dep: Add lzma 19.00

dep/lzma/src/Alloc.c

@@ -0,0 +1,455 @@
+/* Alloc.c -- Memory allocation functions
+2018-04-27 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <stdio.h>
+
+#ifdef _WIN32
+#include <windows.h>
+#endif
+#include <stdlib.h>
+
+#include "Alloc.h"
+
+/* #define _SZ_ALLOC_DEBUG */
+
+/* use _SZ_ALLOC_DEBUG to debug alloc/free operations */
+#ifdef _SZ_ALLOC_DEBUG
+
+#include <stdio.h>
+int g_allocCount = 0;
+int g_allocCountMid = 0;
+int g_allocCountBig = 0;
+
+
+#define CONVERT_INT_TO_STR(charType, tempSize) \
+  unsigned char temp[tempSize]; unsigned i = 0; \
+  while (val >= 10) { temp[i++] = (unsigned char)('0' + (unsigned)(val % 10)); val /= 10; } \
+  *s++ = (charType)('0' + (unsigned)val); \
+  while (i != 0) { i--; *s++ = temp[i]; } \
+  *s = 0;
+
+static void ConvertUInt64ToString(UInt64 val, char *s)
+{
+  CONVERT_INT_TO_STR(char, 24);
+}
+
+#define GET_HEX_CHAR(t) ((char)(((t < 10) ? ('0' + t) : ('A' + (t - 10)))))
+
+static void ConvertUInt64ToHex(UInt64 val, char *s)
+{
+  UInt64 v = val;
+  unsigned i;
+  for (i = 1;; i++)
+  {
+    v >>= 4;
+    if (v == 0)
+      break;
+  }
+  s[i] = 0;
+  do
+  {
+    unsigned t = (unsigned)(val & 0xF);
+    val >>= 4;
+    s[--i] = GET_HEX_CHAR(t);
+  }
+  while (i);
+}
+
+#define DEBUG_OUT_STREAM stderr
+
+static void Print(const char *s)
+{
+  fputs(s, DEBUG_OUT_STREAM);
+}
+
+static void PrintAligned(const char *s, size_t align)
+{
+  size_t len = strlen(s);
+  for(;;)
+  {
+    fputc(' ', DEBUG_OUT_STREAM);
+    if (len >= align)
+      break;
+    ++len;
+  }
+  Print(s);
+}
+
+static void PrintLn()
+{
+  Print("\n");
+}
+
+static void PrintHex(UInt64 v, size_t align)
+{
+  char s[32];
+  ConvertUInt64ToHex(v, s);
+  PrintAligned(s, align);
+}
+
+static void PrintDec(UInt64 v, size_t align)
+{
+  char s[32];
+  ConvertUInt64ToString(v, s);
+  PrintAligned(s, align);
+}
+
+static void PrintAddr(void *p)
+{
+  PrintHex((UInt64)(size_t)(ptrdiff_t)p, 12);
+}
+
+
+#define PRINT_ALLOC(name, cnt, size, ptr) \
+    Print(name " "); \
+    PrintDec(cnt++, 10); \
+    PrintHex(size, 10); \
+    PrintAddr(ptr); \
+    PrintLn();
+ 
+#define PRINT_FREE(name, cnt, ptr) if (ptr) { \
+    Print(name " "); \
+    PrintDec(--cnt, 10); \
+    PrintAddr(ptr); \
+    PrintLn(); }
+ 
+#else
+
+#define PRINT_ALLOC(name, cnt, size, ptr)
+#define PRINT_FREE(name, cnt, ptr)
+#define Print(s)
+#define PrintLn()
+#define PrintHex(v, align)
+#define PrintDec(v, align)
+#define PrintAddr(p)
+
+#endif
+
+
+
+void *MyAlloc(size_t size)
+{
+  if (size == 0)
+    return NULL;
+  #ifdef _SZ_ALLOC_DEBUG
+  {
+    void *p = malloc(size);
+    PRINT_ALLOC("Alloc    ", g_allocCount, size, p);
+    return p;
+  }
+  #else
+  return malloc(size);
+  #endif
+}
+
+void MyFree(void *address)
+{
+  PRINT_FREE("Free    ", g_allocCount, address);
+  
+  free(address);
+}
+
+#ifdef _WIN32
+
+void *MidAlloc(size_t size)
+{
+  if (size == 0)
+    return NULL;
+  
+  PRINT_ALLOC("Alloc-Mid", g_allocCountMid, size, NULL);
+  
+  return VirtualAlloc(NULL, size, MEM_COMMIT, PAGE_READWRITE);
+}
+
+void MidFree(void *address)
+{
+  PRINT_FREE("Free-Mid", g_allocCountMid, address);
+
+  if (!address)
+    return;
+  VirtualFree(address, 0, MEM_RELEASE);
+}
+
+#ifndef MEM_LARGE_PAGES
+#undef _7ZIP_LARGE_PAGES
+#endif
+
+#ifdef _7ZIP_LARGE_PAGES
+SIZE_T g_LargePageSize = 0;
