = ok; - length += read_variable_length(&ip, iend-RUN_MASK, endOnInput, endOnInput, &error); - if (error == initial_error) goto _output_error; - 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 defined(__i386__) || defined(__x86_64__) - safe_literal_copy: -#endif - LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH); - if ( ((endOnInput) && ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) ) - || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) ) - { - if (partialDecoding) { - if (cpy > oend) { cpy = oend; length = oend-op; } /* Partial decoding : stop in the middle of literal segment */ - if ((endOnInput) && (ip+length > iend)) goto _output_error; /* Error : read attempt beyond end of input buffer */ - } 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 */ - } - memcpy(op, ip, length); - ip += length; - op += length; - if (!partialDecoding || (cpy == oend)) { - /* Necessarily EOF, due to parsing restrictions */ - break; - } - - } else { - LZ4_wildCopy(op, ip, cpy); /* may overwrite up to WILDCOPYLENGTH beyond cpy */ - ip += length; op = cpy; - } - - /* get offset */ - offset = LZ4_readLE16(ip); ip+=2; - match = op - offset; - - /* get matchlength */ - length = token & ML_MASK; - - _copy_match: - if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */ - if (!partialDecoding) { - assert(oend > op); - assert(oend - op >= 4); - LZ4_write32(op, 0); /* silence an msan warning when offset==0; costs <1%; */ - } /* note : when partialDecoding, there is no guarantee that at least 4 bytes remain available in output buffer */ - - if (length == ML_MASK) { - variable_length_error error = ok; - length += read_variable_length(&ip, iend - LASTLITERALS + 1, endOnInput, 0, &error); - if (error != ok) goto _output_error; - if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */ - } - length += MINMATCH; - -#if defined(__i386__) || defined(__x86_64__) - safe_match_copy: -#endif - /* match starting within external dictionary */ - if ((dict==usingExtDict) && (match < lowPrefix)) { - if (unlikely(op+length > oend-LASTLITERALS)) { - if (partialDecoding) length = MIN(length, (size_t)(oend-op)); - else goto _output_error; /* doesn't respect parsing restriction */ - } - - if (length <= (size_t)(lowPrefix-match)) { - /* match fits entirely within external dictionary : just copy */ - memmove(op, dictEnd - (lowPrefix-match), length); - op += length; - } else { - /* match stretches into both 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; - 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, restSize); - op += restSize; - } } - continue; - } - - /* copy match within block */ - cpy = op + length; - - /* partialDecoding : may not respect endBlock parsing restrictions */ - assert(op<=oend); - if (partialDecoding && (cpy > oend-MATCH_SAFEGUARD_DISTANCE)) { - size_t const mlen = MIN(length, (size_t)(oend-op)); - const BYTE* const matchEnd = match + mlen; - BYTE* const copyEnd = op + mlen; - if (matchEnd > op) { /* overlap copy */ - while (op < copyEnd) *op++ = *match++; - } else { - memcpy(op, match, mlen); - } - op = copyEnd; - if (op==oend) break; - continue; - } - - if (unlikely(offset<8)) { - op[0] = match[0]; - op[1] = match[1]; - op[2] = match[2]; - op[3] = match[3]; - match += inc32table[offset]; - memcpy(op+4, match, 4); - match -= dec64table[offset]; - } else { - memcpy(op, match, 8); - match += 8; - } - op += 8; - - if (unlikely(cpy > oend-MATCH_SAFEGUARD_DISTANCE)) { - 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 { - memcpy(op, match, 8); - if (length > 16) LZ4_wildCopy(op+8, match+8, cpy); - } - op = cpy; /* wildcopy correction */ - } - - /* end of decoding */ - if (endOnInput) - return (int) (((char*)op)-dst); /* Nb of output bytes decoded */ - else - return (int) (((const char*)ip)-src); /* Nb of input bytes read */ - - /* Overflow error detected */ - _output_error: - return (int) (-(((const char*)ip)-src))-1; - } -} - - -/*===== Instantiate the API decoding functions. =====*/ - -LZ4_FORCE_O2_GCC_PPC64LE -int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize) -{ - return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, - endOnInputSize, decode_full_block, noDict, - (BYTE*)dest, NULL, 0); -} - -LZ4_FORCE_O2_GCC_PPC64LE -int LZ4_decompress_safe_partial(const char* src, char* dst, int compressedSize, int targetOutputSize, int dstCapacity) -{ - dstCapacity = MIN(targetOutputSize, dstCapacity); - return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity, - endOnInputSize, partial_decode, - noDict, (BYTE*)dst, NULL, 0); -} - -LZ4_FORCE_O2_GCC_PPC64LE -int LZ4_decompress_fast(const char* source, char* dest, int originalSize) -{ - return LZ4_decompress_generic(source, dest, 0, originalSize, - endOnOutputSize, decode_full_block, withPrefix64k, - (BYTE*)dest - 64 KB, NULL, 0); -} - -/*===== Instantiate a few more decoding cases, used more than once. =====*/ - -LZ4_FORCE_O2_GCC_PPC64LE /* Exported, an obsolete API function. */ -int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize) -{ - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, decode_full_block, withPrefix64k, - (BYTE*)dest - 64 KB, NULL, 0); -} - -/* Another obsolete API function, paired with the previous one. */ -int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize) -{ - /* LZ4_decompress_fast doesn't validate match offsets, - * and thus serves well with any prefixed dictionary. */ - return LZ4_decompress_fast(source, dest, originalSize); -} - -LZ4_FORCE_O2_GCC_PPC64LE -static int LZ4_decompress_safe_withSmallPrefix(const char* source, char* dest, int compressedSize, int maxOutputSize, - size_t prefixSize) -{ - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, decode_full_block, noDict, - (BYTE*)dest-prefixSize, NULL, 0); -} - -LZ4_FORCE_O2_GCC_PPC64LE -int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, - int compressedSize, int maxOutputSize, - const void* dictStart, size_t dictSize) -{ - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, decode_full_block, usingExtDict, - (BYTE*)dest, (const BYTE*)dictStart, dictSize); -} - -LZ4_FORCE_O2_GCC_PPC64LE -static int LZ4_decompress_fast_extDict(const char* source, char* dest, int originalSize, - const void* dictStart, size_t dictSize) -{ - return LZ4_decompress_generic(source, dest, 0, originalSize, - endOnOutputSize, decode_full_block, usingExtDict, - (BYTE*)dest, (const BYTE*)dictStart, dictSize); -} - -/* The "double dictionary" mode, for use with e.g. ring buffers: the first part - * of the dictionary is passed as prefix, and the second via dictStart + dictSize. - * These routines are used only once, in LZ4_decompress_*_continue(). - */ -LZ4_FORCE_INLINE -int LZ4_decompress_safe_doubleDict(const char* source, char* dest, int compressedSize, int maxOutputSize, - size_t prefixSize, const void* dictStart, size_t dictSize) -{ - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, decode_full_block, usingExtDict, - (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize); -} - -LZ4_FORCE_INLINE -int LZ4_decompress_fast_doubleDict(const char* source, char* dest, int originalSize, - size_t prefixSize, const void* dictStart, size_t dictSize) -{ - return LZ4_decompress_generic(source, dest, 0, originalSize, - endOnOutputSize, decode_full_block, usingExtDict, - (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize); -} - -/*===== streaming decompression functions =====*/ - -LZ4_streamDecode_t* LZ4_createStreamDecode(void) -{ - LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t)); - LZ4_STATIC_ASSERT(LZ4_STREAMDECODESIZE >= sizeof(LZ4_streamDecode_t_internal)); /* A compilation error here means LZ4_STREAMDECODESIZE is not large enough */ - return lz4s; -} - -int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream) -{ - if (LZ4_stream == NULL) return 0; /* support free on NULL */ - FREEMEM(LZ4_stream); - return 0; -} - -/*! 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->internal_donotuse; - lz4sd->prefixSize = (size_t) dictSize; - lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize; - lz4sd->externalDict = NULL; - lz4sd->extDictSize = 0; - return 1; -} - -/*! LZ4_decoderRingBufferSize() : - * when setting a ring buffer for streaming decompression (optional scenario), - * provides the minimum size of this ring buffer - * to be compatible with any source respecting maxBlockSize condition. - * Note : in a ring buffer scenario, - * blocks are presumed decompressed next to each other. - * When not enough space remains for next block (remainingSize < maxBlockSize), - * decoding resumes from beginning of ring buffer. - * @return : minimum ring buffer size, - * or 0 if there is an error (invalid maxBlockSize). - */ -int LZ4_decoderRingBufferSize(int maxBlockSize) -{ - if (maxBlockSize < 0) return 0; - if (maxBlockSize > LZ4_MAX_INPUT_SIZE) return 0; - if (maxBlockSize < 16) maxBlockSize = 16; - return LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize); -} - -/* -*_continue() : - These decoding functions allow decompression of multiple blocks in "streaming" mode. - Previously decoded blocks must still be available at the memory position where they were decoded. - If it's not possible, save the relevant part of decoded data into a safe buffer, - and indicate where it stands using LZ4_setStreamDecode() -*/ -LZ4_FORCE_O2_GCC_PPC64LE -int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize) -{ - LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; - int result; - - if (lz4sd->prefixSize == 0) { - /* The first call, no dictionary yet. */ - assert(lz4sd->extDictSize == 0); - result = LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize); - if (result <= 0) return result; - lz4sd->prefixSize = result; - lz4sd->prefixEnd = (BYTE*)dest + result; - } else if (lz4sd->prefixEnd == (BYTE*)dest) { - /* They're rolling the current segment. */ - if (lz4sd->prefixSize >= 64 KB - 1) - result = LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize); - else if (lz4sd->extDictSize == 0) - result = LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, - lz4sd->prefixSize); - else - result = LZ4_decompress_safe_doubleDict(source, dest, compressedSize, maxOutputSize, - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); - if (result <= 0) return result; - lz4sd->prefixSize += result; - lz4sd->prefixEnd += result; - } else { - /* The buffer wraps around, or they're switching to another buffer. */ - lz4sd->extDictSize = lz4sd->prefixSize; - lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; - result = LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, - lz4sd->externalDict, lz4sd->extDictSize); - if (result <= 0) return result; - lz4sd->prefixSize = result; - lz4sd->prefixEnd = (BYTE*)dest + result; - } - - return result; -} - -LZ4_FORCE_O2_GCC_PPC64LE -int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize) -{ - LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; - int result; - - if (lz4sd->prefixSize == 0) { - assert(lz4sd->extDictSize == 0); - result = LZ4_decompress_fast(source, dest, originalSize); - if (result <= 0) return result; - lz4sd->prefixSize = originalSize; - lz4sd->prefixEnd = (BYTE*)dest + originalSize; - } else if (lz4sd->prefixEnd == (BYTE*)dest) { - if (lz4sd->prefixSize >= 64 KB - 1 || lz4sd->extDictSize == 0) - result = LZ4_decompress_fast(source, dest, originalSize); - else - result = LZ4_decompress_fast_doubleDict(source, dest, originalSize, - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); - if (result <= 0) return result; - lz4sd->prefixSize += originalSize; - lz4sd->prefixEnd += originalSize; - } else { - lz4sd->extDictSize = lz4sd->prefixSize; - lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; - result = LZ4_decompress_fast_extDict(source, dest, originalSize, - lz4sd->externalDict, lz4sd->extDictSize); - if (result <= 0) return result; - lz4sd->prefixSize = originalSize; - lz4sd->prefixEnd = (BYTE*)dest + originalSize; - } - - return result; -} - - -/* -Advanced decoding functions : -*_usingDict() : - These decoding functions work the same as "_continue" ones, - the dictionary must be explicitly provided within parameters -*/ - -int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize) -{ - if (dictSize==0) - return LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize); - if (dictStart+dictSize == dest) { - if (dictSize >= 64 KB - 1) - return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize); - return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, dictSize); - } - return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, dictSize); -} - -int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize) -{ - if (dictSize==0 || dictStart+dictSize == dest) - return LZ4_decompress_fast(source, dest, originalSize); - return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, dictSize); -} - - -/*=************************************************* -* Obsolete Functions -***************************************************/ -/* obsolete compression functions */ -int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) -{ - return LZ4_compress_default(source, dest, inputSize, maxOutputSize); -} -int LZ4_compress(const char* source, char* dest, int inputSize) -{ - return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize)); -} -int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) -{ - return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1); -} -int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize) -{ - return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1); -} -int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int dstCapacity) -{ - return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, dstCapacity, 1); -} -int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) -{ - return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); -} - -/* -These decompression functions are deprecated and should no longer be used. -They are only provided here for compatibility with older user programs. -- LZ4_uncompress is totally equivalent to LZ4_decompress_fast -- LZ4_uncompress_unknownOutputSize is totally equivalent to LZ4_decompress_safe -*/ -int LZ4_uncompress (const char* source, char* dest, int outputSize) -{ - return LZ4_decompress_fast(source, dest, outputSize); -} -int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) -{ - return LZ4_decompress_safe(source, dest, isize, maxOutputSize); -} - -/* Obsolete Streaming functions */ - -int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; } - -int LZ4_resetStreamState(void* state, char* inputBuffer) -{ - (void)inputBuffer; - LZ4_resetStream((LZ4_stream_t*)state); - return 0; -} - -void* LZ4_create (char* inputBuffer) -{ - (void)inputBuffer; - return LZ4_createStream(); -} - -char* LZ4_slideInputBuffer (void* state) -{ - /* avoid const char * -> char * conversion warning */ - return (char *)(uptrval)((LZ4_stream_t*)state)->internal_donotuse.dictionary; -} - -#endif /* LZ4_COMMONDEFS_ONLY */ diff --git a/uppsrc/plugin/lz4/lz4.h b/uppsrc/plugin/lz4/lz4.h deleted file mode 100644 index c78f12381..000000000 --- a/uppsrc/plugin/lz4/lz4.h +++ /dev/null @@ -1,644 +0,0 @@ -/* - * LZ4 - Fast LZ compression algorithm - * Header File - * Copyright (C) 2011-present, Yann Collet. - - BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) - - Redistribution and use in source and binary forms, with or without - modification, are permitted provided that the following conditions are - met: - - * Redistributions of source code must retain the above copyright - notice, this list of conditions and the following disclaimer. - * Redistributions in binary form must reproduce the above - copyright notice, this list of conditions and the following disclaimer - in the documentation and/or other materials provided with the - distribution. - - THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - - You can contact the author at : - - LZ4 homepage : http://www.lz4.org - - LZ4 source repository : https://github.com/lz4/lz4 -*/ -#if defined (__cplusplus) -extern "C" { -#endif - -#ifndef LZ4_H_2983827168210 -#define LZ4_H_2983827168210 - -/* --- Dependency --- */ -#include /* size_t */ - - -/** - Introduction - - LZ4 is lossless compression algorithm, providing compression speed at 500 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. - Frame format is required for interoperability. - It is delivered through a companion API, declared in lz4frame.h. -*/ - -/*^*************************************************************** -* Export parameters -*****************************************************************/ -/* -* LZ4_DLL_EXPORT : -* Enable exporting of functions when building a Windows DLL -* LZ4LIB_VISIBILITY : -* Control library symbols visibility. -*/ -#ifndef LZ4LIB_VISIBILITY -# if defined(__GNUC__) && (__GNUC__ >= 4) -# define LZ4LIB_VISIBILITY __attribute__ ((visibility ("default"))) -# else -# define LZ4LIB_VISIBILITY -# endif -#endif -#if defined(LZ4_DLL_EXPORT) && (LZ4_DLL_EXPORT==1) -# define LZ4LIB_API __declspec(dllexport) LZ4LIB_VISIBILITY -#elif defined(LZ4_DLL_IMPORT) && (LZ4_DLL_IMPORT==1) -# define LZ4LIB_API __declspec(dllimport) LZ4LIB_VISIBILITY /* 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 LZ4LIB_VISIBILITY -#endif - -/*------ Version ------*/ -#define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */ -#define LZ4_VERSION_MINOR 8 /* for new (non-breaking) interface capabilities */ -#define LZ4_VERSION_RELEASE 3 /* for tweaks, bug-fixes, or development */ - -#define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE) - -#define LZ4_LIB_VERSION LZ4_VERSION_MAJOR.LZ4_VERSION_MINOR.LZ4_VERSION_RELEASE -#define LZ4_QUOTE(str) #str -#define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str) -#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION) - -LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; useful to check dll version */ -LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; useful to check dll version */ - - -/*-************************************ -* Tuning parameter -**************************************/ -/*! - * LZ4_MEMORY_USAGE : - * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.) - * Increasing memory usage improves compression ratio. - * Reduced memory usage may improve speed, thanks to better cache locality. - * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache - */ -#ifndef LZ4_MEMORY_USAGE -# define LZ4_MEMORY_USAGE 14 -#endif - - -/*-************************************ -* Simple Functions -**************************************/ -/*! LZ4_compress_default() : - Compresses 'srcSize' bytes from buffer 'src' - into already allocated 'dst' buffer of size 'dstCapacity'. - Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize). - It also runs faster, so it's a recommended setting. - If the function cannot compress 'src' into a more limited 'dst' budget, - compression stops *immediately*, and the function result is zero. - In which case, 'dst' content is undefined (invalid). - srcSize : max supported value is LZ4_MAX_INPUT_SIZE. - dstCapacity : size of buffer 'dst' (which must be already allocated) - @return : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity) - or 0 if compression fails - Note : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer). -*/ -LZ4LIB_API int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity); - -/*! LZ4_decompress_safe() : - compressedSize : is the exact complete size of the compressed block. - dstCapacity : is the size of destination buffer, which must be already allocated. - @return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity) - If destination buffer is not large enough, decoding will stop and output an error code (negative value). - If the source stream is detected malformed, the function will stop decoding and return a negative result. - Note : This function is protected against malicious data packets (never writes outside 'dst' buffer, nor read outside 'source' buffer). -*/ -LZ4LIB_API int LZ4_decompress_safe (const char* src, char* dst, int compressedSize, int dstCapacity); - - -/*-************************************ -* 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). - Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example). - Note that LZ4_compress_default() compresses faster when dstCapacity is >= LZ4_compressBound(srcSize) - inputSize : max supported value is LZ4_MAX_INPUT_SIZE - return : maximum output size in a "worst case" scenario - or 0, if input size is incorrect (too large or negative) -*/ -LZ4LIB_API int LZ4_compressBound(int inputSize); - -/*! LZ4_compress_fast() : - Same as LZ4_compress_default(), but allows selection of "acceleration" factor. - The larger the acceleration value, the faster the algorithm, but also the lesser the compression. - It's a trade-off. It can be fine tuned, with each successive value providing roughly +~3% to speed. - An acceleration value of "1" is the same as regular LZ4_compress_default() - Values <= 0 will be replaced by ACCELERATION_DEFAULT (currently == 1, see lz4.c). -*/ -LZ4LIB_API int LZ4_compress_fast (const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); - - -/*! LZ4_compress_fast_extState() : - * Same as LZ4_compress_fast(), using an externally allocated memory space for its state. - * Use LZ4_sizeofState() to know how much memory must be allocated, - * and allocate it on 8-bytes boundaries (using `malloc()` typically). - * Then, provide this buffer as `void* state` to compression function. - */ -LZ4LIB_API int LZ4_sizeofState(void); -LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); - - -/*! LZ4_compress_destSize() : - * Reverse the logic : compresses as much data as possible from 'src' buffer - * into already allocated buffer 'dst', of size >= 'targetDestSize'. - * This function either compresses the entire 'src' content into 'dst' if it's large enough, - * or fill 'dst' buffer completely with as much data as possible from 'src'. - * note: acceleration parameter is fixed to "default". - * - * *srcSizePtr : will be modified to indicate how many bytes where read from 'src' to fill 'dst'. - * New value is necessarily <= input value. - * @return : Nb bytes written into 'dst' (necessarily <= targetDestSize) - * or 0 if compression fails. -*/ -LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePtr, int targetDstSize); - - -/*! LZ4_decompress_fast() : **unsafe!