From c248d29056abbc1fc4c5dc178bab48fb8d2c1fcb Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Fri, 19 Apr 2024 19:40:56 +0200 Subject: Adding upstream version 1:0.5.47. Signed-off-by: Daniel Baumann --- htp/lzma/7zTypes.h | 375 ++++++++++++++++ htp/lzma/Compiler.h | 33 ++ htp/lzma/LzFind.c | 1127 ++++++++++++++++++++++++++++++++++++++++++++++ htp/lzma/LzFind.h | 121 +++++ htp/lzma/LzHash.h | 57 +++ htp/lzma/LzmaDec.c | 1223 ++++++++++++++++++++++++++++++++++++++++++++++++++ htp/lzma/LzmaDec.h | 234 ++++++++++ htp/lzma/Makefile.am | 16 + htp/lzma/Precomp.h | 10 + 9 files changed, 3196 insertions(+) create mode 100644 htp/lzma/7zTypes.h create mode 100644 htp/lzma/Compiler.h create mode 100644 htp/lzma/LzFind.c create mode 100644 htp/lzma/LzFind.h create mode 100644 htp/lzma/LzHash.h create mode 100644 htp/lzma/LzmaDec.c create mode 100644 htp/lzma/LzmaDec.h create mode 100644 htp/lzma/Makefile.am create mode 100644 htp/lzma/Precomp.h (limited to 'htp/lzma') diff --git a/htp/lzma/7zTypes.h b/htp/lzma/7zTypes.h new file mode 100644 index 0000000..f5d7505 --- /dev/null +++ b/htp/lzma/7zTypes.h @@ -0,0 +1,375 @@ +/* 7zTypes.h -- Basic types +2018-08-04 : Igor Pavlov : Public domain */ + +#ifndef __7Z_TYPES_H +#define __7Z_TYPES_H + +#ifdef _WIN32 +/* #include */ +#endif + +#include +#include + +#ifndef EXTERN_C_BEGIN +#ifdef __cplusplus +#define EXTERN_C_BEGIN extern "C" { +#define EXTERN_C_END } +#else +#define EXTERN_C_BEGIN +#define EXTERN_C_END +#endif +#endif + +EXTERN_C_BEGIN + +#define SZ_OK 0 + +#define SZ_ERROR_DATA 1 +#define SZ_ERROR_MEM 2 +#define SZ_ERROR_CRC 3 +#define SZ_ERROR_UNSUPPORTED 4 +#define SZ_ERROR_PARAM 5 +#define SZ_ERROR_INPUT_EOF 6 +#define SZ_ERROR_OUTPUT_EOF 7 +#define SZ_ERROR_READ 8 +#define SZ_ERROR_WRITE 9 +#define SZ_ERROR_PROGRESS 10 +#define SZ_ERROR_FAIL 11 +#define SZ_ERROR_THREAD 12 + +#define SZ_ERROR_ARCHIVE 16 +#define SZ_ERROR_NO_ARCHIVE 17 + +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 + +typedef short Int16; +typedef unsigned short UInt16; + +#ifdef _LZMA_UINT32_IS_ULONG +typedef long Int32; +typedef unsigned long UInt32; +#else +typedef int Int32; +typedef unsigned int UInt32; +#endif + +#ifdef _SZ_NO_INT_64 + +/* define _SZ_NO_INT_64, if your compiler doesn't support 64-bit integers. + NOTES: Some code will work incorrectly in that case! */ + +typedef long Int64; +typedef unsigned long UInt64; + +#else + +#if defined(_MSC_VER) || defined(__BORLANDC__) +typedef __int64 Int64; +typedef unsigned __int64 UInt64; +#define UINT64_CONST(n) n +#else +typedef long long int Int64; +typedef unsigned long long int UInt64; +#define UINT64_CONST(n) n ## ULL +#endif + +#endif + +#ifdef _LZMA_NO_SYSTEM_SIZE_T +typedef UInt32 SizeT; +#else +typedef size_t SizeT; +#endif + +typedef int BoolInt; +/* typedef BoolInt Bool; */ +#define True 1 +#define False 0 + + +#ifdef _WIN32 +#define MY_STD_CALL __stdcall +#else +#define MY_STD_CALL +#endif + +#ifdef _MSC_VER + +#if _MSC_VER >= 1300 +#define MY_NO_INLINE __declspec(noinline) +#else +#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 IByteIn IByteIn; +struct 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 IByteOut IByteOut; +struct IByteOut +{ + 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 */ +}; +#define ISeqInStream_Read(p, buf, size) (p)->Read(p, buf, size) + +/* it can return SZ_ERROR_INPUT_EOF */ +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 ISeqOutStream ISeqOutStream; +struct ISeqOutStream +{ + size_t (*Write)(const ISeqOutStream *p, const void *buf, size_t size); + /* Returns: result - the number of actually written bytes. + (result < size) means error */ +}; +#define ISeqOutStream_Write(p, buf, size) (p)->Write(p, buf, size) + +typedef enum +{ + SZ_SEEK_SET = 0, + SZ_SEEK_CUR = 1, + SZ_SEEK_END = 2 +} ESzSeek; + + +typedef struct ISeekInStream ISeekInStream; +struct ISeekInStream +{ + 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)(const ILookInStream *p, size_t offset); + /* offset must be <= output(*size) of Look */ + + SRes (*Read)(const ILookInStream *p, void *buf, size_t *size); + /* reads directly (without buffer). It's same as ISeqInStream::Read */ + SRes (*Seek)(const ILookInStream *p, Int64 *pos, ESzSeek origin); +}; + +#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(const ILookInStream *stream, void *buf, size_t size, SRes errorType); +SRes LookInStream_Read(const ILookInStream *stream, void *buf, size_t size); + + + +typedef struct +{ + ILookInStream vt; + const ISeekInStream *realStream; + + size_t pos; + 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; } + + +typedef struct +{ + ISeqInStream vt; + const ILookInStream *realStream; +} CSecToLook; + +void SecToLook_CreateVTable(CSecToLook *p); + + + +typedef struct +{ + ISeqInStream vt; + const ILookInStream *realStream; +} CSecToRead; + +void SecToRead_CreateVTable(CSecToRead *p); + + +typedef struct ICompressProgress ICompressProgress; + +struct ICompressProgress +{ + 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. */ +}; +#define ICompressProgress_Progress(p, inSize, outSize) (p)->Progress(p, inSize, outSize) + + + +typedef struct ISzAlloc ISzAlloc; +typedef const ISzAlloc * ISzAllocPtr; + +struct 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) +*/ + + + +#ifdef _WIN32 + +#define CHAR_PATH_SEPARATOR '\\' +#define WCHAR_PATH_SEPARATOR L'\\' +#define STRING_PATH_SEPARATOR "\\" +#define WSTRING_PATH_SEPARATOR L"\\" + +#else + +#define CHAR_PATH_SEPARATOR '/' +#define WCHAR_PATH_SEPARATOR L'/' +#define STRING_PATH_SEPARATOR "/" +#define WSTRING_PATH_SEPARATOR L"/" + +#endif + +EXTERN_C_END + +#endif diff --git a/htp/lzma/Compiler.h b/htp/lzma/Compiler.h new file mode 100644 index 0000000..c788648 --- /dev/null +++ b/htp/lzma/Compiler.h @@ -0,0 +1,33 @@ +/* Compiler.h +2017-04-03 : Igor Pavlov : Public domain */ + +#ifndef __7Z_COMPILER_H +#define __7Z_COMPILER_H + +#ifdef _MSC_VER + + #ifdef UNDER_CE + #define RPC_NO_WINDOWS_H + /* #pragma warning(disable : 4115) // '_RPC_ASYNC_STATE' : named type definition in parentheses */ + #pragma warning(disable : 4201) // nonstandard extension used : nameless struct/union + #pragma warning(disable : 4214) // nonstandard extension used : bit field types other than int + #endif + + #if _MSC_VER >= 1300 + #pragma warning(disable : 4996) // This function or variable may be unsafe + #else + #pragma warning(disable : 4511) // copy constructor could not be generated + #pragma warning(disable : 4512) // assignment operator could not be generated + #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 + +#endif + +#define UNUSED_VAR(x) (void)x; +/* #define UNUSED_VAR(x) x=x; */ + +#endif diff --git a/htp/lzma/LzFind.c b/htp/lzma/LzFind.c new file mode 100644 index 0000000..ee5375c --- /dev/null +++ b/htp/lzma/LzFind.c @@ -0,0 +1,1127 @@ +/* LzFind.c -- Match finder for LZ algorithms +2018-07-08 : Igor Pavlov : Public domain */ + +#include "Precomp.h" + +#include + +#include "LzFind.h" +#include "LzHash.h" + +#define kEmptyHashValue 0 +#define kMaxValForNormalize ((UInt32)0xFFFFFFFF) +#define kNormalizeStepMin (1 << 10) /* it must be power of 2 */ +#define kNormalizeMask (~(UInt32)(kNormalizeStepMin - 1)) +#define kMaxHistorySize ((UInt32)7 << 29) + +#define kStartMaxLen 3 + +static void LzInWindow_Free(CMatchFinder *p, ISzAllocPtr alloc) +{ + if (!p->directInput) + { + ISzAlloc_Free(alloc, p->bufferBase); + p->bufferBase = NULL; + } +} + +/* keepSizeBefore + keepSizeAfter + keepSizeReserv must be < 4G) */ + +static int LzInWindow_Create(CMatchFinder *p, UInt32 keepSizeReserv, ISzAllocPtr alloc) +{ + UInt32 blockSize = p->keepSizeBefore + p->keepSizeAfter + keepSizeReserv; + if (p->directInput) + { + p->blockSize = blockSize; + return 1; + } + if (!p->bufferBase || p->blockSize != blockSize) + { + LzInWindow_Free(p, alloc); + p->blockSize = blockSize; + p->bufferBase = (Byte *)ISzAlloc_Alloc(alloc, (size_t)blockSize); + } + return (p->bufferBase != NULL); +} + +Byte *MatchFinder_GetPointerToCurrentPos(CMatchFinder *p) { return p->buffer; } + +static UInt32 MatchFinder_GetNumAvailableBytes(CMatchFinder *p) { return p->streamPos - p->pos; } + +void MatchFinder_ReduceOffsets(CMatchFinder *p, UInt32 subValue) +{ + p->posLimit -= subValue; + p->pos -= subValue; + p->streamPos -= subValue; +} + +static void MatchFinder_ReadBlock(CMatchFinder *p) +{ + if (p->streamEndWasReached || p->result != SZ_OK) + return; + + /* We use (p->streamPos - p->pos) value. (p->streamPos < p->pos) is allowed. */ + + if (p->directInput) + { + UInt32 curSize = 0xFFFFFFFF - (p->streamPos - p->pos); + if (curSize > p->directInputRem) + curSize = (UInt32)p->directInputRem; + p->directInputRem -= curSize; + p->streamPos += curSize; + if (p->directInputRem == 0) + p->streamEndWasReached = 1; + return; + } + + for (;;) + { + Byte *dest = p->buffer + (p->streamPos - p->pos); + size_t size = (p->bufferBase + p->blockSize - dest); + if (size == 0) + return; + + p->result = ISeqInStream_Read(p->stream, dest, &size); + if (p->result != SZ_OK) + return; + if (size == 0) + { + p->streamEndWasReached = 1; + return; + } + p->streamPos += (UInt32)size; + if (p->streamPos - p->pos > p->keepSizeAfter) + return; + } +} + +void MatchFinder_MoveBlock(CMatchFinder *p) +{ + memmove(p->bufferBase, + p->buffer - p->keepSizeBefore, + (size_t)(p->streamPos - p->pos) + p->keepSizeBefore); + p->buffer = p->bufferBase + p->keepSizeBefore; +} + +int MatchFinder_NeedMove(CMatchFinder *p) +{ + if (p->directInput) + return 0; + /* if (p->streamEndWasReached) return 0; */ + return ((size_t)(p->bufferBase + p->blockSize - p->buffer) <= p->keepSizeAfter); +} + +void MatchFinder_ReadIfRequired(CMatchFinder *p) +{ + if (p->streamEndWasReached) + return; + if (p->keepSizeAfter >= p->streamPos - p->pos) + MatchFinder_ReadBlock(p); +} + +static void MatchFinder_CheckAndMoveAndRead(CMatchFinder *p) +{ + if (MatchFinder_NeedMove(p)) + MatchFinder_MoveBlock(p); + MatchFinder_ReadBlock(p); +} + +static void MatchFinder_SetDefaultSettings(CMatchFinder *p) +{ + p->cutValue = 32; + p->btMode = 1; + p->numHashBytes = 4; + p->bigHash = 0; +} + +#define kCrcPoly 0xEDB88320 + +void MatchFinder_Construct(CMatchFinder *p) +{ + 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 = (UInt32)i; + unsigned j; + for (j = 0; j < 8; j++) + r = (r >> 1) ^ (kCrcPoly & ((UInt32)0 - (r & 1))); + p->crc[i] = r; + } +} + +static void MatchFinder_FreeThisClassMemory(CMatchFinder *p, ISzAllocPtr alloc) +{ + ISzAlloc_Free(alloc, p->hash); + p->hash = NULL; +} + +void MatchFinder_Free(CMatchFinder *p, ISzAllocPtr alloc) +{ + MatchFinder_FreeThisClassMemory(p, alloc); + LzInWindow_Free(p, 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 *)ISzAlloc_Alloc(alloc, sizeInBytes); +} + +int MatchFinder_Create(CMatchFinder *p, UInt32 historySize, + UInt32 keepAddBufferBefore, UInt32 matchMaxLen, UInt32 keepAddBufferAfter, + ISzAllocPtr alloc) +{ + UInt32 sizeReserv; + + if (historySize > kMaxHistorySize) + { + MatchFinder_Free(p, alloc); + return 0; + } + + sizeReserv = historySize >> 1; + if (historySize >= ((UInt32)3 << 30)) sizeReserv = historySize >> 3; + else if (historySize >= ((UInt32)2 << 30)) sizeReserv = historySize >> 2; + + sizeReserv += (keepAddBufferBefore + matchMaxLen + keepAddBufferAfter) / 2 + (1 << 19); + + p->keepSizeBefore = historySize + keepAddBufferBefore + 1; + p->keepSizeAfter = matchMaxLen + keepAddBufferAfter; + + /* we need one additional byte, since we use MoveBlock after pos++ and before dictionary using */ + + if (LzInWindow_Create(p, sizeReserv, alloc)) + { + UInt32 newCyclicBufferSize = historySize + 1; + UInt32 hs; + p->matchMaxLen = matchMaxLen; + { + p->fixedHashSize = 0; + if (p->numHashBytes == 2) + hs = (1 << 16) - 1; + else + { + hs = historySize; + if (hs > p->expectedDataSize) + hs = (UInt32)p->expectedDataSize; + if (hs != 0) + hs--; + hs |= (hs >> 1); + hs |= (hs >> 2); + hs |= (hs >> 4); + hs |= (hs >> 8); + hs >>= 1; + hs |= 0xFFFF; /* don't change it! It's required for Deflate */ + if (hs > (1 << 24)) + { + if (p->numHashBytes == 3) + hs = (1 << 24) - 1; + else + hs >>= 1; + /* if (bigHash) mode, GetHeads4b() in LzFindMt.c needs (hs >= ((1 << 24) - 1))) */ + } + } + p->hashMask = hs; + hs++; + if (p->numHashBytes > 2) p->fixedHashSize += kHash2Size; + if (p->numHashBytes > 3) p->fixedHashSize += kHash3Size; + if (p->numHashBytes > 4) p->fixedHashSize += kHash4Size; + hs += p->fixedHashSize; + } + + { + size_t newSize; + size_t numSons; + p->historySize = historySize; + p->hashSizeSum = hs; + p->cyclicBufferSize = newCyclicBufferSize; + + numSons = newCyclicBufferSize; + if (p->btMode) + numSons <<= 1; + newSize = hs + numSons; + + if (p->hash && p->numRefs == newSize) + return 1; + + MatchFinder_FreeThisClassMemory(p, alloc); + p->numRefs = newSize; + p->hash = AllocRefs(newSize, alloc); + + if (p->hash) + { + p->son = p->hash + p->hashSizeSum; + return 1; + } + } + } + + MatchFinder_Free(p, alloc); + return 0; +} + +static void MatchFinder_SetLimits(CMatchFinder *p) +{ + UInt32 limit = kMaxValForNormalize - p->pos; + UInt32 limit2 = p->cyclicBufferSize - p->cyclicBufferPos; + + if (limit2 < limit) + limit = limit2; + limit2 = p->streamPos - p->pos; + + if (limit2 <= p->keepSizeAfter) + { + if (limit2 > 0) + limit2 = 1; + } + else + limit2 -= p->keepSizeAfter; + + if (limit2 < limit) + limit = limit2; + + { + UInt32 lenLimit = p->streamPos - p->pos; + if (lenLimit > p->matchMaxLen) + lenLimit = p->matchMaxLen; + p->lenLimit = lenLimit; + } + p->posLimit = p->pos + limit; +} + + +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) +{ + p->cyclicBufferPos = 0; + p->buffer = p->bufferBase; + p->pos = + p->streamPos = p->cyclicBufferSize; + p->result = SZ_OK; + p->streamEndWasReached = 0; + + if (readData) + MatchFinder_ReadBlock(p); + + MatchFinder_SetLimits(p); +} + + +void MatchFinder_Init(CMatchFinder *p) +{ + MatchFinder_Init_HighHash(p); + MatchFinder_Init_LowHash(p); + MatchFinder_Init_3(p, True); +} + + +static UInt32 MatchFinder_GetSubValue(CMatchFinder *p) +{ + return (p->pos - p->historySize - 1) & kNormalizeMask; +} + +void MatchFinder_Normalize3(UInt32 subValue, CLzRef *items, size_t numItems) +{ + size_t i; + for (i = 0; i < numItems; i++) + { + UInt32 value = items[i]; + if (value <= subValue) + value = kEmptyHashValue; + else + value -= subValue; + items[i] = value; + } +} + +static void MatchFinder_Normalize(CMatchFinder *p) +{ + UInt32 subValue = MatchFinder_GetSubValue(p); + MatchFinder_Normalize3(subValue, p->hash, p->numRefs); + MatchFinder_ReduceOffsets(p, subValue); +} + + +MY_NO_INLINE +static void MatchFinder_CheckLimits(CMatchFinder *p) +{ + if (p->pos == kMaxValForNormalize) + MatchFinder_Normalize(p); + if (!p->streamEndWasReached && p->keepSizeAfter == p->streamPos - p->pos) + MatchFinder_CheckAndMoveAndRead(p); + if (p->cyclicBufferPos == p->cyclicBufferSize) + p->cyclicBufferPos = 0; + MatchFinder_SetLimits(p); +} + + +/* + (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, unsigned maxLen) +{ + /* + son[_cyclicBufferPos] = curMatch; + for (;;) + { + UInt32 delta = pos - curMatch; + if (cutValue-- == 0 || delta >= _cyclicBufferSize) + return distances; + { + const Byte *pb = cur - delta; + curMatch = son[_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)]; + if (pb[maxLen] == cur[maxLen] && *pb == *cur) + { + UInt32 len = 0; + while (++len != lenLimit) + if (pb[len] != cur[len]) + break; + if (maxLen < len) + { + maxLen = len; + *distances++ = len; + *distances++ = delta - 1; + if (len == lenLimit) + return distances; + } + } + } + } + */ + + 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 + ((size_t)_cyclicBufferPos << 1) + 1; + CLzRef *ptr1 = son + ((size_t)_cyclicBufferPos << 