zstd: Update to upstream version 1.3.0

thirdparty/README.md

@@ -371,7 +371,7 @@ Files extracted from upstream source:
 ## zstd
 
 - Upstream: https://github.com/facebook/zstd
-- Version: 1.2.0
+- Version: 1.3.0
 - License: BSD-3-Clause
 
 Files extracted from upstream source:

thirdparty/zstd/README.md

@@ -6,10 +6,17 @@ and a command line utility producing and decoding `.zst` and `.gz` files.
 For other programming languages,
 you can consult a list of known ports on [Zstandard homepage](http://www.zstd.net/#other-languages).
 
-|Branch      |Status   |
-|------------|---------|
-|master      | [![Build Status](https://travis-ci.org/facebook/zstd.svg?branch=master)](https://travis-ci.org/facebook/zstd) |
-|dev         | [![Build Status](https://travis-ci.org/facebook/zstd.svg?branch=dev)](https://travis-ci.org/facebook/zstd) |
+| dev branch status |
+|-------------------|
+| [![Build Status][travisDevBadge]][travisLink]   [![Build status][AppveyorDevBadge]][AppveyorLink]   [![Build status][CircleDevBadge]][CircleLink]
+
+[travisDevBadge]: https://travis-ci.org/facebook/zstd.svg?branch=dev "Continuous Integration test suite"
+[travisLink]: https://travis-ci.org/facebook/zstd
+[AppveyorDevBadge]: https://ci.appveyor.com/api/projects/status/xt38wbdxjk5mrbem/branch/dev?svg=true "Windows test suite"
+[AppveyorLink]: https://ci.appveyor.com/project/YannCollet/zstd-p0yf0
+[CircleDevBadge]: https://circleci.com/gh/facebook/zstd/tree/dev.svg?style=shield "Short test suite"
+[CircleLink]: https://circleci.com/gh/facebook/zstd
+
 
 As a reference, several fast compression algorithms were tested and compared
 on a server running Linux Debian (`Linux version 4.8.0-1-amd64`),
@@ -60,11 +67,11 @@ Previous charts provide results applicable to typical file and stream scenarios
 The smaller the amount of data to compress, the more difficult it is to compress. This problem is common to all compression algorithms, and reason is, compression algorithms learn from past data how to compress future data. But at the beginning of a new data set, there is no "past" to build upon.
 
 To solve this situation, Zstd offers a __training mode__, which can be used to tune the algorithm for a selected type of data.
-Training Zstandard is achieved by provide it with a few samples (one file per sample). The result of this training is stored in a file called "dictionary", which must be loaded before compression and decompression.
+Training Zstandard is achieved by providing it with a few samples (one file per sample). The result of this training is stored in a file called "dictionary", which must be loaded before compression and decompression.
 Using this dictionary, the compression ratio achievable on small data improves dramatically.
 
 The following example uses the `github-users` [sample set](https://github.com/facebook/zstd/releases/tag/v1.1.3), created from [github public API](https://developer.github.com/v3/users/#get-all-users).
-It consists of roughly 10K records weighting about 1KB each.
+It consists of roughly 10K records weighing about 1KB each.
 
 Compression Ratio | Compression Speed | Decompression Speed
 ------------------|-------------------|--------------------

thirdparty/zstd/common/bitstream.h

@@ -39,7 +39,6 @@
 extern "C" {
 #endif
 
-
 /*
 *  This API consists of small unitary functions, which must be inlined for best performance.
 *  Since link-time-optimization is not available for all compilers,
@@ -59,7 +58,9 @@ extern "C" {
 #if defined(BIT_DEBUG) && (BIT_DEBUG>=1)
 #  include <assert.h>
 #else
-#  define assert(condition) ((void)0)
+#  ifndef assert
+#    define assert(condition) ((void)0)
+#  endif
 #endif
 
 
@@ -74,6 +75,7 @@ extern "C" {
 #define STREAM_ACCUMULATOR_MIN_64  57
 #define STREAM_ACCUMULATOR_MIN    ((U32)(MEM_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64))
 
+
 /*-******************************************
 *  bitStream encoding API (write forward)
 ********************************************/
@@ -303,13 +305,25 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si
         bitD->bitContainer = *(const BYTE*)(bitD->start);
         switch(srcSize)
         {
-            case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
-            case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
-            case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
-            case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
-            case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
-            case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) <<  8;
-            default:;
+	    case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
+	            /* fall-through */
+
+	    case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
+	            /* fall-through */
+
+	    case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
+	            /* fall-through */
+
+	    case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
+	            /* fall-through */
+
+	    case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
+	            /* fall-through */
+
+	    case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) <<  8;
+	            /* fall-through */
+
+            default: break;
         }
         { BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
           bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0;

thirdparty/zstd/common/error_private.c

@@ -24,7 +24,8 @@ const char* ERR_getErrorString(ERR_enum code)
     case PREFIX(frameParameter_unsupported): return "Unsupported frame parameter";
     case PREFIX(frameParameter_unsupportedBy32bits): return "Frame parameter unsupported in 32-bits mode";
     case PREFIX(frameParameter_windowTooLarge): return "Frame requires too much memory for decoding";
-    case PREFIX(compressionParameter_unsupported): return "Compression parameter is out of bound";
+    case PREFIX(compressionParameter_unsupported): return "Compression parameter is not supported";
+    case PREFIX(compressionParameter_outOfBound): return "Compression parameter is out of bound";
     case PREFIX(init_missing): return "Context should be init first";
     case PREFIX(memory_allocation): return "Allocation error : not enough memory";
     case PREFIX(stage_wrong): return "Operation not authorized at current processing stage";
@@ -38,6 +39,8 @@ const char* ERR_getErrorString(ERR_enum code)
     case PREFIX(dictionary_corrupted): return "Dictionary is corrupted";
     case PREFIX(dictionary_wrong): return "Dictionary mismatch";
     case PREFIX(dictionaryCreation_failed): return "Cannot create Dictionary from provided samples";
+    case PREFIX(frameIndex_tooLarge): return "Frame index is too large";
+    case PREFIX(seekableIO): return "An I/O error occurred when reading/seeking";
     case PREFIX(maxCode):
     default: return notErrorCode;
     }

thirdparty/zstd/common/huf.h

@@ -111,6 +111,18 @@ HUF_PUBLIC_API size_t HUF_compress2 (void* dst, size_t dstCapacity, const void*
 #define HUF_WORKSPACE_SIZE_U32 (HUF_WORKSPACE_SIZE / sizeof(U32))
 HUF_PUBLIC_API size_t HUF_compress4X_wksp (void* dst, size_t dstCapacity, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
 
+/**
+ *  The minimum workspace size for the `workSpace` used in
+ *  HUF_readDTableX2_wksp() and HUF_readDTableX4_wksp().
+ *
+ *  The space used depends on HUF_TABLELOG_MAX, ranging from ~1500 bytes when
+ *  HUF_TABLE_LOG_MAX=12 to ~1850 bytes when HUF_TABLE_LOG_MAX=15.
+ *  Buffer overflow errors may potentially occur if code modifications result in
+ *  a required workspace size greater than that specified in the following
+ *  macro.
+ */
+#define HUF_DECOMPRESS_WORKSPACE_SIZE (2 << 10)
+#define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32))
 
 
 /* ******************************************************************
@@ -170,8 +182,11 @@ size_t HUF_decompress4X4 (void* dst, size_t dstSize, const void* cSrc, size_t cS
 
 size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /**< decodes RLE and uncompressed */
 size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< considers RLE and uncompressed as errors */
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< considers RLE and uncompressed as errors */
 size_t HUF_decompress4X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /**< single-symbol decoder */
+size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /**< single-symbol decoder */
 size_t HUF_decompress4X4_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /**< double-symbols decoder */
+size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /**< double-symbols decoder */
 
 
 /* ****************************************
@@ -243,7 +258,9 @@ HUF_decompress() does the following:
 U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize);
 
 size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize);
+size_t HUF_readDTableX2_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
 size_t HUF_readDTableX4 (HUF_DTable* DTable, const void* src, size_t srcSize);
+size_t HUF_readDTableX4_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
 
 size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
 size_t HUF_decompress4X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
@@ -266,8 +283,11 @@ size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cS
 size_t HUF_decompress1X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* double-symbol decoder */
 
 size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);
+size_t HUF_decompress1X_DCtx_wksp (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);
 size_t HUF_decompress1X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /**< single-symbol decoder */
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /**< single-symbol decoder */
 size_t HUF_decompress1X4_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /**< double-symbols decoder */
+size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /**< double-symbols decoder */
 
 size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);   /**< automatic selection of sing or double symbol decoder, based on DTable */
 size_t HUF_decompress1X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);

thirdparty/zstd/common/mem.h

@@ -352,20 +352,6 @@ MEM_STATIC void MEM_writeBEST(void* memPtr, size_t val)
 }
 
 
-/* function safe only for comparisons */
-MEM_STATIC U32 MEM_readMINMATCH(const void* memPtr, U32 length)
-{
-    switch (length)
-    {
-    default :
-    case 4 : return MEM_read32(memPtr);
-    case 3 : if (MEM_isLittleEndian())
-                return MEM_read32(memPtr)<<8;
-             else
-                return MEM_read32(memPtr)>>8;
-    }
-}
-
 #if defined (__cplusplus)
 }
 #endif

thirdparty/zstd/common/pool.c

@@ -146,6 +146,13 @@ void POOL_free(POOL_ctx *ctx) {
     free(ctx);
 }
 
+size_t POOL_sizeof(POOL_ctx *ctx) {
+    if (ctx==NULL) return 0;  /* supports sizeof NULL */
+    return sizeof(*ctx)
+        + ctx->queueSize * sizeof(POOL_job)
+        + ctx->numThreads * sizeof(pthread_t);
+}
+
 void POOL_add(void *ctxVoid, POOL_function function, void *opaque) {
     POOL_ctx *ctx = (POOL_ctx *)ctxVoid;
     if (!ctx) { return; }
@@ -191,4 +198,9 @@ void POOL_add(void *ctx, POOL_function function, void *opaque) {
   function(opaque);
 }
 
+size_t POOL_sizeof(POOL_ctx *ctx) {
+    if (ctx==NULL) return 0;  /* supports sizeof NULL */
+    return sizeof(*ctx);
+}
+
 #endif  /* ZSTD_MULTITHREAD */

thirdparty/zstd/common/pool.h

@@ -32,6 +32,11 @@ POOL_ctx *POOL_create(size_t numThreads, size_t queueSize);
 */
 void POOL_free(POOL_ctx *ctx);
 
+/*! POOL_sizeof() :
+    return memory usage of pool returned by POOL_create().
+*/
+size_t POOL_sizeof(POOL_ctx *ctx);
+
 /*! POOL_function :
     The function type that can be added to a thread pool.
 */

thirdparty/zstd/common/threading.c

@@ -1,4 +1,3 @@
-
 /**
  * Copyright (c) 2016 Tino Reichardt
  * All rights reserved.

thirdparty/zstd/common/zstd_common.c

@@ -12,16 +12,19 @@
 /*-*************************************
 *  Dependencies
 ***************************************/
-#include <stdlib.h>         /* malloc */
+#include <stdlib.h>      /* malloc, calloc, free */
+#include <string.h>      /* memset */
 #include "error_private.h"
 #define ZSTD_STATIC_LINKING_ONLY
-#include "zstd.h"           /* declaration of ZSTD_isError, ZSTD_getErrorName, ZSTD_getErrorCode, ZSTD_getErrorString, ZSTD_versionNumber */
+#include "zstd.h"
 
 
 /*-****************************************
 *  Version
 ******************************************/
-unsigned ZSTD_versionNumber (void) { return ZSTD_VERSION_NUMBER; }
+unsigned ZSTD_versionNumber(void) { return ZSTD_VERSION_NUMBER; }
+
+const char* ZSTD_versionString(void) { return ZSTD_VERSION_STRING; }
 
 
 /*-****************************************
@@ -47,27 +50,31 @@ const char* ZSTD_getErrorString(ZSTD_ErrorCode code) { return ERR_getErrorString
 /*=**************************************************************
 *  Custom allocator
 ****************************************************************/
-/* default uses stdlib */
-void* ZSTD_defaultAllocFunction(void* opaque, size_t size)
-{
-    void* address = malloc(size);
-    (void)opaque;
-    return address;
-}
-
-void ZSTD_defaultFreeFunction(void* opaque, void* address)
+void* ZSTD_malloc(size_t size, ZSTD_customMem customMem)
 {
-    (void)opaque;
-    free(address);
+    if (customMem.customAlloc)
+        return customMem.customAlloc(customMem.opaque, size);
+    return malloc(size);
 }
 
-void* ZSTD_malloc(size_t size, ZSTD_customMem customMem)
+void* ZSTD_calloc(size_t size, ZSTD_customMem customMem)
 {
-    return customMem.customAlloc(customMem.opaque, size);
+    if (customMem.customAlloc) {
+        /* calloc implemented as malloc+memset;
+         * not as efficient as calloc, but next best guess for custom malloc */
+        void* const ptr = customMem.customAlloc(customMem.opaque, size);
+        memset(ptr, 0, size);
+        return ptr;
+    }
+    return calloc(1, size);
 }
 
 void ZSTD_free(void* ptr, ZSTD_customMem customMem)
 {
-    if (ptr!=NULL)
-        customMem.customFree(customMem.opaque, ptr);
+    if (ptr!=NULL) {
+        if (customMem.customFree)
+            customMem.customFree(customMem.opaque, ptr);
+        else
+            free(ptr);
+    }
 }

thirdparty/zstd/common/zstd_errors.h

@@ -19,10 +19,12 @@ extern "C" {
 
 
 /* =====   ZSTDERRORLIB_API : control library symbols visibility   ===== */
-#if defined(__GNUC__) && (__GNUC__ >= 4)
-#  define ZSTDERRORLIB_VISIBILITY __attribute__ ((visibility ("default")))
-#else
-#  define ZSTDERRORLIB_VISIBILITY
+#ifndef ZSTDERRORLIB_VISIBILITY
+#  if defined(__GNUC__) && (__GNUC__ >= 4)
+#    define ZSTDERRORLIB_VISIBILITY __attribute__ ((visibility ("default")))
+#  else
+#    define ZSTDERRORLIB_VISIBILITY
+#  endif
 #endif
 #if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1)
 #  define ZSTDERRORLIB_API __declspec(dllexport) ZSTDERRORLIB_VISIBILITY
@@ -33,8 +35,11 @@ extern "C" {
 #endif
 
 /*-****************************************
-*  error codes list
-******************************************/
+ *  error codes list
+ *  note : this API is still considered unstable
+ *         it should not be used with a dynamic library
+ *         only static linking is allowed
+ ******************************************/
 typedef enum {
   ZSTD_error_no_error,
   ZSTD_error_GENERIC,
@@ -45,6 +50,7 @@ typedef enum {
   ZSTD_error_frameParameter_unsupportedBy32bits,
   ZSTD_error_frameParameter_windowTooLarge,
   ZSTD_error_compressionParameter_unsupported,
+  ZSTD_error_compressionParameter_outOfBound,
   ZSTD_error_init_missing,
   ZSTD_error_memory_allocation,
   ZSTD_error_stage_wrong,
@@ -58,12 +64,14 @@ typedef enum {
   ZSTD_error_dictionary_corrupted,
   ZSTD_error_dictionary_wrong,
   ZSTD_error_dictionaryCreation_failed,
+  ZSTD_error_frameIndex_tooLarge,
+  ZSTD_error_seekableIO,
   ZSTD_error_maxCode
 } ZSTD_ErrorCode;
 
 /*! ZSTD_getErrorCode() :
     convert a `size_t` function result into a `ZSTD_ErrorCode` enum type,
-    which can be used to compare directly with enum list published into "error_public.h" */
+    which can be used to compare with enum list published above */
 ZSTDERRORLIB_API ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult);
 ZSTDERRORLIB_API const char* ZSTD_getErrorString(ZSTD_ErrorCode code);
 

thirdparty/zstd/common/zstd_internal.h

@@ -18,6 +18,7 @@
 #  include <intrin.h>                    /* For Visual 2005 */
 #  pragma warning(disable : 4100)        /* disable: C4100: unreferenced formal parameter */
 #  pragma warning(disable : 4127)        /* disable: C4127: conditional expression is constant */
+#  pragma warning(disable : 4204)        /* disable: C4204: non-constant aggregate initializer */
 #  pragma warning(disable : 4324)        /* disable: C4324: padded structure */
 #else
 #  if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */
@@ -50,9 +51,42 @@
 #define ZSTD_STATIC_LINKING_ONLY
 #include "zstd.h"
 #ifndef XXH_STATIC_LINKING_ONLY
-#  define XXH_STATIC_LINKING_ONLY   /* XXH64_state_t */
+#  define XXH_STATIC_LINKING_ONLY  /* XXH64_state_t */
+#endif
+#include "xxhash.h"                /* XXH_reset, update, digest */
+
+
+/*-*************************************
+*  Debug
+***************************************/
+#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=1)
+#  include <assert.h>
+#else
+#  ifndef assert
+#    define assert(condition) ((void)0)
+#  endif
+#endif
+
+#define ZSTD_STATIC_ASSERT(c) { enum { ZSTD_static_assert = 1/(int)(!!(c)) }; }
+
+#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=2)
+#  include <stdio.h>
+/* recommended values for ZSTD_DEBUG display levels :
+ * 1 : no display, enables assert() only
+ * 2 : reserved for currently active debugging path
+ * 3 : events once per object lifetime (CCtx, CDict)
+ * 4 : events once per frame
+ * 5 : events once per block
+ * 6 : events once per sequence (*very* verbose) */
+#  define DEBUGLOG(l, ...) {                         \
+                if (l<=ZSTD_DEBUG) {                 \
+                    fprintf(stderr, __FILE__ ": ");  \
+                    fprintf(stderr, __VA_ARGS__);    \
+                    fprintf(stderr, " \n");          \
+            }   }
+#else
+#  define DEBUGLOG(l, ...)      {}    /* disabled */
 #endif
-#include "xxhash.h"               /* XXH_reset, update, digest */
 
 
 /*-*************************************
@@ -70,7 +104,6 @@
 *  Common constants
 ***************************************/
 #define ZSTD_OPT_NUM    (1<<12)
-#define ZSTD_DICT_MAGIC  0xEC30A437   /* v0.7+ */
 
 #define ZSTD_REP_NUM      3                 /* number of repcodes */
 #define ZSTD_REP_CHECK    (ZSTD_REP_NUM)    /* number of repcodes to check by the optimal parser */
@@ -235,15 +268,10 @@ typedef struct {
 
 const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx);
 void ZSTD_seqToCodes(const seqStore_t* seqStorePtr);
-int ZSTD_isSkipFrame(ZSTD_DCtx* dctx);
 
 /* custom memory allocation functions */
-void* ZSTD_defaultAllocFunction(void* opaque, size_t size);
-void ZSTD_defaultFreeFunction(void* opaque, void* address);
-#ifndef ZSTD_DLL_IMPORT
-static const ZSTD_customMem defaultCustomMem = { ZSTD_defaultAllocFunction, ZSTD_defaultFreeFunction, NULL };
-#endif
 void* ZSTD_malloc(size_t size, ZSTD_customMem customMem);
+void* ZSTD_calloc(size_t size, ZSTD_customMem customMem);
 void ZSTD_free(void* ptr, ZSTD_customMem customMem);
 
