Picklock_RCM/bdk/libs/compr/lz4.c

/*
   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
**************************************/
/*
 * ACCELERATION_DEFAULT :
 * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0
 */
#define ACCELERATION_DEFAULT 1


/*-************************************
*  Dependency
**************************************/
#define LZ4_STATIC_LINKING_ONLY
#include "lz4.h"
/* see also "memory routines" below */


/*-************************************
*  Compiler Options
**************************************/
#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

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


/*-************************************
*  Memory routines
**************************************/
#include <mem/heap.h>   /* malloc, calloc, free */
#define ALLOC(s) malloc(s)
#define ALLOC_AND_ZERO(s) calloc(1,s)
#define FREEMEM        free
#include <string.h>   /* memset, memcpy */
#define MEM_INIT       memset


/*-************************************
*  Basic Types
**************************************/
typedef uint16_t U16;
typedef uint32_t U32;
typedef  int32_t S32;
typedef uint64_t U64;
typedef uintptr_t uptrval;
typedef size_t reg_t;   /* 32-bits in x32 mode */

/*-************************************
*  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];
}

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));
}

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

#define LZ4_STATIC_ASSERT(c)   { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use only *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) {
            return (__builtin_ctzll((U64)val) >> 3);
        } else /* 32 bits */ {
            return (__builtin_ctz((U32)val) >> 3);
        }
    } else   /* Big Endian CPU */ {
        if (sizeof(val)==8) {   /* 64-bits */
            return (__builtin_clzll((U64)val) >> 3);
        } else /* 32 bits */ {
            return (__builtin_clz((U32)val) >> 3);
        }
    }
}

#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 } 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! */ return; }
    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; }
    case byU16: { U16* hashTable = (U16*) tableBase; 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! */ 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; return hashTable[h]; }
    if (tableType == byU16) { const U16* const hashTable = (const U16*) tableBase; return hashTable[h]; }
    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,
                 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 :   /* is it possible that dictCtx->currentOffset != dictCtx->dictSize ? Yes if the dictionary context is not reset */
        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 ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0;   /* Unsupported inputSize, too large (or negative) */

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

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

    /* 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;

                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);
                ip = forwardIp;
                forwardIp += step;
                step = (searchMatchNb++ >> LZ4_skipTrigger);

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

                if (dictDirective == usingDictCtx) {
                    if (matchIndex < startIndex) {
                        /* there was no match, try the dictionary */
                        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);
                        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 */
                if ((tableType != byU16) && (current - matchIndex > MAX_DISTANCE)) continue; /* too far - note: works even if matchIndex overflows */

                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) &&  /* Check output buffer overflow */
                (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
                return 0;
            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
         */

        /* Encode Offset */
        if (maybe_extMem) {   /* static test */
            LZ4_writeLE16(op, (U16)offset); op+=2;
        } else  {
            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);
                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)) )
                return 0;
            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);
            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 */
                }
            } else if (dictDirective==usingExtDict) {
                if (matchIndex < startIndex) {
                    match = dictBase + matchIndex;
                    lowLimit = dictionary;   /* required for match length counter */
                } else {
                    match = base + matchIndex;
                    lowLimit = (const BYTE*)source;   /* required for match length counter */
                }
            } else {   /* single memory segment */
                match = base + matchIndex;
            }
            LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
            if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1)
              && ((tableType==byU16) ? 1 : (current - matchIndex <= MAX_DISTANCE))
              && (LZ4_read32(match) == LZ4_read32(ip)) ) {
                token=op++;
                *token=0;
                if (maybe_extMem) offset = current - matchIndex;
                DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i", (int)(anchor-(const BYTE*)source), 0, (int)(ip-(const BYTE*)source));
                goto _next_match;
            }
        }

        /* Prepare next loop */
        forwardH = LZ4_hashPosition(++ip, tableType);

    }

_last_literals:
    /* Encode Last Literals */
    {   size_t const lastRun = (size_t)(iend - anchor);
        if ( (outputLimited) &&  /* Check output buffer overflow */
            ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) )
            return 0;
        if (lastRun >= RUN_MASK) {
            size_t accumulator = lastRun - RUN_MASK;
            *op++ = RUN_MASK << ML_BITS;
            for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
            *op++ = (BYTE) accumulator;
        } else {
            *op++ = (BYTE)(lastRun<<ML_BITS);
        }
        memcpy(op, anchor, lastRun);
        op += lastRun;
    }

