Skip to content

compress: support high dictionary IDs on 32-bit builds #4864

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
trestoncuzzort wants to merge 1 commit into
base: dev
Choose a base branch
from
Draft

compress: support high dictionary IDs on 32-bit builds #4864

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 20 additions & 18 deletions lib/compress/zstd_compress.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5183,7 +5183,7 @@ size_t ZSTD_loadCEntropy(ZSTD_compressedBlockState_t* bs, void* workspace,
* https://github.com/facebook/zstd/blob/release/doc/zstd_compression_format.md#dictionary-format
*/
/*! ZSTD_loadZstdDictionary() :
* @return : dictID, or an error code
* @return : 0, or an error code. The dictionary ID is written to dictIDPtr.
* assumptions : magic number supposed already checked
* dictSize supposed >= 8
*/
Expand All @@ -5194,11 +5194,11 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs,
const void* dict, size_t dictSize,
ZSTD_dictTableLoadMethod_e dtlm,
ZSTD_tableFillPurpose_e tfp,
void* workspace)
void* workspace, U32* dictIDPtr)
{
const BYTE* dictPtr = (const BYTE*)dict;
const BYTE* const dictEnd = dictPtr + dictSize;
size_t dictID;
U32 dictID;
size_t eSize;
ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<<MAX(MLFSELog,LLFSELog)));
assert(dictSize >= 8);
Expand All @@ -5214,11 +5214,12 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs,
FORWARD_IF_ERROR(ZSTD_loadDictionaryContent(
ms, NULL, ws, params, dictPtr, dictContentSize, dtlm, tfp), "");
}
return dictID;
*dictIDPtr = dictID;
return 0;
}

/** ZSTD_compress_insertDictionary() :
* @return : dictID, or an error code */
* @return : 0, or an error code. The dictionary ID is written to dictIDPtr. */
static size_t
ZSTD_compress_insertDictionary(ZSTD_compressedBlockState_t* bs,
ZSTD_MatchState_t* ms,
Expand All @@ -5229,9 +5230,10 @@ ZSTD_compress_insertDictionary(ZSTD_compressedBlockState_t* bs,
ZSTD_dictContentType_e dictContentType,
ZSTD_dictTableLoadMethod_e dtlm,
ZSTD_tableFillPurpose_e tfp,
void* workspace)
void* workspace, U32* dictIDPtr)
{
DEBUGLOG(4, "ZSTD_compress_insertDictionary (dictSize=%u)", (U32)dictSize);
*dictIDPtr = 0;
if ((dict==NULL) || (dictSize<8)) {
RETURN_ERROR_IF(dictContentType == ZSTD_dct_fullDict, dictionary_wrong, "");
return 0;
Expand All @@ -5255,7 +5257,7 @@ ZSTD_compress_insertDictionary(ZSTD_compressedBlockState_t* bs,

/* dict as full zstd dictionary */
return ZSTD_loadZstdDictionary(
bs, ms, ws, params, dict, dictSize, dtlm, tfp, workspace);
bs, ms, ws, params, dict, dictSize, dtlm, tfp, workspace, dictIDPtr);
}

