zstd-ruby 0.1.2 → 1.1.3.0

data/ext/zstdruby/libzstd/dictBuilder/zdict.c

@@ -36,12 +36,11 @@
 #include <time.h>          /* clock */
 
 #include "mem.h"           /* read */
-#include "error_private.h"
 #include "fse.h"           /* FSE_normalizeCount, FSE_writeNCount */
 #define HUF_STATIC_LINKING_ONLY
-#include "huf.h"
+#include "huf.h"           /* HUF_buildCTable, HUF_writeCTable */
 #include "zstd_internal.h" /* includes zstd.h */
-#include "xxhash.h"
+#include "xxhash.h"        /* XXH64 */
 #include "divsufsort.h"
 #ifndef ZDICT_STATIC_LINKING_ONLY
 #  define ZDICT_STATIC_LINKING_ONLY
@@ -61,7 +60,7 @@
 #define NOISELENGTH 32
 
 #define MINRATIO 4
-static const int g_compressionLevel_default = 5;
+static const int g_compressionLevel_default = 6;
 static const U32 g_selectivity_default = 9;
 static const size_t g_provision_entropySize = 200;
 static const size_t g_min_fast_dictContent = 192;
@@ -307,13 +306,13 @@ static dictItem ZDICT_analyzePos(
         } while (length >=MINMATCHLENGTH);
 
         /* look backward */
-		length = MINMATCHLENGTH;
-		while ((length >= MINMATCHLENGTH) & (start > 0)) {
-			length = ZDICT_count(b + pos, b + suffix[start - 1]);
-			if (length >= LLIMIT) length = LLIMIT - 1;
-			lengthList[length]++;
-			if (length >= MINMATCHLENGTH) start--;
-		}
+        length = MINMATCHLENGTH;
+        while ((length >= MINMATCHLENGTH) & (start > 0)) {
+        	length = ZDICT_count(b + pos, b + suffix[start - 1]);
+        	if (length >= LLIMIT) length = LLIMIT - 1;
+        	lengthList[length]++;
+        	if (length >= MINMATCHLENGTH) start--;
+        }
 
         /* largest useful length */
         memset(cumulLength, 0, sizeof(cumulLength));
@@ -570,7 +569,7 @@ static void ZDICT_countEStats(EStats_ress_t esr, ZSTD_parameters params,
             if (ZSTD_isError(errorCode)) { DISPLAYLEVEL(1, "warning : ZSTD_copyCCtx failed \n"); return; }
     }
     cSize = ZSTD_compressBlock(esr.zc, esr.workPlace, ZSTD_BLOCKSIZE_ABSOLUTEMAX, src, srcSize);
-    if (ZSTD_isError(cSize)) { DISPLAYLEVEL(1, "warning : could not compress sample size %u \n", (U32)srcSize); return; }
+    if (ZSTD_isError(cSize)) { DISPLAYLEVEL(3, "warning : could not compress sample size %u \n", (U32)srcSize); return; }
 
     if (cSize) {  /* if == 0; block is not compressible */
         const seqStore_t* seqStorePtr = ZSTD_getSeqStore(esr.zc);
@@ -825,6 +824,55 @@ _cleanup:
 }
 