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


int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
    LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse;
    if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
    LZ4_resetStream((LZ4_stream_t*)state);
    if (maxOutputSize >= LZ4_compressBound(inputSize)) {
        if (inputSize < LZ4_64Klimit) {
            return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue, acceleration);
        } else {
            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > MAX_DISTANCE)) ? byPtr : byU32;
            return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
        }
    } else {
        if (inputSize < LZ4_64Klimit) {;
            return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration);
        } else {
            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > MAX_DISTANCE)) ? byPtr : byU32;
            return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration);
        }
    }
}

/**
 * LZ4_compress_fast_extState_fastReset() :
 * A variant of LZ4_compress_fast_extState().
 *
 * Using this variant avoids an expensive initialization step. It is only safe
 * to call if the state buffer is known to be correctly initialized already
 * (see comment in lz4.h on LZ4_resetStream_fast() for a definition of
 * "correctly initialized").
 */
int LZ4_compress_fast_extState_fastReset(void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration)
{
    LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse;
    if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;

    if (dstCapacity >= LZ4_compressBound(srcSize)) {
        if (srcSize < LZ4_64Klimit) {
            const tableType_t tableType = byU16;
            LZ4_prepareTable(ctx, srcSize, tableType);
            if (ctx->currentOffset) {
                return LZ4_compress_generic(ctx, src, dst, srcSize, 0, notLimited, tableType, noDict, dictSmall, acceleration);
            } else {
                return LZ4_compress_generic(ctx, src, dst, srcSize, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
            }
        } else {
            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32;
            LZ4_prepareTable(ctx, srcSize, tableType);
            return LZ4_compress_generic(ctx, src, dst, srcSize, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
        }
    } else {
        if (srcSize < LZ4_64Klimit) {
            const tableType_t tableType = byU16;
            LZ4_prepareTable(ctx, srcSize, tableType);
            if (ctx->currentOffset) {
                return LZ4_compress_generic(ctx, src, dst, srcSize, dstCapacity, limitedOutput, tableType, noDict, dictSmall, acceleration);
            } else {
                return LZ4_compress_generic(ctx, src, dst, srcSize, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration);
            }
        } else {
            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32;
            LZ4_prepareTable(ctx, srcSize, tableType);
            return LZ4_compress_generic(ctx, src, dst, srcSize, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration);
        }
    }
}


int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
    int result;
    LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));
    LZ4_stream_t* const ctxPtr = ctx;
    result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration);

    FREEMEM(ctx);

    return result;
}


int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxOutputSize)
{
    return LZ4_compress_fast(source, dest, inputSize, maxOutputSize, 1);
}


/* hidden debug function */
/* strangely enough, gcc generates faster code when this function is uncommented, even if unused */
int LZ4_compress_fast_force(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
    int result;
    LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));
    LZ4_resetStream(ctx);

    if (inputSize < LZ4_64Klimit)
        result = LZ4_compress_generic(&ctx->internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, byU16,                        noDict, noDictIssue, acceleration);
    else
        result = LZ4_compress_generic(&ctx->internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, sizeof(void*)==8 ? byU32 : byPtr, noDict, noDictIssue, acceleration);

    FREEMEM(ctx);

    return result;
}


/*-******************************
*  *_destSize() variant
********************************/

static int LZ4_compress_destSize_generic(
                       LZ4_stream_t_internal* const ctx,
                 const char* const src,
                       char* const dst,
                       int*  const srcSizePtr,
                 const int targetDstSize,
                 const tableType_t tableType)
{
    const BYTE* ip = (const BYTE*) src;
    const BYTE* base = (const BYTE*) src;
    const BYTE* lowLimit = (const BYTE*) src;
    const BYTE* anchor = ip;
    const BYTE* const iend = ip + *srcSizePtr;
    const BYTE* const mflimit = iend - MFLIMIT;
    const BYTE* const matchlimit = iend - LASTLITERALS;

