/*

   LZ4 - Fast LZ compression algorithm

   Copyright (C) 2011-2017, 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

   modification, are permitted provided that the following conditions are

   met:

       * Redistributions of source code must retain the above copyright

   notice, this list of conditions and the following disclaimer.

       * Redistributions in binary form must reproduce the above

   copyright notice, this list of conditions and the following disclaimer

   in the documentation and/or other materials provided with the

   distribution.

   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS

   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT

   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR

   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT

   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,

   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT

   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,

   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY

   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT

   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE

   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

   You can contact the author at :

    - LZ4 homepage : http://www.lz4.org

    - LZ4 source repository : https://github.com/lz4/lz4

*/

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

*  Tuning parameters

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

/*

 * LZ4_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 malloc()).

 */

#ifndef LZ4_HEAPMODE

#  define LZ4_HEAPMODE 0

#endif

/*

 * ACCELERATION_DEFAULT :

 * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0

 */

#define ACCELERATION_DEFAULT 1

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

*  CPU Feature Detection

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

/* LZ4_FORCE_MEMORY_ACCESS

 * By default, access to unaligned memory is controlled by `memcpy()`, which is safe and portable.

 * Unfortunately, on some target/compiler combinations, the generated assembly is sub-optimal.

 * The below switch allow to select different access method for improved performance.

 * Method 0 (default) : use `memcpy()`. Safe and portable.

 * Method 1 : `__packed` statement. It depends on compiler extension (ie, not portable).

 *            This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`.

 * Method 2 : direct access. This method is portable but violate C standard.

 *            It can generate buggy code on targets which assembly generation depends on alignment.

 *            But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6)

 * See https://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details.

 * Prefer these methods in priority order (0 > 1 > 2)

 */

#ifndef LZ4_FORCE_MEMORY_ACCESS   /* can be defined externally */

#  if defined(__GNUC__) && \

  ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) \

  || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )

#    define LZ4_FORCE_MEMORY_ACCESS 2

#  elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__)

#    define LZ4_FORCE_MEMORY_ACCESS 1

#  endif

#endif

/*

 * LZ4_FORCE_SW_BITCOUNT

 * Define this parameter if your target system or compiler does not support hardware bit count

 */

#if defined(_MSC_VER) && defined(_WIN32_WCE)   /* Visual Studio for WinCE doesn't support Hardware bit count */

#  define LZ4_FORCE_SW_BITCOUNT

#endif

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

*  Dependency

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

#define LZ4_STATIC_LINKING_ONLY

#define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */

#include "lz4.h"

/* see also "memory routines" below */

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

*  Compiler Options

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

#ifdef _MSC_VER    /* Visual Studio */

#  include <intrin.h>

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

#  pragma warning(disable : 4293)        /* disable: C4293: too large shift (32-bits) */

#endif  /* _MSC_VER */

#ifndef LZ4_FORCE_INLINE

#  ifdef _MSC_VER    /* Visual Studio */

#    define LZ4_FORCE_INLINE static __forceinline

#  else

#    if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */

#      ifdef __GNUC__

#        define LZ4_FORCE_INLINE static inline __attribute__((always_inline))

#      else

#        define LZ4_FORCE_INLINE static inline

#      endif

#    else

#      define LZ4_FORCE_INLINE static

#    endif /* __STDC_VERSION__ */

#  endif  /* _MSC_VER */

#endif /* LZ4_FORCE_INLINE */

/* LZ4_FORCE_O2_GCC_PPC64LE and LZ4_FORCE_O2_INLINE_GCC_PPC64LE

 * Gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy,

 * together with a simple 8-byte copy loop as a fall-back path.

 * However, this optimization hurts the decompression speed by >30%,

 * because the execution does not go to the optimized loop

 * for typical compressible data, and all of the preamble checks

 * before going to the fall-back path become useless overhead.

 * This optimization happens only with the -O3 flag, and -O2 generates

 * a simple 8-byte copy loop.

 * With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy

 * functions are annotated with __attribute__((optimize("O2"))),

 * and also LZ4_wildCopy is forcibly inlined, so that the O2 attribute

 * of LZ4_wildCopy does not affect the compression speed.

