3rdparty: Add lzma/7Z SDK 21.07

3rdparty/lzma/CMakeLists.txt

@@ -0,0 +1,77 @@
+add_library(pcsx2-lzma STATIC
+	include/7z.h
+	include/7zAlloc.h
+	include/7zBuf.h
+	include/7zCrc.h
+	include/7zFile.h
+	include/7zTypes.h
+	include/7zVersion.h
+	include/Alloc.h
+	include/Bcj2.h
+	include/Bra.h
+	include/Compiler.h
+	include/CpuArch.h
+	include/Delta.h
+	include/LzFind.h
+	include/LzHash.h
+	include/Lzma2Dec.h
+	include/Lzma2DecMt.h
+	include/Lzma2Enc.h
+	include/Lzma86.h
+	include/LzmaDec.h
+	include/LzmaEnc.h
+	include/LzmaLib.h
+	include/Ppmd.h
+	include/Ppmd7.h
+	include/Precomp.h
+	include/RotateDefs.h
+	include/Sha256.h
+	include/Xz.h
+	include/XzCrc64.h
+	include/XzEnc.h
+	src/7zAlloc.c
+	src/7zArcIn.c
+	src/7zBuf.c
+	src/7zBuf2.c
+	src/7zCrc.c
+	src/7zCrcOpt.c
+	src/7zDec.c
+	src/7zFile.c
+	src/7zStream.c
+	src/Alloc.c
+	src/Bcj2.c
+	src/Bcj2Enc.c
+	src/Bra.c
+	src/Bra86.c
+	src/BraIA64.c
+	src/CpuArch.c
+	src/Delta.c
+	src/LzFind.c
+	src/LzFindOpt.c
+	src/Lzma2Dec.c
+	src/Lzma2DecMt.c
+	src/Lzma2Enc.c
+	src/Lzma86Dec.c
+	src/Lzma86Enc.c
+	src/LzmaDec.c
+	src/LzmaEnc.c
+	src/LzmaLib.c
+	src/Ppmd7.c
+	src/Ppmd7Dec.c
+	src/Ppmd7Enc.c
+	src/Sha256.c
+	src/Sha256Opt.c
+	src/Xz.c
+	src/XzCrc64.c
+	src/XzCrc64Opt.c
+	src/XzDec.c
+	src/XzEnc.c
+	src/XzIn.c
+)
+
+target_compile_definitions(pcsx2-lzma PRIVATE _7ZIP_ST)
+
+target_include_directories(pcsx2-lzma PRIVATE "${CMAKE_CURRENT_SOURCE_DIR}/include")
+target_include_directories(pcsx2-lzma INTERFACE "${CMAKE_CURRENT_SOURCE_DIR}/include")
+
+add_library(LZMA::LZMA ALIAS pcsx2-lzma)

3rdparty/lzma/LICENSE.txt

@@ -0,0 +1,5 @@
+https://www.7-zip.org/sdk.html
+
+LZMA SDK is placed in the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or distribute the original LZMA SDK code, either in source code form or as a compiled binary, for any purpose, commercial or non-commercial, and by any means.

3rdparty/lzma/include/7z.h

@@ -0,0 +1,204 @@
+/* 7z.h -- 7z interface
+2018-07-02 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_H
+#define __7Z_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define k7zStartHeaderSize 0x20
+#define k7zSignatureSize 6
+
+extern const Byte k7zSignature[k7zSignatureSize];
+
+typedef struct
+{
+  const Byte *Data;
+  size_t Size;
+} CSzData;
+
+/* CSzCoderInfo & CSzFolder support only default methods */
+
+typedef struct
+{
+  size_t PropsOffset;
+  UInt32 MethodID;
+  Byte NumStreams;
+  Byte PropsSize;
+} CSzCoderInfo;
+
+typedef struct
+{
+  UInt32 InIndex;
+  UInt32 OutIndex;
+} CSzBond;
+
+#define SZ_NUM_CODERS_IN_FOLDER_MAX 4
+#define SZ_NUM_BONDS_IN_FOLDER_MAX 3
+#define SZ_NUM_PACK_STREAMS_IN_FOLDER_MAX 4
+
+typedef struct
+{
+  UInt32 NumCoders;
+  UInt32 NumBonds;
+  UInt32 NumPackStreams;
+  UInt32 UnpackStream;
+  UInt32 PackStreams[SZ_NUM_PACK_STREAMS_IN_FOLDER_MAX];
+  CSzBond Bonds[SZ_NUM_BONDS_IN_FOLDER_MAX];
+  CSzCoderInfo Coders[SZ_NUM_CODERS_IN_FOLDER_MAX];
+} CSzFolder;
+
+
+SRes SzGetNextFolderItem(CSzFolder *f, CSzData *sd);
+
+typedef struct
+{
+  UInt32 Low;
+  UInt32 High;
+} CNtfsFileTime;
+
+typedef struct
+{
+  Byte *Defs; /* MSB 0 bit numbering */
+  UInt32 *Vals;
+} CSzBitUi32s;
+
+typedef struct
+{
+  Byte *Defs; /* MSB 0 bit numbering */
+  // UInt64 *Vals;
+  CNtfsFileTime *Vals;
+} CSzBitUi64s;
+
+#define SzBitArray_Check(p, i) (((p)[(i) >> 3] & (0x80 >> ((i) & 7))) != 0)
+
+#define SzBitWithVals_Check(p, i) ((p)->Defs && ((p)->Defs[(i) >> 3] & (0x80 >> ((i) & 7))) != 0)
+
+typedef struct
+{
+  UInt32 NumPackStreams;
+  UInt32 NumFolders;
+
+  UInt64 *PackPositions;          // NumPackStreams + 1
+  CSzBitUi32s FolderCRCs;         // NumFolders
+
+  size_t *FoCodersOffsets;        // NumFolders + 1
+  UInt32 *FoStartPackStreamIndex; // NumFolders + 1
+  UInt32 *FoToCoderUnpackSizes;   // NumFolders + 1
+  Byte *FoToMainUnpackSizeIndex;  // NumFolders
+  UInt64 *CoderUnpackSizes;       // for all coders in all folders
+
+  Byte *CodersData;
+
+  UInt64 RangeLimit;
+} CSzAr;
+
+UInt64 SzAr_GetFolderUnpackSize(const CSzAr *p, UInt32 folderIndex);
+
+SRes SzAr_DecodeFolder(const CSzAr *p, UInt32 folderIndex,
+    ILookInStream *stream, UInt64 startPos,
+    Byte *outBuffer, size_t outSize,
+    ISzAllocPtr allocMain);
+
+typedef struct
+{
+  CSzAr db;
+
+  UInt64 startPosAfterHeader;
+  UInt64 dataPos;
+  
+  UInt32 NumFiles;
+
+  UInt64 *UnpackPositions;  // NumFiles + 1
+  // Byte *IsEmptyFiles;
+  Byte *IsDirs;
+  CSzBitUi32s CRCs;
+
+  CSzBitUi32s Attribs;
+  // CSzBitUi32s Parents;
+  CSzBitUi64s MTime;
+  CSzBitUi64s CTime;
+
+  UInt32 *FolderToFile;   // NumFolders + 1
+  UInt32 *FileToFolder;   // NumFiles
+
+  size_t *FileNameOffsets; /* in 2-byte steps */
+  Byte *FileNames;  /* UTF-16-LE */
+} CSzArEx;
+
+#define SzArEx_IsDir(p, i) (SzBitArray_Check((p)->IsDirs, i))
+
+#define SzArEx_GetFileSize(p, i) ((p)->UnpackPositions[(i) + 1] - (p)->UnpackPositions[i])
+
+void SzArEx_Init(CSzArEx *p);
+void SzArEx_Free(CSzArEx *p, ISzAllocPtr alloc);
+UInt64 SzArEx_GetFolderStreamPos(const CSzArEx *p, UInt32 folderIndex, UInt32 indexInFolder);
+int SzArEx_GetFolderFullPackSize(const CSzArEx *p, UInt32 folderIndex, UInt64 *resSize);
+
+/*
+if dest == NULL, the return value specifies the required size of the buffer,
+  in 16-bit characters, including the null-terminating character.
+if dest != NULL, the return value specifies the number of 16-bit characters that
+  are written to the dest, including the null-terminating character. */
+
+size_t SzArEx_GetFileNameUtf16(const CSzArEx *p, size_t fileIndex, UInt16 *dest);
+
+/*
+size_t SzArEx_GetFullNameLen(const CSzArEx *p, size_t fileIndex);
+UInt16 *SzArEx_GetFullNameUtf16_Back(const CSzArEx *p, size_t fileIndex, UInt16 *dest);
+*/
+
+
+
+/*
+  SzArEx_Extract extracts file from archive
+
+  *outBuffer must be 0 before first call for each new archive.
+
+  Extracting cache:
+    If you need to decompress more than one file, you can send
+    these values from previous call:
+      *blockIndex,
+      *outBuffer,
+      *outBufferSize
+    You can consider "*outBuffer" as cache of solid block. If your archive is solid,
+    it will increase decompression speed.
+  
+    If you use external function, you can declare these 3 cache variables
+    (blockIndex, outBuffer, outBufferSize) as static in that external function.
+    
+    Free *outBuffer and set *outBuffer to 0, if you want to flush cache.
+*/
+
+SRes SzArEx_Extract(
+    const CSzArEx *db,
+    ILookInStream *inStream,
+    UInt32 fileIndex,         /* index of file */
+    UInt32 *blockIndex,       /* index of solid block */
+    Byte **outBuffer,         /* pointer to pointer to output buffer (allocated with allocMain) */
+    size_t *outBufferSize,    /* buffer size for output buffer */
+    size_t *offset,           /* offset of stream for required file in *outBuffer */
+    size_t *outSizeProcessed, /* size of file in *outBuffer */
+    ISzAllocPtr allocMain,
+    ISzAllocPtr allocTemp);
+
+
+/*
+SzArEx_Open Errors:
+SZ_ERROR_NO_ARCHIVE
+SZ_ERROR_ARCHIVE
+SZ_ERROR_UNSUPPORTED
+SZ_ERROR_MEM
+SZ_ERROR_CRC
+SZ_ERROR_INPUT_EOF
+SZ_ERROR_FAIL
+*/
+
+SRes SzArEx_Open(CSzArEx *p, ILookInStream *inStream,
+    ISzAllocPtr allocMain, ISzAllocPtr allocTemp);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/7zAlloc.h

@@ -0,0 +1,19 @@
+/* 7zAlloc.h -- Allocation functions
+2017-04-03 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_ALLOC_H
+#define __7Z_ALLOC_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+void *SzAlloc(ISzAllocPtr p, size_t size);
+void SzFree(ISzAllocPtr p, void *address);
+
+void *SzAllocTemp(ISzAllocPtr p, size_t size);
+void SzFreeTemp(ISzAllocPtr p, void *address);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/7zBuf.h

@@ -0,0 +1,35 @@
+/* 7zBuf.h -- Byte Buffer
+2017-04-03 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_BUF_H
+#define __7Z_BUF_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+typedef struct
+{
+  Byte *data;
+  size_t size;
+} CBuf;
+
+void Buf_Init(CBuf *p);
+int Buf_Create(CBuf *p, size_t size, ISzAllocPtr alloc);
+void Buf_Free(CBuf *p, ISzAllocPtr alloc);
+
+typedef struct
+{
+  Byte *data;
+  size_t size;
+  size_t pos;
+} CDynBuf;
+
+void DynBuf_Construct(CDynBuf *p);
+void DynBuf_SeekToBeg(CDynBuf *p);
+int DynBuf_Write(CDynBuf *p, const Byte *buf, size_t size, ISzAllocPtr alloc);
+void DynBuf_Free(CDynBuf *p, ISzAllocPtr alloc);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/7zCrc.h

@@ -0,0 +1,25 @@
+/* 7zCrc.h -- CRC32 calculation
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_CRC_H
+#define __7Z_CRC_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+extern UInt32 g_CrcTable[];
+
+/* Call CrcGenerateTable one time before other CRC functions */
+void MY_FAST_CALL CrcGenerateTable(void);
+
+#define CRC_INIT_VAL 0xFFFFFFFF
+#define CRC_GET_DIGEST(crc) ((crc) ^ CRC_INIT_VAL)
+#define CRC_UPDATE_BYTE(crc, b) (g_CrcTable[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+
+UInt32 MY_FAST_CALL CrcUpdate(UInt32 crc, const void *data, size_t size);
+UInt32 MY_FAST_CALL CrcCalc(const void *data, size_t size);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/7zFile.h

@@ -0,0 +1,91 @@
+/* 7zFile.h -- File IO
+2021-02-15 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_FILE_H
+#define __7Z_FILE_H
+
+#ifdef _WIN32
+#define USE_WINDOWS_FILE
+// #include <windows.h>
+#endif
+
+#ifdef USE_WINDOWS_FILE
+#include <windows.h>
+#else
+// note: USE_FOPEN mode is limited to 32-bit file size
+// #define USE_FOPEN
+// #include <stdio.h>
+#endif
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+/* ---------- File ---------- */
+
+typedef struct
+{
+  #ifdef USE_WINDOWS_FILE
+  HANDLE handle;
+  #elif defined(USE_FOPEN)
+  FILE *file;
+  #else
+  int fd;
+  #endif
+} CSzFile;
+
+void File_Construct(CSzFile *p);
+#if !defined(UNDER_CE) || !defined(USE_WINDOWS_FILE)
+WRes InFile_Open(CSzFile *p, const char *name);
+WRes OutFile_Open(CSzFile *p, const char *name);
+#endif
+#ifdef USE_WINDOWS_FILE
+WRes InFile_OpenW(CSzFile *p, const WCHAR *name);
+WRes OutFile_OpenW(CSzFile *p, const WCHAR *name);
+#endif
+WRes File_Close(CSzFile *p);
+
+/* reads max(*size, remain file's size) bytes */
+WRes File_Read(CSzFile *p, void *data, size_t *size);
+
+/* writes *size bytes */
+WRes File_Write(CSzFile *p, const void *data, size_t *size);
+
+WRes File_Seek(CSzFile *p, Int64 *pos, ESzSeek origin);
+WRes File_GetLength(CSzFile *p, UInt64 *length);
+
+
+/* ---------- FileInStream ---------- */
+
+typedef struct
+{
+  ISeqInStream vt;
+  CSzFile file;
+  WRes wres;
+} CFileSeqInStream;
+
+void FileSeqInStream_CreateVTable(CFileSeqInStream *p);
+
+
+typedef struct
+{
+  ISeekInStream vt;
+  CSzFile file;
+  WRes wres;
+} CFileInStream;
+
+void FileInStream_CreateVTable(CFileInStream *p);
+
+
+typedef struct
+{
+  ISeqOutStream vt;
+  CSzFile file;
+  WRes wres;
+} CFileOutStream;
+
+void FileOutStream_CreateVTable(CFileOutStream *p);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/7zTypes.h

@@ -0,0 +1,525 @@
+/* 7zTypes.h -- Basic types
+2021-12-25 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_TYPES_H
+#define __7Z_TYPES_H
+
+#ifdef _WIN32
+/* #include <windows.h> */
+#else
+#include <errno.h>
+#endif
+
+#include <stddef.h>
+
+#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 _MSC_VER
+  #if _MSC_VER > 1200
+    #define MY_ALIGN(n) __declspec(align(n))
+  #else
+    #define MY_ALIGN(n)
+  #endif
+#else
+  #define MY_ALIGN(n) __attribute__ ((aligned(n)))
+#endif
+
+
+#ifdef _WIN32
+
+/* typedef DWORD WRes; */
+typedef unsigned WRes;
+#define MY_SRes_HRESULT_FROM_WRes(x) HRESULT_FROM_WIN32(x)
+
+// #define MY_HRES_ERROR__INTERNAL_ERROR  MY_SRes_HRESULT_FROM_WRes(ERROR_INTERNAL_ERROR)
+
+#else // _WIN32
+
+// #define ENV_HAVE_LSTAT
+typedef int WRes;
+
+// (FACILITY_ERRNO = 0x800) is 7zip's FACILITY constant to represent (errno) errors in HRESULT
+#define MY__FACILITY_ERRNO  0x800
+#define MY__FACILITY_WIN32  7
+#define MY__FACILITY__WRes  MY__FACILITY_ERRNO
+
+#define MY_HRESULT_FROM_errno_CONST_ERROR(x) ((HRESULT)( \
+          ( (HRESULT)(x) & 0x0000FFFF) \
+          | (MY__FACILITY__WRes << 16)  \
+          | (HRESULT)0x80000000 ))
+
+#define MY_SRes_HRESULT_FROM_WRes(x) \
+  ((HRESULT)(x) <= 0 ? ((HRESULT)(x)) : MY_HRESULT_FROM_errno_CONST_ERROR(x))
+
+// we call macro HRESULT_FROM_WIN32 for system errors (WRes) that are (errno)
+#define HRESULT_FROM_WIN32(x) MY_SRes_HRESULT_FROM_WRes(x)
+
+/*
+#define ERROR_FILE_NOT_FOUND             2L
+#define ERROR_ACCESS_DENIED              5L
+#define ERROR_NO_MORE_FILES              18L
+#define ERROR_LOCK_VIOLATION             33L
+#define ERROR_FILE_EXISTS                80L
+#define ERROR_DISK_FULL                  112L
+#define ERROR_NEGATIVE_SEEK              131L
+#define ERROR_ALREADY_EXISTS             183L
+#define ERROR_DIRECTORY                  267L
+#define ERROR_TOO_MANY_POSTS             298L
+
+#define ERROR_INTERNAL_ERROR             1359L
+#define ERROR_INVALID_REPARSE_DATA       4392L
+#define ERROR_REPARSE_TAG_INVALID        4393L
+#define ERROR_REPARSE_TAG_MISMATCH       4394L
+*/
+
+// we use errno equivalents for some WIN32 errors:
+
+#define ERROR_INVALID_PARAMETER     EINVAL
+#define ERROR_INVALID_FUNCTION      EINVAL
+#define ERROR_ALREADY_EXISTS        EEXIST
+#define ERROR_FILE_EXISTS           EEXIST
+#define ERROR_PATH_NOT_FOUND        ENOENT
+#define ERROR_FILE_NOT_FOUND        ENOENT
+#define ERROR_DISK_FULL             ENOSPC
+// #define ERROR_INVALID_HANDLE        EBADF
+
+// we use FACILITY_WIN32 for errors that has no errno equivalent
+// Too many posts were made to a semaphore.
+#define ERROR_TOO_MANY_POSTS        ((HRESULT)0x8007012AL)
+#define ERROR_INVALID_REPARSE_DATA  ((HRESULT)0x80071128L)
+#define ERROR_REPARSE_TAG_INVALID   ((HRESULT)0x80071129L)
+
+// if (MY__FACILITY__WRes != FACILITY_WIN32),
+// we use FACILITY_WIN32 for COM errors:
+#define E_OUTOFMEMORY               ((HRESULT)0x8007000EL)
+#define E_INVALIDARG                ((HRESULT)0x80070057L)
+#define MY__E_ERROR_NEGATIVE_SEEK   ((HRESULT)0x80070083L)
+
+/*
+// we can use FACILITY_ERRNO for some COM errors, that have errno equivalents:
+#define E_OUTOFMEMORY             MY_HRESULT_FROM_errno_CONST_ERROR(ENOMEM)
+#define E_INVALIDARG              MY_HRESULT_FROM_errno_CONST_ERROR(EINVAL)
+#define MY__E_ERROR_NEGATIVE_SEEK MY_HRESULT_FROM_errno_CONST_ERROR(EINVAL)
+*/
+
+// gcc / clang : (sizeof(long) == sizeof(void*)) in 32/64 bits
+typedef          long INT_PTR;
+typedef unsigned long UINT_PTR;
+
+#define TEXT(quote) quote
+
+#define FILE_ATTRIBUTE_READONLY       0x0001
+#define FILE_ATTRIBUTE_HIDDEN         0x0002
+#define FILE_ATTRIBUTE_SYSTEM         0x0004
+#define FILE_ATTRIBUTE_DIRECTORY      0x0010
+#define FILE_ATTRIBUTE_ARCHIVE        0x0020
+#define FILE_ATTRIBUTE_DEVICE         0x0040
+#define FILE_ATTRIBUTE_NORMAL         0x0080
+#define FILE_ATTRIBUTE_TEMPORARY      0x0100
+#define FILE_ATTRIBUTE_SPARSE_FILE    0x0200
+#define FILE_ATTRIBUTE_REPARSE_POINT  0x0400
+#define FILE_ATTRIBUTE_COMPRESSED     0x0800
+#define FILE_ATTRIBUTE_OFFLINE        0x1000
+#define FILE_ATTRIBUTE_NOT_CONTENT_INDEXED 0x2000
+#define FILE_ATTRIBUTE_ENCRYPTED      0x4000
+
+#define FILE_ATTRIBUTE_UNIX_EXTENSION 0x8000   /* trick for Unix */
+
+#endif
+
+
+#ifndef RINOK
+#define RINOK(x) { int __result__ = (x); if (__result__ != 0) return __result__; }
+#endif
+
+#ifndef RINOK_WRes
+#define RINOK_WRes(x) { WRes __result__ = (x); if (__result__ != 0) return __result__; }
+#endif
+
+typedef unsigned char Byte;
+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
+
+
+#ifndef _WIN32
+
+typedef int INT;
+typedef Int32 INT32;
+typedef unsigned int UINT;
+typedef UInt32 UINT32;
+typedef INT32 LONG;   // LONG, ULONG and DWORD must be 32-bit for _WIN32 compatibility
+typedef UINT32 ULONG;
+
+#undef DWORD
+typedef UINT32 DWORD;
+
+#define VOID void
+
+#define HRESULT LONG
+
+typedef void *LPVOID;
+// typedef void VOID;
+// typedef ULONG_PTR DWORD_PTR, *PDWORD_PTR;
+// gcc / clang on Unix  : sizeof(long==sizeof(void*) in 32 or 64 bits)
+typedef          long  INT_PTR;
+typedef unsigned long  UINT_PTR;
+typedef          long  LONG_PTR;
+typedef unsigned long  DWORD_PTR;
+
+typedef size_t SIZE_T;
+
+#endif //  _WIN32
+
+
+#define MY_HRES_ERROR__INTERNAL_ERROR  ((HRESULT)0x8007054FL)
+
+
+#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 //  _MSC_VER
+
+#if (defined(__GNUC__) && (__GNUC__ >= 4)) \
+    || (defined(__clang__) && (__clang_major__ >= 4)) \
+    || defined(__INTEL_COMPILER) \
+    || defined(__xlC__)
+#define MY_NO_INLINE __attribute__((noinline))
+// #define MY_FORCE_INLINE __attribute__((always_inline)) inline
+#else
+#define MY_NO_INLINE
+#endif
+
+#define MY_FORCE_INLINE
+
+
+#define MY_CDECL
+
+#if  defined(_M_IX86) \
+  || defined(__i386__)
+// #define MY_FAST_CALL __attribute__((fastcall))
+// #define MY_FAST_CALL __attribute__((cdecl))
+#define MY_FAST_CALL
+#elif defined(MY_CPU_AMD64)
+// #define MY_FAST_CALL __attribute__((ms_abi))
+#define MY_FAST_CALL
+#else
+#define MY_FAST_CALL
+#endif
+
+#endif //  _MSC_VER
+
+
+/* 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 *)(void *)((char *)(void *)(1 ? (ptr) : &((type *)0)->m) - MY_offsetof(type, m)))
+
+#endif
+
+#define CONTAINER_FROM_VTBL_SIMPLE(ptr, type, m) ((type *)(void *)(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 MY_memset_0_ARRAY(a) memset((a), 0, sizeof(a))
+
+#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

3rdparty/lzma/include/7zVersion.h

@@ -0,0 +1,27 @@
+#define MY_VER_MAJOR 21
+#define MY_VER_MINOR 07
+#define MY_VER_BUILD 0
+#define MY_VERSION_NUMBERS "21.07"
+#define MY_VERSION MY_VERSION_NUMBERS
+
+#ifdef MY_CPU_NAME
+  #define MY_VERSION_CPU MY_VERSION " (" MY_CPU_NAME ")"
+#else
+  #define MY_VERSION_CPU MY_VERSION
+#endif
+
+#define MY_DATE "2021-12-26"
+#undef MY_COPYRIGHT
+#undef MY_VERSION_COPYRIGHT_DATE
+#define MY_AUTHOR_NAME "Igor Pavlov"
+#define MY_COPYRIGHT_PD "Igor Pavlov : Public domain"
+#define MY_COPYRIGHT_CR "Copyright (c) 1999-2021 Igor Pavlov"
+
+#ifdef USE_COPYRIGHT_CR
+  #define MY_COPYRIGHT MY_COPYRIGHT_CR
+#else
+  #define MY_COPYRIGHT MY_COPYRIGHT_PD
+#endif
+
+#define MY_COPYRIGHT_DATE MY_COPYRIGHT " : " MY_DATE
+#define MY_VERSION_COPYRIGHT_DATE MY_VERSION_CPU " : " MY_COPYRIGHT " : " MY_DATE

3rdparty/lzma/include/Alloc.h

@@ -0,0 +1,58 @@
+/* Alloc.h -- Memory allocation functions
+2021-07-13 : Igor Pavlov : Public domain */
+
+#ifndef __COMMON_ALLOC_H
+#define __COMMON_ALLOC_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+void *MyAlloc(size_t size);
+void MyFree(void *address);
+
+#ifdef _WIN32
+
+void SetLargePageSize(void);
+
+void *MidAlloc(size_t size);
+void MidFree(void *address);
+void *BigAlloc(size_t size);
+void BigFree(void *address);
+
+#else
+
+#define MidAlloc(size) MyAlloc(size)
+#define MidFree(address) MyFree(address)
+#define BigAlloc(size) MyAlloc(size)
+#define BigFree(address) MyFree(address)
+
+#endif
+
+extern const ISzAlloc g_Alloc;
+
+#ifdef _WIN32
+extern const ISzAlloc g_BigAlloc;
+extern const ISzAlloc g_MidAlloc;
+#else
+#define g_BigAlloc g_AlignedAlloc
+#define g_MidAlloc g_AlignedAlloc
+#endif
+
+extern const ISzAlloc g_AlignedAlloc;
+
+
+typedef struct
+{
+  ISzAlloc vt;
+  ISzAllocPtr baseAlloc;
+  unsigned numAlignBits; /* ((1 << numAlignBits) >= sizeof(void *)) */
+  size_t offset;         /* (offset == (k * sizeof(void *)) && offset < (1 << numAlignBits) */
+} CAlignOffsetAlloc;
+
+void AlignOffsetAlloc_CreateVTable(CAlignOffsetAlloc *p);
+
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/Bcj2.h

@@ -0,0 +1,146 @@
+/* Bcj2.h -- BCJ2 Converter for x86 code
+2014-11-10 : Igor Pavlov : Public domain */
+
+#ifndef __BCJ2_H
+#define __BCJ2_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define BCJ2_NUM_STREAMS 4
+
+enum
+{
+  BCJ2_STREAM_MAIN,
+  BCJ2_STREAM_CALL,
+  BCJ2_STREAM_JUMP,
+  BCJ2_STREAM_RC
+};
+
+enum
+{
+  BCJ2_DEC_STATE_ORIG_0 = BCJ2_NUM_STREAMS,
+  BCJ2_DEC_STATE_ORIG_1,
+  BCJ2_DEC_STATE_ORIG_2,
+  BCJ2_DEC_STATE_ORIG_3,
+  
+  BCJ2_DEC_STATE_ORIG,
+  BCJ2_DEC_STATE_OK
+};
+
+enum
+{
+  BCJ2_ENC_STATE_ORIG = BCJ2_NUM_STREAMS,
+  BCJ2_ENC_STATE_OK
+};
+
+
+#define BCJ2_IS_32BIT_STREAM(s) ((s) == BCJ2_STREAM_CALL || (s) == BCJ2_STREAM_JUMP)
+
+/*
+CBcj2Dec / CBcj2Enc
+bufs sizes:
+  BUF_SIZE(n) = lims[n] - bufs[n]
+bufs sizes for BCJ2_STREAM_CALL and BCJ2_STREAM_JUMP must be mutliply of 4:
+    (BUF_SIZE(BCJ2_STREAM_CALL) & 3) == 0
+    (BUF_SIZE(BCJ2_STREAM_JUMP) & 3) == 0
+*/
+
+/*
+CBcj2Dec:
+dest is allowed to overlap with bufs[BCJ2_STREAM_MAIN], with the following conditions:
+  bufs[BCJ2_STREAM_MAIN] >= dest &&
+  bufs[BCJ2_STREAM_MAIN] - dest >= tempReserv +
+        BUF_SIZE(BCJ2_STREAM_CALL) +
+        BUF_SIZE(BCJ2_STREAM_JUMP)
+     tempReserv = 0 : for first call of Bcj2Dec_Decode
+     tempReserv = 4 : for any other calls of Bcj2Dec_Decode
+  overlap with offset = 1 is not allowed
+*/
+
+typedef struct
+{
+  const Byte *bufs[BCJ2_NUM_STREAMS];
+  const Byte *lims[BCJ2_NUM_STREAMS];
+  Byte *dest;
+  const Byte *destLim;
+
+  unsigned state; /* BCJ2_STREAM_MAIN has more priority than BCJ2_STATE_ORIG */
+
+  UInt32 ip;
+  Byte temp[4];
+  UInt32 range;
+  UInt32 code;
+  UInt16 probs[2 + 256];
+} CBcj2Dec;
+
+void Bcj2Dec_Init(CBcj2Dec *p);
+
+/* Returns: SZ_OK or SZ_ERROR_DATA */
+SRes Bcj2Dec_Decode(CBcj2Dec *p);
+
+#define Bcj2Dec_IsFinished(_p_) ((_p_)->code == 0)
+
+
+
+typedef enum
+{
+  BCJ2_ENC_FINISH_MODE_CONTINUE,
+  BCJ2_ENC_FINISH_MODE_END_BLOCK,
+  BCJ2_ENC_FINISH_MODE_END_STREAM
+} EBcj2Enc_FinishMode;
+
+typedef struct
+{
+  Byte *bufs[BCJ2_NUM_STREAMS];
+  const Byte *lims[BCJ2_NUM_STREAMS];
+  const Byte *src;
+  const Byte *srcLim;
+
+  unsigned state;
+  EBcj2Enc_FinishMode finishMode;
+
+  Byte prevByte;
+
+  Byte cache;
+  UInt32 range;
+  UInt64 low;
+  UInt64 cacheSize;
+
+  UInt32 ip;
+
+  /* 32-bit ralative offset in JUMP/CALL commands is
+       - (mod 4 GB)   in 32-bit mode
+       - signed Int32 in 64-bit mode
+     We use (mod 4 GB) check for fileSize.
+     Use fileSize up to 2 GB, if you want to support 32-bit and 64-bit code conversion. */
+  UInt32 fileIp;
+  UInt32 fileSize;    /* (fileSize <= ((UInt32)1 << 31)), 0 means no_limit */
+  UInt32 relatLimit;  /* (relatLimit <= ((UInt32)1 << 31)), 0 means desable_conversion */
+
+  UInt32 tempTarget;
+  unsigned tempPos;
+  Byte temp[4 * 2];
+
+  unsigned flushPos;
+  
+  UInt16 probs[2 + 256];
+} CBcj2Enc;
+
+void Bcj2Enc_Init(CBcj2Enc *p);
+void Bcj2Enc_Encode(CBcj2Enc *p);
+
+#define Bcj2Enc_Get_InputData_Size(p) ((SizeT)((p)->srcLim - (p)->src) + (p)->tempPos)
+#define Bcj2Enc_IsFinished(p) ((p)->flushPos == 5)
+
+
+#define BCJ2_RELAT_LIMIT_NUM_BITS 26
+#define BCJ2_RELAT_LIMIT ((UInt32)1 << BCJ2_RELAT_LIMIT_NUM_BITS)
+
+/* limit for CBcj2Enc::fileSize variable */
+#define BCJ2_FileSize_MAX ((UInt32)1 << 31)
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/Bra.h

@@ -0,0 +1,64 @@
+/* Bra.h -- Branch converters for executables
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __BRA_H
+#define __BRA_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+/*
+These functions convert relative addresses to absolute addresses
+in CALL instructions to increase the compression ratio.
+  
+  In:
+    data     - data buffer
+    size     - size of data
+    ip       - current virtual Instruction Pinter (IP) value
+    state    - state variable for x86 converter
+    encoding - 0 (for decoding), 1 (for encoding)
+  
+  Out:
+    state    - state variable for x86 converter
+
+  Returns:
+    The number of processed bytes. If you call these functions with multiple calls,
+    you must start next call with first byte after block of processed bytes.
+  
+  Type   Endian  Alignment  LookAhead
+  
+  x86    little      1          4
+  ARMT   little      2          2
+  ARM    little      4          0
+  PPC     big        4          0
+  SPARC   big        4          0
+  IA64   little     16          0
+
+  size must be >= Alignment + LookAhead, if it's not last block.
+  If (size < Alignment + LookAhead), converter returns 0.
+
+  Example:
+
+    UInt32 ip = 0;
+    for ()
+    {
+      ; size must be >= Alignment + LookAhead, if it's not last block
+      SizeT processed = Convert(data, size, ip, 1);
+      data += processed;
+      size -= processed;
+      ip += processed;
+    }
+*/
+
+#define x86_Convert_Init(state) { state = 0; }
+SizeT x86_Convert(Byte *data, SizeT size, UInt32 ip, UInt32 *state, int encoding);
+SizeT ARM_Convert(Byte *data, SizeT size, UInt32 ip, int encoding);
+SizeT ARMT_Convert(Byte *data, SizeT size, UInt32 ip, int encoding);
+SizeT PPC_Convert(Byte *data, SizeT size, UInt32 ip, int encoding);
+SizeT SPARC_Convert(Byte *data, SizeT size, UInt32 ip, int encoding);
+SizeT IA64_Convert(Byte *data, SizeT size, UInt32 ip, int encoding);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/Compiler.h

@@ -0,0 +1,43 @@
+/* Compiler.h
+2021-01-05 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_COMPILER_H
+#define __7Z_COMPILER_H
+
+  #ifdef __clang__
+    #pragma clang diagnostic ignored "-Wunused-private-field"
+  #endif
+
+#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
+
+  #ifdef __clang__
+    #pragma clang diagnostic ignored "-Wdeprecated-declarations"
+    #pragma clang diagnostic ignored "-Wmicrosoft-exception-spec"
+    // #pragma clang diagnostic ignored "-Wreserved-id-macro"
+  #endif
+
+#endif
+
+#define UNUSED_VAR(x) (void)x;
+/* #define UNUSED_VAR(x) x=x; */
+
+#endif

3rdparty/lzma/include/CpuArch.h

@@ -0,0 +1,442 @@
+/* CpuArch.h -- CPU specific code
+2021-07-13 : Igor Pavlov : Public domain */
+
+#ifndef __CPU_ARCH_H
+#define __CPU_ARCH_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+/*
+MY_CPU_LE means that CPU is LITTLE ENDIAN.
+MY_CPU_BE means that CPU is BIG ENDIAN.
+If MY_CPU_LE and MY_CPU_BE are not defined, we don't know about ENDIANNESS of platform.
+
+MY_CPU_LE_UNALIGN means that CPU is LITTLE ENDIAN and CPU supports unaligned memory accesses.
+
+MY_CPU_64BIT means that processor can work with 64-bit registers.
+  MY_CPU_64BIT can be used to select fast code branch
+  MY_CPU_64BIT doesn't mean that (sizeof(void *) == 8)
+*/
+
+#if  defined(_M_X64) \
+  || defined(_M_AMD64) \
+  || defined(__x86_64__) \
+  || defined(__AMD64__) \
+  || defined(__amd64__)
+  #define MY_CPU_AMD64
+  #ifdef __ILP32__
+    #define MY_CPU_NAME "x32"
+    #define MY_CPU_SIZEOF_POINTER 4
+  #else
+    #define MY_CPU_NAME "x64"
+    #define MY_CPU_SIZEOF_POINTER 8
+  #endif
+  #define MY_CPU_64BIT
+#endif
+
+
+#if  defined(_M_IX86) \
+  || defined(__i386__)
+  #define MY_CPU_X86
+  #define MY_CPU_NAME "x86"
+  /* #define MY_CPU_32BIT */
+  #define MY_CPU_SIZEOF_POINTER 4
+#endif
+
+
+#if  defined(_M_ARM64) \
+  || defined(__AARCH64EL__) \
+  || defined(__AARCH64EB__) \
+  || defined(__aarch64__)
+  #define MY_CPU_ARM64
+  #define MY_CPU_NAME "arm64"
+  #define MY_CPU_64BIT
+#endif
+
+
+#if  defined(_M_ARM) \
+  || defined(_M_ARM_NT) \
+  || defined(_M_ARMT) \
+  || defined(__arm__) \
+  || defined(__thumb__) \
+  || defined(__ARMEL__) \
+  || defined(__ARMEB__) \
+  || defined(__THUMBEL__) \
+  || defined(__THUMBEB__)
+  #define MY_CPU_ARM
+
+  #if defined(__thumb__) || defined(__THUMBEL__) || defined(_M_ARMT)
+    #define MY_CPU_NAME "armt"
+  #else
+    #define MY_CPU_NAME "arm"
+  #endif
+  /* #define MY_CPU_32BIT */
+  #define MY_CPU_SIZEOF_POINTER 4
+#endif
+
+
+#if  defined(_M_IA64) \
+  || defined(__ia64__)
+  #define MY_CPU_IA64
+  #define MY_CPU_NAME "ia64"
+  #define MY_CPU_64BIT
+#endif
+
+
+#if  defined(__mips64) \
+  || defined(__mips64__) \
+  || (defined(__mips) && (__mips == 64 || __mips == 4 || __mips == 3))
+  #define MY_CPU_NAME "mips64"
+  #define MY_CPU_64BIT
+#elif defined(__mips__)
+  #define MY_CPU_NAME "mips"
+  /* #define MY_CPU_32BIT */
+#endif
+
+
+#if  defined(__ppc64__) \
+  || defined(__powerpc64__) \
+  || defined(__ppc__) \
+  || defined(__powerpc__) \
+  || defined(__PPC__) \
+  || defined(_POWER)
+
+#if  defined(__ppc64__) \
+  || defined(__powerpc64__) \
+  || defined(_LP64) \
+  || defined(__64BIT__)
+  #ifdef __ILP32__
+    #define MY_CPU_NAME "ppc64-32"
+    #define MY_CPU_SIZEOF_POINTER 4
+  #else
+    #define MY_CPU_NAME "ppc64"
+    #define MY_CPU_SIZEOF_POINTER 8
+  #endif
+  #define MY_CPU_64BIT
+#else
+  #define MY_CPU_NAME "ppc"
+  #define MY_CPU_SIZEOF_POINTER 4
+  /* #define MY_CPU_32BIT */
+#endif
+#endif
+
+
+#if  defined(__sparc64__)
+  #define MY_CPU_NAME "sparc64"
+  #define MY_CPU_64BIT
+#elif defined(__sparc__)
+  #define MY_CPU_NAME "sparc"
+  /* #define MY_CPU_32BIT */
+#endif
+
+
+#if defined(MY_CPU_X86) || defined(MY_CPU_AMD64)
+#define MY_CPU_X86_OR_AMD64
+#endif
+
+#if defined(MY_CPU_ARM) || defined(MY_CPU_ARM64)
+#define MY_CPU_ARM_OR_ARM64
+#endif
+
+
+#ifdef _WIN32
+
+  #ifdef MY_CPU_ARM
+  #define MY_CPU_ARM_LE
+  #endif
+
+  #ifdef MY_CPU_ARM64
+  #define MY_CPU_ARM64_LE
+  #endif
+
+  #ifdef _M_IA64
+  #define MY_CPU_IA64_LE
+  #endif
+
+#endif
+
+
+#if defined(MY_CPU_X86_OR_AMD64) \
+    || defined(MY_CPU_ARM_LE) \
+    || defined(MY_CPU_ARM64_LE) \
+    || defined(MY_CPU_IA64_LE) \
+    || defined(__LITTLE_ENDIAN__) \
+    || defined(__ARMEL__) \
+    || defined(__THUMBEL__) \
+    || defined(__AARCH64EL__) \
+    || defined(__MIPSEL__) \
+    || defined(__MIPSEL) \
+    || defined(_MIPSEL) \
+    || defined(__BFIN__) \
+    || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__))
+  #define MY_CPU_LE
+#endif
+
+#if defined(__BIG_ENDIAN__) \
+    || defined(__ARMEB__) \
+    || defined(__THUMBEB__) \
+    || defined(__AARCH64EB__) \
+    || defined(__MIPSEB__) \
+    || defined(__MIPSEB) \
+    || defined(_MIPSEB) \
+    || defined(__m68k__) \
+    || defined(__s390__) \
+    || defined(__s390x__) \
+    || defined(__zarch__) \
+    || (defined(__BYTE_ORDER__) && (__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__))
+  #define MY_CPU_BE
+#endif
+
+
+#if defined(MY_CPU_LE) && defined(MY_CPU_BE)
+  #error Stop_Compiling_Bad_Endian
+#endif
+
+
+#if defined(MY_CPU_32BIT) && defined(MY_CPU_64BIT)
+  #error Stop_Compiling_Bad_32_64_BIT
+#endif
+
+#ifdef __SIZEOF_POINTER__
+  #ifdef MY_CPU_SIZEOF_POINTER
+    #if MY_CPU_SIZEOF_POINTER != __SIZEOF_POINTER__
+      #error Stop_Compiling_Bad_MY_CPU_PTR_SIZE
+    #endif
+  #else
+    #define MY_CPU_SIZEOF_POINTER  __SIZEOF_POINTER__
+  #endif
+#endif
+
+#if defined(MY_CPU_SIZEOF_POINTER) && (MY_CPU_SIZEOF_POINTER == 4)
+#if defined (_LP64)
+      #error Stop_Compiling_Bad_MY_CPU_PTR_SIZE
+#endif
+#endif
+
+#ifdef _MSC_VER
+  #if _MSC_VER >= 1300
+    #define MY_CPU_pragma_pack_push_1   __pragma(pack(push, 1))
+    #define MY_CPU_pragma_pop           __pragma(pack(pop))
+  #else
+    #define MY_CPU_pragma_pack_push_1
+    #define MY_CPU_pragma_pop
+  #endif
+#else
+  #ifdef __xlC__
+    #define MY_CPU_pragma_pack_push_1   _Pragma("pack(1)")
+    #define MY_CPU_pragma_pop           _Pragma("pack()")
+  #else
+    #define MY_CPU_pragma_pack_push_1   _Pragma("pack(push, 1)")
+    #define MY_CPU_pragma_pop           _Pragma("pack(pop)")
+  #endif
+#endif
+
+
+#ifndef MY_CPU_NAME
+  #ifdef MY_CPU_LE
+    #define MY_CPU_NAME "LE"
+  #elif defined(MY_CPU_BE)
+    #define MY_CPU_NAME "BE"
+  #else
+    /*
+    #define MY_CPU_NAME ""
+    */
+  #endif
+#endif
+
+
+
+
+
+#ifdef MY_CPU_LE
+  #if defined(MY_CPU_X86_OR_AMD64) \
+      || defined(MY_CPU_ARM64)
+    #define MY_CPU_LE_UNALIGN
+    #define MY_CPU_LE_UNALIGN_64
+  #elif defined(__ARM_FEATURE_UNALIGNED)
+    /* gcc9 for 32-bit arm can use LDRD instruction that requires 32-bit alignment.
+       So we can't use unaligned 64-bit operations. */
+    #define MY_CPU_LE_UNALIGN
+  #endif
+#endif
+
+
+#ifdef MY_CPU_LE_UNALIGN
+
+#define GetUi16(p) (*(const UInt16 *)(const void *)(p))
+#define GetUi32(p) (*(const UInt32 *)(const void *)(p))
+#ifdef MY_CPU_LE_UNALIGN_64
+#define GetUi64(p) (*(const UInt64 *)(const void *)(p))
+#endif
+
+#define SetUi16(p, v) { *(UInt16 *)(void *)(p) = (v); }
+#define SetUi32(p, v) { *(UInt32 *)(void *)(p) = (v); }
+#ifdef MY_CPU_LE_UNALIGN_64
+#define SetUi64(p, v) { *(UInt64 *)(void *)(p) = (v); }
+#endif
+
+#else
+
+#define GetUi16(p) ( (UInt16) ( \
+             ((const Byte *)(p))[0] | \
+    ((UInt16)((const Byte *)(p))[1] << 8) ))
+
+#define GetUi32(p) ( \
+             ((const Byte *)(p))[0]        | \
+    ((UInt32)((const Byte *)(p))[1] <<  8) | \
+    ((UInt32)((const Byte *)(p))[2] << 16) | \
+    ((UInt32)((const Byte *)(p))[3] << 24))
+
+#define SetUi16(p, v) { Byte *_ppp_ = (Byte *)(p); UInt32 _vvv_ = (v); \
+    _ppp_[0] = (Byte)_vvv_; \
+    _ppp_[1] = (Byte)(_vvv_ >> 8); }
+
+#define SetUi32(p, v) { Byte *_ppp_ = (Byte *)(p); UInt32 _vvv_ = (v); \
+    _ppp_[0] = (Byte)_vvv_; \
+    _ppp_[1] = (Byte)(_vvv_ >> 8); \
+    _ppp_[2] = (Byte)(_vvv_ >> 16); \
+    _ppp_[3] = (Byte)(_vvv_ >> 24); }
+
+#endif
+
+
+#ifndef MY_CPU_LE_UNALIGN_64
+
+#define GetUi64(p) (GetUi32(p) | ((UInt64)GetUi32(((const Byte *)(p)) + 4) << 32))
+
+#define SetUi64(p, v) { Byte *_ppp2_ = (Byte *)(p); UInt64 _vvv2_ = (v); \
+    SetUi32(_ppp2_    , (UInt32)_vvv2_); \
+    SetUi32(_ppp2_ + 4, (UInt32)(_vvv2_ >> 32)); }
+
+#endif
+
+
+
+
+#ifdef __has_builtin
+  #define MY__has_builtin(x) __has_builtin(x)
+#else
+  #define MY__has_builtin(x) 0
+#endif
+
+#if defined(MY_CPU_LE_UNALIGN) && /* defined(_WIN64) && */ defined(_MSC_VER) && (_MSC_VER >= 1300)
+
+/* Note: we use bswap instruction, that is unsupported in 386 cpu */
+
+#include <stdlib.h>
+
+#pragma intrinsic(_byteswap_ushort)
+#pragma intrinsic(_byteswap_ulong)
+#pragma intrinsic(_byteswap_uint64)
+
+/* #define GetBe16(p) _byteswap_ushort(*(const UInt16 *)(const Byte *)(p)) */
+#define GetBe32(p) _byteswap_ulong (*(const UInt32 *)(const void *)(p))
+#define GetBe64(p) _byteswap_uint64(*(const UInt64 *)(const void *)(p))
+
+#define SetBe32(p, v) (*(UInt32 *)(void *)(p)) = _byteswap_ulong(v)
+
+#elif defined(MY_CPU_LE_UNALIGN) && ( \
+       (defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3))) \
+    || (defined(__clang__) && MY__has_builtin(__builtin_bswap16)) )
+
+/* #define GetBe16(p) __builtin_bswap16(*(const UInt16 *)(const void *)(p)) */
+#define GetBe32(p) __builtin_bswap32(*(const UInt32 *)(const void *)(p))
+#define GetBe64(p) __builtin_bswap64(*(const UInt64 *)(const void *)(p))
+
+#define SetBe32(p, v) (*(UInt32 *)(void *)(p)) = __builtin_bswap32(v)
+
+#else
+
+#define GetBe32(p) ( \
+    ((UInt32)((const Byte *)(p))[0] << 24) | \
+    ((UInt32)((const Byte *)(p))[1] << 16) | \
+    ((UInt32)((const Byte *)(p))[2] <<  8) | \
+             ((const Byte *)(p))[3] )
+
+#define GetBe64(p) (((UInt64)GetBe32(p) << 32) | GetBe32(((const Byte *)(p)) + 4))
+
+#define SetBe32(p, v) { Byte *_ppp_ = (Byte *)(p); UInt32 _vvv_ = (v); \
+    _ppp_[0] = (Byte)(_vvv_ >> 24); \
+    _ppp_[1] = (Byte)(_vvv_ >> 16); \
+    _ppp_[2] = (Byte)(_vvv_ >> 8); \
+    _ppp_[3] = (Byte)_vvv_; }
+
+#endif
+
+
+#ifndef GetBe16
+
+#define GetBe16(p) ( (UInt16) ( \
+    ((UInt16)((const Byte *)(p))[0] << 8) | \
+             ((const Byte *)(p))[1] ))
+
+#endif
+
+
+
+#ifdef MY_CPU_X86_OR_AMD64
+
+typedef struct
+{
+  UInt32 maxFunc;
+  UInt32 vendor[3];
+  UInt32 ver;
+  UInt32 b;
+  UInt32 c;
+  UInt32 d;
+} Cx86cpuid;
+
+enum
+{
+  CPU_FIRM_INTEL,
+  CPU_FIRM_AMD,
+  CPU_FIRM_VIA
+};
+
+void MyCPUID(UInt32 function, UInt32 *a, UInt32 *b, UInt32 *c, UInt32 *d);
+
+BoolInt x86cpuid_CheckAndRead(Cx86cpuid *p);
+int x86cpuid_GetFirm(const Cx86cpuid *p);
+
+#define x86cpuid_GetFamily(ver) (((ver >> 16) & 0xFF0) | ((ver >> 8) & 0xF))
+#define x86cpuid_GetModel(ver)  (((ver >> 12) &  0xF0) | ((ver >> 4) & 0xF))
+#define x86cpuid_GetStepping(ver) (ver & 0xF)
+
+BoolInt CPU_Is_InOrder(void);
+
+BoolInt CPU_IsSupported_AES(void);
+BoolInt CPU_IsSupported_AVX2(void);
+BoolInt CPU_IsSupported_VAES_AVX2(void);
+BoolInt CPU_IsSupported_SSSE3(void);
+BoolInt CPU_IsSupported_SSE41(void);
+BoolInt CPU_IsSupported_SHA(void);
+BoolInt CPU_IsSupported_PageGB(void);
+
+#elif defined(MY_CPU_ARM_OR_ARM64)
+
+BoolInt CPU_IsSupported_CRC32(void);
+BoolInt CPU_IsSupported_NEON(void);
+
+#if defined(_WIN32)
+BoolInt CPU_IsSupported_CRYPTO(void);
+#define CPU_IsSupported_SHA1  CPU_IsSupported_CRYPTO
+#define CPU_IsSupported_SHA2  CPU_IsSupported_CRYPTO
+#define CPU_IsSupported_AES   CPU_IsSupported_CRYPTO
+#else
+BoolInt CPU_IsSupported_SHA1(void);
+BoolInt CPU_IsSupported_SHA2(void);
+BoolInt CPU_IsSupported_AES(void);
+#endif
+
+#endif
+
+#if defined(__APPLE__)
+int My_sysctlbyname_Get(const char *name, void *buf, size_t *bufSize);
+int My_sysctlbyname_Get_UInt32(const char *name, UInt32 *val);
+#endif
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/Delta.h