    BYTE* op = (BYTE*) dst;
    BYTE* const oend = op + targetDstSize;
    BYTE* const oMaxLit = op + targetDstSize - 2 /* offset */ - 8 /* because 8+MINMATCH==MFLIMIT */ - 1 /* token */;
    BYTE* const oMaxMatch = op + targetDstSize - (LASTLITERALS + 1 /* token */);
    BYTE* const oMaxSeq = oMaxLit - 1 /* token */;

    U32 forwardH;


    /* Init conditions */
    if (targetDstSize < 1) return 0;                                     /* Impossible to store anything */
    if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0;            /* Unsupported input size, too large (or negative) */
    if ((tableType == byU16) && (*srcSizePtr>=LZ4_64Klimit)) return 0;   /* Size too large (not within 64K limit) */
    if (*srcSizePtr<LZ4_minLength) goto _last_literals;                  /* Input too small, no compression (all literals) */

    /* First Byte */
    *srcSizePtr = 0;
    LZ4_putPosition(ip, ctx->hashTable, tableType, base);
    ip++; forwardH = LZ4_hashPosition(ip, tableType);

    /* Main Loop */
    for ( ; ; ) {
        const BYTE* match;
        BYTE* token;

        /* Find a match */
        {   const BYTE* forwardIp = ip;
            unsigned step = 1;
            unsigned searchMatchNb = 1 << LZ4_skipTrigger;

            do {
                U32 h = forwardH;
                ip = forwardIp;
                forwardIp += step;
                step = (searchMatchNb++ >> LZ4_skipTrigger);

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

                match = LZ4_getPositionOnHash(h, ctx->hashTable, tableType, base);
                forwardH = LZ4_hashPosition(forwardIp, tableType);
                LZ4_putPositionOnHash(ip, h, ctx->hashTable, tableType, base);

            } while ( ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
                || (LZ4_read32(match) != LZ4_read32(ip)) );
        }

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

        /* Encode Literal length */
        {   unsigned litLength = (unsigned)(ip - anchor);
            token = op++;
            if (op + ((litLength+240)/255) + litLength > oMaxLit) {
                /* Not enough space for a last match */
                op--;
                goto _last_literals;
            }
            if (litLength>=RUN_MASK) {
                unsigned len = 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;
        }

_next_match:
        /* Encode Offset */
        LZ4_writeLE16(op, (U16)(ip-match)); op+=2;

        /* Encode MatchLength */
        {   size_t matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);

            if (op + ((matchLength+240)/255) > oMaxMatch) {
                /* Match description too long : reduce it */
                matchLength = (15-1) + (oMaxMatch-op) * 255;
            }
            ip += MINMATCH + matchLength;

            if (matchLength>=ML_MASK) {
                *token += ML_MASK;
                matchLength -= ML_MASK;
                while (matchLength >= 255) { matchLength-=255; *op++ = 255; }
                *op++ = (BYTE)matchLength;
            }
            else *token += (BYTE)(matchLength);
        }

        anchor = ip;

        /* Test end of block */
        if (ip > mflimit) break;
        if (op > oMaxSeq) break;

        /* Fill table */
        LZ4_putPosition(ip-2, ctx->hashTable, tableType, base);

        /* Test next position */
        match = LZ4_getPosition(ip, ctx->hashTable, tableType, base);
        LZ4_putPosition(ip, ctx->hashTable, tableType, base);
        if ( (match+MAX_DISTANCE>=ip)
            && (LZ4_read32(match)==LZ4_read32(ip)) )
        { token=op++; *token=0; goto _next_match; }

        /* Prepare next loop */
        forwardH = LZ4_hashPosition(++ip, tableType);
    }

