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

feat(rust): port block entropy statistics

Browse Source 
Continue the incremental zstd_compress.c migration with its sequence
statistics and seqStore entropy-compression layer.  The following now
live in rust/src/zstd_compress_stats.rs:

- ZSTD_seqToCodes(), exported under its original name because the C
  dictionary builder (zdict.c) and decodecorpus link against it,
- ZSTD_buildSequencesStatistics() and its dummy variant, whose result
  struct no longer crosses the language boundary,
- ZSTD_entropyCompressSeqStore_internal(), _wExtLitBuffer(), and
  ZSTD_entropyCompressSeqStore(),
- ZSTD_buildBlockEntropyStats() with its literals/sequences helpers,
- ZSTD_copyBlockSequences() and the ZSTD_updateRep() rules it shares
  with the superblock writer.

Boundary: ZSTD_CCtx and ZSTD_CCtx_params stay private to C.  These
paths read exactly two parameter fields, so the C shims keep the
original static/exported function names and forward the strategy and
ZSTD_literalsCompressionIsDisabled() as int scalars alongside the
seqStore and entropy-table leaves.  The leaf layouts (SeqDef,
SeqStore_t, ZSTD_hufCTables_t, ZSTD_fseCTables_t, entropy metadata,
SeqCollector, ZSTD_Sequence) are pinned by compile-time asserts in
zstd_compress.c and by both-pointer-width layout tests in Rust.
ZSTD_buildSeqStore, block dispatch/splitting, and the block-size
estimation helpers remain C for a later slice.

The superblock module previously round-tripped through the C export of
ZSTD_buildBlockEntropyStats and mirrored the entropy leaf structs
privately.  It now calls the crate-internal builder directly, and the
shared struct definitions moved to zstd_compress_stats; consequently
ZSTD_rust_compressSuperBlock() takes the two parameter scalars instead
of an opaque ZSTD_CCtx_params pointer, extracted by its C shim.  Its
layout and repcode tests moved with the definitions.

One C helper family gets no shim: the static
ZSTD_entropyCompressSeqStore_wExtLitBuffer() had a single caller and
was folded into the Rust implementation.

Byte-identity was verified against the pre-change compressor: COPYING,
datagen -g5000000 -s7, and datagen -g300000 -s21 -P90, each at levels
1/3/9/19 and --fast=5, plus a superblock-heavy pass at level 19 with
--target-compressed-block-size=1024; all 18 frames are byte-identical,
covering the repeat-mode state machine, longOffsets, RLE/raw fallback,
and dstSize_tooSmall paths through the block splitter and superblock.

Test plan:
- cd rust && cargo fmt --check && cargo clippy --all-targets -- -D
  warnings && cargo test --all-targets (131 tests: new reference
  vectors for seqToCodes, RLE table headers, empty-seqStore repeat
  copies, literal-stats type selection, and repcode resolution in
  copyBlockSequences)
- cargo build --release --no-default-features --features compression
  and --features decompression
- make -C tests fuzzer && ./tests/fuzzer -i1 --no-big-tests (covers
  ZSTD_generateSequences and ZDICT training over the Rust seqToCodes)
- make -C tests test-rust-lib-smoke
- ./tests/zstreamtest -i1 and ./tests/zstreamtest --newapi -t1 -i1
- ./tests/decodecorpus -t -T1s (decodecorpus links Rust seqToCodes)
- /tmp/ref vs /tmp/got frame diff as described above: byte-identical
This commit is contained in:
ddidderr
2026-07-11 23:11:57 +02:00
parent 322f99dfd0
commit daeac5238c
7 changed files with 1702 additions and 782 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/compress/zstd_compress.c
+88 -587
View File
@@ -88,6 +88,67 @@ size_t ZSTD_rust_params_estimateCDictSizeFromCParams(
size_t dictSize, ZSTD_compressionParameters cParams,
int dictLoadMethod, const ZSTD_rustCDictSizing* sizing);
/* Sequence statistics and seqStore entropy compression live in Rust
* (rust/src/zstd_compress_stats.rs), which also exports ZSTD_seqToCodes()
* under its original name. The shims below extract the sequence store, the
* entropy-table leaves, and the only two ZSTD_CCtx_params fields these paths
* read (the strategy and the literals-compression switch), so the private
