zstd-ruby 1.2.0.0 → 1.3.0.0

data/ext/zstdruby/libzstd/compress/zstdmt_compress.h

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

data/ext/zstdruby/libzstd/decompress/huf_decompress.c

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

data/ext/zstdruby/libzstd/decompress/zstd_decompress.c

@@ -53,8 +53,7 @@
 #  include "zstd_legacy.h"
 #endif
 
-
-#if defined(_MSC_VER)
+#if defined(_MSC_VER) && !defined(_M_IA64)  /* _mm_prefetch() is not defined for ia64 */
 #  include <mmintrin.h>   /* https://msdn.microsoft.com/fr-fr/library/84szxsww(v=vs.90).aspx */
 #  define ZSTD_PREFETCH(ptr)   _mm_prefetch((const char*)ptr, _MM_HINT_T0)
 #elif defined(__GNUC__)
@@ -63,8 +62,9 @@
 #  define ZSTD_PREFETCH(ptr)   /* disabled */
 #endif
 
+
 /*-*************************************
-*  Macros
+*  Errors
 ***************************************/
 #define ZSTD_isError ERR_isError   /* for inlining */
 #define FSE_isError  ERR_isError
@@ -85,11 +85,15 @@ typedef enum { ZSTDds_getFrameHeaderSize, ZSTDds_decodeFrameHeader,
                ZSTDds_decompressLastBlock, ZSTDds_checkChecksum,
                ZSTDds_decodeSkippableHeader, ZSTDds_skipFrame } ZSTD_dStage;
 
+typedef enum { zdss_init=0, zdss_loadHeader,
+               zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage;
+
 typedef struct {
     FSE_DTable LLTable[FSE_DTABLE_SIZE_U32(LLFSELog)];
     FSE_DTable OFTable[FSE_DTABLE_SIZE_U32(OffFSELog)];
     FSE_DTable MLTable[FSE_DTABLE_SIZE_U32(MLFSELog)];
     HUF_DTable hufTable[HUF_DTABLE_SIZE(HufLog)];  /* can accommodate HUF_decompress4X */
+    U32 workspace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
     U32 rep[ZSTD_REP_NUM];
 } ZSTD_entropyTables_t;
 
@@ -105,7 +109,7 @@ struct ZSTD_DCtx_s
     const void* vBase;            /* virtual start of previous segment if it was just before current one */
     const void* dictEnd;          /* end of previous segment */
     size_t expected;
-    ZSTD_frameParams fParams;
+    ZSTD_frameHeader fParams;
     blockType_e bType;   /* used in ZSTD_decompressContinue(), to transfer blockType between header decoding and block decoding stages */
     ZSTD_dStage stage;
     U32 litEntropy;
@@ -117,11 +121,39 @@ struct ZSTD_DCtx_s
     ZSTD_customMem customMem;
     size_t litSize;
     size_t rleSize;
-    BYTE litBuffer[ZSTD_BLOCKSIZE_ABSOLUTEMAX + WILDCOPY_OVERLENGTH];
+    size_t staticSize;
+
+    /* streaming */
+    ZSTD_DDict* ddictLocal;
+    const ZSTD_DDict* ddict;
+    ZSTD_dStreamStage streamStage;
+    char*  inBuff;
+    size_t inBuffSize;
+    size_t inPos;
+    size_t maxWindowSize;
+    char*  outBuff;
+    size_t outBuffSize;
+    size_t outStart;
+    size_t outEnd;
+    size_t blockSize;
+    size_t lhSize;
+    void* legacyContext;
+    U32 previousLegacyVersion;
+    U32 legacyVersion;
+    U32 hostageByte;
+
+    /* workspace */
+    BYTE litBuffer[ZSTD_BLOCKSIZE_MAX + WILDCOPY_OVERLENGTH];
     BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX];
 };  /* typedef'd to ZSTD_DCtx within "zstd.h" */
 
