duckdb 1.1.4-dev2.0 → 1.1.4-dev9.0

package/src/duckdb/third_party/zstd/include/zstd/common/fse.h

@@ -1,7 +1,7 @@
 /* ******************************************************************
  * FSE : Finite State Entropy codec
  * Public Prototypes declaration
- * Copyright (c) 2013-2020, Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  *
  * You can contact the author at :
  * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
@@ -12,6 +12,7 @@
  * You may select, at your option, one of the above-listed licenses.
 ****************************************************************** */
 
+
 #ifndef FSE_H
 #define FSE_H
 
@@ -19,10 +20,11 @@
 /*-*****************************************
 *  Dependencies
 ******************************************/
-#include <stddef.h>    /* size_t, ptrdiff_t */
 
+#include "zstd/common/zstd_deps.h"    /* size_t, ptrdiff_t */
 
 namespace duckdb_zstd {
+
 /*-*****************************************
 *  FSE_PUBLIC_API : control library symbols visibility
 ******************************************/
@@ -50,34 +52,6 @@ namespace duckdb_zstd {
 FSE_PUBLIC_API unsigned FSE_versionNumber(void);   /**< library version number; to be used when checking dll version */
 
 
-/*-****************************************
-*  FSE simple functions
-******************************************/
-/*! FSE_compress() :
-    Compress content of buffer 'src', of size 'srcSize', into destination buffer 'dst'.
-    'dst' buffer must be already allocated. Compression runs faster is dstCapacity >= FSE_compressBound(srcSize).
-    @return : size of compressed data (<= dstCapacity).
-    Special values : if return == 0, srcData is not compressible => Nothing is stored within dst !!!
-                     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())
-*/
-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',
-    into already allocated destination buffer 'dst', of size 'dstCapacity'.
-    @return : size of regenerated data (<= maxDstSize),
-              or an error code, which can be tested using FSE_isError() .
-
-    ** Important ** : FSE_decompress() does not decompress non-compressible nor RLE data !!!
-    Why ? : making this distinction requires a header.
-    Header management is intentionally delegated to the user layer, which can better manage special cases.
-*/
-FSE_PUBLIC_API size_t FSE_decompress(void* dst,  size_t dstCapacity,
-                               const void* cSrc, size_t cSrcSize);
-
-
 /*-*****************************************
 *  Tool functions
 ******************************************/
@@ -88,20 +62,6 @@ FSE_PUBLIC_API unsigned    FSE_isError(size_t code);        /* tells if a return
 FSE_PUBLIC_API const char* FSE_getErrorName(size_t code);   /* provides error code string (useful for debugging) */
 
 
-/*-*****************************************
-*  FSE advanced functions
-******************************************/
-/*! FSE_compress2() :
-    Same as FSE_compress(), but allows the selection of 'maxSymbolValue' and 'tableLog'
-    Both parameters can be defined as '0' to mean : use default value
-    @return : size of compressed data
-    Special values : if return == 0, srcData is not compressible => Nothing is stored within cSrc !!!
-                     if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression.
-                     if FSE_isError(return), it's an error code.
-*/
-FSE_PUBLIC_API size_t FSE_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
-
-
 /*-*****************************************
 *  FSE detailed API
 ******************************************/
@@ -134,10 +94,16 @@ FSE_PUBLIC_API unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize
 /*! FSE_normalizeCount():
     normalize counts so that sum(count[]) == Power_of_2 (2^tableLog)
     'normalizedCounter' is a table of short, of minimum size (maxSymbolValue+1).
+    useLowProbCount is a boolean parameter which trades off compressed size for
+    faster header decoding. When it is set to 1, the compressed data will be slightly
+    smaller. And when it is set to 0, FSE_readNCount() and FSE_buildDTable() will be
+    faster. If you are compressing a small amount of data (< 2 KB) then useLowProbCount=0
+    is a good default, since header deserialization makes a big speed difference.
+    Otherwise, useLowProbCount=1 is a good default, since the speed difference is small.
     @return : tableLog,
               or an errorCode, which can be tested using FSE_isError() */
 FSE_PUBLIC_API size_t FSE_normalizeCount(short* normalizedCounter, unsigned tableLog,
-                    const unsigned* count, size_t srcSize, unsigned maxSymbolValue);
+                    const unsigned* count, size_t srcSize, unsigned maxSymbolValue, unsigned useLowProbCount);
 