* parameter structure layout never crosses the language boundary. The
* shared leaf layouts are pinned by the compile-time asserts that follow. */
size_t ZSTD_rust_entropyCompressSeqStore_internal(
void* dst, size_t dstCapacity,
const void* literals, size_t litSize,
const SeqStore_t* seqStorePtr,
const ZSTD_entropyCTables_t* prevEntropy,
ZSTD_entropyCTables_t* nextEntropy,
int strategy, int disableLiteralCompression,
void* entropyWorkspace, size_t entropyWkspSize,
int bmi2);
size_t ZSTD_rust_entropyCompressSeqStore(
const SeqStore_t* seqStorePtr,
const ZSTD_entropyCTables_t* prevEntropy,
ZSTD_entropyCTables_t* nextEntropy,
int strategy, int disableLiteralCompression,
void* dst, size_t dstCapacity,
size_t srcSize,
void* entropyWorkspace, size_t entropyWkspSize,
int bmi2);
size_t ZSTD_rust_buildBlockEntropyStats(
const SeqStore_t* seqStorePtr,
const ZSTD_entropyCTables_t* prevEntropy,
ZSTD_entropyCTables_t* nextEntropy,
int strategy, int disableLiteralCompression,
ZSTD_entropyCTablesMetadata_t* entropyMetadata,
void* workspace, size_t wkspSize);
size_t ZSTD_rust_copyBlockSequences(
SeqCollector* seqCollector, const SeqStore_t* seqStore,
const U32 prevRepcodes[ZSTD_REP_NUM]);
typedef char ZSTD_rust_stats_seqdef_layout[(sizeof(SeqDef) == 8) ? 1 : -1];
typedef char ZSTD_rust_stats_seqstore_long_length_pos[
(offsetof(SeqStore_t, longLengthPos) == 9 * sizeof(size_t) + 4) ? 1 : -1];
typedef char ZSTD_rust_stats_seqstore_layout[
(sizeof(SeqStore_t) == 9 * sizeof(size_t) + 8) ? 1 : -1];
typedef char ZSTD_rust_stats_huf_layout[
(sizeof(ZSTD_hufCTables_t) == 258 * sizeof(size_t)) ? 1 : -1];
typedef char ZSTD_rust_stats_fse_layout[(sizeof(ZSTD_fseCTables_t) == 3552) ? 1 : -1];
typedef char ZSTD_rust_stats_entropy_fse_offset[
(offsetof(ZSTD_entropyCTables_t, fse) == sizeof(ZSTD_hufCTables_t)) ? 1 : -1];
typedef char ZSTD_rust_stats_huf_metadata_buffer[
(offsetof(ZSTD_hufCTablesMetadata_t, hufDesBuffer) == 4
&& ZSTD_MAX_HUF_HEADER_SIZE == 128) ? 1 : -1];
typedef char ZSTD_rust_stats_fse_metadata_buffer[
(offsetof(ZSTD_fseCTablesMetadata_t, fseTablesBuffer) == 12
&& ZSTD_MAX_FSE_HEADERS_SIZE == 133) ? 1 : -1];
typedef char ZSTD_rust_stats_entropy_metadata_layout[
(offsetof(ZSTD_entropyCTablesMetadata_t, fseMetadata)
== sizeof(ZSTD_hufCTablesMetadata_t)) ? 1 : -1];
typedef char ZSTD_rust_stats_sequence_layout[(sizeof(ZSTD_Sequence) == 16) ? 1 : -1];
typedef char ZSTD_rust_stats_seqcollector_layout[
(offsetof(SeqCollector, seqStart) == sizeof(size_t)
&& offsetof(SeqCollector, seqIndex) == 2 * sizeof(size_t)
&& sizeof(SeqCollector) == 4 * sizeof(size_t)) ? 1 : -1];
#if ZSTD_ADDRESS_SANITIZER && !defined (ZSTD_ASAN_DONT_POISON_WORKSPACE)
# define ZSTD_RUST_ASAN_REDZONE_SIZE ((size_t)ZSTD_CWKSP_ASAN_REDZONE_SIZE)
#else
@@ -2561,33 +2622,7 @@ static void ZSTD_reduceIndex (ZSTD_MatchState_t* ms, ZSTD_CCtx_params const* par
/* See doc/zstd_compression_format.md for detailed format description */
int ZSTD_seqToCodes(const SeqStore_t* seqStorePtr)
{
const SeqDef* const sequences = seqStorePtr->sequencesStart;
BYTE* const llCodeTable = seqStorePtr->llCode;
BYTE* const ofCodeTable = seqStorePtr->ofCode;
BYTE* const mlCodeTable = seqStorePtr->mlCode;
U32 const nbSeq = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
U32 u;
int longOffsets = 0;
assert(nbSeq <= seqStorePtr->maxNbSeq);
for (u=0; u<nbSeq; u++) {
U32 const llv = sequences[u].litLength;
U32 const ofCode = ZSTD_highbit32(sequences[u].offBase);
U32 const mlv = sequences[u].mlBase;
llCodeTable[u] = (BYTE)ZSTD_LLcode(llv);
ofCodeTable[u] = (BYTE)ofCode;
mlCodeTable[u] = (BYTE)ZSTD_MLcode(mlv);
assert(!(MEM_64bits() && ofCode >= STREAM_ACCUMULATOR_MIN));
if (MEM_32bits() && ofCode >= STREAM_ACCUMULATOR_MIN)
longOffsets = 1;
}
if (seqStorePtr->longLengthType==ZSTD_llt_literalLength)
llCodeTable[seqStorePtr->longLengthPos] = MaxLL;
if (seqStorePtr->longLengthType==ZSTD_llt_matchLength)
mlCodeTable[seqStorePtr->longLengthPos] = MaxML;
return longOffsets;
}
/* ZSTD_seqToCodes() lives in rust/src/zstd_compress_stats.rs. */
/* ZSTD_useTargetCBlockSize():
* Returns if target compressed block size param is being used.