 
+
+size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity,
+                          const void* customDictContent, size_t dictContentSize,
+                          const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
+                          ZDICT_params_t params)
+{
+    size_t hSize;
+#define HBUFFSIZE 256
+    BYTE header[HBUFFSIZE];
+    int const compressionLevel = (params.compressionLevel <= 0) ? g_compressionLevel_default : params.compressionLevel;
+    U32 const notificationLevel = params.notificationLevel;
+
+    /* check conditions */
+    if (dictBufferCapacity < dictContentSize) return ERROR(dstSize_tooSmall);
+    if (dictContentSize < ZDICT_CONTENTSIZE_MIN) return ERROR(srcSize_wrong);
+    if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) return ERROR(dstSize_tooSmall);
+
+    /* dictionary header */
+    MEM_writeLE32(header, ZSTD_DICT_MAGIC);
+    {   U64 const randomID = XXH64(customDictContent, dictContentSize, 0);
+        U32 const compliantID = (randomID % ((1U<<31)-32768)) + 32768;
+        U32 const dictID = params.dictID ? params.dictID : compliantID;
+        MEM_writeLE32(header+4, dictID);
+    }
+    hSize = 8;
+
+    /* entropy tables */
+    DISPLAYLEVEL(2, "\r%70s\r", "");   /* clean display line */
+    DISPLAYLEVEL(2, "statistics ... \n");
+    {   size_t const eSize = ZDICT_analyzeEntropy(header+hSize, HBUFFSIZE-hSize,
+                                  compressionLevel,
+                                  samplesBuffer, samplesSizes, nbSamples,
+                                  customDictContent, dictContentSize,
+                                  notificationLevel);
+        if (ZDICT_isError(eSize)) return eSize;
+        hSize += eSize;
+    }
+
+    /* copy elements in final buffer ; note : src and dst buffer can overlap */
+    if (hSize + dictContentSize > dictBufferCapacity) dictContentSize = dictBufferCapacity - hSize;
+    {   size_t const dictSize = hSize + dictContentSize;
+        char* dictEnd = (char*)dictBuffer + dictSize;
+        memmove(dictEnd - dictContentSize, customDictContent, dictContentSize);
+        memcpy(dictBuffer, header, hSize);
+        return dictSize;
+    }
+}
+
+
 size_t ZDICT_addEntropyTablesFromBuffer_advanced(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity,
                                                  const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
                                                  ZDICT_params_t params)

data/ext/zstdruby/libzstd/dictBuilder/zdict.h

@@ -19,15 +19,18 @@ extern "C" {
 #include <stddef.h>  /* size_t */
 
 
-/*======  Export for Windows  ======*/
-/*!
-*  ZSTD_DLL_EXPORT :
-*  Enable exporting of functions when building a Windows DLL
-*/
-#if defined(_WIN32) && defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1)
-#  define ZDICTLIB_API __declspec(dllexport)
+/* =====   ZDICTLIB_API : control library symbols visibility   ===== */
+#if defined(__GNUC__) && (__GNUC__ >= 4)
+#  define ZDICTLIB_VISIBILITY __attribute__ ((visibility ("default")))
+#else
+#  define ZDICTLIB_VISIBILITY
+#endif
+#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1)
+#  define ZDICTLIB_API __declspec(dllexport) ZDICTLIB_VISIBILITY
+#elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1)
+#  define ZDICTLIB_API __declspec(dllimport) ZDICTLIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
 #else
-#  define ZDICTLIB_API
+#  define ZDICTLIB_API ZDICTLIB_VISIBILITY
 #endif
 
 
@@ -79,29 +82,116 @@ typedef struct {
               or an error code, which can be tested by ZDICT_isError().
     note : ZDICT_trainFromBuffer_advanced() will send notifications into stderr if instructed to, using notificationLevel>0.
 */
-size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacity,
+ZDICTLIB_API size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacity,
                                 const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
                                 ZDICT_params_t parameters);
 
+/*! COVER_params_t :
+    For all values 0 means default.
+    kMin and d are the only required parameters.
+*/
+typedef struct {
+    unsigned k;                  /* Segment size : constraint: 0 < k : Reasonable range [16, 2048+] */
+    unsigned d;                  /* dmer size : constraint: 0 < d <= k : Reasonable range [6, 16] */
+    unsigned steps;              /* Number of steps : Only used for optimization : 0 means default (32) : Higher means more parameters checked */
+
+    unsigned nbThreads;          /* Number of threads : constraint: 0 < nbThreads : 1 means single-threaded : Only used for optimization : Ignored if ZSTD_MULTITHREAD is not defined */
+    unsigned notificationLevel;  /* Write to stderr; 0 = none (default); 1 = errors; 2 = progression; 3 = details; 4 = debug; */
+    unsigned dictID;             /* 0 means auto mode (32-bits random value); other : force dictID value */
+    int      compressionLevel;   /* 0 means default; target a specific zstd compression level */
+} COVER_params_t;
 
