Squashed 'external/ircolib/' changes from ce3cd726c..de6e324bd

de6e324bd separate emu thread
10d3daf86 Roms List improvements
95d202f37 Let's make the rom list process on a separate thread so the emulator doesnt take ages to load.
fc306967f Wow the ROM Header was just completely busted. Game list view works now
bad1691ee fuck this shit
2b59e5f46 game list in progress
d26417b83 remappable inputs in progress
ac4af8106 input
e72abc240 update readme
430139dc9 Qt6 frontend
3080d4d45 Fix this small bug too
08cd13b85 Cop0 unused functions do not actually pose a threat (as per manual). They don't do anything, so shall we.
61bb4fb44 make idle loop detection a little more specific with where the load goes
b037de4c3 SAZDFsdff
12e81e73e need to figure out why n64-systemtest loops indefinitely at some address that appears to be valid (i think it's me not invalidating the cache properly)
204f0e13b idle skipping seems to work!
cb8bb634a sdkfjlasdf
58e5c89c1 Fix compilation issue on my machine (no idea)
24fb2898e attempting more serious idle skipping
214719577 Place rsp.Step inside cached interpreter. Gains about 3 more fps
bb97dcc23 mmmmm
920b77d38 wjkhasdfjhkasdf
430ccdab4 it's a start...
4f42a673a Cached interpreter plays Mario 64. Start looking into RSP as well
c9a030787 idle skipping works!
5fbda03ce new idea
366637aba Idle skipping... maybe?
609fa2fb0 Cache instructions implemented but broken lmao. Commented out for now
e140a6d12 - Stop using inheritance for CPU, instead use composition. - Introduce KAIZEN_JIT_ENABLED optional define instead of relying on __aarch64__ and the like. - More cache work
68e613057 prep cache impl
811b4d809 fix clang format
fda755f7d idk
d5024ebbf small MI refactor in preparation of (eventually) implementing the RDRAM interface properly
694b45341 Merge commit '206dcdedf195fb320913584180edb12c7731e396' as 'external/SDL'
206dcdedf Squashed 'external/SDL/' content from commit 4d17b99d0a
4d16e1cb4 need to update sdl
848b19920 Fix compilation error
db61b5299 Merge commit 'e94a94559f28e49678fbcf72199a5258137b0fe9' as 'external/imgui'
e94a94559 Squashed 'external/imgui/' content from commit 02e9b8cac
52edb3757 need to update imgui
c1a705e86 Emulate weird JALR behaviour
4b4c32f4b Fix exception for "unusable COP1" in 4 instructions i missed accidentally (again)
df5828142 Bug putting 0s in the log everywhere
f8b580048 Make isviewer a sink to file
8241e9735 Fix exception for "unusable COP1" in 4 instructions i missed accidentally
b29715f20 small changes
d9a620bc1 make use of my new small utility library
0d1aa938e Add 'external/ircolib/' from commit 'ce3cd726c8df8388d554abf8bb55d55020eb4450'
e64eb40b3 Fuck git

git-subtree-dir: external/ircolib
git-subtree-split: de6e324bde

external/unarr/lzmasdk/7z.h

@@ -0,0 +1,204 @@
+/* 7z.h -- 7z interface
+2023-04-02 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_7Z_H
+#define ZIP7_INC_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,
+    ILookInStreamPtr 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,
+    ILookInStreamPtr 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, ILookInStreamPtr inStream,
+    ISzAllocPtr allocMain, ISzAllocPtr allocTemp);
+
+EXTERN_C_END
+
+#endif

external/unarr/lzmasdk/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;
+}

external/unarr/lzmasdk/7zBuf.h

@@ -0,0 +1,35 @@
+/* 7zBuf.h -- Byte Buffer
+2023-03-04 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_7Z_BUF_H
+#define ZIP7_INC_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

external/unarr/lzmasdk/7zCrc.h

@@ -0,0 +1,27 @@
+/* 7zCrc.h -- CRC32 calculation
+2023-04-02 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_7Z_CRC_H
+#define ZIP7_INC_7Z_CRC_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+extern UInt32 g_CrcTable[];
+
+/* Call CrcGenerateTable one time before other CRC functions */
+void Z7_FASTCALL 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 Z7_FASTCALL CrcUpdate(UInt32 crc, const void *data, size_t size);
+UInt32 Z7_FASTCALL CrcCalc(const void *data, size_t size);
+
+typedef UInt32 (Z7_FASTCALL *CRC_FUNC)(UInt32 v, const void *data, size_t size, const UInt32 *table);
+
+EXTERN_C_END
+
+#endif

external/unarr/lzmasdk/7zDec.c

@@ -0,0 +1,648 @@
+/* 7zDec.c -- Decoding from 7z folder
+2023-04-02 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+/* #define Z7_PPMD_SUPPORT */
+
+#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 Z7_PPMD_SUPPORT
+#include "Ppmd7.h"
+#endif
+
+#define k_Copy 0
+#ifndef Z7_NO_METHOD_LZMA2
+#define k_LZMA2 0x21
+#endif
+#define k_LZMA  0x30101
+#define k_BCJ2  0x303011B
+
+#if !defined(Z7_NO_METHODS_FILTERS)
+#define Z7_USE_BRANCH_FILTER
+#endif
+
+#if !defined(Z7_NO_METHODS_FILTERS) || \
+     defined(Z7_USE_NATIVE_BRANCH_FILTER) && defined(MY_CPU_ARM64)
+#define Z7_USE_FILTER_ARM64
+#ifndef Z7_USE_BRANCH_FILTER
+#define Z7_USE_BRANCH_FILTER
+#endif
+#define k_ARM64 0xa
+#endif
+
+#if !defined(Z7_NO_METHODS_FILTERS) || \
+     defined(Z7_USE_NATIVE_BRANCH_FILTER) && defined(MY_CPU_ARMT)
+#define Z7_USE_FILTER_ARMT
+#ifndef Z7_USE_BRANCH_FILTER
+#define Z7_USE_BRANCH_FILTER
+#endif
+#define k_ARMT  0x3030701
+#endif
+
+#ifndef Z7_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_SPARC 0x3030805
+#endif
+
+#ifdef Z7_PPMD_SUPPORT
+
+#define k_PPMD 0x30401
+
+typedef struct
+{
+  IByteIn vt;
+  const Byte *cur;
+  const Byte *end;
+  const Byte *begin;
+  UInt64 processed;
+  BoolInt extra;
+  SRes res;
+  ILookInStreamPtr inStream;
+} CByteInToLook;
+
+static Byte ReadByte(IByteInPtr pp)
+{
+  Z7_CONTAINER_FROM_VTBL_TO_DECL_VAR_pp_vt_p(CByteInToLook)
+  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, ILookInStreamPtr 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, ILookInStreamPtr 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 Z7_NO_METHOD_LZMA2
+
+static SRes SzDecodeLzma2(const Byte *props, unsigned propsSize, UInt64 inSize, ILookInStreamPtr 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, ILookInStreamPtr 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 Z7_NO_METHOD_LZMA2
+    case k_LZMA2:
+  #endif
+  #ifdef Z7_PPMD_SUPPORT
+    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;
+  }
+  
+  
+  #if defined(Z7_USE_BRANCH_FILTER)
+
+  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)
+    {
+    #if !defined(Z7_NO_METHODS_FILTERS)
+      case k_Delta:
+      case k_BCJ:
+      case k_PPC:
+      case k_IA64:
+      case k_SPARC:
+      case k_ARM:
+    #endif
+    #ifdef Z7_USE_FILTER_ARM64
+      case k_ARM64:
+    #endif
+    #ifdef Z7_USE_FILTER_ARMT
+      case k_ARMT:
+    #endif
+        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;
+}
+
+
+
+
+
+
+static SRes SzFolder_Decode2(const CSzFolder *folder,
+    const Byte *propsData,
+    const UInt64 *unpackSizes,
+    const UInt64 *packPositions,
+    ILookInStreamPtr 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)
+      {
+        const UInt32 indices[] = { 3, 2, 0 };
+        const 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 Z7_NO_METHOD_LZMA2
+      else if (coder->MethodID == k_LZMA2)
+      {
+        RINOK(SzDecodeLzma2(propsData + coder->PropsOffset, coder->PropsSize, inSize, inStream, outBufCur, outSizeCur, allocMain))
+      }
+    #endif
+    #ifdef Z7_PPMD_SUPPORT
+      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)
+    {
+      const UInt64 offset = packPositions[1];
+      const 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 (p.dest != p.destLim || !Bcj2Dec_IsMaybeFinished(&p))
+            return SZ_ERROR_DATA;
+        }
+      }
+    }
+  #if defined(Z7_USE_BRANCH_FILTER)
+    else if (ci == 1)
+    {
+     #if !defined(Z7_NO_METHODS_FILTERS)
+      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);
+        }
+        continue;
+      }
+     #endif
+     
+     #ifdef Z7_USE_FILTER_ARM64
+      if (coder->MethodID == k_ARM64)
+      {
+        UInt32 pc = 0;
+        if (coder->PropsSize == 4)
+          pc = GetUi32(propsData + coder->PropsOffset);
+        else if (coder->PropsSize != 0)
+          return SZ_ERROR_UNSUPPORTED;
+        z7_BranchConv_ARM64_Dec(outBuffer, outSize, pc);
+        continue;
+      }
+     #endif
+     
+     #if !defined(Z7_NO_METHODS_FILTERS) || defined(Z7_USE_FILTER_ARMT)
+      {
+        if (coder->PropsSize != 0)
+          return SZ_ERROR_UNSUPPORTED;
+       #define CASE_BRA_CONV(isa) case k_ ## isa: Z7_BRANCH_CONV_DEC(isa)(outBuffer, outSize, 0); break; // pc = 0;
+        switch (coder->MethodID)
+        {
+         #if !defined(Z7_NO_METHODS_FILTERS)
+          case k_BCJ:
+          {
+            UInt32 state = Z7_BRANCH_CONV_ST_X86_STATE_INIT_VAL;
+            z7_BranchConvSt_X86_Dec(outBuffer, outSize, 0, &state); // pc = 0
+            break;
+          }
+          CASE_BRA_CONV(PPC)
+          CASE_BRA_CONV(IA64)
+          CASE_BRA_CONV(SPARC)
+          CASE_BRA_CONV(ARM)
+         #endif
+         #if !defined(Z7_NO_METHODS_FILTERS) || defined(Z7_USE_FILTER_ARMT)
+          CASE_BRA_CONV(ARMT)
+         #endif
+          default:
+            return SZ_ERROR_UNSUPPORTED;
+        }
+        continue;
+      }
+     #endif
+    } // (c == 1)
+  #endif
+    else
+      return SZ_ERROR_UNSUPPORTED;
+  }
+
+  return SZ_OK;
+}
+
+
+SRes SzAr_DecodeFolder(const CSzAr *p, UInt32 folderIndex,
+    ILookInStreamPtr 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;
+  }
+}

external/unarr/lzmasdk/7zStream.c

@@ -0,0 +1,199 @@
+/* 7zStream.c -- 7z Stream functions
+2023-04-02 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "7zTypes.h"
+
+
+SRes SeqInStream_ReadMax(ISeqInStreamPtr stream, void *buf, size_t *processedSize)
+{
+  size_t size = *processedSize;
+  *processedSize = 0;
+  while (size != 0)
+  {
+    size_t cur = size;
+    const SRes res = ISeqInStream_Read(stream, buf, &cur);
+    *processedSize += cur;
+    buf = (void *)((Byte *)buf + cur);
+    size -= cur;
+    if (res != SZ_OK)
+      return res;
+    if (cur == 0)
+      return SZ_OK;
+  }
+  return SZ_OK;
+}
+
+/*
+SRes SeqInStream_Read2(ISeqInStreamPtr 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(ISeqInStreamPtr stream, void *buf, size_t size)
+{
+  return SeqInStream_Read2(stream, buf, size, SZ_ERROR_INPUT_EOF);
+}
+*/
+
+
+SRes SeqInStream_ReadByte(ISeqInStreamPtr 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(ILookInStreamPtr stream, UInt64 offset)
+{
+  Int64 t = (Int64)offset;
+  return ILookInStream_Seek(stream, &t, SZ_SEEK_SET);
+}
+
+SRes LookInStream_LookRead(ILookInStreamPtr 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(ILookInStreamPtr 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(ILookInStreamPtr stream, void *buf, size_t size)
+{
+  return LookInStream_Read2(stream, buf, size, SZ_ERROR_INPUT_EOF);
+}
+
+
+
+#define GET_LookToRead2  Z7_CONTAINER_FROM_VTBL_TO_DECL_VAR_pp_vt_p(CLookToRead2)
+
+static SRes LookToRead2_Look_Lookahead(ILookInStreamPtr 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(ILookInStreamPtr 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(ILookInStreamPtr pp, size_t offset)
+{
+  GET_LookToRead2
+  p->pos += offset;
+  return SZ_OK;
+}
+
+static SRes LookToRead2_Read(ILookInStreamPtr 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(ILookInStreamPtr 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(ISeqInStreamPtr pp, void *buf, size_t *size)
+{
+  Z7_CONTAINER_FROM_VTBL_TO_DECL_VAR_pp_vt_p(CSecToLook)
+  return LookInStream_LookRead(p->realStream, buf, size);
+}
+
+void SecToLook_CreateVTable(CSecToLook *p)
+{
+  p->vt.Read = SecToLook_Read;
+}
+
+static SRes SecToRead_Read(ISeqInStreamPtr pp, void *buf, size_t *size)
+{
+  Z7_CONTAINER_FROM_VTBL_TO_DECL_VAR_pp_vt_p(CSecToRead)
+  return ILookInStream_Read(p->realStream, buf, size);
+}
+
+void SecToRead_CreateVTable(CSecToRead *p)
+{
+  p->vt.Read = SecToRead_Read;
+}

