You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@orc.apache.org by om...@apache.org on 2017/07/24 17:49:50 UTC
[48/51] [partial] orc git commit: ORC-204 Update and use CMake
External Project to build C++ compression libraries.
http://git-wip-us.apache.org/repos/asf/orc/blob/590245a0/c++/libs/lz4-r131/lib/lz4hc.c
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/lib/lz4hc.c b/c++/libs/lz4-r131/lib/lz4hc.c
deleted file mode 100644
index bbe7a9d..0000000
--- a/c++/libs/lz4-r131/lib/lz4hc.c
+++ /dev/null
@@ -1,731 +0,0 @@
-/*
- LZ4 HC - High Compression Mode of LZ4
- Copyright (C) 2011-2015, 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 source repository : https://github.com/Cyan4973/lz4
- - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
-*/
-
-
-
-/**************************************
-* Tuning Parameter
-**************************************/
-static const int LZ4HC_compressionLevel_default = 9;
-
-
-/**************************************
-* Includes
-**************************************/
-#include "lz4hc.h"
-
-
-/**************************************
-* Local Compiler Options
-**************************************/
-#if defined(__GNUC__)
-# pragma GCC diagnostic ignored "-Wunused-function"
-#endif
-
-#if defined (__clang__)
-# pragma clang diagnostic ignored "-Wunused-function"
-#endif
-
-
-/**************************************
-* Common LZ4 definition
-**************************************/
-#define LZ4_COMMONDEFS_ONLY
-#include "lz4.c"
-
-
-/**************************************
-* Local Constants
-**************************************/
-#define DICTIONARY_LOGSIZE 16
-#define MAXD (1<<DICTIONARY_LOGSIZE)
-#define MAXD_MASK (MAXD - 1)
-
-#define HASH_LOG (DICTIONARY_LOGSIZE-1)
-#define HASHTABLESIZE (1 << HASH_LOG)
-#define HASH_MASK (HASHTABLESIZE - 1)
-
-#define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH)
-
-static const int g_maxCompressionLevel = 16;
-
-
-/**************************************
-* Local Types
-**************************************/
-typedef struct
-{
- U32 hashTable[HASHTABLESIZE];
- U16 chainTable[MAXD];
- const BYTE* end; /* next block here to continue on current prefix */
- const BYTE* base; /* All index relative to this position */
- const BYTE* dictBase; /* alternate base for extDict */
- BYTE* inputBuffer; /* deprecated */
- U32 dictLimit; /* below that point, need extDict */
- U32 lowLimit; /* below that point, no more dict */
- U32 nextToUpdate; /* index from which to continue dictionary update */
- U32 compressionLevel;
-} LZ4HC_Data_Structure;
-
-
-/**************************************
-* Local Macros
-**************************************/
-#define HASH_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH*8)-HASH_LOG))
-//#define DELTANEXTU16(p) chainTable[(p) & MAXD_MASK] /* flexible, MAXD dependent */
-#define DELTANEXTU16(p) chainTable[(U16)(p)] /* faster */
-
-static U32 LZ4HC_hashPtr(const void* ptr) { return HASH_FUNCTION(LZ4_read32(ptr)); }
-
-
-
-/**************************************
-* HC Compression
-**************************************/
-static void LZ4HC_init (LZ4HC_Data_Structure* hc4, const BYTE* start)
-{
- MEM_INIT((void*)hc4->hashTable, 0, sizeof(hc4->hashTable));
- MEM_INIT(hc4->chainTable, 0xFF, sizeof(hc4->chainTable));
- hc4->nextToUpdate = 64 KB;
- hc4->base = start - 64 KB;
- hc4->end = start;
- hc4->dictBase = start - 64 KB;
- hc4->dictLimit = 64 KB;
- hc4->lowLimit = 64 KB;
-}
-
-
-/* Update chains up to ip (excluded) */
-FORCE_INLINE void LZ4HC_Insert (LZ4HC_Data_Structure* hc4, const BYTE* ip)
-{
- U16* chainTable = hc4->chainTable;
- U32* HashTable = hc4->hashTable;
- const BYTE* const base = hc4->base;
- const U32 target = (U32)(ip - base);
- U32 idx = hc4->nextToUpdate;
-
- while(idx < target)
- {
- U32 h = LZ4HC_hashPtr(base+idx);
- size_t delta = idx - HashTable[h];
- if (delta>MAX_DISTANCE) delta = MAX_DISTANCE;
- DELTANEXTU16(idx) = (U16)delta;
- HashTable[h] = idx;
- idx++;
- }
-
- hc4->nextToUpdate = target;
-}
-
-
-FORCE_INLINE int LZ4HC_InsertAndFindBestMatch (LZ4HC_Data_Structure* hc4, /* Index table will be updated */
- const BYTE* ip, const BYTE* const iLimit,
- const BYTE** matchpos,
- const int maxNbAttempts)
-{
- U16* const chainTable = hc4->chainTable;
- U32* const HashTable = hc4->hashTable;
- const BYTE* const base = hc4->base;
- const BYTE* const dictBase = hc4->dictBase;
- const U32 dictLimit = hc4->dictLimit;
- const U32 lowLimit = (hc4->lowLimit + 64 KB > (U32)(ip-base)) ? hc4->lowLimit : (U32)(ip - base) - (64 KB - 1);
- U32 matchIndex;
- const BYTE* match;
- int nbAttempts=maxNbAttempts;
- size_t ml=0;
-
- /* HC4 match finder */
- LZ4HC_Insert(hc4, ip);
- matchIndex = HashTable[LZ4HC_hashPtr(ip)];
-
- while ((matchIndex>=lowLimit) && (nbAttempts))
- {
- nbAttempts--;
- if (matchIndex >= dictLimit)
- {
- match = base + matchIndex;
- if (*(match+ml) == *(ip+ml)
- && (LZ4_read32(match) == LZ4_read32(ip)))
- {
- size_t mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, iLimit) + MINMATCH;
- if (mlt > ml) { ml = mlt; *matchpos = match; }
- }
- }
- else
- {
- match = dictBase + matchIndex;
- if (LZ4_read32(match) == LZ4_read32(ip))
- {
- size_t mlt;
- const BYTE* vLimit = ip + (dictLimit - matchIndex);
- if (vLimit > iLimit) vLimit = iLimit;
- mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, vLimit) + MINMATCH;
- if ((ip+mlt == vLimit) && (vLimit < iLimit))
- mlt += LZ4_count(ip+mlt, base+dictLimit, iLimit);
- if (mlt > ml) { ml = mlt; *matchpos = base + matchIndex; } /* virtual matchpos */
- }
- }
- matchIndex -= DELTANEXTU16(matchIndex);
- }
-
- return (int)ml;
-}
-
-
-FORCE_INLINE int LZ4HC_InsertAndGetWiderMatch (
- LZ4HC_Data_Structure* hc4,
- const BYTE* const ip,
- const BYTE* const iLowLimit,
- const BYTE* const iHighLimit,
- int longest,
- const BYTE** matchpos,
- const BYTE** startpos,
- const int maxNbAttempts)
-{
- U16* const chainTable = hc4->chainTable;
- U32* const HashTable = hc4->hashTable;
- const BYTE* const base = hc4->base;
- const U32 dictLimit = hc4->dictLimit;
- const BYTE* const lowPrefixPtr = base + dictLimit;
- const U32 lowLimit = (hc4->lowLimit + 64 KB > (U32)(ip-base)) ? hc4->lowLimit : (U32)(ip - base) - (64 KB - 1);
- const BYTE* const dictBase = hc4->dictBase;
- U32 matchIndex;
- int nbAttempts = maxNbAttempts;
- int delta = (int)(ip-iLowLimit);
-
-
- /* First Match */
- LZ4HC_Insert(hc4, ip);
- matchIndex = HashTable[LZ4HC_hashPtr(ip)];
-
- while ((matchIndex>=lowLimit) && (nbAttempts))
- {
- nbAttempts--;
- if (matchIndex >= dictLimit)
- {
- const BYTE* matchPtr = base + matchIndex;
- if (*(iLowLimit + longest) == *(matchPtr - delta + longest))
- if (LZ4_read32(matchPtr) == LZ4_read32(ip))
- {
- int mlt = MINMATCH + LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, iHighLimit);
- int back = 0;
-
- while ((ip+back>iLowLimit)
- && (matchPtr+back > lowPrefixPtr)
- && (ip[back-1] == matchPtr[back-1]))
- back--;
-
- mlt -= back;
-
- if (mlt > longest)
- {
- longest = (int)mlt;
- *matchpos = matchPtr+back;
- *startpos = ip+back;
- }
- }
- }
- else
- {
- const BYTE* matchPtr = dictBase + matchIndex;
- if (LZ4_read32(matchPtr) == LZ4_read32(ip))
- {
- size_t mlt;
- int back=0;
- const BYTE* vLimit = ip + (dictLimit - matchIndex);
- if (vLimit > iHighLimit) vLimit = iHighLimit;
- mlt = LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, vLimit) + MINMATCH;
- if ((ip+mlt == vLimit) && (vLimit < iHighLimit))
- mlt += LZ4_count(ip+mlt, base+dictLimit, iHighLimit);
- while ((ip+back > iLowLimit) && (matchIndex+back > lowLimit) && (ip[back-1] == matchPtr[back-1])) back--;
- mlt -= back;
- if ((int)mlt > longest) { longest = (int)mlt; *matchpos = base + matchIndex + back; *startpos = ip+back; }
- }
- }
- matchIndex -= DELTANEXTU16(matchIndex);
- }
-
- return longest;
-}
-
-
-typedef enum { noLimit = 0, limitedOutput = 1 } limitedOutput_directive;
-
-#define LZ4HC_DEBUG 0
-#if LZ4HC_DEBUG
-static unsigned debug = 0;
-#endif
-
-FORCE_INLINE int LZ4HC_encodeSequence (