 */

#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__)

#  define LZ4_FORCE_O2_GCC_PPC64LE __attribute__((optimize("O2")))

#  define LZ4_FORCE_O2_INLINE_GCC_PPC64LE __attribute__((optimize("O2"))) LZ4_FORCE_INLINE

#else

#  define LZ4_FORCE_O2_GCC_PPC64LE

#  define LZ4_FORCE_O2_INLINE_GCC_PPC64LE static

#endif

#if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__)

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

#else

#  define expect(expr,value)    (expr)

#endif

#ifndef likely

#define likely(expr)     expect((expr) != 0, 1)

#endif

#ifndef unlikely

#define unlikely(expr)   expect((expr) != 0, 0)

#endif

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

*  Memory routines

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

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

#define ALLOC(s)          malloc(s)

#define ALLOC_AND_ZERO(s) calloc(1,s)

#define FREEMEM(p)        free(p)

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

#define MEM_INIT(p,v,s)   memset((p),(v),(s))

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

*  Basic Types

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

#if defined(__cplusplus) || (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;

  typedef uintptr_t uptrval;

#else

  typedef unsigned char       BYTE;

  typedef unsigned short      U16;

  typedef unsigned int        U32;

  typedef   signed int        S32;

  typedef unsigned long long  U64;

  typedef size_t              uptrval;   /* generally true, except OpenVMS-64 */

#endif

#if defined(__x86_64__)

  typedef U64    reg_t;   /* 64-bits in x32 mode */

#else

  typedef size_t reg_t;   /* 32-bits in x32 mode */

#endif

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

*  Reading and writing into memory

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

static unsigned LZ4_isLittleEndian(void)

{

    const union { U32 u; BYTE c[4]; } one = { 1 };   /* don't use static : performance detrimental */

    return one.c[0];

}

#if defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==2)

/* lie to the compiler about data alignment; use with caution */

static U16 LZ4_read16(const void* memPtr) { return *(const U16*) memPtr; }

static U32 LZ4_read32(const void* memPtr) { return *(const U32*) memPtr; }

static reg_t LZ4_read_ARCH(const void* memPtr) { return *(const reg_t*) memPtr; }

static void LZ4_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; }

static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; }

#elif defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==1)

/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */

/* currently only defined for gcc and icc */

typedef union { U16 u16; U32 u32; reg_t uArch; } __attribute__((packed)) unalign;

static U16 LZ4_read16(const void* ptr) { return ((const unalign*)ptr)->u16; }

static U32 LZ4_read32(const void* ptr) { return ((const unalign*)ptr)->u32; }

static reg_t LZ4_read_ARCH(const void* ptr) { return ((const unalign*)ptr)->uArch; }

static void LZ4_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; }

static void LZ4_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; }

#else  /* safe and portable access through memcpy() */

static U16 LZ4_read16(const void* memPtr)

{

    U16 val; memcpy(&val, memPtr, sizeof(val)); return val;

}

static U32 LZ4_read32(const void* memPtr)

{

    U32 val; memcpy(&val, memPtr, sizeof(val)); return val;

}

static reg_t LZ4_read_ARCH(const void* memPtr)

{

    reg_t val; memcpy(&val, memPtr, sizeof(val)); return val;

}

static void LZ4_write16(void* memPtr, U16 value)

{

    memcpy(memPtr, &value, sizeof(value));

}

static void LZ4_write32(void* memPtr, U32 value)

{

    memcpy(memPtr, &value, sizeof(value));

}

#endif /* LZ4_FORCE_MEMORY_ACCESS */

static U16 LZ4_readLE16(const void* memPtr)

{

    if (LZ4_isLittleEndian()) {

        return LZ4_read16(memPtr);

    } else {

        const BYTE* p = (const BYTE*)memPtr;

        return (U16)((U16)p[0] + (p[1]<<8));

    }

}

static void LZ4_writeLE16(void* memPtr, U16 value)

{

    if (LZ4_isLittleEndian()) {

        LZ4_write16(memPtr, value);

    } else {

        BYTE* p = (BYTE*)memPtr;

        p[0] = (BYTE) value;

        p[1] = (BYTE)(value>>8);

    }

}

/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */

LZ4_FORCE_O2_INLINE_GCC_PPC64LE

void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd)