external/unarr/lzmasdk/7zTypes.h

@@ -0,0 +1,597 @@
+/* 7zTypes.h -- Basic types
+2023-04-02 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_7Z_TYPES_H
+#define ZIP7_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
+  /*
+  // C11/C++11:
+  #include <stdalign.h>
+  #define MY_ALIGN(n) alignas(n)
+  */
+  #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)
+*/
+
+#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) { const int _result_ = (x); if (_result_ != 0) return _result_; }
+#endif
+
+#ifndef RINOK_WRes
+#define RINOK_WRes(x) { const WRes _result_ = (x); if (_result_ != 0) return _result_; }
+#endif
+
+typedef unsigned char Byte;
+typedef short Int16;
+typedef unsigned short UInt16;
+
+#ifdef Z7_DECL_Int32_AS_long
+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 Z7_DECL_Int64_AS_long
+
+typedef long Int64;
+typedef unsigned long UInt64;
+
+#else
+
+#if (defined(_MSC_VER) || defined(__BORLANDC__)) && !defined(__clang__)
+typedef __int64 Int64;
+typedef unsigned __int64 UInt64;
+#else
+#if defined(__clang__) || defined(__GNUC__)
+#include <stdint.h>
+typedef int64_t Int64;
+typedef uint64_t UInt64;
+#else
+typedef long long int Int64;
+typedef unsigned long long int UInt64;
+// #define UINT64_CONST(n) n ## ULL
+#endif
+#endif
+
+#endif
+
+#define UINT64_CONST(n) n
+
+
+#ifdef Z7_DECL_SizeT_AS_unsigned_int
+typedef unsigned int SizeT;
+#else
+typedef size_t SizeT;
+#endif
+
+/*
+#if (defined(_MSC_VER) && _MSC_VER <= 1200)
+typedef size_t MY_uintptr_t;
+#else
+#include <stdint.h>
+typedef uintptr_t MY_uintptr_t;
+#endif
+*/
+
+typedef int BoolInt;
+/* typedef BoolInt Bool; */
+#define True 1
+#define False 0
+
+
+#ifdef _WIN32
+#define Z7_STDCALL __stdcall
+#else
+#define Z7_STDCALL
+#endif
+
+#ifdef _MSC_VER
+
+#if _MSC_VER >= 1300
+#define Z7_NO_INLINE __declspec(noinline)
+#else
+#define Z7_NO_INLINE
+#endif
+
+#define Z7_FORCE_INLINE __forceinline
+
+#define Z7_CDECL      __cdecl
+#define Z7_FASTCALL  __fastcall
+
+#else //  _MSC_VER
+
+#if (defined(__GNUC__) && (__GNUC__ >= 4)) \
+    || (defined(__clang__) && (__clang_major__ >= 4)) \
+    || defined(__INTEL_COMPILER) \
+    || defined(__xlC__)
+#define Z7_NO_INLINE      __attribute__((noinline))
+#define Z7_FORCE_INLINE   __attribute__((always_inline)) inline
+#else
+#define Z7_NO_INLINE
+#define Z7_FORCE_INLINE
+#endif
+
+#define Z7_CDECL
+
+#if  defined(_M_IX86) \
+  || defined(__i386__)
+// #define Z7_FASTCALL __attribute__((fastcall))
+// #define Z7_FASTCALL __attribute__((cdecl))
+#define Z7_FASTCALL
+#elif defined(MY_CPU_AMD64)
+// #define Z7_FASTCALL __attribute__((ms_abi))
+#define Z7_FASTCALL
+#else
+#define Z7_FASTCALL
+#endif
+
+#endif //  _MSC_VER
+
+
+/* The following interfaces use first parameter as pointer to structure */
+
+// #define Z7_C_IFACE_CONST_QUAL
+#define Z7_C_IFACE_CONST_QUAL const
+
+#define Z7_C_IFACE_DECL(a) \
+  struct a ## _; \
+  typedef Z7_C_IFACE_CONST_QUAL struct a ## _ * a ## Ptr; \
+  typedef struct a ## _ a; \
+  struct a ## _
+
+
+Z7_C_IFACE_DECL (IByteIn)
+{
+  Byte (*Read)(IByteInPtr p); /* reads one byte, returns 0 in case of EOF or error */
+};
+#define IByteIn_Read(p) (p)->Read(p)
+
+
+Z7_C_IFACE_DECL (IByteOut)
+{
+  void (*Write)(IByteOutPtr p, Byte b);
+};
+#define IByteOut_Write(p, b) (p)->Write(p, b)
+
+
+Z7_C_IFACE_DECL (ISeqInStream)
+{
+  SRes (*Read)(ISeqInStreamPtr 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)
+
+/* try to read as much as avail in stream and limited by (*processedSize) */
+SRes SeqInStream_ReadMax(ISeqInStreamPtr stream, void *buf, size_t *processedSize);
+/* it can return SZ_ERROR_INPUT_EOF */
+// SRes SeqInStream_Read(ISeqInStreamPtr stream, void *buf, size_t size);
+// SRes SeqInStream_Read2(ISeqInStreamPtr stream, void *buf, size_t size, SRes errorType);
+SRes SeqInStream_ReadByte(ISeqInStreamPtr stream, Byte *buf);
+
+
+Z7_C_IFACE_DECL (ISeqOutStream)
+{
+  size_t (*Write)(ISeqOutStreamPtr 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;
+
+
+Z7_C_IFACE_DECL (ISeekInStream)
+{
+  SRes (*Read)(ISeekInStreamPtr p, void *buf, size_t *size);  /* same as ISeqInStream::Read */
+  SRes (*Seek)(ISeekInStreamPtr 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)
+
+
+Z7_C_IFACE_DECL (ILookInStream)
+{
+  SRes (*Look)(ILookInStreamPtr 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)(ILookInStreamPtr p, size_t offset);
+    /* offset must be <= output(*size) of Look */
+  SRes (*Read)(ILookInStreamPtr p, void *buf, size_t *size);
+    /* reads directly (without buffer). It's same as ISeqInStream::Read */
+  SRes (*Seek)(ILookInStreamPtr 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(ILookInStreamPtr stream, void *buf, size_t *size);
+SRes LookInStream_SeekTo(ILookInStreamPtr stream, UInt64 offset);
+
+/* reads via ILookInStream::Read */
+SRes LookInStream_Read2(ILookInStreamPtr stream, void *buf, size_t size, SRes errorType);
+SRes LookInStream_Read(ILookInStreamPtr stream, void *buf, size_t size);
+
+
+typedef struct
+{
+  ILookInStream vt;
+  ISeekInStreamPtr 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;
+  ILookInStreamPtr realStream;
+} CSecToLook;
+
+void SecToLook_CreateVTable(CSecToLook *p);
+
+
+
+typedef struct
+{
+  ISeqInStream vt;
+  ILookInStreamPtr realStream;
+} CSecToRead;
+
+void SecToRead_CreateVTable(CSecToRead *p);
+
+
+Z7_C_IFACE_DECL (ICompressProgress)
+{
+  SRes (*Progress)(ICompressProgressPtr 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 Z7_container_of
+
+/*
+#define Z7_container_of(ptr, type, m) container_of(ptr, type, m)
+#define Z7_container_of(ptr, type, m) CONTAINING_RECORD(ptr, type, m)
+#define Z7_container_of(ptr, type, m) ((type *)((char *)(ptr) - offsetof(type, m)))
+#define Z7_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 Z7_container_of(ptr, type, m) \
+  ((type *)(void *)((char *)(void *) \
+  (1 ? (ptr) : &((type *)NULL)->m) - MY_offsetof(type, m)))
+
+#define Z7_container_of_CONST(ptr, type, m) \
+  ((const type *)(const void *)((const char *)(const void *) \
+  (1 ? (ptr) : &((type *)NULL)->m) - MY_offsetof(type, m)))
+
+/*
+#define Z7_container_of_NON_CONST_FROM_CONST(ptr, type, m) \
+  ((type *)(void *)(const void *)((const char *)(const void *) \
+  (1 ? (ptr) : &((type *)NULL)->m) - MY_offsetof(type, m)))
+*/
+
+#endif
+
+#define Z7_CONTAINER_FROM_VTBL_SIMPLE(ptr, type, m) ((type *)(void *)(ptr))
+
+// #define Z7_CONTAINER_FROM_VTBL(ptr, type, m) Z7_CONTAINER_FROM_VTBL_SIMPLE(ptr, type, m)
+#define Z7_CONTAINER_FROM_VTBL(ptr, type, m) Z7_container_of(ptr, type, m)
+// #define Z7_CONTAINER_FROM_VTBL(ptr, type, m) Z7_container_of_NON_CONST_FROM_CONST(ptr, type, m)
+
+#define Z7_CONTAINER_FROM_VTBL_CONST(ptr, type, m) Z7_container_of_CONST(ptr, type, m)
+
+#define Z7_CONTAINER_FROM_VTBL_CLS(ptr, type, m) Z7_CONTAINER_FROM_VTBL_SIMPLE(ptr, type, m)
+/*
+#define Z7_CONTAINER_FROM_VTBL_CLS(ptr, type, m) Z7_CONTAINER_FROM_VTBL(ptr, type, m)
+*/
+#if defined (__clang__) || defined(__GNUC__)
+#define Z7_DIAGNOSCTIC_IGNORE_BEGIN_CAST_QUAL \
+  _Pragma("GCC diagnostic push") \
+  _Pragma("GCC diagnostic ignored \"-Wcast-qual\"")
+#define Z7_DIAGNOSCTIC_IGNORE_END_CAST_QUAL \
+  _Pragma("GCC diagnostic pop")
+#else
+#define Z7_DIAGNOSCTIC_IGNORE_BEGIN_CAST_QUAL
+#define Z7_DIAGNOSCTIC_IGNORE_END_CAST_QUAL
+#endif
+
+#define Z7_CONTAINER_FROM_VTBL_TO_DECL_VAR(ptr, type, m, p) \
+  Z7_DIAGNOSCTIC_IGNORE_BEGIN_CAST_QUAL \
+  type *p = Z7_CONTAINER_FROM_VTBL(ptr, type, m); \
+  Z7_DIAGNOSCTIC_IGNORE_END_CAST_QUAL
+
+#define Z7_CONTAINER_FROM_VTBL_TO_DECL_VAR_pp_vt_p(type) \
+  Z7_CONTAINER_FROM_VTBL_TO_DECL_VAR(pp, type, vt, p)
+
+
+// #define ZIP7_DECLARE_HANDLE(name)  typedef void *name;
+#define Z7_DECLARE_HANDLE(name)  struct name##_dummy{int unused;}; typedef struct name##_dummy *name;
+
+
+#define Z7_memset_0_ARRAY(a)  memset((a), 0, sizeof(a))
+
+#ifndef Z7_ARRAY_SIZE
+#define Z7_ARRAY_SIZE(a) (sizeof(a) / sizeof((a)[0]))
+#endif
+
+
+#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
+
+#define k_PropVar_TimePrec_0        0
+#define k_PropVar_TimePrec_Unix     1
+#define k_PropVar_TimePrec_DOS      2
+#define k_PropVar_TimePrec_HighPrec 3
+#define k_PropVar_TimePrec_Base     16
+#define k_PropVar_TimePrec_100ns (k_PropVar_TimePrec_Base + 7)
+#define k_PropVar_TimePrec_1ns   (k_PropVar_TimePrec_Base + 9)
+
+EXTERN_C_END
+
+#endif
+
+/*
+#ifndef Z7_ST
+#ifdef _7ZIP_ST
+#define Z7_ST
+#endif
+#endif
+*/

external/unarr/lzmasdk/7zWindows.h

@@ -0,0 +1,101 @@
+/* 7zWindows.h -- StdAfx
+2023-04-02 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_7Z_WINDOWS_H
+#define ZIP7_INC_7Z_WINDOWS_H
+
+#ifdef _WIN32
+
+#if defined(__clang__)
+# pragma clang diagnostic push
+#endif
+
+#if defined(_MSC_VER)
+
+#pragma warning(push)
+#pragma warning(disable : 4668) // '_WIN32_WINNT' is not defined as a preprocessor macro, replacing with '0' for '#if/#elif'
+
+#if _MSC_VER == 1900
+// for old kit10 versions
+// #pragma warning(disable : 4255) // winuser.h(13979): warning C4255: 'GetThreadDpiAwarenessContext':
+#endif
+// win10 Windows Kit:
+#endif // _MSC_VER
+
+#if defined(_MSC_VER) && _MSC_VER <= 1200 && !defined(_WIN64)
+// for msvc6 without sdk2003
+#define RPC_NO_WINDOWS_H
+#endif
+
+#if defined(__MINGW32__) || defined(__MINGW64__)
+// #if defined(__GNUC__) && !defined(__clang__)
+#include <windows.h>
+#else
+#include <Windows.h>
+#endif
+// #include <basetsd.h>
+// #include <wtypes.h>
+
+// but if precompiled with clang-cl then we need
+// #include <windows.h>
+#if defined(_MSC_VER)
+#pragma warning(pop)
+#endif
+
+#if defined(__clang__)
+# pragma clang diagnostic pop
+#endif
+
+#if defined(_MSC_VER) && _MSC_VER <= 1200 && !defined(_WIN64)
+#ifndef _W64
+
+typedef long LONG_PTR, *PLONG_PTR;
+typedef unsigned long ULONG_PTR, *PULONG_PTR;
+typedef ULONG_PTR DWORD_PTR, *PDWORD_PTR;
+
+#define Z7_OLD_WIN_SDK
+#endif // _W64
+#endif // _MSC_VER == 1200
+
+#ifdef Z7_OLD_WIN_SDK
+
+#ifndef INVALID_FILE_ATTRIBUTES
+#define INVALID_FILE_ATTRIBUTES ((DWORD)-1)
+#endif
+#ifndef INVALID_SET_FILE_POINTER
+#define INVALID_SET_FILE_POINTER ((DWORD)-1)
+#endif
+#ifndef FILE_SPECIAL_ACCESS
+#define FILE_SPECIAL_ACCESS    (FILE_ANY_ACCESS)
+#endif
+
+// ShlObj.h:
+// #define BIF_NEWDIALOGSTYLE     0x0040
+
+#pragma warning(disable : 4201)
+// #pragma warning(disable : 4115)
+
+#undef  VARIANT_TRUE
+#define VARIANT_TRUE ((VARIANT_BOOL)-1)
+#endif
+
+#endif // Z7_OLD_WIN_SDK
+
+#ifdef UNDER_CE
+#undef  VARIANT_TRUE
+#define VARIANT_TRUE ((VARIANT_BOOL)-1)
+#endif
+
+
+#if defined(_MSC_VER)
+#if _MSC_VER >= 1400 && _MSC_VER <= 1600
+  // BaseTsd.h(148) : 'HandleToULong' : unreferenced inline function has been removed
+  // string.h
+  // #pragma warning(disable : 4514)
+#endif
+#endif
+
+
+/* #include "7zTypes.h" */
+
+#endif

external/unarr/lzmasdk/Bcj2.c

@@ -0,0 +1,290 @@
+/* Bcj2.c -- BCJ2 Decoder (Converter for x86 code)
+2023-03-01 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Bcj2.h"
+#include "CpuArch.h"
+
+#define kTopValue ((UInt32)1 << 24)
+#define kNumBitModelTotalBits 11
+#define kBitModelTotal (1 << kNumBitModelTotalBits)
+#define kNumMoveBits 5
+
+// UInt32 bcj2_stats[256 + 2][2];
+
+void Bcj2Dec_Init(CBcj2Dec *p)
+{
+  unsigned i;
+  p->state = BCJ2_STREAM_RC; // BCJ2_DEC_STATE_OK;
+  p->ip = 0;
+  p->temp = 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)
+{
+  UInt32 v = p->temp;
+  // const Byte *src;
+  if (p->range <= 5)
+  {
+    UInt32 code = p->code;
+    p->state = BCJ2_DEC_STATE_ERROR; /* for case if we return SZ_ERROR_DATA; */
+    for (; p->range != 5; p->range++)
+    {
+      if (p->range == 1 && 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;
+      }
+      code = (code << 8) | *(p->bufs[BCJ2_STREAM_RC])++;
+      p->code = code;
+    }
+    if (code == 0xffffffff)
+      return SZ_ERROR_DATA;
+    p->range = 0xffffffff;
+  }
+  // else
+  {
+    unsigned state = p->state;
+    // we check BCJ2_IS_32BIT_STREAM() here instead of check in the main loop
+    if (BCJ2_IS_32BIT_STREAM(state))
+    {
+      const Byte *cur = p->bufs[state];
+      if (cur == p->lims[state])
+        return SZ_OK;
+      p->bufs[state] = cur + 4;
+      {
+        const UInt32 ip = p->ip + 4;
+        v = GetBe32a(cur) - ip;
+        p->ip = ip;
+      }
+      state = BCJ2_DEC_STATE_ORIG_0;
+    }
+    if ((unsigned)(state - BCJ2_DEC_STATE_ORIG_0) < 4)
+    {
+      Byte *dest = p->dest;
+      for (;;)
+      {
+        if (dest == p->destLim)
+        {
+          p->state = state;
+          p->temp = v;
+          return SZ_OK;
+        }
+        *dest++ = (Byte)v;
+        p->dest = dest;
+        if (++state == BCJ2_DEC_STATE_ORIG_3 + 1)
+          break;
+        v >>= 8;
+      }
+    }
+  }
+
+  // src = p->bufs[BCJ2_STREAM_MAIN];
+  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;
+          p->temp = v;
+          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 = p->dest;
+        {
+          const SizeT rem = (SizeT)(p->lims[BCJ2_STREAM_MAIN] - src);
+          SizeT num = (SizeT)(p->destLim - dest);
+          if (num >= rem)
+            num = rem;
+        #define NUM_ITERS 4
+        #if (NUM_ITERS & (NUM_ITERS - 1)) == 0
+          num &= ~((SizeT)NUM_ITERS - 1);   // if (NUM_ITERS == (1 << x))
+        #else
+          num -= num % NUM_ITERS; // if (NUM_ITERS != (1 << x))
+        #endif
+          srcLim = src + num;
+        }
+
+        #define NUM_SHIFT_BITS  24
+        #define ONE_ITER(indx) { \
+          const unsigned b = src[indx]; \
+          *dest++ = (Byte)b; \
+          v = (v << NUM_SHIFT_BITS) | b; \
+          if (((b + (0x100 - 0xe8)) & 0xfe) == 0) break; \
+          if (((v - (((UInt32)0x0f << (NUM_SHIFT_BITS)) + 0x80)) & \
+              ((((UInt32)1 << (4 + NUM_SHIFT_BITS)) - 0x1) << 4)) == 0) break; \
+            /* ++dest */; /* v = b; */ }
+          
+        if (src != srcLim)
+        for (;;)
+        {
+            /* The dependency chain of 2-cycle for (v) calculation is not big problem here.
+               But we can remove dependency chain with v = b in the end of loop. */
+          ONE_ITER(0)
+          #if (NUM_ITERS > 1)
+            ONE_ITER(1)
+          #if (NUM_ITERS > 2)
+            ONE_ITER(2)
+          #if (NUM_ITERS > 3)
+            ONE_ITER(3)
+          #if (NUM_ITERS > 4)
+            ONE_ITER(4)
+          #if (NUM_ITERS > 5)
+            ONE_ITER(5)
+          #if (NUM_ITERS > 6)
+            ONE_ITER(6)
+          #if (NUM_ITERS > 7)
+            ONE_ITER(7)
+          #endif
+          #endif
+          #endif
+          #endif
+          #endif
+          #endif
+          #endif
+          
+          src += NUM_ITERS;
+          if (src == srcLim)
+            break;
+        }
+
+        if (src == srcLim)
+      #if (NUM_ITERS > 1)
+        for (;;)
+      #endif
+        {
+        #if (NUM_ITERS > 1)
+          if (src == p->lims[BCJ2_STREAM_MAIN] || dest == p->destLim)
+        #endif
+          {
+            const SizeT num = (SizeT)(src - p->bufs[BCJ2_STREAM_MAIN]);
+            p->bufs[BCJ2_STREAM_MAIN] = src;
+            p->dest = dest;
+            p->ip += (UInt32)num;
+            /* state BCJ2_STREAM_MAIN has more priority than BCJ2_STATE_ORIG */
+            p->state =
+              src == p->lims[BCJ2_STREAM_MAIN] ?
+                (unsigned)BCJ2_STREAM_MAIN :
+                (unsigned)BCJ2_DEC_STATE_ORIG;
+            p->temp = v;
+            return SZ_OK;
+          }
+        #if (NUM_ITERS > 1)
+          ONE_ITER(0)
+          src++;
+        #endif
+        }
+
+        {
+          const SizeT num = (SizeT)(dest - p->dest);
+          p->dest = dest; // p->dest += num;
+          p->bufs[BCJ2_STREAM_MAIN] += num; // = src;
+          p->ip += (UInt32)num;
+        }
+        {
+          UInt32 bound, ttt;
+          CBcj2Prob *prob; // unsigned index;
+          /*
+          prob = p->probs + (unsigned)((Byte)v == 0xe8 ?
+              2 + (Byte)(v >> 8) :
+              ((v >> 5) & 1));  // ((Byte)v < 0xe8 ? 0 : 1));
+          */
+          {
+            const unsigned c = ((v + 0x17) >> 6) & 1;
+            prob = p->probs + (unsigned)
+                (((0 - c) & (Byte)(v >> NUM_SHIFT_BITS)) + c + ((v >> 5) & 1));
+                // (Byte)
+                // 8x->0     : e9->1     : xxe8->xx+2
+                // 8x->0x100 : e9->0x101 : xxe8->xx
+                // (((0x100 - (e & ~v)) & (0x100 | (v >> 8))) + (e & v));
+                // (((0x101 + (~e | v)) & (0x100 | (v >> 8))) + (e & v));
+          }
+          ttt = *prob;
+          bound = (p->range >> kNumBitModelTotalBits) * ttt;
+          if (p->code < bound)
+          {
+            // bcj2_stats[prob - p->probs][0]++;
+            p->range = bound;
+            *prob = (CBcj2Prob)(ttt + ((kBitModelTotal - ttt) >> kNumMoveBits));
+            continue;
+          }
+          {
+            // bcj2_stats[prob - p->probs][1]++;
+            p->range -= bound;
+            p->code -= bound;
+            *prob = (CBcj2Prob)(ttt - (ttt >> kNumMoveBits));
+          }
+        }
+      }
+    }
+    {
+      /* (v == 0xe8 ? 0 : 1) uses setcc instruction with additional zero register usage in x64 MSVC. */
+      // const unsigned cj = ((Byte)v == 0xe8) ? BCJ2_STREAM_CALL : BCJ2_STREAM_JUMP;
+      const unsigned cj = (((v + 0x57) >> 6) & 1) + BCJ2_STREAM_CALL;
+      const Byte *cur = p->bufs[cj];
+      Byte *dest;
+      SizeT rem;
+      if (cur == p->lims[cj])
+      {
+        p->state = cj;
+        break;
+      }
+      v = GetBe32a(cur);
+      p->bufs[cj] = cur + 4;
+      {
+        const UInt32 ip = p->ip + 4;
+        v -= ip;
+        p->ip = ip;
+      }
+      dest = p->dest;
+      rem = (SizeT)(p->destLim - dest);
+      if (rem < 4)
+      {
+        if ((unsigned)rem > 0) { dest[0] = (Byte)v;  v >>= 8;
+        if ((unsigned)rem > 1) { dest[1] = (Byte)v;  v >>= 8;
+        if ((unsigned)rem > 2) { dest[2] = (Byte)v;  v >>= 8; }}}
+        p->temp = v;
+        p->dest = dest + rem;
+        p->state = BCJ2_DEC_STATE_ORIG_0 + (unsigned)rem;
+        break;
+      }
+      SetUi32(dest, v)
+      v >>= 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;
+}
+
+#undef NUM_ITERS
+#undef ONE_ITER
+#undef NUM_SHIFT_BITS
+#undef kTopValue
+#undef kNumBitModelTotalBits
+#undef kBitModelTotal
+#undef kNumMoveBits