 
@@ -281,4 +309,26 @@ MEM_STATIC U32 ZSTD_highbit32(U32 val)
 void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx);
 
 
+/*! ZSTD_initCStream_internal() :
+ *  Private use only. Init streaming operation.
+ *  expects params to be valid.
+ *  must receive dict, or cdict, or none, but not both.
+ *  @return : 0, or an error code */
+size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
+                     const void* dict, size_t dictSize,
+                     const ZSTD_CDict* cdict,
+                     ZSTD_parameters params, unsigned long long pledgedSrcSize);
+
+/*! 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,
+                                   ZSTD_outBuffer* output,
+                                   ZSTD_inBuffer* input,
+                                   ZSTD_EndDirective const flushMode);
+
+/*! ZSTD_getParamsFromCDict() :
+ *  as the name implies */
+ZSTD_parameters ZSTD_getParamsFromCDict(const ZSTD_CDict* cdict);
+
+
 #endif   /* ZSTD_CCOMMON_H_MODULE */

thirdparty/zstd/compress/huf_compress.c

@@ -266,7 +266,8 @@ static U32 HUF_setMaxHeight(nodeElt* huffNode, U32 lastNonNull, U32 maxNbBits)
                         if (highTotal <= lowTotal) break;
                 }   }
                 /* only triggered when no more rank 1 symbol left => find closest one (note : there is necessarily at least one !) */
-                while ((nBitsToDecrease<=HUF_TABLELOG_MAX) && (rankLast[nBitsToDecrease] == noSymbol))  /* HUF_MAX_TABLELOG test just to please gcc 5+; but it should not be necessary */
+                /* HUF_MAX_TABLELOG test just to please gcc 5+; but it should not be necessary */
+                while ((nBitsToDecrease<=HUF_TABLELOG_MAX) && (rankLast[nBitsToDecrease] == noSymbol))
                     nBitsToDecrease ++;
                 totalCost -= 1 << (nBitsToDecrease-1);
                 if (rankLast[nBitsToDecrease-1] == noSymbol)
@@ -463,12 +464,15 @@ size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, si
     {
         case 3 : HUF_encodeSymbol(&bitC, ip[n+ 2], CTable);
                  HUF_FLUSHBITS_2(&bitC);
+		 /* fall-through */
         case 2 : HUF_encodeSymbol(&bitC, ip[n+ 1], CTable);
                  HUF_FLUSHBITS_1(&bitC);
+		 /* fall-through */
         case 1 : HUF_encodeSymbol(&bitC, ip[n+ 0], CTable);
                  HUF_FLUSHBITS(&bitC);
-        case 0 :
-        default: ;
+		 /* fall-through */
+        case 0 : /* fall-through */
+        default: break;
     }
 
     for (; n>0; n-=4) {  /* note : n&3==0 at this stage */

thirdparty/zstd/compress/zstd_opt.h

@@ -43,6 +43,7 @@ MEM_STATIC void ZSTD_rescaleFreqs(seqStore_t* ssPtr, const BYTE* src, size_t src
     if (ssPtr->litLengthSum == 0) {
         if (srcSize <= 1024) ssPtr->staticPrices = 1;
 
+        assert(ssPtr->litFreq!=NULL);
         for (u=0; u<=MaxLit; u++)
             ssPtr->litFreq[u] = 0;
         for (u=0; u<srcSize; u++)
@@ -201,6 +202,20 @@ MEM_STATIC void ZSTD_updatePrice(seqStore_t* seqStorePtr, U32 litLength, const B
     }
 
 
+/* function safe only for comparisons */
+MEM_STATIC U32 ZSTD_readMINMATCH(const void* memPtr, U32 length)
+{
+    switch (length)
+    {
+    default :
+    case 4 : return MEM_read32(memPtr);
+    case 3 : if (MEM_isLittleEndian())
+                return MEM_read32(memPtr)<<8;
+             else
+                return MEM_read32(memPtr)>>8;
+    }
+}
+
 
 /* Update hashTable3 up to ip (excluded)
    Assumption : always within prefix (i.e. not within extDict) */
@@ -234,12 +249,12 @@ static U32 ZSTD_insertBtAndGetAllMatches (
 {
     const BYTE* const base = zc->base;
     const U32 current = (U32)(ip-base);
-    const U32 hashLog = zc->params.cParams.hashLog;
+    const U32 hashLog = zc->appliedParams.cParams.hashLog;
     const size_t h  = ZSTD_hashPtr(ip, hashLog, mls);
     U32* const hashTable = zc->hashTable;
     U32 matchIndex  = hashTable[h];
     U32* const bt   = zc->chainTable;
-    const U32 btLog = zc->params.cParams.chainLog - 1;
+    const U32 btLog = zc->appliedParams.cParams.chainLog - 1;
     const U32 btMask= (1U << btLog) - 1;
     size_t commonLengthSmaller=0, commonLengthLarger=0;
     const BYTE* const dictBase = zc->dictBase;
@@ -267,7 +282,7 @@ static U32 ZSTD_insertBtAndGetAllMatches (
                 if (match[bestLength] == ip[bestLength]) currentMl = ZSTD_count(ip, match, iLimit);
             } else {
                 match = dictBase + matchIndex3;
-                if (MEM_readMINMATCH(match, MINMATCH) == MEM_readMINMATCH(ip, MINMATCH))    /* assumption : matchIndex3 <= dictLimit-4 (by table construction) */
+                if (ZSTD_readMINMATCH(match, MINMATCH) == ZSTD_readMINMATCH(ip, MINMATCH))    /* assumption : matchIndex3 <= dictLimit-4 (by table construction) */
                     currentMl = ZSTD_count_2segments(ip+MINMATCH, match+MINMATCH, iLimit, dictEnd, prefixStart) + MINMATCH;
             }
 
@@ -410,10 +425,10 @@ void ZSTD_compressBlock_opt_generic(ZSTD_CCtx* ctx,
     const BYTE* const base = ctx->base;
     const BYTE* const prefixStart = base + ctx->dictLimit;
 
-    const U32 maxSearches = 1U << ctx->params.cParams.searchLog;
-    const U32 sufficient_len = ctx->params.cParams.targetLength;
-    const U32 mls = ctx->params.cParams.searchLength;
-    const U32 minMatch = (ctx->params.cParams.searchLength == 3) ? 3 : 4;
+    const U32 maxSearches = 1U << ctx->appliedParams.cParams.searchLog;
+    const U32 sufficient_len = ctx->appliedParams.cParams.targetLength;
+    const U32 mls = ctx->appliedParams.cParams.searchLength;
+    const U32 minMatch = (ctx->appliedParams.cParams.searchLength == 3) ? 3 : 4;
 
     ZSTD_optimal_t* opt = seqStorePtr->priceTable;
     ZSTD_match_t* matches = seqStorePtr->matchTable;
@@ -439,7 +454,7 @@ void ZSTD_compressBlock_opt_generic(ZSTD_CCtx* ctx,
             for (i=(ip == anchor); i<last_i; i++) {
                 const S32 repCur = (i==ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : rep[i];
                 if ( (repCur > 0) && (repCur < (S32)(ip-prefixStart))
-                    && (MEM_readMINMATCH(ip, minMatch) == MEM_readMINMATCH(ip - repCur, minMatch))) {
+                    && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(ip - repCur, minMatch))) {
                     mlen = (U32)ZSTD_count(ip+minMatch, ip+minMatch-repCur, iend) + minMatch;
                     if (mlen > sufficient_len || mlen >= ZSTD_OPT_NUM) {
                         best_mlen = mlen; best_off = i; cur = 0; last_pos = 1;
@@ -524,7 +539,7 @@ void ZSTD_compressBlock_opt_generic(ZSTD_CCtx* ctx,
                 for (i=(opt[cur].mlen != 1); i<last_i; i++) {  /* check rep */
                     const S32 repCur = (i==ZSTD_REP_MOVE_OPT) ? (opt[cur].rep[0] - 1) : opt[cur].rep[i];
                     if ( (repCur > 0) && (repCur < (S32)(inr-prefixStart))
-                       && (MEM_readMINMATCH(inr, minMatch) == MEM_readMINMATCH(inr - repCur, minMatch))) {
+                       && (ZSTD_readMINMATCH(inr, minMatch) == ZSTD_readMINMATCH(inr - repCur, minMatch))) {
                        mlen = (U32)ZSTD_count(inr+minMatch, inr+minMatch - repCur, iend) + minMatch;
 
                        if (mlen > sufficient_len || cur + mlen >= ZSTD_OPT_NUM) {
@@ -663,10 +678,10 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx,
     const BYTE* const dictBase = ctx->dictBase;
     const BYTE* const dictEnd  = dictBase + dictLimit;
 
-    const U32 maxSearches = 1U << ctx->params.cParams.searchLog;
-    const U32 sufficient_len = ctx->params.cParams.targetLength;
-    const U32 mls = ctx->params.cParams.searchLength;
-    const U32 minMatch = (ctx->params.cParams.searchLength == 3) ? 3 : 4;
+    const U32 maxSearches = 1U << ctx->appliedParams.cParams.searchLog;
+    const U32 sufficient_len = ctx->appliedParams.cParams.targetLength;
+    const U32 mls = ctx->appliedParams.cParams.searchLength;
+    const U32 minMatch = (ctx->appliedParams.cParams.searchLength == 3) ? 3 : 4;
 
     ZSTD_optimal_t* opt = seqStorePtr->priceTable;
     ZSTD_match_t* matches = seqStorePtr->matchTable;
@@ -698,7 +713,7 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx,
                 const BYTE* const repMatch = repBase + repIndex;
                 if ( (repCur > 0 && repCur <= (S32)current)
                    && (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex>lowestIndex))  /* intentional overflow */
-                   && (MEM_readMINMATCH(ip, minMatch) == MEM_readMINMATCH(repMatch, minMatch)) ) {
+                   && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) {
                     /* repcode detected we should take it */
                     const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
                     mlen = (U32)ZSTD_count_2segments(ip+minMatch, repMatch+minMatch, iend, repEnd, prefixStart) + minMatch;
@@ -794,7 +809,7 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx,
                     const BYTE* const repMatch = repBase + repIndex;
                     if ( (repCur > 0 && repCur <= (S32)(current+cur))
                       && (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex>lowestIndex))  /* intentional overflow */
-                      && (MEM_readMINMATCH(inr, minMatch) == MEM_readMINMATCH(repMatch, minMatch)) ) {
+                      && (ZSTD_readMINMATCH(inr, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) {
                         /* repcode detected */
                         const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
                         mlen = (U32)ZSTD_count_2segments(inr+minMatch, repMatch+minMatch, iend, repEnd, prefixStart) + minMatch;

thirdparty/zstd/compress/zstdmt_compress.c

@@ -14,34 +14,31 @@
 
 /* ======   Compiler specifics   ====== */
 #if defined(_MSC_VER)
-#  pragma warning(disable : 4204)        /* disable: C4204: non-constant aggregate initializer */
+#  pragma warning(disable : 4204)   /* disable: C4204: non-constant aggregate initializer */
 #endif
 
 
 /* ======   Dependencies   ====== */
-#include <stdlib.h>   /* malloc */
-#include <string.h>   /* memcpy */
-#include "pool.h"     /* threadpool */
-#include "threading.h"  /* mutex */
-#include "zstd_internal.h"   /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */
+#include <string.h>      /* memcpy, memset */
+#include "pool.h"        /* threadpool */
+#include "threading.h"   /* mutex */
+#include "zstd_internal.h"  /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */
 #include "zstdmt_compress.h"
 
 
 /* ======   Debug   ====== */
-#if 0
+#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=2)
 
 #  include <stdio.h>
 #  include <unistd.h>
 #  include <sys/times.h>
-   static unsigned g_debugLevel = 5;
-#  define DEBUGLOGRAW(l, ...) if (l<=g_debugLevel) { fprintf(stderr, __VA_ARGS__); }
-#  define DEBUGLOG(l, ...) if (l<=g_debugLevel) { fprintf(stderr, __FILE__ ": "); fprintf(stderr, __VA_ARGS__); fprintf(stderr, " \n"); }
+#  define DEBUGLOGRAW(l, ...) if (l<=ZSTD_DEBUG) { fprintf(stderr, __VA_ARGS__); }
 
-#  define DEBUG_PRINTHEX(l,p,n) { \
-    unsigned debug_u;                   \
-    for (debug_u=0; debug_u<(n); debug_u++)           \
+#  define DEBUG_PRINTHEX(l,p,n) {            \
+    unsigned debug_u;                        \
+    for (debug_u=0; debug_u<(n); debug_u++)  \
         DEBUGLOGRAW(l, "%02X ", ((const unsigned char*)(p))[debug_u]); \
-    DEBUGLOGRAW(l, " \n");       \
+    DEBUGLOGRAW(l, " \n");                   \
 }
 
 static unsigned long long GetCurrentClockTimeMicroseconds(void)
@@ -53,22 +50,22 @@ static unsigned long long GetCurrentClockTimeMicroseconds(void)
      return ((((unsigned long long)newTicks)*(1000000))/_ticksPerSecond); }
 }
 
-#define MUTEX_WAIT_TIME_DLEVEL 5
-#define PTHREAD_MUTEX_LOCK(mutex) \
-if (g_debugLevel>=MUTEX_WAIT_TIME_DLEVEL) { \
-    unsigned long long const beforeTime = GetCurrentClockTimeMicroseconds(); \
-    pthread_mutex_lock(mutex); \
-    {   unsigned long long const afterTime = GetCurrentClockTimeMicroseconds(); \
-        unsigned long long const elapsedTime = (afterTime-beforeTime); \
-        if (elapsedTime > 1000) {  /* or whatever threshold you like; I'm using 1 millisecond here */ \
-            DEBUGLOG(MUTEX_WAIT_TIME_DLEVEL, "Thread took %llu microseconds to acquire mutex %s \n", \
-               elapsedTime, #mutex); \
-    }   } \
-} else pthread_mutex_lock(mutex);
+#define MUTEX_WAIT_TIME_DLEVEL 6
+#define PTHREAD_MUTEX_LOCK(mutex) {               \
+    if (ZSTD_DEBUG>=MUTEX_WAIT_TIME_DLEVEL) {   \
+        unsigned long long const beforeTime = GetCurrentClockTimeMicroseconds(); \
+        pthread_mutex_lock(mutex);                \
+        {   unsigned long long const afterTime = GetCurrentClockTimeMicroseconds(); \
+            unsigned long long const elapsedTime = (afterTime-beforeTime); \
+            if (elapsedTime > 1000) {  /* or whatever threshold you like; I'm using 1 millisecond here */ \
+                DEBUGLOG(MUTEX_WAIT_TIME_DLEVEL, "Thread took %llu microseconds to acquire mutex %s \n", \
+                   elapsedTime, #mutex);          \
+        }   }                                     \
+    } else pthread_mutex_lock(mutex);             \
+}
 
 #else
 
-#  define DEBUGLOG(l, ...)      {}    /* disabled */
 #  define PTHREAD_MUTEX_LOCK(m) pthread_mutex_lock(m)
 #  define DEBUG_PRINTHEX(l,p,n) {}
 
@@ -87,16 +84,19 @@ static const buffer_t g_nullBuffer = { NULL, 0 };
 typedef struct ZSTDMT_bufferPool_s {
     unsigned totalBuffers;
     unsigned nbBuffers;
+    ZSTD_customMem cMem;
     buffer_t bTable[1];   /* variable size */
 } ZSTDMT_bufferPool;
 
-static ZSTDMT_bufferPool* ZSTDMT_createBufferPool(unsigned nbThreads)
+static ZSTDMT_bufferPool* ZSTDMT_createBufferPool(unsigned nbThreads, ZSTD_customMem cMem)
 {
     unsigned const maxNbBuffers = 2*nbThreads + 2;
-    ZSTDMT_bufferPool* const bufPool = (ZSTDMT_bufferPool*)calloc(1, sizeof(ZSTDMT_bufferPool) + (maxNbBuffers-1) * sizeof(buffer_t));
+    ZSTDMT_bufferPool* const bufPool = (ZSTDMT_bufferPool*)ZSTD_calloc(
+        sizeof(ZSTDMT_bufferPool) + (maxNbBuffers-1) * sizeof(buffer_t), cMem);
     if (bufPool==NULL) return NULL;
     bufPool->totalBuffers = maxNbBuffers;
     bufPool->nbBuffers = 0;
+    bufPool->cMem = cMem;
     return bufPool;
 }
 
@@ -105,23 +105,39 @@ static void ZSTDMT_freeBufferPool(ZSTDMT_bufferPool* bufPool)
     unsigned u;
     if (!bufPool) return;   /* compatibility with free on NULL */
     for (u=0; u<bufPool->totalBuffers; u++)
-        free(bufPool->bTable[u].start);
-    free(bufPool);
+        ZSTD_free(bufPool->bTable[u].start, bufPool->cMem);
+    ZSTD_free(bufPool, bufPool->cMem);
+}
+
+/* only works at initialization, not during compression */
+static size_t ZSTDMT_sizeof_bufferPool(ZSTDMT_bufferPool* bufPool)
+{
+    size_t const poolSize = sizeof(*bufPool)
+                            + (bufPool->totalBuffers - 1) * sizeof(buffer_t);
+    unsigned u;
+    size_t totalBufferSize = 0;
+    for (u=0; u<bufPool->totalBuffers; u++)
+        totalBufferSize += bufPool->bTable[u].size;
+
+    return poolSize + totalBufferSize;
 }
 
-/* assumption : invocation from main thread only ! */
+/** ZSTDMT_getBuffer() :
+ *  assumption : invocation from main thread only ! */
 static buffer_t ZSTDMT_getBuffer(ZSTDMT_bufferPool* pool, size_t bSize)
 {
     if (pool->nbBuffers) {   /* try to use an existing buffer */
         buffer_t const buf = pool->bTable[--(pool->nbBuffers)];
         size_t const availBufferSize = buf.size;
-        if ((availBufferSize >= bSize) & (availBufferSize <= 10*bSize))   /* large enough, but not too much */
+        if ((availBufferSize >= bSize) & (availBufferSize <= 10*bSize))
+            /* large enough, but not too much */
             return buf;
-        free(buf.start);   /* size conditions not respected : scratch this buffer and create a new one */
+        /* size conditions not respected : scratch this buffer, create new one */
+        ZSTD_free(buf.start, pool->cMem);
     }
     /* create new buffer */
     {   buffer_t buffer;
-        void* const start = malloc(bSize);
+        void* const start = ZSTD_malloc(bSize, pool->cMem);
         if (start==NULL) bSize = 0;
         buffer.start = start;   /* note : start can be NULL if malloc fails ! */
         buffer.size = bSize;
@@ -138,7 +154,7 @@ static void ZSTDMT_releaseBuffer(ZSTDMT_bufferPool* pool, buffer_t buf)
         return;
     }
     /* Reached bufferPool capacity (should not happen) */
-    free(buf.start);
+    ZSTD_free(buf.start, pool->cMem);
 }
 
