extzstd 0.1.1 → 0.2

data/contrib/zstd/lib/compress/zstdmt_compress.h

@@ -1,10 +1,11 @@
-/**
+/*
  * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of this source tree. An additional grant
- * of patent rights can be found in the PATENTS file in the same directory.
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
  */
 
  #ifndef ZSTDMT_COMPRESS_H
@@ -15,31 +16,41 @@
  #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 : This is an internal API.
+ *        Some methods are still exposed (ZSTDLIB_API),
+ *        because it used to be the only way to invoke MT compression.
+ *        Now, it's recommended to use ZSTD_compress_generic() instead.
+ *        These methods will stop being exposed in a future version */
 
 /* ===   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   === */
 
 ZSTDLIB_API size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel);
-ZSTDLIB_API size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize);    /**< pledgedSrcSize is optional and can be zero == unknown */
+ZSTDLIB_API size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize);  /**< if srcSize is not known at reset time, use ZSTD_CONTENTSIZE_UNKNOWN. Note: for compatibility with older programs, 0 means the same as ZSTD_CONTENTSIZE_UNKNOWN, but it may change in the future, to mean "empty" */
 
 ZSTDLIB_API size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
 
@@ -49,26 +60,77 @@ ZSTDLIB_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);
 
 /* ===   Advanced functions and parameters  === */
 
-#ifndef ZSTDMT_SECTION_SIZE_MIN
-#  define ZSTDMT_SECTION_SIZE_MIN (1U << 20)   /* 1 MB - Minimum size of each compression job */
+#ifndef ZSTDMT_JOBSIZE_MIN
+#  define ZSTDMT_JOBSIZE_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 overlapLog);
+
+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 :
+/* ZSTDMT_parameter :
  * List of parameters that can be set using ZSTDMT_setMTCtxParameter() */
 typedef enum {
-    ZSTDMT_p_sectionSize,        /* size of input "section". Each section is compressed in parallel. 0 means default, which is dynamically determined within compression functions */
-    ZSTDMT_p_overlapSectionLog   /* Log of overlapped section; 0 == no overlap, 6(default) == use 1/8th of window, >=9 == use full window */
-} ZSDTMT_parameter;
+    ZSTDMT_p_jobSize,           /* Each job is compressed in parallel. By default, this value is dynamically determined depending on compression parameters. Can be set explicitly here. */
+    ZSTDMT_p_overlapSectionLog  /* Each job may reload a part of previous job to enhance compressionr ratio; 0 == no overlap, 6(default) == use 1/8th of window, >=9 == use full window */
+} ZSTDMT_parameter;
 
 /* ZSTDMT_setMTCtxParameter() :
  * allow setting individual parameters, one at a time, among a list of enums defined in ZSTDMT_parameter.
- * The function must be called typically after ZSTD_createCCtx().
+ * The function must be called typically after ZSTD_createCCtx() but __before ZSTDMT_init*() !__
  * Parameters not explicitly reset by ZSTDMT_init*() remain the same in consecutive compression sessions.
  * @return : 0, or an error code (which can be tested using ZSTD_isError()) */
-ZSTDLIB_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter, unsigned value);
+ZSTDLIB_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_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);
+
+
+/* ===   Private definitions; never ever use directly  === */
+
+size_t ZSTDMT_CCtxParam_setMTCtxParameter(ZSTD_CCtx_params* params, ZSTDMT_parameter parameter, unsigned value);
+
+/* ZSTDMT_CCtxParam_setNbThreads()
+ * Set nbThreads, and clamp it correctly,
+ * also reset jobSize and overlapLog */
+size_t ZSTDMT_CCtxParam_setNbThreads(ZSTD_CCtx_params* params, unsigned nbThreads);
+
+/* ZSTDMT_getNbThreads():
+ * @return nb threads currently active in mtctx.
+ * mtctx must be valid */
+size_t ZSTDMT_getNbThreads(const ZSTDMT_CCtx* mtctx);
+
+/*! ZSTDMT_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 ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
+                    const void* dict, size_t dictSize, ZSTD_dictMode_e dictMode,
+                    const ZSTD_CDict* cdict,
+                    ZSTD_CCtx_params params, unsigned long long pledgedSrcSize);
 