-size_t ZSTD_sizeof_DCtx (const ZSTD_DCtx* dctx) { return (dctx==NULL) ? 0 : sizeof(ZSTD_DCtx); }
+size_t ZSTD_sizeof_DCtx (const ZSTD_DCtx* dctx)
+{
+    if (dctx==NULL) return 0;   /* support sizeof NULL */
+    return sizeof(*dctx)
+           + ZSTD_sizeof_DDict(dctx->ddictLocal)
+           + dctx->inBuffSize + dctx->outBuffSize;
+}
 
 size_t ZSTD_estimateDCtxSize(void) { return sizeof(ZSTD_DCtx); }
 
@@ -145,40 +177,76 @@ size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx)
     return 0;
 }
 
+static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx)
+{
+    ZSTD_decompressBegin(dctx);   /* cannot fail */
+    dctx->staticSize = 0;
+    dctx->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
+    dctx->ddict   = NULL;
+    dctx->ddictLocal = NULL;
+    dctx->inBuff  = NULL;
+    dctx->inBuffSize = 0;
+    dctx->outBuffSize= 0;
+    dctx->streamStage = zdss_init;
+}
+
 ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem)
 {
-    ZSTD_DCtx* dctx;
+    if (!customMem.customAlloc ^ !customMem.customFree) return NULL;
 
-    if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
-    if (!customMem.customAlloc || !customMem.customFree) return NULL;
+    {   ZSTD_DCtx* const dctx = (ZSTD_DCtx*)ZSTD_malloc(sizeof(*dctx), customMem);
+        if (!dctx) return NULL;
+        dctx->customMem = customMem;
+        dctx->legacyContext = NULL;
+        dctx->previousLegacyVersion = 0;
+        ZSTD_initDCtx_internal(dctx);
+        return dctx;
+    }
+}
 
-    dctx = (ZSTD_DCtx*)ZSTD_malloc(sizeof(ZSTD_DCtx), customMem);
-    if (!dctx) return NULL;
-    memcpy(&dctx->customMem, &customMem, sizeof(customMem));
-    ZSTD_decompressBegin(dctx);
+ZSTD_DCtx* ZSTD_initStaticDCtx(void *workspace, size_t workspaceSize)
+{
+    ZSTD_DCtx* dctx = (ZSTD_DCtx*) workspace;
+
+    if ((size_t)workspace & 7) return NULL;  /* 8-aligned */
+    if (workspaceSize < sizeof(ZSTD_DCtx)) return NULL;  /* minimum size */
+
+    ZSTD_initDCtx_internal(dctx);
+    dctx->staticSize = workspaceSize;
+    dctx->inBuff = (char*)(dctx+1);
     return dctx;
 }
 
 ZSTD_DCtx* ZSTD_createDCtx(void)
 {
-    return ZSTD_createDCtx_advanced(defaultCustomMem);
+    return ZSTD_createDCtx_advanced(ZSTD_defaultCMem);
 }
 
 size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx)
 {
     if (dctx==NULL) return 0;   /* support free on NULL */
-    ZSTD_free(dctx, dctx->customMem);
-    return 0;   /* reserved as a potential error code in the future */
+    if (dctx->staticSize) return ERROR(memory_allocation);   /* not compatible with static DCtx */
+    {   ZSTD_customMem const cMem = dctx->customMem;
+        ZSTD_freeDDict(dctx->ddictLocal);
+        dctx->ddictLocal = NULL;
+        ZSTD_free(dctx->inBuff, cMem);
+        dctx->inBuff = NULL;
+#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
+        if (dctx->legacyContext)
+            ZSTD_freeLegacyStreamContext(dctx->legacyContext, dctx->previousLegacyVersion);
+#endif
+        ZSTD_free(dctx, cMem);
+        return 0;
+    }
 }
 
+/* no longer useful */
 void ZSTD_copyDCtx(ZSTD_DCtx* dstDCtx, const ZSTD_DCtx* srcDCtx)
 {
-    size_t const workSpaceSize = (ZSTD_BLOCKSIZE_ABSOLUTEMAX+WILDCOPY_OVERLENGTH) + ZSTD_frameHeaderSize_max;
-    memcpy(dstDCtx, srcDCtx, sizeof(ZSTD_DCtx) - workSpaceSize);  /* no need to copy workspace */
+    size_t const toCopy = (size_t)((char*)(&dstDCtx->inBuff) - (char*)dstDCtx);
+    memcpy(dstDCtx, srcDCtx, toCopy);  /* no need to copy workspace */
 }
 