external/unarr/lzmasdk/Bcj2.h

@@ -0,0 +1,332 @@
+/* Bcj2.h -- BCJ2 converter for x86 code (Branch CALL/JUMP variant2)
+2023-03-02 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_BCJ2_H
+#define ZIP7_INC_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_ERROR     /* after detected data error */
+};
+
+enum
+{
+  BCJ2_ENC_STATE_ORIG = BCJ2_NUM_STREAMS,
+  BCJ2_ENC_STATE_FINISHED  /* it's state after fully encoded stream */
+};
+
+
+/* #define BCJ2_IS_32BIT_STREAM(s) ((s) == BCJ2_STREAM_CALL || (s) == BCJ2_STREAM_JUMP) */
+#define BCJ2_IS_32BIT_STREAM(s) ((unsigned)((unsigned)(s) - (unsigned)BCJ2_STREAM_CALL) < 2)
+
+/*
+CBcj2Dec / CBcj2Enc
+bufs sizes:
+  BUF_SIZE(n) = lims[n] - bufs[n]
+bufs sizes for BCJ2_STREAM_CALL and BCJ2_STREAM_JUMP must be multiply of 4:
+    (BUF_SIZE(BCJ2_STREAM_CALL) & 3) == 0
+    (BUF_SIZE(BCJ2_STREAM_JUMP) & 3) == 0
+*/
+
+// typedef UInt32 CBcj2Prob;
+typedef UInt16 CBcj2Prob;
+
+/*
+BCJ2 encoder / decoder internal requirements:
+  - If last bytes of stream contain marker (e8/e8/0f8x), then
+    there is also encoded symbol (0 : no conversion) in RC stream.
+  - One case of overlapped instructions is supported,
+    if last byte of converted instruction is (0f) and next byte is (8x):
+      marker [xx xx xx 0f] 8x
+    then the pair (0f 8x) is treated as marker.
+*/
+
+/* ---------- BCJ2 Decoder ---------- */
+
+/*
+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 >=
+        BUF_SIZE(BCJ2_STREAM_CALL) +
+        BUF_SIZE(BCJ2_STREAM_JUMP)
+  reserve = bufs[BCJ2_STREAM_MAIN] - dest -
+      ( BUF_SIZE(BCJ2_STREAM_CALL) +
+        BUF_SIZE(BCJ2_STREAM_JUMP) )
+  and additional conditions:
+  if (it's first call of Bcj2Dec_Decode() after Bcj2Dec_Init())
+  {
+    (reserve != 1) : if (ver <  v23.00)
+  }
+  else // if there are more than one calls of Bcj2Dec_Decode() after Bcj2Dec_Init())
+  {
+    (reserve >= 6) : if (ver <  v23.00)
+    (reserve >= 4) : if (ver >= v23.00)
+    We need that (reserve) because after first call of Bcj2Dec_Decode(),
+    CBcj2Dec::temp can contain up to 4 bytes for writing to (dest).
+  }
+  (reserve == 0) is allowed, if we decode full stream via single call of Bcj2Dec_Decode().
+  (reserve == 0) also is allowed in case of multi-call, if we use fixed buffers,
+     and (reserve) is calculated from full (final) sizes of all streams before first call.
+*/
+
+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;      /* property of starting base for decoding */
+  UInt32 temp;    /* Byte temp[4]; */
+  UInt32 range;
+  UInt32 code;
+  CBcj2Prob probs[2 + 256];
+} CBcj2Dec;
+
+
+/* Note:
+   Bcj2Dec_Init() sets (CBcj2Dec::ip = 0)
+   if (ip != 0) property is required, the caller must set CBcj2Dec::ip after Bcj2Dec_Init()
+*/
+void Bcj2Dec_Init(CBcj2Dec *p);
+
+
+/* Bcj2Dec_Decode():
+   returns:
+     SZ_OK
+     SZ_ERROR_DATA : if data in 5 starting bytes of BCJ2_STREAM_RC stream are not correct
+*/
+SRes Bcj2Dec_Decode(CBcj2Dec *p);
+
+/* To check that decoding was finished you can compare
+   sizes of processed streams with sizes known from another sources.
+   You must do at least one mandatory check from the two following options:
+      - the check for size of processed output (ORIG) stream.
+      - the check for size of processed input  (MAIN) stream.
+   additional optional checks:
+      - the checks for processed sizes of all input streams (MAIN, CALL, JUMP, RC)
+      - the checks Bcj2Dec_IsMaybeFinished*()
+   also before actual decoding you can check that the
+   following condition is met for stream sizes:
+     ( size(ORIG) == size(MAIN) + size(CALL) + size(JUMP) )
+*/
+
+/* (state == BCJ2_STREAM_MAIN) means that decoder is ready for
+      additional input data in BCJ2_STREAM_MAIN stream.
+   Note that (state == BCJ2_STREAM_MAIN) is allowed for non-finished decoding.
+*/
+#define Bcj2Dec_IsMaybeFinished_state_MAIN(_p_) ((_p_)->state == BCJ2_STREAM_MAIN)
+
+/* if the stream decoding was finished correctly, then range decoder
+   part of CBcj2Dec also was finished, and then (CBcj2Dec::code == 0).
+   Note that (CBcj2Dec::code == 0) is allowed for non-finished decoding.
+*/
+#define Bcj2Dec_IsMaybeFinished_code(_p_) ((_p_)->code == 0)
+
+/* use Bcj2Dec_IsMaybeFinished() only as additional check
+    after at least one mandatory check from the two following options:
+      - the check for size of processed output (ORIG) stream.
+      - the check for size of processed input  (MAIN) stream.
+*/
+#define Bcj2Dec_IsMaybeFinished(_p_) ( \
+        Bcj2Dec_IsMaybeFinished_state_MAIN(_p_) && \
+        Bcj2Dec_IsMaybeFinished_code(_p_))
+
+
+
+/* ---------- BCJ2 Encoder ---------- */
+
+typedef enum
+{
+  BCJ2_ENC_FINISH_MODE_CONTINUE,
+  BCJ2_ENC_FINISH_MODE_END_BLOCK,
+  BCJ2_ENC_FINISH_MODE_END_STREAM
+} EBcj2Enc_FinishMode;
+
+/*
+  BCJ2_ENC_FINISH_MODE_CONTINUE:
+     process non finished encoding.
+     It notifies the encoder that additional further calls
+     can provide more input data (src) than provided by current call.
+     In  that case the CBcj2Enc encoder still can move (src) pointer
+     up to (srcLim), but CBcj2Enc encoder can store some of the last
+     processed bytes (up to 4 bytes) from src to internal CBcj2Enc::temp[] buffer.
+   at return:
+       (CBcj2Enc::src will point to position that includes
+       processed data and data copied to (temp[]) buffer)
+       That data from (temp[]) buffer will be used in further calls.
+  
+  BCJ2_ENC_FINISH_MODE_END_BLOCK:
+     finish encoding of current block (ended at srcLim) without RC flushing.
+   at return: if (CBcj2Enc::state == BCJ2_ENC_STATE_ORIG) &&
+                  CBcj2Enc::src == CBcj2Enc::srcLim)
+        :  it shows that block encoding was finished. And the encoder is
+           ready for new (src) data or for stream finish operation.
+     finished block means
+     {
+       CBcj2Enc has completed block encoding up to (srcLim).
+       (1 + 4 bytes) or (2 + 4 bytes) CALL/JUMP cortages will
+       not cross block boundary at (srcLim).
+       temporary CBcj2Enc buffer for (ORIG) src data is empty.
+       3 output uncompressed streams (MAIN, CALL, JUMP) were flushed.
+       RC stream was not flushed. And RC stream will cross block boundary.
+     }
+     Note: some possible implementation of BCJ2 encoder could
+     write branch marker (e8/e8/0f8x) in one call of Bcj2Enc_Encode(),
+     and it could calculate symbol for RC in another call of Bcj2Enc_Encode().
+     BCJ2 encoder uses ip/fileIp/fileSize/relatLimit values to calculate RC symbol.
+     And these CBcj2Enc variables can have different values in different Bcj2Enc_Encode() calls.
+     So caller must finish each block with BCJ2_ENC_FINISH_MODE_END_BLOCK
+     to ensure that RC symbol is calculated and written in proper block.
+    
+  BCJ2_ENC_FINISH_MODE_END_STREAM
+     finish encoding of stream (ended at srcLim) fully including RC flushing.
+   at return: if (CBcj2Enc::state == BCJ2_ENC_STATE_FINISHED)
+        : it shows that stream encoding was finished fully,
+          and all output streams were flushed fully.
+     also Bcj2Enc_IsFinished() can be called.
+*/
+
+
+/*
+  32-bit relative offset in JUMP/CALL commands is
+    - (mod 4 GiB)  for 32-bit x86 code
+    - signed Int32 for 64-bit x86-64 code
+  BCJ2 encoder also does internal relative to absolute address conversions.
+  And there are 2 possible ways to do it:
+    before v23: we used 32-bit variables and (mod 4 GiB) conversion
+    since  v23: we use  64-bit variables and (signed Int32 offset) conversion.
+  The absolute address condition for conversion in v23:
+    ((UInt64)((Int64)ip64 - (Int64)fileIp64 + 5 + (Int32)offset) < (UInt64)fileSize64)
+  note that if (fileSize64 > 2 GiB). there is difference between
+  old (mod 4 GiB) way (v22) and new (signed Int32 offset) way (v23).
+  And new (v23) way is more suitable to encode 64-bit x86-64 code for (fileSize64 > 2 GiB) cases.
+*/
+
+/*
+// for old (v22) way for conversion:
+typedef UInt32 CBcj2Enc_ip_unsigned;
+typedef  Int32 CBcj2Enc_ip_signed;
+#define BCJ2_ENC_FileSize_MAX ((UInt32)1 << 31)
+*/
+typedef UInt64 CBcj2Enc_ip_unsigned;
+typedef  Int64 CBcj2Enc_ip_signed;
+
+/* maximum size of file that can be used for conversion condition */
+#define BCJ2_ENC_FileSize_MAX             ((CBcj2Enc_ip_unsigned)0 - 2)
+
+/* default value of fileSize64_minus1 variable that means
+   that absolute address limitation will not be used */
+#define BCJ2_ENC_FileSizeField_UNLIMITED  ((CBcj2Enc_ip_unsigned)0 - 1)
+
+/* calculate value that later can be set to CBcj2Enc::fileSize64_minus1 */
+#define BCJ2_ENC_GET_FileSizeField_VAL_FROM_FileSize(fileSize) \
+    ((CBcj2Enc_ip_unsigned)(fileSize) - 1)
+
+/* set CBcj2Enc::fileSize64_minus1 variable from size of file */
+#define Bcj2Enc_SET_FileSize(p, fileSize) \
+    (p)->fileSize64_minus1 = BCJ2_ENC_GET_FileSizeField_VAL_FROM_FileSize(fileSize);
+
+
+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 context;
+  Byte flushRem;
+  Byte isFlushState;
+
+  Byte cache;
+  UInt32 range;
+  UInt64 low;
+  UInt64 cacheSize;
+  
+  // UInt32 context;  // for marker version, it can include marker flag.
+
+  /* (ip64) and (fileIp64) correspond to virtual source stream position
+     that doesn't include data in temp[] */
+  CBcj2Enc_ip_unsigned ip64;         /* current (ip) position */
+  CBcj2Enc_ip_unsigned fileIp64;     /* start (ip) position of current file */
+  CBcj2Enc_ip_unsigned fileSize64_minus1;   /* size of current file (for conversion limitation) */
+  UInt32 relatLimit;  /* (relatLimit <= ((UInt32)1 << 31)) : 0 means disable_conversion */
+  // UInt32 relatExcludeBits;
+
+  UInt32 tempTarget;
+  unsigned tempPos; /* the number of bytes that were copied to temp[] buffer
+                       (tempPos <= 4) outside of Bcj2Enc_Encode() */
+  // Byte temp[4]; // for marker version
+  Byte temp[8];
+  CBcj2Prob probs[2 + 256];
+} CBcj2Enc;
+
+void Bcj2Enc_Init(CBcj2Enc *p);
+
+
+/*
+Bcj2Enc_Encode(): at exit:
+  p->State <  BCJ2_NUM_STREAMS    : we need more buffer space for output stream
+                                    (bufs[p->State] == lims[p->State])
+  p->State == BCJ2_ENC_STATE_ORIG : we need more data in input src stream
+                                    (src == srcLim)
+  p->State == BCJ2_ENC_STATE_FINISHED : after fully encoded stream
+*/
+void Bcj2Enc_Encode(CBcj2Enc *p);
+
+/* Bcj2Enc encoder can look ahead for up 4 bytes of source stream.
+   CBcj2Enc::tempPos : is the number of bytes that were copied from input stream to temp[] buffer.
+   (CBcj2Enc::src) after Bcj2Enc_Encode() is starting position after
+   fully processed data and after data copied to temp buffer.
+   So if the caller needs to get real number of fully processed input
+   bytes (without look ahead data in temp buffer),
+   the caller must subtruct (CBcj2Enc::tempPos) value from processed size
+   value that is calculated based on current (CBcj2Enc::src):
+     cur_processed_pos = Calc_Big_Processed_Pos(enc.src)) -
+        Bcj2Enc_Get_AvailInputSize_in_Temp(&enc);
+*/
+/* get the size of input data that was stored in temp[] buffer: */
+#define Bcj2Enc_Get_AvailInputSize_in_Temp(p) ((p)->tempPos)
+
+#define Bcj2Enc_IsFinished(p) ((p)->flushRem == 0)
+
+/* Note : the decoder supports overlapping of marker (0f 80).
+   But we can eliminate such overlapping cases by setting
+   the limit for relative offset conversion as
+     CBcj2Enc::relatLimit <= (0x0f << 24) == (240 MiB)
+*/
+/* default value for CBcj2Enc::relatLimit */
+#define BCJ2_ENC_RELAT_LIMIT_DEFAULT  ((UInt32)0x0f << 24)
+#define BCJ2_ENC_RELAT_LIMIT_MAX      ((UInt32)1 << 31)
+// #define BCJ2_RELAT_EXCLUDE_NUM_BITS 5
+
+EXTERN_C_END
+
+#endif