{

    BYTE* d = (BYTE*)dstPtr;

    const BYTE* s = (const BYTE*)srcPtr;

    BYTE* const e = (BYTE*)dstEnd;

    do { memcpy(d,s,8); d+=8; s+=8; } while (d<e);

}

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

*  Common Constants

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

#define MINMATCH 4

#define WILDCOPYLENGTH 8

#define LASTLITERALS 5

#define MFLIMIT (WILDCOPYLENGTH+MINMATCH)

static const int LZ4_minLength = (MFLIMIT+1);

#define KB *(1 <<10)

#define MB *(1 <<20)

#define GB *(1U<<30)

#define MAXD_LOG 16

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

#define ML_BITS  4

#define ML_MASK  ((1U<<ML_BITS)-1)

#define RUN_BITS (8-ML_BITS)

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

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

*  Error detection

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

#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=1)

#  include <assert.h>

#else

#  ifndef assert

#    define assert(condition) ((void)0)

#  endif

#endif

#define LZ4_STATIC_ASSERT(c)   { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use after variable declarations */

#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2)

#  include <stdio.h>

static int g_debuglog_enable = 1;

#  define DEBUGLOG(l, ...) {                                  \

                if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) {  \

                    fprintf(stderr, __FILE__ ": ");           \

                    fprintf(stderr, __VA_ARGS__);             \

                    fprintf(stderr, " \n");                   \

            }   }

#else

#  define DEBUGLOG(l, ...)      {}    /* disabled */

#endif

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

*  Common functions

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

static unsigned LZ4_NbCommonBytes (reg_t val)

{

    if (LZ4_isLittleEndian()) {

        if (sizeof(val)==8) {

#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)

            unsigned long r = 0;

            _BitScanForward64( &r, (U64)val );

            return (int)(r>>3);

#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)

            return (__builtin_ctzll((U64)val) >> 3);

#       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 & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];

#       endif

        } else /* 32 bits */ {

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

            unsigned long r;

            _BitScanForward( &r, (U32)val );

            return (int)(r>>3);

#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)

            return (__builtin_ctz((U32)val) >> 3);

#       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

        }

    } else   /* Big Endian CPU */ {

        if (sizeof(val)==8) {   /* 64-bits */

#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)

            unsigned long r = 0;

            _BitScanReverse64( &r, val );

            return (unsigned)(r>>3);

#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)

            return (__builtin_clzll((U64)val) >> 3);

#       else

            static const U32 by32 = sizeof(val)*4;  /* 32 on 64 bits (goal), 16 on 32 bits.

                Just to avoid some static analyzer complaining about shift by 32 on 32-bits target.

                Note that this code path is never triggered in 32-bits mode. */

            unsigned r;

            if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; }

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

            r += (!val);

            return r;

#       endif

        } else /* 32 bits */ {

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

            unsigned long r = 0;

            _BitScanReverse( &r, (unsigned long)val );

            return (unsigned)(r>>3);

#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)

            return (__builtin_clz((U32)val) >> 3);

#       else

            unsigned r;

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

            r += (!val);

            return r;

#       endif

        }

    }

}

#define STEPSIZE sizeof(reg_t)

LZ4_FORCE_INLINE

unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)

{

    const BYTE* const pStart = pIn;

    if (likely(pIn < pInLimit-(STEPSIZE-1))) {

        reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);

        if (!diff) {

            pIn+=STEPSIZE; pMatch+=STEPSIZE;

        } else {

            return LZ4_NbCommonBytes(diff);

    }   }

    while (likely(pIn < pInLimit-(STEPSIZE-1))) {

        reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);

        if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; }

        pIn += LZ4_NbCommonBytes(diff);

        return (unsigned)(pIn - pStart);

    }

    if ((STEPSIZE==8) && (pIn<(pInLimit-3)) && (LZ4_read32(pMatch) == LZ4_read32(pIn))) { pIn+=4; pMatch+=4; }

    if ((pIn<(pInLimit-1)) && (LZ4_read16(pMatch) == LZ4_read16(pIn))) { pIn+=2; pMatch+=2; }

    if ((pIn<pInLimit) && (*pMatch == *pIn)) pIn++;

    return (unsigned)(pIn - pStart);

}

#ifndef LZ4_COMMONDEFS_ONLY

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

*  Local Constants

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

static const int LZ4_64Klimit = ((64 KB) + (MFLIMIT-1));

static const U32 LZ4_skipTrigger = 6;  /* Increase this value ==> compression run slower on incompressible data */

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

*  Local Structures and types

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

typedef enum { notLimited = 0, limitedOutput = 1, fillOutput = 2 } limitedOutput_directive;

typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t;

/**

 * This enum distinguishes several different modes of accessing previous

 * content in the stream.