** - * This function used to be a bit faster than LZ4_decompress_safe(), - * though situation has changed in recent versions, - * and now `LZ4_decompress_safe()` can be as fast and sometimes faster than `LZ4_decompress_fast()`. - * Moreover, LZ4_decompress_fast() is not protected vs malformed input, as it doesn't perform full validation of compressed data. - * As a consequence, this function is no longer recommended, and may be deprecated in future versions. - * It's last remaining specificity is that it can decompress data without knowing its compressed size. - * - * originalSize : is the uncompressed size to regenerate. - * `dst` must be already allocated, its size must be >= 'originalSize' bytes. - * @return : number of bytes read from source buffer (== compressed size). - * If the source stream is detected malformed, the function stops decoding and returns a negative result. - * note : This function requires uncompressed originalSize to be known in advance. - * The function never writes past the output buffer. - * However, since it doesn't know its 'src' size, it may read past the intended input. - * Also, because match offsets are not validated during decoding, - * reads from 'src' may underflow. - * Use this function in trusted environment **only**. - */ -LZ4LIB_API int LZ4_decompress_fast (const char* src, char* dst, int originalSize); - -/*! LZ4_decompress_safe_partial() : - * Decompress an LZ4 compressed block, of size 'srcSize' at position 'src', - * into destination buffer 'dst' of size 'dstCapacity'. - * Up to 'targetOutputSize' bytes will be decoded. - * The function stops decoding on reaching this objective, - * which can boost performance when only the beginning of a block is required. - * - * @return : the number of bytes decoded in `dst` (necessarily <= dstCapacity) - * If source stream is detected malformed, function returns a negative result. - * - * Note : @return can be < targetOutputSize, if compressed block contains less data. - * - * Note 2 : this function features 2 parameters, targetOutputSize and dstCapacity, - * and expects targetOutputSize <= dstCapacity. - * It effectively stops decoding on reaching targetOutputSize, - * so dstCapacity is kind of redundant. - * This is because in a previous version of this function, - * decoding operation would not "break" a sequence in the middle. - * As a consequence, there was no guarantee that decoding would stop at exactly targetOutputSize, - * it could write more bytes, though only up to dstCapacity. - * Some "margin" used to be required for this operation to work properly. - * This is no longer necessary. - * The function nonetheless keeps its signature, in an effort to not break API. - */ -LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcSize, int targetOutputSize, int dstCapacity); - - -/*-********************************************* -* Streaming Compression Functions -***********************************************/ -typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */ - -LZ4LIB_API LZ4_stream_t* LZ4_createStream(void); -LZ4LIB_API int LZ4_freeStream (LZ4_stream_t* streamPtr); - -/*! LZ4_resetStream() : - * An LZ4_stream_t structure can be allocated once and re-used multiple times. - * Use this function to start compressing a new stream. - */ -LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr); - -/*! LZ4_loadDict() : - * Use this function to load a static dictionary into LZ4_stream_t. - * Any previous data will be forgotten, only 'dictionary' will remain in memory. - * Loading a size of 0 is allowed, and is the same as reset. - * @return : dictionary size, in bytes (necessarily <= 64 KB) - */ -LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize); - -/*! LZ4_compress_fast_continue() : - * Compress 'src' content using data from previously compressed blocks, for better compression ratio. - * 'dst' buffer must be already allocated. - * If dstCapacity >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster. - * - * @return : size of compressed block - * or 0 if there is an error (typically, cannot fit into 'dst'). - * - * Note 1 : Each invocation to LZ4_compress_fast_continue() generates a new block. - * Each block has precise boundaries. - * Each block must be decompressed separately, calling LZ4_decompress_*() with relevant metadata. - * It's not possible to append blocks together and expect a single invocation of LZ4_decompress_*() to decompress them together. - * - * Note 2 : The previous 64KB of source data is __assumed__ to remain present, unmodified, at same address in memory ! - * - * Note 3 : When input is structured as a double-buffer, each buffer can have any size, including < 64 KB. - * Make sure that buffers are separated, by at least one byte. - * This construction ensures that each block only depends on previous block. - * - * Note 4 : If input buffer is a ring-buffer, it can have any size, including < 64 KB. - * - * Note 5 : After an error, the stream status is undefined (invalid), it can only be reset or freed. - */ -LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); - -/*! LZ4_saveDict() : - * If last 64KB data cannot be guaranteed to remain available at its current memory location, - * save it into a safer place (char* safeBuffer). - * This is schematically equivalent to a memcpy() followed by LZ4_loadDict(), - * but is much faster, because LZ4_saveDict() doesn't need to rebuild tables. - * @return : saved dictionary size in bytes (necessarily <= maxDictSize), or 0 if error. - */ -LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int maxDictSize); - - -/*-********************************************** -* Streaming Decompression Functions -* Bufferless synchronous API -************************************************/ -typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* tracking context */ - -/*! LZ4_createStreamDecode() and LZ4_freeStreamDecode() : - * creation / destruction of streaming decompression tracking context. - * A tracking context can be re-used multiple times. - */ -LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void); -LZ4LIB_API int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream); - -/*! LZ4_setStreamDecode() : - * An LZ4_streamDecode_t context can be allocated once and re-used multiple times. - * Use this function to start decompression of a new stream of blocks. - * A dictionary can optionally be set. Use NULL or size 0 for a reset order. - * Dictionary is presumed stable : it must remain accessible and unmodified during next decompression. - * @return : 1 if OK, 0 if error - */ -LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize); - -/*! LZ4_decoderRingBufferSize() : v1.8.2+ - * Note : in a ring buffer scenario (optional), - * blocks are presumed decompressed next to each other - * up to the moment there is not enough remaining space for next block (remainingSize < maxBlockSize), - * at which stage it resumes from beginning of ring buffer. - * When setting such a ring buffer for streaming decompression, - * provides the minimum size of this ring buffer - * to be compatible with any source respecting maxBlockSize condition. - * @return : minimum ring buffer size, - * or 0 if there is an error (invalid maxBlockSize). - */ -LZ4LIB_API int LZ4_decoderRingBufferSize(int maxBlockSize); -#define LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize) (65536 + 14 + (maxBlockSize)) /* for static allocation; maxBlockSize presumed valid */ - -/*! LZ4_decompress_*_continue() : - * These decoding functions allow decompression of consecutive blocks in "streaming" mode. - * A block is an unsplittable entity, it must be presented entirely to a decompression function. - * Decompression functions only accepts one block at a time. - * The last 64KB of previously decoded data *must* remain available and unmodified at the memory position where they were decoded. - * If less than 64KB of data has been decoded, all the data must be present. - * - * Special : if decompression side sets a ring buffer, it must respect one of the following conditions : - * - Decompression buffer size is _at least_ LZ4_decoderRingBufferSize(maxBlockSize). - * maxBlockSize is the maximum size of any single block. It can have any value > 16 bytes. - * In which case, encoding and decoding buffers do not need to be synchronized. - * Actually, data can be produced by any source compliant with LZ4 format specification, and respecting maxBlockSize. - * - Synchronized mode : - * Decompression buffer size is _exactly_ the same as compression buffer size, - * and follows exactly same update rule (block boundaries at same positions), - * and decoding function is provided with exact decompressed size of each block (exception for last block of the stream), - * _then_ decoding & encoding ring buffer can have any size, including small ones ( < 64 KB). - * - Decompression buffer is larger than encoding buffer, by a minimum of maxBlockSize more bytes. - * In which case, encoding and decoding buffers do not need to be synchronized, - * and encoding ring buffer can have any size, including small ones ( < 64 KB). - * - * Whenever these conditions are not possible, - * save the last 64KB of decoded data into a safe buffer where it can't be modified during decompression, - * then indicate where this data is saved using LZ4_setStreamDecode(), before decompressing next block. -*/ -LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int srcSize, int dstCapacity); -LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int originalSize); - - -/*! LZ4_decompress_*_usingDict() : - * These decoding functions work the same as - * a combination of LZ4_setStreamDecode() followed by LZ4_decompress_*_continue() - * They are stand-alone, and don't need an LZ4_streamDecode_t structure. - * Dictionary is presumed stable : it must remain accessible and unmodified during decompression. - * Performance tip : Decompression speed can be substantially increased - * when dst == dictStart + dictSize. - */ -LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int srcSize, int dstCapcity, const char* dictStart, int dictSize); -LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int originalSize, const char* dictStart, int dictSize); - - -/*^************************************* - * !!!!!! STATIC LINKING ONLY !!!!!! - ***************************************/ - -/*-**************************************************************************** - * Symbols declared in this section must be considered unstable. Their - * signatures or semantics may change, or they may be removed altogether in the - * future. They are therefore only safe to depend on when the caller is - * statically linked against the library. - * - * To protect against unsafe usage, not only are the declarations guarded, the - * definitions are hidden by default when building LZ4 as a shared/dynamic - * library. - * - * In order to access these declarations, define LZ4_STATIC_LINKING_ONLY in - * your application before including LZ4's headers. - * - * In order to make their implementations accessible dynamically, you must - * define LZ4_PUBLISH_STATIC_FUNCTIONS when building the LZ4 library. - ******************************************************************************/ - -#ifdef LZ4_PUBLISH_STATIC_FUNCTIONS -#define LZ4LIB_STATIC_API LZ4LIB_API -#else -#define LZ4LIB_STATIC_API -#endif - -#ifdef LZ4_STATIC_LINKING_ONLY - -/*! LZ4_resetStream_fast() : - * Use this to prepare a context for a new chain of calls to a streaming API - * (e.g., LZ4_compress_fast_continue()). - * - * Note: - * To stay on the safe side, when LZ4_stream_t is used for the first time, - * it should be either created using LZ4_createStream() or - * initialized using LZ4_resetStream(). - * - * Note: - * Using this in advance of a non-streaming-compression function is redundant, - * since they all perform their own custom reset internally. - * - * Differences from LZ4_resetStream(): - * When an LZ4_stream_t is known to be in an internally coherent state, - * it will be prepared for a new compression with almost no work. - * Otherwise, it will fall back to the full, expensive reset. - * - * LZ4_streams are guaranteed to be in a valid state when: - * - returned from LZ4_createStream() - * - reset by LZ4_resetStream() - * - memset(stream, 0, sizeof(LZ4_stream_t)), though this is discouraged - * - the stream was in a valid state and was reset by LZ4_resetStream_fast() - * - the stream was in a valid state and was then used in any compression call - * that returned success - * - the stream was in an indeterminate state and was used in a compression - * call that fully reset the state (e.g., LZ4_compress_fast_extState()) and - * that returned success - * - * Note: - * A stream that was used in a compression call that did not return success - * (e.g., LZ4_compress_fast_continue()), can still be passed to this function, - * however, it's history is not preserved because of previous compression - * failure. - */ -LZ4LIB_STATIC_API void LZ4_resetStream_fast (LZ4_stream_t* streamPtr); - -/*! LZ4_compress_fast_extState_fastReset() : - * A variant of LZ4_compress_fast_extState(). - * - * Using this variant avoids an expensive initialization step. - * It is only safe to call if the state buffer is known to be correctly initialized already - * (see above comment on LZ4_resetStream_fast() for a definition of "correctly initialized"). - * From a high level, the difference is that - * this function initializes the provided state with a call to something like LZ4_resetStream_fast() - * while LZ4_compress_fast_extState() starts with a call to LZ4_resetStream(). - */ -LZ4LIB_STATIC_API int LZ4_compress_fast_extState_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); - -/*! LZ4_attach_dictionary() : - * This is an experimental API that allows - * efficient use of a static dictionary many times. - * - * Rather than re-loading the dictionary buffer into a working context before - * each compression, or copying a pre-loaded dictionary's LZ4_stream_t into a - * working LZ4_stream_t, this function introduces a no-copy setup mechanism, - * in which the working stream references the dictionary stream in-place. - * - * Several assumptions are made about the state of the dictionary stream. - * Currently, only streams which have been prepared by LZ4_loadDict() should - * be expected to work. - * - * Alternatively, the provided dictionaryStream may be NULL, - * in which case any existing dictionary stream is unset. - * - * If a dictionary is provided, it replaces any pre-existing stream history. - * The dictionary contents are the only history that can be referenced and - * logically immediately precede the data compressed in the first subsequent - * compression call. - * - * The dictionary will only remain attached to the working stream through the - * first compression call, at the end of which it is cleared. The dictionary - * stream (and source buffer) must remain in-place / accessible / unchanged - * through the completion of the first compression call on the stream. - */ -LZ4LIB_STATIC_API void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream); - -#endif - - -/*-************************************************************ - * PRIVATE DEFINITIONS - ************************************************************** - * Do not use these definitions directly. - * They are only exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`. - * Accessing members will expose code to API and/or ABI break in future versions of the library. - **************************************************************/ -#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2) -#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE) -#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG) /* required as macro for static allocation */ - -#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) -#include - -typedef struct LZ4_stream_t_internal LZ4_stream_t_internal; -struct LZ4_stream_t_internal { - uint32_t hashTable[LZ4_HASH_SIZE_U32]; - uint32_t currentOffset; - uint16_t dirty; - uint16_t tableType; - const uint8_t* dictionary; - const LZ4_stream_t_internal* dictCtx; - uint32_t dictSize; -}; - -typedef struct { - const uint8_t* externalDict; - size_t extDictSize; - const uint8_t* prefixEnd; - size_t prefixSize; -} LZ4_streamDecode_t_internal; - -#else - -typedef struct LZ4_stream_t_internal LZ4_stream_t_internal; -struct LZ4_stream_t_internal { - unsigned int hashTable[LZ4_HASH_SIZE_U32]; - unsigned int currentOffset; - unsigned short dirty; - unsigned short tableType; - const unsigned char* dictionary; - const LZ4_stream_t_internal* dictCtx; - unsigned int dictSize; -}; - -typedef struct { - const unsigned char* externalDict; - const unsigned char* prefixEnd; - size_t extDictSize; - size_t prefixSize; -} LZ4_streamDecode_t_internal; - -#endif - -/*! LZ4_stream_t : - * information structure to track an LZ4 stream. - * init this structure with LZ4_resetStream() before first use. - * note : only use in association with static linking ! - * this definition is not API/ABI safe, - * it may change in a future version ! - */ -#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4 + ((sizeof(void*)==16) ? 4 : 0) /*AS-400*/ ) -#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() 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 + ((sizeof(void*)==16) ? 2 : 0) /*AS-400*/ ) -#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 -**************************************/ - -/*! Deprecation warnings - * Should deprecation warnings be a problem, - * it is generally possible to disable them, - * typically with -Wno-deprecated-declarations for gcc - * or _CRT_SECURE_NO_WARNINGS in Visual. - * Otherwise, it's also possible to define LZ4_DISABLE_DEPRECATE_WARNINGS */ -#ifdef LZ4_DISABLE_DEPRECATE_WARNINGS -# define LZ4_DEPRECATED(message) /* disable deprecation warnings */ -#else -# define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) -# if defined (__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)) -# elif defined(_MSC_VER) -# define LZ4_DEPRECATED(message) __declspec(deprecated(message)) -# else -# pragma message("WARNING: You need to implement LZ4_DEPRECATED for this compiler") -# define LZ4_DEPRECATED(message) -# endif -#endif /* LZ4_DISABLE_DEPRECATE_WARNINGS */ - -/* Obsolete compression functions */ -LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress (const char* source, char* dest, int sourceSize); -LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize); -LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize); -LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); -LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize); -LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize); - -/* Obsolete decompression functions */ -LZ4_DEPRECATED("use LZ4_decompress_fast() instead") LZ4LIB_API int LZ4_uncompress (const char* source, char* dest, int outputSize); -LZ4_DEPRECATED("use LZ4_decompress_safe() instead") LZ4LIB_API int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize); - -/* Obsolete streaming functions; degraded functionality; do not use! - * - * In order to perform streaming compression, these functions depended on data - * that is no longer tracked in the state. They have been preserved as well as - * possible: using them will still produce a correct output. However, they don't - * actually retain any history between compression calls. The compression ratio - * achieved will therefore be no better than compressing each chunk - * independently. - */ -LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API void* LZ4_create (char* inputBuffer); -LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API int LZ4_sizeofStreamState(void); -LZ4_DEPRECATED("Use LZ4_resetStream() instead") LZ4LIB_API int LZ4_resetStreamState(void* state, char* inputBuffer); -LZ4_DEPRECATED("Use LZ4_saveDict() instead") LZ4LIB_API char* LZ4_slideInputBuffer (void* state); - -/* Obsolete streaming decoding functions */ -LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") LZ4LIB_API int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize); -LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") LZ4LIB_API int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize); - -#endif /* LZ4_H_2983827168210 */ - - -#if defined (__cplusplus) -} -#endif diff --git a/uppsrc/plugin/lzma/lib/7zTypes.h b/uppsrc/plugin/lzma/lib/7zTypes.h index b99afc317..f960038bb 100644 --- a/uppsrc/plugin/lzma/lib/7zTypes.h +++ b/uppsrc/plugin/lzma/lib/7zTypes.h @@ -1,5 +1,5 @@ /* 7zTypes.h -- Basic types -2013-11-12 : Igor Pavlov : Public domain */ +2018-08-04 : Igor Pavlov : Public domain */ #ifndef __7Z_TYPES_H #define __7Z_TYPES_H @@ -44,13 +44,23 @@ EXTERN_C_BEGIN typedef int SRes; + #ifdef _WIN32 + /* typedef DWORD WRes; */ typedef unsigned WRes; +#define MY_SRes_HRESULT_FROM_WRes(x) HRESULT_FROM_WIN32(x) + #else + typedef int WRes; +#define MY__FACILITY_WIN32 7 +#define MY__FACILITY__WRes MY__FACILITY_WIN32 +#define MY_SRes_HRESULT_FROM_WRes(x) ((HRESULT)(x) <= 0 ? ((HRESULT)(x)) : ((HRESULT) (((x) & 0x0000FFFF) | (MY__FACILITY__WRes << 16) | 0x80000000))) + #endif + #ifndef RINOK #define RINOK(x) { int __result__ = (x); if (__result__ != 0) return __result__; } #endif @@ -95,7 +105,8 @@ typedef UInt32 SizeT; typedef size_t SizeT; #endif -typedef int Bool; +typedef int BoolInt; +/* typedef BoolInt Bool; */ #define True 1 #define False 0 @@ -114,48 +125,72 @@ typedef int Bool; #define MY_NO_INLINE #endif +#define MY_FORCE_INLINE __forceinline + #define MY_CDECL __cdecl #define MY_FAST_CALL __fastcall #else #define MY_NO_INLINE +#define MY_FORCE_INLINE #define MY_CDECL #define MY_FAST_CALL +/* inline keyword : for C++ / C99 */ + +/* GCC, clang: */ +/* +#if defined (__GNUC__) && (__GNUC__ >= 4) +#define MY_FORCE_INLINE __attribute__((always_inline)) +#define MY_NO_INLINE __attribute__((noinline)) +#endif +*/ + #endif /* The following interfaces use first parameter as pointer to structure */ -typedef struct +typedef struct IByteIn IByteIn; +struct IByteIn { - Byte (*Read)(void *p); /* reads one byte, returns 0 in case of EOF or error */ -} IByteIn; + Byte (*Read)(const IByteIn *p); /* reads one byte, returns 0 in case of EOF or error */ +}; +#define IByteIn_Read(p) (p)->Read(p) -typedef struct -{ - void (*Write)(void *p, Byte b); -} IByteOut; -typedef struct +typedef struct IByteOut IByteOut; +struct IByteOut { - SRes (*Read)(void *p, void *buf, size_t *size); + void (*Write)(const IByteOut *p, Byte b); +}; +#define IByteOut_Write(p, b) (p)->Write(p, b) + + +typedef struct ISeqInStream ISeqInStream; +struct ISeqInStream +{ + SRes (*Read)(const ISeqInStream *p, void *buf, size_t *size); /* if (input(*size) != 0 && output(*size) == 0) means end_of_stream. (output(*size) < input(*size)) is allowed */ -} ISeqInStream; +}; +#define ISeqInStream_Read(p, buf, size) (p)->Read(p, buf, size) /* it can return SZ_ERROR_INPUT_EOF */ -SRes SeqInStream_Read(ISeqInStream *stream, void *buf, size_t size); -SRes SeqInStream_Read2(ISeqInStream *stream, void *buf, size_t size, SRes errorType); -SRes SeqInStream_ReadByte(ISeqInStream *stream, Byte *buf); +SRes SeqInStream_Read(const ISeqInStream *stream, void *buf, size_t size); +SRes SeqInStream_Read2(const ISeqInStream *stream, void *buf, size_t size, SRes errorType); +SRes SeqInStream_ReadByte(const ISeqInStream *stream, Byte *buf); -typedef struct + +typedef struct ISeqOutStream ISeqOutStream; +struct ISeqOutStream { - size_t (*Write)(void *p, const void *buf, size_t size); + size_t (*Write)(const ISeqOutStream *p, const void *buf, size_t size); /* Returns: result - the number of actually written bytes. (result < size) means error */ -} ISeqOutStream; +}; +#define ISeqOutStream_Write(p, buf, size) (p)->Write(p, buf, size) typedef enum { @@ -164,78 +199,162 @@ typedef enum SZ_SEEK_END = 2 } ESzSeek; -typedef struct -{ - SRes (*Read)(void *p, void *buf, size_t *size); /* same as ISeqInStream::Read */ - SRes (*Seek)(void *p, Int64 *pos, ESzSeek origin); -} ISeekInStream; -typedef struct +typedef struct ISeekInStream ISeekInStream; +struct ISeekInStream { - SRes (*Look)(void *p, const void **buf, size_t *size); + SRes (*Read)(const ISeekInStream *p, void *buf, size_t *size); /* same as ISeqInStream::Read */ + SRes (*Seek)(const ISeekInStream *p, Int64 *pos, ESzSeek origin); +}; +#define ISeekInStream_Read(p, buf, size) (p)->Read(p, buf, size) +#define ISeekInStream_Seek(p, pos, origin) (p)->Seek(p, pos, origin) + + +typedef struct ILookInStream ILookInStream; +struct ILookInStream +{ + SRes (*Look)(const ILookInStream *p, const void **buf, size_t *size); /* if (input(*size) != 0 && output(*size) == 0) means end_of_stream. (output(*size) > input(*size)) is not allowed (output(*size) < input(*size)) is allowed */ - SRes (*Skip)(void *p, size_t offset); + SRes (*Skip)(const ILookInStream *p, size_t offset); /* offset must be <= output(*size) of Look */ - SRes (*Read)(void *p, void *buf, size_t *size); + SRes (*Read)(const ILookInStream *p, void *buf, size_t *size); /* reads directly (without buffer). It's same as ISeqInStream::Read */ - SRes (*Seek)(void *p, Int64 *pos, ESzSeek origin); -} ILookInStream; + SRes (*Seek)(const ILookInStream *p, Int64 *pos, ESzSeek origin); +}; -SRes LookInStream_LookRead(ILookInStream *stream, void *buf, size_t *size); -SRes LookInStream_SeekTo(ILookInStream *stream, UInt64 offset); +#define ILookInStream_Look(p, buf, size) (p)->Look(p, buf, size) +#define ILookInStream_Skip(p, offset) (p)->Skip(p, offset) +#define ILookInStream_Read(p, buf, size) (p)->Read(p, buf, size) +#define ILookInStream_Seek(p, pos, origin) (p)->Seek(p, pos, origin) + + +SRes LookInStream_LookRead(const ILookInStream *stream, void *buf, size_t *size); +SRes LookInStream_SeekTo(const ILookInStream *stream, UInt64 offset); /* reads via ILookInStream::Read */ -SRes LookInStream_Read2(ILookInStream *stream, void *buf, size_t size, SRes errorType); -SRes LookInStream_Read(ILookInStream *stream, void *buf, size_t size); +SRes LookInStream_Read2(const ILookInStream *stream, void *buf, size_t size, SRes errorType); +SRes LookInStream_Read(const ILookInStream *stream, void *buf, size_t size); + -#define LookToRead_BUF_SIZE (1 << 14) typedef struct { - ILookInStream s; - ISeekInStream *realStream; + ILookInStream vt; + const ISeekInStream *realStream; + size_t pos; - size_t size; - Byte buf[LookToRead_BUF_SIZE]; -} CLookToRead; + size_t size; /* it's data size */ + + /* the following variables must be set outside */ + Byte *buf; + size_t bufSize; +} CLookToRead2; + +void LookToRead2_CreateVTable(CLookToRead2 *p, int lookahead); + +#define LookToRead2_Init(p) { (p)->pos = (p)->size = 0; } -void LookToRead_CreateVTable(CLookToRead *p, int lookahead); -void LookToRead_Init(CLookToRead *p); typedef struct { - ISeqInStream s; - ILookInStream *realStream; + ISeqInStream vt; + const ILookInStream *realStream; } CSecToLook; void SecToLook_CreateVTable(CSecToLook *p); + + typedef struct { - ISeqInStream s; - ILookInStream *realStream; + ISeqInStream vt; + const ILookInStream *realStream; } CSecToRead; void SecToRead_CreateVTable(CSecToRead *p); -typedef struct + +typedef struct ICompressProgress ICompressProgress; + +struct ICompressProgress { - SRes (*Progress)(void *p, UInt64 inSize, UInt64 outSize); + SRes (*Progress)(const ICompressProgress *p, UInt64 inSize, UInt64 outSize); /* Returns: result. (result != SZ_OK) means break. Value (UInt64)(Int64)-1 for size means unknown value. */ -} ICompressProgress; +}; +#define ICompressProgress_Progress(p, inSize, outSize) (p)->Progress(p, inSize, outSize) -typedef struct + + +typedef struct ISzAlloc ISzAlloc; +typedef const ISzAlloc * ISzAllocPtr; + +struct ISzAlloc { - void *(*Alloc)(void *p, size_t size); - void (*Free)(void *p, void *address); /* address can be 0 */ -} ISzAlloc; + void *(*Alloc)(ISzAllocPtr p, size_t size); + void (*Free)(ISzAllocPtr p, void *address); /* address can be 0 */ +}; + +#define ISzAlloc_Alloc(p, size) (p)->Alloc(p, size) +#define ISzAlloc_Free(p, a) (p)->Free(p, a) + +/* deprecated */ +#define IAlloc_Alloc(p, size) ISzAlloc_Alloc(p, size) +#define IAlloc_Free(p, a) ISzAlloc_Free(p, a) + + + + + +#ifndef MY_offsetof + #ifdef offsetof + #define MY_offsetof(type, m) offsetof(type, m) + /* + #define MY_offsetof(type, m) FIELD_OFFSET(type, m) + */ + #else + #define MY_offsetof(type, m) ((size_t)&(((type *)0)->m)) + #endif +#endif + + + +#ifndef MY_container_of + +/* +#define MY_container_of(ptr, type, m) container_of(ptr, type, m) +#define MY_container_of(ptr, type, m) CONTAINING_RECORD(ptr, type, m) +#define MY_container_of(ptr, type, m) ((type *)((char *)(ptr) - offsetof(type, m))) +#define MY_container_of(ptr, type, m) (&((type *)0)->m == (ptr), ((type *)(((char *)(ptr)) - MY_offsetof(type, m)))) +*/ + +/* + GCC shows warning: "perhaps the 'offsetof' macro was used incorrectly" + GCC 3.4.4 : classes with constructor + GCC 4.8.1 : classes with non-public variable members" +*/ + +#define MY_container_of(ptr, type, m) ((type *)((char *)(1 ? (ptr) : &((type *)0)->m) - MY_offsetof(type, m))) + + +#endif + +#define CONTAINER_FROM_VTBL_SIMPLE(ptr, type, m) ((type *)(ptr)) + +/* +#define CONTAINER_FROM_VTBL(ptr, type, m) CONTAINER_FROM_VTBL_SIMPLE(ptr, type, m) +*/ +#define CONTAINER_FROM_VTBL(ptr, type, m) MY_container_of(ptr, type, m) + +#define CONTAINER_FROM_VTBL_CLS(ptr, type, m) CONTAINER_FROM_VTBL_SIMPLE(ptr, type, m) +/* +#define CONTAINER_FROM_VTBL_CLS(ptr, type, m) CONTAINER_FROM_VTBL(ptr, type, m) +*/ + -#define IAlloc_Alloc(p, size) (p)->Alloc((p), size) -#define IAlloc_Free(p, a) (p)->Free((p), a) #ifdef _WIN32 diff --git a/uppsrc/plugin/lzma/lib/Compiler.h b/uppsrc/plugin/lzma/lib/Compiler.h index de8fab374..c788648cd 100644 --- a/uppsrc/plugin/lzma/lib/Compiler.h +++ b/uppsrc/plugin/lzma/lib/Compiler.h @@ -1,5 +1,5 @@ /* Compiler.h -2015-08-02 : Igor Pavlov : Public domain */ +2017-04-03 : Igor Pavlov : Public domain */ #ifndef __7Z_COMPILER_H #define __7Z_COMPILER_H @@ -21,6 +21,7 @@ #pragma warning(disable : 4514) // unreferenced inline function has been removed #pragma warning(disable : 4702) // unreachable code #pragma warning(disable : 4710) // not inlined + #pragma warning(disable : 4714) // function marked as __forceinline not inlined #pragma warning(disable : 4786) // identifier was truncated to '255' characters in the debug information #endif diff --git a/uppsrc/plugin/lzma/lib/LzFind.c b/uppsrc/plugin/lzma/lib/LzFind.c index c335d363c..4eefc17dd 100644 --- a/uppsrc/plugin/lzma/lib/LzFind.c +++ b/uppsrc/plugin/lzma/lib/LzFind.c @@ -1,5 +1,5 @@ /* LzFind.c -- Match finder for LZ algorithms -2015-10-15 : Igor Pavlov : Public domain */ +2018-07-08 : Igor Pavlov : Public domain */ #include "Precomp.h" @@ -16,18 +16,18 @@ #define kStartMaxLen 3 -static void LzInWindow_Free(CMatchFinder *p, ISzAlloc *alloc) +static void LzInWindow_Free(CMatchFinder *p, ISzAllocPtr alloc) { if (!p->directInput) { - alloc->Free(alloc, p->bufferBase); + ISzAlloc_Free(alloc, p->bufferBase); p->bufferBase = NULL; } } /* keepSizeBefore + keepSizeAfter + keepSizeReserv must be < 4G) */ -static int LzInWindow_Create(CMatchFinder *p, UInt32 keepSizeReserv, ISzAlloc *alloc) +static int LzInWindow_Create(CMatchFinder *p, UInt32 keepSizeReserv, ISzAllocPtr alloc) { UInt32 blockSize = p->keepSizeBefore + p->keepSizeAfter + keepSizeReserv; if (p->directInput) @@ -39,7 +39,7 @@ static int LzInWindow_Create(CMatchFinder *p, UInt32 keepSizeReserv, ISzAlloc *a { LzInWindow_Free(p, alloc); p->blockSize = blockSize; - p->bufferBase = (Byte *)alloc->Alloc(alloc, (size_t)blockSize); + p->bufferBase = (Byte *)ISzAlloc_Alloc(alloc, (size_t)blockSize); } return (p->bufferBase != NULL); } @@ -81,7 +81,7 @@ static void MatchFinder_ReadBlock(CMatchFinder *p) if (size == 0) return; - p->result = p->stream->Read(p->stream, dest, &size); + p->result = ISeqInStream_Read(p->stream, dest, &size); if (p->result != SZ_OK) return; if (size == 0) @@ -138,45 +138,46 @@ static void MatchFinder_SetDefaultSettings(CMatchFinder *p) void MatchFinder_Construct(CMatchFinder *p) { - UInt32 i; + unsigned i; p->bufferBase = NULL; p->directInput = 0; p->hash = NULL; + p->expectedDataSize = (UInt64)(Int64)-1; MatchFinder_SetDefaultSettings(p); for (i = 0; i < 256; i++) { - UInt32 r = i; + UInt32 r = (UInt32)i; unsigned j; for (j = 0; j < 8; j++) - r = (r >> 1) ^ (kCrcPoly & ~((r & 1) - 1)); + r = (r >> 1) ^ (kCrcPoly & ((UInt32)0 - (r & 1))); p->crc[i] = r; } } -static void MatchFinder_FreeThisClassMemory(CMatchFinder *p, ISzAlloc *alloc) +static void MatchFinder_FreeThisClassMemory(CMatchFinder *p, ISzAllocPtr alloc) { - alloc->Free(alloc, p->hash); + ISzAlloc_Free(alloc, p->hash); p->hash = NULL; } -void MatchFinder_Free(CMatchFinder *p, ISzAlloc *alloc) +void MatchFinder_Free(CMatchFinder *p, ISzAllocPtr alloc) { MatchFinder_FreeThisClassMemory(p, alloc); LzInWindow_Free(p, alloc); } -static CLzRef* AllocRefs(size_t num, ISzAlloc *alloc) +static CLzRef* AllocRefs(size_t num, ISzAllocPtr alloc) { size_t sizeInBytes = (size_t)num * sizeof(CLzRef); if (sizeInBytes / sizeof(CLzRef) != num) return NULL; - return (CLzRef *)alloc->Alloc(alloc, sizeInBytes); + return (CLzRef *)ISzAlloc_Alloc(alloc, sizeInBytes); } int MatchFinder_Create(CMatchFinder *p, UInt32 historySize, UInt32 keepAddBufferBefore, UInt32 matchMaxLen, UInt32 keepAddBufferAfter, - ISzAlloc *alloc) + ISzAllocPtr alloc) { UInt32 sizeReserv; @@ -208,7 +209,11 @@ int MatchFinder_Create(CMatchFinder *p, UInt32 historySize, hs = (1 << 16) - 1; else { - hs = historySize - 1; + hs = historySize; + if (hs > p->expectedDataSize) + hs = (UInt32)p->expectedDataSize; + if (hs != 0) + hs--; hs |= (hs >> 1); hs |= (hs >> 2); hs |= (hs >> 4); @@ -292,17 +297,33 @@ static void MatchFinder_SetLimits(CMatchFinder *p) p->posLimit = p->pos + limit; } -void MatchFinder_Init_2(CMatchFinder *p, int readData) + +void MatchFinder_Init_LowHash(CMatchFinder *p) +{ + size_t i; + CLzRef *items = p->hash; + size_t numItems = p->fixedHashSize; + for (i = 0; i < numItems; i++) + items[i] = kEmptyHashValue; +} + + +void MatchFinder_Init_HighHash(CMatchFinder *p) +{ + size_t i; + CLzRef *items = p->hash + p->fixedHashSize; + size_t numItems = (size_t)p->hashMask + 1; + for (i = 0; i < numItems; i++) + items[i] = kEmptyHashValue; +} + + +void MatchFinder_Init_3(CMatchFinder *p, int readData) { - UInt32 i; - UInt32 *hash = p->hash; - UInt32 num = p->hashSizeSum; - for (i = 0; i < num; i++) - hash[i] = kEmptyHashValue; - p->cyclicBufferPos = 0; p->buffer = p->bufferBase; - p->pos = p->streamPos = p->cyclicBufferSize; + p->pos = + p->streamPos = p->cyclicBufferSize; p->result = SZ_OK; p->streamEndWasReached = 0; @@ -312,10 +333,14 @@ void MatchFinder_Init_2(CMatchFinder *p, int readData) MatchFinder_SetLimits(p); } + void MatchFinder_Init(CMatchFinder *p) { - MatchFinder_Init_2(p, True); + MatchFinder_Init_HighHash(p); + MatchFinder_Init_LowHash(p); + MatchFinder_Init_3(p, True); } + static UInt32 MatchFinder_GetSubValue(CMatchFinder *p) { @@ -343,6 +368,8 @@ static void MatchFinder_Normalize(CMatchFinder *p) MatchFinder_ReduceOffsets(p, subValue); } + +MY_NO_INLINE static void MatchFinder_CheckLimits(CMatchFinder *p) { if (p->pos == kMaxValForNormalize) @@ -354,10 +381,16 @@ static void MatchFinder_CheckLimits(CMatchFinder *p) MatchFinder_SetLimits(p); } -static UInt32 * Hc_GetMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byte *cur, CLzRef *son, + +/* + (lenLimit > maxLen) +*/ +MY_FORCE_INLINE +static UInt32 * Hc_GetMatchesSpec(unsigned lenLimit, UInt32 curMatch, UInt32 pos, const Byte *cur, CLzRef *son, UInt32 _cyclicBufferPos, UInt32 _cyclicBufferSize, UInt32 cutValue, - UInt32 *distances, UInt32 maxLen) + UInt32 *distances, unsigned maxLen) { + /* son[_cyclicBufferPos] = curMatch; for (;;) { @@ -375,7 +408,8 @@ static UInt32 * Hc_GetMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, break; if (maxLen < len) { - *distances++ = maxLen = len; + maxLen = len; + *distances++ = len; *distances++ = delta - 1; if (len == lenLimit) return distances; @@ -383,15 +417,58 @@ static UInt32 * Hc_GetMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, } } } + */ + + const Byte *lim = cur + lenLimit; + son[_cyclicBufferPos] = curMatch; + do + { + UInt32 delta = pos - curMatch; + if (delta >= _cyclicBufferSize) + break; + { + ptrdiff_t diff; + curMatch = son[_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)]; + diff = (ptrdiff_t)0 - delta; + if (cur[maxLen] == cur[maxLen + diff]) + { + const Byte *c = cur; + while (*c == c[diff]) + { + if (++c == lim) + { + distances[0] = (UInt32)(lim - cur); + distances[1] = delta - 1; + return distances + 2; + } + } + { + unsigned len = (unsigned)(c - cur); + if (maxLen < len) + { + maxLen = len; + distances[0] = (UInt32)len; + distances[1] = delta - 1; + distances += 2; + } + } + } + } + } + while (--cutValue); + + return distances; } + +MY_FORCE_INLINE UInt32 * GetMatchesSpec1(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byte *cur, CLzRef *son, UInt32 _cyclicBufferPos, UInt32 _cyclicBufferSize, UInt32 cutValue, UInt32 *distances, UInt32 maxLen) { - CLzRef *ptr0 = son + (_cyclicBufferPos << 1) + 1; - CLzRef *ptr1 = son + (_cyclicBufferPos << 1); - UInt32 len0 = 0, len1 = 0; + CLzRef *ptr0 = son + ((size_t)_cyclicBufferPos << 1) + 1; + CLzRef *ptr1 = son + ((size_t)_cyclicBufferPos << 1); + unsigned len0 = 0, len1 = 0; for (;;) { UInt32 delta = pos - curMatch; @@ -401,9 +478,10 @@ UInt32 * GetMatchesSpec1(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byt return distances; } { - CLzRef *pair = son + ((_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)) << 1); + CLzRef *pair = son + ((size_t)(_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)) << 1); const Byte *pb = cur - delta; - UInt32 len = (len0 < len1 ? len0 : len1); + unsigned len = (len0 < len1 ? len0 : len1); + UInt32 pair0 = pair[0]; if (pb[len] == cur[len]) { if (++len != lenLimit && pb[len] == cur[len]) @@ -412,11 +490,12 @@ UInt32 * GetMatchesSpec1(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byt break; if (maxLen < len) { - *distances++ = maxLen = len; + maxLen = (UInt32)len; + *distances++ = (UInt32)len; *distances++ = delta - 1; if (len == lenLimit) { - *ptr1 = pair[0]; + *ptr1 = pair0; *ptr0 = pair[1]; return distances; } @@ -443,9 +522,9 @@ UInt32 * GetMatchesSpec1(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byt static void SkipMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byte *cur, CLzRef *son, UInt32 _cyclicBufferPos, UInt32 _cyclicBufferSize, UInt32 cutValue) { - CLzRef *ptr0 = son + (_cyclicBufferPos << 1) + 1; - CLzRef *ptr1 = son + (_cyclicBufferPos << 1); - UInt32 len0 = 0, len1 = 0; + CLzRef *ptr0 = son + ((size_t)_cyclicBufferPos << 1) + 1; + CLzRef *ptr1 = son + ((size_t)_cyclicBufferPos << 1); + unsigned len0 = 0, len1 = 0; for (;;) { UInt32 delta = pos - curMatch; @@ -455,9 +534,9 @@ static void SkipMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const return; } { - CLzRef *pair = son + ((_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)) << 1); + CLzRef *pair = son + ((size_t)(_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)) << 1); const Byte *pb = cur - delta; - UInt32 len = (len0 < len1 ? len0 : len1); + unsigned len = (len0 < len1 ? len0 : len1); if (pb[len] == cur[len]) { while (++len != lenLimit) @@ -495,13 +574,13 @@ static void SkipMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const p->buffer++; \ if (++p->pos == p->posLimit) MatchFinder_CheckLimits(p); -#define MOVE_POS_RET MOVE_POS return offset; +#define MOVE_POS_RET MOVE_POS return (UInt32)offset; static void MatchFinder_MovePos(CMatchFinder *p) { MOVE_POS; } #define GET_MATCHES_HEADER2(minLen, ret_op) \ - UInt32 lenLimit; UInt32 hv; const Byte *cur; UInt32 curMatch; \ - lenLimit = p->lenLimit; { if (lenLimit < minLen) { MatchFinder_MovePos(p); ret_op; }} \ + unsigned lenLimit; UInt32 hv; const Byte *cur; UInt32 curMatch; \ + lenLimit = (unsigned)p->lenLimit; { if (lenLimit < minLen) { MatchFinder_MovePos(p); ret_op; }} \ cur = p->buffer; #define GET_MATCHES_HEADER(minLen) GET_MATCHES_HEADER2(minLen, return 0) @@ -510,22 +589,22 @@ static void MatchFinder_MovePos(CMatchFinder *p) { MOVE_POS; } #define MF_PARAMS(p) p->pos, p->buffer, p->son, p->cyclicBufferPos, p->cyclicBufferSize, p->cutValue #define GET_MATCHES_FOOTER(offset, maxLen) \ - offset = (UInt32)(GetMatchesSpec1(lenLimit, curMatch, MF_PARAMS(p), \ - distances + offset, maxLen) - distances); MOVE_POS_RET; + offset = (unsigned)(GetMatchesSpec1((UInt32)lenLimit, curMatch, MF_PARAMS(p), \ + distances + offset, (UInt32)maxLen) - distances); MOVE_POS_RET; #define SKIP_FOOTER \ - SkipMatchesSpec(lenLimit, curMatch, MF_PARAMS(p)); MOVE_POS; + SkipMatchesSpec((UInt32)lenLimit, curMatch, MF_PARAMS(p)); MOVE_POS; #define UPDATE_maxLen { \ ptrdiff_t diff = (ptrdiff_t)0 - d2; \ const Byte *c = cur + maxLen; \ const Byte *lim = cur + lenLimit; \ for (; c != lim; c++) if (*(c + diff) != *c) break; \ - maxLen = (UInt32)(c - cur); } + maxLen = (unsigned)(c - cur); } static UInt32 Bt2_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) { - UInt32 offset; + unsigned offset; GET_MATCHES_HEADER(2) HASH2_CALC; curMatch = p->hash[hv]; @@ -536,7 +615,7 @@ static UInt32 Bt2_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) UInt32 Bt3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) { - UInt32 offset; + unsigned offset; GET_MATCHES_HEADER(3) HASH_ZIP_CALC; curMatch = p->hash[hv]; @@ -547,7 +626,8 @@ UInt32 Bt3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) static UInt32 Bt3_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) { - UInt32 h2, d2, maxLen, offset, pos; + UInt32 h2, d2, pos; + unsigned maxLen, offset; UInt32 *hash; GET_MATCHES_HEADER(3) @@ -558,10 +638,10 @@ static UInt32 Bt3_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) d2 = pos - hash[h2]; - curMatch = hash[kFix3HashSize + hv]; + curMatch = (hash + kFix3HashSize)[hv]; hash[h2] = pos; - hash[kFix3HashSize + hv] = pos; + (hash + kFix3HashSize)[hv] = pos; maxLen = 2; offset = 0; @@ -569,12 +649,12 @@ static UInt32 Bt3_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) if (d2 < p->cyclicBufferSize && *(cur - d2) == *cur) { UPDATE_maxLen - distances[0] = maxLen; + distances[0] = (UInt32)maxLen; distances[1] = d2 - 1; offset = 2; if (maxLen == lenLimit) { - SkipMatchesSpec(lenLimit, curMatch, MF_PARAMS(p)); + SkipMatchesSpec((UInt32)lenLimit, curMatch, MF_PARAMS(p)); MOVE_POS_RET; } } @@ -584,7 +664,8 @@ static UInt32 Bt3_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) static UInt32 Bt4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) { - UInt32 h2, h3, d2, d3, maxLen, offset, pos; + UInt32 h2, h3, d2, d3, pos; + unsigned maxLen, offset; UInt32 *hash; GET_MATCHES_HEADER(4) @@ -593,21 +674,22 @@ static UInt32 Bt4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) hash = p->hash; pos = p->pos; - d2 = pos - hash[ h2]; - d3 = pos - hash[kFix3HashSize + h3]; + d2 = pos - hash [h2]; + d3 = pos - (hash + kFix3HashSize)[h3]; - curMatch = hash[kFix4HashSize + hv]; + curMatch = (hash + kFix4HashSize)[hv]; - hash[ h2] = pos; - hash[kFix3HashSize + h3] = pos; - hash[kFix4HashSize + hv] = pos; + hash [h2] = pos; + (hash + kFix3HashSize)[h3] = pos; + (hash + kFix4HashSize)[hv] = pos; maxLen = 0; offset = 0; if (d2 < p->cyclicBufferSize && *(cur - d2) == *cur) { - distances[0] = maxLen = 2; + maxLen = 2; + distances[0] = 2; distances[1] = d2 - 1; offset = 2; } @@ -615,7 +697,7 @@ static UInt32 Bt4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) if (d2 != d3 && d3 < p->cyclicBufferSize && *(cur - d3) == *cur) { maxLen = 3; - distances[offset + 1] = d3 - 1; + distances[(size_t)offset + 1] = d3 - 1; offset += 2; d2 = d3; } @@ -623,10 +705,10 @@ static UInt32 Bt4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) if (offset != 0) { UPDATE_maxLen - distances[offset - 2] = maxLen; + distances[(size_t)offset - 2] = (UInt32)maxLen; if (maxLen == lenLimit) { - SkipMatchesSpec(lenLimit, curMatch, MF_PARAMS(p)); + SkipMatchesSpec((UInt32)lenLimit, curMatch, MF_PARAMS(p)); MOVE_POS_RET; } } @@ -649,16 +731,16 @@ static UInt32 Bt5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) hash = p->hash; pos = p->pos; - d2 = pos - hash[ h2]; - d3 = pos - hash[kFix3HashSize + h3]; - d4 = pos - hash[kFix4HashSize + h4]; + d2 = pos - hash [h2]; + d3 = pos - (hash + kFix3HashSize)[h3]; + d4 = pos - (hash + kFix4HashSize)[h4]; - curMatch = hash[kFix5HashSize + hv]; + curMatch = (hash + kFix5HashSize)[hv]; - hash[ h2] = pos; - hash[kFix3HashSize + h3] = pos; - hash[kFix4HashSize + h4] = pos; - hash[kFix5HashSize + hv] = pos; + hash [h2] = pos; + (hash + kFix3HashSize)[h3] = pos; + (hash + kFix4HashSize)[h4] = pos; + (hash + kFix5HashSize)[hv] = pos; maxLen = 0; offset = 0; @@ -691,7 +773,7 @@ static UInt32 Bt5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) && *(cur - d4 + 3) == *(cur + 3)) { maxLen = 4; - distances[offset + 1] = d4 - 1; + distances[(size_t)offset + 1] = d4 - 1; offset += 2; d2 = d4; } @@ -699,7 +781,7 @@ static UInt32 Bt5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) if (offset != 0) { UPDATE_maxLen - distances[offset - 2] = maxLen; + distances[(size_t)offset - 2] = maxLen; if (maxLen == lenLimit) { SkipMatchesSpec(lenLimit, curMatch, MF_PARAMS(p)); @@ -716,7 +798,8 @@ static UInt32 Bt5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) static UInt32 Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) { - UInt32 h2, h3, d2, d3, maxLen, offset, pos; + UInt32 h2, h3, d2, d3, pos; + unsigned maxLen, offset; UInt32 *hash; GET_MATCHES_HEADER(4) @@ -725,21 +808,21 @@ static UInt32 Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) hash = p->hash; pos = p->pos; - d2 = pos - hash[ h2]; - d3 = pos - hash[kFix3HashSize + h3]; - - curMatch = hash[kFix4HashSize + hv]; + d2 = pos - hash [h2]; + d3 = pos - (hash + kFix3HashSize)[h3]; + curMatch = (hash + kFix4HashSize)[hv]; - hash[ h2] = pos; - hash[kFix3HashSize + h3] = pos; - hash[kFix4HashSize + hv] = pos; + hash [h2] = pos; + (hash + kFix3HashSize)[h3] = pos; + (hash + kFix4HashSize)[hv] = pos; maxLen = 0; offset = 0; if (d2 < p->cyclicBufferSize && *(cur - d2) == *cur) { - distances[0] = maxLen = 2; + maxLen = 2; + distances[0] = 2; distances[1] = d2 - 1; offset = 2; } @@ -747,7 +830,7 @@ static UInt32 Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) if (d2 != d3 && d3 < p->cyclicBufferSize && *(cur - d3) == *cur) { maxLen = 3; - distances[offset + 1] = d3 - 1; + distances[(size_t)offset + 1] = d3 - 1; offset += 2; d2 = d3; } @@ -755,7 +838,7 @@ static UInt32 Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) if (offset != 0) { UPDATE_maxLen - distances[offset - 2] = maxLen; + distances[(size_t)offset - 2] = (UInt32)maxLen; if (maxLen == lenLimit) { p->son[p->cyclicBufferPos] = curMatch; @@ -766,7 +849,7 @@ static UInt32 Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) if (maxLen < 3) maxLen = 3; - offset = (UInt32)(Hc_GetMatchesSpec(lenLimit, curMatch, MF_PARAMS(p), + offset = (unsigned)(Hc_GetMatchesSpec(lenLimit, curMatch, MF_PARAMS(p), distances + offset, maxLen) - (distances)); MOVE_POS_RET } @@ -783,16 +866,16 @@ static UInt32 Hc5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) hash = p->hash; pos = p->pos; - d2 = pos - hash[ h2]; - d3 = pos - hash[kFix3HashSize + h3]; - d4 = pos - hash[kFix4HashSize + h4]; + d2 = pos - hash [h2]; + d3 = pos - (hash + kFix3HashSize)[h3]; + d4 = pos - (hash + kFix4HashSize)[h4]; - curMatch = hash[kFix5HashSize + hv]; + curMatch = (hash + kFix5HashSize)[hv]; - hash[ h2] = pos; - hash[kFix3HashSize + h3] = pos; - hash[kFix4HashSize + h4] = pos; - hash[kFix5HashSize + hv] = pos; + hash [h2] = pos; + (hash + kFix3HashSize)[h3] = pos; + (hash + kFix4HashSize)[h4] = pos; + (hash + kFix5HashSize)[hv] = pos; maxLen = 0; offset = 0; @@ -825,7 +908,7 @@ static UInt32 Hc5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) && *(cur - d4 + 3) == *(cur + 3)) { maxLen = 4; - distances[offset + 1] = d4 - 1; + distances[(size_t)offset + 1] = d4 - 1; offset += 2; d2 = d4; } @@ -833,7 +916,7 @@ static UInt32 Hc5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) if (offset != 0) { UPDATE_maxLen - distances[offset - 2] = maxLen; + distances[(size_t)offset - 2] = maxLen; if (maxLen == lenLimit) { p->son[p->cyclicBufferPos] = curMatch; @@ -852,12 +935,12 @@ static UInt32 Hc5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) UInt32 Hc3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) { - UInt32 offset; + unsigned offset; GET_MATCHES_HEADER(3) HASH_ZIP_CALC; curMatch = p->hash[hv]; p->hash[hv] = p->pos; - offset = (UInt32)(Hc_GetMatchesSpec(lenLimit, curMatch, MF_PARAMS(p), + offset = (unsigned)(Hc_GetMatchesSpec(lenLimit, curMatch, MF_PARAMS(p), distances, 2) - (distances)); MOVE_POS_RET } @@ -897,9 +980,9 @@ static void Bt3_MatchFinder_Skip(CMatchFinder *p, UInt32 num) SKIP_HEADER(3) HASH3_CALC; hash = p->hash; - curMatch = hash[kFix3HashSize + hv]; + curMatch = (hash + kFix3HashSize)[hv]; hash[h2] = - hash[kFix3HashSize + hv] = p->pos; + (hash + kFix3HashSize)[hv] = p->pos; SKIP_FOOTER } while (--num != 0); @@ -914,10 +997,10 @@ static void Bt4_MatchFinder_Skip(CMatchFinder *p, UInt32 num) SKIP_HEADER(4) HASH4_CALC; hash = p->hash; - curMatch = hash[kFix4HashSize + hv]; - hash[ h2] = - hash[kFix3HashSize + h3] = - hash[kFix4HashSize + hv] = p->pos; + curMatch = (hash + kFix4HashSize)[hv]; + hash [h2] = + (hash + kFix3HashSize)[h3] = + (hash + kFix4HashSize)[hv] = p->pos; SKIP_FOOTER } while (--num != 0); @@ -933,11 +1016,11 @@ static void Bt5_MatchFinder_Skip(CMatchFinder *p, UInt32 num) SKIP_HEADER(5) HASH5_CALC; hash = p->hash; - curMatch = hash[kFix5HashSize + hv]; - hash[ h2] = - hash[kFix3HashSize + h3] = - hash[kFix4HashSize + h4] = - hash[kFix5HashSize + hv] = p->pos; + curMatch = (hash + kFix5HashSize)[hv]; + hash [h2] = + (hash + kFix3HashSize)[h3] = + (hash + kFix4HashSize)[h4] = + (hash + kFix5HashSize)[hv] = p->pos; SKIP_FOOTER } while (--num != 0); @@ -953,10 +1036,10 @@ static void Hc4_MatchFinder_Skip(CMatchFinder *p, UInt32 num) SKIP_HEADER(4) HASH4_CALC; hash = p->hash; - curMatch = hash[kFix4HashSize + hv]; - hash[ h2] = - hash[kFix3HashSize + h3] = - hash[kFix4HashSize + hv] = p->pos; + curMatch = (hash + kFix4HashSize)[hv]; + hash [h2] = + (hash + kFix3HashSize)[h3] = + (hash + kFix4HashSize)[hv] = p->pos; p->son[p->cyclicBufferPos] = curMatch; MOVE_POS } @@ -973,11 +1056,11 @@ static void Hc5_MatchFinder_Skip(CMatchFinder *p, UInt32 num) SKIP_HEADER(5) HASH5_CALC; hash = p->hash; - curMatch = p->hash[kFix5HashSize + hv]; - hash[ h2] = - hash[kFix3HashSize + h3] = - hash[kFix4HashSize + h4] = - hash[kFix5HashSize + hv] = p->pos; + curMatch = hash + kFix5HashSize)[hv]; + hash [h2] = + (hash + kFix3HashSize)[h3] = + (hash + kFix4HashSize)[h4] = + (hash + kFix5HashSize)[hv] = p->pos; p->son[p->cyclicBufferPos] = curMatch; MOVE_POS } diff --git a/uppsrc/plugin/lzma/lib/LzFind.h b/uppsrc/plugin/lzma/lib/LzFind.h index 2ff667377..c77added7 100644 --- a/uppsrc/plugin/lzma/lib/LzFind.h +++ b/uppsrc/plugin/lzma/lib/LzFind.h @@ -1,5 +1,5 @@ /* LzFind.h -- Match finder for LZ algorithms -2015-10-15 : Igor Pavlov : Public domain */ +2017-06-10 : Igor Pavlov : Public domain */ #ifndef __LZ_FIND_H #define __LZ_FIND_H @@ -47,6 +47,8 @@ typedef struct _CMatchFinder SRes result; UInt32 crc[256]; size_t numRefs; + + UInt64 expectedDataSize; } CMatchFinder; #define Inline_MatchFinder_GetPointerToCurrentPos(p) ((p)->buffer) @@ -71,8 +73,8 @@ void MatchFinder_Construct(CMatchFinder *p); */ int MatchFinder_Create(CMatchFinder *p, UInt32 historySize, UInt32 keepAddBufferBefore, UInt32 matchMaxLen, UInt32 keepAddBufferAfter, - ISzAlloc *alloc); -void MatchFinder_Free(CMatchFinder *p, ISzAlloc *alloc); + ISzAllocPtr alloc); +void MatchFinder_Free(CMatchFinder *p, ISzAllocPtr alloc); void MatchFinder_Normalize3(UInt32 subValue, CLzRef *items, size_t numItems); void MatchFinder_ReduceOffsets(CMatchFinder *p, UInt32 subValue); @@ -103,7 +105,9 @@ typedef struct _IMatchFinder void MatchFinder_CreateVTable(CMatchFinder *p, IMatchFinder *vTable); -void MatchFinder_Init_2(CMatchFinder *p, int readData); +void MatchFinder_Init_LowHash(CMatchFinder *p); +void MatchFinder_Init_HighHash(CMatchFinder *p); +void MatchFinder_Init_3(CMatchFinder *p, int readData); void MatchFinder_Init(CMatchFinder *p); UInt32 Bt3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances); diff --git a/uppsrc/plugin/lzma/lib/LzmaDec.c b/uppsrc/plugin/lzma/lib/LzmaDec.c index 64f1164f3..4d1576419 100644 --- a/uppsrc/plugin/lzma/lib/LzmaDec.c +++ b/uppsrc/plugin/lzma/lib/LzmaDec.c @@ -1,12 +1,13 @@ /* LzmaDec.c -- LZMA Decoder -2016-05-16 : Igor Pavlov : Public domain */ +2018-07-04 : Igor Pavlov : Public domain */ #include "Precomp.h" -#include "LzmaDec.h" - #include +/* #include "CpuArch.h" */ +#include "LzmaDec.h" + #define kNumTopBits 24 #define kTopValue ((UInt32)1 << kNumTopBits) @@ -18,15 +19,22 @@ #define NORMALIZE if (range < kTopValue) { range <<= 8; code = (code << 8) | (*buf++); } -#define IF_BIT_0(p) ttt = *(p); NORMALIZE; bound = (range >> kNumBitModelTotalBits) * ttt; if (code < bound) +#define IF_BIT_0(p) ttt = *(p); NORMALIZE; bound = (range >> kNumBitModelTotalBits) * (UInt32)ttt; if (code < bound) #define UPDATE_0(p) range = bound; *(p) = (CLzmaProb)(ttt + ((kBitModelTotal - ttt) >> kNumMoveBits)); #define UPDATE_1(p) range -= bound; code -= bound; *(p) = (CLzmaProb)(ttt - (ttt >> kNumMoveBits)); #define GET_BIT2(p, i, A0, A1) IF_BIT_0(p) \ { UPDATE_0(p); i = (i + i); A0; } else \ { UPDATE_1(p); i = (i + i) + 1; A1; } -#define GET_BIT(p, i) GET_BIT2(p, i, ; , ;) -#define TREE_GET_BIT(probs, i) { GET_BIT((probs + i), i); } +#define TREE_GET_BIT(probs, i) { GET_BIT2(probs + i, i, ;, ;); } + +#define REV_BIT(p, i, A0, A1) IF_BIT_0(p + i) \ + { UPDATE_0(p + i); A0; } else \ + { UPDATE_1(p + i); A1; } +#define REV_BIT_VAR( p, i, m) REV_BIT(p, i, i += m; m += m, m += m; i += m; ) +#define REV_BIT_CONST(p, i, m) REV_BIT(p, i, i += m; , i += m * 2; ) +#define REV_BIT_LAST( p, i, m) REV_BIT(p, i, i -= m , ; ) + #define TREE_DECODE(probs, limit, i) \ { i = 1; do { TREE_GET_BIT(probs, i); } while (i < limit); i -= limit; } @@ -46,16 +54,19 @@ i -= 0x40; } #endif -#define NORMAL_LITER_DEC GET_BIT(prob + symbol, symbol) +#define NORMAL_LITER_DEC TREE_GET_BIT(prob, symbol) #define MATCHED_LITER_DEC \ - matchByte <<= 1; \ - bit = (matchByte & offs); \ - probLit = prob + offs + bit + symbol; \ - GET_BIT2(probLit, symbol, offs &= ~bit, offs &= bit) + matchByte += matchByte; \ + bit = offs; \ + offs &= matchByte; \ + probLit = prob + (offs + bit + symbol); \ + GET_BIT2(probLit, symbol, offs ^= bit; , ;) + + #define NORMALIZE_CHECK if (range < kTopValue) { if (buf >= bufLimit) return DUMMY_ERROR; range <<= 8; code = (code << 8) | (*buf++); } -#define IF_BIT_0_CHECK(p) ttt = *(p); NORMALIZE_CHECK; bound = (range >> kNumBitModelTotalBits) * ttt; if (code < bound) +#define IF_BIT_0_CHECK(p) ttt = *(p); NORMALIZE_CHECK; bound = (range >> kNumBitModelTotalBits) * (UInt32)ttt; if (code < bound) #define UPDATE_0_CHECK range = bound; #define UPDATE_1_CHECK range -= bound; code -= bound; #define GET_BIT2_CHECK(p, i, A0, A1) IF_BIT_0_CHECK(p) \ @@ -66,25 +77,28 @@ { i = 1; do { GET_BIT_CHECK(probs + i, i) } while (i < limit); i -= limit; } +#define REV_BIT_CHECK(p, i, m) IF_BIT_0_CHECK(p + i) \ + { UPDATE_0_CHECK; i += m; m += m; } else \ + { UPDATE_1_CHECK; m += m; i += m; } + + #define kNumPosBitsMax 4 #define kNumPosStatesMax (1 << kNumPosBitsMax) #define kLenNumLowBits 3 #define kLenNumLowSymbols (1 << kLenNumLowBits) -#define kLenNumMidBits 3 -#define kLenNumMidSymbols (1 << kLenNumMidBits) #define kLenNumHighBits 8 #define kLenNumHighSymbols (1 << kLenNumHighBits) -#define LenChoice 0 -#define LenChoice2 (LenChoice + 1) -#define LenLow (LenChoice2 + 1) -#define LenMid (LenLow + (kNumPosStatesMax << kLenNumLowBits)) -#define LenHigh (LenMid + (kNumPosStatesMax << kLenNumMidBits)) +#define LenLow 0 +#define LenHigh (LenLow + 2 * (kNumPosStatesMax << kLenNumLowBits)) #define kNumLenProbs (LenHigh + kLenNumHighSymbols) +#define LenChoice LenLow +#define LenChoice2 (LenLow + (1 << kLenNumLowBits)) #define kNumStates 12 +#define kNumStates2 16 #define kNumLitStates 7 #define kStartPosModelIndex 4 @@ -98,54 +112,117 @@ #define kAlignTableSize (1 << kNumAlignBits) #define kMatchMinLen 2 -#define kMatchSpecLenStart (kMatchMinLen + kLenNumLowSymbols + kLenNumMidSymbols + kLenNumHighSymbols) +#define kMatchSpecLenStart (kMatchMinLen + kLenNumLowSymbols * 2 + kLenNumHighSymbols) -#define IsMatch 0 -#define IsRep (IsMatch + (kNumStates << kNumPosBitsMax)) +/* External ASM code needs same CLzmaProb array layout. So don't change it. */ + +/* (probs_1664) is faster and better for code size at some platforms */ +/* +#ifdef MY_CPU_X86_OR_AMD64 +*/ +#define kStartOffset 1664 +#define GET_PROBS p->probs_1664 +/* +#define GET_PROBS p->probs + kStartOffset +#else +#define kStartOffset 0 +#define GET_PROBS p->probs +#endif +*/ + +#define SpecPos (-kStartOffset) +#define IsRep0Long (SpecPos + kNumFullDistances) +#define RepLenCoder (IsRep0Long + (kNumStates2 << kNumPosBitsMax)) +#define LenCoder (RepLenCoder + kNumLenProbs) +#define IsMatch (LenCoder + kNumLenProbs) +#define Align (IsMatch + (kNumStates2 << kNumPosBitsMax)) +#define IsRep (Align + kAlignTableSize) #define IsRepG0 (IsRep + kNumStates) #define IsRepG1 (IsRepG0 + kNumStates) #define IsRepG2 (IsRepG1 + kNumStates) -#define IsRep0Long (IsRepG2 + kNumStates) -#define PosSlot (IsRep0Long + (kNumStates << kNumPosBitsMax)) -#define SpecPos (PosSlot + (kNumLenToPosStates << kNumPosSlotBits)) -#define Align (SpecPos + kNumFullDistances - kEndPosModelIndex) -#define LenCoder (Align + kAlignTableSize) -#define RepLenCoder (LenCoder + kNumLenProbs) -#define Literal (RepLenCoder + kNumLenProbs) +#define PosSlot (IsRepG2 + kNumStates) +#define Literal (PosSlot + (kNumLenToPosStates << kNumPosSlotBits)) +#define NUM_BASE_PROBS (Literal + kStartOffset) -#define LZMA_BASE_SIZE 1846 -#define LZMA_LIT_SIZE 0x300 - -#if Literal != LZMA_BASE_SIZE -StopCompilingDueBUG +#if Align != 0 && kStartOffset != 0 + #error Stop_Compiling_Bad_LZMA_kAlign #endif -#define LzmaProps_GetNumProbs(p) (Literal + ((UInt32)LZMA_LIT_SIZE << ((p)->lc + (p)->lp))) +#if NUM_BASE_PROBS != 1984 + #error Stop_Compiling_Bad_LZMA_PROBS +#endif + + +#define LZMA_LIT_SIZE 0x300 + +#define LzmaProps_GetNumProbs(p) (NUM_BASE_PROBS + ((UInt32)LZMA_LIT_SIZE << ((p)->lc + (p)->lp))) + + +#define CALC_POS_STATE(processedPos, pbMask) (((processedPos) & (pbMask)) << 4) +#define COMBINED_PS_STATE (posState + state) +#define GET_LEN_STATE (posState) #define LZMA_DIC_MIN (1 << 12) -/* First LZMA-symbol is always decoded. -And it decodes new LZMA-symbols while (buf < bufLimit), but "buf" is without last normalization +/* +p->remainLen : shows status of LZMA decoder: + < kMatchSpecLenStart : normal remain + = kMatchSpecLenStart : finished + = kMatchSpecLenStart + 1 : need init range coder + = kMatchSpecLenStart + 2 : need init range coder and state +*/ + +/* ---------- LZMA_DECODE_REAL ---------- */ +/* +LzmaDec_DecodeReal_3() can be implemented in external ASM file. +3 - is the code compatibility version of that function for check at link time. +*/ + +#define LZMA_DECODE_REAL LzmaDec_DecodeReal_3 + +/* +LZMA_DECODE_REAL() +In: + RangeCoder is normalized + if (p->dicPos == limit) + { + LzmaDec_TryDummy() was called before to exclude LITERAL and MATCH-REP cases. + So first symbol can be only MATCH-NON-REP. And if that MATCH-NON-REP symbol + is not END_OF_PAYALOAD_MARKER, then function returns error code. + } + +Processing: + first LZMA symbol will be decoded in any case + All checks for limits are at the end of main loop, + It will decode new LZMA-symbols while (p->buf < bufLimit && dicPos < limit), + RangeCoder is still without last normalization when (p->buf < bufLimit) is being checked. + Out: + RangeCoder is normalized Result: SZ_OK - OK SZ_ERROR_DATA - Error p->remainLen: < kMatchSpecLenStart : normal remain = kMatchSpecLenStart : finished - = kMatchSpecLenStart + 1 : Flush marker (unused now) - = kMatchSpecLenStart + 2 : State Init Marker (unused now) */ -static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte *bufLimit) -{ - CLzmaProb *probs = p->probs; - unsigned state = p->state; +#ifdef _LZMA_DEC_OPT + +int MY_FAST_CALL LZMA_DECODE_REAL(CLzmaDec *p, SizeT limit, const Byte *bufLimit); + +#else + +static +int MY_FAST_CALL LZMA_DECODE_REAL(CLzmaDec *p, SizeT limit, const Byte *bufLimit) +{ + CLzmaProb *probs = GET_PROBS; + unsigned state = (unsigned)p->state; UInt32 rep0 = p->reps[0], rep1 = p->reps[1], rep2 = p->reps[2], rep3 = p->reps[3]; unsigned pbMask = ((unsigned)1 << (p->prop.pb)) - 1; - unsigned lpMask = ((unsigned)1 << (p->prop.lp)) - 1; unsigned lc = p->prop.lc; + unsigned lpMask = ((unsigned)0x100 << p->prop.lp) - ((unsigned)0x100 >> lc); Byte *dic = p->dic; SizeT dicBufSize = p->dicBufSize; @@ -164,17 +241,16 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte CLzmaProb *prob; UInt32 bound; unsigned ttt; - unsigned posState = processedPos & pbMask; + unsigned posState = CALC_POS_STATE(processedPos, pbMask); - prob = probs + IsMatch + (state << kNumPosBitsMax) + posState; + prob = probs + IsMatch + COMBINED_PS_STATE; IF_BIT_0(prob) { unsigned symbol; UPDATE_0(prob); prob = probs + Literal; if (processedPos != 0 || checkDicSize != 0) - prob += ((UInt32)LZMA_LIT_SIZE * (((processedPos & lpMask) << lc) + - (dic[(dicPos == 0 ? dicBufSize : dicPos) - 1] >> (8 - lc)))); + prob += (UInt32)3 * ((((processedPos << 8) + dic[(dicPos == 0 ? dicBufSize : dicPos) - 1]) & lpMask) << lc); processedPos++; if (state < kNumLitStates) @@ -240,13 +316,16 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte else { UPDATE_1(prob); + /* + // that case was checked before with kBadRepCode if (checkDicSize == 0 && processedPos == 0) return SZ_ERROR_DATA; + */ prob = probs + IsRepG0 + state; IF_BIT_0(prob) { UPDATE_0(prob); - prob = probs + IsRep0Long + (state << kNumPosBitsMax) + posState; + prob = probs + IsRep0Long + COMBINED_PS_STATE; IF_BIT_0(prob) { UPDATE_0(prob); @@ -299,7 +378,7 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte IF_BIT_0(probLen) { UPDATE_0(probLen); - probLen = prob + LenLow + (posState << kLenNumLowBits); + probLen = prob + LenLow + GET_LEN_STATE; offset = 0; lim = (1 << kLenNumLowBits); } @@ -310,15 +389,15 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte IF_BIT_0(probLen) { UPDATE_0(probLen); - probLen = prob + LenMid + (posState << kLenNumMidBits); + probLen = prob + LenLow + GET_LEN_STATE + (1 << kLenNumLowBits); offset = kLenNumLowSymbols; - lim = (1 << kLenNumMidBits); + lim = (1 << kLenNumLowBits); } else { UPDATE_1(probLen); probLen = prob + LenHigh; - offset = kLenNumLowSymbols + kLenNumMidSymbols; + offset = kLenNumLowSymbols * 2; lim = (1 << kLenNumHighBits); } } @@ -331,7 +410,7 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte IF_BIT_0(probLen) { UPDATE_0(probLen); - probLen = prob + LenLow + (posState << kLenNumLowBits); + probLen = prob + LenLow + GET_LEN_STATE; len = 1; TREE_GET_BIT(probLen, len); TREE_GET_BIT(probLen, len); @@ -345,7 +424,7 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte IF_BIT_0(probLen) { UPDATE_0(probLen); - probLen = prob + LenMid + (posState << kLenNumMidBits); + probLen = prob + LenLow + GET_LEN_STATE + (1 << kLenNumLowBits); len = 1; TREE_GET_BIT(probLen, len); TREE_GET_BIT(probLen, len); @@ -356,7 +435,7 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte UPDATE_1(probLen); probLen = prob + LenHigh; TREE_DECODE(probLen, (1 << kLenNumHighBits), len); - len += kLenNumLowSymbols + kLenNumMidSymbols; + len += kLenNumLowSymbols * 2; } } } @@ -376,16 +455,16 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte if (posSlot < kEndPosModelIndex) { distance <<= numDirectBits; - prob = probs + SpecPos + distance - posSlot - 1; + prob = probs + SpecPos; { - UInt32 mask = 1; - unsigned i = 1; + UInt32 m = 1; + distance++; do { - GET_BIT2(prob + i, i, ; , distance |= mask); - mask <<= 1; + REV_BIT_VAR(prob, distance, m); } - while (--numDirectBits != 0); + while (--numDirectBits); + distance -= m; } } else @@ -412,19 +491,20 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte } */ } - while (--numDirectBits != 0); + while (--numDirectBits); prob = probs + Align; distance <<= kNumAlignBits; { unsigned i = 1; - GET_BIT2(prob + i, i, ; , distance |= 1); - GET_BIT2(prob + i, i, ; , distance |= 2); - GET_BIT2(prob + i, i, ; , distance |= 4); - GET_BIT2(prob + i, i, ; , distance |= 8); + REV_BIT_CONST(prob, i, 1); + REV_BIT_CONST(prob, i, 2); + REV_BIT_CONST(prob, i, 4); + REV_BIT_LAST (prob, i, 8); + distance |= i; } if (distance == (UInt32)0xFFFFFFFF) { - len += kMatchSpecLenStart; + len = kMatchSpecLenStart; state -= kNumStates; break; } @@ -435,20 +515,12 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte rep2 = rep1; rep1 = rep0; rep0 = distance + 1; - if (checkDicSize == 0) - { - if (distance >= processedPos) - { - p->dicPos = dicPos; - return SZ_ERROR_DATA; - } - } - else if (distance >= checkDicSize) + state = (state < kNumStates + kNumLitStates) ? kNumLitStates : kNumLitStates + 3; + if (distance >= (checkDicSize == 0 ? processedPos: checkDicSize)) { p->dicPos = dicPos; return SZ_ERROR_DATA; } - state = (state < kNumStates + kNumLitStates) ? kNumLitStates : kNumLitStates + 3; } len += kMatchMinLen; @@ -467,7 +539,7 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte curLen = ((rem < len) ? (unsigned)rem : len); pos = dicPos - rep0 + (dicPos < rep0 ? dicBufSize : 0); - processedPos += curLen; + processedPos += (UInt32)curLen; len -= curLen; if (curLen <= dicBufSize - pos) @@ -475,7 +547,7 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte Byte *dest = dic + dicPos; ptrdiff_t src = (ptrdiff_t)pos - (ptrdiff_t)dicPos; const Byte *lim = dest + curLen; - dicPos += curLen; + dicPos += (SizeT)curLen; do *(dest) = (Byte)*(dest + src); while (++dest != lim); @@ -500,17 +572,18 @@ static int MY_FAST_CALL LzmaDec_DecodeReal(CLzmaDec *p, SizeT limit, const Byte p->buf = buf; p->range = range; p->code = code; - p->remainLen = len; + p->remainLen = (UInt32)len; p->dicPos = dicPos; p->processedPos = processedPos; p->reps[0] = rep0; p->reps[1] = rep1; p->reps[2] = rep2; p->reps[3] = rep3; - p->state = state; + p->state = (UInt32)state; return SZ_OK; } +#endif static void MY_FAST_CALL LzmaDec_WriteRem(CLzmaDec *p, SizeT limit) { @@ -519,7 +592,7 @@ static void MY_FAST_CALL LzmaDec_WriteRem(CLzmaDec *p, SizeT limit) Byte *dic = p->dic; SizeT dicPos = p->dicPos; SizeT dicBufSize = p->dicBufSize; - unsigned len = p->remainLen; + unsigned len = (unsigned)p->remainLen; SizeT rep0 = p->reps[0]; /* we use SizeT to avoid the BUG of VC14 for AMD64 */ SizeT rem = limit - dicPos; if (rem < len) @@ -528,8 +601,8 @@ static void MY_FAST_CALL LzmaDec_WriteRem(CLzmaDec *p, SizeT limit) if (p->checkDicSize == 0 && p->prop.dicSize - p->processedPos <= len) p->checkDicSize = p->prop.dicSize; - p->processedPos += len; - p->remainLen -= len; + p->processedPos += (UInt32)len; + p->remainLen -= (UInt32)len; while (len != 0) { len--; @@ -540,6 +613,14 @@ static void MY_FAST_CALL LzmaDec_WriteRem(CLzmaDec *p, SizeT limit) } } + +#define kRange0 0xFFFFFFFF +#define kBound0 ((kRange0 >> kNumBitModelTotalBits) << (kNumBitModelTotalBits - 1)) +#define kBadRepCode (kBound0 + (((kRange0 - kBound0) >> kNumBitModelTotalBits) << (kNumBitModelTotalBits - 1))) +#if kBadRepCode != (0xC0000000 - 0x400) + #error Stop_Compiling_Bad_LZMA_Check +#endif + static int MY_FAST_CALL LzmaDec_DecodeReal2(CLzmaDec *p, SizeT limit, const Byte *bufLimit) { do @@ -550,9 +631,13 @@ static int MY_FAST_CALL LzmaDec_DecodeReal2(CLzmaDec *p, SizeT limit, const Byte UInt32 rem = p->prop.dicSize - p->processedPos; if (limit - p->dicPos > rem) limit2 = p->dicPos + rem; + + if (p->processedPos == 0) + if (p->code >= kBadRepCode) + return SZ_ERROR_DATA; } - - RINOK(LzmaDec_DecodeReal(p, limit2, bufLimit)); + + RINOK(LZMA_DECODE_REAL(p, limit2, bufLimit)); if (p->checkDicSize == 0 && p->processedPos >= p->prop.dicSize) p->checkDicSize = p->prop.dicSize; @@ -561,9 +646,6 @@ static int MY_FAST_CALL LzmaDec_DecodeReal2(CLzmaDec *p, SizeT limit, const Byte } while (p->dicPos < limit && p->buf < bufLimit && p->remainLen < kMatchSpecLenStart); - if (p->remainLen > kMatchSpecLenStart) - p->remainLen = kMatchSpecLenStart; - return 0; } @@ -580,17 +662,17 @@ static ELzmaDummy LzmaDec_TryDummy(const CLzmaDec *p, const Byte *buf, SizeT inS UInt32 range = p->range; UInt32 code = p->code; const Byte *bufLimit = buf + inSize; - const CLzmaProb *probs = p->probs; - unsigned state = p->state; + const CLzmaProb *probs = GET_PROBS; + unsigned state = (unsigned)p->state; ELzmaDummy res; { const CLzmaProb *prob; UInt32 bound; unsigned ttt; - unsigned posState = (p->processedPos) & ((1 << p->prop.pb) - 1); + unsigned posState = CALC_POS_STATE(p->processedPos, (1 << p->prop.pb) - 1); - prob = probs + IsMatch + (state << kNumPosBitsMax) + posState; + prob = probs + IsMatch + COMBINED_PS_STATE; IF_BIT_0_CHECK(prob) { UPDATE_0_CHECK @@ -618,10 +700,11 @@ static ELzmaDummy LzmaDec_TryDummy(const CLzmaDec *p, const Byte *buf, SizeT inS { unsigned bit; const CLzmaProb *probLit; - matchByte <<= 1; - bit = (matchByte & offs); - probLit = prob + offs + bit + symbol; - GET_BIT2_CHECK(probLit, symbol, offs &= ~bit, offs &= bit) + matchByte += matchByte; + bit = offs; + offs &= matchByte; + probLit = prob + (offs + bit + symbol); + GET_BIT2_CHECK(probLit, symbol, offs ^= bit; , ; ) } while (symbol < 0x100); } @@ -648,7 +731,7 @@ static ELzmaDummy LzmaDec_TryDummy(const CLzmaDec *p, const Byte *buf, SizeT inS IF_BIT_0_CHECK(prob) { UPDATE_0_CHECK; - prob = probs + IsRep0Long + (state << kNumPosBitsMax) + posState; + prob = probs + IsRep0Long + COMBINED_PS_STATE; IF_BIT_0_CHECK(prob) { UPDATE_0_CHECK; @@ -691,7 +774,7 @@ static ELzmaDummy LzmaDec_TryDummy(const CLzmaDec *p, const Byte *buf, SizeT inS IF_BIT_0_CHECK(probLen) { UPDATE_0_CHECK; - probLen = prob + LenLow + (posState << kLenNumLowBits); + probLen = prob + LenLow + GET_LEN_STATE; offset = 0; limit = 1 << kLenNumLowBits; } @@ -702,15 +785,15 @@ static ELzmaDummy LzmaDec_TryDummy(const CLzmaDec *p, const Byte *buf, SizeT inS IF_BIT_0_CHECK(probLen) { UPDATE_0_CHECK; - probLen = prob + LenMid + (posState << kLenNumMidBits); + probLen = prob + LenLow + GET_LEN_STATE + (1 << kLenNumLowBits); offset = kLenNumLowSymbols; - limit = 1 << kLenNumMidBits; + limit = 1 << kLenNumLowBits; } else { UPDATE_1_CHECK; probLen = prob + LenHigh; - offset = kLenNumLowSymbols + kLenNumMidSymbols; + offset = kLenNumLowSymbols * 2; limit = 1 << kLenNumHighBits; } } @@ -722,7 +805,7 @@ static ELzmaDummy LzmaDec_TryDummy(const CLzmaDec *p, const Byte *buf, SizeT inS { unsigned posSlot; prob = probs + PosSlot + - ((len < kNumLenToPosStates ? len : kNumLenToPosStates - 1) << + ((len < kNumLenToPosStates - 1 ? len : kNumLenToPosStates - 1) << kNumPosSlotBits); TREE_DECODE_CHECK(prob, 1 << kNumPosSlotBits, posSlot); if (posSlot >= kStartPosModelIndex) @@ -733,7 +816,7 @@ static ELzmaDummy LzmaDec_TryDummy(const CLzmaDec *p, const Byte *buf, SizeT inS if (posSlot < kEndPosModelIndex) { - prob = probs + SpecPos + ((2 | (posSlot & 1)) << numDirectBits) - posSlot - 1; + prob = probs + SpecPos + ((2 | (posSlot & 1)) << numDirectBits); } else { @@ -745,17 +828,18 @@ static ELzmaDummy LzmaDec_TryDummy(const CLzmaDec *p, const Byte *buf, SizeT inS code -= range & (((code - range) >> 31) - 1); /* if (code >= range) code -= range; */ } - while (--numDirectBits != 0); + while (--numDirectBits); prob = probs + Align; numDirectBits = kNumAlignBits; } { unsigned i = 1; + unsigned m = 1; do { - GET_BIT_CHECK(prob + i, i); + REV_BIT_CHECK(prob, i, m); } - while (--numDirectBits != 0); + while (--numDirectBits); } } } @@ -766,20 +850,19 @@ static ELzmaDummy LzmaDec_TryDummy(const CLzmaDec *p, const Byte *buf, SizeT inS } -void LzmaDec_InitDicAndState(CLzmaDec *p, Bool initDic, Bool initState) +void LzmaDec_InitDicAndState(CLzmaDec *p, BoolInt initDic, BoolInt initState) { - p->needFlush = 1; - p->remainLen = 0; + p->remainLen = kMatchSpecLenStart + 1; p->tempBufSize = 0; if (initDic) { p->processedPos = 0; p->checkDicSize = 0; - p->needInitState = 1; + p->remainLen = kMatchSpecLenStart + 2; } if (initState) - p->needInitState = 1; + p->remainLen = kMatchSpecLenStart + 2; } void LzmaDec_Init(CLzmaDec *p) @@ -788,53 +871,54 @@ void LzmaDec_Init(CLzmaDec *p) LzmaDec_InitDicAndState(p, True, True); } -static void LzmaDec_InitStateReal(CLzmaDec *p) -{ - SizeT numProbs = LzmaProps_GetNumProbs(&p->prop); - SizeT i; - CLzmaProb *probs = p->probs; - for (i = 0; i < numProbs; i++) - probs[i] = kBitModelTotal >> 1; - p->reps[0] = p->reps[1] = p->reps[2] = p->reps[3] = 1; - p->state = 0; - p->needInitState = 0; -} SRes LzmaDec_DecodeToDic(CLzmaDec *p, SizeT dicLimit, const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status) { SizeT inSize = *srcLen; (*srcLen) = 0; - LzmaDec_WriteRem(p, dicLimit); *status = LZMA_STATUS_NOT_SPECIFIED; + if (p->remainLen > kMatchSpecLenStart) + { + for (; inSize > 0 && p->tempBufSize < RC_INIT_SIZE; (*srcLen)++, inSize--) + p->tempBuf[p->tempBufSize++] = *src++; + if (p->tempBufSize != 0 && p->tempBuf[0] != 0) + return SZ_ERROR_DATA; + if (p->tempBufSize < RC_INIT_SIZE) + { + *status = LZMA_STATUS_NEEDS_MORE_INPUT; + return SZ_OK; + } + p->code = + ((UInt32)p->tempBuf[1] << 24) + | ((UInt32)p->tempBuf[2] << 16) + | ((UInt32)p->tempBuf[3] << 8) + | ((UInt32)p->tempBuf[4]); + p->range = 0xFFFFFFFF; + p->tempBufSize = 0; + + if (p->remainLen > kMatchSpecLenStart + 1) + { + SizeT numProbs = LzmaProps_GetNumProbs(&p->prop); + SizeT i; + CLzmaProb *probs = p->probs; + for (i = 0; i < numProbs; i++) + probs[i] = kBitModelTotal >> 1; + p->reps[0] = p->reps[1] = p->reps[2] = p->reps[3] = 1; + p->state = 0; + } + + p->remainLen = 0; + } + + LzmaDec_WriteRem(p, dicLimit); + while (p->remainLen != kMatchSpecLenStart) { - int checkEndMarkNow; + int checkEndMarkNow = 0; - if (p->needFlush) - { - for (; inSize > 0 && p->tempBufSize < RC_INIT_SIZE; (*srcLen)++, inSize--) - p->tempBuf[p->tempBufSize++] = *src++; - if (p->tempBufSize < RC_INIT_SIZE) - { - *status = LZMA_STATUS_NEEDS_MORE_INPUT; - return SZ_OK; - } - if (p->tempBuf[0] != 0) - return SZ_ERROR_DATA; - p->code = - ((UInt32)p->tempBuf[1] << 24) - | ((UInt32)p->tempBuf[2] << 16) - | ((UInt32)p->tempBuf[3] << 8) - | ((UInt32)p->tempBuf[4]); - p->range = 0xFFFFFFFF; - p->needFlush = 0; - p->tempBufSize = 0; - } - - checkEndMarkNow = 0; if (p->dicPos >= dicLimit) { if (p->remainLen == 0 && p->code == 0) @@ -855,9 +939,6 @@ SRes LzmaDec_DecodeToDic(CLzmaDec *p, SizeT dicLimit, const Byte *src, SizeT *sr checkEndMarkNow = 1; } - if (p->needInitState) - LzmaDec_InitStateReal(p); - if (p->tempBufSize == 0) { SizeT processed; @@ -898,10 +979,10 @@ SRes LzmaDec_DecodeToDic(CLzmaDec *p, SizeT dicLimit, const Byte *src, SizeT *sr p->tempBufSize = rem; if (rem < LZMA_REQUIRED_INPUT_MAX || checkEndMarkNow) { - int dummyRes = LzmaDec_TryDummy(p, p->tempBuf, rem); + int dummyRes = LzmaDec_TryDummy(p, p->tempBuf, (SizeT)rem); if (dummyRes == DUMMY_ERROR) { - (*srcLen) += lookAhead; + (*srcLen) += (SizeT)lookAhead; *status = LZMA_STATUS_NEEDS_MORE_INPUT; return SZ_OK; } @@ -924,17 +1005,20 @@ SRes LzmaDec_DecodeToDic(CLzmaDec *p, SizeT dicLimit, const Byte *src, SizeT *sr return SZ_ERROR_FAIL; /* some internal error */ lookAhead -= rem; } - (*srcLen) += lookAhead; + (*srcLen) += (SizeT)lookAhead; src += lookAhead; - inSize -= lookAhead; + inSize -= (SizeT)lookAhead; p->tempBufSize = 0; } } - if (p->code == 0) - *status = LZMA_STATUS_FINISHED_WITH_MARK; - return (p->code == 0) ? SZ_OK : SZ_ERROR_DATA; + + if (p->code != 0) + return SZ_ERROR_DATA; + *status = LZMA_STATUS_FINISHED_WITH_MARK; + return SZ_OK; } + SRes LzmaDec_DecodeToBuf(CLzmaDec *p, Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status) { SizeT outSize = *destLen; @@ -975,19 +1059,19 @@ SRes LzmaDec_DecodeToBuf(CLzmaDec *p, Byte *dest, SizeT *destLen, const Byte *sr } } -void LzmaDec_FreeProbs(CLzmaDec *p, ISzAlloc *alloc) +void LzmaDec_FreeProbs(CLzmaDec *p, ISzAllocPtr alloc) { - alloc->Free(alloc, p->probs); + ISzAlloc_Free(alloc, p->probs); p->probs = NULL; } -static void LzmaDec_FreeDict(CLzmaDec *p, ISzAlloc *alloc) +static void LzmaDec_FreeDict(CLzmaDec *p, ISzAllocPtr alloc) { - alloc->Free(alloc, p->dic); + ISzAlloc_Free(alloc, p->dic); p->dic = NULL; } -void LzmaDec_Free(CLzmaDec *p, ISzAlloc *alloc) +void LzmaDec_Free(CLzmaDec *p, ISzAllocPtr alloc) { LzmaDec_FreeProbs(p, alloc); LzmaDec_FreeDict(p, alloc); @@ -1011,29 +1095,30 @@ SRes LzmaProps_Decode(CLzmaProps *p, const Byte *data, unsigned size) if (d >= (9 * 5 * 5)) return SZ_ERROR_UNSUPPORTED; - p->lc = d % 9; + p->lc = (Byte)(d % 9); d /= 9; - p->pb = d / 5; - p->lp = d % 5; + p->pb = (Byte)(d / 5); + p->lp = (Byte)(d % 5); return SZ_OK; } -static SRes LzmaDec_AllocateProbs2(CLzmaDec *p, const CLzmaProps *propNew, ISzAlloc *alloc) +static SRes LzmaDec_AllocateProbs2(CLzmaDec *p, const CLzmaProps *propNew, ISzAllocPtr alloc) { UInt32 numProbs = LzmaProps_GetNumProbs(propNew); if (!p->probs || numProbs != p->numProbs) { LzmaDec_FreeProbs(p, alloc); - p->probs = (CLzmaProb *)alloc->Alloc(alloc, numProbs * sizeof(CLzmaProb)); - p->numProbs = numProbs; + p->probs = (CLzmaProb *)ISzAlloc_Alloc(alloc, numProbs * sizeof(CLzmaProb)); if (!p->probs) return SZ_ERROR_MEM; + p->probs_1664 = p->probs + 1664; + p->numProbs = numProbs; } return SZ_OK; } -SRes LzmaDec_AllocateProbs(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAlloc *alloc) +SRes LzmaDec_AllocateProbs(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAllocPtr alloc) { CLzmaProps propNew; RINOK(LzmaProps_Decode(&propNew, props, propsSize)); @@ -1042,7 +1127,7 @@ SRes LzmaDec_AllocateProbs(CLzmaDec *p, const Byte *props, unsigned propsSize, I return SZ_OK; } -SRes LzmaDec_Allocate(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAlloc *alloc) +SRes LzmaDec_Allocate(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAllocPtr alloc) { CLzmaProps propNew; SizeT dicBufSize; @@ -1062,7 +1147,7 @@ SRes LzmaDec_Allocate(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAll if (!p->dic || dicBufSize != p->dicBufSize) { LzmaDec_FreeDict(p, alloc); - p->dic = (Byte *)alloc->Alloc(alloc, dicBufSize); + p->dic = (Byte *)ISzAlloc_Alloc(alloc, dicBufSize); if (!p->dic) { LzmaDec_FreeProbs(p, alloc); @@ -1076,7 +1161,7 @@ SRes LzmaDec_Allocate(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAll SRes LzmaDecode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen, const Byte *propData, unsigned propSize, ELzmaFinishMode finishMode, - ELzmaStatus *status, ISzAlloc *alloc) + ELzmaStatus *status, ISzAllocPtr alloc) { CLzmaDec p; SRes res; diff --git a/uppsrc/plugin/lzma/lib/LzmaDec.h b/uppsrc/plugin/lzma/lib/LzmaDec.h index 2633abeac..28ce60c3e 100644 --- a/uppsrc/plugin/lzma/lib/LzmaDec.h +++ b/uppsrc/plugin/lzma/lib/LzmaDec.h @@ -1,5 +1,5 @@ /* LzmaDec.h -- LZMA Decoder -2013-01-18 : Igor Pavlov : Public domain */ +2018-04-21 : Igor Pavlov : Public domain */ #ifndef __LZMA_DEC_H #define __LZMA_DEC_H @@ -12,11 +12,13 @@ EXTERN_C_BEGIN /* _LZMA_PROB32 can increase the speed on some CPUs, but memory usage for CLzmaDec::probs will be doubled in that case */ +typedef #ifdef _LZMA_PROB32 -#define CLzmaProb UInt32 + UInt32 #else -#define CLzmaProb UInt16 + UInt16 #endif + CLzmaProb; /* ---------- LZMA Properties ---------- */ @@ -25,7 +27,10 @@ EXTERN_C_BEGIN typedef struct _CLzmaProps { - unsigned lc, lp, pb; + Byte lc; + Byte lp; + Byte pb; + Byte _pad_; UInt32 dicSize; } CLzmaProps; @@ -47,32 +52,34 @@ SRes LzmaProps_Decode(CLzmaProps *p, const Byte *data, unsigned size); typedef struct { + /* Don't change this structure. ASM code can use it. */ CLzmaProps prop; CLzmaProb *probs; + CLzmaProb *probs_1664; Byte *dic; - const Byte *buf; - UInt32 range, code; - SizeT dicPos; SizeT dicBufSize; + SizeT dicPos; + const Byte *buf; + UInt32 range; + UInt32 code; UInt32 processedPos; UInt32 checkDicSize; - unsigned state; UInt32 reps[4]; - unsigned remainLen; - int needFlush; - int needInitState; + UInt32 state; + UInt32 remainLen; + UInt32 numProbs; unsigned tempBufSize; Byte tempBuf[LZMA_REQUIRED_INPUT_MAX]; } CLzmaDec; -#define LzmaDec_Construct(p) { (p)->dic = 0; (p)->probs = 0; } +#define LzmaDec_Construct(p) { (p)->dic = NULL; (p)->probs = NULL; } void LzmaDec_Init(CLzmaDec *p); /* There are two types of LZMA streams: - 0) Stream with end mark. That end mark adds about 6 bytes to compressed size. - 1) Stream without end mark. You must know exact uncompressed size to decompress such stream. */ + - Stream with end mark. That end mark adds about 6 bytes to compressed size. + - Stream without end mark. You must know exact uncompressed size to decompress such stream. */ typedef enum { @@ -129,11 +136,11 @@ LzmaDec_Allocate* can return: SZ_ERROR_UNSUPPORTED - Unsupported properties */ -SRes LzmaDec_AllocateProbs(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAlloc *alloc); -void LzmaDec_FreeProbs(CLzmaDec *p, ISzAlloc *alloc); +SRes LzmaDec_AllocateProbs(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAllocPtr alloc); +void LzmaDec_FreeProbs(CLzmaDec *p, ISzAllocPtr alloc); -SRes LzmaDec_Allocate(CLzmaDec *state, const Byte *prop, unsigned propsSize, ISzAlloc *alloc); -void LzmaDec_Free(CLzmaDec *state, ISzAlloc *alloc); +SRes LzmaDec_Allocate(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAllocPtr alloc); +void LzmaDec_Free(CLzmaDec *p, ISzAllocPtr alloc); /* ---------- Dictionary Interface ---------- */ @@ -142,7 +149,7 @@ void LzmaDec_Free(CLzmaDec *state, ISzAlloc *alloc); You must work with CLzmaDec variables directly in this interface. STEPS: - LzmaDec_Constr() + LzmaDec_Construct() LzmaDec_Allocate() for (each new stream) { @@ -220,7 +227,7 @@ Returns: SRes LzmaDecode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen, const Byte *propData, unsigned propSize, ELzmaFinishMode finishMode, - ELzmaStatus *status, ISzAlloc *alloc); + ELzmaStatus *status, ISzAllocPtr alloc); EXTERN_C_END diff --git a/uppsrc/plugin/lzma/lib/LzmaEnc.c b/uppsrc/plugin/lzma/lib/LzmaEnc.c index 462ca6756..14086fc4f 100644 --- a/uppsrc/plugin/lzma/lib/LzmaEnc.c +++ b/uppsrc/plugin/lzma/lib/LzmaEnc.c @@ -1,5 +1,5 @@ /* LzmaEnc.c -- LZMA Encoder -2016-05-16 : Igor Pavlov : Public domain */ +2019-01-10: Igor Pavlov : Public domain */ #include "Precomp.h" @@ -23,17 +23,8 @@ static unsigned g_STAT_OFFSET = 0; #endif -#define kMaxHistorySize ((UInt32)3 << 29) -/* #define kMaxHistorySize ((UInt32)7 << 29) */ - -#define kBlockSizeMax ((1 << LZMA_NUM_BLOCK_SIZE_BITS) - 1) - -#define kBlockSize (9 << 10) -#define kUnpackBlockSize (1 << 18) -#define kMatchArraySize (1 << 21) -#define kMatchRecordMaxSize ((LZMA_MATCH_LEN_MAX * 2 + 3) * LZMA_MATCH_LEN_MAX) - -#define kNumMaxDirectBits (31) +#define kLzmaMaxHistorySize ((UInt32)3 << 29) +/* #define kLzmaMaxHistorySize ((UInt32)7 << 29) */ #define kNumTopBits 24 #define kTopValue ((UInt32)1 << kNumTopBits) @@ -47,6 +38,8 @@ static unsigned g_STAT_OFFSET = 0; #define kNumBitPriceShiftBits 4 #define kBitPrice (1 << kNumBitPriceShiftBits) +#define REP_LEN_COUNT 64 + void LzmaEncProps_Init(CLzmaEncProps *p) { p->level = 5; @@ -62,14 +55,15 @@ void LzmaEncProps_Normalize(CLzmaEncProps *p) if (level < 0) level = 5; p->level = level; - if (p->dictSize == 0) p->dictSize = (level <= 5 ? (1 << (level * 2 + 14)) : (level == 6 ? (1 << 25) : (1 << 26))); + if (p->dictSize == 0) p->dictSize = (level <= 5 ? (1 << (level * 2 + 14)) : (level <= 7 ? (1 << 25) : (1 << 26))); if (p->dictSize > p->reduceSize) { unsigned i; + UInt32 reduceSize = (UInt32)p->reduceSize; for (i = 11; i <= 30; i++) { - if ((UInt32)p->reduceSize <= ((UInt32)2 << i)) { p->dictSize = ((UInt32)2 << i); break; } - if ((UInt32)p->reduceSize <= ((UInt32)3 << i)) { p->dictSize = ((UInt32)3 << i); break; } + if (reduceSize <= ((UInt32)2 << i)) { p->dictSize = ((UInt32)2 << i); break; } + if (reduceSize <= ((UInt32)3 << i)) { p->dictSize = ((UInt32)3 << i); break; } } } @@ -110,9 +104,9 @@ UInt32 LzmaEncProps_GetDictSize(const CLzmaEncProps *props2) #define BSR2_RET(pos, res) { unsigned long zz; _BitScanReverse(&zz, (pos)); res = (zz + zz) + ((pos >> (zz - 1)) & 1); } -static UInt32 GetPosSlot1(UInt32 pos) +static unsigned GetPosSlot1(UInt32 pos) { - UInt32 res; + unsigned res; BSR2_RET(pos, res); return res; } @@ -145,18 +139,18 @@ static void LzmaEnc_FastPosInit(Byte *g_FastPos) /* we can use ((limit - pos) >> 31) only if (pos < ((UInt32)1 << 31)) */ /* -#define BSR2_RET(pos, res) { UInt32 zz = 6 + ((kNumLogBits - 1) & \ +#define BSR2_RET(pos, res) { unsigned zz = 6 + ((kNumLogBits - 1) & \ (0 - (((((UInt32)1 << (kNumLogBits + 6)) - 1) - pos) >> 31))); \ res = p->g_FastPos[pos >> zz] + (zz * 2); } */ /* -#define BSR2_RET(pos, res) { UInt32 zz = 6 + ((kNumLogBits - 1) & \ +#define BSR2_RET(pos, res) { unsigned zz = 6 + ((kNumLogBits - 1) & \ (0 - (((((UInt32)1 << (kNumLogBits)) - 1) - (pos >> 6)) >> 31))); \ res = p->g_FastPos[pos >> zz] + (zz * 2); } */ -#define BSR2_RET(pos, res) { UInt32 zz = (pos < (1 << (kNumLogBits + 6))) ? 