external/unarr/lzmasdk/Bra.c

@@ -0,0 +1,420 @@
+/* Bra.c -- Branch converters for RISC code
+2023-04-02 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Bra.h"
+#include "CpuArch.h"
+#include "RotateDefs.h"
+
+#if defined(MY_CPU_SIZEOF_POINTER) \
+    && ( MY_CPU_SIZEOF_POINTER == 4 \
+      || MY_CPU_SIZEOF_POINTER == 8)
+  #define BR_CONV_USE_OPT_PC_PTR
+#endif
+
+#ifdef BR_CONV_USE_OPT_PC_PTR
+#define BR_PC_INIT  pc -= (UInt32)(SizeT)p;
+#define BR_PC_GET   (pc + (UInt32)(SizeT)p)
+#else
+#define BR_PC_INIT  pc += (UInt32)size;
+#define BR_PC_GET   (pc - (UInt32)(SizeT)(lim - p))
+// #define BR_PC_INIT
+// #define BR_PC_GET   (pc + (UInt32)(SizeT)(p - data))
+#endif
+
+#define BR_CONVERT_VAL(v, c) if (encoding) v += c; else v -= c;
+// #define BR_CONVERT_VAL(v, c) if (!encoding) c = (UInt32)0 - c; v += c;
+
+#define Z7_BRANCH_CONV(name) z7_BranchConv_ ## name
+
+#define Z7_BRANCH_FUNC_MAIN(name) \
+static \
+Z7_FORCE_INLINE \
+Z7_ATTRIB_NO_VECTOR \
+Byte *Z7_BRANCH_CONV(name)(Byte *p, SizeT size, UInt32 pc, int encoding)
+
+#define Z7_BRANCH_FUNC_IMP(name, m, encoding) \
+Z7_NO_INLINE \
+Z7_ATTRIB_NO_VECTOR \
+Byte *m(name)(Byte *data, SizeT size, UInt32 pc) \
+  { return Z7_BRANCH_CONV(name)(data, size, pc, encoding); } \
+
+#ifdef Z7_EXTRACT_ONLY
+#define Z7_BRANCH_FUNCS_IMP(name) \
+  Z7_BRANCH_FUNC_IMP(name, Z7_BRANCH_CONV_DEC, 0)
+#else
+#define Z7_BRANCH_FUNCS_IMP(name) \
+  Z7_BRANCH_FUNC_IMP(name, Z7_BRANCH_CONV_DEC, 0) \
+  Z7_BRANCH_FUNC_IMP(name, Z7_BRANCH_CONV_ENC, 1)
+#endif
+
+#if defined(__clang__)
+#define BR_EXTERNAL_FOR
+#define BR_NEXT_ITERATION  continue;
+#else
+#define BR_EXTERNAL_FOR    for (;;)
+#define BR_NEXT_ITERATION  break;
+#endif
+
+#if defined(__clang__) && (__clang_major__ >= 8) \
+  || defined(__GNUC__) && (__GNUC__ >= 1000) \
+  // GCC is not good for __builtin_expect() here
+  /* || defined(_MSC_VER) && (_MSC_VER >= 1920) */
+  // #define Z7_unlikely [[unlikely]]
+  // #define Z7_LIKELY(x)   (__builtin_expect((x), 1))
+  #define Z7_UNLIKELY(x) (__builtin_expect((x), 0))
+  // #define Z7_likely [[likely]]
+#else
+  // #define Z7_LIKELY(x)   (x)
+  #define Z7_UNLIKELY(x) (x)
+  // #define Z7_likely
+#endif
+
+
+Z7_BRANCH_FUNC_MAIN(ARM64)
+{
+  // Byte *p = data;
+  const Byte *lim;
+  const UInt32 flag = (UInt32)1 << (24 - 4);
+  const UInt32 mask = ((UInt32)1 << 24) - (flag << 1);
+  size &= ~(SizeT)3;
+  // if (size == 0) return p;
+  lim = p + size;
+  BR_PC_INIT
+  pc -= 4;  // because (p) will point to next instruction
+  
+  BR_EXTERNAL_FOR
+  {
+    // Z7_PRAGMA_OPT_DISABLE_LOOP_UNROLL_VECTORIZE
+    for (;;)
+    {
+      UInt32 v;
+      if Z7_UNLIKELY(p == lim)
+        return p;
+      v = GetUi32a(p);
+      p += 4;
+      if Z7_UNLIKELY(((v - 0x94000000) & 0xfc000000) == 0)
+      {
+        UInt32 c = BR_PC_GET >> 2;
+        BR_CONVERT_VAL(v, c)
+        v &= 0x03ffffff;
+        v |= 0x94000000;
+        SetUi32a(p - 4, v)
+        BR_NEXT_ITERATION
+      }
+      // v = rotlFixed(v, 8);  v += (flag << 8) - 0x90;  if Z7_UNLIKELY((v & ((mask << 8) + 0x9f)) == 0)
+      v -= 0x90000000;  if Z7_UNLIKELY((v & 0x9f000000) == 0)
+      {
+        UInt32 z, c;
+        // v = rotrFixed(v, 8);
+        v += flag; if Z7_UNLIKELY(v & mask) continue;
+        z = (v & 0xffffffe0) | (v >> 26);
+        c = (BR_PC_GET >> (12 - 3)) & ~(UInt32)7;
+        BR_CONVERT_VAL(z, c)
+        v &= 0x1f;
+        v |= 0x90000000;
+        v |= z << 26;
+        v |= 0x00ffffe0 & ((z & (((flag << 1) - 1))) - flag);
+        SetUi32a(p - 4, v)
+      }
+    }
+  }
+}
+Z7_BRANCH_FUNCS_IMP(ARM64)
+
+
+Z7_BRANCH_FUNC_MAIN(ARM)
+{
+  // Byte *p = data;
+  const Byte *lim;
+  size &= ~(SizeT)3;
+  lim = p + size;
+  BR_PC_INIT
+  /* in ARM: branch offset is relative to the +2 instructions from current instruction.
+     (p) will point to next instruction */
+  pc += 8 - 4;
+  
+  for (;;)
+  {
+    for (;;)
+    {
+      if Z7_UNLIKELY(p >= lim) { return p; }  p += 4;  if Z7_UNLIKELY(p[-1] == 0xeb) break;
+      if Z7_UNLIKELY(p >= lim) { return p; }  p += 4;  if Z7_UNLIKELY(p[-1] == 0xeb) break;
+    }
+    {
+      UInt32 v = GetUi32a(p - 4);
+      UInt32 c = BR_PC_GET >> 2;
+      BR_CONVERT_VAL(v, c)
+      v &= 0x00ffffff;
+      v |= 0xeb000000;
+      SetUi32a(p - 4, v)
+    }
+  }
+}
+Z7_BRANCH_FUNCS_IMP(ARM)
+
+
+Z7_BRANCH_FUNC_MAIN(PPC)
+{
+  // Byte *p = data;
+  const Byte *lim;
+  size &= ~(SizeT)3;
+  lim = p + size;
+  BR_PC_INIT
+  pc -= 4;  // because (p) will point to next instruction
+  
+  for (;;)
+  {
+    UInt32 v;
+    for (;;)
+    {
+      if Z7_UNLIKELY(p == lim)
+        return p;
+      // v = GetBe32a(p);
+      v = *(UInt32 *)(void *)p;
+      p += 4;
+      // if ((v & 0xfc000003) == 0x48000001) break;
+      // if ((p[-4] & 0xFC) == 0x48 && (p[-1] & 3) == 1) break;
+      if Z7_UNLIKELY(
+          ((v - Z7_CONV_BE_TO_NATIVE_CONST32(0x48000001))
+              & Z7_CONV_BE_TO_NATIVE_CONST32(0xfc000003)) == 0) break;
+    }
+    {
+      v = Z7_CONV_NATIVE_TO_BE_32(v);
+      {
+        UInt32 c = BR_PC_GET;
+        BR_CONVERT_VAL(v, c)
+      }
+      v &= 0x03ffffff;
+      v |= 0x48000000;
+      SetBe32a(p - 4, v)
+    }
+  }
+}
+Z7_BRANCH_FUNCS_IMP(PPC)
+
+
+#ifdef Z7_CPU_FAST_ROTATE_SUPPORTED
+#define BR_SPARC_USE_ROTATE
+#endif
+
+Z7_BRANCH_FUNC_MAIN(SPARC)
+{
+  // Byte *p = data;
+  const Byte *lim;
+  const UInt32 flag = (UInt32)1 << 22;
+  size &= ~(SizeT)3;
+  lim = p + size;
+  BR_PC_INIT
+  pc -= 4;  // because (p) will point to next instruction
+  for (;;)
+  {
+    UInt32 v;
+    for (;;)
+    {
+      if Z7_UNLIKELY(p == lim)
+        return p;
+      /* // the code without GetBe32a():
+      { const UInt32 v = GetUi16a(p) & 0xc0ff; p += 4; if (v == 0x40 || v == 0xc07f) break; }
+      */
+      v = GetBe32a(p);
+      p += 4;
+    #ifdef BR_SPARC_USE_ROTATE
+      v = rotlFixed(v, 2);
+      v += (flag << 2) - 1;
+      if Z7_UNLIKELY((v & (3 - (flag << 3))) == 0)
+    #else
+      v += (UInt32)5 << 29;
+      v ^= (UInt32)7 << 29;
+      v += flag;
+      if Z7_UNLIKELY((v & (0 - (flag << 1))) == 0)
+    #endif
+        break;
+    }
+    {
+      // UInt32 v = GetBe32a(p - 4);
+    #ifndef BR_SPARC_USE_ROTATE
+      v <<= 2;
+    #endif
+      {
+        UInt32 c = BR_PC_GET;
+        BR_CONVERT_VAL(v, c)
+      }
+      v &= (flag << 3) - 1;
+    #ifdef BR_SPARC_USE_ROTATE
+      v -= (flag << 2) - 1;
+      v = rotrFixed(v, 2);
+    #else
+      v -= (flag << 2);
+      v >>= 2;
+      v |= (UInt32)1 << 30;
+    #endif
+      SetBe32a(p - 4, v)
+    }
+  }
+}
+Z7_BRANCH_FUNCS_IMP(SPARC)
+
+
+Z7_BRANCH_FUNC_MAIN(ARMT)
+{
+  // Byte *p = data;
+  Byte *lim;
+  size &= ~(SizeT)1;
+  // if (size == 0) return p;
+  if (size <= 2) return p;
+  size -= 2;
+  lim = p + size;
+  BR_PC_INIT
+  /* in ARM: branch offset is relative to the +2 instructions from current instruction.
+     (p) will point to the +2 instructions from current instruction */
+  // pc += 4 - 4;
+  // if (encoding) pc -= 0xf800 << 1; else pc += 0xf800 << 1;
+  // #define ARMT_TAIL_PROC { goto armt_tail; }
+  #define ARMT_TAIL_PROC { return p; }
+  
+  do
+  {
+    /* in MSVC 32-bit x86 compilers:
+       UInt32 version : it loads value from memory with movzx
+       Byte   version : it loads value to 8-bit register (AL/CL)
+       movzx version is slightly faster in some cpus
+    */
+    unsigned b1;
+    // Byte / unsigned
+    b1 = p[1];
+    // optimized version to reduce one (p >= lim) check:
+    // unsigned a1 = p[1];  b1 = p[3];  p += 2;  if Z7_LIKELY((b1 & (a1 ^ 8)) < 0xf8)
+    for (;;)
+    {
+      unsigned b3; // Byte / UInt32
+      /* (Byte)(b3) normalization can use low byte computations in MSVC.
+         It gives smaller code, and no loss of speed in some compilers/cpus.
+         But new MSVC 32-bit x86 compilers use more slow load
+         from memory to low byte register in that case.
+         So we try to use full 32-bit computations for faster code.
+      */
+      // if (p >= lim) { ARMT_TAIL_PROC }  b3 = b1 + 8;  b1 = p[3];  p += 2;  if ((b3 & b1) >= 0xf8) break;
+      if Z7_UNLIKELY(p >= lim) { ARMT_TAIL_PROC }  b3 = p[3];  p += 2;  if Z7_UNLIKELY((b3 & (b1 ^ 8)) >= 0xf8) break;
+      if Z7_UNLIKELY(p >= lim) { ARMT_TAIL_PROC }  b1 = p[3];  p += 2;  if Z7_UNLIKELY((b1 & (b3 ^ 8)) >= 0xf8) break;
+    }
+    {
+      /* we can adjust pc for (0xf800) to rid of (& 0x7FF) operation.
+         But gcc/clang for arm64 can use bfi instruction for full code here */
+      UInt32 v =
+          ((UInt32)GetUi16a(p - 2) << 11) |
+          ((UInt32)GetUi16a(p) & 0x7FF);
+      /*
+      UInt32 v =
+            ((UInt32)p[1 - 2] << 19)
+          + (((UInt32)p[1] & 0x7) << 8)
+          + (((UInt32)p[-2] << 11))
+          + (p[0]);
+      */
+      p += 2;
+      {
+        UInt32 c = BR_PC_GET >> 1;
+        BR_CONVERT_VAL(v, c)
+      }
+      SetUi16a(p - 4, (UInt16)(((v >> 11) & 0x7ff) | 0xf000))
+      SetUi16a(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));
+      */
+    }
+  }
+  while (p < lim);
+  return p;
+  // armt_tail:
+  // if ((Byte)((lim[1] & 0xf8)) != 0xf0) { lim += 2; }  return lim;
+  // return (Byte *)(lim + ((Byte)((lim[1] ^ 0xf0) & 0xf8) == 0 ? 0 : 2));
+  // return (Byte *)(lim + (((lim[1] ^ ~0xfu) & ~7u) == 0 ? 0 : 2));
+  // return (Byte *)(lim + 2 - (((((unsigned)lim[1] ^ 8) + 8) >> 7) & 2));
+}
+Z7_BRANCH_FUNCS_IMP(ARMT)
+
+
+// #define BR_IA64_NO_INLINE
+
+Z7_BRANCH_FUNC_MAIN(IA64)
+{
+  // Byte *p = data;
+  const Byte *lim;
+  size &= ~(SizeT)15;
+  lim = p + size;
+  pc -= 1 << 4;
+  pc >>= 4 - 1;
+  // pc -= 1 << 1;
+  
+  for (;;)
+  {
+    unsigned m;
+    for (;;)
+    {
+      if Z7_UNLIKELY(p == lim)
+        return p;
+      m = (unsigned)((UInt32)0x334b0000 >> (*p & 0x1e));
+      p += 16;
+      pc += 1 << 1;
+      if (m &= 3)
+        break;
+    }
+    {
+      p += (ptrdiff_t)m * 5 - 20; // negative value is expected here.
+      do
+      {
+        const UInt32 t =
+          #if defined(MY_CPU_X86_OR_AMD64)
+            // we use 32-bit load here to reduce code size on x86:
+            GetUi32(p);
+          #else
+            GetUi16(p);
+          #endif
+        UInt32 z = GetUi32(p + 1) >> m;
+        p += 5;
+        if (((t >> m) & (0x70 << 1)) == 0
+            && ((z - (0x5000000 << 1)) & (0xf000000 << 1)) == 0)
+        {
+          UInt32 v = (UInt32)((0x8fffff << 1) | 1) & z;
+          z ^= v;
+        #ifdef BR_IA64_NO_INLINE
+          v |= (v & ((UInt32)1 << (23 + 1))) >> 3;
+          {
+            UInt32 c = pc;
+            BR_CONVERT_VAL(v, c)
+          }
+          v &= (0x1fffff << 1) | 1;
+        #else
+          {
+            if (encoding)
+            {
+              // pc &= ~(0xc00000 << 1); // we just need to clear at least 2 bits
+              pc &= (0x1fffff << 1) | 1;
+              v += pc;
+            }
+            else
+            {
+              // pc |= 0xc00000 << 1; // we need to set at least 2 bits
+              pc |= ~(UInt32)((0x1fffff << 1) | 1);
+              v -= pc;
+            }
+          }
+          v &= ~(UInt32)(0x600000 << 1);
+        #endif
+          v += (0x700000 << 1);
+          v &= (0x8fffff << 1) | 1;
+          z |= v;
+          z <<= m;
+          SetUi32(p + 1 - 5, z)
+        }
+        m++;
+      }
+      while (m &= 3); // while (m < 4);
+    }
+  }
+}
+Z7_BRANCH_FUNCS_IMP(IA64)

external/unarr/lzmasdk/Bra.h

@@ -0,0 +1,99 @@
+/* Bra.h -- Branch converters for executables
+2023-04-02 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_BRA_H
+#define ZIP7_INC_BRA_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+#define Z7_BRANCH_CONV_DEC(name)    z7_BranchConv_   ## name ## _Dec
+#define Z7_BRANCH_CONV_ENC(name)    z7_BranchConv_   ## name ## _Enc
+#define Z7_BRANCH_CONV_ST_DEC(name) z7_BranchConvSt_ ## name ## _Dec
+#define Z7_BRANCH_CONV_ST_ENC(name) z7_BranchConvSt_ ## name ## _Enc
+
+#define Z7_BRANCH_CONV_DECL(name)    Byte * name(Byte *data, SizeT size, UInt32 pc)
+#define Z7_BRANCH_CONV_ST_DECL(name) Byte * name(Byte *data, SizeT size, UInt32 pc, UInt32 *state)
+
+typedef Z7_BRANCH_CONV_DECL(   (*z7_Func_BranchConv));
+typedef Z7_BRANCH_CONV_ST_DECL((*z7_Func_BranchConvSt));
+
+#define Z7_BRANCH_CONV_ST_X86_STATE_INIT_VAL 0
+Z7_BRANCH_CONV_ST_DECL(Z7_BRANCH_CONV_ST_DEC(X86));
+Z7_BRANCH_CONV_ST_DECL(Z7_BRANCH_CONV_ST_ENC(X86));
+
+#define Z7_BRANCH_FUNCS_DECL(name) \
+Z7_BRANCH_CONV_DECL(Z7_BRANCH_CONV_DEC(name)); \
+Z7_BRANCH_CONV_DECL(Z7_BRANCH_CONV_ENC(name));
+
+Z7_BRANCH_FUNCS_DECL(ARM64)
+Z7_BRANCH_FUNCS_DECL(ARM)
+Z7_BRANCH_FUNCS_DECL(ARMT)
+Z7_BRANCH_FUNCS_DECL(PPC)
+Z7_BRANCH_FUNCS_DECL(SPARC)
+Z7_BRANCH_FUNCS_DECL(IA64)
+
+/*
+These functions convert data that contain CPU instructions.
+Each such function converts relative addresses to absolute addresses in some
+branch instructions: CALL (in all converters) and JUMP (X86 converter only).
+Such conversion allows to increase compression ratio, if we compress that data.
+
+There are 2 types of converters:
+  Byte * Conv_RISC (Byte *data, SizeT size, UInt32 pc);
+  Byte * ConvSt_X86(Byte *data, SizeT size, UInt32 pc, UInt32 *state);
+Each Converter supports 2 versions: one for encoding
+and one for decoding (_Enc/_Dec postfixes in function name).
+
+In params:
+  data  : data buffer
+  size  : size of data
+  pc    : current virtual Program Counter (Instruction Pinter) value
+In/Out param:
+  state : pointer to state variable (for X86 converter only)
+
+Return:
+  The pointer to position in (data) buffer after last byte that was processed.
+  If the caller calls converter again, it must call it starting with that position.
+  But the caller is allowed to move data in buffer. so pointer to
+  current processed position also will be changed for next call.
+  Also the caller must increase internal (pc) value for next call.
+  
+Each converter has some characteristics: Endian, Alignment, LookAhead.
+  Type   Endian  Alignment  LookAhead
+  
+  X86    little      1          4
+  ARMT   little      2          2
+  ARM    little      4          0
+  ARM64  little      4          0
+  PPC     big        4          0
+  SPARC   big        4          0
+  IA64   little     16          0
+
+  (data) must be aligned for (Alignment).
+  processed size can be calculated as:
+    SizeT processed = Conv(data, size, pc) - data;
+  if (processed == 0)
+    it means that converter needs more data for processing.
+  If (size < Alignment + LookAhead)
+    then (processed == 0) is allowed.
+
+Example code for conversion in loop:
+  UInt32 pc = 0;
+  size = 0;
+  for (;;)
+  {
+    size += Load_more_input_data(data + size);
+    SizeT processed = Conv(data, size, pc) - data;
+    if (processed == 0 && no_more_input_data_after_size)
+      break; // we stop convert loop
+    data += processed;
+    size -= processed;
+    pc += processed;
+  }
+*/
+
+EXTERN_C_END
+
+#endif