- const BYTE** ip,
- BYTE** op,
- const BYTE** anchor,
- int matchLength,
- const BYTE* const match,
- limitedOutput_directive limitedOutputBuffer,
- BYTE* oend)
-{
- int length;
- BYTE* token;
-
-#if LZ4HC_DEBUG
- if (debug) printf("literal : %u -- match : %u -- offset : %u\n", (U32)(*ip - *anchor), (U32)matchLength, (U32)(*ip-match));
-#endif
-
- /* Encode Literal length */
- length = (int)(*ip - *anchor);
- token = (*op)++;
- if ((limitedOutputBuffer) && ((*op + (length>>8) + length + (2 + 1 + LASTLITERALS)) > oend)) return 1; /* Check output limit */
- if (length>=(int)RUN_MASK) { int len; *token=(RUN_MASK<<ML_BITS); len = length-RUN_MASK; for(; len > 254 ; len-=255) *(*op)++ = 255; *(*op)++ = (BYTE)len; }
- else *token = (BYTE)(length<<ML_BITS);
-
- /* Copy Literals */
- LZ4_wildCopy(*op, *anchor, (*op) + length);
- *op += length;
-
- /* Encode Offset */
- LZ4_writeLE16(*op, (U16)(*ip-match)); *op += 2;
-
- /* Encode MatchLength */
- length = (int)(matchLength-MINMATCH);
- if ((limitedOutputBuffer) && (*op + (length>>8) + (1 + LASTLITERALS) > oend)) return 1; /* Check output limit */
- if (length>=(int)ML_MASK) { *token+=ML_MASK; length-=ML_MASK; for(; length > 509 ; length-=510) { *(*op)++ = 255; *(*op)++ = 255; } if (length > 254) { length-=255; *(*op)++ = 255; } *(*op)++ = (BYTE)length; }
- else *token += (BYTE)(length);
-
- /* Prepare next loop */
- *ip += matchLength;
- *anchor = *ip;
-
- return 0;
-}
-
-
-static int LZ4HC_compress_generic (
- void* ctxvoid,
- const char* source,
- char* dest,
- int inputSize,
- int maxOutputSize,
- int compressionLevel,
- limitedOutput_directive limit
- )
-{
- LZ4HC_Data_Structure* ctx = (LZ4HC_Data_Structure*) ctxvoid;
- const BYTE* ip = (const BYTE*) source;
- const BYTE* anchor = ip;
- const BYTE* const iend = ip + inputSize;
- const BYTE* const mflimit = iend - MFLIMIT;
- const BYTE* const matchlimit = (iend - LASTLITERALS);
-
- BYTE* op = (BYTE*) dest;
- BYTE* const oend = op + maxOutputSize;
-
- unsigned maxNbAttempts;
- int ml, ml2, ml3, ml0;
- const BYTE* ref=NULL;
- const BYTE* start2=NULL;
- const BYTE* ref2=NULL;
- const BYTE* start3=NULL;
- const BYTE* ref3=NULL;
- const BYTE* start0;
- const BYTE* ref0;
-
-
- /* init */
- if (compressionLevel > g_maxCompressionLevel) compressionLevel = g_maxCompressionLevel;
- if (compressionLevel < 1) compressionLevel = LZ4HC_compressionLevel_default;
- maxNbAttempts = 1 << (compressionLevel-1);
- ctx->end += inputSize;
-
- ip++;
-
- /* Main Loop */
- while (ip < mflimit)
- {
- ml = LZ4HC_InsertAndFindBestMatch (ctx, ip, matchlimit, (&ref), maxNbAttempts);
- if (!ml) { ip++; continue; }
-
- /* saved, in case we would skip too much */
- start0 = ip;
- ref0 = ref;
- ml0 = ml;
-
-_Search2:
- if (ip+ml < mflimit)
- ml2 = LZ4HC_InsertAndGetWiderMatch(ctx, ip + ml - 2, ip + 1, matchlimit, ml, &ref2, &start2, maxNbAttempts);
- else ml2 = ml;
-
- if (ml2 == ml) /* No better match */
- {
- if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0;
- continue;
- }
-
- if (start0 < ip)
- {
- if (start2 < ip + ml0) /* empirical */
- {
- ip = start0;
- ref = ref0;
- ml = ml0;
- }
- }
-
- /* Here, start0==ip */
- if ((start2 - ip) < 3) /* First Match too small : removed */
- {
- ml = ml2;
- ip = start2;
- ref =ref2;
- goto _Search2;
- }
-
-_Search3:
- /*
- * Currently we have :
- * ml2 > ml1, and
- * ip1+3 <= ip2 (usually < ip1+ml1)
- */
- if ((start2 - ip) < OPTIMAL_ML)
- {
- int correction;
- int new_ml = ml;
- if (new_ml > OPTIMAL_ML) new_ml = OPTIMAL_ML;
- if (ip+new_ml > start2 + ml2 - MINMATCH) new_ml = (int)(start2 - ip) + ml2 - MINMATCH;
- correction = new_ml - (int)(start2 - ip);
- if (correction > 0)
- {
- start2 += correction;
- ref2 += correction;
- ml2 -= correction;
- }
- }
- /* Now, we have start2 = ip+new_ml, with new_ml = min(ml, OPTIMAL_ML=18) */
-
- if (start2 + ml2 < mflimit)
- ml3 = LZ4HC_InsertAndGetWiderMatch(ctx, start2 + ml2 - 3, start2, matchlimit, ml2, &ref3, &start3, maxNbAttempts);
- else ml3 = ml2;
-
- if (ml3 == ml2) /* No better match : 2 sequences to encode */
- {
- /* ip & ref are known; Now for ml */
- if (start2 < ip+ml) ml = (int)(start2 - ip);
- /* Now, encode 2 sequences */
- if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0;
- ip = start2;
- if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml2, ref2, limit, oend)) return 0;
- continue;
- }
-
- if (start3 < ip+ml+3) /* Not enough space for match 2 : remove it */
- {
- if (start3 >= (ip+ml)) /* can write Seq1 immediately ==> Seq2 is removed, so Seq3 becomes Seq1 */
- {
- if (start2 < ip+ml)
- {
- int correction = (int)(ip+ml - start2);
- start2 += correction;
- ref2 += correction;
- ml2 -= correction;
- if (ml2 < MINMATCH)
- {
- start2 = start3;
- ref2 = ref3;
- ml2 = ml3;
- }
- }
-
- if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0;
- ip = start3;
- ref = ref3;
- ml = ml3;
-
- start0 = start2;
- ref0 = ref2;
- ml0 = ml2;
- goto _Search2;
- }
-
- start2 = start3;
- ref2 = ref3;
- ml2 = ml3;
- goto _Search3;
- }
-
- /*
- * OK, now we have 3 ascending matches; let's write at least the first one
- * ip & ref are known; Now for ml
- */
- if (start2 < ip+ml)
- {
- if ((start2 - ip) < (int)ML_MASK)
- {
- int correction;
- if (ml > OPTIMAL_ML) ml = OPTIMAL_ML;
- if (ip + ml > start2 + ml2 - MINMATCH) ml = (int)(start2 - ip) + ml2 - MINMATCH;
- correction = ml - (int)(start2 - ip);
- if (correction > 0)
- {
- start2 += correction;
- ref2 += correction;
- ml2 -= correction;
- }
- }
- else
- {
- ml = (int)(start2 - ip);
- }
- }
- if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0;
-
- ip = start2;
- ref = ref2;
- ml = ml2;
-
- start2 = start3;
- ref2 = ref3;
- ml2 = ml3;
-
- goto _Search3;
- }
-
- /* Encode Last Literals */
- {
- int lastRun = (int)(iend - anchor);
- if ((limit) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize)) return 0; /* Check output limit */
- if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun > 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }
- else *op++ = (BYTE)(lastRun<<ML_BITS);
- memcpy(op, anchor, iend - anchor);
- op += iend-anchor;
- }
-
- /* End */
- return (int) (((char*)op)-dest);
-}
-
-
-int LZ4_sizeofStateHC(void) { return sizeof(LZ4HC_Data_Structure); }
-
-int LZ4_compress_HC_extStateHC (void* state, const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel)
-{
- if (((size_t)(state)&(sizeof(void*)-1)) != 0) return 0; /* Error : state is not aligned for pointers (32 or 64 bits) */
- LZ4HC_init ((LZ4HC_Data_Structure*)state, (const BYTE*)src);
- if (maxDstSize < LZ4_compressBound(srcSize))
- return LZ4HC_compress_generic (state, src, dst, srcSize, maxDstSize, compressionLevel, limitedOutput);
- else
- return LZ4HC_compress_generic (state, src, dst, srcSize, maxDstSize, compressionLevel, noLimit);
-}
-
-int LZ4_compress_HC(const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel)
-{
- LZ4HC_Data_Structure state;
- return LZ4_compress_HC_extStateHC(&state, src, dst, srcSize, maxDstSize, compressionLevel);
-}
-
-
-
-/**************************************
-* Streaming Functions
-**************************************/
-/* allocation */
-LZ4_streamHC_t* LZ4_createStreamHC(void) { return (LZ4_streamHC_t*)malloc(sizeof(LZ4_streamHC_t)); }
-int LZ4_freeStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr) { free(LZ4_streamHCPtr); return 0; }
-
-
-/* initialization */
-void LZ4_resetStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel)
-{
- LZ4_STATIC_ASSERT(sizeof(LZ4HC_Data_Structure) <= sizeof(LZ4_streamHC_t)); /* if compilation fails here, LZ4_STREAMHCSIZE must be increased */
- ((LZ4HC_Data_Structure*)LZ4_streamHCPtr)->base = NULL;
- ((LZ4HC_Data_Structure*)LZ4_streamHCPtr)->compressionLevel = (unsigned)compressionLevel;
-}
-
-int LZ4_loadDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, const char* dictionary, int dictSize)
-{
- LZ4HC_Data_Structure* ctxPtr = (LZ4HC_Data_Structure*) LZ4_streamHCPtr;
- if (dictSize > 64 KB)
- {
- dictionary += dictSize - 64 KB;
