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

feat(compress): move external sequence sizing leaves to Rust

Browse Source 
Port repcode offBase finalization and explicit-delimiter block sizing through the Rust compression ABI. Preserve wrapped sequence arithmetic, external-sequence error codes, and the no-delimiter target-size policy while keeping the C control flow intact.

Test Plan: cargo test --manifest-path rust/Cargo.toml --no-default-features --features compression (176 passed); cargo clippy root, benches, and tests; make -B -C lib -j2 lib; make -B -C tests -j2 test-zstream (84 named tests plus 6,230 and 8,598 fuzz cases passed).
This commit is contained in:
ddidderr
2026-07-18 04:31:22 +02:00
parent 42481fb366
commit d5ae2a450b
2 changed files with 224 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/compress/zstd_compress.c
+10 -52
View File
@@ -251,6 +251,12 @@ void ZSTD_rust_deriveSeqStoreChunk(SeqStore_t* resultSeqStore,
size_t startIdx, size_t endIdx);
U32 ZSTD_rust_resolveRepcodeToRawOffset(const U32 rep[ZSTD_REP_NUM],
U32 offBase, U32 ll0);
U32 ZSTD_rust_finalizeOffBase(U32 rawOffset, const U32 rep[ZSTD_REP_NUM], U32 ll0);
size_t ZSTD_rust_blockSizeExplicitDelimiter(const ZSTD_Sequence* inSeqs,
size_t inSeqsSize, U32 seqIdx);
size_t ZSTD_rust_determineBlockSize(int mode, size_t blockSize, size_t remaining,
const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
U32 seqIdx);
typedef char ZSTD_rust_stats_seqdef_layout[(sizeof(SeqDef) == 8) ? 1 : -1];
typedef char ZSTD_rust_stats_seqstore_long_length_pos[
@@ -5440,18 +5446,7 @@ ZSTD_validateSequence(U32 offBase, U32 matchLength, U32 minMatch,
/* 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)
{
U32 offBase = OFFSET_TO_OFFBASE(rawOffset);
if (!ll0 && rawOffset == rep[0]) {
offBase = REPCODE1_TO_OFFBASE;
} else if (rawOffset == rep[1]) {
offBase = REPCODE_TO_OFFBASE(2 - ll0);
} else if (rawOffset == rep[2]) {
offBase = REPCODE_TO_OFFBASE(3 - ll0);
} else if (ll0 && rawOffset == rep[0] - 1) {
offBase = REPCODE3_TO_OFFBASE;
}
return offBase;
return ZSTD_rust_finalizeOffBase(rawOffset, rep, ll0);
}
/* This function scans through an array of ZSTD_Sequence,
@@ -5707,52 +5702,15 @@ static ZSTD_SequenceCopier_f ZSTD_selectSequenceCopier(ZSTD_SequenceFormat_e mod
return ZSTD_transferSequences_noDelim;
}
/* Discover the size of next block by searching for the delimiter.
* Note that a block delimiter **must** exist in this mode,
* otherwise it's an input error.
* The block size retrieved will be later compared to ensure it remains within bounds */
static size_t
blockSize_explicitDelimiter(const ZSTD_Sequence* inSeqs, size_t inSeqsSize, ZSTD_SequencePosition seqPos)
{
int end = 0;
size_t blockSize = 0;
size_t spos = seqPos.idx;
DEBUGLOG(6, "blockSize_explicitDelimiter : seq %zu / %zu", spos, inSeqsSize);
assert(spos <= inSeqsSize);
while (spos < inSeqsSize) {
end = (inSeqs[spos].offset == 0);
blockSize += inSeqs[spos].litLength + inSeqs[spos].matchLength;
if (end) {
if (inSeqs[spos].matchLength != 0)
RETURN_ERROR(externalSequences_invalid, "delimiter format error : both matchlength and offset must be == 0");
break;
}
spos++;
}
if (!end)
RETURN_ERROR(externalSequences_invalid, "Reached end of sequences without finding a block delimiter");
return blockSize;
}
static size_t determine_blockSize(ZSTD_SequenceFormat_e mode,
size_t blockSize, size_t remaining,
const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
ZSTD_SequencePosition seqPos)
{
DEBUGLOG(6, "determine_blockSize : remainingSize = %zu", remaining);
if (mode == ZSTD_sf_noBlockDelimiters) {
/* Note: more a "target" block size */
return MIN(remaining, blockSize);
}
assert(mode == ZSTD_sf_explicitBlockDelimiters);
{ size_t const explicitBlockSize = blockSize_explicitDelimiter(inSeqs, inSeqsSize, seqPos);
FORWARD_IF_ERROR(explicitBlockSize, "Error while determining block size with explicit delimiters");
if (explicitBlockSize > blockSize)
RETURN_ERROR(externalSequences_invalid, "sequences incorrectly define a too large block");
if (explicitBlockSize > remaining)
RETURN_ERROR(externalSequences_invalid, "sequences define a frame longer than source");
return explicitBlockSize;
}
assert(mode == ZSTD_sf_noBlockDelimiters || mode == ZSTD_sf_explicitBlockDelimiters);
return ZSTD_rust_determineBlockSize((int)mode, blockSize, remaining,
inSeqs, inSeqsSize, seqPos.idx);
}
/* Compress all provided sequences, block-by-block.