-/*! ZDICT_addEntropyTablesFromBuffer() :
 
-    Given a content-only dictionary (built using any 3rd party algorithm),
-    add entropy tables computed from an array of samples.
+/*! COVER_trainFromBuffer() :
+    Train a dictionary from an array of samples using the COVER algorithm.
+    Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
+    supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
+    The resulting dictionary will be saved into `dictBuffer`.
+    @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
+              or an error code, which can be tested with ZDICT_isError().
+    Note : COVER_trainFromBuffer() requires about 9 bytes of memory for each input byte.
+    Tips : In general, a reasonable dictionary has a size of ~ 100 KB.
+           It's obviously possible to target smaller or larger ones, just by specifying different `dictBufferCapacity`.
+           In general, it's recommended to provide a few thousands samples, but this can vary a lot.
+           It's recommended that total size of all samples be about ~x100 times the target size of dictionary.
+*/
+ZDICTLIB_API size_t COVER_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
+                              const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
+                              COVER_params_t parameters);
+
+/*! COVER_optimizeTrainFromBuffer() :
+    The same requirements as above hold for all the parameters except `parameters`.
+    This function tries many parameter combinations and picks the best parameters.
+    `*parameters` is filled with the best parameters found, and the dictionary
+    constructed with those parameters is stored in `dictBuffer`.
+
+    All of the parameters d, k, steps are optional.
+    If d is non-zero then we don't check multiple values of d, otherwise we check d = {6, 8, 10, 12, 14, 16}.
+    if steps is zero it defaults to its default value.
+    If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [16, 2048].
+
+    @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
+              or an error code, which can be tested with ZDICT_isError().
+              On success `*parameters` contains the parameters selected.
+    Note : COVER_optimizeTrainFromBuffer() requires about 8 bytes of memory for each input byte and additionally another 5 bytes of memory for each byte of memory for each thread.
+*/
+ZDICTLIB_API size_t COVER_optimizeTrainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
+                                     const void* samplesBuffer, const size_t *samplesSizes, unsigned nbSamples,
+                                     COVER_params_t *parameters);
+
+/*! ZDICT_finalizeDictionary() :
+
+    Given a custom content as a basis for dictionary, and a set of samples,
+    finalize dictionary by adding headers and statistics.
+
     Samples must be stored concatenated in a flat buffer `samplesBuffer`,
     supplied with an array of sizes `samplesSizes`, providing the size of each sample in order.
 
-    The input dictionary content must be stored *at the end* of `dictBuffer`.
-    Its size is `dictContentSize`.
-    The resulting dictionary with added entropy tables will be *written back to `dictBuffer`*,
-    starting from its beginning.
-    @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`).
+    dictContentSize must be > ZDICT_CONTENTSIZE_MIN bytes.
+    maxDictSize must be >= dictContentSize, and must be > ZDICT_DICTSIZE_MIN bytes.
+
+    @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`),
+              or an error code, which can be tested by ZDICT_isError().
+    note : ZDICT_finalizeDictionary() will push notifications into stderr if instructed to, using notificationLevel>0.
+    note 2 : dictBuffer and customDictContent can overlap
 */
-size_t ZDICT_addEntropyTablesFromBuffer(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity,
-                                        const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples);
+#define ZDICT_CONTENTSIZE_MIN 256
+#define ZDICT_DICTSIZE_MIN    512
+ZDICTLIB_API size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity,
+                                const void* customDictContent, size_t dictContentSize,
+                                const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
+                                ZDICT_params_t parameters);
 
 
 
