Upgrade LZ4, remove extraneous files, put tap-mac into ext/ to declutter root.

1 files changed, 403 insertions, 487 deletions

diff --git a/ext/lz4/lz4.c b/ext/lz4/lz4.c
index 1f2eafde..5668521f 100644
--- a/ext/lz4/lz4.c
+++ b/ext/lz4/lz4.c
@@ -1,6 +1,6 @@
 /*

    LZ4 - Fast LZ compression algorithm

-   Copyright (C) 2011-2012, Yann Collet.

+   Copyright (C) 2011-2013, Yann Collet.

    BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)

 

    Redistribution and use in source and binary forms, with or without

@@ -27,8 +27,8 @@
    OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

 

    You can contact the author at :

-   - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html

    - LZ4 source repository : http://code.google.com/p/lz4/

+   - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c

 */

 

 //**************************************

@@ -41,19 +41,20 @@
 // Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache

 #define MEMORY_USAGE 14

 

-// BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE :

-// This will provide a small boost to performance for big endian cpu, but the resulting compressed stream will be incompatible with little-endian CPU.

-// You can set this option to 1 in situations where data will remain within closed environment

-// This option is useless on Little_Endian CPU (such as x86)

-//#define BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE 1

-

+// HEAPMODE :

+// Select how default compression functions will allocate memory for their hash table,

+// in memory stack (0:default, fastest), or in memory heap (1:requires memory allocation (malloc)).

+#define HEAPMODE 0

 

 

 //**************************************

 // CPU Feature Detection

 //**************************************

 // 32 or 64 bits ?

-#if (defined(__x86_64__) || defined(__x86_64) || defined(__amd64__) || defined(__amd64) || defined(__ppc64__) || defined(_WIN64) || defined(__LP64__) || defined(_LP64) )   // Detects 64 bits mode

+#if (defined(__x86_64__) || defined(_M_X64) || defined(_WIN64) \

+  || defined(__powerpc64__) || defined(__ppc64__) || defined(__PPC64__) \

+  || defined(__64BIT__) || defined(_LP64) || defined(__LP64__) \

+  || defined(__ia64) || defined(__itanium__) || defined(_M_IA64) )   // Detects 64 bits mode

 #  define LZ4_ARCH64 1

 #else

 #  define LZ4_ARCH64 0

@@ -69,7 +70,7 @@
 #elif (defined(__BIG_ENDIAN__) || defined(__BIG_ENDIAN) || defined(_BIG_ENDIAN)) && !(defined(__LITTLE_ENDIAN__) || defined(__LITTLE_ENDIAN) || defined(_LITTLE_ENDIAN))

 #  define LZ4_BIG_ENDIAN 1

 #elif defined(__sparc) || defined(__sparc__) \

-   || defined(__ppc__) || defined(_POWER) || defined(__powerpc__) || defined(_ARCH_PPC) || defined(__PPC__) || defined(__PPC) || defined(PPC) || defined(__powerpc__) || defined(__powerpc) || defined(powerpc) \

+   || defined(__powerpc__) || defined(__ppc__) || defined(__PPC__) \

    || defined(__hpux)  || defined(__hppa) \

    || defined(_MIPSEB) || defined(__s390__)

 #  define LZ4_BIG_ENDIAN 1

@@ -78,7 +79,7 @@
 #endif

 

 // Unaligned memory access is automatically enabled for "common" CPU, such as x86.

-// For others CPU, the compiler will be more cautious, and insert extra code to ensure aligned access is respected

+// For others CPU, such as ARM, the compiler may be more cautious, inserting unnecessary extra code to ensure aligned access property

 // If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance

 #if defined(__ARM_FEATURE_UNALIGNED)

 #  define LZ4_FORCE_UNALIGNED_ACCESS 1

@@ -89,27 +90,39 @@
 #  define LZ4_FORCE_SW_BITCOUNT

 #endif

 

+// BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE :

+// This option may provide a small boost to performance for some big endian cpu, although probably modest.

+// You may set this option to 1 if data will remain within closed environment.

+// This option is useless on Little_Endian CPU (such as x86)

+//#define BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE 1

+

 

 //**************************************

 // Compiler Options

 //**************************************

-#if __STDC_VERSION__ >= 199901L   // C99

+#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)   // C99

 /* "restrict" is a known keyword */

 #else

 #  define restrict // Disable restrict

 #endif

 

-#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)

-

-#ifdef _MSC_VER  // Visual Studio

-#  include <intrin.h>   // For Visual 2005

-#  if LZ4_ARCH64	// 64-bit

+#ifdef _MSC_VER    // Visual Studio

+#  define FORCE_INLINE static __forceinline

+#  include <intrin.h>                    // For Visual 2005

+#  if LZ4_ARCH64   // 64-bits

 #    pragma intrinsic(_BitScanForward64) // For Visual 2005

 #    pragma intrinsic(_BitScanReverse64) // For Visual 2005

-#  else

+#  else            // 32-bits

 #    pragma intrinsic(_BitScanForward)   // For Visual 2005

 #    pragma intrinsic(_BitScanReverse)   // For Visual 2005

 #  endif

+#  pragma warning(disable : 4127)        // disable: C4127: conditional expression is constant

+#else 

+#  ifdef __GNUC__

+#    define FORCE_INLINE static inline __attribute__((always_inline))

+#  else

+#    define FORCE_INLINE static inline

+#  endif

 #endif

 

 #ifdef _MSC_VER

@@ -118,6 +131,8 @@
 #  define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8)))

 #endif

 

+#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)

+

 #if (GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__)

 #  define expect(expr,value)    (__builtin_expect ((expr),(value)) )

 #else

@@ -129,71 +144,88 @@
 

 

 //**************************************

+// Memory routines

+//**************************************

+#include <stdlib.h>   // malloc, calloc, free

+#define ALLOCATOR(n,s) calloc(n,s)

+#define FREEMEM        free

+#include <string.h>   // memset, memcpy

+#define MEM_INIT       memset

+

+

+//**************************************

 // Includes

 //**************************************

-#include <stdlib.h>   // for malloc

-#include <string.h>   // for memset

 #include "lz4.h"

 

 

 //**************************************

 // Basic Types

 //**************************************

-#if defined(_MSC_VER)    // Visual Studio does not support 'stdint' natively

-#  define BYTE	unsigned __int8

-#  define U16		unsigned __int16

-#  define U32		unsigned __int32

-#  define S32		__int32

-#  define U64		unsigned __int64

+#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   // C99

+# include <stdint.h>

+  typedef  uint8_t BYTE;