6 : 6 + kNumLogBits - 1; \ +#define BSR2_RET(pos, res) { unsigned zz = (pos < (1 << (kNumLogBits + 6))) ? 6 : 6 + kNumLogBits - 1; \ res = p->g_FastPos[pos >> zz] + (zz * 2); } /* @@ -167,32 +161,35 @@ static void LzmaEnc_FastPosInit(Byte *g_FastPos) #define GetPosSlot1(pos) p->g_FastPos[pos] #define GetPosSlot2(pos, res) { BSR2_RET(pos, res); } -#define GetPosSlot(pos, res) { if (pos < kNumFullDistances) res = p->g_FastPos[pos]; else BSR2_RET(pos, res); } +#define GetPosSlot(pos, res) { if (pos < kNumFullDistances) res = p->g_FastPos[pos & (kNumFullDistances - 1)]; else BSR2_RET(pos, res); } #endif #define LZMA_NUM_REPS 4 -typedef unsigned CState; +typedef UInt16 CState; +typedef UInt16 CExtra; typedef struct { UInt32 price; - CState state; - int prev1IsChar; - int prev2; - - UInt32 posPrev2; - UInt32 backPrev2; - - UInt32 posPrev; - UInt32 backPrev; - UInt32 backs[LZMA_NUM_REPS]; + CExtra extra; + // 0 : normal + // 1 : LIT : MATCH + // > 1 : MATCH (extra-1) : LIT : REP0 (len) + UInt32 len; + UInt32 dist; + UInt32 reps[LZMA_NUM_REPS]; } COptimal; -#define kNumOpts (1 << 12) + +// 18.06 +#define kNumOpts (1 << 11) +#define kPackReserve (kNumOpts * 8) +// #define kNumOpts (1 << 12) +// #define kPackReserve (1 + kNumOpts * 2) #define kNumLenToPosStates 4 #define kNumPosSlotBits 6 @@ -200,22 +197,21 @@ typedef struct #define kDicLogSizeMax 32 #define kDistTableSizeMax (kDicLogSizeMax * 2) - #define kNumAlignBits 4 #define kAlignTableSize (1 << kNumAlignBits) #define kAlignMask (kAlignTableSize - 1) #define kStartPosModelIndex 4 #define kEndPosModelIndex 14 -#define kNumPosModels (kEndPosModelIndex - kStartPosModelIndex) - #define kNumFullDistances (1 << (kEndPosModelIndex >> 1)) +typedef #ifdef _LZMA_PROB32 -#define CLzmaProb UInt32 + UInt32 #else -#define CLzmaProb UInt16 + UInt16 #endif + CLzmaProb; #define LZMA_PB_MAX 4 #define LZMA_LC_MAX 8 @@ -223,15 +219,11 @@ typedef struct #define LZMA_NUM_PB_STATES_MAX (1 << LZMA_PB_MAX) - #define kLenNumLowBits 3 #define kLenNumLowSymbols (1 << kLenNumLowBits) -#define kLenNumMidBits 3 -#define kLenNumMidSymbols (1 << kLenNumMidBits) #define kLenNumHighBits 8 #define kLenNumHighSymbols (1 << kLenNumHighBits) - -#define kLenNumSymbolsTotal (kLenNumLowSymbols + kLenNumMidSymbols + kLenNumHighSymbols) +#define kLenNumSymbolsTotal (kLenNumLowSymbols * 2 + kLenNumHighSymbols) #define LZMA_MATCH_LEN_MIN 2 #define LZMA_MATCH_LEN_MAX (LZMA_MATCH_LEN_MIN + kLenNumSymbolsTotal - 1) @@ -241,27 +233,31 @@ typedef struct typedef struct { - CLzmaProb choice; - CLzmaProb choice2; - CLzmaProb low[LZMA_NUM_PB_STATES_MAX << kLenNumLowBits]; - CLzmaProb mid[LZMA_NUM_PB_STATES_MAX << kLenNumMidBits]; + CLzmaProb low[LZMA_NUM_PB_STATES_MAX << (kLenNumLowBits + 1)]; CLzmaProb high[kLenNumHighSymbols]; } CLenEnc; typedef struct { - CLenEnc p; - UInt32 tableSize; + unsigned tableSize; UInt32 prices[LZMA_NUM_PB_STATES_MAX][kLenNumSymbolsTotal]; - UInt32 counters[LZMA_NUM_PB_STATES_MAX]; + // UInt32 prices1[LZMA_NUM_PB_STATES_MAX][kLenNumLowSymbols * 2]; + // UInt32 prices2[kLenNumSymbolsTotal]; } CLenPriceEnc; +#define GET_PRICE_LEN(p, posState, len) \ + ((p)->prices[posState][(size_t)(len) - LZMA_MATCH_LEN_MIN]) + +/* +#define GET_PRICE_LEN(p, posState, len) \ + ((p)->prices2[(size_t)(len) - 2] + ((p)->prices1[posState][((len) - 2) & (kLenNumLowSymbols * 2 - 1)] & (((len) - 2 - kLenNumLowSymbols * 2) >> 9))) +*/ typedef struct { UInt32 range; - Byte cache; + unsigned cache; UInt64 low; UInt64 cacheSize; Byte *buf; @@ -277,69 +273,77 @@ typedef struct { CLzmaProb *litProbs; - UInt32 state; + unsigned state; UInt32 reps[LZMA_NUM_REPS]; - CLzmaProb isMatch[kNumStates][LZMA_NUM_PB_STATES_MAX]; + CLzmaProb posAlignEncoder[1 << kNumAlignBits]; CLzmaProb isRep[kNumStates]; CLzmaProb isRepG0[kNumStates]; CLzmaProb isRepG1[kNumStates]; CLzmaProb isRepG2[kNumStates]; + CLzmaProb isMatch[kNumStates][LZMA_NUM_PB_STATES_MAX]; CLzmaProb isRep0Long[kNumStates][LZMA_NUM_PB_STATES_MAX]; CLzmaProb posSlotEncoder[kNumLenToPosStates][1 << kNumPosSlotBits]; - CLzmaProb posEncoders[kNumFullDistances - kEndPosModelIndex]; - CLzmaProb posAlignEncoder[1 << kNumAlignBits]; + CLzmaProb posEncoders[kNumFullDistances]; - CLenPriceEnc lenEnc; - CLenPriceEnc repLenEnc; + CLenEnc lenProbs; + CLenEnc repLenProbs; + } CSaveState; +typedef UInt32 CProbPrice; + + typedef struct { void *matchFinderObj; IMatchFinder matchFinder; - UInt32 optimumEndIndex; - UInt32 optimumCurrentIndex; + unsigned optCur; + unsigned optEnd; - UInt32 longestMatchLength; - UInt32 numPairs; + unsigned longestMatchLen; + unsigned numPairs; UInt32 numAvail; - UInt32 numFastBytes; - UInt32 additionalOffset; + unsigned state; + unsigned numFastBytes; + unsigned additionalOffset; UInt32 reps[LZMA_NUM_REPS]; - UInt32 state; + unsigned lpMask, pbMask; + CLzmaProb *litProbs; + CRangeEnc rc; + + UInt32 backRes; unsigned lc, lp, pb; - unsigned lpMask, pbMask; unsigned lclp; - CLzmaProb *litProbs; - - Bool fastMode; - Bool writeEndMark; - Bool finished; - Bool multiThread; - Bool needInit; + BoolInt fastMode; + BoolInt writeEndMark; + BoolInt finished; + BoolInt multiThread; + BoolInt needInit; + // BoolInt _maxMode; UInt64 nowPos64; - UInt32 matchPriceCount; - UInt32 alignPriceCount; + unsigned matchPriceCount; + // unsigned alignPriceCount; + int repLenEncCounter; - UInt32 distTableSize; + unsigned distTableSize; UInt32 dictSize; SRes result; - CRangeEnc rc; - #ifndef _7ZIP_ST - Bool mtMode; + BoolInt mtMode; + // begin of CMatchFinderMt is used in LZ thread CMatchFinderMt matchFinderMt; + // end of CMatchFinderMt is used in BT and HASH threads #endif CMatchFinder matchFinderBase; @@ -348,33 +352,37 @@ typedef struct Byte pad[128]; #endif - COptimal opt[kNumOpts]; - - #ifndef LZMA_LOG_BSR - Byte g_FastPos[1 << kNumLogBits]; - #endif + // LZ thread + CProbPrice ProbPrices[kBitModelTotal >> kNumMoveReducingBits]; - UInt32 ProbPrices[kBitModelTotal >> kNumMoveReducingBits]; UInt32 matches[LZMA_MATCH_LEN_MAX * 2 + 2 + 1]; + UInt32 alignPrices[kAlignTableSize]; UInt32 posSlotPrices[kNumLenToPosStates][kDistTableSizeMax]; UInt32 distancesPrices[kNumLenToPosStates][kNumFullDistances]; - UInt32 alignPrices[kAlignTableSize]; - CLzmaProb isMatch[kNumStates][LZMA_NUM_PB_STATES_MAX]; + CLzmaProb posAlignEncoder[1 << kNumAlignBits]; CLzmaProb isRep[kNumStates]; CLzmaProb isRepG0[kNumStates]; CLzmaProb isRepG1[kNumStates]; CLzmaProb isRepG2[kNumStates]; + CLzmaProb isMatch[kNumStates][LZMA_NUM_PB_STATES_MAX]; CLzmaProb isRep0Long[kNumStates][LZMA_NUM_PB_STATES_MAX]; - CLzmaProb posSlotEncoder[kNumLenToPosStates][1 << kNumPosSlotBits]; - CLzmaProb posEncoders[kNumFullDistances - kEndPosModelIndex]; - CLzmaProb posAlignEncoder[1 << kNumAlignBits]; + CLzmaProb posEncoders[kNumFullDistances]; + CLenEnc lenProbs; + CLenEnc repLenProbs; + + #ifndef LZMA_LOG_BSR + Byte g_FastPos[1 << kNumLogBits]; + #endif + CLenPriceEnc lenEnc; CLenPriceEnc repLenEnc; + COptimal opt[kNumOpts]; + CSaveState saveState; #ifndef _7ZIP_ST @@ -383,58 +391,62 @@ typedef struct } CLzmaEnc; + +#define COPY_ARR(dest, src, arr) memcpy(dest->arr, src->arr, sizeof(src->arr)); + void LzmaEnc_SaveState(CLzmaEncHandle pp) { CLzmaEnc *p = (CLzmaEnc *)pp; CSaveState *dest = &p->saveState; - int i; - dest->lenEnc = p->lenEnc; - dest->repLenEnc = p->repLenEnc; + dest->state = p->state; + + dest->lenProbs = p->lenProbs; + dest->repLenProbs = p->repLenProbs; + + COPY_ARR(dest, p, reps); + + COPY_ARR(dest, p, posAlignEncoder); + COPY_ARR(dest, p, isRep); + COPY_ARR(dest, p, isRepG0); + COPY_ARR(dest, p, isRepG1); + COPY_ARR(dest, p, isRepG2); + COPY_ARR(dest, p, isMatch); + COPY_ARR(dest, p, isRep0Long); + COPY_ARR(dest, p, posSlotEncoder); + COPY_ARR(dest, p, posEncoders); - for (i = 0; i < kNumStates; i++) - { - memcpy(dest->isMatch[i], p->isMatch[i], sizeof(p->isMatch[i])); - memcpy(dest->isRep0Long[i], p->isRep0Long[i], sizeof(p->isRep0Long[i])); - } - for (i = 0; i < kNumLenToPosStates; i++) - memcpy(dest->posSlotEncoder[i], p->posSlotEncoder[i], sizeof(p->posSlotEncoder[i])); - memcpy(dest->isRep, p->isRep, sizeof(p->isRep)); - memcpy(dest->isRepG0, p->isRepG0, sizeof(p->isRepG0)); - memcpy(dest->isRepG1, p->isRepG1, sizeof(p->isRepG1)); - memcpy(dest->isRepG2, p->isRepG2, sizeof(p->isRepG2)); - memcpy(dest->posEncoders, p->posEncoders, sizeof(p->posEncoders)); - memcpy(dest->posAlignEncoder, p->posAlignEncoder, sizeof(p->posAlignEncoder)); - memcpy(dest->reps, p->reps, sizeof(p->reps)); memcpy(dest->litProbs, p->litProbs, ((UInt32)0x300 << p->lclp) * sizeof(CLzmaProb)); } + void LzmaEnc_RestoreState(CLzmaEncHandle pp) { CLzmaEnc *dest = (CLzmaEnc *)pp; const CSaveState *p = &dest->saveState; - int i; - dest->lenEnc = p->lenEnc; - dest->repLenEnc = p->repLenEnc; + dest->state = p->state; - for (i = 0; i < kNumStates; i++) - { - memcpy(dest->isMatch[i], p->isMatch[i], sizeof(p->isMatch[i])); - memcpy(dest->isRep0Long[i], p->isRep0Long[i], sizeof(p->isRep0Long[i])); - } - for (i = 0; i < kNumLenToPosStates; i++) - memcpy(dest->posSlotEncoder[i], p->posSlotEncoder[i], sizeof(p->posSlotEncoder[i])); - memcpy(dest->isRep, p->isRep, sizeof(p->isRep)); - memcpy(dest->isRepG0, p->isRepG0, sizeof(p->isRepG0)); - memcpy(dest->isRepG1, p->isRepG1, sizeof(p->isRepG1)); - memcpy(dest->isRepG2, p->isRepG2, sizeof(p->isRepG2)); - memcpy(dest->posEncoders, p->posEncoders, sizeof(p->posEncoders)); - memcpy(dest->posAlignEncoder, p->posAlignEncoder, sizeof(p->posAlignEncoder)); - memcpy(dest->reps, p->reps, sizeof(p->reps)); + dest->lenProbs = p->lenProbs; + dest->repLenProbs = p->repLenProbs; + + COPY_ARR(dest, p, reps); + + COPY_ARR(dest, p, posAlignEncoder); + COPY_ARR(dest, p, isRep); + COPY_ARR(dest, p, isRepG0); + COPY_ARR(dest, p, isRepG1); + COPY_ARR(dest, p, isRepG2); + COPY_ARR(dest, p, isMatch); + COPY_ARR(dest, p, isRep0Long); + COPY_ARR(dest, p, posSlotEncoder); + COPY_ARR(dest, p, posEncoders); + memcpy(dest->litProbs, p->litProbs, ((UInt32)0x300 << dest->lclp) * sizeof(CLzmaProb)); } + + SRes LzmaEnc_SetProps(CLzmaEncHandle pp, const CLzmaEncProps *props2) { CLzmaEnc *p = (CLzmaEnc *)pp; @@ -445,7 +457,7 @@ SRes LzmaEnc_SetProps(CLzmaEncHandle pp, const CLzmaEncProps *props2) || props.lp > LZMA_LP_MAX || props.pb > LZMA_PB_MAX || props.dictSize > ((UInt64)1 << kDicLogSizeMaxCompress) - || props.dictSize > kMaxHistorySize) + || props.dictSize > kLzmaMaxHistorySize) return SZ_ERROR_PARAM; p->dictSize = props.dictSize; @@ -461,9 +473,10 @@ SRes LzmaEnc_SetProps(CLzmaEncHandle pp, const CLzmaEncProps *props2) p->lp = props.lp; p->pb = props.pb; p->fastMode = (props.algo == 0); + // p->_maxMode = True; p->matchFinderBase.btMode = (Byte)(props.btMode ? 1 : 0); { - UInt32 numHashBytes = 4; + unsigned numHashBytes = 4; if (props.btMode) { if (props.numHashBytes < 2) @@ -492,13 +505,27 @@ SRes LzmaEnc_SetProps(CLzmaEncHandle pp, const CLzmaEncProps *props2) return SZ_OK; } -static const int kLiteralNextStates[kNumStates] = {0, 0, 0, 0, 1, 2, 3, 4, 5, 6, 4, 5}; -static const int kMatchNextStates[kNumStates] = {7, 7, 7, 7, 7, 7, 7, 10, 10, 10, 10, 10}; -static const int kRepNextStates[kNumStates] = {8, 8, 8, 8, 8, 8, 8, 11, 11, 11, 11, 11}; -static const int kShortRepNextStates[kNumStates]= {9, 9, 9, 9, 9, 9, 9, 11, 11, 11, 11, 11}; -#define IsCharState(s) ((s) < 7) +void LzmaEnc_SetDataSize(CLzmaEncHandle pp, UInt64 expectedDataSiize) +{ + CLzmaEnc *p = (CLzmaEnc *)pp; + p->matchFinderBase.expectedDataSize = expectedDataSiize; +} + +#define kState_Start 0 +#define kState_LitAfterMatch 4 +#define kState_LitAfterRep 5 +#define kState_MatchAfterLit 7 +#define kState_RepAfterLit 8 + +static const Byte kLiteralNextStates[kNumStates] = {0, 0, 0, 0, 1, 2, 3, 4, 5, 6, 4, 5}; +static const Byte kMatchNextStates[kNumStates] = {7, 7, 7, 7, 7, 7, 7, 10, 10, 10, 10, 10}; +static const Byte kRepNextStates[kNumStates] = {8, 8, 8, 8, 8, 8, 8, 11, 11, 11, 11, 11}; +static const Byte kShortRepNextStates[kNumStates]= {9, 9, 9, 9, 9, 9, 9, 11, 11, 11, 11, 11}; + +#define IsLitState(s) ((s) < 7) +#define GetLenToPosState2(len) (((len) < kNumLenToPosStates - 1) ? (len) : kNumLenToPosStates - 1) #define GetLenToPosState(len) (((len) < kNumLenToPosStates + 1) ? (len) - 2 : kNumLenToPosStates - 1) #define kInfinityPrice (1 << 30) @@ -509,14 +536,16 @@ static void RangeEnc_Construct(CRangeEnc *p) p->bufBase = NULL; } -#define RangeEnc_GetProcessed(p) ((p)->processed + ((p)->buf - (p)->bufBase) + (p)->cacheSize) +#define RangeEnc_GetProcessed(p) ((p)->processed + ((p)->buf - (p)->bufBase) + (p)->cacheSize) +#define RangeEnc_GetProcessed_sizet(p) ((size_t)(p)->processed + ((p)->buf - (p)->bufBase) + (size_t)(p)->cacheSize) #define RC_BUF_SIZE (1 << 16) -static int RangeEnc_Alloc(CRangeEnc *p, ISzAlloc *alloc) + +static int RangeEnc_Alloc(CRangeEnc *p, ISzAllocPtr alloc) { if (!p->bufBase) { - p->bufBase = (Byte *)alloc->Alloc(alloc, RC_BUF_SIZE); + p->bufBase = (Byte *)ISzAlloc_Alloc(alloc, RC_BUF_SIZE); if (!p->bufBase) return 0; p->bufLim = p->bufBase + RC_BUF_SIZE; @@ -524,19 +553,19 @@ static int RangeEnc_Alloc(CRangeEnc *p, ISzAlloc *alloc) return 1; } -static void RangeEnc_Free(CRangeEnc *p, ISzAlloc *alloc) +static void RangeEnc_Free(CRangeEnc *p, ISzAllocPtr alloc) { - alloc->Free(alloc, p->bufBase); + ISzAlloc_Free(alloc, p->bufBase); p->bufBase = 0; } static void RangeEnc_Init(CRangeEnc *p) { /* Stream.Init(); */ - p->low = 0; p->range = 0xFFFFFFFF; - p->cacheSize = 1; p->cache = 0; + p->low = 0; + p->cacheSize = 0; p->buf = p->bufBase; @@ -544,37 +573,48 @@ static void RangeEnc_Init(CRangeEnc *p) p->res = SZ_OK; } -static void RangeEnc_FlushStream(CRangeEnc *p) +MY_NO_INLINE static void RangeEnc_FlushStream(CRangeEnc *p) { size_t num; if (p->res != SZ_OK) return; num = p->buf - p->bufBase; - if (num != p->outStream->Write(p->outStream, p->bufBase, num)) + if (num != ISeqOutStream_Write(p->outStream, p->bufBase, num)) p->res = SZ_ERROR_WRITE; p->processed += num; p->buf = p->bufBase; } -static void MY_FAST_CALL RangeEnc_ShiftLow(CRangeEnc *p) +MY_NO_INLINE static void MY_FAST_CALL RangeEnc_ShiftLow(CRangeEnc *p) { - if ((UInt32)p->low < (UInt32)0xFF000000 || (unsigned)(p->low >> 32) != 0) + UInt32 low = (UInt32)p->low; + unsigned high = (unsigned)(p->low >> 32); + p->low = (UInt32)(low << 8); + if (low < (UInt32)0xFF000000 || high != 0) { - Byte temp = p->cache; - do { Byte *buf = p->buf; - *buf++ = (Byte)(temp + (Byte)(p->low >> 32)); + *buf++ = (Byte)(p->cache + high); + p->cache = (unsigned)(low >> 24); p->buf = buf; if (buf == p->bufLim) RangeEnc_FlushStream(p); - temp = 0xFF; + if (p->cacheSize == 0) + return; + } + high += 0xFF; + for (;;) + { + Byte *buf = p->buf; + *buf++ = (Byte)(high); + p->buf = buf; + if (buf == p->bufLim) + RangeEnc_FlushStream(p); + if (--p->cacheSize == 0) + return; } - while (--p->cacheSize != 0); - p->cache = (Byte)((UInt32)p->low >> 24); } p->cacheSize++; - p->low = (UInt32)p->low << 8; } static void RangeEnc_FlushData(CRangeEnc *p) @@ -584,78 +624,121 @@ static void RangeEnc_FlushData(CRangeEnc *p) RangeEnc_ShiftLow(p); } -static void RangeEnc_EncodeDirectBits(CRangeEnc *p, UInt32 value, unsigned numBits) +#define RC_NORM(p) if (range < kTopValue) { range <<= 8; RangeEnc_ShiftLow(p); } + +#define RC_BIT_PRE(p, prob) \ + ttt = *(prob); \ + newBound = (range >> kNumBitModelTotalBits) * ttt; + +// #define _LZMA_ENC_USE_BRANCH + +#ifdef _LZMA_ENC_USE_BRANCH + +#define RC_BIT(p, prob, bit) { \ + RC_BIT_PRE(p, prob) \ + if (bit == 0) { range = newBound; ttt += (kBitModelTotal - ttt) >> kNumMoveBits; } \ + else { (p)->low += newBound; range -= newBound; ttt -= ttt >> kNumMoveBits; } \ + *(prob) = (CLzmaProb)ttt; \ + RC_NORM(p) \ + } + +#else + +#define RC_BIT(p, prob, bit) { \ + UInt32 mask; \ + RC_BIT_PRE(p, prob) \ + mask = 0 - (UInt32)bit; \ + range &= mask; \ + mask &= newBound; \ + range -= mask; \ + (p)->low += mask; \ + mask = (UInt32)bit - 1; \ + range += newBound & mask; \ + mask &= (kBitModelTotal - ((1 << kNumMoveBits) - 1)); \ + mask += ((1 << kNumMoveBits) - 1); \ + ttt += (Int32)(mask - ttt) >> kNumMoveBits; \ + *(prob) = (CLzmaProb)ttt; \ + RC_NORM(p) \ + } + +#endif + + + + +#define RC_BIT_0_BASE(p, prob) \ + range = newBound; *(prob) = (CLzmaProb)(ttt + ((kBitModelTotal - ttt) >> kNumMoveBits)); + +#define RC_BIT_1_BASE(p, prob) \ + range -= newBound; (p)->low += newBound; *(prob) = (CLzmaProb)(ttt - (ttt >> kNumMoveBits)); \ + +#define RC_BIT_0(p, prob) \ + RC_BIT_0_BASE(p, prob) \ + RC_NORM(p) + +#define RC_BIT_1(p, prob) \ + RC_BIT_1_BASE(p, prob) \ + RC_NORM(p) + +static void RangeEnc_EncodeBit_0(CRangeEnc *p, CLzmaProb *prob) { + UInt32 range, ttt, newBound; + range = p->range; + RC_BIT_PRE(p, prob) + RC_BIT_0(p, prob) + p->range = range; +} + +static void LitEnc_Encode(CRangeEnc *p, CLzmaProb *probs, UInt32 sym) +{ + UInt32 range = p->range; + sym |= 0x100; do { - p->range >>= 1; - p->low += p->range & (0 - ((value >> --numBits) & 1)); - if (p->range < kTopValue) - { - p->range <<= 8; - RangeEnc_ShiftLow(p); - } + UInt32 ttt, newBound; + // RangeEnc_EncodeBit(p, probs + (sym >> 8), (sym >> 7) & 1); + CLzmaProb *prob = probs + (sym >> 8); + UInt32 bit = (sym >> 7) & 1; + sym <<= 1; + RC_BIT(p, prob, bit); } - while (numBits != 0); + while (sym < 0x10000); + p->range = range; } -static void RangeEnc_EncodeBit(CRangeEnc *p, CLzmaProb *prob, UInt32 symbol) -{ - UInt32 ttt = *prob; - UInt32 newBound = (p->range >> kNumBitModelTotalBits) * ttt; - if (symbol == 0) - { - p->range = newBound; - ttt += (kBitModelTotal - ttt) >> kNumMoveBits; - } - else - { - p->low += newBound; - p->range -= newBound; - ttt -= ttt >> kNumMoveBits; - } - *prob = (CLzmaProb)ttt; - if (p->range < kTopValue) - { - p->range <<= 8; - RangeEnc_ShiftLow(p); - } -} - -static void LitEnc_Encode(CRangeEnc *p, CLzmaProb *probs, UInt32 symbol) -{ - symbol |= 0x100; - do - { - RangeEnc_EncodeBit(p, probs + (symbol >> 8), (symbol >> 7) & 1); - symbol <<= 1; - } - while (symbol < 0x10000); -} - -static void LitEnc_EncodeMatched(CRangeEnc *p, CLzmaProb *probs, UInt32 symbol, UInt32 matchByte) +static void LitEnc_EncodeMatched(CRangeEnc *p, CLzmaProb *probs, UInt32 sym, UInt32 matchByte) { + UInt32 range = p->range; UInt32 offs = 0x100; - symbol |= 0x100; + sym |= 0x100; do { + UInt32 ttt, newBound; + CLzmaProb *prob; + UInt32 bit; matchByte <<= 1; - RangeEnc_EncodeBit(p, probs + (offs + (matchByte & offs) + (symbol >> 8)), (symbol >> 7) & 1); - symbol <<= 1; - offs &= ~(matchByte ^ symbol); + // RangeEnc_EncodeBit(p, probs + (offs + (matchByte & offs) + (sym >> 8)), (sym >> 7) & 1); + prob = probs + (offs + (matchByte & offs) + (sym >> 8)); + bit = (sym >> 7) & 1; + sym <<= 1; + offs &= ~(matchByte ^ sym); + RC_BIT(p, prob, bit); } - while (symbol < 0x10000); + while (sym < 0x10000); + p->range = range; } -static void LzmaEnc_InitPriceTables(UInt32 *ProbPrices) + + +static void LzmaEnc_InitPriceTables(CProbPrice *ProbPrices) { UInt32 i; - for (i = (1 << kNumMoveReducingBits) / 2; i < kBitModelTotal; i += (1 << kNumMoveReducingBits)) + for (i = 0; i < (kBitModelTotal >> kNumMoveReducingBits); i++) { - const int kCyclesBits = kNumBitPriceShiftBits; - UInt32 w = i; - UInt32 bitCount = 0; - int j; + const unsigned kCyclesBits = kNumBitPriceShiftBits; + UInt32 w = (i << kNumMoveReducingBits) + (1 << (kNumMoveReducingBits - 1)); + unsigned bitCount = 0; + unsigned j; for (j = 0; j < kCyclesBits; j++) { w = w * w; @@ -666,567 +749,655 @@ static void LzmaEnc_InitPriceTables(UInt32 *ProbPrices) bitCount++; } } - ProbPrices[i >> kNumMoveReducingBits] = ((kNumBitModelTotalBits << kCyclesBits) - 15 - bitCount); + ProbPrices[i] = (CProbPrice)((kNumBitModelTotalBits << kCyclesBits) - 15 - bitCount); + // printf("\n%3d: %5d", i, ProbPrices[i]); } } -#define GET_PRICE(prob, symbol) \ - p->ProbPrices[((prob) ^ (((-(int)(symbol))) & (kBitModelTotal - 1))) >> kNumMoveReducingBits]; +#define GET_PRICE(prob, bit) \ + p->ProbPrices[((prob) ^ (unsigned)(((-(int)(bit))) & (kBitModelTotal - 1))) >> kNumMoveReducingBits]; -#define GET_PRICEa(prob, symbol) \ - ProbPrices[((prob) ^ ((-((int)(symbol))) & (kBitModelTotal - 1))) >> kNumMoveReducingBits]; +#define GET_PRICEa(prob, bit) \ + ProbPrices[((prob) ^ (unsigned)((-((int)(bit))) & (kBitModelTotal - 1))) >> kNumMoveReducingBits]; #define GET_PRICE_0(prob) p->ProbPrices[(prob) >> kNumMoveReducingBits] #define GET_PRICE_1(prob) p->ProbPrices[((prob) ^ (kBitModelTotal - 1)) >> kNumMoveReducingBits] -#define GET_PRICE_0a(prob) ProbPrices[(prob) >> kNumMoveReducingBits] -#define GET_PRICE_1a(prob) ProbPrices[((prob) ^ (kBitModelTotal - 1)) >> kNumMoveReducingBits] +#define GET_PRICEa_0(prob) ProbPrices[(prob) >> kNumMoveReducingBits] +#define GET_PRICEa_1(prob) ProbPrices[((prob) ^ (kBitModelTotal - 1)) >> kNumMoveReducingBits] -static UInt32 LitEnc_GetPrice(const CLzmaProb *probs, UInt32 symbol, const UInt32 *ProbPrices) + +static UInt32 LitEnc_GetPrice(const CLzmaProb *probs, UInt32 sym, const CProbPrice *ProbPrices) { UInt32 price = 0; - symbol |= 0x100; + sym |= 0x100; do { - price += GET_PRICEa(probs[symbol >> 8], (symbol >> 7) & 1); - symbol <<= 1; + unsigned bit = sym & 1; + sym >>= 1; + price += GET_PRICEa(probs[sym], bit); } - while (symbol < 0x10000); + while (sym >= 2); return price; } -static UInt32 LitEnc_GetPriceMatched(const CLzmaProb *probs, UInt32 symbol, UInt32 matchByte, const UInt32 *ProbPrices) + +static UInt32 LitEnc_Matched_GetPrice(const CLzmaProb *probs, UInt32 sym, UInt32 matchByte, const CProbPrice *ProbPrices) { UInt32 price = 0; UInt32 offs = 0x100; - symbol |= 0x100; + sym |= 0x100; do { matchByte <<= 1; - price += GET_PRICEa(probs[offs + (matchByte & offs) + (symbol >> 8)], (symbol >> 7) & 1); - symbol <<= 1; - offs &= ~(matchByte ^ symbol); + price += GET_PRICEa(probs[offs + (matchByte & offs) + (sym >> 8)], (sym >> 7) & 1); + sym <<= 1; + offs &= ~(matchByte ^ sym); } - while (symbol < 0x10000); + while (sym < 0x10000); return price; } -static void RcTree_Encode(CRangeEnc *rc, CLzmaProb *probs, int numBitLevels, UInt32 symbol) +static void RcTree_ReverseEncode(CRangeEnc *rc, CLzmaProb *probs, unsigned numBits, unsigned sym) { - UInt32 m = 1; - int i; - for (i = numBitLevels; i != 0;) + UInt32 range = rc->range; + unsigned m = 1; + do { - UInt32 bit; - i--; - bit = (symbol >> i) & 1; - RangeEnc_EncodeBit(rc, probs + m, bit); + UInt32 ttt, newBound; + unsigned bit = sym & 1; + // RangeEnc_EncodeBit(rc, probs + m, bit); + sym >>= 1; + RC_BIT(rc, probs + m, bit); m = (m << 1) | bit; } + while (--numBits); + rc->range = range; } -static void RcTree_ReverseEncode(CRangeEnc *rc, CLzmaProb *probs, int numBitLevels, UInt32 symbol) -{ - UInt32 m = 1; - int i; - for (i = 0; i < numBitLevels; i++) - { - UInt32 bit = symbol & 1; - RangeEnc_EncodeBit(rc, probs + m, bit); - m = (m << 1) | bit; - symbol >>= 1; - } -} - -static UInt32 RcTree_GetPrice(const CLzmaProb *probs, int numBitLevels, UInt32 symbol, const UInt32 *ProbPrices) -{ - UInt32 price = 0; - symbol |= (1 << numBitLevels); - while (symbol != 1) - { - price += GET_PRICEa(probs[symbol >> 1], symbol & 