-static void ZSTD_refDDict(ZSTD_DCtx* dstDCtx, const ZSTD_DDict* ddict);
-
 
 /*-*************************************************************
 *   Decompression section
@@ -206,7 +274,7 @@ unsigned ZSTD_isFrame(const void* buffer, size_t size)
 /** ZSTD_frameHeaderSize() :
 *   srcSize must be >= ZSTD_frameHeaderSize_prefix.
 *   @return : size of the Frame Header */
-static size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize)
+size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize)
 {
     if (srcSize < ZSTD_frameHeaderSize_prefix) return ERROR(srcSize_wrong);
     {   BYTE const fhd = ((const BYTE*)src)[4];
@@ -219,22 +287,24 @@ static size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize)
 }
 
 
-/** ZSTD_getFrameParams() :
+/** ZSTD_getFrameHeader() :
 *   decode Frame Header, or require larger `srcSize`.
-*   @return : 0, `fparamsPtr` is correctly filled,
+*   @return : 0, `zfhPtr` is correctly filled,
 *            >0, `srcSize` is too small, result is expected `srcSize`,
 *             or an error code, which can be tested using ZSTD_isError() */
-size_t ZSTD_getFrameParams(ZSTD_frameParams* fparamsPtr, const void* src, size_t srcSize)
+size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize)
 {
     const BYTE* ip = (const BYTE*)src;
-
     if (srcSize < ZSTD_frameHeaderSize_prefix) return ZSTD_frameHeaderSize_prefix;
+
     if (MEM_readLE32(src) != ZSTD_MAGICNUMBER) {
         if ((MEM_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
-            if (srcSize < ZSTD_skippableHeaderSize) return ZSTD_skippableHeaderSize; /* magic number + skippable frame length */
-            memset(fparamsPtr, 0, sizeof(*fparamsPtr));
-            fparamsPtr->frameContentSize = MEM_readLE32((const char *)src + 4);
-            fparamsPtr->windowSize = 0; /* windowSize==0 means a frame is skippable */
+            /* skippable frame */
+            if (srcSize < ZSTD_skippableHeaderSize)
+                return ZSTD_skippableHeaderSize; /* magic number + frame length */
+            memset(zfhPtr, 0, sizeof(*zfhPtr));
+            zfhPtr->frameContentSize = MEM_readLE32((const char *)src + 4);
+            zfhPtr->windowSize = 0; /* windowSize==0 means a frame is skippable */
             return 0;
         }
         return ERROR(prefix_unknown);
@@ -254,11 +324,13 @@ size_t ZSTD_getFrameParams(ZSTD_frameParams* fparamsPtr, const void* src, size_t
         U32 windowSize = 0;
         U32 dictID = 0;
         U64 frameContentSize = 0;
-        if ((fhdByte & 0x08) != 0) return ERROR(frameParameter_unsupported);   /* reserved bits, which must be zero */
+        if ((fhdByte & 0x08) != 0)
+            return ERROR(frameParameter_unsupported);   /* reserved bits, must be zero */
         if (!singleSegment) {
             BYTE const wlByte = ip[pos++];
             U32 const windowLog = (wlByte >> 3) + ZSTD_WINDOWLOG_ABSOLUTEMIN;
-            if (windowLog > ZSTD_WINDOWLOG_MAX) return ERROR(frameParameter_windowTooLarge);  /* avoids issue with 1 << windowLog */
+            if (windowLog > ZSTD_WINDOWLOG_MAX)
+                return ERROR(frameParameter_windowTooLarge);
             windowSize = (1U << windowLog);
             windowSize += (windowSize >> 3) * (wlByte&7);
         }
@@ -281,10 +353,10 @@ size_t ZSTD_getFrameParams(ZSTD_frameParams* fparamsPtr, const void* src, size_t
         }
         if (!windowSize) windowSize = (U32)frameContentSize;
         if (windowSize > windowSizeMax) return ERROR(frameParameter_windowTooLarge);
-        fparamsPtr->frameContentSize = frameContentSize;
-        fparamsPtr->windowSize = windowSize;
-        fparamsPtr->dictID = dictID;
-        fparamsPtr->checksumFlag = checksumFlag;
+        zfhPtr->frameContentSize = frameContentSize;
+        zfhPtr->windowSize = windowSize;
+        zfhPtr->dictID = dictID;
+        zfhPtr->checksumFlag = checksumFlag;
     }
     return 0;
 }
@@ -302,9 +374,8 @@ unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize)
         return ret == 0 ? ZSTD_CONTENTSIZE_UNKNOWN : ret;
     }
 #endif
-    {
-        ZSTD_frameParams fParams;
-        if (ZSTD_getFrameParams(&fParams, src, srcSize) != 0) return ZSTD_CONTENTSIZE_ERROR;
+    {   ZSTD_frameHeader fParams;
+        if (ZSTD_getFrameHeader(&fParams, src, srcSize) != 0) return ZSTD_CONTENTSIZE_ERROR;
         if (fParams.windowSize == 0) {
             /* Either skippable or empty frame, size == 0 either way */
             return 0;
@@ -323,51 +394,48 @@ unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize)
  *  @return : decompressed size of the frames contained */
 unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize)
 {
-    {
-        unsigned long long totalDstSize = 0;
-        while (srcSize >= ZSTD_frameHeaderSize_prefix) {
-            const U32 magicNumber = MEM_readLE32(src);
+    unsigned long long totalDstSize = 0;
 