_last_literals:
    /* Encode Last Literals */
    {   size_t lastRunSize = (size_t)(iend - anchor);
        if (op + 1 /* token */ + ((lastRunSize+240)/255) /* litLength */ + lastRunSize /* literals */ > oend) {
            /* adapt lastRunSize to fill 'dst' */
            lastRunSize  = (oend-op) - 1;
            lastRunSize -= (lastRunSize+240)/255;
        }
        ip = anchor + lastRunSize;

        if (lastRunSize >= RUN_MASK) {
            size_t accumulator = lastRunSize - RUN_MASK;
            *op++ = RUN_MASK << ML_BITS;
            for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
            *op++ = (BYTE) accumulator;
        } else {
            *op++ = (BYTE)(lastRunSize<<ML_BITS);
        }
        memcpy(op, anchor, lastRunSize);
        op += lastRunSize;
    }

    /* End */
    *srcSizePtr = (int) (((const char*)ip)-src);
    return (int) (((char*)op)-dst);
}


static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize)
{
    LZ4_resetStream(state);

    if (targetDstSize >= LZ4_compressBound(*srcSizePtr)) {  /* compression success is guaranteed */
        return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1);
    } else {
        if (*srcSizePtr < LZ4_64Klimit) {
            return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, byU16);
        } else {
            tableType_t const tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32;
            return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, tableType);
    }   }
}


int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize)
{
    LZ4_stream_t* ctxBody = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));;
    LZ4_stream_t* ctx = ctxBody;

    int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize);

    FREEMEM(ctxBody);

    return result;
}



/*-******************************
*  Streaming functions
********************************/

LZ4_stream_t* LZ4_createStream(void)
{
    LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));
    LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal));    /* A compilation error here means LZ4_STREAMSIZE is not large enough */
    DEBUGLOG(4, "LZ4_createStream %p", lz4s);
    if (lz4s == NULL) return NULL;
    LZ4_resetStream(lz4s);
    return lz4s;
}

void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
{
    DEBUGLOG(5, "LZ4_resetStream (ctx:%p)", LZ4_stream);
    MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t));
}

void LZ4_resetStream_fast(LZ4_stream_t* ctx) {
    LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32);
}

int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
{
    if (!LZ4_stream) return 0;   /* support free on NULL */
    DEBUGLOG(5, "LZ4_freeStream %p", LZ4_stream);
    FREEMEM(LZ4_stream);
    return (0);
}


#define HASH_UNIT sizeof(reg_t)
int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
{
    LZ4_stream_t_internal* dict = &LZ4_dict->internal_donotuse;
    const tableType_t tableType = byU32;
    const BYTE* p = (const BYTE*)dictionary;
    const BYTE* const dictEnd = p + dictSize;
    const BYTE* base;

    DEBUGLOG(4, "LZ4_loadDict (%i bytes from %p into %p)", dictSize, dictionary, LZ4_dict);

    LZ4_prepareTable(dict, 0, tableType);

    /* We always increment the offset by 64 KB, since, if the dict is longer,
     * we truncate it to the last 64k, and if it's shorter, we still want to
     * advance by a whole window length so we can provide the guarantee that
     * there are only valid offsets in the window, which allows an optimization
     * in LZ4_compress_fast_continue() where it uses noDictIssue even when the
     * dictionary isn't a full 64k. */

    if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB;
    base = dictEnd - 64 KB - dict->currentOffset;
    dict->dictionary = p;
    dict->dictSize = (U32)(dictEnd - p);
    dict->currentOffset += 64 KB;
    dict->tableType = tableType;

    if (dictSize < (int)HASH_UNIT) {
        return 0;
    }

    while (p <= dictEnd-HASH_UNIT) {
        LZ4_putPosition(p, dict->hashTable, tableType, base);
        p+=3;
    }

    return dict->dictSize;
}

void LZ4_attach_dictionary(LZ4_stream_t *working_stream, const LZ4_stream_t *dictionary_stream) {
    if (dictionary_stream != NULL) {
        /* If the current offset is zero, we will never look in the
         * external dictionary context, since there is no value a table
         * entry can take that indicate a miss. In that case, we need
         * to bump the offset to something non-zero.
         */
        if (working_stream->internal_donotuse.currentOffset == 0) {
            working_stream->internal_donotuse.currentOffset = 64 KB;
        }
        working_stream->internal_donotuse.dictCtx = &(dictionary_stream->internal_donotuse);
    } else {
        working_stream->internal_donotuse.dictCtx = NULL;
    }
}


