[Minor] Update bundled zstd to version 1.3

1 files changed, 110 insertions, 40 deletions

diff --git a/contrib/zstd/fse.h b/contrib/zstd/fse.h
index 720d54b11..6d5d41def 100644
--- a/contrib/zstd/fse.h
+++ b/contrib/zstd/fse.h
@@ -45,6 +45,32 @@ extern "C" {
 #include <stddef.h>    /* size_t, ptrdiff_t */
 
 
+/*-*****************************************
+*  FSE_PUBLIC_API : control library symbols visibility
+******************************************/
+#if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4)
+#  define FSE_PUBLIC_API __attribute__ ((visibility ("default")))
+#elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1)   /* Visual expected */
+#  define FSE_PUBLIC_API __declspec(dllexport)
+#elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1)
+#  define FSE_PUBLIC_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.*/
+#else
+#  define FSE_PUBLIC_API
+#endif
+
+/*------   Version   ------*/
+#define FSE_VERSION_MAJOR    0
+#define FSE_VERSION_MINOR    9
+#define FSE_VERSION_RELEASE  0
+
+#define FSE_LIB_VERSION FSE_VERSION_MAJOR.FSE_VERSION_MINOR.FSE_VERSION_RELEASE
+#define FSE_QUOTE(str) #str
+#define FSE_EXPAND_AND_QUOTE(str) FSE_QUOTE(str)
+#define FSE_VERSION_STRING FSE_EXPAND_AND_QUOTE(FSE_LIB_VERSION)
+
+#define FSE_VERSION_NUMBER  (FSE_VERSION_MAJOR *100*100 + FSE_VERSION_MINOR *100 + FSE_VERSION_RELEASE)
+FSE_PUBLIC_API unsigned FSE_versionNumber(void);   /**< library version number; to be used when checking dll version */
+
 /*-****************************************
 *  FSE simple functions
 ******************************************/
@@ -56,8 +82,8 @@ extern "C" {
                      if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression instead.
                      if FSE_isError(return), compression failed (more details using FSE_getErrorName())
 */
-size_t FSE_compress(void* dst, size_t dstCapacity,
-              const void* src, size_t srcSize);
+FSE_PUBLIC_API size_t FSE_compress(void* dst, size_t dstCapacity,
+                             const void* src, size_t srcSize);
 
 /*! FSE_decompress():
     Decompress FSE data from buffer 'cSrc', of size 'cSrcSize',
@@ -69,18 +95,18 @@ size_t FSE_compress(void* dst, size_t dstCapacity,
     Why ? : making this distinction requires a header.
     Header management is intentionally delegated to the user layer, which can better manage special cases.
 */
-size_t FSE_decompress(void* dst,  size_t dstCapacity,
-                const void* cSrc, size_t cSrcSize);
+FSE_PUBLIC_API size_t FSE_decompress(void* dst,  size_t dstCapacity,
+                               const void* cSrc, size_t cSrcSize);
 
 
 /*-*****************************************
 *  Tool functions
 ******************************************/
-size_t FSE_compressBound(size_t size);       /* maximum compressed size */
+FSE_PUBLIC_API size_t FSE_compressBound(size_t size);       /* maximum compressed size */
 
 /* Error Management */
-unsigned    FSE_isError(size_t code);        /* tells if a return value is an error code */
-const char* FSE_getErrorName(size_t code);   /* provides error code string (useful for debugging) */
+FSE_PUBLIC_API unsigned    FSE_isError(size_t code);        /* tells if a return value is an error code */
+FSE_PUBLIC_API const char* FSE_getErrorName(size_t code);   /* provides error code string (useful for debugging) */
 
 
 /*-*****************************************
@@ -94,7 +120,7 @@ const char* FSE_getErrorName(size_t code);   /* provides error code string (usef
                      if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression.
                      if FSE_isError(return), it's an error code.
 */
-size_t FSE_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
+FSE_PUBLIC_API size_t FSE_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
 
 
 /*-*****************************************
@@ -127,50 +153,50 @@ or to save and provide normalized distribution using external method.
     @return : the count of the most frequent symbol (which is not identified).
               if return == srcSize, there is only one symbol.
               Can also return an error code, which can be tested with FSE_isError(). */
-size_t FSE_count(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize);
+FSE_PUBLIC_API size_t FSE_count(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize);
 