1); + unsigned len0 = 0, len1 = 0; + for (;;) + { + UInt32 delta = pos - curMatch; + if (cutValue-- == 0 || delta >= _cyclicBufferSize) + { + *ptr0 = *ptr1 = kEmptyHashValue; + return distances; + } + { + CLzRef *pair = son + ((size_t)(_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)) << 1); + const Byte *pb = cur - delta; + unsigned len = (len0 < len1 ? len0 : len1); + UInt32 pair0 = pair[0]; + if (pb[len] == cur[len]) + { + if (++len != lenLimit && pb[len] == cur[len]) + while (++len != lenLimit) + if (pb[len] != cur[len]) + break; + if (maxLen < len) + { + maxLen = (UInt32)len; + *distances++ = (UInt32)len; + *distances++ = delta - 1; + if (len == lenLimit) + { + *ptr1 = pair0; + *ptr0 = pair[1]; + return distances; + } + } + } + if (pb[len] < cur[len]) + { + *ptr1 = curMatch; + ptr1 = pair + 1; + curMatch = *ptr1; + len1 = len; + } + else + { + *ptr0 = curMatch; + ptr0 = pair; + curMatch = *ptr0; + len0 = len; + } + } + } +} + +static void SkipMatchesSpec(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byte *cur, CLzRef *son, + UInt32 _cyclicBufferPos, UInt32 _cyclicBufferSize, UInt32 cutValue) +{ + 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; + if (cutValue-- == 0 || delta >= _cyclicBufferSize) + { + *ptr0 = *ptr1 = kEmptyHashValue; + return; + } + { + CLzRef *pair = son + ((size_t)(_cyclicBufferPos - delta + ((delta > _cyclicBufferPos) ? _cyclicBufferSize : 0)) << 1); + const Byte *pb = cur - delta; + unsigned len = (len0 < len1 ? len0 : len1); + if (pb[len] == cur[len]) + { + while (++len != lenLimit) + if (pb[len] != cur[len]) + break; + { + if (len == lenLimit) + { + *ptr1 = pair[0]; + *ptr0 = pair[1]; + return; + } + } + } + if (pb[len] < cur[len]) + { + *ptr1 = curMatch; + ptr1 = pair + 1; + curMatch = *ptr1; + len1 = len; + } + else + { + *ptr0 = curMatch; + ptr0 = pair; + curMatch = *ptr0; + len0 = len; + } + } + } +} + +#define MOVE_POS \ + ++p->cyclicBufferPos; \ + p->buffer++; \ + if (++p->pos == p->posLimit) MatchFinder_CheckLimits(p); + +#define MOVE_POS_RET MOVE_POS return (UInt32)offset; + +static void MatchFinder_MovePos(CMatchFinder *p) { MOVE_POS; } + +#define GET_MATCHES_HEADER2(minLen, 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) +#define SKIP_HEADER(minLen) GET_MATCHES_HEADER2(minLen, continue) + +#define MF_PARAMS(p) p->pos, p->buffer, p->son, p->cyclicBufferPos, p->cyclicBufferSize, p->cutValue + +#define GET_MATCHES_FOOTER(offset, maxLen) \ + offset = (unsigned)(GetMatchesSpec1((UInt32)lenLimit, curMatch, MF_PARAMS(p), \ + distances + offset, (UInt32)maxLen) - distances); MOVE_POS_RET; + +#define SKIP_FOOTER \ + 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 = (unsigned)(c - cur); } + +static UInt32 Bt2_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) +{ + unsigned offset; + GET_MATCHES_HEADER(2) + HASH2_CALC; + curMatch = p->hash[hv]; + p->hash[hv] = p->pos; + offset = 0; + GET_MATCHES_FOOTER(offset, 1) +} + +UInt32 Bt3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) +{ + unsigned offset; + GET_MATCHES_HEADER(3) + HASH_ZIP_CALC; + curMatch = p->hash[hv]; + p->hash[hv] = p->pos; + offset = 0; + GET_MATCHES_FOOTER(offset, 2) +} + +static UInt32 Bt3_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) +{ + UInt32 h2, d2, pos; + unsigned maxLen, offset; + UInt32 *hash; + GET_MATCHES_HEADER(3) + + HASH3_CALC; + + hash = p->hash; + pos = p->pos; + + d2 = pos - hash[h2]; + + curMatch = (hash + kFix3HashSize)[hv]; + + hash[h2] = pos; + (hash + kFix3HashSize)[hv] = pos; + + maxLen = 2; + offset = 0; + + if (d2 < p->cyclicBufferSize && *(cur - d2) == *cur) + { + UPDATE_maxLen + distances[0] = (UInt32)maxLen; + distances[1] = d2 - 1; + offset = 2; + if (maxLen == lenLimit) + { + SkipMatchesSpec((UInt32)lenLimit, curMatch, MF_PARAMS(p)); + MOVE_POS_RET; + } + } + + GET_MATCHES_FOOTER(offset, maxLen) +} + +static UInt32 Bt4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) +{ + UInt32 h2, h3, d2, d3, pos; + unsigned maxLen, offset; + UInt32 *hash; + GET_MATCHES_HEADER(4) + + HASH4_CALC; + + hash = p->hash; + pos = p->pos; + + d2 = pos - hash [h2]; + d3 = pos - (hash + kFix3HashSize)[h3]; + + curMatch = (hash + kFix4HashSize)[hv]; + + hash [h2] = pos; + (hash + kFix3HashSize)[h3] = pos; + (hash + kFix4HashSize)[hv] = pos; + + maxLen = 0; + offset = 0; + + if (d2 < p->cyclicBufferSize && *(cur - d2) == *cur) + { + maxLen = 2; + distances[0] = 2; + distances[1] = d2 - 1; + offset = 2; + } + + if (d2 != d3 && d3 < p->cyclicBufferSize && *(cur - d3) == *cur) + { + maxLen = 3; + distances[(size_t)offset + 1] = d3 - 1; + offset += 2; + d2 = d3; + } + + if (offset != 0) + { + UPDATE_maxLen + distances[(size_t)offset - 2] = (UInt32)maxLen; + if (maxLen == lenLimit) + { + SkipMatchesSpec((UInt32)lenLimit, curMatch, MF_PARAMS(p)); + MOVE_POS_RET; + } + } + + if (maxLen < 3) + maxLen = 3; + + GET_MATCHES_FOOTER(offset, maxLen) +} + +/* +static UInt32 Bt5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) +{ + UInt32 h2, h3, h4, d2, d3, d4, maxLen, offset, pos; + UInt32 *hash; + GET_MATCHES_HEADER(5) + + HASH5_CALC; + + hash = p->hash; + pos = p->pos; + + d2 = pos - hash [h2]; + d3 = pos - (hash + kFix3HashSize)[h3]; + d4 = pos - (hash + kFix4HashSize)[h4]; + + curMatch = (hash + kFix5HashSize)[hv]; + + hash [h2] = pos; + (hash + kFix3HashSize)[h3] = pos; + (hash + kFix4HashSize)[h4] = pos; + (hash + kFix5HashSize)[hv] = pos; + + maxLen = 0; + offset = 0; + + if (d2 < p->cyclicBufferSize && *(cur - d2) == *cur) + { + distances[0] = maxLen = 2; + distances[1] = d2 - 1; + offset = 2; + if (*(cur - d2 + 2) == cur[2]) + distances[0] = maxLen = 3; + else if (d3 < p->cyclicBufferSize && *(cur - d3) == *cur) + { + distances[2] = maxLen = 3; + distances[3] = d3 - 1; + offset = 4; + d2 = d3; + } + } + else if (d3 < p->cyclicBufferSize && *(cur - d3) == *cur) + { + distances[0] = maxLen = 3; + distances[1] = d3 - 1; + offset = 2; + d2 = d3; + } + + if (d2 != d4 && d4 < p->cyclicBufferSize + && *(cur - d4) == *cur + && *(cur - d4 + 3) == *(cur + 3)) + { + maxLen = 4; + distances[(size_t)offset + 1] = d4 - 1; + offset += 2; + d2 = d4; + } + + if (offset != 0) + { + UPDATE_maxLen + distances[(size_t)offset - 2] = maxLen; + if (maxLen == lenLimit) + { + SkipMatchesSpec(lenLimit, curMatch, MF_PARAMS(p)); + MOVE_POS_RET; + } + } + + if (maxLen < 4) + maxLen = 4; + + GET_MATCHES_FOOTER(offset, maxLen) +} +*/ + +static UInt32 Hc4_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) +{ + UInt32 h2, h3, d2, d3, pos; + unsigned maxLen, offset; + UInt32 *hash; + GET_MATCHES_HEADER(4) + + HASH4_CALC; + + hash = p->hash; + pos = p->pos; + + d2 = pos - hash [h2]; + d3 = pos - (hash + kFix3HashSize)[h3]; + curMatch = (hash + kFix4HashSize)[hv]; + + hash [h2] = pos; + (hash + kFix3HashSize)[h3] = pos; + (hash + kFix4HashSize)[hv] = pos; + + maxLen = 0; + offset = 0; + + if (d2 < p->cyclicBufferSize && *(cur - d2) == *cur) + { + maxLen = 2; + distances[0] = 2; + distances[1] = d2 - 1; + offset = 2; + } + + if (d2 != d3 && d3 < p->cyclicBufferSize && *(cur - d3) == *cur) + { + maxLen = 3; + distances[(size_t)offset + 1] = d3 - 1; + offset += 2; + d2 = d3; + } + + if (offset != 0) + { + UPDATE_maxLen + distances[(size_t)offset - 2] = (UInt32)maxLen; + if (maxLen == lenLimit) + { + p->son[p->cyclicBufferPos] = curMatch; + MOVE_POS_RET; + } + } + + if (maxLen < 3) + maxLen = 3; + + offset = (unsigned)(Hc_GetMatchesSpec(lenLimit, curMatch, MF_PARAMS(p), + distances + offset, maxLen) - (distances)); + MOVE_POS_RET +} + +/* +static UInt32 Hc5_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) +{ + UInt32 h2, h3, h4, d2, d3, d4, maxLen, offset, pos + UInt32 *hash; + GET_MATCHES_HEADER(5) + + HASH5_CALC; + + hash = p->hash; + pos = p->pos; + + d2 = pos - hash [h2]; + d3 = pos - (hash + kFix3HashSize)[h3]; + d4 = pos - (hash + kFix4HashSize)[h4]; + + curMatch = (hash + kFix5HashSize)[hv]; + + hash [h2] = pos; + (hash + kFix3HashSize)[h3] = pos; + (hash + kFix4HashSize)[h4] = pos; + (hash + kFix5HashSize)[hv] = pos; + + maxLen = 0; + offset = 0; + + if (d2 < p->cyclicBufferSize && *(cur - d2) == *cur) + { + distances[0] = maxLen = 2; + distances[1] = d2 - 1; + offset = 2; + if (*(cur - d2 + 2) == cur[2]) + distances[0] = maxLen = 3; + else if (d3 < p->cyclicBufferSize && *(cur - d3) == *cur) + { + distances[2] = maxLen = 3; + distances[3] = d3 - 1; + offset = 4; + d2 = d3; + } + } + else if (d3 < p->cyclicBufferSize && *(cur - d3) == *cur) + { + distances[0] = maxLen = 3; + distances[1] = d3 - 1; + offset = 2; + d2 = d3; + } + + if (d2 != d4 && d4 < p->cyclicBufferSize + && *(cur - d4) == *cur + && *(cur - d4 + 3) == *(cur + 3)) + { + maxLen = 4; + distances[(size_t)offset + 1] = d4 - 1; + offset += 2; + d2 = d4; + } + + if (offset != 0) + { + UPDATE_maxLen + distances[(size_t)offset - 2] = maxLen; + if (maxLen == lenLimit) + { + p->son[p->cyclicBufferPos] = curMatch; + MOVE_POS_RET; + } + } + + if (maxLen < 4) + maxLen = 4; + + offset = (UInt32)(Hc_GetMatchesSpec(lenLimit, curMatch, MF_PARAMS(p), + distances + offset, maxLen) - (distances)); + MOVE_POS_RET +} +*/ + +UInt32 Hc3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances) +{ + unsigned offset; + GET_MATCHES_HEADER(3) + HASH_ZIP_CALC; + curMatch = p->hash[hv]; + p->hash[hv] = p->pos; + offset = (unsigned)(Hc_GetMatchesSpec(lenLimit, curMatch, MF_PARAMS(p), + distances, 2) - (distances)); + MOVE_POS_RET +} + +static void Bt2_MatchFinder_Skip(CMatchFinder *p, UInt32 num) +{ + do + { + SKIP_HEADER(2) + HASH2_CALC; + curMatch = p->hash[hv]; + p->hash[hv] = p->pos; + SKIP_FOOTER + } + while (--num != 0); +} + +void Bt3Zip_MatchFinder_Skip(CMatchFinder *p, UInt32 num) +{ + do + { + SKIP_HEADER(3) + HASH_ZIP_CALC; + curMatch = p->hash[hv]; + p->hash[hv] = p->pos; + SKIP_FOOTER + } + while (--num != 0); +} + +static void Bt3_MatchFinder_Skip(CMatchFinder *p, UInt32 num) +{ + do + { + UInt32 h2; + UInt32 *hash; + SKIP_HEADER(3) + HASH3_CALC; + hash = p->hash; + curMatch = (hash + kFix3HashSize)[hv]; + hash[h2] = + (hash + kFix3HashSize)[hv] = p->pos; + SKIP_FOOTER + } + while (--num != 0); +} + +static void Bt4_MatchFinder_Skip(CMatchFinder *p, UInt32 num) +{ + do + { + UInt32 h2, h3; + UInt32 *hash; + SKIP_HEADER(4) + HASH4_CALC; + hash = p->hash; + curMatch = (hash + kFix4HashSize)[hv]; + hash [h2] = + (hash + kFix3HashSize)[h3] = + (hash + kFix4HashSize)[hv] = p->pos; + SKIP_FOOTER + } + while (--num != 0); +} + +/* +static void Bt5_MatchFinder_Skip(CMatchFinder *p, UInt32 num) +{ + do + { + UInt32 h2, h3, h4; + UInt32 *hash; + 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; + SKIP_FOOTER + } + while (--num != 0); +} +*/ + +static void Hc4_MatchFinder_Skip(CMatchFinder *p, UInt32 num) +{ + do + { + UInt32 h2, h3; + UInt32 *hash; + SKIP_HEADER(4) + HASH4_CALC; + hash = p->hash; + curMatch = (hash + kFix4HashSize)[hv]; + hash [h2] = + (hash + kFix3HashSize)[h3] = + (hash + kFix4HashSize)[hv] = p->pos; + p->son[p->cyclicBufferPos] = curMatch; + MOVE_POS + } + while (--num != 0); +} + +/* +static void Hc5_MatchFinder_Skip(CMatchFinder *p, UInt32 num) +{ + do + { + UInt32 h2, h3, h4; + UInt32 *hash; + 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; + p->son[p->cyclicBufferPos] = curMatch; + MOVE_POS + } + while (--num != 0); +} +*/ + +void Hc3Zip_MatchFinder_Skip(CMatchFinder *p, UInt32 num) +{ + do + { + SKIP_HEADER(3) + HASH_ZIP_CALC; + curMatch = p->hash[hv]; + p->hash[hv] = p->pos; + p->son[p->cyclicBufferPos] = curMatch; + MOVE_POS + } + while (--num != 0); +} + +void MatchFinder_CreateVTable(CMatchFinder *p, IMatchFinder *vTable) +{ + vTable->Init = (Mf_Init_Func)MatchFinder_Init; + vTable->GetNumAvailableBytes = (Mf_GetNumAvailableBytes_Func)MatchFinder_GetNumAvailableBytes; + vTable->GetPointerToCurrentPos = (Mf_GetPointerToCurrentPos_Func)MatchFinder_GetPointerToCurrentPos; + if (!p->btMode) + { + /* if (p->numHashBytes <= 4) */ + { + vTable->GetMatches = (Mf_GetMatches_Func)Hc4_MatchFinder_GetMatches; + vTable->Skip = (Mf_Skip_Func)Hc4_MatchFinder_Skip; + } + /* + else + { + vTable->GetMatches = (Mf_GetMatches_Func)Hc5_MatchFinder_GetMatches; + vTable->Skip = (Mf_Skip_Func)Hc5_MatchFinder_Skip; + } + */ + } + else if (p->numHashBytes == 2) + { + vTable->GetMatches = (Mf_GetMatches_Func)Bt2_MatchFinder_GetMatches; + vTable->Skip = (Mf_Skip_Func)Bt2_MatchFinder_Skip; + } + else if (p->numHashBytes == 3) + { + vTable->GetMatches = (Mf_GetMatches_Func)Bt3_MatchFinder_GetMatches; + vTable->Skip = (Mf_Skip_Func)Bt3_MatchFinder_Skip; + } + else /* if (p->numHashBytes == 4) */ + { + vTable->GetMatches = (Mf_GetMatches_Func)Bt4_MatchFinder_GetMatches; + vTable->Skip = (Mf_Skip_Func)Bt4_MatchFinder_Skip; + } + /* + else + { + vTable->GetMatches = (Mf_GetMatches_Func)Bt5_MatchFinder_GetMatches; + vTable->Skip = (Mf_Skip_Func)Bt5_MatchFinder_Skip; + } + */ +} diff --git a/htp/lzma/LzFind.h b/htp/lzma/LzFind.h new file mode 100644 index 0000000..c77adde --- /dev/null +++ b/htp/lzma/LzFind.h @@ -0,0 +1,121 @@ +/* LzFind.h -- Match finder for LZ algorithms +2017-06-10 : Igor Pavlov : Public domain */ + +#ifndef __LZ_FIND_H +#define __LZ_FIND_H + +#include "7zTypes.h" + +EXTERN_C_BEGIN + +typedef UInt32 CLzRef; + +typedef struct _CMatchFinder +{ + Byte *buffer; + UInt32 pos; + UInt32 posLimit; + UInt32 streamPos; + UInt32 lenLimit; + + UInt32 cyclicBufferPos; + UInt32 cyclicBufferSize; /* it must be = (historySize + 1) */ + + Byte streamEndWasReached; + Byte btMode; + Byte bigHash; + Byte directInput; + + UInt32 matchMaxLen; + CLzRef *hash; + CLzRef *son; + UInt32 hashMask; + UInt32 cutValue; + + Byte *bufferBase; + ISeqInStream *stream; + + UInt32 blockSize; + UInt32 keepSizeBefore; + UInt32 keepSizeAfter; + + UInt32 numHashBytes; + size_t directInputRem; + UInt32 historySize; + UInt32 fixedHashSize; + UInt32 hashSizeSum; + SRes result; + UInt32 crc[256]; + size_t numRefs; + + UInt64 expectedDataSize; +} CMatchFinder; + +#define Inline_MatchFinder_GetPointerToCurrentPos(p) ((p)->buffer) + +#define Inline_MatchFinder_GetNumAvailableBytes(p) ((p)->streamPos - (p)->pos) + +#define Inline_MatchFinder_IsFinishedOK(p) \ + ((p)->streamEndWasReached \ + && (p)->streamPos == (p)->pos \ + && (!(p)->directInput || (p)->directInputRem == 0)) + +int MatchFinder_NeedMove(CMatchFinder *p); +Byte *MatchFinder_GetPointerToCurrentPos(CMatchFinder *p); +void MatchFinder_MoveBlock(CMatchFinder *p); +void MatchFinder_ReadIfRequired(CMatchFinder *p); + +void MatchFinder_Construct(CMatchFinder *p); + +/* Conditions: + historySize <= 3 GB + keepAddBufferBefore + matchMaxLen + keepAddBufferAfter < 511MB +*/ +int MatchFinder_Create(CMatchFinder *p, UInt32 historySize, + UInt32 keepAddBufferBefore, UInt32 matchMaxLen, UInt32 keepAddBufferAfter, + 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); + +UInt32 * GetMatchesSpec1(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byte *buffer, CLzRef *son, + UInt32 _cyclicBufferPos, UInt32 _cyclicBufferSize, UInt32 _cutValue, + UInt32 *distances, UInt32 maxLen); + +/* +Conditions: + Mf_GetNumAvailableBytes_Func must be called before each Mf_GetMatchLen_Func. + Mf_GetPointerToCurrentPos_Func's result must be used only before any other function +*/ + +typedef void (*Mf_Init_Func)(void *object); +typedef UInt32 (*Mf_GetNumAvailableBytes_Func)(void *object); +typedef const Byte * (*Mf_GetPointerToCurrentPos_Func)(void *object); +typedef UInt32 (*Mf_GetMatches_Func)(void *object, UInt32 *distances); +typedef void (*Mf_Skip_Func)(void *object, UInt32); + +typedef struct _IMatchFinder +{ + Mf_Init_Func Init; + Mf_GetNumAvailableBytes_Func GetNumAvailableBytes; + Mf_GetPointerToCurrentPos_Func GetPointerToCurrentPos; + Mf_GetMatches_Func GetMatches; + Mf_Skip_Func Skip; +} IMatchFinder; + +void