@@ -2611,150 +2646,11 @@ static int ZSTD_blockSplitterEnabled(ZSTD_CCtx_params* cctxParams)
return (cctxParams->postBlockSplitter == ZSTD_ps_enable);
}
/* Type returned by ZSTD_buildSequencesStatistics containing finalized symbol encoding types
* and size of the sequences statistics
*/
typedef struct {
U32 LLtype;
U32 Offtype;
U32 MLtype;
size_t size;
size_t lastCountSize; /* Accounts for bug in 1.3.4. More detail in ZSTD_entropyCompressSeqStore_internal() */
int longOffsets;
} ZSTD_symbolEncodingTypeStats_t;
/* ZSTD_buildSequencesStatistics() and the ZSTD_entropyCompressSeqStore*()
* implementations live in rust/src/zstd_compress_stats.rs. The wrappers
* below keep the original signatures and extract the only two
* ZSTD_CCtx_params fields those paths read. */
/* ZSTD_buildSequencesStatistics():
* Returns a ZSTD_symbolEncodingTypeStats_t, or a zstd error code in the `size` field.
* Modifies `nextEntropy` to have the appropriate values as a side effect.
* nbSeq must be greater than 0.
*
* entropyWkspSize must be of size at least ENTROPY_WORKSPACE_SIZE - (MaxSeq + 1)*sizeof(U32)
*/
static ZSTD_symbolEncodingTypeStats_t
ZSTD_buildSequencesStatistics(
const SeqStore_t* seqStorePtr, size_t nbSeq,
const ZSTD_fseCTables_t* prevEntropy, ZSTD_fseCTables_t* nextEntropy,
BYTE* dst, const BYTE* const dstEnd,
ZSTD_strategy strategy, unsigned* countWorkspace,
void* entropyWorkspace, size_t entropyWkspSize)
{
BYTE* const ostart = dst;
const BYTE* const oend = dstEnd;
BYTE* op = ostart;
FSE_CTable* CTable_LitLength = nextEntropy->litlengthCTable;
FSE_CTable* CTable_OffsetBits = nextEntropy->offcodeCTable;
FSE_CTable* CTable_MatchLength = nextEntropy->matchlengthCTable;
const BYTE* const ofCodeTable = seqStorePtr->ofCode;
const BYTE* const llCodeTable = seqStorePtr->llCode;
const BYTE* const mlCodeTable = seqStorePtr->mlCode;
ZSTD_symbolEncodingTypeStats_t stats;
stats.lastCountSize = 0;
/* convert length/distances into codes */
stats.longOffsets = ZSTD_seqToCodes(seqStorePtr);
assert(op <= oend);
assert(nbSeq != 0); /* ZSTD_selectEncodingType() divides by nbSeq */
/* build CTable for Literal Lengths */
{ unsigned max = MaxLL;
size_t const mostFrequent = HIST_countFast_wksp(countWorkspace, &max, llCodeTable, nbSeq, entropyWorkspace, entropyWkspSize); /* can't fail */
DEBUGLOG(5, "Building LL table");
nextEntropy->litlength_repeatMode = prevEntropy->litlength_repeatMode;
stats.LLtype = ZSTD_selectEncodingType(&nextEntropy->litlength_repeatMode,
countWorkspace, max, mostFrequent, nbSeq,
LLFSELog, prevEntropy->litlengthCTable,
LL_defaultNorm, LL_defaultNormLog,
ZSTD_defaultAllowed, strategy);
assert(set_basic < set_compressed && set_rle < set_compressed);
assert(!(stats.LLtype < set_compressed && nextEntropy->litlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */
{ size_t const countSize = ZSTD_buildCTable(
op, (size_t)(oend - op),
CTable_LitLength, LLFSELog, (SymbolEncodingType_e)stats.LLtype,
countWorkspace, max, llCodeTable, nbSeq,
LL_defaultNorm, LL_defaultNormLog, MaxLL,
prevEntropy->litlengthCTable,
sizeof(prevEntropy->litlengthCTable),
entropyWorkspace, entropyWkspSize);
if (ZSTD_isError(countSize)) {
DEBUGLOG(3, "ZSTD_buildCTable for LitLens failed");
stats.size = countSize;
return stats;
}
if (stats.LLtype == set_compressed)
stats.lastCountSize = countSize;
op += countSize;
assert(op <= oend);
} }
/* build CTable for Offsets */
{ unsigned max = MaxOff;
size_t const mostFrequent = HIST_countFast_wksp(
countWorkspace, &max, ofCodeTable, nbSeq, entropyWorkspace, entropyWkspSize); /* can't fail */
/* We can only use the basic table if max <= DefaultMaxOff, otherwise the offsets are too large */
ZSTD_DefaultPolicy_e const defaultPolicy = (max <= DefaultMaxOff) ? ZSTD_defaultAllowed : ZSTD_defaultDisallowed;
DEBUGLOG(5, "Building OF table");
nextEntropy->offcode_repeatMode = prevEntropy->offcode_repeatMode;
stats.Offtype = ZSTD_selectEncodingType(&nextEntropy->offcode_repeatMode,
countWorkspace, max, mostFrequent, nbSeq,