 /*! FSE_NCountWriteBound():
     Provides the maximum possible size of an FSE normalized table, given 'maxSymbolValue' and 'tableLog'.
@@ -155,8 +121,6 @@ FSE_PUBLIC_API size_t FSE_writeNCount (void* buffer, size_t bufferSize,
 /*! 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_PUBLIC_API FSE_CTable* FSE_createCTable (unsigned maxSymbolValue, unsigned tableLog);
-FSE_PUBLIC_API void        FSE_freeCTable (FSE_CTable* ct);
 
 /*! FSE_buildCTable():
     Builds `ct`, which must be already allocated, using FSE_createCTable().
@@ -225,23 +189,14 @@ 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' */
+/*! FSE_readNCount_bmi2():
+ * Same as FSE_readNCount() but pass bmi2=1 when your CPU supports BMI2 and 0 otherwise.
+ */
+FSE_PUBLIC_API size_t FSE_readNCount_bmi2(short* normalizedCounter,
+                           unsigned* maxSymbolValuePtr, unsigned* tableLogPtr,
+                           const void* rBuffer, size_t rBuffSize, int bmi2);
+
 typedef unsigned FSE_DTable;   /* don't allocate that. It's just a way to be more restrictive than void* */
-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() */
-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() */
-FSE_PUBLIC_API size_t FSE_decompress_usingDTable(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt);
 
 /*!
 Tutorial :
@@ -271,7 +226,412 @@ FSE_decompress_usingDTable() result will tell how many bytes were regenerated (<
 If there is an error, the function will return an error code, which can be tested using FSE_isError(). (ex: dst buffer too small)
 */
 
