zstd/lib/compress/zstd_double_fast.c

/*
 * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
 * All rights reserved.
 *
 * This source code is licensed under both the BSD-style license (found in the
 * LICENSE file in the root directory of this source tree) and the GPLv2 (found
 * in the COPYING file in the root directory of this source tree).
 * You may select, at your option, one of the above-listed licenses.
 */

#include "zstd_compress_internal.h"
#include "zstd_double_fast.h"


void ZSTD_fillDoubleHashTable(ZSTD_matchState_t* ms,
                              ZSTD_compressionParameters const* cParams,
                              void const* end, ZSTD_dictTableLoadMethod_e dtlm)
{
    U32* const hashLarge = ms->hashTable;
    U32  const hBitsL = cParams->hashLog;
    U32  const mls = cParams->searchLength;
    U32* const hashSmall = ms->chainTable;
    U32  const hBitsS = cParams->chainLog;
    const BYTE* const base = ms->window.base;
    const BYTE* ip = base + ms->nextToUpdate;
    const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE;
    const U32 fastHashFillStep = 3;

    /* Always insert every fastHashFillStep position into the hash tables.
     * Insert the other positions into the large hash table if their entry
     * is empty.
     */
    for (; ip + fastHashFillStep - 1 <= iend; ip += fastHashFillStep) {
        U32 const current = (U32)(ip - base);
        U32 i;
        for (i = 0; i < fastHashFillStep; ++i) {
            size_t const smHash = ZSTD_hashPtr(ip + i, hBitsS, mls);
            size_t const lgHash = ZSTD_hashPtr(ip + i, hBitsL, 8);
            if (i == 0)
                hashSmall[smHash] = current + i;
            if (i == 0 || hashLarge[lgHash] == 0)
                hashLarge[lgHash] = current + i;
            /* Only load extra positions for ZSTD_dtlm_full */
            if (dtlm == ZSTD_dtlm_fast)
                break;
        }
    }
}


FORCE_INLINE_TEMPLATE
size_t ZSTD_compressBlock_doubleFast_generic(
        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
        ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize,
        U32 const mls /* template */, ZSTD_dictMode_e const dictMode)
{
    U32* const hashLong = ms->hashTable;
    const U32 hBitsL = cParams->hashLog;
    U32* const hashSmall = ms->chainTable;
    const U32 hBitsS = cParams->chainLog;
    const BYTE* const base = ms->window.base;
    const BYTE* const istart = (const BYTE*)src;
    const BYTE* ip = istart;
    const BYTE* anchor = istart;
    const U32 prefixLowestIndex = ms->window.dictLimit;
    const BYTE* const prefixLowest = base + prefixLowestIndex;
    const BYTE* const iend = istart + srcSize;
    const BYTE* const ilimit = iend - HASH_READ_SIZE;
    U32 offset_1=rep[0], offset_2=rep[1];
    U32 offsetSaved = 0;

    const ZSTD_matchState_t* const dms = ms->dictMatchState;
    const U32* const dictHashLong  = dictMode == ZSTD_dictMatchState ?
                                     dms->hashTable : NULL;
    const U32* const dictHashSmall = dictMode == ZSTD_dictMatchState ?
                                     dms->hashTable : NULL;
    const U32 dictLowestIndex      = dictMode == ZSTD_dictMatchState ?
                                     dms->window.dictLimit : 0;
    const BYTE* const dictBase     = dictMode == ZSTD_dictMatchState ?
                                     dms->window.base : NULL;
    const BYTE* const dictLowest   = dictMode == ZSTD_dictMatchState ?
                                     dictBase + dictLowestIndex : NULL;
    const BYTE* const dictEnd      = dictMode == ZSTD_dictMatchState ?
                                     dms->window.nextSrc : NULL;
    const U32 dictIndexDelta       = dictMode == ZSTD_dictMatchState ?
                                     prefixLowestIndex - (U32)(dictEnd - dictBase) :
                                     0;

    assert(dictMode == ZSTD_noDict || dictMode == ZSTD_dictMatchState);