+typedef SIZE_T (WINAPI *GetLargePageMinimumP)();
+#endif
+
+void SetLargePageSize()
+{
+  #ifdef _7ZIP_LARGE_PAGES
+  SIZE_T size;
+  GetLargePageMinimumP largePageMinimum = (GetLargePageMinimumP)
+        GetProcAddress(GetModuleHandle(TEXT("kernel32.dll")), "GetLargePageMinimum");
+  if (!largePageMinimum)
+    return;
+  size = largePageMinimum();
+  if (size == 0 || (size & (size - 1)) != 0)
+    return;
+  g_LargePageSize = size;
+  #endif
+}
+
+
+void *BigAlloc(size_t size)
+{
+  if (size == 0)
+    return NULL;
+
+  PRINT_ALLOC("Alloc-Big", g_allocCountBig, size, NULL);
+  
+  #ifdef _7ZIP_LARGE_PAGES
+  {
+    SIZE_T ps = g_LargePageSize;
+    if (ps != 0 && ps <= (1 << 30) && size > (ps / 2))
+    {
+      size_t size2;
+      ps--;
+      size2 = (size + ps) & ~ps;
+      if (size2 >= size)
+      {
+        void *res = VirtualAlloc(NULL, size2, MEM_COMMIT | MEM_LARGE_PAGES, PAGE_READWRITE);
+        if (res)
+          return res;
+      }
+    }
+  }
+  #endif
+
+  return VirtualAlloc(NULL, size, MEM_COMMIT, PAGE_READWRITE);
+}
+
+void BigFree(void *address)
+{
+  PRINT_FREE("Free-Big", g_allocCountBig, address);
+  
+  if (!address)
+    return;
+  VirtualFree(address, 0, MEM_RELEASE);
+}
+
+#endif
+
+
+static void *SzAlloc(ISzAllocPtr p, size_t size) { UNUSED_VAR(p); return MyAlloc(size); }
+static void SzFree(ISzAllocPtr p, void *address) { UNUSED_VAR(p); MyFree(address); }
+const ISzAlloc g_Alloc = { SzAlloc, SzFree };
+
+static void *SzMidAlloc(ISzAllocPtr p, size_t size) { UNUSED_VAR(p); return MidAlloc(size); }
+static void SzMidFree(ISzAllocPtr p, void *address) { UNUSED_VAR(p); MidFree(address); }
+const ISzAlloc g_MidAlloc = { SzMidAlloc, SzMidFree };
+
+static void *SzBigAlloc(ISzAllocPtr p, size_t size) { UNUSED_VAR(p); return BigAlloc(size); }
+static void SzBigFree(ISzAllocPtr p, void *address) { UNUSED_VAR(p); BigFree(address); }
+const ISzAlloc g_BigAlloc = { SzBigAlloc, SzBigFree };
+
+
+/*
+  uintptr_t : <stdint.h> C99 (optional)
+            : unsupported in VS6
+*/
+
+#ifdef _WIN32
+  typedef UINT_PTR UIntPtr;
+#else
+  /*
+  typedef uintptr_t UIntPtr;
+  */
+  typedef ptrdiff_t UIntPtr;
+#endif
+
+
+#define ADJUST_ALLOC_SIZE 0
+/*
+#define ADJUST_ALLOC_SIZE (sizeof(void *) - 1)
+*/
+/*
+  Use (ADJUST_ALLOC_SIZE = (sizeof(void *) - 1)), if
+     MyAlloc() can return address that is NOT multiple of sizeof(void *).
+*/
+
+
+/*
+#define MY_ALIGN_PTR_DOWN(p, align) ((void *)((char *)(p) - ((size_t)(UIntPtr)(p) & ((align) - 1))))
+*/
+#define MY_ALIGN_PTR_DOWN(p, align) ((void *)((((UIntPtr)(p)) & ~((UIntPtr)(align) - 1))))
+
+#define MY_ALIGN_PTR_UP_PLUS(p, align) MY_ALIGN_PTR_DOWN(((char *)(p) + (align) + ADJUST_ALLOC_SIZE), align)
+
+
+#if (_POSIX_C_SOURCE >= 200112L) && !defined(_WIN32)
+  #define USE_posix_memalign
+#endif
+
+/*
+  This posix_memalign() is for test purposes only.
+  We also need special Free() function instead of free(),
+  if this posix_memalign() is used.
+*/
+
+/*
+static int posix_memalign(void **ptr, size_t align, size_t size)
+{
+  size_t newSize = size + align;
+  void *p;
+  void *pAligned;
+  *ptr = NULL;
+  if (newSize < size)
+    return 12; // ENOMEM
+  p = MyAlloc(newSize);
+  if (!p)
+    return 12; // ENOMEM
+  pAligned = MY_ALIGN_PTR_UP_PLUS(p, align);
+  ((void **)pAligned)[-1] = p;
+  *ptr = pAligned;
+  return 0;
+}