-}
+} // namespace duckdb_zstd
 
 #endif  /* FSE_H */
 
+#if defined(FSE_STATIC_LINKING_ONLY) && !defined(FSE_H_FSE_STATIC_LINKING_ONLY)
+#define FSE_H_FSE_STATIC_LINKING_ONLY
+
+/* *** Dependency *** */
+#include "zstd/common/bitstream.h"
+
+namespace duckdb_zstd {
+
+/* *****************************************
+*  Static allocation
+*******************************************/
+/* FSE buffer bounds */
+#define FSE_NCOUNTBOUND 512
+#define FSE_BLOCKBOUND(size) ((size) + ((size)>>7) + 4 /* fse states */ + sizeof(size_t) /* bitContainer */)
+#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 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
+ ***************************************** */
+
+unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus);
+/**< same as FSE_optimalTableLog(), which used `minus==2` */
+
+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 >= `FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(maxSymbolValue, tableLog)` of `unsigned`.
+ * See FSE_buildCTable_wksp() for breakdown of workspace usage.
+ */
+#define FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(maxSymbolValue, tableLog) (((maxSymbolValue + 2) + (1ull << (tableLog)))/2 + sizeof(U64)/sizeof(U32) /* additional 8 bytes for potential table overwrite */)
+#define FSE_BUILD_CTABLE_WORKSPACE_SIZE(maxSymbolValue, tableLog) (sizeof(unsigned) * FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(maxSymbolValue, tableLog))
+size_t FSE_buildCTable_wksp(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
+
+#define FSE_BUILD_DTABLE_WKSP_SIZE(maxTableLog, maxSymbolValue) (sizeof(short) * (maxSymbolValue + 1) + (1ULL << maxTableLog) + 8)
+#define FSE_BUILD_DTABLE_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) ((FSE_BUILD_DTABLE_WKSP_SIZE(maxTableLog, maxSymbolValue) + sizeof(unsigned) - 1) / sizeof(unsigned))
+FSE_PUBLIC_API size_t FSE_buildDTable_wksp(FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
+/**< Same as FSE_buildDTable(), using an externally allocated `workspace` produced with `FSE_BUILD_DTABLE_WKSP_SIZE_U32(maxSymbolValue)` */
+
+#define FSE_DECOMPRESS_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) (FSE_DTABLE_SIZE_U32(maxTableLog) + 1 + FSE_BUILD_DTABLE_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) + (FSE_MAX_SYMBOL_VALUE + 1) / 2 + 1)
+#define FSE_DECOMPRESS_WKSP_SIZE(maxTableLog, maxSymbolValue) (FSE_DECOMPRESS_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) * sizeof(unsigned))
+size_t FSE_decompress_wksp_bmi2(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize, int bmi2);
+/**< same as FSE_decompress(), using an externally allocated `workSpace` produced with `FSE_DECOMPRESS_WKSP_SIZE_U32(maxLog, maxSymbolValue)`.
+ * Set bmi2 to 1 if your CPU supports BMI2 or 0 if it doesn't */
+
+typedef enum {
+   FSE_repeat_none,  /**< Cannot use the previous table */
+   FSE_repeat_check, /**< Can use the previous table but it must be checked */
+   FSE_repeat_valid  /**< Can use the previous table and it is assumed to be valid */
+ } FSE_repeat;
+
+/* *****************************************
+*  FSE symbol compression API
+*******************************************/
+/*!
+   This API consists of small unitary functions, which highly benefit from being inlined.
+   Hence their body are included in next section.
+*/
+typedef struct {
+    ptrdiff_t   value;
+    const void* stateTable;
+    const void* symbolTT;
+    unsigned    stateLog;
+} FSE_CState_t;
+
+static void FSE_initCState(FSE_CState_t* CStatePtr, const FSE_CTable* ct);
+
+static void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* CStatePtr, unsigned symbol);
+
+static void FSE_flushCState(BIT_CStream_t* bitC, const FSE_CState_t* CStatePtr);
+
+/**<
+These functions are inner components of FSE_compress_usingCTable().
+They allow the creation of custom streams, mixing multiple tables and bit sources.
+
+A key property to keep in mind is that encoding and decoding are done **in reverse direction**.
+So the first symbol you will encode is the last you will decode, like a LIFO stack.
+
+You will need a few variables to track your CStream. They are :
+
+FSE_CTable    ct;         // Provided by FSE_buildCTable()
+BIT_CStream_t bitStream;  // bitStream tracking structure
