Added multiplier, renamed new enum to something more useful

diff --git a/lib/compress/zstd_compress.c b/lib/compress/zstd_compress.c
index 3aa111ddb6f17385ebd215501f4479bb9fc0b78f..73e6618c1a5061286bed3b94a46e0a09f9b7d6c5 100644 (file)
--- a/lib/compress/zstd_compress.c
+++ b/lib/compress/zstd_compress.c
@@ -387,7 +387,7 @@ ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param)
     case ZSTD_c_forceAttachDict:
         ZSTD_STATIC_ASSERT(ZSTD_dictDefaultAttach < ZSTD_dictForceCopy);
         bounds.lowerBound = ZSTD_dictDefaultAttach;
-        bounds.upperBound = ZSTD_dictForceSource;       /* note : how to ensure at compile time that this is the highest value enum ? */
+        bounds.upperBound = ZSTD_dictForceLoad;       /* note : how to ensure at compile time that this is the highest value enum ? */
         return bounds;
 
     case ZSTD_c_literalCompressionMode:
@@ -2890,7 +2890,8 @@ ZSTD_compress_insertDictionary(ZSTD_compressedBlockState_t* bs,
         bs, ms, ws, params, dict, dictSize, dtlm, workspace);
 }
 
-#define ZSTD_USE_CDICT_PARAMS_CUTOFF (1 MB)
+#define ZSTD_USE_CDICT_PARAMS_SRCSIZE_CUTOFF (128 KB)
+#define ZSTD_USE_CDICT_PARAMS_DICTSIZE_MULTIPLIER (6)
 
 /*! ZSTD_compressBegin_internal() :
  * @return : 0, or an error code */
@@ -2908,8 +2909,10 @@ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx,
     assert(!((dict) && (cdict)));  /* either dict or cdict, not both */
     if ( (cdict)
       && (cdict->dictContentSize > 0)
-      && (pledgedSrcSize < ZSTD_USE_CDICT_PARAMS_CUTOFF || cdict->compressionLevel == 0)
-      && (params->attachDictPref != ZSTD_dictForceSource) ) {
+      && ( (pledgedSrcSize < ZSTD_USE_CDICT_PARAMS_SRCSIZE_CUTOFF
+          || pledgedSrcSize < cdict->dictContentSize * ZSTD_USE_CDICT_PARAMS_DICTSIZE_MULTIPLIER)
+        || cdict->compressionLevel == 0)
+      && (params->attachDictPref != ZSTD_dictForceLoad) ) {
         return ZSTD_resetCCtx_usingCDict(cctx, cdict, params, pledgedSrcSize, zbuff);
     }
 
@@ -3357,8 +3360,10 @@ size_t ZSTD_compressBegin_usingCDict_advanced(
     DEBUGLOG(4, "ZSTD_compressBegin_usingCDict_advanced");
     RETURN_ERROR_IF(cdict==NULL, dictionary_wrong);
     {   ZSTD_CCtx_params params = cctx->requestedParams;
-        params.cParams = ( (pledgedSrcSize < ZSTD_USE_CDICT_PARAMS_CUTOFF) || (cdict->compressionLevel == 0) )
-                      && (params.attachDictPref != ZSTD_dictForceSource) ?
+        params.cParams = ( (pledgedSrcSize < ZSTD_USE_CDICT_PARAMS_SRCSIZE_CUTOFF
+                          || pledgedSrcSize < cdict->dictContentSize * ZSTD_USE_CDICT_PARAMS_DICTSIZE_MULTIPLIER)
+                        || (cdict->compressionLevel == 0) )
+                      && (params.attachDictPref != ZSTD_dictForceLoad) ?
                 ZSTD_getCParamsFromCDict(cdict)
               : ZSTD_getCParams(cdict->compressionLevel,
                                 pledgedSrcSize,

diff --git a/lib/zstd.h b/lib/zstd.h
index 5468c34ccf8870e8c397253e43939ffeed5094c9..3ba476e880bf07ebca7feb95adea43cfb589f665 100644 (file)
--- a/lib/zstd.h
+++ b/lib/zstd.h
@@ -1166,8 +1166,10 @@ typedef enum {
      *   faster than copying the CDict's tables.
      * 
      * - The CDict's tables are not used at all, and instead we use the working
-     *   context alone to determine how our tables are initialized. This method
-     *   should be used when using a small dictionary to compress a large input.
+     *   context alone to reload the dictionary and use params based on the source
+     *   size. See ZSTD_compress_insertDictionary() and ZSTD_compress_usingDict().
+     *   This method is effective when the dictionary sizes are very small relative
+     *   to the input size, and the input size is fairly large to begin with.
      *
      * Zstd has a simple internal heuristic that selects which strategy to use
      * at the beginning of a compression. However, if experimentation shows that
@@ -1177,7 +1179,7 @@ typedef enum {
     ZSTD_dictDefaultAttach = 0, /* Use the default heuristic. */
     ZSTD_dictForceAttach   = 1, /* Never copy the dictionary. */
     ZSTD_dictForceCopy     = 2, /* Always copy the dictionary. */
-    ZSTD_dictForceSource   = 3, /* Always use src input to determine tables */
+    ZSTD_dictForceLoad     = 3, /* Always reload the dictionary */
 } ZSTD_dictAttachPref_e;
 
 typedef enum {