@@ -0,0 +1,19 @@
+/* Delta.h -- Delta converter
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __DELTA_H
+#define __DELTA_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define DELTA_STATE_SIZE 256
+
+void Delta_Init(Byte *state);
+void Delta_Encode(Byte *state, unsigned delta, Byte *data, SizeT size);
+void Delta_Decode(Byte *state, unsigned delta, Byte *data, SizeT size);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/LzFind.h

@@ -0,0 +1,136 @@
+/* LzFind.h -- Match finder for LZ algorithms
+2021-07-13 : 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;  /* wrap over Zero is allowed (streamPos < pos). Use (UInt32)(streamPos - pos) */
+  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) ((const Byte *)(p)->buffer)
+
+#define Inline_MatchFinder_GetNumAvailableBytes(p) ((UInt32)((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);
+
+/*
+#define Inline_MatchFinder_InitPos(p, val) \
+    (p)->pos = (val); \
+    (p)->streamPos = (val);
+*/
+
+#define Inline_MatchFinder_ReduceOffsets(p, subValue) \
+    (p)->pos -= (subValue); \
+    (p)->streamPos -= (subValue);
+
+
+UInt32 * GetMatchesSpec1(UInt32 lenLimit, UInt32 curMatch, UInt32 pos, const Byte *buffer, CLzRef *son,
+    size_t _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;
+} IMatchFinder2;
+
+void MatchFinder_CreateVTable(CMatchFinder *p, IMatchFinder2 *vTable);
+
+void MatchFinder_Init_LowHash(CMatchFinder *p);
+void MatchFinder_Init_HighHash(CMatchFinder *p);
+void MatchFinder_Init_4(CMatchFinder *p);
+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);
+
+void LzFindPrepare(void);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/LzHash.h

@@ -0,0 +1,34 @@
+/* LzHash.h -- HASH functions for LZ algorithms
+2019-10-30 : Igor Pavlov : Public domain */
+
+#ifndef __LZ_HASH_H
+#define __LZ_HASH_H
+
+/*
+  (kHash2Size >= (1 <<  8)) : Required
+  (kHash3Size >= (1 << 16)) : Required
+*/
+
+#define kHash2Size (1 << 10)
+#define kHash3Size (1 << 16)
+// #define kHash4Size (1 << 20)
+
+#define kFix3HashSize (kHash2Size)
+#define kFix4HashSize (kHash2Size + kHash3Size)
+// #define kFix5HashSize (kHash2Size + kHash3Size + kHash4Size)
+
+/*
+  We use up to 3 crc values for hash:
+    crc0
+    crc1 << Shift_1
+    crc2 << Shift_2
+  (Shift_1 = 5) and (Shift_2 = 10) is good tradeoff.
+  Small values for Shift are not good for collision rate.
+  Big value for Shift_2 increases the minimum size
+  of hash table, that will be slow for small files.
+*/
+
+#define kLzHash_CrcShift_1 5
+#define kLzHash_CrcShift_2 10
+
+#endif

3rdparty/lzma/include/Lzma2Dec.h

@@ -0,0 +1,120 @@
+/* Lzma2Dec.h -- LZMA2 Decoder
+2018-02-19 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA2_DEC_H
+#define __LZMA2_DEC_H
+
+#include "LzmaDec.h"
+
+EXTERN_C_BEGIN
+
+/* ---------- State Interface ---------- */
+
+typedef struct
+{
+  unsigned state;
+  Byte control;
+  Byte needInitLevel;
+  Byte isExtraMode;
+  Byte _pad_;
+  UInt32 packSize;
+  UInt32 unpackSize;
+  CLzmaDec decoder;
+} CLzma2Dec;
+
+#define Lzma2Dec_Construct(p) LzmaDec_Construct(&(p)->decoder)
+#define Lzma2Dec_FreeProbs(p, alloc) LzmaDec_FreeProbs(&(p)->decoder, alloc)
+#define Lzma2Dec_Free(p, alloc) LzmaDec_Free(&(p)->decoder, alloc)
+
+SRes Lzma2Dec_AllocateProbs(CLzma2Dec *p, Byte prop, ISzAllocPtr alloc);
+SRes Lzma2Dec_Allocate(CLzma2Dec *p, Byte prop, ISzAllocPtr alloc);
+void Lzma2Dec_Init(CLzma2Dec *p);
+
+/*
+finishMode:
+  It has meaning only if the decoding reaches output limit (*destLen or dicLimit).
+  LZMA_FINISH_ANY - use smallest number of input bytes
+  LZMA_FINISH_END - read EndOfStream marker after decoding
+
+Returns:
+  SZ_OK
+    status:
+      LZMA_STATUS_FINISHED_WITH_MARK
+      LZMA_STATUS_NOT_FINISHED
+      LZMA_STATUS_NEEDS_MORE_INPUT
+  SZ_ERROR_DATA - Data error
+*/
+
+SRes Lzma2Dec_DecodeToDic(CLzma2Dec *p, SizeT dicLimit,
+    const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status);
+
+SRes Lzma2Dec_DecodeToBuf(CLzma2Dec *p, Byte *dest, SizeT *destLen,
+    const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status);
+
+
+/* ---------- LZMA2 block and chunk parsing ---------- */
+
+/*
+Lzma2Dec_Parse() parses compressed data stream up to next independent block or next chunk data.
+It can return LZMA_STATUS_* code or LZMA2_PARSE_STATUS_* code:
+  - LZMA2_PARSE_STATUS_NEW_BLOCK - there is new block, and 1 additional byte (control byte of next block header) was read from input.
+  - LZMA2_PARSE_STATUS_NEW_CHUNK - there is new chunk, and only lzma2 header of new chunk was read.
+                                   CLzma2Dec::unpackSize contains unpack size of that chunk
+*/
+
+typedef enum
+{
+/*
+  LZMA_STATUS_NOT_SPECIFIED                 // data error
+  LZMA_STATUS_FINISHED_WITH_MARK
+  LZMA_STATUS_NOT_FINISHED                  //
+  LZMA_STATUS_NEEDS_MORE_INPUT
+  LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK   // unused
+*/
+  LZMA2_PARSE_STATUS_NEW_BLOCK = LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK + 1,
+  LZMA2_PARSE_STATUS_NEW_CHUNK
+} ELzma2ParseStatus;
+
+ELzma2ParseStatus Lzma2Dec_Parse(CLzma2Dec *p,
+    SizeT outSize,   // output size
+    const Byte *src, SizeT *srcLen,
+    int checkFinishBlock   // set (checkFinishBlock = 1), if it must read full input data, if decoder.dicPos reaches blockMax position.
+    );
+
+/*
+LZMA2 parser doesn't decode LZMA chunks, so we must read
+  full input LZMA chunk to decode some part of LZMA chunk.
+
+Lzma2Dec_GetUnpackExtra() returns the value that shows
+    max possible number of output bytes that can be output by decoder
+    at current input positon.
+*/
+
+#define Lzma2Dec_GetUnpackExtra(p) ((p)->isExtraMode ? (p)->unpackSize : 0);
+
+
+/* ---------- One Call Interface ---------- */
+
+/*
+finishMode:
+  It has meaning only if the decoding reaches output limit (*destLen).
+  LZMA_FINISH_ANY - use smallest number of input bytes
+  LZMA_FINISH_END - read EndOfStream marker after decoding
+
+Returns:
+  SZ_OK
+    status:
+      LZMA_STATUS_FINISHED_WITH_MARK
+      LZMA_STATUS_NOT_FINISHED
+  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 Lzma2Decode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen,
+    Byte prop, ELzmaFinishMode finishMode, ELzmaStatus *status, ISzAllocPtr alloc);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/Lzma2DecMt.h

@@ -0,0 +1,79 @@
+/* Lzma2DecMt.h -- LZMA2 Decoder Multi-thread
+2018-02-17 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA2_DEC_MT_H
+#define __LZMA2_DEC_MT_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+typedef struct
+{
+  size_t inBufSize_ST;
+  size_t outStep_ST;
+  
+  #ifndef _7ZIP_ST
+  unsigned numThreads;
+  size_t inBufSize_MT;
+  size_t outBlockMax;
+  size_t inBlockMax;
+  #endif
+} CLzma2DecMtProps;
+
+/* init to single-thread mode */
+void Lzma2DecMtProps_Init(CLzma2DecMtProps *p);
+
+
+/* ---------- CLzma2DecMtHandle Interface ---------- */
+
+/* Lzma2DecMt_ * 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  - 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 - error in multithreading functions (only for Mt version)
+*/
+
+typedef void * CLzma2DecMtHandle;
+
+CLzma2DecMtHandle Lzma2DecMt_Create(ISzAllocPtr alloc, ISzAllocPtr allocMid);
+void Lzma2DecMt_Destroy(CLzma2DecMtHandle p);
+
+SRes Lzma2DecMt_Decode(CLzma2DecMtHandle p,
+    Byte prop,
+    const CLzma2DecMtProps *props,
+    ISeqOutStream *outStream,
+    const UInt64 *outDataSize, // NULL means undefined
+    int finishMode,            // 0 - partial unpacking is allowed, 1 - if lzma2 stream must be finished
+    // Byte *outBuf, size_t *outBufSize,
+    ISeqInStream *inStream,
+    // const Byte *inData, size_t inDataSize,
+    
+    // out variables:
+    UInt64 *inProcessed,
+    int *isMT,  /* out: (*isMT == 0), if single thread decoding was used */
+
+    // UInt64 *outProcessed,
+    ICompressProgress *progress);
+
+
+/* ---------- Read from CLzma2DecMtHandle Interface ---------- */
+
+SRes Lzma2DecMt_Init(CLzma2DecMtHandle pp,
+    Byte prop,
+    const CLzma2DecMtProps *props,
+    const UInt64 *outDataSize, int finishMode,
+    ISeqInStream *inStream);
+
+SRes Lzma2DecMt_Read(CLzma2DecMtHandle pp,
+    Byte *data, size_t *outSize,
+    UInt64 *inStreamProcessed);
+
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/Lzma2Enc.h

@@ -0,0 +1,55 @@
+/* Lzma2Enc.h -- LZMA2 Encoder
+2017-07-27 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA2_ENC_H
+#define __LZMA2_ENC_H
+
+#include "LzmaEnc.h"
+
+EXTERN_C_BEGIN
+
+#define LZMA2_ENC_PROPS__BLOCK_SIZE__AUTO 0
+#define LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID ((UInt64)(Int64)-1)
+
+typedef struct
+{
+  CLzmaEncProps lzmaProps;
+  UInt64 blockSize;
+  int numBlockThreads_Reduced;
+  int numBlockThreads_Max;
+  int numTotalThreads;
+} CLzma2EncProps;
+
+void Lzma2EncProps_Init(CLzma2EncProps *p);
+void Lzma2EncProps_Normalize(CLzma2EncProps *p);
+
+/* ---------- CLzmaEnc2Handle Interface ---------- */
+
+/* Lzma2Enc_* 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  - 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 - error in multithreading functions (only for Mt version)
+*/
+
+typedef void * CLzma2EncHandle;
+
+CLzma2EncHandle Lzma2Enc_Create(ISzAllocPtr alloc, ISzAllocPtr allocBig);
+void Lzma2Enc_Destroy(CLzma2EncHandle p);
+SRes Lzma2Enc_SetProps(CLzma2EncHandle p, const CLzma2EncProps *props);
+void Lzma2Enc_SetDataSize(CLzma2EncHandle p, UInt64 expectedDataSiize);
+Byte Lzma2Enc_WriteProperties(CLzma2EncHandle p);
+SRes Lzma2Enc_Encode2(CLzma2EncHandle p,
+    ISeqOutStream *outStream,
+    Byte *outBuf, size_t *outBufSize,
+    ISeqInStream *inStream,
+    const Byte *inData, size_t inDataSize,
+    ICompressProgress *progress);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/Lzma86.h

@@ -0,0 +1,111 @@
+/* Lzma86.h -- LZMA + x86 (BCJ) Filter
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA86_H
+#define __LZMA86_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define LZMA86_SIZE_OFFSET (1 + 5)
+#define LZMA86_HEADER_SIZE (LZMA86_SIZE_OFFSET + 8)
+
+/*
+It's an example for LZMA + x86 Filter use.
+You can use .lzma86 extension, if you write that stream to file.
+.lzma86 header adds one additional byte to standard .lzma header.
+.lzma86 header (14 bytes):
+  Offset Size  Description
+    0     1    = 0 - no filter, pure LZMA
+               = 1 - x86 filter + LZMA
+    1     1    lc, lp and pb in encoded form
+    2     4    dictSize (little endian)
+    6     8    uncompressed size (little endian)
+
+
+Lzma86_Encode
+-------------
+level - compression level: 0 <= level <= 9, the default value for "level" is 5.
+
+dictSize - The dictionary size in bytes. The maximum value is
+        128 MB = (1 << 27) bytes for 32-bit version
+          1 GB = (1 << 30) bytes for 64-bit version
+     The default value is 16 MB = (1 << 24) bytes, for level = 5.
+     It's recommended to use the dictionary that is larger than 4 KB and
+     that can be calculated as (1 << N) or (3 << N) sizes.
+     For better compression ratio dictSize must be >= inSize.
+
+filterMode:
+    SZ_FILTER_NO   - no Filter
+    SZ_FILTER_YES  - x86 Filter
+    SZ_FILTER_AUTO - it tries both alternatives to select best.
+              Encoder will use 2 or 3 passes:
+              2 passes when FILTER_NO provides better compression.
+              3 passes when FILTER_YES provides better compression.
+
+Lzma86Encode allocates Data with MyAlloc functions.
+RAM Requirements for compressing:
+  RamSize = dictionarySize * 11.5 + 6MB + FilterBlockSize
+      filterMode     FilterBlockSize
+     SZ_FILTER_NO         0
+     SZ_FILTER_YES      inSize
+     SZ_FILTER_AUTO     inSize
+
+
+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)
+*/
+
+enum ESzFilterMode
+{
+  SZ_FILTER_NO,
+  SZ_FILTER_YES,
+  SZ_FILTER_AUTO
+};
+
+SRes Lzma86_Encode(Byte *dest, size_t *destLen, const Byte *src, size_t srcLen,
+    int level, UInt32 dictSize, int filterMode);
+
+
+/*
+Lzma86_GetUnpackSize:
+  In:
+    src      - input data
+    srcLen   - input data size
+  Out:
+    unpackSize - size of uncompressed stream
+  Return code:
+    SZ_OK               - OK
+    SZ_ERROR_INPUT_EOF  - Error in headers
+*/
+
+SRes Lzma86_GetUnpackSize(const Byte *src, SizeT srcLen, UInt64 *unpackSize);
+
+/*
+Lzma86_Decode:
+  In:
+    dest     - output data
+    destLen  - output data size
+    src      - input data
+    srcLen   - input data size
+  Out:
+    destLen  - processed output size
+    srcLen   - processed input size
+  Return code:
+    SZ_OK           - OK
+    SZ_ERROR_DATA  - Data error
+    SZ_ERROR_MEM   - Memory allocation error
+    SZ_ERROR_UNSUPPORTED - unsupported file
+    SZ_ERROR_INPUT_EOF - it needs more bytes in input buffer
+*/
+
+SRes Lzma86_Decode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/LzmaDec.h

@@ -0,0 +1,236 @@
+/* LzmaDec.h -- LZMA Decoder
+2020-03-19 : 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
+  SZ_ERROR_FAIL - Some unexpected error: internal error of code, memory corruption or hardware failure
+*/
+
+SRes LzmaDec_DecodeToDic(CLzmaDec *p, SizeT dicLimit,
+    const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status);
+
+
+/* ---------- 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);
+
+
+/* ---------- 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).
+  SZ_ERROR_FAIL - Some unexpected error: internal error of code, memory corruption or hardware failure
+*/
+
+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

3rdparty/lzma/include/LzmaEnc.h

@@ -0,0 +1,78 @@
+/*  LzmaEnc.h -- LZMA Encoder
+2019-10-30 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA_ENC_H
+#define __LZMA_ENC_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define LZMA_PROPS_SIZE 5
+
+typedef struct _CLzmaEncProps
+{
+  int level;       /* 0 <= level <= 9 */
+  UInt32 dictSize; /* (1 << 12) <= dictSize <= (1 << 27) for 32-bit version
+                      (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 */
+  int algo;        /* 0 - fast, 1 - normal, default = 1 */
+  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 */
+  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 */
+
+  UInt64 affinity;
+} CLzmaEncProps;
+
+void LzmaEncProps_Init(CLzmaEncProps *p);
+void LzmaEncProps_Normalize(CLzmaEncProps *p);
+UInt32 LzmaEncProps_GetDictSize(const CLzmaEncProps *props2);
+
+
+/* ---------- CLzmaEncHandle Interface ---------- */
+
+/* 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  - 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 - error in multithreading functions (only for Mt version)
+*/
+
+typedef void * CLzmaEncHandle;
+
+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, ISzAllocPtr alloc, ISzAllocPtr allocBig);
+SRes LzmaEnc_MemEncode(CLzmaEncHandle p, Byte *dest, SizeT *destLen, const Byte *src, SizeT srcLen,
+    int writeEndMark, ICompressProgress *progress, ISzAllocPtr alloc, ISzAllocPtr allocBig);
+
+
+/* ---------- One Call Interface ---------- */
+
+SRes LzmaEncode(Byte *dest, SizeT *destLen, const Byte *src, SizeT srcLen,
+    const CLzmaEncProps *props, Byte *propsEncoded, SizeT *propsSize, int writeEndMark,
+    ICompressProgress *progress, ISzAllocPtr alloc, ISzAllocPtr allocBig);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/LzmaLib.h

@@ -0,0 +1,138 @@
+/* LzmaLib.h -- LZMA library interface
+2021-04-03 : Igor Pavlov : Public domain */
+
+#ifndef __LZMA_LIB_H
+#define __LZMA_LIB_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define MY_STDAPI int MY_STD_CALL
+
+#define LZMA_PROPS_SIZE 5
+
+/*
+RAM requirements for LZMA:
+  for compression:   (dictSize * 11.5 + 6 MB) + state_size
+  for decompression: dictSize + state_size
+    state_size = (4 + (1.5 << (lc + lp))) KB
+    by default (lc=3, lp=0), state_size = 16 KB.
+
+LZMA properties (5 bytes) format
+    Offset Size  Description
+      0     1    lc, lp and pb in encoded form.
+      1     4    dictSize (little endian).
+*/
+
+/*
+LzmaCompress
+------------
+
+outPropsSize -
+     In:  the pointer to the size of outProps buffer; *outPropsSize = LZMA_PROPS_SIZE = 5.
+     Out: the pointer to the size of written properties in outProps buffer; *outPropsSize = LZMA_PROPS_SIZE = 5.
+
+  LZMA Encoder will use defult values for any parameter, if it is
+  -1  for any from: level, loc, lp, pb, fb, numThreads
+   0  for dictSize
+  
+level - compression level: 0 <= level <= 9;
+
+  level dictSize algo  fb
+    0:    64 KB   0    32
+    1:   256 KB   0    32
+    2:     1 MB   0    32
+    3:     4 MB   0    32
+    4:    16 MB   0    32
+    5:    16 MB   1    32
+    6:    32 MB   1    32
+    7:    32 MB   1    64
+    8:    64 MB   1    64
+    9:    64 MB   1    64
+ 
+  The default value for "level" is 5.
+
+  algo = 0 means fast method
+  algo = 1 means normal method
+
+dictSize - The dictionary size in bytes. The maximum value is
+        128 MB = (1 << 27) bytes for 32-bit version
+          1 GB = (1 << 30) bytes for 64-bit version
+     The default value is 16 MB = (1 << 24) bytes.
+     It's recommended to use the dictionary that is larger than 4 KB and
+     that can be calculated as (1 << N) or (3 << N) sizes.
+
+lc - The number of literal context bits (high bits of previous literal).
+     It can be in the range from 0 to 8. The default value is 3.
+     Sometimes lc=4 gives the gain for big files.
+
+lp - The number of literal pos bits (low bits of current position for literals).
+     It can be in the range from 0 to 4. The default value is 0.
+     The lp switch is intended for periodical data when the period is equal to 2^lp.
+     For example, for 32-bit (4 bytes) periodical data you can use lp=2. Often it's
+     better to set lc=0, if you change lp switch.
+
+pb - The number of pos bits (low bits of current position).
+     It can be in the range from 0 to 4. The default value is 2.
+     The pb switch is intended for periodical data when the period is equal 2^pb.
+
+fb - Word size (the number of fast bytes).
+     It can be in the range from 5 to 273. The default value is 32.
+     Usually, a big number gives a little bit better compression ratio and
+     slower compression process.
+
+numThreads - The number of thereads. 1 or 2. The default value is 2.
+     Fast mode (algo = 0) can use only 1 thread.
+
+In:
+  dest     - output data buffer
+  destLen  - output data buffer size
+  src      - input data
+  srcLen   - input data size
+Out:
+  destLen  - processed output size
+Returns:
+  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)
+*/
+
+MY_STDAPI LzmaCompress(unsigned char *dest, size_t *destLen, const unsigned char *src, size_t srcLen,
+  unsigned char *outProps, size_t *outPropsSize, /* *outPropsSize must be = 5 */
+  int level,      /* 0 <= level <= 9, default = 5 */
+  unsigned dictSize,  /* default = (1 << 24) */
+  int lc,        /* 0 <= lc <= 8, default = 3  */
+  int lp,        /* 0 <= lp <= 4, default = 0  */
+  int pb,        /* 0 <= pb <= 4, default = 2  */
+  int fb,        /* 5 <= fb <= 273, default = 32 */
+  int numThreads /* 1 or 2, default = 2 */
+  );
+
+/*
+LzmaUncompress
+--------------
+In:
+  dest     - output data buffer
+  destLen  - output data buffer size
+  src      - input data
+  srcLen   - input data size
+Out:
+  destLen  - processed output size
+  srcLen   - processed input size
+Returns:
+  SZ_OK                - OK
+  SZ_ERROR_DATA        - Data error
+  SZ_ERROR_MEM         - Memory allocation arror
+  SZ_ERROR_UNSUPPORTED - Unsupported properties
+  SZ_ERROR_INPUT_EOF   - it needs more bytes in input buffer (src)
+*/
+
+MY_STDAPI LzmaUncompress(unsigned char *dest, size_t *destLen, const unsigned char *src, SizeT *srcLen,
+  const unsigned char *props, size_t propsSize);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/Ppmd.h

@@ -0,0 +1,167 @@
+/* Ppmd.h -- PPMD codec common code
+2021-04-13 : Igor Pavlov : Public domain
+This code is based on PPMd var.H (2001): Dmitry Shkarin : Public domain */
+
+#ifndef __PPMD_H
+#define __PPMD_H
+
+#include "CpuArch.h"
+
+EXTERN_C_BEGIN
+
+#if defined(MY_CPU_SIZEOF_POINTER) && (MY_CPU_SIZEOF_POINTER == 4)
+/*
+   PPMD code always uses 32-bit internal fields in PPMD structures to store internal references in main block.
+   if (PPMD_32BIT is     defined), the PPMD code stores internal pointers to 32-bit reference fields.
+   if (PPMD_32BIT is NOT defined), the PPMD code stores internal UInt32 offsets to reference fields.
+   if (pointer size is 64-bit), then (PPMD_32BIT) mode is not allowed,
+   if (pointer size is 32-bit), then (PPMD_32BIT) mode is optional,
+     and it's allowed to disable PPMD_32BIT mode even if pointer is 32-bit.
+   PPMD code works slightly faster in (PPMD_32BIT) mode.
+*/
+  #define PPMD_32BIT
+#endif
+
+#define PPMD_INT_BITS 7
+#define PPMD_PERIOD_BITS 7
+#define PPMD_BIN_SCALE (1 << (PPMD_INT_BITS + PPMD_PERIOD_BITS))
+
+#define PPMD_GET_MEAN_SPEC(summ, shift, round) (((summ) + (1 << ((shift) - (round)))) >> (shift))
+#define PPMD_GET_MEAN(summ) PPMD_GET_MEAN_SPEC((summ), PPMD_PERIOD_BITS, 2)
+#define PPMD_UPDATE_PROB_0(prob) ((prob) + (1 << PPMD_INT_BITS) - PPMD_GET_MEAN(prob))
+#define PPMD_UPDATE_PROB_1(prob) ((prob) - PPMD_GET_MEAN(prob))
+
+#define PPMD_N1 4
+#define PPMD_N2 4
+#define PPMD_N3 4
+#define PPMD_N4 ((128 + 3 - 1 * PPMD_N1 - 2 * PPMD_N2 - 3 * PPMD_N3) / 4)
+#define PPMD_NUM_INDEXES (PPMD_N1 + PPMD_N2 + PPMD_N3 + PPMD_N4)
+
+MY_CPU_pragma_pack_push_1
+/* Most compilers works OK here even without #pragma pack(push, 1), but some GCC compilers need it. */
+
+/* SEE-contexts for PPM-contexts with masked symbols */
+typedef struct
+{
+  UInt16 Summ; /* Freq */
+  Byte Shift;  /* Speed of Freq change; low Shift is for fast change */
+  Byte Count;  /* Count to next change of Shift */
+} CPpmd_See;
+
+#define Ppmd_See_Update(p)  if ((p)->Shift < PPMD_PERIOD_BITS && --(p)->Count == 0) \
+    { (p)->Summ = (UInt16)((p)->Summ << 1); (p)->Count = (Byte)(3 << (p)->Shift++); }
+
+
+typedef struct
+{
+  Byte Symbol;
+  Byte Freq;
+  UInt16 Successor_0;
+  UInt16 Successor_1;
+} CPpmd_State;
+
+typedef struct CPpmd_State2_
+{
+  Byte Symbol;
+  Byte Freq;
+} CPpmd_State2;
+
+typedef struct CPpmd_State4_
+{
+  UInt16 Successor_0;
+  UInt16 Successor_1;
+} CPpmd_State4;
+
+MY_CPU_pragma_pop
+
+/*
+   PPMD code can write full CPpmd_State structure data to CPpmd*_Context
+      at (byte offset = 2) instead of some fields of original CPpmd*_Context structure.
+   
+   If we use pointers to different types, but that point to shared
+   memory space, we can have aliasing problem (strict aliasing).
+   
+   XLC compiler in -O2 mode can change the order of memory write instructions
+   in relation to read instructions, if we have use pointers to different types.
+   
+   To solve that aliasing problem we use combined CPpmd*_Context structure
+   with unions that contain the fields from both structures:
+   the original CPpmd*_Context and CPpmd_State.
+   So we can access the fields from both structures via one pointer,
+   and the compiler doesn't change the order of write instructions
+   in relation to read instructions.
+
+   If we don't use memory write instructions to shared memory in
+   some local code, and we use only reading instructions (read only),
+   then probably it's safe to use pointers to different types for reading.
+*/
+  
+
+
+#ifdef PPMD_32BIT
+
+  #define Ppmd_Ref_Type(type)   type *
+  #define Ppmd_GetRef(p, ptr)   (ptr)
+  #define Ppmd_GetPtr(p, ptr)   (ptr)
+  #define Ppmd_GetPtr_Type(p, ptr, note_type) (ptr)
+
+#else
+
+  #define Ppmd_Ref_Type(type)   UInt32
+  #define Ppmd_GetRef(p, ptr)   ((UInt32)((Byte *)(ptr) - (p)->Base))
+  #define Ppmd_GetPtr(p, offs)  ((void *)((p)->Base + (offs)))
+  #define Ppmd_GetPtr_Type(p, offs, type) ((type *)Ppmd_GetPtr(p, offs))
+
+#endif // PPMD_32BIT
+
+
+typedef Ppmd_Ref_Type(CPpmd_State) CPpmd_State_Ref;
+typedef Ppmd_Ref_Type(void)        CPpmd_Void_Ref;
+typedef Ppmd_Ref_Type(Byte)        CPpmd_Byte_Ref;
+
+
+/*
+#ifdef MY_CPU_LE_UNALIGN
+// the unaligned 32-bit access latency can be too large, if the data is not in L1 cache.
+#define Ppmd_GET_SUCCESSOR(p) ((CPpmd_Void_Ref)*(const UInt32 *)(const void *)&(p)->Successor_0)
+#define Ppmd_SET_SUCCESSOR(p, v) *(UInt32 *)(void *)(void *)&(p)->Successor_0 = (UInt32)(v)
+
+#else
+*/
+
+/*
+   We can write 16-bit halves to 32-bit (Successor) field in any selected order.
+   But the native order is more consistent way.
+   So we use the native order, if LE/BE order can be detected here at compile time.
+*/
+
+#ifdef MY_CPU_BE
+
+  #define Ppmd_GET_SUCCESSOR(p) \
+    ( (CPpmd_Void_Ref) (((UInt32)(p)->Successor_0 << 16) | (p)->Successor_1) )
+
+  #define Ppmd_SET_SUCCESSOR(p, v) { \
+    (p)->Successor_0 = (UInt16)(((UInt32)(v) >> 16) /* & 0xFFFF */); \
+    (p)->Successor_1 = (UInt16)((UInt32)(v) /* & 0xFFFF */); }
+
+#else
+
+  #define Ppmd_GET_SUCCESSOR(p) \
+    ( (CPpmd_Void_Ref) ((p)->Successor_0 | ((UInt32)(p)->Successor_1 << 16)) )
+
+  #define Ppmd_SET_SUCCESSOR(p, v) { \
+    (p)->Successor_0 = (UInt16)((UInt32)(v) /* & 0xFFFF */); \
+    (p)->Successor_1 = (UInt16)(((UInt32)(v) >> 16) /* & 0xFFFF */); }
+
+#endif
+
+// #endif
+
+
+#define PPMD_SetAllBitsIn256Bytes(p) \
+  { size_t z; for (z = 0; z < 256 / sizeof(p[0]); z += 8) { \
+  p[z+7] = p[z+6] = p[z+5] = p[z+4] = p[z+3] = p[z+2] = p[z+1] = p[z+0] = ~(size_t)0; }}
+
+EXTERN_C_END
+ 
+#endif

3rdparty/lzma/include/Ppmd7.h

@@ -0,0 +1,181 @@
+/* Ppmd7.h -- Ppmd7 (PPMdH) compression codec
+2021-04-13 : Igor Pavlov : Public domain
+This code is based on:
+  PPMd var.H (2001): Dmitry Shkarin : Public domain */
+ 
+
+#ifndef __PPMD7_H
+#define __PPMD7_H
+
+#include "Ppmd.h"
+
+EXTERN_C_BEGIN
+
+#define PPMD7_MIN_ORDER 2
+#define PPMD7_MAX_ORDER 64
+
+#define PPMD7_MIN_MEM_SIZE (1 << 11)
+#define PPMD7_MAX_MEM_SIZE (0xFFFFFFFF - 12 * 3)
+
+struct CPpmd7_Context_;
+
+typedef Ppmd_Ref_Type(struct CPpmd7_Context_) CPpmd7_Context_Ref;
+
+// MY_CPU_pragma_pack_push_1
+
+typedef struct CPpmd7_Context_
+{
+  UInt16 NumStats;
+
+
+  union
+  {
+    UInt16 SummFreq;
+    CPpmd_State2 State2;
+  } Union2;
+
+  union
+  {
+    CPpmd_State_Ref Stats;
+    CPpmd_State4 State4;
+  } Union4;
+
+  CPpmd7_Context_Ref Suffix;
+} CPpmd7_Context;
+
+// MY_CPU_pragma_pop
+
+#define Ppmd7Context_OneState(p) ((CPpmd_State *)&(p)->Union2)
+
+
+
+
+typedef struct
+{
+  UInt32 Range;
+  UInt32 Code;
+  UInt32 Low;
+  IByteIn *Stream;
+} CPpmd7_RangeDec;
+
+
+typedef struct
+{
+  UInt32 Range;
+  Byte Cache;
+  // Byte _dummy_[3];
+  UInt64 Low;
+  UInt64 CacheSize;
+  IByteOut *Stream;
+} CPpmd7z_RangeEnc;
+
+
+typedef struct
+{
+  CPpmd7_Context *MinContext, *MaxContext;
+  CPpmd_State *FoundState;
+  unsigned OrderFall, InitEsc, PrevSuccess, MaxOrder, HiBitsFlag;
+  Int32 RunLength, InitRL; /* must be 32-bit at least */
+
+  UInt32 Size;
+  UInt32 GlueCount;
+  UInt32 AlignOffset;
+  Byte *Base, *LoUnit, *HiUnit, *Text, *UnitsStart;
+
+
+  
+  
+  union
+  {
+    CPpmd7_RangeDec dec;
+    CPpmd7z_RangeEnc enc;
+  } rc;
+  
+  Byte Indx2Units[PPMD_NUM_INDEXES + 2]; // +2 for alignment
+  Byte Units2Indx[128];
+  CPpmd_Void_Ref FreeList[PPMD_NUM_INDEXES];
+
+  Byte NS2BSIndx[256], NS2Indx[256];
+  Byte ExpEscape[16];
+  CPpmd_See DummySee, See[25][16];
+  UInt16 BinSumm[128][64];
+  // int LastSymbol;
+} CPpmd7;
+
+
+void Ppmd7_Construct(CPpmd7 *p);
+BoolInt Ppmd7_Alloc(CPpmd7 *p, UInt32 size, ISzAllocPtr alloc);
+void Ppmd7_Free(CPpmd7 *p, ISzAllocPtr alloc);
+void Ppmd7_Init(CPpmd7 *p, unsigned maxOrder);
+#define Ppmd7_WasAllocated(p) ((p)->Base != NULL)
+
+
+/* ---------- Internal Functions ---------- */
+
+#define Ppmd7_GetPtr(p, ptr)     Ppmd_GetPtr(p, ptr)
+#define Ppmd7_GetContext(p, ptr) Ppmd_GetPtr_Type(p, ptr, CPpmd7_Context)
+#define Ppmd7_GetStats(p, ctx)   Ppmd_GetPtr_Type(p, (ctx)->Union4.Stats, CPpmd_State)
+
+void Ppmd7_Update1(CPpmd7 *p);
+void Ppmd7_Update1_0(CPpmd7 *p);
+void Ppmd7_Update2(CPpmd7 *p);
+
+#define PPMD7_HiBitsFlag_3(sym) ((((unsigned)sym + 0xC0) >> (8 - 3)) & (1 << 3))
+#define PPMD7_HiBitsFlag_4(sym) ((((unsigned)sym + 0xC0) >> (8 - 4)) & (1 << 4))
+// #define PPMD7_HiBitsFlag_3(sym) ((sym) < 0x40 ? 0 : (1 << 3))
+// #define PPMD7_HiBitsFlag_4(sym) ((sym) < 0x40 ? 0 : (1 << 4))
+
+#define Ppmd7_GetBinSumm(p) \
+    &p->BinSumm[(size_t)(unsigned)Ppmd7Context_OneState(p->MinContext)->Freq - 1] \
+    [ p->PrevSuccess + ((p->RunLength >> 26) & 0x20) \
+    + p->NS2BSIndx[(size_t)Ppmd7_GetContext(p, p->MinContext->Suffix)->NumStats - 1] \
+    + PPMD7_HiBitsFlag_4(Ppmd7Context_OneState(p->MinContext)->Symbol) \
+    + (p->HiBitsFlag = PPMD7_HiBitsFlag_3(p->FoundState->Symbol)) ]
+
+CPpmd_See *Ppmd7_MakeEscFreq(CPpmd7 *p, unsigned numMasked, UInt32 *scale);
+
+
+/*
+We support two versions of Ppmd7 (PPMdH) methods that use same CPpmd7 structure:
+  1) Ppmd7a_*: original PPMdH
+  2) Ppmd7z_*: modified PPMdH with 7z Range Coder
+Ppmd7_*: the structures and functions that are common for both versions of PPMd7 (PPMdH)
+*/
+
+/* ---------- Decode ---------- */
+
+#define PPMD7_SYM_END    (-1)
+#define PPMD7_SYM_ERROR  (-2)
+
+/*
+You must set (CPpmd7::rc.dec.Stream) before Ppmd7*_RangeDec_Init()
+
+Ppmd7*_DecodeSymbol()
+out:
+  >= 0 : decoded byte
+    -1 : PPMD7_SYM_END   : End of payload marker
+    -2 : PPMD7_SYM_ERROR : Data error
+*/
+
+/* Ppmd7a_* : original PPMdH */
+BoolInt Ppmd7a_RangeDec_Init(CPpmd7_RangeDec *p);
+#define Ppmd7a_RangeDec_IsFinishedOK(p) ((p)->Code == 0)
+int Ppmd7a_DecodeSymbol(CPpmd7 *p);
+
+/* Ppmd7z_* : modified PPMdH with 7z Range Coder */
+BoolInt Ppmd7z_RangeDec_Init(CPpmd7_RangeDec *p);
+#define Ppmd7z_RangeDec_IsFinishedOK(p) ((p)->Code == 0)
+int Ppmd7z_DecodeSymbol(CPpmd7 *p);
+// Byte *Ppmd7z_DecodeSymbols(CPpmd7 *p, Byte *buf, const Byte *lim);
+
+
+/* ---------- Encode ---------- */
+
+void Ppmd7z_Init_RangeEnc(CPpmd7 *p);
+void Ppmd7z_Flush_RangeEnc(CPpmd7 *p);
+// void Ppmd7z_EncodeSymbol(CPpmd7 *p, int symbol);
+void Ppmd7z_EncodeSymbols(CPpmd7 *p, const Byte *buf, const Byte *lim);
+
+EXTERN_C_END
+ 
+#endif

3rdparty/lzma/include/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

3rdparty/lzma/include/RotateDefs.h

@@ -0,0 +1,30 @@
+/* RotateDefs.h -- Rotate functions
+2015-03-25 : Igor Pavlov : Public domain */
+
+#ifndef __ROTATE_DEFS_H
+#define __ROTATE_DEFS_H
+
+#ifdef _MSC_VER
+
+#include <stdlib.h>
+
+/* don't use _rotl with MINGW. It can insert slow call to function. */
+ 
+/* #if (_MSC_VER >= 1200) */
+#pragma intrinsic(_rotl)
+#pragma intrinsic(_rotr)
+/* #endif */
+
+#define rotlFixed(x, n) _rotl((x), (n))
+#define rotrFixed(x, n) _rotr((x), (n))
+
+#else
+
+/* new compilers can translate these macros to fast commands. */
+
+#define rotlFixed(x, n) (((x) << (n)) | ((x) >> (32 - (n))))
+#define rotrFixed(x, n) (((x) >> (n)) | ((x) << (32 - (n))))
+
+#endif
+
+#endif

3rdparty/lzma/include/Sha256.h

@@ -0,0 +1,76 @@
+/* Sha256.h -- SHA-256 Hash
+2021-01-01 : Igor Pavlov : Public domain */
+
+#ifndef __7Z_SHA256_H
+#define __7Z_SHA256_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define SHA256_NUM_BLOCK_WORDS  16
+#define SHA256_NUM_DIGEST_WORDS  8
+
+#define SHA256_BLOCK_SIZE   (SHA256_NUM_BLOCK_WORDS * 4)
+#define SHA256_DIGEST_SIZE  (SHA256_NUM_DIGEST_WORDS * 4)
+
+typedef void (MY_FAST_CALL *SHA256_FUNC_UPDATE_BLOCKS)(UInt32 state[8], const Byte *data, size_t numBlocks);
+
+/*
+  if (the system supports different SHA256 code implementations)
+  {
+    (CSha256::func_UpdateBlocks) will be used
+    (CSha256::func_UpdateBlocks) can be set by
+       Sha256_Init()        - to default (fastest)
+       Sha256_SetFunction() - to any algo
+  }
+  else
+  {
+    (CSha256::func_UpdateBlocks) is ignored.
+  }
+*/
+
+typedef struct
+{
+  SHA256_FUNC_UPDATE_BLOCKS func_UpdateBlocks;
+  UInt64 count;
+  UInt64 __pad_2[2];
+  UInt32 state[SHA256_NUM_DIGEST_WORDS];
+
+  Byte buffer[SHA256_BLOCK_SIZE];
+} CSha256;
+
+
+#define SHA256_ALGO_DEFAULT 0
+#define SHA256_ALGO_SW      1
+#define SHA256_ALGO_HW      2
+
+/*
+Sha256_SetFunction()
+return:
+  0 - (algo) value is not supported, and func_UpdateBlocks was not changed
+  1 - func_UpdateBlocks was set according (algo) value.
+*/
+
+BoolInt Sha256_SetFunction(CSha256 *p, unsigned algo);
+
+void Sha256_InitState(CSha256 *p);
+void Sha256_Init(CSha256 *p);
+void Sha256_Update(CSha256 *p, const Byte *data, size_t size);
+void Sha256_Final(CSha256 *p, Byte *digest);
+
+
+
+
+// void MY_FAST_CALL Sha256_UpdateBlocks(UInt32 state[8], const Byte *data, size_t numBlocks);
+
+/*
+call Sha256Prepare() once at program start.
+It prepares all supported implementations, and detects the fastest implementation.
+*/
+
+void Sha256Prepare(void);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/Xz.h

