denuvo-ref/zstd
1
0
Fork 0
mirror of https://github.com/facebook/zstd synced 2026-08-22 22:32:07 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge b63c5e2618 into 82d322c497

Browse source
This commit is contained in:
Rohit 2026-08-03 11:10:35 +00:00 • committed by GitHub
commit 37f7e9d333
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 29 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

10
lib/dictBuilder/cover.c
View file

@ -644,6 +644,16 @@ static size_t COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer,
(unsigned)(totalSamplesSize>>20), (COVER_MAX_SAMPLES_SIZE >> 20));
return ERROR(srcSize_wrong);
}
/* The training set must be large enough for the partial suffix array, whose
* size is `trainingSamplesSize - MAX(d, sizeof(U64)) + 1`. When splitPoint
* < 1.0 the training set is a subset of the corpus, so it can be smaller
* than the total even after the check above. Guard against the size_t
* subtraction underflowing into a huge allocation. */
if (trainingSamplesSize < MAX(d, sizeof(U64))) {
DISPLAYLEVEL(1, "Training samples size is too small (%u), minimum size is %u\n",
(unsigned)trainingSamplesSize, (unsigned)MAX(d, sizeof(U64)));
return ERROR(srcSize_wrong);
}
/* Check if there are at least 5 training samples */
if (nbTrainSamples < 5) {
DISPLAYLEVEL(1, "Total number of training samples is %u and is invalid.", nbTrainSamples);

19
tests/fuzzer.c
View file

@ -3812,6 +3812,25 @@ static int basicUnitTests(U32 const seed, double compressibility)
if (dictID==0) goto _output_error;
DISPLAYLEVEL(3, "OK : %u \n", (unsigned)dictID);
DISPLAYLEVEL(3, "test%3i : ZDICT_optimizeTrainFromBuffer_cover with tiny training set : ", testNb++);
{ /* With splitPoint < 1.0 the training set is a subset of the corpus.
* If that subset is smaller than MAX(d, sizeof(U64)) the partial
* suffix array size used to underflow size_t (issue #4682). The
* builder must reject it cleanly instead. The first few samples are
* tiny so the 0.75 training split stays below the threshold, while
* the total corpus is comfortably large. */
size_t tinySizes[8] = { 1, 1, 1, 1, 1, 1, 100, 100 };
ZDICT_cover_params_t tinyParams;
size_t tinyResult;
memset(&tinyParams, 0, sizeof(tinyParams));
tinyParams.steps = 4;
tinyParams.splitPoint = 0.75;
tinyResult = ZDICT_optimizeTrainFromBuffer_cover(
dictBuffer, optDictSize, CNBuffer, tinySizes, 8, &tinyParams);
if (!ZDICT_isError(tinyResult)) goto _output_error;
}
DISPLAYLEVEL(3, "OK \n");
ZSTD_freeCCtx(cctx);
free(dictBuffer);
free(samplesSizes);