-            if ((magicNumber & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
-                size_t skippableSize;
-                if (srcSize < ZSTD_skippableHeaderSize)
-                    return ERROR(srcSize_wrong);
-                skippableSize = MEM_readLE32((const BYTE *)src + 4) +
-                                ZSTD_skippableHeaderSize;
-                if (srcSize < skippableSize) {
-                    return ZSTD_CONTENTSIZE_ERROR;
-                }
-
-                src = (const BYTE *)src + skippableSize;
-                srcSize -= skippableSize;
-                continue;
+    while (srcSize >= ZSTD_frameHeaderSize_prefix) {
+        const U32 magicNumber = MEM_readLE32(src);
+
+        if ((magicNumber & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
+            size_t skippableSize;
+            if (srcSize < ZSTD_skippableHeaderSize)
+                return ERROR(srcSize_wrong);
+            skippableSize = MEM_readLE32((const BYTE *)src + 4) +
+                            ZSTD_skippableHeaderSize;
+            if (srcSize < skippableSize) {
+                return ZSTD_CONTENTSIZE_ERROR;
             }
 
-            {
-                unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize);
-                if (ret >= ZSTD_CONTENTSIZE_ERROR) return ret;
+            src = (const BYTE *)src + skippableSize;
+            srcSize -= skippableSize;
+            continue;
+        }
 
-                /* check for overflow */
-                if (totalDstSize + ret < totalDstSize) return ZSTD_CONTENTSIZE_ERROR;
-                totalDstSize += ret;
-            }
-            {
-                size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize);
-                if (ZSTD_isError(frameSrcSize)) {
-                    return ZSTD_CONTENTSIZE_ERROR;
-                }
+        {   unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize);
+            if (ret >= ZSTD_CONTENTSIZE_ERROR) return ret;
 
-                src = (const BYTE *)src + frameSrcSize;
-                srcSize -= frameSrcSize;
-            }
+            /* check for overflow */
+            if (totalDstSize + ret < totalDstSize) return ZSTD_CONTENTSIZE_ERROR;
+            totalDstSize += ret;
         }
+        {   size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize);
+            if (ZSTD_isError(frameSrcSize)) {
+                return ZSTD_CONTENTSIZE_ERROR;
+            }
 