@@ -0,0 +1,517 @@
+/* Xz.h - Xz interface
+2021-04-01 : Igor Pavlov : Public domain */
+
+#ifndef __XZ_H
+#define __XZ_H
+
+#include "Sha256.h"
+
+EXTERN_C_BEGIN
+
+#define XZ_ID_Subblock 1
+#define XZ_ID_Delta 3
+#define XZ_ID_X86 4
+#define XZ_ID_PPC 5
+#define XZ_ID_IA64 6
+#define XZ_ID_ARM 7
+#define XZ_ID_ARMT 8
+#define XZ_ID_SPARC 9
+#define XZ_ID_LZMA2 0x21
+
+unsigned Xz_ReadVarInt(const Byte *p, size_t maxSize, UInt64 *value);
+unsigned Xz_WriteVarInt(Byte *buf, UInt64 v);
+
+/* ---------- xz block ---------- */
+
+#define XZ_BLOCK_HEADER_SIZE_MAX 1024
+
+#define XZ_NUM_FILTERS_MAX 4
+#define XZ_BF_NUM_FILTERS_MASK 3
+#define XZ_BF_PACK_SIZE (1 << 6)
+#define XZ_BF_UNPACK_SIZE (1 << 7)
+
+#define XZ_FILTER_PROPS_SIZE_MAX 20
+
+typedef struct
+{
+  UInt64 id;
+  UInt32 propsSize;
+  Byte props[XZ_FILTER_PROPS_SIZE_MAX];
+} CXzFilter;
+
+typedef struct
+{
+  UInt64 packSize;
+  UInt64 unpackSize;
+  Byte flags;
+  CXzFilter filters[XZ_NUM_FILTERS_MAX];
+} CXzBlock;
+
+#define XzBlock_GetNumFilters(p) (((unsigned)(p)->flags & XZ_BF_NUM_FILTERS_MASK) + 1)
+#define XzBlock_HasPackSize(p)   (((p)->flags & XZ_BF_PACK_SIZE) != 0)
+#define XzBlock_HasUnpackSize(p) (((p)->flags & XZ_BF_UNPACK_SIZE) != 0)
+#define XzBlock_HasUnsupportedFlags(p) (((p)->flags & ~(XZ_BF_NUM_FILTERS_MASK | XZ_BF_PACK_SIZE | XZ_BF_UNPACK_SIZE)) != 0)
+
+SRes XzBlock_Parse(CXzBlock *p, const Byte *header);
+SRes XzBlock_ReadHeader(CXzBlock *p, ISeqInStream *inStream, BoolInt *isIndex, UInt32 *headerSizeRes);
+
+/* ---------- xz stream ---------- */
+
+#define XZ_SIG_SIZE 6
+#define XZ_FOOTER_SIG_SIZE 2
+
+extern const Byte XZ_SIG[XZ_SIG_SIZE];
+
+/*
+extern const Byte XZ_FOOTER_SIG[XZ_FOOTER_SIG_SIZE];
+*/
+
+#define XZ_FOOTER_SIG_0 'Y'
+#define XZ_FOOTER_SIG_1 'Z'
+
+#define XZ_STREAM_FLAGS_SIZE 2
+#define XZ_STREAM_CRC_SIZE 4
+
+#define XZ_STREAM_HEADER_SIZE (XZ_SIG_SIZE + XZ_STREAM_FLAGS_SIZE + XZ_STREAM_CRC_SIZE)
+#define XZ_STREAM_FOOTER_SIZE (XZ_FOOTER_SIG_SIZE + XZ_STREAM_FLAGS_SIZE + XZ_STREAM_CRC_SIZE + 4)
+
+#define XZ_CHECK_MASK 0xF
+#define XZ_CHECK_NO 0
+#define XZ_CHECK_CRC32 1
+#define XZ_CHECK_CRC64 4
+#define XZ_CHECK_SHA256 10
+
+typedef struct
+{
+  unsigned mode;
+  UInt32 crc;
+  UInt64 crc64;
+  CSha256 sha;
+} CXzCheck;
+
+void XzCheck_Init(CXzCheck *p, unsigned mode);
+void XzCheck_Update(CXzCheck *p, const void *data, size_t size);
+int XzCheck_Final(CXzCheck *p, Byte *digest);
+
+typedef UInt16 CXzStreamFlags;
+
+#define XzFlags_IsSupported(f) ((f) <= XZ_CHECK_MASK)
+#define XzFlags_GetCheckType(f) ((f) & XZ_CHECK_MASK)
+#define XzFlags_HasDataCrc32(f) (Xz_GetCheckType(f) == XZ_CHECK_CRC32)
+unsigned XzFlags_GetCheckSize(CXzStreamFlags f);
+
+SRes Xz_ParseHeader(CXzStreamFlags *p, const Byte *buf);
+SRes Xz_ReadHeader(CXzStreamFlags *p, ISeqInStream *inStream);
+
+typedef struct
+{
+  UInt64 unpackSize;
+  UInt64 totalSize;
+} CXzBlockSizes;
+
+typedef struct
+{
+  CXzStreamFlags flags;
+  size_t numBlocks;
+  CXzBlockSizes *blocks;
+  UInt64 startOffset;
+} CXzStream;
+
+void Xz_Construct(CXzStream *p);
+void Xz_Free(CXzStream *p, ISzAllocPtr alloc);
+
+#define XZ_SIZE_OVERFLOW ((UInt64)(Int64)-1)
+
+UInt64 Xz_GetUnpackSize(const CXzStream *p);
+UInt64 Xz_GetPackSize(const CXzStream *p);
+
+typedef struct
+{
+  size_t num;
+  size_t numAllocated;
+  CXzStream *streams;
+} CXzs;
+
+void Xzs_Construct(CXzs *p);
+void Xzs_Free(CXzs *p, ISzAllocPtr alloc);
+SRes Xzs_ReadBackward(CXzs *p, ILookInStream *inStream, Int64 *startOffset, ICompressProgress *progress, ISzAllocPtr alloc);
+
+UInt64 Xzs_GetNumBlocks(const CXzs *p);
+UInt64 Xzs_GetUnpackSize(const CXzs *p);
+
+
+// ECoderStatus values are identical to ELzmaStatus values of LZMA2 decoder
+
+typedef enum
+{
+  CODER_STATUS_NOT_SPECIFIED,               /* use main error code instead */
+  CODER_STATUS_FINISHED_WITH_MARK,          /* stream was finished with end mark. */
+  CODER_STATUS_NOT_FINISHED,                /* stream was not finished */
+  CODER_STATUS_NEEDS_MORE_INPUT             /* you must provide more input bytes */
+} ECoderStatus;
+
+
+// ECoderFinishMode values are identical to ELzmaFinishMode
+
+typedef enum
+{
+  CODER_FINISH_ANY,   /* finish at any point */
+  CODER_FINISH_END    /* block must be finished at the end */
+} ECoderFinishMode;
+
+
+typedef struct _IStateCoder
+{
+  void *p;
+  void (*Free)(void *p, ISzAllocPtr alloc);
+  SRes (*SetProps)(void *p, const Byte *props, size_t propSize, ISzAllocPtr alloc);
+  void (*Init)(void *p);
+  SRes (*Code2)(void *p, Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen,
+      int srcWasFinished, ECoderFinishMode finishMode,
+      // int *wasFinished,
+      ECoderStatus *status);
+  SizeT (*Filter)(void *p, Byte *data, SizeT size);
+} IStateCoder;
+
+
+
+#define MIXCODER_NUM_FILTERS_MAX 4
+
+typedef struct
+{
+  ISzAllocPtr alloc;
+  Byte *buf;
+  unsigned numCoders;
+
+  Byte *outBuf;
+  size_t outBufSize;
+  size_t outWritten; // is equal to lzmaDecoder.dicPos (in outBuf mode)
+  BoolInt wasFinished;
+  SRes res;
+  ECoderStatus status;
+  // BoolInt SingleBufMode;
+  
+  int finished[MIXCODER_NUM_FILTERS_MAX - 1];
+  size_t pos[MIXCODER_NUM_FILTERS_MAX - 1];
+  size_t size[MIXCODER_NUM_FILTERS_MAX - 1];
+  UInt64 ids[MIXCODER_NUM_FILTERS_MAX];
+  SRes results[MIXCODER_NUM_FILTERS_MAX];
+  IStateCoder coders[MIXCODER_NUM_FILTERS_MAX];
+} CMixCoder;
+
+
+typedef enum
+{
+  XZ_STATE_STREAM_HEADER,
+  XZ_STATE_STREAM_INDEX,
+  XZ_STATE_STREAM_INDEX_CRC,
+  XZ_STATE_STREAM_FOOTER,
+  XZ_STATE_STREAM_PADDING,
+  XZ_STATE_BLOCK_HEADER,
+  XZ_STATE_BLOCK,
+  XZ_STATE_BLOCK_FOOTER
+} EXzState;
+
+
+typedef struct
+{
+  EXzState state;
+  UInt32 pos;
+  unsigned alignPos;
+  unsigned indexPreSize;
+
+  CXzStreamFlags streamFlags;
+  
+  UInt32 blockHeaderSize;
+  UInt64 packSize;
+  UInt64 unpackSize;
+
+  UInt64 numBlocks; // number of finished blocks in current stream
+  UInt64 indexSize;
+  UInt64 indexPos;
+  UInt64 padSize;
+
+  UInt64 numStartedStreams;
+  UInt64 numFinishedStreams;
+  UInt64 numTotalBlocks;
+
+  UInt32 crc;
+  CMixCoder decoder;
+  CXzBlock block;
+  CXzCheck check;
+  CSha256 sha;
+
+  BoolInt parseMode;
+  BoolInt headerParsedOk;
+  BoolInt decodeToStreamSignature;
+  unsigned decodeOnlyOneBlock;
+
+  Byte *outBuf;
+  size_t outBufSize;
+  size_t outDataWritten; // the size of data in (outBuf) that were fully unpacked
+
+  Byte shaDigest[SHA256_DIGEST_SIZE];
+  Byte buf[XZ_BLOCK_HEADER_SIZE_MAX];
+} CXzUnpacker;
+
+/* alloc : aligned for cache line allocation is better */
+void XzUnpacker_Construct(CXzUnpacker *p, ISzAllocPtr alloc);
+void XzUnpacker_Init(CXzUnpacker *p);
+void XzUnpacker_SetOutBuf(CXzUnpacker *p, Byte *outBuf, size_t outBufSize);
+void XzUnpacker_Free(CXzUnpacker *p);
+
+/*
+  XzUnpacker
+  The sequence for decoding functions:
+  {
+    XzUnpacker_Construct()
+    [Decoding_Calls]
+    XzUnpacker_Free()
+  }
+
+  [Decoding_Calls]
+
+  There are 3 types of interfaces for [Decoding_Calls] calls:
+
+  Interface-1 : Partial output buffers:
+    {
+      XzUnpacker_Init()
+      for()
+      {
+        XzUnpacker_Code();
+      }
+      XzUnpacker_IsStreamWasFinished()
+    }
+    
+  Interface-2 : Direct output buffer:
+    Use it, if you know exact size of decoded data, and you need
+    whole xz unpacked data in one output buffer.
+    xz unpacker doesn't allocate additional buffer for lzma2 dictionary in that mode.
+    {
+      XzUnpacker_Init()
+      XzUnpacker_SetOutBufMode(); // to set output buffer and size
+      for()
+      {
+        XzUnpacker_Code(); // (dest = NULL) in XzUnpacker_Code()
+      }
+      XzUnpacker_IsStreamWasFinished()
+    }
+
+  Interface-3 : Direct output buffer : One call full decoding
+    It unpacks whole input buffer to output buffer in one call.
+    It uses Interface-2 internally.
+    {
+      XzUnpacker_CodeFull()
+      XzUnpacker_IsStreamWasFinished()
+    }
+*/
+
+/*
+finishMode:
+  It has meaning only if the decoding reaches output limit (*destLen).
+  CODER_FINISH_ANY - use smallest number of input bytes
+  CODER_FINISH_END - read EndOfStream marker after decoding
+
+Returns:
+  SZ_OK
+    status:
+      CODER_STATUS_NOT_FINISHED,
+      CODER_STATUS_NEEDS_MORE_INPUT - the decoder can return it in two cases:
+         1) it needs more input data to finish current xz stream
+         2) xz stream was finished successfully. But the decoder supports multiple
+            concatented xz streams. So it expects more input data for new xz streams.
+         Call XzUnpacker_IsStreamWasFinished() to check that latest xz stream was finished successfully.
+
+  SZ_ERROR_MEM  - Memory allocation error
+  SZ_ERROR_DATA - Data error
+  SZ_ERROR_UNSUPPORTED - Unsupported method or method properties
+  SZ_ERROR_CRC  - CRC error
+  // SZ_ERROR_INPUT_EOF - It needs more bytes in input buffer (src).
+
+  SZ_ERROR_NO_ARCHIVE - the error with xz Stream Header with one of the following reasons:
+     - xz Stream Signature failure
+     - CRC32 of xz Stream Header is failed
+     - The size of Stream padding is not multiple of four bytes.
+    It's possible to get that error, if xz stream was finished and the stream
+    contains some another data. In that case you can call XzUnpacker_GetExtraSize()
+    function to get real size of xz stream.
+*/
+
+
+SRes XzUnpacker_Code(CXzUnpacker *p, Byte *dest, SizeT *destLen,
+    const Byte *src, SizeT *srcLen, int srcFinished,
+    ECoderFinishMode finishMode, ECoderStatus *status);
+
+SRes XzUnpacker_CodeFull(CXzUnpacker *p, Byte *dest, SizeT *destLen,
+    const Byte *src, SizeT *srcLen,
+    ECoderFinishMode finishMode, ECoderStatus *status);
+
+/*
+If you decode full xz stream(s), then you can call XzUnpacker_IsStreamWasFinished()
+after successful XzUnpacker_CodeFull() or after last call of XzUnpacker_Code().
+*/
+
+BoolInt XzUnpacker_IsStreamWasFinished(const CXzUnpacker *p);
+
+/*
+XzUnpacker_GetExtraSize() returns then number of unconfirmed bytes,
+ if it's in (XZ_STATE_STREAM_HEADER) state or in (XZ_STATE_STREAM_PADDING) state.
+These bytes can be some data after xz archive, or
+it can be start of new xz stream.
+ 
+Call XzUnpacker_GetExtraSize() after XzUnpacker_Code() function to detect real size of
+xz stream in two cases, if XzUnpacker_Code() returns:
+  res == SZ_OK && status == CODER_STATUS_NEEDS_MORE_INPUT
+  res == SZ_ERROR_NO_ARCHIVE
+*/
+
+UInt64 XzUnpacker_GetExtraSize(const CXzUnpacker *p);
+
+
+/*
+  for random block decoding:
+    XzUnpacker_Init();
+    set CXzUnpacker::streamFlags
+    XzUnpacker_PrepareToRandomBlockDecoding()
+    loop
+    {
+      XzUnpacker_Code()
+      XzUnpacker_IsBlockFinished()
+    }
+*/
+
+void XzUnpacker_PrepareToRandomBlockDecoding(CXzUnpacker *p);
+BoolInt XzUnpacker_IsBlockFinished(const CXzUnpacker *p);
+
+#define XzUnpacker_GetPackSizeForIndex(p) ((p)->packSize + (p)->blockHeaderSize + XzFlags_GetCheckSize((p)->streamFlags))
+
+
+
+
+
+
+/* ---- Single-Thread and Multi-Thread xz Decoding with Input/Output Streams ---- */
+
+/*
+  if (CXzDecMtProps::numThreads > 1), the decoder can try to use
+  Multi-Threading. The decoder analyses xz block header, and if
+  there are pack size and unpack size values stored in xz block header,
+  the decoder reads compressed data of block to internal buffers,
+  and then it can start parallel decoding, if there are another blocks.
+  The decoder can switch back to Single-Thread decoding after some conditions.
+
+  The sequence of calls for xz decoding with in/out Streams:
+  {
+    XzDecMt_Create()
+    XzDecMtProps_Init(XzDecMtProps) to set default values of properties
+    // then you can change some XzDecMtProps parameters with required values
+    // here you can set the number of threads and (memUseMax) - the maximum
+    Memory usage for multithreading decoding.
+    for()
+    {
+      XzDecMt_Decode() // one call per one file
+    }
+    XzDecMt_Destroy()
+  }
+*/
+
+
+typedef struct
+{
+  size_t inBufSize_ST;    // size of input buffer for Single-Thread decoding
+  size_t outStep_ST;      // size of output buffer for Single-Thread decoding
+  BoolInt ignoreErrors;   // if set to 1, the decoder can ignore some errors and it skips broken parts of data.
+  
+  #ifndef _7ZIP_ST
+  unsigned numThreads;    // the number of threads for Multi-Thread decoding. if (umThreads == 1) it will use Single-thread decoding
+  size_t inBufSize_MT;    // size of small input data buffers for Multi-Thread decoding. Big number of such small buffers can be created
+  size_t memUseMax;       // the limit of total memory usage for Multi-Thread decoding.
+                          // it's recommended to set (memUseMax) manually to value that is smaller of total size of RAM in computer.
+  #endif
+} CXzDecMtProps;
+
+void XzDecMtProps_Init(CXzDecMtProps *p);
+
+
+typedef void * CXzDecMtHandle;
+
+/*
+  alloc    : XzDecMt uses CAlignOffsetAlloc internally for addresses allocated by (alloc).
+  allocMid : for big allocations, aligned allocation is better
+*/
+
+CXzDecMtHandle XzDecMt_Create(ISzAllocPtr alloc, ISzAllocPtr allocMid);
+void XzDecMt_Destroy(CXzDecMtHandle p);
+
+
+typedef struct
+{
+  Byte UnpackSize_Defined;
+  Byte NumStreams_Defined;
+  Byte NumBlocks_Defined;
+
+  Byte DataAfterEnd;      // there are some additional data after good xz streams, and that data is not new xz stream.
+  Byte DecodingTruncated; // Decoding was Truncated, we need only partial output data
+
+  UInt64 InSize;          // pack size processed. That value doesn't include the data after
+                          // end of xz stream, if that data was not correct
+  UInt64 OutSize;
+
+  UInt64 NumStreams;
+  UInt64 NumBlocks;
+
+  SRes DecodeRes;         // the error code of xz streams data decoding
+  SRes ReadRes;           // error code from ISeqInStream:Read()
+  SRes ProgressRes;       // error code from ICompressProgress:Progress()
+
+  SRes CombinedRes;       // Combined result error code that shows main rusult
+                          // = S_OK, if there is no error.
+                          // but check also (DataAfterEnd) that can show additional minor errors.
+ 
+  SRes CombinedRes_Type;  // = SZ_ERROR_READ,     if error from ISeqInStream
+                          // = SZ_ERROR_PROGRESS, if error from ICompressProgress
+                          // = SZ_ERROR_WRITE,    if error from ISeqOutStream
+                          // = SZ_ERROR_* codes for decoding
+} CXzStatInfo;
+
+void XzStatInfo_Clear(CXzStatInfo *p);
+
+/*
+
+XzDecMt_Decode()
+SRes: it's combined decoding result. It also is equal to stat->CombinedRes.
+
+  SZ_OK               - no error
+                        check also output value in (stat->DataAfterEnd)
+                        that can show additional possible error
+
+  SZ_ERROR_MEM        - Memory allocation error
+  SZ_ERROR_NO_ARCHIVE - is not xz archive
+  SZ_ERROR_ARCHIVE    - Headers error
+  SZ_ERROR_DATA       - Data Error
+  SZ_ERROR_UNSUPPORTED - Unsupported method or method properties
+  SZ_ERROR_CRC        - CRC Error
+  SZ_ERROR_INPUT_EOF  - it needs more input data
+  SZ_ERROR_WRITE      - ISeqOutStream error
+  (SZ_ERROR_READ)     - ISeqInStream errors
+  (SZ_ERROR_PROGRESS) - ICompressProgress errors
+  // SZ_ERROR_THREAD     - error in multi-threading functions
+  MY_SRes_HRESULT_FROM_WRes(WRes_error) - error in multi-threading function
+*/
+
+SRes XzDecMt_Decode(CXzDecMtHandle p,
+    const CXzDecMtProps *props,
+    const UInt64 *outDataSize, // NULL means undefined
+    int finishMode,            // 0 - partial unpacking is allowed, 1 - xz stream(s) must be finished
+    ISeqOutStream *outStream,
+    // Byte *outBuf, size_t *outBufSize,
+    ISeqInStream *inStream,
+    // const Byte *inData, size_t inDataSize,
+    CXzStatInfo *stat,         // out: decoding results and statistics
+    int *isMT,                 // out: 0 means that ST (Single-Thread) version was used
+                               //      1 means that MT (Multi-Thread) version was used
+    ICompressProgress *progress);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/XzCrc64.h

@@ -0,0 +1,26 @@
+/* XzCrc64.h -- CRC64 calculation
+2013-01-18 : Igor Pavlov : Public domain */
+
+#ifndef __XZ_CRC64_H
+#define __XZ_CRC64_H
+
+#include <stddef.h>
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+extern UInt64 g_Crc64Table[];
+
+void MY_FAST_CALL Crc64GenerateTable(void);
+
+#define CRC64_INIT_VAL UINT64_CONST(0xFFFFFFFFFFFFFFFF)
+#define CRC64_GET_DIGEST(crc) ((crc) ^ CRC64_INIT_VAL)
+#define CRC64_UPDATE_BYTE(crc, b) (g_Crc64Table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+
+UInt64 MY_FAST_CALL Crc64Update(UInt64 crc, const void *data, size_t size);
+UInt64 MY_FAST_CALL Crc64Calc(const void *data, size_t size);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/include/XzEnc.h

@@ -0,0 +1,60 @@
+/* XzEnc.h -- Xz Encode
+2017-06-27 : Igor Pavlov : Public domain */
+
+#ifndef __XZ_ENC_H
+#define __XZ_ENC_H
+
+#include "Lzma2Enc.h"
+
+#include "Xz.h"
+
+EXTERN_C_BEGIN
+
+
+#define XZ_PROPS__BLOCK_SIZE__AUTO   LZMA2_ENC_PROPS__BLOCK_SIZE__AUTO
+#define XZ_PROPS__BLOCK_SIZE__SOLID  LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID
+
+
+typedef struct
+{
+  UInt32 id;
+  UInt32 delta;
+  UInt32 ip;
+  int ipDefined;
+} CXzFilterProps;
+
+void XzFilterProps_Init(CXzFilterProps *p);
+
+
+typedef struct
+{
+  CLzma2EncProps lzma2Props;
+  CXzFilterProps filterProps;
+  unsigned checkId;
+  UInt64 blockSize;
+  int numBlockThreads_Reduced;
+  int numBlockThreads_Max;
+  int numTotalThreads;
+  int forceWriteSizesInHeader;
+  UInt64 reduceSize;
+} CXzProps;
+
+void XzProps_Init(CXzProps *p);
+
+
+typedef void * CXzEncHandle;
+
+CXzEncHandle XzEnc_Create(ISzAllocPtr alloc, ISzAllocPtr allocBig);
+void XzEnc_Destroy(CXzEncHandle p);
+SRes XzEnc_SetProps(CXzEncHandle p, const CXzProps *props);
+void XzEnc_SetDataSize(CXzEncHandle p, UInt64 expectedDataSiize);
+SRes XzEnc_Encode(CXzEncHandle p, ISeqOutStream *outStream, ISeqInStream *inStream, ICompressProgress *progress);
+
+SRes Xz_Encode(ISeqOutStream *outStream, ISeqInStream *inStream,
+    const CXzProps *props, ICompressProgress *progress);
+
+SRes Xz_EncodeEmpty(ISeqOutStream *outStream);
+
+EXTERN_C_END
+
+#endif

3rdparty/lzma/lzma.vcxproj

@@ -0,0 +1,112 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <Import Project="$(SolutionDir)common\vsprops\BaseProjectConfig.props" />
+  <Import Project="$(SolutionDir)common\vsprops\WinSDK.props" />
+  <PropertyGroup Label="Globals">
+    <ProjectGuid>{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}</ProjectGuid>
+  </PropertyGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+  <PropertyGroup Label="Configuration">
+    <ConfigurationType>StaticLibrary</ConfigurationType>
+    <PlatformToolset>$(DefaultPlatformToolset)</PlatformToolset>
+    <CharacterSet>MultiByte</CharacterSet>
+    <WholeProgramOptimization Condition="$(Configuration.Contains(Release))">true</WholeProgramOptimization>
+    <UseDebugLibraries Condition="$(Configuration.Contains(Debug))">true</UseDebugLibraries>
+    <UseDebugLibraries Condition="!$(Configuration.Contains(Debug))">false</UseDebugLibraries>
+  </PropertyGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+  <ImportGroup Label="ExtensionSettings" />
+  <ImportGroup Label="PropertySheets">
+    <Import Project="..\DefaultProjectRootDir.props" />
+    <Import Project="..\3rdparty.props" />
+    <Import Condition="$(Configuration.Contains(Debug))" Project="..\..\common\vsprops\CodeGen_Debug.props" />
+    <Import Condition="$(Configuration.Contains(Devel))" Project="..\..\common\vsprops\CodeGen_Devel.props" />
+    <Import Condition="$(Configuration.Contains(Release))" Project="..\..\common\vsprops\CodeGen_Release.props" />
+    <Import Condition="!$(Configuration.Contains(Release))" Project="..\..\common\vsprops\IncrementalLinking.props" />
+  </ImportGroup>
+  <PropertyGroup Label="UserMacros" />
+  <PropertyGroup>
+    <CodeAnalysisRuleSet>AllRules.ruleset</CodeAnalysisRuleSet>
+  </PropertyGroup>
+  <ItemGroup>
+    <ClCompile Include="src\7zAlloc.c" />
+    <ClCompile Include="src\7zArcIn.c" />
+    <ClCompile Include="src\7zBuf.c" />
+    <ClCompile Include="src\7zBuf2.c" />
+    <ClCompile Include="src\7zCrc.c" />
+    <ClCompile Include="src\7zCrcOpt.c" />
+    <ClCompile Include="src\7zDec.c" />
+    <ClCompile Include="src\7zFile.c" />
+    <ClCompile Include="src\7zStream.c" />
+    <ClCompile Include="src\Alloc.c" />
+    <ClCompile Include="src\Bcj2.c" />
+    <ClCompile Include="src\Bcj2Enc.c" />
+    <ClCompile Include="src\Bra.c" />
+    <ClCompile Include="src\Bra86.c" />
+    <ClCompile Include="src\BraIA64.c" />
+    <ClCompile Include="src\CpuArch.c" />
+    <ClCompile Include="src\Delta.c" />
+    <ClCompile Include="src\LzFind.c" />
+    <ClCompile Include="src\LzFindOpt.c" />
+    <ClCompile Include="src\Lzma2Dec.c" />
+    <ClCompile Include="src\Lzma2DecMt.c" />
+    <ClCompile Include="src\Lzma2Enc.c" />
+    <ClCompile Include="src\Lzma86Dec.c" />
+    <ClCompile Include="src\Lzma86Enc.c" />
+    <ClCompile Include="src\LzmaDec.c" />
+    <ClCompile Include="src\LzmaEnc.c" />
+    <ClCompile Include="src\LzmaLib.c" />
+    <ClCompile Include="src\Ppmd7.c" />
+    <ClCompile Include="src\Ppmd7Dec.c" />
+    <ClCompile Include="src\Ppmd7Enc.c" />
+    <ClCompile Include="src\Sha256.c" />
+    <ClCompile Include="src\Sha256Opt.c" />
+    <ClCompile Include="src\Xz.c" />
+    <ClCompile Include="src\XzCrc64.c" />
+    <ClCompile Include="src\XzCrc64Opt.c" />
+    <ClCompile Include="src\XzDec.c" />
+    <ClCompile Include="src\XzEnc.c" />
+    <ClCompile Include="src\XzIn.c" />
+  </ItemGroup>
+  <ItemGroup>
+    <ClInclude Include="include\7z.h" />
+    <ClInclude Include="include\7zAlloc.h" />
+    <ClInclude Include="include\7zBuf.h" />
+    <ClInclude Include="include\7zCrc.h" />
+    <ClInclude Include="include\7zFile.h" />
+    <ClInclude Include="include\7zTypes.h" />
+    <ClInclude Include="include\7zVersion.h" />
+    <ClInclude Include="include\Alloc.h" />
+    <ClInclude Include="include\Bcj2.h" />
+    <ClInclude Include="include\Bra.h" />
+    <ClInclude Include="include\Compiler.h" />
+    <ClInclude Include="include\CpuArch.h" />
+    <ClInclude Include="include\Delta.h" />
+    <ClInclude Include="include\LzFind.h" />
+    <ClInclude Include="include\LzHash.h" />
+    <ClInclude Include="include\Lzma2Dec.h" />
+    <ClInclude Include="include\Lzma2DecMt.h" />
+    <ClInclude Include="include\Lzma2Enc.h" />
+    <ClInclude Include="include\Lzma86.h" />
+    <ClInclude Include="include\LzmaDec.h" />
+    <ClInclude Include="include\LzmaEnc.h" />
+    <ClInclude Include="include\LzmaLib.h" />
+    <ClInclude Include="include\Ppmd.h" />
+    <ClInclude Include="include\Ppmd7.h" />
+    <ClInclude Include="include\Precomp.h" />
+    <ClInclude Include="include\RotateDefs.h" />
+    <ClInclude Include="include\Sha256.h" />
+    <ClInclude Include="include\Xz.h" />
+    <ClInclude Include="include\XzCrc64.h" />
+    <ClInclude Include="include\XzEnc.h" />
+  </ItemGroup>
+  <ItemDefinitionGroup>
+    <ClCompile>
+      <PreprocessorDefinitions>_7ZIP_ST;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <WarningLevel>TurnOffAllWarnings</WarningLevel>
+      <AdditionalIncludeDirectories>$(SolutionDir)3rdparty\lzma\include;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+    </ClCompile>
+  </ItemDefinitionGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+  <ImportGroup Label="ExtensionTargets" />
+</Project>

3rdparty/lzma/lzma.vcxproj.filters

@@ -0,0 +1,75 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <ItemGroup>
+    <ClCompile Include="src\Alloc.c" />
+    <ClCompile Include="src\Bcj2.c" />
+    <ClCompile Include="src\Bcj2Enc.c" />
+    <ClCompile Include="src\Bra.c" />
+    <ClCompile Include="src\Bra86.c" />
+    <ClCompile Include="src\BraIA64.c" />
+    <ClCompile Include="src\CpuArch.c" />
+    <ClCompile Include="src\Delta.c" />
+    <ClCompile Include="src\LzFind.c" />
+    <ClCompile Include="src\Lzma2Dec.c" />
+    <ClCompile Include="src\Lzma2DecMt.c" />
+    <ClCompile Include="src\Lzma2Enc.c" />
+    <ClCompile Include="src\Lzma86Dec.c" />
+    <ClCompile Include="src\Lzma86Enc.c" />
+    <ClCompile Include="src\LzmaDec.c" />
+    <ClCompile Include="src\LzmaEnc.c" />
+    <ClCompile Include="src\LzmaLib.c" />
+    <ClCompile Include="src\Ppmd7.c" />
+    <ClCompile Include="src\Ppmd7Dec.c" />
+    <ClCompile Include="src\Ppmd7Enc.c" />
+    <ClCompile Include="src\Sha256.c" />
+    <ClCompile Include="src\Xz.c" />
+    <ClCompile Include="src\XzCrc64.c" />
+    <ClCompile Include="src\XzCrc64Opt.c" />
+    <ClCompile Include="src\XzDec.c" />
+    <ClCompile Include="src\XzEnc.c" />
+    <ClCompile Include="src\XzIn.c" />
+    <ClCompile Include="src\7zAlloc.c" />
+    <ClCompile Include="src\7zArcIn.c" />
+    <ClCompile Include="src\7zBuf.c" />
+    <ClCompile Include="src\7zBuf2.c" />
+    <ClCompile Include="src\7zCrc.c" />
+    <ClCompile Include="src\7zCrcOpt.c" />
+    <ClCompile Include="src\7zDec.c" />
+    <ClCompile Include="src\7zFile.c" />
+    <ClCompile Include="src\7zStream.c" />
+    <ClCompile Include="src\LzFindOpt.c" />
+    <ClCompile Include="src\Sha256Opt.c" />
+  </ItemGroup>
+  <ItemGroup>
+    <ClInclude Include="include\Alloc.h" />
+    <ClInclude Include="include\Bcj2.h" />
+    <ClInclude Include="include\Bra.h" />
+    <ClInclude Include="include\Compiler.h" />
+    <ClInclude Include="include\CpuArch.h" />
+    <ClInclude Include="include\Delta.h" />
+    <ClInclude Include="include\LzFind.h" />
+    <ClInclude Include="include\LzHash.h" />
+    <ClInclude Include="include\Lzma2Dec.h" />
+    <ClInclude Include="include\Lzma2DecMt.h" />
+    <ClInclude Include="include\Lzma2Enc.h" />
+    <ClInclude Include="include\Lzma86.h" />
+    <ClInclude Include="include\LzmaDec.h" />
+    <ClInclude Include="include\LzmaEnc.h" />
+    <ClInclude Include="include\LzmaLib.h" />
+    <ClInclude Include="include\Ppmd.h" />
+    <ClInclude Include="include\Ppmd7.h" />
+    <ClInclude Include="include\Precomp.h" />
+    <ClInclude Include="include\RotateDefs.h" />
+    <ClInclude Include="include\Sha256.h" />
+    <ClInclude Include="include\Xz.h" />
+    <ClInclude Include="include\XzCrc64.h" />
+    <ClInclude Include="include\XzEnc.h" />
+    <ClInclude Include="include\7z.h" />
+    <ClInclude Include="include\7zAlloc.h" />
+    <ClInclude Include="include\7zBuf.h" />
+    <ClInclude Include="include\7zCrc.h" />
+    <ClInclude Include="include\7zFile.h" />
+    <ClInclude Include="include\7zTypes.h" />
+    <ClInclude Include="include\7zVersion.h" />
+  </ItemGroup>
+</Project>

3rdparty/lzma/src/7zAlloc.c

@@ -0,0 +1,80 @@
+/* 7zAlloc.c -- Allocation functions
+2017-04-03 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <stdlib.h>
+
+#include "7zAlloc.h"
+
+/* #define _SZ_ALLOC_DEBUG */
+/* use _SZ_ALLOC_DEBUG to debug alloc/free operations */
+
+#ifdef _SZ_ALLOC_DEBUG
+
+#ifdef _WIN32
+#include <windows.h>
+#endif
+
+#include <stdio.h>
+int g_allocCount = 0;
+int g_allocCountTemp = 0;
+
+#endif
+
+void *SzAlloc(ISzAllocPtr p, size_t size)
+{
+  UNUSED_VAR(p);
+  if (size == 0)
+    return 0;
+  #ifdef _SZ_ALLOC_DEBUG
+  fprintf(stderr, "\nAlloc %10u bytes; count = %10d", (unsigned)size, g_allocCount);
+  g_allocCount++;
+  #endif
+  return malloc(size);
+}
+
+void SzFree(ISzAllocPtr p, void *address)
+{
+  UNUSED_VAR(p);
+  #ifdef _SZ_ALLOC_DEBUG
+  if (address != 0)
+  {
+    g_allocCount--;
+    fprintf(stderr, "\nFree; count = %10d", g_allocCount);
+  }
+  #endif
+  free(address);
+}
+
+void *SzAllocTemp(ISzAllocPtr p, size_t size)
+{
+  UNUSED_VAR(p);
+  if (size == 0)
+    return 0;
+  #ifdef _SZ_ALLOC_DEBUG
+  fprintf(stderr, "\nAlloc_temp %10u bytes;  count = %10d", (unsigned)size, g_allocCountTemp);
+  g_allocCountTemp++;
+  #ifdef _WIN32
+  return HeapAlloc(GetProcessHeap(), 0, size);
+  #endif
+  #endif
+  return malloc(size);
+}
+
+void SzFreeTemp(ISzAllocPtr p, void *address)
+{
+  UNUSED_VAR(p);
+  #ifdef _SZ_ALLOC_DEBUG
+  if (address != 0)
+  {
+    g_allocCountTemp--;
+    fprintf(stderr, "\nFree_temp; count = %10d", g_allocCountTemp);
+  }
+  #ifdef _WIN32
+  HeapFree(GetProcessHeap(), 0, address);
+  return;
+  #endif
+  #endif
+  free(address);
+}

3rdparty/lzma/src/7zBuf.c

@@ -0,0 +1,36 @@
+/* 7zBuf.c -- Byte Buffer
+2017-04-03 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "7zBuf.h"
+
+void Buf_Init(CBuf *p)
+{
+  p->data = 0;
+  p->size = 0;
+}
+
+int Buf_Create(CBuf *p, size_t size, ISzAllocPtr alloc)
+{
+  p->size = 0;
+  if (size == 0)
+  {
+    p->data = 0;
+    return 1;
+  }
+  p->data = (Byte *)ISzAlloc_Alloc(alloc, size);
+  if (p->data)
+  {
+    p->size = size;
+    return 1;
+  }
+  return 0;
+}
+
+void Buf_Free(CBuf *p, ISzAllocPtr alloc)
+{
+  ISzAlloc_Free(alloc, p->data);
+  p->data = 0;
+  p->size = 0;
+}

3rdparty/lzma/src/7zBuf2.c

@@ -0,0 +1,52 @@
+/* 7zBuf2.c -- Byte Buffer
+2017-04-03 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "7zBuf.h"
+
+void DynBuf_Construct(CDynBuf *p)
+{
+  p->data = 0;
+  p->size = 0;
+  p->pos = 0;
+}
+
+void DynBuf_SeekToBeg(CDynBuf *p)
+{
+  p->pos = 0;
+}
+
+int DynBuf_Write(CDynBuf *p, const Byte *buf, size_t size, ISzAllocPtr alloc)
+{
+  if (size > p->size - p->pos)
+  {
+    size_t newSize = p->pos + size;
+    Byte *data;
+    newSize += newSize / 4;
+    data = (Byte *)ISzAlloc_Alloc(alloc, newSize);
+    if (!data)
+      return 0;
+    p->size = newSize;
+    if (p->pos != 0)
+      memcpy(data, p->data, p->pos);
+    ISzAlloc_Free(alloc, p->data);
+    p->data = data;
+  }
+  if (size != 0)
+  {
+    memcpy(p->data + p->pos, buf, size);
+    p->pos += size;
+  }
+  return 1;
+}
+
+void DynBuf_Free(CDynBuf *p, ISzAllocPtr alloc)
+{
+  ISzAlloc_Free(alloc, p->data);
+  p->data = 0;
+  p->size = 0;
+  p->pos = 0;
+}

3rdparty/lzma/src/7zCrc.c

@@ -0,0 +1,322 @@
+/* 7zCrc.c -- CRC32 init
+2021-04-01 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "7zCrc.h"
+#include "CpuArch.h"
+
+#define kCrcPoly 0xEDB88320
+
+#ifdef MY_CPU_LE
+  #define CRC_NUM_TABLES 8
+#else
+  #define CRC_NUM_TABLES 9
+
+  #define CRC_UINT32_SWAP(v) ((v >> 24) | ((v >> 8) & 0xFF00) | ((v << 8) & 0xFF0000) | (v << 24))
+
+  UInt32 MY_FAST_CALL CrcUpdateT1_BeT4(UInt32 v, const void *data, size_t size, const UInt32 *table);
+  UInt32 MY_FAST_CALL CrcUpdateT1_BeT8(UInt32 v, const void *data, size_t size, const UInt32 *table);
+#endif
+
+#ifndef MY_CPU_BE
+  UInt32 MY_FAST_CALL CrcUpdateT4(UInt32 v, const void *data, size_t size, const UInt32 *table);
+  UInt32 MY_FAST_CALL CrcUpdateT8(UInt32 v, const void *data, size_t size, const UInt32 *table);
+#endif
+
+typedef UInt32 (MY_FAST_CALL *CRC_FUNC)(UInt32 v, const void *data, size_t size, const UInt32 *table);
+
+extern
+CRC_FUNC g_CrcUpdateT4;
+CRC_FUNC g_CrcUpdateT4;
+extern
+CRC_FUNC g_CrcUpdateT8;
+CRC_FUNC g_CrcUpdateT8;
+extern
+CRC_FUNC g_CrcUpdateT0_32;
+CRC_FUNC g_CrcUpdateT0_32;
+extern
+CRC_FUNC g_CrcUpdateT0_64;
+CRC_FUNC g_CrcUpdateT0_64;
+extern
+CRC_FUNC g_CrcUpdate;
+CRC_FUNC g_CrcUpdate;
+
+UInt32 g_CrcTable[256 * CRC_NUM_TABLES];
+
+UInt32 MY_FAST_CALL CrcUpdate(UInt32 v, const void *data, size_t size)
+{
+  return g_CrcUpdate(v, data, size, g_CrcTable);
+}
+
+UInt32 MY_FAST_CALL CrcCalc(const void *data, size_t size)
+{
+  return g_CrcUpdate(CRC_INIT_VAL, data, size, g_CrcTable) ^ CRC_INIT_VAL;
+}
+
+#define CRC_UPDATE_BYTE_2(crc, b) (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+
+UInt32 MY_FAST_CALL CrcUpdateT1(UInt32 v, const void *data, size_t size, const UInt32 *table);
+UInt32 MY_FAST_CALL CrcUpdateT1(UInt32 v, const void *data, size_t size, const UInt32 *table)
+{
+  const Byte *p = (const Byte *)data;
+  const Byte *pEnd = p + size;
+  for (; p != pEnd; p++)
+    v = CRC_UPDATE_BYTE_2(v, *p);
+  return v;
+}
+
+
+/* ---------- hardware CRC ---------- */
+
+#ifdef MY_CPU_LE
+
+#if defined(MY_CPU_ARM_OR_ARM64)
+
+// #pragma message("ARM*")
+
+  #if defined(_MSC_VER)
+    #if defined(MY_CPU_ARM64)
+    #if (_MSC_VER >= 1910)
+        #define USE_ARM64_CRC
+    #endif
+    #endif
+  #elif (defined(__clang__) && (__clang_major__ >= 3)) \
+     || (defined(__GNUC__) && (__GNUC__ > 4))
+      #if !defined(__ARM_FEATURE_CRC32)
+        #define __ARM_FEATURE_CRC32 1
+          #if (!defined(__clang__) || (__clang_major__ > 3)) // fix these numbers
+            #define ATTRIB_CRC __attribute__((__target__("arch=armv8-a+crc")))
+          #endif
+      #endif
+      #if defined(__ARM_FEATURE_CRC32)
+        #define USE_ARM64_CRC
+        #include <arm_acle.h>
+      #endif
+  #endif
+
+#else
+
+// no hardware CRC
+
+// #define USE_CRC_EMU
+
+#ifdef USE_CRC_EMU
+
+#pragma message("ARM64 CRC emulation")
+
+MY_FORCE_INLINE
+UInt32 __crc32b(UInt32 v, UInt32 data)
+{
+  const UInt32 *table = g_CrcTable;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data);
+  return v;
+}
+
+MY_FORCE_INLINE
+UInt32 __crc32w(UInt32 v, UInt32 data)
+{
+  const UInt32 *table = g_CrcTable;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
+  return v;
+}
+
+MY_FORCE_INLINE
+UInt32 __crc32d(UInt32 v, UInt64 data)
+{
+  const UInt32 *table = g_CrcTable;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
+  v = CRC_UPDATE_BYTE_2(v, (Byte)data); data >>= 8;
+  return v;
+}
+
+#endif // USE_CRC_EMU
+
+#endif // defined(MY_CPU_ARM64) && defined(MY_CPU_LE)
+
+
+
+#if defined(USE_ARM64_CRC) || defined(USE_CRC_EMU)
+
+#define T0_32_UNROLL_BYTES (4 * 4)
+#define T0_64_UNROLL_BYTES (4 * 8)
+
+#ifndef ATTRIB_CRC
+#define ATTRIB_CRC
+#endif
+// #pragma message("USE ARM HW CRC")
+
+ATTRIB_CRC
+UInt32 MY_FAST_CALL CrcUpdateT0_32(UInt32 v, const void *data, size_t size, const UInt32 *table);
+ATTRIB_CRC
+UInt32 MY_FAST_CALL CrcUpdateT0_32(UInt32 v, const void *data, size_t size, const UInt32 *table)
+{
+  const Byte *p = (const Byte *)data;
+  UNUSED_VAR(table);
+
+  for (; size != 0 && ((unsigned)(ptrdiff_t)p & (T0_32_UNROLL_BYTES - 1)) != 0; size--)
+    v = __crc32b(v, *p++);
+
+  if (size >= T0_32_UNROLL_BYTES)
+  {
+    const Byte *lim = p + size;
+    size &= (T0_32_UNROLL_BYTES - 1);
+    lim -= size;
+    do
+    {
+      v = __crc32w(v, *(const UInt32 *)(const void *)(p));
+      v = __crc32w(v, *(const UInt32 *)(const void *)(p + 4)); p += 2 * 4;
+      v = __crc32w(v, *(const UInt32 *)(const void *)(p));
+      v = __crc32w(v, *(const UInt32 *)(const void *)(p + 4)); p += 2 * 4;
+    }
+    while (p != lim);
+  }
+  
+  for (; size != 0; size--)
+    v = __crc32b(v, *p++);
+
+  return v;
+}
+
+ATTRIB_CRC
+UInt32 MY_FAST_CALL CrcUpdateT0_64(UInt32 v, const void *data, size_t size, const UInt32 *table);
+ATTRIB_CRC
+UInt32 MY_FAST_CALL CrcUpdateT0_64(UInt32 v, const void *data, size_t size, const UInt32 *table)
+{
+  const Byte *p = (const Byte *)data;
+  UNUSED_VAR(table);
+
+  for (; size != 0 && ((unsigned)(ptrdiff_t)p & (T0_64_UNROLL_BYTES - 1)) != 0; size--)
+    v = __crc32b(v, *p++);
+
+  if (size >= T0_64_UNROLL_BYTES)
+  {
+    const Byte *lim = p + size;
+    size &= (T0_64_UNROLL_BYTES - 1);
+    lim -= size;
+    do
+    {
+      v = __crc32d(v, *(const UInt64 *)(const void *)(p));
+      v = __crc32d(v, *(const UInt64 *)(const void *)(p + 8)); p += 2 * 8;
+      v = __crc32d(v, *(const UInt64 *)(const void *)(p));
+      v = __crc32d(v, *(const UInt64 *)(const void *)(p + 8)); p += 2 * 8;
+    }
+    while (p != lim);
+  }
+  
+  for (; size != 0; size--)
+    v = __crc32b(v, *p++);
+
+  return v;
+}
+
+#endif // defined(USE_ARM64_CRC) || defined(USE_CRC_EMU)
+
+#endif // MY_CPU_LE
+
+
+
+
+void MY_FAST_CALL CrcGenerateTable()
+{
+  UInt32 i;
+  for (i = 0; i < 256; i++)
+  {
+    UInt32 r = i;
+    unsigned j;
+    for (j = 0; j < 8; j++)
+      r = (r >> 1) ^ (kCrcPoly & ((UInt32)0 - (r & 1)));
+    g_CrcTable[i] = r;
+  }
+  for (i = 256; i < 256 * CRC_NUM_TABLES; i++)
+  {
+    UInt32 r = g_CrcTable[(size_t)i - 256];
+    g_CrcTable[i] = g_CrcTable[r & 0xFF] ^ (r >> 8);
+  }
+
+  #if CRC_NUM_TABLES < 4
+  
+  g_CrcUpdate = CrcUpdateT1;
+  
+  #else
+ 
+  #ifdef MY_CPU_LE
+
+    g_CrcUpdateT4 = CrcUpdateT4;
+    g_CrcUpdate = CrcUpdateT4;
+
+    #if CRC_NUM_TABLES >= 8
+      g_CrcUpdateT8 = CrcUpdateT8;
+  
+      #ifdef MY_CPU_X86_OR_AMD64
+      if (!CPU_Is_InOrder())
+      #endif
+        g_CrcUpdate = CrcUpdateT8;
+    #endif
+
+  #else
+  {
+    #ifndef MY_CPU_BE
+    UInt32 k = 0x01020304;
+    const Byte *p = (const Byte *)&k;
+    if (p[0] == 4 && p[1] == 3)
+    {
+      g_CrcUpdateT4 = CrcUpdateT4;
+      g_CrcUpdate = CrcUpdateT4;
+      #if CRC_NUM_TABLES >= 8
+      g_CrcUpdateT8 = CrcUpdateT8;
+      g_CrcUpdate = CrcUpdateT8;
+      #endif
+    }
+    else if (p[0] != 1 || p[1] != 2)
+      g_CrcUpdate = CrcUpdateT1;
+    else
+    #endif
+    {
+      for (i = 256 * CRC_NUM_TABLES - 1; i >= 256; i--)
+      {
+        UInt32 x = g_CrcTable[(size_t)i - 256];
+        g_CrcTable[i] = CRC_UINT32_SWAP(x);
+      }
+      g_CrcUpdateT4 = CrcUpdateT1_BeT4;
+      g_CrcUpdate = CrcUpdateT1_BeT4;
+      #if CRC_NUM_TABLES >= 8
+      g_CrcUpdateT8 = CrcUpdateT1_BeT8;
+      g_CrcUpdate = CrcUpdateT1_BeT8;
+      #endif
+    }
+  }
+  #endif
+  #endif
+
+  #ifdef MY_CPU_LE
+    #ifdef USE_ARM64_CRC
+      if (CPU_IsSupported_CRC32())
+      {
+        g_CrcUpdateT0_32 = CrcUpdateT0_32;
+        g_CrcUpdateT0_64 = CrcUpdateT0_64;
+        g_CrcUpdate =
+          #if defined(MY_CPU_ARM)
+            CrcUpdateT0_32;
+          #else
+            CrcUpdateT0_64;
+          #endif
+      }
+    #endif
+    
+    #ifdef USE_CRC_EMU
+      g_CrcUpdateT0_32 = CrcUpdateT0_32;
+      g_CrcUpdateT0_64 = CrcUpdateT0_64;
+      g_CrcUpdate = CrcUpdateT0_64;
+    #endif
+  #endif
+}

3rdparty/lzma/src/7zCrcOpt.c

@@ -0,0 +1,117 @@
+/* 7zCrcOpt.c -- CRC32 calculation
+2021-02-09 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+
+#ifndef MY_CPU_BE
+
+#define CRC_UPDATE_BYTE_2(crc, b) (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+
+UInt32 MY_FAST_CALL CrcUpdateT4(UInt32 v, const void *data, size_t size, const UInt32 *table);
+UInt32 MY_FAST_CALL CrcUpdateT4(UInt32 v, const void *data, size_t size, const UInt32 *table)
+{
+  const Byte *p = (const Byte *)data;
+  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 3) != 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2(v, *p);
+  for (; size >= 4; size -= 4, p += 4)
+  {
+    v ^= *(const UInt32 *)(const void *)p;
+    v =
+          (table + 0x300)[((v      ) & 0xFF)]
+        ^ (table + 0x200)[((v >>  8) & 0xFF)]
+        ^ (table + 0x100)[((v >> 16) & 0xFF)]
+        ^ (table + 0x000)[((v >> 24))];
+  }
+  for (; size > 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2(v, *p);
+  return v;
+}
+
+UInt32 MY_FAST_CALL CrcUpdateT8(UInt32 v, const void *data, size_t size, const UInt32 *table);
+UInt32 MY_FAST_CALL CrcUpdateT8(UInt32 v, const void *data, size_t size, const UInt32 *table)
+{
+  const Byte *p = (const Byte *)data;
+  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 7) != 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2(v, *p);
+  for (; size >= 8; size -= 8, p += 8)
+  {
+    UInt32 d;
+    v ^= *(const UInt32 *)(const void *)p;
+    v =
+          (table + 0x700)[((v      ) & 0xFF)]
+        ^ (table + 0x600)[((v >>  8) & 0xFF)]
+        ^ (table + 0x500)[((v >> 16) & 0xFF)]
+        ^ (table + 0x400)[((v >> 24))];
+    d = *((const UInt32 *)(const void *)p + 1);
+    v ^=
+          (table + 0x300)[((d      ) & 0xFF)]
+        ^ (table + 0x200)[((d >>  8) & 0xFF)]
+        ^ (table + 0x100)[((d >> 16) & 0xFF)]
+        ^ (table + 0x000)[((d >> 24))];
+  }
+  for (; size > 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2(v, *p);
+  return v;
+}
+
+#endif
+
+
+#ifndef MY_CPU_LE
+
+#define CRC_UINT32_SWAP(v) ((v >> 24) | ((v >> 8) & 0xFF00) | ((v << 8) & 0xFF0000) | (v << 24))
+
+#define CRC_UPDATE_BYTE_2_BE(crc, b) (table[(((crc) >> 24) ^ (b))] ^ ((crc) << 8))
+
+UInt32 MY_FAST_CALL CrcUpdateT1_BeT4(UInt32 v, const void *data, size_t size, const UInt32 *table)
+{
+  const Byte *p = (const Byte *)data;
+  table += 0x100;
+  v = CRC_UINT32_SWAP(v);
+  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 3) != 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2_BE(v, *p);
+  for (; size >= 4; size -= 4, p += 4)
+  {
+    v ^= *(const UInt32 *)(const void *)p;
+    v =
+          (table + 0x000)[((v      ) & 0xFF)]
+        ^ (table + 0x100)[((v >>  8) & 0xFF)]
+        ^ (table + 0x200)[((v >> 16) & 0xFF)]
+        ^ (table + 0x300)[((v >> 24))];
+  }
+  for (; size > 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2_BE(v, *p);
+  return CRC_UINT32_SWAP(v);
+}
+
+UInt32 MY_FAST_CALL CrcUpdateT1_BeT8(UInt32 v, const void *data, size_t size, const UInt32 *table)
+{
+  const Byte *p = (const Byte *)data;
+  table += 0x100;
+  v = CRC_UINT32_SWAP(v);
+  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 7) != 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2_BE(v, *p);
+  for (; size >= 8; size -= 8, p += 8)
+  {
+    UInt32 d;
+    v ^= *(const UInt32 *)(const void *)p;
+    v =
+          (table + 0x400)[((v      ) & 0xFF)]
+        ^ (table + 0x500)[((v >>  8) & 0xFF)]
+        ^ (table + 0x600)[((v >> 16) & 0xFF)]
+        ^ (table + 0x700)[((v >> 24))];
+    d = *((const UInt32 *)(const void *)p + 1);
+    v ^=
+          (table + 0x000)[((d      ) & 0xFF)]
+        ^ (table + 0x100)[((d >>  8) & 0xFF)]
+        ^ (table + 0x200)[((d >> 16) & 0xFF)]
+        ^ (table + 0x300)[((d >> 24))];
+  }
+  for (; size > 0; size--, p++)
+    v = CRC_UPDATE_BYTE_2_BE(v, *p);
+  return CRC_UINT32_SWAP(v);
+}
+
+#endif