    /* init */
    ip += (dictMode == ZSTD_noDict && ip == prefixLowest);
    {   U32 const maxRep = dictMode == ZSTD_dictMatchState ?
                           (U32)(ip - dictLowest) :
                           (U32)(ip - prefixLowest);
        if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
        if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
    }

    /* Main Search Loop */
    while (ip < ilimit) {   /* < instead of <=, because repcode check at (ip+1) */
        size_t mLength;
        size_t const h2 = ZSTD_hashPtr(ip, hBitsL, 8);
        size_t const h = ZSTD_hashPtr(ip, hBitsS, mls);
        U32 const current = (U32)(ip-base);
        U32 const matchIndexL = hashLong[h2];
        U32 const matchIndexS = hashSmall[h];
        const BYTE* matchLong = base + matchIndexL;
        const BYTE* match = base + matchIndexS;
        const U32 repIndex = current + 1 - offset_1;
        const BYTE* repMatch = (dictMode == ZSTD_dictMatchState
                            && repIndex < prefixLowestIndex) ?
                               dictBase + (repIndex - dictIndexDelta) :
                               base + repIndex;
        hashLong[h2] = hashSmall[h] = current;   /* update hash tables */

        if (dictMode == ZSTD_dictMatchState
            && ((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */)
            && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
            const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend;
            mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, istart) + 4;
            ip++;
            ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
        } else if ( dictMode == ZSTD_noDict
                 && ((offset_1 > 0) & (MEM_read32(ip+1-offset_1) == MEM_read32(ip+1)))) {
            mLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4;
            ip++;
            ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
        } else {
            U32 offset;
            if ( (matchIndexL > prefixLowestIndex) && (MEM_read64(matchLong) == MEM_read64(ip)) ) {
                mLength = ZSTD_count(ip+8, matchLong+8, iend) + 8;
                offset = (U32)(ip-matchLong);
                while (((ip>anchor) & (matchLong>prefixLowest)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */
            } else if ( (matchIndexS > prefixLowestIndex) && (MEM_read32(match) == MEM_read32(ip)) ) {
                size_t const hl3 = ZSTD_hashPtr(ip+1, hBitsL, 8);
                U32 const matchIndexL3 = hashLong[hl3];
                const BYTE* matchL3 = base + matchIndexL3;
                hashLong[hl3] = current + 1;
                if ( (matchIndexL3 > prefixLowestIndex) && (MEM_read64(matchL3) == MEM_read64(ip+1)) ) {
                    mLength = ZSTD_count(ip+9, matchL3+8, iend) + 8;
                    ip++;
                    offset = (U32)(ip-matchL3);
                    while (((ip>anchor) & (matchL3>prefixLowest)) && (ip[-1] == matchL3[-1])) { ip--; matchL3--; mLength++; } /* catch up */
                } else {
                    mLength = ZSTD_count(ip+4, match+4, iend) + 4;
                    offset = (U32)(ip-match);
                    while (((ip>anchor) & (match>prefixLowest)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
                }
            } else if (dictMode == ZSTD_dictMatchState) {
                U32 const dictMatchIndexL = dictHashLong[h2];
                U32 const dictMatchIndexS = dictHashSmall[h];
                const BYTE* dictMatchL = dictBase + dictMatchIndexL;
                const BYTE* dictMatchS = dictBase + dictMatchIndexS;
                assert(dictMatchL < dictEnd);
                assert(dictMatchS < dictEnd);
                if (dictMatchL > dictLowest && MEM_read64(dictMatchL) == MEM_read64(ip)) {
                    mLength = ZSTD_count_2segments(ip+8, dictMatchL+8, iend, dictEnd, prefixLowest) + 8;
                    offset = (U32)(current - dictMatchIndexL - dictIndexDelta);
                    while (((ip>anchor) & (dictMatchL>dictLowest)) && (ip[-1] == dictMatchL[-1])) { ip--; dictMatchL--; mLength++; } /* catch up */
                } else if (dictMatchS > dictLowest && MEM_read32(dictMatchS) == MEM_read32(ip)) {
                    size_t const hl3 = ZSTD_hashPtr(ip+1, hBitsL, 8);
                    U32 const dictMatchIndexL3 = dictHashLong[hl3];
                    const BYTE* dictMatchL3 = dictBase + dictMatchIndexL3;
                    assert(dictMatchL3 < dictEnd);
                    if (dictMatchL3 > dictLowest && MEM_read64(dictMatchL3) == MEM_read64(ip)) {
                        mLength = ZSTD_count_2segments(ip+1+8, dictMatchL3+8, iend, dictEnd, prefixLowest) + 8;
                        ip++;
                        offset = (U32)(current + 1 - dictMatchIndexL3 - dictIndexDelta);
                        while (((ip>anchor) & (dictMatchL3>dictLowest)) && (ip[-1] == dictMatchL3[-1])) { ip--; dictMatchL3--; mLength++; } /* catch up */
                    } else {
                        mLength = ZSTD_count_2segments(ip+4, dictMatchS+4, iend, dictEnd, istart) + 4;
                        offset = (U32)(current - dictMatchIndexS - dictIndexDelta);
                        while (((ip>anchor) & (dictMatchS>dictLowest)) && (ip[-1] == dictMatchS[-1])) { ip--; dictMatchS--; mLength++; } /* catch up */
                    }
                } else {
                    ip += ((ip-anchor) >> kSearchStrength) + 1;
                    continue;
                }
            } else {
                ip += ((ip-anchor) >> kSearchStrength) + 1;
                continue;
            }

