ddidderr/zstd-rs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat(compress): move no-delimiter sequence transfer to Rust

Browse Source 
Port the no-delimiter external-sequence block scanner, match splitting, repcode updates, validation, and sequence/literal storage behind a narrow C shim. Preserve trailing bytes as literals when the sequence buffer ends before the requested block, and remove the obsolete C validation wrapper.

Test Plan:

- cargo test --manifest-path rust/Cargo.toml --no-default-features --features compression (242 passed)

- cargo clippy --manifest-path rust/Cargo.toml --no-default-features --features compression [--benches|--tests] (clean)

- cargo +nightly fmt --manifest-path rust/Cargo.toml (clean)

- make -B -C lib -j2 lib (passed)

- make -C tests -j2 test-zstream (84 deterministic; 5960 and 8307 randomized passed)

- make -C tests -j2 test-fuzzer (existing test 56 CCtx-reuse mismatch; also fails at 37eb75758)

- make -C tests -j2 test-zstd (existing Rust CLI --patch-from gap)
This commit is contained in:
ddidderr
2026-07-18 07:49:11 +02:00
parent 37eb757585
commit 7ee445c431
2 changed files with 385 additions and 124 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/compress/zstd_compress.c
+18 -124
View File
@@ -300,9 +300,6 @@ size_t ZSTD_rust_blockSizeExplicitDelimiter(const ZSTD_Sequence* inSeqs,
size_t ZSTD_rust_determineBlockSize(int mode, size_t blockSize, size_t remaining,
const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
U32 seqIdx);
size_t ZSTD_rust_validateSequence(U32 offBase, U32 matchLength, U32 minMatch,
size_t posInSrc, U32 windowLog, size_t dictSize,
int useSequenceProducer);
size_t ZSTD_rust_loadCEntropy(ZSTD_compressedBlockState_t* bs, void* workspace,
const void* dict, size_t dictSize);
size_t ZSTD_rust_transferSequencesWBlockDelim(
@@ -313,6 +310,14 @@ size_t ZSTD_rust_transferSequencesWBlockDelim(
U32 nextRepcodes[ZSTD_REP_NUM], U32 dictSize,
int validateSequences, U32 minMatch, U32 windowLog,
int useSequenceProducer);
size_t ZSTD_rust_transferSequencesNoDelim(
SeqStore_t* seqStore, ZSTD_SequencePosition* seqPos,
const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
const BYTE* src, size_t blockSize,
const U32 prevRepcodes[ZSTD_REP_NUM],
U32 nextRepcodes[ZSTD_REP_NUM], U32 dictSize,
int validateSequences, U32 minMatch, U32 windowLog,
int useSequenceProducer);
size_t ZSTD_rust_optimalBlockSize(const void* src, size_t srcSize,
size_t blockSizeMax, int splitLevel,
int strategy, S64 savings,
@@ -5124,19 +5129,6 @@ size_t ZSTD_compress2_c(ZSTD_CCtx* cctx,
}
}
/* ZSTD_validateSequence() :
* @offBase : must use the format required by ZSTD_storeSeq()
* @returns a ZSTD error code if sequence is not valid
*/
static size_t
ZSTD_validateSequence(U32 offBase, U32 matchLength, U32 minMatch,
size_t posInSrc, U32 windowLog, size_t dictSize, int useSequenceProducer)
{
return ZSTD_rust_validateSequence(offBase, matchLength, minMatch,
posInSrc, windowLog, dictSize,
useSequenceProducer);
}
/* Returns an offset code, given a sequence's raw offset, the ongoing repcode array, and whether litLength == 0 */
static U32 ZSTD_finalizeOffBase(U32 rawOffset, const U32 rep[ZSTD_REP_NUM], U32 ll0)
{
@@ -5194,19 +5186,7 @@ ZSTD_transferSequences_noDelim(ZSTD_CCtx* cctx,
const void* src, size_t blockSize,
ZSTD_ParamSwitch_e externalRepSearch)
{
U32 idx = seqPos->idx;
U32 startPosInSequence = seqPos->posInSequence;
U32 endPosInSequence = seqPos->posInSequence + (U32)blockSize;
size_t dictSize;
const BYTE* const istart = (const BYTE*)(src);
const BYTE* ip = istart;
const BYTE* iend = istart + blockSize; /* May be adjusted if we decide to process fewer than blockSize bytes */
Repcodes_t updatedRepcodes;
U32 bytesAdjustment = 0;
U32 finalMatchSplit = 0;
/* TODO(embg) support fast parsing mode in noBlockDelim mode */
(void)externalRepSearch;
if (cctx->cdict) {
dictSize = cctx->cdict->dictContentSize;
@@ -5215,102 +5195,16 @@ ZSTD_transferSequences_noDelim(ZSTD_CCtx* cctx,
} else {
dictSize = 0;
}
DEBUGLOG(5, "ZSTD_transferSequences_noDelim: idx: %u PIS: %u blockSize: %zu", idx, startPosInSequence, blockSize);
DEBUGLOG(5, "Start seq: idx: %u (of: %u ml: %u ll: %u)", idx, inSeqs[idx].offset, inSeqs[idx].matchLength, inSeqs[idx].litLength);
ZSTD_memcpy(updatedRepcodes.rep, cctx->blockState.prevCBlock->rep, sizeof(Repcodes_t));
while (endPosInSequence && idx < inSeqsSize && !finalMatchSplit) {
const ZSTD_Sequence currSeq = inSeqs[idx];
U32 litLength = currSeq.litLength;