3rdparty/lzma/src/7zDec.c

@@ -0,0 +1,600 @@
+/* 7zDec.c -- Decoding from 7z folder
+2021-02-09 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+/* #define _7ZIP_PPMD_SUPPPORT */
+
+#include "7z.h"
+#include "7zCrc.h"
+
+#include "Bcj2.h"
+#include "Bra.h"
+#include "CpuArch.h"
+#include "Delta.h"
+#include "LzmaDec.h"
+#include "Lzma2Dec.h"
+#ifdef _7ZIP_PPMD_SUPPPORT
+#include "Ppmd7.h"
+#endif
+
+#define k_Copy 0
+#ifndef _7Z_NO_METHOD_LZMA2
+#define k_LZMA2 0x21
+#endif
+#define k_LZMA  0x30101
+#define k_BCJ2  0x303011B
+#ifndef _7Z_NO_METHODS_FILTERS
+#define k_Delta 3
+#define k_BCJ   0x3030103
+#define k_PPC   0x3030205
+#define k_IA64  0x3030401
+#define k_ARM   0x3030501
+#define k_ARMT  0x3030701
+#define k_SPARC 0x3030805
+#endif
+
+#ifdef _7ZIP_PPMD_SUPPPORT
+
+#define k_PPMD 0x30401
+
+typedef struct
+{
+  IByteIn vt;
+  const Byte *cur;
+  const Byte *end;
+  const Byte *begin;
+  UInt64 processed;
+  BoolInt extra;
+  SRes res;
+  const ILookInStream *inStream;
+} CByteInToLook;
+
+static Byte ReadByte(const IByteIn *pp)
+{
+  CByteInToLook *p = CONTAINER_FROM_VTBL(pp, CByteInToLook, vt);
+  if (p->cur != p->end)
+    return *p->cur++;
+  if (p->res == SZ_OK)
+  {
+    size_t size = (size_t)(p->cur - p->begin);
+    p->processed += size;
+    p->res = ILookInStream_Skip(p->inStream, size);
+    size = (1 << 25);
+    p->res = ILookInStream_Look(p->inStream, (const void **)&p->begin, &size);
+    p->cur = p->begin;
+    p->end = p->begin + size;
+    if (size != 0)
+      return *p->cur++;;
+  }
+  p->extra = True;
+  return 0;
+}
+
+static SRes SzDecodePpmd(const Byte *props, unsigned propsSize, UInt64 inSize, const ILookInStream *inStream,
+    Byte *outBuffer, SizeT outSize, ISzAllocPtr allocMain)
+{
+  CPpmd7 ppmd;
+  CByteInToLook s;
+  SRes res = SZ_OK;
+
+  s.vt.Read = ReadByte;
+  s.inStream = inStream;
+  s.begin = s.end = s.cur = NULL;
+  s.extra = False;
+  s.res = SZ_OK;
+  s.processed = 0;
+
+  if (propsSize != 5)
+    return SZ_ERROR_UNSUPPORTED;
+
+  {
+    unsigned order = props[0];
+    UInt32 memSize = GetUi32(props + 1);
+    if (order < PPMD7_MIN_ORDER ||
+        order > PPMD7_MAX_ORDER ||
+        memSize < PPMD7_MIN_MEM_SIZE ||
+        memSize > PPMD7_MAX_MEM_SIZE)
+      return SZ_ERROR_UNSUPPORTED;
+    Ppmd7_Construct(&ppmd);
+    if (!Ppmd7_Alloc(&ppmd, memSize, allocMain))
+      return SZ_ERROR_MEM;
+    Ppmd7_Init(&ppmd, order);
+  }
+  {
+    ppmd.rc.dec.Stream = &s.vt;
+    if (!Ppmd7z_RangeDec_Init(&ppmd.rc.dec))
+      res = SZ_ERROR_DATA;
+    else if (!s.extra)
+    {
+      Byte *buf = outBuffer;
+      const Byte *lim = buf + outSize;
+      for (; buf != lim; buf++)
+      {
+        int sym = Ppmd7z_DecodeSymbol(&ppmd);
+        if (s.extra || sym < 0)
+          break;
+        *buf = (Byte)sym;
+      }
+      if (buf != lim)
+        res = SZ_ERROR_DATA;
+      else if (!Ppmd7z_RangeDec_IsFinishedOK(&ppmd.rc.dec))
+      {
+        /* if (Ppmd7z_DecodeSymbol(&ppmd) != PPMD7_SYM_END || !Ppmd7z_RangeDec_IsFinishedOK(&ppmd.rc.dec)) */
+        res = SZ_ERROR_DATA;
+      }
+    }
+    if (s.extra)
+      res = (s.res != SZ_OK ? s.res : SZ_ERROR_DATA);
+    else if (s.processed + (size_t)(s.cur - s.begin) != inSize)
+      res = SZ_ERROR_DATA;
+  }
+  Ppmd7_Free(&ppmd, allocMain);
+  return res;
+}
+
+#endif
+
+
+static SRes SzDecodeLzma(const Byte *props, unsigned propsSize, UInt64 inSize, ILookInStream *inStream,
+    Byte *outBuffer, SizeT outSize, ISzAllocPtr allocMain)
+{
+  CLzmaDec state;
+  SRes res = SZ_OK;
+
+  LzmaDec_Construct(&state);
+  RINOK(LzmaDec_AllocateProbs(&state, props, propsSize, allocMain));
+  state.dic = outBuffer;
+  state.dicBufSize = outSize;
+  LzmaDec_Init(&state);
+
+  for (;;)
+  {
+    const void *inBuf = NULL;
+    size_t lookahead = (1 << 18);
+    if (lookahead > inSize)
+      lookahead = (size_t)inSize;
+    res = ILookInStream_Look(inStream, &inBuf, &lookahead);
+    if (res != SZ_OK)
+      break;
+
+    {
+      SizeT inProcessed = (SizeT)lookahead, dicPos = state.dicPos;
+      ELzmaStatus status;
+      res = LzmaDec_DecodeToDic(&state, outSize, (const Byte *)inBuf, &inProcessed, LZMA_FINISH_END, &status);
+      lookahead -= inProcessed;
+      inSize -= inProcessed;
+      if (res != SZ_OK)
+        break;
+
+      if (status == LZMA_STATUS_FINISHED_WITH_MARK)
+      {
+        if (outSize != state.dicPos || inSize != 0)
+          res = SZ_ERROR_DATA;
+        break;
+      }
+
+      if (outSize == state.dicPos && inSize == 0 && status == LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK)
+        break;
+
+      if (inProcessed == 0 && dicPos == state.dicPos)
+      {
+        res = SZ_ERROR_DATA;
+        break;
+      }
+
+      res = ILookInStream_Skip(inStream, inProcessed);
+      if (res != SZ_OK)
+        break;
+    }
+  }
+
+  LzmaDec_FreeProbs(&state, allocMain);
+  return res;
+}
+
+
+#ifndef _7Z_NO_METHOD_LZMA2
+
+static SRes SzDecodeLzma2(const Byte *props, unsigned propsSize, UInt64 inSize, ILookInStream *inStream,
+    Byte *outBuffer, SizeT outSize, ISzAllocPtr allocMain)
+{
+  CLzma2Dec state;
+  SRes res = SZ_OK;
+
+  Lzma2Dec_Construct(&state);
+  if (propsSize != 1)
+    return SZ_ERROR_DATA;
+  RINOK(Lzma2Dec_AllocateProbs(&state, props[0], allocMain));
+  state.decoder.dic = outBuffer;
+  state.decoder.dicBufSize = outSize;
+  Lzma2Dec_Init(&state);
+
+  for (;;)
+  {
+    const void *inBuf = NULL;
+    size_t lookahead = (1 << 18);
+    if (lookahead > inSize)
+      lookahead = (size_t)inSize;
+    res = ILookInStream_Look(inStream, &inBuf, &lookahead);
+    if (res != SZ_OK)
+      break;
+
+    {
+      SizeT inProcessed = (SizeT)lookahead, dicPos = state.decoder.dicPos;
+      ELzmaStatus status;
+      res = Lzma2Dec_DecodeToDic(&state, outSize, (const Byte *)inBuf, &inProcessed, LZMA_FINISH_END, &status);
+      lookahead -= inProcessed;
+      inSize -= inProcessed;
+      if (res != SZ_OK)
+        break;
+
+      if (status == LZMA_STATUS_FINISHED_WITH_MARK)
+      {
+        if (outSize != state.decoder.dicPos || inSize != 0)
+          res = SZ_ERROR_DATA;
+        break;
+      }
+
+      if (inProcessed == 0 && dicPos == state.decoder.dicPos)
+      {
+        res = SZ_ERROR_DATA;
+        break;
+      }
+
+      res = ILookInStream_Skip(inStream, inProcessed);
+      if (res != SZ_OK)
+        break;
+    }
+  }
+
+  Lzma2Dec_FreeProbs(&state, allocMain);
+  return res;
+}
+
+#endif
+
+
+static SRes SzDecodeCopy(UInt64 inSize, ILookInStream *inStream, Byte *outBuffer)
+{
+  while (inSize > 0)
+  {
+    const void *inBuf;
+    size_t curSize = (1 << 18);
+    if (curSize > inSize)
+      curSize = (size_t)inSize;
+    RINOK(ILookInStream_Look(inStream, &inBuf, &curSize));
+    if (curSize == 0)
+      return SZ_ERROR_INPUT_EOF;
+    memcpy(outBuffer, inBuf, curSize);
+    outBuffer += curSize;
+    inSize -= curSize;
+    RINOK(ILookInStream_Skip(inStream, curSize));
+  }
+  return SZ_OK;
+}
+
+static BoolInt IS_MAIN_METHOD(UInt32 m)
+{
+  switch (m)
+  {
+    case k_Copy:
+    case k_LZMA:
+    #ifndef _7Z_NO_METHOD_LZMA2
+    case k_LZMA2:
+    #endif
+    #ifdef _7ZIP_PPMD_SUPPPORT
+    case k_PPMD:
+    #endif
+      return True;
+  }
+  return False;
+}
+
+static BoolInt IS_SUPPORTED_CODER(const CSzCoderInfo *c)
+{
+  return
+      c->NumStreams == 1
+      /* && c->MethodID <= (UInt32)0xFFFFFFFF */
+      && IS_MAIN_METHOD((UInt32)c->MethodID);
+}
+
+#define IS_BCJ2(c) ((c)->MethodID == k_BCJ2 && (c)->NumStreams == 4)
+
+static SRes CheckSupportedFolder(const CSzFolder *f)
+{
+  if (f->NumCoders < 1 || f->NumCoders > 4)
+    return SZ_ERROR_UNSUPPORTED;
+  if (!IS_SUPPORTED_CODER(&f->Coders[0]))
+    return SZ_ERROR_UNSUPPORTED;
+  if (f->NumCoders == 1)
+  {
+    if (f->NumPackStreams != 1 || f->PackStreams[0] != 0 || f->NumBonds != 0)
+      return SZ_ERROR_UNSUPPORTED;
+    return SZ_OK;
+  }
+  
+  
+  #ifndef _7Z_NO_METHODS_FILTERS
+
+  if (f->NumCoders == 2)
+  {
+    const CSzCoderInfo *c = &f->Coders[1];
+    if (
+        /* c->MethodID > (UInt32)0xFFFFFFFF || */
+        c->NumStreams != 1
+        || f->NumPackStreams != 1
+        || f->PackStreams[0] != 0
+        || f->NumBonds != 1
+        || f->Bonds[0].InIndex != 1
+        || f->Bonds[0].OutIndex != 0)
+      return SZ_ERROR_UNSUPPORTED;
+    switch ((UInt32)c->MethodID)
+    {
+      case k_Delta:
+      case k_BCJ:
+      case k_PPC:
+      case k_IA64:
+      case k_SPARC:
+      case k_ARM:
+      case k_ARMT:
+        break;
+      default:
+        return SZ_ERROR_UNSUPPORTED;
+    }
+    return SZ_OK;
+  }
+
+  #endif
+
+  
+  if (f->NumCoders == 4)
+  {
+    if (!IS_SUPPORTED_CODER(&f->Coders[1])
+        || !IS_SUPPORTED_CODER(&f->Coders[2])
+        || !IS_BCJ2(&f->Coders[3]))
+      return SZ_ERROR_UNSUPPORTED;
+    if (f->NumPackStreams != 4
+        || f->PackStreams[0] != 2
+        || f->PackStreams[1] != 6
+        || f->PackStreams[2] != 1
+        || f->PackStreams[3] != 0
+        || f->NumBonds != 3
+        || f->Bonds[0].InIndex != 5 || f->Bonds[0].OutIndex != 0
+        || f->Bonds[1].InIndex != 4 || f->Bonds[1].OutIndex != 1
+        || f->Bonds[2].InIndex != 3 || f->Bonds[2].OutIndex != 2)
+      return SZ_ERROR_UNSUPPORTED;
+    return SZ_OK;
+  }
+  
+  return SZ_ERROR_UNSUPPORTED;
+}
+
+#ifndef _7Z_NO_METHODS_FILTERS
+#define CASE_BRA_CONV(isa) case k_ ## isa: isa ## _Convert(outBuffer, outSize, 0, 0); break;
+#endif
+
+static SRes SzFolder_Decode2(const CSzFolder *folder,
+    const Byte *propsData,
+    const UInt64 *unpackSizes,
+    const UInt64 *packPositions,
+    ILookInStream *inStream, UInt64 startPos,
+    Byte *outBuffer, SizeT outSize, ISzAllocPtr allocMain,
+    Byte *tempBuf[])
+{
+  UInt32 ci;
+  SizeT tempSizes[3] = { 0, 0, 0};
+  SizeT tempSize3 = 0;
+  Byte *tempBuf3 = 0;
+
+  RINOK(CheckSupportedFolder(folder));
+
+  for (ci = 0; ci < folder->NumCoders; ci++)
+  {
+    const CSzCoderInfo *coder = &folder->Coders[ci];
+
+    if (IS_MAIN_METHOD((UInt32)coder->MethodID))
+    {
+      UInt32 si = 0;
+      UInt64 offset;
+      UInt64 inSize;
+      Byte *outBufCur = outBuffer;
+      SizeT outSizeCur = outSize;
+      if (folder->NumCoders == 4)
+      {
+        UInt32 indices[] = { 3, 2, 0 };
+        UInt64 unpackSize = unpackSizes[ci];
+        si = indices[ci];
+        if (ci < 2)
+        {
+          Byte *temp;
+          outSizeCur = (SizeT)unpackSize;
+          if (outSizeCur != unpackSize)
+            return SZ_ERROR_MEM;
+          temp = (Byte *)ISzAlloc_Alloc(allocMain, outSizeCur);
+          if (!temp && outSizeCur != 0)
+            return SZ_ERROR_MEM;
+          outBufCur = tempBuf[1 - ci] = temp;
+          tempSizes[1 - ci] = outSizeCur;
+        }
+        else if (ci == 2)
+        {
+          if (unpackSize > outSize) /* check it */
+            return SZ_ERROR_PARAM;
+          tempBuf3 = outBufCur = outBuffer + (outSize - (size_t)unpackSize);
+          tempSize3 = outSizeCur = (SizeT)unpackSize;
+        }
+        else
+          return SZ_ERROR_UNSUPPORTED;
+      }
+      offset = packPositions[si];
+      inSize = packPositions[(size_t)si + 1] - offset;
+      RINOK(LookInStream_SeekTo(inStream, startPos + offset));
+
+      if (coder->MethodID == k_Copy)
+      {
+        if (inSize != outSizeCur) /* check it */
+          return SZ_ERROR_DATA;
+        RINOK(SzDecodeCopy(inSize, inStream, outBufCur));
+      }
+      else if (coder->MethodID == k_LZMA)
+      {
+        RINOK(SzDecodeLzma(propsData + coder->PropsOffset, coder->PropsSize, inSize, inStream, outBufCur, outSizeCur, allocMain));
+      }
+      #ifndef _7Z_NO_METHOD_LZMA2
+      else if (coder->MethodID == k_LZMA2)
+      {
+        RINOK(SzDecodeLzma2(propsData + coder->PropsOffset, coder->PropsSize, inSize, inStream, outBufCur, outSizeCur, allocMain));
+      }
+      #endif
+      #ifdef _7ZIP_PPMD_SUPPPORT
+      else if (coder->MethodID == k_PPMD)
+      {
+        RINOK(SzDecodePpmd(propsData + coder->PropsOffset, coder->PropsSize, inSize, inStream, outBufCur, outSizeCur, allocMain));
+      }
+      #endif
+      else
+        return SZ_ERROR_UNSUPPORTED;
+    }
+    else if (coder->MethodID == k_BCJ2)
+    {
+      UInt64 offset = packPositions[1];
+      UInt64 s3Size = packPositions[2] - offset;
+      
+      if (ci != 3)
+        return SZ_ERROR_UNSUPPORTED;
+      
+      tempSizes[2] = (SizeT)s3Size;
+      if (tempSizes[2] != s3Size)
+        return SZ_ERROR_MEM;
+      tempBuf[2] = (Byte *)ISzAlloc_Alloc(allocMain, tempSizes[2]);
+      if (!tempBuf[2] && tempSizes[2] != 0)
+        return SZ_ERROR_MEM;
+      
+      RINOK(LookInStream_SeekTo(inStream, startPos + offset));
+      RINOK(SzDecodeCopy(s3Size, inStream, tempBuf[2]));
+
+      if ((tempSizes[0] & 3) != 0 ||
+          (tempSizes[1] & 3) != 0 ||
+          tempSize3 + tempSizes[0] + tempSizes[1] != outSize)
+        return SZ_ERROR_DATA;
+
+      {
+        CBcj2Dec p;
+        
+        p.bufs[0] = tempBuf3;   p.lims[0] = tempBuf3 + tempSize3;
+        p.bufs[1] = tempBuf[0]; p.lims[1] = tempBuf[0] + tempSizes[0];
+        p.bufs[2] = tempBuf[1]; p.lims[2] = tempBuf[1] + tempSizes[1];
+        p.bufs[3] = tempBuf[2]; p.lims[3] = tempBuf[2] + tempSizes[2];
+        
+        p.dest = outBuffer;
+        p.destLim = outBuffer + outSize;
+        
+        Bcj2Dec_Init(&p);
+        RINOK(Bcj2Dec_Decode(&p));
+
+        {
+          unsigned i;
+          for (i = 0; i < 4; i++)
+            if (p.bufs[i] != p.lims[i])
+              return SZ_ERROR_DATA;
+          
+          if (!Bcj2Dec_IsFinished(&p))
+            return SZ_ERROR_DATA;
+
+          if (p.dest != p.destLim
+             || p.state != BCJ2_STREAM_MAIN)
+            return SZ_ERROR_DATA;
+        }
+      }
+    }
+    #ifndef _7Z_NO_METHODS_FILTERS
+    else if (ci == 1)
+    {
+      if (coder->MethodID == k_Delta)
+      {
+        if (coder->PropsSize != 1)
+          return SZ_ERROR_UNSUPPORTED;
+        {
+          Byte state[DELTA_STATE_SIZE];
+          Delta_Init(state);
+          Delta_Decode(state, (unsigned)(propsData[coder->PropsOffset]) + 1, outBuffer, outSize);
+        }
+      }
+      else
+      {
+        if (coder->PropsSize != 0)
+          return SZ_ERROR_UNSUPPORTED;
+        switch (coder->MethodID)
+        {
+          case k_BCJ:
+          {
+            UInt32 state;
+            x86_Convert_Init(state);
+            x86_Convert(outBuffer, outSize, 0, &state, 0);
+            break;
+          }
+          CASE_BRA_CONV(PPC)
+          CASE_BRA_CONV(IA64)
+          CASE_BRA_CONV(SPARC)
+          CASE_BRA_CONV(ARM)
+          CASE_BRA_CONV(ARMT)
+          default:
+            return SZ_ERROR_UNSUPPORTED;
+        }
+      }
+    }
+    #endif
+    else
+      return SZ_ERROR_UNSUPPORTED;
+  }
+
+  return SZ_OK;
+}
+
+
+SRes SzAr_DecodeFolder(const CSzAr *p, UInt32 folderIndex,
+    ILookInStream *inStream, UInt64 startPos,
+    Byte *outBuffer, size_t outSize,
+    ISzAllocPtr allocMain)
+{
+  SRes res;
+  CSzFolder folder;
+  CSzData sd;
+  
+  const Byte *data = p->CodersData + p->FoCodersOffsets[folderIndex];
+  sd.Data = data;
+  sd.Size = p->FoCodersOffsets[(size_t)folderIndex + 1] - p->FoCodersOffsets[folderIndex];
+  
+  res = SzGetNextFolderItem(&folder, &sd);
+  
+  if (res != SZ_OK)
+    return res;
+
+  if (sd.Size != 0
+      || folder.UnpackStream != p->FoToMainUnpackSizeIndex[folderIndex]
+      || outSize != SzAr_GetFolderUnpackSize(p, folderIndex))
+    return SZ_ERROR_FAIL;
+  {
+    unsigned i;
+    Byte *tempBuf[3] = { 0, 0, 0};
+
+    res = SzFolder_Decode2(&folder, data,
+        &p->CoderUnpackSizes[p->FoToCoderUnpackSizes[folderIndex]],
+        p->PackPositions + p->FoStartPackStreamIndex[folderIndex],
+        inStream, startPos,
+        outBuffer, (SizeT)outSize, allocMain, tempBuf);
+    
+    for (i = 0; i < 3; i++)
+      ISzAlloc_Free(allocMain, tempBuf[i]);
+
+    if (res == SZ_OK)
+      if (SzBitWithVals_Check(&p->FolderCRCs, folderIndex))
+        if (CrcCalc(outBuffer, outSize) != p->FolderCRCs.Vals[folderIndex])
+          res = SZ_ERROR_CRC;
+
+    return res;
+  }
+}

3rdparty/lzma/src/7zFile.c

@@ -0,0 +1,442 @@
+/* 7zFile.c -- File IO
+2021-04-29 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "7zFile.h"
+
+#ifndef USE_WINDOWS_FILE
+
+  #include <errno.h>
+
+  #ifndef USE_FOPEN
+    #include <stdio.h>
+    #include <fcntl.h>
+    #ifdef _WIN32
+      #include <io.h>
+      typedef int ssize_t;
+      typedef int off_t;
+    #else
+      #include <unistd.h>
+    #endif
+  #endif
+
+#else
+
+/*
+   ReadFile and WriteFile functions in Windows have BUG:
+   If you Read or Write 64MB or more (probably min_failure_size = 64MB - 32KB + 1)
+   from/to Network file, it returns ERROR_NO_SYSTEM_RESOURCES
+   (Insufficient system resources exist to complete the requested service).
+   Probably in some version of Windows there are problems with other sizes:
+   for 32 MB (maybe also for 16 MB).
+   And message can be "Network connection was lost"
+*/
+
+#endif
+
+#define kChunkSizeMax (1 << 22)
+
+void File_Construct(CSzFile *p)
+{
+  #ifdef USE_WINDOWS_FILE
+  p->handle = INVALID_HANDLE_VALUE;
+  #elif defined(USE_FOPEN)
+  p->file = NULL;
+  #else
+  p->fd = -1;
+  #endif
+}
+
+#if !defined(UNDER_CE) || !defined(USE_WINDOWS_FILE)
+
+static WRes File_Open(CSzFile *p, const char *name, int writeMode)
+{
+  #ifdef USE_WINDOWS_FILE
+  
+  p->handle = CreateFileA(name,
+      writeMode ? GENERIC_WRITE : GENERIC_READ,
+      FILE_SHARE_READ, NULL,
+      writeMode ? CREATE_ALWAYS : OPEN_EXISTING,
+      FILE_ATTRIBUTE_NORMAL, NULL);
+  return (p->handle != INVALID_HANDLE_VALUE) ? 0 : GetLastError();
+  
+  #elif defined(USE_FOPEN)
+  
+  p->file = fopen(name, writeMode ? "wb+" : "rb");
+  return (p->file != 0) ? 0 :
+    #ifdef UNDER_CE
+    2; /* ENOENT */
+    #else
+    errno;
+    #endif
+  
+  #else
+
+  int flags = (writeMode ? (O_CREAT | O_EXCL | O_WRONLY) : O_RDONLY);
+  #ifdef O_BINARY
+  flags |= O_BINARY;
+  #endif
+  p->fd = open(name, flags, 0666);
+  return (p->fd != -1) ? 0 : errno;
+
+  #endif
+}
+
+WRes InFile_Open(CSzFile *p, const char *name) { return File_Open(p, name, 0); }
+
+WRes OutFile_Open(CSzFile *p, const char *name)
+{
+  #if defined(USE_WINDOWS_FILE) || defined(USE_FOPEN)
+  return File_Open(p, name, 1);
+  #else
+  p->fd = creat(name, 0666);
+  return (p->fd != -1) ? 0 : errno;
+  #endif
+}
+
+#endif
+
+
+#ifdef USE_WINDOWS_FILE
+static WRes File_OpenW(CSzFile *p, const WCHAR *name, int writeMode)
+{
+  p->handle = CreateFileW(name,
+      writeMode ? GENERIC_WRITE : GENERIC_READ,
+      FILE_SHARE_READ, NULL,
+      writeMode ? CREATE_ALWAYS : OPEN_EXISTING,
+      FILE_ATTRIBUTE_NORMAL, NULL);
+  return (p->handle != INVALID_HANDLE_VALUE) ? 0 : GetLastError();
+}
+WRes InFile_OpenW(CSzFile *p, const WCHAR *name) { return File_OpenW(p, name, 0); }
+WRes OutFile_OpenW(CSzFile *p, const WCHAR *name) { return File_OpenW(p, name, 1); }
+#endif
+
+WRes File_Close(CSzFile *p)
+{
+  #ifdef USE_WINDOWS_FILE
+  
+  if (p->handle != INVALID_HANDLE_VALUE)
+  {
+    if (!CloseHandle(p->handle))
+      return GetLastError();
+    p->handle = INVALID_HANDLE_VALUE;
+  }
+  
+  #elif defined(USE_FOPEN)
+
+  if (p->file != NULL)
+  {
+    int res = fclose(p->file);
+    if (res != 0)
+    {
+      if (res == EOF)
+        return errno;
+      return res;
+    }
+    p->file = NULL;
+  }
+
+  #else
+
+  if (p->fd != -1)
+  {
+    if (close(p->fd) != 0)
+      return errno;
+    p->fd = -1;
+  }
+
+  #endif
+
+  return 0;
+}
+
+
+WRes File_Read(CSzFile *p, void *data, size_t *size)
+{
+  size_t originalSize = *size;
+  *size = 0;
+  if (originalSize == 0)
+    return 0;
+
+  #ifdef USE_WINDOWS_FILE
+
+  do
+  {
+    const DWORD curSize = (originalSize > kChunkSizeMax) ? kChunkSizeMax : (DWORD)originalSize;
+    DWORD processed = 0;
+    const BOOL res = ReadFile(p->handle, data, curSize, &processed, NULL);
+    data = (void *)((Byte *)data + processed);
+    originalSize -= processed;
+    *size += processed;
+    if (!res)
+      return GetLastError();
+    // debug : we can break here for partial reading mode
+    if (processed == 0)
+      break;
+  }
+  while (originalSize > 0);
+
+  #elif defined(USE_FOPEN)
+
+  do
+  {
+    const size_t curSize = (originalSize > kChunkSizeMax) ? kChunkSizeMax : originalSize;
+    const size_t processed = fread(data, 1, curSize, p->file);
+    data = (void *)((Byte *)data + (size_t)processed);
+    originalSize -= processed;
+    *size += processed;
+    if (processed != curSize)
+      return ferror(p->file);
+    // debug : we can break here for partial reading mode
+    if (processed == 0)
+      break;
+  }
+  while (originalSize > 0);
+
+  #else
+
+  do
+  {
+    const size_t curSize = (originalSize > kChunkSizeMax) ? kChunkSizeMax : originalSize;
+    const ssize_t processed = read(p->fd, data, curSize);
+    if (processed == -1)
+      return errno;
+    if (processed == 0)
+      break;
+    data = (void *)((Byte *)data + (size_t)processed);
+    originalSize -= (size_t)processed;
+    *size += (size_t)processed;
+    // debug : we can break here for partial reading mode
+    // break;
+  }
+  while (originalSize > 0);
+
+  #endif
+
+  return 0;
+}
+
+
+WRes File_Write(CSzFile *p, const void *data, size_t *size)
+{
+  size_t originalSize = *size;
+  *size = 0;
+  if (originalSize == 0)
+    return 0;
+  
+  #ifdef USE_WINDOWS_FILE
+
+  do
+  {
+    const DWORD curSize = (originalSize > kChunkSizeMax) ? kChunkSizeMax : (DWORD)originalSize;
+    DWORD processed = 0;
+    const BOOL res = WriteFile(p->handle, data, curSize, &processed, NULL);
+    data = (const void *)((const Byte *)data + processed);
+    originalSize -= processed;
+    *size += processed;
+    if (!res)
+      return GetLastError();
+    if (processed == 0)
+      break;
+  }
+  while (originalSize > 0);
+
+  #elif defined(USE_FOPEN)
+
+  do
+  {
+    const size_t curSize = (originalSize > kChunkSizeMax) ? kChunkSizeMax : originalSize;
+    const size_t processed = fwrite(data, 1, curSize, p->file);
+    data = (void *)((Byte *)data + (size_t)processed);
+    originalSize -= processed;
+    *size += processed;
+    if (processed != curSize)
+      return ferror(p->file);
+    if (processed == 0)
+      break;
+  }
+  while (originalSize > 0);
+
+  #else
+
+  do
+  {
+    const size_t curSize = (originalSize > kChunkSizeMax) ? kChunkSizeMax : originalSize;
+    const ssize_t processed = write(p->fd, data, curSize);
+    if (processed == -1)
+      return errno;
+    if (processed == 0)
+      break;
+    data = (void *)((Byte *)data + (size_t)processed);
+    originalSize -= (size_t)processed;
+    *size += (size_t)processed;
+  }
+  while (originalSize > 0);
+
+  #endif
+
+  return 0;
+}
+
+
+WRes File_Seek(CSzFile *p, Int64 *pos, ESzSeek origin)
+{
+  #ifdef USE_WINDOWS_FILE
+
+  DWORD moveMethod;
+  UInt32 low = (UInt32)*pos;
+  LONG high = (LONG)((UInt64)*pos >> 16 >> 16); /* for case when UInt64 is 32-bit only */
+  switch (origin)
+  {
+    case SZ_SEEK_SET: moveMethod = FILE_BEGIN; break;
+    case SZ_SEEK_CUR: moveMethod = FILE_CURRENT; break;
+    case SZ_SEEK_END: moveMethod = FILE_END; break;
+    default: return ERROR_INVALID_PARAMETER;
+  }
+  low = SetFilePointer(p->handle, (LONG)low, &high, moveMethod);
+  if (low == (UInt32)0xFFFFFFFF)
+  {
+    WRes res = GetLastError();
+    if (res != NO_ERROR)
+      return res;
+  }
+  *pos = ((Int64)high << 32) | low;
+  return 0;
+
+  #else
+  
+  int moveMethod; // = origin;
+
+  switch (origin)
+  {
+    case SZ_SEEK_SET: moveMethod = SEEK_SET; break;
+    case SZ_SEEK_CUR: moveMethod = SEEK_CUR; break;
+    case SZ_SEEK_END: moveMethod = SEEK_END; break;
+    default: return EINVAL;
+  }
+  
+  #if defined(USE_FOPEN)
+  {
+    int res = fseek(p->file, (long)*pos, moveMethod);
+    if (res == -1)
+      return errno;
+    *pos = ftell(p->file);
+    if (*pos == -1)
+      return errno;
+    return 0;
+  }
+  #else
+  {
+    off_t res = lseek(p->fd, (off_t)*pos, moveMethod);
+    if (res == -1)
+      return errno;
+    *pos = res;
+    return 0;
+  }
+  
+  #endif // USE_FOPEN
+  #endif // USE_WINDOWS_FILE
+}
+
+
+WRes File_GetLength(CSzFile *p, UInt64 *length)
+{
+  #ifdef USE_WINDOWS_FILE
+  
+  DWORD sizeHigh;
+  DWORD sizeLow = GetFileSize(p->handle, &sizeHigh);
+  if (sizeLow == 0xFFFFFFFF)
+  {
+    DWORD res = GetLastError();
+    if (res != NO_ERROR)
+      return res;
+  }
+  *length = (((UInt64)sizeHigh) << 32) + sizeLow;
+  return 0;
+  
+  #elif defined(USE_FOPEN)
+  
+  long pos = ftell(p->file);
+  int res = fseek(p->file, 0, SEEK_END);
+  *length = ftell(p->file);
+  fseek(p->file, pos, SEEK_SET);
+  return res;
+
+  #else
+
+  off_t pos;
+  *length = 0;
+  pos = lseek(p->fd, 0, SEEK_CUR);
+  if (pos != -1)
+  {
+    const off_t len2 = lseek(p->fd, 0, SEEK_END);
+    const off_t res2 = lseek(p->fd, pos, SEEK_SET);
+    if (len2 != -1)
+    {
+      *length = (UInt64)len2;
+      if (res2 != -1)
+        return 0;
+    }
+  }
+  return errno;
+  
+  #endif
+}
+
+
+/* ---------- FileSeqInStream ---------- */
+
+static SRes FileSeqInStream_Read(const ISeqInStream *pp, void *buf, size_t *size)
+{
+  CFileSeqInStream *p = CONTAINER_FROM_VTBL(pp, CFileSeqInStream, vt);
+  WRes wres = File_Read(&p->file, buf, size);
+  p->wres = wres;
+  return (wres == 0) ? SZ_OK : SZ_ERROR_READ;
+}
+
+void FileSeqInStream_CreateVTable(CFileSeqInStream *p)
+{
+  p->vt.Read = FileSeqInStream_Read;
+}
+
+
+/* ---------- FileInStream ---------- */
+
+static SRes FileInStream_Read(const ISeekInStream *pp, void *buf, size_t *size)
+{
+  CFileInStream *p = CONTAINER_FROM_VTBL(pp, CFileInStream, vt);
+  WRes wres = File_Read(&p->file, buf, size);
+  p->wres = wres;
+  return (wres == 0) ? SZ_OK : SZ_ERROR_READ;
+}
+
+static SRes FileInStream_Seek(const ISeekInStream *pp, Int64 *pos, ESzSeek origin)
+{
+  CFileInStream *p = CONTAINER_FROM_VTBL(pp, CFileInStream, vt);
+  WRes wres = File_Seek(&p->file, pos, origin);
+  p->wres = wres;
+  return (wres == 0) ? SZ_OK : SZ_ERROR_READ;
+}
+
+void FileInStream_CreateVTable(CFileInStream *p)
+{
+  p->vt.Read = FileInStream_Read;
+  p->vt.Seek = FileInStream_Seek;
+}
+
+
+/* ---------- FileOutStream ---------- */
+
+static size_t FileOutStream_Write(const ISeqOutStream *pp, const void *data, size_t size)
+{
+  CFileOutStream *p = CONTAINER_FROM_VTBL(pp, CFileOutStream, vt);
+  WRes wres = File_Write(&p->file, data, &size);
+  p->wres = wres;
+  return size;
+}
+
+void FileOutStream_CreateVTable(CFileOutStream *p)
+{
+  p->vt.Write = FileOutStream_Write;
+}

3rdparty/lzma/src/7zStream.c

@@ -0,0 +1,176 @@
+/* 7zStream.c -- 7z Stream functions
+2021-02-09 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "7zTypes.h"
+
+SRes SeqInStream_Read2(const ISeqInStream *stream, void *buf, size_t size, SRes errorType)
+{
+  while (size != 0)
+  {
+    size_t processed = size;
+    RINOK(ISeqInStream_Read(stream, buf, &processed));
+    if (processed == 0)
+      return errorType;
+    buf = (void *)((Byte *)buf + processed);
+    size -= processed;
+  }
+  return SZ_OK;
+}
+
+SRes SeqInStream_Read(const ISeqInStream *stream, void *buf, size_t size)
+{
+  return SeqInStream_Read2(stream, buf, size, SZ_ERROR_INPUT_EOF);
+}
+
+SRes SeqInStream_ReadByte(const ISeqInStream *stream, Byte *buf)
+{
+  size_t processed = 1;
+  RINOK(ISeqInStream_Read(stream, buf, &processed));
+  return (processed == 1) ? SZ_OK : SZ_ERROR_INPUT_EOF;
+}
+
+
+
+SRes LookInStream_SeekTo(const ILookInStream *stream, UInt64 offset)
+{
+  Int64 t = (Int64)offset;
+  return ILookInStream_Seek(stream, &t, SZ_SEEK_SET);
+}
+
+SRes LookInStream_LookRead(const ILookInStream *stream, void *buf, size_t *size)
+{
+  const void *lookBuf;
+  if (*size == 0)
+    return SZ_OK;
+  RINOK(ILookInStream_Look(stream, &lookBuf, size));
+  memcpy(buf, lookBuf, *size);
+  return ILookInStream_Skip(stream, *size);
+}
+
+SRes LookInStream_Read2(const ILookInStream *stream, void *buf, size_t size, SRes errorType)
+{
+  while (size != 0)
+  {
+    size_t processed = size;
+    RINOK(ILookInStream_Read(stream, buf, &processed));
+    if (processed == 0)
+      return errorType;
+    buf = (void *)((Byte *)buf + processed);
+    size -= processed;
+  }
+  return SZ_OK;
+}
+
+SRes LookInStream_Read(const ILookInStream *stream, void *buf, size_t size)
+{
+  return LookInStream_Read2(stream, buf, size, SZ_ERROR_INPUT_EOF);
+}
+
+
+
+#define GET_LookToRead2 CLookToRead2 *p = CONTAINER_FROM_VTBL(pp, CLookToRead2, vt);
+
+static SRes LookToRead2_Look_Lookahead(const ILookInStream *pp, const void **buf, size_t *size)
+{
+  SRes res = SZ_OK;
+  GET_LookToRead2
+  size_t size2 = p->size - p->pos;
+  if (size2 == 0 && *size != 0)
+  {
+    p->pos = 0;
+    p->size = 0;
+    size2 = p->bufSize;
+    res = ISeekInStream_Read(p->realStream, p->buf, &size2);
+    p->size = size2;
+  }
+  if (*size > size2)
+    *size = size2;
+  *buf = p->buf + p->pos;
+  return res;
+}
+
+static SRes LookToRead2_Look_Exact(const ILookInStream *pp, const void **buf, size_t *size)
+{
+  SRes res = SZ_OK;
+  GET_LookToRead2
+  size_t size2 = p->size - p->pos;
+  if (size2 == 0 && *size != 0)
+  {
+    p->pos = 0;
+    p->size = 0;
+    if (*size > p->bufSize)
+      *size = p->bufSize;
+    res = ISeekInStream_Read(p->realStream, p->buf, size);
+    size2 = p->size = *size;
+  }
+  if (*size > size2)
+    *size = size2;
+  *buf = p->buf + p->pos;
+  return res;
+}
+
+static SRes LookToRead2_Skip(const ILookInStream *pp, size_t offset)
+{
+  GET_LookToRead2
+  p->pos += offset;
+  return SZ_OK;
+}
+
+static SRes LookToRead2_Read(const ILookInStream *pp, void *buf, size_t *size)
+{
+  GET_LookToRead2
+  size_t rem = p->size - p->pos;
+  if (rem == 0)
+    return ISeekInStream_Read(p->realStream, buf, size);
+  if (rem > *size)
+    rem = *size;
+  memcpy(buf, p->buf + p->pos, rem);
+  p->pos += rem;
+  *size = rem;
+  return SZ_OK;
+}
+
+static SRes LookToRead2_Seek(const ILookInStream *pp, Int64 *pos, ESzSeek origin)
+{
+  GET_LookToRead2
+  p->pos = p->size = 0;
+  return ISeekInStream_Seek(p->realStream, pos, origin);
+}
+
+void LookToRead2_CreateVTable(CLookToRead2 *p, int lookahead)
+{
+  p->vt.Look = lookahead ?
+      LookToRead2_Look_Lookahead :
+      LookToRead2_Look_Exact;
+  p->vt.Skip = LookToRead2_Skip;
+  p->vt.Read = LookToRead2_Read;
+  p->vt.Seek = LookToRead2_Seek;
+}
+
+
+
+static SRes SecToLook_Read(const ISeqInStream *pp, void *buf, size_t *size)
+{
+  CSecToLook *p = CONTAINER_FROM_VTBL(pp, CSecToLook, vt);
+  return LookInStream_LookRead(p->realStream, buf, size);
+}
+
+void SecToLook_CreateVTable(CSecToLook *p)
+{
+  p->vt.Read = SecToLook_Read;
+}
+
+static SRes SecToRead_Read(const ISeqInStream *pp, void *buf, size_t *size)
+{
+  CSecToRead *p = CONTAINER_FROM_VTBL(pp, CSecToRead, vt);
+  return ILookInStream_Read(p->realStream, buf, size);
+}
+
+void SecToRead_CreateVTable(CSecToRead *p)
+{
+  p->vt.Read = SecToRead_Read;
+}

3rdparty/lzma/src/Alloc.c

@@ -0,0 +1,463 @@
+/* Alloc.c -- Memory allocation functions
+2021-07-13 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <stdio.h>
+
+#ifdef _WIN32
+#include <Windows.h>
+#endif
+#include <stdlib.h>
+
+#include "Alloc.h"
+
+/* #define _SZ_ALLOC_DEBUG */
+
+/* use _SZ_ALLOC_DEBUG to debug alloc/free operations */
+#ifdef _SZ_ALLOC_DEBUG
+
+#include <stdio.h>
+int g_allocCount = 0;
+int g_allocCountMid = 0;
+int g_allocCountBig = 0;
+
+
+#define CONVERT_INT_TO_STR(charType, tempSize) \
+  unsigned char temp[tempSize]; unsigned i = 0; \
+  while (val >= 10) { temp[i++] = (unsigned char)('0' + (unsigned)(val % 10)); val /= 10; } \
+  *s++ = (charType)('0' + (unsigned)val); \
+  while (i != 0) { i--; *s++ = temp[i]; } \
+  *s = 0;
+
+static void ConvertUInt64ToString(UInt64 val, char *s)
+{
+  CONVERT_INT_TO_STR(char, 24);
+}
+
+#define GET_HEX_CHAR(t) ((char)(((t < 10) ? ('0' + t) : ('A' + (t - 10)))))
+
+static void ConvertUInt64ToHex(UInt64 val, char *s)
+{
+  UInt64 v = val;
+  unsigned i;
+  for (i = 1;; i++)
+  {
+    v >>= 4;
+    if (v == 0)
+      break;
+  }
+  s[i] = 0;
+  do
+  {
+    unsigned t = (unsigned)(val & 0xF);
+    val >>= 4;
+    s[--i] = GET_HEX_CHAR(t);
+  }
+  while (i);
+}
+
+#define DEBUG_OUT_STREAM stderr
+
+static void Print(const char *s)
+{
+  fputs(s, DEBUG_OUT_STREAM);
+}
+
+static void PrintAligned(const char *s, size_t align)
+{
+  size_t len = strlen(s);
+  for(;;)
+  {
+    fputc(' ', DEBUG_OUT_STREAM);
+    if (len >= align)
+      break;
+    ++len;
+  }
+  Print(s);
+}
+
+static void PrintLn()
+{
+  Print("\n");
+}
+
+static void PrintHex(UInt64 v, size_t align)
+{
+  char s[32];
+  ConvertUInt64ToHex(v, s);
+  PrintAligned(s, align);
+}
+
+static void PrintDec(UInt64 v, size_t align)
+{
+  char s[32];
+  ConvertUInt64ToString(v, s);
+  PrintAligned(s, align);
+}
+
+static void PrintAddr(void *p)
+{
+  PrintHex((UInt64)(size_t)(ptrdiff_t)p, 12);
+}
+
+
+#define PRINT_ALLOC(name, cnt, size, ptr) \
+    Print(name " "); \
+    PrintDec(cnt++, 10); \
+    PrintHex(size, 10); \
+    PrintAddr(ptr); \
+    PrintLn();
+ 
+#define PRINT_FREE(name, cnt, ptr) if (ptr) { \
+    Print(name " "); \
+    PrintDec(--cnt, 10); \
+    PrintAddr(ptr); \
+    PrintLn(); }
+ 
+#else
+
+#define PRINT_ALLOC(name, cnt, size, ptr)
+#define PRINT_FREE(name, cnt, ptr)
+#define Print(s)
+#define PrintLn()
+#define PrintHex(v, align)
+#define PrintAddr(p)
+
+#endif
+
+
+
+void *MyAlloc(size_t size)
+{
+  if (size == 0)
+    return NULL;
+  PRINT_ALLOC("Alloc    ", g_allocCount, size, NULL);
+  #ifdef _SZ_ALLOC_DEBUG
+  {
+    void *p = malloc(size);
+    // PRINT_ALLOC("Alloc    ", g_allocCount, size, p);
+    return p;
+  }
+  #else
+  return malloc(size);
+  #endif
+}
+
+void MyFree(void *address)
+{
+  PRINT_FREE("Free    ", g_allocCount, address);
+  
+  free(address);
+}
+
+#ifdef _WIN32
+
+void *MidAlloc(size_t size)
+{
+  if (size == 0)
+    return NULL;
+  
+  PRINT_ALLOC("Alloc-Mid", g_allocCountMid, size, NULL);
+  
+  return VirtualAlloc(NULL, size, MEM_COMMIT, PAGE_READWRITE);
+}
+
+void MidFree(void *address)
+{
+  PRINT_FREE("Free-Mid", g_allocCountMid, address);
+
+  if (!address)
+    return;
+  VirtualFree(address, 0, MEM_RELEASE);
+}
+
+#ifdef _7ZIP_LARGE_PAGES
+
+#ifdef MEM_LARGE_PAGES
+  #define MY__MEM_LARGE_PAGES  MEM_LARGE_PAGES
+#else
+  #define MY__MEM_LARGE_PAGES  0x20000000
+#endif
+
+extern
+SIZE_T g_LargePageSize;
+SIZE_T g_LargePageSize = 0;
+typedef SIZE_T (WINAPI *GetLargePageMinimumP)(VOID);
+
+#endif // _7ZIP_LARGE_PAGES
+
+void SetLargePageSize()
+{
+  #ifdef _7ZIP_LARGE_PAGES
+  SIZE_T size;
+  GetLargePageMinimumP largePageMinimum = (GetLargePageMinimumP)
+        GetProcAddress(GetModuleHandle(TEXT("kernel32.dll")), "GetLargePageMinimum");
+  if (!largePageMinimum)
+    return;
+  size = largePageMinimum();
+  if (size == 0 || (size & (size - 1)) != 0)
+    return;
+  g_LargePageSize = size;
+  #endif
+}
+
+
+void *BigAlloc(size_t size)
+{
+  if (size == 0)
+    return NULL;
+
+  PRINT_ALLOC("Alloc-Big", g_allocCountBig, size, NULL);
+  
+  #ifdef _7ZIP_LARGE_PAGES
+  {
+    SIZE_T ps = g_LargePageSize;
+    if (ps != 0 && ps <= (1 << 30) && size > (ps / 2))
+    {
+      size_t size2;
+      ps--;
+      size2 = (size + ps) & ~ps;
+      if (size2 >= size)
+      {
+        void *res = VirtualAlloc(NULL, size2, MEM_COMMIT | MY__MEM_LARGE_PAGES, PAGE_READWRITE);
+        if (res)
+          return res;
+      }
+    }
+  }
+  #endif
+
+  return VirtualAlloc(NULL, size, MEM_COMMIT, PAGE_READWRITE);
+}
+
+void BigFree(void *address)
+{
+  PRINT_FREE("Free-Big", g_allocCountBig, address);
+  
+  if (!address)
+    return;
+  VirtualFree(address, 0, MEM_RELEASE);
+}
+
+#endif
+
+
+static void *SzAlloc(ISzAllocPtr p, size_t size) { UNUSED_VAR(p); return MyAlloc(size); }
+static void SzFree(ISzAllocPtr p, void *address) { UNUSED_VAR(p); MyFree(address); }
+const ISzAlloc g_Alloc = { SzAlloc, SzFree };
+
+#ifdef _WIN32
+static void *SzMidAlloc(ISzAllocPtr p, size_t size) { UNUSED_VAR(p); return MidAlloc(size); }
+static void SzMidFree(ISzAllocPtr p, void *address) { UNUSED_VAR(p); MidFree(address); }
+static void *SzBigAlloc(ISzAllocPtr p, size_t size) { UNUSED_VAR(p); return BigAlloc(size); }
+static void SzBigFree(ISzAllocPtr p, void *address) { UNUSED_VAR(p); BigFree(address); }
+const ISzAlloc g_MidAlloc = { SzMidAlloc, SzMidFree };
+const ISzAlloc g_BigAlloc = { SzBigAlloc, SzBigFree };
+#endif
+
+/*
+  uintptr_t : <stdint.h> C99 (optional)
+            : unsupported in VS6
+*/
+
+#ifdef _WIN32
+  typedef UINT_PTR UIntPtr;
+#else
+  /*
+  typedef uintptr_t UIntPtr;
+  */
+  typedef ptrdiff_t UIntPtr;
+#endif
+
+
+#define ADJUST_ALLOC_SIZE 0
+/*
+#define ADJUST_ALLOC_SIZE (sizeof(void *) - 1)
+*/
+/*
+  Use (ADJUST_ALLOC_SIZE = (sizeof(void *) - 1)), if
+     MyAlloc() can return address that is NOT multiple of sizeof(void *).
+*/
+
+
+/*
+#define MY_ALIGN_PTR_DOWN(p, align) ((void *)((char *)(p) - ((size_t)(UIntPtr)(p) & ((align) - 1))))
+*/
+#define MY_ALIGN_PTR_DOWN(p, align) ((void *)((((UIntPtr)(p)) & ~((UIntPtr)(align) - 1))))
+
+
+#if !defined(_WIN32) && defined(_POSIX_C_SOURCE) && (_POSIX_C_SOURCE >= 200112L)
+  #define USE_posix_memalign
+#endif
+
+#ifndef USE_posix_memalign
+#define MY_ALIGN_PTR_UP_PLUS(p, align) MY_ALIGN_PTR_DOWN(((char *)(p) + (align) + ADJUST_ALLOC_SIZE), align)
+#endif
+
+/*
+  This posix_memalign() is for test purposes only.
+  We also need special Free() function instead of free(),
+  if this posix_memalign() is used.
+*/
+
+/*
+static int posix_memalign(void **ptr, size_t align, size_t size)
+{
+  size_t newSize = size + align;
+  void *p;
+  void *pAligned;
+  *ptr = NULL;
+  if (newSize < size)
+    return 12; // ENOMEM
+  p = MyAlloc(newSize);
+  if (!p)
+    return 12; // ENOMEM
+  pAligned = MY_ALIGN_PTR_UP_PLUS(p, align);
+  ((void **)pAligned)[-1] = p;
+  *ptr = pAligned;
+  return 0;
+}
+*/
+
+/*
+  ALLOC_ALIGN_SIZE >= sizeof(void *)
+  ALLOC_ALIGN_SIZE >= cache_line_size
+*/
+
+#define ALLOC_ALIGN_SIZE ((size_t)1 << 7)
+
+static void *SzAlignedAlloc(ISzAllocPtr pp, size_t size)
+{
+  #ifndef USE_posix_memalign
+  
+  void *p;
+  void *pAligned;
+  size_t newSize;
+  UNUSED_VAR(pp);
+
+  /* also we can allocate additional dummy ALLOC_ALIGN_SIZE bytes after aligned
+     block to prevent cache line sharing with another allocated blocks */
+
+  newSize = size + ALLOC_ALIGN_SIZE * 1 + ADJUST_ALLOC_SIZE;
+  if (newSize < size)
+    return NULL;
+
+  p = MyAlloc(newSize);
+  
+  if (!p)
+    return NULL;
+  pAligned = MY_ALIGN_PTR_UP_PLUS(p, ALLOC_ALIGN_SIZE);
+
+  Print(" size="); PrintHex(size, 8);
+  Print(" a_size="); PrintHex(newSize, 8);
+  Print(" ptr="); PrintAddr(p);
+  Print(" a_ptr="); PrintAddr(pAligned);
+  PrintLn();
+
+  ((void **)pAligned)[-1] = p;
+
+  return pAligned;
+
+  #else
+
+  void *p;
+  UNUSED_VAR(pp);
+  if (posix_memalign(&p, ALLOC_ALIGN_SIZE, size))
+    return NULL;
+
+  Print(" posix_memalign="); PrintAddr(p);
+  PrintLn();
+
+  return p;
+
+  #endif
+}
+
+
+static void SzAlignedFree(ISzAllocPtr pp, void *address)
+{
+  UNUSED_VAR(pp);
+  #ifndef USE_posix_memalign
+  if (address)
+    MyFree(((void **)address)[-1]);
+  #else
+  free(address);
+  #endif
+}
+
+
+const ISzAlloc g_AlignedAlloc = { SzAlignedAlloc, SzAlignedFree };
+
+
+
+#define MY_ALIGN_PTR_DOWN_1(p) MY_ALIGN_PTR_DOWN(p, sizeof(void *))
+
+/* we align ptr to support cases where CAlignOffsetAlloc::offset is not multiply of sizeof(void *) */
+#define REAL_BLOCK_PTR_VAR(p) ((void **)MY_ALIGN_PTR_DOWN_1(p))[-1]
+/*
+#define REAL_BLOCK_PTR_VAR(p) ((void **)(p))[-1]
+*/
+
+static void *AlignOffsetAlloc_Alloc(ISzAllocPtr pp, size_t size)
+{
+  CAlignOffsetAlloc *p = CONTAINER_FROM_VTBL(pp, CAlignOffsetAlloc, vt);
+  void *adr;
+  void *pAligned;
+  size_t newSize;
+  size_t extra;
+  size_t alignSize = (size_t)1 << p->numAlignBits;
+
+  if (alignSize < sizeof(void *))
+    alignSize = sizeof(void *);
+  
+  if (p->offset >= alignSize)
+    return NULL;
+
+  /* also we can allocate additional dummy ALLOC_ALIGN_SIZE bytes after aligned
+     block to prevent cache line sharing with another allocated blocks */
+  extra = p->offset & (sizeof(void *) - 1);
+  newSize = size + alignSize + extra + ADJUST_ALLOC_SIZE;
+  if (newSize < size)
+    return NULL;
+
+  adr = ISzAlloc_Alloc(p->baseAlloc, newSize);
+  
+  if (!adr)
+    return NULL;
+
+  pAligned = (char *)MY_ALIGN_PTR_DOWN((char *)adr +
+      alignSize - p->offset + extra + ADJUST_ALLOC_SIZE, alignSize) + p->offset;
+
+  PrintLn();
+  Print("- Aligned: ");
+  Print(" size="); PrintHex(size, 8);
+  Print(" a_size="); PrintHex(newSize, 8);
+  Print(" ptr="); PrintAddr(adr);
+  Print(" a_ptr="); PrintAddr(pAligned);
+  PrintLn();
+
+  REAL_BLOCK_PTR_VAR(pAligned) = adr;
+
+  return pAligned;
+}
+
+
+static void AlignOffsetAlloc_Free(ISzAllocPtr pp, void *address)
+{
+  if (address)
+  {
+    CAlignOffsetAlloc *p = CONTAINER_FROM_VTBL(pp, CAlignOffsetAlloc, vt);
+    PrintLn();
+    Print("- Aligned Free: ");
+    PrintLn();
+    ISzAlloc_Free(p->baseAlloc, REAL_BLOCK_PTR_VAR(address));
+  }
+}
+
+
+void AlignOffsetAlloc_CreateVTable(CAlignOffsetAlloc *p)
+{
+  p->vt.Alloc = AlignOffsetAlloc_Alloc;
+  p->vt.Free = AlignOffsetAlloc_Free;
+}