external/unarr/lzmasdk/Bra86.c

@@ -0,0 +1,187 @@
+/* Bra86.c -- Branch converter for X86 code (BCJ)
+2023-04-02 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Bra.h"
+#include "CpuArch.h"
+
+
+#if defined(MY_CPU_SIZEOF_POINTER) \
+    && ( MY_CPU_SIZEOF_POINTER == 4 \
+      || MY_CPU_SIZEOF_POINTER == 8)
+  #define BR_CONV_USE_OPT_PC_PTR
+#endif
+
+#ifdef BR_CONV_USE_OPT_PC_PTR
+#define BR_PC_INIT  pc -= (UInt32)(SizeT)p; // (MY_uintptr_t)
+#define BR_PC_GET   (pc + (UInt32)(SizeT)p)
+#else
+#define BR_PC_INIT  pc += (UInt32)size;
+#define BR_PC_GET   (pc - (UInt32)(SizeT)(lim - p))
+// #define BR_PC_INIT
+// #define BR_PC_GET   (pc + (UInt32)(SizeT)(p - data))
+#endif
+
+#define BR_CONVERT_VAL(v, c) if (encoding) v += c; else v -= c;
+// #define BR_CONVERT_VAL(v, c) if (!encoding) c = (UInt32)0 - c; v += c;
+
+#define Z7_BRANCH_CONV_ST(name) z7_BranchConvSt_ ## name
+
+#define BR86_NEED_CONV_FOR_MS_BYTE(b) ((((b) + 1) & 0xfe) == 0)
+
+#ifdef MY_CPU_LE_UNALIGN
+  #define BR86_PREPARE_BCJ_SCAN  const UInt32 v = GetUi32(p) ^ 0xe8e8e8e8;
+  #define BR86_IS_BCJ_BYTE(n)    ((v & ((UInt32)0xfe << (n) * 8)) == 0)
+#else
+  #define BR86_PREPARE_BCJ_SCAN
+  // bad for MSVC X86 (partial write to byte reg):
+  #define BR86_IS_BCJ_BYTE(n)    ((p[n - 4] & 0xfe) == 0xe8)
+  // bad for old MSVC (partial write to byte reg):
+  // #define BR86_IS_BCJ_BYTE(n)    (((*p ^ 0xe8) & 0xfe) == 0)
+#endif
+ 
+static
+Z7_FORCE_INLINE
+Z7_ATTRIB_NO_VECTOR
+Byte *Z7_BRANCH_CONV_ST(X86)(Byte *p, SizeT size, UInt32 pc, UInt32 *state, int encoding)
+{
+  if (size < 5)
+    return p;
+ {
+  // Byte *p = data;
+  const Byte *lim = p + size - 4;
+  unsigned mask = (unsigned)*state;  // & 7;
+#ifdef BR_CONV_USE_OPT_PC_PTR
+  /* if BR_CONV_USE_OPT_PC_PTR is defined: we need to adjust (pc) for (+4),
+        because call/jump offset is relative to the next instruction.
+     if BR_CONV_USE_OPT_PC_PTR is not defined : we don't need to adjust (pc) for (+4),
+         because  BR_PC_GET uses (pc - (lim - p)), and lim was adjusted for (-4) before.
+  */
+  pc += 4;
+#endif
+  BR_PC_INIT
+  goto start;
+
+  for (;; mask |= 4)
+  {
+    // cont: mask |= 4;
+  start:
+    if (p >= lim)
+      goto fin;
+    {
+      BR86_PREPARE_BCJ_SCAN
+      p += 4;
+      if (BR86_IS_BCJ_BYTE(0))  { goto m0; }  mask >>= 1;
+      if (BR86_IS_BCJ_BYTE(1))  { goto m1; }  mask >>= 1;
+      if (BR86_IS_BCJ_BYTE(2))  { goto m2; }  mask = 0;
+      if (BR86_IS_BCJ_BYTE(3))  { goto a3; }
+    }
+    goto main_loop;
+
+  m0: p--;
+  m1: p--;
+  m2: p--;
+    if (mask == 0)
+      goto a3;
+    if (p > lim)
+      goto fin_p;
+   
+    // if (((0x17u >> mask) & 1) == 0)
+    if (mask > 4 || mask == 3)
+    {
+      mask >>= 1;
+      continue; // goto cont;
+    }
+    mask >>= 1;
+    if (BR86_NEED_CONV_FOR_MS_BYTE(p[mask]))
+      continue; // goto cont;
+    // if (!BR86_NEED_CONV_FOR_MS_BYTE(p[3])) continue; // goto cont;
+    {
+      UInt32 v = GetUi32(p);
+      UInt32 c;
+      v += (1 << 24);  if (v & 0xfe000000) continue; // goto cont;
+      c = BR_PC_GET;
+      BR_CONVERT_VAL(v, c)
+      {
+        mask <<= 3;
+        if (BR86_NEED_CONV_FOR_MS_BYTE(v >> mask))
+        {
+          v ^= (((UInt32)0x100 << mask) - 1);
+          #ifdef MY_CPU_X86
+          // for X86 : we can recalculate (c) to reduce register pressure
+            c = BR_PC_GET;
+          #endif
+          BR_CONVERT_VAL(v, c)
+        }
+        mask = 0;
+      }
+      // v = (v & ((1 << 24) - 1)) - (v & (1 << 24));
+      v &= (1 << 25) - 1;  v -= (1 << 24);
+      SetUi32(p, v)
+      p += 4;
+      goto main_loop;
+    }
+
+  main_loop:
+    if (p >= lim)
+      goto fin;
+    for (;;)
+    {
+      BR86_PREPARE_BCJ_SCAN
+      p += 4;
+      if (BR86_IS_BCJ_BYTE(0))  { goto a0; }
+      if (BR86_IS_BCJ_BYTE(1))  { goto a1; }
+      if (BR86_IS_BCJ_BYTE(2))  { goto a2; }
+      if (BR86_IS_BCJ_BYTE(3))  { goto a3; }
+      if (p >= lim)
+        goto fin;
+    }
+  
+  a0: p--;
+  a1: p--;
+  a2: p--;
+  a3:
+    if (p > lim)
+      goto fin_p;
+    // if (!BR86_NEED_CONV_FOR_MS_BYTE(p[3])) continue; // goto cont;
+    {
+      UInt32 v = GetUi32(p);
+      UInt32 c;
+      v += (1 << 24);  if (v & 0xfe000000) continue; // goto cont;
+      c = BR_PC_GET;
+      BR_CONVERT_VAL(v, c)
+      // v = (v & ((1 << 24) - 1)) - (v & (1 << 24));
+      v &= (1 << 25) - 1;  v -= (1 << 24);
+      SetUi32(p, v)
+      p += 4;
+      goto main_loop;
+    }
+  }
+
+fin_p:
+  p--;
+fin:
+  // the following processing for tail is optional and can be commented
+  /*
+  lim += 4;
+  for (; p < lim; p++, mask >>= 1)
+    if ((*p & 0xfe) == 0xe8)
+      break;
+  */
+  *state = (UInt32)mask;
+  return p;
+ }
+}
+
+
+#define Z7_BRANCH_CONV_ST_FUNC_IMP(name, m, encoding) \
+Z7_NO_INLINE \
+Z7_ATTRIB_NO_VECTOR \
+Byte *m(name)(Byte *data, SizeT size, UInt32 pc, UInt32 *state) \
+  { return Z7_BRANCH_CONV_ST(name)(data, size, pc, state, encoding); }
+
+Z7_BRANCH_CONV_ST_FUNC_IMP(X86, Z7_BRANCH_CONV_ST_DEC, 0)
+#ifndef Z7_EXTRACT_ONLY
+Z7_BRANCH_CONV_ST_FUNC_IMP(X86, Z7_BRANCH_CONV_ST_ENC, 1)
+#endif

external/unarr/lzmasdk/Compiler.h

@@ -0,0 +1,159 @@
+/* Compiler.h : Compiler specific defines and pragmas
+2023-04-02 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_COMPILER_H
+#define ZIP7_INC_COMPILER_H
+
+#if defined(__clang__)
+# define Z7_CLANG_VERSION  (__clang_major__ * 10000 + __clang_minor__ * 100 + __clang_patchlevel__)
+#endif
+#if defined(__clang__) && defined(__apple_build_version__)
+# define Z7_APPLE_CLANG_VERSION   Z7_CLANG_VERSION
+#elif defined(__clang__)
+# define Z7_LLVM_CLANG_VERSION    Z7_CLANG_VERSION
+#elif defined(__GNUC__)
+# define Z7_GCC_VERSION (__GNUC__ * 10000 + __GNUC_MINOR__ * 100 + __GNUC_PATCHLEVEL__)
+#endif
+
+#ifdef _MSC_VER
+#if !defined(__clang__) && !defined(__GNUC__)
+#define Z7_MSC_VER_ORIGINAL _MSC_VER
+#endif
+#endif
+
+#if defined(__MINGW32__) || defined(__MINGW64__)
+#define Z7_MINGW
+#endif
+
+// #pragma GCC diagnostic ignored "-Wunknown-pragmas"
+
+#ifdef __clang__
+// padding size of '' with 4 bytes to alignment boundary
+#pragma GCC diagnostic ignored "-Wpadded"
+#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 defined(_MSC_VER) && _MSC_VER >= 1800
+#pragma warning(disable : 4464) // relative include path contains '..'
+#endif
+
+// == 1200 : -O1 : for __forceinline
+// >= 1900 : -O1 : for printf
+#pragma warning(disable : 4710) // function not inlined
+
+#if _MSC_VER < 1900
+// winnt.h: 'Int64ShllMod32'
+#pragma warning(disable : 4514) // unreferenced inline function has been removed
+#endif
+    
+#if _MSC_VER < 1300
+// #pragma warning(disable : 4702) // unreachable code
+// Bra.c : -O1:
+#pragma warning(disable : 4714) // function marked as __forceinline not inlined
+#endif
+
+/*
+#if _MSC_VER > 1400 && _MSC_VER <= 1900
+// strcat: This function or variable may be unsafe
+// sysinfoapi.h: kit10: GetVersion was declared deprecated
+#pragma warning(disable : 4996)
+#endif
+*/
+
+#if _MSC_VER > 1200
+// -Wall warnings
+
+#pragma warning(disable : 4711) // function selected for automatic inline expansion
+#pragma warning(disable : 4820) // '2' bytes padding added after data member
+
+#if _MSC_VER >= 1400 && _MSC_VER < 1920
+// 1400: string.h: _DBG_MEMCPY_INLINE_
+// 1600 - 191x : smmintrin.h __cplusplus'
+// is not defined as a preprocessor macro, replacing with '0' for '#if/#elif'
+#pragma warning(disable : 4668)
+
+// 1400 - 1600 : WinDef.h : 'FARPROC' :
+// 1900 - 191x : immintrin.h: _readfsbase_u32
+// no function prototype given : converting '()' to '(void)'
+#pragma warning(disable : 4255)
+#endif
+
+#if _MSC_VER >= 1914
+// Compiler will insert Spectre mitigation for memory load if /Qspectre switch specified
+#pragma warning(disable : 5045)
+#endif
+
+#endif // _MSC_VER > 1200
+#endif // _MSC_VER
+
+
+#if defined(__clang__) && (__clang_major__ >= 4)
+  #define Z7_PRAGMA_OPT_DISABLE_LOOP_UNROLL_VECTORIZE \
+    _Pragma("clang loop unroll(disable)") \
+    _Pragma("clang loop vectorize(disable)")
+  #define Z7_ATTRIB_NO_VECTORIZE
+#elif defined(__GNUC__) && (__GNUC__ >= 5)
+  #define Z7_ATTRIB_NO_VECTORIZE __attribute__((optimize("no-tree-vectorize")))
+  // __attribute__((optimize("no-unroll-loops")));
+  #define Z7_PRAGMA_OPT_DISABLE_LOOP_UNROLL_VECTORIZE
+#elif defined(_MSC_VER) && (_MSC_VER >= 1920)
+  #define Z7_PRAGMA_OPT_DISABLE_LOOP_UNROLL_VECTORIZE \
+    _Pragma("loop( no_vector )")
+  #define Z7_ATTRIB_NO_VECTORIZE
+#else
+  #define Z7_PRAGMA_OPT_DISABLE_LOOP_UNROLL_VECTORIZE
+  #define Z7_ATTRIB_NO_VECTORIZE
+#endif
+
+#if defined(MY_CPU_X86_OR_AMD64) && ( \
+       defined(__clang__) && (__clang_major__ >= 4) \
+    || defined(__GNUC__) && (__GNUC__ >= 5))
+  #define Z7_ATTRIB_NO_SSE  __attribute__((__target__("no-sse")))
+#else
+  #define Z7_ATTRIB_NO_SSE
+#endif
+
+#define Z7_ATTRIB_NO_VECTOR \
+  Z7_ATTRIB_NO_VECTORIZE \
+  Z7_ATTRIB_NO_SSE
+
+
+#if defined(__clang__) && (__clang_major__ >= 8) \
+  || defined(__GNUC__) && (__GNUC__ >= 1000) \
+  /* || defined(_MSC_VER) && (_MSC_VER >= 1920) */
+  // GCC is not good for __builtin_expect()
+  #define Z7_LIKELY(x)   (__builtin_expect((x), 1))
+  #define Z7_UNLIKELY(x) (__builtin_expect((x), 0))
+  // #define Z7_unlikely [[unlikely]]
+  // #define Z7_likely [[likely]]
+#else
+  #define Z7_LIKELY(x)   (x)
+  #define Z7_UNLIKELY(x) (x)
+  // #define Z7_likely
+#endif
+
+
+#if (defined(Z7_CLANG_VERSION) && (Z7_CLANG_VERSION >= 36000))
+#define Z7_DIAGNOSCTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER \
+  _Pragma("GCC diagnostic push") \
+  _Pragma("GCC diagnostic ignored \"-Wreserved-macro-identifier\"")
+#define Z7_DIAGNOSCTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER \
+  _Pragma("GCC diagnostic pop")
+#else
+#define Z7_DIAGNOSCTIC_IGNORE_BEGIN_RESERVED_MACRO_IDENTIFIER
+#define Z7_DIAGNOSCTIC_IGNORE_END_RESERVED_MACRO_IDENTIFIER
+#endif
+
+#define UNUSED_VAR(x) (void)x;
+/* #define UNUSED_VAR(x) x=x; */
+
+#endif