 
@@ -147,6 +163,7 @@ static void ZSTDMT_releaseBuffer(ZSTDMT_bufferPool* pool, buffer_t buf)
 typedef struct {
     unsigned totalCCtx;
     unsigned availCCtx;
+    ZSTD_customMem cMem;
     ZSTD_CCtx* cctx[1];   /* variable size */
 } ZSTDMT_CCtxPool;
 
@@ -158,23 +175,40 @@ static void ZSTDMT_freeCCtxPool(ZSTDMT_CCtxPool* pool)
     unsigned u;
     for (u=0; u<pool->totalCCtx; u++)
         ZSTD_freeCCtx(pool->cctx[u]);  /* note : compatible with free on NULL */
-    free(pool);
+    ZSTD_free(pool, pool->cMem);
 }
 
 /* ZSTDMT_createCCtxPool() :
  * implies nbThreads >= 1 , checked by caller ZSTDMT_createCCtx() */
-static ZSTDMT_CCtxPool* ZSTDMT_createCCtxPool(unsigned nbThreads)
+static ZSTDMT_CCtxPool* ZSTDMT_createCCtxPool(unsigned nbThreads,
+                                              ZSTD_customMem cMem)
 {
-    ZSTDMT_CCtxPool* const cctxPool = (ZSTDMT_CCtxPool*) calloc(1, sizeof(ZSTDMT_CCtxPool) + (nbThreads-1)*sizeof(ZSTD_CCtx*));
+    ZSTDMT_CCtxPool* const cctxPool = (ZSTDMT_CCtxPool*) ZSTD_calloc(
+        sizeof(ZSTDMT_CCtxPool) + (nbThreads-1)*sizeof(ZSTD_CCtx*), cMem);
     if (!cctxPool) return NULL;
+    cctxPool->cMem = cMem;
     cctxPool->totalCCtx = nbThreads;
     cctxPool->availCCtx = 1;   /* at least one cctx for single-thread mode */
-    cctxPool->cctx[0] = ZSTD_createCCtx();
+    cctxPool->cctx[0] = ZSTD_createCCtx_advanced(cMem);
     if (!cctxPool->cctx[0]) { ZSTDMT_freeCCtxPool(cctxPool); return NULL; }
-    DEBUGLOG(1, "cctxPool created, with %u threads", nbThreads);
+    DEBUGLOG(3, "cctxPool created, with %u threads", nbThreads);
     return cctxPool;
 }
 
+/* only works during initialization phase, not during compression */
+static size_t ZSTDMT_sizeof_CCtxPool(ZSTDMT_CCtxPool* cctxPool)
+{
+    unsigned const nbThreads = cctxPool->totalCCtx;
+    size_t const poolSize = sizeof(*cctxPool)
+                            + (nbThreads-1)*sizeof(ZSTD_CCtx*);
+    unsigned u;
+    size_t totalCCtxSize = 0;
+    for (u=0; u<nbThreads; u++)
+        totalCCtxSize += ZSTD_sizeof_CCtx(cctxPool->cctx[u]);
+
+    return poolSize + totalCCtxSize;
+}
+
 static ZSTD_CCtx* ZSTDMT_getCCtx(ZSTDMT_CCtxPool* pool)
 {
     if (pool->availCCtx) {
@@ -218,7 +252,7 @@ typedef struct {
     pthread_mutex_t* jobCompleted_mutex;
     pthread_cond_t* jobCompleted_cond;
     ZSTD_parameters params;
-    ZSTD_CDict* cdict;
+    const ZSTD_CDict* cdict;
     unsigned long long fullFrameSize;
 } ZSTDMT_jobDescription;
 
@@ -228,11 +262,11 @@ void ZSTDMT_compressChunk(void* jobDescription)
     ZSTDMT_jobDescription* const job = (ZSTDMT_jobDescription*)jobDescription;
     const void* const src = (const char*)job->srcStart + job->dictSize;
     buffer_t const dstBuff = job->dstBuff;
-    DEBUGLOG(3, "job (first:%u) (last:%u) : dictSize %u, srcSize %u",
+    DEBUGLOG(5, "job (first:%u) (last:%u) : dictSize %u, srcSize %u",
                  job->firstChunk, job->lastChunk, (U32)job->dictSize, (U32)job->srcSize);
     if (job->cdict) {  /* should only happen for first segment */
         size_t const initError = ZSTD_compressBegin_usingCDict_advanced(job->cctx, job->cdict, job->params.fParams, job->fullFrameSize);
-        if (job->cdict) DEBUGLOG(3, "using CDict ");
+        DEBUGLOG(5, "using CDict");
         if (ZSTD_isError(initError)) { job->cSize = initError; goto _endJob; }
     } else {  /* srcStart points at reloaded section */
         if (!job->firstChunk) job->params.fParams.contentSizeFlag = 0;  /* ensure no srcSize control */
@@ -247,12 +281,12 @@ void ZSTDMT_compressChunk(void* jobDescription)
         ZSTD_invalidateRepCodes(job->cctx);
     }
 
-    DEBUGLOG(4, "Compressing : ");
+    DEBUGLOG(5, "Compressing : ");
     DEBUG_PRINTHEX(4, job->srcStart, 12);
     job->cSize = (job->lastChunk) ?
                  ZSTD_compressEnd     (job->cctx, dstBuff.start, dstBuff.size, src, job->srcSize) :
                  ZSTD_compressContinue(job->cctx, dstBuff.start, dstBuff.size, src, job->srcSize);
-    DEBUGLOG(3, "compressed %u bytes into %u bytes   (first:%u) (last:%u)",
+    DEBUGLOG(5, "compressed %u bytes into %u bytes   (first:%u) (last:%u)",
                 (unsigned)job->srcSize, (unsigned)job->cSize, job->firstChunk, job->lastChunk);
     DEBUGLOG(5, "dstBuff.size : %u ; => %s", (U32)dstBuff.size, ZSTD_getErrorName(job->cSize));
 
@@ -271,6 +305,7 @@ _endJob:
 
 struct ZSTDMT_CCtx_s {
     POOL_ctx* factory;
+    ZSTDMT_jobDescription* jobs;
     ZSTDMT_bufferPool* buffPool;
     ZSTDMT_CCtxPool* cctxPool;
     pthread_mutex_t jobCompleted_mutex;
@@ -292,50 +327,64 @@ struct ZSTDMT_CCtx_s {
     unsigned overlapRLog;
     unsigned long long frameContentSize;
     size_t sectionSize;
-    ZSTD_CDict* cdict;
-    ZSTD_CStream* cstream;
-    ZSTDMT_jobDescription jobs[1];   /* variable size (must lies at the end) */
+    ZSTD_customMem cMem;
+    ZSTD_CDict* cdictLocal;
+    const ZSTD_CDict* cdict;
 };
 
-ZSTDMT_CCtx *ZSTDMT_createCCtx(unsigned nbThreads)
+static ZSTDMT_jobDescription* ZSTDMT_allocJobsTable(U32* nbJobsPtr, ZSTD_customMem cMem)
 {
-    ZSTDMT_CCtx* cctx;
-    U32 const minNbJobs = nbThreads + 2;
-    U32 const nbJobsLog2 = ZSTD_highbit32(minNbJobs) + 1;
+    U32 const nbJobsLog2 = ZSTD_highbit32(*nbJobsPtr) + 1;
     U32 const nbJobs = 1 << nbJobsLog2;
-    DEBUGLOG(5, "nbThreads : %u  ; minNbJobs : %u ;  nbJobsLog2 : %u ;  nbJobs : %u  \n",
-            nbThreads, minNbJobs, nbJobsLog2, nbJobs);
+    *nbJobsPtr = nbJobs;
+    return (ZSTDMT_jobDescription*) ZSTD_calloc(
+                            nbJobs * sizeof(ZSTDMT_jobDescription), cMem);
+}
+
+ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbThreads, ZSTD_customMem cMem)
+{
+    ZSTDMT_CCtx* mtctx;
+    U32 nbJobs = nbThreads + 2;
+    DEBUGLOG(3, "ZSTDMT_createCCtx_advanced");
+
     if ((nbThreads < 1) | (nbThreads > ZSTDMT_NBTHREADS_MAX)) return NULL;
-    cctx = (ZSTDMT_CCtx*) calloc(1, sizeof(ZSTDMT_CCtx) + nbJobs*sizeof(ZSTDMT_jobDescription));
-    if (!cctx) return NULL;
-    cctx->nbThreads = nbThreads;
-    cctx->jobIDMask = nbJobs - 1;
-    cctx->allJobsCompleted = 1;
-    cctx->sectionSize = 0;
-    cctx->overlapRLog = 3;
-    cctx->factory = POOL_create(nbThreads, 1);
-    cctx->buffPool = ZSTDMT_createBufferPool(nbThreads);
-    cctx->cctxPool = ZSTDMT_createCCtxPool(nbThreads);
-    if (!cctx->factory | !cctx->buffPool | !cctx->cctxPool) {  /* one object was not created */
-        ZSTDMT_freeCCtx(cctx);
+    if ((cMem.customAlloc!=NULL) ^ (cMem.customFree!=NULL))
+        /* invalid custom allocator */
+        return NULL;
+
+    mtctx = (ZSTDMT_CCtx*) ZSTD_calloc(sizeof(ZSTDMT_CCtx), cMem);
+    if (!mtctx) return NULL;
+    mtctx->cMem = cMem;
+    mtctx->nbThreads = nbThreads;
+    mtctx->allJobsCompleted = 1;
+    mtctx->sectionSize = 0;
+    mtctx->overlapRLog = 3;
+    mtctx->factory = POOL_create(nbThreads, 1);
+    mtctx->jobs = ZSTDMT_allocJobsTable(&nbJobs, cMem);
+    mtctx->jobIDMask = nbJobs - 1;
+    mtctx->buffPool = ZSTDMT_createBufferPool(nbThreads, cMem);
+    mtctx->cctxPool = ZSTDMT_createCCtxPool(nbThreads, cMem);
+    if (!mtctx->factory | !mtctx->jobs | !mtctx->buffPool | !mtctx->cctxPool) {
+        ZSTDMT_freeCCtx(mtctx);
         return NULL;
     }
-    if (nbThreads==1) {
-        cctx->cstream = ZSTD_createCStream();
-        if (!cctx->cstream) {
-            ZSTDMT_freeCCtx(cctx); return NULL;
-    }   }
-    pthread_mutex_init(&cctx->jobCompleted_mutex, NULL);   /* Todo : check init function return */
-    pthread_cond_init(&cctx->jobCompleted_cond, NULL);
-    DEBUGLOG(4, "mt_cctx created, for %u threads \n", nbThreads);
-    return cctx;
+    pthread_mutex_init(&mtctx->jobCompleted_mutex, NULL);   /* Todo : check init function return */
+    pthread_cond_init(&mtctx->jobCompleted_cond, NULL);
+    DEBUGLOG(3, "mt_cctx created, for %u threads", nbThreads);
+    return mtctx;
+}
+
+ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbThreads)
+{
+    return ZSTDMT_createCCtx_advanced(nbThreads, ZSTD_defaultCMem);
 }
 
 /* ZSTDMT_releaseAllJobResources() :
- * Ensure all workers are killed first. */
+ * note : ensure all workers are killed first ! */
 static void ZSTDMT_releaseAllJobResources(ZSTDMT_CCtx* mtctx)
 {
     unsigned jobID;
+    DEBUGLOG(3, "ZSTDMT_releaseAllJobResources");
     for (jobID=0; jobID <= mtctx->jobIDMask; jobID++) {
         ZSTDMT_releaseBuffer(mtctx->buffPool, mtctx->jobs[jobID].dstBuff);
         mtctx->jobs[jobID].dstBuff = g_nullBuffer;
@@ -356,15 +405,26 @@ size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx)
     POOL_free(mtctx->factory);
     if (!mtctx->allJobsCompleted) ZSTDMT_releaseAllJobResources(mtctx); /* stop workers first */
     ZSTDMT_freeBufferPool(mtctx->buffPool);  /* release job resources into pools first */
+    ZSTD_free(mtctx->jobs, mtctx->cMem);
     ZSTDMT_freeCCtxPool(mtctx->cctxPool);
-    ZSTD_freeCDict(mtctx->cdict);
-    ZSTD_freeCStream(mtctx->cstream);
+    ZSTD_freeCDict(mtctx->cdictLocal);
     pthread_mutex_destroy(&mtctx->jobCompleted_mutex);
     pthread_cond_destroy(&mtctx->jobCompleted_cond);
-    free(mtctx);
+    ZSTD_free(mtctx, mtctx->cMem);
     return 0;
 }
 
+size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx)
+{
+    if (mtctx == NULL) return 0;   /* supports sizeof NULL */
+    return sizeof(*mtctx)
+        + POOL_sizeof(mtctx->factory)
+        + ZSTDMT_sizeof_bufferPool(mtctx->buffPool)
+        + (mtctx->jobIDMask+1) * sizeof(ZSTDMT_jobDescription)
+        + ZSTDMT_sizeof_CCtxPool(mtctx->cctxPool)
+        + ZSTD_sizeof_CDict(mtctx->cdictLocal);
+}
+
 size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter, unsigned value)
 {
     switch(parameter)
@@ -373,7 +433,7 @@ size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter,
         mtctx->sectionSize = value;
         return 0;
     case ZSTDMT_p_overlapSectionLog :
-    DEBUGLOG(4, "ZSTDMT_p_overlapSectionLog : %u", value);
+        DEBUGLOG(5, "ZSTDMT_p_overlapSectionLog : %u", value);
         mtctx->overlapRLog = (value >= 9) ? 0 : 9 - value;
         return 0;
     default :
@@ -386,31 +446,49 @@ size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter,
 /* =====   Multi-threaded compression   ===== */
 /* ------------------------------------------ */
 
-size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
+static unsigned computeNbChunks(size_t srcSize, unsigned windowLog, unsigned nbThreads) {
+    size_t const chunkSizeTarget = (size_t)1 << (windowLog + 2);
+    size_t const chunkMaxSize = chunkSizeTarget << 2;
+    size_t const passSizeMax = chunkMaxSize * nbThreads;
+    unsigned const multiplier = (unsigned)(srcSize / passSizeMax) + 1;
+    unsigned const nbChunksLarge = multiplier * nbThreads;
+    unsigned const nbChunksMax = (unsigned)(srcSize / chunkSizeTarget) + 1;
+    unsigned const nbChunksSmall = MIN(nbChunksMax, nbThreads);
+    return (multiplier>1) ? nbChunksLarge : nbChunksSmall;
+}
+
+
+size_t ZSTDMT_compress_advanced(ZSTDMT_CCtx* mtctx,
                            void* dst, size_t dstCapacity,
                      const void* src, size_t srcSize,
-                           int compressionLevel)
+                     const ZSTD_CDict* cdict,
+                           ZSTD_parameters const params,
+                           unsigned overlapRLog)
 {
-    ZSTD_parameters params = ZSTD_getParams(compressionLevel, srcSize, 0);
-    U32 const overlapLog = (compressionLevel >= ZSTD_maxCLevel()) ? 0 : 3;
-    size_t const overlapSize = (size_t)1 << (params.cParams.windowLog - overlapLog);
-    size_t const chunkTargetSize = (size_t)1 << (params.cParams.windowLog + 2);
-    unsigned const nbChunksMax = (unsigned)(srcSize / chunkTargetSize) + 1;
-    unsigned nbChunks = MIN(nbChunksMax, mtctx->nbThreads);
+    size_t const overlapSize = (overlapRLog>=9) ? 0 : (size_t)1 << (params.cParams.windowLog - overlapRLog);
+    unsigned nbChunks = computeNbChunks(srcSize, params.cParams.windowLog, mtctx->nbThreads);
     size_t const proposedChunkSize = (srcSize + (nbChunks-1)) / nbChunks;
-    size_t const avgChunkSize = ((proposedChunkSize & 0x1FFFF) < 0xFFFF) ? proposedChunkSize + 0xFFFF : proposedChunkSize;   /* avoid too small last block */
-    size_t remainingSrcSize = srcSize;
+    size_t const avgChunkSize = ((proposedChunkSize & 0x1FFFF) < 0x7FFF) ? proposedChunkSize + 0xFFFF : proposedChunkSize;   /* avoid too small last block */
     const char* const srcStart = (const char*)src;
+    size_t remainingSrcSize = srcSize;
     unsigned const compressWithinDst = (dstCapacity >= ZSTD_compressBound(srcSize)) ? nbChunks : (unsigned)(dstCapacity / ZSTD_compressBound(avgChunkSize));  /* presumes avgChunkSize >= 256 KB, which should be the case */
     size_t frameStartPos = 0, dstBufferPos = 0;
 
-    DEBUGLOG(3, "windowLog : %2u => chunkTargetSize : %u bytes  ", params.cParams.windowLog, (U32)chunkTargetSize);
-    DEBUGLOG(2, "nbChunks  : %2u   (chunkSize : %u bytes)   ", nbChunks, (U32)avgChunkSize);
-    params.fParams.contentSizeFlag = 1;
-
+    DEBUGLOG(4, "nbChunks  : %2u   (chunkSize : %u bytes)   ", nbChunks, (U32)avgChunkSize);
     if (nbChunks==1) {   /* fallback to single-thread mode */
         ZSTD_CCtx* const cctx = mtctx->cctxPool->cctx[0];
-        return ZSTD_compressCCtx(cctx, dst, dstCapacity, src, srcSize, compressionLevel);
+        if (cdict) return ZSTD_compress_usingCDict_advanced(cctx, dst, dstCapacity, src, srcSize, cdict, params.fParams);
+        return ZSTD_compress_advanced(cctx, dst, dstCapacity, src, srcSize, NULL, 0, params);
+    }
+    assert(avgChunkSize >= 256 KB);  /* condition for ZSTD_compressBound(A) + ZSTD_compressBound(B) <= ZSTD_compressBound(A+B), which is useful to avoid allocating extra buffers */
+
+    if (nbChunks > mtctx->jobIDMask+1) {  /* enlarge job table */
+        U32 nbJobs = nbChunks;
+        ZSTD_free(mtctx->jobs, mtctx->cMem);
+        mtctx->jobIDMask = 0;
+        mtctx->jobs = ZSTDMT_allocJobsTable(&nbJobs, mtctx->cMem);
+        if (mtctx->jobs==NULL) return ERROR(memory_allocation);
+        mtctx->jobIDMask = nbJobs - 1;
     }
 
     {   unsigned u;
@@ -425,15 +503,18 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
             if ((cctx==NULL) || (dstBuffer.start==NULL)) {
                 mtctx->jobs[u].cSize = ERROR(memory_allocation);   /* job result */
                 mtctx->jobs[u].jobCompleted = 1;
-                nbChunks = u+1;
+                nbChunks = u+1;   /* only wait and free u jobs, instead of initially expected nbChunks ones */
                 break;   /* let's wait for previous jobs to complete, but don't start new ones */
             }
 
             mtctx->jobs[u].srcStart = srcStart + frameStartPos - dictSize;
             mtctx->jobs[u].dictSize = dictSize;
             mtctx->jobs[u].srcSize = chunkSize;
+            mtctx->jobs[u].cdict = mtctx->nextJobID==0 ? cdict : NULL;
             mtctx->jobs[u].fullFrameSize = srcSize;
             mtctx->jobs[u].params = params;
+            /* do not calculate checksum within sections, but write it in header for first section */
+            if (u!=0) mtctx->jobs[u].params.fParams.checksumFlag = 0;
             mtctx->jobs[u].dstBuff = dstBuffer;
             mtctx->jobs[u].cctx = cctx;
             mtctx->jobs[u].firstChunk = (u==0);
@@ -442,27 +523,27 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
             mtctx->jobs[u].jobCompleted_mutex = &mtctx->jobCompleted_mutex;
             mtctx->jobs[u].jobCompleted_cond = &mtctx->jobCompleted_cond;
 
