Add --size-hint=# option

lib/compress/zstd_compress.c

@@ -392,6 +392,11 @@ ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param)
         bounds.upperBound = ZSTD_TARGETCBLOCKSIZE_MAX;
         return bounds;
 
+    case ZSTD_c_srcSizeHint:
+        bounds.lowerBound = 0;
+        bounds.upperBound = ZSTD_SRCSIZEHINT_MAX;
+        return bounds;
+
     default:
         {   ZSTD_bounds const boundError = { ERROR(parameter_unsupported), 0, 0 };
             return boundError;
@@ -448,6 +453,7 @@ static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param)
     case ZSTD_c_forceAttachDict:
     case ZSTD_c_literalCompressionMode:
     case ZSTD_c_targetCBlockSize:
+    case ZSTD_c_srcSizeHint:
     default:
         return 0;
     }
@@ -494,6 +500,7 @@ size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value)
     case ZSTD_c_ldmMinMatch:
     case ZSTD_c_ldmBucketSizeLog:
     case ZSTD_c_targetCBlockSize:
+    case ZSTD_c_srcSizeHint:
         break;
 
     default: RETURN_ERROR(parameter_unsupported);
@@ -674,6 +681,12 @@ size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams,
         CCtxParams->targetCBlockSize = value;
         return CCtxParams->targetCBlockSize;
 
+    case ZSTD_c_srcSizeHint :
+        if (value!=0)    /* 0 ==> default */
+            BOUNDCHECK(ZSTD_c_srcSizeHint, value);
+        CCtxParams->srcSizeHint = value;
+        return CCtxParams->srcSizeHint;
+
     default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
     }
 }
@@ -779,6 +792,8 @@ size_t ZSTD_CCtxParams_getParameter(
     case ZSTD_c_targetCBlockSize :
         *value = (int)CCtxParams->targetCBlockSize;
         break;
+    case ZSTD_c_srcSizeHint :
+        *value = (int)CCtxParams->srcSizeHint;
     default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
     }
     return 0;
@@ -1029,7 +1044,11 @@ ZSTD_adjustCParams(ZSTD_compressionParameters cPar,
 ZSTD_compressionParameters ZSTD_getCParamsFromCCtxParams(
         const ZSTD_CCtx_params* CCtxParams, U64 srcSizeHint, size_t dictSize)
 {
-    ZSTD_compressionParameters cParams = ZSTD_getCParams(CCtxParams->compressionLevel, srcSizeHint, dictSize);
+    ZSTD_compressionParameters cParams;
+    if (srcSizeHint == ZSTD_CONTENTSIZE_UNKNOWN && CCtxParams->srcSizeHint > 0) {
+      srcSizeHint = CCtxParams->srcSizeHint;
+    }
+    cParams = ZSTD_getCParams(CCtxParams->compressionLevel, srcSizeHint, dictSize);
     if (CCtxParams->ldmParams.enableLdm) cParams.windowLog = ZSTD_LDM_DEFAULT_WINDOW_LOG;
     if (CCtxParams->cParams.windowLog) cParams.windowLog = CCtxParams->cParams.windowLog;
     if (CCtxParams->cParams.hashLog) cParams.hashLog = CCtxParams->cParams.hashLog;

lib/compress/zstd_compress_internal.h

@@ -203,6 +203,9 @@ struct ZSTD_CCtx_params_s {
     size_t targetCBlockSize;   /* Tries to fit compressed block size to be around targetCBlockSize.
                                 * No target when targetCBlockSize == 0.
                                 * There is no guarantee on compressed block size */
+    size_t srcSizeHint;        /* User's best guess of source size.
+                                * Hint is not valid when srcSizeHint == 0.
+                                * There is no guarantee that hint is close to actual source size */
 
     ZSTD_dictAttachPref_e attachDictPref;
     ZSTD_literalCompressionMode_e literalCompressionMode;

lib/zstd.h

@@ -386,6 +386,7 @@ typedef enum {
      * ZSTD_c_forceAttachDict
      * ZSTD_c_literalCompressionMode
      * ZSTD_c_targetCBlockSize
+     * ZSTD_c_srcSizeHint
      * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them.
      * note : never ever use experimentalParam? names directly;
      *        also, the enums values themselves are unstable and can still change.
@@ -396,6 +397,7 @@ typedef enum {
      ZSTD_c_experimentalParam4=1001,
      ZSTD_c_experimentalParam5=1002,
      ZSTD_c_experimentalParam6=1003,
+     ZSTD_c_experimentalParam7=1004,
 } ZSTD_cParameter;
 
 typedef struct {
@@ -1063,6 +1065,7 @@ ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
 /* Advanced parameter bounds */
 #define ZSTD_TARGETCBLOCKSIZE_MIN   64
 #define ZSTD_TARGETCBLOCKSIZE_MAX   ZSTD_BLOCKSIZE_MAX
+#define ZSTD_SRCSIZEHINT_MAX        1e9  /* 1 GB */
 
 /* internal */
 #define ZSTD_HASHLOG3_MAX           17
@@ -1441,6 +1444,11 @@ ZSTDLIB_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const void* pre
  * There is no guarantee on compressed block size (default:0) */
 #define ZSTD_c_targetCBlockSize ZSTD_c_experimentalParam6
 
+/* User's best guess of source size.
+ * Hint is not valid when srcSizeHint == 0.
+ * There is no guarantee that hint is close to actual source size */
+#define ZSTD_c_srcSizeHint ZSTD_c_experimentalParam7
+
 /*! ZSTD_CCtx_getParameter() :
  *  Get the requested compression parameter value, selected by enum ZSTD_cParameter,
  *  and store it into int* value.