external/unarr/lzmasdk/CpuArch.c

@@ -0,0 +1,823 @@
+/* CpuArch.c -- CPU specific code
+2023-05-18 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+// #include <stdio.h>
+
+#include "CpuArch.h"
+
+#ifdef MY_CPU_X86_OR_AMD64
+
+#undef NEED_CHECK_FOR_CPUID
+#if !defined(MY_CPU_AMD64)
+#define NEED_CHECK_FOR_CPUID
+#endif
+
+/*
+  cpuid instruction supports (subFunction) parameter in ECX,
+  that is used only with some specific (function) parameter values.
+  But we always use only (subFunction==0).
+*/
+/*
+  __cpuid(): MSVC and GCC/CLANG use same function/macro name
+             but parameters are different.
+   We use MSVC __cpuid() parameters style for our z7_x86_cpuid() function.
+*/
+
+#if defined(__GNUC__) /* && (__GNUC__ >= 10) */ \
+    || defined(__clang__) /* && (__clang_major__ >= 10) */
+
+/* there was some CLANG/GCC compilers that have issues with
+   rbx(ebx) handling in asm blocks in -fPIC mode (__PIC__ is defined).
+   compiler's <cpuid.h> contains the macro __cpuid() that is similar to our code.
+   The history of __cpuid() changes in CLANG/GCC:
+   GCC:
+     2007: it preserved ebx for (__PIC__ && __i386__)
+     2013: it preserved rbx and ebx for __PIC__
+     2014: it doesn't preserves rbx and ebx anymore
+     we suppose that (__GNUC__ >= 5) fixed that __PIC__ ebx/rbx problem.
+   CLANG:
+     2014+: it preserves rbx, but only for 64-bit code. No __PIC__ check.
+   Why CLANG cares about 64-bit mode only, and doesn't care about ebx (in 32-bit)?
+   Do we need __PIC__ test for CLANG or we must care about rbx even if
+   __PIC__ is not defined?
+*/
+
+#define ASM_LN "\n"
+   
+#if defined(MY_CPU_AMD64) && defined(__PIC__) \
+    && ((defined (__GNUC__) && (__GNUC__ < 5)) || defined(__clang__))
+
+#define x86_cpuid_MACRO(p, func) { \
+  __asm__ __volatile__ ( \
+    ASM_LN   "mov     %%rbx, %q1"  \
+    ASM_LN   "cpuid"               \
+    ASM_LN   "xchg    %%rbx, %q1"  \
+    : "=a" ((p)[0]), "=&r" ((p)[1]), "=c" ((p)[2]), "=d" ((p)[3]) : "0" (func), "2"(0)); }
+
+  /* "=&r" selects free register. It can select even rbx, if that register is free.
+     "=&D" for (RDI) also works, but the code can be larger with "=&D"
+     "2"(0) means (subFunction = 0),
+     2 is (zero-based) index in the output constraint list "=c" (ECX). */
+
+#elif defined(MY_CPU_X86) && defined(__PIC__) \
+    && ((defined (__GNUC__) && (__GNUC__ < 5)) || defined(__clang__))
+
+#define x86_cpuid_MACRO(p, func) { \
+  __asm__ __volatile__ ( \
+    ASM_LN   "mov     %%ebx, %k1"  \
+    ASM_LN   "cpuid"               \
+    ASM_LN   "xchg    %%ebx, %k1"  \
+    : "=a" ((p)[0]), "=&r" ((p)[1]), "=c" ((p)[2]), "=d" ((p)[3]) : "0" (func), "2"(0)); }
+
+#else
+
+#define x86_cpuid_MACRO(p, func) { \
+  __asm__ __volatile__ ( \
+    ASM_LN   "cpuid"               \
+    : "=a" ((p)[0]), "=b" ((p)[1]), "=c" ((p)[2]), "=d" ((p)[3]) : "0" (func), "2"(0)); }
+
+#endif
+
+
+void Z7_FASTCALL z7_x86_cpuid(UInt32 p[4], UInt32 func)
+{
+  x86_cpuid_MACRO(p, func)
+}
+
+
+Z7_NO_INLINE
+UInt32 Z7_FASTCALL z7_x86_cpuid_GetMaxFunc(void)
+{
+ #if defined(NEED_CHECK_FOR_CPUID)
+  #define EFALGS_CPUID_BIT 21
+  UInt32 a;
+  __asm__ __volatile__ (
+    ASM_LN   "pushf"
+    ASM_LN   "pushf"
+    ASM_LN   "pop     %0"
+    // ASM_LN   "movl    %0, %1"
+    // ASM_LN   "xorl    $0x200000, %0"
+    ASM_LN   "btc     %1, %0"
+    ASM_LN   "push    %0"
+    ASM_LN   "popf"
+    ASM_LN   "pushf"
+    ASM_LN   "pop     %0"
+    ASM_LN   "xorl    (%%esp), %0"
+
+    ASM_LN   "popf"
+    ASM_LN
+    : "=&r" (a) // "=a"
+    : "i" (EFALGS_CPUID_BIT)
+    );
+  if ((a & (1 << EFALGS_CPUID_BIT)) == 0)
+    return 0;
+ #endif
+  {
+    UInt32 p[4];
+    x86_cpuid_MACRO(p, 0)
+    return p[0];
+  }
+}
+
+#undef ASM_LN
+
+#elif !defined(_MSC_VER)
+
+/*
+// for gcc/clang and other: we can try to use __cpuid macro:
+#include <cpuid.h>
+void Z7_FASTCALL z7_x86_cpuid(UInt32 p[4], UInt32 func)
+{
+  __cpuid(func, p[0], p[1], p[2], p[3]);
+}
+UInt32 Z7_FASTCALL z7_x86_cpuid_GetMaxFunc(void)
+{
+  return (UInt32)__get_cpuid_max(0, NULL);
+}
+*/
+// for unsupported cpuid:
+void Z7_FASTCALL z7_x86_cpuid(UInt32 p[4], UInt32 func)
+{
+  UNUSED_VAR(func)
+  p[0] = p[1] = p[2] = p[3] = 0;
+}
+UInt32 Z7_FASTCALL z7_x86_cpuid_GetMaxFunc(void)
+{
+  return 0;
+}
+
+#else // _MSC_VER
+
+#if !defined(MY_CPU_AMD64)
+
+UInt32 __declspec(naked) Z7_FASTCALL z7_x86_cpuid_GetMaxFunc(void)
+{
+  #if defined(NEED_CHECK_FOR_CPUID)
+  #define EFALGS_CPUID_BIT 21
+  __asm   pushfd
+  __asm   pushfd
+  /*
+  __asm   pop     eax
+  // __asm   mov     edx, eax
+  __asm   btc     eax, EFALGS_CPUID_BIT
+  __asm   push    eax
+  */
+  __asm   btc     dword ptr [esp], EFALGS_CPUID_BIT
+  __asm   popfd
+  __asm   pushfd
+  __asm   pop     eax
+  // __asm   xor     eax, edx
+  __asm   xor     eax, [esp]
+  // __asm   push    edx
+  __asm   popfd
+  __asm   and     eax, (1 shl EFALGS_CPUID_BIT)
+  __asm   jz end_func
+  #endif
+  __asm   push    ebx
+  __asm   xor     eax, eax    // func
+  __asm   xor     ecx, ecx    // subFunction (optional) for (func == 0)
+  __asm   cpuid
+  __asm   pop     ebx
+  #if defined(NEED_CHECK_FOR_CPUID)
+  end_func:
+  #endif
+  __asm   ret 0
+}
+
+void __declspec(naked) Z7_FASTCALL z7_x86_cpuid(UInt32 p[4], UInt32 func)
+{
+  UNUSED_VAR(p)
+  UNUSED_VAR(func)
+  __asm   push    ebx
+  __asm   push    edi
+  __asm   mov     edi, ecx    // p
+  __asm   mov     eax, edx    // func
+  __asm   xor     ecx, ecx    // subfunction (optional) for (func == 0)
+  __asm   cpuid
+  __asm   mov     [edi     ], eax
+  __asm   mov     [edi +  4], ebx
+  __asm   mov     [edi +  8], ecx
+  __asm   mov     [edi + 12], edx
+  __asm   pop     edi
+  __asm   pop     ebx
+  __asm   ret     0
+}
+
+#else // MY_CPU_AMD64
+
+    #if _MSC_VER >= 1600
+      #include <intrin.h>
+      #define MY_cpuidex  __cpuidex
+    #else
+/*
+ __cpuid (func == (0 or 7)) 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) x64 doesn't clear ECX
+ We still can use __cpuid for low (func) values that don't require ECX,
+ but __cpuid() in old MSVC will be incorrect for some func values: (func == 7).
+ 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 FASTCALL / NO_INLINE func,
+ 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 Z7_NO_INLINE and Z7_FASTCALL for MY_cpuidex_HACK(): !!!
+*/
+static
+Z7_NO_INLINE void Z7_FASTCALL MY_cpuidex_HACK(UInt32 subFunction, UInt32 func, int *CPUInfo)
+{
+  UNUSED_VAR(subFunction)
+  __cpuid(CPUInfo, func);
+}
+      #define MY_cpuidex(info, func, func2)  MY_cpuidex_HACK(func2, func, info)
+      #pragma message("======== MY_cpuidex_HACK WAS USED ========")
+    #endif // _MSC_VER >= 1600
+
+#if !defined(MY_CPU_AMD64)
+/* inlining for __cpuid() in MSVC x86 (32-bit) produces big ineffective code,
+   so we disable inlining here */
+Z7_NO_INLINE
+#endif
+void Z7_FASTCALL z7_x86_cpuid(UInt32 p[4], UInt32 func)
+{
+  MY_cpuidex((int *)p, (int)func, 0);
+}
+
+Z7_NO_INLINE
+UInt32 Z7_FASTCALL z7_x86_cpuid_GetMaxFunc(void)
+{
+  int a[4];
+  MY_cpuidex(a, 0, 0);
+  return a[0];
+}
+
+#endif // MY_CPU_AMD64
+#endif // _MSC_VER
+
+#if defined(NEED_CHECK_FOR_CPUID)
+#define CHECK_CPUID_IS_SUPPORTED { if (z7_x86_cpuid_GetMaxFunc() == 0) return 0; }
+#else
+#define CHECK_CPUID_IS_SUPPORTED
+#endif
+#undef NEED_CHECK_FOR_CPUID
+
+
+static
+BoolInt x86cpuid_Func_1(UInt32 *p)
+{
+  CHECK_CPUID_IS_SUPPORTED
+  z7_x86_cpuid(p, 1);
+  return True;
+}
+
+/*
+static const UInt32 kVendors[][1] =
+{
+  { 0x756E6547 }, // , 0x49656E69, 0x6C65746E },
+  { 0x68747541 }, // , 0x69746E65, 0x444D4163 },
+  { 0x746E6543 }  // , 0x48727561, 0x736C7561 }
+};
+*/
+
+/*
+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
+};
+int x86cpuid_GetFirm(const Cx86cpuid *p);
+#define x86cpuid_ver_GetFamily(ver) (((ver >> 16) & 0xff0) | ((ver >> 8) & 0xf))
+#define x86cpuid_ver_GetModel(ver)  (((ver >> 12) &  0xf0) | ((ver >> 4) & 0xf))
+#define x86cpuid_ver_GetStepping(ver) (ver & 0xf)
+
+int x86cpuid_GetFirm(const Cx86cpuid *p)
+{
+  unsigned i;
+  for (i = 0; i < sizeof(kVendors) / sizeof(kVendors[0]); 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;
+  UInt32 family, model;
+  if (!x86cpuid_CheckAndRead(&p))
+    return True;
+
+  family = x86cpuid_ver_GetFamily(p.ver);
+  model = x86cpuid_ver_GetModel(p.ver);
+
+  switch (x86cpuid_GetFirm(&p))
+  {
+    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 False; // v23 : unknown processors are not In-Order
+}
+*/
+
+#ifdef _WIN32
+#include "7zWindows.h"
+#endif
+
+#if !defined(MY_CPU_AMD64) && defined(_WIN32)
+
+/* for legacy SSE ia32: there is no user-space cpu instruction to check
+   that OS supports SSE register storing/restoring on context switches.
+   So we need some OS-specific function to check that it's safe to use SSE registers.
+*/
+
+Z7_FORCE_INLINE
+static BoolInt CPU_Sys_Is_SSE_Supported(void)
+{
+#ifdef _MSC_VER
+  #pragma warning(push)
+  #pragma warning(disable : 4996) // `GetVersion': was declared deprecated
+#endif
+  /* low byte is major version of Windows
+     We suppose that any Windows version since
+     Windows2000 (major == 5) supports SSE registers */
+  return (Byte)GetVersion() >= 5;
+#if defined(_MSC_VER)
+  #pragma warning(pop)
+#endif
+}
+#define CHECK_SYS_SSE_SUPPORT if (!CPU_Sys_Is_SSE_Supported()) return False;
+#else
+#define CHECK_SYS_SSE_SUPPORT
+#endif
+
+
+#if !defined(MY_CPU_AMD64)
+
+BoolInt CPU_IsSupported_CMOV(void)
+{
+  UInt32 a[4];
+  if (!x86cpuid_Func_1(&a[0]))
+    return 0;
+  return (a[3] >> 15) & 1;
+}
+
+BoolInt CPU_IsSupported_SSE(void)
+{
+  UInt32 a[4];
+  CHECK_SYS_SSE_SUPPORT
+  if (!x86cpuid_Func_1(&a[0]))
+    return 0;
+  return (a[3] >> 25) & 1;
+}
+
+BoolInt CPU_IsSupported_SSE2(void)
+{
+  UInt32 a[4];
+  CHECK_SYS_SSE_SUPPORT
+  if (!x86cpuid_Func_1(&a[0]))
+    return 0;
+  return (a[3] >> 26) & 1;
+}
+
+#endif
+
+
+static UInt32 x86cpuid_Func_1_ECX(void)
+{
+  UInt32 a[4];
+  CHECK_SYS_SSE_SUPPORT
+  if (!x86cpuid_Func_1(&a[0]))
+    return 0;
+  return a[2];
+}
+
+BoolInt CPU_IsSupported_AES(void)
+{
+  return (x86cpuid_Func_1_ECX() >> 25) & 1;
+}
+
+BoolInt CPU_IsSupported_SSSE3(void)
+{
+  return (x86cpuid_Func_1_ECX() >> 9) & 1;
+}
+
+BoolInt CPU_IsSupported_SSE41(void)
+{
+  return (x86cpuid_Func_1_ECX() >> 19) & 1;
+}
+
+BoolInt CPU_IsSupported_SHA(void)
+{
+  CHECK_SYS_SSE_SUPPORT
+
+  if (z7_x86_cpuid_GetMaxFunc() < 7)
+    return False;
+  {
+    UInt32 d[4];
+    z7_x86_cpuid(d, 7);
+    return (d[1] >> 29) & 1;
+  }
+}
+
+/*
+MSVC: _xgetbv() intrinsic is available since VS2010SP1.
+   MSVC also defines (_XCR_XFEATURE_ENABLED_MASK) macro in
+   <immintrin.h> that we can use or check.
+   For any 32-bit x86 we can use asm code in MSVC,
+   but MSVC asm code is huge after compilation.
+   So _xgetbv() is better
+
+ICC: _xgetbv() intrinsic is available (in what version of ICC?)
+   ICC defines (__GNUC___) and it supports gnu assembler
+   also ICC supports MASM style code with -use-msasm switch.
+   but ICC doesn't support __attribute__((__target__))
+
+GCC/CLANG 9:
+  _xgetbv() is macro that works via __builtin_ia32_xgetbv()
+  and we need __attribute__((__target__("xsave")).
+  But with __target__("xsave") the function will be not
+  inlined to function that has no __target__("xsave") attribute.
+  If we want _xgetbv() call inlining, then we should use asm version
+  instead of calling _xgetbv().
+  Note:intrinsic is broke before GCC 8.2:
+    https://gcc.gnu.org/bugzilla/show_bug.cgi?id=85684
+*/
+
+#if    defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 1100) \
+    || defined(_MSC_VER) && (_MSC_VER >= 1600) && (_MSC_FULL_VER >= 160040219)  \
+    || defined(__GNUC__) && (__GNUC__ >= 9) \
+    || defined(__clang__) && (__clang_major__ >= 9)
+// we define ATTRIB_XGETBV, if we want to use predefined _xgetbv() from compiler
+#if defined(__INTEL_COMPILER)
+#define ATTRIB_XGETBV
+#elif defined(__GNUC__) || defined(__clang__)
+// we don't define ATTRIB_XGETBV here, because asm version is better for inlining.
+// #define ATTRIB_XGETBV __attribute__((__target__("xsave")))
+#else
+#define ATTRIB_XGETBV
+#endif
+#endif
+
+#if defined(ATTRIB_XGETBV)
+#include <immintrin.h>
+#endif
+
+
+// XFEATURE_ENABLED_MASK/XCR0
+#define MY_XCR_XFEATURE_ENABLED_MASK 0
+
+#if defined(ATTRIB_XGETBV)
+ATTRIB_XGETBV
+#endif
+static UInt64 x86_xgetbv_0(UInt32 num)
+{
+#if defined(ATTRIB_XGETBV)
+  {
+    return
+      #if (defined(_MSC_VER))
+        _xgetbv(num);
+      #else
+        __builtin_ia32_xgetbv(
+          #if !defined(__clang__)
+            (int)
+          #endif
+            num);
+      #endif
+  }
+
+#elif defined(__GNUC__) || defined(__clang__) || defined(__SUNPRO_CC)
+
+  UInt32 a, d;
+ #if defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 4))
+  __asm__
+  (
+    "xgetbv"
+    : "=a"(a), "=d"(d) : "c"(num) : "cc"
+  );
+ #else // is old gcc
+  __asm__
+  (
+    ".byte 0x0f, 0x01, 0xd0" "\n\t"
+    : "=a"(a), "=d"(d) : "c"(num) : "cc"
+  );
+ #endif
+  return ((UInt64)d << 32) | a;
+  // return a;
+
+#elif defined(_MSC_VER) && !defined(MY_CPU_AMD64)
+  
+  UInt32 a, d;
+  __asm {
+    push eax
+    push edx
+    push ecx
+    mov ecx, num;
+    // xor ecx, ecx // = MY_XCR_XFEATURE_ENABLED_MASK
+    _emit 0x0f
+    _emit 0x01
+    _emit 0xd0
+    mov a, eax
+    mov d, edx
+    pop ecx
+    pop edx
+    pop eax
+  }
+  return ((UInt64)d << 32) | a;
+  // return a;
+
+#else // it's unknown compiler
+  // #error "Need xgetbv function"
+  UNUSED_VAR(num)
+  // for MSVC-X64 we could call external function from external file.
+  /* Actually we had checked OSXSAVE/AVX in cpuid before.
+     So it's expected that OS supports at least AVX and below. */
+  // if (num != MY_XCR_XFEATURE_ENABLED_MASK) return 0; // if not XCR0
+  return
+      // (1 << 0) |  // x87
+        (1 << 1)   // SSE
+      | (1 << 2);  // AVX
+  
+#endif
+}
+
+#ifdef _WIN32
+/*
+  Windows versions do not know about new ISA extensions that
+  can be introduced. But we still can use new extensions,
+  even if Windows doesn't report about supporting them,
+  But we can use new extensions, only if Windows knows about new ISA extension
+  that changes the number or size of registers: SSE, AVX/XSAVE, AVX512
+  So it's enough to check
+    MY_PF_AVX_INSTRUCTIONS_AVAILABLE
+      instead of
+    MY_PF_AVX2_INSTRUCTIONS_AVAILABLE
+*/
+#define MY_PF_XSAVE_ENABLED                            17
+// #define MY_PF_SSSE3_INSTRUCTIONS_AVAILABLE             36
+// #define MY_PF_SSE4_1_INSTRUCTIONS_AVAILABLE            37
+// #define MY_PF_SSE4_2_INSTRUCTIONS_AVAILABLE            38
+// #define MY_PF_AVX_INSTRUCTIONS_AVAILABLE               39
+// #define MY_PF_AVX2_INSTRUCTIONS_AVAILABLE              40
+// #define MY_PF_AVX512F_INSTRUCTIONS_AVAILABLE           41
+#endif
+
+BoolInt CPU_IsSupported_AVX(void)
+{
+  #ifdef _WIN32
+  if (!IsProcessorFeaturePresent(MY_PF_XSAVE_ENABLED))
+    return False;
+  /* PF_AVX_INSTRUCTIONS_AVAILABLE probably is supported starting from
+     some latest Win10 revisions. But we need AVX in older Windows also.
+     So we don't use the following check: */
+  /*
+  if (!IsProcessorFeaturePresent(MY_PF_AVX_INSTRUCTIONS_AVAILABLE))
+    return False;
+  */
+  #endif
+
+  /*
+    OS must use new special XSAVE/XRSTOR instructions to save
+    AVX registers when it required for context switching.
+    At OS statring:
+      OS sets CR4.OSXSAVE flag to signal the processor that OS supports the XSAVE extensions.
+      Also OS sets bitmask in XCR0 register that defines what
+      registers will be processed by XSAVE instruction:
+        XCR0.SSE[bit 0] - x87 registers and state
+        XCR0.SSE[bit 1] - SSE registers and state
+        XCR0.AVX[bit 2] - AVX registers and state
+    CR4.OSXSAVE is reflected to CPUID.1:ECX.OSXSAVE[bit 27].
+       So we can read that bit in user-space.
+    XCR0 is available for reading in user-space by new XGETBV instruction.
+  */
+  {
+    const UInt32 c = x86cpuid_Func_1_ECX();
+    if (0 == (1
+        & (c >> 28)   // AVX instructions are supported by hardware
+        & (c >> 27))) // OSXSAVE bit: XSAVE and related instructions are enabled by OS.
+      return False;
+  }
+
+  /* also we can check
+     CPUID.1:ECX.XSAVE [bit 26] : that shows that
+        XSAVE, XRESTOR, XSETBV, XGETBV instructions are supported by hardware.
+     But that check is redundant, because if OSXSAVE bit is set, then XSAVE is also set */
+
+  /* If OS have enabled XSAVE extension instructions (OSXSAVE == 1),
+     in most cases we expect that OS also will support storing/restoring
+     for AVX and SSE states at least.
+     But to be ensure for that we call user-space instruction
+     XGETBV(0) to get XCR0 value that contains bitmask that defines
+     what exact states(registers) OS have enabled for storing/restoring.
+  */
+
+  {
+    const UInt32 bm = (UInt32)x86_xgetbv_0(MY_XCR_XFEATURE_ENABLED_MASK);
+    // printf("\n=== XGetBV=%d\n", bm);
+    return 1
+        & (bm >> 1)  // SSE state is supported (set by OS) for storing/restoring
+        & (bm >> 2); // AVX state is supported (set by OS) for storing/restoring
+  }
+  // since Win7SP1: we can use GetEnabledXStateFeatures();
+}
+
+
+BoolInt CPU_IsSupported_AVX2(void)
+{
+  if (!CPU_IsSupported_AVX())
+    return False;
+  if (z7_x86_cpuid_GetMaxFunc() < 7)
+    return False;
+  {
+    UInt32 d[4];
+    z7_x86_cpuid(d, 7);
+    // printf("\ncpuid(7): ebx=%8x ecx=%8x\n", d[1], d[2]);
+    return 1
+      & (d[1] >> 5); // avx2
+  }
+}
+
+BoolInt CPU_IsSupported_VAES_AVX2(void)
+{
+  if (!CPU_IsSupported_AVX())
+    return False;
+  if (z7_x86_cpuid_GetMaxFunc() < 7)
+    return False;
+  {
+    UInt32 d[4];
+    z7_x86_cpuid(d, 7);
+    // 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(void)
+{
+  CHECK_CPUID_IS_SUPPORTED
+  {
+    UInt32 d[4];
+    z7_x86_cpuid(d, 0x80000000);
+    if (d[0] < 0x80000001)
+      return False;
+    z7_x86_cpuid(d, 0x80000001);
+    return (d[3] >> 26) & 1;
+  }
+}
+
+
+#elif defined(MY_CPU_ARM_OR_ARM64)
+
+#ifdef _WIN32
+
+#include "7zWindows.h"
+
+BoolInt CPU_IsSupported_CRC32(void)  { return IsProcessorFeaturePresent(PF_ARM_V8_CRC32_INSTRUCTIONS_AVAILABLE) ? 1 : 0; }
+BoolInt CPU_IsSupported_CRYPTO(void) { return IsProcessorFeaturePresent(PF_ARM_V8_CRYPTO_INSTRUCTIONS_AVAILABLE) ? 1 : 0; }
+BoolInt CPU_IsSupported_NEON(void)   { 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]);
+
+  }
+}
+*/
+/*
+  Print_sysctlbyname("hw.pagesize");
+  Print_sysctlbyname("machdep.cpu.brand_string");
+*/
+
+static BoolInt z7_sysctlbyname_Get_BoolInt(const char *name)
+{
+  UInt32 val = 0;
+  if (z7_sysctlbyname_Get_UInt32(name, &val) == 0 && val == 1)
+    return 1;
+  return 0;
+}
+
+BoolInt CPU_IsSupported_CRC32(void)
+{
+  return z7_sysctlbyname_Get_BoolInt("hw.optional.armv8_crc32");
+}
+
+BoolInt CPU_IsSupported_NEON(void)
+{
+  return z7_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 z7_sysctlbyname_Get(const char *name, void *buf, size_t *bufSize)
+{
+  return sysctlbyname(name, buf, bufSize, NULL, 0);
+}
+
+int z7_sysctlbyname_Get_UInt32(const char *name, UInt32 *val)
+{
+  size_t bufSize = sizeof(*val);
+  const int res = z7_sysctlbyname_Get(name, val, &bufSize);
+  if (res == 0 && bufSize != sizeof(*val))
+    return EFAULT;
+  return res;
+}
+
+#endif