OffFSELog, prevEntropy->offcodeCTable,
OF_defaultNorm, OF_defaultNormLog,
defaultPolicy, strategy);
assert(!(stats.Offtype < set_compressed && nextEntropy->offcode_repeatMode != FSE_repeat_none)); /* We don't copy tables */
{ size_t const countSize = ZSTD_buildCTable(
op, (size_t)(oend - op),
CTable_OffsetBits, OffFSELog, (SymbolEncodingType_e)stats.Offtype,
countWorkspace, max, ofCodeTable, nbSeq,
OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff,
prevEntropy->offcodeCTable,
sizeof(prevEntropy->offcodeCTable),
entropyWorkspace, entropyWkspSize);
if (ZSTD_isError(countSize)) {
DEBUGLOG(3, "ZSTD_buildCTable for Offsets failed");
stats.size = countSize;
return stats;
}
if (stats.Offtype == set_compressed)
stats.lastCountSize = countSize;
op += countSize;
assert(op <= oend);
} }
/* build CTable for MatchLengths */
{ unsigned max = MaxML;
size_t const mostFrequent = HIST_countFast_wksp(
countWorkspace, &max, mlCodeTable, nbSeq, entropyWorkspace, entropyWkspSize); /* can't fail */
DEBUGLOG(5, "Building ML table (remaining space : %i)", (int)(oend-op));
nextEntropy->matchlength_repeatMode = prevEntropy->matchlength_repeatMode;
stats.MLtype = ZSTD_selectEncodingType(&nextEntropy->matchlength_repeatMode,
countWorkspace, max, mostFrequent, nbSeq,
MLFSELog, prevEntropy->matchlengthCTable,
ML_defaultNorm, ML_defaultNormLog,
ZSTD_defaultAllowed, strategy);
assert(!(stats.MLtype < set_compressed && nextEntropy->matchlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */
{ size_t const countSize = ZSTD_buildCTable(
op, (size_t)(oend - op),
CTable_MatchLength, MLFSELog, (SymbolEncodingType_e)stats.MLtype,
countWorkspace, max, mlCodeTable, nbSeq,
ML_defaultNorm, ML_defaultNormLog, MaxML,
prevEntropy->matchlengthCTable,
sizeof(prevEntropy->matchlengthCTable),
entropyWorkspace, entropyWkspSize);
if (ZSTD_isError(countSize)) {
DEBUGLOG(3, "ZSTD_buildCTable for MatchLengths failed");
stats.size = countSize;
return stats;
}
if (stats.MLtype == set_compressed)
stats.lastCountSize = countSize;
op += countSize;
assert(op <= oend);
} }
stats.size = (size_t)(op-ostart);
return stats;
}
/* ZSTD_entropyCompressSeqStore_internal():
* compresses both literals and sequences
* Returns compressed size of block, or a zstd error.
*/
#define SUSPECT_UNCOMPRESSIBLE_LITERAL_RATIO 20
MEM_STATIC size_t
ZSTD_entropyCompressSeqStore_internal(
void* dst, size_t dstCapacity,
@@ -2766,150 +2662,13 @@ ZSTD_entropyCompressSeqStore_internal(
void* entropyWorkspace, size_t entropyWkspSize,
const int bmi2)
{
ZSTD_strategy const strategy = cctxParams->cParams.strategy;
unsigned* count = (unsigned*)entropyWorkspace;
FSE_CTable* CTable_LitLength = nextEntropy->fse.litlengthCTable;
FSE_CTable* CTable_OffsetBits = nextEntropy->fse.offcodeCTable;
FSE_CTable* CTable_MatchLength = nextEntropy->fse.matchlengthCTable;
const SeqDef* const sequences = seqStorePtr->sequencesStart;
const size_t nbSeq = (size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
const BYTE* const ofCodeTable = seqStorePtr->ofCode;
const BYTE* const llCodeTable = seqStorePtr->llCode;
const BYTE* const mlCodeTable = seqStorePtr->mlCode;
BYTE* const ostart = (BYTE*)dst;
BYTE* const oend = ostart + dstCapacity;
BYTE* op = ostart;
size_t lastCountSize;
int longOffsets = 0;
entropyWorkspace = count + (MaxSeq + 1);
entropyWkspSize -= (MaxSeq + 1) * sizeof(*count);
DEBUGLOG(5, "ZSTD_entropyCompressSeqStore_internal (nbSeq=%zu, dstCapacity=%zu)", nbSeq, dstCapacity);
ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<<MAX(MLFSELog,LLFSELog)));
assert(entropyWkspSize >= HUF_WORKSPACE_SIZE);
/* Compress literals */
{ size_t const numSequences = (size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
/* Base suspicion of uncompressibility on ratio of literals to sequences */
int const suspectUncompressible = (numSequences == 0) || (litSize / numSequences >= SUSPECT_UNCOMPRESSIBLE_LITERAL_RATIO);
size_t const cSize = ZSTD_compressLiterals(
op, dstCapacity,
literals, litSize,