MatchFinder_CreateVTable(CMatchFinder *p, IMatchFinder *vTable); + +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); +UInt32 Hc3Zip_MatchFinder_GetMatches(CMatchFinder *p, UInt32 *distances); + +void Bt3Zip_MatchFinder_Skip(CMatchFinder *p, UInt32 num); +void Hc3Zip_MatchFinder_Skip(CMatchFinder *p, UInt32 num); + +EXTERN_C_END + +#endif diff --git a/htp/lzma/LzHash.h b/htp/lzma/LzHash.h new file mode 100644 index 0000000..2191444 --- /dev/null +++ b/htp/lzma/LzHash.h @@ -0,0 +1,57 @@ +/* LzHash.h -- HASH functions for LZ algorithms +2015-04-12 : Igor Pavlov : Public domain */ + +#ifndef __LZ_HASH_H +#define __LZ_HASH_H + +#define kHash2Size (1 << 10) +#define kHash3Size (1 << 16) +#define kHash4Size (1 << 20) + +#define kFix3HashSize (kHash2Size) +#define kFix4HashSize (kHash2Size + kHash3Size) +#define kFix5HashSize (kHash2Size + kHash3Size + kHash4Size) + +#define HASH2_CALC hv = cur[0] | ((UInt32)cur[1] << 8); + +#define HASH3_CALC { \ + UInt32 temp = p->crc[cur[0]] ^ cur[1]; \ + h2 = temp & (kHash2Size - 1); \ + hv = (temp ^ ((UInt32)cur[2] << 8)) & p->hashMask; } + +#define HASH4_CALC { \ + UInt32 temp = p->crc[cur[0]] ^ cur[1]; \ + h2 = temp & (kHash2Size - 1); \ + temp ^= ((UInt32)cur[2] << 8); \ + h3 = temp & (kHash3Size - 1); \ + hv = (temp ^ (p->crc[cur[3]] << 5)) & p->hashMask; } + +#define HASH5_CALC { \ + UInt32 temp = p->crc[cur[0]] ^ cur[1]; \ + h2 = temp & (kHash2Size - 1); \ + temp ^= ((UInt32)cur[2] << 8); \ + h3 = temp & (kHash3Size - 1); \ + temp ^= (p->crc[cur[3]] << 5); \ + h4 = temp & (kHash4Size - 1); \ + hv = (temp ^ (p->crc[cur[4]] << 3)) & p->hashMask; } + +/* #define HASH_ZIP_CALC hv = ((cur[0] | ((UInt32)cur[1] << 8)) ^ p->crc[cur[2]]) & 0xFFFF; */ +#define HASH_ZIP_CALC hv = ((cur[2] | ((UInt32)cur[0] << 8)) ^ p->crc[cur[1]]) & 0xFFFF; + + +#define MT_HASH2_CALC \ + h2 = (p->crc[cur[0]] ^ cur[1]) & (kHash2Size - 1); + +#define MT_HASH3_CALC { \ + UInt32 temp = p->crc[cur[0]] ^ cur[1]; \ + h2 = temp & (kHash2Size - 1); \ + h3 = (temp ^ ((UInt32)cur[2] << 8)) & (kHash3Size - 1); } + +#define MT_HASH4_CALC { \ + UInt32 temp = p->crc[cur[0]] ^ cur[1]; \ + h2 = temp & (kHash2Size - 1); \ + temp ^= ((UInt32)cur[2] << 8); \ + h3 = temp & (kHash3Size - 1); \ + h4 = (temp ^ (p->crc[cur[3]] << 5)) & (kHash4Size - 1); } + +#endif diff --git a/htp/lzma/LzmaDec.c b/htp/lzma/LzmaDec.c new file mode 100644 index 0000000..138c36c --- /dev/null +++ b/htp/lzma/LzmaDec.c @@ -0,0 +1,1223 @@ +/* LzmaDec.c -- LZMA Decoder +2018-07-04 : Igor Pavlov : Public domain */ + +#include "Precomp.h" + +#include +#include +#include + +/* #include "CpuArch.h" */ +#include "LzmaDec.h" + +#define kNumTopBits 24 +#define kTopValue ((UInt32)1 << kNumTopBits) + +#define kNumBitModelTotalBits 11 +#define kBitModelTotal (1 << kNumBitModelTotalBits) +#define kNumMoveBits 5 + +#define RC_INIT_SIZE 5 + +#define NORMALIZE if (range < kTopValue) { range <<= 8; code = (code << 8) | (*buf++); } + +#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 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; } + +/* #define _LZMA_SIZE_OPT */ + +#ifdef _LZMA_SIZE_OPT +#define TREE_6_DECODE(probs, i) TREE_DECODE(probs, (1 << 6), i) +#else +#define TREE_6_DECODE(probs, i) \ + { i = 1; \ + TREE_GET_BIT(probs, i); \ + TREE_GET_BIT(probs, i); \ + TREE_GET_BIT(probs, i); \ + TREE_GET_BIT(probs, i); \ + TREE_GET_BIT(probs, i); \ + TREE_GET_BIT(probs, i); \ + i -= 0x40; } +#endif + +#define NORMAL_LITER_DEC TREE_GET_BIT(prob, symbol) +#define MATCHED_LITER_DEC \ + 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) * (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) \ + { UPDATE_0_CHECK; i = (i + i); A0; } else \ + { UPDATE_1_CHECK; i = (i + i) + 1; A1; } +#define GET_BIT_CHECK(p, i) GET_BIT2_CHECK(p, i, ; , ;) +#define TREE_DECODE_CHECK(probs, limit, i) \ + { 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 kLenNumHighBits 8 +#define kLenNumHighSymbols (1 << kLenNumHighBits) + +#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 +#define kEndPosModelIndex 14 +#define kNumFullDistances (1 << (kEndPosModelIndex >> 1)) + +#define kNumPosSlotBits 6 +#define kNumLenToPosStates 4 + +#define kNumAlignBits 4 +#define kAlignTableSize (1 << kNumAlignBits) + +#define kMatchMinLen 2 +#define kMatchSpecLenStart (kMatchMinLen + kLenNumLowSymbols * 2 + kLenNumHighSymbols) + +/* 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 PosSlot (IsRepG2 + kNumStates) +#define Literal (PosSlot + (kNumLenToPosStates << kNumPosSlotBits)) +#define NUM_BASE_PROBS (Literal + kStartOffset) + +#if Align != 0 && kStartOffset != 0 + #error Stop_Compiling_Bad_LZMA_kAlign +#endif + +#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) + +/* +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 +*/ + + +#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 lc = p->prop.lc; + unsigned lpMask = ((unsigned)0x100 << p->prop.lp) - ((unsigned)0x100 >> lc); + + Byte *dic = p->dic; + SizeT dicBufSize = p->dicBufSize; + SizeT dicPos = p->dicPos; + + UInt32 processedPos = p->processedPos; + UInt32 checkDicSize = p->checkDicSize; + unsigned len = 0; + + const Byte *buf = p->buf; + UInt32 range = p->range; + UInt32 code = p->code; + + do + { + CLzmaProb *prob; + UInt32 bound; + unsigned ttt; + unsigned posState = CALC_POS_STATE(processedPos, pbMask); + + 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)3 * ((((processedPos << 8) + dic[(dicPos == 0 ? dicBufSize : dicPos) - 1]) & lpMask) << lc); + processedPos++; + + if (state < kNumLitStates) + { + state -= (state < 4) ? state : 3; + symbol = 1; + #ifdef _LZMA_SIZE_OPT + do { NORMAL_LITER_DEC } while (symbol < 0x100); + #else + NORMAL_LITER_DEC + NORMAL_LITER_DEC + NORMAL_LITER_DEC + NORMAL_LITER_DEC + NORMAL_LITER_DEC + NORMAL_LITER_DEC + NORMAL_LITER_DEC + NORMAL_LITER_DEC + #endif + } + else + { + unsigned matchByte = dic[dicPos - rep0 + (dicPos < rep0 ? dicBufSize : 0)]; + unsigned offs = 0x100; + state -= (state < 10) ? 3 : 6; + symbol = 1; + #ifdef _LZMA_SIZE_OPT + do + { + unsigned bit; + CLzmaProb *probLit; + MATCHED_LITER_DEC + } + while (symbol < 0x100); + #else + { + unsigned bit; + CLzmaProb *probLit; + MATCHED_LITER_DEC + MATCHED_LITER_DEC + MATCHED_LITER_DEC + MATCHED_LITER_DEC + MATCHED_LITER_DEC + MATCHED_LITER_DEC + MATCHED_LITER_DEC + MATCHED_LITER_DEC + } + #endif + } + + dic[dicPos++] = (Byte)symbol; + continue; + } + + { + UPDATE_1(prob); + prob = probs + IsRep + state; + IF_BIT_0(prob) + { + UPDATE_0(prob); + state += kNumStates; + prob = probs + LenCoder; + } + 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 + COMBINED_PS_STATE; + IF_BIT_0(prob) + { + UPDATE_0(prob); + dic[dicPos] = dic[dicPos - rep0 + (dicPos < rep0 ? dicBufSize : 0)]; + dicPos++; + processedPos++; + state = state < kNumLitStates ? 9 : 11; + continue; + } + UPDATE_1(prob); + } + else + { + UInt32 distance; + UPDATE_1(prob); + prob = probs + IsRepG1 + state; + IF_BIT_0(prob) + { + UPDATE_0(prob); + distance = rep1; + } + else + { + UPDATE_1(prob); + prob = probs + IsRepG2 + state; + IF_BIT_0(prob) + { + UPDATE_0(prob); + distance = rep2; + } + else + { + UPDATE_1(prob); + distance = rep3; + rep3 = rep2; + } + rep2 = rep1; + } + rep1 = rep0; + rep0 = distance; + } + state = state < kNumLitStates ? 