+*/
+
+/*
+  ALLOC_ALIGN_SIZE >= sizeof(void *)
+  ALLOC_ALIGN_SIZE >= cache_line_size
+*/
+
+#define ALLOC_ALIGN_SIZE ((size_t)1 << 7)
+
+static void *SzAlignedAlloc(ISzAllocPtr pp, size_t size)
+{
+  #ifndef USE_posix_memalign
+  
+  void *p;
+  void *pAligned;
+  size_t newSize;
+  UNUSED_VAR(pp);
+
+  /* also we can allocate additional dummy ALLOC_ALIGN_SIZE bytes after aligned
+     block to prevent cache line sharing with another allocated blocks */
+
+  newSize = size + ALLOC_ALIGN_SIZE * 1 + ADJUST_ALLOC_SIZE;
+  if (newSize < size)
+    return NULL;
+
+  p = MyAlloc(newSize);
+  
+  if (!p)
+    return NULL;
+  pAligned = MY_ALIGN_PTR_UP_PLUS(p, ALLOC_ALIGN_SIZE);
+
+  Print(" size="); PrintHex(size, 8);
+  Print(" a_size="); PrintHex(newSize, 8);
+  Print(" ptr="); PrintAddr(p);
+  Print(" a_ptr="); PrintAddr(pAligned);
+  PrintLn();
+
+  ((void **)pAligned)[-1] = p;
+
+  return pAligned;
+
+  #else
+
+  void *p;
+  UNUSED_VAR(pp);
+  if (posix_memalign(&p, ALLOC_ALIGN_SIZE, size))
+    return NULL;
+
+  Print(" posix_memalign="); PrintAddr(p);
+  PrintLn();
+
+  return p;
+
+  #endif
+}
+
+
+static void SzAlignedFree(ISzAllocPtr pp, void *address)
+{
+  UNUSED_VAR(pp);
+  #ifndef USE_posix_memalign
+  if (address)
+    MyFree(((void **)address)[-1]);
+  #else
+  free(address);
+  #endif
+}
+
+
+const ISzAlloc g_AlignedAlloc = { SzAlignedAlloc, SzAlignedFree };
+
+
+
+#define MY_ALIGN_PTR_DOWN_1(p) MY_ALIGN_PTR_DOWN(p, sizeof(void *))
+
+/* we align ptr to support cases where CAlignOffsetAlloc::offset is not multiply of sizeof(void *) */
+#define REAL_BLOCK_PTR_VAR(p) ((void **)MY_ALIGN_PTR_DOWN_1(p))[-1]
+/*
+#define REAL_BLOCK_PTR_VAR(p) ((void **)(p))[-1]
+*/
+
+static void *AlignOffsetAlloc_Alloc(ISzAllocPtr pp, size_t size)
+{
+  CAlignOffsetAlloc *p = CONTAINER_FROM_VTBL(pp, CAlignOffsetAlloc, vt);
+  void *adr;
+  void *pAligned;
+  size_t newSize;
+  size_t extra;
+  size_t alignSize = (size_t)1 << p->numAlignBits;
+
+  if (alignSize < sizeof(void *))
+    alignSize = sizeof(void *);
+  
+  if (p->offset >= alignSize)
+    return NULL;
+
+  /* also we can allocate additional dummy ALLOC_ALIGN_SIZE bytes after aligned
+     block to prevent cache line sharing with another allocated blocks */
+  extra = p->offset & (sizeof(void *) - 1);
+  newSize = size + alignSize + extra + ADJUST_ALLOC_SIZE;
+  if (newSize < size)
+    return NULL;
+
+  adr = ISzAlloc_Alloc(p->baseAlloc, newSize);
+  
+  if (!adr)
+    return NULL;
+
+  pAligned = (char *)MY_ALIGN_PTR_DOWN((char *)adr +
+      alignSize - p->offset + extra + ADJUST_ALLOC_SIZE, alignSize) + p->offset;
+
+  PrintLn();
+  Print("- Aligned: ");
+  Print(" size="); PrintHex(size, 8);
+  Print(" a_size="); PrintHex(newSize, 8);
+  Print(" ptr="); PrintAddr(adr);
+  Print(" a_ptr="); PrintAddr(pAligned);
+  PrintLn();
+
+  REAL_BLOCK_PTR_VAR(pAligned) = adr;
+
+  return pAligned;
+}
+
+
+static void AlignOffsetAlloc_Free(ISzAllocPtr pp, void *address)
+{
+  if (address)
+  {
+    CAlignOffsetAlloc *p = CONTAINER_FROM_VTBL(pp, CAlignOffsetAlloc, vt);
+    PrintLn();
+    Print("- Aligned Free: ");
+    PrintLn();
+    ISzAlloc_Free(p->baseAlloc, REAL_BLOCK_PTR_VAR(address));
+  }
+}
+
+
+void AlignOffsetAlloc_CreateVTable(CAlignOffsetAlloc *p)
+{
+  p->vt.Alloc = AlignOffsetAlloc_Alloc;
+  p->vt.Free = AlignOffsetAlloc_Free;
+}

