view contrib/python-zstandard/zstd/decompress/zstd_ddict.c @ 45027:0ea9c86fac89 stable 5.4.2

convert: handle percent-encoded bytes in file URLs like Subversion

75b59d221aa3 added most of the code that gets removed by this patch. It helped
making progress on Python 3, but the reasoning was wrong in many ways. I tried
to retract it while it was queued, but it was too late.

Back then, I was asssuming that what happened on Python 2 (preserving bytes) is
correct and my Python 3 change is a hack. However it turned out that Subversion
interprets percent-encoded bytes as UTF-8. Accepting the same format as
Subversion is a good idea.

Consistency with urlreq.pathname2url() (as described in the removed comment)
doesn’t matter because that function is only used for passing paths to urllib.

This is not a backwards-incompatible change because before 5c0d5b48e58c,
non-ASCII filenames didn’t work at all on Python 2.

When the locale encoding is ISO-8859-15, `svn` accepts `file:///tmp/a%E2%82%AC`
for `/tmp/a€`. Before this patch, this was the case for this extension on
Python 3, but not on Python 2. This patch makes it work like with `svn` on both
Python 2 and Python 3.

/*
 * 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.
 */

/* zstd_ddict.c :
 * concentrates all logic that needs to know the internals of ZSTD_DDict object */

/*-*******************************************************
*  Dependencies
*********************************************************/
#include <string.h>      /* memcpy, memmove, memset */
#include "cpu.h"         /* bmi2 */
#include "mem.h"         /* low level memory routines */
#define FSE_STATIC_LINKING_ONLY
#include "fse.h"
#define HUF_STATIC_LINKING_ONLY
#include "huf.h"
#include "zstd_decompress_internal.h"
#include "zstd_ddict.h"

#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
#  include "zstd_legacy.h"
#endif



/*-*******************************************************
*  Types
*********************************************************/
struct ZSTD_DDict_s {
    void* dictBuffer;
    const void* dictContent;
    size_t dictSize;
    ZSTD_entropyDTables_t entropy;
    U32 dictID;
    U32 entropyPresent;
    ZSTD_customMem cMem;
};  /* typedef'd to ZSTD_DDict within "zstd.h" */

const void* ZSTD_DDict_dictContent(const ZSTD_DDict* ddict)
{
    assert(ddict != NULL);
    return ddict->dictContent;
}

size_t ZSTD_DDict_dictSize(const ZSTD_DDict* ddict)
{
    assert(ddict != NULL);
    return ddict->dictSize;
}

void ZSTD_copyDDictParameters(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict)
{
    DEBUGLOG(4, "ZSTD_copyDDictParameters");
    assert(dctx != NULL);
    assert(ddict != NULL);
    dctx->dictID = ddict->dictID;
    dctx->prefixStart = ddict->dictContent;
    dctx->virtualStart = ddict->dictContent;
    dctx->dictEnd = (const BYTE*)ddict->dictContent + ddict->dictSize;
    dctx->previousDstEnd = dctx->dictEnd;
    if (ddict->entropyPresent) {
        dctx->litEntropy = 1;
        dctx->fseEntropy = 1;
        dctx->LLTptr = ddict->entropy.LLTable;
        dctx->MLTptr = ddict->entropy.MLTable;
        dctx->OFTptr = ddict->entropy.OFTable;
        dctx->HUFptr = ddict->entropy.hufTable;
        dctx->entropy.rep[0] = ddict->entropy.rep[0];
        dctx->entropy.rep[1] = ddict->entropy.rep[1];
        dctx->entropy.rep[2] = ddict->entropy.rep[2];
    } else {
        dctx->litEntropy = 0;
        dctx->fseEntropy = 0;
    }
}


static size_t
ZSTD_loadEntropy_intoDDict(ZSTD_DDict* ddict,
                           ZSTD_dictContentType_e dictContentType)
{
    ddict->dictID = 0;
    ddict->entropyPresent = 0;
    if (dictContentType == ZSTD_dct_rawContent) return 0;

    if (ddict->dictSize < 8) {
        if (dictContentType == ZSTD_dct_fullDict)
            return ERROR(dictionary_corrupted);   /* only accept specified dictionaries */
        return 0;   /* pure content mode */
    }
    {   U32 const magic = MEM_readLE32(ddict->dictContent);
        if (magic != ZSTD_MAGIC_DICTIONARY) {
            if (dictContentType == ZSTD_dct_fullDict)
                return ERROR(dictionary_corrupted);   /* only accept specified dictionaries */
            return 0;   /* pure content mode */
        }
    }
    ddict->dictID = MEM_readLE32((const char*)ddict->dictContent + ZSTD_FRAMEIDSIZE);