+  typedef uint16_t U16;

+  typedef uint32_t U32;

+  typedef  int32_t S32;

+  typedef uint64_t U64;

 #else

-#  include <stdint.h>

-#  define BYTE	uint8_t

-#  define U16		uint16_t

-#  define U32		uint32_t

-#  define S32		int32_t

-#  define U64		uint64_t

+  typedef unsigned char       BYTE;

+  typedef unsigned short      U16;

+  typedef unsigned int        U32;

+  typedef   signed int        S32;

+  typedef unsigned long long  U64;

 #endif

 

-#ifndef LZ4_FORCE_UNALIGNED_ACCESS

-#  pragma pack(push, 1)

+#if defined(__GNUC__)  && !defined(LZ4_FORCE_UNALIGNED_ACCESS)

+#  define _PACKED __attribute__ ((packed))

+#else

+#  define _PACKED

+#endif

+

+#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__)

+#  if defined(__IBMC__) || defined(__SUNPRO_C) || defined(__SUNPRO_CC)

+#    pragma pack(1)

+#  else

+#    pragma pack(push, 1)

+#  endif

 #endif

 

-typedef struct _U16_S { U16 v; } U16_S;

-typedef struct _U32_S { U32 v; } U32_S;

-typedef struct _U64_S { U64 v; } U64_S;

+typedef struct { U16 v; }  _PACKED U16_S;

+typedef struct { U32 v; }  _PACKED U32_S;

+typedef struct { U64 v; }  _PACKED U64_S;

+typedef struct {size_t v;} _PACKED size_t_S;

 

-#ifndef LZ4_FORCE_UNALIGNED_ACCESS

-#  pragma pack(pop)

+#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__)

+#  if defined(__SUNPRO_C) || defined(__SUNPRO_CC)

+#    pragma pack(0)

+#  else

+#    pragma pack(pop)

+#  endif

 #endif

 

-#define A64(x) (((U64_S *)(x))->v)

-#define A32(x) (((U32_S *)(x))->v)

-#define A16(x) (((U16_S *)(x))->v)

+#define A16(x)   (((U16_S *)(x))->v)

+#define A32(x)   (((U32_S *)(x))->v)

+#define A64(x)   (((U64_S *)(x))->v)

+#define AARCH(x) (((size_t_S *)(x))->v)

 

 

 //**************************************

 // Constants

 //**************************************

+#define LZ4_HASHLOG   (MEMORY_USAGE-2)

+#define HASHTABLESIZE (1 << MEMORY_USAGE)

+#define HASHNBCELLS4  (1 << LZ4_HASHLOG)

+

 #define MINMATCH 4

 

-#define HASH_LOG (MEMORY_USAGE-2)

-#define HASHTABLESIZE (1 << HASH_LOG)

-#define HASH_MASK (HASHTABLESIZE - 1)

-

-// NOTCOMPRESSIBLE_DETECTIONLEVEL :

-// Decreasing this value will make the algorithm skip faster data segments considered "incompressible"

-// This may decrease compression ratio dramatically, but will be faster on incompressible data

-// Increasing this value will make the algorithm search more before declaring a segment "incompressible"

-// This could improve compression a bit, but will be slower on incompressible data

-// The default value (6) is recommended

-#define NOTCOMPRESSIBLE_DETECTIONLEVEL 6

-#define SKIPSTRENGTH (NOTCOMPRESSIBLE_DETECTIONLEVEL>2?NOTCOMPRESSIBLE_DETECTIONLEVEL:2)

-#define STACKLIMIT 13

-#define HEAPMODE (HASH_LOG>STACKLIMIT)  // Defines if memory is allocated into the stack (local variable), or into the heap (malloc()).

 #define COPYLENGTH 8

 #define LASTLITERALS 5

 #define MFLIMIT (COPYLENGTH+MINMATCH)

-#define MINLENGTH (MFLIMIT+1)

+const int LZ4_minLength = (MFLIMIT+1);

+

+#define LZ4_64KLIMIT ((1<<16) + (MFLIMIT-1))

+#define SKIPSTRENGTH 6     // Increasing this value will make the compression run slower on incompressible data

 

 #define MAXD_LOG 16

 #define MAX_DISTANCE ((1 << MAXD_LOG) - 1)

@@ -203,26 +235,43 @@ typedef struct _U64_S { U64 v; } U64_S;
 #define RUN_BITS (8-ML_BITS)

 #define RUN_MASK ((1U<<RUN_BITS)-1)

 

+#define KB *(1U<<10)

+#define MB *(1U<<20)

+#define GB *(1U<<30)

+

+

+//**************************************

+// Structures and local types

+//**************************************

+

+typedef struct {

+    U32 hashTable[HASHNBCELLS4];

+    const BYTE* bufferStart;

+    const BYTE* base;

+    const BYTE* nextBlock;

+} LZ4_Data_Structure;

+

+typedef enum { notLimited = 0, limited = 1 } limitedOutput_directive;

+typedef enum { byPtr, byU32, byU16 } tableType_t;

+

+typedef enum { noPrefix = 0, withPrefix = 1 } prefix64k_directive;

+

+typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;

+typedef enum { full = 0, partial = 1 } earlyEnd_directive;

+

 

 //**************************************

 // Architecture-specific macros

 //**************************************

-#if LZ4_ARCH64	// 64-bit

-#  define STEPSIZE 8

-#  define UARCH U64

-#  define AARCH A64

-#  define LZ4_COPYSTEP(s,d)       A64(d) = A64(s); d+=8; s+=8;

-#  define LZ4_COPYPACKET(s,d)     LZ4_COPYSTEP(s,d)

-#  define LZ4_SECURECOPY(s,d,e)   if (d<e) LZ4_WILDCOPY(s,d,e)

+#define STEPSIZE                  sizeof(size_t)

+#define LZ4_COPYSTEP(d,s)         { AARCH(d) = AARCH(s); d+=STEPSIZE; s+=STEPSIZE; }

+#define LZ4_COPY8(d,s)            { LZ4_COPYSTEP(d,s); if (STEPSIZE<8) LZ4_COPYSTEP(d,s); }

+#define LZ4_SECURECOPY(d,s,e)     { if ((STEPSIZE==4)||(d<e)) LZ4_WILDCOPY(d,s,e); }