static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, int nextSize)
{
    if (LZ4_dict->currentOffset + nextSize > 0x80000000) {   /* potential ptrdiff_t overflow (32-bits mode) */
        /* rescale hash table */
        U32 const delta = LZ4_dict->currentOffset - 64 KB;
        const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
        int i;
        DEBUGLOG(4, "LZ4_renormDictT");
        for (i=0; i<LZ4_HASH_SIZE_U32; i++) {
            if (LZ4_dict->hashTable[i] < delta) LZ4_dict->hashTable[i]=0;
            else LZ4_dict->hashTable[i] -= delta;
        }
        LZ4_dict->currentOffset = 64 KB;
        if (LZ4_dict->dictSize > 64 KB) LZ4_dict->dictSize = 64 KB;
        LZ4_dict->dictionary = dictEnd - LZ4_dict->dictSize;
    }
}


int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
    const tableType_t tableType = byU32;
    LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse;
    const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;

    if (streamPtr->initCheck) return 0;   /* Uninitialized structure detected */
    LZ4_renormDictT(streamPtr, inputSize);   /* avoid index overflow */
    if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;

    /* Check overlapping input/dictionary space */
    {   const BYTE* sourceEnd = (const BYTE*) source + inputSize;
        if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) {
            streamPtr->dictSize = (U32)(dictEnd - sourceEnd);
            if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB;
            if (streamPtr->dictSize < 4) streamPtr->dictSize = 0;
            streamPtr->dictionary = dictEnd - streamPtr->dictSize;
        }
    }

    /* prefix mode : source data follows dictionary */
    if (dictEnd == (const BYTE*)source) {
        if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
            return LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration);
        else
            return LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, withPrefix64k, noDictIssue, acceleration);
    }

    /* external dictionary mode */
    {   int result;
        if (streamPtr->dictCtx) {
            /* We depend here on the fact that dictCtx'es (produced by
             * LZ4_loadDict) guarantee that their tables contain no references
             * to offsets between dictCtx->currentOffset - 64 KB and
             * dictCtx->currentOffset - dictCtx->dictSize. This makes it safe
             * to use noDictIssue even when the dict isn't a full 64 KB.
             */
            if (inputSize > 4 KB) {
                /* For compressing large blobs, it is faster to pay the setup
                 * cost to copy the dictionary's tables into the active context,
                 * so that the compression loop is only looking into one table.
                 */
                memcpy(streamPtr, streamPtr->dictCtx, sizeof(LZ4_stream_t));
                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
            } else {
                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration);
            }
        } else {
            if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration);
            } else {
                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
            }
        }
        streamPtr->dictionary = (const BYTE*)source;
        streamPtr->dictSize = (U32)inputSize;
        return result;
    }
}


/* Hidden debug function, to force-test external dictionary mode */
int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize)
{
    LZ4_stream_t_internal* streamPtr = &LZ4_dict->internal_donotuse;
    int result;

    LZ4_renormDictT(streamPtr, srcSize);

    if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
        result = LZ4_compress_generic(streamPtr, source, dest, srcSize, 0, notLimited, byU32, usingExtDict, dictSmall, 1);
    } else {
        result = LZ4_compress_generic(streamPtr, source, dest, srcSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
    }

    streamPtr->dictionary = (const BYTE*)source;
    streamPtr->dictSize = (U32)srcSize;

    return result;
}


/*! LZ4_saveDict() :
 *  If previously compressed data block is not guaranteed to remain available at its memory location,
 *  save it into a safer place (char* safeBuffer).
 *  Note : you don't need to call LZ4_loadDict() afterwards,
 *         dictionary is immediately usable, you can therefore call LZ4_compress_fast_continue().
 *  Return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error.
 */
int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
{
    LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse;
    const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize;

    if ((U32)dictSize > 64 KB) dictSize = 64 KB;   /* useless to define a dictionary > 64 KB */
    if ((U32)dictSize > dict->dictSize) dictSize = dict->dictSize;

    memmove(safeBuffer, previousDictEnd - dictSize, dictSize);