external/unarr/lzmasdk/CpuArch.h

@@ -0,0 +1,523 @@
+/* CpuArch.h -- CPU specific code
+2023-04-02 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_CPU_ARCH_H
+#define ZIP7_INC_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
+  #ifdef __ILP32__
+    #define MY_CPU_NAME "arm64-32"
+    #define MY_CPU_SIZEOF_POINTER 4
+  #else
+    #define MY_CPU_NAME "arm64"
+    #define MY_CPU_SIZEOF_POINTER 8
+  #endif
+  #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_ARMT
+    #define MY_CPU_NAME "armt"
+  #else
+    #define MY_CPU_ARM32
+    #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)
+
+#define MY_CPU_PPC_OR_PPC64
+
+#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(__riscv) \
+  || defined(__riscv__)
+  #if __riscv_xlen == 32
+    #define MY_CPU_NAME "riscv32"
+  #elif __riscv_xlen == 64
+    #define MY_CPU_NAME "riscv64"
+  #else
+    #define MY_CPU_NAME "riscv"
+  #endif
+#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_LE) && !defined(MY_CPU_BE)
+  #error Stop_Compiling_CPU_ENDIAN_must_be_detected_at_compile_time
+#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 __has_builtin
+  #define Z7_has_builtin(x)  __has_builtin(x)
+#else
+  #define Z7_has_builtin(x)  0
+#endif
+
+
+#define Z7_BSWAP32_CONST(v) \
+       ( (((UInt32)(v) << 24)                   ) \
+       | (((UInt32)(v) <<  8) & (UInt32)0xff0000) \
+       | (((UInt32)(v) >>  8) & (UInt32)0xff00  ) \
+       | (((UInt32)(v) >> 24)                   ))
+
+
+#if defined(_MSC_VER) && (_MSC_VER >= 1300)
+
+#include <stdlib.h>
+
+/* Note: these macros will use bswap instruction (486), that is unsupported in 386 cpu */
+
+#pragma intrinsic(_byteswap_ushort)
+#pragma intrinsic(_byteswap_ulong)
+#pragma intrinsic(_byteswap_uint64)
+
+#define Z7_BSWAP16(v)  _byteswap_ushort(v)
+#define Z7_BSWAP32(v)  _byteswap_ulong (v)
+#define Z7_BSWAP64(v)  _byteswap_uint64(v)
+#define Z7_CPU_FAST_BSWAP_SUPPORTED
+
+#elif  (defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3))) \
+    || (defined(__clang__) && Z7_has_builtin(__builtin_bswap16))
+ 
+#define Z7_BSWAP16(v)  __builtin_bswap16(v)
+#define Z7_BSWAP32(v)  __builtin_bswap32(v)
+#define Z7_BSWAP64(v)  __builtin_bswap64(v)
+#define Z7_CPU_FAST_BSWAP_SUPPORTED
+
+#else
+
+#define Z7_BSWAP16(v) ((UInt16) \
+       ( ((UInt32)(v) << 8) \
+       | ((UInt32)(v) >> 8) \
+       ))
+
+#define Z7_BSWAP32(v) Z7_BSWAP32_CONST(v)
+
+#define Z7_BSWAP64(v) \
+       ( ( ( (UInt64)(v)                           ) << 8 * 7 ) \
+       | ( ( (UInt64)(v) & ((UInt32)0xff << 8 * 1) ) << 8 * 5 ) \
+       | ( ( (UInt64)(v) & ((UInt32)0xff << 8 * 2) ) << 8 * 3 ) \
+       | ( ( (UInt64)(v) & ((UInt32)0xff << 8 * 3) ) << 8 * 1 ) \
+       | ( ( (UInt64)(v) >> 8 * 1 ) & ((UInt32)0xff << 8 * 3) ) \
+       | ( ( (UInt64)(v) >> 8 * 3 ) & ((UInt32)0xff << 8 * 2) ) \
+       | ( ( (UInt64)(v) >> 8 * 5 ) & ((UInt32)0xff << 8 * 1) ) \
+       | ( ( (UInt64)(v) >> 8 * 7 )                           ) \
+       )
+
+#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))
+#define SetUi64(p, v) { *(UInt64 *)(void *)(p) = (v); }
+#endif
+
+#define SetUi16(p, v) { *(UInt16 *)(void *)(p) = (v); }
+#define SetUi32(p, v) { *(UInt32 *)(void *)(p) = (v); }
+
+#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 GetUi64
+#define GetUi64(p) (GetUi32(p) | ((UInt64)GetUi32(((const Byte *)(p)) + 4) << 32))
+#endif
+
+#ifndef SetUi64
+#define SetUi64(p, v) { Byte *_ppp2_ = (Byte *)(p); UInt64 _vvv2_ = (v); \
+    SetUi32(_ppp2_    , (UInt32)_vvv2_) \
+    SetUi32(_ppp2_ + 4, (UInt32)(_vvv2_ >> 32)) }
+#endif
+
+
+#if defined(MY_CPU_LE_UNALIGN) && defined(Z7_CPU_FAST_BSWAP_SUPPORTED)
+
+#define GetBe32(p)  Z7_BSWAP32 (*(const UInt32 *)(const void *)(p))
+#define SetBe32(p, v) { (*(UInt32 *)(void *)(p)) = Z7_BSWAP32(v); }
+
+#if defined(MY_CPU_LE_UNALIGN_64)
+#define GetBe64(p)  Z7_BSWAP64 (*(const UInt64 *)(const void *)(p))
+#endif
+
+#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 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 GetBe64
+#define GetBe64(p) (((UInt64)GetBe32(p) << 32) | GetBe32(((const Byte *)(p)) + 4))
+#endif
+
+#ifndef GetBe16
+#define GetBe16(p) ( (UInt16) ( \
+    ((UInt16)((const Byte *)(p))[0] << 8) | \
+             ((const Byte *)(p))[1] ))
+#endif
+
+
+#if defined(MY_CPU_BE)
+#define Z7_CONV_BE_TO_NATIVE_CONST32(v)  (v)
+#define Z7_CONV_LE_TO_NATIVE_CONST32(v)  Z7_BSWAP32_CONST(v)
+#define Z7_CONV_NATIVE_TO_BE_32(v)       (v)
+#elif defined(MY_CPU_LE)
+#define Z7_CONV_BE_TO_NATIVE_CONST32(v)  Z7_BSWAP32_CONST(v)
+#define Z7_CONV_LE_TO_NATIVE_CONST32(v)  (v)
+#define Z7_CONV_NATIVE_TO_BE_32(v)       Z7_BSWAP32(v)
+#else
+#error Stop_Compiling_Unknown_Endian_CONV
+#endif
+
+
+#if defined(MY_CPU_BE)
+
+#define GetBe32a(p)      (*(const UInt32 *)(const void *)(p))
+#define GetBe16a(p)      (*(const UInt16 *)(const void *)(p))
+#define SetBe32a(p, v)   { *(UInt32 *)(void *)(p) = (v); }
+#define SetBe16a(p, v)   { *(UInt16 *)(void *)(p) = (v); }
+
+#define GetUi32a(p)      GetUi32(p)
+#define GetUi16a(p)      GetUi16(p)
+#define SetUi32a(p, v)   SetUi32(p, v)
+#define SetUi16a(p, v)   SetUi16(p, v)
+
+#elif defined(MY_CPU_LE)
+
+#define GetUi32a(p)      (*(const UInt32 *)(const void *)(p))
+#define GetUi16a(p)      (*(const UInt16 *)(const void *)(p))
+#define SetUi32a(p, v)   { *(UInt32 *)(void *)(p) = (v); }
+#define SetUi16a(p, v)   { *(UInt16 *)(void *)(p) = (v); }
+
+#define GetBe32a(p)      GetBe32(p)
+#define GetBe16a(p)      GetBe16(p)
+#define SetBe32a(p, v)   SetBe32(p, v)
+#define SetBe16a(p, v)   SetBe16(p, v)
+
+#else
+#error Stop_Compiling_Unknown_Endian_CPU_a
+#endif
+
+
+#if defined(MY_CPU_X86_OR_AMD64) \
+  || defined(MY_CPU_ARM_OR_ARM64) \
+  || defined(MY_CPU_PPC_OR_PPC64)
+  #define Z7_CPU_FAST_ROTATE_SUPPORTED
+#endif
+
+
+#ifdef MY_CPU_X86_OR_AMD64
+
+void Z7_FASTCALL z7_x86_cpuid(UInt32 a[4], UInt32 function);
+UInt32 Z7_FASTCALL z7_x86_cpuid_GetMaxFunc(void);
+#if defined(MY_CPU_AMD64)
+#define Z7_IF_X86_CPUID_SUPPORTED
+#else
+#define Z7_IF_X86_CPUID_SUPPORTED if (z7_x86_cpuid_GetMaxFunc())
+#endif
+
+BoolInt CPU_IsSupported_AES(void);
+BoolInt CPU_IsSupported_AVX(void);
+BoolInt CPU_IsSupported_AVX2(void);
+BoolInt CPU_IsSupported_VAES_AVX2(void);
+BoolInt CPU_IsSupported_CMOV(void);
+BoolInt CPU_IsSupported_SSE(void);
+BoolInt CPU_IsSupported_SSE2(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 z7_sysctlbyname_Get(const char *name, void *buf, size_t *bufSize);
+int z7_sysctlbyname_Get_UInt32(const char *name, UInt32 *val);
+#endif
+
+EXTERN_C_END
+
+#endif

external/unarr/lzmasdk/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);
+}

external/unarr/lzmasdk/Delta.h

@@ -0,0 +1,19 @@
+/* Delta.h -- Delta converter
+2023-03-03 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_DELTA_H
+#define ZIP7_INC_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

external/unarr/lzmasdk/Lzma2Dec.c

@@ -0,0 +1,491 @@
+/* Lzma2Dec.c -- LZMA2 Decoder
+2023-03-03 : 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;
+}
+
+#undef PRF

external/unarr/lzmasdk/Lzma2Dec.h

@@ -0,0 +1,121 @@
+/* Lzma2Dec.h -- LZMA2 Decoder
+2023-03-03 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_LZMA2_DEC_H
+#define ZIP7_INC_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_Construct(p)  Lzma2Dec_CONSTRUCT(p)
+#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

external/unarr/lzmasdk/LzmaDec.h

@@ -0,0 +1,237 @@
+/* LzmaDec.h -- LZMA Decoder
+2023-04-02 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_LZMA_DEC_H
+#define ZIP7_INC_LZMA_DEC_H
+
+#include "7zTypes.h"
+
+EXTERN_C_BEGIN
+
+/* #define Z7_LZMA_PROB32 */
+/* Z7_LZMA_PROB32 can increase the speed on some CPUs,
+   but memory usage for CLzmaDec::probs will be doubled in that case */
+
+typedef
+#ifdef Z7_LZMA_PROB32
+  UInt32
+#else
+  UInt16
+#endif
+  CLzmaProb;
+
+
+/* ---------- LZMA Properties ---------- */
+
+#define LZMA_PROPS_SIZE 5
+
+typedef struct
+{
+  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; }
+#define LzmaDec_Construct(p) LzmaDec_CONSTRUCT(p)
+
+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

external/unarr/lzmasdk/Ppmd.h

@@ -0,0 +1,169 @@
+/* Ppmd.h -- PPMD codec common code
+2023-03-05 : Igor Pavlov : Public domain
+This code is based on PPMd var.H (2001): Dmitry Shkarin : Public domain */
+
+#ifndef ZIP7_INC_PPMD_H
+#define ZIP7_INC_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

external/unarr/lzmasdk/Ppmd7.h

@@ -0,0 +1,181 @@
+/* Ppmd7.h -- Ppmd7 (PPMdH) compression codec
+2023-04-02 : Igor Pavlov : Public domain
+This code is based on:
+  PPMd var.H (2001): Dmitry Shkarin : Public domain */
+ 
+
+#ifndef ZIP7_INC_PPMD7_H
+#define ZIP7_INC_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;
+  IByteInPtr Stream;
+} CPpmd7_RangeDec;
+
+
+typedef struct
+{
+  UInt32 Range;
+  Byte Cache;
+  // Byte _dummy_[3];
+  UInt64 Low;
+  UInt64 CacheSize;
+  IByteOutPtr 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

external/unarr/lzmasdk/Ppmd7Dec.c

@@ -0,0 +1,312 @@
+/* Ppmd7Dec.c -- Ppmd7z (PPMdH with 7z Range Coder) Decoder
+2023-04-02 : 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 ((UInt32)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)
+
+Z7_FORCE_INLINE
+// Z7_NO_INLINE
+static void Ppmd7z_RD_Decode(CPpmd7 *p, UInt32 start, UInt32 size)
+{
+
+  
+  R->Code -= start * R->Range;
+  R->Range *= size;
+  RC_NORM_LOCAL(R)
+}
+
+#define RC_Decode(start, size)  Ppmd7z_RD_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]
+// Z7_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;
+    const 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;
+        CPpmd7_Context *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;
+}
+*/
+
+#undef kTopValue
+#undef READ_BYTE
+#undef RC_NORM_BASE
+#undef RC_NORM_1
+#undef RC_NORM
+#undef RC_NORM_LOCAL
+#undef RC_NORM_REMOTE
+#undef R
+#undef RC_Decode
+#undef RC_DecodeFinal
+#undef RC_GetThreshold
+#undef CTX
+#undef SUCCESSOR
+#undef MASK