+/* Deprecation warnings */
+/* It is generally possible to disable deprecation warnings from compiler,
+   for example with -Wno-deprecated-declarations for gcc
+   or _CRT_SECURE_NO_WARNINGS in Visual.
+   Otherwise, it's also possible to manually define ZDICT_DISABLE_DEPRECATE_WARNINGS */
+#ifdef ZDICT_DISABLE_DEPRECATE_WARNINGS
+#  define ZDICT_DEPRECATED(message) ZDICTLIB_API   /* disable deprecation warnings */
+#else
+#  define ZDICT_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
+#  if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */
+#    define ZDICT_DEPRECATED(message) ZDICTLIB_API [[deprecated(message)]]
+#  elif (ZDICT_GCC_VERSION >= 405) || defined(__clang__)
+#    define ZDICT_DEPRECATED(message) ZDICTLIB_API __attribute__((deprecated(message)))
+#  elif (ZDICT_GCC_VERSION >= 301)
+#    define ZDICT_DEPRECATED(message) ZDICTLIB_API __attribute__((deprecated))
+#  elif defined(_MSC_VER)
+#    define ZDICT_DEPRECATED(message) ZDICTLIB_API __declspec(deprecated(message))
+#  else
+#    pragma message("WARNING: You need to implement ZDICT_DEPRECATED for this compiler")
+#    define ZDICT_DEPRECATED(message) ZDICTLIB_API
+#  endif
+#endif /* ZDICT_DISABLE_DEPRECATE_WARNINGS */
+
+ZDICT_DEPRECATED("use ZDICT_finalizeDictionary() instead")
+size_t ZDICT_addEntropyTablesFromBuffer(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity,
+                                  const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples);
+
+
 #endif   /* ZDICT_STATIC_LINKING_ONLY */
 
 #if defined (__cplusplus)

data/ext/zstdruby/libzstd/dll/example/fullbench-dll.vcxproj

@@ -100,6 +100,7 @@
       <GenerateDebugInformation>true</GenerateDebugInformation>
       <AdditionalLibraryDirectories>$(SolutionDir)..\dll;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
       <AdditionalDependencies>libzstd.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
     </Link>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
@@ -141,6 +142,7 @@
       <OptimizeReferences>true</OptimizeReferences>
       <AdditionalLibraryDirectories>$(SolutionDir)..\dll;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
       <AdditionalDependencies>libzstd.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <ImageHasSafeExceptionHandlers>false</ImageHasSafeExceptionHandlers>
     </Link>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">

data/ext/zstdruby/libzstd/legacy/zstd_v04.c

@@ -3012,21 +3012,19 @@ static void ZSTD_decodeSequence(seq_t* seq, seqState_t* seqState)
     /* Literal length */
     litLength = FSE_decodeSymbol(&(seqState->stateLL), &(seqState->DStream));
     prevOffset = litLength ? seq->offset : seqState->prevOffset;
-    if (litLength == MaxLL)
-    {
+    if (litLength == MaxLL) {
         U32 add = *dumps++;
         if (add < 255) litLength += add;
-        else
-        {
-            litLength = MEM_readLE32(dumps) & 0xFFFFFF;  /* no pb : dumps is always followed by seq tables > 1 byte */
+        else {
+            litLength = dumps[0] + (dumps[1]<<8) + (dumps[2]<<16);
             dumps += 3;
         }
-        if (dumps >= de) dumps = de-1;   /* late correction, to avoid read overflow (data is now corrupted anyway) */
+        if (dumps > de) { litLength = MaxLL+255; }  /* late correction, to avoid using uninitialized memory */
+        if (dumps >= de) { dumps = de-1; }  /* late correction, to avoid read overflow (data is now corrupted anyway) */
     }
 
     /* Offset */
-    {
-        static const U32 offsetPrefix[MaxOff+1] = {
+    {   static const U32 offsetPrefix[MaxOff+1] = {
                 1 /*fake*/, 1, 2, 4, 8, 16, 32, 64, 128, 256,
                 512, 1024, 2048, 4096, 8192, 16384, 32768, 65536, 131072, 262144,
                 524288, 1048576, 2097152, 4194304, 8388608, 16777216, 33554432, /*fake*/ 1, 1, 1, 1, 1 };
@@ -3043,16 +3041,15 @@ static void ZSTD_decodeSequence(seq_t* seq, seqState_t* seqState)
 