 /*! FSE_optimalTableLog():
     dynamically downsize 'tableLog' when conditions are met.
     It saves CPU time, by using smaller tables, while preserving or even improving compression ratio.
     @return : recommended tableLog (necessarily <= 'maxTableLog') */
-unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
+FSE_PUBLIC_API unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
 
 /*! FSE_normalizeCount():
     normalize counts so that sum(count[]) == Power_of_2 (2^tableLog)
     'normalizedCounter' is a table of short, of minimum size (maxSymbolValue+1).
     @return : tableLog,
               or an errorCode, which can be tested using FSE_isError() */
-size_t FSE_normalizeCount(short* normalizedCounter, unsigned tableLog, const unsigned* count, size_t srcSize, unsigned maxSymbolValue);
+FSE_PUBLIC_API size_t FSE_normalizeCount(short* normalizedCounter, unsigned tableLog, const unsigned* count, size_t srcSize, unsigned maxSymbolValue);
 
 /*! FSE_NCountWriteBound():
     Provides the maximum possible size of an FSE normalized table, given 'maxSymbolValue' and 'tableLog'.
     Typically useful for allocation purpose. */
-size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog);
+FSE_PUBLIC_API size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog);
 
 /*! FSE_writeNCount():
     Compactly save 'normalizedCounter' into 'buffer'.
     @return : size of the compressed table,
               or an errorCode, which can be tested using FSE_isError(). */
-size_t FSE_writeNCount (void* buffer, size_t bufferSize, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
+FSE_PUBLIC_API size_t FSE_writeNCount (void* buffer, size_t bufferSize, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
 
 
 /*! Constructor and Destructor of FSE_CTable.
     Note that FSE_CTable size depends on 'tableLog' and 'maxSymbolValue' */
 typedef unsigned FSE_CTable;   /* don't allocate that. It's only meant to be more restrictive than void* */
-FSE_CTable* FSE_createCTable (unsigned tableLog, unsigned maxSymbolValue);
-void        FSE_freeCTable (FSE_CTable* ct);
+FSE_PUBLIC_API FSE_CTable* FSE_createCTable (unsigned tableLog, unsigned maxSymbolValue);
+FSE_PUBLIC_API void        FSE_freeCTable (FSE_CTable* ct);
 
 /*! FSE_buildCTable():
     Builds `ct`, which must be already allocated, using FSE_createCTable().
     @return : 0, or an errorCode, which can be tested using FSE_isError() */
-size_t FSE_buildCTable(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
+FSE_PUBLIC_API size_t FSE_buildCTable(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
 
 /*! FSE_compress_usingCTable():
     Compress `src` using `ct` into `dst` which must be already allocated.
     @return : size of compressed data (<= `dstCapacity`),
               or 0 if compressed data could not fit into `dst`,
               or an errorCode, which can be tested using FSE_isError() */
-size_t FSE_compress_usingCTable (void* dst, size_t dstCapacity, const void* src, size_t srcSize, const FSE_CTable* ct);
+FSE_PUBLIC_API size_t FSE_compress_usingCTable (void* dst, size_t dstCapacity, const void* src, size_t srcSize, const FSE_CTable* ct);
 
 /*!
 Tutorial :
@@ -223,25 +249,25 @@ If there is an error, the function will return an ErrorCode (which can be tested
     @return : size read from 'rBuffer',
               or an errorCode, which can be tested using FSE_isError().
               maxSymbolValuePtr[0] and tableLogPtr[0] will also be updated with their respective values */
-size_t FSE_readNCount (short* normalizedCounter, unsigned* maxSymbolValuePtr, unsigned* tableLogPtr, const void* rBuffer, size_t rBuffSize);
+FSE_PUBLIC_API size_t FSE_readNCount (short* normalizedCounter, unsigned* maxSymbolValuePtr, unsigned* tableLogPtr, const void* rBuffer, size_t rBuffSize);
 