    /* load entropy tables */
    RETURN_ERROR_IF(ZSTD_isError(ZSTD_loadDEntropy(
            &ddict->entropy, ddict->dictContent, ddict->dictSize)),
        dictionary_corrupted);
    ddict->entropyPresent = 1;
    return 0;
}


static size_t ZSTD_initDDict_internal(ZSTD_DDict* ddict,
                                      const void* dict, size_t dictSize,
                                      ZSTD_dictLoadMethod_e dictLoadMethod,
                                      ZSTD_dictContentType_e dictContentType)
{
    if ((dictLoadMethod == ZSTD_dlm_byRef) || (!dict) || (!dictSize)) {
        ddict->dictBuffer = NULL;
        ddict->dictContent = dict;
        if (!dict) dictSize = 0;
    } else {
        void* const internalBuffer = ZSTD_malloc(dictSize, ddict->cMem);
        ddict->dictBuffer = internalBuffer;
        ddict->dictContent = internalBuffer;
        if (!internalBuffer) return ERROR(memory_allocation);
        memcpy(internalBuffer, dict, dictSize);
    }
    ddict->dictSize = dictSize;
    ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001);  /* cover both little and big endian */

    /* parse dictionary content */
    FORWARD_IF_ERROR( ZSTD_loadEntropy_intoDDict(ddict, dictContentType) );

    return 0;
}

ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize,
                                      ZSTD_dictLoadMethod_e dictLoadMethod,
                                      ZSTD_dictContentType_e dictContentType,
                                      ZSTD_customMem customMem)
{
    if (!customMem.customAlloc ^ !customMem.customFree) return NULL;

    {   ZSTD_DDict* const ddict = (ZSTD_DDict*) ZSTD_malloc(sizeof(ZSTD_DDict), customMem);
        if (ddict == NULL) return NULL;
        ddict->cMem = customMem;
        {   size_t const initResult = ZSTD_initDDict_internal(ddict,
                                            dict, dictSize,
                                            dictLoadMethod, dictContentType);
            if (ZSTD_isError(initResult)) {
                ZSTD_freeDDict(ddict);
                return NULL;
        }   }
        return ddict;
    }
}

/*! ZSTD_createDDict() :
*   Create a digested dictionary, to start decompression without startup delay.
*   `dict` content is copied inside DDict.
*   Consequently, `dict` can be released after `ZSTD_DDict` creation */
ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize)
{
    ZSTD_customMem const allocator = { NULL, NULL, NULL };
    return ZSTD_createDDict_advanced(dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto, allocator);
}

/*! ZSTD_createDDict_byReference() :
 *  Create a digested dictionary, to start decompression without startup delay.
 *  Dictionary content is simply referenced, it will be accessed during decompression.
 *  Warning : dictBuffer must outlive DDict (DDict must be freed before dictBuffer) */
ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize)
{
    ZSTD_customMem const allocator = { NULL, NULL, NULL };
    return ZSTD_createDDict_advanced(dictBuffer, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto, allocator);
}


const ZSTD_DDict* ZSTD_initStaticDDict(
                                void* sBuffer, size_t sBufferSize,
                                const void* dict, size_t dictSize,
                                ZSTD_dictLoadMethod_e dictLoadMethod,
                                ZSTD_dictContentType_e dictContentType)
{
    size_t const neededSpace = sizeof(ZSTD_DDict)
                             + (dictLoadMethod == ZSTD_dlm_byRef ? 0 : dictSize);
    ZSTD_DDict* const ddict = (ZSTD_DDict*)sBuffer;
    assert(sBuffer != NULL);
    assert(dict != NULL);
    if ((size_t)sBuffer & 7) return NULL;   /* 8-aligned */
    if (sBufferSize < neededSpace) return NULL;
    if (dictLoadMethod == ZSTD_dlm_byCopy) {
        memcpy(ddict+1, dict, dictSize);  /* local copy */
        dict = ddict+1;
    }
    if (ZSTD_isError( ZSTD_initDDict_internal(ddict,
                                              dict, dictSize,
                                              ZSTD_dlm_byRef, dictContentType) ))
        return NULL;
    return ddict;
}


size_t ZSTD_freeDDict(ZSTD_DDict* ddict)
{
    if (ddict==NULL) return 0;   /* support free on NULL */
    {   ZSTD_customMem const cMem = ddict->cMem;
        ZSTD_free(ddict->dictBuffer, cMem);
        ZSTD_free(ddict, cMem);
        return 0;
    }
}

/*! ZSTD_estimateDDictSize() :
 *  Estimate amount of memory that will be needed to create a dictionary for decompression.
 *  Note : dictionary created by reference using ZSTD_dlm_byRef are smaller */
size_t ZSTD_estimateDDictSize(size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod)
{
    return sizeof(ZSTD_DDict) + (dictLoadMethod == ZSTD_dlm_byRef ? 0 : dictSize);
}

size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict)
{
    if (ddict==NULL) return 0;   /* support sizeof on NULL */
    return sizeof(*ddict) + (ddict->dictBuffer ? ddict->dictSize : 0) ;
}

/*! ZSTD_getDictID_fromDDict() :
 *  Provides the dictID of the dictionary loaded into `ddict`.
 *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
 *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict)
{
    if (ddict==NULL) return 0;
    return ZSTD_getDictID_fromDict(ddict->dictContent, ddict->dictSize);
}