     /* MatchLength */
     matchLength = FSE_decodeSymbol(&(seqState->stateML), &(seqState->DStream));
-    if (matchLength == MaxML)
-    {
+    if (matchLength == MaxML) {
         U32 add = *dumps++;
         if (add < 255) matchLength += add;
-        else
-        {
-            matchLength = MEM_readLE32(dumps) & 0xFFFFFF;  /* no pb : dumps is always followed by seq tables > 1 byte */
+        else {
+            matchLength = dumps[0] + (dumps[1]<<8) + (dumps[2]<<16);
             dumps += 3;
         }
-        if (dumps >= de) dumps = de-1;   /* late correction, to avoid read overflow (data is now corrupted anyway) */
+        if (dumps > de) { matchLength = MaxML+255; }  /* late correction, to avoid using uninitialized memory */
+        if (dumps >= de) { dumps = de-1; }  /* late correction, to avoid read overflow (data is now corrupted anyway) */
     }
     matchLength += MINMATCH;
 
@@ -3116,8 +3113,7 @@ static size_t ZSTD_execSequence(BYTE* op,
     /* Requirement: op <= oend_8 */
 
     /* match within prefix */
-    if (sequence.offset < 8)
-    {
+    if (sequence.offset < 8) {
         /* close range match, overlap */
         const int sub2 = dec64table[sequence.offset];
         op[0] = match[0];
@@ -3127,9 +3123,7 @@ static size_t ZSTD_execSequence(BYTE* op,
         match += dec32table[sequence.offset];
         ZSTD_copy4(op+4, match);
         match -= sub2;
-    }
-    else
-    {
+    } else {
         ZSTD_copy8(op, match);
     }
     op += 8; match += 8;

data/ext/zstdruby/libzstd/legacy/zstd_v05.c

@@ -3230,7 +3230,8 @@ static void ZSTDv05_decodeSequence(seq_t* seq, seqState_t* seqState)
             if (litLength&1) litLength>>=1, dumps += 3;
             else litLength = (U16)(litLength)>>1, dumps += 2;
         }
-        if (dumps >= de) dumps = de-1;   /* late correction, to avoid read overflow (data is now corrupted anyway) */
+        if (dumps > de) { litLength = MaxLL+255; }  /* late correction, to avoid using uninitialized memory */
+        if (dumps >= de) { dumps = de-1; }  /* late correction, to avoid read overflow (data is now corrupted anyway) */
     }
 
     /* Offset */
@@ -3263,7 +3264,8 @@ static void ZSTDv05_decodeSequence(seq_t* seq, seqState_t* seqState)
             if (matchLength&1) matchLength>>=1, dumps += 3;
             else matchLength = (U16)(matchLength)>>1, dumps += 2;
         }
-        if (dumps >= de) dumps = de-1;   /* late correction, to avoid read overflow (data is now corrupted anyway) */
+        if (dumps > de) { matchLength = MaxML+255; }  /* late correction, to avoid using uninitialized memory */
+        if (dumps >= de) { dumps = de-1; }  /* late correction, to avoid read overflow (data is now corrupted anyway) */
     }
     matchLength += MINMATCH;
 

data/ext/zstdruby/libzstd/legacy/zstd_v07.c

@@ -4134,9 +4134,9 @@ static size_t ZSTDv07_loadEntropy(ZSTDv07_DCtx* dctx, const void* const dict, si
     }
 