            offset_2 = offset_1;
            offset_1 = offset;

            ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
        }

        /* match found */
        ip += mLength;
        anchor = ip;

        if (ip <= ilimit) {
            /* Fill Table */
            hashLong[ZSTD_hashPtr(base+current+2, hBitsL, 8)] =
                hashSmall[ZSTD_hashPtr(base+current+2, hBitsS, mls)] = current+2;  /* here because current+2 could be > iend-8 */
            hashLong[ZSTD_hashPtr(ip-2, hBitsL, 8)] =
                hashSmall[ZSTD_hashPtr(ip-2, hBitsS, mls)] = (U32)(ip-2-base);

            /* check immediate repcode */
            if (dictMode == ZSTD_dictMatchState) {
                while (ip <= ilimit) {
                    U32 const current2 = (U32)(ip-base);
                    U32 const repIndex2 = current2 - offset_2;
                    const BYTE* repMatch2 = dictMode == ZSTD_dictMatchState
                        && repIndex2 < prefixLowestIndex ?
                            dictBase - dictIndexDelta + repIndex2 :
                            base + repIndex2;
                    if ( ((U32)((prefixLowestIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
                       && (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
                        const BYTE* const repEnd2 = repIndex2 < prefixLowestIndex ? dictEnd : iend;
                        size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, istart) + 4;
                        U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset;   /* swap offset_2 <=> offset_1 */
                        ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
                        hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = current2;
                        hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = current2;
                        ip += repLength2;
                        anchor = ip;
                        continue;
                    }
                    break;
                }
            }

            if (dictMode == ZSTD_noDict) {
                while ( (ip <= ilimit)
                     && (ip - offset_2 >= istart)
                     && ( (offset_2>0)
                        & (MEM_read32(ip) == MEM_read32(ip - offset_2)) )) {
                    /* store sequence */
                    size_t const rLength = ZSTD_count(ip+4, ip+4-offset_2, iend) + 4;
                    U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff;  /* swap offset_2 <=> offset_1 */
                    hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = (U32)(ip-base);
                    hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = (U32)(ip-base);
                    ZSTD_storeSeq(seqStore, 0, anchor, 0, rLength-MINMATCH);
                    ip += rLength;
                    anchor = ip;
                    continue;   /* faster when present ... (?) */
    }   }   }   }

    /* save reps for next block */
    rep[0] = offset_1 ? offset_1 : offsetSaved;
    rep[1] = offset_2 ? offset_2 : offsetSaved;