-            DEBUGLOG(3, "posting job %u   (%u bytes)", u, (U32)chunkSize);
-            DEBUG_PRINTHEX(3, mtctx->jobs[u].srcStart, 12);
+            DEBUGLOG(5, "posting job %u   (%u bytes)", u, (U32)chunkSize);
+            DEBUG_PRINTHEX(6, mtctx->jobs[u].srcStart, 12);
             POOL_add(mtctx->factory, ZSTDMT_compressChunk, &mtctx->jobs[u]);
 
             frameStartPos += chunkSize;
             dstBufferPos += dstBufferCapacity;
             remainingSrcSize -= chunkSize;
     }   }
-    /* note : since nbChunks <= nbThreads, all jobs should be running immediately in parallel */
 
+    /* collect result */
     {   unsigned chunkID;
         size_t error = 0, dstPos = 0;
         for (chunkID=0; chunkID<nbChunks; chunkID++) {
-            DEBUGLOG(3, "waiting for chunk %u ", chunkID);
+            DEBUGLOG(5, "waiting for chunk %u ", chunkID);
             PTHREAD_MUTEX_LOCK(&mtctx->jobCompleted_mutex);
             while (mtctx->jobs[chunkID].jobCompleted==0) {
-                DEBUGLOG(4, "waiting for jobCompleted signal from chunk %u", chunkID);
+                DEBUGLOG(5, "waiting for jobCompleted signal from chunk %u", chunkID);
                 pthread_cond_wait(&mtctx->jobCompleted_cond, &mtctx->jobCompleted_mutex);
             }
             pthread_mutex_unlock(&mtctx->jobCompleted_mutex);
-            DEBUGLOG(3, "ready to write chunk %u ", chunkID);
+            DEBUGLOG(5, "ready to write chunk %u ", chunkID);
 
             ZSTDMT_releaseCCtx(mtctx->cctxPool, mtctx->jobs[chunkID].cctx);
             mtctx->jobs[chunkID].cctx = NULL;
@@ -470,20 +551,33 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
             {   size_t const cSize = mtctx->jobs[chunkID].cSize;
                 if (ZSTD_isError(cSize)) error = cSize;
                 if ((!error) && (dstPos + cSize > dstCapacity)) error = ERROR(dstSize_tooSmall);
-                if (chunkID) {   /* note : chunk 0 is already written directly into dst */
+                if (chunkID) {   /* note : chunk 0 is written directly at dst, which is correct position */
                     if (!error)
-                        memmove((char*)dst + dstPos, mtctx->jobs[chunkID].dstBuff.start, cSize);  /* may overlap if chunk decompressed within dst */
-                    if (chunkID >= compressWithinDst)   /* otherwise, it decompresses within dst */
+                        memmove((char*)dst + dstPos, mtctx->jobs[chunkID].dstBuff.start, cSize);  /* may overlap when chunk compressed within dst */
+                    if (chunkID >= compressWithinDst) {  /* chunk compressed into its own buffer, which must be released */
+                        DEBUGLOG(5, "releasing buffer %u>=%u", chunkID, compressWithinDst);
                         ZSTDMT_releaseBuffer(mtctx->buffPool, mtctx->jobs[chunkID].dstBuff);
+                    }
                     mtctx->jobs[chunkID].dstBuff = g_nullBuffer;
                 }
                 dstPos += cSize ;
             }
         }
-        if (!error) DEBUGLOG(3, "compressed size : %u  ", (U32)dstPos);
+        if (!error) DEBUGLOG(4, "compressed size : %u  ", (U32)dstPos);
         return error ? error : dstPos;
     }
+}
+
 
+size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
+                           void* dst, size_t dstCapacity,
+                     const void* src, size_t srcSize,
+                           int compressionLevel)
+{
+    U32 const overlapRLog = (compressionLevel >= ZSTD_maxCLevel()) ? 0 : 3;
+    ZSTD_parameters params = ZSTD_getParams(compressionLevel, srcSize, 0);
+    params.fParams.contentSizeFlag = 1;
+    return ZSTDMT_compress_advanced(mtctx, dst, dstCapacity, src, srcSize, NULL, params, overlapRLog);
 }
 
 
@@ -491,12 +585,14 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
 /* =======      Streaming API     ======= */
 /* ====================================== */
 
-static void ZSTDMT_waitForAllJobsCompleted(ZSTDMT_CCtx* zcs) {
+static void ZSTDMT_waitForAllJobsCompleted(ZSTDMT_CCtx* zcs)
+{
+    DEBUGLOG(4, "ZSTDMT_waitForAllJobsCompleted");
     while (zcs->doneJobID < zcs->nextJobID) {
         unsigned const jobID = zcs->doneJobID & zcs->jobIDMask;
         PTHREAD_MUTEX_LOCK(&zcs->jobCompleted_mutex);
         while (zcs->jobs[jobID].jobCompleted==0) {
-            DEBUGLOG(4, "waiting for jobCompleted signal from chunk %u", zcs->doneJobID);   /* we want to block when waiting for data to flush */
+            DEBUGLOG(5, "waiting for jobCompleted signal from chunk %u", zcs->doneJobID);   /* we want to block when waiting for data to flush */
             pthread_cond_wait(&zcs->jobCompleted_cond, &zcs->jobCompleted_mutex);
         }
         pthread_mutex_unlock(&zcs->jobCompleted_mutex);
@@ -505,33 +601,54 @@ static void ZSTDMT_waitForAllJobsCompleted(ZSTDMT_CCtx* zcs) {
 }
 
 
-static size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
-                                    const void* dict, size_t dictSize, unsigned updateDict,
-                                    ZSTD_parameters params, unsigned long long pledgedSrcSize)
+/** ZSTDMT_initCStream_internal() :
+ *  internal usage only */
+size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
+                    const void* dict, size_t dictSize, const ZSTD_CDict* cdict,
+                    ZSTD_parameters params, unsigned long long pledgedSrcSize)
 {
-    ZSTD_customMem const cmem = { NULL, NULL, NULL };
-    DEBUGLOG(3, "Started new compression, with windowLog : %u", params.cParams.windowLog);
-    if (zcs->nbThreads==1) return ZSTD_initCStream_advanced(zcs->cstream, dict, dictSize, params, pledgedSrcSize);
-    if (zcs->allJobsCompleted == 0) {   /* previous job not correctly finished */
+    DEBUGLOG(4, "ZSTDMT_initCStream_internal");
+    /* params are supposed to be fully validated at this point */
+    assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
+    assert(!((dict) && (cdict)));  /* either dict or cdict, not both */
+
+    if (zcs->nbThreads==1) {
+        DEBUGLOG(4, "single thread mode");
+        return ZSTD_initCStream_internal(zcs->cctxPool->cctx[0],
+                                dict, dictSize, cdict,
+                                params, pledgedSrcSize);
+    }
+
+    if (zcs->allJobsCompleted == 0) {   /* previous compression not correctly finished */
         ZSTDMT_waitForAllJobsCompleted(zcs);
         ZSTDMT_releaseAllJobResources(zcs);
         zcs->allJobsCompleted = 1;
     }
+
     zcs->params = params;
-    if (updateDict) {
-        ZSTD_freeCDict(zcs->cdict); zcs->cdict = NULL;
-        if (dict && dictSize) {
-            zcs->cdict = ZSTD_createCDict_advanced(dict, dictSize, 0, params.cParams, cmem);
-            if (zcs->cdict == NULL) return ERROR(memory_allocation);
-    }   }
     zcs->frameContentSize = pledgedSrcSize;
+    if (dict) {
+        DEBUGLOG(4,"cdictLocal: %08X", (U32)(size_t)zcs->cdictLocal);
+        ZSTD_freeCDict(zcs->cdictLocal);
+        zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize,
+                                                    0 /* byRef */, ZSTD_dm_auto,   /* note : a loadPrefix becomes an internal CDict */
+                                                    params.cParams, zcs->cMem);
+        zcs->cdict = zcs->cdictLocal;
+        if (zcs->cdictLocal == NULL) return ERROR(memory_allocation);
+    } else {
+        DEBUGLOG(4,"cdictLocal: %08X", (U32)(size_t)zcs->cdictLocal);
+        ZSTD_freeCDict(zcs->cdictLocal);
+        zcs->cdictLocal = NULL;
+        zcs->cdict = cdict;
+    }
+
     zcs->targetDictSize = (zcs->overlapRLog>=9) ? 0 : (size_t)1 << (zcs->params.cParams.windowLog - zcs->overlapRLog);
     DEBUGLOG(4, "overlapRLog : %u ", zcs->overlapRLog);
-    DEBUGLOG(3, "overlap Size : %u KB", (U32)(zcs->targetDictSize>>10));
+    DEBUGLOG(4, "overlap Size : %u KB", (U32)(zcs->targetDictSize>>10));
     zcs->targetSectionSize = zcs->sectionSize ? zcs->sectionSize : (size_t)1 << (zcs->params.cParams.windowLog + 2);
     zcs->targetSectionSize = MAX(ZSTDMT_SECTION_SIZE_MIN, zcs->targetSectionSize);
     zcs->targetSectionSize = MAX(zcs->targetDictSize, zcs->targetSectionSize);
-    DEBUGLOG(3, "Section Size : %u KB", (U32)(zcs->targetSectionSize>>10));
+    DEBUGLOG(4, "Section Size : %u KB", (U32)(zcs->targetSectionSize>>10));
     zcs->marginSize = zcs->targetSectionSize >> 2;
     zcs->inBuffSize = zcs->targetDictSize + zcs->targetSectionSize + zcs->marginSize;
     zcs->inBuff.buffer = ZSTDMT_getBuffer(zcs->buffPool, zcs->inBuffSize);
@@ -546,24 +663,39 @@ static size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
     return 0;
 }
 
-size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* zcs,
+size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx,
                                 const void* dict, size_t dictSize,
                                 ZSTD_parameters params, unsigned long long pledgedSrcSize)
 {
-    return ZSTDMT_initCStream_internal(zcs, dict, dictSize, 1, params, pledgedSrcSize);
+    DEBUGLOG(5, "ZSTDMT_initCStream_advanced");
+    return ZSTDMT_initCStream_internal(mtctx, dict, dictSize, NULL, params, pledgedSrcSize);
 }
 
+size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
+                               const ZSTD_CDict* cdict,
+                                     ZSTD_frameParameters fParams,
+                                     unsigned long long pledgedSrcSize)
+{
+    ZSTD_parameters params = ZSTD_getParamsFromCDict(cdict);
+    if (cdict==NULL) return ERROR(dictionary_wrong);   /* method incompatible with NULL cdict */
+    params.fParams = fParams;
+    return ZSTDMT_initCStream_internal(mtctx, NULL, 0 /*dictSize*/, cdict,
+                                        params, pledgedSrcSize);
+}
+
+
 /* ZSTDMT_resetCStream() :
  * pledgedSrcSize is optional and can be zero == unknown */
 size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* zcs, unsigned long long pledgedSrcSize)
 {
-    if (zcs->nbThreads==1) return ZSTD_resetCStream(zcs->cstream, pledgedSrcSize);
+    if (zcs->nbThreads==1)
+        return ZSTD_resetCStream(zcs->cctxPool->cctx[0], pledgedSrcSize);
     return ZSTDMT_initCStream_internal(zcs, NULL, 0, 0, zcs->params, pledgedSrcSize);
 }
 
 size_t ZSTDMT_initCStream(ZSTDMT_CCtx* zcs, int compressionLevel) {
     ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, 0);
-    return ZSTDMT_initCStream_internal(zcs, NULL, 0, 1, params, 0);
+    return ZSTDMT_initCStream_internal(zcs, NULL, 0, NULL, params, 0);
 }
 
 
@@ -582,13 +714,16 @@ static size_t ZSTDMT_createCompressionJob(ZSTDMT_CCtx* zcs, size_t srcSize, unsi
         return ERROR(memory_allocation);
     }
 
-    DEBUGLOG(4, "preparing job %u to compress %u bytes with %u preload ", zcs->nextJobID, (U32)srcSize, (U32)zcs->dictSize);
+    DEBUGLOG(4, "preparing job %u to compress %u bytes with %u preload ",
+                zcs->nextJobID, (U32)srcSize, (U32)zcs->dictSize);
     zcs->jobs[jobID].src = zcs->inBuff.buffer;
     zcs->jobs[jobID].srcStart = zcs->inBuff.buffer.start;
     zcs->jobs[jobID].srcSize = srcSize;
-    zcs->jobs[jobID].dictSize = zcs->dictSize;   /* note : zcs->inBuff.filled is presumed >= srcSize + dictSize */
+    zcs->jobs[jobID].dictSize = zcs->dictSize;
+    assert(zcs->inBuff.filled >= srcSize + zcs->dictSize);
     zcs->jobs[jobID].params = zcs->params;
-    if (zcs->nextJobID) zcs->jobs[jobID].params.fParams.checksumFlag = 0;  /* do not calculate checksum within sections, just keep it in header for first section */
+    /* do not calculate checksum within sections, but write it in header for first section */
+    if (zcs->nextJobID) zcs->jobs[jobID].params.fParams.checksumFlag = 0;
     zcs->jobs[jobID].cdict = zcs->nextJobID==0 ? zcs->cdict : NULL;
     zcs->jobs[jobID].fullFrameSize = zcs->frameContentSize;
     zcs->jobs[jobID].dstBuff = dstBuffer;
@@ -603,6 +738,7 @@ static size_t ZSTDMT_createCompressionJob(ZSTDMT_CCtx* zcs, size_t srcSize, unsi
     /* get a new buffer for next input */
     if (!endFrame) {
         size_t const newDictSize = MIN(srcSize + zcs->dictSize, zcs->targetDictSize);
+        DEBUGLOG(5, "ZSTDMT_createCompressionJob::endFrame = %u", endFrame);
         zcs->inBuff.buffer = ZSTDMT_getBuffer(zcs->buffPool, zcs->inBuffSize);
         if (zcs->inBuff.buffer.start == NULL) {   /* not enough memory to allocate next input buffer */
             zcs->jobs[jobID].jobCompleted = 1;
@@ -611,22 +747,33 @@ static size_t ZSTDMT_createCompressionJob(ZSTDMT_CCtx* zcs, size_t srcSize, unsi
             ZSTDMT_releaseAllJobResources(zcs);
             return ERROR(memory_allocation);
         }
-        DEBUGLOG(5, "inBuff filled to %u", (U32)zcs->inBuff.filled);
+        DEBUGLOG(5, "inBuff currently filled to %u", (U32)zcs->inBuff.filled);
         zcs->inBuff.filled -= srcSize + zcs->dictSize - newDictSize;
-        DEBUGLOG(5, "new job : filled to %u, with %u dict and %u src", (U32)zcs->inBuff.filled, (U32)newDictSize, (U32)(zcs->inBuff.filled - newDictSize));
-        memmove(zcs->inBuff.buffer.start, (const char*)zcs->jobs[jobID].srcStart + zcs->dictSize + srcSize - newDictSize, zcs->inBuff.filled);
+        DEBUGLOG(5, "new job : inBuff filled to %u, with %u dict and %u src",
+                    (U32)zcs->inBuff.filled, (U32)newDictSize,
+                    (U32)(zcs->inBuff.filled - newDictSize));
+        memmove(zcs->inBuff.buffer.start,
+            (const char*)zcs->jobs[jobID].srcStart + zcs->dictSize + srcSize - newDictSize,
+            zcs->inBuff.filled);
         DEBUGLOG(5, "new inBuff pre-filled");
         zcs->dictSize = newDictSize;
-    } else {
+    } else {   /* if (endFrame==1) */
+        DEBUGLOG(5, "ZSTDMT_createCompressionJob::endFrame = %u", endFrame);
         zcs->inBuff.buffer = g_nullBuffer;
         zcs->inBuff.filled = 0;
         zcs->dictSize = 0;
         zcs->frameEnded = 1;
         if (zcs->nextJobID == 0)
-            zcs->params.fParams.checksumFlag = 0;   /* single chunk : checksum is calculated directly within worker thread */
+            /* single chunk exception : checksum is calculated directly within worker thread */
+            zcs->params.fParams.checksumFlag = 0;
     }
 
-    DEBUGLOG(3, "posting job %u : %u bytes  (end:%u) (note : doneJob = %u=>%u)", zcs->nextJobID, (U32)zcs->jobs[jobID].srcSize, zcs->jobs[jobID].lastChunk, zcs->doneJobID, zcs->doneJobID & zcs->jobIDMask);
+    DEBUGLOG(4, "posting job %u : %u bytes  (end:%u) (note : doneJob = %u=>%u)",
+                zcs->nextJobID,
+                (U32)zcs->jobs[jobID].srcSize,
+                zcs->jobs[jobID].lastChunk,
+                zcs->doneJobID,
+                zcs->doneJobID & zcs->jobIDMask);
     POOL_add(zcs->factory, ZSTDMT_compressChunk, &zcs->jobs[jobID]);   /* this call is blocking when thread worker pool is exhausted */
     zcs->nextJobID++;
     return 0;
@@ -664,7 +811,7 @@ static size_t ZSTDMT_flushNextJob(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, unsi
                 XXH64_update(&zcs->xxhState, (const char*)job.srcStart + job.dictSize, job.srcSize);
                 if (zcs->frameEnded && (zcs->doneJobID+1 == zcs->nextJobID)) {  /* write checksum at end of last section */
                     U32 const checksum = (U32)XXH64_digest(&zcs->xxhState);
-                    DEBUGLOG(4, "writing checksum : %08X \n", checksum);
+                    DEBUGLOG(5, "writing checksum : %08X \n", checksum);
                     MEM_writeLE32((char*)job.dstBuff.start + job.cSize, checksum);
                     job.cSize += 4;
                     zcs->jobs[wJobID].cSize += 4;
@@ -675,7 +822,7 @@ static size_t ZSTDMT_flushNextJob(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, unsi
             zcs->jobs[wJobID].jobScanned = 1;
         }
         {   size_t const toWrite = MIN(job.cSize - job.dstFlushed, output->size - output->pos);
-            DEBUGLOG(4, "Flushing %u bytes from job %u ", (U32)toWrite, zcs->doneJobID);
+            DEBUGLOG(5, "Flushing %u bytes from job %u ", (U32)toWrite, zcs->doneJobID);
             memcpy((char*)output->dst + output->pos, (const char*)job.dstBuff.start + job.dstFlushed, toWrite);
             output->pos += toWrite;
             job.dstFlushed += toWrite;
@@ -696,26 +843,81 @@ static size_t ZSTDMT_flushNextJob(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, unsi
 }   }
 