1); - symbol >>= 1; - } - return price; -} - -static UInt32 RcTree_ReverseGetPrice(const CLzmaProb *probs, int numBitLevels, UInt32 symbol, const UInt32 *ProbPrices) -{ - UInt32 price = 0; - UInt32 m = 1; - int i; - for (i = numBitLevels; i != 0; i--) - { - UInt32 bit = symbol & 1; - symbol >>= 1; - price += GET_PRICEa(probs[m], bit); - m = (m << 1) | bit; - } - return price; -} static void LenEnc_Init(CLenEnc *p) { unsigned i; - p->choice = p->choice2 = kProbInitValue; - for (i = 0; i < (LZMA_NUM_PB_STATES_MAX << kLenNumLowBits); i++) + for (i = 0; i < (LZMA_NUM_PB_STATES_MAX << (kLenNumLowBits + 1)); i++) p->low[i] = kProbInitValue; - for (i = 0; i < (LZMA_NUM_PB_STATES_MAX << kLenNumMidBits); i++) - p->mid[i] = kProbInitValue; for (i = 0; i < kLenNumHighSymbols; i++) p->high[i] = kProbInitValue; } -static void LenEnc_Encode(CLenEnc *p, CRangeEnc *rc, UInt32 symbol, UInt32 posState) +static void LenEnc_Encode(CLenEnc *p, CRangeEnc *rc, unsigned sym, unsigned posState) { - if (symbol < kLenNumLowSymbols) + UInt32 range, ttt, newBound; + CLzmaProb *probs = p->low; + range = rc->range; + RC_BIT_PRE(rc, probs); + if (sym >= kLenNumLowSymbols) { - RangeEnc_EncodeBit(rc, &p->choice, 0); - RcTree_Encode(rc, p->low + (posState << kLenNumLowBits), kLenNumLowBits, symbol); - } - else - { - RangeEnc_EncodeBit(rc, &p->choice, 1); - if (symbol < kLenNumLowSymbols + kLenNumMidSymbols) + RC_BIT_1(rc, probs); + probs += kLenNumLowSymbols; + RC_BIT_PRE(rc, probs); + if (sym >= kLenNumLowSymbols * 2) { - RangeEnc_EncodeBit(rc, &p->choice2, 0); - RcTree_Encode(rc, p->mid + (posState << kLenNumMidBits), kLenNumMidBits, symbol - kLenNumLowSymbols); + RC_BIT_1(rc, probs); + rc->range = range; + // RcTree_Encode(rc, p->high, kLenNumHighBits, sym - kLenNumLowSymbols * 2); + LitEnc_Encode(rc, p->high, sym - kLenNumLowSymbols * 2); + return; } - else + sym -= kLenNumLowSymbols; + } + + // RcTree_Encode(rc, probs + (posState << kLenNumLowBits), kLenNumLowBits, sym); + { + unsigned m; + unsigned bit; + RC_BIT_0(rc, probs); + probs += (posState << (1 + kLenNumLowBits)); + bit = (sym >> 2) ; RC_BIT(rc, probs + 1, bit); m = (1 << 1) + bit; + bit = (sym >> 1) & 1; RC_BIT(rc, probs + m, bit); m = (m << 1) + bit; + bit = sym & 1; RC_BIT(rc, probs + m, bit); + rc->range = range; + } +} + +static void SetPrices_3(const CLzmaProb *probs, UInt32 startPrice, UInt32 *prices, const CProbPrice *ProbPrices) +{ + unsigned i; + for (i = 0; i < 8; i += 2) + { + UInt32 price = startPrice; + UInt32 prob; + price += GET_PRICEa(probs[1 ], (i >> 2)); + price += GET_PRICEa(probs[2 + (i >> 2)], (i >> 1) & 1); + prob = probs[4 + (i >> 1)]; + prices[i ] = price + GET_PRICEa_0(prob); + prices[i + 1] = price + GET_PRICEa_1(prob); + } +} + + +MY_NO_INLINE static void MY_FAST_CALL LenPriceEnc_UpdateTables( + CLenPriceEnc *p, + unsigned numPosStates, + const CLenEnc *enc, + const CProbPrice *ProbPrices) +{ + UInt32 b; + + { + unsigned prob = enc->low[0]; + UInt32 a, c; + unsigned posState; + b = GET_PRICEa_1(prob); + a = GET_PRICEa_0(prob); + c = b + GET_PRICEa_0(enc->low[kLenNumLowSymbols]); + for (posState = 0; posState < numPosStates; posState++) { - RangeEnc_EncodeBit(rc, &p->choice2, 1); - RcTree_Encode(rc, p->high, kLenNumHighBits, symbol - kLenNumLowSymbols - kLenNumMidSymbols); + UInt32 *prices = p->prices[posState]; + const CLzmaProb *probs = enc->low + (posState << (1 + kLenNumLowBits)); + SetPrices_3(probs, a, prices, ProbPrices); + SetPrices_3(probs + kLenNumLowSymbols, c, prices + kLenNumLowSymbols, ProbPrices); + } + } + + /* + { + unsigned i; + UInt32 b; + a = GET_PRICEa_0(enc->low[0]); + for (i = 0; i < kLenNumLowSymbols; i++) + p->prices2[i] = a; + a = GET_PRICEa_1(enc->low[0]); + b = a + GET_PRICEa_0(enc->low[kLenNumLowSymbols]); + for (i = kLenNumLowSymbols; i < kLenNumLowSymbols * 2; i++) + p->prices2[i] = b; + a += GET_PRICEa_1(enc->low[kLenNumLowSymbols]); + } + */ + + // p->counter = numSymbols; + // p->counter = 64; + + { + unsigned i = p->tableSize; + + if (i > kLenNumLowSymbols * 2) + { + const CLzmaProb *probs = enc->high; + UInt32 *prices = p->prices[0] + kLenNumLowSymbols * 2; + i -= kLenNumLowSymbols * 2 - 1; + i >>= 1; + b += GET_PRICEa_1(enc->low[kLenNumLowSymbols]); + do + { + /* + p->prices2[i] = a + + // RcTree_GetPrice(enc->high, kLenNumHighBits, i - kLenNumLowSymbols * 2, ProbPrices); + LitEnc_GetPrice(probs, i - kLenNumLowSymbols * 2, ProbPrices); + */ + // UInt32 price = a + RcTree_GetPrice(probs, kLenNumHighBits - 1, sym, ProbPrices); + unsigned sym = --i + (1 << (kLenNumHighBits - 1)); + UInt32 price = b; + do + { + unsigned bit = sym & 1; + sym >>= 1; + price += GET_PRICEa(probs[sym], bit); + } + while (sym >= 2); + + { + unsigned prob = probs[(size_t)i + (1 << (kLenNumHighBits - 1))]; + prices[(size_t)i * 2 ] = price + GET_PRICEa_0(prob); + prices[(size_t)i * 2 + 1] = price + GET_PRICEa_1(prob); + } + } + while (i); + + { + unsigned posState; + size_t num = (p->tableSize - kLenNumLowSymbols * 2) * sizeof(p->prices[0][0]); + for (posState = 1; posState < numPosStates; posState++) + memcpy(p->prices[posState] + kLenNumLowSymbols * 2, p->prices[0] + kLenNumLowSymbols * 2, num); + } } } } -static void LenEnc_SetPrices(CLenEnc *p, UInt32 posState, UInt32 numSymbols, UInt32 *prices, const UInt32 *ProbPrices) -{ - UInt32 a0 = GET_PRICE_0a(p->choice); - UInt32 a1 = GET_PRICE_1a(p->choice); - UInt32 b0 = a1 + GET_PRICE_0a(p->choice2); - UInt32 b1 = a1 + GET_PRICE_1a(p->choice2); - UInt32 i = 0; - for (i = 0; i < kLenNumLowSymbols; i++) - { - if (i >= numSymbols) - return; - prices[i] = a0 + RcTree_GetPrice(p->low + (posState << kLenNumLowBits), kLenNumLowBits, i, ProbPrices); - } - for (; i < kLenNumLowSymbols + kLenNumMidSymbols; i++) - { - if (i >= numSymbols) - return; - prices[i] = b0 + RcTree_GetPrice(p->mid + (posState << kLenNumMidBits), kLenNumMidBits, i - kLenNumLowSymbols, ProbPrices); - } - for (; i < numSymbols; i++) - prices[i] = b1 + RcTree_GetPrice(p->high, kLenNumHighBits, i - kLenNumLowSymbols - kLenNumMidSymbols, ProbPrices); -} - -static void MY_FAST_CALL LenPriceEnc_UpdateTable(CLenPriceEnc *p, UInt32 posState, const UInt32 *ProbPrices) -{ - LenEnc_SetPrices(&p->p, posState, p->tableSize, p->prices[posState], ProbPrices); - p->counters[posState] = p->tableSize; -} - -static void LenPriceEnc_UpdateTables(CLenPriceEnc *p, UInt32 numPosStates, const UInt32 *ProbPrices) -{ - UInt32 posState; - for (posState = 0; posState < numPosStates; posState++) - LenPriceEnc_UpdateTable(p, posState, ProbPrices); -} - -static void LenEnc_Encode2(CLenPriceEnc *p, CRangeEnc *rc, UInt32 symbol, UInt32 posState, Bool updatePrice, const UInt32 *ProbPrices) -{ - LenEnc_Encode(&p->p, rc, symbol, posState); - if (updatePrice) - if (--p->counters[posState] == 0) - LenPriceEnc_UpdateTable(p, posState, ProbPrices); -} - - - - -static void MovePos(CLzmaEnc *p, UInt32 num) -{ +/* #ifdef SHOW_STAT g_STAT_OFFSET += num; printf("\n MovePos %u", num); #endif +*/ - if (num != 0) - { - p->additionalOffset += num; - p->matchFinder.Skip(p->matchFinderObj, num); - } -} +#define MOVE_POS(p, num) { \ + p->additionalOffset += (num); \ + p->matchFinder.Skip(p->matchFinderObj, (UInt32)(num)); } -static UInt32 ReadMatchDistances(CLzmaEnc *p, UInt32 *numDistancePairsRes) + +static unsigned ReadMatchDistances(CLzmaEnc *p, unsigned *numPairsRes) { - UInt32 lenRes = 0, numPairs; + unsigned numPairs; + + p->additionalOffset++; p->numAvail = p->matchFinder.GetNumAvailableBytes(p->matchFinderObj); numPairs = p->matchFinder.GetMatches(p->matchFinderObj, p->matches); + *numPairsRes = numPairs; #ifdef SHOW_STAT printf("\n i = %u numPairs = %u ", g_STAT_OFFSET, numPairs / 2); g_STAT_OFFSET++; { - UInt32 i; + unsigned i; for (i = 0; i < numPairs; i += 2) printf("%2u %6u | ", p->matches[i], p->matches[i + 1]); } #endif - if (numPairs > 0) + if (numPairs == 0) + return 0; { - lenRes = p->matches[numPairs - 2]; - if (lenRes == p->numFastBytes) + unsigned len = p->matches[(size_t)numPairs - 2]; + if (len != p->numFastBytes) + return len; { UInt32 numAvail = p->numAvail; if (numAvail > LZMA_MATCH_LEN_MAX) numAvail = LZMA_MATCH_LEN_MAX; { - const Byte *pbyCur = p->matchFinder.GetPointerToCurrentPos(p->matchFinderObj) - 1; - const Byte *pby = pbyCur + lenRes; - ptrdiff_t dif = (ptrdiff_t)-1 - p->matches[numPairs - 1]; - const Byte *pbyLim = pbyCur + numAvail; - for (; pby != pbyLim && *pby == pby[dif]; pby++); - lenRes = (UInt32)(pby - pbyCur); + const Byte *p1 = p->matchFinder.GetPointerToCurrentPos(p->matchFinderObj) - 1; + const Byte *p2 = p1 + len; + ptrdiff_t dif = (ptrdiff_t)-1 - p->matches[(size_t)numPairs - 1]; + const Byte *lim = p1 + numAvail; + for (; p2 != lim && *p2 == p2[dif]; p2++) + {} + return (unsigned)(p2 - p1); } } } - p->additionalOffset++; - *numDistancePairsRes = numPairs; - return lenRes; } +#define MARK_LIT ((UInt32)(Int32)-1) -#define MakeAsChar(p) (p)->backPrev = (UInt32)(-1); (p)->prev1IsChar = False; -#define MakeAsShortRep(p) (p)->backPrev = 0; (p)->prev1IsChar = False; -#define IsShortRep(p) ((p)->backPrev == 0) +#define MakeAs_Lit(p) { (p)->dist = MARK_LIT; (p)->extra = 0; } +#define MakeAs_ShortRep(p) { (p)->dist = 0; (p)->extra = 0; } +#define IsShortRep(p) ((p)->dist == 0) -static UInt32 GetRepLen1Price(CLzmaEnc *p, UInt32 state, UInt32 posState) -{ - return - GET_PRICE_0(p->isRepG0[state]) + - GET_PRICE_0(p->isRep0Long[state][posState]); -} -static UInt32 GetPureRepPrice(CLzmaEnc *p, UInt32 repIndex, UInt32 state, UInt32 posState) +#define GetPrice_ShortRep(p, state, posState) \ + ( GET_PRICE_0(p->isRepG0[state]) + GET_PRICE_0(p->isRep0Long[state][posState])) + +#define GetPrice_Rep_0(p, state, posState) ( \ + GET_PRICE_1(p->isMatch[state][posState]) \ + + GET_PRICE_1(p->isRep0Long[state][posState])) \ + + GET_PRICE_1(p->isRep[state]) \ + + GET_PRICE_0(p->isRepG0[state]) + +MY_FORCE_INLINE +static UInt32 GetPrice_PureRep(const CLzmaEnc *p, unsigned repIndex, size_t state, size_t posState) { UInt32 price; + UInt32 prob = p->isRepG0[state]; if (repIndex == 0) { - price = GET_PRICE_0(p->isRepG0[state]); + price = GET_PRICE_0(prob); price += GET_PRICE_1(p->isRep0Long[state][posState]); } else { - price = GET_PRICE_1(p->isRepG0[state]); + price = GET_PRICE_1(prob); + prob = p->isRepG1[state]; if (repIndex == 1) - price += GET_PRICE_0(p->isRepG1[state]); + price += GET_PRICE_0(prob); else { - price += GET_PRICE_1(p->isRepG1[state]); + price += GET_PRICE_1(prob); price += GET_PRICE(p->isRepG2[state], repIndex - 2); } } return price; } -static UInt32 GetRepPrice(CLzmaEnc *p, UInt32 repIndex, UInt32 len, UInt32 state, UInt32 posState) -{ - return p->repLenEnc.prices[posState][len - LZMA_MATCH_LEN_MIN] + - GetPureRepPrice(p, repIndex, state, posState); -} -static UInt32 Backward(CLzmaEnc *p, UInt32 *backRes, UInt32 cur) +static unsigned Backward(CLzmaEnc *p, unsigned cur) { - UInt32 posMem = p->opt[cur].posPrev; - UInt32 backMem = p->opt[cur].backPrev; - p->optimumEndIndex = cur; - do + unsigned wr = cur + 1; + p->optEnd = wr; + + for (;;) { - if (p->opt[cur].prev1IsChar) + UInt32 dist = p->opt[cur].dist; + unsigned len = (unsigned)p->opt[cur].len; + unsigned extra = (unsigned)p->opt[cur].extra; + cur -= len; + + if (extra) { - MakeAsChar(&p->opt[posMem]) - p->opt[posMem].posPrev = posMem - 1; - if (p->opt[cur].prev2) + wr--; + p->opt[wr].len = (UInt32)len; + cur -= extra; + len = extra; + if (extra == 1) { - p->opt[posMem - 1].prev1IsChar = False; - p->opt[posMem - 1].posPrev = p->opt[cur].posPrev2; - p->opt[posMem - 1].backPrev = p->opt[cur].backPrev2; + p->opt[wr].dist = dist; + dist = MARK_LIT; + } + else + { + p->opt[wr].dist = 0; + len--; + wr--; + p->opt[wr].dist = MARK_LIT; + p->opt[wr].len = 1; } } + + if (cur == 0) { - UInt32 posPrev = posMem; - UInt32 backCur = backMem; - - backMem = p->opt[posPrev].backPrev; - posMem = p->opt[posPrev].posPrev; - - p->opt[posPrev].backPrev = backCur; - p->opt[posPrev].posPrev = cur; - cur = posPrev; + p->backRes = dist; + p->optCur = wr; + return len; } + + wr--; + p->opt[wr].dist = dist; + p->opt[wr].len = (UInt32)len; } - while (cur != 0); - *backRes = p->opt[0].backPrev; - p->optimumCurrentIndex = p->opt[0].posPrev; - return p->optimumCurrentIndex; } -#define LIT_PROBS(pos, prevByte) (p->litProbs + ((((pos) & p->lpMask) << p->lc) + ((prevByte) >> (8 - p->lc))) * (UInt32)0x300) -static UInt32 GetOptimum(CLzmaEnc *p, UInt32 position, UInt32 *backRes) + +#define LIT_PROBS(pos, prevByte) \ + (p->litProbs + (UInt32)3 * (((((pos) << 8) + (prevByte)) & p->lpMask) << p->lc)) + + +static unsigned GetOptimum(CLzmaEnc *p, UInt32 position) { - UInt32 lenEnd, cur; - UInt32 reps[LZMA_NUM_REPS], repLens[LZMA_NUM_REPS]; + unsigned last, cur; + UInt32 reps[LZMA_NUM_REPS]; + unsigned repLens[LZMA_NUM_REPS]; UInt32 *matches; { - - UInt32 numAvail, mainLen, numPairs, repMaxIndex, i, posState, len; - UInt32 matchPrice, repMatchPrice, normalMatchPrice; - const Byte *data; - Byte curByte, matchByte; - - if (p->optimumEndIndex != p->optimumCurrentIndex) - { - const COptimal *opt = &p->opt[p->optimumCurrentIndex]; - UInt32 lenRes = opt->posPrev - p->optimumCurrentIndex; - *backRes = opt->backPrev; - p->optimumCurrentIndex = opt->posPrev; - return lenRes; - } - p->optimumCurrentIndex = p->optimumEndIndex = 0; - - if (p->additionalOffset == 0) - mainLen = ReadMatchDistances(p, &numPairs); - else - { - mainLen = p->longestMatchLength; - numPairs = p->numPairs; - } - - numAvail = p->numAvail; - if (numAvail < 2) - { - *backRes = (UInt32)(-1); - return 1; - } - if (numAvail > LZMA_MATCH_LEN_MAX) - numAvail = LZMA_MATCH_LEN_MAX; - - data = p->matchFinder.GetPointerToCurrentPos(p->matchFinderObj) - 1; - repMaxIndex = 0; - for (i = 0; i < LZMA_NUM_REPS; i++) - { - UInt32 lenTest; - const Byte *data2; - reps[i] = p->reps[i]; - data2 = data - reps[i] - 1; - if (data[0] != data2[0] || data[1] != data2[1]) + UInt32 numAvail; + unsigned numPairs, mainLen, repMaxIndex, i, posState; + UInt32 matchPrice, repMatchPrice; + const Byte *data; + Byte curByte, matchByte; + + p->optCur = p->optEnd = 0; + + if (p->additionalOffset == 0) + mainLen = ReadMatchDistances(p, &numPairs); + else { - repLens[i] = 0; - continue; + mainLen = p->longestMatchLen; + numPairs = p->numPairs; } - for (lenTest = 2; lenTest < numAvail && data[lenTest] == data2[lenTest]; lenTest++); - repLens[i] = lenTest; - if (lenTest > repLens[repMaxIndex]) - repMaxIndex = i; - } - if (repLens[repMaxIndex] >= p->numFastBytes) - { - UInt32 lenRes; - *backRes = repMaxIndex; - lenRes = repLens[repMaxIndex]; - MovePos(p, lenRes - 1); - return lenRes; - } + + numAvail = p->numAvail; + if (numAvail < 2) + { + p->backRes = MARK_LIT; + return 1; + } + if (numAvail > LZMA_MATCH_LEN_MAX) + numAvail = LZMA_MATCH_LEN_MAX; + + data = p->matchFinder.GetPointerToCurrentPos(p->matchFinderObj) - 1; + repMaxIndex = 0; + + for (i = 0; i < LZMA_NUM_REPS; i++) + { + unsigned len; + const Byte *data2; + reps[i] = p->reps[i]; + data2 = data - reps[i]; + if (data[0] != data2[0] || data[1] != data2[1]) + { + repLens[i] = 0; + continue; + } + for (len = 2; len < numAvail && data[len] == data2[len]; len++) + {} + repLens[i] = len; + if (len > repLens[repMaxIndex]) + repMaxIndex = i; + } + + if (repLens[repMaxIndex] >= p->numFastBytes) + { + unsigned len; + p->backRes = (UInt32)repMaxIndex; + len = repLens[repMaxIndex]; + MOVE_POS(p, len - 1) + return len; + } + + matches = p->matches; + + if (mainLen >= p->numFastBytes) + { + p->backRes = matches[(size_t)numPairs - 1] + LZMA_NUM_REPS; + MOVE_POS(p, mainLen - 1) + return mainLen; + } + + curByte = *data; + matchByte = *(data - reps[0]); - matches = p->matches; - if (mainLen >= p->numFastBytes) - { - *backRes = matches[numPairs - 1] + LZMA_NUM_REPS; - MovePos(p, mainLen - 1); - return mainLen; - } - curByte = *data; - matchByte = *(data - (reps[0] + 1)); - - if (mainLen < 2 && curByte != matchByte && repLens[repMaxIndex] < 2) - { - *backRes = (UInt32)-1; - return 1; - } - - p->opt[0].state = (CState)p->state; - - posState = (position & p->pbMask); - - { - const CLzmaProb *probs = LIT_PROBS(position, *(data - 1)); - p->opt[1].price = GET_PRICE_0(p->isMatch[p->state][posState]) + - (!IsCharState(p->state) ? - LitEnc_GetPriceMatched(probs, curByte, matchByte, p->ProbPrices) : + last = repLens[repMaxIndex]; + if (last <= mainLen) + last = mainLen; + + if (last < 2 && curByte != matchByte) + { + p->backRes = MARK_LIT; + return 1; + } + + p->opt[0].state = (CState)p->state; + + posState = (position & p->pbMask); + + { + const CLzmaProb *probs = LIT_PROBS(position, *(data - 1)); + p->opt[1].price = GET_PRICE_0(p->isMatch[p->state][posState]) + + (!IsLitState(p->state) ? + LitEnc_Matched_GetPrice(probs, curByte, matchByte, p->ProbPrices) : LitEnc_GetPrice(probs, curByte, p->ProbPrices)); - } - - MakeAsChar(&p->opt[1]); - - matchPrice = GET_PRICE_1(p->isMatch[p->state][posState]); - repMatchPrice = matchPrice + GET_PRICE_1(p->isRep[p->state]); - - if (matchByte == curByte) - { - UInt32 shortRepPrice = repMatchPrice + GetRepLen1Price(p, p->state, posState); - if (shortRepPrice < p->opt[1].price) - { - p->opt[1].price = shortRepPrice; - MakeAsShortRep(&p->opt[1]); } - } - lenEnd = ((mainLen >= repLens[repMaxIndex]) ? mainLen : repLens[repMaxIndex]); - if (lenEnd < 2) - { - *backRes = p->opt[1].backPrev; - return 1; - } - - p->opt[1].posPrev = 0; - for (i = 0; i < LZMA_NUM_REPS; i++) - p->opt[0].backs[i] = reps[i]; - - len = lenEnd; - do - p->opt[len--].price = kInfinityPrice; - while (len >= 2); - - for (i = 0; i < LZMA_NUM_REPS; i++) - { - UInt32 repLen = repLens[i]; - UInt32 price; - if (repLen < 2) - continue; - price = repMatchPrice + GetPureRepPrice(p, i, p->state, posState); - do + MakeAs_Lit(&p->opt[1]); + + matchPrice = GET_PRICE_1(p->isMatch[p->state][posState]); + repMatchPrice = matchPrice + GET_PRICE_1(p->isRep[p->state]); + + // 18.06 + if (matchByte == curByte && repLens[0] == 0) { - UInt32 curAndLenPrice = price + p->repLenEnc.prices[posState][repLen - 2]; - COptimal *opt = &p->opt[repLen]; - if (curAndLenPrice < opt->price) + UInt32 shortRepPrice = repMatchPrice + GetPrice_ShortRep(p, p->state, posState); + if (shortRepPrice < p->opt[1].price) { - opt->price = curAndLenPrice; - opt->posPrev = 0; - opt->backPrev = i; - opt->prev1IsChar = False; + p->opt[1].price = shortRepPrice; + MakeAs_ShortRep(&p->opt[1]); + } + if (last < 2) + { + p->backRes = p->opt[1].dist; + return 1; } } - while (--repLen >= 2); - } - - normalMatchPrice = matchPrice + GET_PRICE_0(p->isRep[p->state]); - - len = ((repLens[0] >= 2) ? repLens[0] + 1 : 2); - if (len <= mainLen) - { - UInt32 offs = 0; - while (len > matches[offs]) - offs += 2; - for (; ; len++) + + p->opt[1].len = 1; + + p->opt[0].reps[0] = reps[0]; + p->opt[0].reps[1] = reps[1]; + p->opt[0].reps[2] = reps[2]; + p->opt[0].reps[3] = reps[3]; + + // ---------- REP ---------- + + for (i = 0; i < LZMA_NUM_REPS; i++) { - COptimal *opt; - UInt32 distance = matches[offs + 1]; + unsigned repLen = repLens[i]; + UInt32 price; + if (repLen < 2) + continue; + price = repMatchPrice + GetPrice_PureRep(p, i, p->state, posState); + do + { + UInt32 price2 = price + GET_PRICE_LEN(&p->repLenEnc, posState, repLen); + COptimal *opt = &p->opt[repLen]; + if (price2 < opt->price) + { + opt->price = price2; + opt->len = (UInt32)repLen; + opt->dist = (UInt32)i; + opt->extra = 0; + } + } + while (--repLen >= 2); + } + + + // ---------- MATCH ---------- + { + unsigned len = repLens[0] + 1; + if (len <= mainLen) + { + unsigned offs = 0; + UInt32 normalMatchPrice = matchPrice + GET_PRICE_0(p->isRep[p->state]); - UInt32 curAndLenPrice = normalMatchPrice + p->lenEnc.prices[posState][len - LZMA_MATCH_LEN_MIN]; - UInt32 lenToPosState = GetLenToPosState(len); - if (distance < kNumFullDistances) - curAndLenPrice += p->distancesPrices[lenToPosState][distance]; - else - { - UInt32 slot; - GetPosSlot2(distance, slot); - curAndLenPrice += p->alignPrices[distance & kAlignMask] + p->posSlotPrices[lenToPosState][slot]; - } - opt = &p->opt[len]; - if (curAndLenPrice < opt->price) - { - opt->price = curAndLenPrice; - opt->posPrev = 0; - opt->backPrev = distance + LZMA_NUM_REPS; - opt->prev1IsChar = False; - } - if (len == matches[offs]) - { - offs += 2; - if (offs == numPairs) - break; + if (len < 2) + len = 2; + else + while (len > matches[offs]) + offs += 2; + + for (; ; len++) + { + COptimal *opt; + UInt32 dist = matches[(size_t)offs + 1]; + UInt32 price = normalMatchPrice + GET_PRICE_LEN(&p->lenEnc, posState, len); + unsigned lenToPosState = GetLenToPosState(len); + + if (dist < kNumFullDistances) + price += p->distancesPrices[lenToPosState][dist & (kNumFullDistances - 1)]; + else + { + unsigned slot; + GetPosSlot2(dist, slot); + price += p->alignPrices[dist & kAlignMask]; + price += p->posSlotPrices[lenToPosState][slot]; + } + + opt = &p->opt[len]; + + if (price < opt->price) + { + opt->price = price; + opt->len = (UInt32)len; + opt->dist = dist + LZMA_NUM_REPS; + opt->extra = 0; + } + + if (len == matches[offs]) + { + offs += 2; + if (offs == numPairs) + break; + } + } } } - } + - cur = 0; + cur = 0; #ifdef SHOW_STAT2 /* if (position >= 0) */ { unsigned i; printf("\n pos = %4X", position); - for (i = cur; i <= lenEnd; i++) + for (i = cur; i <= last; i++) printf("\nprice[%4X] = %u", position - cur + i, p->opt[i].price); } #endif - } + + + // ---------- Optimal Parsing ---------- + for (;;) { - UInt32 numAvail; - UInt32 numAvailFull, newLen, numPairs, posPrev, state, posState, startLen; - UInt32 curPrice, curAnd1Price, matchPrice, repMatchPrice; - Bool nextIsChar; + unsigned numAvail; + UInt32 numAvailFull; + unsigned newLen, numPairs, prev, state, posState, startLen; + UInt32 litPrice, matchPrice, repMatchPrice; + BoolInt nextIsLit; Byte curByte, matchByte; const Byte *data; - COptimal *curOpt; - COptimal *nextOpt; + COptimal *curOpt, *nextOpt; - cur++; - if (cur == lenEnd) - return Backward(p, backRes, cur); + if (++cur == last) + break; + + // 18.06 + if (cur >= kNumOpts - 64) + { + unsigned j, best; + UInt32 price = p->opt[cur].price; + best = cur; + for (j = cur + 1; j <= last; j++) + { + UInt32 price2 = p->opt[j].price; + if (price >= price2) + { + price = price2; + best = j; + } + } + { + unsigned delta = best - cur; + if (delta != 0) + { + MOVE_POS(p, delta); + } + } + cur = best; + break; + } newLen = ReadMatchDistances(p, &numPairs); + if (newLen >= p->numFastBytes) { p->numPairs = numPairs; - p->longestMatchLength = newLen; - return Backward(p, backRes, cur); + p->longestMatchLen = newLen; + break; } - position++; + curOpt = &p->opt[cur]; - posPrev = curOpt->posPrev; - if (curOpt->prev1IsChar) - { - posPrev--; - if (curOpt->prev2) - { - state = p->opt[curOpt->posPrev2].state; - if (curOpt->backPrev2 < LZMA_NUM_REPS) - state = kRepNextStates[state]; - else - state = kMatchNextStates[state]; - } - else - state = p->opt[posPrev].state; - state = kLiteralNextStates[state]; - } - else - state = p->opt[posPrev].state; - if (posPrev == cur - 1) + + position++; + + // we need that check here, if skip_items in p->opt are possible + /* + if (curOpt->price >= kInfinityPrice) + continue; + */ + + prev = cur - curOpt->len; + + if (curOpt->len == 1) { + state = (unsigned)p->opt[prev].state; if (IsShortRep(curOpt)) state = kShortRepNextStates[state]; else @@ -1234,357 +1405,499 @@ static UInt32 GetOptimum(CLzmaEnc *p, UInt32 position, UInt32 *backRes) } else { - UInt32 pos; const COptimal *prevOpt; - if (curOpt->prev1IsChar && curOpt->prev2) + UInt32 b0; + UInt32 dist = curOpt->dist; + + if (curOpt->extra) { - posPrev = curOpt->posPrev2; - pos = curOpt->backPrev2; - state = kRepNextStates[state]; + prev -= (unsigned)curOpt->extra; + state = kState_RepAfterLit; + if (curOpt->extra == 1) + state = (dist < LZMA_NUM_REPS ? kState_RepAfterLit : kState_MatchAfterLit); } else { - pos = curOpt->backPrev; - if (pos < LZMA_NUM_REPS) + state = (unsigned)p->opt[prev].state; + if (dist < LZMA_NUM_REPS) state = kRepNextStates[state]; else state = kMatchNextStates[state]; } - prevOpt = &p->opt[posPrev]; - if (pos < LZMA_NUM_REPS) + + prevOpt = &p->opt[prev]; + b0 = prevOpt->reps[0]; + + if (dist < LZMA_NUM_REPS) { - UInt32 i; - reps[0] = prevOpt->backs[pos]; - for (i = 1; i <= pos; i++) - reps[i] = prevOpt->backs[i - 1]; - for (; i < LZMA_NUM_REPS; i++) - reps[i] = prevOpt->backs[i]; + if (dist == 0) + { + reps[0] = b0; + reps[1] = prevOpt->reps[1]; + reps[2] = prevOpt->reps[2]; + reps[3] = prevOpt->reps[3]; + } + else + { + reps[1] = b0; + b0 = prevOpt->reps[1]; + if (dist == 1) + { + reps[0] = b0; + reps[2] = prevOpt->reps[2]; + reps[3] = prevOpt->reps[3]; + } + else + { + reps[2] = b0; + reps[0] = prevOpt->reps[dist]; + reps[3] = prevOpt->reps[dist ^ 1]; + } + } } else { - UInt32 i; - reps[0] = (pos - LZMA_NUM_REPS); - for (i = 1; i < LZMA_NUM_REPS; i++) - reps[i] = prevOpt->backs[i - 1]; + reps[0] = (dist - LZMA_NUM_REPS + 1); + reps[1] = b0; + reps[2] = prevOpt->reps[1]; + reps[3] = prevOpt->reps[2]; } } + curOpt->state = (CState)state; + curOpt->reps[0] = reps[0]; + curOpt->reps[1] = reps[1]; + curOpt->reps[2] = reps[2]; + curOpt->reps[3] = reps[3]; - curOpt->backs[0] = reps[0]; - curOpt->backs[1] = reps[1]; - curOpt->backs[2] = reps[2]; - curOpt->backs[3] = reps[3]; - - curPrice = curOpt->price; - nextIsChar = False; data = p->matchFinder.GetPointerToCurrentPos(p->matchFinderObj) - 1; curByte = *data; - matchByte = *(data - (reps[0] + 1)); + matchByte = *(data - reps[0]); posState = (position & p->pbMask); - curAnd1Price = curPrice + GET_PRICE_0(p->isMatch[state][posState]); + /* + The order of Price checks: + < LIT + <= SHORT_REP + < LIT : REP_0 + < REP [ : LIT : REP_0 ] + < MATCH [ : LIT : REP_0 ] + */ + + { + UInt32 curPrice = curOpt->price; + unsigned prob = p->isMatch[state][posState]; + matchPrice = curPrice + GET_PRICE_1(prob); + litPrice = curPrice + GET_PRICE_0(prob); + } + + nextOpt = &p->opt[(size_t)cur + 1]; + nextIsLit = False; + + // here we can allow skip_items in p->opt, if we don't check (nextOpt->price < kInfinityPrice) + // 18.new.06 + if ((nextOpt->price < kInfinityPrice + // && !IsLitState(state) + && matchByte == curByte) + || litPrice > nextOpt->price + ) + litPrice = 0; + else { const CLzmaProb *probs = LIT_PROBS(position, *(data - 1)); - curAnd1Price += - (!IsCharState(state) ? - LitEnc_GetPriceMatched(probs, curByte, matchByte, p->ProbPrices) : + litPrice += (!IsLitState(state) ? + LitEnc_Matched_GetPrice(probs, curByte, matchByte, p->ProbPrices) : LitEnc_GetPrice(probs, curByte, p->ProbPrices)); - } - - nextOpt = &p->opt[cur + 1]; - - if (curAnd1Price < nextOpt->price) - { - nextOpt->price = curAnd1Price; - nextOpt->posPrev = cur; - MakeAsChar(nextOpt); - nextIsChar = True; - } - - matchPrice = curPrice + GET_PRICE_1(p->isMatch[state][posState]); - repMatchPrice = matchPrice + GET_PRICE_1(p->isRep[state]); - - if (matchByte == curByte && !