    /* Return the last literals size */
    return iend - anchor;
}


size_t ZSTD_compressBlock_doubleFast(
        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
        ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize)
{
    const U32 mls = cParams->searchLength;
    switch(mls)
    {
    default: /* includes case 3 */
    case 4 :
        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, cParams, src, srcSize, 4, ZSTD_noDict);
    case 5 :
        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, cParams, src, srcSize, 5, ZSTD_noDict);
    case 6 :
        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, cParams, src, srcSize, 6, ZSTD_noDict);
    case 7 :
        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, cParams, src, srcSize, 7, ZSTD_noDict);
    }
}


size_t ZSTD_compressBlock_doubleFast_dictMatchState(
        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
        ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize)
{
    const U32 mls = cParams->searchLength;
    switch(mls)
    {
    default: /* includes case 3 */
    case 4 :
        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, cParams, src, srcSize, 4, ZSTD_dictMatchState);
    case 5 :
        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, cParams, src, srcSize, 5, ZSTD_dictMatchState);
    case 6 :
        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, cParams, src, srcSize, 6, ZSTD_dictMatchState);
    case 7 :
        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, cParams, src, srcSize, 7, ZSTD_dictMatchState);
    }
}


static size_t ZSTD_compressBlock_doubleFast_extDict_generic(
        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
        ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize,
        U32 const mls /* template */)
{
    U32* const hashLong = ms->hashTable;
    U32  const hBitsL = cParams->hashLog;
    U32* const hashSmall = ms->chainTable;
    U32  const hBitsS = cParams->chainLog;
    const BYTE* const base = ms->window.base;
    const BYTE* const dictBase = ms->window.dictBase;
    const BYTE* const istart = (const BYTE*)src;
    const BYTE* ip = istart;
    const BYTE* anchor = istart;
    const U32   lowestIndex = ms->window.lowLimit;
    const BYTE* const dictStart = dictBase + lowestIndex;
    const U32   dictLimit = ms->window.dictLimit;
    const BYTE* const lowPrefixPtr = base + dictLimit;
    const BYTE* const dictEnd = dictBase + dictLimit;
    const BYTE* const iend = istart + srcSize;
    const BYTE* const ilimit = iend - 8;
    U32 offset_1=rep[0], offset_2=rep[1];

    DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_extDict_generic (srcSize=%zu)", srcSize);

    /* Search Loop */
    while (ip < ilimit) {  /* < instead of <=, because (ip+1) */
        const size_t hSmall = ZSTD_hashPtr(ip, hBitsS, mls);
        const U32 matchIndex = hashSmall[hSmall];
        const BYTE* matchBase = matchIndex < dictLimit ? dictBase : base;
        const BYTE* match = matchBase + matchIndex;

        const size_t hLong = ZSTD_hashPtr(ip, hBitsL, 8);
        const U32 matchLongIndex = hashLong[hLong];
        const BYTE* matchLongBase = matchLongIndex < dictLimit ? dictBase : base;
        const BYTE* matchLong = matchLongBase + matchLongIndex;

        const U32 current = (U32)(ip-base);
        const U32 repIndex = current + 1 - offset_1;   /* offset_1 expected <= current +1 */
        const BYTE* repBase = repIndex < dictLimit ? dictBase : base;
        const BYTE* repMatch = repBase + repIndex;
        size_t mLength;
        hashSmall[hSmall] = hashLong[hLong] = current;   /* update hash table */

        if ( (((U32)((dictLimit-1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > lowestIndex))
           && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
            const BYTE* repMatchEnd = repIndex < dictLimit ? dictEnd : iend;
            mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, lowPrefixPtr) + 4;
            ip++;
            ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
        } else {
            if ((matchLongIndex > lowestIndex) && (MEM_read64(matchLong) == MEM_read64(ip))) {
                const BYTE* matchEnd = matchLongIndex < dictLimit ? dictEnd : iend;
                const BYTE* lowMatchPtr = matchLongIndex < dictLimit ? dictStart : lowPrefixPtr;
                U32 offset;
                mLength = ZSTD_count_2segments(ip+8, matchLong+8, iend, matchEnd, lowPrefixPtr) + 8;
                offset = current - matchLongIndex;
                while (((ip>anchor) & (matchLong>lowMatchPtr)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; }   /* catch up */
                offset_2 = offset_1;
                offset_1 = offset;
                ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);