 *

 * - noDict        : There is no preceding content.

 * - withPrefix64k : Table entries up to ctx->dictSize before the current blob

 *                   blob being compressed are valid and refer to the preceding

 *                   content (of length ctx->dictSize), which is available

 *                   contiguously preceding in memory the content currently

 *                   being compressed.

 * - usingExtDict  : Like withPrefix64k, but the preceding content is somewhere

 *                   else in memory, starting at ctx->dictionary with length

 *                   ctx->dictSize.

 * - usingDictCtx  : Like usingExtDict, but everything concerning the preceding

 *                   content is in a separate context, pointed to by

 *                   ctx->dictCtx. ctx->dictionary, ctx->dictSize, and table

 *                   entries in the current context that refer to positions

 *                   preceding the beginning of the current compression are

 *                   ignored. Instead, ctx->dictCtx->dictionary and ctx->dictCtx

 *                   ->dictSize describe the location and size of the preceding

 *                   content, and matches are found by looking in the ctx

 *                   ->dictCtx->hashTable.

 */

typedef enum { noDict = 0, withPrefix64k, usingExtDict, usingDictCtx } dict_directive;

typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;

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

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

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

*  Local Utils

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

int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; }

const char* LZ4_versionString(void) { return LZ4_VERSION_STRING; }

int LZ4_compressBound(int isize)  { return LZ4_COMPRESSBOUND(isize); }

int LZ4_sizeofState() { return LZ4_STREAMSIZE; }

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

*  Compression functions

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

static U32 LZ4_hash4(U32 sequence, tableType_t const tableType)

{

    if (tableType == byU16)

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

    else

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

}

static U32 LZ4_hash5(U64 sequence, tableType_t const tableType)

{

    static const U64 prime5bytes = 889523592379ULL;

    static const U64 prime8bytes = 11400714785074694791ULL;

    const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG;

    if (LZ4_isLittleEndian())

        return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog));

    else

        return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog));

}

LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType)

{

    if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType);

    return LZ4_hash4(LZ4_read32(p), tableType);

}

static void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType)

{

    switch (tableType)

    {

    default: /* fallthrough */

    case clearedTable: /* fallthrough */

    case byPtr: { /* illegal! */ assert(0); return; }

    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; }

    case byU16: { U16* hashTable = (U16*) tableBase; assert(idx < 65536); hashTable[h] = (U16)idx; return; }

    }

}

static void LZ4_putPositionOnHash(const BYTE* p, U32 h,

                                  void* tableBase, tableType_t const tableType,

                            const BYTE* srcBase)

{

    switch (tableType)

    {

    case clearedTable: { /* illegal! */ assert(0); return; }

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

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

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

    }

}

LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)

{

    U32 const h = LZ4_hashPosition(p, tableType);

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

}

/* LZ4_getIndexOnHash() :

 * Index of match position registered in hash table.

 * hash position must be calculated by using base+index, or dictBase+index.

 * Assumption 1 : only valid if tableType == byU32 or byU16.

 * Assumption 2 : h is presumed valid (within limits of hash table)

 */

static U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType)

{

    LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2);

    if (tableType == byU32) {

        const U32* const hashTable = (const U32*) tableBase;

        assert(h < (1U << (LZ4_MEMORY_USAGE-2)));

        return hashTable[h];

    }

    if (tableType == byU16) {

        const U16* const hashTable = (const U16*) tableBase;

        assert(h < (1U << (LZ4_MEMORY_USAGE-1)));

        return hashTable[h];

    }

    assert(0); return 0;  /* forbidden case */

}

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

{

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

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

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

}

LZ4_FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p,

                                             const void* tableBase, tableType_t tableType,

                                             const BYTE* srcBase)

{

    U32 const h = LZ4_hashPosition(p, tableType);

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

}

LZ4_FORCE_INLINE void LZ4_prepareTable(

        LZ4_stream_t_internal* const cctx,

        const int inputSize,

        const tableType_t tableType) {

    /* If the table hasn't been used, it's guaranteed to be zeroed out, and is

     * therefore safe to use no matter what mode we're in. Otherwise, we figure

     * out if it's safe to leave as is or whether it needs to be reset.

