comparison contrib/python-zstandard/zstd/compress/huf_compress.c @ 40121:73fef626dae3

zstandard: vendor python-zstandard 0.10.1

This was just released.

The upstream source distribution from PyPI was extracted. Unwanted
files were removed.

The clang-format ignore list was updated to reflect the new source
of files.

setup.py was updated to pass a new argument to python-zstandard's
function for returning an Extension instance. Upstream had to change
to use relative paths because Python 3.7's packaging doesn't
seem to like absolute paths when defining sources, includes, etc.
The default relative path calculation is relative to setup_zstd.py
which is different from the directory of Mercurial's setup.py.

The project contains a vendored copy of zstandard 1.3.6. The old
version was 1.3.4.

The API should be backwards compatible and nothing in core should
need adjusted. However, there is a new "chunker" API that we
may find useful in places where we want to emit compressed chunks
of a fixed size.

There are a pair of bug fixes in 0.10.0 with regards to
compressobj() and decompressobj() when block flushing is used. I
actually found these bugs when introducing these APIs in Mercurial!
But existing Mercurial code is not affected because we don't
perform block flushing.

# no-check-commit because 3rd party code has different style guidelines

Differential Revision: https://phab.mercurial-scm.org/D4911

40120:89742f1fa6cb

/* **************************************************************
*  Includes
****************************************************************/
#include <string.h>     /* memcpy, memset */
#include <stdio.h>      /* printf (debug) */
#include "bitstream.h"
#include "compiler.h"
#define FSE_STATIC_LINKING_ONLY   /* FSE_optimalTableLog_internal */
#include "fse.h"        /* header compression */
#define HUF_STATIC_LINKING_ONLY
#include "huf.h"
#include "error_private.h"

/* **************************************************************
*  Error Management
****************************************************************/
#define HUF_isError ERR_isError
#define HUF_STATIC_ASSERT(c) { enum { HUF_static_assert = 1/(int)(!!(c)) }; }   /* use only *after* variable declarations */
#define CHECK_V_F(e, f) size_t const e = f; if (ERR_isError(e)) return e
#define CHECK_F(f)   { CHECK_V_F(_var_err__, f); }


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

 * Same as FSE_compress(), but dedicated to huff0's weights compression.
 * The use case needs much less stack memory.
 * Note : all elements within weightTable are supposed to be <= HUF_TABLELOG_MAX.
 */
#define MAX_FSE_TABLELOG_FOR_HUFF_HEADER 6
size_t HUF_compressWeights (void* dst, size_t dstSize, const void* weightTable, size_t wtSize)
{
    BYTE* const ostart = (BYTE*) dst;
    BYTE* op = ostart;
    BYTE* const oend = ostart + dstSize;

    /* init conditions */
    if (wtSize <= 1) return 0;  /* Not compressible */

    /* Scan input and build symbol stats */
    {   CHECK_V_F(maxCount, FSE_count_simple(count, &maxSymbolValue, weightTable, wtSize) );
        if (maxCount == wtSize) return 1;   /* only a single symbol in src : rle */
        if (maxCount == 1) return 0;         /* each symbol present maximum once => not compressible */
    }

    tableLog = FSE_optimalTableLog(tableLog, wtSize, maxSymbolValue);
    CHECK_F( FSE_normalizeCount(norm, tableLog, count, wtSize, maxSymbolValue) );

        { U32 n; for (n=0; n<nbSymbols; n++) CTable[n].val = valPerRank[CTable[n].nbBits]++; }
    }

    *maxSymbolValuePtr = nbSymbols - 1;
    return readSize;
}


typedef struct nodeElt_s {
    U32 count;

                                           src, srcSize,
                                           singleStream, oldHufTable, bmi2);
    }

    /* Scan input and build symbol stats */
    {   CHECK_V_F(largest, FSE_count_wksp (table->count, &maxSymbolValue, (const BYTE*)src, srcSize, table->count) );
        if (largest == srcSize) { *ostart = ((const BYTE*)src)[0]; return 1; }   /* single symbol, rle */
        if (largest <= (srcSize >> 7)+1) return 0;   /* heuristic : probably not compressible enough */
    }

    /* Check validity of previous table */
    if ( repeat
      && *repeat == HUF_repeat_check

40121:73fef626dae3

/* **************************************************************
*  Includes
****************************************************************/
#include <string.h>     /* memcpy, memset */
#include <stdio.h>      /* printf (debug) */
#include "compiler.h"
#include "bitstream.h"
#include "hist.h"
#define FSE_STATIC_LINKING_ONLY   /* FSE_optimalTableLog_internal */
#include "fse.h"        /* header compression */
#define HUF_STATIC_LINKING_ONLY
#include "huf.h"
#include "error_private.h"

/* **************************************************************
*  Error Management
****************************************************************/
#define HUF_isError ERR_isError
#define HUF_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c)   /* use only *after* variable declarations */
#define CHECK_V_F(e, f) size_t const e = f; if (ERR_isError(e)) return e
#define CHECK_F(f)   { CHECK_V_F(_var_err__, f); }


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

 * Same as FSE_compress(), but dedicated to huff0's weights compression.
 * The use case needs much less stack memory.
 * Note : all elements within weightTable are supposed to be <= HUF_TABLELOG_MAX.
 */
#define MAX_FSE_TABLELOG_FOR_HUFF_HEADER 6
static size_t HUF_compressWeights (void* dst, size_t dstSize, const void* weightTable, size_t wtSize)
{
    BYTE* const ostart = (BYTE*) dst;
    BYTE* op = ostart;
    BYTE* const oend = ostart + dstSize;

    /* init conditions */
    if (wtSize <= 1) return 0;  /* Not compressible */

    /* Scan input and build symbol stats */
    {   unsigned const maxCount = HIST_count_simple(count, &maxSymbolValue, weightTable, wtSize);   /* never fails */
        if (maxCount == wtSize) return 1;   /* only a single symbol in src : rle */
        if (maxCount == 1) return 0;        /* each symbol present maximum once => not compressible */
    }

    tableLog = FSE_optimalTableLog(tableLog, wtSize, maxSymbolValue);
    CHECK_F( FSE_normalizeCount(norm, tableLog, count, wtSize, maxSymbolValue) );

        { U32 n; for (n=0; n<nbSymbols; n++) CTable[n].val = valPerRank[CTable[n].nbBits]++; }
    }

    *maxSymbolValuePtr = nbSymbols - 1;
    return readSize;
}

U32 HUF_getNbBits(const void* symbolTable, U32 symbolValue)
{
    const HUF_CElt* table = (const HUF_CElt*)symbolTable;
    assert(symbolValue <= HUF_SYMBOLVALUE_MAX);
    return table[symbolValue].nbBits;
}


typedef struct nodeElt_s {
    U32 count;

                                           src, srcSize,
                                           singleStream, oldHufTable, bmi2);
    }

    /* Scan input and build symbol stats */
    {   CHECK_V_F(largest, HIST_count_wksp (table->count, &maxSymbolValue, (const BYTE*)src, srcSize, table->count) );
        if (largest == srcSize) { *ostart = ((const BYTE*)src)[0]; return 1; }   /* single symbol, rle */
        if (largest <= (srcSize >> 7)+4) return 0;   /* heuristic : probably not compressible enough */
    }

    /* Check validity of previous table */
    if ( repeat
      && *repeat == HUF_repeat_check