+

+#if LZ4_ARCH64   // 64-bit

 #  define HTYPE                   U32

 #  define INITBASE(base)          const BYTE* const base = ip

-#else		// 32-bit

-#  define STEPSIZE 4

-#  define UARCH U32

-#  define AARCH A32

-#  define LZ4_COPYSTEP(s,d)       A32(d) = A32(s); d+=4; s+=4;

-#  define LZ4_COPYPACKET(s,d)     LZ4_COPYSTEP(s,d); LZ4_COPYSTEP(s,d);

-#  define LZ4_SECURECOPY          LZ4_WILDCOPY

+#else            // 32-bit

 #  define HTYPE                   const BYTE*

 #  define INITBASE(base)          const int base = 0

 #endif

@@ -230,28 +279,16 @@ typedef struct _U64_S { U64 v; } U64_S;
 #if (defined(LZ4_BIG_ENDIAN) && !defined(BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE))

 #  define LZ4_READ_LITTLEENDIAN_16(d,s,p) { U16 v = A16(p); v = lz4_bswap16(v); d = (s) - v; }

 #  define LZ4_WRITE_LITTLEENDIAN_16(p,i)  { U16 v = (U16)(i); v = lz4_bswap16(v); A16(p) = v; p+=2; }

-#else		// Little Endian

+#else      // Little Endian

 #  define LZ4_READ_LITTLEENDIAN_16(d,s,p) { d = (s) - A16(p); }

 #  define LZ4_WRITE_LITTLEENDIAN_16(p,v)  { A16(p) = v; p+=2; }

 #endif

 

 

 //**************************************

-// Local structures

-//**************************************

-struct refTables

-{

-    HTYPE hashTable[HASHTABLESIZE];

-};

-

-

-//**************************************

 // Macros

 //**************************************

-#define LZ4_HASH_FUNCTION(i)	(((i) * 2654435761U) >> ((MINMATCH*8)-HASH_LOG))

-#define LZ4_HASH_VALUE(p)		LZ4_HASH_FUNCTION(A32(p))

-#define LZ4_WILDCOPY(s,d,e)		do { LZ4_COPYPACKET(s,d) } while (d<e);

-#define LZ4_BLINDCOPY(s,d,l)	{ BYTE* e=(d)+l; LZ4_WILDCOPY(s,d,e); d=e; }

+#define LZ4_WILDCOPY(d,s,e)     { do { LZ4_COPY8(d,s) } while (d<e); }           // at the end, d>=e;

 

 

 //****************************

@@ -259,100 +296,131 @@ struct refTables
 //****************************

 #if LZ4_ARCH64

 

-static inline int LZ4_NbCommonBytes (register U64 val)

+FORCE_INLINE int LZ4_NbCommonBytes (register U64 val)

 {

-#if defined(LZ4_BIG_ENDIAN)

-    #if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)

+# if defined(LZ4_BIG_ENDIAN)

+#   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)

     unsigned long r = 0;

     _BitScanReverse64( &r, val );

     return (int)(r>>3);

-    #elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)

+#   elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)

     return (__builtin_clzll(val) >> 3);

-    #else

+#   else

     int r;

     if (!(val>>32)) { r=4; } else { r=0; val>>=32; }

     if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }

     r += (!val);

     return r;

-    #endif

-#else

-    #if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)

+#   endif

+# else

+#   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)

     unsigned long r = 0;

     _BitScanForward64( &r, val );

     return (int)(r>>3);

-    #elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)

+#   elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)

     return (__builtin_ctzll(val) >> 3);

-    #else

+#   else

     static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 };

-    return DeBruijnBytePos[((U64)((val & -val) * 0x0218A392CDABBD3F)) >> 58];

-    #endif

-#endif

+    return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];

+#   endif

+# endif

 }

 

 #else

 

-static inline int LZ4_NbCommonBytes (register U32 val)

+FORCE_INLINE int LZ4_NbCommonBytes (register U32 val)

 {

-#if defined(LZ4_BIG_ENDIAN)

-    #if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)

+# if defined(LZ4_BIG_ENDIAN)

+#   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)

     unsigned long r = 0;

     _BitScanReverse( &r, val );

     return (int)(r>>3);

-    #elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)

+#   elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)

     return (__builtin_clz(val) >> 3);

-    #else

+#   else

     int r;

     if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }

     r += (!val);

     return r;

-    #endif

-#else

-    #if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)

+#   endif

+# else

+#   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)

     unsigned long r;

     _BitScanForward( &r, val );

     return (int)(r>>3);

-    #elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)

+#   elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)

     return (__builtin_ctz(val) >> 3);

-    #else

+#   else

     static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 };

     return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];

-    #endif

-#endif

+#   endif

+# endif

 }

 

 #endif

 

 

-

-//******************************

+//****************************

 // Compression functions

-//******************************

+//****************************

+FORCE_INLINE int LZ4_hashSequence(U32 sequence, tableType_t tableType)

+{

+    if (tableType == byU16)

+        return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));

+    else

+        return (((sequence) * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));

+}

 

-// LZ4_compressCtx :

-// -----------------

-// Compress 'isize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'.

-// If it cannot achieve it, compression will stop, and result of the function will be zero.

-// return : the number of bytes written in buffer 'dest', or 0 if the compression fails

+FORCE_INLINE int LZ4_hashPosition(const BYTE* p, tableType_t tableType) { return LZ4_hashSequence(A32(p), tableType); }

 

-static inline int LZ4_compressCtx(void** ctx,

+FORCE_INLINE void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase)

+{

+    switch (tableType)

+    {

+    case byPtr: { const BYTE** hashTable = (const BYTE**) tableBase; hashTable[h] = p; break; }

+    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); break; }

+    case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); break; }

+    }

+}

+

+FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)

+{

+    U32 h = LZ4_hashPosition(p, tableType);

+    LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);

+}

+

+FORCE_INLINE const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase)

+{

+    if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; }

+    if (tableType == byU32) { U32* hashTable = (U32*) tableBase; return hashTable[h] + srcBase; }

+    { U16* hashTable = (U16*) tableBase; return hashTable[h] + srcBase; }   // default, to ensure a return

+}

+

+FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)

+{

+    U32 h = LZ4_hashPosition(p, tableType);

+    return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);

+}

+

+

+FORCE_INLINE int LZ4_compress_generic(

+                 void* ctx,

                  const char* source,

                  char* dest,

-                 int isize,

-                 int maxOutputSize)