dep/lzma/src/Bra86.c

@@ -0,0 +1,82 @@
+/* Bra86.c -- Converter for x86 code (BCJ)
+2017-04-03 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Bra.h"
+
+#define Test86MSByte(b) ((((b) + 1) & 0xFE) == 0)
+
+SizeT x86_Convert(Byte *data, SizeT size, UInt32 ip, UInt32 *state, int encoding)
+{
+  SizeT pos = 0;
+  UInt32 mask = *state & 7;
+  if (size < 5)
+    return 0;
+  size -= 4;
+  ip += 5;
+
+  for (;;)
+  {
+    Byte *p = data + pos;
+    const Byte *limit = data + size;
+    for (; p < limit; p++)
+      if ((*p & 0xFE) == 0xE8)
+        break;
+
+    {
+      SizeT d = (SizeT)(p - data - pos);
+      pos = (SizeT)(p - data);
+      if (p >= limit)
+      {
+        *state = (d > 2 ? 0 : mask >> (unsigned)d);
+        return pos;
+      }
+      if (d > 2)
+        mask = 0;
+      else
+      {
+        mask >>= (unsigned)d;
+        if (mask != 0 && (mask > 4 || mask == 3 || Test86MSByte(p[(size_t)(mask >> 1) + 1])))
+        {
+          mask = (mask >> 1) | 4;
+          pos++;
+          continue;
+        }
+      }
+    }
+
+    if (Test86MSByte(p[4]))
+    {
+      UInt32 v = ((UInt32)p[4] << 24) | ((UInt32)p[3] << 16) | ((UInt32)p[2] << 8) | ((UInt32)p[1]);
+      UInt32 cur = ip + (UInt32)pos;
+      pos += 5;
+      if (encoding)
+        v += cur;
+      else
+        v -= cur;
+      if (mask != 0)
+      {
+        unsigned sh = (mask & 6) << 2;
+        if (Test86MSByte((Byte)(v >> sh)))
+        {
+          v ^= (((UInt32)0x100 << sh) - 1);
+          if (encoding)
+            v += cur;
+          else
+            v -= cur;
+        }
+        mask = 0;
+      }
+      p[1] = (Byte)v;
+      p[2] = (Byte)(v >> 8);
+      p[3] = (Byte)(v >> 16);
+      p[4] = (Byte)(0 - ((v >> 24) & 1));
+    }
+    else
+    {
+      mask = (mask >> 1) | 4;
+      pos++;
+    }
+  }
+}