     if (dictPtr+12 > dictEnd) return ERROR(dictionary_corrupted);
-    dctx->rep[0] = MEM_readLE32(dictPtr+0); if (dctx->rep[0] >= dictSize) return ERROR(dictionary_corrupted);
-    dctx->rep[1] = MEM_readLE32(dictPtr+4); if (dctx->rep[1] >= dictSize) return ERROR(dictionary_corrupted);
-    dctx->rep[2] = MEM_readLE32(dictPtr+8); if (dctx->rep[2] >= dictSize) return ERROR(dictionary_corrupted);
+    dctx->rep[0] = MEM_readLE32(dictPtr+0); if (dctx->rep[0] == 0 || dctx->rep[0] >= dictSize) return ERROR(dictionary_corrupted);
+    dctx->rep[1] = MEM_readLE32(dictPtr+4); if (dctx->rep[1] == 0 || dctx->rep[1] >= dictSize) return ERROR(dictionary_corrupted);
+    dctx->rep[2] = MEM_readLE32(dictPtr+8); if (dctx->rep[2] == 0 || dctx->rep[2] >= dictSize) return ERROR(dictionary_corrupted);
     dictPtr += 12;
 
     dctx->litEntropy = dctx->fseEntropy = 1;

data/ext/zstdruby/libzstd/zstd.h

@@ -20,13 +20,16 @@ extern "C" {
 
 /* =====   ZSTDLIB_API : control library symbols visibility   ===== */
 #if defined(__GNUC__) && (__GNUC__ >= 4)
-#  define ZSTDLIB_API __attribute__ ((visibility ("default")))
-#elif defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1)
-#  define ZSTDLIB_API __declspec(dllexport)
+#  define ZSTDLIB_VISIBILITY __attribute__ ((visibility ("default")))
+#else
+#  define ZSTDLIB_VISIBILITY
+#endif
+#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1)
+#  define ZSTDLIB_API __declspec(dllexport) ZSTDLIB_VISIBILITY
 #elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1)
-#  define ZSTDLIB_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
+#  define ZSTDLIB_API __declspec(dllimport) ZSTDLIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
 #else
-#  define ZSTDLIB_API
+#  define ZSTDLIB_API ZSTDLIB_VISIBILITY
 #endif
 
 
@@ -53,7 +56,7 @@ extern "C" {
 /*------   Version   ------*/
 #define ZSTD_VERSION_MAJOR    1
 #define ZSTD_VERSION_MINOR    1
-#define ZSTD_VERSION_RELEASE  2
+#define ZSTD_VERSION_RELEASE  3
 
 #define ZSTD_LIB_VERSION ZSTD_VERSION_MAJOR.ZSTD_VERSION_MINOR.ZSTD_VERSION_RELEASE
 #define ZSTD_QUOTE(str) #str
@@ -170,8 +173,8 @@ typedef struct ZSTD_CDict_s ZSTD_CDict;
 *   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.
-*   `dict` can be released after ZSTD_CDict creation. */
-ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dict, size_t dictSize, int compressionLevel);
+*   `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);
 
 /*! ZSTD_freeCDict() :
 *   Function frees memory allocated by ZSTD_createCDict(). */
@@ -191,8 +194,8 @@ typedef struct ZSTD_DDict_s ZSTD_DDict;
 
 /*! ZSTD_createDDict() :
 *   Create a digested dictionary, ready to start decompression operation without startup delay.
-*   `dict` can be released after creation. */
-ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize);
+*   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() */
@@ -325,7 +328,7 @@ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void);   /*!< recommended size for output
  * ***************************************************************************************/
 
 /* --- Constants ---*/
-#define ZSTD_MAGICNUMBER            0xFD2FB528   /* v0.8 */
+#define ZSTD_MAGICNUMBER            0xFD2FB528   /* >= v0.8.0 */
 #define ZSTD_MAGIC_SKIPPABLE_START  0x184D2A50U
 
 #define ZSTD_WINDOWLOG_MAX_32  25
@@ -345,8 +348,9 @@ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void);   /*!< recommended size for output
 #define ZSTD_TARGETLENGTH_MAX 999
 
 #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 = 6;
+static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN;
 static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX;
 static const size_t ZSTD_skippableHeaderSize = 8;  /* magic number + skippable frame length */
 