U32 matchLength = currSeq.matchLength;
U32 const rawOffset = currSeq.offset;
U32 offBase;
/* Modify the sequence depending on where endPosInSequence lies */
if (endPosInSequence >= currSeq.litLength + currSeq.matchLength) {
if (startPosInSequence >= litLength) {
startPosInSequence -= litLength;
litLength = 0;
matchLength -= startPosInSequence;
} else {
litLength -= startPosInSequence;
}
/* Move to the next sequence */
endPosInSequence -= currSeq.litLength + currSeq.matchLength;
startPosInSequence = 0;
} else {
/* This is the final (partial) sequence we're adding from inSeqs, and endPosInSequence
does not reach the end of the match. So, we have to split the sequence */
DEBUGLOG(6, "Require a split: diff: %u, idx: %u PIS: %u",
currSeq.litLength + currSeq.matchLength - endPosInSequence, idx, endPosInSequence);
if (endPosInSequence > litLength) {
U32 firstHalfMatchLength;
litLength = startPosInSequence >= litLength ? 0 : litLength - startPosInSequence;
firstHalfMatchLength = endPosInSequence - startPosInSequence - litLength;
if (matchLength > blockSize && firstHalfMatchLength >= cctx->appliedParams.cParams.minMatch) {
/* Only ever split the match if it is larger than the block size */
U32 secondHalfMatchLength = currSeq.matchLength + currSeq.litLength - endPosInSequence;
if (secondHalfMatchLength < cctx->appliedParams.cParams.minMatch) {
/* Move the endPosInSequence backward so that it creates match of minMatch length */
endPosInSequence -= cctx->appliedParams.cParams.minMatch - secondHalfMatchLength;
bytesAdjustment = cctx->appliedParams.cParams.minMatch - secondHalfMatchLength;
firstHalfMatchLength -= bytesAdjustment;
}
matchLength = firstHalfMatchLength;
/* Flag that we split the last match - after storing the sequence, exit the loop,
but keep the value of endPosInSequence */
finalMatchSplit = 1;
} else {
/* Move the position in sequence backwards so that we don't split match, and break to store
* the last literals. We use the original currSeq.litLength as a marker for where endPosInSequence
* should go. We prefer to do this whenever it is not necessary to split the match, or if doing so
* would cause the first half of the match to be too small
*/
bytesAdjustment = endPosInSequence - currSeq.litLength;
endPosInSequence = currSeq.litLength;
break;
}
} else {
/* This sequence ends inside the literals, break to store the last literals */
break;
}
}
/* Check if this offset can be represented with a repcode */
{ U32 const ll0 = (litLength == 0);
offBase = ZSTD_finalizeOffBase(rawOffset, updatedRepcodes.rep, ll0);
ZSTD_updateRep(updatedRepcodes.rep, offBase, ll0);
}
if (cctx->appliedParams.validateSequences) {
seqPos->posInSrc += litLength + matchLength;
FORWARD_IF_ERROR(ZSTD_validateSequence(offBase, matchLength, cctx->appliedParams.cParams.minMatch, seqPos->posInSrc,
cctx->appliedParams.cParams.windowLog, dictSize, ZSTD_hasExtSeqProd(&cctx->appliedParams)),
"Sequence validation failed");
}
DEBUGLOG(6, "Storing sequence: (of: %u, ml: %u, ll: %u)", offBase, matchLength, litLength);
RETURN_ERROR_IF(idx - seqPos->idx >= cctx->seqStore.maxNbSeq, externalSequences_invalid,
"Not enough memory allocated. Try adjusting ZSTD_c_minMatch.");
ZSTD_storeSeq(&cctx->seqStore, litLength, ip, iend, offBase, matchLength);
ip += matchLength + litLength;
if (!finalMatchSplit)
idx++; /* Next Sequence */
}
DEBUGLOG(5, "Ending seq: idx: %u (of: %u ml: %u ll: %u)", idx, inSeqs[idx].offset, inSeqs[idx].matchLength, inSeqs[idx].litLength);
assert(idx == inSeqsSize || endPosInSequence <= inSeqs[idx].litLength + inSeqs[idx].matchLength);
seqPos->idx = idx;
seqPos->posInSequence = endPosInSequence;
ZSTD_memcpy(cctx->blockState.nextCBlock->rep, updatedRepcodes.rep, sizeof(Repcodes_t));
iend -= bytesAdjustment;
if (ip != iend) {
/* Store any last literals */
U32 const lastLLSize = (U32)(iend - ip);
assert(ip <= iend);
DEBUGLOG(6, "Storing last literals of size: %u", lastLLSize);
ZSTD_storeLastLiterals(&cctx->seqStore, ip, lastLLSize);
seqPos->posInSrc += lastLLSize;
}
return (size_t)(iend-istart);
(void)externalRepSearch;
return ZSTD_rust_transferSequencesNoDelim(
&cctx->seqStore, seqPos, inSeqs, inSeqsSize,
(const BYTE*)src, blockSize,
cctx->blockState.prevCBlock->rep,
cctx->blockState.nextCBlock->rep, (U32)dictSize,
cctx->appliedParams.validateSequences,
cctx->appliedParams.cParams.minMatch,
cctx->appliedParams.cParams.windowLog,
ZSTD_hasExtSeqProd(&cctx->appliedParams));
}
/* @seqPos represents a position within @inSeqs,