Skip to content

opt: allow bitCost == scaleLog in ZSTD_rescaleFreqs (fixes #4681) #4749

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

Open
tvost2 wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

opt: allow bitCost == scaleLog in ZSTD_rescaleFreqs (fixes #4681) #4749

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
11 changes: 8 additions & 3 deletions lib/compress/zstd_opt.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,7 +180,12 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
for (ll=0; ll<=MaxLL; ll++) {
U32 const scaleLog = 10; /* scale to 1K */
U32 const bitCost = FSE_getMaxNbBits(llstate.symbolTT, ll);
assert(bitCost < scaleLog);
/* FSE_getMaxNbBits() returns a "fake cost" of tableLog+1 for
* zero-frequency symbols, and the FSE table log can be as
* large as scaleLog-1, so bitCost==scaleLog is reachable.
* The value computation below already handles it (1<<0==1),
* matching the literal-stats loop above. */
assert(bitCost <= scaleLog);
optPtr->litLengthFreq[ll] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/;
optPtr->litLengthSum += optPtr->litLengthFreq[ll];
} }
Expand All @@ -192,7 +197,7 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
for (ml=0; ml<=MaxML; ml++) {
U32 const scaleLog = 10;
U32 const bitCost = FSE_getMaxNbBits(mlstate.symbolTT, ml);
assert(bitCost < scaleLog);
assert(bitCost <= scaleLog); /* see litLength loop above */
optPtr->matchLengthFreq[ml] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/;
optPtr->matchLengthSum += optPtr->matchLengthFreq[ml];
} }
Expand All @@ -204,7 +209,7 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
for (of=0; of<=MaxOff; of++) {
U32 const scaleLog = 10;
U32 const bitCost = FSE_getMaxNbBits(ofstate.symbolTT, of);
assert(bitCost < scaleLog);
assert(bitCost <= scaleLog); /* see litLength loop above */
optPtr->offCodeFreq[of] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/;
optPtr->offCodeSum += optPtr->offCodeFreq[of];
} }
Expand Down
74 changes: 74 additions & 0 deletions tests/fuzzer.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2080,6 +2080,80 @@ static int basicUnitTests(U32 const seed, double compressibility)
}
DISPLAYLEVEL(3, "OK \n");