 
-size_t ZSTDMT_compressStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
+/** ZSTDMT_compressStream_generic() :
+ *  internal use only
+ *  assumption : output and input are valid (pos <= size)
+ * @return : minimum amount of data remaining to flush, 0 if none */
+size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
+                                     ZSTD_outBuffer* output,
+                                     ZSTD_inBuffer* input,
+                                     ZSTD_EndDirective endOp)
 {
-    size_t const newJobThreshold = zcs->dictSize + zcs->targetSectionSize + zcs->marginSize;
-    if (zcs->frameEnded) return ERROR(stage_wrong);   /* current frame being ended. Only flush is allowed. Restart with init */
-    if (zcs->nbThreads==1) return ZSTD_compressStream(zcs->cstream, output, input);
+    size_t const newJobThreshold = mtctx->dictSize + mtctx->targetSectionSize + mtctx->marginSize;
+    assert(output->pos <= output->size);
+    assert(input->pos  <= input->size);
+    if ((mtctx->frameEnded) && (endOp==ZSTD_e_continue)) {
+        /* current frame being ended. Only flush/end are allowed. Or start new frame with init */
+        return ERROR(stage_wrong);
+    }
+    if (mtctx->nbThreads==1) {
+        return ZSTD_compressStream_generic(mtctx->cctxPool->cctx[0], output, input, endOp);
+    }
+
+    /* single-pass shortcut (note : this is blocking-mode) */
+    if ( (mtctx->nextJobID==0)      /* just started */
+      && (mtctx->inBuff.filled==0)  /* nothing buffered */
+      && (endOp==ZSTD_e_end)        /* end order */
+      && (output->size - output->pos >= ZSTD_compressBound(input->size - input->pos)) ) { /* enough room */
+        size_t const cSize = ZSTDMT_compress_advanced(mtctx,
+                (char*)output->dst + output->pos, output->size - output->pos,
+                (const char*)input->src + input->pos, input->size - input->pos,
+                mtctx->cdict, mtctx->params, mtctx->overlapRLog);
+        if (ZSTD_isError(cSize)) return cSize;
+        input->pos = input->size;
+        output->pos += cSize;
+        ZSTDMT_releaseBuffer(mtctx->buffPool, mtctx->inBuff.buffer);  /* was allocated in initStream */
+        mtctx->allJobsCompleted = 1;
+        mtctx->frameEnded = 1;
+        return 0;
+    }
 
     /* fill input buffer */
-    {   size_t const toLoad = MIN(input->size - input->pos, zcs->inBuffSize - zcs->inBuff.filled);
-        memcpy((char*)zcs->inBuff.buffer.start + zcs->inBuff.filled, input->src, toLoad);
+    if ((input->src) && (mtctx->inBuff.buffer.start)) {   /* support NULL input */
+        size_t const toLoad = MIN(input->size - input->pos, mtctx->inBuffSize - mtctx->inBuff.filled);
+        DEBUGLOG(2, "inBuff:%08X;  inBuffSize=%u;  ToCopy=%u", (U32)(size_t)mtctx->inBuff.buffer.start, (U32)mtctx->inBuffSize, (U32)toLoad);
+        memcpy((char*)mtctx->inBuff.buffer.start + mtctx->inBuff.filled, (const char*)input->src + input->pos, toLoad);
         input->pos += toLoad;
-        zcs->inBuff.filled += toLoad;
+        mtctx->inBuff.filled += toLoad;
     }
 
-    if ( (zcs->inBuff.filled >= newJobThreshold)  /* filled enough : let's compress */
-        && (zcs->nextJobID <= zcs->doneJobID + zcs->jobIDMask) ) {   /* avoid overwriting job round buffer */
-        CHECK_F( ZSTDMT_createCompressionJob(zcs, zcs->targetSectionSize, 0) );
+    if ( (mtctx->inBuff.filled >= newJobThreshold)  /* filled enough : let's compress */
+      && (mtctx->nextJobID <= mtctx->doneJobID + mtctx->jobIDMask) ) {   /* avoid overwriting job round buffer */
+        CHECK_F( ZSTDMT_createCompressionJob(mtctx, mtctx->targetSectionSize, 0 /* endFrame */) );
     }
 
-    /* check for data to flush */
-    CHECK_F( ZSTDMT_flushNextJob(zcs, output, (zcs->inBuff.filled == zcs->inBuffSize)) ); /* block if it wasn't possible to create new job due to saturation */
+    /* check for potential compressed data ready to be flushed */
+    CHECK_F( ZSTDMT_flushNextJob(mtctx, output, (mtctx->inBuff.filled == mtctx->inBuffSize) /* blockToFlush */) ); /* block if it wasn't possible to create new job due to saturation */
+
+    if (input->pos < input->size)  /* input not consumed : do not flush yet */
+        endOp = ZSTD_e_continue;
+
+    switch(endOp)
+    {
+        case ZSTD_e_flush:
+            return ZSTDMT_flushStream(mtctx, output);
+        case ZSTD_e_end:
+            return ZSTDMT_endStream(mtctx, output);
+        case ZSTD_e_continue:
+            return 1;
+        default:
+            return ERROR(GENERIC);   /* invalid endDirective */
+    }
+}
+
+
+size_t ZSTDMT_compressStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
+{
+    CHECK_F( ZSTDMT_compressStream_generic(zcs, output, input, ZSTD_e_continue) );
 
     /* recommended next input size : fill current input buffer */
     return zcs->inBuffSize - zcs->inBuff.filled;   /* note : could be zero when input buffer is fully filled and no more availability to create new job */
@@ -726,26 +928,28 @@ static size_t ZSTDMT_flushStream_internal(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* outp
 {
     size_t const srcSize = zcs->inBuff.filled - zcs->dictSize;
 
-    if (srcSize) DEBUGLOG(4, "flushing : %u bytes left to compress", (U32)srcSize);
     if ( ((srcSize > 0) || (endFrame && !zcs->frameEnded))
        && (zcs->nextJobID <= zcs->doneJobID + zcs->jobIDMask) ) {
         CHECK_F( ZSTDMT_createCompressionJob(zcs, srcSize, endFrame) );
     }
 
     /* check if there is any data available to flush */
-    DEBUGLOG(5, "zcs->doneJobID : %u  ; zcs->nextJobID : %u ", zcs->doneJobID, zcs->nextJobID);
-    return ZSTDMT_flushNextJob(zcs, output, 1);
+    return ZSTDMT_flushNextJob(zcs, output, 1 /* blockToFlush */);
 }
 
 
 size_t ZSTDMT_flushStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output)
 {
-    if (zcs->nbThreads==1) return ZSTD_flushStream(zcs->cstream, output);
-    return ZSTDMT_flushStream_internal(zcs, output, 0);
+    DEBUGLOG(5, "ZSTDMT_flushStream");
+    if (zcs->nbThreads==1)
+        return ZSTD_flushStream(zcs->cctxPool->cctx[0], output);
+    return ZSTDMT_flushStream_internal(zcs, output, 0 /* endFrame */);
 }
 
 size_t ZSTDMT_endStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output)
 {
-    if (zcs->nbThreads==1) return ZSTD_endStream(zcs->cstream, output);
-    return ZSTDMT_flushStream_internal(zcs, output, 1);
+    DEBUGLOG(4, "ZSTDMT_endStream");
+    if (zcs->nbThreads==1)
+        return ZSTD_endStream(zcs->cctxPool->cctx[0], output);
+    return ZSTDMT_flushStream_internal(zcs, output, 1 /* endFrame */);
 }

thirdparty/zstd/compress/zstdmt_compress.h

@@ -15,25 +15,34 @@
  #endif
 
 
-/* Note : All prototypes defined in this file shall be considered experimental.
- *        There is no guarantee of API continuity (yet) on any of these prototypes */
+/* Note : All prototypes defined in this file are labelled experimental.
+ *        No guarantee of API continuity is provided on any of them.
+ *        In fact, the expectation is that these prototypes will be replaced
+ *        by ZSTD_compress_generic() API in the near future */
 
 /* ===   Dependencies   === */
-#include <stddef.h>   /* size_t */
+#include <stddef.h>                /* size_t */
 #define ZSTD_STATIC_LINKING_ONLY   /* ZSTD_parameters */
-#include "zstd.h"     /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTDLIB_API */
+#include "zstd.h"            /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTDLIB_API */
 
 
-/* ===   Simple one-pass functions   === */
-
+/* ===   Memory management   === */
 typedef struct ZSTDMT_CCtx_s ZSTDMT_CCtx;
 ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbThreads);
-ZSTDLIB_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* cctx);
+ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbThreads,
+                                                    ZSTD_customMem cMem);
+ZSTDLIB_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx);
+
+ZSTDLIB_API size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx);
+
+
+/* ===   Simple buffer-to-butter one-pass function   === */
+
+ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
+                                       void* dst, size_t dstCapacity,
+                                 const void* src, size_t srcSize,
+                                       int compressionLevel);
 
-ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* cctx,
-                           void* dst, size_t dstCapacity,
-                     const void* src, size_t srcSize,
-                           int compressionLevel);
 
 
 /* ===   Streaming functions   === */
@@ -53,8 +62,22 @@ ZSTDLIB_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);
 #  define ZSTDMT_SECTION_SIZE_MIN (1U << 20)   /* 1 MB - Minimum size of each compression job */
 #endif
 
-ZSTDLIB_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx, const void* dict, size_t dictSize,  /**< dict can be released after init, a local copy is preserved within zcs */
-                                          ZSTD_parameters params, unsigned long long pledgedSrcSize);  /**< pledgedSrcSize is optional and can be zero == unknown */
+ZSTDLIB_API size_t ZSTDMT_compress_advanced(ZSTDMT_CCtx* mtctx,
+                                           void* dst, size_t dstCapacity,
+                                     const void* src, size_t srcSize,
+                                     const ZSTD_CDict* cdict,
+                                           ZSTD_parameters const params,
+                                           unsigned overlapRLog);
+
+ZSTDLIB_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx,
+                                        const void* dict, size_t dictSize,   /* dict can be released after init, a local copy is preserved within zcs */
+                                        ZSTD_parameters params,
+                                        unsigned long long pledgedSrcSize);  /* pledgedSrcSize is optional and can be zero == unknown */
+
+ZSTDLIB_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
+                                        const ZSTD_CDict* cdict,
+                                        ZSTD_frameParameters fparams,
+                                        unsigned long long pledgedSrcSize);  /* note : zero means empty */
 
 /* ZSDTMT_parameter :
  * List of parameters that can be set using ZSTDMT_setMTCtxParameter() */
@@ -71,6 +94,19 @@ typedef enum {
 ZSTDLIB_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter, unsigned value);
 
 
+/*! ZSTDMT_compressStream_generic() :
+ *  Combines ZSTDMT_compressStream() with ZSTDMT_flushStream() or ZSTDMT_endStream()
+ *  depending on flush directive.
+ * @return : minimum amount of data still to be flushed
+ *           0 if fully flushed
+ *           or an error code */
+ZSTDLIB_API size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
+                                                ZSTD_outBuffer* output,
+                                                ZSTD_inBuffer* input,
+                                                ZSTD_EndDirective endOp);
+
+
+
 #if defined (__cplusplus)
 }
 #endif

thirdparty/zstd/decompress/huf_decompress.c

@@ -67,6 +67,12 @@
 #define HUF_STATIC_ASSERT(c) { enum { HUF_static_assert = 1/(int)(!!(c)) }; }   /* use only *after* variable declarations */
 
 
+/* **************************************************************
+*  Byte alignment for workSpace management
+****************************************************************/
+#define HUF_ALIGN(x, a) HUF_ALIGN_MASK((x), (a) - 1)
+#define HUF_ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask))
+
 /*-***************************/
 /*  generic DTableDesc       */
 /*-***************************/
@@ -87,16 +93,28 @@ static DTableDesc HUF_getDTableDesc(const HUF_DTable* table)
 
 typedef struct { BYTE byte; BYTE nbBits; } HUF_DEltX2;   /* single-symbol decoding */
 
-size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize)
+size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize)
 {
-    BYTE huffWeight[HUF_SYMBOLVALUE_MAX + 1];
-    U32 rankVal[HUF_TABLELOG_ABSOLUTEMAX + 1];   /* large enough for values from 0 to 16 */
     U32 tableLog = 0;
     U32 nbSymbols = 0;
     size_t iSize;
     void* const dtPtr = DTable + 1;
     HUF_DEltX2* const dt = (HUF_DEltX2*)dtPtr;
 
+    U32* rankVal;
+    BYTE* huffWeight;
+    size_t spaceUsed32 = 0;
+
+    rankVal = (U32 *)workSpace + spaceUsed32;
+    spaceUsed32 += HUF_TABLELOG_ABSOLUTEMAX + 1;
+    huffWeight = (BYTE *)((U32 *)workSpace + spaceUsed32);
+    spaceUsed32 += HUF_ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
+
+    if ((spaceUsed32 << 2) > wkspSize)
+        return ERROR(tableLog_tooLarge);
+    workSpace = (U32 *)workSpace + spaceUsed32;
+    wkspSize -= (spaceUsed32 << 2);
+
     HUF_STATIC_ASSERT(sizeof(DTableDesc) == sizeof(HUF_DTable));
     /* memset(huffWeight, 0, sizeof(huffWeight)); */   /* is not necessary, even though some analyzer complain ... */
 
@@ -135,6 +153,13 @@ size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize)
     return iSize;
 }
 
+size_t HUF_readDTableX2(HUF_DTable* DTable, const void* src, size_t srcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_readDTableX2_wksp(DTable, src, srcSize,
+                                 workSpace, sizeof(workSpace));
+}
+
 
 static BYTE HUF_decodeSymbolX2(BIT_DStream_t* Dstream, const HUF_DEltX2* dt, const U32 dtLog)
 {
@@ -212,11 +237,13 @@ size_t HUF_decompress1X2_usingDTable(
     return HUF_decompress1X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
 }
 
-size_t HUF_decompress1X2_DCtx (HUF_DTable* DCtx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
 {
     const BYTE* ip = (const BYTE*) cSrc;
 
-    size_t const hSize = HUF_readDTableX2 (DCtx, cSrc, cSrcSize);
+    size_t const hSize = HUF_readDTableX2_wksp(DCtx, cSrc, cSrcSize, workSpace, wkspSize);
     if (HUF_isError(hSize)) return hSize;
     if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
     ip += hSize; cSrcSize -= hSize;
@@ -224,6 +251,15 @@ size_t HUF_decompress1X2_DCtx (HUF_DTable* DCtx, void* dst, size_t dstSize, cons
     return HUF_decompress1X2_usingDTable_internal (dst, dstSize, ip, cSrcSize, DCtx);
 }
 
+
+size_t HUF_decompress1X2_DCtx(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                              const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress1X2_DCtx_wksp(DCtx, dst, dstSize, cSrc, cSrcSize,
+                                       workSpace, sizeof(workSpace));
+}
+
 size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
 {
     HUF_CREATE_STATIC_DTABLEX2(DTable, HUF_TABLELOG_MAX);
@@ -335,11 +371,14 @@ size_t HUF_decompress4X2_usingDTable(
 }
 
 
-size_t HUF_decompress4X2_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
 {
     const BYTE* ip = (const BYTE*) cSrc;
 
-    size_t const hSize = HUF_readDTableX2 (dctx, cSrc, cSrcSize);
+    size_t const hSize = HUF_readDTableX2_wksp (dctx, cSrc, cSrcSize,
+                                                workSpace, wkspSize);
     if (HUF_isError(hSize)) return hSize;
     if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
     ip += hSize; cSrcSize -= hSize;
@@ -347,6 +386,13 @@ size_t HUF_decompress4X2_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, cons
     return HUF_decompress4X2_usingDTable_internal (dst, dstSize, ip, cSrcSize, dctx);
 }
 
+
+size_t HUF_decompress4X2_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+                                       workSpace, sizeof(workSpace));
+}
 size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
 {
     HUF_CREATE_STATIC_DTABLEX2(DTable, HUF_TABLELOG_MAX);
@@ -403,7 +449,8 @@ static void HUF_fillDTableX4Level2(HUF_DEltX4* DTable, U32 sizeLog, const U32 co
     }   }
 }
 
-typedef U32 rankVal_t[HUF_TABLELOG_MAX][HUF_TABLELOG_MAX + 1];
+typedef U32 rankValCol_t[HUF_TABLELOG_MAX + 1];
+typedef rankValCol_t rankVal_t[HUF_TABLELOG_MAX];
 
 static void HUF_fillDTableX4(HUF_DEltX4* DTable, const U32 targetLog,
                            const sortedSymbol_t* sortedList, const U32 sortedListSize,
@@ -447,20 +494,43 @@ static void HUF_fillDTableX4(HUF_DEltX4* DTable, const U32 targetLog,
     }
 }
 
-size_t HUF_readDTableX4 (HUF_DTable* DTable, const void* src, size_t srcSize)
+size_t HUF_readDTableX4_wksp(HUF_DTable* DTable, const void* src,
+                             size_t srcSize, void* workSpace,
+                             size_t wkspSize)
 {
-    BYTE weightList[HUF_SYMBOLVALUE_MAX + 1];
-    sortedSymbol_t sortedSymbol[HUF_SYMBOLVALUE_MAX + 1];
-    U32 rankStats[HUF_TABLELOG_MAX + 1] = { 0 };
-    U32 rankStart0[HUF_TABLELOG_MAX + 2] = { 0 };
-    U32* const rankStart = rankStart0+1;
-    rankVal_t rankVal;
     U32 tableLog, maxW, sizeOfSort, nbSymbols;
     DTableDesc dtd = HUF_getDTableDesc(DTable);
     U32 const maxTableLog = dtd.maxTableLog;
     size_t iSize;
     void* dtPtr = DTable+1;   /* force compiler to avoid strict-aliasing */
     HUF_DEltX4* const dt = (HUF_DEltX4*)dtPtr;
+    U32 *rankStart;
+
+    rankValCol_t* rankVal;
+    U32* rankStats;
+    U32* rankStart0;
+    sortedSymbol_t* sortedSymbol;
+    BYTE* weightList;
+    size_t spaceUsed32 = 0;
+
+    rankVal = (rankValCol_t *)((U32 *)workSpace + spaceUsed32);
+    spaceUsed32 += (sizeof(rankValCol_t) * HUF_TABLELOG_MAX) >> 2;
+    rankStats = (U32 *)workSpace + spaceUsed32;
+    spaceUsed32 += HUF_TABLELOG_MAX + 1;
+    rankStart0 = (U32 *)workSpace + spaceUsed32;
+    spaceUsed32 += HUF_TABLELOG_MAX + 2;
+    sortedSymbol = (sortedSymbol_t *)workSpace + (spaceUsed32 * sizeof(U32)) / sizeof(sortedSymbol_t);
+    spaceUsed32 += HUF_ALIGN(sizeof(sortedSymbol_t) * (HUF_SYMBOLVALUE_MAX + 1), sizeof(U32)) >> 2;
+    weightList = (BYTE *)((U32 *)workSpace + spaceUsed32);
+    spaceUsed32 += HUF_ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
+
+    if ((spaceUsed32 << 2) > wkspSize)
+        return ERROR(tableLog_tooLarge);
+    workSpace = (U32 *)workSpace + spaceUsed32;
+    wkspSize -= (spaceUsed32 << 2);
+
+    rankStart = rankStart0 + 1;
+    memset(rankStats, 0, sizeof(U32) * (2 * HUF_TABLELOG_MAX + 2 + 1));
 