dep/lzma/src/BraIA64.c

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

dep/lzma/src/CpuArch.c

@@ -0,0 +1,218 @@
+/* CpuArch.c -- CPU specific code
+2018-02-18: Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "CpuArch.h"
+
+#ifdef MY_CPU_X86_OR_AMD64
+
+#if (defined(_MSC_VER) && !defined(MY_CPU_AMD64)) || defined(__GNUC__)
+#define USE_ASM
+#endif
+
+#if !defined(USE_ASM) && _MSC_VER >= 1500
+#include <intrin.h>
+#endif
+
+#if defined(USE_ASM) && !defined(MY_CPU_AMD64)
+static UInt32 CheckFlag(UInt32 flag)
+{
+  #ifdef _MSC_VER
+  __asm pushfd;
+  __asm pop EAX;
+  __asm mov EDX, EAX;
+  __asm xor EAX, flag;
+  __asm push EAX;
+  __asm popfd;
+  __asm pushfd;
+  __asm pop EAX;
+  __asm xor EAX, EDX;
+  __asm push EDX;
+  __asm popfd;
+  __asm and flag, EAX;
+  #else
+  __asm__ __volatile__ (
+    "pushf\n\t"
+    "pop  %%EAX\n\t"
+    "movl %%EAX,%%EDX\n\t"
+    "xorl %0,%%EAX\n\t"
+    "push %%EAX\n\t"
+    "popf\n\t"
+    "pushf\n\t"
+    "pop  %%EAX\n\t"
+    "xorl %%EDX,%%EAX\n\t"
+    "push %%EDX\n\t"
+    "popf\n\t"
+    "andl %%EAX, %0\n\t":
+    "=c" (flag) : "c" (flag) :
+    "%eax", "%edx");
+  #endif
+  return flag;
+}
+#define CHECK_CPUID_IS_SUPPORTED if (CheckFlag(1 << 18) == 0 || CheckFlag(1 << 21) == 0) return False;
+#else
+#define CHECK_CPUID_IS_SUPPORTED
+#endif
+
+void MyCPUID(UInt32 function, UInt32 *a, UInt32 *b, UInt32 *c, UInt32 *d)
+{
+  #ifdef USE_ASM
+
+  #ifdef _MSC_VER
+
+  UInt32 a2, b2, c2, d2;
+  __asm xor EBX, EBX;
+  __asm xor ECX, ECX;
+  __asm xor EDX, EDX;
+  __asm mov EAX, function;
+  __asm cpuid;
+  __asm mov a2, EAX;
+  __asm mov b2, EBX;
+  __asm mov c2, ECX;
+  __asm mov d2, EDX;
+
+  *a = a2;
+  *b = b2;
+  *c = c2;
+  *d = d2;
+
+  #else
+
+  __asm__ __volatile__ (
+  #if defined(MY_CPU_AMD64) && defined(__PIC__)
+    "mov %%rbx, %%rdi;"
+    "cpuid;"
+    "xchg %%rbx, %%rdi;"
+    : "=a" (*a) ,
+      "=D" (*b) ,
+  #elif defined(MY_CPU_X86) && defined(__PIC__)
+    "mov %%ebx, %%edi;"
+    "cpuid;"
+    "xchgl %%ebx, %%edi;"
+    : "=a" (*a) ,
+      "=D" (*b) ,
+  #else
+    "cpuid"
+    : "=a" (*a) ,
+      "=b" (*b) ,
+  #endif
+      "=c" (*c) ,
+      "=d" (*d)
+    : "0" (function)) ;
+
+  #endif
+  
+  #else
+
+  int CPUInfo[4];
+  __cpuid(CPUInfo, function);
+  *a = CPUInfo[0];
+  *b = CPUInfo[1];
+  *c = CPUInfo[2];
+  *d = CPUInfo[3];
+
+  #endif
+}
+
+BoolInt x86cpuid_CheckAndRead(Cx86cpuid *p)
+{