DISPLAYLEVEL(3, "test%3d : optimal parser + dictionary with sparse FSE tables : ", testNb++);
{ /* Regression test for #4681: a dictionary whose FSE NCount has
* zero-frequency symbols within 0..MaxML makes FSE_getMaxNbBits()
* return tableLog+1 == 10, which tripped assert(bitCost < scaleLog)
* in ZSTD_rescaleFreqs() for the litLength/matchLength/offCode loops. */
static const BYTE dict[] = {
0x37, 0xa4, 0x30, 0xec, 0x63, 0x00, 0x00, 0x00, 0x08, 0x10, 0x00, 0x1f,
0x0f, 0x00, 0x28, 0xe5, 0x03, 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x80, 0x0f, 0x9e, 0x0f, 0x00, 0x00, 0x24, 0x40, 0x80, 0x00, 0x01,
0x02, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0xde, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0xbc, 0xe1, 0x4b, 0x92, 0x0e, 0xb4, 0x7b, 0x18, 0x86, 0x61,
0x18, 0xc6, 0x18, 0x63, 0x8c, 0x31, 0xc6, 0x18, 0x63, 0x8c, 0x31, 0x66,
0x66, 0x66, 0x66, 0xb6, 0x6d, 0x01, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00,
0x00, 0x08, 0x00, 0x00, 0x00, 0x20, 0x73, 0x6f, 0x64, 0x61, 0x6c, 0x65,
0x73, 0x20, 0x74, 0x6f, 0x72, 0x74, 0x6f, 0x72, 0x20, 0x65, 0x6c, 0x65,
0x69, 0x66, 0x65, 0x6e, 0x64, 0x2e, 0x20, 0x41, 0x6c, 0x69, 0x64, 0x69,
0x63, 0x74, 0x69, 0x6f, 0x6e, 0x61, 0x72, 0x79, 0x20, 0x6d, 0x61, 0x74,
0x63, 0x68, 0x20, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x64,
0x69, 0x63, 0x74, 0x69, 0x6f, 0x6e, 0x61, 0x72, 0x79, 0x20, 0x6d, 0x61,
0x74, 0x63, 0x68, 0x20, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61,
0x64, 0x69, 0x63, 0x74, 0x69, 0x6f, 0x6e, 0x61, 0x72, 0x79, 0x20, 0x6d,
0x61, 0x74, 0x63, 0x68, 0x20, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61,
0x61, 0x64, 0x69, 0x63, 0x74, 0x61, 0x72, 0x79, 0x20, 0x6d, 0x61, 0x74,
0x63, 0x68, 0x20, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x64,
0x69, 0x63, 0x74, 0x69, 0x6f, 0x6e, 0x61, 0x72, 0x79, 0x20, 0x6d, 0x61,
0x74, 0x63, 0x68, 0x20, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61,
0x64, 0x69, 0x63, 0x74, 0x69, 0x6f, 0x6e, 0x61, 0x72, 0x79, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0xbc, 0xe1, 0x4b, 0x92, 0x0e, 0xb4, 0x7b, 0x18, 0x86,
0x61, 0x18, 0xc6, 0x18, 0x63, 0x8c, 0x31, 0xc6, 0x18, 0x63, 0x72, 0x79,
0x20, 0x6d, 0x61, 0x74, 0x63, 0x68, 0x20, 0x61, 0x61, 0x61, 0x61, 0x61,
0x61, 0x79, 0x20, 0x6d, 0x61, 0x74, 0x63, 0x68, 0x20, 0x61, 0x61, 0x61,
0x61, 0x61, 0x61, 0x61, 0x61, 0x64, 0x69, 0x63, 0x74, 0x69, 0x6f, 0x6e,
0x61, 0x72, 0x79, 0x20, 0x6d, 0x61, 0x74, 0x63, 0x68, 0x20, 0x61, 0x61,
0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x64, 0x69, 0x63, 0x74, 0x69, 0x6f,
0x6e, 0x61, 0x72, 0x79, 0x20, 0x6d, 0x61, 0x74, 0x63, 0x68, 0x20, 0x61,
0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x61, 0x64, 0x69, 0x63, 0x74, 0x69,
0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38,
0x39, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x30, 0x31, 0x32, 0x33, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x0b, 0x00, 0x10, 0x00, 0x02,
0x6f
};
static const char* const src =
"0123453456789abcdef0123 dictionary match aaaaaaaa\n";
size_t const srcSize = strlen(src);
int strategy;
for (strategy = ZSTD_btopt; strategy <= ZSTD_btultra2; strategy++) {
ZSTD_compressionParameters cParams = ZSTD_getCParams(1, srcSize, sizeof(dict));
ZSTD_CCtx* const cctx = ZSTD_createCCtx();
ZSTD_DCtx* const dctx = ZSTD_createDCtx();
ZSTD_CDict* cdict;
size_t cSize;
cParams.strategy = (ZSTD_strategy)strategy;
cParams = ZSTD_adjustCParams(cParams, srcSize, sizeof(dict));
cdict = ZSTD_createCDict_advanced(dict, sizeof(dict), ZSTD_dlm_byRef,
ZSTD_dct_fullDict, cParams, ZSTD_defaultCMem);
CHECK(cdict != NULL);
cSize = ZSTD_compress_usingCDict(cctx, compressedBuffer, compressedBufferSize,
src, srcSize, cdict);
CHECK_Z(cSize); /* must not assert / error */
{ size_t const dSize = ZSTD_decompress_usingDict(dctx, decodedBuffer, CNBuffSize,
compressedBuffer, cSize, dict, sizeof(dict));
CHECK_Z(dSize);
CHECK(dSize == srcSize && !memcmp(decodedBuffer, src, srcSize));
}
ZSTD_freeCDict(cdict);
ZSTD_freeCCtx(cctx);
ZSTD_freeDCtx(dctx);
}
}
DISPLAYLEVEL(3, "OK \n");

DISPLAYLEVEL(3, "test%3d : ZSTD_CCtx_getParameter() : ", testNb++);
{ ZSTD_CCtx* const cctx = ZSTD_createCCtx();
ZSTD_outBuffer out = {NULL, 0, 0};
Expand Down