- dictSize = 64 KB;
- }
- LZ4HC_init (ctxPtr, (const BYTE*)dictionary);
- if (dictSize >= 4) LZ4HC_Insert (ctxPtr, (const BYTE*)dictionary +(dictSize-3));
- ctxPtr->end = (const BYTE*)dictionary + dictSize;
- return dictSize;
-}
-
-
-/* compression */
-
-static void LZ4HC_setExternalDict(LZ4HC_Data_Structure* ctxPtr, const BYTE* newBlock)
-{
- if (ctxPtr->end >= ctxPtr->base + 4)
- LZ4HC_Insert (ctxPtr, ctxPtr->end-3); /* Referencing remaining dictionary content */
- /* Only one memory segment for extDict, so any previous extDict is lost at this stage */
- ctxPtr->lowLimit = ctxPtr->dictLimit;
- ctxPtr->dictLimit = (U32)(ctxPtr->end - ctxPtr->base);
- ctxPtr->dictBase = ctxPtr->base;
- ctxPtr->base = newBlock - ctxPtr->dictLimit;
- ctxPtr->end = newBlock;
- ctxPtr->nextToUpdate = ctxPtr->dictLimit; /* match referencing will resume from there */
-}
-
-static int LZ4_compressHC_continue_generic (LZ4HC_Data_Structure* ctxPtr,
- const char* source, char* dest,
- int inputSize, int maxOutputSize, limitedOutput_directive limit)
-{
- /* auto-init if forgotten */
- if (ctxPtr->base == NULL)
- LZ4HC_init (ctxPtr, (const BYTE*) source);
-
- /* Check overflow */
- if ((size_t)(ctxPtr->end - ctxPtr->base) > 2 GB)
- {
- size_t dictSize = (size_t)(ctxPtr->end - ctxPtr->base) - ctxPtr->dictLimit;
- if (dictSize > 64 KB) dictSize = 64 KB;
-
- LZ4_loadDictHC((LZ4_streamHC_t*)ctxPtr, (const char*)(ctxPtr->end) - dictSize, (int)dictSize);
- }
-
- /* Check if blocks follow each other */
- if ((const BYTE*)source != ctxPtr->end)
- LZ4HC_setExternalDict(ctxPtr, (const BYTE*)source);
-
- /* Check overlapping input/dictionary space */
- {
- const BYTE* sourceEnd = (const BYTE*) source + inputSize;
- const BYTE* dictBegin = ctxPtr->dictBase + ctxPtr->lowLimit;
- const BYTE* dictEnd = ctxPtr->dictBase + ctxPtr->dictLimit;
- if ((sourceEnd > dictBegin) && ((const BYTE*)source < dictEnd))
- {
- if (sourceEnd > dictEnd) sourceEnd = dictEnd;
- ctxPtr->lowLimit = (U32)(sourceEnd - ctxPtr->dictBase);
- if (ctxPtr->dictLimit - ctxPtr->lowLimit < 4) ctxPtr->lowLimit = ctxPtr->dictLimit;
- }
- }
-
- return LZ4HC_compress_generic (ctxPtr, source, dest, inputSize, maxOutputSize, ctxPtr->compressionLevel, limit);
-}
-
-int LZ4_compress_HC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize)
-{
- if (maxOutputSize < LZ4_compressBound(inputSize))
- return LZ4_compressHC_continue_generic ((LZ4HC_Data_Structure*)LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, limitedOutput);
- else
- return LZ4_compressHC_continue_generic ((LZ4HC_Data_Structure*)LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, noLimit);
-}
-
-
-/* dictionary saving */
-
-int LZ4_saveDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, char* safeBuffer, int dictSize)
-{
- LZ4HC_Data_Structure* streamPtr = (LZ4HC_Data_Structure*)LZ4_streamHCPtr;
- int prefixSize = (int)(streamPtr->end - (streamPtr->base + streamPtr->dictLimit));
- if (dictSize > 64 KB) dictSize = 64 KB;
- if (dictSize < 4) dictSize = 0;
- if (dictSize > prefixSize) dictSize = prefixSize;
- memmove(safeBuffer, streamPtr->end - dictSize, dictSize);
- {
- U32 endIndex = (U32)(streamPtr->end - streamPtr->base);
- streamPtr->end = (const BYTE*)safeBuffer + dictSize;
- streamPtr->base = streamPtr->end - endIndex;
- streamPtr->dictLimit = endIndex - dictSize;
- streamPtr->lowLimit = endIndex - dictSize;
- if (streamPtr->nextToUpdate < streamPtr->dictLimit) streamPtr->nextToUpdate = streamPtr->dictLimit;
- }
- return dictSize;
-}
-
-
-/***********************************
-* Deprecated Functions
-***********************************/
-/* Deprecated compression functions */
-/* These functions are planned to start generate warnings by r131 approximately */
-int LZ4_compressHC(const char* src, char* dst, int srcSize) { return LZ4_compress_HC (src, dst, srcSize, LZ4_compressBound(srcSize), 0); }
-int LZ4_compressHC_limitedOutput(const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_HC(src, dst, srcSize, maxDstSize, 0); }
-int LZ4_compressHC2(const char* src, char* dst, int srcSize, int cLevel) { return LZ4_compress_HC (src, dst, srcSize, LZ4_compressBound(srcSize), cLevel); }
-int LZ4_compressHC2_limitedOutput(const char* src, char* dst, int srcSize, int maxDstSize, int cLevel) { return LZ4_compress_HC(src, dst, srcSize, maxDstSize, cLevel); }
-int LZ4_compressHC_withStateHC (void* state, const char* src, char* dst, int srcSize) { return LZ4_compress_HC_extStateHC (state, src, dst, srcSize, LZ4_compressBound(srcSize), 0); }
-int LZ4_compressHC_limitedOutput_withStateHC (void* state, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_HC_extStateHC (state, src, dst, srcSize, maxDstSize, 0); }
-int LZ4_compressHC2_withStateHC (void* state, const char* src, char* dst, int srcSize, int cLevel) { return LZ4_compress_HC_extStateHC(state, src, dst, srcSize, LZ4_compressBound(srcSize), cLevel); }
-int LZ4_compressHC2_limitedOutput_withStateHC (void* state, const char* src, char* dst, int srcSize, int maxDstSize, int cLevel) { return LZ4_compress_HC_extStateHC(state, src, dst, srcSize, maxDstSize, cLevel); }
-int LZ4_compressHC_continue (LZ4_streamHC_t* ctx, const char* src, char* dst, int srcSize) { return LZ4_compress_HC_continue (ctx, src, dst, srcSize, LZ4_compressBound(srcSize)); }
-int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* ctx, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_HC_continue (ctx, src, dst, srcSize, maxDstSize); }
-
-
-/* Deprecated streaming functions */
-/* These functions currently generate deprecation warnings */
-int LZ4_sizeofStreamStateHC(void) { return LZ4_STREAMHCSIZE; }
-
-int LZ4_resetStreamStateHC(void* state, char* inputBuffer)
-{
- if ((((size_t)state) & (sizeof(void*)-1)) != 0) return 1; /* Error : pointer is not aligned for pointer (32 or 64 bits) */
- LZ4HC_init((LZ4HC_Data_Structure*)state, (const BYTE*)inputBuffer);
- ((LZ4HC_Data_Structure*)state)->inputBuffer = (BYTE*)inputBuffer;
- return 0;
-}
-
-void* LZ4_createHC (char* inputBuffer)
-{
- void* hc4 = ALLOCATOR(1, sizeof(LZ4HC_Data_Structure));
- if (hc4 == NULL) return NULL; /* not enough memory */
- LZ4HC_init ((LZ4HC_Data_Structure*)hc4, (const BYTE*)inputBuffer);
- ((LZ4HC_Data_Structure*)hc4)->inputBuffer = (BYTE*)inputBuffer;
- return hc4;
-}
-
-int LZ4_freeHC (void* LZ4HC_Data)
-{
- FREEMEM(LZ4HC_Data);
- return (0);
-}
-
-int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel)
-{
- return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, 0, compressionLevel, noLimit);
-}
-
-int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel)
-{
- return LZ4HC_compress_generic (LZ4HC_Data, source, dest, inputSize, maxOutputSize, compressionLevel, limitedOutput);
-}
-
-char* LZ4_slideInputBufferHC(void* LZ4HC_Data)
-{
- LZ4HC_Data_Structure* hc4 = (LZ4HC_Data_Structure*)LZ4HC_Data;
- int dictSize = LZ4_saveDictHC((LZ4_streamHC_t*)LZ4HC_Data, (char*)(hc4->inputBuffer), 64 KB);
- return (char*)(hc4->inputBuffer + dictSize);
-}
http://git-wip-us.apache.org/repos/asf/orc/blob/590245a0/c++/libs/lz4-r131/lib/lz4hc.h
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/lib/lz4hc.h b/c++/libs/lz4-r131/lib/lz4hc.h
deleted file mode 100644
index 431f7c8..0000000
--- a/c++/libs/lz4-r131/lib/lz4hc.h
+++ /dev/null
@@ -1,189 +0,0 @@
-/*
- LZ4 HC - High Compression Mode of LZ4
- Header File
- Copyright (C) 2011-2015, 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 source repository : https://github.com/Cyan4973/lz4
- - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
-*/
-#pragma once
-
-
-#if defined (__cplusplus)
-extern "C" {
-#endif
-
-/*****************************
-* Includes
-*****************************/
-#include <stddef.h> /* size_t */
-
-
-/**************************************
-* Block Compression
-**************************************/
-int LZ4_compress_HC (const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel);
-/*
-LZ4_compress_HC :
- Destination buffer 'dst' must be already allocated.