     HUF_STATIC_ASSERT(sizeof(HUF_DEltX4) == sizeof(HUF_DTable));   /* if compiler fails here, assertion is wrong */
     if (maxTableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge);
@@ -527,6 +597,12 @@ size_t HUF_readDTableX4 (HUF_DTable* DTable, const void* src, size_t srcSize)
     return iSize;
 }
 
+size_t HUF_readDTableX4(HUF_DTable* DTable, const void* src, size_t srcSize)
+{
+  U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+  return HUF_readDTableX4_wksp(DTable, src, srcSize,
+                               workSpace, sizeof(workSpace));
+}
 
 static U32 HUF_decodeSymbolX4(void* op, BIT_DStream_t* DStream, const HUF_DEltX4* dt, const U32 dtLog)
 {
@@ -545,7 +621,8 @@ static U32 HUF_decodeLastSymbolX4(void* op, BIT_DStream_t* DStream, const HUF_DE
         if (DStream->bitsConsumed < (sizeof(DStream->bitContainer)*8)) {
             BIT_skipBits(DStream, dt[val].nbBits);
             if (DStream->bitsConsumed > (sizeof(DStream->bitContainer)*8))
-                DStream->bitsConsumed = (sizeof(DStream->bitContainer)*8);   /* ugly hack; works only because it's the last symbol. Note : can't easily extract nbBits from just this symbol */
+                /* ugly hack; works only because it's the last symbol. Note : can't easily extract nbBits from just this symbol */
+                DStream->bitsConsumed = (sizeof(DStream->bitContainer)*8);
     }   }
     return 1;
 }
@@ -626,11 +703,14 @@ size_t HUF_decompress1X4_usingDTable(
     return HUF_decompress1X4_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
 }
 
-size_t HUF_decompress1X4_DCtx (HUF_DTable* DCtx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
 {
     const BYTE* ip = (const BYTE*) cSrc;
 
-    size_t const hSize = HUF_readDTableX4 (DCtx, cSrc, cSrcSize);
+    size_t const hSize = HUF_readDTableX4_wksp(DCtx, cSrc, cSrcSize,
+                                               workSpace, wkspSize);
     if (HUF_isError(hSize)) return hSize;
     if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
     ip += hSize; cSrcSize -= hSize;
@@ -638,6 +718,15 @@ size_t HUF_decompress1X4_DCtx (HUF_DTable* DCtx, void* dst, size_t dstSize, cons
     return HUF_decompress1X4_usingDTable_internal (dst, dstSize, ip, cSrcSize, DCtx);
 }
 
+
+size_t HUF_decompress1X4_DCtx(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                              const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress1X4_DCtx_wksp(DCtx, dst, dstSize, cSrc, cSrcSize,
+                                       workSpace, sizeof(workSpace));
+}
+
 size_t HUF_decompress1X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
 {
     HUF_CREATE_STATIC_DTABLEX4(DTable, HUF_TABLELOG_MAX);
@@ -748,11 +837,14 @@ size_t HUF_decompress4X4_usingDTable(
 }
 
 
-size_t HUF_decompress4X4_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
 {
     const BYTE* ip = (const BYTE*) cSrc;
 
-    size_t hSize = HUF_readDTableX4 (dctx, cSrc, cSrcSize);
+    size_t hSize = HUF_readDTableX4_wksp(dctx, cSrc, cSrcSize,
+                                         workSpace, wkspSize);
     if (HUF_isError(hSize)) return hSize;
     if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
     ip += hSize; cSrcSize -= hSize;
@@ -760,6 +852,15 @@ size_t HUF_decompress4X4_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, cons
     return HUF_decompress4X4_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx);
 }
 
+
+size_t HUF_decompress4X4_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize,
+                              const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+                                       workSpace, sizeof(workSpace));
+}
+
 size_t HUF_decompress4X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
 {
     HUF_CREATE_STATIC_DTABLEX4(DTable, HUF_TABLELOG_MAX);
@@ -861,19 +962,32 @@ size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const
     }
 }
 
-size_t HUF_decompress4X_hufOnly (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress4X_hufOnly_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+                                         workSpace, sizeof(workSpace));
+}
+
+
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst,
+                                     size_t dstSize, const void* cSrc,
+                                     size_t cSrcSize, void* workSpace,
+                                     size_t wkspSize)
 {
     /* validation checks */
     if (dstSize == 0) return ERROR(dstSize_tooSmall);
     if ((cSrcSize >= dstSize) || (cSrcSize <= 1)) return ERROR(corruption_detected);   /* invalid */
 
     {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
-        return algoNb ? HUF_decompress4X4_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) :
-                        HUF_decompress4X2_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) ;
+        return algoNb ? HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize):
+                        HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
     }
 }
 
-size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress1X_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                  const void* cSrc, size_t cSrcSize,
+                                  void* workSpace, size_t wkspSize)
 {
     /* validation checks */
     if (dstSize == 0) return ERROR(dstSize_tooSmall);
@@ -882,7 +996,17 @@ size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const
     if (cSrcSize == 1) { memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; }   /* RLE */
 
     {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
-        return algoNb ? HUF_decompress1X4_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) :
-                        HUF_decompress1X2_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) ;
+        return algoNb ? HUF_decompress1X4_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize):
+                        HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize);
     }
 }
+
+size_t HUF_decompress1X_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize,
+                             const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress1X_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+                                      workSpace, sizeof(workSpace));
+}

thirdparty/zstd/zstd.h

@@ -19,10 +19,12 @@ extern "C" {
 
 
 /* =====   ZSTDLIB_API : control library symbols visibility   ===== */
-#if defined(__GNUC__) && (__GNUC__ >= 4)
-#  define ZSTDLIB_VISIBILITY __attribute__ ((visibility ("default")))
-#else
-#  define ZSTDLIB_VISIBILITY
+#ifndef ZSTDLIB_VISIBILITY
+#  if defined(__GNUC__) && (__GNUC__ >= 4)
+#    define ZSTDLIB_VISIBILITY __attribute__ ((visibility ("default")))
+#  else
+#    define ZSTDLIB_VISIBILITY
+#  endif
 #endif
 #if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1)
 #  define ZSTDLIB_API __declspec(dllexport) ZSTDLIB_VISIBILITY
@@ -36,35 +38,37 @@ extern "C" {
 /*******************************************************************************************************
   Introduction
 
-  zstd, short for Zstandard, is a fast lossless compression algorithm, targeting real-time compression scenarios
-  at zlib-level and better compression ratios. The zstd compression library provides in-memory compression and
-  decompression functions. The library supports compression levels from 1 up to ZSTD_maxCLevel() which is 22.
+  zstd, short for Zstandard, is a fast lossless compression algorithm,
+  targeting real-time compression scenarios at zlib-level and better compression ratios.
+  The zstd compression library provides in-memory compression and decompression functions.
+  The library supports compression levels from 1 up to ZSTD_maxCLevel() which is currently 22.
   Levels >= 20, labeled `--ultra`, should be used with caution, as they require more memory.
   Compression can be done in:
     - a single step (described as Simple API)
     - a single step, reusing a context (described as Explicit memory management)
     - unbounded multiple steps (described as Streaming compression)
-  The compression ratio achievable on small data can be highly improved using compression with a dictionary in:
+  The compression ratio achievable on small data can be highly improved using a dictionary in:
     - a single step (described as Simple dictionary API)
     - a single step, reusing a dictionary (described as Fast dictionary API)
 
   Advanced experimental functions can be accessed using #define ZSTD_STATIC_LINKING_ONLY before including zstd.h.
-  These APIs shall never be used with a dynamic library.
+  Advanced experimental APIs shall never be used with a dynamic library.
   They are not "stable", their definition may change in the future. Only static linking is allowed.
 *********************************************************************************************************/
 
 /*------   Version   ------*/
 #define ZSTD_VERSION_MAJOR    1
-#define ZSTD_VERSION_MINOR    2
+#define ZSTD_VERSION_MINOR    3
 #define ZSTD_VERSION_RELEASE  0
 
+#define ZSTD_VERSION_NUMBER  (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE)
+ZSTDLIB_API unsigned ZSTD_versionNumber(void);   /**< useful to check dll version */
+
 #define ZSTD_LIB_VERSION ZSTD_VERSION_MAJOR.ZSTD_VERSION_MINOR.ZSTD_VERSION_RELEASE
 #define ZSTD_QUOTE(str) #str
 #define ZSTD_EXPAND_AND_QUOTE(str) ZSTD_QUOTE(str)
 #define ZSTD_VERSION_STRING ZSTD_EXPAND_AND_QUOTE(ZSTD_LIB_VERSION)
-
-#define ZSTD_VERSION_NUMBER  (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE)
-ZSTDLIB_API unsigned ZSTD_versionNumber(void);   /**< library version number; to be used when checking dll version */
+ZSTDLIB_API const char* ZSTD_versionString(void);   /* v1.3.0 */
 
 
 /***************************************
@@ -81,38 +85,48 @@ ZSTDLIB_API size_t ZSTD_compress( void* dst, size_t dstCapacity,
 
 /*! ZSTD_decompress() :
  *  `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames.
- *  `dstCapacity` is an upper bound of originalSize.
+ *  `dstCapacity` is an upper bound of originalSize to regenerate.
  *  If user cannot imply a maximum upper bound, it's better to use streaming mode to decompress data.
  *  @return : the number of bytes decompressed into `dst` (<= `dstCapacity`),
  *            or an errorCode if it fails (which can be tested using ZSTD_isError()). */
 ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity,
                               const void* src, size_t compressedSize);
 
-/*! ZSTD_getDecompressedSize() :
- *  NOTE: This function is planned to be obsolete, in favour of ZSTD_getFrameContentSize.
- *  ZSTD_getFrameContentSize functions the same way, returning the decompressed size of a single
- *  frame, but distinguishes empty frames from frames with an unknown size, or errors.
- *
- *  Additionally, ZSTD_findDecompressedSize can be used instead.  It can handle multiple
- *  concatenated frames in one buffer, and so is more general.
- *  As a result however, it requires more computation and entire frames to be passed to it,
- *  as opposed to ZSTD_getFrameContentSize which requires only a single frame's header.
- *
- *  'src' is the start of a zstd compressed frame.
- *  @return : content size to be decompressed, as a 64-bits value _if known_, 0 otherwise.
- *   note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode.
- *            When `return==0`, data to decompress could be any size.
+/*! ZSTD_getFrameContentSize() : v1.3.0
+ *  `src` should point to the start of a ZSTD encoded frame.
+ *  `srcSize` must be at least as large as the frame header.
+ *            hint : any size >= `ZSTD_frameHeaderSize_max` is large enough.
+ *  @return : - decompressed size of the frame in `src`, if known
+ *            - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined
+ *            - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small)
+ *   note 1 : a 0 return value means the frame is valid but "empty".
+ *   note 2 : decompressed size is an optional field, it may not be present, typically in streaming mode.
+ *            When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size.
  *            In which case, it's necessary to use streaming mode to decompress data.
- *            Optionally, application can still use ZSTD_decompress() while relying on implied limits.
- *            (For example, data may be necessarily cut into blocks <= 16 KB).
- *   note 2 : decompressed size is always present when compression is done with ZSTD_compress()
- *   note 3 : decompressed size can be very large (64-bits value),
+ *            Optionally, application can rely on some implicit limit,
+ *            as ZSTD_decompress() only needs an upper bound of decompressed size.
+ *            (For example, data could be necessarily cut into blocks <= 16 KB).
+ *   note 3 : decompressed size is always present when compression is done with ZSTD_compress()
+ *   note 4 : decompressed size can be very large (64-bits value),
  *            potentially larger than what local system can handle as a single memory segment.
  *            In which case, it's necessary to use streaming mode to decompress data.
- *   note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified.
- *            Always ensure result fits within application's authorized limits.
+ *   note 5 : If source is untrusted, decompressed size could be wrong or intentionally modified.
+ *            Always ensure return value fits within application's authorized limits.
  *            Each application can set its own limits.
- *   note 5 : when `return==0`, if precise failure cause is needed, use ZSTD_getFrameParams() to know more. */
+ *   note 6 : This function replaces ZSTD_getDecompressedSize() */
+#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1)
+#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
+ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize);
+
+/*! ZSTD_getDecompressedSize() :
+ *  NOTE: This function is now obsolete, in favor of ZSTD_getFrameContentSize().
+ *  Both functions work the same way,
+ *  but ZSTD_getDecompressedSize() blends
+ *  "empty", "unknown" and "error" results in the same return value (0),
+ *  while ZSTD_getFrameContentSize() distinguishes them.
+ *
+ *  'src' is the start of a zstd compressed frame.
+ *  @return : content size to be decompressed, as a 64-bits value _if known and not empty_, 0 otherwise. */
 ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize);
 
 
@@ -137,29 +151,35 @@ ZSTDLIB_API size_t     ZSTD_freeCCtx(ZSTD_CCtx* cctx);
 
 /*! ZSTD_compressCCtx() :
  *  Same as ZSTD_compress(), requires an allocated ZSTD_CCtx (see ZSTD_createCCtx()). */
-ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, int compressionLevel);
+ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* ctx,
+                                     void* dst, size_t dstCapacity,
+                               const void* src, size_t srcSize,
+                                     int compressionLevel);
 
 /*= Decompression context
  *  When decompressing many times,
- *  it is recommended to allocate a context just once, and re-use it for each successive compression operation.
+ *  it is recommended to allocate a context only once,
+ *  and re-use it for each successive compression operation.
  *  This will make workload friendlier for system's memory.
- *  Use one context per thread for parallel execution in multi-threaded environments. */
+ *  Use one context per thread for parallel execution. */
 typedef struct ZSTD_DCtx_s ZSTD_DCtx;
 ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx(void);
 ZSTDLIB_API size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);
 
 /*! ZSTD_decompressDCtx() :
- *  Same as ZSTD_decompress(), requires an allocated ZSTD_DCtx (see ZSTD_createDCtx()). */
-ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+ *  Same as ZSTD_decompress(), requires an allocated ZSTD_DCtx (see ZSTD_createDCtx()) */
+ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* ctx,
+                                       void* dst, size_t dstCapacity,
+                                 const void* src, size_t srcSize);
 
 
 /**************************
 *  Simple dictionary API
 ***************************/
 /*! ZSTD_compress_usingDict() :
-*   Compression using a predefined Dictionary (see dictBuilder/zdict.h).
-*   Note : This function loads the dictionary, resulting in significant startup delay.
-*   Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
+ *  Compression using a predefined Dictionary (see dictBuilder/zdict.h).
+ *  Note : This function loads the dictionary, resulting in significant startup delay.
+ *  Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
 ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
                                            void* dst, size_t dstCapacity,
                                      const void* src, size_t srcSize,
@@ -167,30 +187,31 @@ ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
                                            int compressionLevel);
 
 /*! ZSTD_decompress_usingDict() :
-*   Decompression using a predefined Dictionary (see dictBuilder/zdict.h).
-*   Dictionary must be identical to the one used during compression.
-*   Note : This function loads the dictionary, resulting in significant startup delay.
-*   Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
+ *  Decompression using a predefined Dictionary (see dictBuilder/zdict.h).
+ *  Dictionary must be identical to the one used during compression.
+ *  Note : This function loads the dictionary, resulting in significant startup delay.
+ *  Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
 ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
                                              void* dst, size_t dstCapacity,
                                        const void* src, size_t srcSize,
                                        const void* dict,size_t dictSize);
 
 
-/****************************
-*  Fast dictionary API
-****************************/
+/**********************************
+ *  Bulk processing dictionary API
+ *********************************/
 typedef struct ZSTD_CDict_s ZSTD_CDict;
 
 /*! ZSTD_createCDict() :
-*   When compressing multiple messages / blocks with the same dictionary, it's recommended to load it just once.
-*   ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup delay.
-*   ZSTD_CDict can be created once and used by multiple threads concurrently, as its usage is read-only.
-*   `dictBuffer` can be released after ZSTD_CDict creation, as its content is copied within CDict */
-ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, int compressionLevel);
+ *  When compressing multiple messages / blocks with the same dictionary, it's recommended to load it just once.
+ *  ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup delay.
+ *  ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only.
+ *  `dictBuffer` can be released after ZSTD_CDict creation, since its content is copied within CDict */
+ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize,
+                                         int compressionLevel);
 
 /*! ZSTD_freeCDict() :
-*   Function frees memory allocated by ZSTD_createCDict(). */
+ *  Function frees memory allocated by ZSTD_createCDict(). */
 ZSTDLIB_API size_t      ZSTD_freeCDict(ZSTD_CDict* CDict);
 
 /*! ZSTD_compress_usingCDict() :
@@ -207,17 +228,17 @@ ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
 typedef struct ZSTD_DDict_s ZSTD_DDict;
 
 /*! ZSTD_createDDict() :
-*   Create a digested dictionary, ready to start decompression operation without startup delay.
-*   dictBuffer can be released after DDict creation, as its content is copied inside DDict */
+ *  Create a digested dictionary, ready to start decompression operation without startup delay.
+ *  dictBuffer can be released after DDict creation, as its content is copied inside DDict */
 ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize);
 
 /*! ZSTD_freeDDict() :
-*   Function frees memory allocated with ZSTD_createDDict() */
+ *  Function frees memory allocated with ZSTD_createDDict() */
 ZSTDLIB_API size_t      ZSTD_freeDDict(ZSTD_DDict* ddict);
 
 /*! ZSTD_decompress_usingDDict() :
-*   Decompression using a digested Dictionary.
-*   Faster startup than ZSTD_decompress_usingDict(), recommended when same dictionary is used multiple times. */
+ *  Decompression using a digested Dictionary.
+ *  Faster startup than ZSTD_decompress_usingDict(), recommended when same dictionary is used multiple times. */
 ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
                                               void* dst, size_t dstCapacity,
                                         const void* src, size_t srcSize,
@@ -274,14 +295,17 @@ typedef struct ZSTD_outBuffer_s {
 *  ZSTD_endStream() instructs to finish a frame.
 *  It will perform a flush and write frame epilogue.
 *  The epilogue is required for decoders to consider a frame completed.
-*  Similar to ZSTD_flushStream(), it may not be able to flush the full content if `output->size` is too small.
+*  ZSTD_endStream() may not be able to flush full data if `output->size` is too small.
 *  In which case, call again ZSTD_endStream() to complete the flush.
-*  @return : nb of bytes still present within internal buffer (0 if it's empty, hence compression completed)
+*  @return : 0 if frame fully completed and fully flushed,
+             or >0 if some data is still present within internal buffer
+                  (value is minimum size estimation for remaining data to flush, but it could be more)
 *            or an error code, which can be tested using ZSTD_isError().
 *
 * *******************************************************************/
 
-typedef struct ZSTD_CStream_s ZSTD_CStream;
+typedef ZSTD_CCtx ZSTD_CStream;  /**< CCtx and CStream are now effectively same object (>= v1.3.0) */
+                                 /* Continue to distinguish them for compatibility with versions <= v1.2.0 */
 /*===== ZSTD_CStream management functions =====*/
 ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void);
 ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs);
@@ -319,7 +343,8 @@ ZSTDLIB_API size_t ZSTD_CStreamOutSize(void);   /**< recommended size for output
 *            The return value is a suggested next input size (a hint to improve latency) that will never load more than the current frame.
 * *******************************************************************************/
 