     */

    if (cctx->tableType != clearedTable) {

        if (cctx->tableType != tableType

          || (tableType == byU16 && cctx->currentOffset + inputSize >= 0xFFFFU)

          || (tableType == byU32 && cctx->currentOffset > 1 GB)

          || tableType == byPtr

          || inputSize >= 4 KB)

        {

            DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", cctx);

            MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE);

            cctx->currentOffset = 0;

            cctx->tableType = clearedTable;

        } else {

            DEBUGLOG(4, "LZ4_prepareTable: Re-use hash table (no reset)");

        }

    }

    /* Adding a gap, so all previous entries are > MAX_DISTANCE back, is faster

     * than compressing without a gap. However, compressing with

     * currentOffset == 0 is faster still, so we preserve that case.

     */

    if (cctx->currentOffset != 0 && tableType == byU32) {

        DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset");

        cctx->currentOffset += 64 KB;

    }

    /* Finally, clear history */

    cctx->dictCtx = NULL;

    cctx->dictionary = NULL;

    cctx->dictSize = 0;

}

/** LZ4_compress_generic() :

    inlined, to ensure branches are decided at compilation time */

LZ4_FORCE_INLINE int LZ4_compress_generic(

                 LZ4_stream_t_internal* const cctx,

                 const char* const source,

                 char* const dest,

                 const int inputSize,

                 int *inputConsumed, /* only written when outputLimited == fillOutput */

                 const int maxOutputSize,

                 const limitedOutput_directive outputLimited,

                 const tableType_t tableType,

                 const dict_directive dictDirective,

                 const dictIssue_directive dictIssue,

                 const U32 acceleration)

{

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

    U32 const startIndex = cctx->currentOffset;

    const BYTE* base = (const BYTE*) source - startIndex;

    const BYTE* lowLimit;

    const LZ4_stream_t_internal* dictCtx = (const LZ4_stream_t_internal*) cctx->dictCtx;

    const BYTE* const dictionary =

        dictDirective == usingDictCtx ? dictCtx->dictionary : cctx->dictionary;

    const U32 dictSize =

        dictDirective == usingDictCtx ? dictCtx->dictSize : cctx->dictSize;

    const U32 dictDelta = (dictDirective == usingDictCtx) ? startIndex - dictCtx->currentOffset : 0;   /* make indexes in dictCtx comparable with index in current context */

    int const maybe_extMem = (dictDirective == usingExtDict) || (dictDirective == usingDictCtx);

    U32 const prefixIdxLimit = startIndex - dictSize;   /* used when dictDirective == dictSmall */

    const BYTE* const dictEnd = dictionary + dictSize;

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

    const BYTE* const iend = ip + inputSize;

    const BYTE* const mflimitPlusOne = iend - MFLIMIT + 1;

    const BYTE* const matchlimit = iend - LASTLITERALS;

    /* the dictCtx currentOffset is indexed on the start of the dictionary,

     * while a dictionary in the current context precedes the currentOffset */

    const BYTE* dictBase = dictDirective == usingDictCtx ?

        dictionary + dictSize - dictCtx->currentOffset :

        dictionary + dictSize - startIndex;

    BYTE* op = (BYTE*) dest;

    BYTE* const olimit = op + maxOutputSize;

    U32 offset = 0;

    U32 forwardH;

    DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, tableType=%u", inputSize, tableType);

    /* Init conditions */

    if (outputLimited == fillOutput && maxOutputSize < 1) return 0; /* Impossible to store anything */

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

    if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0;  /* Size too large (not within 64K limit) */

    if (tableType==byPtr) assert(dictDirective==noDict);      /* only supported use case with byPtr */

    assert(acceleration >= 1);

    lowLimit = (const BYTE*)source - (dictDirective == withPrefix64k ? dictSize : 0);