- Compression completion is guaranteed if 'dst' buffer is sized to handle worst circumstances (data not compressible)
- Worst size evaluation is provided by function LZ4_compressBound() (see "lz4.h")
- srcSize : Max supported value is LZ4_MAX_INPUT_SIZE (see "lz4.h")
- compressionLevel : Recommended values are between 4 and 9, although any value between 0 and 16 will work.
- 0 means "use default value" (see lz4hc.c).
- Values >16 behave the same as 16.
- return : the number of bytes written into buffer 'dst'
- or 0 if compression fails.
-*/
-
-
-/* Note :
- Decompression functions are provided within LZ4 source code (see "lz4.h") (BSD license)
-*/
-
-
-int LZ4_sizeofStateHC(void);
-int LZ4_compress_HC_extStateHC(void* state, const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel);
-/*
-LZ4_compress_HC_extStateHC() :
- Use this function if you prefer to manually allocate memory for compression tables.
- To know how much memory must be allocated for the compression tables, use :
- int LZ4_sizeofStateHC();
-
- Allocated memory must be aligned on 8-bytes boundaries (which a normal malloc() will do properly).
-
- The allocated memory can then be provided to the compression functions using 'void* state' parameter.
- LZ4_compress_HC_extStateHC() is equivalent to previously described function.
- It just uses externally allocated memory for stateHC.
-*/
-
-
-/**************************************
-* Streaming Compression
-**************************************/
-#define LZ4_STREAMHCSIZE 262192
-#define LZ4_STREAMHCSIZE_SIZET (LZ4_STREAMHCSIZE / sizeof(size_t))
-typedef struct { size_t table[LZ4_STREAMHCSIZE_SIZET]; } LZ4_streamHC_t;
-/*
- LZ4_streamHC_t
- This structure allows static allocation of LZ4 HC streaming state.
- State must then be initialized using LZ4_resetStreamHC() before first use.
-
- Static allocation should only be used in combination with static linking.
- If you want to use LZ4 as a DLL, please use construction functions below, which are future-proof.
-*/
-
-
-LZ4_streamHC_t* LZ4_createStreamHC(void);
-int LZ4_freeStreamHC (LZ4_streamHC_t* streamHCPtr);
-/*
- These functions create and release memory for LZ4 HC streaming state.
- Newly created states are already initialized.
- Existing state space can be re-used anytime using LZ4_resetStreamHC().
- If you use LZ4 as a DLL, use these functions instead of static structure allocation,
- to avoid size mismatch between different versions.
-*/
-
-void LZ4_resetStreamHC (LZ4_streamHC_t* streamHCPtr, int compressionLevel);
-int LZ4_loadDictHC (LZ4_streamHC_t* streamHCPtr, const char* dictionary, int dictSize);
-
-int LZ4_compress_HC_continue (LZ4_streamHC_t* streamHCPtr, const char* src, char* dst, int srcSize, int maxDstSize);
-
-int LZ4_saveDictHC (LZ4_streamHC_t* streamHCPtr, char* safeBuffer, int maxDictSize);
-
-/*
- These functions compress data in successive blocks of any size, using previous blocks as dictionary.
- One key assumption is that previous blocks (up to 64 KB) remain read-accessible while compressing next blocks.
- There is an exception for ring buffers, which can be smaller 64 KB.
- Such case is automatically detected and correctly handled by LZ4_compress_HC_continue().
-
- Before starting compression, state must be properly initialized, using LZ4_resetStreamHC().
- A first "fictional block" can then be designated as initial dictionary, using LZ4_loadDictHC() (Optional).
-
- Then, use LZ4_compress_HC_continue() to compress each successive block.
- It works like LZ4_compress_HC(), but use previous memory blocks as dictionary to improve compression.
- Previous memory blocks (including initial dictionary when present) must remain accessible and unmodified during compression.
- As a reminder, size 'dst' buffer to handle worst cases, using LZ4_compressBound(), to ensure success of compression operation.
-
- If, for any reason, previous data blocks can't be preserved unmodified in memory during next compression block,
- you must save it to a safer memory space, using LZ4_saveDictHC().
- Return value of LZ4_saveDictHC() is the size of dictionary effectively saved into 'safeBuffer'.
-*/
-
-
-
-/**************************************
-* Deprecated Functions
-**************************************/
-/* Deprecate Warnings */
-/* Should these warnings messages be a problem,
- it is generally possible to disable them,
- with -Wno-deprecated-declarations for gcc
- or _CRT_SECURE_NO_WARNINGS in Visual for example.
- You can also define LZ4_DEPRECATE_WARNING_DEFBLOCK. */
-#ifndef LZ4_DEPRECATE_WARNING_DEFBLOCK
-# define LZ4_DEPRECATE_WARNING_DEFBLOCK
-# define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
-# if (LZ4_GCC_VERSION >= 405) || defined(__clang__)
-# define LZ4_DEPRECATED(message) __attribute__((deprecated(message)))
-# elif (LZ4_GCC_VERSION >= 301)
-# define LZ4_DEPRECATED(message) __attribute__((deprecated))
-# elif defined(_MSC_VER)
-# define LZ4_DEPRECATED(message) __declspec(deprecated(message))
-# else
-# pragma message("WARNING: You need to implement LZ4_DEPRECATED for this compiler")
-# define LZ4_DEPRECATED(message)
-# endif
-#endif // LZ4_DEPRECATE_WARNING_DEFBLOCK
-
-/* compression functions */
-/* these functions are planned to trigger warning messages by r131 approximately */
-int LZ4_compressHC (const char* source, char* dest, int inputSize);
-int LZ4_compressHC_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize);
-int LZ4_compressHC2 (const char* source, char* dest, int inputSize, int compressionLevel);
-int LZ4_compressHC2_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel);
-int LZ4_compressHC_withStateHC (void* state, const char* source, char* dest, int inputSize);
-int LZ4_compressHC_limitedOutput_withStateHC (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
-int LZ4_compressHC2_withStateHC (void* state, const char* source, char* dest, int inputSize, int compressionLevel);
-int LZ4_compressHC2_limitedOutput_withStateHC(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel);
-int LZ4_compressHC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize);
-int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize);
-
-/* Streaming functions following the older model; should no longer be used */
-LZ4_DEPRECATED("use LZ4_createStreamHC() instead") void* LZ4_createHC (char* inputBuffer);
-LZ4_DEPRECATED("use LZ4_saveDictHC() instead") char* LZ4_slideInputBufferHC (void* LZ4HC_Data);
-LZ4_DEPRECATED("use LZ4_freeStreamHC() instead") int LZ4_freeHC (void* LZ4HC_Data);
-LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel);
-LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel);
-LZ4_DEPRECATED("use LZ4_createStreamHC() instead") int LZ4_sizeofStreamStateHC(void);
-LZ4_DEPRECATED("use LZ4_resetStreamHC() instead") int LZ4_resetStreamStateHC(void* state, char* inputBuffer);
-
-
-#if defined (__cplusplus)
-}
-#endif
http://git-wip-us.apache.org/repos/asf/orc/blob/590245a0/c++/libs/lz4-r131/lib/xxhash.c
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/lib/xxhash.c b/c++/libs/lz4-r131/lib/xxhash.c
deleted file mode 100644
index e6fb8f1..0000000
--- a/c++/libs/lz4-r131/lib/xxhash.c
+++ /dev/null
@@ -1,915 +0,0 @@
-/*
-xxHash - Fast Hash algorithm
-Copyright (C) 2012-2015, 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 :
-- xxHash source repository : https://github.com/Cyan4973/xxHash
-*/
-
-
-/**************************************
-* Tuning parameters
-**************************************/
-/* Unaligned memory access is automatically enabled for "common" CPU, such as x86.
- * For others CPU, the compiler will be more cautious, and insert extra code to ensure aligned access is respected.
- * If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance.
- * You can also enable this parameter if you know your input data will always be aligned (boundaries of 4, for U32).
- */
-#if defined(__ARM_FEATURE_UNALIGNED) || defined(__i386) || defined(_M_IX86) || defined(__x86_64__) || defined(_M_X64)
-# define XXH_USE_UNALIGNED_ACCESS 1
-#endif
-
-/* XXH_ACCEPT_NULL_INPUT_POINTER :
- * If the input pointer is a null pointer, xxHash default behavior is to trigger a memory access error, since it is a bad pointer.
- * When this option is enabled, xxHash output for null input pointers will be the same as a null-length input.
- * By default, this option is disabled. To enable it, uncomment below define :
- */
-/* #define XXH_ACCEPT_NULL_INPUT_POINTER 1 */
-
-/* XXH_FORCE_NATIVE_FORMAT :
- * By default, xxHash library provides endian-independant Hash values, based on little-endian convention.
- * Results are therefore identical for little-endian and big-endian CPU.
- * This comes at a performance cost for big-endian CPU, since some swapping is required to emulate little-endian format.
- * Should endian-independance be of no importance for your application, you may set the #define below to 1.
- * It will improve speed for Big-endian CPU.
- * This option has no impact on Little_Endian CPU.