 
 #if defined (__cplusplus)

data/contrib/zstd/lib/decompress/huf_decompress.c

@@ -32,41 +32,31 @@
     - Public forum : https://groups.google.com/forum/#!forum/lz4c
 ****************************************************************** */
 
-/* **************************************************************
-*  Compiler specifics
-****************************************************************/
-#ifdef _MSC_VER    /* Visual Studio */
-#  define FORCE_INLINE static __forceinline
-#  pragma warning(disable : 4127)        /* disable: C4127: conditional expression is constant */
-#else
-#  if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */
-#    ifdef __GNUC__
-#      define FORCE_INLINE static inline __attribute__((always_inline))
-#    else
-#      define FORCE_INLINE static inline
-#    endif
-#  else
-#    define FORCE_INLINE static
-#  endif /* __STDC_VERSION__ */
-#endif
-
-
 /* **************************************************************
 *  Dependencies
 ****************************************************************/
 #include <string.h>     /* memcpy, memset */
 #include "bitstream.h"  /* BIT_* */
+#include "compiler.h"
 #include "fse.h"        /* header compression */
 #define HUF_STATIC_LINKING_ONLY
 #include "huf.h"
+#include "error_private.h"
 
 
 /* **************************************************************
 *  Error Management
 ****************************************************************/
+#define HUF_isError ERR_isError
 #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 +77,28 @@ 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 +137,13 @@ 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)
 {
@@ -155,7 +164,7 @@ static BYTE HUF_decodeSymbolX2(BIT_DStream_t* Dstream, const HUF_DEltX2* dt, con
     if (MEM_64bits()) \
         HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr)
 
-FORCE_INLINE size_t HUF_decodeStreamX2(BYTE* p, BIT_DStream_t* const bitDPtr, BYTE* const pEnd, const HUF_DEltX2* const dt, const U32 dtLog)
+HINT_INLINE size_t HUF_decodeStreamX2(BYTE* p, BIT_DStream_t* const bitDPtr, BYTE* const pEnd, const HUF_DEltX2* const dt, const U32 dtLog)
 {
     BYTE* const pStart = p;
 
@@ -212,11 +221,13 @@ 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 +235,15 @@ 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 +355,14 @@ 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 +370,13 @@ 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 +433,8 @@ 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 +478,43 @@ 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 +581,12 @@ 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 +605,8 @@ 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;
 }
@@ -562,7 +623,7 @@ static U32 HUF_decodeLastSymbolX4(void* op, BIT_DStream_t* DStream, const HUF_DE
     if (MEM_64bits()) \
         ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog)
 
-FORCE_INLINE size_t HUF_decodeStreamX4(BYTE* p, BIT_DStream_t* bitDPtr, BYTE* const pEnd, const HUF_DEltX4* const dt, const U32 dtLog)
+HINT_INLINE size_t HUF_decodeStreamX4(BYTE* p, BIT_DStream_t* bitDPtr, BYTE* const pEnd, const HUF_DEltX4* const dt, const U32 dtLog)
 {
     BYTE* const pStart = p;
 
@@ -626,11 +687,14 @@ 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 +702,15 @@ 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 +821,14 @@ 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 +836,15 @@ 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);
@@ -816,11 +901,11 @@ static const algo_time_t algoTime[16 /* Quantization */][3 /* single, double, qu
 *   Tells which decoder is likely to decode faster,
 *   based on a set of pre-determined metrics.
 *   @return : 0==HUF_decompress4X2, 1==HUF_decompress4X4 .
-*   Assumption : 0 < cSrcSize < dstSize <= 128 KB */
+*   Assumption : 0 < cSrcSize, dstSize <= 128 KB */
 U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize)
 {
     /* decoder timing evaluation */
-    U32 const Q = (U32)(cSrcSize * 16 / dstSize);   /* Q < 16 since dstSize > cSrcSize */
+    U32 const Q = cSrcSize >= dstSize ? 15 : (U32)(cSrcSize * 16 / dstSize);   /* Q < 16 */
     U32 const D256 = (U32)(dstSize >> 8);
     U32 const DTime0 = algoTime[Q][0].tableTime + (algoTime[Q][0].decode256Time * D256);
     U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256);
@@ -861,19 +946,32 @@ 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 */
+    if (cSrcSize == 0) return ERROR(corruption_detected);
 
     {   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 +980,17 @@ 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));
+}