+  CHECK_CPUID_IS_SUPPORTED
+  MyCPUID(0, &p->maxFunc, &p->vendor[0], &p->vendor[2], &p->vendor[1]);
+  MyCPUID(1, &p->ver, &p->b, &p->c, &p->d);
+  return True;
+}
+
+static const UInt32 kVendors[][3] =
+{
+  { 0x756E6547, 0x49656E69, 0x6C65746E},
+  { 0x68747541, 0x69746E65, 0x444D4163},
+  { 0x746E6543, 0x48727561, 0x736C7561}
+};
+
+int x86cpuid_GetFirm(const Cx86cpuid *p)
+{
+  unsigned i;
+  for (i = 0; i < sizeof(kVendors) / sizeof(kVendors[i]); i++)
+  {
+    const UInt32 *v = kVendors[i];
+    if (v[0] == p->vendor[0] &&
+        v[1] == p->vendor[1] &&
+        v[2] == p->vendor[2])
+      return (int)i;
+  }
+  return -1;
+}
+
+BoolInt CPU_Is_InOrder()
+{
+  Cx86cpuid p;
+  int firm;
+  UInt32 family, model;
+  if (!x86cpuid_CheckAndRead(&p))
+    return True;
+
+  family = x86cpuid_GetFamily(p.ver);
+  model = x86cpuid_GetModel(p.ver);
+  
+  firm = x86cpuid_GetFirm(&p);
+
+  switch (firm)
+  {
+    case CPU_FIRM_INTEL: return (family < 6 || (family == 6 && (
+        /* In-Order Atom CPU */
+           model == 0x1C  /* 45 nm, N4xx, D4xx, N5xx, D5xx, 230, 330 */
+        || model == 0x26  /* 45 nm, Z6xx */
+        || model == 0x27  /* 32 nm, Z2460 */
+        || model == 0x35  /* 32 nm, Z2760 */
+        || model == 0x36  /* 32 nm, N2xxx, D2xxx */
+        )));
+    case CPU_FIRM_AMD: return (family < 5 || (family == 5 && (model < 6 || model == 0xA)));
+    case CPU_FIRM_VIA: return (family < 6 || (family == 6 && model < 0xF));
+  }
+  return True;
+}
+
+#if !defined(MY_CPU_AMD64) && defined(_WIN32)
+#include <windows.h>
+static BoolInt CPU_Sys_Is_SSE_Supported()
+{
+  OSVERSIONINFO vi;
+  vi.dwOSVersionInfoSize = sizeof(vi);
+  if (!GetVersionEx(&vi))
+    return False;
+  return (vi.dwMajorVersion >= 5);
+}
+#define CHECK_SYS_SSE_SUPPORT if (!CPU_Sys_Is_SSE_Supported()) return False;
+#else
+#define CHECK_SYS_SSE_SUPPORT
+#endif
+
+BoolInt CPU_Is_Aes_Supported()
+{
+  Cx86cpuid p;
+  CHECK_SYS_SSE_SUPPORT
+  if (!x86cpuid_CheckAndRead(&p))
+    return False;
+  return (p.c >> 25) & 1;
+}
+
+BoolInt CPU_IsSupported_PageGB()
+{
+  Cx86cpuid cpuid;
+  if (!x86cpuid_CheckAndRead(&cpuid))
+    return False;
+  {
+    UInt32 d[4] = { 0 };
+    MyCPUID(0x80000000, &d[0], &d[1], &d[2], &d[3]);
+    if (d[0] < 0x80000001)
+      return False;
+  }
+  {
+    UInt32 d[4] = { 0 };
+    MyCPUID(0x80000001, &d[0], &d[1], &d[2], &d[3]);
+    return (d[3] >> 26) & 1;
+  }
+}
+
+#endif