- */
-#define XXH_FORCE_NATIVE_FORMAT 0
-
-
-/**************************************
-* Compiler Specific Options
-***************************************/
-#ifdef _MSC_VER /* Visual Studio */
-# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
-# define FORCE_INLINE static __forceinline
-#else
-# if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */
-# ifdef __GNUC__
-# define FORCE_INLINE static inline __attribute__((always_inline))
-# else
-# define FORCE_INLINE static inline
-# endif
-# else
-# define FORCE_INLINE static
-# endif /* __STDC_VERSION__ */
-#endif
-
-
-/**************************************
-* Includes & Memory related functions
-***************************************/
-#include "xxhash.h"
-/* Modify the local functions below should you wish to use some other memory routines */
-/* for malloc(), free() */
-#include <stdlib.h>
-static void* XXH_malloc(size_t s) { return malloc(s); }
-static void XXH_free (void* p) { free(p); }
-/* for memcpy() */
-#include <string.h>
-static void* XXH_memcpy(void* dest, const void* src, size_t size) { return memcpy(dest,src,size); }
-
-
-/**************************************
-* Basic Types
-***************************************/
-#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */
-# include <stdint.h>
- typedef uint8_t BYTE;
- typedef uint16_t U16;
- typedef uint32_t U32;
- typedef int32_t S32;
- typedef uint64_t U64;
-#else
- typedef unsigned char BYTE;
- typedef unsigned short U16;
- typedef unsigned int U32;
- typedef signed int S32;
- typedef unsigned long long U64;
-#endif
-
-static U32 XXH_read32(const void* memPtr)
-{
- U32 val32;
- memcpy(&val32, memPtr, 4);
- return val32;
-}
-
-static U64 XXH_read64(const void* memPtr)
-{
- U64 val64;
- memcpy(&val64, memPtr, 8);
- return val64;
-}
-
-
-
-/******************************************
-* Compiler-specific Functions and Macros
-******************************************/
-#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
-
-/* Note : although _rotl exists for minGW (GCC under windows), performance seems poor */
-#if defined(_MSC_VER)
-# define XXH_rotl32(x,r) _rotl(x,r)
-# define XXH_rotl64(x,r) _rotl64(x,r)
-#else
-# define XXH_rotl32(x,r) ((x << r) | (x >> (32 - r)))
-# define XXH_rotl64(x,r) ((x << r) | (x >> (64 - r)))
-#endif
-
-#if defined(_MSC_VER) /* Visual Studio */
-# define XXH_swap32 _byteswap_ulong
-# define XXH_swap64 _byteswap_uint64
-#elif GCC_VERSION >= 403
-# define XXH_swap32 __builtin_bswap32
-# define XXH_swap64 __builtin_bswap64
-#else
-static U32 XXH_swap32 (U32 x)
-{
- return ((x << 24) & 0xff000000 ) |
- ((x << 8) & 0x00ff0000 ) |
- ((x >> 8) & 0x0000ff00 ) |
- ((x >> 24) & 0x000000ff );
-}
-static U64 XXH_swap64 (U64 x)
-{
- return ((x << 56) & 0xff00000000000000ULL) |
- ((x << 40) & 0x00ff000000000000ULL) |
- ((x << 24) & 0x0000ff0000000000ULL) |
- ((x << 8) & 0x000000ff00000000ULL) |
- ((x >> 8) & 0x00000000ff000000ULL) |
- ((x >> 24) & 0x0000000000ff0000ULL) |
- ((x >> 40) & 0x000000000000ff00ULL) |
- ((x >> 56) & 0x00000000000000ffULL);
-}
-#endif
-
-
-/***************************************
-* Architecture Macros
-***************************************/
-typedef enum { XXH_bigEndian=0, XXH_littleEndian=1 } XXH_endianess;
-#ifndef XXH_CPU_LITTLE_ENDIAN /* XXH_CPU_LITTLE_ENDIAN can be defined externally, for example using a compiler switch */
-static const int one = 1;
-# define XXH_CPU_LITTLE_ENDIAN (*(const char*)(&one))
-#endif
-
-
-/*****************************
-* Memory reads
-*****************************/
-typedef enum { XXH_aligned, XXH_unaligned } XXH_alignment;
-
-FORCE_INLINE U32 XXH_readLE32_align(const void* ptr, XXH_endianess endian, XXH_alignment align)
-{
- if (align==XXH_unaligned)
- return endian==XXH_littleEndian ? XXH_read32(ptr) : XXH_swap32(XXH_read32(ptr));
- else
- return endian==XXH_littleEndian ? *(const U32*)ptr : XXH_swap32(*(const U32*)ptr);
-}
-
-FORCE_INLINE U32 XXH_readLE32(const void* ptr, XXH_endianess endian)
-{
- return XXH_readLE32_align(ptr, endian, XXH_unaligned);
-}
-
-FORCE_INLINE U64 XXH_readLE64_align(const void* ptr, XXH_endianess endian, XXH_alignment align)
-{
- if (align==XXH_unaligned)
- return endian==XXH_littleEndian ? XXH_read64(ptr) : XXH_swap64(XXH_read64(ptr));
- else
- return endian==XXH_littleEndian ? *(const U64*)ptr : XXH_swap64(*(const U64*)ptr);
-}
-
-FORCE_INLINE U64 XXH_readLE64(const void* ptr, XXH_endianess endian)
-{
- return XXH_readLE64_align(ptr, endian, XXH_unaligned);
-}
-
-
-/***************************************
-* Macros
-***************************************/
-#define XXH_STATIC_ASSERT(c) { enum { XXH_static_assert = 1/(!!(c)) }; } /* use only *after* variable declarations */
-
-
-/***************************************
-* Constants
-***************************************/
-#define PRIME32_1 2654435761U
-#define PRIME32_2 2246822519U
-#define PRIME32_3 3266489917U
-#define PRIME32_4 668265263U
-#define PRIME32_5 374761393U
-
-#define PRIME64_1 11400714785074694791ULL
-#define PRIME64_2 14029467366897019727ULL
-#define PRIME64_3 1609587929392839161ULL
-#define PRIME64_4 9650029242287828579ULL
-#define PRIME64_5 2870177450012600261ULL
-
-
-/*****************************
-* Simple Hash Functions
-*****************************/
-FORCE_INLINE U32 XXH32_endian_align(const void* input, size_t len, U32 seed, XXH_endianess endian, XXH_alignment align)
-{
- const BYTE* p = (const BYTE*)input;
- const BYTE* bEnd = p + len;
- U32 h32;
-#define XXH_get32bits(p) XXH_readLE32_align(p, endian, align)
-
-#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
- if (p==NULL)
- {
- len=0;
- bEnd=p=(const BYTE*)(size_t)16;
- }
-#endif
-
- if (len>=16)
- {
- const BYTE* const limit = bEnd - 16;
- U32 v1 = seed + PRIME32_1 + PRIME32_2;
- U32 v2 = seed + PRIME32_2;
- U32 v3 = seed + 0;
- U32 v4 = seed - PRIME32_1;
-
- do
- {
- v1 += XXH_get32bits(p) * PRIME32_2;
- v1 = XXH_rotl32(v1, 13);
- v1 *= PRIME32_1;
- p+=4;
- v2 += XXH_get32bits(p) * PRIME32_2;
- v2 = XXH_rotl32(v2, 13);
- v2 *= PRIME32_1;
- p+=4;
- v3 += XXH_get32bits(p) * PRIME32_2;
- v3 = XXH_rotl32(v3, 13);
- v3 *= PRIME32_1;
- p+=4;
- v4 += XXH_get32bits(p) * PRIME32_2;
- v4 = XXH_rotl32(v4, 13);
- v4 *= PRIME32_1;
- p+=4;
- }
- while (p<=limit);
-
- h32 = XXH_rotl32(v1, 1) + XXH_rotl32(v2, 7) + XXH_rotl32(v3, 12) + XXH_rotl32(v4, 18);
- }
- else
- {
- h32 = seed + PRIME32_5;
- }
-
- h32 += (U32) len;
-
- while (p+4<=bEnd)
- {
- h32 += XXH_get32bits(p) * PRIME32_3;
- h32 = XXH_rotl32(h32, 17) * PRIME32_4 ;
- p+=4;
- }
-
- while (p<bEnd)
- {
- h32 += (*p) * PRIME32_5;
- h32 = XXH_rotl32(h32, 11) * PRIME32_1 ;
- p++;
- }
-
- h32 ^= h32 >> 15;
- h32 *= PRIME32_2;
- h32 ^= h32 >> 13;
- h32 *= PRIME32_3;
- h32 ^= h32 >> 16;
-
- return h32;
-}
-
-
-unsigned XXH32 (const void* input, size_t len, unsigned seed)
-{
-#if 0
- /* Simple version, good for code maintenance, but unfortunately slow for small inputs */
- XXH32_state_t state;
- XXH32_reset(&state, seed);
- XXH32_update(&state, input, len);
- return XXH32_digest(&state);
-#else
- XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
-
-# if !defined(XXH_USE_UNALIGNED_ACCESS)
- if ((((size_t)input) & 3) == 0) /* Input is 4-bytes aligned, leverage the speed benefit */
- {
- if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
- return XXH32_endian_align(input, len, seed, XXH_littleEndian, XXH_aligned);
- else
- return XXH32_endian_align(input, len, seed, XXH_bigEndian, XXH_aligned);