-{

-#if HEAPMODE

-    struct refTables *srt = (struct refTables *) (*ctx);

-    HTYPE* HashTable;

-#else

-    HTYPE HashTable[HASHTABLESIZE] = {0};

-#endif

+                 int inputSize,

+                 int maxOutputSize,

 

-    const BYTE* ip = (BYTE*) source;

-    INITBASE(base);

-    const BYTE* anchor = ip;

-    const BYTE* const iend = ip + isize;

+                 limitedOutput_directive limitedOutput,

+                 tableType_t tableType,

+                 prefix64k_directive prefix)

+{

+    const BYTE* ip = (const BYTE*) source;

+    const BYTE* const base = (prefix==withPrefix) ? ((LZ4_Data_Structure*)ctx)->base : (const BYTE*) source;

+    const BYTE* const lowLimit = ((prefix==withPrefix) ? ((LZ4_Data_Structure*)ctx)->bufferStart : (const BYTE*)source);

+    const BYTE* anchor = (const BYTE*) source;

+    const BYTE* const iend = ip + inputSize;

     const BYTE* const mflimit = iend - MFLIMIT;

-#define matchlimit (iend - LASTLITERALS)

+    const BYTE* const matchlimit = iend - LASTLITERALS;

 

     BYTE* op = (BYTE*) dest;

     BYTE* const oend = op + maxOutputSize;

@@ -361,25 +429,16 @@ static inline int LZ4_compressCtx(void** ctx,
     const int skipStrength = SKIPSTRENGTH;

     U32 forwardH;

 

-

-    // Init

-    if (isize<MINLENGTH) goto _last_literals;

-#if HEAPMODE

-    if (*ctx == NULL)

-    {

-        srt = (struct refTables *) malloc ( sizeof(struct refTables) );

-        *ctx = (void*) srt;

-    }

-    HashTable = (HTYPE*)(srt->hashTable);

-    memset((void*)HashTable, 0, sizeof(srt->hashTable));

-#else

-    (void) ctx;

-#endif

-

+    // Init conditions

+    if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0;                                // Unsupported input size, too large (or negative)

+    if ((prefix==withPrefix) && (ip != ((LZ4_Data_Structure*)ctx)->nextBlock)) return 0;   // must continue from end of previous block

+    if (prefix==withPrefix) ((LZ4_Data_Structure*)ctx)->nextBlock=iend;                    // do it now, due to potential early exit

+    if ((tableType == byU16) && (inputSize>=LZ4_64KLIMIT)) return 0;                       // Size too large (not within 64K limit)

+    if (inputSize<LZ4_minLength) goto _last_literals;                                      // Input too small, no compression (all literals)

 

     // First Byte

-    HashTable[LZ4_HASH_VALUE(ip)] = ip - base;

-    ip++; forwardH = LZ4_HASH_VALUE(ip);

+    LZ4_putPosition(ip, ctx, tableType, base);

+    ip++; forwardH = LZ4_hashPosition(ip, tableType);

 

     // Main Loop

     for ( ; ; )

@@ -398,50 +457,30 @@ static inline int LZ4_compressCtx(void** ctx,
 

             if unlikely(forwardIp > mflimit) { goto _last_literals; }

 

-            forwardH = LZ4_HASH_VALUE(forwardIp);

-            ref = base + HashTable[h];

-            HashTable[h] = ip - base;

+            forwardH = LZ4_hashPosition(forwardIp, tableType);

+            ref = LZ4_getPositionOnHash(h, ctx, tableType, base);

+            LZ4_putPositionOnHash(ip, h, ctx, tableType, base);

 

-        } while ((ref < ip - MAX_DISTANCE) || (A32(ref) != A32(ip)));

+        } while ((ref + MAX_DISTANCE < ip) || (A32(ref) != A32(ip)));

 

         // Catch up

-        while ((ip>anchor) && (ref>(BYTE*)source) && unlikely(ip[-1]==ref[-1])) { ip--; ref--; }

+        while ((ip>anchor) && (ref > lowLimit) && unlikely(ip[-1]==ref[-1])) { ip--; ref--; }

 

         // Encode Literal length

         length = (int)(ip - anchor);

         token = op++;

-        if unlikely(op + length + (2 + 1 + LASTLITERALS) + (length>>8) > oend) return 0; 		// Check output limit

-#ifdef _MSC_VER

+        if ((limitedOutput) && unlikely(op + length + (2 + 1 + LASTLITERALS) + (length>>8) > oend)) return 0;   // Check output limit

         if (length>=(int)RUN_MASK) 

         { 

             int len = length-RUN_MASK; 

             *token=(RUN_MASK<<ML_BITS); 

-            if (len>254)

-            {

-                do { *op++ = 255; len -= 255; } while (len>254);

-                *op++ = (BYTE)len; 

-                memcpy(op, anchor, length);

-                op += length;

-                goto _next_match;

-            }

-            else

+            for(; len >= 255 ; len-=255) *op++ = 255; 

             *op++ = (BYTE)len; 

         }

-        else *token = (length<<ML_BITS);

-#else

-        if (length>=(int)RUN_MASK) 

-        { 

-            int len;

-            *token=(RUN_MASK<<ML_BITS); 

-            len = length-RUN_MASK; 

-            for(; len > 254 ; len-=255) *op++ = 255; 

-            *op++ = (BYTE)len; 

-        }

-        else *token = (length<<ML_BITS);

-#endif

+        else *token = (BYTE)(length<<ML_BITS);

 

         // Copy Literals

-        LZ4_BLINDCOPY(anchor, op, length);

+        { BYTE* end=(op)+(length); LZ4_WILDCOPY(op,anchor,end); op=end; }

 

 _next_match:

         // Encode Offset

@@ -452,7 +491,7 @@ _next_match:
         anchor = ip;

         while likely(ip<matchlimit-(STEPSIZE-1))

         {

-            UARCH diff = AARCH(ref) ^ AARCH(ip);

+            size_t diff = AARCH(ref) ^ AARCH(ip);

             if (!diff) { ip+=STEPSIZE; ref+=STEPSIZE; continue; }

             ip += LZ4_NbCommonBytes(diff);

             goto _endCount;

@@ -464,40 +503,40 @@ _endCount:
 

         // Encode MatchLength

         length = (int)(ip - anchor);

-        if unlikely(op + (1 + LASTLITERALS) + (length>>8) > oend) return 0; 		// Check output limit