 /*! Constructor and Destructor of FSE_DTable.
     Note that its size depends on 'tableLog' */
 typedef unsigned FSE_DTable;   /* don't allocate that. It's just a way to be more restrictive than void* */
-FSE_DTable* FSE_createDTable(unsigned tableLog);
-void        FSE_freeDTable(FSE_DTable* dt);
+FSE_PUBLIC_API FSE_DTable* FSE_createDTable(unsigned tableLog);
+FSE_PUBLIC_API void        FSE_freeDTable(FSE_DTable* dt);
 
 /*! FSE_buildDTable():
     Builds 'dt', which must be already allocated, using FSE_createDTable().
     return : 0, or an errorCode, which can be tested using FSE_isError() */
-size_t FSE_buildDTable (FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
+FSE_PUBLIC_API size_t FSE_buildDTable (FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
 
 /*! FSE_decompress_usingDTable():
     Decompress compressed source `cSrc` of size `cSrcSize` using `dt`
     into `dst` which must be already allocated.
     @return : size of regenerated data (necessarily <= `dstCapacity`),
               or an errorCode, which can be tested using FSE_isError() */
-size_t FSE_decompress_usingDTable(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt);
+FSE_PUBLIC_API size_t FSE_decompress_usingDTable(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt);
 
 /*!
 Tutorial :
@@ -286,45 +312,84 @@ If there is an error, the function will return an error code, which can be teste
 #define FSE_BLOCKBOUND(size) (size + (size>>7))
 #define FSE_COMPRESSBOUND(size) (FSE_NCOUNTBOUND + FSE_BLOCKBOUND(size))   /* Macro version, useful for static allocation */
 
-/* It is possible to statically allocate FSE CTable/DTable as a table of unsigned using below macros */
+/* It is possible to statically allocate FSE CTable/DTable as a table of FSE_CTable/FSE_DTable using below macros */
 #define FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue)   (1 + (1<<(maxTableLog-1)) + ((maxSymbolValue+1)*2))
 #define FSE_DTABLE_SIZE_U32(maxTableLog)                   (1 + (1<<maxTableLog))
 
+/* or use the size to malloc() space directly. Pay attention to alignment restrictions though */
+#define FSE_CTABLE_SIZE(maxTableLog, maxSymbolValue)   (FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) * sizeof(FSE_CTable))
+#define FSE_DTABLE_SIZE(maxTableLog)                   (FSE_DTABLE_SIZE_U32(maxTableLog) * sizeof(FSE_DTable))
+
 
 /* *****************************************
 *  FSE advanced API
 *******************************************/
+/* FSE_count_wksp() :
+ * Same as FSE_count(), but using an externally provided scratch buffer.
+ * `workSpace` size must be table of >= `1024` unsigned
+ */
+size_t FSE_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                 const void* source, size_t sourceSize, unsigned* workSpace);
+
+/** FSE_countFast() :
+ *  same as FSE_count(), but blindly trusts that all byte values within src are <= *maxSymbolValuePtr
+ */
 size_t FSE_countFast(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize);
-/**< same as FSE_count(), but blindly trusts that all byte values within src are <= *maxSymbolValuePtr  */
+
+/* FSE_countFast_wksp() :
+ * Same as FSE_countFast(), but using an externally provided scratch buffer.
+ * `workSpace` must be a table of minimum `1024` unsigned
+ */
+size_t FSE_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize, unsigned* workSpace);
+
+/*! FSE_count_simple
+ * Same as FSE_countFast(), but does not use any additional memory (not even on stack).
+ * This function is unsafe, and will segfault if any value within `src` is `> *maxSymbolValuePtr` (presuming it's also the size of `count`).
+*/
+size_t FSE_count_simple(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize);
+
+
 
 unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus);
 /**< same as FSE_optimalTableLog(), which used `minus==2` */
 
+/* FSE_compress_wksp() :
+ * Same as FSE_compress2(), but using an externally allocated scratch buffer (`workSpace`).
+ * FSE_WKSP_SIZE_U32() provides the minimum size required for `workSpace` as a table of FSE_CTable.
+ */
+#define FSE_WKSP_SIZE_U32(maxTableLog, maxSymbolValue)   ( FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) + ((maxTableLog > 12) ? (1 << (maxTableLog - 2)) : 1024) )
+size_t FSE_compress_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
+
 size_t FSE_buildCTable_raw (FSE_CTable* ct, unsigned nbBits);
-/**< build a fake FSE_CTable, designed to not compress an input, where each symbol uses nbBits */
+/**< build a fake FSE_CTable, designed for a flat distribution, where each symbol uses nbBits */
 
 size_t FSE_buildCTable_rle (FSE_CTable* ct, unsigned char symbolValue);
 /**< build a fake FSE_CTable, designed to compress always the same symbolValue */
 