8 : 11; + prob = probs + RepLenCoder; + } + + #ifdef _LZMA_SIZE_OPT + { + unsigned lim, offset; + CLzmaProb *probLen = prob + LenChoice; + IF_BIT_0(probLen) + { + UPDATE_0(probLen); + probLen = prob + LenLow + GET_LEN_STATE; + offset = 0; + lim = (1 << kLenNumLowBits); + } + else + { + UPDATE_1(probLen); + probLen = prob + LenChoice2; + IF_BIT_0(probLen) + { + UPDATE_0(probLen); + probLen = prob + LenLow + GET_LEN_STATE + (1 << kLenNumLowBits); + offset = kLenNumLowSymbols; + lim = (1 << kLenNumLowBits); + } + else + { + UPDATE_1(probLen); + probLen = prob + LenHigh; + offset = kLenNumLowSymbols * 2; + lim = (1 << kLenNumHighBits); + } + } + TREE_DECODE(probLen, lim, len); + len += offset; + } + #else + { + CLzmaProb *probLen = prob + LenChoice; + IF_BIT_0(probLen) + { + UPDATE_0(probLen); + probLen = prob + LenLow + GET_LEN_STATE; + len = 1; + TREE_GET_BIT(probLen, len); + TREE_GET_BIT(probLen, len); + TREE_GET_BIT(probLen, len); + len -= 8; + } + else + { + UPDATE_1(probLen); + probLen = prob + LenChoice2; + IF_BIT_0(probLen) + { + UPDATE_0(probLen); + probLen = prob + LenLow + GET_LEN_STATE + (1 << kLenNumLowBits); + len = 1; + TREE_GET_BIT(probLen, len); + TREE_GET_BIT(probLen, len); + TREE_GET_BIT(probLen, len); + } + else + { + UPDATE_1(probLen); + probLen = prob + LenHigh; + TREE_DECODE(probLen, (1 << kLenNumHighBits), len); + len += kLenNumLowSymbols * 2; + } + } + } + #endif + + if (state >= kNumStates) + { + UInt32 distance; + prob = probs + PosSlot + + ((len < kNumLenToPosStates ? len : kNumLenToPosStates - 1) << kNumPosSlotBits); + TREE_6_DECODE(prob, distance); + if (distance >= kStartPosModelIndex) + { + unsigned posSlot = (unsigned)distance; + unsigned numDirectBits = (unsigned)(((distance >> 1) - 1)); + distance = (2 | (distance & 1)); + if (posSlot < kEndPosModelIndex) + { + distance <<= numDirectBits; + prob = probs + SpecPos; + { + UInt32 m = 1; + distance++; + do + { + REV_BIT_VAR(prob, distance, m); + } + while (--numDirectBits); + distance -= m; + } + } + else + { + numDirectBits -= kNumAlignBits; + do + { + NORMALIZE + range >>= 1; + + { + UInt32 t; + code -= range; + t = (0 - ((UInt32)code >> 31)); /* (UInt32)((Int32)code >> 31) */ + distance = (distance << 1) + (t + 1); + code += range & t; + } + /* + distance <<= 1; + if (code >= range) + { + code -= range; + distance |= 1; + } + */ + } + while (--numDirectBits); + prob = probs + Align; + distance <<= kNumAlignBits; + { + unsigned i = 1; + 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; + state -= kNumStates; + break; + } + } + } + + rep3 = rep2; + rep2 = rep1; + rep1 = rep0; + rep0 = distance + 1; + state = (state < kNumStates + kNumLitStates) ? kNumLitStates : kNumLitStates + 3; + if (distance >= (checkDicSize == 0 ? processedPos: checkDicSize)) + { + p->dicPos = dicPos; + return SZ_ERROR_DATA; + } + } + + len += kMatchMinLen; + + { + SizeT rem; + unsigned curLen; + SizeT pos; + + if ((rem = limit - dicPos) == 0) + { + p->dicPos = dicPos; + return SZ_ERROR_DATA; + } + + curLen = ((rem < len) ? (unsigned)rem : len); + pos = dicPos - rep0 + (dicPos < rep0 ? dicBufSize : 0); + + processedPos += (UInt32)curLen; + + len -= curLen; + if (curLen <= dicBufSize - pos) + { + Byte *dest = dic + dicPos; + ptrdiff_t src = (ptrdiff_t)pos - (ptrdiff_t)dicPos; + const Byte *lim = dest + curLen; + dicPos += (SizeT)curLen; + do + *(dest) = (Byte)*(dest + src); + while (++dest != lim); + } + else + { + do + { + dic[dicPos++] = dic[pos]; + if (++pos == dicBufSize) + pos = 0; + } + while (--curLen != 0); + } + } + } + } + while (dicPos < limit && buf < bufLimit); + + NORMALIZE; + + p->buf = buf; + p->range = range; + p->code = code; + 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 = (UInt32)state; + + return SZ_OK; +} +#endif + +static void MY_FAST_CALL LzmaDec_WriteRem(CLzmaDec *p, SizeT limit) +{ + if (p->remainLen != 0 && p->remainLen < kMatchSpecLenStart) + { + Byte *dic = p->dic; + SizeT dicPos = p->dicPos; + SizeT dicBufSize = p->dicBufSize; + 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) + len = (unsigned)(rem); + + if (p->checkDicSize == 0 && p->prop.dicSize - p->processedPos <= len) + p->checkDicSize = p->prop.dicSize; + + p->processedPos += (UInt32)len; + p->remainLen -= (UInt32)len; + while (len != 0) + { + len--; + dic[dicPos] = dic[dicPos - rep0 + (dicPos < rep0 ? dicBufSize : 0)]; + dicPos++; + } + p->dicPos = dicPos; + } +} + + +#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, SizeT memlimit) +{ + do + { + SizeT limit2 = limit; + if (p->checkDicSize == 0) + { + UInt32 rem = p->prop.dicSize - p->processedPos; + if (limit - p->dicPos > rem) { + if (p->dicBufSize < p->prop.dicSize) { + p->dicBufSize = p->prop.dicSize; + if (p->dicBufSize > memlimit) { + return SZ_ERROR_MEM; + } + Byte *tmp = realloc(p->dic, p->dicBufSize); + if (!tmp) { + return SZ_ERROR_MEM; + } + p->dic = tmp; + } + limit2 = p->dicPos + rem; + } + + if (p->processedPos == 0) + if (p->code >= kBadRepCode) + return SZ_ERROR_DATA; + } + + RINOK(LZMA_DECODE_REAL(p, limit2, bufLimit)); + + if (p->checkDicSize == 0 && p->processedPos >= p->prop.dicSize) + p->checkDicSize = p->prop.dicSize; + + LzmaDec_WriteRem(p, limit); + } + while (p->dicPos < limit && p->buf < bufLimit && p->remainLen < kMatchSpecLenStart); + + return 0; +} + +typedef enum +{ + DUMMY_ERROR, /* unexpected end of input stream */ + DUMMY_LIT, + DUMMY_MATCH, + DUMMY_REP +} ELzmaDummy; + +static ELzmaDummy LzmaDec_TryDummy(const CLzmaDec *p, const Byte *buf, SizeT inSize) +{ + UInt32 range = p->range; + UInt32 code = p->code; + const Byte *bufLimit = buf + inSize; + const CLzmaProb *probs = GET_PROBS; + unsigned state = (unsigned)p->state; + ELzmaDummy res; + + { + const CLzmaProb *prob; + UInt32 bound; + unsigned ttt; + unsigned posState = CALC_POS_STATE(p->processedPos, (1 << p->prop.pb) - 1); + + prob = probs + IsMatch + COMBINED_PS_STATE; + IF_BIT_0_CHECK(prob) + { + UPDATE_0_CHECK + + /* if (bufLimit - buf >= 7) return DUMMY_LIT; */ + + prob = probs + Literal; + if (p->checkDicSize != 0 || p->processedPos != 0) + prob += ((UInt32)LZMA_LIT_SIZE * + ((((p->processedPos) & ((1 << (p->prop.lp)) - 1)) << p->prop.lc) + + (p->dic[(p->dicPos == 0 ? p->dicBufSize : p->dicPos) - 1] >> (8 - p->prop.lc)))); + + if (state < kNumLitStates) + { + unsigned symbol = 1; + do { GET_BIT_CHECK(prob + symbol, symbol) } while (symbol < 0x100); + } + else + { + unsigned matchByte = p->dic[p->dicPos - p->reps[0] + + (p->dicPos < p->reps[0] ? p->dicBufSize : 0)]; + unsigned offs = 0x100; + unsigned symbol = 1; + do + { + unsigned bit; + const CLzmaProb *probLit; + matchByte += matchByte; + bit = offs; + offs &= matchByte; + probLit = prob + (offs + bit + symbol); + GET_BIT2_CHECK(probLit, symbol, offs ^= bit; , ; ) + } + while (symbol < 0x100); + } + res = DUMMY_LIT; + } + else + { + unsigned len; + UPDATE_1_CHECK; + + prob = probs + IsRep + state; + IF_BIT_0_CHECK(prob) + { + UPDATE_0_CHECK; + state = 0; + prob = probs + LenCoder; + res = DUMMY_MATCH; + } + else + { + UPDATE_1_CHECK; + res = DUMMY_REP; + prob = probs + IsRepG0 + state; + IF_BIT_0_CHECK(prob) + { + UPDATE_0_CHECK; + prob = probs + IsRep0Long + COMBINED_PS_STATE; + IF_BIT_0_CHECK(prob) + { + UPDATE_0_CHECK; + NORMALIZE_CHECK; + return DUMMY_REP; + } + else + { + UPDATE_1_CHECK; + } + } + else + { + UPDATE_1_CHECK; + prob = probs + IsRepG1 + state; + IF_BIT_0_CHECK(prob) + { + UPDATE_0_CHECK; + } + else + { + UPDATE_1_CHECK; + prob = probs + IsRepG2 + state; + IF_BIT_0_CHECK(prob) + { + UPDATE_0_CHECK; + } + else + { + UPDATE_1_CHECK; + } + } + } + state = kNumStates; + prob = probs + RepLenCoder; + } + { + unsigned limit, offset; + const CLzmaProb *probLen = prob + LenChoice; + IF_BIT_0_CHECK(probLen) + { + UPDATE_0_CHECK; + probLen = prob + LenLow + GET_LEN_STATE; + offset = 0; + limit = 1 << kLenNumLowBits; + } + else + { + UPDATE_1_CHECK; + probLen = prob + LenChoice2; + IF_BIT_0_CHECK(probLen) + { + UPDATE_0_CHECK; + probLen = prob + LenLow + GET_LEN_STATE + (1 << kLenNumLowBits); + offset = kLenNumLowSymbols; + limit = 1 << kLenNumLowBits; + } + else + { + UPDATE_1_CHECK; + probLen = prob + LenHigh; + offset = kLenNumLowSymbols * 2; + limit = 1 << kLenNumHighBits; + } + } + TREE_DECODE_CHECK(probLen, limit, len); + len += offset; + } + + if (state < 4) + { + unsigned posSlot; + prob = probs + PosSlot + + ((len < kNumLenToPosStates - 1 ? len : kNumLenToPosStates - 1) << + kNumPosSlotBits); + TREE_DECODE_CHECK(prob, 1 << kNumPosSlotBits, posSlot); + if (posSlot >= kStartPosModelIndex) + { + unsigned numDirectBits = ((posSlot >> 1) - 1); + + /* if (bufLimit - buf >= 8) return DUMMY_MATCH; */ + + if (posSlot < kEndPosModelIndex) + { + prob = probs + SpecPos + ((2 | (posSlot & 1)) << numDirectBits); + } + else + { + numDirectBits -= kNumAlignBits; + do + { + NORMALIZE_CHECK + range >>= 1; + code -= range & (((code - range) >> 31) - 1); + /* if (code >= range) code -= range; */ + } + while (--numDirectBits); + prob = probs + Align; + numDirectBits = kNumAlignBits; + } + { + unsigned i = 1; + unsigned m = 1; + do + { + REV_BIT_CHECK(prob, i, m); + } + while (--numDirectBits); + } + } + } + } + } + NORMALIZE_CHECK; + return res; +} + + +static void LzmaDec_InitDicAndState(CLzmaDec *p, BoolInt initDic, BoolInt initState) +{ + p->remainLen = kMatchSpecLenStart + 1; + p->tempBufSize = 0; + + if (initDic) + { + p->processedPos = 0; + p->checkDicSize = 0; + p->remainLen = kMatchSpecLenStart + 2; + } + if (initState) + p->remainLen = kMatchSpecLenStart + 2; +} + +void LzmaDec_Init(CLzmaDec *p) +{ + p->dicPos = 0; + LzmaDec_InitDicAndState(p, True, True); +} + + +SRes LzmaDec_DecodeToDic(CLzmaDec *p, SizeT dicLimit, const Byte *src, SizeT *srcLen, + ELzmaFinishMode finishMode, ELzmaStatus *status, SizeT memlimit) +{ + SizeT inSize = *srcLen; + (*srcLen) = 0; + + *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 = 0; + + if (p->dicPos >= dicLimit) + { + if (p->remainLen == 0 && p->code == 0) + { + *status = LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK; + return SZ_OK; + } + if (finishMode == LZMA_FINISH_ANY) + { + *status = LZMA_STATUS_NOT_FINISHED; + return SZ_OK; + } + if (p->remainLen != 0) + { + *status = LZMA_STATUS_NOT_FINISHED; + return SZ_ERROR_DATA; + } + checkEndMarkNow = 1; + } + + if (p->tempBufSize == 0) + { + SizeT processed; + const Byte *bufLimit; + if (inSize < LZMA_REQUIRED_INPUT_MAX || checkEndMarkNow) + { + int dummyRes = LzmaDec_TryDummy(p, src, inSize); + if (dummyRes == DUMMY_ERROR) + { + memcpy(p->tempBuf, src, inSize); + p->tempBufSize = (unsigned)inSize; + (*srcLen) += inSize; + *status = LZMA_STATUS_NEEDS_MORE_INPUT; + return SZ_OK; + } + if (checkEndMarkNow && dummyRes != DUMMY_MATCH) + { + *status = LZMA_STATUS_NOT_FINISHED; + return SZ_ERROR_DATA; + } + bufLimit = src; + } + else + bufLimit = src + inSize - LZMA_REQUIRED_INPUT_MAX; + p->buf = src; + if (LzmaDec_DecodeReal2(p, dicLimit, bufLimit, memlimit) != 0) + return SZ_ERROR_DATA; + processed = (SizeT)(p->buf - src); + (*srcLen) += processed; + src += processed; + inSize -= processed; + } + else + { + unsigned rem = p->tempBufSize, lookAhead = 0; + while (rem < LZMA_REQUIRED_INPUT_MAX && lookAhead < inSize) + p->tempBuf[rem++] = src[lookAhead++]; + p->tempBufSize = rem; + if (rem < LZMA_REQUIRED_INPUT_MAX || checkEndMarkNow) + { + int dummyRes = LzmaDec_TryDummy(p, p->tempBuf, (SizeT)rem); + if (dummyRes == DUMMY_ERROR) + { + (*srcLen) += (SizeT)lookAhead; + *status = LZMA_STATUS_NEEDS_MORE_INPUT; + return SZ_OK; + } + if (checkEndMarkNow && dummyRes != DUMMY_MATCH) + { + *status = LZMA_STATUS_NOT_FINISHED; + return SZ_ERROR_DATA; + } + } + p->buf = p->tempBuf; + if (LzmaDec_DecodeReal2(p, dicLimit, p->buf, memlimit) != 0) + return SZ_ERROR_DATA; + + { + unsigned kkk = (unsigned)(p->buf - p->tempBuf); + if (rem < kkk) + return SZ_ERROR_FAIL; /* some internal error */ + rem -= kkk; + if (lookAhead < rem) + return SZ_ERROR_FAIL; /* some internal error */ + lookAhead -= rem; + } + (*srcLen) += (SizeT)lookAhead; + src += lookAhead; + inSize -= (SizeT)lookAhead; + p->tempBufSize = 0; + } + } + + 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 memlimit) +{ + SizeT outSize = *destLen; + SizeT inSize = *srcLen; + *srcLen = *destLen = 0; + for (;;) + { + SizeT inSizeCur = inSize, outSizeCur, dicPos; + ELzmaFinishMode curFinishMode; + SRes res; + if (p->dicPos == p->dicBufSize) { + if (p->dicBufSize < p->prop.dicSize) { + if (p->dicBufSize < memlimit) { + p->dicBufSize = p->dicBufSize << 2; + if (p->dicBufSize > memlimit) { + p->dicBufSize = memlimit; + } + if (p->dicBufSize > p->prop.dicSize) { + p->dicBufSize = p->prop.dicSize; + } + Byte *tmp = realloc(p->dic, p->dicBufSize); + if (!tmp) { + return SZ_ERROR_MEM; + } + p->dic = tmp; + } else { + return SZ_ERROR_MEM; + } + } else { + p->dicPos = 0; + } + } + dicPos = p->dicPos; + if (outSize > p->dicBufSize - dicPos) + { + outSizeCur = p->dicBufSize; + curFinishMode = LZMA_FINISH_ANY; + } + else + { + outSizeCur = dicPos + outSize; + curFinishMode = finishMode; + } + + res = LzmaDec_DecodeToDic(p, outSizeCur, src, &inSizeCur, curFinishMode, status, memlimit); + src += inSizeCur; + inSize -= inSizeCur; + *srcLen += inSizeCur; + outSizeCur = p->dicPos - dicPos; + memcpy(dest, p->dic + dicPos, outSizeCur); + dest += outSizeCur; + outSize -= outSizeCur; + *destLen += outSizeCur; + if (res != 0) + return res; + if (outSizeCur == 0 || outSize == 0) + return SZ_OK; + } +} + +void LzmaDec_FreeProbs(CLzmaDec *p, ISzAllocPtr alloc) +{ + ISzAlloc_Free(alloc, p->probs); + p->probs = NULL; +} + +static void LzmaDec_FreeDict(CLzmaDec *p, ISzAllocPtr alloc) +{ + ISzAlloc_Free(alloc, p->dic); + p->dic = NULL; +} + +void LzmaDec_Free(CLzmaDec *p, ISzAllocPtr alloc) +{ + LzmaDec_FreeProbs(p, alloc); + LzmaDec_FreeDict(p, alloc); +} + +SRes LzmaProps_Decode(CLzmaProps *p, const Byte *data, unsigned size) +{ + UInt32 dicSize; + Byte d; + + if (size < LZMA_PROPS_SIZE) + return SZ_ERROR_UNSUPPORTED; + else + dicSize = data[1] | ((UInt32)data[2] << 8) | ((UInt32)data[3] << 16) | ((UInt32)data[4] << 24); + + if (dicSize < LZMA_DIC_MIN) + dicSize = LZMA_DIC_MIN; + p->dicSize = dicSize; + + d = data[0]; + if (d >= (9 * 5 * 5)) + return SZ_ERROR_UNSUPPORTED; + + p->lc = (Byte)(d % 9); + d /= 9; + p->pb = (Byte)(d / 5); + p->lp = (Byte)(d % 5); + p->_pad_ = 0; + + return SZ_OK; +} + +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 *)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, ISzAllocPtr alloc) +{ + CLzmaProps propNew; + RINOK(LzmaProps_Decode(&propNew, props, propsSize)); + RINOK(LzmaDec_AllocateProbs2(p, &propNew, alloc)); + p->prop = propNew; + return SZ_OK; +} + +SRes LzmaDec_Allocate(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAllocPtr alloc) +{ + CLzmaProps propNew; + SizeT dicBufSize; + RINOK(LzmaProps_Decode(&propNew, props, propsSize)); + RINOK(LzmaDec_AllocateProbs2(p, &propNew, alloc)); + + { + UInt32 dictSize = propNew.dicSize; + SizeT mask = ((UInt32)1 << 12) - 1; + if (dictSize >= ((UInt32)1 << 30)) mask = ((UInt32)1 << 22) - 1; + else if (dictSize >= ((UInt32)1 << 22)) mask = ((UInt32)1 << 20) - 1;; + dicBufSize = ((SizeT)dictSize + mask) & ~mask; + if (dicBufSize < dictSize) + dicBufSize = dictSize; + } + if (dicBufSize > LZMA_DIC_MIN) { + dicBufSize = LZMA_DIC_MIN; + } + + if (!p->dic || dicBufSize != p->dicBufSize) + { + LzmaDec_FreeDict(p, alloc); + p->dic = (Byte *)ISzAlloc_Alloc(alloc, dicBufSize); + if (!p->dic) + { + LzmaDec_FreeProbs(p, alloc); + return SZ_ERROR_MEM; + } + } + p->dicBufSize = dicBufSize; + p->prop = propNew; + return SZ_OK; +} + +SRes LzmaDecode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen, + const Byte *propData, unsigned propSize, ELzmaFinishMode finishMode, + ELzmaStatus *status, ISzAllocPtr alloc) +{ + CLzmaDec p; + SRes res; + SizeT outSize = *destLen, inSize = *srcLen; + *destLen = *srcLen = 0; + *status = LZMA_STATUS_NOT_SPECIFIED; + if (inSize < RC_INIT_SIZE) + return SZ_ERROR_INPUT_EOF; + LzmaDec_Construct(&p); + RINOK(LzmaDec_AllocateProbs(&p, propData, propSize, alloc)); + p.dic = dest; + p.dicBufSize = outSize; + LzmaDec_Init(&p); + *srcLen = inSize; + res = LzmaDec_DecodeToDic(&p, outSize, src, srcLen, finishMode, status, SIZE_MAX); + *destLen = p.dicPos; + if (res == SZ_OK && *status == LZMA_STATUS_NEEDS_MORE_INPUT) + res = SZ_ERROR_INPUT_EOF; + LzmaDec_FreeProbs(&p, alloc); + return