3rdparty/lzma/src/Bcj2.c

@@ -0,0 +1,257 @@
+/* Bcj2.c -- BCJ2 Decoder (Converter for x86 code)
+2021-02-09 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Bcj2.h"
+#include "CpuArch.h"
+
+#define CProb UInt16
+
+#define kTopValue ((UInt32)1 << 24)
+#define kNumModelBits 11
+#define kBitModelTotal (1 << kNumModelBits)
+#define kNumMoveBits 5
+
+#define _IF_BIT_0 ttt = *prob; bound = (p->range >> kNumModelBits) * ttt; if (p->code < bound)
+#define _UPDATE_0 p->range = bound; *prob = (CProb)(ttt + ((kBitModelTotal - ttt) >> kNumMoveBits));
+#define _UPDATE_1 p->range -= bound; p->code -= bound; *prob = (CProb)(ttt - (ttt >> kNumMoveBits));
+
+void Bcj2Dec_Init(CBcj2Dec *p)
+{
+  unsigned i;
+
+  p->state = BCJ2_DEC_STATE_OK;
+  p->ip = 0;
+  p->temp[3] = 0;
+  p->range = 0;
+  p->code = 0;
+  for (i = 0; i < sizeof(p->probs) / sizeof(p->probs[0]); i++)
+    p->probs[i] = kBitModelTotal >> 1;
+}
+
+SRes Bcj2Dec_Decode(CBcj2Dec *p)
+{
+  if (p->range <= 5)
+  {
+    p->state = BCJ2_DEC_STATE_OK;
+    for (; p->range != 5; p->range++)
+    {
+      if (p->range == 1 && p->code != 0)
+        return SZ_ERROR_DATA;
+      
+      if (p->bufs[BCJ2_STREAM_RC] == p->lims[BCJ2_STREAM_RC])
+      {
+        p->state = BCJ2_STREAM_RC;
+        return SZ_OK;
+      }
+
+      p->code = (p->code << 8) | *(p->bufs[BCJ2_STREAM_RC])++;
+    }
+    
+    if (p->code == 0xFFFFFFFF)
+      return SZ_ERROR_DATA;
+    
+    p->range = 0xFFFFFFFF;
+  }
+  else if (p->state >= BCJ2_DEC_STATE_ORIG_0)
+  {
+    while (p->state <= BCJ2_DEC_STATE_ORIG_3)
+    {
+      Byte *dest = p->dest;
+      if (dest == p->destLim)
+        return SZ_OK;
+      *dest = p->temp[(size_t)p->state - BCJ2_DEC_STATE_ORIG_0];
+      p->state++;
+      p->dest = dest + 1;
+    }
+  }
+
+  /*
+  if (BCJ2_IS_32BIT_STREAM(p->state))
+  {
+    const Byte *cur = p->bufs[p->state];
+    if (cur == p->lims[p->state])
+      return SZ_OK;
+    p->bufs[p->state] = cur + 4;
+    
+    {
+      UInt32 val;
+      Byte *dest;
+      SizeT rem;
+      
+      p->ip += 4;
+      val = GetBe32(cur) - p->ip;
+      dest = p->dest;
+      rem = p->destLim - dest;
+      if (rem < 4)
+      {
+        SizeT i;
+        SetUi32(p->temp, val);
+        for (i = 0; i < rem; i++)
+          dest[i] = p->temp[i];
+        p->dest = dest + rem;
+        p->state = BCJ2_DEC_STATE_ORIG_0 + (unsigned)rem;
+        return SZ_OK;
+      }
+      SetUi32(dest, val);
+      p->temp[3] = (Byte)(val >> 24);
+      p->dest = dest + 4;
+      p->state = BCJ2_DEC_STATE_OK;
+    }
+  }
+  */
+
+  for (;;)
+  {
+    if (BCJ2_IS_32BIT_STREAM(p->state))
+      p->state = BCJ2_DEC_STATE_OK;
+    else
+    {
+      if (p->range < kTopValue)
+      {
+        if (p->bufs[BCJ2_STREAM_RC] == p->lims[BCJ2_STREAM_RC])
+        {
+          p->state = BCJ2_STREAM_RC;
+          return SZ_OK;
+        }
+        p->range <<= 8;
+        p->code = (p->code << 8) | *(p->bufs[BCJ2_STREAM_RC])++;
+      }
+
+      {
+        const Byte *src = p->bufs[BCJ2_STREAM_MAIN];
+        const Byte *srcLim;
+        Byte *dest;
+        SizeT num = (SizeT)(p->lims[BCJ2_STREAM_MAIN] - src);
+        
+        if (num == 0)
+        {
+          p->state = BCJ2_STREAM_MAIN;
+          return SZ_OK;
+        }
+        
+        dest = p->dest;
+        if (num > (SizeT)(p->destLim - dest))
+        {
+          num = (SizeT)(p->destLim - dest);
+          if (num == 0)
+          {
+            p->state = BCJ2_DEC_STATE_ORIG;
+            return SZ_OK;
+          }
+        }
+       
+        srcLim = src + num;
+
+        if (p->temp[3] == 0x0F && (src[0] & 0xF0) == 0x80)
+          *dest = src[0];
+        else for (;;)
+        {
+          Byte b = *src;
+          *dest = b;
+          if (b != 0x0F)
+          {
+            if ((b & 0xFE) == 0xE8)
+              break;
+            dest++;
+            if (++src != srcLim)
+              continue;
+            break;
+          }
+          dest++;
+          if (++src == srcLim)
+            break;
+          if ((*src & 0xF0) != 0x80)
+            continue;
+          *dest = *src;
+          break;
+        }
+        
+        num = (SizeT)(src - p->bufs[BCJ2_STREAM_MAIN]);
+        
+        if (src == srcLim)
+        {
+          p->temp[3] = src[-1];
+          p->bufs[BCJ2_STREAM_MAIN] = src;
+          p->ip += (UInt32)num;
+          p->dest += num;
+          p->state =
+            p->bufs[BCJ2_STREAM_MAIN] ==
+            p->lims[BCJ2_STREAM_MAIN] ?
+              (unsigned)BCJ2_STREAM_MAIN :
+              (unsigned)BCJ2_DEC_STATE_ORIG;
+          return SZ_OK;
+        }
+        
+        {
+          UInt32 bound, ttt;
+          CProb *prob;
+          Byte b = src[0];
+          Byte prev = (Byte)(num == 0 ? p->temp[3] : src[-1]);
+          
+          p->temp[3] = b;
+          p->bufs[BCJ2_STREAM_MAIN] = src + 1;
+          num++;
+          p->ip += (UInt32)num;
+          p->dest += num;
+          
+          prob = p->probs + (unsigned)(b == 0xE8 ? 2 + (unsigned)prev : (b == 0xE9 ? 1 : 0));
+          
+          _IF_BIT_0
+          {
+            _UPDATE_0
+            continue;
+          }
+          _UPDATE_1
+            
+        }
+      }
+    }
+
+    {
+      UInt32 val;
+      unsigned cj = (p->temp[3] == 0xE8) ? BCJ2_STREAM_CALL : BCJ2_STREAM_JUMP;
+      const Byte *cur = p->bufs[cj];
+      Byte *dest;
+      SizeT rem;
+      
+      if (cur == p->lims[cj])
+      {
+        p->state = cj;
+        break;
+      }
+      
+      val = GetBe32(cur);
+      p->bufs[cj] = cur + 4;
+
+      p->ip += 4;
+      val -= p->ip;
+      dest = p->dest;
+      rem = (SizeT)(p->destLim - dest);
+      
+      if (rem < 4)
+      {
+        p->temp[0] = (Byte)val; if (rem > 0) dest[0] = (Byte)val; val >>= 8;
+        p->temp[1] = (Byte)val; if (rem > 1) dest[1] = (Byte)val; val >>= 8;
+        p->temp[2] = (Byte)val; if (rem > 2) dest[2] = (Byte)val; val >>= 8;
+        p->temp[3] = (Byte)val;
+        p->dest = dest + rem;
+        p->state = BCJ2_DEC_STATE_ORIG_0 + (unsigned)rem;
+        break;
+      }
+      
+      SetUi32(dest, val);
+      p->temp[3] = (Byte)(val >> 24);
+      p->dest = dest + 4;
+    }
+  }
+
+  if (p->range < kTopValue && p->bufs[BCJ2_STREAM_RC] != p->lims[BCJ2_STREAM_RC])
+  {
+    p->range <<= 8;
+    p->code = (p->code << 8) | *(p->bufs[BCJ2_STREAM_RC])++;
+  }
+
+  return SZ_OK;
+}

3rdparty/lzma/src/Bcj2Enc.c

@@ -0,0 +1,311 @@
+/* Bcj2Enc.c -- BCJ2 Encoder (Converter for x86 code)
+2021-02-09 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+/* #define SHOW_STAT */
+
+#ifdef SHOW_STAT
+#include <stdio.h>
+#define PRF(x) x
+#else
+#define PRF(x)
+#endif
+
+#include <string.h>
+
+#include "Bcj2.h"
+#include "CpuArch.h"
+
+#define CProb UInt16
+
+#define kTopValue ((UInt32)1 << 24)
+#define kNumModelBits 11
+#define kBitModelTotal (1 << kNumModelBits)
+#define kNumMoveBits 5
+
+void Bcj2Enc_Init(CBcj2Enc *p)
+{
+  unsigned i;
+
+  p->state = BCJ2_ENC_STATE_OK;
+  p->finishMode = BCJ2_ENC_FINISH_MODE_CONTINUE;
+
+  p->prevByte = 0;
+
+  p->cache = 0;
+  p->range = 0xFFFFFFFF;
+  p->low = 0;
+  p->cacheSize = 1;
+
+  p->ip = 0;
+
+  p->fileIp = 0;
+  p->fileSize = 0;
+  p->relatLimit = BCJ2_RELAT_LIMIT;
+
+  p->tempPos = 0;
+
+  p->flushPos = 0;
+
+  for (i = 0; i < sizeof(p->probs) / sizeof(p->probs[0]); i++)
+    p->probs[i] = kBitModelTotal >> 1;
+}
+
+static BoolInt MY_FAST_CALL RangeEnc_ShiftLow(CBcj2Enc *p)
+{
+  if ((UInt32)p->low < (UInt32)0xFF000000 || (UInt32)(p->low >> 32) != 0)
+  {
+    Byte *buf = p->bufs[BCJ2_STREAM_RC];
+    do
+    {
+      if (buf == p->lims[BCJ2_STREAM_RC])
+      {
+        p->state = BCJ2_STREAM_RC;
+        p->bufs[BCJ2_STREAM_RC] = buf;
+        return True;
+      }
+      *buf++ = (Byte)(p->cache + (Byte)(p->low >> 32));
+      p->cache = 0xFF;
+    }
+    while (--p->cacheSize);
+    p->bufs[BCJ2_STREAM_RC] = buf;
+    p->cache = (Byte)((UInt32)p->low >> 24);
+  }
+  p->cacheSize++;
+  p->low = (UInt32)p->low << 8;
+  return False;
+}
+
+static void Bcj2Enc_Encode_2(CBcj2Enc *p)
+{
+  if (BCJ2_IS_32BIT_STREAM(p->state))
+  {
+    Byte *cur = p->bufs[p->state];
+    if (cur == p->lims[p->state])
+      return;
+    SetBe32(cur, p->tempTarget);
+    p->bufs[p->state] = cur + 4;
+  }
+
+  p->state = BCJ2_ENC_STATE_ORIG;
+
+  for (;;)
+  {
+    if (p->range < kTopValue)
+    {
+      if (RangeEnc_ShiftLow(p))
+        return;
+      p->range <<= 8;
+    }
+
+    {
+      {
+        const Byte *src = p->src;
+        const Byte *srcLim;
+        Byte *dest;
+        SizeT num = (SizeT)(p->srcLim - src);
+
+        if (p->finishMode == BCJ2_ENC_FINISH_MODE_CONTINUE)
+        {
+          if (num <= 4)
+            return;
+          num -= 4;
+        }
+        else if (num == 0)
+          break;
+
+        dest = p->bufs[BCJ2_STREAM_MAIN];
+        if (num > (SizeT)(p->lims[BCJ2_STREAM_MAIN] - dest))
+        {
+          num = (SizeT)(p->lims[BCJ2_STREAM_MAIN] - dest);
+          if (num == 0)
+          {
+            p->state = BCJ2_STREAM_MAIN;
+            return;
+          }
+        }
+       
+        srcLim = src + num;
+
+        if (p->prevByte == 0x0F && (src[0] & 0xF0) == 0x80)
+          *dest = src[0];
+        else for (;;)
+        {
+          Byte b = *src;
+          *dest = b;
+          if (b != 0x0F)
+          {
+            if ((b & 0xFE) == 0xE8)
+              break;
+            dest++;
+            if (++src != srcLim)
+              continue;
+            break;
+          }
+          dest++;
+          if (++src == srcLim)
+            break;
+          if ((*src & 0xF0) != 0x80)
+            continue;
+          *dest = *src;
+          break;
+        }
+        
+        num = (SizeT)(src - p->src);
+        
+        if (src == srcLim)
+        {
+          p->prevByte = src[-1];
+          p->bufs[BCJ2_STREAM_MAIN] = dest;
+          p->src = src;
+          p->ip += (UInt32)num;
+          continue;
+        }
+ 
+        {
+          Byte context = (Byte)(num == 0 ? p->prevByte : src[-1]);
+          BoolInt needConvert;
+
+          p->bufs[BCJ2_STREAM_MAIN] = dest + 1;
+          p->ip += (UInt32)num + 1;
+          src++;
+          
+          needConvert = False;
+
+          if ((SizeT)(p->srcLim - src) >= 4)
+          {
+            UInt32 relatVal = GetUi32(src);
+            if ((p->fileSize == 0 || (UInt32)(p->ip + 4 + relatVal - p->fileIp) < p->fileSize)
+                && ((relatVal + p->relatLimit) >> 1) < p->relatLimit)
+              needConvert = True;
+          }
+
+          {
+            UInt32 bound;
+            unsigned ttt;
+            Byte b = src[-1];
+            CProb *prob = p->probs + (unsigned)(b == 0xE8 ? 2 + (unsigned)context : (b == 0xE9 ? 1 : 0));
+
+            ttt = *prob;
+            bound = (p->range >> kNumModelBits) * ttt;
+            
+            if (!needConvert)
+            {
+              p->range = bound;
+              *prob = (CProb)(ttt + ((kBitModelTotal - ttt) >> kNumMoveBits));
+              p->src = src;
+              p->prevByte = b;
+              continue;
+            }
+            
+            p->low += bound;
+            p->range -= bound;
+            *prob = (CProb)(ttt - (ttt >> kNumMoveBits));
+
+            {
+              UInt32 relatVal = GetUi32(src);
+              UInt32 absVal;
+              p->ip += 4;
+              absVal = p->ip + relatVal;
+              p->prevByte = src[3];
+              src += 4;
+              p->src = src;
+              {
+                unsigned cj = (b == 0xE8) ? BCJ2_STREAM_CALL : BCJ2_STREAM_JUMP;
+                Byte *cur = p->bufs[cj];
+                if (cur == p->lims[cj])
+                {
+                  p->state = cj;
+                  p->tempTarget = absVal;
+                  return;
+                }
+                SetBe32(cur, absVal);
+                p->bufs[cj] = cur + 4;
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+
+  if (p->finishMode != BCJ2_ENC_FINISH_MODE_END_STREAM)
+    return;
+
+  for (; p->flushPos < 5; p->flushPos++)
+    if (RangeEnc_ShiftLow(p))
+      return;
+  p->state = BCJ2_ENC_STATE_OK;
+}
+
+
+void Bcj2Enc_Encode(CBcj2Enc *p)
+{
+  PRF(printf("\n"));
+  PRF(printf("---- ip = %8d   tempPos = %8d   src = %8d\n", p->ip, p->tempPos, p->srcLim - p->src));
+
+  if (p->tempPos != 0)
+  {
+    unsigned extra = 0;
+   
+    for (;;)
+    {
+      const Byte *src = p->src;
+      const Byte *srcLim = p->srcLim;
+      EBcj2Enc_FinishMode finishMode = p->finishMode;
+      
+      p->src = p->temp;
+      p->srcLim = p->temp + p->tempPos;
+      if (src != srcLim)
+        p->finishMode = BCJ2_ENC_FINISH_MODE_CONTINUE;
+      
+      PRF(printf("     ip = %8d   tempPos = %8d   src = %8d\n", p->ip, p->tempPos, p->srcLim - p->src));
+
+      Bcj2Enc_Encode_2(p);
+      
+      {
+        unsigned num = (unsigned)(p->src - p->temp);
+        unsigned tempPos = p->tempPos - num;
+        unsigned i;
+        p->tempPos = tempPos;
+        for (i = 0; i < tempPos; i++)
+          p->temp[i] = p->temp[(size_t)i + num];
+      
+        p->src = src;
+        p->srcLim = srcLim;
+        p->finishMode = finishMode;
+        
+        if (p->state != BCJ2_ENC_STATE_ORIG || src == srcLim)
+          return;
+        
+        if (extra >= tempPos)
+        {
+          p->src = src - tempPos;
+          p->tempPos = 0;
+          break;
+        }
+        
+        p->temp[tempPos] = src[0];
+        p->tempPos = tempPos + 1;
+        p->src = src + 1;
+        extra++;
+      }
+    }
+  }
+
+  PRF(printf("++++ ip = %8d   tempPos = %8d   src = %8d\n", p->ip, p->tempPos, p->srcLim - p->src));
+
+  Bcj2Enc_Encode_2(p);
+  
+  if (p->state == BCJ2_ENC_STATE_ORIG)
+  {
+    const Byte *src = p->src;
+    unsigned rem = (unsigned)(p->srcLim - src);
+    unsigned i;
+    for (i = 0; i < rem; i++)
+      p->temp[i] = src[i];
+    p->tempPos = rem;
+    p->src = src + rem;
+  }
+}

3rdparty/lzma/src/Bra.c

@@ -0,0 +1,230 @@
+/* Bra.c -- Converters for RISC code
+2021-02-09 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+#include "Bra.h"
+
+SizeT ARM_Convert(Byte *data, SizeT size, UInt32 ip, int encoding)
+{
+  Byte *p;
+  const Byte *lim;
+  size &= ~(size_t)3;
+  ip += 4;
+  p = data;
+  lim = data + size;
+
+  if (encoding)
+
+  for (;;)
+  {
+    for (;;)
+    {
+      if (p >= lim)
+        return (SizeT)(p - data);
+      p += 4;
+      if (p[-1] == 0xEB)
+        break;
+    }
+    {
+      UInt32 v = GetUi32(p - 4);
+      v <<= 2;
+        v += ip + (UInt32)(p - data);
+      v >>= 2;
+      v &= 0x00FFFFFF;
+      v |= 0xEB000000;
+      SetUi32(p - 4, v);
+    }
+  }
+
+  for (;;)
+  {
+    for (;;)
+    {
+      if (p >= lim)
+        return (SizeT)(p - data);
+      p += 4;
+      if (p[-1] == 0xEB)
+        break;
+    }
+    {
+      UInt32 v = GetUi32(p - 4);
+      v <<= 2;
+        v -= ip + (UInt32)(p - data);
+      v >>= 2;
+      v &= 0x00FFFFFF;
+      v |= 0xEB000000;
+      SetUi32(p - 4, v);
+    }
+  }
+}
+
+
+SizeT ARMT_Convert(Byte *data, SizeT size, UInt32 ip, int encoding)
+{
+  Byte *p;
+  const Byte *lim;
+  size &= ~(size_t)1;
+  p = data;
+  lim = data + size - 4;
+
+  if (encoding)
+  
+  for (;;)
+  {
+    UInt32 b1;
+    for (;;)
+    {
+      UInt32 b3;
+      if (p > lim)
+        return (SizeT)(p - data);
+      b1 = p[1];
+      b3 = p[3];
+      p += 2;
+      b1 ^= 8;
+      if ((b3 & b1) >= 0xF8)
+        break;
+    }
+    {
+      UInt32 v =
+             ((UInt32)b1 << 19)
+          + (((UInt32)p[1] & 0x7) << 8)
+          + (((UInt32)p[-2] << 11))
+          + (p[0]);
+
+      p += 2;
+      {
+        UInt32 cur = (ip + (UInt32)(p - data)) >> 1;
+          v += cur;
+      }
+
+      p[-4] = (Byte)(v >> 11);
+      p[-3] = (Byte)(0xF0 | ((v >> 19) & 0x7));
+      p[-2] = (Byte)v;
+      p[-1] = (Byte)(0xF8 | (v >> 8));
+    }
+  }
+  
+  for (;;)
+  {
+    UInt32 b1;
+    for (;;)
+    {
+      UInt32 b3;
+      if (p > lim)
+        return (SizeT)(p - data);
+      b1 = p[1];
+      b3 = p[3];
+      p += 2;
+      b1 ^= 8;
+      if ((b3 & b1) >= 0xF8)
+        break;
+    }
+    {
+      UInt32 v =
+             ((UInt32)b1 << 19)
+          + (((UInt32)p[1] & 0x7) << 8)
+          + (((UInt32)p[-2] << 11))
+          + (p[0]);
+
+      p += 2;
+      {
+        UInt32 cur = (ip + (UInt32)(p - data)) >> 1;
+          v -= cur;
+      }
+
+      /*
+      SetUi16(p - 4, (UInt16)(((v >> 11) & 0x7FF) | 0xF000));
+      SetUi16(p - 2, (UInt16)(v | 0xF800));
+      */
+      
+      p[-4] = (Byte)(v >> 11);
+      p[-3] = (Byte)(0xF0 | ((v >> 19) & 0x7));
+      p[-2] = (Byte)v;
+      p[-1] = (Byte)(0xF8 | (v >> 8));
+    }
+  }
+}
+
+
+SizeT PPC_Convert(Byte *data, SizeT size, UInt32 ip, int encoding)
+{
+  Byte *p;
+  const Byte *lim;
+  size &= ~(size_t)3;
+  ip -= 4;
+  p = data;
+  lim = data + size;
+
+  for (;;)
+  {
+    for (;;)
+    {
+      if (p >= lim)
+        return (SizeT)(p - data);
+      p += 4;
+      /* if ((v & 0xFC000003) == 0x48000001) */
+      if ((p[-4] & 0xFC) == 0x48 && (p[-1] & 3) == 1)
+        break;
+    }
+    {
+      UInt32 v = GetBe32(p - 4);
+      if (encoding)
+        v += ip + (UInt32)(p - data);
+      else
+        v -= ip + (UInt32)(p - data);
+      v &= 0x03FFFFFF;
+      v |= 0x48000000;
+      SetBe32(p - 4, v);
+    }
+  }
+}
+
+
+SizeT SPARC_Convert(Byte *data, SizeT size, UInt32 ip, int encoding)
+{
+  Byte *p;
+  const Byte *lim;
+  size &= ~(size_t)3;
+  ip -= 4;
+  p = data;
+  lim = data + size;
+
+  for (;;)
+  {
+    for (;;)
+    {
+      if (p >= lim)
+        return (SizeT)(p - data);
+      /*
+      v = GetBe32(p);
+      p += 4;
+      m = v + ((UInt32)5 << 29);
+      m ^= (UInt32)7 << 29;
+      m += (UInt32)1 << 22;
+      if ((m & ((UInt32)0x1FF << 23)) == 0)
+        break;
+      */
+      p += 4;
+      if ((p[-4] == 0x40 && (p[-3] & 0xC0) == 0) ||
+          (p[-4] == 0x7F && (p[-3] >= 0xC0)))
+        break;
+    }
+    {
+      UInt32 v = GetBe32(p - 4);
+      v <<= 2;
+      if (encoding)
+        v += ip + (UInt32)(p - data);
+      else
+        v -= ip + (UInt32)(p - data);
+      
+      v &= 0x01FFFFFF;
+      v -= (UInt32)1 << 24;
+      v ^= 0xFF000000;
+      v >>= 2;
+      v |= 0x40000000;
+      SetBe32(p - 4, v);
+    }
+  }
+}

3rdparty/lzma/src/Bra86.c

@@ -0,0 +1,82 @@
+/* Bra86.c -- Converter for x86 code (BCJ)
+2021-02-09 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Bra.h"
+
+#define Test86MSByte(b) ((((b) + 1) & 0xFE) == 0)
+
+SizeT x86_Convert(Byte *data, SizeT size, UInt32 ip, UInt32 *state, int encoding)
+{
+  SizeT pos = 0;
+  UInt32 mask = *state & 7;
+  if (size < 5)
+    return 0;
+  size -= 4;
+  ip += 5;
+
+  for (;;)
+  {
+    Byte *p = data + pos;
+    const Byte *limit = data + size;
+    for (; p < limit; p++)
+      if ((*p & 0xFE) == 0xE8)
+        break;
+
+    {
+      SizeT d = (SizeT)(p - data) - pos;
+      pos = (SizeT)(p - data);
+      if (p >= limit)
+      {
+        *state = (d > 2 ? 0 : mask >> (unsigned)d);
+        return pos;
+      }
+      if (d > 2)
+        mask = 0;
+      else
+      {
+        mask >>= (unsigned)d;
+        if (mask != 0 && (mask > 4 || mask == 3 || Test86MSByte(p[(size_t)(mask >> 1) + 1])))
+        {
+          mask = (mask >> 1) | 4;
+          pos++;
+          continue;
+        }
+      }
+    }
+
+    if (Test86MSByte(p[4]))
+    {
+      UInt32 v = ((UInt32)p[4] << 24) | ((UInt32)p[3] << 16) | ((UInt32)p[2] << 8) | ((UInt32)p[1]);
+      UInt32 cur = ip + (UInt32)pos;
+      pos += 5;
+      if (encoding)
+        v += cur;
+      else
+        v -= cur;
+      if (mask != 0)
+      {
+        unsigned sh = (mask & 6) << 2;
+        if (Test86MSByte((Byte)(v >> sh)))
+        {
+          v ^= (((UInt32)0x100 << sh) - 1);
+          if (encoding)
+            v += cur;
+          else
+            v -= cur;
+        }
+        mask = 0;
+      }
+      p[1] = (Byte)v;
+      p[2] = (Byte)(v >> 8);
+      p[3] = (Byte)(v >> 16);
+      p[4] = (Byte)(0 - ((v >> 24) & 1));
+    }
+    else
+    {
+      mask = (mask >> 1) | 4;
+      pos++;
+    }
+  }
+}

3rdparty/lzma/src/BraIA64.c

@@ -0,0 +1,53 @@
+/* BraIA64.c -- Converter for IA-64 code
+2017-01-26 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+#include "Bra.h"
+
+SizeT IA64_Convert(Byte *data, SizeT size, UInt32 ip, int encoding)
+{
+  SizeT i;
+  if (size < 16)
+    return 0;
+  size -= 16;
+  i = 0;
+  do
+  {
+    unsigned m = ((UInt32)0x334B0000 >> (data[i] & 0x1E)) & 3;
+    if (m)
+    {
+      m++;
+      do
+      {
+        Byte *p = data + (i + (size_t)m * 5 - 8);
+        if (((p[3] >> m) & 15) == 5
+            && (((p[-1] | ((UInt32)p[0] << 8)) >> m) & 0x70) == 0)
+        {
+          unsigned raw = GetUi32(p);
+          unsigned v = raw >> m;
+          v = (v & 0xFFFFF) | ((v & (1 << 23)) >> 3);
+          
+          v <<= 4;
+          if (encoding)
+            v += ip + (UInt32)i;
+          else
+            v -= ip + (UInt32)i;
+          v >>= 4;
+          
+          v &= 0x1FFFFF;
+          v += 0x700000;
+          v &= 0x8FFFFF;
+          raw &= ~((UInt32)0x8FFFFF << m);
+          raw |= (v << m);
+          SetUi32(p, raw);
+        }
+      }
+      while (++m <= 4);
+    }
+    i += 16;
+  }
+  while (i <= size);
+  return i;
+}

3rdparty/lzma/src/CpuArch.c

@@ -0,0 +1,478 @@
+/* CpuArch.c -- CPU specific code
+2021-07-13 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+
+#ifdef MY_CPU_X86_OR_AMD64
+
+#if (defined(_MSC_VER) && !defined(MY_CPU_AMD64)) || defined(__GNUC__)
+#define USE_ASM
+#endif
+
+#if !defined(USE_ASM) && _MSC_VER >= 1500
+#include <intrin.h>
+#endif
+
+#if defined(USE_ASM) && !defined(MY_CPU_AMD64)
+static UInt32 CheckFlag(UInt32 flag)
+{
+  #ifdef _MSC_VER
+  __asm pushfd;
+  __asm pop EAX;
+  __asm mov EDX, EAX;
+  __asm xor EAX, flag;
+  __asm push EAX;
+  __asm popfd;
+  __asm pushfd;
+  __asm pop EAX;
+  __asm xor EAX, EDX;
+  __asm push EDX;
+  __asm popfd;
+  __asm and flag, EAX;
+  #else
+  __asm__ __volatile__ (
+    "pushf\n\t"
+    "pop  %%EAX\n\t"
+    "movl %%EAX,%%EDX\n\t"
+    "xorl %0,%%EAX\n\t"
+    "push %%EAX\n\t"
+    "popf\n\t"
+    "pushf\n\t"
+    "pop  %%EAX\n\t"
+    "xorl %%EDX,%%EAX\n\t"
+    "push %%EDX\n\t"
+    "popf\n\t"
+    "andl %%EAX, %0\n\t":
+    "=c" (flag) : "c" (flag) :
+    "%eax", "%edx");
+  #endif
+  return flag;
+}
+#define CHECK_CPUID_IS_SUPPORTED if (CheckFlag(1 << 18) == 0 || CheckFlag(1 << 21) == 0) return False;
+#else
+#define CHECK_CPUID_IS_SUPPORTED
+#endif
+
+#ifndef USE_ASM
+  #ifdef _MSC_VER
+    #if _MSC_VER >= 1600
+      #define MY__cpuidex  __cpuidex
+    #else
+
+/*
+ __cpuid (function == 4) requires subfunction number in ECX.
+  MSDN: The __cpuid intrinsic clears the ECX register before calling the cpuid instruction.
+   __cpuid() in new MSVC clears ECX.
+   __cpuid() in old MSVC (14.00) doesn't clear ECX
+ We still can use __cpuid for low (function) values that don't require ECX,
+ but __cpuid() in old MSVC will be incorrect for some function values: (function == 4).
+ So here we use the hack for old MSVC to send (subFunction) in ECX register to cpuid instruction,
+ where ECX value is first parameter for FAST_CALL / NO_INLINE function,
+ So the caller of MY__cpuidex_HACK() sets ECX as subFunction, and
+ old MSVC for __cpuid() doesn't change ECX and cpuid instruction gets (subFunction) value.
+ 
+ DON'T remove MY_NO_INLINE and MY_FAST_CALL for MY__cpuidex_HACK() !!!
+*/
+
+static
+MY_NO_INLINE
+void MY_FAST_CALL MY__cpuidex_HACK(UInt32 subFunction, int *CPUInfo, UInt32 function)
+{
+  UNUSED_VAR(subFunction);
+  __cpuid(CPUInfo, function);
+}
+
+      #define MY__cpuidex(info, func, func2)  MY__cpuidex_HACK(func2, info, func)
+      #pragma message("======== MY__cpuidex_HACK WAS USED ========")
+    #endif
+  #else
+     #define MY__cpuidex(info, func, func2)  __cpuid(info, func)
+     #pragma message("======== (INCORRECT ?) cpuid WAS USED ========")
+  #endif
+#endif
+
+
+
+
+void MyCPUID(UInt32 function, UInt32 *a, UInt32 *b, UInt32 *c, UInt32 *d)
+{
+  #ifdef USE_ASM
+
+  #ifdef _MSC_VER
+
+  UInt32 a2, b2, c2, d2;
+  __asm xor EBX, EBX;
+  __asm xor ECX, ECX;
+  __asm xor EDX, EDX;
+  __asm mov EAX, function;
+  __asm cpuid;
+  __asm mov a2, EAX;
+  __asm mov b2, EBX;
+  __asm mov c2, ECX;
+  __asm mov d2, EDX;
+
+  *a = a2;
+  *b = b2;
+  *c = c2;
+  *d = d2;
+
+  #else
+
+  __asm__ __volatile__ (
+  #if defined(MY_CPU_AMD64) && defined(__PIC__)
+    "mov %%rbx, %%rdi;"
+    "cpuid;"
+    "xchg %%rbx, %%rdi;"
+    : "=a" (*a) ,
+      "=D" (*b) ,
+  #elif defined(MY_CPU_X86) && defined(__PIC__)
+    "mov %%ebx, %%edi;"
+    "cpuid;"
+    "xchgl %%ebx, %%edi;"
+    : "=a" (*a) ,
+      "=D" (*b) ,
+  #else
+    "cpuid"
+    : "=a" (*a) ,
+      "=b" (*b) ,
+  #endif
+      "=c" (*c) ,
+      "=d" (*d)
+    : "0" (function), "c"(0) ) ;
+
+  #endif
+  
+  #else
+
+  int CPUInfo[4];
+
+  MY__cpuidex(CPUInfo, (int)function, 0);
+
+  *a = (UInt32)CPUInfo[0];
+  *b = (UInt32)CPUInfo[1];
+  *c = (UInt32)CPUInfo[2];
+  *d = (UInt32)CPUInfo[3];
+
+  #endif
+}
+
+BoolInt x86cpuid_CheckAndRead(Cx86cpuid *p)
+{
+  CHECK_CPUID_IS_SUPPORTED
+  MyCPUID(0, &p->maxFunc, &p->vendor[0], &p->vendor[2], &p->vendor[1]);
+  MyCPUID(1, &p->ver, &p->b, &p->c, &p->d);
+  return True;
+}
+
+static const UInt32 kVendors[][3] =
+{
+  { 0x756E6547, 0x49656E69, 0x6C65746E},
+  { 0x68747541, 0x69746E65, 0x444D4163},
+  { 0x746E6543, 0x48727561, 0x736C7561}
+};
+
+int x86cpuid_GetFirm(const Cx86cpuid *p)
+{
+  unsigned i;
+  for (i = 0; i < sizeof(kVendors) / sizeof(kVendors[i]); i++)
+  {
+    const UInt32 *v = kVendors[i];
+    if (v[0] == p->vendor[0] &&
+        v[1] == p->vendor[1] &&
+        v[2] == p->vendor[2])
+      return (int)i;
+  }
+  return -1;
+}
+
+BoolInt CPU_Is_InOrder()
+{
+  Cx86cpuid p;
+  int firm;
+  UInt32 family, model;
+  if (!x86cpuid_CheckAndRead(&p))
+    return True;
+
+  family = x86cpuid_GetFamily(p.ver);
+  model = x86cpuid_GetModel(p.ver);
+  
+  firm = x86cpuid_GetFirm(&p);
+
+  switch (firm)
+  {
+    case CPU_FIRM_INTEL: return (family < 6 || (family == 6 && (
+        /* In-Order Atom CPU */
+           model == 0x1C  /* 45 nm, N4xx, D4xx, N5xx, D5xx, 230, 330 */
+        || model == 0x26  /* 45 nm, Z6xx */
+        || model == 0x27  /* 32 nm, Z2460 */
+        || model == 0x35  /* 32 nm, Z2760 */
+        || model == 0x36  /* 32 nm, N2xxx, D2xxx */
+        )));
+    case CPU_FIRM_AMD: return (family < 5 || (family == 5 && (model < 6 || model == 0xA)));
+    case CPU_FIRM_VIA: return (family < 6 || (family == 6 && model < 0xF));
+  }
+  return True;
+}
+
+#if !defined(MY_CPU_AMD64) && defined(_WIN32)
+#include <Windows.h>
+static BoolInt CPU_Sys_Is_SSE_Supported()
+{
+  OSVERSIONINFO vi;
+  vi.dwOSVersionInfoSize = sizeof(vi);
+  if (!GetVersionEx(&vi))
+    return False;
+  return (vi.dwMajorVersion >= 5);
+}
+#define CHECK_SYS_SSE_SUPPORT if (!CPU_Sys_Is_SSE_Supported()) return False;
+#else
+#define CHECK_SYS_SSE_SUPPORT
+#endif
+
+
+static UInt32 X86_CPUID_ECX_Get_Flags()
+{
+  Cx86cpuid p;
+  CHECK_SYS_SSE_SUPPORT
+  if (!x86cpuid_CheckAndRead(&p))
+    return 0;
+  return p.c;
+}
+
+BoolInt CPU_IsSupported_AES()
+{
+  return (X86_CPUID_ECX_Get_Flags() >> 25) & 1;
+}
+
+BoolInt CPU_IsSupported_SSSE3()
+{
+  return (X86_CPUID_ECX_Get_Flags() >> 9) & 1;
+}
+
+BoolInt CPU_IsSupported_SSE41()
+{
+  return (X86_CPUID_ECX_Get_Flags() >> 19) & 1;
+}
+
+BoolInt CPU_IsSupported_SHA()
+{
+  Cx86cpuid p;
+  CHECK_SYS_SSE_SUPPORT
+  if (!x86cpuid_CheckAndRead(&p))
+    return False;
+
+  if (p.maxFunc < 7)
+    return False;
+  {
+    UInt32 d[4] = { 0 };
+    MyCPUID(7, &d[0], &d[1], &d[2], &d[3]);
+    return (d[1] >> 29) & 1;
+  }
+}
+
+// #include <stdio.h>
+
+#ifdef _WIN32
+#include <Windows.h>
+#endif
+
+BoolInt CPU_IsSupported_AVX2()
+{
+  Cx86cpuid p;
+  CHECK_SYS_SSE_SUPPORT
+
+  #ifdef _WIN32
+  #define MY__PF_XSAVE_ENABLED  17
+  if (!IsProcessorFeaturePresent(MY__PF_XSAVE_ENABLED))
+    return False;
+  #endif
+
+  if (!x86cpuid_CheckAndRead(&p))
+    return False;
+  if (p.maxFunc < 7)
+    return False;
+  {
+    UInt32 d[4] = { 0 };
+    MyCPUID(7, &d[0], &d[1], &d[2], &d[3]);
+    // printf("\ncpuid(7): ebx=%8x ecx=%8x\n", d[1], d[2]);
+    return 1
+      & (d[1] >> 5); // avx2
+  }
+}
+
+BoolInt CPU_IsSupported_VAES_AVX2()
+{
+  Cx86cpuid p;
+  CHECK_SYS_SSE_SUPPORT
+
+  #ifdef _WIN32
+  #define MY__PF_XSAVE_ENABLED  17
+  if (!IsProcessorFeaturePresent(MY__PF_XSAVE_ENABLED))
+    return False;
+  #endif
+
+  if (!x86cpuid_CheckAndRead(&p))
+    return False;
+  if (p.maxFunc < 7)
+    return False;
+  {
+    UInt32 d[4] = { 0 };
+    MyCPUID(7, &d[0], &d[1], &d[2], &d[3]);
+    // printf("\ncpuid(7): ebx=%8x ecx=%8x\n", d[1], d[2]);
+    return 1
+      & (d[1] >> 5) // avx2
+      // & (d[1] >> 31) // avx512vl
+      & (d[2] >> 9); // vaes // VEX-256/EVEX
+  }
+}
+
+BoolInt CPU_IsSupported_PageGB()
+{
+  Cx86cpuid cpuid;
+  if (!x86cpuid_CheckAndRead(&cpuid))
+    return False;
+  {
+    UInt32 d[4] = { 0 };
+    MyCPUID(0x80000000, &d[0], &d[1], &d[2], &d[3]);
+    if (d[0] < 0x80000001)
+      return False;
+  }
+  {
+    UInt32 d[4] = { 0 };
+    MyCPUID(0x80000001, &d[0], &d[1], &d[2], &d[3]);
+    return (d[3] >> 26) & 1;
+  }
+}
+
+
+#elif defined(MY_CPU_ARM_OR_ARM64)
+
+#ifdef _WIN32
+
+#include <Windows.h>
+
+BoolInt CPU_IsSupported_CRC32()  { return IsProcessorFeaturePresent(PF_ARM_V8_CRC32_INSTRUCTIONS_AVAILABLE) ? 1 : 0; }
+BoolInt CPU_IsSupported_CRYPTO() { return IsProcessorFeaturePresent(PF_ARM_V8_CRYPTO_INSTRUCTIONS_AVAILABLE) ? 1 : 0; }
+BoolInt CPU_IsSupported_NEON()   { return IsProcessorFeaturePresent(PF_ARM_NEON_INSTRUCTIONS_AVAILABLE) ? 1 : 0; }
+
+#else
+
+#if defined(__APPLE__)
+
+/*
+#include <stdio.h>
+#include <string.h>
+static void Print_sysctlbyname(const char *name)
+{
+  size_t bufSize = 256;
+  char buf[256];
+  int res = sysctlbyname(name, &buf, &bufSize, NULL, 0);
+  {
+    int i;
+    printf("\nres = %d : %s : '%s' : bufSize = %d, numeric", res, name, buf, (unsigned)bufSize);
+    for (i = 0; i < 20; i++)
+      printf(" %2x", (unsigned)(Byte)buf[i]);
+
+  }
+}
+*/
+
+static BoolInt My_sysctlbyname_Get_BoolInt(const char *name)
+{
+  UInt32 val = 0;
+  if (My_sysctlbyname_Get_UInt32(name, &val) == 0 && val == 1)
+    return 1;
+  return 0;
+}
+
+  /*
+  Print_sysctlbyname("hw.pagesize");
+  Print_sysctlbyname("machdep.cpu.brand_string");
+  */
+
+BoolInt CPU_IsSupported_CRC32(void)
+{
+  return My_sysctlbyname_Get_BoolInt("hw.optional.armv8_crc32");
+}
+
+BoolInt CPU_IsSupported_NEON(void)
+{
+  return My_sysctlbyname_Get_BoolInt("hw.optional.neon");
+}
+
+#ifdef MY_CPU_ARM64
+#define APPLE_CRYPTO_SUPPORT_VAL 1
+#else
+#define APPLE_CRYPTO_SUPPORT_VAL 0
+#endif
+
+BoolInt CPU_IsSupported_SHA1(void) { return APPLE_CRYPTO_SUPPORT_VAL; }
+BoolInt CPU_IsSupported_SHA2(void) { return APPLE_CRYPTO_SUPPORT_VAL; }
+BoolInt CPU_IsSupported_AES (void) { return APPLE_CRYPTO_SUPPORT_VAL; }
+
+
+#else // __APPLE__
+
+#include <sys/auxv.h>
+
+#define USE_HWCAP
+
+#ifdef USE_HWCAP
+
+#include <asm/hwcap.h>
+
+  #define MY_HWCAP_CHECK_FUNC_2(name1, name2) \
+  BoolInt CPU_IsSupported_ ## name1() { return (getauxval(AT_HWCAP)  & (HWCAP_  ## name2)) ? 1 : 0; }
+
+#ifdef MY_CPU_ARM64
+  #define MY_HWCAP_CHECK_FUNC(name) \
+  MY_HWCAP_CHECK_FUNC_2(name, name)
+  MY_HWCAP_CHECK_FUNC_2(NEON, ASIMD)
+// MY_HWCAP_CHECK_FUNC (ASIMD)
+#elif defined(MY_CPU_ARM)
+  #define MY_HWCAP_CHECK_FUNC(name) \
+  BoolInt CPU_IsSupported_ ## name() { return (getauxval(AT_HWCAP2) & (HWCAP2_ ## name)) ? 1 : 0; }
+  MY_HWCAP_CHECK_FUNC_2(NEON, NEON)
+#endif
+
+#else // USE_HWCAP
+
+  #define MY_HWCAP_CHECK_FUNC(name) \
+  BoolInt CPU_IsSupported_ ## name() { return 0; }
+  MY_HWCAP_CHECK_FUNC(NEON)
+
+#endif // USE_HWCAP
+
+MY_HWCAP_CHECK_FUNC (CRC32)
+MY_HWCAP_CHECK_FUNC (SHA1)
+MY_HWCAP_CHECK_FUNC (SHA2)
+MY_HWCAP_CHECK_FUNC (AES)
+
+#endif // __APPLE__
+#endif // _WIN32
+
+#endif // MY_CPU_ARM_OR_ARM64
+
+
+
+#ifdef __APPLE__
+
+#include <sys/sysctl.h>
+
+int My_sysctlbyname_Get(const char *name, void *buf, size_t *bufSize)
+{
+  return sysctlbyname(name, buf, bufSize, NULL, 0);
+}
+
+int My_sysctlbyname_Get_UInt32(const char *name, UInt32 *val)
+{
+  size_t bufSize = sizeof(*val);
+  int res = My_sysctlbyname_Get(name, val, &bufSize);
+  if (res == 0 && bufSize != sizeof(*val))
+    return EFAULT;
+  return res;
+}
+
+#endif