entropyWorkspace, entropyWkspSize,
&prevEntropy->huf, &nextEntropy->huf,
cctxParams->cParams.strategy,
ZSTD_literalsCompressionIsDisabled(cctxParams),
suspectUncompressible, bmi2);
FORWARD_IF_ERROR(cSize, "ZSTD_compressLiterals failed");
assert(cSize <= dstCapacity);
op += cSize;
}
/* Sequences Header */
RETURN_ERROR_IF((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/,
dstSize_tooSmall, "Can't fit seq hdr in output buf!");
if (nbSeq < 128) {
*op++ = (BYTE)nbSeq;
} else if (nbSeq < LONGNBSEQ) {
op[0] = (BYTE)((nbSeq>>8) + 0x80);
op[1] = (BYTE)nbSeq;
op+=2;
} else {
op[0]=0xFF;
MEM_writeLE16(op+1, (U16)(nbSeq - LONGNBSEQ));
op+=3;
}
assert(op <= oend);
if (nbSeq==0) {
/* Copy the old tables over as if we repeated them */
ZSTD_memcpy(&nextEntropy->fse, &prevEntropy->fse, sizeof(prevEntropy->fse));
return (size_t)(op - ostart);
}
{ BYTE* const seqHead = op++;
/* build stats for sequences */
const ZSTD_symbolEncodingTypeStats_t stats =
ZSTD_buildSequencesStatistics(seqStorePtr, nbSeq,
&prevEntropy->fse, &nextEntropy->fse,
op, oend,
strategy, count,
entropyWorkspace, entropyWkspSize);
FORWARD_IF_ERROR(stats.size, "ZSTD_buildSequencesStatistics failed!");
*seqHead = (BYTE)((stats.LLtype<<6) + (stats.Offtype<<4) + (stats.MLtype<<2));
lastCountSize = stats.lastCountSize;
op += stats.size;
longOffsets = stats.longOffsets;
}
{ size_t const bitstreamSize = ZSTD_encodeSequences(
op, (size_t)(oend - op),
CTable_MatchLength, mlCodeTable,
CTable_OffsetBits, ofCodeTable,
CTable_LitLength, llCodeTable,
sequences, nbSeq,
longOffsets, bmi2);
FORWARD_IF_ERROR(bitstreamSize, "ZSTD_encodeSequences failed");
op += bitstreamSize;
assert(op <= oend);
/* zstd versions <= 1.3.4 mistakenly report corruption when
* FSE_readNCount() receives a buffer < 4 bytes.
* Fixed by https://github.com/facebook/zstd/pull/1146.
* This can happen when the last set_compressed table present is 2
* bytes and the bitstream is only one byte.
* In this exceedingly rare case, we will simply emit an uncompressed
* block, since it isn't worth optimizing.
*/
if (lastCountSize && (lastCountSize + bitstreamSize) < 4) {
/* lastCountSize >= 2 && bitstreamSize > 0 ==> lastCountSize == 3 */
assert(lastCountSize + bitstreamSize == 3);
DEBUGLOG(5, "Avoiding bug in zstd decoder in versions <= 1.3.4 by "
"emitting an uncompressed block.");
return 0;
}
}
DEBUGLOG(5, "compressed block size : %u", (unsigned)(op - ostart));
return (size_t)(op - ostart);
}
static size_t
ZSTD_entropyCompressSeqStore_wExtLitBuffer(
void* dst, size_t dstCapacity,
const void* literals, size_t litSize,
size_t blockSize,
const SeqStore_t* seqStorePtr,
const ZSTD_entropyCTables_t* prevEntropy,
ZSTD_entropyCTables_t* nextEntropy,
const ZSTD_CCtx_params* cctxParams,
void* entropyWorkspace, size_t entropyWkspSize,
int bmi2)
{
size_t const cSize = ZSTD_entropyCompressSeqStore_internal(
dst, dstCapacity,
literals, litSize,
seqStorePtr, prevEntropy, nextEntropy, cctxParams,
entropyWorkspace, entropyWkspSize, bmi2);
if (cSize == 0) return 0;
/* When srcSize <= dstCapacity, there is enough space to write a raw uncompressed block.
* Since we ran out of space, block must be not compressible, so fall back to raw uncompressed block.
*/
if ((cSize == ERROR(dstSize_tooSmall)) & (blockSize <= dstCapacity)) {
DEBUGLOG(4, "not enough dstCapacity (%zu) for ZSTD_entropyCompressSeqStore_internal()=> do not compress block", dstCapacity);
return 0; /* block not compressed */
}
FORWARD_IF_ERROR(cSize, "ZSTD_entropyCompressSeqStore_internal failed");
/* Check compressibility */
{ size_t const maxCSize = blockSize - ZSTD_minGain(blockSize, cctxParams->cParams.strategy);
if (cSize >= maxCSize) return 0; /* block not compressed */
}
DEBUGLOG(5, "ZSTD_entropyCompressSeqStore() cSize: %zu", cSize);
/* libzstd decoder before > v1.5.4 is not compatible with compressed blocks of size ZSTD_BLOCKSIZE_MAX exactly.
* This restriction is indirectly already fulfilled by respecting ZSTD_minGain() condition above.