res; +} diff --git a/htp/lzma/LzmaDec.h b/htp/lzma/LzmaDec.h new file mode 100644 index 0000000..20b5228 --- /dev/null +++ b/htp/lzma/LzmaDec.h @@ -0,0 +1,234 @@ +/* LzmaDec.h -- LZMA Decoder +2018-04-21 : Igor Pavlov : Public domain */ + +#ifndef __LZMA_DEC_H +#define __LZMA_DEC_H + +#include "7zTypes.h" + +EXTERN_C_BEGIN + +/* #define _LZMA_PROB32 */ +/* _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 + UInt32 +#else + UInt16 +#endif + CLzmaProb; + + +/* ---------- LZMA Properties ---------- */ + +#define LZMA_PROPS_SIZE 5 + +typedef struct _CLzmaProps +{ + Byte lc; + Byte lp; + Byte pb; + Byte _pad_; + UInt32 dicSize; +} CLzmaProps; + +/* LzmaProps_Decode - decodes properties +Returns: + SZ_OK + SZ_ERROR_UNSUPPORTED - Unsupported properties +*/ + +SRes LzmaProps_Decode(CLzmaProps *p, const Byte *data, unsigned size); + + +/* ---------- LZMA Decoder state ---------- */ + +/* LZMA_REQUIRED_INPUT_MAX = number of required input bytes for worst case. + Num bits = log2((2^11 / 31) ^ 22) + 26 < 134 + 26 = 160; */ + +#define LZMA_REQUIRED_INPUT_MAX 20 + +typedef struct +{ + /* Don't change this structure. ASM code can use it. */ + CLzmaProps prop; + CLzmaProb *probs; + CLzmaProb *probs_1664; + Byte *dic; + SizeT dicBufSize; + SizeT dicPos; + const Byte *buf; + UInt32 range; + UInt32 code; + UInt32 processedPos; + UInt32 checkDicSize; + UInt32 reps[4]; + UInt32 state; + UInt32 remainLen; + + UInt32 numProbs; + unsigned tempBufSize; + Byte tempBuf[LZMA_REQUIRED_INPUT_MAX]; +} CLzmaDec; + +#define LzmaDec_Construct(p) { (p)->dic = NULL; (p)->probs = NULL; } + +void LzmaDec_Init(CLzmaDec *p); + +/* There are two types of LZMA streams: + - 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 +{ + LZMA_FINISH_ANY, /* finish at any point */ + LZMA_FINISH_END /* block must be finished at the end */ +} ELzmaFinishMode; + +/* ELzmaFinishMode has meaning only if the decoding reaches output limit !!! + + You must use LZMA_FINISH_END, when you know that current output buffer + covers last bytes of block. In other cases you must use LZMA_FINISH_ANY. + + If LZMA decoder sees end marker before reaching output limit, it returns SZ_OK, + and output value of destLen will be less than output buffer size limit. + You can check status result also. + + You can use multiple checks to test data integrity after full decompression: + 1) Check Result and "status" variable. + 2) Check that output(destLen) = uncompressedSize, if you know real uncompressedSize. + 3) Check that output(srcLen) = compressedSize, if you know real compressedSize. + You must use correct finish mode in that case. */ + +typedef enum +{ + LZMA_STATUS_NOT_SPECIFIED, /* use main error code instead */ + LZMA_STATUS_FINISHED_WITH_MARK, /* stream was finished with end mark. */ + LZMA_STATUS_NOT_FINISHED, /* stream was not finished */ + LZMA_STATUS_NEEDS_MORE_INPUT, /* you must provide more input bytes */ + LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK /* there is probability that stream was finished without end mark */ +} ELzmaStatus; + +/* ELzmaStatus is used only as output value for function call */ + + +/* ---------- Interfaces ---------- */ + +/* There are 3 levels of interfaces: + 1) Dictionary Interface + 2) Buffer Interface + 3) One Call Interface + You can select any of these interfaces, but don't mix functions from different + groups for same object. */ + + +/* There are two variants to allocate state for Dictionary Interface: + 1) LzmaDec_Allocate / LzmaDec_Free + 2) LzmaDec_AllocateProbs / LzmaDec_FreeProbs + You can use variant 2, if you set dictionary buffer manually. + For Buffer Interface you must always use variant 1. + +LzmaDec_Allocate* can return: + SZ_OK + SZ_ERROR_MEM - Memory allocation error + SZ_ERROR_UNSUPPORTED - Unsupported properties +*/ + +SRes LzmaDec_AllocateProbs(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAllocPtr alloc); +void LzmaDec_FreeProbs(CLzmaDec *p, ISzAllocPtr alloc); + +SRes LzmaDec_Allocate(CLzmaDec *p, const Byte *props, unsigned propsSize, ISzAllocPtr alloc); +void LzmaDec_Free(CLzmaDec *p, ISzAllocPtr alloc); + +/* ---------- Dictionary Interface ---------- */ + +/* You can use it, if you want to eliminate the overhead for data copying from + dictionary to some other external buffer. + You must work with CLzmaDec variables directly in this interface. + + STEPS: + LzmaDec_Construct() + LzmaDec_Allocate() + for (each new stream) + { + LzmaDec_Init() + while (it needs more decompression) + { + LzmaDec_DecodeToDic() + use data from CLzmaDec::dic and update CLzmaDec::dicPos + } + } + LzmaDec_Free() +*/ + +/* LzmaDec_DecodeToDic + + The decoding to internal dictionary buffer (CLzmaDec::dic). + You must manually update CLzmaDec::dicPos, if it reaches CLzmaDec::dicBufSize !!! + +finishMode: + It has meaning only if the decoding reaches output limit (dicLimit). + LZMA_FINISH_ANY - Decode just dicLimit bytes. + LZMA_FINISH_END - Stream must be finished after dicLimit. + +Returns: + SZ_OK + status: + LZMA_STATUS_FINISHED_WITH_MARK + LZMA_STATUS_NOT_FINISHED + LZMA_STATUS_NEEDS_MORE_INPUT + LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK + SZ_ERROR_DATA - Data error +*/ + +SRes LzmaDec_DecodeToDic(CLzmaDec *p, SizeT dicLimit, + const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status, SizeT memlimit); + + +/* ---------- Buffer Interface ---------- */ + +/* It's zlib-like interface. + See LzmaDec_DecodeToDic description for information about STEPS and return results, + but you must use LzmaDec_DecodeToBuf instead of LzmaDec_DecodeToDic and you don't need + to work with CLzmaDec variables manually. + +finishMode: + It has meaning only if the decoding reaches output limit (*destLen). + LZMA_FINISH_ANY - Decode just destLen bytes. + LZMA_FINISH_END - Stream must be finished after (*destLen). +*/ + +SRes LzmaDec_DecodeToBuf(CLzmaDec *p, Byte *dest, SizeT *destLen, + const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status, SizeT memlimit); + + +/* ---------- One Call Interface ---------- */ + +/* LzmaDecode + +finishMode: + It has meaning only if the decoding reaches output limit (*destLen). + LZMA_FINISH_ANY - Decode just destLen bytes. + LZMA_FINISH_END - Stream must be finished after (*destLen). + +Returns: + SZ_OK + status: + LZMA_STATUS_FINISHED_WITH_MARK + LZMA_STATUS_NOT_FINISHED + LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK + SZ_ERROR_DATA - Data error + SZ_ERROR_MEM - Memory allocation error + SZ_ERROR_UNSUPPORTED - Unsupported properties + SZ_ERROR_INPUT_EOF - It needs more bytes in input buffer (src). +*/ + +SRes LzmaDecode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen, + const Byte *propData, unsigned propSize, ELzmaFinishMode finishMode, + ELzmaStatus *status, ISzAllocPtr alloc); + +EXTERN_C_END + +#endif diff --git a/htp/lzma/Makefile.am b/htp/lzma/Makefile.am new file mode 100644 index 0000000..5fa3ec5 --- /dev/null +++ b/htp/lzma/Makefile.am @@ -0,0 +1,16 @@ + +h_sources = LzmaDec.h 7zTypes.h + +h_sources_private = LzFind.h LzHash.h Compiler.h Precomp.h + +c_sources = LzFind.c LzmaDec.c + +AM_CFLAGS = -I$(top_srcdir) -D_GNU_SOURCE -g -Wall -Wextra -std=gnu99 -pedantic \ + -Wextra -Wno-missing-field-initializers -Wshadow -Wpointer-arith \ + -Wstrict-prototypes -Wmissing-prototypes -Wno-unused-parameter + +library_includedir = $(includedir)/$(GENERIC_LIBRARY_NAME)/lzma +library_include_HEADERS = $(h_sources) + +noinst_LTLIBRARIES = liblzma-c.la +liblzma_c_la_SOURCES = $(h_sources) $(h_sources_private) $(c_sources) diff --git a/htp/lzma/Precomp.h b/htp/lzma/Precomp.h new file mode 100644 index 0000000..edb5814 --- /dev/null +++ b/htp/lzma/Precomp.h @@ -0,0 +1,10 @@ +/* Precomp.h -- StdAfx +2013-11-12 : Igor Pavlov : Public domain */ + +#ifndef __7Z_PRECOMP_H +#define __7Z_PRECOMP_H + +#include "Compiler.h" +/* #include "7zTypes.h" */ + +#endif -- cgit v1.2.3