3rdparty/lzma/src/Delta.c

@@ -0,0 +1,169 @@
+/* Delta.c -- Delta converter
+2021-02-09 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Delta.h"
+
+void Delta_Init(Byte *state)
+{
+  unsigned i;
+  for (i = 0; i < DELTA_STATE_SIZE; i++)
+    state[i] = 0;
+}
+
+
+void Delta_Encode(Byte *state, unsigned delta, Byte *data, SizeT size)
+{
+  Byte temp[DELTA_STATE_SIZE];
+
+  if (size == 0)
+    return;
+
+  {
+    unsigned i = 0;
+    do
+      temp[i] = state[i];
+    while (++i != delta);
+  }
+
+  if (size <= delta)
+  {
+    unsigned i = 0, k;
+    do
+    {
+      Byte b = *data;
+      *data++ = (Byte)(b - temp[i]);
+      temp[i] = b;
+    }
+    while (++i != size);
+    
+    k = 0;
+    
+    do
+    {
+      if (i == delta)
+        i = 0;
+      state[k] = temp[i++];
+    }
+    while (++k != delta);
+    
+    return;
+  }
+    
+  {
+    Byte *p = data + size - delta;
+    {
+      unsigned i = 0;
+      do
+        state[i] = *p++;
+      while (++i != delta);
+    }
+    {
+      const Byte *lim = data + delta;
+      ptrdiff_t dif = -(ptrdiff_t)delta;
+      
+      if (((ptrdiff_t)size + dif) & 1)
+      {
+        --p;  *p = (Byte)(*p - p[dif]);
+      }
+
+      while (p != lim)
+      {
+        --p;  *p = (Byte)(*p - p[dif]);
+        --p;  *p = (Byte)(*p - p[dif]);
+      }
+      
+      dif = -dif;
+      
+      do
+      {
+        --p;  *p = (Byte)(*p - temp[--dif]);
+      }
+      while (dif != 0);
+    }
+  }
+}
+
+
+void Delta_Decode(Byte *state, unsigned delta, Byte *data, SizeT size)
+{
+  unsigned i;
+  const Byte *lim;
+
+  if (size == 0)
+    return;
+  
+  i = 0;
+  lim = data + size;
+  
+  if (size <= delta)
+  {
+    do
+      *data = (Byte)(*data + state[i++]);
+    while (++data != lim);
+
+    for (; delta != i; state++, delta--)
+      *state = state[i];
+    data -= i;
+  }
+  else
+  {
+    /*
+    #define B(n) b ## n
+    #define I(n) Byte B(n) = state[n];
+    #define U(n) { B(n) = (Byte)((B(n)) + *data++); data[-1] = (B(n)); }
+    #define F(n) if (data != lim) { U(n) }
+
+    if (delta == 1)
+    {
+      I(0)
+      if ((lim - data) & 1) { U(0) }
+      while (data != lim) { U(0) U(0) }
+      data -= 1;
+    }
+    else if (delta == 2)
+    {
+      I(0) I(1)
+      lim -= 1; while (data < lim) { U(0) U(1) }
+      lim += 1; F(0)
+      data -= 2;
+    }
+    else if (delta == 3)
+    {
+      I(0) I(1) I(2)
+      lim -= 2; while (data < lim) { U(0) U(1) U(2) }
+      lim += 2; F(0) F(1)
+      data -= 3;
+    }
+    else if (delta == 4)
+    {
+      I(0) I(1) I(2) I(3)
+      lim -= 3; while (data < lim) { U(0) U(1) U(2) U(3) }
+      lim += 3; F(0) F(1) F(2)
+      data -= 4;
+    }
+    else
+    */
+    {
+      do
+      {
+        *data = (Byte)(*data + state[i++]);
+        data++;
+      }
+      while (i != delta);
+  
+      {
+        ptrdiff_t dif = -(ptrdiff_t)delta;
+        do
+          *data = (Byte)(*data + data[dif]);
+        while (++data != lim);
+        data += dif;
+      }
+    }
+  }
+
+  do
+    *state++ = *data;
+  while (++data != lim);
+}

3rdparty/lzma/src/LzFindOpt.c

@@ -0,0 +1,578 @@
+/* LzFindOpt.c -- multithreaded Match finder for LZ algorithms
+2021-07-13 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+#include "LzFind.h"
+
+// #include "LzFindMt.h"
+
+// #define LOG_ITERS
+
+// #define LOG_THREAD
+
+#ifdef LOG_THREAD
+#include <stdio.h>
+#define PRF(x) x
+#else
+// #define PRF(x)
+#endif
+
+#ifdef LOG_ITERS
+#include <stdio.h>
+UInt64 g_NumIters_Tree;
+UInt64 g_NumIters_Loop;
+UInt64 g_NumIters_Bytes;
+#define LOG_ITER(x) x
+#else
+#define LOG_ITER(x)
+#endif
+
+// ---------- BT THREAD ----------
+
+#define USE_SON_PREFETCH
+#define USE_LONG_MATCH_OPT
+
+#define kEmptyHashValue 0
+
+// #define CYC_TO_POS_OFFSET 0
+
+// #define CYC_TO_POS_OFFSET 1 // for debug
+
+/*
+MY_NO_INLINE
+UInt32 * MY_FAST_CALL GetMatchesSpecN_1(const Byte *lenLimit, size_t pos, const Byte *cur, CLzRef *son,
+    UInt32 _cutValue, UInt32 *d, size_t _maxLen, const UInt32 *hash, const UInt32 *limit, const UInt32 *size, UInt32 *posRes)
+{
+  do
+  {
+    UInt32 delta;
+    if (hash == size)
+      break;
+    delta = *hash++;
+
+    if (delta == 0 || delta > (UInt32)pos)
+      return NULL;
+
+    lenLimit++;
+
+    if (delta == (UInt32)pos)
+    {
+      CLzRef *ptr1 = son + ((size_t)pos << 1) - CYC_TO_POS_OFFSET * 2;
+      *d++ = 0;
+      ptr1[0] = kEmptyHashValue;
+      ptr1[1] = kEmptyHashValue;
+    }
+else
+{
+  UInt32 *_distances = ++d;
+
+  CLzRef *ptr0 = son + ((size_t)(pos) << 1) - CYC_TO_POS_OFFSET * 2 + 1;
+  CLzRef *ptr1 = son + ((size_t)(pos) << 1) - CYC_TO_POS_OFFSET * 2;
+
+  const Byte *len0 = cur, *len1 = cur;
+  UInt32 cutValue = _cutValue;
+  const Byte *maxLen = cur + _maxLen;
+
+  for (LOG_ITER(g_NumIters_Tree++);;)
+  {
+    LOG_ITER(g_NumIters_Loop++);
+    {
+      const ptrdiff_t diff = (ptrdiff_t)0 - (ptrdiff_t)delta;
+      CLzRef *pair = son + ((size_t)(((ptrdiff_t)pos - CYC_TO_POS_OFFSET) + diff) << 1);
+      const Byte *len = (len0 < len1 ? len0 : len1);
+
+    #ifdef USE_SON_PREFETCH
+      const UInt32 pair0 = *pair;
+    #endif
+
+      if (len[diff] == len[0])
+      {
+        if (++len != lenLimit && len[diff] == len[0])
+          while (++len != lenLimit)
+          {
+            LOG_ITER(g_NumIters_Bytes++);
+            if (len[diff] != len[0])
+              break;
+          }
+        if (maxLen < len)
+        {
+          maxLen = len;
+          *d++ = (UInt32)(len - cur);
+          *d++ = delta - 1;
+          
+          if (len == lenLimit)
+          {
+            const UInt32 pair1 = pair[1];
+            *ptr1 =
+              #ifdef USE_SON_PREFETCH
+                pair0;
+              #else
+                pair[0];
+              #endif
+            *ptr0 = pair1;
+
+            _distances[-1] = (UInt32)(d - _distances);
+
+            #ifdef USE_LONG_MATCH_OPT
+
+                if (hash == size || *hash != delta || lenLimit[diff] != lenLimit[0] || d >= limit)
+                  break;
+
+            {
+              for (;;)
+              {
+                hash++;
+                pos++;
+                cur++;
+                lenLimit++;
+                {
+                  CLzRef *ptr = son + ((size_t)(pos) << 1) - CYC_TO_POS_OFFSET * 2;
+                  #if 0
+                  *(UInt64 *)(void *)ptr = ((const UInt64 *)(const void *)ptr)[diff];
+                  #else
+                  const UInt32 p0 = ptr[0 + (diff * 2)];
+                  const UInt32 p1 = ptr[1 + (diff * 2)];
+                  ptr[0] = p0;
+                  ptr[1] = p1;
+                  // ptr[0] = ptr[0 + (diff * 2)];
+                  // ptr[1] = ptr[1 + (diff * 2)];
+                  #endif
+                }
+                // PrintSon(son + 2, pos - 1);
+                // printf("\npos = %x delta = %x\n", pos, delta);
+                len++;
+                *d++ = 2;
+                *d++ = (UInt32)(len - cur);
+                *d++ = delta - 1;
+                if (hash == size || *hash != delta || lenLimit[diff] != lenLimit[0] || d >= limit)
+                  break;
+              }
+            }
+            #endif
+
+            break;
+          }
+        }
+      }
+
+      {
+        const UInt32 curMatch = (UInt32)pos - delta; // (UInt32)(pos + diff);
+        if (len[diff] < len[0])
+        {
+          delta = pair[1];
+          if (delta >= curMatch)
+            return NULL;
+          *ptr1 = curMatch;
+          ptr1 = pair + 1;
+          len1 = len;
+        }
+        else
+        {
+          delta = *pair;
+          if (delta >= curMatch)
+            return NULL;
+          *ptr0 = curMatch;
+          ptr0 = pair;
+          len0 = len;
+        }
+
+        delta = (UInt32)pos - delta;
+ 
+        if (--cutValue == 0 || delta >= pos)
+        {
+          *ptr0 = *ptr1 = kEmptyHashValue;
+          _distances[-1] = (UInt32)(d - _distances);
+          break;
+        }
+      }
+    }
+  } // for (tree iterations)
+}
+    pos++;
+    cur++;
+  }
+  while (d < limit);
+  *posRes = (UInt32)pos;
+  return d;
+}
+*/
+
+/* define cbs if you use 2 functions.
+       GetMatchesSpecN_1() :  (pos <  _cyclicBufferSize)
+       GetMatchesSpecN_2() :  (pos >= _cyclicBufferSize)
+
+  do not define cbs if you use 1 function:
+       GetMatchesSpecN_2()
+*/
+
+// #define cbs _cyclicBufferSize
+
+/*
+  we use size_t for (pos) and (_cyclicBufferPos_ instead of UInt32
+  to eliminate "movsx" BUG in old MSVC x64 compiler.
+*/
+
+UInt32 * MY_FAST_CALL GetMatchesSpecN_2(const Byte *lenLimit, size_t pos, const Byte *cur, CLzRef *son,
+    UInt32 _cutValue, UInt32 *d, size_t _maxLen, const UInt32 *hash, const UInt32 *limit, const UInt32 *size,
+    size_t _cyclicBufferPos, UInt32 _cyclicBufferSize,
+    UInt32 *posRes);
+
+MY_NO_INLINE
+UInt32 * MY_FAST_CALL GetMatchesSpecN_2(const Byte *lenLimit, size_t pos, const Byte *cur, CLzRef *son,
+    UInt32 _cutValue, UInt32 *d, size_t _maxLen, const UInt32 *hash, const UInt32 *limit, const UInt32 *size,
+    size_t _cyclicBufferPos, UInt32 _cyclicBufferSize,
+    UInt32 *posRes)
+{
+  do // while (hash != size)
+  {
+    UInt32 delta;
+    
+  #ifndef cbs
+    UInt32 cbs;
+  #endif
+
+    if (hash == size)
+      break;
+
+    delta = *hash++;
+
+    if (delta == 0)
+      return NULL;
+
+    lenLimit++;
+
+  #ifndef cbs
+    cbs = _cyclicBufferSize;
+    if ((UInt32)pos < cbs)
+    {
+      if (delta > (UInt32)pos)
+        return NULL;
+      cbs = (UInt32)pos;
+    }
+  #endif
+
+    if (delta >= cbs)
+    {
+      CLzRef *ptr1 = son + ((size_t)_cyclicBufferPos << 1);
+      *d++ = 0;
+      ptr1[0] = kEmptyHashValue;
+      ptr1[1] = kEmptyHashValue;
+    }
+else
+{
+  UInt32 *_distances = ++d;
+
+  CLzRef *ptr0 = son + ((size_t)_cyclicBufferPos << 1) + 1;
+  CLzRef *ptr1 = son + ((size_t)_cyclicBufferPos << 1);
+
+  UInt32 cutValue = _cutValue;
+  const Byte *len0 = cur, *len1 = cur;
+  const Byte *maxLen = cur + _maxLen;
+
+  // if (cutValue == 0) { *ptr0 = *ptr1 = kEmptyHashValue; } else
+  for (LOG_ITER(g_NumIters_Tree++);;)
+  {
+    LOG_ITER(g_NumIters_Loop++);
+    {
+      // SPEC code
+      CLzRef *pair = son + ((size_t)((ptrdiff_t)_cyclicBufferPos - (ptrdiff_t)delta
+          + (ptrdiff_t)(UInt32)(_cyclicBufferPos < delta ? cbs : 0)
+          ) << 1);
+
+      const ptrdiff_t diff = (ptrdiff_t)0 - (ptrdiff_t)delta;
+      const Byte *len = (len0 < len1 ? len0 : len1);
+
+    #ifdef USE_SON_PREFETCH
+      const UInt32 pair0 = *pair;
+    #endif
+
+      if (len[diff] == len[0])
+      {
+        if (++len != lenLimit && len[diff] == len[0])
+          while (++len != lenLimit)
+          {
+            LOG_ITER(g_NumIters_Bytes++);
+            if (len[diff] != len[0])
+              break;
+          }
+        if (maxLen < len)
+        {
+          maxLen = len;
+          *d++ = (UInt32)(len - cur);
+          *d++ = delta - 1;
+          
+          if (len == lenLimit)
+          {
+            const UInt32 pair1 = pair[1];
+            *ptr1 =
+              #ifdef USE_SON_PREFETCH
+                pair0;
+              #else
+                pair[0];
+              #endif
+            *ptr0 = pair1;
+
+            _distances[-1] = (UInt32)(d - _distances);
+
+            #ifdef USE_LONG_MATCH_OPT
+
+                if (hash == size || *hash != delta || lenLimit[diff] != lenLimit[0] || d >= limit)
+                  break;
+
+            {
+              for (;;)
+              {
+                *d++ = 2;
+                *d++ = (UInt32)(lenLimit - cur);
+                *d++ = delta - 1;
+                cur++;
+                lenLimit++;
+                // SPEC
+                _cyclicBufferPos++;
+                {
+                  // SPEC code
+                  CLzRef *dest = son + ((size_t)(_cyclicBufferPos) << 1);
+                  const CLzRef *src = dest + ((diff
+                      + (ptrdiff_t)(UInt32)((_cyclicBufferPos < delta) ? cbs : 0)) << 1);
+                  // CLzRef *ptr = son + ((size_t)(pos) << 1) - CYC_TO_POS_OFFSET * 2;
+                  #if 0
+                  *(UInt64 *)(void *)dest = *((const UInt64 *)(const void *)src);
+                  #else
+                  const UInt32 p0 = src[0];
+                  const UInt32 p1 = src[1];
+                  dest[0] = p0;
+                  dest[1] = p1;
+                  #endif
+                }
+                pos++;
+                hash++;
+                if (hash == size || *hash != delta || lenLimit[diff] != lenLimit[0] || d >= limit)
+                  break;
+              } // for() end for long matches
+            }
+            #endif
+
+            break; // break from TREE iterations
+          }
+        }
+      }
+      {
+        const UInt32 curMatch = (UInt32)pos - delta; // (UInt32)(pos + diff);
+        if (len[diff] < len[0])
+        {
+          delta = pair[1];
+          *ptr1 = curMatch;
+          ptr1 = pair + 1;
+          len1 = len;
+          if (delta >= curMatch)
+            return NULL;
+        }
+        else
+        {
+          delta = *pair;
+          *ptr0 = curMatch;
+          ptr0 = pair;
+          len0 = len;
+          if (delta >= curMatch)
+            return NULL;
+        }
+        delta = (UInt32)pos - delta;
+ 
+        if (--cutValue == 0 || delta >= cbs)
+        {
+          *ptr0 = *ptr1 = kEmptyHashValue;
+          _distances[-1] = (UInt32)(d - _distances);
+          break;
+        }
+      }
+    }
+  } // for (tree iterations)
+}
+    pos++;
+    _cyclicBufferPos++;
+    cur++;
+  }
+  while (d < limit);
+  *posRes = (UInt32)pos;
+  return d;
+}
+
+
+
+/*
+typedef UInt32 uint32plus; // size_t
+
+UInt32 * MY_FAST_CALL GetMatchesSpecN_3(uint32plus lenLimit, size_t pos, const Byte *cur, CLzRef *son,
+    UInt32 _cutValue, UInt32 *d, uint32plus _maxLen, const UInt32 *hash, const UInt32 *limit, const UInt32 *size,
+    size_t _cyclicBufferPos, UInt32 _cyclicBufferSize,
+    UInt32 *posRes)
+{
+  do // while (hash != size)
+  {
+    UInt32 delta;
+
+  #ifndef cbs
+    UInt32 cbs;
+  #endif
+
+    if (hash == size)
+      break;
+
+    delta = *hash++;
+
+    if (delta == 0)
+      return NULL;
+
+  #ifndef cbs
+    cbs = _cyclicBufferSize;
+    if ((UInt32)pos < cbs)
+    {
+      if (delta > (UInt32)pos)
+        return NULL;
+      cbs = (UInt32)pos;
+    }
+  #endif
+    
+    if (delta >= cbs)
+    {
+      CLzRef *ptr1 = son + ((size_t)_cyclicBufferPos << 1);
+      *d++ = 0;
+      ptr1[0] = kEmptyHashValue;
+      ptr1[1] = kEmptyHashValue;
+    }
+else
+{
+  CLzRef *ptr0 = son + ((size_t)_cyclicBufferPos << 1) + 1;
+  CLzRef *ptr1 = son + ((size_t)_cyclicBufferPos << 1);
+  UInt32 *_distances = ++d;
+  uint32plus len0 = 0, len1 = 0;
+  UInt32 cutValue = _cutValue;
+  uint32plus maxLen = _maxLen;
+  // lenLimit++; // const Byte *lenLimit = cur + _lenLimit;
+
+  for (LOG_ITER(g_NumIters_Tree++);;)
+  {
+    LOG_ITER(g_NumIters_Loop++);
+    {
+      // const ptrdiff_t diff = (ptrdiff_t)0 - (ptrdiff_t)delta;
+      CLzRef *pair = son + ((size_t)((ptrdiff_t)_cyclicBufferPos - delta
+          + (ptrdiff_t)(UInt32)(_cyclicBufferPos < delta ? cbs : 0)
+          ) << 1);
+      const Byte *pb = cur - delta;
+      uint32plus len = (len0 < len1 ? len0 : len1);
+
+    #ifdef USE_SON_PREFETCH
+      const UInt32 pair0 = *pair;
+    #endif
+
+      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 = len;
+          *d++ = (UInt32)len;
+          *d++ = delta - 1;
+          if (len == lenLimit)
+          {
+            {
+              const UInt32 pair1 = pair[1];
+              *ptr0 = pair1;
+              *ptr1 =
+              #ifdef USE_SON_PREFETCH
+                pair0;
+              #else
+                pair[0];
+              #endif
+            }
+
+            _distances[-1] = (UInt32)(d - _distances);
+
+            #ifdef USE_LONG_MATCH_OPT
+
+                if (hash == size || *hash != delta || pb[lenLimit] != cur[lenLimit] || d >= limit)
+                  break;
+
+            {
+              const ptrdiff_t diff = (ptrdiff_t)0 - (ptrdiff_t)delta;
+              for (;;)
+              {
+                *d++ = 2;
+                *d++ = (UInt32)lenLimit;
+                *d++ = delta - 1;
+                _cyclicBufferPos++;
+                {
+                  CLzRef *dest = son + ((size_t)_cyclicBufferPos << 1);
+                  const CLzRef *src = dest + ((diff +
+                      (ptrdiff_t)(UInt32)(_cyclicBufferPos < delta ? cbs : 0)) << 1);
+                #if 0
+                  *(UInt64 *)(void *)dest = *((const UInt64 *)(const void *)src);
+                #else
+                  const UInt32 p0 = src[0];
+                  const UInt32 p1 = src[1];
+                  dest[0] = p0;
+                  dest[1] = p1;
+                #endif
+                }
+                hash++;
+                pos++;
+                cur++;
+                pb++;
+                if (hash == size || *hash != delta || pb[lenLimit] != cur[lenLimit] || d >= limit)
+                  break;
+              }
+            }
+            #endif
+
+            break;
+          }
+        }
+      }
+      {
+        const UInt32 curMatch = (UInt32)pos - delta;
+        if (pb[len] < cur[len])
+        {
+          delta = pair[1];
+          *ptr1 = curMatch;
+          ptr1 = pair + 1;
+          len1 = len;
+        }
+        else
+        {
+          delta = *pair;
+          *ptr0 = curMatch;
+          ptr0 = pair;
+          len0 = len;
+        }
+
+        {
+          if (delta >= curMatch)
+            return NULL;
+          delta = (UInt32)pos - delta;
+          if (delta >= cbs
+              // delta >= _cyclicBufferSize || delta >= pos
+              || --cutValue == 0)
+          {
+            *ptr0 = *ptr1 = kEmptyHashValue;
+            _distances[-1] = (UInt32)(d - _distances);
+            break;
+          }
+        }
+      }
+    }
+  } // for (tree iterations)
+}
+    pos++;
+    _cyclicBufferPos++;
+    cur++;
+  }
+  while (d < limit);
+  *posRes = (UInt32)pos;
+  return d;
+}
+*/

3rdparty/lzma/src/Lzma2Dec.c

@@ -0,0 +1,489 @@
+/* Lzma2Dec.c -- LZMA2 Decoder
+2021-02-09 : Igor Pavlov : Public domain */
+
+/* #define SHOW_DEBUG_INFO */
+
+#include "Precomp.h"
+
+#ifdef SHOW_DEBUG_INFO
+#include <stdio.h>
+#endif
+
+#include <string.h>
+
+#include "Lzma2Dec.h"
+
+/*
+00000000  -  End of data
+00000001 U U  -  Uncompressed, reset dic, need reset state and set new prop
+00000010 U U  -  Uncompressed, no reset
+100uuuuu U U P P  -  LZMA, no reset
+101uuuuu U U P P  -  LZMA, reset state
+110uuuuu U U P P S  -  LZMA, reset state + set new prop
+111uuuuu U U P P S  -  LZMA, reset state + set new prop, reset dic
+
+  u, U - Unpack Size
+  P - Pack Size
+  S - Props
+*/
+
+#define LZMA2_CONTROL_COPY_RESET_DIC 1
+
+#define LZMA2_IS_UNCOMPRESSED_STATE(p) (((p)->control & (1 << 7)) == 0)
+
+#define LZMA2_LCLP_MAX 4
+#define LZMA2_DIC_SIZE_FROM_PROP(p) (((UInt32)2 | ((p) & 1)) << ((p) / 2 + 11))
+
+#ifdef SHOW_DEBUG_INFO
+#define PRF(x) x
+#else
+#define PRF(x)
+#endif
+
+typedef enum
+{
+  LZMA2_STATE_CONTROL,
+  LZMA2_STATE_UNPACK0,
+  LZMA2_STATE_UNPACK1,
+  LZMA2_STATE_PACK0,
+  LZMA2_STATE_PACK1,
+  LZMA2_STATE_PROP,
+  LZMA2_STATE_DATA,
+  LZMA2_STATE_DATA_CONT,
+  LZMA2_STATE_FINISHED,
+  LZMA2_STATE_ERROR
+} ELzma2State;
+
+static SRes Lzma2Dec_GetOldProps(Byte prop, Byte *props)
+{
+  UInt32 dicSize;
+  if (prop > 40)
+    return SZ_ERROR_UNSUPPORTED;
+  dicSize = (prop == 40) ? 0xFFFFFFFF : LZMA2_DIC_SIZE_FROM_PROP(prop);
+  props[0] = (Byte)LZMA2_LCLP_MAX;
+  props[1] = (Byte)(dicSize);
+  props[2] = (Byte)(dicSize >> 8);
+  props[3] = (Byte)(dicSize >> 16);
+  props[4] = (Byte)(dicSize >> 24);
+  return SZ_OK;
+}
+
+SRes Lzma2Dec_AllocateProbs(CLzma2Dec *p, Byte prop, ISzAllocPtr alloc)
+{
+  Byte props[LZMA_PROPS_SIZE];
+  RINOK(Lzma2Dec_GetOldProps(prop, props));
+  return LzmaDec_AllocateProbs(&p->decoder, props, LZMA_PROPS_SIZE, alloc);
+}
+
+SRes Lzma2Dec_Allocate(CLzma2Dec *p, Byte prop, ISzAllocPtr alloc)
+{
+  Byte props[LZMA_PROPS_SIZE];
+  RINOK(Lzma2Dec_GetOldProps(prop, props));
+  return LzmaDec_Allocate(&p->decoder, props, LZMA_PROPS_SIZE, alloc);
+}
+
+void Lzma2Dec_Init(CLzma2Dec *p)
+{
+  p->state = LZMA2_STATE_CONTROL;
+  p->needInitLevel = 0xE0;
+  p->isExtraMode = False;
+  p->unpackSize = 0;
+  
+  // p->decoder.dicPos = 0; // we can use it instead of full init
+  LzmaDec_Init(&p->decoder);
+}
+
+// ELzma2State
+static unsigned Lzma2Dec_UpdateState(CLzma2Dec *p, Byte b)
+{
+  switch (p->state)
+  {
+    case LZMA2_STATE_CONTROL:
+      p->isExtraMode = False;
+      p->control = b;
+      PRF(printf("\n %8X", (unsigned)p->decoder.dicPos));
+      PRF(printf(" %02X", (unsigned)b));
+      if (b == 0)
+        return LZMA2_STATE_FINISHED;
+      if (LZMA2_IS_UNCOMPRESSED_STATE(p))
+      {
+        if (b == LZMA2_CONTROL_COPY_RESET_DIC)
+          p->needInitLevel = 0xC0;
+        else if (b > 2 || p->needInitLevel == 0xE0)
+          return LZMA2_STATE_ERROR;
+      }
+      else
+      {
+        if (b < p->needInitLevel)
+          return LZMA2_STATE_ERROR;
+        p->needInitLevel = 0;
+        p->unpackSize = (UInt32)(b & 0x1F) << 16;
+      }
+      return LZMA2_STATE_UNPACK0;
+    
+    case LZMA2_STATE_UNPACK0:
+      p->unpackSize |= (UInt32)b << 8;
+      return LZMA2_STATE_UNPACK1;
+    
+    case LZMA2_STATE_UNPACK1:
+      p->unpackSize |= (UInt32)b;
+      p->unpackSize++;
+      PRF(printf(" %7u", (unsigned)p->unpackSize));
+      return LZMA2_IS_UNCOMPRESSED_STATE(p) ? LZMA2_STATE_DATA : LZMA2_STATE_PACK0;
+    
+    case LZMA2_STATE_PACK0:
+      p->packSize = (UInt32)b << 8;
+      return LZMA2_STATE_PACK1;
+
+    case LZMA2_STATE_PACK1:
+      p->packSize |= (UInt32)b;
+      p->packSize++;
+      // if (p->packSize < 5) return LZMA2_STATE_ERROR;
+      PRF(printf(" %5u", (unsigned)p->packSize));
+      return (p->control & 0x40) ? LZMA2_STATE_PROP : LZMA2_STATE_DATA;
+
+    case LZMA2_STATE_PROP:
+    {
+      unsigned lc, lp;
+      if (b >= (9 * 5 * 5))
+        return LZMA2_STATE_ERROR;
+      lc = b % 9;
+      b /= 9;
+      p->decoder.prop.pb = (Byte)(b / 5);
+      lp = b % 5;
+      if (lc + lp > LZMA2_LCLP_MAX)
+        return LZMA2_STATE_ERROR;
+      p->decoder.prop.lc = (Byte)lc;
+      p->decoder.prop.lp = (Byte)lp;
+      return LZMA2_STATE_DATA;
+    }
+  }
+  return LZMA2_STATE_ERROR;
+}
+
+static void LzmaDec_UpdateWithUncompressed(CLzmaDec *p, const Byte *src, SizeT size)
+{
+  memcpy(p->dic + p->dicPos, src, size);
+  p->dicPos += size;
+  if (p->checkDicSize == 0 && p->prop.dicSize - p->processedPos <= size)
+    p->checkDicSize = p->prop.dicSize;
+  p->processedPos += (UInt32)size;
+}
+
+void LzmaDec_InitDicAndState(CLzmaDec *p, BoolInt initDic, BoolInt initState);
+
+
+SRes Lzma2Dec_DecodeToDic(CLzma2Dec *p, SizeT dicLimit,
+    const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status)
+{
+  SizeT inSize = *srcLen;
+  *srcLen = 0;
+  *status = LZMA_STATUS_NOT_SPECIFIED;
+
+  while (p->state != LZMA2_STATE_ERROR)
+  {
+    SizeT dicPos;
+
+    if (p->state == LZMA2_STATE_FINISHED)
+    {
+      *status = LZMA_STATUS_FINISHED_WITH_MARK;
+      return SZ_OK;
+    }
+    
+    dicPos = p->decoder.dicPos;
+    
+    if (dicPos == dicLimit && finishMode == LZMA_FINISH_ANY)
+    {
+      *status = LZMA_STATUS_NOT_FINISHED;
+      return SZ_OK;
+    }
+
+    if (p->state != LZMA2_STATE_DATA && p->state != LZMA2_STATE_DATA_CONT)
+    {
+      if (*srcLen == inSize)
+      {
+        *status = LZMA_STATUS_NEEDS_MORE_INPUT;
+        return SZ_OK;
+      }
+      (*srcLen)++;
+      p->state = Lzma2Dec_UpdateState(p, *src++);
+      if (dicPos == dicLimit && p->state != LZMA2_STATE_FINISHED)
+        break;
+      continue;
+    }
+    
+    {
+      SizeT inCur = inSize - *srcLen;
+      SizeT outCur = dicLimit - dicPos;
+      ELzmaFinishMode curFinishMode = LZMA_FINISH_ANY;
+      
+      if (outCur >= p->unpackSize)
+      {
+        outCur = (SizeT)p->unpackSize;
+        curFinishMode = LZMA_FINISH_END;
+      }
+
+      if (LZMA2_IS_UNCOMPRESSED_STATE(p))
+      {
+        if (inCur == 0)
+        {
+          *status = LZMA_STATUS_NEEDS_MORE_INPUT;
+          return SZ_OK;
+        }
+
+        if (p->state == LZMA2_STATE_DATA)
+        {
+          BoolInt initDic = (p->control == LZMA2_CONTROL_COPY_RESET_DIC);
+          LzmaDec_InitDicAndState(&p->decoder, initDic, False);
+        }
+
+        if (inCur > outCur)
+          inCur = outCur;
+        if (inCur == 0)
+          break;
+
+        LzmaDec_UpdateWithUncompressed(&p->decoder, src, inCur);
+
+        src += inCur;
+        *srcLen += inCur;
+        p->unpackSize -= (UInt32)inCur;
+        p->state = (p->unpackSize == 0) ? LZMA2_STATE_CONTROL : LZMA2_STATE_DATA_CONT;
+      }
+      else
+      {
+        SRes res;
+
+        if (p->state == LZMA2_STATE_DATA)
+        {
+          BoolInt initDic = (p->control >= 0xE0);
+          BoolInt initState = (p->control >= 0xA0);
+          LzmaDec_InitDicAndState(&p->decoder, initDic, initState);
+          p->state = LZMA2_STATE_DATA_CONT;
+        }
+  
+        if (inCur > p->packSize)
+          inCur = (SizeT)p->packSize;
+        
+        res = LzmaDec_DecodeToDic(&p->decoder, dicPos + outCur, src, &inCur, curFinishMode, status);
+
+        src += inCur;
+        *srcLen += inCur;
+        p->packSize -= (UInt32)inCur;
+        outCur = p->decoder.dicPos - dicPos;
+        p->unpackSize -= (UInt32)outCur;
+
+        if (res != 0)
+          break;
+        
+        if (*status == LZMA_STATUS_NEEDS_MORE_INPUT)
+        {
+          if (p->packSize == 0)
+            break;
+          return SZ_OK;
+        }
+
+        if (inCur == 0 && outCur == 0)
+        {
+          if (*status != LZMA_STATUS_MAYBE_FINISHED_WITHOUT_MARK
+              || p->unpackSize != 0
+              || p->packSize != 0)
+            break;
+          p->state = LZMA2_STATE_CONTROL;
+        }
+        
+        *status = LZMA_STATUS_NOT_SPECIFIED;
+      }
+    }
+  }
+  
+  *status = LZMA_STATUS_NOT_SPECIFIED;
+  p->state = LZMA2_STATE_ERROR;
+  return SZ_ERROR_DATA;
+}
+
+
+
+
+ELzma2ParseStatus Lzma2Dec_Parse(CLzma2Dec *p,
+    SizeT outSize,
+    const Byte *src, SizeT *srcLen,
+    int checkFinishBlock)
+{
+  SizeT inSize = *srcLen;
+  *srcLen = 0;
+
+  while (p->state != LZMA2_STATE_ERROR)
+  {
+    if (p->state == LZMA2_STATE_FINISHED)
+      return (ELzma2ParseStatus)LZMA_STATUS_FINISHED_WITH_MARK;
+
+    if (outSize == 0 && !checkFinishBlock)
+      return (ELzma2ParseStatus)LZMA_STATUS_NOT_FINISHED;
+    
+    if (p->state != LZMA2_STATE_DATA && p->state != LZMA2_STATE_DATA_CONT)
+    {
+      if (*srcLen == inSize)
+        return (ELzma2ParseStatus)LZMA_STATUS_NEEDS_MORE_INPUT;
+      (*srcLen)++;
+
+      p->state = Lzma2Dec_UpdateState(p, *src++);
+
+      if (p->state == LZMA2_STATE_UNPACK0)
+      {
+        // if (p->decoder.dicPos != 0)
+        if (p->control == LZMA2_CONTROL_COPY_RESET_DIC || p->control >= 0xE0)
+          return LZMA2_PARSE_STATUS_NEW_BLOCK;
+        // if (outSize == 0) return LZMA_STATUS_NOT_FINISHED;
+      }
+
+      // The following code can be commented.
+      // It's not big problem, if we read additional input bytes.
+      // It will be stopped later in LZMA2_STATE_DATA / LZMA2_STATE_DATA_CONT state.
+
+      if (outSize == 0 && p->state != LZMA2_STATE_FINISHED)
+      {
+        // checkFinishBlock is true. So we expect that block must be finished,
+        // We can return LZMA_STATUS_NOT_SPECIFIED or LZMA_STATUS_NOT_FINISHED here
+        // break;
+        return (ELzma2ParseStatus)LZMA_STATUS_NOT_FINISHED;
+      }
+
+      if (p->state == LZMA2_STATE_DATA)
+        return LZMA2_PARSE_STATUS_NEW_CHUNK;
+
+      continue;
+    }
+
+    if (outSize == 0)
+      return (ELzma2ParseStatus)LZMA_STATUS_NOT_FINISHED;
+
+    {
+      SizeT inCur = inSize - *srcLen;
+
+      if (LZMA2_IS_UNCOMPRESSED_STATE(p))
+      {
+        if (inCur == 0)
+          return (ELzma2ParseStatus)LZMA_STATUS_NEEDS_MORE_INPUT;
+        if (inCur > p->unpackSize)
+          inCur = p->unpackSize;
+        if (inCur > outSize)
+          inCur = outSize;
+        p->decoder.dicPos += inCur;
+        src += inCur;
+        *srcLen += inCur;
+        outSize -= inCur;
+        p->unpackSize -= (UInt32)inCur;
+        p->state = (p->unpackSize == 0) ? LZMA2_STATE_CONTROL : LZMA2_STATE_DATA_CONT;
+      }
+      else
+      {
+        p->isExtraMode = True;
+
+        if (inCur == 0)
+        {
+          if (p->packSize != 0)
+            return (ELzma2ParseStatus)LZMA_STATUS_NEEDS_MORE_INPUT;
+        }
+        else if (p->state == LZMA2_STATE_DATA)
+        {
+          p->state = LZMA2_STATE_DATA_CONT;
+          if (*src != 0)
+          {
+            // first byte of lzma chunk must be Zero
+            *srcLen += 1;
+            p->packSize--;
+            break;
+          }
+        }
+  
+        if (inCur > p->packSize)
+          inCur = (SizeT)p->packSize;
+
+        src += inCur;
+        *srcLen += inCur;
+        p->packSize -= (UInt32)inCur;
+
+        if (p->packSize == 0)
+        {
+          SizeT rem = outSize;
+          if (rem > p->unpackSize)
+            rem = p->unpackSize;
+          p->decoder.dicPos += rem;
+          p->unpackSize -= (UInt32)rem;
+          outSize -= rem;
+          if (p->unpackSize == 0)
+            p->state = LZMA2_STATE_CONTROL;
+        }
+      }
+    }
+  }
+  
+  p->state = LZMA2_STATE_ERROR;
+  return (ELzma2ParseStatus)LZMA_STATUS_NOT_SPECIFIED;
+}
+
+
+
+
+SRes Lzma2Dec_DecodeToBuf(CLzma2Dec *p, Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen, ELzmaFinishMode finishMode, ELzmaStatus *status)
+{
+  SizeT outSize = *destLen, inSize = *srcLen;
+  *srcLen = *destLen = 0;
+  
+  for (;;)
+  {
+    SizeT inCur = inSize, outCur, dicPos;
+    ELzmaFinishMode curFinishMode;
+    SRes res;
+    
+    if (p->decoder.dicPos == p->decoder.dicBufSize)
+      p->decoder.dicPos = 0;
+    dicPos = p->decoder.dicPos;
+    curFinishMode = LZMA_FINISH_ANY;
+    outCur = p->decoder.dicBufSize - dicPos;
+    
+    if (outCur >= outSize)
+    {
+      outCur = outSize;
+      curFinishMode = finishMode;
+    }
+
+    res = Lzma2Dec_DecodeToDic(p, dicPos + outCur, src, &inCur, curFinishMode, status);
+    
+    src += inCur;
+    inSize -= inCur;
+    *srcLen += inCur;
+    outCur = p->decoder.dicPos - dicPos;
+    memcpy(dest, p->decoder.dic + dicPos, outCur);
+    dest += outCur;
+    outSize -= outCur;
+    *destLen += outCur;
+    if (res != 0)
+      return res;
+    if (outCur == 0 || outSize == 0)
+      return SZ_OK;
+  }
+}
+
+
+SRes Lzma2Decode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen,
+    Byte prop, ELzmaFinishMode finishMode, ELzmaStatus *status, ISzAllocPtr alloc)
+{
+  CLzma2Dec p;
+  SRes res;
+  SizeT outSize = *destLen, inSize = *srcLen;
+  *destLen = *srcLen = 0;
+  *status = LZMA_STATUS_NOT_SPECIFIED;
+  Lzma2Dec_Construct(&p);
+  RINOK(Lzma2Dec_AllocateProbs(&p, prop, alloc));
+  p.decoder.dic = dest;
+  p.decoder.dicBufSize = outSize;
+  Lzma2Dec_Init(&p);
+  *srcLen = inSize;
+  res = Lzma2Dec_DecodeToDic(&p, outSize, src, srcLen, finishMode, status);
+  *destLen = p.decoder.dicPos;
+  if (res == SZ_OK && *status == LZMA_STATUS_NEEDS_MORE_INPUT)
+    res = SZ_ERROR_INPUT_EOF;
+  Lzma2Dec_FreeProbs(&p, alloc);
+  return res;
+}