+FSE_CState_t  state;      // State tracking structure (can have several)
+
+
+The first thing to do is to init bitStream and state.
+    size_t errorCode = BIT_initCStream(&bitStream, dstBuffer, maxDstSize);
+    FSE_initCState(&state, ct);
+
+Note that BIT_initCStream() can produce an error code, so its result should be tested, using FSE_isError();
+You can then encode your input data, byte after byte.
+FSE_encodeSymbol() outputs a maximum of 'tableLog' bits at a time.
+Remember decoding will be done in reverse direction.
+    FSE_encodeByte(&bitStream, &state, symbol);
+
+At any time, you can also add any bit sequence.
+Note : maximum allowed nbBits is 25, for compatibility with 32-bits decoders
+    BIT_addBits(&bitStream, bitField, nbBits);
+
+The above methods don't commit data to memory, they just store it into local register, for speed.
+Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t).
+Writing data to memory is a manual operation, performed by the flushBits function.
+    BIT_flushBits(&bitStream);
+
+Your last FSE encoding operation shall be to flush your last state value(s).
+    FSE_flushState(&bitStream, &state);
+
+Finally, you must close the bitStream.
+The function returns the size of CStream in bytes.
+If data couldn't fit into dstBuffer, it will return a 0 ( == not compressible)
+If there is an error, it returns an errorCode (which can be tested using FSE_isError()).
+    size_t size = BIT_closeCStream(&bitStream);
+*/
+
+
+/* *****************************************
+*  FSE symbol decompression API
+*******************************************/
+typedef struct {
+    size_t      state;
+    const void* table;   /* precise table may vary, depending on U16 */
+} FSE_DState_t;
+
+
+static void     FSE_initDState(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD, const FSE_DTable* dt);
+
+static unsigned char FSE_decodeSymbol(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD);
+
+static unsigned FSE_endOfDState(const FSE_DState_t* DStatePtr);
+
+/**<
+Let's now decompose FSE_decompress_usingDTable() into its unitary components.
+You will decode FSE-encoded symbols from the bitStream,
+and also any other bitFields you put in, **in reverse order**.
+
+You will need a few variables to track your bitStream. They are :
+
+BIT_DStream_t DStream;    // Stream context
+FSE_DState_t  DState;     // State context. Multiple ones are possible
+FSE_DTable*   DTablePtr;  // Decoding table, provided by FSE_buildDTable()
+
+The first thing to do is to init the bitStream.
+    errorCode = BIT_initDStream(&DStream, srcBuffer, srcSize);
+
+You should then retrieve your initial state(s)
+(in reverse flushing order if you have several ones) :
+    errorCode = FSE_initDState(&DState, &DStream, DTablePtr);
+
+You can then decode your data, symbol after symbol.
+For information the maximum number of bits read by FSE_decodeSymbol() is 'tableLog'.
+Keep in mind that symbols are decoded in reverse order, like a LIFO stack (last in, first out).
+    unsigned char symbol = FSE_decodeSymbol(&DState, &DStream);
+
+You can retrieve any bitfield you eventually stored into the bitStream (in reverse order)
+Note : maximum allowed nbBits is 25, for 32-bits compatibility
+    size_t bitField = BIT_readBits(&DStream, nbBits);
+
+All above operations only read from local register (which size depends on size_t).
+Refueling the register from memory is manually performed by the reload method.
+    endSignal = FSE_reloadDStream(&DStream);
+
+BIT_reloadDStream() result tells if there is still some more data to read from DStream.
+BIT_DStream_unfinished : there is still some data left into the DStream.
+BIT_DStream_endOfBuffer : Dstream reached end of buffer. Its container may no longer be completely filled.
+BIT_DStream_completed : Dstream reached its exact end, corresponding in general to decompression completed.
+BIT_DStream_tooFar : Dstream went too far. Decompression result is corrupted.
+
+When reaching end of buffer (BIT_DStream_endOfBuffer), progress slowly, notably if you decode multiple symbols per loop,
+to properly detect the exact end of stream.
+After each decoded symbol, check if DStream is fully consumed using this simple test :
+    BIT_reloadDStream(&DStream) >= BIT_DStream_completed
+