*/
assert(cSize < ZSTD_BLOCKSIZE_MAX);
return cSize;
return ZSTD_rust_entropyCompressSeqStore_internal(
dst, dstCapacity,
literals, litSize,
seqStorePtr, prevEntropy, nextEntropy,
(int)cctxParams->cParams.strategy,
ZSTD_literalsCompressionIsDisabled(cctxParams),
entropyWorkspace, entropyWkspSize, bmi2);
}
static size_t
@@ -2923,13 +2682,12 @@ ZSTD_entropyCompressSeqStore(
void* entropyWorkspace, size_t entropyWkspSize,
int bmi2)
{
return ZSTD_entropyCompressSeqStore_wExtLitBuffer(
return ZSTD_rust_entropyCompressSeqStore(
seqStorePtr, prevEntropy, nextEntropy,
(int)cctxParams->cParams.strategy,
ZSTD_literalsCompressionIsDisabled(cctxParams),
dst, dstCapacity,
seqStorePtr->litStart, (size_t)(seqStorePtr->lit - seqStorePtr->litStart),
srcSize,
seqStorePtr,
prevEntropy, nextEntropy,
cctxParams,
entropyWorkspace, entropyWkspSize,
bmi2);
}
@@ -3299,87 +3057,8 @@ static size_t ZSTD_buildSeqStore(ZSTD_CCtx* zc, const void* src, size_t srcSize)
static size_t ZSTD_copyBlockSequences(SeqCollector* seqCollector, const SeqStore_t* seqStore, const U32 prevRepcodes[ZSTD_REP_NUM])
{
const SeqDef* inSeqs = seqStore->sequencesStart;
const size_t nbInSequences = (size_t)(seqStore->sequences - inSeqs);
const size_t nbInLiterals = (size_t)(seqStore->lit - seqStore->litStart);
ZSTD_Sequence* outSeqs = seqCollector->seqIndex == 0 ? seqCollector->seqStart : seqCollector->seqStart + seqCollector->seqIndex;
const size_t nbOutSequences = nbInSequences + 1;
size_t nbOutLiterals = 0;
Repcodes_t repcodes;
size_t i;
/* Bounds check that we have enough space for every input sequence
* and the block delimiter
*/
assert(seqCollector->seqIndex <= seqCollector->maxSequences);
RETURN_ERROR_IF(
nbOutSequences > (size_t)(seqCollector->maxSequences - seqCollector->seqIndex),
dstSize_tooSmall,
"Not enough space to copy sequences");
ZSTD_memcpy(&repcodes, prevRepcodes, sizeof(repcodes));
for (i = 0; i < nbInSequences; ++i) {
U32 rawOffset;
outSeqs[i].litLength = inSeqs[i].litLength;
outSeqs[i].matchLength = inSeqs[i].mlBase + MINMATCH;
outSeqs[i].rep = 0;
/* Handle the possible single length >= 64K
* There can only be one because we add MINMATCH to every match length,
* and blocks are at most 128K.
*/
if (i == seqStore->longLengthPos) {
if (seqStore->longLengthType == ZSTD_llt_literalLength) {
outSeqs[i].litLength += 0x10000;
} else if (seqStore->longLengthType == ZSTD_llt_matchLength) {
outSeqs[i].matchLength += 0x10000;
}
}
/* Determine the raw offset given the offBase, which may be a repcode. */
if (OFFBASE_IS_REPCODE(inSeqs[i].offBase)) {
const U32 repcode = OFFBASE_TO_REPCODE(inSeqs[i].offBase);
assert(repcode > 0);
outSeqs[i].rep = repcode;
if (outSeqs[i].litLength != 0) {
rawOffset = repcodes.rep[repcode - 1];
} else {
if (repcode == 3) {
assert(repcodes.rep[0] > 1);
rawOffset = repcodes.rep[0] - 1;
} else {
rawOffset = repcodes.rep[repcode];
}
}
} else {
rawOffset = OFFBASE_TO_OFFSET(inSeqs[i].offBase);
}
outSeqs[i].offset = rawOffset;
/* Update repcode history for the sequence */
ZSTD_updateRep(repcodes.rep,
inSeqs[i].offBase,
inSeqs[i].litLength == 0);
nbOutLiterals += outSeqs[i].litLength;
}
/* Insert last literals (if any exist) in the block as a sequence with ml == off == 0.
* If there are no last literals, then we'll emit (of: 0, ml: 0, ll: 0), which is a marker
* for the block boundary, according to the API.
*/
assert(nbInLiterals >= nbOutLiterals);
{
const size_t lastLLSize = nbInLiterals - nbOutLiterals;
outSeqs[nbInSequences].litLength = (U32)lastLLSize;
outSeqs[nbInSequences].matchLength = 0;
outSeqs[nbInSequences].offset = 0;
assert(nbOutSequences == nbInSequences + 1);
}
seqCollector->seqIndex += nbOutSequences;
assert(seqCollector->seqIndex <= seqCollector->maxSequences);
return 0;
/* The implementation lives in rust/src/zstd_compress_stats.rs. */
return ZSTD_rust_copyBlockSequences(seqCollector, seqStore, prevRepcodes);
}
/* ZSTD_sequenceBound() lives in rust/src/zstd_compress_api.rs. */
@@ -3475,178 +3154,14 @@ writeBlockHeader(void* op, size_t cSize, size_t blockSize, U32 lastBlock)
DEBUGLOG(5, "writeBlockHeader: cSize: %zu blockSize: %zu lastBlock: %u", cSize, blockSize, lastBlock);
}
/** ZSTD_buildBlockEntropyStats_literals() :
* Builds entropy for the literals.
* Stores literals block type (raw, rle, compressed, repeat) and
* huffman description table to hufMetadata.