    dict->dictionary = (const BYTE*)safeBuffer;
    dict->dictSize = (U32)dictSize;

    return dictSize;
}



/*-*****************************
*  Decompression functions
*******************************/
/*! LZ4_decompress_generic() :
 *  This generic decompression function covers all use cases.
 *  It shall be instantiated several times, using different sets of directives.
 *  Note that it is important for performance that this function really get inlined,
 *  in order to remove useless branches during compilation optimization.
 */
LZ4_FORCE_O2_GCC_PPC64LE
LZ4_FORCE_INLINE int LZ4_decompress_generic(
                 const char* const src,
                 char* const dst,
                 int srcSize,
                 int outputSize,         /* If endOnInput==endOnInputSize, this value is `dstCapacity` */

                 int endOnInput,         /* endOnOutputSize, endOnInputSize */
                 int partialDecoding,    /* full, partial */
                 int targetOutputSize,   /* only used if partialDecoding==partial */
                 int dict,               /* noDict, withPrefix64k, usingExtDict */
                 const BYTE* const lowPrefix,  /* always <= dst, == dst when no prefix */
                 const BYTE* const dictStart,  /* only if dict==usingExtDict */
                 const size_t dictSize         /* note : = 0 if noDict */
                 )
{
    const BYTE* ip = (const BYTE*) src;
    const BYTE* const iend = ip + srcSize;

    BYTE* op = (BYTE*) dst;
    BYTE* const oend = op + outputSize;
    BYTE* cpy;
    BYTE* oexit = op + targetOutputSize;

    const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize;
    const unsigned inc32table[8] = {0, 1, 2,  1,  0,  4, 4, 4};
    const int      dec64table[8] = {0, 0, 0, -1, -4,  1, 2, 3};

    const int safeDecode = (endOnInput==endOnInputSize);
    const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB)));


    /* Special cases */
    if ((partialDecoding) && (oexit > oend-MFLIMIT)) oexit = oend-MFLIMIT;                      /* targetOutputSize too high => just decode everything */
    if ((endOnInput) && (unlikely(outputSize==0))) return ((srcSize==1) && (*ip==0)) ? 0 : -1;  /* Empty output buffer */
    if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1);

    /* Main Loop : decode sequences */
    while (1) {
        size_t length;
        const BYTE* match;
        size_t offset;

        unsigned const token = *ip++;

        /* shortcut for common case :
         * in most circumstances, we expect to decode small matches (<= 18 bytes) separated by few literals (<= 14 bytes).
         * this shortcut was tested on x86 and x64, where it improves decoding speed.
         * it has not yet been benchmarked on ARM, Power, mips, etc. */
        if (((ip + 14 /*maxLL*/ + 2 /*offset*/ <= iend)
          & (op + 14 /*maxLL*/ + 18 /*maxML*/ <= oend))
          & ((token < (15<<ML_BITS)) & ((token & ML_MASK) != 15)) ) {
            size_t const ll = token >> ML_BITS;
            size_t const off = LZ4_readLE16(ip+ll);
            const BYTE* const matchPtr = op + ll - off;  /* pointer underflow risk ? */
            if ((off >= 8) /* do not deal with overlapping matches */ & (matchPtr >= lowPrefix)) {
                size_t const ml = (token & ML_MASK) + MINMATCH;
                memcpy(op, ip, 16); op += ll; ip += ll + 2 /*offset*/;
                memcpy(op + 0, matchPtr + 0, 8);
                memcpy(op + 8, matchPtr + 8, 8);
                memcpy(op +16, matchPtr +16, 2);
                op += ml;
                continue;
            }
        }

        /* decode literal length */
        if ((length=(token>>ML_BITS)) == RUN_MASK) {
            unsigned s;
            do {
                s = *ip++;
                length += s;
            } while ( likely(endOnInput ? ip<iend-RUN_MASK : 1) & (s==255) );
            if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) goto _output_error;   /* overflow detection */
            if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) goto _output_error;   /* overflow detection */
        }

        /* copy literals */
        cpy = op+length;
        if ( ((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) )
            || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) )
        {
            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(op, ip, cpy);
        ip += length; op = cpy;