- }
-# endif
-
- if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
- return XXH32_endian_align(input, len, seed, XXH_littleEndian, XXH_unaligned);
- else
- return XXH32_endian_align(input, len, seed, XXH_bigEndian, XXH_unaligned);
-#endif
-}
-
-FORCE_INLINE U64 XXH64_endian_align(const void* input, size_t len, U64 seed, XXH_endianess endian, XXH_alignment align)
-{
- const BYTE* p = (const BYTE*)input;
- const BYTE* bEnd = p + len;
- U64 h64;
-#define XXH_get64bits(p) XXH_readLE64_align(p, endian, align)
-
-#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
- if (p==NULL)
- {
- len=0;
- bEnd=p=(const BYTE*)(size_t)32;
- }
-#endif
-
- if (len>=32)
- {
- const BYTE* const limit = bEnd - 32;
- U64 v1 = seed + PRIME64_1 + PRIME64_2;
- U64 v2 = seed + PRIME64_2;
- U64 v3 = seed + 0;
- U64 v4 = seed - PRIME64_1;
-
- do
- {
- v1 += XXH_get64bits(p) * PRIME64_2;
- p+=8;
- v1 = XXH_rotl64(v1, 31);
- v1 *= PRIME64_1;
- v2 += XXH_get64bits(p) * PRIME64_2;
- p+=8;
- v2 = XXH_rotl64(v2, 31);
- v2 *= PRIME64_1;
- v3 += XXH_get64bits(p) * PRIME64_2;
- p+=8;
- v3 = XXH_rotl64(v3, 31);
- v3 *= PRIME64_1;
- v4 += XXH_get64bits(p) * PRIME64_2;
- p+=8;
- v4 = XXH_rotl64(v4, 31);
- v4 *= PRIME64_1;
- }
- while (p<=limit);
-
- h64 = XXH_rotl64(v1, 1) + XXH_rotl64(v2, 7) + XXH_rotl64(v3, 12) + XXH_rotl64(v4, 18);
-
- v1 *= PRIME64_2;
- v1 = XXH_rotl64(v1, 31);
- v1 *= PRIME64_1;
- h64 ^= v1;
- h64 = h64 * PRIME64_1 + PRIME64_4;
-
- v2 *= PRIME64_2;
- v2 = XXH_rotl64(v2, 31);
- v2 *= PRIME64_1;
- h64 ^= v2;
- h64 = h64 * PRIME64_1 + PRIME64_4;
-
- v3 *= PRIME64_2;
- v3 = XXH_rotl64(v3, 31);
- v3 *= PRIME64_1;
- h64 ^= v3;
- h64 = h64 * PRIME64_1 + PRIME64_4;
-
- v4 *= PRIME64_2;
- v4 = XXH_rotl64(v4, 31);
- v4 *= PRIME64_1;
- h64 ^= v4;
- h64 = h64 * PRIME64_1 + PRIME64_4;
- }
- else
- {
- h64 = seed + PRIME64_5;
- }
-
- h64 += (U64) len;
-
- while (p+8<=bEnd)
- {
- U64 k1 = XXH_get64bits(p);
- k1 *= PRIME64_2;
- k1 = XXH_rotl64(k1,31);
- k1 *= PRIME64_1;
- h64 ^= k1;
- h64 = XXH_rotl64(h64,27) * PRIME64_1 + PRIME64_4;
- p+=8;
- }
-
- if (p+4<=bEnd)
- {
- h64 ^= (U64)(XXH_get32bits(p)) * PRIME64_1;
- h64 = XXH_rotl64(h64, 23) * PRIME64_2 + PRIME64_3;
- p+=4;
- }
-
- while (p<bEnd)
- {
- h64 ^= (*p) * PRIME64_5;
- h64 = XXH_rotl64(h64, 11) * PRIME64_1;
- p++;
- }
-
- h64 ^= h64 >> 33;
- h64 *= PRIME64_2;
- h64 ^= h64 >> 29;
- h64 *= PRIME64_3;
- h64 ^= h64 >> 32;
-
- return h64;
-}
-
-
-unsigned long long XXH64 (const void* input, size_t len, unsigned long long seed)
-{
-#if 0
- /* Simple version, good for code maintenance, but unfortunately slow for small inputs */
- XXH64_state_t state;
- XXH64_reset(&state, seed);
- XXH64_update(&state, input, len);
- return XXH64_digest(&state);
-#else
- XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
-
-# if !defined(XXH_USE_UNALIGNED_ACCESS)
- if ((((size_t)input) & 7)==0) /* Input is aligned, let's leverage the speed advantage */
- {
- if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
- return XXH64_endian_align(input, len, seed, XXH_littleEndian, XXH_aligned);
- else
- return XXH64_endian_align(input, len, seed, XXH_bigEndian, XXH_aligned);
- }
-# endif
-
- if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
- return XXH64_endian_align(input, len, seed, XXH_littleEndian, XXH_unaligned);
- else
- return XXH64_endian_align(input, len, seed, XXH_bigEndian, XXH_unaligned);
-#endif
-}
-
-/****************************************************
-* Advanced Hash Functions
-****************************************************/
-
-/*** Allocation ***/
-typedef struct
-{
- U64 total_len;
- U32 seed;
- U32 v1;
- U32 v2;
- U32 v3;
- U32 v4;
- U32 mem32[4]; /* defined as U32 for alignment */
- U32 memsize;
-} XXH_istate32_t;
-
-typedef struct
-{
- U64 total_len;
- U64 seed;
- U64 v1;
- U64 v2;
- U64 v3;
- U64 v4;
- U64 mem64[4]; /* defined as U64 for alignment */
- U32 memsize;
-} XXH_istate64_t;
-
-
-XXH32_state_t* XXH32_createState(void)
-{
- XXH_STATIC_ASSERT(sizeof(XXH32_state_t) >= sizeof(XXH_istate32_t)); /* A compilation error here means XXH32_state_t is not large enough */
- return (XXH32_state_t*)XXH_malloc(sizeof(XXH32_state_t));
-}
-XXH_errorcode XXH32_freeState(XXH32_state_t* statePtr)
-{
- XXH_free(statePtr);
- return XXH_OK;
-}
-
-XXH64_state_t* XXH64_createState(void)
-{
- XXH_STATIC_ASSERT(sizeof(XXH64_state_t) >= sizeof(XXH_istate64_t)); /* A compilation error here means XXH64_state_t is not large enough */
- return (XXH64_state_t*)XXH_malloc(sizeof(XXH64_state_t));
-}
-XXH_errorcode XXH64_freeState(XXH64_state_t* statePtr)
-{
- XXH_free(statePtr);
- return XXH_OK;
-}
-
-
-/*** Hash feed ***/
-
-XXH_errorcode XXH32_reset(XXH32_state_t* state_in, U32 seed)
-{
- XXH_istate32_t* state = (XXH_istate32_t*) state_in;
- state->seed = seed;
- state->v1 = seed + PRIME32_1 + PRIME32_2;
- state->v2 = seed + PRIME32_2;
- state->v3 = seed + 0;
- state->v4 = seed - PRIME32_1;
- state->total_len = 0;
- state->memsize = 0;
- return XXH_OK;
-}
-
-XXH_errorcode XXH64_reset(XXH64_state_t* state_in, unsigned long long seed)
-{
- XXH_istate64_t* state = (XXH_istate64_t*) state_in;
- state->seed = seed;
- state->v1 = seed + PRIME64_1 + PRIME64_2;
- state->v2 = seed + PRIME64_2;
- state->v3 = seed + 0;
- state->v4 = seed - PRIME64_1;
- state->total_len = 0;
- state->memsize = 0;
- return XXH_OK;
-}
-
-
-FORCE_INLINE XXH_errorcode XXH32_update_endian (XXH32_state_t* state_in, const void* input, size_t len, XXH_endianess endian)
-{
- XXH_istate32_t* state = (XXH_istate32_t *) state_in;
- const BYTE* p = (const BYTE*)input;
- const BYTE* const bEnd = p + len;
-
-#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
- if (input==NULL) return XXH_ERROR;
-#endif
-
- state->total_len += len;
-
- if (state->memsize + len < 16) /* fill in tmp buffer */
- {
- XXH_memcpy((BYTE*)(state->mem32) + state->memsize, input, len);
- state->memsize += (U32)len;
- return XXH_OK;
- }
-
- if (state->memsize) /* some data left from previous update */
- {
- XXH_memcpy((BYTE*)(state->mem32) + state->memsize, input, 16-state->memsize);
- {
- const U32* p32 = state->mem32;
- state->v1 += XXH_readLE32(p32, endian) * PRIME32_2;
- state->v1 = XXH_rotl32(state->v1, 13);
- state->v1 *= PRIME32_1;
- p32++;
- state->v2 += XXH_readLE32(p32, endian) * PRIME32_2;
- state->v2 = XXH_rotl32(state->v2, 13);
- state->v2 *= PRIME32_1;
- p32++;
- state->v3 += XXH_readLE32(p32, endian) * PRIME32_2;
- state->v3 = XXH_rotl32(state->v3, 13);
- state->v3 *= PRIME32_1;
- p32++;
- state->v4 += XXH_readLE32(p32, endian) * PRIME32_2;
- state->v4 = XXH_rotl32(state->v4, 13);
- state->v4 *= PRIME32_1;
- p32++;
- }
- p += 16-state->memsize;
- state->memsize = 0;
- }
-
- if (p <= bEnd-16)
- {
- const BYTE* const limit = bEnd - 16;
- U32 v1 = state->v1;
- U32 v2 = state->v2;
- U32 v3 = state->v3;
- U32 v4 = state->v4;
-
- do
- {
- v1 += XXH_readLE32(p, endian) * PRIME32_2;
- v1 = XXH_rotl32(v1, 13);
- v1 *= PRIME32_1;
- p+=4;
- v2 += XXH_readLE32(p, endian) * PRIME32_2;
- v2 = XXH_rotl32(v2, 13);
- v2 *= PRIME32_1;
- p+=4;
- v3 += XXH_readLE32(p, endian) * PRIME32_2;
- v3 = XXH_rotl32(v3, 13);
- v3 *= PRIME32_1;
- p+=4;
- v4 += XXH_readLE32(p, endian) * PRIME32_2;
- v4 = XXH_rotl32(v4, 13);
- v4 *= PRIME32_1;
- p+=4;
- }
- while (p<=limit);
-
- state->v1 = v1;
- state->v2 = v2;
- state->v3 = v3;
- state->v4 = v4;
- }
-
- if (p < bEnd)
- {
- XXH_memcpy(state->mem32, p, bEnd-p);
- state->memsize = (int)(bEnd-p);