* Requires ENTROPY_WORKSPACE_SIZE workspace
* @return : size of huffman description table, or an error code
*/
static size_t
ZSTD_buildBlockEntropyStats_literals(void* const src, size_t srcSize,
const ZSTD_hufCTables_t* prevHuf,
ZSTD_hufCTables_t* nextHuf,
ZSTD_hufCTablesMetadata_t* hufMetadata,
const int literalsCompressionIsDisabled,
void* workspace, size_t wkspSize,
int hufFlags)
{
BYTE* const wkspStart = (BYTE*)workspace;
BYTE* const wkspEnd = wkspStart + wkspSize;
BYTE* const countWkspStart = wkspStart;
unsigned* const countWksp = (unsigned*)workspace;
const size_t countWkspSize = (HUF_SYMBOLVALUE_MAX + 1) * sizeof(unsigned);
BYTE* const nodeWksp = countWkspStart + countWkspSize;
const size_t nodeWkspSize = (size_t)(wkspEnd - nodeWksp);
unsigned maxSymbolValue = HUF_SYMBOLVALUE_MAX;
unsigned huffLog = LitHufLog;
HUF_repeat repeat = prevHuf->repeatMode;
DEBUGLOG(5, "ZSTD_buildBlockEntropyStats_literals (srcSize=%zu)", srcSize);
/* Prepare nextEntropy assuming reusing the existing table */
ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
if (literalsCompressionIsDisabled) {
DEBUGLOG(5, "set_basic - disabled");
hufMetadata->hType = set_basic;
return 0;
}
/* small ? don't even attempt compression (speed opt) */
#ifndef COMPRESS_LITERALS_SIZE_MIN
# define COMPRESS_LITERALS_SIZE_MIN 63 /* heuristic */
#endif
{ size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
if (srcSize <= minLitSize) {
DEBUGLOG(5, "set_basic - too small");
hufMetadata->hType = set_basic;
return 0;
} }
/* Scan input and build symbol stats */
{ size_t const largest =
HIST_count_wksp (countWksp, &maxSymbolValue,
(const BYTE*)src, srcSize,
workspace, wkspSize);
FORWARD_IF_ERROR(largest, "HIST_count_wksp failed");
if (largest == srcSize) {
/* only one literal symbol */
DEBUGLOG(5, "set_rle");
hufMetadata->hType = set_rle;
return 0;
}
if (largest <= (srcSize >> 7)+4) {
/* heuristic: likely not compressible */
DEBUGLOG(5, "set_basic - no gain");
hufMetadata->hType = set_basic;
return 0;
} }
/* Validate the previous Huffman table */
if (repeat == HUF_repeat_check
&& !HUF_validateCTable((HUF_CElt const*)prevHuf->CTable, countWksp, maxSymbolValue)) {
repeat = HUF_repeat_none;
}
/* Build Huffman Tree */
ZSTD_memset(nextHuf->CTable, 0, sizeof(nextHuf->CTable));
huffLog = HUF_optimalTableLog(huffLog, srcSize, maxSymbolValue, nodeWksp, nodeWkspSize, nextHuf->CTable, countWksp, hufFlags);
assert(huffLog <= LitHufLog);
{ size_t const maxBits = HUF_buildCTable_wksp((HUF_CElt*)nextHuf->CTable, countWksp,
maxSymbolValue, huffLog,
nodeWksp, nodeWkspSize);
FORWARD_IF_ERROR(maxBits, "HUF_buildCTable_wksp");
huffLog = (U32)maxBits;
}
{ /* Build and write the CTable */
size_t const newCSize = HUF_estimateCompressedSize(
(HUF_CElt*)nextHuf->CTable, countWksp, maxSymbolValue);
size_t const hSize = HUF_writeCTable_wksp(
hufMetadata->hufDesBuffer, sizeof(hufMetadata->hufDesBuffer),
(HUF_CElt*)nextHuf->CTable, maxSymbolValue, huffLog,
nodeWksp, nodeWkspSize);
/* Check against repeating the previous CTable */
if (repeat != HUF_repeat_none) {
size_t const oldCSize = HUF_estimateCompressedSize(
(HUF_CElt const*)prevHuf->CTable, countWksp, maxSymbolValue);
if (oldCSize < srcSize && (oldCSize <= hSize + newCSize || hSize + 12 >= srcSize)) {
DEBUGLOG(5, "set_repeat - smaller");
ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
hufMetadata->hType = set_repeat;
return 0;
} }
if (newCSize + hSize >= srcSize) {
DEBUGLOG(5, "set_basic - no gains");
ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
hufMetadata->hType = set_basic;
return 0;
}
DEBUGLOG(5, "set_compressed (hSize=%u)", (U32)hSize);
hufMetadata->hType = set_compressed;
nextHuf->repeatMode = HUF_repeat_check;
return hSize;
}
}
/* ZSTD_buildDummySequencesStatistics():
* Returns a ZSTD_symbolEncodingTypeStats_t with all encoding types as set_basic,
* and updates nextEntropy to the appropriate repeatMode.
*/
static ZSTD_symbolEncodingTypeStats_t
ZSTD_buildDummySequencesStatistics(ZSTD_fseCTables_t* nextEntropy)
{
ZSTD_symbolEncodingTypeStats_t stats = {set_basic, set_basic, set_basic, 0, 0, 0};
nextEntropy->litlength_repeatMode = FSE_repeat_none;
nextEntropy->offcode_repeatMode = FSE_repeat_none;
nextEntropy->matchlength_repeatMode = FSE_repeat_none;
return stats;
}
/** ZSTD_buildBlockEntropyStats_sequences() :
* Builds entropy for the sequences.
* Stores symbol compression modes and fse table to fseMetadata.
* Requires ENTROPY_WORKSPACE_SIZE wksp.