+        if ((limitedOutput) && unlikely(op + (1 + LASTLITERALS) + (length>>8) > oend)) return 0;    // Check output limit

         if (length>=(int)ML_MASK) 

         { 

             *token += ML_MASK; 

             length -= ML_MASK; 

             for (; length > 509 ; length-=510) { *op++ = 255; *op++ = 255; } 

-            if (length > 254) { length-=255; *op++ = 255; } 

+            if (length >= 255) { length-=255; *op++ = 255; } 

             *op++ = (BYTE)length; 

         }

-        else *token += length;

+        else *token += (BYTE)(length);

 

         // Test end of chunk

         if (ip > mflimit) { anchor = ip;  break; }

 

         // Fill table

-        HashTable[LZ4_HASH_VALUE(ip-2)] = ip - 2 - base;

+        LZ4_putPosition(ip-2, ctx, tableType, base);

 

         // Test next position

-        ref = base + HashTable[LZ4_HASH_VALUE(ip)];

-        HashTable[LZ4_HASH_VALUE(ip)] = ip - base;

-        if ((ref > ip - (MAX_DISTANCE + 1)) && (A32(ref) == A32(ip))) { token = op++; *token=0; goto _next_match; }

+        ref = LZ4_getPosition(ip, ctx, tableType, base); 

+        LZ4_putPosition(ip, ctx, tableType, base);

+        if ((ref + MAX_DISTANCE >= ip) && (A32(ref) == A32(ip))) { token = op++; *token=0; goto _next_match; }

 

         // Prepare next loop

         anchor = ip++;

-        forwardH = LZ4_HASH_VALUE(ip);

+        forwardH = LZ4_hashPosition(ip, tableType);

     }

 

 _last_literals:

     // Encode Last Literals

     {

         int lastRun = (int)(iend - anchor);

-        if (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) return 0;

-        if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun > 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }

-        else *op++ = (lastRun<<ML_BITS);

+        if ((limitedOutput) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize)) return 0;  // Check output limit

+        if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun >= 255 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }

+        else *op++ = (BYTE)(lastRun<<ML_BITS);

         memcpy(op, anchor, iend - anchor);

         op += iend-anchor;

     }

@@ -507,372 +546,217 @@ _last_literals:
 }

 

 

-

-// Note : this function is valid only if isize < LZ4_64KLIMIT

-#define LZ4_64KLIMIT ((1<<16) + (MFLIMIT-1))

-#define HASHLOG64K (HASH_LOG+1)

-#define HASH64KTABLESIZE (1U<<HASHLOG64K)

-#define LZ4_HASH64K_FUNCTION(i)	(((i) * 2654435761U) >> ((MINMATCH*8)-HASHLOG64K))

-#define LZ4_HASH64K_VALUE(p)	LZ4_HASH64K_FUNCTION(A32(p))

-static inline int LZ4_compress64kCtx(void** ctx,

-                 const char* source,

-                 char* dest,

-                 int isize,

-                 int maxOutputSize)

+int LZ4_compress(const char* source, char* dest, int inputSize)

 {

-#if HEAPMODE

-    struct refTables *srt = (struct refTables *) (*ctx);

-    U16* HashTable;

+#if (HEAPMODE)

+    void* ctx = ALLOCATOR(HASHNBCELLS4, 4);   // Aligned on 4-bytes boundaries

 #else

-    U16 HashTable[HASH64KTABLESIZE] = {0};

+    U32 ctx[1U<<(MEMORY_USAGE-2)] = {0};           // Ensure data is aligned on 4-bytes boundaries

 #endif

+    int result;

 

-    const BYTE* ip = (BYTE*) source;

-    const BYTE* anchor = ip;

-    const BYTE* const base = ip;

-    const BYTE* const iend = ip + isize;

-    const BYTE* const mflimit = iend - MFLIMIT;

-#define matchlimit (iend - LASTLITERALS)

-

-    BYTE* op = (BYTE*) dest;

-    BYTE* const oend = op + maxOutputSize;

-

-    int len, length;

-    const int skipStrength = SKIPSTRENGTH;

-    U32 forwardH;

-

+    if (inputSize < (int)LZ4_64KLIMIT)

+        result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, byU16, noPrefix);

+    else

+        result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noPrefix);

 

-    // Init

-    if (isize<MINLENGTH) goto _last_literals;

-#if HEAPMODE

-    if (*ctx == NULL)

-    {

-        srt = (struct refTables *) malloc ( sizeof(struct refTables) );

-        *ctx = (void*) srt;

-    }

-    HashTable = (U16*)(srt->hashTable);

-    memset((void*)HashTable, 0, sizeof(srt->hashTable));

-#else

-    (void) ctx;

+#if (HEAPMODE)

+    FREEMEM(ctx);

 #endif

+    return result;

+}

 

+int LZ4_compress_continue (void* LZ4_Data, const char* source, char* dest, int inputSize)

+{

+    return LZ4_compress_generic(LZ4_Data, source, dest, inputSize, 0, notLimited, byU32, withPrefix);

+}

 

-    // First Byte

-    ip++; forwardH = LZ4_HASH64K_VALUE(ip);

-

-    // Main Loop

-    for ( ; ; )

-    {

-        int findMatchAttempts = (1U << skipStrength) + 3;

-        const BYTE* forwardIp = ip;

-        const BYTE* ref;

-        BYTE* token;

-

-        // Find a match

-        do {

-            U32 h = forwardH;

-            int step = findMatchAttempts++ >> skipStrength;

-            ip = forwardIp;

-            forwardIp = ip + step;

-

-            if (forwardIp > mflimit) { goto _last_literals; }

-

-            forwardH = LZ4_HASH64K_VALUE(forwardIp);

-            ref = base + HashTable[h];

-            HashTable[h] = (U16)(ip - base);

-

-        } while (A32(ref) != A32(ip));

-

-        // Catch up

-        while ((ip>anchor) && (ref>(BYTE*)source) && (ip[-1]==ref[-1])) { ip--; ref--; }

 

-        // Encode Literal length

-        length = (int)(ip - anchor);

-        token = op++;

-        if unlikely(op + length + (2 + 1 + LASTLITERALS) + (length>>8) > oend) return 0; 		// Check output limit

-#ifdef _MSC_VER

-        if (length>=(int)RUN_MASK) 

-        { 

-            int len = length-RUN_MASK; 

-            *token=(RUN_MASK<<ML_BITS); 

-            if (len>254)

-            {

-                do { *op++ = 255; len -= 255; } while (len>254);