+When it's done, verify decompression is fully completed, by checking both DStream and the relevant states.
+Checking if DStream has reached its end is performed by :
+    BIT_endOfDStream(&DStream);
+Check also the states. There might be some symbols left there, if some high probability ones (>50%) are possible.
+    FSE_endOfDState(&DState);
+*/
+
+
+/* *****************************************
+*  FSE unsafe API
+*******************************************/
+static unsigned char FSE_decodeSymbolFast(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD);
+/* faster, but works only if nbBits is always >= 1 (otherwise, result will be corrupted) */
+
+
+/* *****************************************
+*  Implementation of inlined functions
+*******************************************/
+typedef struct {
+    int deltaFindState;
+    U32 deltaNbBits;
+} FSE_symbolCompressionTransform; /* total 8 bytes */
+
+MEM_STATIC void FSE_initCState(FSE_CState_t* statePtr, const FSE_CTable* ct)
+{
+    const void* ptr = ct;
+    const U16* u16ptr = (const U16*) ptr;
+    const U32 tableLog = MEM_read16(ptr);
+    statePtr->value = (ptrdiff_t)1<<tableLog;
+    statePtr->stateTable = u16ptr+2;
+    statePtr->symbolTT = ct + 1 + (tableLog ? (1<<(tableLog-1)) : 1);
+    statePtr->stateLog = tableLog;
+}
+
+
+/*! FSE_initCState2() :
+*   Same as FSE_initCState(), but the first symbol to include (which will be the last to be read)
+*   uses the smallest state value possible, saving the cost of this symbol */
+MEM_STATIC void FSE_initCState2(FSE_CState_t* statePtr, const FSE_CTable* ct, U32 symbol)
+{
+    FSE_initCState(statePtr, ct);
+    {   const FSE_symbolCompressionTransform symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol];
+        const U16* stateTable = (const U16*)(statePtr->stateTable);
+        U32 nbBitsOut  = (U32)((symbolTT.deltaNbBits + (1<<15)) >> 16);
+        statePtr->value = (nbBitsOut << 16) - symbolTT.deltaNbBits;
+        statePtr->value = stateTable[(statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
+    }
+}
+
+MEM_STATIC void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* statePtr, unsigned symbol)
+{
+    FSE_symbolCompressionTransform const symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol];
+    const U16* const stateTable = (const U16*)(statePtr->stateTable);
+    U32 const nbBitsOut  = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16);
+    BIT_addBits(bitC,  (size_t)statePtr->value, nbBitsOut);
+    statePtr->value = stateTable[ (statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
+}
+
+MEM_STATIC void FSE_flushCState(BIT_CStream_t* bitC, const FSE_CState_t* statePtr)
+{
+    BIT_addBits(bitC, (size_t)statePtr->value, statePtr->stateLog);
+    BIT_flushBits(bitC);
+}
+
+
+/* FSE_getMaxNbBits() :
+ * Approximate maximum cost of a symbol, in bits.
+ * Fractional get rounded up (i.e. a symbol with a normalized frequency of 3 gives the same result as a frequency of 2)
+ * note 1 : assume symbolValue is valid (<= maxSymbolValue)
+ * note 2 : if freq[symbolValue]==0, @return a fake cost of tableLog+1 bits */
+MEM_STATIC U32 FSE_getMaxNbBits(const void* symbolTTPtr, U32 symbolValue)
+{
+    const FSE_symbolCompressionTransform* symbolTT = (const FSE_symbolCompressionTransform*) symbolTTPtr;
+    return (symbolTT[symbolValue].deltaNbBits + ((1<<16)-1)) >> 16;
+}
+
+/* FSE_bitCost() :
+ * Approximate symbol cost, as fractional value, using fixed-point format (accuracyLog fractional bits)
+ * note 1 : assume symbolValue is valid (<= maxSymbolValue)
+ * note 2 : if freq[symbolValue]==0, @return a fake cost of tableLog+1 bits */
+MEM_STATIC U32 FSE_bitCost(const void* symbolTTPtr, U32 tableLog, U32 symbolValue, U32 accuracyLog)
+{
+    const FSE_symbolCompressionTransform* symbolTT = (const FSE_symbolCompressionTransform*) symbolTTPtr;
+    U32 const minNbBits = symbolTT[symbolValue].deltaNbBits >> 16;
+    U32 const threshold = (minNbBits+1) << 16;
+    assert(tableLog < 16);
+    assert(accuracyLog < 31-tableLog);  /* ensure enough room for renormalization double shift */
+    {   U32 const tableSize = 1 << tableLog;
+        U32 const deltaFromThreshold = threshold - (symbolTT[symbolValue].deltaNbBits + tableSize);