* @return : size of fse tables or error code */
static size_t
ZSTD_buildBlockEntropyStats_sequences(
const SeqStore_t* seqStorePtr,
const ZSTD_fseCTables_t* prevEntropy,
ZSTD_fseCTables_t* nextEntropy,
const ZSTD_CCtx_params* cctxParams,
ZSTD_fseCTablesMetadata_t* fseMetadata,
void* workspace, size_t wkspSize)
{
ZSTD_strategy const strategy = cctxParams->cParams.strategy;
size_t const nbSeq = (size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
BYTE* const ostart = fseMetadata->fseTablesBuffer;
BYTE* const oend = ostart + sizeof(fseMetadata->fseTablesBuffer);
BYTE* op = ostart;
unsigned* countWorkspace = (unsigned*)workspace;
unsigned* entropyWorkspace = countWorkspace + (MaxSeq + 1);
size_t entropyWorkspaceSize = wkspSize - (MaxSeq + 1) * sizeof(*countWorkspace);
ZSTD_symbolEncodingTypeStats_t stats;
DEBUGLOG(5, "ZSTD_buildBlockEntropyStats_sequences (nbSeq=%zu)", nbSeq);
stats = nbSeq != 0 ? ZSTD_buildSequencesStatistics(seqStorePtr, nbSeq,
prevEntropy, nextEntropy, op, oend,
strategy, countWorkspace,
entropyWorkspace, entropyWorkspaceSize)
: ZSTD_buildDummySequencesStatistics(nextEntropy);
FORWARD_IF_ERROR(stats.size, "ZSTD_buildSequencesStatistics failed!");
fseMetadata->llType = (SymbolEncodingType_e) stats.LLtype;
fseMetadata->ofType = (SymbolEncodingType_e) stats.Offtype;
fseMetadata->mlType = (SymbolEncodingType_e) stats.MLtype;
fseMetadata->lastCountSize = stats.lastCountSize;
return stats.size;
}
/** ZSTD_buildBlockEntropyStats() :
* Builds entropy for the block.
* Requires workspace size ENTROPY_WORKSPACE_SIZE
* @return : 0 on success, or an error code
* Note : also employed in superblock
*
* The implementation, together with its literals/sequences/dummy helpers,
* lives in rust/src/zstd_compress_stats.rs.
*/
size_t ZSTD_buildBlockEntropyStats(
const SeqStore_t* seqStorePtr,
@@ -3656,26 +3171,12 @@ size_t ZSTD_buildBlockEntropyStats(
ZSTD_entropyCTablesMetadata_t* entropyMetadata,
void* workspace, size_t wkspSize)
{
size_t const litSize = (size_t)(seqStorePtr->lit - seqStorePtr->litStart);
int const huf_useOptDepth = (cctxParams->cParams.strategy >= HUF_OPTIMAL_DEPTH_THRESHOLD);
int const hufFlags = huf_useOptDepth ? HUF_flags_optimalDepth : 0;
entropyMetadata->hufMetadata.hufDesSize =
ZSTD_buildBlockEntropyStats_literals(seqStorePtr->litStart, litSize,
&prevEntropy->huf, &nextEntropy->huf,
&entropyMetadata->hufMetadata,
ZSTD_literalsCompressionIsDisabled(cctxParams),
workspace, wkspSize, hufFlags);
FORWARD_IF_ERROR(entropyMetadata->hufMetadata.hufDesSize, "ZSTD_buildBlockEntropyStats_literals failed");
entropyMetadata->fseMetadata.fseTablesSize =
ZSTD_buildBlockEntropyStats_sequences(seqStorePtr,
&prevEntropy->fse, &nextEntropy->fse,
cctxParams,
&entropyMetadata->fseMetadata,
workspace, wkspSize);
FORWARD_IF_ERROR(entropyMetadata->fseMetadata.fseTablesSize, "ZSTD_buildBlockEntropyStats_sequences failed");
return 0;
return ZSTD_rust_buildBlockEntropyStats(
seqStorePtr, prevEntropy, nextEntropy,
(int)cctxParams->cParams.strategy,
ZSTD_literalsCompressionIsDisabled(cctxParams),
entropyMetadata,
workspace, wkspSize);
}
/* Returns the size estimate for the literals section (header + content) of a block */
lib/compress/zstd_compress_superblock.c
+3 -2
View File
@@ -29,7 +29,7 @@ size_t ZSTD_rust_compressSuperBlock(
const SeqStore_t* seqStore,
const ZSTD_compressedBlockState_t* prevCBlock,
ZSTD_compressedBlockState_t* nextCBlock,
const ZSTD_CCtx_params* cctxParams,
int strategy, int disableLiteralCompression,
void* workspace, size_t wkspSize,
int bmi2, U32 windowLog, size_t targetCBlockSize,
void* dst, size_t dstCapacity,
@@ -45,7 +45,8 @@ size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc,
&zc->seqStore,
zc->blockState.prevCBlock,
zc->blockState.nextCBlock,
&zc->appliedParams,
(int)zc->appliedParams.cParams.strategy,
ZSTD_literalsCompressionIsDisabled(&zc->appliedParams),
zc->tmpWorkspace, zc->tmpWkspSize,
zc->bmi2, zc->appliedParams.cParams.windowLog,
zc->appliedParams.targetCBlockSize,