- }
-
- return XXH_OK;
-}
-
-XXH_errorcode XXH32_update (XXH32_state_t* state_in, const void* input, size_t len)
-{
- XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
-
- if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
- return XXH32_update_endian(state_in, input, len, XXH_littleEndian);
- else
- return XXH32_update_endian(state_in, input, len, XXH_bigEndian);
-}
-
-
-
-FORCE_INLINE U32 XXH32_digest_endian (const XXH32_state_t* state_in, XXH_endianess endian)
-{
- const XXH_istate32_t* state = (const XXH_istate32_t*) state_in;
- const BYTE * p = (const BYTE*)state->mem32;
- const BYTE* bEnd = (const BYTE*)(state->mem32) + state->memsize;
- U32 h32;
-
- if (state->total_len >= 16)
- {
- h32 = XXH_rotl32(state->v1, 1) + XXH_rotl32(state->v2, 7) + XXH_rotl32(state->v3, 12) + XXH_rotl32(state->v4, 18);
- }
- else
- {
- h32 = state->seed + PRIME32_5;
- }
-
- h32 += (U32) state->total_len;
-
- while (p+4<=bEnd)
- {
- h32 += XXH_readLE32(p, endian) * PRIME32_3;
- h32 = XXH_rotl32(h32, 17) * PRIME32_4;
- p+=4;
- }
-
- while (p<bEnd)
- {
- h32 += (*p) * PRIME32_5;
- h32 = XXH_rotl32(h32, 11) * PRIME32_1;
- p++;
- }
-
- h32 ^= h32 >> 15;
- h32 *= PRIME32_2;
- h32 ^= h32 >> 13;
- h32 *= PRIME32_3;
- h32 ^= h32 >> 16;
-
- return h32;
-}
-
-
-U32 XXH32_digest (const XXH32_state_t* state_in)
-{
- XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
-
- if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
- return XXH32_digest_endian(state_in, XXH_littleEndian);
- else
- return XXH32_digest_endian(state_in, XXH_bigEndian);
-}
-
-
-FORCE_INLINE XXH_errorcode XXH64_update_endian (XXH64_state_t* state_in, const void* input, size_t len, XXH_endianess endian)
-{
- XXH_istate64_t * state = (XXH_istate64_t *) state_in;
- const BYTE* p = (const BYTE*)input;
- const BYTE* const bEnd = p + len;
-
-#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
- if (input==NULL) return XXH_ERROR;
-#endif
-
- state->total_len += len;
-
- if (state->memsize + len < 32) /* fill in tmp buffer */
- {
- XXH_memcpy(((BYTE*)state->mem64) + state->memsize, input, len);
- state->memsize += (U32)len;
- return XXH_OK;
- }
-
- if (state->memsize) /* some data left from previous update */
- {
- XXH_memcpy(((BYTE*)state->mem64) + state->memsize, input, 32-state->memsize);
- {
- const U64* p64 = state->mem64;
- state->v1 += XXH_readLE64(p64, endian) * PRIME64_2;
- state->v1 = XXH_rotl64(state->v1, 31);
- state->v1 *= PRIME64_1;
- p64++;
- state->v2 += XXH_readLE64(p64, endian) * PRIME64_2;
- state->v2 = XXH_rotl64(state->v2, 31);
- state->v2 *= PRIME64_1;
- p64++;
- state->v3 += XXH_readLE64(p64, endian) * PRIME64_2;
- state->v3 = XXH_rotl64(state->v3, 31);
- state->v3 *= PRIME64_1;
- p64++;
- state->v4 += XXH_readLE64(p64, endian) * PRIME64_2;
- state->v4 = XXH_rotl64(state->v4, 31);
- state->v4 *= PRIME64_1;
- p64++;
- }
- p += 32-state->memsize;
- state->memsize = 0;
- }
-
- if (p+32 <= bEnd)
- {
- const BYTE* const limit = bEnd - 32;
- U64 v1 = state->v1;
- U64 v2 = state->v2;
- U64 v3 = state->v3;
- U64 v4 = state->v4;
-
- do
- {
- v1 += XXH_readLE64(p, endian) * PRIME64_2;
- v1 = XXH_rotl64(v1, 31);
- v1 *= PRIME64_1;
- p+=8;
- v2 += XXH_readLE64(p, endian) * PRIME64_2;
- v2 = XXH_rotl64(v2, 31);
- v2 *= PRIME64_1;
- p+=8;
- v3 += XXH_readLE64(p, endian) * PRIME64_2;
- v3 = XXH_rotl64(v3, 31);
- v3 *= PRIME64_1;
- p+=8;
- v4 += XXH_readLE64(p, endian) * PRIME64_2;
- v4 = XXH_rotl64(v4, 31);
- v4 *= PRIME64_1;
- p+=8;
- }
- while (p<=limit);
-
- state->v1 = v1;
- state->v2 = v2;
- state->v3 = v3;
- state->v4 = v4;
- }
-
- if (p < bEnd)
- {
- XXH_memcpy(state->mem64, p, bEnd-p);
- state->memsize = (int)(bEnd-p);
- }
-
- return XXH_OK;
-}
-
-XXH_errorcode XXH64_update (XXH64_state_t* state_in, const void* input, size_t len)
-{
- XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
-
- if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
- return XXH64_update_endian(state_in, input, len, XXH_littleEndian);
- else
- return XXH64_update_endian(state_in, input, len, XXH_bigEndian);
-}
-
-
-
-FORCE_INLINE U64 XXH64_digest_endian (const XXH64_state_t* state_in, XXH_endianess endian)
-{
- const XXH_istate64_t * state = (const XXH_istate64_t *) state_in;
- const BYTE * p = (const BYTE*)state->mem64;
- const BYTE* bEnd = (const BYTE*)state->mem64 + state->memsize;
- U64 h64;
-
- if (state->total_len >= 32)
- {
- U64 v1 = state->v1;
- U64 v2 = state->v2;
- U64 v3 = state->v3;
- U64 v4 = state->v4;
-
- h64 = XXH_rotl64(v1, 1) + XXH_rotl64(v2, 7) + XXH_rotl64(v3, 12) + XXH_rotl64(v4, 18);
-
- v1 *= PRIME64_2;
- v1 = XXH_rotl64(v1, 31);
- v1 *= PRIME64_1;
- h64 ^= v1;
- h64 = h64*PRIME64_1 + PRIME64_4;
-
- v2 *= PRIME64_2;
- v2 = XXH_rotl64(v2, 31);
- v2 *= PRIME64_1;
- h64 ^= v2;
- h64 = h64*PRIME64_1 + PRIME64_4;
-
- v3 *= PRIME64_2;
- v3 = XXH_rotl64(v3, 31);
- v3 *= PRIME64_1;
- h64 ^= v3;
- h64 = h64*PRIME64_1 + PRIME64_4;
-
- v4 *= PRIME64_2;
- v4 = XXH_rotl64(v4, 31);
- v4 *= PRIME64_1;
- h64 ^= v4;
- h64 = h64*PRIME64_1 + PRIME64_4;
- }
- else
- {
- h64 = state->seed + PRIME64_5;
- }
-
- h64 += (U64) state->total_len;
-
- while (p+8<=bEnd)
- {
- U64 k1 = XXH_readLE64(p, endian);
- k1 *= PRIME64_2;
- k1 = XXH_rotl64(k1,31);
- k1 *= PRIME64_1;
- h64 ^= k1;
- h64 = XXH_rotl64(h64,27) * PRIME64_1 + PRIME64_4;
- p+=8;
- }
-
- if (p+4<=bEnd)
- {
- h64 ^= (U64)(XXH_readLE32(p, endian)) * PRIME64_1;
- h64 = XXH_rotl64(h64, 23) * PRIME64_2 + PRIME64_3;
- p+=4;
- }
-
- while (p<bEnd)
- {
- h64 ^= (*p) * PRIME64_5;
- h64 = XXH_rotl64(h64, 11) * PRIME64_1;
- p++;
- }
-
- h64 ^= h64 >> 33;
- h64 *= PRIME64_2;
- h64 ^= h64 >> 29;
- h64 *= PRIME64_3;
- h64 ^= h64 >> 32;
-
- return h64;
-}
-
-
-unsigned long long XXH64_digest (const XXH64_state_t* state_in)
-{
- XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
-
- if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
- return XXH64_digest_endian(state_in, XXH_littleEndian);
- else
- return XXH64_digest_endian(state_in, XXH_bigEndian);
-}
-
-
http://git-wip-us.apache.org/repos/asf/orc/blob/590245a0/c++/libs/lz4-r131/lib/xxhash.h
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/lib/xxhash.h b/c++/libs/lz4-r131/lib/xxhash.h
deleted file mode 100644
index c60aa61..0000000
--- a/c++/libs/lz4-r131/lib/xxhash.h
+++ /dev/null
@@ -1,192 +0,0 @@
-/*
- xxHash - Extremely Fast Hash algorithm
- Header File
- Copyright (C) 2012-2015, 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 :
- - xxHash source repository : https://github.com/Cyan4973/xxHash
-*/
-
-/* Notice extracted from xxHash homepage :
-
-xxHash is an extremely fast Hash algorithm, running at RAM speed limits.
-It also successfully passes all tests from the SMHasher suite.
-
-Comparison (single thread, Windows Seven 32 bits, using SMHasher on a Core 2 Duo @3GHz)
-
-Name Speed Q.Score Author
-xxHash 5.4 GB/s 10
-CrapWow 3.2 GB/s 2 Andrew
-MumurHash 3a 2.7 GB/s 10 Austin Appleby
-SpookyHash 2.0 GB/s 10 Bob Jenkins
-SBox 1.4 GB/s 9 Bret Mulvey
-Lookup3 1.2 GB/s 9 Bob Jenkins
-SuperFastHash 1.2 GB/s 1 Paul Hsieh
-CityHash64 1.05 GB/s 10 Pike & Alakuijala
-FNV 0.55 GB/s 5 Fowler, Noll, Vo
-CRC32 0.43 GB/s 9
-MD5-32 0.33 GB/s 10 Ronald L. Rivest
-SHA1-32 0.28 GB/s 10
-
-Q.Score is a measure of quality of the hash function.
-It depends on successfully passing SMHasher test set.
-10 is a perfect score.
-
-A 64-bits version, named XXH64, is available since r35.
-It offers much better speed, but for 64-bits applications only.