        /* get offset */
        offset = LZ4_readLE16(ip); ip+=2;
        match = op - offset;
        if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error;   /* Error : offset outside buffers */
        LZ4_write32(op, (U32)offset);   /* costs ~1%; silence an msan warning when offset==0 */

        /* get matchlength */
        length = token & ML_MASK;
        if (length == ML_MASK) {
            unsigned s;
            do {
                s = *ip++;
                if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
                length += s;
            } while (s==255);
            if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error;   /* overflow detection */
        }
        length += MINMATCH;

        /* check external dictionary */
        if ((dict==usingExtDict) && (match < lowPrefix)) {
            if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error;   /* doesn't respect parsing restriction */

            if (length <= (size_t)(lowPrefix-match)) {
                /* match can be copied as a single segment from external dictionary */
                memmove(op, dictEnd - (lowPrefix-match), length);
                op += length;
            } else {
                /* match encompass external dictionary and current block */
                size_t const copySize = (size_t)(lowPrefix-match);
                size_t const restSize = length - copySize;
                memcpy(op, dictEnd - copySize, copySize);
                op += copySize;
                if (restSize > (size_t)(op-lowPrefix)) {  /* overlap copy */
                    BYTE* const endOfMatch = op + restSize;
                    const BYTE* copyFrom = lowPrefix;
                    while (op < endOfMatch) *op++ = *copyFrom++;
                } else {
                    memcpy(op, lowPrefix, restSize);
                    op += restSize;
            }   }
            continue;
        }

        /* copy match within block */
        cpy = op + length;
        if (unlikely(offset<8)) {
            op[0] = match[0];
            op[1] = match[1];
            op[2] = match[2];
            op[3] = match[3];
            match += inc32table[offset];
            memcpy(op+4, match, 4);
            match -= dec64table[offset];
        } else { memcpy(op, match, 8); match+=8; }
        op += 8;

        if (unlikely(cpy>oend-12)) {
            BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1);
            if (cpy > oend-LASTLITERALS) goto _output_error;    /* Error : last LASTLITERALS bytes must be literals (uncompressed) */
            if (op < oCopyLimit) {
                LZ4_wildCopy(op, match, oCopyLimit);
                match += oCopyLimit - op;
                op = oCopyLimit;
            }
            while (op<cpy) *op++ = *match++;
        } else {
            memcpy(op, match, 8);
            if (length>16) LZ4_wildCopy(op+8, match+8, cpy);
        }
        op = cpy;   /* correction */
    }

    /* end of decoding */
    if (endOnInput)
       return (int) (((char*)op)-dst);     /* Nb of output bytes decoded */
    else
       return (int) (((const char*)ip)-src);   /* Nb of input bytes read */

    /* Overflow error detected */
_output_error:
    return (int) (-(((const char*)ip)-src))-1;
}


LZ4_FORCE_O2_GCC_PPC64LE
int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, NULL, 0);
}

LZ4_FORCE_O2_GCC_PPC64LE
int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, NULL, 0);
}

LZ4_FORCE_O2_GCC_PPC64LE
int LZ4_decompress_fast(const char* source, char* dest, int originalSize)
{
    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)(dest - 64 KB), NULL, 64 KB);
}


/*===== streaming decompression functions =====*/

LZ4_streamDecode_t* LZ4_createStreamDecode(void)
{
    LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t));
    return lz4s;
}

int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
{
    if (!LZ4_stream) return 0;   /* support free on NULL */
    FREEMEM(LZ4_stream);
    return 0;
}

/*!
 * LZ4_setStreamDecode() :
 * Use this function to instruct where to find the dictionary.
 * This function is not necessary if previous data is still available where it was decoded.
 * Loading a size of 0 is allowed (same effect as no dictionary).
 * Return : 1 if OK, 0 if error
 */
int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize)
{
    LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
    lz4sd->prefixSize = (size_t) dictSize;
    lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize;
    lz4sd->externalDict = NULL;
    lz4sd->extDictSize  = 0;
    return 1;
}