3rdparty/lzma/src/Lzma2Enc.c

@@ -0,0 +1,803 @@
+/* Lzma2Enc.c -- LZMA2 Encoder
+2021-02-09 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+/* #define _7ZIP_ST */
+
+#include "Lzma2Enc.h"
+
+#ifndef _7ZIP_ST
+#include "MtCoder.h"
+#else
+#define MTCODER__THREADS_MAX 1
+#endif
+
+#define LZMA2_CONTROL_LZMA (1 << 7)
+#define LZMA2_CONTROL_COPY_NO_RESET 2
+#define LZMA2_CONTROL_COPY_RESET_DIC 1
+#define LZMA2_CONTROL_EOF 0
+
+#define LZMA2_LCLP_MAX 4
+
+#define LZMA2_DIC_SIZE_FROM_PROP(p) (((UInt32)2 | ((p) & 1)) << ((p) / 2 + 11))
+
+#define LZMA2_PACK_SIZE_MAX (1 << 16)
+#define LZMA2_COPY_CHUNK_SIZE LZMA2_PACK_SIZE_MAX
+#define LZMA2_UNPACK_SIZE_MAX (1 << 21)
+#define LZMA2_KEEP_WINDOW_SIZE LZMA2_UNPACK_SIZE_MAX
+
+#define LZMA2_CHUNK_SIZE_COMPRESSED_MAX ((1 << 16) + 16)
+
+
+#define PRF(x) /* x */
+
+
+/* ---------- CLimitedSeqInStream ---------- */
+
+typedef struct
+{
+  ISeqInStream vt;
+  ISeqInStream *realStream;
+  UInt64 limit;
+  UInt64 processed;
+  int finished;
+} CLimitedSeqInStream;
+
+static void LimitedSeqInStream_Init(CLimitedSeqInStream *p)
+{
+  p->limit = (UInt64)(Int64)-1;
+  p->processed = 0;
+  p->finished = 0;
+}
+
+static SRes LimitedSeqInStream_Read(const ISeqInStream *pp, void *data, size_t *size)
+{
+  CLimitedSeqInStream *p = CONTAINER_FROM_VTBL(pp, CLimitedSeqInStream, vt);
+  size_t size2 = *size;
+  SRes res = SZ_OK;
+  
+  if (p->limit != (UInt64)(Int64)-1)
+  {
+    UInt64 rem = p->limit - p->processed;
+    if (size2 > rem)
+      size2 = (size_t)rem;
+  }
+  if (size2 != 0)
+  {
+    res = ISeqInStream_Read(p->realStream, data, &size2);
+    p->finished = (size2 == 0 ? 1 : 0);
+    p->processed += size2;
+  }
+  *size = size2;
+  return res;
+}
+
+
+/* ---------- CLzma2EncInt ---------- */
+
+typedef struct
+{
+  CLzmaEncHandle enc;
+  Byte propsAreSet;
+  Byte propsByte;
+  Byte needInitState;
+  Byte needInitProp;
+  UInt64 srcPos;
+} CLzma2EncInt;
+
+
+static SRes Lzma2EncInt_InitStream(CLzma2EncInt *p, const CLzma2EncProps *props)
+{
+  if (!p->propsAreSet)
+  {
+    SizeT propsSize = LZMA_PROPS_SIZE;
+    Byte propsEncoded[LZMA_PROPS_SIZE];
+    RINOK(LzmaEnc_SetProps(p->enc, &props->lzmaProps));
+    RINOK(LzmaEnc_WriteProperties(p->enc, propsEncoded, &propsSize));
+    p->propsByte = propsEncoded[0];
+    p->propsAreSet = True;
+  }
+  return SZ_OK;
+}
+
+static void Lzma2EncInt_InitBlock(CLzma2EncInt *p)
+{
+  p->srcPos = 0;
+  p->needInitState = True;
+  p->needInitProp = True;
+}
+
+
+SRes LzmaEnc_PrepareForLzma2(CLzmaEncHandle pp, ISeqInStream *inStream, UInt32 keepWindowSize,
+    ISzAllocPtr alloc, ISzAllocPtr allocBig);
+SRes LzmaEnc_MemPrepare(CLzmaEncHandle pp, const Byte *src, SizeT srcLen,
+    UInt32 keepWindowSize, ISzAllocPtr alloc, ISzAllocPtr allocBig);
+SRes LzmaEnc_CodeOneMemBlock(CLzmaEncHandle pp, BoolInt reInit,
+    Byte *dest, size_t *destLen, UInt32 desiredPackSize, UInt32 *unpackSize);
+const Byte *LzmaEnc_GetCurBuf(CLzmaEncHandle pp);
+void LzmaEnc_Finish(CLzmaEncHandle pp);
+void LzmaEnc_SaveState(CLzmaEncHandle pp);
+void LzmaEnc_RestoreState(CLzmaEncHandle pp);
+
+/*
+UInt32 LzmaEnc_GetNumAvailableBytes(CLzmaEncHandle pp);
+*/
+
+static SRes Lzma2EncInt_EncodeSubblock(CLzma2EncInt *p, Byte *outBuf,
+    size_t *packSizeRes, ISeqOutStream *outStream)
+{
+  size_t packSizeLimit = *packSizeRes;
+  size_t packSize = packSizeLimit;
+  UInt32 unpackSize = LZMA2_UNPACK_SIZE_MAX;
+  unsigned lzHeaderSize = 5 + (p->needInitProp ? 1 : 0);
+  BoolInt useCopyBlock;
+  SRes res;
+
+  *packSizeRes = 0;
+  if (packSize < lzHeaderSize)
+    return SZ_ERROR_OUTPUT_EOF;
+  packSize -= lzHeaderSize;
+  
+  LzmaEnc_SaveState(p->enc);
+  res = LzmaEnc_CodeOneMemBlock(p->enc, p->needInitState,
+      outBuf + lzHeaderSize, &packSize, LZMA2_PACK_SIZE_MAX, &unpackSize);
+  
+  PRF(printf("\npackSize = %7d unpackSize = %7d  ", packSize, unpackSize));
+
+  if (unpackSize == 0)
+    return res;
+
+  if (res == SZ_OK)
+    useCopyBlock = (packSize + 2 >= unpackSize || packSize > (1 << 16));
+  else
+  {
+    if (res != SZ_ERROR_OUTPUT_EOF)
+      return res;
+    res = SZ_OK;
+    useCopyBlock = True;
+  }
+
+  if (useCopyBlock)
+  {
+    size_t destPos = 0;
+    PRF(printf("################# COPY           "));
+
+    while (unpackSize > 0)
+    {
+      UInt32 u = (unpackSize < LZMA2_COPY_CHUNK_SIZE) ? unpackSize : LZMA2_COPY_CHUNK_SIZE;
+      if (packSizeLimit - destPos < u + 3)
+        return SZ_ERROR_OUTPUT_EOF;
+      outBuf[destPos++] = (Byte)(p->srcPos == 0 ? LZMA2_CONTROL_COPY_RESET_DIC : LZMA2_CONTROL_COPY_NO_RESET);
+      outBuf[destPos++] = (Byte)((u - 1) >> 8);
+      outBuf[destPos++] = (Byte)(u - 1);
+      memcpy(outBuf + destPos, LzmaEnc_GetCurBuf(p->enc) - unpackSize, u);
+      unpackSize -= u;
+      destPos += u;
+      p->srcPos += u;
+      
+      if (outStream)
+      {
+        *packSizeRes += destPos;
+        if (ISeqOutStream_Write(outStream, outBuf, destPos) != destPos)
+          return SZ_ERROR_WRITE;
+        destPos = 0;
+      }
+      else
+        *packSizeRes = destPos;
+      /* needInitState = True; */
+    }
+    
+    LzmaEnc_RestoreState(p->enc);
+    return SZ_OK;
+  }
+
+  {
+    size_t destPos = 0;
+    UInt32 u = unpackSize - 1;
+    UInt32 pm = (UInt32)(packSize - 1);
+    unsigned mode = (p->srcPos == 0) ? 3 : (p->needInitState ? (p->needInitProp ? 2 : 1) : 0);
+
+    PRF(printf("               "));
+
+    outBuf[destPos++] = (Byte)(LZMA2_CONTROL_LZMA | (mode << 5) | ((u >> 16) & 0x1F));
+    outBuf[destPos++] = (Byte)(u >> 8);
+    outBuf[destPos++] = (Byte)u;
+    outBuf[destPos++] = (Byte)(pm >> 8);
+    outBuf[destPos++] = (Byte)pm;
+    
+    if (p->needInitProp)
+      outBuf[destPos++] = p->propsByte;
+    
+    p->needInitProp = False;
+    p->needInitState = False;
+    destPos += packSize;
+    p->srcPos += unpackSize;
+
+    if (outStream)
+      if (ISeqOutStream_Write(outStream, outBuf, destPos) != destPos)
+        return SZ_ERROR_WRITE;
+    
+    *packSizeRes = destPos;
+    return SZ_OK;
+  }
+}
+
+
+/* ---------- Lzma2 Props ---------- */
+
+void Lzma2EncProps_Init(CLzma2EncProps *p)
+{
+  LzmaEncProps_Init(&p->lzmaProps);
+  p->blockSize = LZMA2_ENC_PROPS__BLOCK_SIZE__AUTO;
+  p->numBlockThreads_Reduced = -1;
+  p->numBlockThreads_Max = -1;
+  p->numTotalThreads = -1;
+}
+
+void Lzma2EncProps_Normalize(CLzma2EncProps *p)
+{
+  UInt64 fileSize;
+  int t1, t1n, t2, t2r, t3;
+  {
+    CLzmaEncProps lzmaProps = p->lzmaProps;
+    LzmaEncProps_Normalize(&lzmaProps);
+    t1n = lzmaProps.numThreads;
+  }
+
+  t1 = p->lzmaProps.numThreads;
+  t2 = p->numBlockThreads_Max;
+  t3 = p->numTotalThreads;
+
+  if (t2 > MTCODER__THREADS_MAX)
+    t2 = MTCODER__THREADS_MAX;
+
+  if (t3 <= 0)
+  {
+    if (t2 <= 0)
+      t2 = 1;
+    t3 = t1n * t2;
+  }
+  else if (t2 <= 0)
+  {
+    t2 = t3 / t1n;
+    if (t2 == 0)
+    {
+      t1 = 1;
+      t2 = t3;
+    }
+    if (t2 > MTCODER__THREADS_MAX)
+      t2 = MTCODER__THREADS_MAX;
+  }
+  else if (t1 <= 0)
+  {
+    t1 = t3 / t2;
+    if (t1 == 0)
+      t1 = 1;
+  }
+  else
+    t3 = t1n * t2;
+
+  p->lzmaProps.numThreads = t1;
+
+  t2r = t2;
+
+  fileSize = p->lzmaProps.reduceSize;
+
+  if (   p->blockSize != LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID
+      && p->blockSize != LZMA2_ENC_PROPS__BLOCK_SIZE__AUTO
+      && (p->blockSize < fileSize || fileSize == (UInt64)(Int64)-1))
+    p->lzmaProps.reduceSize = p->blockSize;
+
+  LzmaEncProps_Normalize(&p->lzmaProps);
+
+  p->lzmaProps.reduceSize = fileSize;
+
+  t1 = p->lzmaProps.numThreads;
+
+  if (p->blockSize == LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID)
+  {
+    t2r = t2 = 1;
+    t3 = t1;
+  }
+  else if (p->blockSize == LZMA2_ENC_PROPS__BLOCK_SIZE__AUTO && t2 <= 1)
+  {
+    /* if there is no block multi-threading, we use SOLID block */
+    p->blockSize = LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID;
+  }
+  else
+  {
+    if (p->blockSize == LZMA2_ENC_PROPS__BLOCK_SIZE__AUTO)
+    {
+      const UInt32 kMinSize = (UInt32)1 << 20;
+      const UInt32 kMaxSize = (UInt32)1 << 28;
+      const UInt32 dictSize = p->lzmaProps.dictSize;
+      UInt64 blockSize = (UInt64)dictSize << 2;
+      if (blockSize < kMinSize) blockSize = kMinSize;
+      if (blockSize > kMaxSize) blockSize = kMaxSize;
+      if (blockSize < dictSize) blockSize = dictSize;
+      blockSize += (kMinSize - 1);
+      blockSize &= ~(UInt64)(kMinSize - 1);
+      p->blockSize = blockSize;
+    }
+    
+    if (t2 > 1 && fileSize != (UInt64)(Int64)-1)
+    {
+      UInt64 numBlocks = fileSize / p->blockSize;
+      if (numBlocks * p->blockSize != fileSize)
+        numBlocks++;
+      if (numBlocks < (unsigned)t2)
+      {
+        t2r = (int)numBlocks;
+        if (t2r == 0)
+          t2r = 1;
+        t3 = t1 * t2r;
+      }
+    }
+  }
+  
+  p->numBlockThreads_Max = t2;
+  p->numBlockThreads_Reduced = t2r;
+  p->numTotalThreads = t3;
+}
+
+
+static SRes Progress(ICompressProgress *p, UInt64 inSize, UInt64 outSize)
+{
+  return (p && ICompressProgress_Progress(p, inSize, outSize) != SZ_OK) ? SZ_ERROR_PROGRESS : SZ_OK;
+}
+
+
+/* ---------- Lzma2 ---------- */
+
+typedef struct
+{
+  Byte propEncoded;
+  CLzma2EncProps props;
+  UInt64 expectedDataSize;
+  
+  Byte *tempBufLzma;
+
+  ISzAllocPtr alloc;
+  ISzAllocPtr allocBig;
+
+  CLzma2EncInt coders[MTCODER__THREADS_MAX];
+
+  #ifndef _7ZIP_ST
+  
+  ISeqOutStream *outStream;
+  Byte *outBuf;
+  size_t outBuf_Rem;   /* remainder in outBuf */
+
+  size_t outBufSize;   /* size of allocated outBufs[i] */
+  size_t outBufsDataSizes[MTCODER__BLOCKS_MAX];
+  BoolInt mtCoder_WasConstructed;
+  CMtCoder mtCoder;
+  Byte *outBufs[MTCODER__BLOCKS_MAX];
+
+  #endif
+
+} CLzma2Enc;
+
+
+
+CLzma2EncHandle Lzma2Enc_Create(ISzAllocPtr alloc, ISzAllocPtr allocBig)
+{
+  CLzma2Enc *p = (CLzma2Enc *)ISzAlloc_Alloc(alloc, sizeof(CLzma2Enc));
+  if (!p)
+    return NULL;
+  Lzma2EncProps_Init(&p->props);
+  Lzma2EncProps_Normalize(&p->props);
+  p->expectedDataSize = (UInt64)(Int64)-1;
+  p->tempBufLzma = NULL;
+  p->alloc = alloc;
+  p->allocBig = allocBig;
+  {
+    unsigned i;
+    for (i = 0; i < MTCODER__THREADS_MAX; i++)
+      p->coders[i].enc = NULL;
+  }
+  
+  #ifndef _7ZIP_ST
+  p->mtCoder_WasConstructed = False;
+  {
+    unsigned i;
+    for (i = 0; i < MTCODER__BLOCKS_MAX; i++)
+      p->outBufs[i] = NULL;
+    p->outBufSize = 0;
+  }
+  #endif
+
+  return p;
+}
+
+
+#ifndef _7ZIP_ST
+
+static void Lzma2Enc_FreeOutBufs(CLzma2Enc *p)
+{
+  unsigned i;
+  for (i = 0; i < MTCODER__BLOCKS_MAX; i++)
+    if (p->outBufs[i])
+    {
+      ISzAlloc_Free(p->alloc, p->outBufs[i]);
+      p->outBufs[i] = NULL;
+    }
+  p->outBufSize = 0;
+}
+
+#endif
+
+
+void Lzma2Enc_Destroy(CLzma2EncHandle pp)
+{
+  CLzma2Enc *p = (CLzma2Enc *)pp;
+  unsigned i;
+  for (i = 0; i < MTCODER__THREADS_MAX; i++)
+  {
+    CLzma2EncInt *t = &p->coders[i];
+    if (t->enc)
+    {
+      LzmaEnc_Destroy(t->enc, p->alloc, p->allocBig);
+      t->enc = NULL;
+    }
+  }
+
+
+  #ifndef _7ZIP_ST
+  if (p->mtCoder_WasConstructed)
+  {
+    MtCoder_Destruct(&p->mtCoder);
+    p->mtCoder_WasConstructed = False;
+  }
+  Lzma2Enc_FreeOutBufs(p);
+  #endif
+
+  ISzAlloc_Free(p->alloc, p->tempBufLzma);
+  p->tempBufLzma = NULL;
+
+  ISzAlloc_Free(p->alloc, pp);
+}
+
+
+SRes Lzma2Enc_SetProps(CLzma2EncHandle pp, const CLzma2EncProps *props)
+{
+  CLzma2Enc *p = (CLzma2Enc *)pp;
+  CLzmaEncProps lzmaProps = props->lzmaProps;
+  LzmaEncProps_Normalize(&lzmaProps);
+  if (lzmaProps.lc + lzmaProps.lp > LZMA2_LCLP_MAX)
+    return SZ_ERROR_PARAM;
+  p->props = *props;
+  Lzma2EncProps_Normalize(&p->props);
+  return SZ_OK;
+}
+
+
+void Lzma2Enc_SetDataSize(CLzmaEncHandle pp, UInt64 expectedDataSiize)
+{
+  CLzma2Enc *p = (CLzma2Enc *)pp;
+  p->expectedDataSize = expectedDataSiize;
+}
+
+
+Byte Lzma2Enc_WriteProperties(CLzma2EncHandle pp)
+{
+  CLzma2Enc *p = (CLzma2Enc *)pp;
+  unsigned i;
+  UInt32 dicSize = LzmaEncProps_GetDictSize(&p->props.lzmaProps);
+  for (i = 0; i < 40; i++)
+    if (dicSize <= LZMA2_DIC_SIZE_FROM_PROP(i))
+      break;
+  return (Byte)i;
+}
+
+
+static SRes Lzma2Enc_EncodeMt1(
+    CLzma2Enc *me,
+    CLzma2EncInt *p,
+    ISeqOutStream *outStream,
+    Byte *outBuf, size_t *outBufSize,
+    ISeqInStream *inStream,
+    const Byte *inData, size_t inDataSize,
+    int finished,
+    ICompressProgress *progress)
+{
+  UInt64 unpackTotal = 0;
+  UInt64 packTotal = 0;
+  size_t outLim = 0;
+  CLimitedSeqInStream limitedInStream;
+
+  if (outBuf)
+  {
+    outLim = *outBufSize;
+    *outBufSize = 0;
+  }
+
+  if (!p->enc)
+  {
+    p->propsAreSet = False;
+    p->enc = LzmaEnc_Create(me->alloc);
+    if (!p->enc)
+      return SZ_ERROR_MEM;
+  }
+
+  limitedInStream.realStream = inStream;
+  if (inStream)
+  {
+    limitedInStream.vt.Read = LimitedSeqInStream_Read;
+  }
+  
+  if (!outBuf)
+  {
+    // outStream version works only in one thread. So we use CLzma2Enc::tempBufLzma
+    if (!me->tempBufLzma)
+    {
+      me->tempBufLzma = (Byte *)ISzAlloc_Alloc(me->alloc, LZMA2_CHUNK_SIZE_COMPRESSED_MAX);
+      if (!me->tempBufLzma)
+        return SZ_ERROR_MEM;
+    }
+  }
+
+  RINOK(Lzma2EncInt_InitStream(p, &me->props));
+
+  for (;;)
+  {
+    SRes res = SZ_OK;
+    size_t inSizeCur = 0;
+
+    Lzma2EncInt_InitBlock(p);
+    
+    LimitedSeqInStream_Init(&limitedInStream);
+    limitedInStream.limit = me->props.blockSize;
+
+    if (inStream)
+    {
+      UInt64 expected = (UInt64)(Int64)-1;
+      // inStream version works only in one thread. So we use CLzma2Enc::expectedDataSize
+      if (me->expectedDataSize != (UInt64)(Int64)-1
+          && me->expectedDataSize >= unpackTotal)
+        expected = me->expectedDataSize - unpackTotal;
+      if (me->props.blockSize != LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID
+          && expected > me->props.blockSize)
+        expected = (size_t)me->props.blockSize;
+
+      LzmaEnc_SetDataSize(p->enc, expected);
+
+      RINOK(LzmaEnc_PrepareForLzma2(p->enc,
+          &limitedInStream.vt,
+          LZMA2_KEEP_WINDOW_SIZE,
+          me->alloc,
+          me->allocBig));
+    }
+    else
+    {
+      inSizeCur = inDataSize - (size_t)unpackTotal;
+      if (me->props.blockSize != LZMA2_ENC_PROPS__BLOCK_SIZE__SOLID
+          && inSizeCur > me->props.blockSize)
+        inSizeCur = (size_t)me->props.blockSize;
+    
+      // LzmaEnc_SetDataSize(p->enc, inSizeCur);
+      
+      RINOK(LzmaEnc_MemPrepare(p->enc,
+          inData + (size_t)unpackTotal, inSizeCur,
+          LZMA2_KEEP_WINDOW_SIZE,
+          me->alloc,
+          me->allocBig));
+    }
+
+    for (;;)
+    {
+      size_t packSize = LZMA2_CHUNK_SIZE_COMPRESSED_MAX;
+      if (outBuf)
+        packSize = outLim - (size_t)packTotal;
+      
+      res = Lzma2EncInt_EncodeSubblock(p,
+          outBuf ? outBuf + (size_t)packTotal : me->tempBufLzma, &packSize,
+          outBuf ? NULL : outStream);
+      
+      if (res != SZ_OK)
+        break;
+
+      packTotal += packSize;
+      if (outBuf)
+        *outBufSize = (size_t)packTotal;
+      
+      res = Progress(progress, unpackTotal + p->srcPos, packTotal);
+      if (res != SZ_OK)
+        break;
+
+      /*
+      if (LzmaEnc_GetNumAvailableBytes(p->enc) == 0)
+        break;
+      */
+
+      if (packSize == 0)
+        break;
+    }
+    
+    LzmaEnc_Finish(p->enc);
+    
+    unpackTotal += p->srcPos;
+    
+    RINOK(res);
+
+    if (p->srcPos != (inStream ? limitedInStream.processed : inSizeCur))
+      return SZ_ERROR_FAIL;
+    
+    if (inStream ? limitedInStream.finished : (unpackTotal == inDataSize))
+    {
+      if (finished)
+      {
+        if (outBuf)
+        {
+          const size_t destPos = *outBufSize;
+          if (destPos >= outLim)
+            return SZ_ERROR_OUTPUT_EOF;
+          outBuf[destPos] = LZMA2_CONTROL_EOF; // 0
+          *outBufSize = destPos + 1;
+        }
+        else
+        {
+          const Byte b = LZMA2_CONTROL_EOF; // 0;
+          if (ISeqOutStream_Write(outStream, &b, 1) != 1)
+            return SZ_ERROR_WRITE;
+        }
+      }
+      return SZ_OK;
+    }
+  }
+}
+
+
+
+#ifndef _7ZIP_ST
+
+static SRes Lzma2Enc_MtCallback_Code(void *pp, unsigned coderIndex, unsigned outBufIndex,
+    const Byte *src, size_t srcSize, int finished)
+{
+  CLzma2Enc *me = (CLzma2Enc *)pp;
+  size_t destSize = me->outBufSize;
+  SRes res;
+  CMtProgressThunk progressThunk;
+
+  Byte *dest = me->outBufs[outBufIndex];
+
+  me->outBufsDataSizes[outBufIndex] = 0;
+
+  if (!dest)
+  {
+    dest = (Byte *)ISzAlloc_Alloc(me->alloc, me->outBufSize);
+    if (!dest)
+      return SZ_ERROR_MEM;
+    me->outBufs[outBufIndex] = dest;
+  }
+
+  MtProgressThunk_CreateVTable(&progressThunk);
+  progressThunk.mtProgress = &me->mtCoder.mtProgress;
+  progressThunk.inSize = 0;
+  progressThunk.outSize = 0;
+
+  res = Lzma2Enc_EncodeMt1(me,
+      &me->coders[coderIndex],
+      NULL, dest, &destSize,
+      NULL, src, srcSize,
+      finished,
+      &progressThunk.vt);
+
+  me->outBufsDataSizes[outBufIndex] = destSize;
+
+  return res;
+}
+
+
+static SRes Lzma2Enc_MtCallback_Write(void *pp, unsigned outBufIndex)
+{
+  CLzma2Enc *me = (CLzma2Enc *)pp;
+  size_t size = me->outBufsDataSizes[outBufIndex];
+  const Byte *data = me->outBufs[outBufIndex];
+  
+  if (me->outStream)
+    return ISeqOutStream_Write(me->outStream, data, size) == size ? SZ_OK : SZ_ERROR_WRITE;
+  
+  if (size > me->outBuf_Rem)
+    return SZ_ERROR_OUTPUT_EOF;
+  memcpy(me->outBuf, data, size);
+  me->outBuf_Rem -= size;
+  me->outBuf += size;
+  return SZ_OK;
+}
+
+#endif
+
+
+
+SRes Lzma2Enc_Encode2(CLzma2EncHandle pp,
+    ISeqOutStream *outStream,
+    Byte *outBuf, size_t *outBufSize,
+    ISeqInStream *inStream,
+    const Byte *inData, size_t inDataSize,
+    ICompressProgress *progress)
+{
+  CLzma2Enc *p = (CLzma2Enc *)pp;
+
+  if (inStream && inData)
+    return SZ_ERROR_PARAM;
+
+  if (outStream && outBuf)
+    return SZ_ERROR_PARAM;
+
+  {
+    unsigned i;
+    for (i = 0; i < MTCODER__THREADS_MAX; i++)
+      p->coders[i].propsAreSet = False;
+  }
+
+  #ifndef _7ZIP_ST
+  
+  if (p->props.numBlockThreads_Reduced > 1)
+  {
+    IMtCoderCallback2 vt;
+
+    if (!p->mtCoder_WasConstructed)
+    {
+      p->mtCoder_WasConstructed = True;
+      MtCoder_Construct(&p->mtCoder);
+    }
+
+    vt.Code = Lzma2Enc_MtCallback_Code;
+    vt.Write = Lzma2Enc_MtCallback_Write;
+
+    p->outStream = outStream;
+    p->outBuf = NULL;
+    p->outBuf_Rem = 0;
+    if (!outStream)
+    {
+      p->outBuf = outBuf;
+      p->outBuf_Rem = *outBufSize;
+      *outBufSize = 0;
+    }
+
+    p->mtCoder.allocBig = p->allocBig;
+    p->mtCoder.progress = progress;
+    p->mtCoder.inStream = inStream;
+    p->mtCoder.inData = inData;
+    p->mtCoder.inDataSize = inDataSize;
+    p->mtCoder.mtCallback = &vt;
+    p->mtCoder.mtCallbackObject = p;
+
+    p->mtCoder.blockSize = (size_t)p->props.blockSize;
+    if (p->mtCoder.blockSize != p->props.blockSize)
+      return SZ_ERROR_PARAM; /* SZ_ERROR_MEM */
+
+    {
+      size_t destBlockSize = p->mtCoder.blockSize + (p->mtCoder.blockSize >> 10) + 16;
+      if (destBlockSize < p->mtCoder.blockSize)
+        return SZ_ERROR_PARAM;
+      if (p->outBufSize != destBlockSize)
+        Lzma2Enc_FreeOutBufs(p);
+      p->outBufSize = destBlockSize;
+    }
+
+    p->mtCoder.numThreadsMax = (unsigned)p->props.numBlockThreads_Max;
+    p->mtCoder.expectedDataSize = p->expectedDataSize;
+    
+    {
+      SRes res = MtCoder_Code(&p->mtCoder);
+      if (!outStream)
+        *outBufSize = (size_t)(p->outBuf - outBuf);
+      return res;
+    }
+  }
+
+  #endif
+
+
+  return Lzma2Enc_EncodeMt1(p,
+      &p->coders[0],
+      outStream, outBuf, outBufSize,
+      inStream, inData, inDataSize,
+      True, /* finished */
+      progress);
+}

3rdparty/lzma/src/Lzma86Dec.c

@@ -0,0 +1,54 @@
+/* Lzma86Dec.c -- LZMA + x86 (BCJ) Filter Decoder
+2016-05-16 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Lzma86.h"
+
+#include "Alloc.h"
+#include "Bra.h"
+#include "LzmaDec.h"
+
+SRes Lzma86_GetUnpackSize(const Byte *src, SizeT srcLen, UInt64 *unpackSize)
+{
+  unsigned i;
+  if (srcLen < LZMA86_HEADER_SIZE)
+    return SZ_ERROR_INPUT_EOF;
+  *unpackSize = 0;
+  for (i = 0; i < sizeof(UInt64); i++)
+    *unpackSize += ((UInt64)src[LZMA86_SIZE_OFFSET + i]) << (8 * i);
+  return SZ_OK;
+}
+
+SRes Lzma86_Decode(Byte *dest, SizeT *destLen, const Byte *src, SizeT *srcLen)
+{
+  SRes res;
+  int useFilter;
+  SizeT inSizePure;
+  ELzmaStatus status;
+
+  if (*srcLen < LZMA86_HEADER_SIZE)
+    return SZ_ERROR_INPUT_EOF;
+
+  useFilter = src[0];
+
+  if (useFilter > 1)
+  {
+    *destLen = 0;
+    return SZ_ERROR_UNSUPPORTED;
+  }
+
+  inSizePure = *srcLen - LZMA86_HEADER_SIZE;
+  res = LzmaDecode(dest, destLen, src + LZMA86_HEADER_SIZE, &inSizePure,
+      src + 1, LZMA_PROPS_SIZE, LZMA_FINISH_ANY, &status, &g_Alloc);
+  *srcLen = inSizePure + LZMA86_HEADER_SIZE;
+  if (res != SZ_OK)
+    return res;
+  if (useFilter == 1)
+  {
+    UInt32 x86State;
+    x86_Convert_Init(x86State);
+    x86_Convert(dest, *destLen, 0, &x86State, 0);
+  }
+  return SZ_OK;
+}

3rdparty/lzma/src/Lzma86Enc.c

@@ -0,0 +1,104 @@
+/* Lzma86Enc.c -- LZMA + x86 (BCJ) Filter Encoder
+2018-07-04 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "Lzma86.h"
+
+#include "Alloc.h"
+#include "Bra.h"
+#include "LzmaEnc.h"
+
+int Lzma86_Encode(Byte *dest, size_t *destLen, const Byte *src, size_t srcLen,
+    int level, UInt32 dictSize, int filterMode)
+{
+  size_t outSize2 = *destLen;
+  Byte *filteredStream;
+  BoolInt useFilter;
+  int mainResult = SZ_ERROR_OUTPUT_EOF;
+  CLzmaEncProps props;
+  LzmaEncProps_Init(&props);
+  props.level = level;
+  props.dictSize = dictSize;
+  
+  *destLen = 0;
+  if (outSize2 < LZMA86_HEADER_SIZE)
+    return SZ_ERROR_OUTPUT_EOF;
+
+  {
+    int i;
+    UInt64 t = srcLen;
+    for (i = 0; i < 8; i++, t >>= 8)
+      dest[LZMA86_SIZE_OFFSET + i] = (Byte)t;
+  }
+
+  filteredStream = 0;
+  useFilter = (filterMode != SZ_FILTER_NO);
+  if (useFilter)
+  {
+    if (srcLen != 0)
+    {
+      filteredStream = (Byte *)MyAlloc(srcLen);
+      if (filteredStream == 0)
+        return SZ_ERROR_MEM;
+      memcpy(filteredStream, src, srcLen);
+    }
+    {
+      UInt32 x86State;
+      x86_Convert_Init(x86State);
+      x86_Convert(filteredStream, srcLen, 0, &x86State, 1);
+    }
+  }
+
+  {
+    size_t minSize = 0;
+    BoolInt bestIsFiltered = False;
+
+    /* passes for SZ_FILTER_AUTO:
+        0 - BCJ + LZMA
+        1 - LZMA
+        2 - BCJ + LZMA agaian, if pass 0 (BCJ + LZMA) is better.
+    */
+    int numPasses = (filterMode == SZ_FILTER_AUTO) ? 3 : 1;
+
+    int i;
+    for (i = 0; i < numPasses; i++)
+    {
+      size_t outSizeProcessed = outSize2 - LZMA86_HEADER_SIZE;
+      size_t outPropsSize = 5;
+      SRes curRes;
+      BoolInt curModeIsFiltered = (numPasses > 1 && i == numPasses - 1);
+      if (curModeIsFiltered && !bestIsFiltered)
+        break;
+      if (useFilter && i == 0)
+        curModeIsFiltered = True;
+      
+      curRes = LzmaEncode(dest + LZMA86_HEADER_SIZE, &outSizeProcessed,
+          curModeIsFiltered ? filteredStream : src, srcLen,
+          &props, dest + 1, &outPropsSize, 0,
+          NULL, &g_Alloc, &g_Alloc);
+      
+      if (curRes != SZ_ERROR_OUTPUT_EOF)
+      {
+        if (curRes != SZ_OK)
+        {
+          mainResult = curRes;
+          break;
+        }
+        if (outSizeProcessed <= minSize || mainResult != SZ_OK)
+        {
+          minSize = outSizeProcessed;
+          bestIsFiltered = curModeIsFiltered;
+          mainResult = SZ_OK;
+        }
+      }
+    }
+    dest[0] = (Byte)(bestIsFiltered ? 1 : 0);
+    *destLen = LZMA86_HEADER_SIZE + minSize;
+  }
+  if (useFilter)
+    MyFree(filteredStream);
+  return mainResult;
+}

3rdparty/lzma/src/LzmaLib.c

@@ -0,0 +1,40 @@
+/* LzmaLib.c -- LZMA library wrapper
+2015-06-13 : Igor Pavlov : Public domain */
+
+#include "Alloc.h"
+#include "LzmaDec.h"
+#include "LzmaEnc.h"
+#include "LzmaLib.h"
+
+MY_STDAPI LzmaCompress(unsigned char *dest, size_t *destLen, const unsigned char *src, size_t srcLen,
+  unsigned char *outProps, size_t *outPropsSize,
+  int level, /* 0 <= level <= 9, default = 5 */
+  unsigned dictSize, /* use (1 << N) or (3 << N). 4 KB < dictSize <= 128 MB */
+  int lc, /* 0 <= lc <= 8, default = 3  */
+  int lp, /* 0 <= lp <= 4, default = 0  */
+  int pb, /* 0 <= pb <= 4, default = 2  */
+  int fb,  /* 5 <= fb <= 273, default = 32 */
+  int numThreads /* 1 or 2, default = 2 */
+)
+{
+  CLzmaEncProps props;
+  LzmaEncProps_Init(&props);
+  props.level = level;
+  props.dictSize = dictSize;
+  props.lc = lc;
+  props.lp = lp;
+  props.pb = pb;
+  props.fb = fb;
+  props.numThreads = numThreads;
+
+  return LzmaEncode(dest, destLen, src, srcLen, &props, outProps, outPropsSize, 0,
+      NULL, &g_Alloc, &g_Alloc);
+}
+
+
+MY_STDAPI LzmaUncompress(unsigned char *dest, size_t *destLen, const unsigned char *src, size_t *srcLen,
+  const unsigned char *props, size_t propsSize)
+{
+  ELzmaStatus status;
+  return LzmaDecode(dest, destLen, src, srcLen, props, (unsigned)propsSize, LZMA_FINISH_ANY, &status, &g_Alloc);
+}

3rdparty/lzma/src/Ppmd7Dec.c

@@ -0,0 +1,297 @@
+/* Ppmd7Dec.c -- Ppmd7z (PPMdH with 7z Range Coder) Decoder
+2021-04-13 : Igor Pavlov : Public domain
+This code is based on:
+  PPMd var.H (2001): Dmitry Shkarin : Public domain */
+
+
+#include "Precomp.h"
+
+#include "Ppmd7.h"
+
+#define kTopValue (1 << 24)
+
+
+#define READ_BYTE(p) IByteIn_Read((p)->Stream)
+
+BoolInt Ppmd7z_RangeDec_Init(CPpmd7_RangeDec *p)
+{
+  unsigned i;
+  p->Code = 0;
+  p->Range = 0xFFFFFFFF;
+  if (READ_BYTE(p) != 0)
+    return False;
+  for (i = 0; i < 4; i++)
+    p->Code = (p->Code << 8) | READ_BYTE(p);
+  return (p->Code < 0xFFFFFFFF);
+}
+
+#define RC_NORM_BASE(p) if ((p)->Range < kTopValue) \
+  { (p)->Code = ((p)->Code << 8) | READ_BYTE(p); (p)->Range <<= 8;
+
+#define RC_NORM_1(p)  RC_NORM_BASE(p) }
+#define RC_NORM(p)    RC_NORM_BASE(p) RC_NORM_BASE(p) }}
+
+// we must use only one type of Normalization from two: LOCAL or REMOTE
+#define RC_NORM_LOCAL(p)    // RC_NORM(p)
+#define RC_NORM_REMOTE(p)   RC_NORM(p)
+
+#define R (&p->rc.dec)
+
+MY_FORCE_INLINE
+// MY_NO_INLINE
+static void RangeDec_Decode(CPpmd7 *p, UInt32 start, UInt32 size)
+{
+
+  
+  R->Code -= start * R->Range;
+  R->Range *= size;
+  RC_NORM_LOCAL(R)
+}
+
+#define RC_Decode(start, size) RangeDec_Decode(p, start, size);
+#define RC_DecodeFinal(start, size) RC_Decode(start, size) RC_NORM_REMOTE(R)
+#define RC_GetThreshold(total) (R->Code / (R->Range /= (total)))
+
+
+#define CTX(ref) ((CPpmd7_Context *)Ppmd7_GetContext(p, ref))
+typedef CPpmd7_Context * CTX_PTR;
+#define SUCCESSOR(p) Ppmd_GET_SUCCESSOR(p)
+void Ppmd7_UpdateModel(CPpmd7 *p);
+
+#define MASK(sym) ((unsigned char *)charMask)[sym]
+// MY_FORCE_INLINE
+// static
+int Ppmd7z_DecodeSymbol(CPpmd7 *p)
+{
+  size_t charMask[256 / sizeof(size_t)];
+
+  if (p->MinContext->NumStats != 1)
+  {
+    CPpmd_State *s = Ppmd7_GetStats(p, p->MinContext);
+    unsigned i;
+    UInt32 count, hiCnt;
+    UInt32 summFreq = p->MinContext->Union2.SummFreq;
+
+    
+    
+    
+    count = RC_GetThreshold(summFreq);
+    hiCnt = count;
+    
+    if ((Int32)(count -= s->Freq) < 0)
+    {
+      Byte sym;
+      RC_DecodeFinal(0, s->Freq);
+      p->FoundState = s;
+      sym = s->Symbol;
+      Ppmd7_Update1_0(p);
+      return sym;
+    }
+  
+    p->PrevSuccess = 0;
+    i = (unsigned)p->MinContext->NumStats - 1;
+    
+    do
+    {
+      if ((Int32)(count -= (++s)->Freq) < 0)
+      {
+        Byte sym;
+        RC_DecodeFinal((hiCnt - count) - s->Freq, s->Freq);
+        p->FoundState = s;
+        sym = s->Symbol;
+        Ppmd7_Update1(p);
+        return sym;
+      }
+    }
+    while (--i);
+    
+    if (hiCnt >= summFreq)
+      return PPMD7_SYM_ERROR;
+    
+    hiCnt -= count;
+    RC_Decode(hiCnt, summFreq - hiCnt);
+
+    p->HiBitsFlag = PPMD7_HiBitsFlag_3(p->FoundState->Symbol);
+    PPMD_SetAllBitsIn256Bytes(charMask);
+    // i = p->MinContext->NumStats - 1;
+    // do { MASK((--s)->Symbol) = 0; } while (--i);
+    {
+      CPpmd_State *s2 = Ppmd7_GetStats(p, p->MinContext);
+      MASK(s->Symbol) = 0;
+      do
+      {
+        unsigned sym0 = s2[0].Symbol;
+        unsigned sym1 = s2[1].Symbol;
+        s2 += 2;
+        MASK(sym0) = 0;
+        MASK(sym1) = 0;
+      }
+      while (s2 < s);
+    }
+  }
+  else
+  {
+    CPpmd_State *s = Ppmd7Context_OneState(p->MinContext);
+    UInt16 *prob = Ppmd7_GetBinSumm(p);
+    UInt32 pr = *prob;
+    UInt32 size0 = (R->Range >> 14) * pr;
+    pr = PPMD_UPDATE_PROB_1(pr);
+
+    if (R->Code < size0)
+    {
+      Byte sym;
+      *prob = (UInt16)(pr + (1 << PPMD_INT_BITS));
+      
+      // RangeDec_DecodeBit0(size0);
+      R->Range = size0;
+      RC_NORM_1(R)
+      /* we can use single byte normalization here because of
+         (min(BinSumm[][]) = 95) > (1 << (14 - 8)) */
+
+      // sym = (p->FoundState = Ppmd7Context_OneState(p->MinContext))->Symbol;
+      // Ppmd7_UpdateBin(p);
+      {
+        unsigned freq = s->Freq;
+        CTX_PTR c = CTX(SUCCESSOR(s));
+        sym = s->Symbol;
+        p->FoundState = s;
+        p->PrevSuccess = 1;
+        p->RunLength++;
+        s->Freq = (Byte)(freq + (freq < 128));
+        // NextContext(p);
+        if (p->OrderFall == 0 && (const Byte *)c > p->Text)
+          p->MaxContext = p->MinContext = c;
+        else
+          Ppmd7_UpdateModel(p);
+      }
+      return sym;
+    }
+
+    *prob = (UInt16)pr;
+    p->InitEsc = p->ExpEscape[pr >> 10];
+
+    // RangeDec_DecodeBit1(size0);
+    
+    R->Code -= size0;
+    R->Range -= size0;
+    RC_NORM_LOCAL(R)
+    
+    PPMD_SetAllBitsIn256Bytes(charMask);
+    MASK(Ppmd7Context_OneState(p->MinContext)->Symbol) = 0;
+    p->PrevSuccess = 0;
+  }
+
+  for (;;)
+  {
+    CPpmd_State *s, *s2;
+    UInt32 freqSum, count, hiCnt;
+
+    CPpmd_See *see;
+    CPpmd7_Context *mc;
+    unsigned numMasked;
+    RC_NORM_REMOTE(R)
+    mc = p->MinContext;
+    numMasked = mc->NumStats;
+
+    do
+    {
+      p->OrderFall++;
+      if (!mc->Suffix)
+        return PPMD7_SYM_END;
+      mc = Ppmd7_GetContext(p, mc->Suffix);
+    }
+    while (mc->NumStats == numMasked);
+    
+    s = Ppmd7_GetStats(p, mc);
+
+    {
+      unsigned num = mc->NumStats;
+      unsigned num2 = num / 2;
+      
+      num &= 1;
+      hiCnt = (s->Freq & (unsigned)(MASK(s->Symbol))) & (0 - (UInt32)num);
+      s += num;
+      p->MinContext = mc;
+
+      do
+      {
+        unsigned sym0 = s[0].Symbol;
+        unsigned sym1 = s[1].Symbol;
+        s += 2;
+        hiCnt += (s[-2].Freq & (unsigned)(MASK(sym0)));
+        hiCnt += (s[-1].Freq & (unsigned)(MASK(sym1)));
+      }
+      while (--num2);
+    }
+
+    see = Ppmd7_MakeEscFreq(p, numMasked, &freqSum);
+    freqSum += hiCnt;
+
+
+
+
+    count = RC_GetThreshold(freqSum);
+    
+    if (count < hiCnt)
+    {
+      Byte sym;
+
+      s = Ppmd7_GetStats(p, p->MinContext);
+      hiCnt = count;
+      // count -= s->Freq & (unsigned)(MASK(s->Symbol));
+      // if ((Int32)count >= 0)
+      {
+        for (;;)
+        {
+          count -= s->Freq & (unsigned)(MASK((s)->Symbol)); s++; if ((Int32)count < 0) break;
+          // count -= s->Freq & (unsigned)(MASK((s)->Symbol)); s++; if ((Int32)count < 0) break;
+        };
+      }
+      s--;
+      RC_DecodeFinal((hiCnt - count) - s->Freq, s->Freq);
+
+      // new (see->Summ) value can overflow over 16-bits in some rare cases
+      Ppmd_See_Update(see);
+      p->FoundState = s;
+      sym = s->Symbol;
+      Ppmd7_Update2(p);
+      return sym;
+    }
+
+    if (count >= freqSum)
+      return PPMD7_SYM_ERROR;
+    
+    RC_Decode(hiCnt, freqSum - hiCnt);
+
+    // We increase (see->Summ) for sum of Freqs of all non_Masked symbols.
+    // new (see->Summ) value can overflow over 16-bits in some rare cases
+    see->Summ = (UInt16)(see->Summ + freqSum);
+
+    s = Ppmd7_GetStats(p, p->MinContext);
+    s2 = s + p->MinContext->NumStats;
+    do
+    {
+      MASK(s->Symbol) = 0;
+      s++;
+    }
+    while (s != s2);
+  }
+}
+
+/*
+Byte *Ppmd7z_DecodeSymbols(CPpmd7 *p, Byte *buf, const Byte *lim)
+{
+  int sym = 0;
+  if (buf != lim)
+  do
+  {
+    sym = Ppmd7z_DecodeSymbol(p);
+    if (sym < 0)
+      break;
+    *buf = (Byte)sym;
+  }
+  while (++buf < lim);
+  p->LastSymbol = sym;
+  return buf;
+}
+*/

3rdparty/lzma/src/Ppmd7Enc.c

@@ -0,0 +1,323 @@
+/* Ppmd7Enc.c -- Ppmd7z (PPMdH with 7z Range Coder) Encoder
+2021-04-13 : Igor Pavlov : Public domain
+This code is based on:
+  PPMd var.H (2001): Dmitry Shkarin : Public domain */
+
+
+#include "Precomp.h"
+
+#include "Ppmd7.h"
+
+#define kTopValue (1 << 24)
+
+#define R (&p->rc.enc)
+
+void Ppmd7z_Init_RangeEnc(CPpmd7 *p)
+{
+  R->Low = 0;
+  R->Range = 0xFFFFFFFF;
+  R->Cache = 0;
+  R->CacheSize = 1;
+}
+
+MY_NO_INLINE
+static void RangeEnc_ShiftLow(CPpmd7 *p)
+{
+  if ((UInt32)R->Low < (UInt32)0xFF000000 || (unsigned)(R->Low >> 32) != 0)
+  {
+    Byte temp = R->Cache;
+    do
+    {
+      IByteOut_Write(R->Stream, (Byte)(temp + (Byte)(R->Low >> 32)));
+      temp = 0xFF;
+    }
+    while (--R->CacheSize != 0);
+    R->Cache = (Byte)((UInt32)R->Low >> 24);
+  }
+  R->CacheSize++;
+  R->Low = (UInt32)((UInt32)R->Low << 8);
+}
+
+#define RC_NORM_BASE(p) if (R->Range < kTopValue) { R->Range <<= 8; RangeEnc_ShiftLow(p);
+#define RC_NORM_1(p) RC_NORM_BASE(p) }
+#define RC_NORM(p) RC_NORM_BASE(p) RC_NORM_BASE(p) }}
+
+// we must use only one type of Normalization from two: LOCAL or REMOTE
+#define RC_NORM_LOCAL(p)    // RC_NORM(p)
+#define RC_NORM_REMOTE(p)   RC_NORM(p)
+
+/*
+#define RangeEnc_Encode(p, start, _size_) \
+  { UInt32 size = _size_; \
+    R->Low += start * R->Range; \
+    R->Range *= size; \
+    RC_NORM_LOCAL(p); }
+*/
+
+MY_FORCE_INLINE
+// MY_NO_INLINE
+static void RangeEnc_Encode(CPpmd7 *p, UInt32 start, UInt32 size)
+{
+  R->Low += start * R->Range;
+  R->Range *= size;
+  RC_NORM_LOCAL(p);
+}
+
+void Ppmd7z_Flush_RangeEnc(CPpmd7 *p)
+{
+  unsigned i;
+  for (i = 0; i < 5; i++)
+    RangeEnc_ShiftLow(p);
+}
+
+
+
+#define RC_Encode(start, size) RangeEnc_Encode(p, start, size);
+#define RC_EncodeFinal(start, size) RC_Encode(start, size); RC_NORM_REMOTE(p);
+
+#define CTX(ref) ((CPpmd7_Context *)Ppmd7_GetContext(p, ref))
+#define SUFFIX(ctx) CTX((ctx)->Suffix)
+typedef CPpmd7_Context * CTX_PTR;
+#define SUCCESSOR(p) Ppmd_GET_SUCCESSOR(p)
+
+void Ppmd7_UpdateModel(CPpmd7 *p);
+
+#define MASK(sym) ((unsigned char *)charMask)[sym]
+
+MY_FORCE_INLINE
+static
+void Ppmd7z_EncodeSymbol(CPpmd7 *p, int symbol)
+{
+  size_t charMask[256 / sizeof(size_t)];
+  
+  if (p->MinContext->NumStats != 1)
+  {
+    CPpmd_State *s = Ppmd7_GetStats(p, p->MinContext);
+    UInt32 sum;
+    unsigned i;
+   
+
+    
+    
+    R->Range /= p->MinContext->Union2.SummFreq;
+    
+    if (s->Symbol == symbol)
+    {
+      // R->Range /= p->MinContext->Union2.SummFreq;
+      RC_EncodeFinal(0, s->Freq);
+      p->FoundState = s;
+      Ppmd7_Update1_0(p);
+      return;
+    }
+    p->PrevSuccess = 0;
+    sum = s->Freq;
+    i = (unsigned)p->MinContext->NumStats - 1;
+    do
+    {
+      if ((++s)->Symbol == symbol)
+      {
+        // R->Range /= p->MinContext->Union2.SummFreq;
+        RC_EncodeFinal(sum, s->Freq);
+        p->FoundState = s;
+        Ppmd7_Update1(p);
+        return;
+      }
+      sum += s->Freq;
+    }
+    while (--i);
+
+    // R->Range /= p->MinContext->Union2.SummFreq;
+    RC_Encode(sum, p->MinContext->Union2.SummFreq - sum);
+    
+    p->HiBitsFlag = PPMD7_HiBitsFlag_3(p->FoundState->Symbol);
+    PPMD_SetAllBitsIn256Bytes(charMask);
+    // MASK(s->Symbol) = 0;
+    // i = p->MinContext->NumStats - 1;
+    // do { MASK((--s)->Symbol) = 0; } while (--i);
+    {
+      CPpmd_State *s2 = Ppmd7_GetStats(p, p->MinContext);
+      MASK(s->Symbol) = 0;
+      do
+      {
+        unsigned sym0 = s2[0].Symbol;
+        unsigned sym1 = s2[1].Symbol;
+        s2 += 2;
+        MASK(sym0) = 0;
+        MASK(sym1) = 0;
+      }
+      while (s2 < s);
+    }
+  }
+  else
+  {
+    UInt16 *prob = Ppmd7_GetBinSumm(p);
+    CPpmd_State *s = Ppmd7Context_OneState(p->MinContext);
+    UInt32 pr = *prob;
+    UInt32 bound = (R->Range >> 14) * pr;
+    pr = PPMD_UPDATE_PROB_1(pr);
+    if (s->Symbol == symbol)
+    {
+      *prob = (UInt16)(pr + (1 << PPMD_INT_BITS));
+      // RangeEnc_EncodeBit_0(p, bound);
+      R->Range = bound;
+      RC_NORM_1(p);
+      
+      // p->FoundState = s;
+      // Ppmd7_UpdateBin(p);
+      {
+        unsigned freq = s->Freq;
+        CTX_PTR c = CTX(SUCCESSOR(s));
+        p->FoundState = s;
+        p->PrevSuccess = 1;
+        p->RunLength++;
+        s->Freq = (Byte)(freq + (freq < 128));
+        // NextContext(p);
+        if (p->OrderFall == 0 && (const Byte *)c > p->Text)
+          p->MaxContext = p->MinContext = c;
+        else
+          Ppmd7_UpdateModel(p);
+      }
+      return;
+    }
+
+    *prob = (UInt16)pr;
+    p->InitEsc = p->ExpEscape[pr >> 10];
+    // RangeEnc_EncodeBit_1(p, bound);
+    R->Low += bound;
+    R->Range -= bound;
+    RC_NORM_LOCAL(p)
+    
+    PPMD_SetAllBitsIn256Bytes(charMask);
+    MASK(s->Symbol) = 0;
+    p->PrevSuccess = 0;
+  }
+
+  for (;;)
+  {
+    CPpmd_See *see;
+    CPpmd_State *s;
+    UInt32 sum, escFreq;
+    CPpmd7_Context *mc;
+    unsigned i, numMasked;
+    
+    RC_NORM_REMOTE(p)
+
+    mc = p->MinContext;
+    numMasked = mc->NumStats;
+
+    do
+    {
+      p->OrderFall++;
+      if (!mc->Suffix)
+        return; /* EndMarker (symbol = -1) */
+      mc = Ppmd7_GetContext(p, mc->Suffix);
+      i = mc->NumStats;
+    }
+    while (i == numMasked);
+
+    p->MinContext = mc;
+    
+    // see = Ppmd7_MakeEscFreq(p, numMasked, &escFreq);
+    {
+      if (i != 256)
+      {
+        unsigned nonMasked = i - numMasked;
+        see = p->See[(unsigned)p->NS2Indx[(size_t)nonMasked - 1]]
+            + p->HiBitsFlag
+            + (nonMasked < (unsigned)SUFFIX(mc)->NumStats - i)
+            + 2 * (unsigned)(mc->Union2.SummFreq < 11 * i)
+            + 4 * (unsigned)(numMasked > nonMasked);
+        {
+          // if (see->Summ) field is larger than 16-bit, we need only low 16 bits of Summ
+          unsigned summ = (UInt16)see->Summ; // & 0xFFFF
+          unsigned r = (summ >> see->Shift);
+          see->Summ = (UInt16)(summ - r);
+          escFreq = r + (r == 0);
+        }
+      }
+      else
+      {
+        see = &p->DummySee;
+        escFreq = 1;
+      }
+    }
+
+    s = Ppmd7_GetStats(p, mc);
+    sum = 0;
+    // i = mc->NumStats;
+
+    do
+    {
+      unsigned cur = s->Symbol;
+      if ((int)cur == symbol)
+      {
+        UInt32 low = sum;
+        UInt32 freq = s->Freq;
+        unsigned num2;
+
+        Ppmd_See_Update(see);
+        p->FoundState = s;
+        sum += escFreq;
+
+        num2 = i / 2;
+        i &= 1;
+        sum += freq & (0 - (UInt32)i);
+        if (num2 != 0)
+        {
+          s += i;
+          for (;;)
+          {
+            unsigned sym0 = s[0].Symbol;
+            unsigned sym1 = s[1].Symbol;
+            s += 2;
+            sum += (s[-2].Freq & (unsigned)(MASK(sym0)));
+            sum += (s[-1].Freq & (unsigned)(MASK(sym1)));
+            if (--num2 == 0)
+              break;
+          }
+        }
+
+        
+        R->Range /= sum;
+        RC_EncodeFinal(low, freq);
+        Ppmd7_Update2(p);
+        return;
+      }
+      sum += (s->Freq & (unsigned)(MASK(cur)));
+      s++;
+    }
+    while (--i);
+    
+    {
+      UInt32 total = sum + escFreq;
+      see->Summ = (UInt16)(see->Summ + total);
+
+      R->Range /= total;
+      RC_Encode(sum, escFreq);
+    }
+
+    {
+      CPpmd_State *s2 = Ppmd7_GetStats(p, p->MinContext);
+      s--;
+      MASK(s->Symbol) = 0;
+      do
+      {
+        unsigned sym0 = s2[0].Symbol;
+        unsigned sym1 = s2[1].Symbol;
+        s2 += 2;
+        MASK(sym0) = 0;
+        MASK(sym1) = 0;
+      }
+      while (s2 < s);
+    }
+  }
+}
+
+
+void Ppmd7z_EncodeSymbols(CPpmd7 *p, const Byte *buf, const Byte *lim)
+{
+  for (; buf < lim; buf++)
+  {
+    Ppmd7z_EncodeSymbol(p, *buf);
+  }
+}