(nextOpt->posPrev < cur && nextOpt->backPrev == 0)) - { - UInt32 shortRepPrice = repMatchPrice + GetRepLen1Price(p, state, posState); - if (shortRepPrice <= nextOpt->price) + + if (litPrice < nextOpt->price) { - nextOpt->price = shortRepPrice; - nextOpt->posPrev = cur; - MakeAsShortRep(nextOpt); - nextIsChar = True; + nextOpt->price = litPrice; + nextOpt->len = 1; + MakeAs_Lit(nextOpt); + nextIsLit = True; } } + + repMatchPrice = matchPrice + GET_PRICE_1(p->isRep[state]); + numAvailFull = p->numAvail; { - UInt32 temp = kNumOpts - 1 - cur; - if (temp < numAvailFull) - numAvailFull = temp; + unsigned temp = kNumOpts - 1 - cur; + if (numAvailFull > temp) + numAvailFull = (UInt32)temp; } + // 18.06 + // ---------- SHORT_REP ---------- + if (IsLitState(state)) // 18.new + if (matchByte == curByte) + if (repMatchPrice < nextOpt->price) // 18.new + // if (numAvailFull < 2 || data[1] != *(data - reps[0] + 1)) + if ( + // nextOpt->price >= kInfinityPrice || + nextOpt->len < 2 // we can check nextOpt->len, if skip items are not allowed in p->opt + || (nextOpt->dist != 0 + // && nextOpt->extra <= 1 // 17.old + ) + ) + { + UInt32 shortRepPrice = repMatchPrice + GetPrice_ShortRep(p, state, posState); + // if (shortRepPrice <= nextOpt->price) // 17.old + if (shortRepPrice < nextOpt->price) // 18.new + { + nextOpt->price = shortRepPrice; + nextOpt->len = 1; + MakeAs_ShortRep(nextOpt); + nextIsLit = False; + } + } + if (numAvailFull < 2) continue; numAvail = (numAvailFull <= p->numFastBytes ? numAvailFull : p->numFastBytes); - if (!nextIsChar && matchByte != curByte) /* speed optimization */ - { - /* try Literal + rep0 */ - UInt32 temp; - UInt32 lenTest2; - const Byte *data2 = data - reps[0] - 1; - UInt32 limit = p->numFastBytes + 1; - if (limit > numAvailFull) - limit = numAvailFull; + // numAvail <= p->numFastBytes - for (temp = 1; temp < limit && data[temp] == data2[temp]; temp++); - lenTest2 = temp - 1; - if (lenTest2 >= 2) + // ---------- LIT : REP_0 ---------- + + if (!nextIsLit + && litPrice != 0 // 18.new + && matchByte != curByte + && numAvailFull > 2) + { + const Byte *data2 = data - reps[0]; + if (data[1] == data2[1] && data[2] == data2[2]) { - UInt32 state2 = kLiteralNextStates[state]; - UInt32 posStateNext = (position + 1) & p->pbMask; - UInt32 nextRepMatchPrice = curAnd1Price + - GET_PRICE_1(p->isMatch[state2][posStateNext]) + - GET_PRICE_1(p->isRep[state2]); - /* for (; lenTest2 >= 2; lenTest2--) */ + unsigned len; + unsigned limit = p->numFastBytes + 1; + if (limit > numAvailFull) + limit = numAvailFull; + for (len = 3; len < limit && data[len] == data2[len]; len++) + {} + { - UInt32 curAndLenPrice; - COptimal *opt; - UInt32 offset = cur + 1 + lenTest2; - while (lenEnd < offset) - p->opt[++lenEnd].price = kInfinityPrice; - curAndLenPrice = nextRepMatchPrice + GetRepPrice(p, 0, lenTest2, state2, posStateNext); - opt = &p->opt[offset]; - if (curAndLenPrice < opt->price) + unsigned state2 = kLiteralNextStates[state]; + unsigned posState2 = (position + 1) & p->pbMask; + UInt32 price = litPrice + GetPrice_Rep_0(p, state2, posState2); { - opt->price = curAndLenPrice; - opt->posPrev = cur + 1; - opt->backPrev = 0; - opt->prev1IsChar = True; - opt->prev2 = False; + unsigned offset = cur + len; + + if (last < offset) + last = offset; + + // do + { + UInt32 price2; + COptimal *opt; + len--; + // price2 = price + GetPrice_Len_Rep_0(p, len, state2, posState2); + price2 = price + GET_PRICE_LEN(&p->repLenEnc, posState2, len); + + opt = &p->opt[offset]; + // offset--; + if (price2 < opt->price) + { + opt->price = price2; + opt->len = (UInt32)len; + opt->dist = 0; + opt->extra = 1; + } + } + // while (len >= 3); } } } } startLen = 2; /* speed optimization */ + { - UInt32 repIndex; - for (repIndex = 0; repIndex < LZMA_NUM_REPS; repIndex++) - { - UInt32 lenTest; - UInt32 lenTestTemp; - UInt32 price; - const Byte *data2 = data - reps[repIndex] - 1; - if (data[0] != data2[0] || data[1] != data2[1]) - continue; - for (lenTest = 2; lenTest < numAvail && data[lenTest] == data2[lenTest]; lenTest++); - while (lenEnd < cur + lenTest) - p->opt[++lenEnd].price = kInfinityPrice; - lenTestTemp = lenTest; - price = repMatchPrice + GetPureRepPrice(p, repIndex, state, posState); - do + // ---------- REP ---------- + unsigned repIndex = 0; // 17.old + // unsigned repIndex = IsLitState(state) ? 0 : 1; // 18.notused + for (; repIndex < LZMA_NUM_REPS; repIndex++) { - UInt32 curAndLenPrice = price + p->repLenEnc.prices[posState][lenTest - 2]; - COptimal *opt = &p->opt[cur + lenTest]; - if (curAndLenPrice < opt->price) - { - opt->price = curAndLenPrice; - opt->posPrev = cur; - opt->backPrev = repIndex; - opt->prev1IsChar = False; - } - } - while (--lenTest >= 2); - lenTest = lenTestTemp; - - if (repIndex == 0) - startLen = lenTest + 1; + unsigned len; + UInt32 price; + const Byte *data2 = data - reps[repIndex]; + if (data[0] != data2[0] || data[1] != data2[1]) + continue; - /* if (_maxMode) */ + for (len = 2; len < numAvail && data[len] == data2[len]; len++) + {} + + // if (len < startLen) continue; // 18.new: speed optimization + { - UInt32 lenTest2 = lenTest + 1; - UInt32 limit = lenTest2 + p->numFastBytes; - if (limit > numAvailFull) - limit = numAvailFull; - for (; lenTest2 < limit && data[lenTest2] == data2[lenTest2]; lenTest2++); - lenTest2 -= lenTest + 1; - if (lenTest2 >= 2) + unsigned offset = cur + len; + if (last < offset) + last = offset; + } + { + unsigned len2 = len; + price = repMatchPrice + GetPrice_PureRep(p, repIndex, state, posState); + do { - UInt32 nextRepMatchPrice; - UInt32 state2 = kRepNextStates[state]; - UInt32 posStateNext = (position + lenTest) & p->pbMask; - UInt32 curAndLenCharPrice = - price + p->repLenEnc.prices[posState][lenTest - 2] + - GET_PRICE_0(p->isMatch[state2][posStateNext]) + - LitEnc_GetPriceMatched(LIT_PROBS(position + lenTest, data[lenTest - 1]), - data[lenTest], data2[lenTest], p->ProbPrices); - state2 = kLiteralNextStates[state2]; - posStateNext = (position + lenTest + 1) & p->pbMask; - nextRepMatchPrice = curAndLenCharPrice + - GET_PRICE_1(p->isMatch[state2][posStateNext]) + - GET_PRICE_1(p->isRep[state2]); - - /* for (; lenTest2 >= 2; lenTest2--) */ + UInt32 price2 = price + GET_PRICE_LEN(&p->repLenEnc, posState, len2); + COptimal *opt = &p->opt[cur + len2]; + if (price2 < opt->price) { - UInt32 curAndLenPrice; - COptimal *opt; - UInt32 offset = cur + lenTest + 1 + lenTest2; - while (lenEnd < offset) - p->opt[++lenEnd].price = kInfinityPrice; - curAndLenPrice = nextRepMatchPrice + GetRepPrice(p, 0, lenTest2, state2, posStateNext); - opt = &p->opt[offset]; - if (curAndLenPrice < opt->price) - { - opt->price = curAndLenPrice; - opt->posPrev = cur + lenTest + 1; - opt->backPrev = 0; - opt->prev1IsChar = True; - opt->prev2 = True; - opt->posPrev2 = cur; - opt->backPrev2 = repIndex; - } + opt->price = price2; + opt->len = (UInt32)len2; + opt->dist = (UInt32)repIndex; + opt->extra = 0; } } + while (--len2 >= 2); } + + if (repIndex == 0) startLen = len + 1; // 17.old + // startLen = len + 1; // 18.new + + /* if (_maxMode) */ + { + // ---------- REP : LIT : REP_0 ---------- + // numFastBytes + 1 + numFastBytes + + unsigned len2 = len + 1; + unsigned limit = len2 + p->numFastBytes; + if (limit > numAvailFull) + limit = numAvailFull; + + len2 += 2; + if (len2 <= limit) + if (data[len2 - 2] == data2[len2 - 2]) + if (data[len2 - 1] == data2[len2 - 1]) + { + unsigned state2 = kRepNextStates[state]; + unsigned posState2 = (position + len) & p->pbMask; + price += GET_PRICE_LEN(&p->repLenEnc, posState, len) + + GET_PRICE_0(p->isMatch[state2][posState2]) + + LitEnc_Matched_GetPrice(LIT_PROBS(position + len, data[(size_t)len - 1]), + data[len], data2[len], p->ProbPrices); + + // state2 = kLiteralNextStates[state2]; + state2 = kState_LitAfterRep; + posState2 = (posState2 + 1) & p->pbMask; + + + price += GetPrice_Rep_0(p, state2, posState2); + + for (; len2 < limit && data[len2] == data2[len2]; len2++) + {} + + len2 -= len; + // if (len2 >= 3) + { + { + unsigned offset = cur + len + len2; + + if (last < offset) + last = offset; + // do + { + UInt32 price2; + COptimal *opt; + len2--; + // price2 = price + GetPrice_Len_Rep_0(p, len2, state2, posState2); + price2 = price + GET_PRICE_LEN(&p->repLenEnc, posState2, len2); + + opt = &p->opt[offset]; + // offset--; + if (price2 < opt->price) + { + opt->price = price2; + opt->len = (UInt32)len2; + opt->extra = (CExtra)(len + 1); + opt->dist = (UInt32)repIndex; + } + } + // while (len2 >= 3); + } + } + } + } + } } - } - /* for (UInt32 lenTest = 2; lenTest <= newLen; lenTest++) */ + + + // ---------- MATCH ---------- + /* for (unsigned len = 2; len <= newLen; len++) */ if (newLen > numAvail) { newLen = numAvail; for (numPairs = 0; newLen > matches[numPairs]; numPairs += 2); - matches[numPairs] = newLen; + matches[numPairs] = (UInt32)newLen; numPairs += 2; } + + // startLen = 2; /* speed optimization */ + if (newLen >= startLen) { UInt32 normalMatchPrice = matchPrice + GET_PRICE_0(p->isRep[state]); - UInt32 offs, curBack, posSlot; - UInt32 lenTest; - while (lenEnd < cur + newLen) - p->opt[++lenEnd].price = kInfinityPrice; + UInt32 dist; + unsigned offs, posSlot, len; + + { + unsigned offset = cur + newLen; + if (last < offset) + last = offset; + } offs = 0; while (startLen > matches[offs]) offs += 2; - curBack = matches[offs + 1]; - GetPosSlot2(curBack, posSlot); - for (lenTest = /*2*/ startLen; ; lenTest++) + dist = matches[(size_t)offs + 1]; + + // if (dist >= kNumFullDistances) + GetPosSlot2(dist, posSlot); + + for (len = /*2*/ startLen; ; len++) { - UInt32 curAndLenPrice = normalMatchPrice + p->lenEnc.prices[posState][lenTest - LZMA_MATCH_LEN_MIN]; + UInt32 price = normalMatchPrice + GET_PRICE_LEN(&p->lenEnc, posState, len); { - UInt32 lenToPosState = GetLenToPosState(lenTest); - COptimal *opt; - if (curBack < kNumFullDistances) - curAndLenPrice += p->distancesPrices[lenToPosState][curBack]; - else - curAndLenPrice += p->posSlotPrices[lenToPosState][posSlot] + p->alignPrices[curBack & kAlignMask]; - - opt = &p->opt[cur + lenTest]; - if (curAndLenPrice < opt->price) - { - opt->price = curAndLenPrice; - opt->posPrev = cur; - opt->backPrev = curBack + LZMA_NUM_REPS; - opt->prev1IsChar = False; - } + COptimal *opt; + unsigned lenNorm = len - 2; + lenNorm = GetLenToPosState2(lenNorm); + if (dist < kNumFullDistances) + price += p->distancesPrices[lenNorm][dist & (kNumFullDistances - 1)]; + else + price += p->posSlotPrices[lenNorm][posSlot] + p->alignPrices[dist & kAlignMask]; + + opt = &p->opt[cur + len]; + if (price < opt->price) + { + opt->price = price; + opt->len = (UInt32)len; + opt->dist = dist + LZMA_NUM_REPS; + opt->extra = 0; + } } - if (/*_maxMode && */lenTest == matches[offs]) + if (len == matches[offs]) { - /* Try Match + Literal + Rep0 */ - const Byte *data2 = data - curBack - 1; - UInt32 lenTest2 = lenTest + 1; - UInt32 limit = lenTest2 + p->numFastBytes; + // if (p->_maxMode) { + // MATCH : LIT : REP_0 + + const Byte *data2 = data - dist - 1; + unsigned len2 = len + 1; + unsigned limit = len2 + p->numFastBytes; if (limit > numAvailFull) limit = numAvailFull; - for (; lenTest2 < limit && data[lenTest2] == data2[lenTest2]; lenTest2++); - lenTest2 -= lenTest + 1; - if (lenTest2 >= 2) + + len2 += 2; + if (len2 <= limit) + if (data[len2 - 2] == data2[len2 - 2]) + if (data[len2 - 1] == data2[len2 - 1]) { - UInt32 nextRepMatchPrice; - UInt32 state2 = kMatchNextStates[state]; - UInt32 posStateNext = (position + lenTest) & p->pbMask; - UInt32 curAndLenCharPrice = curAndLenPrice + - GET_PRICE_0(p->isMatch[state2][posStateNext]) + - LitEnc_GetPriceMatched(LIT_PROBS(position + lenTest, data[lenTest - 1]), - data[lenTest], data2[lenTest], p->ProbPrices); - state2 = kLiteralNextStates[state2]; - posStateNext = (posStateNext + 1) & p->pbMask; - nextRepMatchPrice = curAndLenCharPrice + - GET_PRICE_1(p->isMatch[state2][posStateNext]) + - GET_PRICE_1(p->isRep[state2]); - - /* for (; lenTest2 >= 2; lenTest2--) */ + for (; len2 < limit && data[len2] == data2[len2]; len2++) + {} + + len2 -= len; + + // if (len2 >= 3) + { + unsigned state2 = kMatchNextStates[state]; + unsigned posState2 = (position + len) & p->pbMask; + unsigned offset; + price += GET_PRICE_0(p->isMatch[state2][posState2]); + price += LitEnc_Matched_GetPrice(LIT_PROBS(position + len, data[(size_t)len - 1]), + data[len], data2[len], p->ProbPrices); + + // state2 = kLiteralNextStates[state2]; + state2 = kState_LitAfterMatch; + + posState2 = (posState2 + 1) & p->pbMask; + price += GetPrice_Rep_0(p, state2, posState2); + + offset = cur + len + len2; + + if (last < offset) + last = offset; + // do { - UInt32 offset = cur + lenTest + 1 + lenTest2; - UInt32 curAndLenPrice2; + UInt32 price2; COptimal *opt; - while (lenEnd < offset) - p->opt[++lenEnd].price = kInfinityPrice; - curAndLenPrice2 = nextRepMatchPrice + GetRepPrice(p, 0, lenTest2, state2, posStateNext); + len2--; + // price2 = price + GetPrice_Len_Rep_0(p, len2, state2, posState2); + price2 = price + GET_PRICE_LEN(&p->repLenEnc, posState2, len2); opt = &p->opt[offset]; - if (curAndLenPrice2 < opt->price) + // offset--; + if (price2 < opt->price) { - opt->price = curAndLenPrice2; - opt->posPrev = cur + lenTest + 1; - opt->backPrev = 0; - opt->prev1IsChar = True; - opt->prev2 = True; - opt->posPrev2 = cur; - opt->backPrev2 = curBack + LZMA_NUM_REPS; + opt->price = price2; + opt->len = (UInt32)len2; + opt->extra = (CExtra)(len + 1); + opt->dist = dist + LZMA_NUM_REPS; } } + // while (len2 >= 3); } + + } + offs += 2; if (offs == numPairs) break; - curBack = matches[offs + 1]; - if (curBack >= kNumFullDistances) - GetPosSlot2(curBack, posSlot); + dist = matches[(size_t)offs + 1]; + // if (dist >= kNumFullDistances) + GetPosSlot2(dist, posSlot); } } } } + + do + p->opt[last].price = kInfinityPrice; + while (--last); + + return Backward(p, cur); } + + #define ChangePair(smallDist, bigDist) (((bigDist) >> 7) > (smallDist)) -static UInt32 GetOptimumFast(CLzmaEnc *p, UInt32 *backRes) + + +static unsigned GetOptimumFast(CLzmaEnc *p) { - UInt32 numAvail, mainLen, mainDist, numPairs, repIndex, repLen, i; + UInt32 numAvail, mainDist; + unsigned mainLen, numPairs, repIndex, repLen, i; const Byte *data; - const UInt32 *matches; if (p->additionalOffset == 0) mainLen = ReadMatchDistances(p, &numPairs); else { - mainLen = p->longestMatchLength; + mainLen = p->longestMatchLen; numPairs = p->numPairs; } numAvail = p->numAvail; - *backRes = (UInt32)-1; + p->backRes = MARK_LIT; if (numAvail < 2) return 1; + // if (mainLen < 2 && p->state == 0) return 1; // 18.06.notused if (numAvail > LZMA_MATCH_LEN_MAX) numAvail = LZMA_MATCH_LEN_MAX; data = p->matchFinder.GetPointerToCurrentPos(p->matchFinderObj) - 1; - repLen = repIndex = 0; + for (i = 0; i < LZMA_NUM_REPS; i++) { - UInt32 len; - const Byte *data2 = data - p->reps[i] - 1; + unsigned len; + const Byte *data2 = data - p->reps[i]; if (data[0] != data2[0] || data[1] != data2[1]) continue; - for (len = 2; len < numAvail && data[len] == data2[len]; len++); + for (len = 2; len < numAvail && data[len] == data2[len]; len++) + {} if (len >= p->numFastBytes) { - *backRes = i; - MovePos(p, len - 1); + p->backRes = (UInt32)i; + MOVE_POS(p, len - 1) return len; } if (len > repLen) @@ -1594,84 +1907,152 @@ static UInt32 GetOptimumFast(CLzmaEnc *p, UInt32 *backRes) } } - matches = p->matches; if (mainLen >= p->numFastBytes) { - *backRes = matches[numPairs - 1] + LZMA_NUM_REPS; - MovePos(p, mainLen - 1); + p->backRes = p->matches[(size_t)numPairs - 1] + LZMA_NUM_REPS; + MOVE_POS(p, mainLen - 1) return mainLen; } mainDist = 0; /* for GCC */ + if (mainLen >= 2) { - mainDist = matches[numPairs - 1]; - while (numPairs > 2 && mainLen == matches[numPairs - 4] + 1) + mainDist = p->matches[(size_t)numPairs - 1]; + while (numPairs > 2) { - if (!ChangePair(matches[numPairs - 3], mainDist)) + UInt32 dist2; + if (mainLen != p->matches[(size_t)numPairs - 4] + 1) + break; + dist2 = p->matches[(size_t)numPairs - 3]; + if (!ChangePair(dist2, mainDist)) break; numPairs -= 2; - mainLen = matches[numPairs - 2]; - mainDist = matches[numPairs - 1]; + mainLen--; + mainDist = dist2; } if (mainLen == 2 && mainDist >= 0x80) mainLen = 1; } - if (repLen >= 2 && ( - (repLen + 1 >= mainLen) || - (repLen + 2 >= mainLen && mainDist >= (1 << 9)) || - (repLen + 3 >= mainLen && mainDist >= (1 << 15)))) + if (repLen >= 2) + if ( repLen + 1 >= mainLen + || (repLen + 2 >= mainLen && mainDist >= (1 << 9)) + || (repLen + 3 >= mainLen && mainDist >= (1 << 15))) { - *backRes = repIndex; - MovePos(p, repLen - 1); + p->backRes = (UInt32)repIndex; + MOVE_POS(p, repLen - 1) return repLen; } if (mainLen < 2 || numAvail <= 2) return 1; - p->longestMatchLength = ReadMatchDistances(p, &p->numPairs); - if (p->longestMatchLength >= 2) { - UInt32 newDistance = matches[p->numPairs - 1]; - if ((p->longestMatchLength >= mainLen && newDistance < mainDist) || - (p->longestMatchLength == mainLen + 1 && !ChangePair(mainDist, newDistance)) || - (p->longestMatchLength > mainLen + 1) || - (p->longestMatchLength + 1 >= mainLen && mainLen >= 3 && ChangePair(newDistance, mainDist))) - return 1; + unsigned len1 = ReadMatchDistances(p, &p->numPairs); + p->longestMatchLen = len1; + + if (len1 >= 2) + { + UInt32 newDist = p->matches[(size_t)p->numPairs - 1]; + if ( (len1 >= mainLen && newDist < mainDist) + || (len1 == mainLen + 1 && !ChangePair(mainDist, newDist)) + || (len1 > mainLen + 1) + || (len1 + 1 >= mainLen && mainLen >= 3 && ChangePair(newDist, mainDist))) + return 1; + } } data = p->matchFinder.GetPointerToCurrentPos(p->matchFinderObj) - 1; + for (i = 0; i < LZMA_NUM_REPS; i++) { - UInt32 len, limit; - const Byte *data2 = data - p->reps[i] - 1; + unsigned len, limit; + const Byte *data2 = data - p->reps[i]; if (data[0] != data2[0] || data[1] != data2[1]) continue; limit = mainLen - 1; - for (len = 2; len < limit && data[len] == data2[len]; len++); - if (len >= limit) - return 1; + for (len = 2;; len++) + { + if (len >= limit) + return 1; + if (data[len] != data2[len]) + break; + } + } + + p->backRes = mainDist + LZMA_NUM_REPS; + if (mainLen != 2) + { + MOVE_POS(p, mainLen - 2) } - *backRes = mainDist + LZMA_NUM_REPS; - MovePos(p, mainLen - 2); return mainLen; } -static void WriteEndMarker(CLzmaEnc *p, UInt32 posState) + + + +static void WriteEndMarker(CLzmaEnc *p, unsigned posState) { - UInt32 len; - RangeEnc_EncodeBit(&p->rc, &p->isMatch[p->state][posState], 1); - RangeEnc_EncodeBit(&p->rc, &p->isRep[p->state], 0); + UInt32 range; + range = p->rc.range; + { + UInt32 ttt, newBound; + CLzmaProb *prob = &p->isMatch[p->state][posState]; + RC_BIT_PRE(&p->rc, prob) + RC_BIT_1(&p->rc, prob) + prob = &p->isRep[p->state]; + RC_BIT_PRE(&p->rc, prob) + RC_BIT_0(&p->rc, prob) + } p->state = kMatchNextStates[p->state]; - len = LZMA_MATCH_LEN_MIN; - LenEnc_Encode2(&p->lenEnc, &p->rc, len - LZMA_MATCH_LEN_MIN, posState, !p->fastMode, p->ProbPrices); - RcTree_Encode(&p->rc, p->posSlotEncoder[GetLenToPosState(len)], kNumPosSlotBits, (1 << kNumPosSlotBits) - 1); - RangeEnc_EncodeDirectBits(&p->rc, (((UInt32)1 << 30) - 1) >> kNumAlignBits, 30 - kNumAlignBits); - RcTree_ReverseEncode(&p->rc, p->posAlignEncoder, kNumAlignBits, kAlignMask); + + p->rc.range = range; + LenEnc_Encode(&p->lenProbs, &p->rc, 0, posState); + range = p->rc.range; + + { + // RcTree_Encode_PosSlot(&p->rc, p->posSlotEncoder[0], (1 << kNumPosSlotBits) - 1); + CLzmaProb *probs = p->posSlotEncoder[0]; + unsigned m = 1; + do + { + UInt32 ttt, newBound; + RC_BIT_PRE(p, probs + m) + RC_BIT_1(&p->rc, probs + m); + m = (m << 1) + 1; + } + while (m < (1 << kNumPosSlotBits)); + } + { + // RangeEnc_EncodeDirectBits(&p->rc, ((UInt32)1 << (30 - kNumAlignBits)) - 1, 30 - kNumAlignBits); UInt32 range = p->range; + unsigned numBits = 30 - kNumAlignBits; + do + { + range >>= 1; + p->rc.low += range; + RC_NORM(&p->rc) + } + while (--numBits); + } + + { + // RcTree_ReverseEncode(&p->rc, p->posAlignEncoder, kNumAlignBits, kAlignMask); + CLzmaProb *probs = p->posAlignEncoder; + unsigned m = 1; + do + { + UInt32 ttt, newBound; + RC_BIT_PRE(p, probs + m) + RC_BIT_1(&p->rc, probs + m); + m = (m << 1) + 1; + } + while (m < kAlignTableSize); + } + p->rc.range = range; } + static SRes CheckErrors(CLzmaEnc *p) { if (p->result != SZ_OK) @@ -1685,7 +2066,8 @@ static SRes CheckErrors(CLzmaEnc *p) return p->result; } -static SRes Flush(CLzmaEnc *p, UInt32 nowPos) + +MY_NO_INLINE static SRes Flush(CLzmaEnc *p, UInt32 nowPos) { /* ReleaseMFStream(); */ p->finished = True; @@ -1696,47 +2078,126 @@ static SRes Flush(CLzmaEnc *p, UInt32 nowPos) return CheckErrors(p); } -static void FillAlignPrices(CLzmaEnc *p) + +MY_NO_INLINE static void FillAlignPrices(CLzmaEnc *p) { - UInt32 i; - for (i = 0; i < kAlignTableSize; i++) - p->alignPrices[i] = RcTree_ReverseGetPrice(p->posAlignEncoder, kNumAlignBits, i, p->ProbPrices); - p->alignPriceCount = 0; + unsigned i; + const CProbPrice *ProbPrices = p->ProbPrices; + const CLzmaProb *probs = p->posAlignEncoder; + // p->alignPriceCount = 0; + for (i = 0; i < kAlignTableSize / 2; i++) + { + UInt32 price = 0; + unsigned sym = i; + unsigned m = 1; + unsigned bit; + UInt32 prob; + bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[m], bit); m = (m << 1) + bit; + bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[m], bit); m = (m << 1) + bit; + bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[m], bit); m = (m << 1) + bit; + prob = probs[m]; + p->alignPrices[i ] = price + GET_PRICEa_0(prob); + p->alignPrices[i + 8] = price + GET_PRICEa_1(prob); + // p->alignPrices[i] = RcTree_ReverseGetPrice(p->posAlignEncoder, kNumAlignBits, i, p->ProbPrices); + } } -static void FillDistancesPrices(CLzmaEnc *p) -{ - UInt32 tempPrices[kNumFullDistances]; - UInt32 i, lenToPosState; - for (i = kStartPosModelIndex; i < kNumFullDistances; i++) - { - UInt32 posSlot = GetPosSlot1(i); - UInt32 footerBits = ((posSlot >> 1) - 1); - UInt32 base = ((2 | (posSlot & 1)) << footerBits); - tempPrices[i] = RcTree_ReverseGetPrice(p->posEncoders + base - posSlot - 1, footerBits, i - base, p->ProbPrices); - } - for (lenToPosState = 0; lenToPosState < kNumLenToPosStates; lenToPosState++) +MY_NO_INLINE static void FillDistancesPrices(CLzmaEnc *p) +{ + // int y; for (y = 0; y < 100; y++) { + + UInt32 tempPrices[kNumFullDistances]; + unsigned i, lps; + + const CProbPrice *ProbPrices = p->ProbPrices; + p->matchPriceCount = 0; + + for (i = kStartPosModelIndex / 2; i < kNumFullDistances / 2; i++) { - UInt32 posSlot; - const CLzmaProb *encoder = p->posSlotEncoder[lenToPosState]; - UInt32 *posSlotPrices = p->posSlotPrices[lenToPosState]; - for (posSlot = 0; posSlot < p->distTableSize; posSlot++) - posSlotPrices[posSlot] = RcTree_GetPrice(encoder, kNumPosSlotBits, posSlot, p->ProbPrices); - for (posSlot = kEndPosModelIndex; posSlot < p->distTableSize; posSlot++) - posSlotPrices[posSlot] += ((((posSlot >> 1) - 1) - kNumAlignBits) << kNumBitPriceShiftBits); + unsigned posSlot = GetPosSlot1(i); + unsigned footerBits = (posSlot >> 1) - 1; + unsigned base = ((2 | (posSlot & 1)) << footerBits); + const CLzmaProb *probs = p->posEncoders + (size_t)base * 2; + // tempPrices[i] = RcTree_ReverseGetPrice(p->posEncoders + base, footerBits, i - base, p->ProbPrices); + UInt32 price = 0; + unsigned m = 1; + unsigned sym = i; + unsigned offset = (unsigned)1 << footerBits; + base += i; + + if (footerBits) + do + { + unsigned bit = sym & 1; + sym >>= 1; + price += GET_PRICEa(probs[m], bit); + m = (m << 1) + bit; + } + while (--footerBits); { - UInt32 *distancesPrices = p->distancesPrices[lenToPosState]; - for (i = 0; i < kStartPosModelIndex; i++) - distancesPrices[i] = posSlotPrices[i]; - for (; i < kNumFullDistances; i++) - distancesPrices[i] = posSlotPrices[GetPosSlot1(i)] + tempPrices[i]; + unsigned prob = probs[m]; + tempPrices[base ] = price + GET_PRICEa_0(prob); + tempPrices[base + offset] = price + GET_PRICEa_1(prob); } } - p->matchPriceCount = 0; + + for (lps = 0; lps < kNumLenToPosStates; lps++) + { + unsigned slot; + unsigned distTableSize2 = (p->distTableSize + 1) >> 1; + UInt32 *posSlotPrices = p->posSlotPrices[lps]; + const CLzmaProb *probs = p->posSlotEncoder[lps]; + + for (slot = 0; slot < distTableSize2; slot++) + { + // posSlotPrices[slot] = RcTree_GetPrice(encoder, kNumPosSlotBits, slot, p->ProbPrices); + UInt32 price; + unsigned bit; + unsigned sym = slot + (1 << (kNumPosSlotBits - 1)); + unsigned prob; + bit = sym & 1; sym >>= 1; price = GET_PRICEa(probs[sym], bit); + bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[sym], bit); + bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[sym], bit); + bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[sym], bit); + bit = sym & 1; sym >>= 1; price += GET_PRICEa(probs[sym], bit); + prob = probs[(size_t)slot + (1 << (kNumPosSlotBits - 1))]; + posSlotPrices[(size_t)slot * 2 ] = price + GET_PRICEa_0(prob); + posSlotPrices[(size_t)slot * 2 + 1] = price + GET_PRICEa_1(prob); + } + + { + UInt32 delta = ((UInt32)((kEndPosModelIndex / 2 - 1) - kNumAlignBits) << kNumBitPriceShiftBits); + for (slot = kEndPosModelIndex / 2; slot < distTableSize2; slot++) + { + posSlotPrices[(size_t)slot * 2 ] += delta; + posSlotPrices[(size_t)slot * 2 + 1] += delta; + delta += ((UInt32)1 << kNumBitPriceShiftBits); + } + } + + { + UInt32 *dp = p->distancesPrices[lps]; + + dp[0] = posSlotPrices[0]; + dp[1] = posSlotPrices[1]; + dp[2] = posSlotPrices[2]; + dp[3] = posSlotPrices[3]; + + for (i = 4; i < kNumFullDistances; i += 2) + { + UInt32 slotPrice = posSlotPrices[GetPosSlot1(i)]; + dp[i ] = slotPrice + tempPrices[i]; + dp[i + 1] = slotPrice + tempPrices[i + 1]; + } + } + } + // } } + + void LzmaEnc_Construct(CLzmaEnc *p) { RangeEnc_Construct(&p->rc); @@ -1760,26 +2221,27 @@ void LzmaEnc_Construct(CLzmaEnc *p) LzmaEnc_InitPriceTables(p->ProbPrices); p->litProbs = NULL; p->saveState.litProbs = NULL; + } -CLzmaEncHandle LzmaEnc_Create(ISzAlloc *alloc) +CLzmaEncHandle LzmaEnc_Create(ISzAllocPtr alloc) { void *p; - p = alloc->Alloc(alloc, sizeof(CLzmaEnc)); + p = ISzAlloc_Alloc(alloc, sizeof(CLzmaEnc)); if (p) LzmaEnc_Construct((CLzmaEnc *)p); return p; } -void LzmaEnc_FreeLits(CLzmaEnc *p, ISzAlloc *alloc) +void LzmaEnc_FreeLits(CLzmaEnc *p, ISzAllocPtr alloc) { - alloc->Free(alloc, p->litProbs); - alloc->Free(alloc, p->saveState.litProbs); + ISzAlloc_Free(alloc, p->litProbs); + ISzAlloc_Free(alloc, p->saveState.litProbs); p->litProbs = NULL; p->saveState.litProbs = NULL; } -void LzmaEnc_Destruct(CLzmaEnc *p, ISzAlloc *alloc, ISzAlloc *allocBig) +void LzmaEnc_Destruct(CLzmaEnc *p, ISzAllocPtr alloc, ISzAllocPtr allocBig) { #ifndef _7ZIP_ST MatchFinderMt_Destruct(&p->matchFinderMt, allocBig); @@ -1790,13 +2252,14 @@ void LzmaEnc_Destruct(CLzmaEnc *p, ISzAlloc *alloc, ISzAlloc *allocBig) RangeEnc_Free(&p->rc, alloc); } -void LzmaEnc_Destroy(CLzmaEncHandle p, ISzAlloc *alloc, ISzAlloc *allocBig) +void LzmaEnc_Destroy(CLzmaEncHandle p, ISzAllocPtr alloc, ISzAllocPtr allocBig) { LzmaEnc_Destruct((CLzmaEnc *)p, alloc, allocBig); - alloc->Free(alloc, p); + ISzAlloc_Free(alloc, p); } -static SRes LzmaEnc_CodeOneBlock(CLzmaEnc *p, Bool useLimits, UInt32 maxPackSize, UInt32 maxUnpackSize) + +static SRes LzmaEnc_CodeOneBlock(CLzmaEnc *p, UInt32 maxPackSize, UInt32 maxUnpackSize) { UInt32 nowPos32, startPos32; if (p->needInit) @@ -1814,13 +2277,13 @@ static SRes LzmaEnc_CodeOneBlock(CLzmaEnc *p, Bool useLimits, UInt32 maxPackSize if (p->nowPos64 == 0) { - UInt32 numPairs; + unsigned numPairs; Byte curByte; if (p->matchFinder.GetNumAvailableBytes(p->matchFinderObj) == 0) return Flush(p, nowPos32); ReadMatchDistances(p, &numPairs); - RangeEnc_EncodeBit(&p->rc, &p->isMatch[p->state][0], 0); - p->state = kLiteralNextStates[p->state]; + RangeEnc_EncodeBit_0(&p->rc, &p->isMatch[kState_Start][0]); + // p->state = kLiteralNextStates[p->state]; curByte = *(p->matchFinder.GetPointerToCurrentPos(p->matchFinderObj) - p->additionalOffset); LitEnc_Encode(&p->rc, p->litProbs, curByte); p->additionalOffset--; @@ -1828,123 +2291,253 @@ static SRes LzmaEnc_CodeOneBlock(CLzmaEnc *p, Bool useLimits, UInt32 maxPackSize } if (p->matchFinder.GetNumAvailableBytes(p->matchFinderObj) != 0) + for (;;) { - UInt32 pos, len, posState; - + UInt32 dist; + unsigned len, posState; + UInt32 range, ttt, newBound; + CLzmaProb *probs; + if (p->fastMode) - len = GetOptimumFast(p, &pos); + len = GetOptimumFast(p); else - len = GetOptimum(p, nowPos32, &pos); + { + unsigned oci = p->optCur; + if (p->optEnd == oci) + len = GetOptimum(p, nowPos32); + else + { + const COptimal *opt = &p->opt[oci]; + len = opt->len; + p->backRes = opt->dist; + p->optCur = oci + 1; + } + } + + posState = (unsigned)nowPos32 & p->pbMask; + range = p->rc.range; + probs = &p->isMatch[p->state][posState]; + + RC_BIT_PRE(&p->rc, probs) + + dist = p->backRes; #ifdef SHOW_STAT2 - printf("\n pos = %4X, len = %u pos = %u", nowPos32, len, pos); + printf("\n pos = %6X, len = %3u pos = %6u", nowPos32, len, dist); #endif - posState = nowPos32 & p->pbMask; - if (len == 1 && pos == (UInt32)-1) + if (dist == MARK_LIT) { Byte curByte; - CLzmaProb *probs; const Byte *data; + unsigned state; - RangeEnc_EncodeBit(&p->rc, &p->isMatch[p->state][posState], 0); + RC_BIT_0(&p->rc, probs); + p->rc.range = range; data = p->matchFinder.GetPointerToCurrentPos(p->matchFinderObj) - p->additionalOffset; - curByte = *data; probs = LIT_PROBS(nowPos32, *(data - 1)); - if (IsCharState(p->state)) + curByte = *data; + state = p->state; + p->state = kLiteralNextStates[state]; + if (IsLitState(state)) LitEnc_Encode(&p->rc, probs, curByte); else - LitEnc_EncodeMatched(&p->rc, probs, curByte, *(data - p->reps[0] - 1)); - p->state = kLiteralNextStates[p->state]; + LitEnc_EncodeMatched(&p->rc, probs, curByte, *(data - p->reps[0])); } else { - RangeEnc_EncodeBit(&p->rc, &p->isMatch[p->state][posState], 1); - if (pos < LZMA_NUM_REPS) + RC_BIT_1(&p->rc, probs); + probs = &p->isRep[p->state]; + RC_BIT_PRE(&p->rc, probs) + + if (dist < LZMA_NUM_REPS) { - RangeEnc_EncodeBit(&p->rc, &p->isRep[p->state], 1); - if (pos == 0) + RC_BIT_1(&p->rc, probs); + probs = &p->isRepG0[p->state]; + RC_BIT_PRE(&p->rc, probs) + if (dist == 0) { - RangeEnc_EncodeBit(&p->rc, &p->isRepG0[p->state], 0); - RangeEnc_EncodeBit(&p->rc, &p->isRep0Long[p->state][posState], ((len == 1) ? 0 : 1)); + RC_BIT_0(&p->rc, probs); + probs = &p->isRep0Long[p->state][posState]; + RC_BIT_PRE(&p->rc, probs) + if (len != 1) + { + RC_BIT_1_BASE(&p->rc, probs); + } + else + { + RC_BIT_0_BASE(&p->rc, probs); + p->state = kShortRepNextStates[p->state]; + } } else { - UInt32 distance = p->reps[pos]; - RangeEnc_EncodeBit(&p->rc, &p->isRepG0[p->state], 1); - if (pos == 1) - RangeEnc_EncodeBit(&p->rc, &p->isRepG1[p->state], 0); + RC_BIT_1(&p->rc, probs); + probs = &p->isRepG1[p->state]; + RC_BIT_PRE(&p->rc, probs) + if (dist == 1) + { + RC_BIT_0_BASE(&p->rc, probs); + dist = p->reps[1]; + } else { - RangeEnc_EncodeBit(&p->rc, &p->isRepG1[p->state], 1); - RangeEnc_EncodeBit(&p->rc, &p->isRepG2[p->state], pos - 2); - if (pos == 3) + RC_BIT_1(&p->rc, probs); + probs = &p->isRepG2[p->state]; + RC_BIT_PRE(&p->rc, probs) + if (dist == 2) + { + RC_BIT_0_BASE(&p->rc, probs); + dist = p->reps[2]; + } + else + { + RC_BIT_1_BASE(&p->rc, probs); + dist = p->reps[3]; p->reps[3] = p->reps[2]; + } p->reps[2] = p->reps[1]; } p->reps[1] = p->reps[0]; - p->reps[0] = distance; + p->reps[0] = dist; } - if (len == 1) - p->state = kShortRepNextStates[p->state]; - else + + RC_NORM(&p->rc) + + p->rc.range = range; + + if (len != 1) { - LenEnc_Encode2(&p->repLenEnc, &p->rc, len - LZMA_MATCH_LEN_MIN, posState, !p->fastMode, p->ProbPrices); + LenEnc_Encode(&p->repLenProbs, &p->rc, len - LZMA_MATCH_LEN_MIN, posState); + --p->repLenEncCounter; p->state = kRepNextStates[p->state]; } } else { - UInt32 posSlot; - RangeEnc_EncodeBit(&p->rc, &p->isRep[p->state], 0); + unsigned posSlot; + RC_BIT_0(&p->rc, probs); + p->rc.range = range; p->state = kMatchNextStates[p->state]; - LenEnc_Encode2(&p->lenEnc, &p->rc, len - LZMA_MATCH_LEN_MIN, posState, !p->fastMode, p->ProbPrices); - pos -= LZMA_NUM_REPS; - GetPosSlot(pos, posSlot); - RcTree_Encode(&p->rc, p->posSlotEncoder[GetLenToPosState(len)], kNumPosSlotBits, posSlot); - - if (posSlot >= kStartPosModelIndex) - { - UInt32 footerBits = ((posSlot >> 1) - 1); - UInt32 base = ((2 | (posSlot & 1)) << footerBits); - UInt32 posReduced = pos - base; - if (posSlot < kEndPosModelIndex) - RcTree_ReverseEncode(&p->rc, p->posEncoders + base - posSlot - 1, footerBits, posReduced); - else - { - RangeEnc_EncodeDirectBits(&p->rc, posReduced >> kNumAlignBits, footerBits - kNumAlignBits); - RcTree_ReverseEncode(&p->rc, p->posAlignEncoder, kNumAlignBits, posReduced & kAlignMask); - p->alignPriceCount++; - } - } + LenEnc_Encode(&p->lenProbs, &p->rc, len - LZMA_MATCH_LEN_MIN, posState); + // --p->lenEnc.counter; + + dist -= LZMA_NUM_REPS; p->reps[3] = p->reps[2]; p->reps[2] = p->reps[1]; p->reps[1] = p->reps[0]; - p->reps[0] = pos; + p->reps[0] = dist + 1; + p->matchPriceCount++; + GetPosSlot(dist, posSlot); + // RcTree_Encode_PosSlot(&p->rc, p->posSlotEncoder[GetLenToPosState(len)], posSlot); + { + UInt32 sym = (UInt32)posSlot + (1 << kNumPosSlotBits); + range = p->rc.range; + probs = p->posSlotEncoder[GetLenToPosState(len)]; + do + { + CLzmaProb *prob = probs + (sym >> kNumPosSlotBits); + UInt32 bit = (sym >> (kNumPosSlotBits - 1)) & 1; + sym <<= 1; + RC_BIT(&p->rc, prob, bit); + } + while (sym < (1 << kNumPosSlotBits * 2)); + p->rc.range = range; + } + + if (dist >= kStartPosModelIndex) + { + unsigned footerBits = ((posSlot >> 1) - 1); + + if (dist < kNumFullDistances) + { + unsigned base = ((2 | (posSlot & 1)) << footerBits); + RcTree_ReverseEncode(&p->rc, p->posEncoders + base, footerBits, (unsigned)(dist /* - base */)); + } + else + { + UInt32 pos2 = (dist | 0xF) << (32 - footerBits); + range = p->rc.range; + // RangeEnc_EncodeDirectBits(&p->rc, posReduced >> kNumAlignBits, footerBits - kNumAlignBits); + /* + do + { + range >>= 1; + p->rc.low += range & (0 - ((dist >> --footerBits) & 1)); + RC_NORM(&p->rc) + } + while (footerBits > kNumAlignBits); + */ + do + { + range >>= 1; + p->rc.low += range & (0 - (pos2 >> 31)); + pos2 += pos2; + RC_NORM(&p->rc) + } + while (pos2 != 0xF0000000); + + + // RcTree_ReverseEncode(&p->rc, p->posAlignEncoder, kNumAlignBits, posReduced & kAlignMask); + + { + unsigned m = 1; + unsigned bit; + bit = dist & 1; dist >>= 1; RC_BIT(&p->rc, p->posAlignEncoder + m, bit); m = (m << 1) + bit; + bit = dist & 1; dist >>= 1; RC_BIT(&p->rc, p->posAlignEncoder + m, bit); m = (m << 1) + bit; + bit = dist & 1; dist >>= 1; RC_BIT(&p->rc, p->posAlignEncoder + m, bit); m = (m << 1) + bit; + bit = dist & 1; RC_BIT(&p->rc, p->posAlignEncoder + m, bit); + p->rc.range = range; + // p->alignPriceCount++; + } + } + } } } + + nowPos32 += (UInt32)len; p->additionalOffset -= len; - nowPos32 += len; + if (p->additionalOffset == 0) { UInt32 processed; + if (!p->fastMode) { - if (p->matchPriceCount >= (1 << 7)) - FillDistancesPrices(p); - if (p->alignPriceCount >= kAlignTableSize) + /* + if (p->alignPriceCount >= 16) // kAlignTableSize FillAlignPrices(p); + if (p->matchPriceCount >= 128) + FillDistancesPrices(p); + if (p->lenEnc.counter <= 0) + LenPriceEnc_UpdateTables(&p->lenEnc, 1 << p->pb, &p->lenProbs, p->ProbPrices); + */ + if (p->matchPriceCount >= 64) + { + FillAlignPrices(p); + // { int y; for (y = 0; y < 100; y++) { + FillDistancesPrices(p); + // }} + LenPriceEnc_UpdateTables(&p->lenEnc, 1 << p->pb, &p->lenProbs, p->ProbPrices); + } + if (p->repLenEncCounter <= 0) + { + p->repLenEncCounter = REP_LEN_COUNT; + LenPriceEnc_UpdateTables(&p->repLenEnc, 1 << p->pb, &p->repLenProbs, p->ProbPrices); + } } + if (p->matchFinder.GetNumAvailableBytes(p->matchFinderObj) == 0) break; processed = nowPos32 - startPos32; - if (useLimits) + + if (maxPackSize) { - if (processed + kNumOpts + 300 >= maxUnpackSize || - RangeEnc_GetProcessed(&p->rc) + kNumOpts * 2 >= maxPackSize) + if (processed + kNumOpts + 300 >= maxUnpackSize + || RangeEnc_GetProcessed_sizet(&p->rc) + kPackReserve >= maxPackSize) break; } else if (processed >= (1 << 17)) @@ -1954,13 +2547,16 @@ static SRes LzmaEnc_CodeOneBlock(CLzmaEnc *p, Bool useLimits, UInt32 maxPackSize } } } + p->nowPos64 += nowPos32 - startPos32; return Flush(p, nowPos32); } + + #define kBigHashDicLimit ((UInt32)1 << 24) -static SRes LzmaEnc_Alloc(CLzmaEnc *p, UInt32 keepWindowSize, ISzAlloc *alloc, ISzAlloc *allocBig) +static SRes LzmaEnc_Alloc(CLzmaEnc *p, UInt32 keepWindowSize, ISzAllocPtr alloc, ISzAllocPtr allocBig) { UInt32 beforeSize = kNumOpts; if (!RangeEnc_Alloc(&p->rc, alloc)) @@ -1975,8 +2571,8 @@ static SRes LzmaEnc_Alloc(CLzmaEnc *p, UInt32 keepWindowSize, ISzAlloc *alloc, I if (!p->litProbs || !p->saveState.litProbs || p->lclp != lclp) { LzmaEnc_FreeLits(p, alloc); - p->litProbs = (CLzmaProb *)alloc->Alloc(alloc, ((UInt32)0x300 << lclp) * sizeof(CLzmaProb)); - p->saveState.litProbs = (CLzmaProb *)alloc->Alloc(alloc, ((UInt32)0x300 << lclp) * sizeof(CLzmaProb)); + p->litProbs = (CLzmaProb *)ISzAlloc_Alloc(alloc, ((UInt32)0x300 << lclp) * sizeof(CLzmaProb)); + p->saveState.litProbs = (CLzmaProb *)ISzAlloc_Alloc(alloc, ((UInt32)0x300 << lclp) * sizeof(CLzmaProb)); if (!p->litProbs || !p->saveState.litProbs) { LzmaEnc_FreeLits(p, alloc); @@ -1994,8 +2590,13 @@ static SRes LzmaEnc_Alloc(CLzmaEnc *p, UInt32 keepWindowSize, ISzAlloc *alloc, I #ifndef _7ZIP_ST if (p->mtMode) { - RINOK(MatchFinderMt_Create(&p->matchFinderMt, p->dictSize, beforeSize, p->numFastBytes, LZMA_MATCH_LEN_MAX, allocBig)); + RINOK(MatchFinderMt_Create(&p->matchFinderMt, p->dictSize, beforeSize, p->numFastBytes, + LZMA_MATCH_LEN_MAX + + 1 /* 18.04 */ + , allocBig)); p->matchFinderObj = &p->matchFinderMt; + p->matchFinderBase.bigHash = (Byte)( + (p->dictSize > kBigHashDicLimit && p->matchFinderBase.hashMask >= 0xFFFFFF) ? 1 : 0); MatchFinderMt_CreateVTable(&p->matchFinderMt, &p->matchFinder); } else @@ -2012,17 +2613,21 @@ static SRes LzmaEnc_Alloc(CLzmaEnc *p, UInt32 keepWindowSize, ISzAlloc *alloc, I void LzmaEnc_Init(CLzmaEnc *p) { - UInt32 i; + unsigned i; p->state = 0; - for (i = 0 ; i < LZMA_NUM_REPS; i++) - p->reps[i] = 0; + p->reps[0] = + p->reps[1] = + p->reps[2] = + p->reps[3] = 1; RangeEnc_Init(&p->rc); + for (i = 0; i < (1 << kNumAlignBits); i++) + p->posAlignEncoder[i] = kProbInitValue; for (i = 0; i < kNumStates; i++) { - UInt32 j; + unsigned j; for (j = 0; j < LZMA_NUM_PB_STATES_MAX; j++) { p->isMatch[i][j] = kProbInitValue; @@ -2034,41 +2639,47 @@ void LzmaEnc_Init(CLzmaEnc *p) p->isRepG2[i] = kProbInitValue; } - { - UInt32 num = (UInt32)0x300 << (p->lp + p->lc); - CLzmaProb *probs = p->litProbs; - for (i = 0; i < num; i++) - probs[i] = kProbInitValue; - } - { for (i = 0; i < kNumLenToPosStates; i++) { CLzmaProb *probs = p->posSlotEncoder[i]; - UInt32 j; + unsigned j; for (j = 0; j < (1 << kNumPosSlotBits); j++) probs[j] = kProbInitValue; } } { - for (i = 0; i < kNumFullDistances - kEndPosModelIndex; i++) + for (i = 0; i < kNumFullDistances; i++) p->posEncoders[i] = kProbInitValue; } - LenEnc_Init(&p->lenEnc.p); - LenEnc_Init(&p->repLenEnc.p); + { + UInt32 num = (UInt32)0x300 << (p->lp + p->lc); + UInt32 k; + CLzmaProb *probs = p->litProbs; + for (k = 0; k < num; k++) + probs[k] = kProbInitValue; + } - for (i = 0; i < (1 << kNumAlignBits); i++) - p->posAlignEncoder[i] = kProbInitValue; - p->optimumEndIndex = 0; - p->optimumCurrentIndex = 0; + LenEnc_Init(&p->lenProbs); + LenEnc_Init(&p->repLenProbs); + + p->optEnd = 0; + p->optCur = 0; + + { + for (i = 0; i < kNumOpts; i++) + p->opt[i].price = kInfinityPrice; + } + p->additionalOffset = 0; p->pbMask = (1 << p->pb) - 1; - p->lpMask = (1 << p->lp) - 1; + p->lpMask = ((UInt32)0x100 << p->lp) - ((unsigned)0x100 >> p->lc); } + void LzmaEnc_InitPrices(CLzmaEnc *p) { if (!p->fastMode) @@ -2080,14 +2691,17 @@ void LzmaEnc_InitPrices(CLzmaEnc *p) p->lenEnc.tableSize = p->repLenEnc.tableSize = p->numFastBytes + 1 - LZMA_MATCH_LEN_MIN; - LenPriceEnc_UpdateTables(&p->lenEnc, 1 << p->pb, p->ProbPrices); - LenPriceEnc_UpdateTables(&p->repLenEnc, 1 << p->pb, p->ProbPrices); + + p->repLenEncCounter = REP_LEN_COUNT; + + LenPriceEnc_UpdateTables(&p->lenEnc, 1 << p->pb, &p->lenProbs, p->ProbPrices); + LenPriceEnc_UpdateTables(&p->repLenEnc, 1 << p->pb, &p->repLenProbs, p->ProbPrices); } -static SRes LzmaEnc_AllocAndInit(CLzmaEnc *p, UInt32 keepWindowSize, ISzAlloc *alloc, ISzAlloc *allocBig) +static SRes LzmaEnc_AllocAndInit(CLzmaEnc *p, UInt32 keepWindowSize, ISzAllocPtr alloc, ISzAllocPtr allocBig) { - UInt32 i; - for (i = 0; i < (UInt32)kDicLogSizeMaxCompress; i++) + unsigned i; + for (i = kEndPosModelIndex / 2; i < kDicLogSizeMax; i++) if (p->dictSize <= ((UInt32)1 << i)) break; p->distTableSize = i * 2; @@ -2102,7 +2716,7 @@ static SRes LzmaEnc_AllocAndInit(CLzmaEnc *p, UInt32 keepWindowSize, ISzAlloc *a } static SRes LzmaEnc_Prepare(CLzmaEncHandle pp, ISeqOutStream *outStream, ISeqInStream *inStream, - ISzAlloc *alloc, ISzAlloc *allocBig) + ISzAllocPtr alloc, ISzAllocPtr allocBig) { CLzmaEnc *p = (CLzmaEnc *)pp; p->matchFinderBase.stream = inStream; @@ -2113,7 +2727,7 @@ static SRes LzmaEnc_Prepare(CLzmaEncHandle pp, ISeqOutStream *outStream, ISeqInS SRes LzmaEnc_PrepareForLzma2(CLzmaEncHandle pp, ISeqInStream *inStream, UInt32 keepWindowSize, - ISzAlloc *alloc, ISzAlloc *allocBig) + ISzAllocPtr alloc, ISzAllocPtr allocBig) { CLzmaEnc *p = (CLzmaEnc *)pp; p->matchFinderBase.stream = inStream; @@ -2129,12 +2743,13 @@ static void LzmaEnc_SetInputBuf(CLzmaEnc *p, const Byte *src, SizeT srcLen) } SRes LzmaEnc_MemPrepare(CLzmaEncHandle pp, const Byte *src, SizeT srcLen, - UInt32 keepWindowSize, ISzAlloc *alloc, ISzAlloc *allocBig) + UInt32 keepWindowSize, ISzAllocPtr alloc, ISzAllocPtr allocBig) { CLzmaEnc *p = (CLzmaEnc *)pp; LzmaEnc_SetInputBuf(p, src, srcLen); p->needInit = 1; + LzmaEnc_SetDataSize(pp, srcLen); return LzmaEnc_AllocAndInit(p, keepWindowSize, alloc, allocBig); } @@ -2152,15 +2767,15 @@ void LzmaEnc_Finish(CLzmaEncHandle pp) typedef struct { - ISeqOutStream funcTable; + ISeqOutStream vt; Byte *data; SizeT rem; - Bool overflow; -} CSeqOutStreamBuf; + BoolInt overflow; +} CLzmaEnc_SeqOutStreamBuf; -static size_t MyWrite(void *pp, const void *data, size_t size) +static size_t SeqOutStreamBuf_Write(const ISeqOutStream *pp, const void *data, size_t size) { - CSeqOutStreamBuf *p = (CSeqOutStreamBuf *)pp; + CLzmaEnc_SeqOutStreamBuf *p = CONTAINER_FROM_VTBL(pp, CLzmaEnc_SeqOutStreamBuf, vt); if (p->rem < size) { size = p->rem; @@ -2187,15 +2802,15 @@ const Byte *LzmaEnc_GetCurBuf(CLzmaEncHandle pp) } -SRes LzmaEnc_CodeOneMemBlock(CLzmaEncHandle pp, Bool reInit, +SRes LzmaEnc_CodeOneMemBlock(CLzmaEncHandle pp, BoolInt reInit, Byte *dest, size_t *destLen, UInt32 desiredPackSize, UInt32 *unpackSize) { CLzmaEnc *p = (CLzmaEnc *)pp; UInt64 nowPos64; SRes res; - CSeqOutStreamBuf outStream; + CLzmaEnc_SeqOutStreamBuf outStream; - outStream.funcTable.Write = MyWrite; + outStream.vt.Write = SeqOutStreamBuf_Write; outStream.data = dest; outStream.rem = *destLen; outStream.overflow = False; @@ -2207,11 +2822,15 @@ SRes LzmaEnc_CodeOneMemBlock(CLzmaEncHandle pp, Bool reInit, if (reInit) LzmaEnc_Init(p); LzmaEnc_InitPrices(p); + nowPos64 = p->nowPos64; RangeEnc_Init(&p->rc); - p->rc.outStream = &outStream.funcTable; + p->rc.outStream = &outStream.vt; - res = LzmaEnc_CodeOneBlock(p, True, desiredPackSize, *unpackSize); + if (desiredPackSize == 0) + return SZ_ERROR_OUTPUT_EOF; + + res = LzmaEnc_CodeOneBlock(p, desiredPackSize, *unpackSize); *unpackSize = (UInt32)(p->nowPos64 - nowPos64); *destLen -= outStream.rem; @@ -2234,12 +2853,12 @@ static SRes LzmaEnc_Encode2(CLzmaEnc *p, ICompressProgress *progress) for (;;) { - res = LzmaEnc_CodeOneBlock(p, False, 0, 0); + res = LzmaEnc_CodeOneBlock(p, 0, 0); if (res != SZ_OK || p->finished) break; if (progress) { - res = progress->Progress(progress, p->nowPos64, RangeEnc_GetProcessed(&p->rc)); + res = ICompressProgress_Progress(progress, p->nowPos64, RangeEnc_GetProcessed(&p->rc)); if (res != SZ_OK) { res = SZ_ERROR_PROGRESS; @@ -2251,7 +2870,7 @@ static SRes LzmaEnc_Encode2(CLzmaEnc *p, ICompressProgress *progress) LzmaEnc_Finish(p); /* - if (res == S_OK && !Inline_MatchFinder_IsFinishedOK(&p->matchFinderBase)) + if (res == SZ_OK && !Inline_MatchFinder_IsFinishedOK(&p->matchFinderBase)) res = SZ_ERROR_FAIL; } */ @@ -2261,7 +2880,7 @@ static SRes LzmaEnc_Encode2(CLzmaEnc *p, ICompressProgress *progress) SRes LzmaEnc_Encode(CLzmaEncHandle pp, ISeqOutStream *outStream, ISeqInStream *inStream, ICompressProgress *progress, - ISzAlloc *alloc, ISzAlloc *allocBig) + ISzAllocPtr alloc, ISzAllocPtr allocBig) { RINOK(LzmaEnc_Prepare(pp, outStream, inStream, alloc, allocBig)); return LzmaEnc_Encode2((CLzmaEnc *)pp, progress); @@ -2296,21 +2915,27 @@ SRes LzmaEnc_WriteProperties(CLzmaEncHandle pp, Byte *props, SizeT *size) } +unsigned LzmaEnc_IsWriteEndMark(CLzmaEncHandle pp) +{ + return ((CLzmaEnc *)pp)->writeEndMark; +} + + SRes LzmaEnc_MemEncode(CLzmaEncHandle pp, Byte *dest, SizeT *destLen, const Byte *src, SizeT srcLen, - int writeEndMark, ICompressProgress *progress, ISzAlloc *alloc, ISzAlloc *allocBig) + int writeEndMark, ICompressProgress *progress, ISzAllocPtr alloc, ISzAllocPtr allocBig) { SRes res; CLzmaEnc *p = (CLzmaEnc *)pp; - CSeqOutStreamBuf outStream; + CLzmaEnc_SeqOutStreamBuf outStream; - outStream.funcTable.Write = MyWrite; + outStream.vt.Write = SeqOutStreamBuf_Write; outStream.data = dest; outStream.rem = *destLen; outStream.overflow = False; p->writeEndMark = writeEndMark; - p->rc.outStream = &outStream.funcTable; + p->rc.outStream = &outStream.vt; res = LzmaEnc_MemPrepare(pp, src, srcLen, 0, alloc, allocBig); @@ -2330,7 +2955,7 @@ SRes LzmaEnc_MemEncode(CLzmaEncHandle pp, Byte *dest, SizeT *destLen, const Byte SRes LzmaEncode(Byte *dest, SizeT *destLen, const Byte *src, SizeT srcLen, const CLzmaEncProps *props, Byte *propsEncoded, SizeT *propsSize, int writeEndMark, - ICompressProgress *progress, ISzAlloc *alloc, ISzAlloc *allocBig) + ICompressProgress *progress, ISzAllocPtr alloc, ISzAllocPtr allocBig) { CLzmaEnc *p = (CLzmaEnc *)LzmaEnc_Create(alloc); SRes res; diff --git a/uppsrc/plugin/lzma/lib/LzmaEnc.h b/uppsrc/plugin/lzma/lib/LzmaEnc.h index c2806b45f..c9938f04b 100644 --- a/uppsrc/plugin/lzma/lib/LzmaEnc.h +++ b/uppsrc/plugin/lzma/lib/LzmaEnc.h @@ -1,5 +1,5 @@ /* LzmaEnc.h -- LZMA Encoder -2013-01-18 : Igor Pavlov : Public domain */ +2017-07-27 : Igor Pavlov : Public domain */ #ifndef __LZMA_ENC_H #define __LZMA_ENC_H @@ -12,12 +12,10 @@ EXTERN_C_BEGIN typedef struct _CLzmaEncProps { - int level; /* 0 <= level <= 9 */ + int level; /* 0 <= level <= 9 */ UInt32 dictSize; /* (1 << 12) <= dictSize <= (1 << 27) for 32-bit version - (1 << 12) <= dictSize <= (1 << 30) for 64-bit version - default = (1 << 24) */ - UInt64 reduceSize; /* estimated size of data that will be compressed. default = 0xFFFFFFFF. - Encoder uses this value to reduce dictionary size */ + (1 << 12) <= dictSize <= (3 << 29) for 64-bit version + default = (1 << 24) */ int lc; /* 0 <= lc <= 8, default = 3 */ int lp; /* 0 <= lp <= 4, default = 0 */ int pb; /* 0 <= pb <= 4, default = 2 */ @@ -25,9 +23,12 @@ typedef struct _CLzmaEncProps int fb; /* 5 <= fb <= 273, default = 32 */ int btMode; /* 0 - hashChain Mode, 1 - binTree mode - normal, default = 1 */ int numHashBytes; /* 2, 3 or 4, default = 4 */ - UInt32 mc; /* 1 <= mc <= (1 << 30), default = 32 */ + UInt32 mc; /* 1 <= mc <= (1 << 30), default = 32 */ unsigned writeEndMark; /* 0 - do not write EOPM, 1 - write EOPM, default = 0 */ int numThreads; /* 1 or 2, default = 2 */ + + UInt64 reduceSize; /* estimated size of data that will be compressed. default = (UInt64)(Int64)-1. + Encoder uses this value to reduce dictionary size */ } CLzmaEncProps; void LzmaEncProps_Init(CLzmaEncProps *p); @@ -37,41 +38,38 @@ UInt32 LzmaEncProps_GetDictSize(const CLzmaEncProps *props2); /* ---------- CLzmaEncHandle Interface ---------- */ -/* LzmaEnc_* functions can return the following exit codes: -Returns: +/* LzmaEnc* functions can return the following exit codes: +SRes: SZ_OK - OK SZ_ERROR_MEM - Memory allocation error SZ_ERROR_PARAM - Incorrect paramater in props - SZ_ERROR_WRITE - Write callback error. + SZ_ERROR_WRITE - ISeqOutStream write callback error + SZ_ERROR_OUTPUT_EOF - output buffer overflow - version with (Byte *) output SZ_ERROR_PROGRESS - some break from progress callback - SZ_ERROR_THREAD - errors in multithreading functions (only for Mt version) + SZ_ERROR_THREAD - error in multithreading functions (only for Mt version) */ typedef void * CLzmaEncHandle; -CLzmaEncHandle LzmaEnc_Create(ISzAlloc *alloc); -void LzmaEnc_Destroy(CLzmaEncHandle p, ISzAlloc *alloc, ISzAlloc *allocBig); +CLzmaEncHandle LzmaEnc_Create(ISzAllocPtr alloc); +void LzmaEnc_Destroy(CLzmaEncHandle p, ISzAllocPtr alloc, ISzAllocPtr allocBig); + SRes LzmaEnc_SetProps(CLzmaEncHandle p, const CLzmaEncProps *props); +void LzmaEnc_SetDataSize(CLzmaEncHandle p, UInt64 expectedDataSiize); SRes LzmaEnc_WriteProperties(CLzmaEncHandle p, Byte *properties, SizeT *size); +unsigned LzmaEnc_IsWriteEndMark(CLzmaEncHandle p); + SRes LzmaEnc_Encode(CLzmaEncHandle p, ISeqOutStream *outStream, ISeqInStream *inStream, - ICompressProgress *progress, ISzAlloc *alloc, ISzAlloc *allocBig); + ICompressProgress *progress, ISzAllocPtr alloc, ISzAllocPtr allocBig); SRes LzmaEnc_MemEncode(CLzmaEncHandle p, Byte *dest, SizeT *destLen, const Byte *src, SizeT srcLen, - int writeEndMark, ICompressProgress *progress, ISzAlloc *alloc, ISzAlloc *allocBig); + int writeEndMark, ICompressProgress *progress, ISzAllocPtr alloc, ISzAllocPtr allocBig); + /* ---------- One Call Interface ---------- */ -/* LzmaEncode -Return code: - SZ_OK - OK - SZ_ERROR_MEM - Memory allocation error - SZ_ERROR_PARAM - Incorrect paramater - SZ_ERROR_OUTPUT_EOF - output buffer overflow - SZ_ERROR_THREAD - errors in multithreading functions (only for Mt version) -*/ - SRes LzmaEncode(Byte *dest, SizeT *destLen, const Byte *src, SizeT srcLen, const CLzmaEncProps *props, Byte *propsEncoded, SizeT *propsSize, int writeEndMark, - ICompressProgress *progress, ISzAlloc *alloc, ISzAlloc *allocBig); + ICompressProgress *progress, ISzAllocPtr alloc, ISzAllocPtr allocBig); EXTERN_C_END diff --git a/uppsrc/plugin/lzma/lzma.cpp b/uppsrc/plugin/lzma/lzma.cpp index c135581d0..c1c6ddd1e 100644 --- a/uppsrc/plugin/lzma/lzma.cpp +++ b/uppsrc/plugin/lzma/lzma.cpp @@ -7,12 +7,12 @@ namespace Upp { -static voidpf lzma_alloc_new(void *, size_t size) { +static voidpf lzma_alloc_new(ISzAllocPtr, size_t size) { voidpf t = new byte[size]; return t; } -static void lzma_free_new(void *, void *address) { +static void lzma_free_new(ISzAllocPtr, void *address) { if(!address) return; delete[] (byte *)address; @@ -24,7 +24,7 @@ struct IUppInStream { ISeqInStream s; Stream& in; - static SRes Read(void *pp, void *buf, size_t *size) { + static SRes Read(const ISeqInStream *pp, void *buf, size_t *size) { IUppInStream *p = (IUppInStream *)pp; int64 h = (size_t)p->in.Get64(buf, *size); if(p->in.IsError() || h < 0) { @@ -45,7 +45,7 @@ struct IUppOutStream { Stream& out; int64 len; - static size_t Write(void *pp, const void *buf, size_t size) { + static size_t Write(const ISeqOutStream *pp, const void *buf, size_t size) { IUppOutStream *p = (IUppOutStream *)pp; p->out.Put64(buf, size); p->len += size; @@ -143,7 +143,7 @@ struct LUppProgress { Gate2 progress; int64 total; - static SRes Progress(void *pp, UInt64 inSize, UInt64) + static SRes Progress(const ICompressProgress *pp, UInt64 inSize, UInt64) { LUppProgress *p = (LUppProgress *)pp; return p->progress(inSize, p->total);