view contrib/python-zstandard/zstd/compress/zstd_compress_literals.c @ 44413:4cabeea6d214

hgext: start building a library for simple hooks

Many workflows depend on hooks to enforce certain policies, e.g. to
prevent forced pushes. The Mercurial Guide includes some cases and
Google can help finding others, but it can save users a lot of time
if hg itself has a couple of examples for further customization.

Differential Revision: https://phab.mercurial-scm.org/D6825

/*
 * 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.
 */

 /*-*************************************
 *  Dependencies
 ***************************************/
#include "zstd_compress_literals.h"

size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
    BYTE* const ostart = (BYTE* const)dst;
    U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);

    RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall);

    switch(flSize)
    {
        case 1: /* 2 - 1 - 5 */
            ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3));
            break;
        case 2: /* 2 - 2 - 12 */
            MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
            break;
        case 3: /* 2 - 2 - 20 */
            MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
            break;
        default:   /* not necessary : flSize is {1,2,3} */
            assert(0);
    }

    memcpy(ostart + flSize, src, srcSize);
    return srcSize + flSize;
}

size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
    BYTE* const ostart = (BYTE* const)dst;
    U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);

    (void)dstCapacity;  /* dstCapacity already guaranteed to be >=4, hence large enough */

    switch(flSize)
    {
        case 1: /* 2 - 1 - 5 */
            ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3));
            break;
        case 2: /* 2 - 2 - 12 */
            MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
            break;
        case 3: /* 2 - 2 - 20 */
            MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
            break;
        default:   /* not necessary : flSize is {1,2,3} */
            assert(0);
    }

    ostart[flSize] = *(const BYTE*)src;
    return flSize+1;
}

size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
                              ZSTD_hufCTables_t* nextHuf,
                              ZSTD_strategy strategy, int disableLiteralCompression,
                              void* dst, size_t dstCapacity,
                        const void* src, size_t srcSize,
                              void* entropyWorkspace, size_t entropyWorkspaceSize,
                        const int bmi2)
{
    size_t const minGain = ZSTD_minGain(srcSize, strategy);
    size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
    BYTE*  const ostart = (BYTE*)dst;
    U32 singleStream = srcSize < 256;
    symbolEncodingType_e hType = set_compressed;
    size_t cLitSize;

    DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i)",
                disableLiteralCompression);

    /* Prepare nextEntropy assuming reusing the existing table */
    memcpy(nextHuf, prevHuf, sizeof(*prevHuf));

    if (disableLiteralCompression)
        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);

    /* small ? don't even attempt compression (speed opt) */
#   define COMPRESS_LITERALS_SIZE_MIN 63
    {   size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
        if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
    }

    RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression");
    {   HUF_repeat repeat = prevHuf->repeatMode;
        int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
        if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
        cLitSize = singleStream ?
            HUF_compress1X_repeat(
                ostart+lhSize, dstCapacity-lhSize, src, srcSize,
                255, 11, entropyWorkspace, entropyWorkspaceSize,
                (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2) :
            HUF_compress4X_repeat(
                ostart+lhSize, dstCapacity-lhSize, src, srcSize,
                255, 11, entropyWorkspace, entropyWorkspaceSize,
                (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
        if (repeat != HUF_repeat_none) {
            /* reused the existing table */
            hType = set_repeat;
        }
    }

    if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
        memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
    }
    if (cLitSize==1) {
        memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
        return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
    }

    if (hType == set_compressed) {
        /* using a newly constructed table */
        nextHuf->repeatMode = HUF_repeat_check;
    }

    /* Build header */
    switch(lhSize)
    {
    case 3: /* 2 - 2 - 10 - 10 */
        {   U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
            MEM_writeLE24(ostart, lhc);
            break;
        }
    case 4: /* 2 - 2 - 14 - 14 */
        {   U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18);
            MEM_writeLE32(ostart, lhc);
            break;
        }
    case 5: /* 2 - 2 - 18 - 18 */
        {   U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
            MEM_writeLE32(ostart, lhc);
            ostart[4] = (BYTE)(cLitSize >> 10);
            break;
        }
    default:  /* not possible : lhSize is {3,4,5} */
        assert(0);
    }
    return lhSize+cLitSize;
}