#define ZSTD_USE_CDICT_PARAMS_SRCSIZE_CUTOFF (128 KB)
Expand Down Expand Up @@ -5293,19 +5295,19 @@ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx,
FORWARD_IF_ERROR( ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
dictContentSize,
ZSTDcrp_makeClean, zbuff) , "");
{ size_t const dictID = cdict ?
{ U32 dictID = 0;
size_t const dictStatus = cdict ?
ZSTD_compress_insertDictionary(
cctx->blockState.prevCBlock, &cctx->blockState.matchState,
&cctx->ldmState, &cctx->workspace, &cctx->appliedParams, cdict->dictContent,
cdict->dictContentSize, cdict->dictContentType, dtlm,
ZSTD_tfp_forCCtx, cctx->tmpWorkspace)
ZSTD_tfp_forCCtx, cctx->tmpWorkspace, &dictID)
: ZSTD_compress_insertDictionary(
cctx->blockState.prevCBlock, &cctx->blockState.matchState,
&cctx->ldmState, &cctx->workspace, &cctx->appliedParams, dict, dictSize,
dictContentType, dtlm, ZSTD_tfp_forCCtx, cctx->tmpWorkspace);
FORWARD_IF_ERROR(dictID, "ZSTD_compress_insertDictionary failed");
assert(dictID <= UINT_MAX);
cctx->dictID = (U32)dictID;
dictContentType, dtlm, ZSTD_tfp_forCCtx, cctx->tmpWorkspace, &dictID);
FORWARD_IF_ERROR(dictStatus, "ZSTD_compress_insertDictionary failed");
cctx->dictID = dictID;
cctx->dictContentSize = dictContentSize;
}
return 0;
Expand Down Expand Up @@ -5617,13 +5619,13 @@ static size_t ZSTD_initCDict_internal(
*/
{ params.compressionLevel = ZSTD_CLEVEL_DEFAULT;
params.fParams.contentSizeFlag = 1;
{ size_t const dictID = ZSTD_compress_insertDictionary(
{ U32 dictID = 0;
size_t const dictStatus = ZSTD_compress_insertDictionary(
&cdict->cBlockState, &cdict->matchState, NULL, &cdict->workspace,
&params, cdict->dictContent, cdict->dictContentSize,
dictContentType, ZSTD_dtlm_full, ZSTD_tfp_forCDict, cdict->entropyWorkspace);
FORWARD_IF_ERROR(dictID, "ZSTD_compress_insertDictionary failed");
assert(dictID <= (size_t)(U32)-1);
cdict->dictID = (U32)dictID;
dictContentType, ZSTD_dtlm_full, ZSTD_tfp_forCDict, cdict->entropyWorkspace, &dictID);
FORWARD_IF_ERROR(dictStatus, "ZSTD_compress_insertDictionary failed");
cdict->dictID = dictID;
}
}

Expand Down
43 changes: 43 additions & 0 deletions tests/fuzzer.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3043,6 +3043,49 @@ static int basicUnitTests(U32 const seed, double compressibility)
goto _output_error;
}

DISPLAYLEVEL(3, "test%3i : full range of dictionary IDs : ", testNb++);
{ U32 const dictIDs[] = { 1U, 0x7FFFFFFFU, 0x80000000U, 0xFFFFFFFFU };
BYTE dict[sizeof(dictBufferFixed)];
size_t const srcSize = 1 KB;
ZSTD_DCtx* const dctx = ZSTD_createDCtx();
size_t i;
CHECK(dctx != NULL);
memcpy(dict, dictBufferFixed, sizeof(dict));
for (i = 0; i < sizeof(dictIDs) / sizeof(dictIDs[0]); ++i) {
unsigned mode;
MEM_writeLE32(dict + 4, dictIDs[i]);
for (mode = 0; mode < 3; ++mode) {
if (mode == 0) {
cSize = ZSTD_compress_usingDict(cctx,
compressedBuffer, compressedBufferSize, CNBuffer, srcSize,
dict, sizeof(dict), 1);
} else if (mode == 1) {
ZSTD_CDict* const cdict = ZSTD_createCDict(dict, sizeof(dict), 1);
CHECK(cdict != NULL);
CHECK_EQ(ZSTD_getDictID_fromCDict(cdict), dictIDs[i]);
cSize = ZSTD_compress_usingCDict(cctx,
compressedBuffer, compressedBufferSize, CNBuffer, srcSize, cdict);
ZSTD_freeCDict(cdict);
} else {
CHECK_Z(ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters));
CHECK_Z(ZSTD_CCtx_loadDictionary(cctx, dict, sizeof(dict)));
cSize = ZSTD_compress2(cctx,
compressedBuffer, compressedBufferSize, CNBuffer, srcSize);
}
CHECK_Z(cSize);
CHECK_EQ(ZSTD_getDictID_fromFrame(compressedBuffer, cSize), dictIDs[i]);
{ size_t const r = ZSTD_decompress_usingDict(dctx, decodedBuffer, CNBuffSize,
compressedBuffer, cSize, dict, sizeof(dict));
CHECK_Z(r);
CHECK_EQ(r, srcSize);
}
CHECK(memcmp(decodedBuffer, CNBuffer, srcSize) == 0);
}
}
ZSTD_freeDCtx(dctx);
}
DISPLAYLEVEL(3, "OK \n");

DISPLAYLEVEL(3, "test%3i : dictBuilder on cyclic data : ", testNb++);
assert(compressedBufferSize >= totalSampleSize);
{ U32 u; for (u=0; u<totalSampleSize; u++) ((BYTE*)decodedBuffer)[u] = (BYTE)u; }
Expand Down