@@ -365,9 +369,9 @@ typedef struct {
 } ZSTD_compressionParameters;
 
 typedef struct {
-    unsigned contentSizeFlag; /**< 1: content size will be in frame header (if known). */
-    unsigned checksumFlag;    /**< 1: will generate a 22-bits checksum at end of frame, to be used for error detection by decompressor */
-    unsigned noDictIDFlag;    /**< 1: no dict ID will be saved into frame header (if dictionary compression) */
+    unsigned contentSizeFlag; /**< 1: content size will be in frame header (when known) */
+    unsigned checksumFlag;    /**< 1: generate a 32-bits checksum at end of frame, for error detection */
+    unsigned noDictIDFlag;    /**< 1: no dictID will be saved into frame header (if dictionary compression) */
 } ZSTD_frameParameters;
 
 typedef struct {
@@ -397,9 +401,23 @@ ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem);
  *  Gives the amount of memory used by a given ZSTD_CCtx */
 ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
 
+typedef enum {
+    ZSTD_p_forceWindow   /* Force back-references to remain < windowSize, even when referencing Dictionary content (default:0)*/
+} ZSTD_CCtxParameter;
+/*! ZSTD_setCCtxParameter() :
+ *  Set advanced parameters, selected through enum ZSTD_CCtxParameter
+ *  @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);
+
 /*! 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,
+ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, unsigned byReference,
                                                   ZSTD_parameters params, ZSTD_customMem customMem);
 
 /*! ZSTD_sizeof_CDict() :
@@ -455,6 +473,15 @@ ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem);
  *  Gives the amount of memory used by a given ZSTD_DCtx */
 ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
 
+/*! 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 */
+ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize);
+
+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);
@@ -463,13 +490,13 @@ ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
  *  Provides the dictID stored within dictionary.
  *  if @return == 0, the dictionary is not conformant with Zstandard specification.
  *  It can still be loaded, but as a content-only dictionary. */
-unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize);
+ZSTDLIB_API unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize);
 
 /*! ZSTD_getDictID_fromDDict() :
  *  Provides the dictID of the dictionary loaded into `ddict`.
  *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
  *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
-unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
+ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
 
 /*! ZSTD_getDictID_fromFrame() :
  *  Provides the dictID required to decompressed the frame stored within `src`.
@@ -481,7 +508,7 @@ unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
  *  - `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 used ZSTD_getFrameParams(), which will provide a more precise error code. */
-unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
+ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
 
 
 /********************************************************************
@@ -491,7 +518,7 @@ 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_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);   /**< pledgedSrcSize must be correct */
-ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel);
+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_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize,
                                              ZSTD_parameters params, unsigned long long pledgedSrcSize);  /**< pledgedSrcSize is optional and can be zero == unknown */
 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 */
@@ -500,9 +527,9 @@ ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);
 
 
 /*=====   Advanced Streaming decompression functions  =====*/
-typedef enum { ZSTDdsp_maxWindowSize } ZSTD_DStreamParameter_e;
+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);
+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_setDStreamParameter(ZSTD_DStream* zds, ZSTD_DStreamParameter_e paramType, unsigned paramValue);
 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 */
@@ -542,10 +569,10 @@ ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
     In which case, it will "discard" the relevant memory section from its history.
 
   Finish a frame with ZSTD_compressEnd(), which will write the last block(s) and optional checksum.
-  It's possible to use a NULL,0 src content, in which case, it will write a final empty block to end the frame,
-  Without last block mark, frames will be considered unfinished (broken) by decoders.
+  It's possible to use srcSize==0, in which case, it will write a final empty block to end the frame.
+  Without last block mark, frames will be considered unfinished (corrupted) by decoders.
 
-  You can then reuse `ZSTD_CCtx` (ZSTD_compressBegin()) to compress some new frame.
+  `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new frame.
 */
 
 /*=====   Buffer-less streaming compression functions  =====*/
@@ -553,6 +580,7 @@ ZSTDLIB_API size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel);
 ZSTDLIB_API size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel);
 ZSTDLIB_API size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize);
 ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize);
+ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict, unsigned long long pledgedSrcSize);
 ZSTDLIB_API size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
 ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);