-typedef struct ZSTD_DStream_s ZSTD_DStream;
+typedef ZSTD_DCtx ZSTD_DStream;  /**< DCtx and DStream are now effectively same object (>= v1.3.0) */
+                                 /* Continue to distinguish them for compatibility with versions <= v1.2.0 */
 /*===== ZSTD_DStream management functions =====*/
 ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void);
 ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds);
@@ -334,23 +359,22 @@ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void);   /*!< recommended size for output
 #endif  /* ZSTD_H_235446 */
 
 
-#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY)
-#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY
 
 /****************************************************************************************
  * START OF ADVANCED AND EXPERIMENTAL FUNCTIONS
  * The definitions in this section are considered experimental.
- * They should never be used with a dynamic library, as they may change in the future.
- * They are provided for advanced usages.
+ * They should never be used with a dynamic library, as prototypes may change in the future.
+ * They are provided for advanced scenarios.
  * Use them only in association with static linking.
  * ***************************************************************************************/
 
+#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY)
+#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY
+
 /* --- Constants ---*/
 #define ZSTD_MAGICNUMBER            0xFD2FB528   /* >= v0.8.0 */
 #define ZSTD_MAGIC_SKIPPABLE_START  0x184D2A50U
-
-#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1)
-#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
+#define ZSTD_MAGIC_DICTIONARY       0xEC30A437   /* v0.7+ */
 
 #define ZSTD_WINDOWLOG_MAX_32  27
 #define ZSTD_WINDOWLOG_MAX_64  27
@@ -370,14 +394,15 @@ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void);   /*!< recommended size for output
 
 #define ZSTD_FRAMEHEADERSIZE_MAX 18    /* for static allocation */
 #define ZSTD_FRAMEHEADERSIZE_MIN  6
-static const size_t ZSTD_frameHeaderSize_prefix = 5;
-static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN;
+static const size_t ZSTD_frameHeaderSize_prefix = 5;  /* minimum input size to know frame header size */
 static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX;
+static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN;
 static const size_t ZSTD_skippableHeaderSize = 8;  /* magic number + skippable frame length */
 
 
 /*--- Advanced types ---*/
-typedef enum { ZSTD_fast, ZSTD_dfast, ZSTD_greedy, ZSTD_lazy, ZSTD_lazy2, ZSTD_btlazy2, ZSTD_btopt, ZSTD_btopt2 } ZSTD_strategy;   /* from faster to stronger */
+typedef enum { ZSTD_fast=1, ZSTD_dfast, ZSTD_greedy, ZSTD_lazy, ZSTD_lazy2,
+               ZSTD_btlazy2, ZSTD_btopt, ZSTD_btultra } ZSTD_strategy;   /* from faster to stronger */
 
 typedef struct {
     unsigned windowLog;      /**< largest match distance : larger == more compression, more memory needed during decompression */
@@ -400,76 +425,141 @@ typedef struct {
     ZSTD_frameParameters fParams;
 } ZSTD_parameters;
 
+typedef struct {
+    unsigned long long frameContentSize;
+    size_t windowSize;
+    unsigned dictID;
+    unsigned checksumFlag;
+} ZSTD_frameHeader;
+
 /*= Custom memory allocation functions */
 typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size);
 typedef void  (*ZSTD_freeFunction) (void* opaque, void* address);
 typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem;
+/* use this constant to defer to stdlib's functions */
+static const ZSTD_customMem ZSTD_defaultCMem = { NULL, NULL, NULL };
+
 
 /***************************************
-*  Compressed size functions
+*  Frame size functions
 ***************************************/
 
 /*! ZSTD_findFrameCompressedSize() :
  *  `src` should point to the start of a ZSTD encoded frame or skippable frame
  *  `srcSize` must be at least as large as the frame
- *  @return : the compressed size of the frame pointed to by `src`, suitable to pass to
- *      `ZSTD_decompress` or similar, or an error code if given invalid input. */
+ *  @return : the compressed size of the first frame starting at `src`,
+ *            suitable to pass to `ZSTD_decompress` or similar,
+ *            or an error code if input is invalid */
 ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize);
 
+/*! ZSTD_findDecompressedSize() :
+ *  `src` should point the start of a series of ZSTD encoded and/or skippable frames
+ *  `srcSize` must be the _exact_ size of this series
+ *       (i.e. there should be a frame boundary exactly at `srcSize` bytes after `src`)
+ *  @return : - decompressed size of all data in all successive frames
+ *            - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN
+ *            - if an error occurred: ZSTD_CONTENTSIZE_ERROR
+ *
+ *   note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode.
+ *            When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size.
+ *            In which case, it's necessary to use streaming mode to decompress data.
+ *   note 2 : decompressed size is always present when compression is done with ZSTD_compress()
+ *   note 3 : decompressed size can be very large (64-bits value),
+ *            potentially larger than what local system can handle as a single memory segment.
+ *            In which case, it's necessary to use streaming mode to decompress data.
+ *   note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified.
+ *            Always ensure result fits within application's authorized limits.
+ *            Each application can set its own limits.
+ *   note 5 : ZSTD_findDecompressedSize handles multiple frames, and so it must traverse the input to
+ *            read each contained frame header.  This is fast as most of the data is skipped,
+ *            however it does mean that all frame data must be present and valid. */
+ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize);
+
+/*! ZSTD_frameHeaderSize() :
+*   `src` should point to the start of a ZSTD frame
+*   `srcSize` must be >= ZSTD_frameHeaderSize_prefix.
+*   @return : size of the Frame Header */
+ZSTDLIB_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize);
+
+
 /***************************************
-*  Decompressed size functions
+*  Context memory usage
 ***************************************/
-/*! ZSTD_getFrameContentSize() :
-*   `src` should point to the start of a ZSTD encoded frame
-*   `srcSize` must be at least as large as the frame header.  A value greater than or equal
-*       to `ZSTD_frameHeaderSize_max` is guaranteed to be large enough in all cases.
-*   @return : decompressed size of the frame pointed to be `src` if known, otherwise
-*             - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined
-*             - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) */
-ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize);
 
-/*! ZSTD_findDecompressedSize() :
-*   `src` should point the start of a series of ZSTD encoded and/or skippable frames
-*   `srcSize` must be the _exact_ size of this series
-*       (i.e. there should be a frame boundary exactly `srcSize` bytes after `src`)
-*   @return : the decompressed size of all data in the contained frames, as a 64-bit value _if known_
-*             - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN
-*             - if an error occurred: ZSTD_CONTENTSIZE_ERROR
-*
-*    note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode.
-*             When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size.
-*             In which case, it's necessary to use streaming mode to decompress data.
-*             Optionally, application can still use ZSTD_decompress() while relying on implied limits.
-*             (For example, data may be necessarily cut into blocks <= 16 KB).
-*    note 2 : decompressed size is always present when compression is done with ZSTD_compress()
-*    note 3 : decompressed size can be very large (64-bits value),
-*             potentially larger than what local system can handle as a single memory segment.
-*             In which case, it's necessary to use streaming mode to decompress data.
-*    note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified.
-*             Always ensure result fits within application's authorized limits.
-*             Each application can set its own limits.
-*    note 5 : ZSTD_findDecompressedSize handles multiple frames, and so it must traverse the input to
-*             read each contained frame header.  This is efficient as most of the data is skipped,
-*             however it does mean that all frame data must be present and valid. */
-ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize);
+/*! ZSTD_sizeof_*() :
+ *  These functions give the current memory usage of selected object.
+ *  Object memory usage can evolve if it's re-used multiple times. */
+ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
+ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
+ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);
+ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
+ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
+ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
+
+/*! ZSTD_estimate*() :
+ *  These functions make it possible to estimate memory usage
+ *  of a future {D,C}Ctx, before its creation.
+ *  ZSTD_estimateCCtxSize() will provide a budget large enough for any compression level up to selected one.
+ *  It will also consider src size to be arbitrarily "large", which is worst case.
+ *  If srcSize is known to always be small, ZSTD_estimateCCtxSize_advanced() can provide a tighter estimation.
+ *  ZSTD_estimateCCtxSize_advanced() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel.
+ *  Note : CCtx estimation is only correct for single-threaded compression */
+ZSTDLIB_API size_t ZSTD_estimateCCtxSize(int compressionLevel);
+ZSTDLIB_API size_t ZSTD_estimateCCtxSize_advanced(ZSTD_compressionParameters cParams);
+ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void);
+
+/*! ZSTD_estimate?StreamSize() :
+ *  ZSTD_estimateCStreamSize() will provide a budget large enough for any compression level up to selected one.
+ *  It will also consider src size to be arbitrarily "large", which is worst case.
+ *  If srcSize is known to always be small, ZSTD_estimateCStreamSize_advanced() can provide a tighter estimation.
+ *  ZSTD_estimateCStreamSize_advanced() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel.
+ *  Note : CStream estimation is only correct for single-threaded compression.
+ *  ZSTD_DStream memory budget depends on window Size.
+ *  This information can be passed manually, using ZSTD_estimateDStreamSize,
+ *  or deducted from a valid frame Header, using ZSTD_estimateDStreamSize_fromFrame();
+ *  Note : if streaming is init with function ZSTD_init?Stream_usingDict(),
+ *         an internal ?Dict will be created, which additional size is not estimated here.
+ *         In this case, get total size by adding ZSTD_estimate?DictSize */
+ZSTDLIB_API size_t ZSTD_estimateCStreamSize(int compressionLevel);
+ZSTDLIB_API size_t ZSTD_estimateCStreamSize_advanced(ZSTD_compressionParameters cParams);
+ZSTDLIB_API size_t ZSTD_estimateDStreamSize(size_t windowSize);
+ZSTDLIB_API size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize);
+
+/*! ZSTD_estimate?DictSize() :
+ *  ZSTD_estimateCDictSize() will bet that src size is relatively "small", and content is copied, like ZSTD_createCDict().
+ *  ZSTD_estimateCStreamSize_advanced() makes it possible to control precisely compression parameters, like ZSTD_createCDict_advanced().
+ *  Note : dictionary created "byReference" are smaller */
+ZSTDLIB_API size_t ZSTD_estimateCDictSize(size_t dictSize, int compressionLevel);
+ZSTDLIB_API size_t ZSTD_estimateCDictSize_advanced(size_t dictSize, ZSTD_compressionParameters cParams, unsigned byReference);
+ZSTDLIB_API size_t ZSTD_estimateDDictSize(size_t dictSize, unsigned byReference);
 
 
 /***************************************
 *  Advanced compression functions
 ***************************************/
-/*! ZSTD_estimateCCtxSize() :
- *  Gives the amount of memory allocated for a ZSTD_CCtx given a set of compression parameters.
- *  `frameContentSize` is an optional parameter, provide `0` if unknown */
-ZSTDLIB_API size_t ZSTD_estimateCCtxSize(ZSTD_compressionParameters cParams);
-
 /*! ZSTD_createCCtx_advanced() :
  *  Create a ZSTD compression context using external alloc and free functions */
 ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem);
 
-/*! ZSTD_sizeofCCtx() :
- *  Gives the amount of memory used by a given ZSTD_CCtx */
-ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
+/*! ZSTD_initStaticCCtx() : initialize a fixed-size zstd compression context
+ *  workspace: The memory area to emplace the context into.
+ *             Provided pointer must 8-bytes aligned.
+ *             It must outlive context usage.
+ *  workspaceSize: Use ZSTD_estimateCCtxSize() or ZSTD_estimateCStreamSize()
+ *                 to determine how large workspace must be to support scenario.
+ * @return : pointer to ZSTD_CCtx*, or NULL if error (size too small)
+ *  Note : zstd will never resize nor malloc() when using a static cctx.
+ *         If it needs more memory than available, it will simply error out.
+ *  Note 2 : there is no corresponding "free" function.
+ *           Since workspace was allocated externally, it must be freed externally too.
+ *  Limitation 1 : currently not compatible with internal CDict creation, such as
+ *                 ZSTD_CCtx_loadDictionary() or ZSTD_initCStream_usingDict().
+ *  Limitation 2 : currently not compatible with multi-threading
+ */
+ZSTDLIB_API ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize);
+
 
+/* !!! To be deprecated !!! */
 typedef enum {
     ZSTD_p_forceWindow,   /* Force back-references to remain < windowSize, even when referencing Dictionary content (default:0) */
     ZSTD_p_forceRawDict   /* Force loading dictionary in "content-only" mode (no header analysis) */
@@ -479,20 +569,43 @@ typedef enum {
  *  @result : 0, or an error code (which can be tested with ZSTD_isError()) */
 ZSTDLIB_API size_t ZSTD_setCCtxParameter(ZSTD_CCtx* cctx, ZSTD_CCtxParameter param, unsigned value);
 
+
 /*! ZSTD_createCDict_byReference() :
  *  Create a digested dictionary for compression
  *  Dictionary content is simply referenced, and therefore stays in dictBuffer.
  *  It is important that dictBuffer outlives CDict, it must remain read accessible throughout the lifetime of CDict */
 ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel);
 
+
+typedef enum { ZSTD_dm_auto=0,        /* dictionary is "full" if it starts with ZSTD_MAGIC_DICTIONARY, otherwise it is "rawContent" */
+               ZSTD_dm_rawContent,    /* ensures dictionary is always loaded as rawContent, even if it starts with ZSTD_MAGIC_DICTIONARY */
+               ZSTD_dm_fullDict       /* refuses to load a dictionary if it does not respect Zstandard's specification */
+} ZSTD_dictMode_e;
 /*! ZSTD_createCDict_advanced() :
  *  Create a ZSTD_CDict using external alloc and free, and customized compression parameters */
-ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, unsigned byReference,
-                                                  ZSTD_compressionParameters cParams, ZSTD_customMem customMem);
-
-/*! ZSTD_sizeof_CDict() :
- *  Gives the amount of memory used by a given ZSTD_sizeof_CDict */
-ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
+ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize,
+                                                  unsigned byReference, ZSTD_dictMode_e dictMode,
+                                                  ZSTD_compressionParameters cParams,
+                                                  ZSTD_customMem customMem);
+
+/*! ZSTD_initStaticCDict_advanced() :
+ *  Generate a digested dictionary in provided memory area.
+ *  workspace: The memory area to emplace the dictionary into.
+ *             Provided pointer must 8-bytes aligned.
+ *             It must outlive dictionary usage.
+ *  workspaceSize: Use ZSTD_estimateCDictSize()
+ *                 to determine how large workspace must be.
+ *  cParams : use ZSTD_getCParams() to transform a compression level
+ *            into its relevants cParams.
+ * @return : pointer to ZSTD_CDict*, or NULL if error (size too small)
+ *  Note : there is no corresponding "free" function.
+ *         Since workspace was allocated externally, it must be freed externally.
+ */
+ZSTDLIB_API ZSTD_CDict* ZSTD_initStaticCDict(
+                            void* workspace, size_t workspaceSize,
+                      const void* dict, size_t dictSize,
+                            unsigned byReference, ZSTD_dictMode_e dictMode,
+                            ZSTD_compressionParameters cParams);
 
 /*! ZSTD_getCParams() :
 *   @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize.
@@ -509,8 +622,8 @@ ZSTDLIB_API ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long l
 ZSTDLIB_API size_t ZSTD_checkCParams(ZSTD_compressionParameters params);
 
 /*! ZSTD_adjustCParams() :
-*   optimize params for a given `srcSize` and `dictSize`.
-*   both values are optional, select `0` if unknown. */
+ *  optimize params for a given `srcSize` and `dictSize`.
+ *  both values are optional, select `0` if unknown. */
 ZSTDLIB_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize);
 
 /*! ZSTD_compress_advanced() :
@@ -538,22 +651,32 @@ ZSTDLIB_API size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx,
  *  Note 3 : Skippable Frame Identifiers are considered valid. */
 ZSTDLIB_API unsigned ZSTD_isFrame(const void* buffer, size_t size);
 
-/*! ZSTD_estimateDCtxSize() :
- *  Gives the potential amount of memory allocated to create a ZSTD_DCtx */
-ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void);
-
 /*! ZSTD_createDCtx_advanced() :
  *  Create a ZSTD decompression context using external alloc and free functions */
 ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem);
 
-/*! ZSTD_sizeof_DCtx() :
- *  Gives the amount of memory used by a given ZSTD_DCtx */
-ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
+/*! ZSTD_initStaticDCtx() : initialize a fixed-size zstd decompression context
+ *  workspace: The memory area to emplace the context into.
+ *             Provided pointer must 8-bytes aligned.
+ *             It must outlive context usage.
+ *  workspaceSize: Use ZSTD_estimateDCtxSize() or ZSTD_estimateDStreamSize()
+ *                 to determine how large workspace must be to support scenario.
+ * @return : pointer to ZSTD_DCtx*, or NULL if error (size too small)
+ *  Note : zstd will never resize nor malloc() when using a static dctx.
+ *         If it needs more memory than available, it will simply error out.
+ *  Note 2 : static dctx is incompatible with legacy support
+ *  Note 3 : there is no corresponding "free" function.
+ *           Since workspace was allocated externally, it must be freed externally.
+ *  Limitation : currently not compatible with internal DDict creation,
+ *               such as ZSTD_initDStream_usingDict().
+ */
+ZSTDLIB_API ZSTD_DCtx* ZSTD_initStaticDCtx(void* workspace, size_t workspaceSize);
 
 /*! ZSTD_createDDict_byReference() :
  *  Create a digested dictionary, ready to start decompression operation without startup delay.
- *  Dictionary content is simply referenced, and therefore stays in dictBuffer.
- *  It is important that dictBuffer outlives DDict, it must remain read accessible throughout the lifetime of DDict */
+ *  Dictionary content is referenced, and therefore stays in dictBuffer.
+ *  It is important that dictBuffer outlives DDict,
+ *  it must remain read accessible throughout the lifetime of DDict */
 ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize);
 
 /*! ZSTD_createDDict_advanced() :
@@ -561,9 +684,20 @@ ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, siz
 ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize,
                                                   unsigned byReference, ZSTD_customMem customMem);
 
-/*! ZSTD_sizeof_DDict() :
- *  Gives the amount of memory used by a given ZSTD_DDict */
-ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
+/*! ZSTD_initStaticDDict() :
+ *  Generate a digested dictionary in provided memory area.
+ *  workspace: The memory area to emplace the dictionary into.
+ *             Provided pointer must 8-bytes aligned.
+ *             It must outlive dictionary usage.
+ *  workspaceSize: Use ZSTD_estimateDDictSize()
+ *                 to determine how large workspace must be.
+ * @return : pointer to ZSTD_DDict*, or NULL if error (size too small)
+ *  Note : there is no corresponding "free" function.
+ *         Since workspace was allocated externally, it must be freed externally.
+ */
+ZSTDLIB_API ZSTD_DDict* ZSTD_initStaticDDict(void* workspace, size_t workspaceSize,
+                                             const void* dict, size_t dictSize,
+                                             unsigned byReference);
 
 /*! ZSTD_getDictID_fromDict() :
  *  Provides the dictID stored within dictionary.
@@ -586,7 +720,7 @@ ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
  *    Note : this use case also happens when using a non-conformant dictionary.
  *  - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
  *  - This is not a Zstandard frame.
- *  When identifying the exact failure cause, it's possible to use ZSTD_getFrameParams(), which will provide a more precise error code. */
+ *  When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. */
 ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
 
 
@@ -596,13 +730,13 @@ ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
 
 /*=====   Advanced Streaming compression functions  =====*/
 ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem);
-ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);   /**< size of CStream is variable, depending primarily on compression level */
+ZSTDLIB_API ZSTD_CStream* ZSTD_initStaticCStream(void* workspace, size_t workspaceSize);    /**< same as ZSTD_initStaticCCtx() */
 ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);   /**< pledgedSrcSize must be correct, a size of 0 means unknown.  for a frame size of 0 use initCStream_advanced */
-ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< note: a dict will not be used if dict == NULL or dictSize < 8 */
+ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< creates of an internal CDict (incompatible with static CCtx), except if dict == NULL or dictSize < 8, in which case no dict is used. */
 ZSTDLIB_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize,
                                              ZSTD_parameters params, unsigned long long pledgedSrcSize);  /**< pledgedSrcSize is optional and can be 0 (meaning unknown). note: if the contentSizeFlag is set, pledgedSrcSize == 0 means the source size is actually 0 */
 ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict);  /**< note : cdict will just be referenced, and must outlive compression session */
-ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, unsigned long long pledgedSrcSize, ZSTD_frameParameters fParams);  /**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters */
+ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize);  /**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters */
 
 /*! ZSTD_resetCStream() :
  *  start a new compression job, using same parameters from previous job.
@@ -617,11 +751,11 @@ ZSTDLIB_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledg
 /*=====   Advanced Streaming decompression functions  =====*/
 typedef enum { DStream_p_maxWindowSize } ZSTD_DStreamParameter_e;
 ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem);
-ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); /**< note: a dict will not be used if dict == NULL or dictSize < 8 */
+ZSTDLIB_API ZSTD_DStream* ZSTD_initStaticDStream(void* workspace, size_t workspaceSize);    /**< same as ZSTD_initStaticDCtx() */
 ZSTDLIB_API size_t ZSTD_setDStreamParameter(ZSTD_DStream* zds, ZSTD_DStreamParameter_e paramType, unsigned paramValue);
+ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); /**< note: a dict will not be used if dict == NULL or dictSize < 8 */
 ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict);  /**< note : ddict will just be referenced, and must outlive decompression session */
 ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds);  /**< re-use decompression parameters from previous init; saves dictionary loading */
-ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
 
 
 /*********************************************************************
@@ -683,21 +817,24 @@ ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapaci
   Use ZSTD_createDCtx() / ZSTD_freeDCtx() to manage it.
   A ZSTD_DCtx object can be re-used multiple times.
 