            } else if ((matchIndex > lowestIndex) && (MEM_read32(match) == MEM_read32(ip))) {
                size_t const h3 = ZSTD_hashPtr(ip+1, hBitsL, 8);
                U32 const matchIndex3 = hashLong[h3];
                const BYTE* const match3Base = matchIndex3 < dictLimit ? dictBase : base;
                const BYTE* match3 = match3Base + matchIndex3;
                U32 offset;
                hashLong[h3] = current + 1;
                if ( (matchIndex3 > lowestIndex) && (MEM_read64(match3) == MEM_read64(ip+1)) ) {
                    const BYTE* matchEnd = matchIndex3 < dictLimit ? dictEnd : iend;
                    const BYTE* lowMatchPtr = matchIndex3 < dictLimit ? dictStart : lowPrefixPtr;
                    mLength = ZSTD_count_2segments(ip+9, match3+8, iend, matchEnd, lowPrefixPtr) + 8;
                    ip++;
                    offset = current+1 - matchIndex3;
                    while (((ip>anchor) & (match3>lowMatchPtr)) && (ip[-1] == match3[-1])) { ip--; match3--; mLength++; } /* catch up */
                } else {
                    const BYTE* matchEnd = matchIndex < dictLimit ? dictEnd : iend;
                    const BYTE* lowMatchPtr = matchIndex < dictLimit ? dictStart : lowPrefixPtr;
                    mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, lowPrefixPtr) + 4;
                    offset = current - matchIndex;
                    while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; }   /* catch up */
                }
                offset_2 = offset_1;
                offset_1 = offset;
                ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);

            } else {
                ip += ((ip-anchor) >> kSearchStrength) + 1;
                continue;
        }   }

        /* found a match : store it */
        ip += mLength;
        anchor = ip;

        if (ip <= ilimit) {
            /* Fill Table */
            hashSmall[ZSTD_hashPtr(base+current+2, hBitsS, mls)] = current+2;
            hashLong[ZSTD_hashPtr(base+current+2, hBitsL, 8)] = current+2;
            hashSmall[ZSTD_hashPtr(ip-2, hBitsS, mls)] = (U32)(ip-2-base);
            hashLong[ZSTD_hashPtr(ip-2, hBitsL, 8)] = (U32)(ip-2-base);
            /* check immediate repcode */
            while (ip <= ilimit) {
                U32 const current2 = (U32)(ip-base);
                U32 const repIndex2 = current2 - offset_2;
                const BYTE* repMatch2 = repIndex2 < dictLimit ? dictBase + repIndex2 : base + repIndex2;
                if ( (((U32)((dictLimit-1) - repIndex2) >= 3) & (repIndex2 > lowestIndex))  /* intentional overflow */
                   && (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
                    const BYTE* const repEnd2 = repIndex2 < dictLimit ? dictEnd : iend;
                    size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, lowPrefixPtr) + 4;
                    U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset;   /* swap offset_2 <=> offset_1 */
                    ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
                    hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = current2;
                    hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = current2;
                    ip += repLength2;
                    anchor = ip;
                    continue;
                }
                break;
    }   }   }

    /* save reps for next block */
    rep[0] = offset_1;
    rep[1] = offset_2;

    /* Return the last literals size */
    return iend - anchor;
}


size_t ZSTD_compressBlock_doubleFast_extDict(
        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
        ZSTD_compressionParameters const* cParams, void const* src, size_t srcSize)
{
    U32 const mls = cParams->searchLength;
    switch(mls)
    {
    default: /* includes case 3 */
    case 4 :
        return ZSTD_compressBlock_doubleFast_extDict_generic(ms, seqStore, rep, cParams, src, srcSize, 4);
    case 5 :
        return ZSTD_compressBlock_doubleFast_extDict_generic(ms, seqStore, rep, cParams, src, srcSize, 5);
    case 6 :
        return ZSTD_compressBlock_doubleFast_extDict_generic(ms, seqStore, rep, cParams, src, srcSize, 6);
    case 7 :
        return ZSTD_compressBlock_doubleFast_extDict_generic(ms, seqStore, rep, cParams, src, srcSize, 7);
    }
}