+/* FSE_buildCTable_wksp() :
+ * Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`).
+ * `wkspSize` must be >= `(1<<tableLog)`.
+ */
+size_t FSE_buildCTable_wksp(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
+
 size_t FSE_buildDTable_raw (FSE_DTable* dt, unsigned nbBits);
-/**< build a fake FSE_DTable, designed to read an uncompressed bitstream where each symbol uses nbBits */
+/**< build a fake FSE_DTable, designed to read a flat distribution where each symbol uses nbBits */
 
 size_t FSE_buildDTable_rle (FSE_DTable* dt, unsigned char symbolValue);
 /**< build a fake FSE_DTable, designed to always generate the same symbolValue */
 
+size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, FSE_DTable* workSpace, unsigned maxLog);
+/**< same as FSE_decompress(), using an externally allocated `workSpace` produced with `FSE_DTABLE_SIZE_U32(maxLog)` */
+
 
 /* *****************************************
 *  FSE symbol compression API
 *******************************************/
 /*!
    This API consists of small unitary functions, which highly benefit from being inlined.
-   You will want to enable link-time-optimization to ensure these functions are properly inlined in your binary.
-   Visual seems to do it automatically.
-   For gcc or clang, you'll need to add -flto flag at compilation and linking stages.
-   If none of these solutions is applicable, include "fse.c" directly.
+   Hence their body are included in next section.
 */
-typedef struct
-{
+typedef struct {
     ptrdiff_t   value;
     const void* stateTable;
     const void* symbolTT;
@@ -384,8 +449,7 @@ If there is an error, it returns an errorCode (which can be tested using FSE_isE
 /* *****************************************
 *  FSE symbol decompression API
 *******************************************/
-typedef struct
-{
+typedef struct {
     size_t      state;
     const void* table;   /* precise table may vary, depending on U16 */
 } FSE_DState_t;
@@ -490,9 +554,9 @@ MEM_STATIC void FSE_initCState2(FSE_CState_t* statePtr, const FSE_CTable* ct, U3
 
 MEM_STATIC void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* statePtr, U32 symbol)
 {
-    const FSE_symbolCompressionTransform symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol];
+    FSE_symbolCompressionTransform const symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol];
     const U16* const stateTable = (const U16*)(statePtr->stateTable);
-    U32 nbBitsOut  = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16);
+    U32 const nbBitsOut  = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16);
     BIT_addBits(bitC, statePtr->value, nbBitsOut);
     statePtr->value = stateTable[ (statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
 }
@@ -503,6 +567,7 @@ MEM_STATIC void FSE_flushCState(BIT_CStream_t* bitC, const FSE_CState_t* statePt
     BIT_flushBits(bitC);
 }
 
+
 /* ======    Decompression    ====== */
 
 typedef struct {
@@ -581,14 +646,19 @@ MEM_STATIC unsigned FSE_endOfDState(const FSE_DState_t* DStatePtr)
 *  Increasing memory usage improves compression ratio
 *  Reduced memory usage can improve speed, due to cache effect
 *  Recommended max value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */
-#define FSE_MAX_MEMORY_USAGE 14
-#define FSE_DEFAULT_MEMORY_USAGE 13
+#ifndef FSE_MAX_MEMORY_USAGE
+#  define FSE_MAX_MEMORY_USAGE 14
+#endif
+#ifndef FSE_DEFAULT_MEMORY_USAGE
+#  define FSE_DEFAULT_MEMORY_USAGE 13
+#endif
 
 /*!FSE_MAX_SYMBOL_VALUE :
 *  Maximum symbol value authorized.
 *  Required for proper stack allocation */
-#define FSE_MAX_SYMBOL_VALUE 255
-
+#ifndef FSE_MAX_SYMBOL_VALUE
+#  define FSE_MAX_SYMBOL_VALUE 255
+#endif
 
 /* **************************************************************
 *  template functions type & suffix