-Name Speed on 64 bits Speed on 32 bits
-XXH64 13.8 GB/s 1.9 GB/s
-XXH32 6.8 GB/s 6.0 GB/s
-*/
-
-#pragma once
-
-#if defined (__cplusplus)
-extern "C" {
-#endif
-
-
-/*****************************
-* Definitions
-*****************************/
-#include <stddef.h> /* size_t */
-typedef enum { XXH_OK=0, XXH_ERROR } XXH_errorcode;
-
-
-/*****************************
-* Namespace Emulation
-*****************************/
-/* Motivations :
-
-If you need to include xxHash into your library,
-but wish to avoid xxHash symbols to be present on your library interface
-in an effort to avoid potential name collision if another library also includes xxHash,
-
-you can use XXH_NAMESPACE, which will automatically prefix any symbol from xxHash
-with the value of XXH_NAMESPACE (so avoid to keep it NULL, and avoid numeric values).
-
-Note that no change is required within the calling program :
-it can still call xxHash functions using their regular name.
-They will be automatically translated by this header.
-*/
-#ifdef XXH_NAMESPACE
-# define XXH_CAT(A,B) A##B
-# define XXH_NAME2(A,B) XXH_CAT(A,B)
-# define XXH32 XXH_NAME2(XXH_NAMESPACE, XXH32)
-# define XXH64 XXH_NAME2(XXH_NAMESPACE, XXH64)
-# define XXH32_createState XXH_NAME2(XXH_NAMESPACE, XXH32_createState)
-# define XXH64_createState XXH_NAME2(XXH_NAMESPACE, XXH64_createState)
-# define XXH32_freeState XXH_NAME2(XXH_NAMESPACE, XXH32_freeState)
-# define XXH64_freeState XXH_NAME2(XXH_NAMESPACE, XXH64_freeState)
-# define XXH32_reset XXH_NAME2(XXH_NAMESPACE, XXH32_reset)
-# define XXH64_reset XXH_NAME2(XXH_NAMESPACE, XXH64_reset)
-# define XXH32_update XXH_NAME2(XXH_NAMESPACE, XXH32_update)
-# define XXH64_update XXH_NAME2(XXH_NAMESPACE, XXH64_update)
-# define XXH32_digest XXH_NAME2(XXH_NAMESPACE, XXH32_digest)
-# define XXH64_digest XXH_NAME2(XXH_NAMESPACE, XXH64_digest)
-#endif
-
-
-/*****************************
-* Simple Hash Functions
-*****************************/
-
-unsigned int XXH32 (const void* input, size_t length, unsigned seed);
-unsigned long long XXH64 (const void* input, size_t length, unsigned long long seed);
-
-/*
-XXH32() :
- Calculate the 32-bits hash of sequence "length" bytes stored at memory address "input".
- The memory between input & input+length must be valid (allocated and read-accessible).
- "seed" can be used to alter the result predictably.
- This function successfully passes all SMHasher tests.
- Speed on Core 2 Duo @ 3 GHz (single thread, SMHasher benchmark) : 5.4 GB/s
-XXH64() :
- Calculate the 64-bits hash of sequence of length "len" stored at memory address "input".
- Faster on 64-bits systems. Slower on 32-bits systems.
-*/
-
-
-
-/*****************************
-* Advanced Hash Functions
-*****************************/
-typedef struct { long long ll[ 6]; } XXH32_state_t;
-typedef struct { long long ll[11]; } XXH64_state_t;
-
-/*
-These structures allow static allocation of XXH states.
-States must then be initialized using XXHnn_reset() before first use.
-
-If you prefer dynamic allocation, please refer to functions below.
-*/
-
-XXH32_state_t* XXH32_createState(void);
-XXH_errorcode XXH32_freeState(XXH32_state_t* statePtr);
-
-XXH64_state_t* XXH64_createState(void);
-XXH_errorcode XXH64_freeState(XXH64_state_t* statePtr);
-
-/*
-These functions create and release memory for XXH state.
-States must then be initialized using XXHnn_reset() before first use.
-*/
-
-
-XXH_errorcode XXH32_reset (XXH32_state_t* statePtr, unsigned seed);
-XXH_errorcode XXH32_update (XXH32_state_t* statePtr, const void* input, size_t length);
-unsigned int XXH32_digest (const XXH32_state_t* statePtr);
-
-XXH_errorcode XXH64_reset (XXH64_state_t* statePtr, unsigned long long seed);
-XXH_errorcode XXH64_update (XXH64_state_t* statePtr, const void* input, size_t length);
-unsigned long long XXH64_digest (const XXH64_state_t* statePtr);
-
-/*
-These functions calculate the xxHash of an input provided in multiple smaller packets,
-as opposed to an input provided as a single block.
-
-XXH state space must first be allocated, using either static or dynamic method provided above.
-
-Start a new hash by initializing state with a seed, using XXHnn_reset().
-
-Then, feed the hash state by calling XXHnn_update() as many times as necessary.
-Obviously, input must be valid, meaning allocated and read accessible.
-The function returns an error code, with 0 meaning OK, and any other value meaning there is an error.
-
-Finally, you can produce a hash anytime, by using XXHnn_digest().
-This function returns the final nn-bits hash.
-You can nonetheless continue feeding the hash state with more input,
-and therefore get some new hashes, by calling again XXHnn_digest().
-
-When you are done, don't forget to free XXH state space, using typically XXHnn_freeState().
-*/
-
-
-#if defined (__cplusplus)
-}
-#endif
http://git-wip-us.apache.org/repos/asf/orc/blob/590245a0/c++/libs/lz4-r131/lz4_Block_format.md
----------------------------------------------------------------------
diff --git a/c++/libs/lz4-r131/lz4_Block_format.md b/c++/libs/lz4-r131/lz4_Block_format.md
deleted file mode 100644
index ea568d8..0000000
--- a/c++/libs/lz4-r131/lz4_Block_format.md
+++ /dev/null
@@ -1,127 +0,0 @@
-LZ4 Block Format Description
-============================
-Last revised: 2015-05-07.
-Author : Yann Collet
-
-
-This specification is intended for developers
-willing to produce LZ4-compatible compressed data blocks
-using any programming language.
-
-LZ4 is an LZ77-type compressor with a fixed, byte-oriented encoding.
-There is no entropy encoder back-end nor framing layer.
-The latter is assumed to be handled by other parts of the system (see [LZ4 Frame format]).
-This design is assumed to favor simplicity and speed.
-It helps later on for optimizations, compactness, and features.
-
-This document describes only the block format,
-not how the compressor nor decompressor actually work.
-The correctness of the decompressor should not depend
-on implementation details of the compressor, and vice versa.
-
-[LZ4 Frame format]: LZ4_Frame_format.md
-
-
-
-Compressed block format
------------------------
-An LZ4 compressed block is composed of sequences.
-A sequence is a suite of literals (not-compressed bytes),
-followed by a match copy.
-
-Each sequence starts with a token.
-The token is a one byte value, separated into two 4-bits fields.
-Therefore each field ranges from 0 to 15.
-
-
-The first field uses the 4 high-bits of the token.
-It provides the length of literals to follow.
-
-If the field value is 0, then there is no literal.
-If it is 15, then we need to add some more bytes to indicate the full length.
-Each additional byte then represent a value from 0 to 255,
-which is added to the previous value to produce a total length.
-When the byte value is 255, another byte is output.
-There can be any number of bytes following the token. There is no "size limit".
-(Side note : this is why a not-compressible input block is expanded by 0.4%).
-
-Example 1 : A length of 48 will be represented as :
-
- - 15 : value for the 4-bits High field
- - 33 : (=48-15) remaining length to reach 48
-
-Example 2 : A length of 280 will be represented as :
-
- - 15 : value for the 4-bits High field
- - 255 : following byte is maxed, since 280-15 >= 255
- - 10 : (=280 - 15 - 255) ) remaining length to reach 280
-
-Example 3 : A length of 15 will be represented as :
-
- - 15 : value for the 4-bits High field
- - 0 : (=15-15) yes, the zero must be output
-
-Following the token and optional length bytes, are the literals themselves.
-They are exactly as numerous as previously decoded (length of literals).
-It's possible that there are zero literal.
-
-
-Following the literals is the match copy operation.
-
-It starts by the offset.
-This is a 2 bytes value, in little endian format
-(the 1st byte is the "low" byte, the 2nd one is the "high" byte).
-
-The offset represents the position of the match to be copied from.
-1 means "current position - 1 byte".
-The maximum offset value is 65535, 65536 cannot be coded.
-Note that 0 is an invalid value, not used.
-
-Then we need to extract the match length.
-For this, we use the second token field, the low 4-bits.
-Value, obviously, ranges from 0 to 15.
-However here, 0 means that the copy operation will be minimal.
-The minimum length of a match, called minmatch, is 4.
-As a consequence, a 0 value means 4 bytes, and a value of 15 means 19+ bytes.
-Similar to literal length, on reaching the highest possible value (15),
-we output additional bytes, one at a time, with values ranging from 0 to 255.
-They are added to total to provide the final match length.
-A 255 value means there is another byte to read and add.
-There is no limit to the number of optional bytes that can be output this way.
-(This points towards a maximum achievable compression ratio of about 250).
-
-With the offset and the matchlength,
-the decoder can now proceed to copy the data from the already decoded buffer.
-On decoding the matchlength, we reach the end of the compressed sequence,
-and therefore start another one.
-
-
-Parsing restrictions
------------------------
-There are specific parsing rules to respect in order to remain compatible
-with assumptions made by the decoder :
-
-1. The last 5 bytes are always literals
-2. The last match must start at least 12 bytes before end of block.
- Consequently, a block with less than 13 bytes cannot be compressed.
-
-These rules are in place to ensure that the decoder
-will never read beyond the input buffer, nor write beyond the output buffer.
-
-Note that the last sequence is also incomplete,
-and stops right after literals.
-
-
-Additional notes
------------------------
-There is no assumption nor limits to the way the compressor
-searches and selects matches within the source data block.
-It could be a fast scan, a multi-probe, a full search using BST,
-standard hash chains or MMC, well whatever.
-
-Advanced parsing strategies can also be implemented, such as lazy match,
-or full optimal parsing.
-
-All these trade-off offer distinctive speed/memory/compression advantages.
-Whatever the method used by the compressor, its result will be decodable
-by any LZ4 decoder if it follows the format specification described above.