-                *op++ = (BYTE)len; 

-                memcpy(op, anchor, length);

-                op += length;

-                goto _next_match;

-            }

-            else

-            *op++ = (BYTE)len; 

-        }

-        else *token = (length<<ML_BITS);

+int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize)

+{

+#if (HEAPMODE)

+    void* ctx = ALLOCATOR(HASHNBCELLS4, 4);   // Aligned on 4-bytes boundaries

 #else

-        if (length>=(int)RUN_MASK) { *token=(RUN_MASK<<ML_BITS); len = length-RUN_MASK; for(; len > 254 ; len-=255) *op++ = 255; *op++ = (BYTE)len; }

-        else *token = (length<<ML_BITS);

+    U32 ctx[1U<<(MEMORY_USAGE-2)] = {0};           // Ensure data is aligned on 4-bytes boundaries

 #endif

+    int result;

 

-        // Copy Literals

-        LZ4_BLINDCOPY(anchor, op, length);

-

-_next_match:

-        // Encode Offset

-        LZ4_WRITE_LITTLEENDIAN_16(op,(U16)(ip-ref));

-

-        // Start Counting

-        ip+=MINMATCH; ref+=MINMATCH;   // MinMatch verified

-        anchor = ip;

-        while (ip<matchlimit-(STEPSIZE-1))

-        {

-            UARCH diff = AARCH(ref) ^ AARCH(ip);

-            if (!diff) { ip+=STEPSIZE; ref+=STEPSIZE; continue; }

-            ip += LZ4_NbCommonBytes(diff);

-            goto _endCount;

-        }

-        if (LZ4_ARCH64) if ((ip<(matchlimit-3)) && (A32(ref) == A32(ip))) { ip+=4; ref+=4; }

-        if ((ip<(matchlimit-1)) && (A16(ref) == A16(ip))) { ip+=2; ref+=2; }

-        if ((ip<matchlimit) && (*ref == *ip)) ip++;

-_endCount:

-

-        // Encode MatchLength

-        len = (int)(ip - anchor);

-        if unlikely(op + (1 + LASTLITERALS) + (len>>8) > oend) return 0; 		// Check output limit

-        if (len>=(int)ML_MASK) { *token+=ML_MASK; len-=ML_MASK; for(; len > 509 ; len-=510) { *op++ = 255; *op++ = 255; } if (len > 254) { len-=255; *op++ = 255; } *op++ = (BYTE)len; }

-        else *token += len;

-

-        // Test end of chunk

-        if (ip > mflimit) { anchor = ip;  break; }

-

-        // Fill table

-        HashTable[LZ4_HASH64K_VALUE(ip-2)] = (U16)(ip - 2 - base);

-

-        // Test next position

-        ref = base + HashTable[LZ4_HASH64K_VALUE(ip)];

-        HashTable[LZ4_HASH64K_VALUE(ip)] = (U16)(ip - base);

-        if (A32(ref) == A32(ip)) { token = op++; *token=0; goto _next_match; }

-

-        // Prepare next loop

-        anchor = ip++;

-        forwardH = LZ4_HASH64K_VALUE(ip);

-    }

-

-_last_literals:

-    // Encode Last Literals

-    {

-        int lastRun = (int)(iend - anchor);

-        if (op + lastRun + 1 + (lastRun-RUN_MASK+255)/255 > oend) return 0;

-        if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun > 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }

-        else *op++ = (lastRun<<ML_BITS);

-        memcpy(op, anchor, iend - anchor);

-        op += iend-anchor;

-    }

-

-    // End

-    return (int) (((char*)op)-dest);

-}

-

+    if (inputSize < (int)LZ4_64KLIMIT)

+        result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limited, byU16, noPrefix);

+    else

+        result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limited, (sizeof(void*)==8) ? byU32 : byPtr, noPrefix);

 

-int LZ4_compress_limitedOutput(const char* source, 

-                               char* dest, 

-                               int isize, 

-                               int maxOutputSize)

-{

-#if HEAPMODE

-    void* ctx = malloc(sizeof(struct refTables));

-    int result;

-    if (isize < LZ4_64KLIMIT)

-        result = LZ4_compress64kCtx(&ctx, source, dest, isize, maxOutputSize);

-    else result = LZ4_compressCtx(&ctx, source, dest, isize, maxOutputSize);

-    free(ctx);

-    return result;

-#else

-    if (isize < (int)LZ4_64KLIMIT) return LZ4_compress64kCtx(NULL, source, dest, isize, maxOutputSize);

-    return LZ4_compressCtx(NULL, source, dest, isize, maxOutputSize);

+#if (HEAPMODE)

+    FREEMEM(ctx);

 #endif

+    return result;

 }

 

-

-int LZ4_compress(const char* source,

-                 char* dest,

-                 int isize)

+int LZ4_compress_limitedOutput_continue (void* LZ4_Data, const char* source, char* dest, int inputSize, int maxOutputSize)

 {

-    return LZ4_compress_limitedOutput(source, dest, isize, LZ4_compressBound(isize));

+    return LZ4_compress_generic(LZ4_Data, source, dest, inputSize, maxOutputSize, limited, byU32, withPrefix);

 }

 

 

-

-

 //****************************

-// Decompression functions

+// Stream functions

 //****************************

 

-// Note : The decoding functions LZ4_uncompress() and LZ4_uncompress_unknownOutputSize()

-//		are safe against "buffer overflow" attack type.

-//		They will never write nor read outside of the provided output buffers.

-//      LZ4_uncompress_unknownOutputSize() also insures that it will never read outside of the input buffer.

-//		A corrupted input will produce an error result, a negative int, indicating the position of the error within input stream.