+        U32 const normalizedDeltaFromThreshold = (deltaFromThreshold << accuracyLog) >> tableLog;   /* linear interpolation (very approximate) */
+        U32 const bitMultiplier = 1 << accuracyLog;
+        assert(symbolTT[symbolValue].deltaNbBits + tableSize <= threshold);
+        assert(normalizedDeltaFromThreshold <= bitMultiplier);
+        return (minNbBits+1)*bitMultiplier - normalizedDeltaFromThreshold;
+    }
+}
+
+
+/* ======    Decompression    ====== */
+
+typedef struct {
+    U16 tableLog;
+    U16 fastMode;
+} FSE_DTableHeader;   /* sizeof U32 */
+
+typedef struct
+{
+    unsigned short newState;
+    unsigned char  symbol;
+    unsigned char  nbBits;
+} FSE_decode_t;   /* size == U32 */
+
+MEM_STATIC void FSE_initDState(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD, const FSE_DTable* dt)
+{
+    const void* ptr = dt;
+    const FSE_DTableHeader* const DTableH = (const FSE_DTableHeader*)ptr;
+    DStatePtr->state = BIT_readBits(bitD, DTableH->tableLog);
+    BIT_reloadDStream(bitD);
+    DStatePtr->table = dt + 1;
+}
+
+MEM_STATIC BYTE FSE_peekSymbol(const FSE_DState_t* DStatePtr)
+{
+    FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state];
+    return DInfo.symbol;
+}
+
+MEM_STATIC void FSE_updateState(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD)
+{
+    FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state];
+    U32 const nbBits = DInfo.nbBits;
+    size_t const lowBits = BIT_readBits(bitD, nbBits);
+    DStatePtr->state = DInfo.newState + lowBits;
+}
+
+MEM_STATIC BYTE FSE_decodeSymbol(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD)
+{
+    FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state];
+    U32 const nbBits = DInfo.nbBits;
+    BYTE const symbol = DInfo.symbol;
+    size_t const lowBits = BIT_readBits(bitD, nbBits);
+
+    DStatePtr->state = DInfo.newState + lowBits;
+    return symbol;
+}
+
+/*! FSE_decodeSymbolFast() :
+    unsafe, only works if no symbol has a probability > 50% */
+MEM_STATIC BYTE FSE_decodeSymbolFast(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD)
+{
+    FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state];
+    U32 const nbBits = DInfo.nbBits;
+    BYTE const symbol = DInfo.symbol;
+    size_t const lowBits = BIT_readBitsFast(bitD, nbBits);
+
+    DStatePtr->state = DInfo.newState + lowBits;
+    return symbol;
+}
+
+MEM_STATIC unsigned FSE_endOfDState(const FSE_DState_t* DStatePtr)
+{
+    return DStatePtr->state == 0;
+}
+
+
+
+#ifndef FSE_COMMONDEFS_ONLY
+
+/* **************************************************************
+*  Tuning parameters
+****************************************************************/
+/*!MEMORY_USAGE :
+*  Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
+*  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 */
+#ifndef FSE_MAX_MEMORY_USAGE
+#  define FSE_MAX_MEMORY_USAGE 14
+#endif
+#ifndef FSE_DEFAULT_MEMORY_USAGE
+#  define FSE_DEFAULT_MEMORY_USAGE 13
+#endif
+#if (FSE_DEFAULT_MEMORY_USAGE > FSE_MAX_MEMORY_USAGE)
+#  error "FSE_DEFAULT_MEMORY_USAGE must be <= FSE_MAX_MEMORY_USAGE"
+#endif
+
+/*!FSE_MAX_SYMBOL_VALUE :
+*  Maximum symbol value authorized.
+*  Required for proper stack allocation */
+#ifndef FSE_MAX_SYMBOL_VALUE
+#  define FSE_MAX_SYMBOL_VALUE 255
+#endif
+
+/* **************************************************************
+*  template functions type & suffix
+****************************************************************/
+#define FSE_FUNCTION_TYPE BYTE
+#define FSE_FUNCTION_EXTENSION
+#define FSE_DECODE_TYPE FSE_decode_t
+
+
+#endif   /* !FSE_COMMONDEFS_ONLY */
+
+
+/* ***************************************************************
+*  Constants
+*****************************************************************/
+#define FSE_MAX_TABLELOG  (FSE_MAX_MEMORY_USAGE-2)
+#define FSE_MAX_TABLESIZE (1U<<FSE_MAX_TABLELOG)
+#define FSE_MAXTABLESIZE_MASK (FSE_MAX_TABLESIZE-1)
+#define FSE_DEFAULT_TABLELOG (FSE_DEFAULT_MEMORY_USAGE-2)
+#define FSE_MIN_TABLELOG 5
+
+#define FSE_TABLELOG_ABSOLUTE_MAX 15
+#if FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX
+#  error "FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX is not supported"
+#endif
+
+#define FSE_TABLESTEP(tableSize) (((tableSize)>>1) + ((tableSize)>>3) + 3)
+
+} // namespace duckdb_zstd
+
+#endif /* FSE_STATIC_LINKING_ONLY */