    /* Update context state */

    if (dictDirective == usingDictCtx) {

        /* Subsequent linked blocks can't use the dictionary. */

        /* Instead, they use the block we just compressed. */

        cctx->dictCtx = NULL;

        cctx->dictSize = (U32)inputSize;

    } else {

        cctx->dictSize += (U32)inputSize;

    }

    cctx->currentOffset += (U32)inputSize;

    cctx->tableType = tableType;

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

    /* First Byte */

    LZ4_putPosition(ip, cctx->hashTable, tableType, base);

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

    /* Main Loop */

    for ( ; ; ) {

        const BYTE* match;

        BYTE* token;

        /* Find a match */

        if (tableType == byPtr) {

            const BYTE* forwardIp = ip;

            unsigned step = 1;

            unsigned searchMatchNb = acceleration << LZ4_skipTrigger;

            do {

                U32 const h = forwardH;

                ip = forwardIp;

                forwardIp += step;

                step = (searchMatchNb++ >> LZ4_skipTrigger);

                if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;

                assert(ip < mflimitPlusOne);

                match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base);

                forwardH = LZ4_hashPosition(forwardIp, tableType);

                LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base);

            } while ( (match+MAX_DISTANCE < ip)

                   || (LZ4_read32(match) != LZ4_read32(ip)) );

        } else {   /* byU32, byU16 */

            const BYTE* forwardIp = ip;

            unsigned step = 1;

            unsigned searchMatchNb = acceleration << LZ4_skipTrigger;

            do {

                U32 const h = forwardH;

                U32 const current = (U32)(forwardIp - base);

                U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);

                assert(matchIndex <= current);

                assert(forwardIp - base < (ptrdiff_t)(2 GB - 1));

                ip = forwardIp;

                forwardIp += step;

                step = (searchMatchNb++ >> LZ4_skipTrigger);

                if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;

                assert(ip < mflimitPlusOne);

                if (dictDirective == usingDictCtx) {

                    if (matchIndex < startIndex) {

                        /* there was no match, try the dictionary */

                        assert(tableType == byU32);

                        matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);

                        match = dictBase + matchIndex;

                        matchIndex += dictDelta;   /* make dictCtx index comparable with current context */

                        lowLimit = dictionary;

                    } else {

                        match = base + matchIndex;

                        lowLimit = (const BYTE*)source;

                    }

                } else if (dictDirective==usingExtDict) {

                    if (matchIndex < startIndex) {

                        DEBUGLOG(7, "extDict candidate: matchIndex=%5u  <  startIndex=%5u", matchIndex, startIndex);

                        assert(startIndex - matchIndex >= MINMATCH);

                        match = dictBase + matchIndex;

                        lowLimit = dictionary;

                    } else {

                        match = base + matchIndex;

                        lowLimit = (const BYTE*)source;

                    }

                } else {   /* single continuous memory segment */

                    match = base + matchIndex;

                }

                forwardH = LZ4_hashPosition(forwardIp, tableType);

                LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);

                if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) continue;    /* match outside of valid area */

                assert(matchIndex < current);

                if ((tableType != byU16) && (matchIndex+MAX_DISTANCE < current)) continue;  /* too far */

                if (tableType == byU16) assert((current - matchIndex) <= MAX_DISTANCE);     /* too_far presumed impossible with byU16 */

                if (LZ4_read32(match) == LZ4_read32(ip)) {

                    if (maybe_extMem) offset = current - matchIndex;

                    break;   /* match found */

                }

            } while(1);

        }

        /* Catch up */

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

        /* Encode Literals */

        {   unsigned const litLength = (unsigned)(ip - anchor);

            token = op++;

            if ((outputLimited == limitedOutput) &&  /* Check output buffer overflow */

                (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))

                return 0;

            if ((outputLimited == fillOutput) &&

                (unlikely(op + (litLength+240)/255 /* litlen */ + litLength /* literals */ + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit))) {

                op--;

                goto _last_literals;

            }

            if (litLength >= RUN_MASK) {

                int len = (int)litLength-RUN_MASK;

                *token = (RUN_MASK<<ML_BITS);

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

                *op++ = (BYTE)len;

            }

            else *token = (BYTE)(litLength<<ML_BITS);

            /* Copy Literals */

            LZ4_wildCopy(op, anchor, op+litLength);

            op+=litLength;

            DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",

                        (int)(anchor-(const BYTE*)source), litLength, (int)(ip-(const BYTE*)source));

        }

_next_match:

        /* at this stage, the following variables must be correctly set :

         * - ip : at start of LZ operation

         * - match : at start of previous pattern occurence; can be within current prefix, or within extDict

         * - offset : if maybe_ext_memSegment==1 (constant)

         * - lowLimit : must be == dictionary to mean "match is within extDict"; must be == source otherwise

         * - token and *token : position to write 4-bits for match length; higher 4-bits for literal length supposed already written

         */

        if ((outputLimited == fillOutput) &&

            (op + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit)) {

            /* the match was too close to the end, rewind and go to last literals */

            op = token;

            goto _last_literals;

        }

        /* Encode Offset */

        if (maybe_extMem) {   /* static test */

            DEBUGLOG(6, "             with offset=%u  (ext if > %i)", offset, (int)(ip - (const BYTE*)source));

            assert(offset <= MAX_DISTANCE && offset > 0);

            LZ4_writeLE16(op, (U16)offset); op+=2;

        } else  {

            DEBUGLOG(6, "             with offset=%u  (same segment)", (U32)(ip - match));

            assert(ip-match <= MAX_DISTANCE);

            LZ4_writeLE16(op, (U16)(ip - match)); op+=2;

        }

        /* Encode MatchLength */

        {   unsigned matchCode;

            if ( (dictDirective==usingExtDict || dictDirective==usingDictCtx)

              && (lowLimit==dictionary) /* match within extDict */ ) {

                const BYTE* limit = ip + (dictEnd-match);

                assert(dictEnd > match);

                if (limit > matchlimit) limit = matchlimit;

                matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);

                ip += MINMATCH + matchCode;

                if (ip==limit) {

                    unsigned const more = LZ4_count(limit, (const BYTE*)source, matchlimit);

                    matchCode += more;

                    ip += more;

                }

                DEBUGLOG(6, "             with matchLength=%u starting in extDict", matchCode+MINMATCH);

            } else {

                matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);

                ip += MINMATCH + matchCode;

                DEBUGLOG(6, "             with matchLength=%u", matchCode+MINMATCH);

            }

            if ((outputLimited) &&    /* Check output buffer overflow */

                (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) ) {

                if (outputLimited == limitedOutput)

                  return 0;

                if (outputLimited == fillOutput) {

                    /* Match description too long : reduce it */

                    U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 2 - 1 - LASTLITERALS) * 255;

                    ip -= matchCode - newMatchCode;

                    matchCode = newMatchCode;

                }

            }

            if (matchCode >= ML_MASK) {

                *token += ML_MASK;

                matchCode -= ML_MASK;

                LZ4_write32(op, 0xFFFFFFFF);

                while (matchCode >= 4*255) {

                    op+=4;

                    LZ4_write32(op, 0xFFFFFFFF);

                    matchCode -= 4*255;

                }

                op += matchCode / 255;

                *op++ = (BYTE)(matchCode % 255);

            } else

                *token += (BYTE)(matchCode);

        }

        anchor = ip;

        /* Test end of chunk */

        if (ip >= mflimitPlusOne) break;

        /* Fill table */

        LZ4_putPosition(ip-2, cctx->hashTable, tableType, base);

        /* Test next position */

        if (tableType == byPtr) {

            match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);

            LZ4_putPosition(ip, cctx->hashTable, tableType, base);

            if ( (match+MAX_DISTANCE >= ip)

              && (LZ4_read32(match) == LZ4_read32(ip)) )

            { token=op++; *token=0; goto _next_match; }

        } else {   /* byU32, byU16 */

            U32 const h = LZ4_hashPosition(ip, tableType);

            U32 const current = (U32)(ip-base);

            U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);

            assert(matchIndex < current);

            if (dictDirective == usingDictCtx) {

                if (matchIndex < startIndex) {

                    /* there was no match, try the dictionary */

                    matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);

                    match = dictBase + matchIndex;

                    lowLimit = dictionary;   /* required for match length counter */

                    matchIndex += dictDelta;

                } else {

                    match = base + matchIndex;

                    lowLimit = (const BYTE*)source;  /* required for match length counter */

                }