slightly improved weight calculation

translating into a tiny compression ratio improvement

diff --git a/lib/compress/zstd_compress.c b/lib/compress/zstd_compress.c
index d4191afa1eb7223334a6b4665a33648eba47dbc8..1b4882841636a9c58b790793609747838cece970 100644 (file)
--- a/lib/compress/zstd_compress.c
+++ b/lib/compress/zstd_compress.c
@@ -1977,7 +1977,7 @@ static void ZSTD_storeLastLiterals(seqStore_t* seqStorePtr,
     seqStorePtr->lit += lastLLSize;
 }
 
-static void ZSTD_resetSeqStore(seqStore_t* ssPtr)
+void ZSTD_resetSeqStore(seqStore_t* ssPtr)
 {
     ssPtr->lit = ssPtr->litStart;
     ssPtr->sequences = ssPtr->sequencesStart;

diff --git a/lib/compress/zstd_compress_internal.h b/lib/compress/zstd_compress_internal.h
index 8e13aadd8e3dfbe18ad79901ca5c0e2f2f20b862..18fa87fe5fbff78db2bb69eebd752092d176e765 100644 (file)
--- a/lib/compress/zstd_compress_internal.h
+++ b/lib/compress/zstd_compress_internal.h
@@ -80,12 +80,12 @@ typedef enum { zop_dynamic=0, zop_predef } ZSTD_OptPrice_e;
 
 typedef struct {
     /* All tables are allocated inside cctx->workspace by ZSTD_resetCCtx_internal() */
-    U32* litFreq;               /* table of literals statistics, of size 256 */
-    U32* litLengthFreq;         /* table of litLength statistics, of size (MaxLL+1) */
-    U32* matchLengthFreq;       /* table of matchLength statistics, of size (MaxML+1) */
-    U32* offCodeFreq;           /* table of offCode statistics, of size (MaxOff+1) */
-    ZSTD_match_t* matchTable;   /* list of found matches, of size ZSTD_OPT_NUM+1 */
-    ZSTD_optimal_t* priceTable; /* All positions tracked by optimal parser, of size ZSTD_OPT_NUM+1 */
+    U32* litFreq;                /* table of literals statistics, of size 256 */
+    U32* litLengthFreq;          /* table of litLength statistics, of size (MaxLL+1) */
+    U32* matchLengthFreq;        /* table of matchLength statistics, of size (MaxML+1) */
+    U32* offCodeFreq;            /* table of offCode statistics, of size (MaxOff+1) */
+    ZSTD_match_t* matchTable;    /* list of found matches, of size ZSTD_OPT_NUM+1 */
+    ZSTD_optimal_t* priceTable;  /* All positions tracked by optimal parser, of size ZSTD_OPT_NUM+1 */
 
     U32  litSum;                 /* nb of literals */
     U32  litLengthSum;           /* nb of litLength codes */
@@ -658,6 +658,8 @@ size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
                      const ZSTD_CDict* cdict,
                      ZSTD_CCtx_params  params, unsigned long long pledgedSrcSize);
 
+void ZSTD_resetSeqStore(seqStore_t* ssPtr);
+
 /*! ZSTD_compressStream_generic() :
  *  Private use only. To be called from zstdmt_compress.c in single-thread mode. */
 size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,

diff --git a/lib/compress/zstd_opt.c b/lib/compress/zstd_opt.c
index 274bce1483491c120b021abd9fa2cb3fb66aa8da..827fb49a42917da22f205098b422dfd004ae7e06 100644 (file)
--- a/lib/compress/zstd_opt.c
+++ b/lib/compress/zstd_opt.c
@@ -25,29 +25,29 @@
 #  define BITCOST_ACCURACY 0
 #  define BITCOST_MULTIPLIER (1 << BITCOST_ACCURACY)
 #  define WEIGHT(stat)  ((void)opt, ZSTD_bitWeight(stat))
-#elif 0  /* fractional bit accuracy */
+#elif 1  /* fractional bit accuracy */
 #  define BITCOST_ACCURACY 8
 #  define BITCOST_MULTIPLIER (1 << BITCOST_ACCURACY)
 #  define WEIGHT(stat,opt) ((void)opt, ZSTD_fracWeight(stat))
-#else   /* opt==approx, ultra==accurate */
+#else    /* opt==approx, ultra==accurate */
 #  define BITCOST_ACCURACY 8
 #  define BITCOST_MULTIPLIER (1 << BITCOST_ACCURACY)
-#  define WEIGHT(stat,opt) (opt ? ZSTD_fracWeight(stat) : ZSTD_bitWeight(stat) )
+#  define WEIGHT(stat,opt) (opt ? ZSTD_fracWeight(stat) : ZSTD_bitWeight(stat))
 #endif
 
 MEM_STATIC U32 ZSTD_bitWeight(U32 stat)
 {
-    return (ZSTD_highbit32((stat)+1) * BITCOST_MULTIPLIER);
+    return (ZSTD_highbit32(stat+1) * BITCOST_MULTIPLIER);
 }
 
-MEM_STATIC U32 ZSTD_fracWeight(U32 stat)
+MEM_STATIC U32 ZSTD_fracWeight(U32 rawStat)
 {
-    U32 const hb = stat ? ZSTD_highbit32(stat) : 0;
+    U32 const stat = rawStat + 1;
+    U32 const hb = ZSTD_highbit32(stat);
     U32 const BWeight = hb * BITCOST_MULTIPLIER;
     U32 const FWeight = (stat << BITCOST_ACCURACY) >> hb;
     U32 const weight = BWeight + FWeight;
     assert(hb + BITCOST_ACCURACY < 31);
-    DEBUGLOG(2, "stat=%u, hb=%u, weight=%u", stat, hb, weight)
     return weight;
 }