/*
*_continue() :
    These decoding functions allow decompression of multiple blocks in "streaming" mode.
    Previously decoded blocks must still be available at the memory position where they were decoded.
    If it's not possible, save the relevant part of decoded data into a safe buffer,
    and indicate where it stands using LZ4_setStreamDecode()
*/
LZ4_FORCE_O2_GCC_PPC64LE
int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize)
{
    LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
    int result;

    if (lz4sd->prefixEnd == (BYTE*)dest) {
        result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
                                        endOnInputSize, full, 0,
                                        usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
        if (result <= 0) return result;
        lz4sd->prefixSize += result;
        lz4sd->prefixEnd  += result;
    } else {
        lz4sd->extDictSize = lz4sd->prefixSize;
        lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
        result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
                                        endOnInputSize, full, 0,
                                        usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
        if (result <= 0) return result;
        lz4sd->prefixSize = result;
        lz4sd->prefixEnd  = (BYTE*)dest + result;
    }

    return result;
}

LZ4_FORCE_O2_GCC_PPC64LE
int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize)
{
    LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
    int result;

    if (lz4sd->prefixEnd == (BYTE*)dest) {
        result = LZ4_decompress_generic(source, dest, 0, originalSize,
                                        endOnOutputSize, full, 0,
                                        usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
        if (result <= 0) return result;
        lz4sd->prefixSize += originalSize;
        lz4sd->prefixEnd  += originalSize;
    } else {
        lz4sd->extDictSize = lz4sd->prefixSize;
        lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
        result = LZ4_decompress_generic(source, dest, 0, originalSize,
                                        endOnOutputSize, full, 0,
                                        usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
        if (result <= 0) return result;
        lz4sd->prefixSize = originalSize;
        lz4sd->prefixEnd  = (BYTE*)dest + originalSize;
    }

    return result;
}


/*
Advanced decoding functions :
*_usingDict() :
    These decoding functions work the same as "_continue" ones,
    the dictionary must be explicitly provided within parameters
*/

LZ4_FORCE_O2_GCC_PPC64LE
LZ4_FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest, int compressedSize, int maxOutputSize, int safe, const char* dictStart, int dictSize)
{
    if (dictSize==0)
        return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest, NULL, 0);
    if (dictStart+dictSize == dest) {
        if (dictSize >= (int)(64 KB - 1))
            return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, withPrefix64k, (BYTE*)dest-64 KB, NULL, 0);
        return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest-dictSize, NULL, 0);
    }
    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize);
}

LZ4_FORCE_O2_GCC_PPC64LE
int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
{
    return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize);
}

LZ4_FORCE_O2_GCC_PPC64LE
int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
{
    return LZ4_decompress_usingDict_generic(source, dest, 0, originalSize, 0, dictStart, dictSize);
}

/* debug function */
LZ4_FORCE_O2_GCC_PPC64LE
int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize);
}


/*=*************************************************
*  Obsolete Functions
***************************************************/
/* obsolete compression functions */
int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) { return LZ4_compress_default(source, dest, inputSize, maxOutputSize); }
int LZ4_compress(const char* source, char* dest, int inputSize) { return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize)); }
int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1); }
int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1); }
int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, maxDstSize, 1); }
int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) { return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); }

/*
These function names are deprecated and should no longer be used.
They are only provided here for compatibility with older user programs.
- LZ4_uncompress is totally equivalent to LZ4_decompress_fast
- LZ4_uncompress_unknownOutputSize is totally equivalent to LZ4_decompress_safe
*/
int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); }
int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); }

/* Obsolete Streaming functions */

int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; }

int LZ4_resetStreamState(void* state, char* inputBuffer)
{
    (void)inputBuffer;
    LZ4_resetStream((LZ4_stream_t*)state);
    return 0;
}

void* LZ4_create (char* inputBuffer)
{
    (void)inputBuffer;
    return LZ4_createStream();
}

char* LZ4_slideInputBuffer (void* state)
{
    /* avoid const char * -> char * conversion warning */
    return (char *)(uptrval)((LZ4_stream_t*)state)->internal_donotuse.dictionary;
}

/* Obsolete streaming decompression functions */

int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
{
    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
}

int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
{
    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
}

#endif   /* LZ4_COMMONDEFS_ONLY */