dep/lzma/src/Delta.c

@@ -0,0 +1,64 @@
+/* Delta.c -- Delta converter
+2009-05-26 : 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;
+}
+
+static void MyMemCpy(Byte *dest, const Byte *src, unsigned size)
+{
+  unsigned i;
+  for (i = 0; i < size; i++)
+    dest[i] = src[i];
+}
+
+void Delta_Encode(Byte *state, unsigned delta, Byte *data, SizeT size)
+{
+  Byte buf[DELTA_STATE_SIZE];
+  unsigned j = 0;
+  MyMemCpy(buf, state, delta);
+  {
+    SizeT i;
+    for (i = 0; i < size;)
+    {
+      for (j = 0; j < delta && i < size; i++, j++)
+      {
+        Byte b = data[i];
+        data[i] = (Byte)(b - buf[j]);
+        buf[j] = b;
+      }
+    }
+  }
+  if (j == delta)
+    j = 0;
+  MyMemCpy(state, buf + j, delta - j);
+  MyMemCpy(state + delta - j, buf, j);
+}
+
+void Delta_Decode(Byte *state, unsigned delta, Byte *data, SizeT size)
+{
+  Byte buf[DELTA_STATE_SIZE];
+  unsigned j = 0;
+  MyMemCpy(buf, state, delta);
+  {
+    SizeT i;
+    for (i = 0; i < size;)
+    {
+      for (j = 0; j < delta && i < size; i++, j++)
+      {
+        buf[j] = data[i] = (Byte)(buf[j] + data[i]);
+      }
+    }
+  }
+  if (j == delta)
+    j = 0;
+  MyMemCpy(state, buf + j, delta - j);
+  MyMemCpy(state + delta - j, buf, j);
+}

dep/lzma/src/Lzma86Dec.c

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

dep/lzma/src/Lzma86Enc.c

@@ -0,0 +1,106 @@
+/* Lzma86Enc.c -- LZMA + x86 (BCJ) Filter Encoder
+2018-07-04 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include <string.h>
+
+#include "Lzma86.h"
+
+#include "Alloc.h"
+#include "Bra.h"
+#include "LzmaEnc.h"
+
+#define SZE_OUT_OVERFLOW SZE_DATA_ERROR
+
+int Lzma86_Encode(Byte *dest, size_t *destLen, const Byte *src, size_t srcLen,
+    int level, UInt32 dictSize, int filterMode)
+{
+  size_t outSize2 = *destLen;
+  Byte *filteredStream;
+  BoolInt useFilter;
+  int mainResult = SZ_ERROR_OUTPUT_EOF;
+  CLzmaEncProps props;
+  LzmaEncProps_Init(&props);
+  props.level = level;
+  props.dictSize = dictSize;
+  
+  *destLen = 0;
+  if (outSize2 < LZMA86_HEADER_SIZE)
+    return SZ_ERROR_OUTPUT_EOF;
+
+  {
+    int i;
+    UInt64 t = srcLen;
+    for (i = 0; i < 8; i++, t >>= 8)
+      dest[LZMA86_SIZE_OFFSET + i] = (Byte)t;
+  }
+
+  filteredStream = 0;
+  useFilter = (filterMode != SZ_FILTER_NO);
+  if (useFilter)
+  {
+    if (srcLen != 0)
+    {
+      filteredStream = (Byte *)MyAlloc(srcLen);
+      if (filteredStream == 0)
+        return SZ_ERROR_MEM;
+      memcpy(filteredStream, src, srcLen);
+    }
+    {
+      UInt32 x86State;
+      x86_Convert_Init(x86State);
+      x86_Convert(filteredStream, srcLen, 0, &x86State, 1);
+    }
+  }
+
+  {
+    size_t minSize = 0;
+    BoolInt bestIsFiltered = False;
+
+    /* passes for SZ_FILTER_AUTO:
+        0 - BCJ + LZMA
+        1 - LZMA
+        2 - BCJ + LZMA agaian, if pass 0 (BCJ + LZMA) is better.
+    */
+    int numPasses = (filterMode == SZ_FILTER_AUTO) ? 3 : 1;
+
+    int i;
+    for (i = 0; i < numPasses; i++)
+    {
+      size_t outSizeProcessed = outSize2 - LZMA86_HEADER_SIZE;
+      size_t outPropsSize = 5;
+      SRes curRes;
+      BoolInt curModeIsFiltered = (numPasses > 1 && i == numPasses - 1);
+      if (curModeIsFiltered && !bestIsFiltered)
+        break;
+      if (useFilter && i == 0)
+        curModeIsFiltered = True;
+      
+      curRes = LzmaEncode(dest + LZMA86_HEADER_SIZE, &outSizeProcessed,
+          curModeIsFiltered ? filteredStream : src, srcLen,
+          &props, dest + 1, &outPropsSize, 0,
+          NULL, &g_Alloc, &g_Alloc);
+      
+      if (curRes != SZ_ERROR_OUTPUT_EOF)
+      {
+        if (curRes != SZ_OK)
+        {
+          mainResult = curRes;
+          break;
+        }
+        if (outSizeProcessed <= minSize || mainResult != SZ_OK)
+        {
+          minSize = outSizeProcessed;
+          bestIsFiltered = curModeIsFiltered;
+          mainResult = SZ_OK;
+        }
+      }
+    }
+    dest[0] = (Byte)(bestIsFiltered ? 1 : 0);
+    *destLen = LZMA86_HEADER_SIZE + minSize;
+  }
+  if (useFilter)
+    MyFree(filteredStream);
+  return mainResult;
+}

