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

[libzstd] Handle uncompressed literals

Browse Source
This commit is contained in:
Nick Terrell
2019-02-15 14:58:11 -08:00
parent a96e67af6c
commit 3d7377b874
4 changed files with 40 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/compress/zstd_compress.c
+5 -2
View File
@@ -402,7 +402,6 @@ static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param)
case ZSTD_c_minMatch:
case ZSTD_c_targetLength:
case ZSTD_c_strategy:
case ZSTD_c_literalCompressionMode:
return 1;
case ZSTD_c_format:
@@ -421,6 +420,7 @@ static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param)
case ZSTD_c_ldmBucketSizeLog:
case ZSTD_c_ldmHashRateLog:
case ZSTD_c_forceAttachDict:
case ZSTD_c_literalCompressionMode:
default:
return 0;
}
@@ -2677,7 +2677,10 @@ static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc,
goto out; /* don't even attempt compression below a certain srcSize */
}
ZSTD_resetSeqStore(&(zc->seqStore));
ms->opt.symbolCosts = &zc->blockState.prevCBlock->entropy; /* required for optimal parser to read stats from dictionary */
/* required for optimal parser to read stats from dictionary */
ms->opt.symbolCosts = &zc->blockState.prevCBlock->entropy;
/* tell the optimal parser how we expect to compress literals */
ms->opt.literalCompressionMode = zc->appliedParams.literalCompressionMode;
/* a gap between an attached dict and the current window is not safe,
* they must remain adjacent,
lib/compress/zstd_compress_internal.h
+1
View File
@@ -107,6 +107,7 @@ typedef struct {
U32 offCodeSumBasePrice; /* to compare to log2(offreq) */
ZSTD_OptPrice_e priceType; /* prices can be determined dynamically, or follow a pre-defined cost structure */
const ZSTD_entropyCTables_t* symbolCosts; /* pre-calculated dictionary statistics */
ZSTD_literalCompressionMode_e literalCompressionMode;
} optState_t;
typedef struct {
lib/compress/zstd_opt.c
+25 -9
View File
@@ -64,9 +64,15 @@ MEM_STATIC double ZSTD_fCost(U32 price)
}
#endif
static int ZSTD_compressedLiterals(optState_t const* const optPtr)
{
return optPtr->literalCompressionMode != ZSTD_lcm_uncompressed;
}
static void ZSTD_setBasePrices(optState_t* optPtr, int optLevel)
{
optPtr->litSumBasePrice = WEIGHT(optPtr->litSum, optLevel);
if (ZSTD_compressedLiterals(optPtr))
optPtr->litSumBasePrice = WEIGHT(optPtr->litSum, optLevel);
optPtr->litLengthSumBasePrice = WEIGHT(optPtr->litLengthSum, optLevel);
optPtr->matchLengthSumBasePrice = WEIGHT(optPtr->matchLengthSum, optLevel);
optPtr->offCodeSumBasePrice = WEIGHT(optPtr->offCodeSum, optLevel);
@@ -99,6 +105,7 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
const BYTE* const src, size_t const srcSize,
int const optLevel)
{
int const compressedLiterals = ZSTD_compressedLiterals(optPtr);
DEBUGLOG(5, "ZSTD_rescaleFreqs (srcSize=%u)", (unsigned)srcSize);
optPtr->priceType = zop_dynamic;
@@ -113,9 +120,10 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
/* huffman table presumed generated by dictionary */
optPtr->priceType = zop_dynamic;
assert(optPtr->litFreq != NULL);
optPtr->litSum = 0;
{ unsigned lit;
if (compressedLiterals) {
unsigned lit;
assert(optPtr->litFreq != NULL);
optPtr->litSum = 0;
for (lit=0; lit<=MaxLit; lit++) {
U32 const scaleLog = 11; /* scale to 2K */
U32 const bitCost = HUF_getNbBits(optPtr->symbolCosts->huf.CTable, lit);
@@ -163,10 +171,11 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
} else { /* not a dictionary */
assert(optPtr->litFreq != NULL);
{ unsigned lit = MaxLit;
if (compressedLiterals) {
unsigned lit = MaxLit;
HIST_count_simple(optPtr->litFreq, &lit, src, srcSize); /* use raw first block to init statistics */
optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
}
optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
{ unsigned ll;
for (ll=0; ll<=MaxLL; ll++)
@@ -190,7 +199,8 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
} else { /* new block : re-use previous statistics, scaled down */
optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
if (compressedLiterals)
optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
optPtr->litLengthSum = ZSTD_downscaleStat(optPtr->litLengthFreq, MaxLL, 0);
optPtr->matchLengthSum = ZSTD_downscaleStat(optPtr->matchLengthFreq, MaxML, 0);
optPtr->offCodeSum = ZSTD_downscaleStat(optPtr->offCodeFreq, MaxOff, 0);
@@ -207,6 +217,10 @@ static U32 ZSTD_rawLiteralsCost(const BYTE* const literals, U32 const litLength,
int optLevel)
{
if (litLength == 0) return 0;
if (!ZSTD_compressedLiterals(optPtr))
return (litLength << 3) * BITCOST_MULTIPLIER; /* Uncompressed - 8 bytes per literal. */
if (optPtr->priceType == zop_predef)
return (litLength*6) * BITCOST_MULTIPLIER; /* 6 bit per literal - no statistic used */
@@ -310,7 +324,8 @@ static void ZSTD_updateStats(optState_t* const optPtr,
U32 offsetCode, U32 matchLength)
{
/* literals */
{ U32 u;
if (ZSTD_compressedLiterals(optPtr)) {
U32 u;
for (u=0; u < litLength; u++)
optPtr->litFreq[literals[u]] += ZSTD_LITFREQ_ADD;
optPtr->litSum += litLength*ZSTD_LITFREQ_ADD;
@@ -1108,7 +1123,8 @@ static U32 ZSTD_upscaleStat(unsigned* table, U32 lastEltIndex, int bonus)
/* used in 2-pass strategy */
MEM_STATIC void ZSTD_upscaleStats(optState_t* optPtr)
{
optPtr->litSum = ZSTD_upscaleStat(optPtr->litFreq, MaxLit, 0);
if (ZSTD_compressedLiterals(optPtr))
optPtr->litSum = ZSTD_upscaleStat(optPtr->litFreq, MaxLit, 0);
optPtr->litLengthSum = ZSTD_upscaleStat(optPtr->litLengthFreq, MaxLL, 0);
optPtr->matchLengthSum = ZSTD_upscaleStat(optPtr->matchLengthFreq, MaxML, 0);
optPtr->offCodeSum = ZSTD_upscaleStat(optPtr->offCodeFreq, MaxOff, 0);