3rdparty/lzma/src/Sha256.c

@@ -0,0 +1,486 @@
+/* Sha256.c -- SHA-256 Hash
+2021-04-01 : Igor Pavlov : Public domain
+This code is based on public domain code from Wei Dai's Crypto++ library. */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "CpuArch.h"
+#include "RotateDefs.h"
+#include "Sha256.h"
+
+#if defined(_MSC_VER) && (_MSC_VER < 1900)
+// #define USE_MY_MM
+#endif
+
+#ifdef MY_CPU_X86_OR_AMD64
+  #ifdef _MSC_VER
+    #if _MSC_VER >= 1200
+      #define _SHA_SUPPORTED
+    #endif
+  #elif defined(__clang__)
+    #if (__clang_major__ >= 8) // fix that check
+      #define _SHA_SUPPORTED
+    #endif
+  #elif defined(__GNUC__)
+    #if (__GNUC__ >= 8) // fix that check
+      #define _SHA_SUPPORTED
+    #endif
+  #elif defined(__INTEL_COMPILER)
+    #if (__INTEL_COMPILER >= 1800) // fix that check
+      #define _SHA_SUPPORTED
+    #endif
+  #endif
+#elif defined(MY_CPU_ARM_OR_ARM64)
+  #ifdef _MSC_VER
+    #if _MSC_VER >= 1910
+      #define _SHA_SUPPORTED
+    #endif
+  #elif defined(__clang__)
+    #if (__clang_major__ >= 8) // fix that check
+      #define _SHA_SUPPORTED
+    #endif
+  #elif defined(__GNUC__)
+    #if (__GNUC__ >= 6) // fix that check
+      #define _SHA_SUPPORTED
+    #endif
+  #endif
+#endif
+
+void MY_FAST_CALL Sha256_UpdateBlocks(UInt32 state[8], const Byte *data, size_t numBlocks);
+
+#ifdef _SHA_SUPPORTED
+  void MY_FAST_CALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks);
+
+  static SHA256_FUNC_UPDATE_BLOCKS g_FUNC_UPDATE_BLOCKS = Sha256_UpdateBlocks;
+  static SHA256_FUNC_UPDATE_BLOCKS g_FUNC_UPDATE_BLOCKS_HW;
+
+  #define UPDATE_BLOCKS(p) p->func_UpdateBlocks
+#else
+  #define UPDATE_BLOCKS(p) Sha256_UpdateBlocks
+#endif
+
+
+BoolInt Sha256_SetFunction(CSha256 *p, unsigned algo)
+{
+  SHA256_FUNC_UPDATE_BLOCKS func = Sha256_UpdateBlocks;
+  
+  #ifdef _SHA_SUPPORTED
+    if (algo != SHA256_ALGO_SW)
+    {
+      if (algo == SHA256_ALGO_DEFAULT)
+        func = g_FUNC_UPDATE_BLOCKS;
+      else
+      {
+        if (algo != SHA256_ALGO_HW)
+          return False;
+        func = g_FUNC_UPDATE_BLOCKS_HW;
+        if (!func)
+          return False;
+      }
+    }
+  #else
+    if (algo > 1)
+      return False;
+  #endif
+
+  p->func_UpdateBlocks = func;
+  return True;
+}
+
+
+/* define it for speed optimization */
+
+#ifdef _SFX
+  #define STEP_PRE 1
+  #define STEP_MAIN 1
+#else
+  #define STEP_PRE 2
+  #define STEP_MAIN 4
+  // #define _SHA256_UNROLL
+#endif
+
+#if STEP_MAIN != 16
+  #define _SHA256_BIG_W
+#endif
+
+
+
+
+void Sha256_InitState(CSha256 *p)
+{
+  p->count = 0;
+  p->state[0] = 0x6a09e667;
+  p->state[1] = 0xbb67ae85;
+  p->state[2] = 0x3c6ef372;
+  p->state[3] = 0xa54ff53a;
+  p->state[4] = 0x510e527f;
+  p->state[5] = 0x9b05688c;
+  p->state[6] = 0x1f83d9ab;
+  p->state[7] = 0x5be0cd19;
+}
+
+void Sha256_Init(CSha256 *p)
+{
+  p->func_UpdateBlocks =
+  #ifdef _SHA_SUPPORTED
+      g_FUNC_UPDATE_BLOCKS;
+  #else
+      NULL;
+  #endif
+  Sha256_InitState(p);
+}
+
+#define S0(x) (rotrFixed(x, 2) ^ rotrFixed(x,13) ^ rotrFixed(x, 22))
+#define S1(x) (rotrFixed(x, 6) ^ rotrFixed(x,11) ^ rotrFixed(x, 25))
+#define s0(x) (rotrFixed(x, 7) ^ rotrFixed(x,18) ^ (x >> 3))
+#define s1(x) (rotrFixed(x,17) ^ rotrFixed(x,19) ^ (x >> 10))
+
+#define Ch(x,y,z) (z^(x&(y^z)))
+#define Maj(x,y,z) ((x&y)|(z&(x|y)))
+
+
+#define W_PRE(i) (W[(i) + (size_t)(j)] = GetBe32(data + ((size_t)(j) + i) * 4))
+
+#define blk2_main(j, i)  s1(w(j, (i)-2)) + w(j, (i)-7) + s0(w(j, (i)-15))
+
+#ifdef _SHA256_BIG_W
+    // we use +i instead of +(i) to change the order to solve CLANG compiler warning for signed/unsigned.
+    #define w(j, i)     W[(size_t)(j) + i]
+    #define blk2(j, i)  (w(j, i) = w(j, (i)-16) + blk2_main(j, i))
+#else
+    #if STEP_MAIN == 16
+        #define w(j, i)  W[(i) & 15]
+    #else
+        #define w(j, i)  W[((size_t)(j) + (i)) & 15]
+    #endif
+    #define blk2(j, i)  (w(j, i) += blk2_main(j, i))
+#endif
+
+#define W_MAIN(i)  blk2(j, i)
+
+
+#define T1(wx, i) \
+    tmp = h + S1(e) + Ch(e,f,g) + K[(i)+(size_t)(j)] + wx(i); \
+    h = g; \
+    g = f; \
+    f = e; \
+    e = d + tmp; \
+    tmp += S0(a) + Maj(a, b, c); \
+    d = c; \
+    c = b; \
+    b = a; \
+    a = tmp; \
+
+#define R1_PRE(i)  T1( W_PRE, i)
+#define R1_MAIN(i) T1( W_MAIN, i)
+
+#if (!defined(_SHA256_UNROLL) || STEP_MAIN < 8) && (STEP_MAIN >= 4)
+#define R2_MAIN(i) \
+    R1_MAIN(i) \
+    R1_MAIN(i + 1) \
+
+#endif
+
+
+
+#if defined(_SHA256_UNROLL) && STEP_MAIN >= 8
+
+#define T4( a,b,c,d,e,f,g,h, wx, i) \
+    h += S1(e) + Ch(e,f,g) + K[(i)+(size_t)(j)] + wx(i); \
+    tmp = h; \
+    h += d; \
+    d = tmp + S0(a) + Maj(a, b, c); \
+
+#define R4( wx, i) \
+    T4 ( a,b,c,d,e,f,g,h, wx, (i  )); \
+    T4 ( d,a,b,c,h,e,f,g, wx, (i+1)); \
+    T4 ( c,d,a,b,g,h,e,f, wx, (i+2)); \
+    T4 ( b,c,d,a,f,g,h,e, wx, (i+3)); \
+
+#define R4_PRE(i)  R4( W_PRE, i)
+#define R4_MAIN(i) R4( W_MAIN, i)
+
+
+#define T8( a,b,c,d,e,f,g,h, wx, i) \
+    h += S1(e) + Ch(e,f,g) + K[(i)+(size_t)(j)] + wx(i); \
+    d += h; \
+    h += S0(a) + Maj(a, b, c); \
+
+#define R8( wx, i) \
+    T8 ( a,b,c,d,e,f,g,h, wx, i  ); \
+    T8 ( h,a,b,c,d,e,f,g, wx, i+1); \
+    T8 ( g,h,a,b,c,d,e,f, wx, i+2); \
+    T8 ( f,g,h,a,b,c,d,e, wx, i+3); \
+    T8 ( e,f,g,h,a,b,c,d, wx, i+4); \
+    T8 ( d,e,f,g,h,a,b,c, wx, i+5); \
+    T8 ( c,d,e,f,g,h,a,b, wx, i+6); \
+    T8 ( b,c,d,e,f,g,h,a, wx, i+7); \
+
+#define R8_PRE(i)  R8( W_PRE, i)
+#define R8_MAIN(i) R8( W_MAIN, i)
+
+#endif
+
+void MY_FAST_CALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks);
+
+// static
+extern MY_ALIGN(64)
+const UInt32 SHA256_K_ARRAY[64];
+
+MY_ALIGN(64)
+const UInt32 SHA256_K_ARRAY[64] = {
+  0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5,
+  0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
+  0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3,
+  0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174,
+  0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc,
+  0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
+  0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7,
+  0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967,
+  0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13,
+  0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85,
+  0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3,
+  0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
+  0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5,
+  0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3,
+  0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208,
+  0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+};
+
+#define K SHA256_K_ARRAY
+
+
+MY_NO_INLINE
+void MY_FAST_CALL Sha256_UpdateBlocks(UInt32 state[8], const Byte *data, size_t numBlocks)
+{
+  UInt32 W
+  #ifdef _SHA256_BIG_W
+      [64];
+  #else
+      [16];
+  #endif
+
+  unsigned j;
+
+  UInt32 a,b,c,d,e,f,g,h;
+
+  #if !defined(_SHA256_UNROLL) || (STEP_MAIN <= 4) || (STEP_PRE <= 4)
+  UInt32 tmp;
+  #endif
+  
+  a = state[0];
+  b = state[1];
+  c = state[2];
+  d = state[3];
+  e = state[4];
+  f = state[5];
+  g = state[6];
+  h = state[7];
+
+  while (numBlocks)
+  {
+
+  for (j = 0; j < 16; j += STEP_PRE)
+  {
+    #if STEP_PRE > 4
+
+      #if STEP_PRE < 8
+      R4_PRE(0);
+      #else
+      R8_PRE(0);
+      #if STEP_PRE == 16
+      R8_PRE(8);
+      #endif
+      #endif
+
+    #else
+
+      R1_PRE(0);
+      #if STEP_PRE >= 2
+      R1_PRE(1);
+      #if STEP_PRE >= 4
+      R1_PRE(2);
+      R1_PRE(3);
+      #endif
+      #endif
+    
+    #endif
+  }
+
+  for (j = 16; j < 64; j += STEP_MAIN)
+  {
+    #if defined(_SHA256_UNROLL) && STEP_MAIN >= 8
+
+      #if STEP_MAIN < 8
+      R4_MAIN(0);
+      #else
+      R8_MAIN(0);
+      #if STEP_MAIN == 16
+      R8_MAIN(8);
+      #endif
+      #endif
+
+    #else
+      
+      R1_MAIN(0);
+      #if STEP_MAIN >= 2
+      R1_MAIN(1);
+      #if STEP_MAIN >= 4
+      R2_MAIN(2);
+      #if STEP_MAIN >= 8
+      R2_MAIN(4);
+      R2_MAIN(6);
+      #if STEP_MAIN >= 16
+      R2_MAIN(8);
+      R2_MAIN(10);
+      R2_MAIN(12);
+      R2_MAIN(14);
+      #endif
+      #endif
+      #endif
+      #endif
+    #endif
+  }
+
+  a += state[0]; state[0] = a;
+  b += state[1]; state[1] = b;
+  c += state[2]; state[2] = c;
+  d += state[3]; state[3] = d;
+  e += state[4]; state[4] = e;
+  f += state[5]; state[5] = f;
+  g += state[6]; state[6] = g;
+  h += state[7]; state[7] = h;
+
+  data += 64;
+  numBlocks--;
+  }
+
+  /* Wipe variables */
+  /* memset(W, 0, sizeof(W)); */
+}
+
+#undef S0
+#undef S1
+#undef s0
+#undef s1
+#undef K
+
+#define Sha256_UpdateBlock(p) UPDATE_BLOCKS(p)(p->state, p->buffer, 1)
+
+void Sha256_Update(CSha256 *p, const Byte *data, size_t size)
+{
+  if (size == 0)
+    return;
+
+  {
+    unsigned pos = (unsigned)p->count & 0x3F;
+    unsigned num;
+    
+    p->count += size;
+    
+    num = 64 - pos;
+    if (num > size)
+    {
+      memcpy(p->buffer + pos, data, size);
+      return;
+    }
+    
+    if (pos != 0)
+    {
+      size -= num;
+      memcpy(p->buffer + pos, data, num);
+      data += num;
+      Sha256_UpdateBlock(p);
+    }
+  }
+  {
+    size_t numBlocks = size >> 6;
+    UPDATE_BLOCKS(p)(p->state, data, numBlocks);
+    size &= 0x3F;
+    if (size == 0)
+      return;
+    data += (numBlocks << 6);
+    memcpy(p->buffer, data, size);
+  }
+}
+
+
+void Sha256_Final(CSha256 *p, Byte *digest)
+{
+  unsigned pos = (unsigned)p->count & 0x3F;
+  unsigned i;
+  
+  p->buffer[pos++] = 0x80;
+  
+  if (pos > (64 - 8))
+  {
+    while (pos != 64) { p->buffer[pos++] = 0; }
+    // memset(&p->buf.buffer[pos], 0, 64 - pos);
+    Sha256_UpdateBlock(p);
+    pos = 0;
+  }
+
+  /*
+  if (pos & 3)
+  {
+    p->buffer[pos] = 0;
+    p->buffer[pos + 1] = 0;
+    p->buffer[pos + 2] = 0;
+    pos += 3;
+    pos &= ~3;
+  }
+  {
+    for (; pos < 64 - 8; pos += 4)
+      *(UInt32 *)(&p->buffer[pos]) = 0;
+  }
+  */
+
+  memset(&p->buffer[pos], 0, (64 - 8) - pos);
+
+  {
+    UInt64 numBits = (p->count << 3);
+    SetBe32(p->buffer + 64 - 8, (UInt32)(numBits >> 32));
+    SetBe32(p->buffer + 64 - 4, (UInt32)(numBits));
+  }
+  
+  Sha256_UpdateBlock(p);
+
+  for (i = 0; i < 8; i += 2)
+  {
+    UInt32 v0 = p->state[i];
+    UInt32 v1 = p->state[(size_t)i + 1];
+    SetBe32(digest    , v0);
+    SetBe32(digest + 4, v1);
+    digest += 8;
+  }
+  
+  Sha256_InitState(p);
+}
+
+
+void Sha256Prepare()
+{
+  #ifdef _SHA_SUPPORTED
+  SHA256_FUNC_UPDATE_BLOCKS f, f_hw;
+  f = Sha256_UpdateBlocks;
+  f_hw = NULL;
+  #ifdef MY_CPU_X86_OR_AMD64
+  #ifndef USE_MY_MM
+  if (CPU_IsSupported_SHA()
+      && CPU_IsSupported_SSSE3()
+      // && CPU_IsSupported_SSE41()
+      )
+  #endif
+  #else
+  if (CPU_IsSupported_SHA2())
+  #endif
+  {
+    // printf("\n========== HW SHA256 ======== \n");
+    f = f_hw = Sha256_UpdateBlocks_HW;
+  }
+  g_FUNC_UPDATE_BLOCKS    = f;
+  g_FUNC_UPDATE_BLOCKS_HW = f_hw;
+  #endif
+}

3rdparty/lzma/src/Sha256Opt.c

@@ -0,0 +1,373 @@
+/* Sha256Opt.c -- SHA-256 optimized code for SHA-256 hardware instructions
+2021-04-01 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#if defined(_MSC_VER)
+#if (_MSC_VER < 1900) && (_MSC_VER >= 1200)
+// #define USE_MY_MM
+#endif
+#endif
+
+#include "CpuArch.h"
+
+#ifdef MY_CPU_X86_OR_AMD64
+  #if defined(__clang__)
+    #if (__clang_major__ >= 8) // fix that check
+      #define USE_HW_SHA
+      #ifndef __SHA__
+        #define ATTRIB_SHA __attribute__((__target__("sha,ssse3")))
+        #if defined(_MSC_VER)
+          // SSSE3: for clang-cl:
+          #include <tmmintrin.h>
+          #define __SHA__
+        #endif
+      #endif
+
+    #endif
+  #elif defined(__GNUC__)
+    #if (__GNUC__ >= 8) // fix that check
+      #define USE_HW_SHA
+      #ifndef __SHA__
+        #define ATTRIB_SHA __attribute__((__target__("sha,ssse3")))
+        // #pragma GCC target("sha,ssse3")
+      #endif
+    #endif
+  #elif defined(__INTEL_COMPILER)
+    #if (__INTEL_COMPILER >= 1800) // fix that check
+      #define USE_HW_SHA
+    #endif
+  #elif defined(_MSC_VER)
+    #ifdef USE_MY_MM
+      #define USE_VER_MIN 1300
+    #else
+      #define USE_VER_MIN 1910
+    #endif
+    #if _MSC_VER >= USE_VER_MIN
+      #define USE_HW_SHA
+    #endif
+  #endif
+// #endif // MY_CPU_X86_OR_AMD64
+
+#ifdef USE_HW_SHA
+
+// #pragma message("Sha256 HW")
+// #include <wmmintrin.h>
+
+#if !defined(_MSC_VER) || (_MSC_VER >= 1900)
+#include <immintrin.h>
+#else
+#include <emmintrin.h>
+
+#if defined(_MSC_VER) && (_MSC_VER >= 1600)
+// #include <intrin.h>
+#endif
+
+#ifdef USE_MY_MM
+#include "My_mm.h"
+#endif
+
+#endif
+
+/*
+SHA256 uses:
+SSE2:
+  _mm_loadu_si128
+  _mm_storeu_si128
+  _mm_set_epi32
+  _mm_add_epi32
+  _mm_shuffle_epi32 / pshufd
+
+
+  
+SSSE3:
+  _mm_shuffle_epi8 / pshufb
+  _mm_alignr_epi8
+SHA:
+  _mm_sha256*
+*/
+
+// K array must be aligned for 16-bytes at least.
+// The compiler can look align attribute and selects
+//   movdqu - for code without align attribute
+//   movdqa - for code with    align attribute
+extern
+MY_ALIGN(64)
+const UInt32 SHA256_K_ARRAY[64];
+
+#define K SHA256_K_ARRAY
+
+
+#define ADD_EPI32(dest, src) dest = _mm_add_epi32(dest, src);
+#define SHA256_MSG1(dest, src) dest = _mm_sha256msg1_epu32(dest, src);
+#define SHA25G_MSG2(dest, src) dest = _mm_sha256msg2_epu32(dest, src);
+
+
+#define LOAD_SHUFFLE(m, k) \
+    m = _mm_loadu_si128((const __m128i *)(const void *)(data + (k) * 16)); \
+    m = _mm_shuffle_epi8(m, mask); \
+
+#define SM1(g0, g1, g2, g3) \
+    SHA256_MSG1(g3, g0); \
+
+#define SM2(g0, g1, g2, g3) \
+    tmp = _mm_alignr_epi8(g1, g0, 4); \
+    ADD_EPI32(g2, tmp); \
+    SHA25G_MSG2(g2, g1); \
+
+// #define LS0(k, g0, g1, g2, g3) LOAD_SHUFFLE(g0, k)
+// #define LS1(k, g0, g1, g2, g3) LOAD_SHUFFLE(g1, k+1)
+
+
+#define NNN(g0, g1, g2, g3)
+
+
+#define RND2(t0, t1) \
+    t0 = _mm_sha256rnds2_epu32(t0, t1, msg);
+
+#define RND2_0(m, k) \
+    msg = _mm_add_epi32(m, *(const __m128i *) (const void *) &K[(k) * 4]); \
+    RND2(state0, state1); \
+    msg = _mm_shuffle_epi32(msg, 0x0E); \
+
+
+#define RND2_1 \
+    RND2(state1, state0); \
+
+
+// We use scheme with 3 rounds ahead for SHA256_MSG1 / 2 rounds ahead for SHA256_MSG2
+
+#define R4(k, g0, g1, g2, g3, OP0, OP1) \
+    RND2_0(g0, k); \
+    OP0(g0, g1, g2, g3); \
+    RND2_1; \
+    OP1(g0, g1, g2, g3); \
+
+#define R16(k, OP0, OP1, OP2, OP3, OP4, OP5, OP6, OP7) \
+    R4 ( (k)*4+0, m0, m1, m2, m3, OP0, OP1 ) \
+    R4 ( (k)*4+1, m1, m2, m3, m0, OP2, OP3 ) \
+    R4 ( (k)*4+2, m2, m3, m0, m1, OP4, OP5 ) \
+    R4 ( (k)*4+3, m3, m0, m1, m2, OP6, OP7 ) \
+
+#define PREPARE_STATE \
+    tmp    = _mm_shuffle_epi32(state0, 0x1B); /* abcd */ \
+    state0 = _mm_shuffle_epi32(state1, 0x1B); /* efgh */ \
+    state1 = state0; \
+    state0 = _mm_unpacklo_epi64(state0, tmp); /* cdgh */ \
+    state1 = _mm_unpackhi_epi64(state1, tmp); /* abef */ \
+
+
+void MY_FAST_CALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks);
+#ifdef ATTRIB_SHA
+ATTRIB_SHA
+#endif
+void MY_FAST_CALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks)
+{
+  const __m128i mask = _mm_set_epi32(0x0c0d0e0f, 0x08090a0b, 0x04050607, 0x00010203);
+  __m128i tmp;
+  __m128i state0, state1;
+
+  if (numBlocks == 0)
+    return;
+
+  state0 = _mm_loadu_si128((const __m128i *) (const void *) &state[0]);
+  state1 = _mm_loadu_si128((const __m128i *) (const void *) &state[4]);
+  
+  PREPARE_STATE
+
+  do
+  {
+    __m128i state0_save, state1_save;
+    __m128i m0, m1, m2, m3;
+    __m128i msg;
+    // #define msg tmp
+
+    state0_save = state0;
+    state1_save = state1;
+    
+    LOAD_SHUFFLE (m0, 0)
+    LOAD_SHUFFLE (m1, 1)
+    LOAD_SHUFFLE (m2, 2)
+    LOAD_SHUFFLE (m3, 3)
+
+
+
+    R16 ( 0, NNN, NNN, SM1, NNN, SM1, SM2, SM1, SM2 );
+    R16 ( 1, SM1, SM2, SM1, SM2, SM1, SM2, SM1, SM2 );
+    R16 ( 2, SM1, SM2, SM1, SM2, SM1, SM2, SM1, SM2 );
+    R16 ( 3, SM1, SM2, NNN, SM2, NNN, NNN, NNN, NNN );
+    
+    ADD_EPI32(state0, state0_save);
+    ADD_EPI32(state1, state1_save);
+    
+    data += 64;
+  }
+  while (--numBlocks);
+
+  PREPARE_STATE
+
+  _mm_storeu_si128((__m128i *) (void *) &state[0], state0);
+  _mm_storeu_si128((__m128i *) (void *) &state[4], state1);
+}
+
+#endif // USE_HW_SHA
+
+#elif defined(MY_CPU_ARM_OR_ARM64)
+
+  #if defined(__clang__)
+    #if (__clang_major__ >= 8) // fix that check
+      #define USE_HW_SHA
+    #endif
+  #elif defined(__GNUC__)
+    #if (__GNUC__ >= 6) // fix that check
+      #define USE_HW_SHA
+    #endif
+  #elif defined(_MSC_VER)
+    #if _MSC_VER >= 1910
+      #define USE_HW_SHA
+    #endif
+  #endif
+
+#ifdef USE_HW_SHA
+
+// #pragma message("=== Sha256 HW === ")
+
+#if defined(__clang__) || defined(__GNUC__)
+  #ifdef MY_CPU_ARM64
+    #define ATTRIB_SHA __attribute__((__target__("+crypto")))
+  #else
+    #define ATTRIB_SHA __attribute__((__target__("fpu=crypto-neon-fp-armv8")))
+  #endif
+#else
+  // _MSC_VER
+  // for arm32
+  #define _ARM_USE_NEW_NEON_INTRINSICS
+#endif
+
+#if defined(_MSC_VER) && defined(MY_CPU_ARM64)
+#include <arm64_neon.h>
+#else
+#include <arm_neon.h>
+#endif
+
+typedef uint32x4_t v128;
+// typedef __n128 v128; // MSVC
+
+#ifdef MY_CPU_BE
+  #define MY_rev32_for_LE(x)
+#else
+  #define MY_rev32_for_LE(x) x = vreinterpretq_u32_u8(vrev32q_u8(vreinterpretq_u8_u32(x)))
+#endif
+
+#define LOAD_128(_p)      (*(const v128 *)(const void *)(_p))
+#define STORE_128(_p, _v) *(v128 *)(void *)(_p) = (_v)
+
+#define LOAD_SHUFFLE(m, k) \
+    m = LOAD_128((data + (k) * 16)); \
+    MY_rev32_for_LE(m); \
+
+// K array must be aligned for 16-bytes at least.
+extern
+MY_ALIGN(64)
+const UInt32 SHA256_K_ARRAY[64];
+
+#define K SHA256_K_ARRAY
+
+
+#define SHA256_SU0(dest, src)        dest = vsha256su0q_u32(dest, src);
+#define SHA25G_SU1(dest, src2, src3) dest = vsha256su1q_u32(dest, src2, src3);
+
+#define SM1(g0, g1, g2, g3)  SHA256_SU0(g3, g0)
+#define SM2(g0, g1, g2, g3)  SHA25G_SU1(g2, g0, g1)
+#define NNN(g0, g1, g2, g3)
+
+
+#define R4(k, g0, g1, g2, g3, OP0, OP1) \
+    msg = vaddq_u32(g0, *(const v128 *) (const void *) &K[(k) * 4]); \
+    tmp = state0; \
+    state0 = vsha256hq_u32( state0, state1, msg ); \
+    state1 = vsha256h2q_u32( state1, tmp, msg ); \
+    OP0(g0, g1, g2, g3); \
+    OP1(g0, g1, g2, g3); \
+
+
+#define R16(k, OP0, OP1, OP2, OP3, OP4, OP5, OP6, OP7) \
+    R4 ( (k)*4+0, m0, m1, m2, m3, OP0, OP1 ) \
+    R4 ( (k)*4+1, m1, m2, m3, m0, OP2, OP3 ) \
+    R4 ( (k)*4+2, m2, m3, m0, m1, OP4, OP5 ) \
+    R4 ( (k)*4+3, m3, m0, m1, m2, OP6, OP7 ) \
+
+
+void MY_FAST_CALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks);
+#ifdef ATTRIB_SHA
+ATTRIB_SHA
+#endif
+void MY_FAST_CALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks)
+{
+  v128 state0, state1;
+
+  if (numBlocks == 0)
+    return;
+
+  state0 = LOAD_128(&state[0]);
+  state1 = LOAD_128(&state[4]);
+  
+  do
+  {
+    v128 state0_save, state1_save;
+    v128 m0, m1, m2, m3;
+    v128 msg, tmp;
+
+    state0_save = state0;
+    state1_save = state1;
+    
+    LOAD_SHUFFLE (m0, 0)
+    LOAD_SHUFFLE (m1, 1)
+    LOAD_SHUFFLE (m2, 2)
+    LOAD_SHUFFLE (m3, 3)
+
+    R16 ( 0, NNN, NNN, SM1, NNN, SM1, SM2, SM1, SM2 );
+    R16 ( 1, SM1, SM2, SM1, SM2, SM1, SM2, SM1, SM2 );
+    R16 ( 2, SM1, SM2, SM1, SM2, SM1, SM2, SM1, SM2 );
+    R16 ( 3, SM1, SM2, NNN, SM2, NNN, NNN, NNN, NNN );
+    
+    state0 = vaddq_u32(state0, state0_save);
+    state1 = vaddq_u32(state1, state1_save);
+    
+    data += 64;
+  }
+  while (--numBlocks);
+
+  STORE_128(&state[0], state0);
+  STORE_128(&state[4], state1);
+}
+
+#endif // USE_HW_SHA
+
+#endif // MY_CPU_ARM_OR_ARM64
+
+
+#ifndef USE_HW_SHA
+
+// #error Stop_Compiling_UNSUPPORTED_SHA
+// #include <stdlib.h>
+
+// #include "Sha256.h"
+void MY_FAST_CALL Sha256_UpdateBlocks(UInt32 state[8], const Byte *data, size_t numBlocks);
+
+#pragma message("Sha256 HW-SW stub was used")
+
+void MY_FAST_CALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks);
+void MY_FAST_CALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks)
+{
+  Sha256_UpdateBlocks(state, data, numBlocks);
+  /*
+  UNUSED_VAR(state);
+  UNUSED_VAR(data);
+  UNUSED_VAR(numBlocks);
+  exit(1);
+  return;
+  */
+}
+
+#endif

3rdparty/lzma/src/Xz.c

@@ -0,0 +1,90 @@
+/* Xz.c - Xz
+2021-02-09 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "7zCrc.h"
+#include "CpuArch.h"
+#include "Xz.h"
+#include "XzCrc64.h"
+
+const Byte XZ_SIG[XZ_SIG_SIZE] = { 0xFD, '7', 'z', 'X', 'Z', 0 };
+/* const Byte XZ_FOOTER_SIG[XZ_FOOTER_SIG_SIZE] = { 'Y', 'Z' }; */
+
+unsigned Xz_WriteVarInt(Byte *buf, UInt64 v)
+{
+  unsigned i = 0;
+  do
+  {
+    buf[i++] = (Byte)((v & 0x7F) | 0x80);
+    v >>= 7;
+  }
+  while (v != 0);
+  buf[(size_t)i - 1] &= 0x7F;
+  return i;
+}
+
+void Xz_Construct(CXzStream *p)
+{
+  p->numBlocks = 0;
+  p->blocks = NULL;
+  p->flags = 0;
+}
+
+void Xz_Free(CXzStream *p, ISzAllocPtr alloc)
+{
+  ISzAlloc_Free(alloc, p->blocks);
+  p->numBlocks = 0;
+  p->blocks = NULL;
+}
+
+unsigned XzFlags_GetCheckSize(CXzStreamFlags f)
+{
+  unsigned t = XzFlags_GetCheckType(f);
+  return (t == 0) ? 0 : ((unsigned)4 << ((t - 1) / 3));
+}
+
+void XzCheck_Init(CXzCheck *p, unsigned mode)
+{
+  p->mode = mode;
+  switch (mode)
+  {
+    case XZ_CHECK_CRC32: p->crc = CRC_INIT_VAL; break;
+    case XZ_CHECK_CRC64: p->crc64 = CRC64_INIT_VAL; break;
+    case XZ_CHECK_SHA256: Sha256_Init(&p->sha); break;
+  }
+}
+
+void XzCheck_Update(CXzCheck *p, const void *data, size_t size)
+{
+  switch (p->mode)
+  {
+    case XZ_CHECK_CRC32: p->crc = CrcUpdate(p->crc, data, size); break;
+    case XZ_CHECK_CRC64: p->crc64 = Crc64Update(p->crc64, data, size); break;
+    case XZ_CHECK_SHA256: Sha256_Update(&p->sha, (const Byte *)data, size); break;
+  }
+}
+
+int XzCheck_Final(CXzCheck *p, Byte *digest)
+{
+  switch (p->mode)
+  {
+    case XZ_CHECK_CRC32:
+      SetUi32(digest, CRC_GET_DIGEST(p->crc));
+      break;
+    case XZ_CHECK_CRC64:
+    {
+      int i;
+      UInt64 v = CRC64_GET_DIGEST(p->crc64);
+      for (i = 0; i < 8; i++, v >>= 8)
+        digest[i] = (Byte)(v & 0xFF);
+      break;
+    }
+    case XZ_CHECK_SHA256:
+      Sha256_Final(&p->sha, digest);
+      break;
+    default:
+      return 0;
+  }
+  return 1;
+}

3rdparty/lzma/src/XzCrc64.c

@@ -0,0 +1,86 @@
+/* XzCrc64.c -- CRC64 calculation
+2017-05-23 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "XzCrc64.h"
+#include "CpuArch.h"
+
+#define kCrc64Poly UINT64_CONST(0xC96C5795D7870F42)
+
+#ifdef MY_CPU_LE
+  #define CRC64_NUM_TABLES 4
+#else
+  #define CRC64_NUM_TABLES 5
+  #define CRC_UINT64_SWAP(v) \
+      ((v >> 56) \
+    | ((v >> 40) & ((UInt64)0xFF <<  8)) \
+    | ((v >> 24) & ((UInt64)0xFF << 16)) \
+    | ((v >>  8) & ((UInt64)0xFF << 24)) \
+    | ((v <<  8) & ((UInt64)0xFF << 32)) \
+    | ((v << 24) & ((UInt64)0xFF << 40)) \
+    | ((v << 40) & ((UInt64)0xFF << 48)) \
+    | ((v << 56)))
+
+  UInt64 MY_FAST_CALL XzCrc64UpdateT1_BeT4(UInt64 v, const void *data, size_t size, const UInt64 *table);
+#endif
+
+#ifndef MY_CPU_BE
+  UInt64 MY_FAST_CALL XzCrc64UpdateT4(UInt64 v, const void *data, size_t size, const UInt64 *table);
+#endif
+
+typedef UInt64 (MY_FAST_CALL *CRC64_FUNC)(UInt64 v, const void *data, size_t size, const UInt64 *table);
+
+static CRC64_FUNC g_Crc64Update;
+UInt64 g_Crc64Table[256 * CRC64_NUM_TABLES];
+
+UInt64 MY_FAST_CALL Crc64Update(UInt64 v, const void *data, size_t size)
+{
+  return g_Crc64Update(v, data, size, g_Crc64Table);
+}
+
+UInt64 MY_FAST_CALL Crc64Calc(const void *data, size_t size)
+{
+  return g_Crc64Update(CRC64_INIT_VAL, data, size, g_Crc64Table) ^ CRC64_INIT_VAL;
+}
+
+void MY_FAST_CALL Crc64GenerateTable()
+{
+  UInt32 i;
+  for (i = 0; i < 256; i++)
+  {
+    UInt64 r = i;
+    unsigned j;
+    for (j = 0; j < 8; j++)
+      r = (r >> 1) ^ (kCrc64Poly & ((UInt64)0 - (r & 1)));
+    g_Crc64Table[i] = r;
+  }
+  for (i = 256; i < 256 * CRC64_NUM_TABLES; i++)
+  {
+    UInt64 r = g_Crc64Table[(size_t)i - 256];
+    g_Crc64Table[i] = g_Crc64Table[r & 0xFF] ^ (r >> 8);
+  }
+  
+  #ifdef MY_CPU_LE
+
+  g_Crc64Update = XzCrc64UpdateT4;
+
+  #else
+  {
+    #ifndef MY_CPU_BE
+    UInt32 k = 1;
+    if (*(const Byte *)&k == 1)
+      g_Crc64Update = XzCrc64UpdateT4;
+    else
+    #endif
+    {
+      for (i = 256 * CRC64_NUM_TABLES - 1; i >= 256; i--)
+      {
+        UInt64 x = g_Crc64Table[(size_t)i - 256];
+        g_Crc64Table[i] = CRC_UINT64_SWAP(x);
+      }
+      g_Crc64Update = XzCrc64UpdateT1_BeT4;
+    }
+  }
+  #endif
+}

3rdparty/lzma/src/XzCrc64Opt.c

@@ -0,0 +1,71 @@
+/* XzCrc64Opt.c -- CRC64 calculation
+2021-02-09 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+
+#ifndef MY_CPU_BE
+
+#define CRC64_UPDATE_BYTE_2(crc, b) (table[((crc) ^ (b)) & 0xFF] ^ ((crc) >> 8))
+
+UInt64 MY_FAST_CALL XzCrc64UpdateT4(UInt64 v, const void *data, size_t size, const UInt64 *table);
+UInt64 MY_FAST_CALL XzCrc64UpdateT4(UInt64 v, const void *data, size_t size, const UInt64 *table)
+{
+  const Byte *p = (const Byte *)data;
+  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 3) != 0; size--, p++)
+    v = CRC64_UPDATE_BYTE_2(v, *p);
+  for (; size >= 4; size -= 4, p += 4)
+  {
+    UInt32 d = (UInt32)v ^ *(const UInt32 *)(const void *)p;
+    v = (v >> 32)
+        ^ (table + 0x300)[((d      ) & 0xFF)]
+        ^ (table + 0x200)[((d >>  8) & 0xFF)]
+        ^ (table + 0x100)[((d >> 16) & 0xFF)]
+        ^ (table + 0x000)[((d >> 24))];
+  }
+  for (; size > 0; size--, p++)
+    v = CRC64_UPDATE_BYTE_2(v, *p);
+  return v;
+}
+
+#endif
+
+
+#ifndef MY_CPU_LE
+
+#define CRC_UINT64_SWAP(v) \
+      ((v >> 56) \
+    | ((v >> 40) & ((UInt64)0xFF <<  8)) \
+    | ((v >> 24) & ((UInt64)0xFF << 16)) \
+    | ((v >>  8) & ((UInt64)0xFF << 24)) \
+    | ((v <<  8) & ((UInt64)0xFF << 32)) \
+    | ((v << 24) & ((UInt64)0xFF << 40)) \
+    | ((v << 40) & ((UInt64)0xFF << 48)) \
+    | ((v << 56)))
+
+#define CRC64_UPDATE_BYTE_2_BE(crc, b) (table[(Byte)((crc) >> 56) ^ (b)] ^ ((crc) << 8))
+
+UInt64 MY_FAST_CALL XzCrc64UpdateT1_BeT4(UInt64 v, const void *data, size_t size, const UInt64 *table);
+UInt64 MY_FAST_CALL XzCrc64UpdateT1_BeT4(UInt64 v, const void *data, size_t size, const UInt64 *table)
+{
+  const Byte *p = (const Byte *)data;
+  table += 0x100;
+  v = CRC_UINT64_SWAP(v);
+  for (; size > 0 && ((unsigned)(ptrdiff_t)p & 3) != 0; size--, p++)
+    v = CRC64_UPDATE_BYTE_2_BE(v, *p);
+  for (; size >= 4; size -= 4, p += 4)
+  {
+    UInt32 d = (UInt32)(v >> 32) ^ *(const UInt32 *)(const void *)p;
+    v = (v << 32)
+        ^ (table + 0x000)[((d      ) & 0xFF)]
+        ^ (table + 0x100)[((d >>  8) & 0xFF)]
+        ^ (table + 0x200)[((d >> 16) & 0xFF)]
+        ^ (table + 0x300)[((d >> 24))];
+  }
+  for (; size > 0; size--, p++)
+    v = CRC64_UPDATE_BYTE_2_BE(v, *p);
+  return CRC_UINT64_SWAP(v);
+}
+
+#endif

3rdparty/lzma/src/XzIn.c

@@ -0,0 +1,325 @@
+/* XzIn.c - Xz input
+2021-09-04 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "7zCrc.h"
+#include "CpuArch.h"
+#include "Xz.h"
+
+/*
+#define XZ_FOOTER_SIG_CHECK(p) (memcmp((p), XZ_FOOTER_SIG, XZ_FOOTER_SIG_SIZE) == 0)
+*/
+#define XZ_FOOTER_SIG_CHECK(p) ((p)[0] == XZ_FOOTER_SIG_0 && (p)[1] == XZ_FOOTER_SIG_1)
+
+
+SRes Xz_ReadHeader(CXzStreamFlags *p, ISeqInStream *inStream)
+{
+  Byte sig[XZ_STREAM_HEADER_SIZE];
+  RINOK(SeqInStream_Read2(inStream, sig, XZ_STREAM_HEADER_SIZE, SZ_ERROR_NO_ARCHIVE));
+  if (memcmp(sig, XZ_SIG, XZ_SIG_SIZE) != 0)
+    return SZ_ERROR_NO_ARCHIVE;
+  return Xz_ParseHeader(p, sig);
+}
+
+#define READ_VARINT_AND_CHECK(buf, pos, size, res) \
+  { unsigned s = Xz_ReadVarInt(buf + pos, size - pos, res); \
+  if (s == 0) return SZ_ERROR_ARCHIVE; \
+  pos += s; }
+
+SRes XzBlock_ReadHeader(CXzBlock *p, ISeqInStream *inStream, BoolInt *isIndex, UInt32 *headerSizeRes)
+{
+  Byte header[XZ_BLOCK_HEADER_SIZE_MAX];
+  unsigned headerSize;
+  *headerSizeRes = 0;
+  RINOK(SeqInStream_ReadByte(inStream, &header[0]));
+  headerSize = (unsigned)header[0];
+  if (headerSize == 0)
+  {
+    *headerSizeRes = 1;
+    *isIndex = True;
+    return SZ_OK;
+  }
+
+  *isIndex = False;
+  headerSize = (headerSize << 2) + 4;
+  *headerSizeRes = headerSize;
+  RINOK(SeqInStream_Read(inStream, header + 1, headerSize - 1));
+  return XzBlock_Parse(p, header);
+}
+
+#define ADD_SIZE_CHECK(size, val) \
+  { UInt64 newSize = size + (val); if (newSize < size) return XZ_SIZE_OVERFLOW; size = newSize; }
+
+UInt64 Xz_GetUnpackSize(const CXzStream *p)
+{
+  UInt64 size = 0;
+  size_t i;
+  for (i = 0; i < p->numBlocks; i++)
+    ADD_SIZE_CHECK(size, p->blocks[i].unpackSize);
+  return size;
+}
+
+UInt64 Xz_GetPackSize(const CXzStream *p)
+{
+  UInt64 size = 0;
+  size_t i;
+  for (i = 0; i < p->numBlocks; i++)
+    ADD_SIZE_CHECK(size, (p->blocks[i].totalSize + 3) & ~(UInt64)3);
+  return size;
+}
+
+/*
+SRes XzBlock_ReadFooter(CXzBlock *p, CXzStreamFlags f, ISeqInStream *inStream)
+{
+  return SeqInStream_Read(inStream, p->check, XzFlags_GetCheckSize(f));
+}
+*/
+
+static SRes Xz_ReadIndex2(CXzStream *p, const Byte *buf, size_t size, ISzAllocPtr alloc)
+{
+  size_t numBlocks, pos = 1;
+  UInt32 crc;
+
+  if (size < 5 || buf[0] != 0)
+    return SZ_ERROR_ARCHIVE;
+
+  size -= 4;
+  crc = CrcCalc(buf, size);
+  if (crc != GetUi32(buf + size))
+    return SZ_ERROR_ARCHIVE;
+
+  {
+    UInt64 numBlocks64;
+    READ_VARINT_AND_CHECK(buf, pos, size, &numBlocks64);
+    numBlocks = (size_t)numBlocks64;
+    if (numBlocks != numBlocks64 || numBlocks * 2 > size)
+      return SZ_ERROR_ARCHIVE;
+  }
+  
+  Xz_Free(p, alloc);
+  if (numBlocks != 0)
+  {
+    size_t i;
+    p->numBlocks = numBlocks;
+    p->blocks = (CXzBlockSizes *)ISzAlloc_Alloc(alloc, sizeof(CXzBlockSizes) * numBlocks);
+    if (!p->blocks)
+      return SZ_ERROR_MEM;
+    for (i = 0; i < numBlocks; i++)
+    {
+      CXzBlockSizes *block = &p->blocks[i];
+      READ_VARINT_AND_CHECK(buf, pos, size, &block->totalSize);
+      READ_VARINT_AND_CHECK(buf, pos, size, &block->unpackSize);
+      if (block->totalSize == 0)
+        return SZ_ERROR_ARCHIVE;
+    }
+  }
+  while ((pos & 3) != 0)
+    if (buf[pos++] != 0)
+      return SZ_ERROR_ARCHIVE;
+  return (pos == size) ? SZ_OK : SZ_ERROR_ARCHIVE;
+}
+
+static SRes Xz_ReadIndex(CXzStream *p, ILookInStream *stream, UInt64 indexSize, ISzAllocPtr alloc)
+{
+  SRes res;
+  size_t size;
+  Byte *buf;
+  if (indexSize > ((UInt32)1 << 31))
+    return SZ_ERROR_UNSUPPORTED;
+  size = (size_t)indexSize;
+  if (size != indexSize)
+    return SZ_ERROR_UNSUPPORTED;
+  buf = (Byte *)ISzAlloc_Alloc(alloc, size);
+  if (!buf)
+    return SZ_ERROR_MEM;
+  res = LookInStream_Read2(stream, buf, size, SZ_ERROR_UNSUPPORTED);
+  if (res == SZ_OK)
+    res = Xz_ReadIndex2(p, buf, size, alloc);
+  ISzAlloc_Free(alloc, buf);
+  return res;
+}
+
+static SRes LookInStream_SeekRead_ForArc(ILookInStream *stream, UInt64 offset, void *buf, size_t size)
+{
+  RINOK(LookInStream_SeekTo(stream, offset));
+  return LookInStream_Read(stream, buf, size);
+  /* return LookInStream_Read2(stream, buf, size, SZ_ERROR_NO_ARCHIVE); */
+}
+
+static SRes Xz_ReadBackward(CXzStream *p, ILookInStream *stream, Int64 *startOffset, ISzAllocPtr alloc)
+{
+  UInt64 indexSize;
+  Byte buf[XZ_STREAM_FOOTER_SIZE];
+  UInt64 pos = (UInt64)*startOffset;
+
+  if ((pos & 3) != 0 || pos < XZ_STREAM_FOOTER_SIZE)
+    return SZ_ERROR_NO_ARCHIVE;
+
+  pos -= XZ_STREAM_FOOTER_SIZE;
+  RINOK(LookInStream_SeekRead_ForArc(stream, pos, buf, XZ_STREAM_FOOTER_SIZE));
+  
+  if (!XZ_FOOTER_SIG_CHECK(buf + 10))
+  {
+    UInt32 total = 0;
+    pos += XZ_STREAM_FOOTER_SIZE;
+    
+    for (;;)
+    {
+      size_t i;
+      #define TEMP_BUF_SIZE (1 << 10)
+      Byte temp[TEMP_BUF_SIZE];
+      
+      i = (pos > TEMP_BUF_SIZE) ? TEMP_BUF_SIZE : (size_t)pos;
+      pos -= i;
+      RINOK(LookInStream_SeekRead_ForArc(stream, pos, temp, i));
+      total += (UInt32)i;
+      for (; i != 0; i--)
+        if (temp[i - 1] != 0)
+          break;
+      if (i != 0)
+      {
+        if ((i & 3) != 0)
+          return SZ_ERROR_NO_ARCHIVE;
+        pos += i;
+        break;
+      }
+      if (pos < XZ_STREAM_FOOTER_SIZE || total > (1 << 16))
+        return SZ_ERROR_NO_ARCHIVE;
+    }
+    
+    if (pos < XZ_STREAM_FOOTER_SIZE)
+      return SZ_ERROR_NO_ARCHIVE;
+    pos -= XZ_STREAM_FOOTER_SIZE;
+    RINOK(LookInStream_SeekRead_ForArc(stream, pos, buf, XZ_STREAM_FOOTER_SIZE));
+    if (!XZ_FOOTER_SIG_CHECK(buf + 10))
+      return SZ_ERROR_NO_ARCHIVE;
+  }
+  
+  p->flags = (CXzStreamFlags)GetBe16(buf + 8);
+
+  if (!XzFlags_IsSupported(p->flags))
+    return SZ_ERROR_UNSUPPORTED;
+
+  {
+    /* to eliminate GCC 6.3 warning:
+       dereferencing type-punned pointer will break strict-aliasing rules */
+    const Byte *buf_ptr = buf;
+    if (GetUi32(buf_ptr) != CrcCalc(buf + 4, 6))
+      return SZ_ERROR_ARCHIVE;
+  }
+
+  indexSize = ((UInt64)GetUi32(buf + 4) + 1) << 2;
+
+  if (pos < indexSize)
+    return SZ_ERROR_ARCHIVE;
+
+  pos -= indexSize;
+  RINOK(LookInStream_SeekTo(stream, pos));
+  RINOK(Xz_ReadIndex(p, stream, indexSize, alloc));
+
+  {
+    UInt64 totalSize = Xz_GetPackSize(p);
+    if (totalSize == XZ_SIZE_OVERFLOW
+        || totalSize >= ((UInt64)1 << 63)
+        || pos < totalSize + XZ_STREAM_HEADER_SIZE)
+      return SZ_ERROR_ARCHIVE;
+    pos -= (totalSize + XZ_STREAM_HEADER_SIZE);
+    RINOK(LookInStream_SeekTo(stream, pos));
+    *startOffset = (Int64)pos;
+  }
+  {
+    CXzStreamFlags headerFlags;
+    CSecToRead secToRead;
+    SecToRead_CreateVTable(&secToRead);
+    secToRead.realStream = stream;
+
+    RINOK(Xz_ReadHeader(&headerFlags, &secToRead.vt));
+    return (p->flags == headerFlags) ? SZ_OK : SZ_ERROR_ARCHIVE;
+  }
+}
+
+
+/* ---------- Xz Streams ---------- */
+
+void Xzs_Construct(CXzs *p)
+{
+  p->num = p->numAllocated = 0;
+  p->streams = 0;
+}
+
+void Xzs_Free(CXzs *p, ISzAllocPtr alloc)
+{
+  size_t i;
+  for (i = 0; i < p->num; i++)
+    Xz_Free(&p->streams[i], alloc);
+  ISzAlloc_Free(alloc, p->streams);
+  p->num = p->numAllocated = 0;
+  p->streams = 0;
+}
+
+UInt64 Xzs_GetNumBlocks(const CXzs *p)
+{
+  UInt64 num = 0;
+  size_t i;
+  for (i = 0; i < p->num; i++)
+    num += p->streams[i].numBlocks;
+  return num;
+}
+
+UInt64 Xzs_GetUnpackSize(const CXzs *p)
+{
+  UInt64 size = 0;
+  size_t i;
+  for (i = 0; i < p->num; i++)
+    ADD_SIZE_CHECK(size, Xz_GetUnpackSize(&p->streams[i]));
+  return size;
+}
+
+/*
+UInt64 Xzs_GetPackSize(const CXzs *p)
+{
+  UInt64 size = 0;
+  size_t i;
+  for (i = 0; i < p->num; i++)
+    ADD_SIZE_CHECK(size, Xz_GetTotalSize(&p->streams[i]));
+  return size;
+}
+*/
+
+SRes Xzs_ReadBackward(CXzs *p, ILookInStream *stream, Int64 *startOffset, ICompressProgress *progress, ISzAllocPtr alloc)
+{
+  Int64 endOffset = 0;
+  RINOK(ILookInStream_Seek(stream, &endOffset, SZ_SEEK_END));
+  *startOffset = endOffset;
+  for (;;)
+  {
+    CXzStream st;
+    SRes res;
+    Xz_Construct(&st);
+    res = Xz_ReadBackward(&st, stream, startOffset, alloc);
+    st.startOffset = (UInt64)*startOffset;
+    RINOK(res);
+    if (p->num == p->numAllocated)
+    {
+      const size_t newNum = p->num + p->num / 4 + 1;
+      void *data = ISzAlloc_Alloc(alloc, newNum * sizeof(CXzStream));
+      if (!data)
+        return SZ_ERROR_MEM;
+      p->numAllocated = newNum;
+      if (p->num != 0)
+        memcpy(data, p->streams, p->num * sizeof(CXzStream));
+      ISzAlloc_Free(alloc, p->streams);
+      p->streams = (CXzStream *)data;
+    }
+    p->streams[p->num++] = st;
+    if (*startOffset == 0)
+      break;
+    RINOK(LookInStream_SeekTo(stream, (UInt64)*startOffset));
+    if (progress && ICompressProgress_Progress(progress, (UInt64)(endOffset - *startOffset), (UInt64)(Int64)-1) != SZ_OK)
+      return SZ_ERROR_PROGRESS;
+  }
+  return SZ_OK;
+}

PCSX2_qt.sln

@@ -62,6 +62,8 @@ Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "zstd", "3rdparty\zstd\zstd.
 EndProject
 Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "d3d12memalloc", "3rdparty\d3d12memalloc\d3d12memalloc.vcxproj", "{D45CEC7A-3171-40DD-975D-E1544CF16139}"
 EndProject
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "lzma", "3rdparty\lzma\lzma.vcxproj", "{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}"
+EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
 		Debug AVX2|x64 = Debug AVX2|x64
@@ -384,6 +386,18 @@ Global
 		{D45CEC7A-3171-40DD-975D-E1544CF16139}.Release AVX2|x64.Build.0 = Release|x64
 		{D45CEC7A-3171-40DD-975D-E1544CF16139}.Release|x64.ActiveCfg = Release|x64
 		{D45CEC7A-3171-40DD-975D-E1544CF16139}.Release|x64.Build.0 = Release|x64
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}.Debug AVX2|x64.ActiveCfg = Debug|x64
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}.Debug AVX2|x64.Build.0 = Debug|x64
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}.Debug|x64.ActiveCfg = Debug|x64
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}.Debug|x64.Build.0 = Debug|x64
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}.Devel AVX2|x64.ActiveCfg = Devel|x64
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}.Devel AVX2|x64.Build.0 = Devel|x64
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}.Devel|x64.ActiveCfg = Devel|x64
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}.Devel|x64.Build.0 = Devel|x64
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}.Release AVX2|x64.ActiveCfg = Release|x64
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}.Release AVX2|x64.Build.0 = Release|x64
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}.Release|x64.ActiveCfg = Release|x64
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2}.Release|x64.Build.0 = Release|x64
 	EndGlobalSection
 	GlobalSection(SolutionProperties) = preSolution
 		HideSolutionNode = FALSE
@@ -412,6 +426,7 @@ Global
 		{20B2E9FE-F020-42A0-B324-956F5B06EA68} = {78EBE642-7A4D-4EA7-86BE-5639C6646C38}
 		{52244028-937A-44E9-A76B-2BEA18FD239A} = {78EBE642-7A4D-4EA7-86BE-5639C6646C38}
 		{D45CEC7A-3171-40DD-975D-E1544CF16139} = {78EBE642-7A4D-4EA7-86BE-5639C6646C38}
+		{A4323327-3F2B-4271-83D9-7F9A3C66B6B2} = {78EBE642-7A4D-4EA7-86BE-5639C6646C38}
 	EndGlobalSection
 	GlobalSection(ExtensibilityGlobals) = postSolution
 		SolutionGuid = {0BC474EA-3628-45D3-9DBC-E22D0B7E0F77}

cmake/SearchForStuff.cmake

@@ -17,6 +17,7 @@ if (WIN32)
 	add_subdirectory(3rdparty/wxwidgets3.0 EXCLUDE_FROM_ALL)
 	add_subdirectory(3rdparty/xz EXCLUDE_FROM_ALL)
 	add_subdirectory(3rdparty/D3D12MemAlloc EXCLUDE_FROM_ALL)
+	add_subdirectory(3rdparty/lzma EXCLUDE_FROM_ALL)
 else()
 	## Use cmake package to find module
 	if (Linux)