dep/lzma/src/LzmaLib.c

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

dep/lzma/src/Sort.c

@@ -0,0 +1,141 @@
+/* Sort.c -- Sort functions
+2014-04-05 : Igor Pavlov : Public domain */
+
+#include "Precomp.h"
+
+#include "Sort.h"
+
+#define HeapSortDown(p, k, size, temp) \
+  { for (;;) { \
+    size_t s = (k << 1); \
+    if (s > size) break; \
+    if (s < size && p[s + 1] > p[s]) s++; \
+    if (temp >= p[s]) break; \
+    p[k] = p[s]; k = s; \
+  } p[k] = temp; }
+
+void HeapSort(UInt32 *p, size_t size)
+{
+  if (size <= 1)
+    return;
+  p--;
+  {
+    size_t i = size / 2;
+    do
+    {
+      UInt32 temp = p[i];
+      size_t k = i;
+      HeapSortDown(p, k, size, temp)
+    }
+    while (--i != 0);
+  }
+  /*
+  do
+  {
+    size_t k = 1;
+    UInt32 temp = p[size];
+    p[size--] = p[1];
+    HeapSortDown(p, k, size, temp)
+  }
+  while (size > 1);
+  */
+  while (size > 3)
+  {
+    UInt32 temp = p[size];
+    size_t k = (p[3] > p[2]) ? 3 : 2;
+    p[size--] = p[1];
+    p[1] = p[k];
+    HeapSortDown(p, k, size, temp)
+  }
+  {
+    UInt32 temp = p[size];
+    p[size] = p[1];
+    if (size > 2 && p[2] < temp)
+    {
+      p[1] = p[2];
+      p[2] = temp;
+    }
+    else
+      p[1] = temp;
+  }
+}
+
+void HeapSort64(UInt64 *p, size_t size)
+{
+  if (size <= 1)
+    return;
+  p--;
+  {
+    size_t i = size / 2;
+    do
+    {
+      UInt64 temp = p[i];
+      size_t k = i;
+      HeapSortDown(p, k, size, temp)
+    }
+    while (--i != 0);
+  }
+  /*
+  do
+  {
+    size_t k = 1;
+    UInt64 temp = p[size];
+    p[size--] = p[1];
+    HeapSortDown(p, k, size, temp)
+  }
+  while (size > 1);
+  */
+  while (size > 3)
+  {
+    UInt64 temp = p[size];
+    size_t k = (p[3] > p[2]) ? 3 : 2;
+    p[size--] = p[1];
+    p[1] = p[k];
+    HeapSortDown(p, k, size, temp)
+  }
+  {
+    UInt64 temp = p[size];
+    p[size] = p[1];
+    if (size > 2 && p[2] < temp)
+    {
+      p[1] = p[2];
+      p[2] = temp;
+    }
+    else
+      p[1] = temp;
+  }
+}
+
+/*
+#define HeapSortRefDown(p, vals, n, size, temp) \
+  { size_t k = n; UInt32 val = vals[temp]; for (;;) { \
+    size_t s = (k << 1); \
+    if (s > size) break; \
+    if (s < size && vals[p[s + 1]] > vals[p[s]]) s++; \
+    if (val >= vals[p[s]]) break; \
+    p[k] = p[s]; k = s; \
+  } p[k] = temp; }
+
+void HeapSortRef(UInt32 *p, UInt32 *vals, size_t size)
+{
+  if (size <= 1)
+    return;
+  p--;
+  {
+    size_t i = size / 2;
+    do
+    {
+      UInt32 temp = p[i];
+      HeapSortRefDown(p, vals, i, size, temp);
+    }
+    while (--i != 0);
+  }
+  do
+  {
+    UInt32 temp = p[size];
+    p[size--] = p[1];
+    HeapSortRefDown(p, vals, 1, size, temp);
+  }
+  while (size > 1);
+}
+*/