external/unarr/lzmasdk/Ppmd7aDec.c

@@ -0,0 +1,295 @@
+/* Ppmd7aDec.c -- PPMd7a (PPMdH) Decoder
+2023-04-02 : Igor Pavlov : Public domain
+This code is based on:
+  PPMd var.H (2001): Dmitry Shkarin : Public domain
+  Carryless rangecoder (1999): Dmitry Subbotin : Public domain */
+
+#include "Precomp.h"
+
+#include "Ppmd7.h"
+
+#define kTop ((UInt32)1 << 24)
+#define kBot ((UInt32)1 << 15)
+
+#define READ_BYTE(p) IByteIn_Read((p)->Stream)
+
+BoolInt Ppmd7a_RangeDec_Init(CPpmd7_RangeDec *p)
+{
+  unsigned i;
+  p->Code = 0;
+  p->Range = 0xFFFFFFFF;
+  p->Low = 0;
+  
+  for (i = 0; i < 4; i++)
+    p->Code = (p->Code << 8) | READ_BYTE(p);
+  return (p->Code < 0xFFFFFFFF);
+}
+
+#define RC_NORM(p) \
+  while ((p->Low ^ (p->Low + p->Range)) < kTop \
+    || (p->Range < kBot && ((p->Range = (0 - p->Low) & (kBot - 1)), 1))) { \
+      p->Code = (p->Code << 8) | READ_BYTE(p); \
+      p->Range <<= 8; p->Low <<= 8; }
+
+// 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)
+
+Z7_FORCE_INLINE
+// Z7_NO_INLINE
+static void Ppmd7a_RD_Decode(CPpmd7 *p, UInt32 start, UInt32 size)
+{
+  start *= R->Range;
+  R->Low += start;
+  R->Code -= start;
+  R->Range *= size;
+  RC_NORM_LOCAL(R)
+}
+
+#define RC_Decode(start, size)  Ppmd7a_RD_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]
+
+
+int Ppmd7a_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;
+    const UInt32 summFreq = p->MinContext->Union2.SummFreq;
+
+    if (summFreq > R->Range)
+      return PPMD7_SYM_ERROR;
+
+    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(R)
+      
+        
+        
+      // 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->Low += size0;
+    R->Code -= size0;
+    R->Range = (R->Range & ~((UInt32)PPMD_BIN_SCALE - 1)) - 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;
+
+    if (freqSum > R->Range)
+      return PPMD7_SYM_ERROR;
+
+    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);
+  }
+}
+
+#undef kTop
+#undef kBot
+#undef READ_BYTE
+#undef RC_NORM_BASE
+#undef RC_NORM_1
+#undef RC_NORM
+#undef RC_NORM_LOCAL
+#undef RC_NORM_REMOTE
+#undef R
+#undef RC_Decode
+#undef RC_DecodeFinal
+#undef RC_GetThreshold
+#undef CTX
+#undef SUCCESSOR
+#undef MASK

external/unarr/lzmasdk/Ppmd8.h

@@ -0,0 +1,181 @@
+/* Ppmd8.h -- Ppmd8 (PPMdI) compression codec
+2021-04-13 : Igor Pavlov : Public domain
+This code is based on:
+  PPMd var.I (2002): Dmitry Shkarin : Public domain
+  Carryless rangecoder (1999): Dmitry Subbotin : Public domain */
+
+#ifndef __PPMD8_H
+#define __PPMD8_H
+
+#include "Ppmd.h"
+
+EXTERN_C_BEGIN
+
+#define PPMD8_MIN_ORDER 2
+#define PPMD8_MAX_ORDER 16
+
+
+
+
+struct CPpmd8_Context_;
+
+typedef Ppmd_Ref_Type(struct CPpmd8_Context_) CPpmd8_Context_Ref;
+
+// MY_CPU_pragma_pack_push_1
+
+typedef struct CPpmd8_Context_
+{
+  Byte NumStats;
+  Byte Flags;
+  
+  union
+  {
+    UInt16 SummFreq;
+    CPpmd_State2 State2;
+  } Union2;
+  
+  union
+  {
+    CPpmd_State_Ref Stats;
+    CPpmd_State4 State4;
+  } Union4;
+
+  CPpmd8_Context_Ref Suffix;
+} CPpmd8_Context;
+
+// MY_CPU_pragma_pop
+
+#define Ppmd8Context_OneState(p) ((CPpmd_State *)&(p)->Union2)
+
+/* PPMdI code rev.2 contains the fix over PPMdI code rev.1.
+   But the code PPMdI.2 is not compatible with PPMdI.1 for some files compressed
+   in FREEZE mode. So we disable FREEZE mode support. */
+
+// #define PPMD8_FREEZE_SUPPORT
+
+enum
+{
+  PPMD8_RESTORE_METHOD_RESTART,
+  PPMD8_RESTORE_METHOD_CUT_OFF
+  #ifdef PPMD8_FREEZE_SUPPORT
+  , PPMD8_RESTORE_METHOD_FREEZE
+  #endif
+  , PPMD8_RESTORE_METHOD_UNSUPPPORTED
+};
+
+
+
+
+
+
+
+
+typedef struct
+{
+  CPpmd8_Context *MinContext, *MaxContext;
+  CPpmd_State *FoundState;
+  unsigned OrderFall, InitEsc, PrevSuccess, MaxOrder, RestoreMethod;
+  Int32 RunLength, InitRL; /* must be 32-bit at least */
+
+  UInt32 Size;
+  UInt32 GlueCount;
+  UInt32 AlignOffset;
+  Byte *Base, *LoUnit, *HiUnit, *Text, *UnitsStart;
+
+  UInt32 Range;
+  UInt32 Code;
+  UInt32 Low;
+  union
+  {
+    IByteIn *In;
+    IByteOut *Out;
+  } Stream;
+
+  Byte Indx2Units[PPMD_NUM_INDEXES + 2]; // +2 for alignment
+  Byte Units2Indx[128];
+  CPpmd_Void_Ref FreeList[PPMD_NUM_INDEXES];
+  UInt32 Stamps[PPMD_NUM_INDEXES];
+  Byte NS2BSIndx[256], NS2Indx[260];
+  Byte ExpEscape[16];
+  CPpmd_See DummySee, See[24][32];
+  UInt16 BinSumm[25][64];
+
+} CPpmd8;
+
+
+void Ppmd8_Construct(CPpmd8 *p);
+BoolInt Ppmd8_Alloc(CPpmd8 *p, UInt32 size, ISzAllocPtr alloc);
+void Ppmd8_Free(CPpmd8 *p, ISzAllocPtr alloc);
+void Ppmd8_Init(CPpmd8 *p, unsigned maxOrder, unsigned restoreMethod);
+#define Ppmd8_WasAllocated(p) ((p)->Base != NULL)
+
+
+/* ---------- Internal Functions ---------- */
+
+#define Ppmd8_GetPtr(p, ptr)     Ppmd_GetPtr(p, ptr)
+#define Ppmd8_GetContext(p, ptr) Ppmd_GetPtr_Type(p, ptr, CPpmd8_Context)
+#define Ppmd8_GetStats(p, ctx)   Ppmd_GetPtr_Type(p, (ctx)->Union4.Stats, CPpmd_State)
+
+void Ppmd8_Update1(CPpmd8 *p);
+void Ppmd8_Update1_0(CPpmd8 *p);
+void Ppmd8_Update2(CPpmd8 *p);
+
+
+
+
+
+
+#define Ppmd8_GetBinSumm(p) \
+    &p->BinSumm[p->NS2Indx[(size_t)Ppmd8Context_OneState(p->MinContext)->Freq - 1]] \
+    [ p->PrevSuccess + ((p->RunLength >> 26) & 0x20) \
+    + p->NS2BSIndx[Ppmd8_GetContext(p, p->MinContext->Suffix)->NumStats] + \
+    + p->MinContext->Flags ]
+
+
+CPpmd_See *Ppmd8_MakeEscFreq(CPpmd8 *p, unsigned numMasked, UInt32 *scale);
+
+
+/* 20.01: the original PPMdI encoder and decoder probably could work incorrectly in some rare cases,
+   where the original PPMdI code can give "Divide by Zero" operation.
+   We use the following fix to allow correct working of encoder and decoder in any cases.
+   We correct (Escape_Freq) and (_sum_), if (_sum_) is larger than p->Range) */
+#define PPMD8_CORRECT_SUM_RANGE(p, _sum_) if (_sum_ > p->Range /* /1 */) _sum_ = p->Range;
+
+
+/* ---------- Decode ---------- */
+
+#define PPMD8_SYM_END    (-1)
+#define PPMD8_SYM_ERROR  (-2)
+
+/*
+You must set (CPpmd8::Stream.In) before Ppmd8_RangeDec_Init()
+
+Ppmd8_DecodeSymbol()
+out:
+  >= 0 : decoded byte
+    -1 : PPMD8_SYM_END   : End of payload marker
+    -2 : PPMD8_SYM_ERROR : Data error
+*/
+
+
+BoolInt Ppmd8_Init_RangeDec(CPpmd8 *p);
+#define Ppmd8_RangeDec_IsFinishedOK(p) ((p)->Code == 0)
+int Ppmd8_DecodeSymbol(CPpmd8 *p);
+
+
+
+
+
+
+
+
+/* ---------- Encode ---------- */
+
+#define Ppmd8_Init_RangeEnc(p) { (p)->Low = 0; (p)->Range = 0xFFFFFFFF; }
+void Ppmd8_Flush_RangeEnc(CPpmd8 *p);
+void Ppmd8_EncodeSymbol(CPpmd8 *p, int symbol);
+
+
+EXTERN_C_END
+ 
+#endif

external/unarr/lzmasdk/Ppmd8Dec.c

@@ -0,0 +1,295 @@
+/* Ppmd8Dec.c -- Ppmd8 (PPMdI) Decoder
+2023-04-02 : Igor Pavlov : Public domain
+This code is based on:
+  PPMd var.I (2002): Dmitry Shkarin : Public domain
+  Carryless rangecoder (1999): Dmitry Subbotin : Public domain */
+
+#include "Precomp.h"
+
+#include "Ppmd8.h"
+
+#define kTop ((UInt32)1 << 24)
+#define kBot ((UInt32)1 << 15)
+
+#define READ_BYTE(p) IByteIn_Read((p)->Stream.In)
+
+BoolInt Ppmd8_Init_RangeDec(CPpmd8 *p)
+{
+  unsigned i;
+  p->Code = 0;
+  p->Range = 0xFFFFFFFF;
+  p->Low = 0;
+  
+  for (i = 0; i < 4; i++)
+    p->Code = (p->Code << 8) | READ_BYTE(p);
+  return (p->Code < 0xFFFFFFFF);
+}
+
+#define RC_NORM(p) \
+  while ((p->Low ^ (p->Low + p->Range)) < kTop \
+    || (p->Range < kBot && ((p->Range = (0 - p->Low) & (kBot - 1)), 1))) { \
+      p->Code = (p->Code << 8) | READ_BYTE(p); \
+      p->Range <<= 8; p->Low <<= 8; }
+
+// 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
+
+Z7_FORCE_INLINE
+// Z7_NO_INLINE
+static void Ppmd8_RD_Decode(CPpmd8 *p, UInt32 start, UInt32 size)
+{
+  start *= R->Range;
+  R->Low += start;
+  R->Code -= start;
+  R->Range *= size;
+  RC_NORM_LOCAL(R)
+}
+
+#define RC_Decode(start, size)  Ppmd8_RD_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) ((CPpmd8_Context *)Ppmd8_GetContext(p, ref))
+// typedef CPpmd8_Context * CTX_PTR;
+#define SUCCESSOR(p) Ppmd_GET_SUCCESSOR(p)
+void Ppmd8_UpdateModel(CPpmd8 *p);
+
+#define MASK(sym) ((unsigned char *)charMask)[sym]
+
+
+int Ppmd8_DecodeSymbol(CPpmd8 *p)
+{
+  size_t charMask[256 / sizeof(size_t)];
+
+  if (p->MinContext->NumStats != 0)
+  {
+    CPpmd_State *s = Ppmd8_GetStats(p, p->MinContext);
+    unsigned i;
+    UInt32 count, hiCnt;
+    UInt32 summFreq = p->MinContext->Union2.SummFreq;
+
+    PPMD8_CORRECT_SUM_RANGE(p, 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;
+      Ppmd8_Update1_0(p);
+      return sym;
+    }
+    
+    p->PrevSuccess = 0;
+    i = p->MinContext->NumStats;
+    
+    do
+    {
+      if ((Int32)(count -= (++s)->Freq) < 0)
+      {
+        Byte sym;
+        RC_DecodeFinal((hiCnt - count) - s->Freq, s->Freq)
+        p->FoundState = s;
+        sym = s->Symbol;
+        Ppmd8_Update1(p);
+        return sym;
+      }
+    }
+    while (--i);
+    
+    if (hiCnt >= summFreq)
+      return PPMD8_SYM_ERROR;
+
+    hiCnt -= count;
+    RC_Decode(hiCnt, summFreq - hiCnt)
+    
+    
+    PPMD_SetAllBitsIn256Bytes(charMask)
+    // i = p->MinContext->NumStats - 1;
+    // do { MASK((--s)->Symbol) = 0; } while (--i);
+    {
+      CPpmd_State *s2 = Ppmd8_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 = Ppmd8Context_OneState(p->MinContext);
+    UInt16 *prob = Ppmd8_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(R)
+      
+      
+        
+      // sym = (p->FoundState = Ppmd8Context_OneState(p->MinContext))->Symbol;
+      // Ppmd8_UpdateBin(p);
+      {
+        unsigned freq = s->Freq;
+        CPpmd8_Context *c = CTX(SUCCESSOR(s));
+        sym = s->Symbol;
+        p->FoundState = s;
+        p->PrevSuccess = 1;
+        p->RunLength++;
+        s->Freq = (Byte)(freq + (freq < 196));
+        // NextContext(p);
+        if (p->OrderFall == 0 && (const Byte *)c >= p->UnitsStart)
+          p->MaxContext = p->MinContext = c;
+        else
+          Ppmd8_UpdateModel(p);
+      }
+      return sym;
+    }
+    
+    *prob = (UInt16)pr;
+    p->InitEsc = p->ExpEscape[pr >> 10];
+    
+    // RangeDec_DecodeBit1(rc2, size0);
+    R->Low += size0;
+    R->Code -= size0;
+    R->Range = (R->Range & ~((UInt32)PPMD_BIN_SCALE - 1)) - size0;
+    RC_NORM_LOCAL(R)
+    
+    PPMD_SetAllBitsIn256Bytes(charMask)
+    MASK(Ppmd8Context_OneState(p->MinContext)->Symbol) = 0;
+    p->PrevSuccess = 0;
+  }
+  
+  for (;;)
+  {
+    CPpmd_State *s, *s2;
+    UInt32 freqSum, count, hiCnt;
+    UInt32 freqSum2;
+    CPpmd_See *see;
+    CPpmd8_Context *mc;
+    unsigned numMasked;
+    RC_NORM_REMOTE(R)
+    mc = p->MinContext;
+    numMasked = mc->NumStats;
+    
+    do
+    {
+      p->OrderFall++;
+      if (!mc->Suffix)
+        return PPMD8_SYM_END;
+      mc = Ppmd8_GetContext(p, mc->Suffix);
+    }
+    while (mc->NumStats == numMasked);
+    
+    s = Ppmd8_GetStats(p, mc);
+
+    {
+      unsigned num = (unsigned)mc->NumStats + 1;
+      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 = Ppmd8_MakeEscFreq(p, numMasked, &freqSum);
+    freqSum += hiCnt;
+    freqSum2 = freqSum;
+    PPMD8_CORRECT_SUM_RANGE(R, freqSum2)
+
+
+    count = RC_GetThreshold(freqSum2);
+    
+    if (count < hiCnt)
+    {
+      Byte sym;
+      // Ppmd_See_UPDATE(see) // new (see->Summ) value can overflow over 16-bits in some rare cases
+      s = Ppmd8_GetStats(p, p->MinContext);
+      hiCnt = count;
+
+      
+      {
+        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;
+      Ppmd8_Update2(p);
+      return sym;
+    }
+
+    if (count >= freqSum2)
+      return PPMD8_SYM_ERROR;
+    
+    RC_Decode(hiCnt, freqSum2 - 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 = Ppmd8_GetStats(p, p->MinContext);
+    s2 = s + p->MinContext->NumStats + 1;
+    do
+    {
+      MASK(s->Symbol) = 0;
+      s++;
+    }
+    while (s != s2);
+  }
+}
+
+#undef kTop
+#undef kBot
+#undef READ_BYTE
+#undef RC_NORM_BASE
+#undef RC_NORM_1
+#undef RC_NORM
+#undef RC_NORM_LOCAL
+#undef RC_NORM_REMOTE
+#undef R
+#undef RC_Decode
+#undef RC_DecodeFinal
+#undef RC_GetThreshold
+#undef CTX
+#undef SUCCESSOR
+#undef MASK

external/unarr/lzmasdk/Precomp.h

@@ -0,0 +1,10 @@
+/* Precomp.h -- StdAfx
+2023-04-02 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_PRECOMP_H
+#define ZIP7_INC_PRECOMP_H
+
+#include "Compiler.h"
+/* #include "7zTypes.h" */
+
+#endif

external/unarr/lzmasdk/RotateDefs.h

@@ -0,0 +1,50 @@
+/* RotateDefs.h -- Rotate functions
+2023-06-18 : Igor Pavlov : Public domain */
+
+#ifndef ZIP7_INC_ROTATE_DEFS_H
+#define ZIP7_INC_ROTATE_DEFS_H
+
+#ifdef _MSC_VER
+
+#include <stdlib.h>
+
+/* don't use _rotl with old 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))
+
+#if (_MSC_VER >= 1300)
+#define Z7_ROTL64(x, n) _rotl64((x), (n))
+#define Z7_ROTR64(x, n) _rotr64((x), (n))
+#else
+#define Z7_ROTL64(x, n) (((x) << (n)) | ((x) >> (64 - (n))))
+#define Z7_ROTR64(x, n) (((x) >> (n)) | ((x) << (64 - (n))))
+#endif
+
+#else
+
+/* new compilers can translate these macros to fast commands. */
+
+#if defined(__clang__) && (__clang_major__ >= 4) \
+  || defined(__GNUC__) && (__GNUC__ >= 5)
+/* GCC 4.9.0 and clang 3.5 can recognize more correct version: */
+#define rotlFixed(x, n) (((x) << (n)) | ((x) >> (-(n) & 31)))
+#define rotrFixed(x, n) (((x) >> (n)) | ((x) << (-(n) & 31)))
+#define Z7_ROTL64(x, n) (((x) << (n)) | ((x) >> (-(n) & 63)))
+#define Z7_ROTR64(x, n) (((x) >> (n)) | ((x) << (-(n) & 63)))
+#else
+/* for old GCC / clang: */
+#define rotlFixed(x, n) (((x) << (n)) | ((x) >> (32 - (n))))
+#define rotrFixed(x, n) (((x) >> (n)) | ((x) << (32 - (n))))
+#define Z7_ROTL64(x, n) (((x) << (n)) | ((x) >> (64 - (n))))
+#define Z7_ROTR64(x, n) (((x) >> (n)) | ((x) << (64 - (n))))
+#endif
+
+#endif
+
+#endif