-

-int LZ4_uncompress(const char* source,

-                 char* dest,

-                 int osize)

+FORCE_INLINE void LZ4_init(LZ4_Data_Structure* lz4ds, const BYTE* base)

 {

-    // Local Variables

-    const BYTE* restrict ip = (const BYTE*) source;

-    const BYTE* ref;

-

-    BYTE* op = (BYTE*) dest;

-    BYTE* const oend = op + osize;

-    BYTE* cpy;

-

-    unsigned token;

-

-    size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};

-#if LZ4_ARCH64

-    size_t dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};

-#endif

+    MEM_INIT(lz4ds->hashTable, 0, sizeof(lz4ds->hashTable));

+    lz4ds->bufferStart = base;

+    lz4ds->base = base;

+    lz4ds->nextBlock = base;

+}

 

 

-    // Main Loop

-    while (1)

-    {

-        size_t length;

+void* LZ4_create (const char* inputBuffer)

+{

+    void* lz4ds = ALLOCATOR(1, sizeof(LZ4_Data_Structure));

+    LZ4_init ((LZ4_Data_Structure*)lz4ds, (const BYTE*)inputBuffer);

+    return lz4ds;

+}

 

-        // get runlength

-        token = *ip++;

-        if ((length=(token>>ML_BITS)) == RUN_MASK)  { size_t len; for (;(len=*ip++)==255;length+=255){} length += len; }

 

-        // copy literals

-        cpy = op+length;

-        if (cpy>oend-COPYLENGTH)

-        {

-            if (cpy != oend) goto _output_error;         // Error : not enough place for another match (min 4) + 5 literals

-            memcpy(op, ip, length);

-            ip += length;

-            break;                                       // EOF

-        }

-        LZ4_WILDCOPY(ip, op, cpy); ip -= (op-cpy); op = cpy;

+int LZ4_free (void* LZ4_Data)

+{

+    FREEMEM(LZ4_Data);

+    return (0);

+}

 

-        // get offset

-        LZ4_READ_LITTLEENDIAN_16(ref,cpy,ip); ip+=2;

-        if unlikely(ref < (BYTE* const)dest) goto _output_error;   // Error : offset outside destination buffer

 

-        // get matchlength

-        if ((length=(token&ML_MASK)) == ML_MASK) { for (;*ip==255;length+=255) {ip++;} length += *ip++; }

+char* LZ4_slideInputBuffer (void* LZ4_Data)

+{

+    LZ4_Data_Structure* lz4ds = (LZ4_Data_Structure*)LZ4_Data;

+    size_t delta = lz4ds->nextBlock - (lz4ds->bufferStart + 64 KB);

 

-        // copy repeated sequence

-        if unlikely((op-ref)<STEPSIZE)

-        {

-#if LZ4_ARCH64

-            size_t dec64 = dec64table[op-ref];

-#else

-            const int dec64 = 0;

-#endif

-            op[0] = ref[0];

-            op[1] = ref[1];

-            op[2] = ref[2];

-            op[3] = ref[3];

-            op += 4, ref += 4; ref -= dec32table[op-ref];

-            A32(op) = A32(ref); 

-            op += STEPSIZE-4; ref -= dec64;

-        } else { LZ4_COPYSTEP(ref,op); }

-        cpy = op + length - (STEPSIZE-4);

+    if ( (lz4ds->base - delta > lz4ds->base)                          // underflow control

+       || ((size_t)(lz4ds->nextBlock - lz4ds->base) > 0xE0000000) )   // close to 32-bits limit

+    {

+        size_t deltaLimit = (lz4ds->nextBlock - 64 KB) - lz4ds->base;

+        int nH;

 

-        if unlikely(cpy>oend-(COPYLENGTH)-(STEPSIZE-4))

+        for (nH=0; nH < HASHNBCELLS4; nH++)

         {

-            if (cpy > oend-LASTLITERALS) goto _output_error;    // Error : last 5 bytes must be literals

-            LZ4_SECURECOPY(ref, op, (oend-COPYLENGTH));

-            while(op<cpy) *op++=*ref++;

-            op=cpy;

-            continue;

+            if ((size_t)(lz4ds->hashTable[nH]) < deltaLimit) lz4ds->hashTable[nH] = 0;

+            else lz4ds->hashTable[nH] -= (U32)deltaLimit;

         }

-        

-        LZ4_WILDCOPY(ref, op, cpy);

-        op=cpy;		// correction

+        memcpy((void*)(lz4ds->bufferStart), (const void*)(lz4ds->nextBlock - 64 KB), 64 KB);

+        lz4ds->base = lz4ds->bufferStart;

+        lz4ds->nextBlock = lz4ds->base + 64 KB;

     }

+    else

+    {

+		memcpy((void*)(lz4ds->bufferStart), (const void*)(lz4ds->nextBlock - 64 KB), 64 KB);

+		lz4ds->nextBlock -= delta;

+		lz4ds->base -= delta;

+	}

 

-    // end of decoding

-    return (int) (((char*)ip)-source);

-

-    // write overflow error detected

-_output_error:

-    return (int) (-(((char*)ip)-source));

+    return (char*)(lz4ds->nextBlock);

 }

 

 

-int LZ4_uncompress_unknownOutputSize(

-                const char* source,

-                char* dest,

-                int isize,

-                int maxOutputSize)

+//****************************

+// Decompression functions

+//****************************

+

+// This generic decompression function cover all use cases.

+// It shall be instanciated several times, using different sets of directives

+// Note that it is essential this generic function is really inlined, 

+// in order to remove useless branches during compilation optimisation.

+FORCE_INLINE int LZ4_decompress_generic(

+                 const char* source,

+                 char* dest,

+                 int inputSize,          //

+                 int outputSize,         // If endOnInput==endOnInputSize, this value is the max size of Output Buffer.

+

+                 int endOnInput,         // endOnOutputSize, endOnInputSize

+                 int prefix64k,          // noPrefix, withPrefix

+                 int partialDecoding,    // full, partial

+                 int targetOutputSize    // only used if partialDecoding==partial

+                 )

 {

     // Local Variables

     const BYTE* restrict ip = (const BYTE*) source;

-    const BYTE* const iend = ip + isize;

     const BYTE* ref;

+    const BYTE* const iend = ip + inputSize;

 

     BYTE* op = (BYTE*) dest;

-    BYTE* const oend = op + maxOutputSize;

+    BYTE* const oend = op + outputSize;

     BYTE* cpy;

+    BYTE* oexit = op + targetOutputSize;

 

-    size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};

-#if LZ4_ARCH64

-    size_t dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};

-#endif

+    const size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};   // static reduces speed for LZ4_decompress_safe() on GCC64

+    static const size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3};

 

 

-    // Special case

-    if unlikely(ip==iend) goto _output_error;    // A correctly formed null-compressed LZ4 must have at least one byte (token=0)

+    // Special cases

+    if ((partialDecoding) && (oexit> oend-MFLIMIT)) oexit = oend-MFLIMIT;                        // targetOutputSize too high => decode everything

+    if ((endOnInput) && unlikely(outputSize==0)) return ((inputSize==1) && (*ip==0)) ? 0 : -1;   // Empty output buffer