-  First typical operation is to retrieve frame parameters, using ZSTD_getFrameParams().
-  It fills a ZSTD_frameParams structure which provide important information to correctly decode the frame,
-  such as the minimum rolling buffer size to allocate to decompress data (`windowSize`),
-  and the dictionary ID used.
+  First typical operation is to retrieve frame parameters, using ZSTD_getFrameHeader().
+  It fills a ZSTD_frameHeader structure with important information to correctly decode the frame,
+  such as minimum rolling buffer size to allocate to decompress data (`windowSize`),
+  and the dictionary ID in use.
   (Note : content size is optional, it may not be present. 0 means : content size unknown).
   Note that these values could be wrong, either because of data malformation, or because an attacker is spoofing deliberate false information.
   As a consequence, check that values remain within valid application range, especially `windowSize`, before allocation.
-  Each application can set its own limit, depending on local restrictions. For extended interoperability, it is recommended to support at least 8 MB.
-  Frame parameters are extracted from the beginning of the compressed frame.
-  Data fragment must be large enough to ensure successful decoding, typically `ZSTD_frameHeaderSize_max` bytes.
-  @result : 0 : successful decoding, the `ZSTD_frameParams` structure is correctly filled.
+  Each application can set its own limit, depending on local restrictions.
+  For extended interoperability, it is recommended to support windowSize of at least 8 MB.
+  Frame header is extracted from the beginning of compressed frame, so providing only the frame's beginning is enough.
+  Data fragment must be large enough to ensure successful decoding.
+  `ZSTD_frameHeaderSize_max` bytes is guaranteed to always be large enough.
+  @result : 0 : successful decoding, the `ZSTD_frameHeader` structure is correctly filled.
            >0 : `srcSize` is too small, please provide at least @result bytes on next attempt.
            errorCode, which can be tested using ZSTD_isError().
 
-  Start decompression, with ZSTD_decompressBegin() or ZSTD_decompressBegin_usingDict().
+  Start decompression, with ZSTD_decompressBegin().
+  If decompression requires a dictionary, use ZSTD_decompressBegin_usingDict() or ZSTD_decompressBegin_usingDDict().
   Alternatively, you can copy a prepared context, using ZSTD_copyDCtx().
 
   Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() alternatively.
@@ -729,30 +866,233 @@ ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapaci
   b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits
   c) Frame Content - any content (User Data) of length equal to Frame Size
   For skippable frames ZSTD_decompressContinue() always returns 0.
-  For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 what means that a frame is skippable.
+  For skippable frames ZSTD_getFrameHeader() returns fparamsPtr->windowLog==0 what means that a frame is skippable.
     Note : If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might actually be a Zstd encoded frame with no content.
            For purposes of decompression, it is valid in both cases to skip the frame using
            ZSTD_findFrameCompressedSize to find its size in bytes.
   It also returns Frame Size as fparamsPtr->frameContentSize.
 */
 
-typedef struct {
-    unsigned long long frameContentSize;
-    unsigned windowSize;
-    unsigned dictID;
-    unsigned checksumFlag;
-} ZSTD_frameParams;
-
 /*=====   Buffer-less streaming decompression functions  =====*/
-ZSTDLIB_API size_t ZSTD_getFrameParams(ZSTD_frameParams* fparamsPtr, const void* src, size_t srcSize);   /**< doesn't consume input, see details below */
+ZSTDLIB_API size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize);   /**< doesn't consume input */
 ZSTDLIB_API size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx);
 ZSTDLIB_API size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize);
+ZSTDLIB_API size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict);
 ZSTDLIB_API void   ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx);
+
 ZSTDLIB_API size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx);
 ZSTDLIB_API size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
 typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e;
 ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
 
+
+
+/*===   New advanced API (experimental, and compression only)  ===*/
+
+/* notes on API design :
+ *   In this proposal, parameters are pushed one by one into an existing CCtx,
+ *   and then applied on all subsequent compression jobs.
+ *   When no parameter is ever provided, CCtx is created with compression level ZSTD_CLEVEL_DEFAULT.
+ *
+ *   This API is intended to replace all others experimental API.
+ *   It can basically do all other use cases, and even new ones.
+ *   It stands a good chance to become "stable",
+ *   after a reasonable testing period.
+ */
+
+/* note on naming convention :
+ *   Initially, the API favored names like ZSTD_setCCtxParameter() .
+ *   In this proposal, convention is changed towards ZSTD_CCtx_setParameter() .
+ *   The main driver is that it identifies more clearly the target object type.
+ *   It feels clearer in light of potential variants :
+ *   ZSTD_CDict_setParameter() (rather than ZSTD_setCDictParameter())
+ *   ZSTD_DCtx_setParameter()  (rather than ZSTD_setDCtxParameter() )
+ *   Left variant feels easier to distinguish.
+ */
+
+/* note on enum design :
+ * All enum will be manually set to explicit values before reaching "stable API" status */
+
+typedef enum {
+    /* compression parameters */
+    ZSTD_p_compressionLevel=100, /* Update all compression parameters according to pre-defined cLevel table
+                              * Default level is ZSTD_CLEVEL_DEFAULT==3.
+                              * Special: value 0 means "do not change cLevel". */
+    ZSTD_p_windowLog,        /* Maximum allowed back-reference distance, expressed as power of 2.
+                              * Must be clamped between ZSTD_WINDOWLOG_MIN and ZSTD_WINDOWLOG_MAX.
+                              * Special: value 0 means "do not change windowLog". */
+    ZSTD_p_hashLog,          /* Size of the probe table, as a power of 2.
+                              * Resulting table size is (1 << (hashLog+2)).
+                              * Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX.
+                              * Larger tables improve compression ratio of strategies <= dFast,
+                              * and improve speed of strategies > dFast.
+                              * Special: value 0 means "do not change hashLog". */
+    ZSTD_p_chainLog,         /* Size of the full-search table, as a power of 2.
+                              * Resulting table size is (1 << (chainLog+2)).
+                              * Larger tables result in better and slower compression.
+                              * This parameter is useless when using "fast" strategy.
+                              * Special: value 0 means "do not change chainLog". */
+    ZSTD_p_searchLog,        /* Number of search attempts, as a power of 2.
+                              * More attempts result in better and slower compression.
+                              * This parameter is useless when using "fast" and "dFast" strategies.
+                              * Special: value 0 means "do not change searchLog". */
+    ZSTD_p_minMatch,         /* Minimum size of searched matches (note : repCode matches can be smaller).
+                              * Larger values make faster compression and decompression, but decrease ratio.
+                              * Must be clamped between ZSTD_SEARCHLENGTH_MIN and ZSTD_SEARCHLENGTH_MAX.
+                              * Note that currently, for all strategies < btopt, effective minimum is 4.
+                              * Note that currently, for all strategies > fast, effective maximum is 6.
+                              * Special: value 0 means "do not change minMatchLength". */
+    ZSTD_p_targetLength,     /* Only useful for strategies >= btopt.
+                              * Length of Match considered "good enough" to stop search.
+                              * Larger values make compression stronger and slower.
+                              * Special: value 0 means "do not change targetLength". */
+    ZSTD_p_compressionStrategy, /* See ZSTD_strategy enum definition.
+                              * Cast selected strategy as unsigned for ZSTD_CCtx_setParameter() compatibility.
+                              * The higher the value of selected strategy, the more complex it is,
+                              * resulting in stronger and slower compression.
+                              * Special: value 0 means "do not change strategy". */
+
+    /* frame parameters */
+    ZSTD_p_contentSizeFlag=200, /* Content size is written into frame header _whenever known_ (default:1) */
+    ZSTD_p_checksumFlag,     /* A 32-bits checksum of content is written at end of frame (default:0) */
+    ZSTD_p_dictIDFlag,       /* When applicable, dictID of dictionary is provided in frame header (default:1) */
+
+    /* dictionary parameters (must be set before ZSTD_CCtx_loadDictionary) */
+    ZSTD_p_dictMode=300,     /* Select how dictionary content must be interpreted. Value must be from type ZSTD_dictMode_e.
+                              * default : 0==auto : dictionary will be "full" if it respects specification, otherwise it will be "rawContent" */
+    ZSTD_p_refDictContent,   /* Dictionary content will be referenced, instead of copied (default:0==byCopy).
+                              * It requires that dictionary buffer outlives its users */
+
+    /* multi-threading parameters */
+    ZSTD_p_nbThreads=400,    /* Select how many threads a compression job can spawn (default:1)
+                              * More threads improve speed, but also increase memory usage.
+                              * Can only receive a value > 1 if ZSTD_MULTITHREAD is enabled.
+                              * Special: value 0 means "do not change nbThreads" */
+    ZSTD_p_jobSize,          /* Size of a compression job. Each compression job is completed in parallel.
+                              * 0 means default, which is dynamically determined based on compression parameters.
+                              * Job size must be a minimum of overlapSize, or 1 KB, whichever is largest
+                              * The minimum size is automatically and transparently enforced */
+    ZSTD_p_overlapSizeLog,   /* Size of previous input reloaded at the beginning of each job.
+                              * 0 => no overlap, 6(default) => use 1/8th of windowSize, >=9 => use full windowSize */
+
+    /* advanced parameters - may not remain available after API update */
+    ZSTD_p_forceMaxWindow=1100, /* Force back-reference distances to remain < windowSize,
+                              * even when referencing into Dictionary content (default:0) */
+
+} ZSTD_cParameter;
+
+
+/*! ZSTD_CCtx_setParameter() :
+ *  Set one compression parameter, selected by enum ZSTD_cParameter.
+ *  Note : when `value` is an enum, cast it to unsigned for proper type checking.
+ *  @result : 0, or an error code (which can be tested with ZSTD_isError()). */
+ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, unsigned value);
+
+/*! ZSTD_CCtx_setPledgedSrcSize() :
+ *  Total input data size to be compressed as a single frame.
+ *  This value will be controlled at the end, and result in error if not respected.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Note 1 : 0 means zero, empty.
+ *           In order to mean "unknown content size", pass constant ZSTD_CONTENTSIZE_UNKNOWN.
+ *           Note that ZSTD_CONTENTSIZE_UNKNOWN is default value for new compression jobs.
+ *  Note 2 : If all data is provided and consumed in a single round,
+ *           this value is overriden by srcSize instead. */
+ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize);
+
+/*! ZSTD_CCtx_loadDictionary() :
+ *  Create an internal CDict from dict buffer.
+ *  Decompression will have to use same buffer.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Special : Adding a NULL (or 0-size) dictionary invalidates any previous dictionary,
+ *            meaning "return to no-dictionary mode".
+ *  Note 1 : `dict` content will be copied internally,
+ *           except if ZSTD_p_refDictContent is set before loading.
+ *  Note 2 : Loading a dictionary involves building tables, which are dependent on compression parameters.
+ *           For this reason, compression parameters cannot be changed anymore after loading a dictionary.
+ *           It's also a CPU-heavy operation, with non-negligible impact on latency.
+ *  Note 3 : Dictionary will be used for all future compression jobs.
+ *           To return to "no-dictionary" situation, load a NULL dictionary */
+ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize);
+
+/*! ZSTD_CCtx_refCDict() :
+ *  Reference a prepared dictionary, to be used for all next compression jobs.
+ *  Note that compression parameters are enforced from within CDict,
+ *  and supercede any compression parameter previously set within CCtx.
+ *  The dictionary will remain valid for future compression jobs using same CCtx.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Special : adding a NULL CDict means "return to no-dictionary mode".
+ *  Note 1 : Currently, only one dictionary can be managed.
+ *           Adding a new dictionary effectively "discards" any previous one.
+ *  Note 2 : CDict is just referenced, its lifetime must outlive CCtx.
+ */
+ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict);
+
+/*! ZSTD_CCtx_refPrefix() :
+ *  Reference a prefix (single-usage dictionary) for next compression job.
+ *  Decompression need same prefix to properly regenerate data.
+ *  Prefix is **only used once**. Tables are discarded at end of compression job.
+ *  Subsequent compression jobs will be done without prefix (if none is explicitly referenced).
+ *  If there is a need to use same prefix multiple times, consider embedding it into a ZSTD_CDict instead.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Special : Adding any prefix (including NULL) invalidates any previous prefix or dictionary
+ *  Note 1 : Prefix buffer is referenced. It must outlive compression job.
+ *  Note 2 : Referencing a prefix involves building tables, which are dependent on compression parameters.
+ *           It's a CPU-heavy operation, with non-negligible impact on latency.
+ *  Note 3 : it's possible to alter ZSTD_p_dictMode using ZSTD_CCtx_setParameter() */
+ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize);
+
+
+
+typedef enum {
+    ZSTD_e_continue=0, /* collect more data, encoder transparently decides when to output result, for optimal conditions */
+    ZSTD_e_flush,      /* flush any data provided so far - frame will continue, future data can still reference previous data for better compression */
+    ZSTD_e_end         /* flush any remaining data and ends current frame. Any future compression starts a new frame. */
+} ZSTD_EndDirective;
+
+/*! ZSTD_compress_generic() :
+ *  Behave about the same as ZSTD_compressStream. To note :
+ *  - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_setParameter()
+ *  - Compression parameters cannot be changed once compression is started.
+ *  - *dstPos must be <= dstCapacity, *srcPos must be <= srcSize
+ *  - *dspPos and *srcPos will be updated. They are guaranteed to remain below their respective limit.
+ *  - @return provides the minimum amount of data still to flush from internal buffers
+ *            or an error code, which can be tested using ZSTD_isError().
+ *            if @return != 0, flush is not fully completed, there is some data left within internal buffers.
+ *  - after a ZSTD_e_end directive, if internal buffer is not fully flushed,
+ *            only ZSTD_e_end or ZSTD_e_flush operations are allowed.
+ *            It is necessary to fully flush internal buffers
+ *            before starting a new compression job, or changing compression parameters.
+ */
+ZSTDLIB_API size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
+                                          ZSTD_outBuffer* output,
+                                          ZSTD_inBuffer* input,
+                                          ZSTD_EndDirective endOp);
+
+/*! ZSTD_CCtx_reset() :
+ *  Return a CCtx to clean state.
+ *  Useful after an error, or to interrupt an ongoing compression job and start a new one.
+ *  Any internal data not yet flushed is cancelled.
+ *  Dictionary (if any) is dropped.
+ *  It's possible to modify compression parameters after a reset.
+ */
+ZSTDLIB_API void ZSTD_CCtx_reset(ZSTD_CCtx* cctx);   /* Not ready yet ! */
+
+
+/*! ZSTD_compress_generic_simpleArgs() :
+ *  Same as ZSTD_compress_generic(),
+ *  but using only integral types as arguments.
+ *  Argument list is larger and less expressive than ZSTD_{in,out}Buffer,
+ *  but can be helpful for binders from dynamic languages
+ *  which have troubles handling structures containing memory pointers.
+ */
+size_t ZSTD_compress_generic_simpleArgs (
+                            ZSTD_CCtx* cctx,
+                            void* dst, size_t dstCapacity, size_t* dstPos,
+                      const void* src, size_t srcSize, size_t* srcPos,
+                            ZSTD_EndDirective endOp);
+
+
+
 /**
     Block functions
 
@@ -767,7 +1107,7 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
       + compression : any ZSTD_compressBegin*() variant, including with dictionary
       + decompression : any ZSTD_decompressBegin*() variant, including with dictionary
       + copyCCtx() and copyDCtx() can be used too
-    - Block size is limited, it must be <= ZSTD_getBlockSizeMax() <= ZSTD_BLOCKSIZE_ABSOLUTEMAX
+    - Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX
       + If input is larger than a block size, it's necessary to split input data into multiple blocks
       + For inputs larger than a single block size, consider using the regular ZSTD_compress() instead.
         Frame metadata is not that costly, and quickly becomes negligible as source size grows larger.
@@ -780,9 +1120,10 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
         Use ZSTD_insertBlock() for such a case.
 */
 
-#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024)   /* define, for static allocation */
+#define ZSTD_BLOCKSIZELOG_MAX 17
+#define ZSTD_BLOCKSIZE_MAX   (1<<ZSTD_BLOCKSIZELOG_MAX)   /* define, for static allocation */
 /*=====   Raw zstd block functions  =====*/
-ZSTDLIB_API size_t ZSTD_getBlockSizeMax(ZSTD_CCtx* cctx);
+ZSTDLIB_API size_t ZSTD_getBlockSize   (const ZSTD_CCtx* cctx);
 ZSTDLIB_API size_t ZSTD_compressBlock  (ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
 ZSTDLIB_API size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
 ZSTDLIB_API size_t ZSTD_insertBlock(ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize);  /**< insert block into `dctx` history. Useful for uncompressed blocks */