+    if ((!endOnInput) && unlikely(outputSize==0)) return (*ip==0?1:-1);

+

 

     // Main Loop

-    while (1) 

+    while (1)

     {

         unsigned token;

         size_t length;

 

         // get runlength

         token = *ip++;

-        if ((length=(token>>ML_BITS)) == RUN_MASK) 

+        if ((length=(token>>ML_BITS)) == RUN_MASK)

         { 

-            int s=255; 

-            while (likely(ip<iend) && (s==255)) { s=*ip++; length += s; } 

+            unsigned s=255; 

+            while (((endOnInput)?ip<iend:1) && (s==255))

+            { 

+                s = *ip++; 

+                length += s; 

+            } 

         }

 

         // copy literals

         cpy = op+length;

-        if ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS)))

+        if (((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) )

+            || ((!endOnInput) && (cpy>oend-COPYLENGTH)))

         {

-            if (cpy > oend) goto _output_error;          // Error : writes beyond output buffer

-            if (ip+length != iend) goto _output_error;   // Error : LZ4 format requires to consume all input at this stage (no match within the last 11 bytes, and at least 8 remaining input bytes for another match+literals)

+            if (partialDecoding)

+            {

+                if (cpy > oend) goto _output_error;                           // Error : write attempt beyond end of output buffer

+                if ((endOnInput) && (ip+length > iend)) goto _output_error;   // Error : read attempt beyond end of input buffer

+            }

+            else

+            {

+                if ((!endOnInput) && (cpy != oend)) goto _output_error;       // Error : block decoding must stop exactly there

+                if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error;   // Error : input must be consumed

+            }

             memcpy(op, ip, length);

+            ip += length;

             op += length;

             break;                                       // Necessarily EOF, due to parsing restrictions

         }

-        LZ4_WILDCOPY(ip, op, cpy); ip -= (op-cpy); op = cpy;

+        LZ4_WILDCOPY(op, ip, cpy); ip -= (op-cpy); op = cpy;

 

         // get offset

         LZ4_READ_LITTLEENDIAN_16(ref,cpy,ip); ip+=2;

-        if unlikely(ref < (BYTE* const)dest) goto _output_error;   // Error : offset outside of destination buffer

+        if ((prefix64k==noPrefix) && unlikely(ref < (BYTE* const)dest)) goto _output_error;   // Error : offset outside destination buffer

 

         // get matchlength

-        if ((length=(token&ML_MASK)) == ML_MASK)    

+        if ((length=(token&ML_MASK)) == ML_MASK) 

         { 

-            while likely(ip<iend-(LASTLITERALS+1))    // Error : a minimum input bytes must remain for LASTLITERALS + token

-            { 

-                int s = *ip++; 

-                length +=s; 

+            while ((!endOnInput) || (ip<iend-(LASTLITERALS+1)))   // Ensure enough bytes remain for LASTLITERALS + token

+            {

+                unsigned s = *ip++; 

+                length += s; 

                 if (s==255) continue; 

                 break; 

-            } 

+            }

         }

 

         // copy repeated sequence

-        if unlikely(op-ref<STEPSIZE)

+        if unlikely((op-ref)<(int)STEPSIZE)

         {

-#if LZ4_ARCH64

-            size_t dec64 = dec64table[op-ref];

-#else

-            const int dec64 = 0;

-#endif

+            const size_t dec64 = dec64table[(sizeof(void*)==4) ? 0 : op-ref];

             op[0] = ref[0];

             op[1] = ref[1];

             op[2] = ref[2];

@@ -880,27 +764,59 @@ int LZ4_uncompress_unknownOutputSize(
             op += 4, ref += 4; ref -= dec32table[op-ref];

             A32(op) = A32(ref); 

             op += STEPSIZE-4; ref -= dec64;

-        } else { LZ4_COPYSTEP(ref,op); }

+        } else { LZ4_COPYSTEP(op,ref); }

         cpy = op + length - (STEPSIZE-4);

 

-        if unlikely(cpy>oend-(COPYLENGTH+(STEPSIZE-4)))

+        if unlikely(cpy>oend-COPYLENGTH-(STEPSIZE-4))

         {

             if (cpy > oend-LASTLITERALS) goto _output_error;    // Error : last 5 bytes must be literals

-            LZ4_SECURECOPY(ref, op, (oend-COPYLENGTH));

+            LZ4_SECURECOPY(op, ref, (oend-COPYLENGTH));

             while(op<cpy) *op++=*ref++;

             op=cpy;

             continue;

         }

-

-        LZ4_WILDCOPY(ref, op, cpy);

-        op=cpy;		// correction

+        LZ4_WILDCOPY(op, ref, cpy);

+        op=cpy;   // correction

     }

 

     // end of decoding

-    return (int) (((char*)op)-dest);

+    if (endOnInput)

+       return (int) (((char*)op)-dest);     // Nb of output bytes decoded

+    else

+       return (int) (((char*)ip)-source);   // Nb of input bytes read

 

-    // write overflow error detected

+    // Overflow error detected

 _output_error:

-    return (int) (-(((char*)ip)-source));

+    return (int) (-(((char*)ip)-source))-1;

+}

+

+

+int LZ4_decompress_safe(const char* source, char* dest, int inputSize, int maxOutputSize)

+{

+    return LZ4_decompress_generic(source, dest, inputSize, maxOutputSize, endOnInputSize, noPrefix, full, 0);

+}

+

+int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int inputSize, int maxOutputSize)

+{

+    return LZ4_decompress_generic(source, dest, inputSize, maxOutputSize, endOnInputSize, withPrefix, full, 0);

+}

+

+int LZ4_decompress_safe_partial(const char* source, char* dest, int inputSize, int targetOutputSize, int maxOutputSize)

+{

+    return LZ4_decompress_generic(source, dest, inputSize, maxOutputSize, endOnInputSize, noPrefix, partial, targetOutputSize);

+}

+

+int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int outputSize)

+{

+    return LZ4_decompress_generic(source, dest, 0, outputSize, endOnOutputSize, withPrefix, full, 0);

+}

+

+int LZ4_decompress_fast(const char* source, char* dest, int outputSize)

+{

+#ifdef _MSC_VER   // This version is faster with Visual

+    return LZ4_decompress_generic(source, dest, 0, outputSize, endOnOutputSize, noPrefix, full, 0);

+#else

+    return LZ4_decompress_generic(source, dest, 0, outputSize, endOnOutputSize, withPrefix, full, 0);

+#endif

 }