-        if (srcSize) {
-            return ZSTD_CONTENTSIZE_ERROR;
+            src = (const BYTE *)src + frameSrcSize;
+            srcSize -= frameSrcSize;
         }
+    }
 
-        return totalDstSize;
+    if (srcSize) {
+        return ZSTD_CONTENTSIZE_ERROR;
     }
+
+    return totalDstSize;
 }
 
 /** ZSTD_getDecompressedSize() :
@@ -389,7 +457,7 @@ unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize)
 *   @return : 0 if success, or an error code, which can be tested using ZSTD_isError() */
 static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t headerSize)
 {
-    size_t const result = ZSTD_getFrameParams(&(dctx->fParams), src, headerSize);
+    size_t const result = ZSTD_getFrameHeader(&(dctx->fParams), src, headerSize);
     if (ZSTD_isError(result)) return result;  /* invalid header */
     if (result>0) return ERROR(srcSize_wrong);   /* headerSize too small */
     if (dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID)) return ERROR(dictionary_wrong);
@@ -485,7 +553,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                     litCSize = (lhc >> 22) + (istart[4] << 10);
                     break;
                 }
-                if (litSize > ZSTD_BLOCKSIZE_ABSOLUTEMAX) return ERROR(corruption_detected);
+                if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected);
                 if (litCSize + lhSize > srcSize) return ERROR(corruption_detected);
 
                 if (HUF_isError((litEncType==set_repeat) ?
@@ -493,8 +561,10 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                                         HUF_decompress1X_usingDTable(dctx->litBuffer, litSize, istart+lhSize, litCSize, dctx->HUFptr) :
                                         HUF_decompress4X_usingDTable(dctx->litBuffer, litSize, istart+lhSize, litCSize, dctx->HUFptr) ) :
                                     ( singleStream ?
-                                        HUF_decompress1X2_DCtx(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart+lhSize, litCSize) :
-                                        HUF_decompress4X_hufOnly (dctx->entropy.hufTable, dctx->litBuffer, litSize, istart+lhSize, litCSize)) ))
+                                        HUF_decompress1X2_DCtx_wksp(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart+lhSize, litCSize,
+                                                                    dctx->entropy.workspace, sizeof(dctx->entropy.workspace)) :
+                                        HUF_decompress4X_hufOnly_wksp(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart+lhSize, litCSize,
+                                                                      dctx->entropy.workspace, sizeof(dctx->entropy.workspace)))))
                     return ERROR(corruption_detected);
 
                 dctx->litPtr = dctx->litBuffer;
@@ -557,7 +627,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                     if (srcSize<4) return ERROR(corruption_detected);   /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4 */
                     break;
                 }
-                if (litSize > ZSTD_BLOCKSIZE_ABSOLUTEMAX) return ERROR(corruption_detected);
+                if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected);
                 memset(dctx->litBuffer, istart[lhSize], litSize + WILDCOPY_OVERLENGTH);
                 dctx->litPtr = dctx->litBuffer;
                 dctx->litSize = litSize;
@@ -684,6 +754,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
     const BYTE* const istart = (const BYTE* const)src;
     const BYTE* const iend = istart + srcSize;
     const BYTE* ip = istart;
+    DEBUGLOG(5, "ZSTD_decodeSeqHeaders");
 
     /* check */
     if (srcSize < MIN_SEQUENCES_SIZE) return ERROR(srcSize_wrong);
@@ -864,12 +935,18 @@ static seq_t ZSTD_decodeSequence(seqState_t* seqState)
         seq.offset = offset;
     }
 
-    seq.matchLength = ML_base[mlCode] + ((mlCode>31) ? BIT_readBitsFast(&seqState->DStream, mlBits) : 0);  /* <=  16 bits */
+    seq.matchLength = ML_base[mlCode]
+                    + ((mlCode>31) ? BIT_readBitsFast(&seqState->DStream, mlBits) : 0);  /* <=  16 bits */
     if (MEM_32bits() && (mlBits+llBits>24)) BIT_reloadDStream(&seqState->DStream);
 
-    seq.litLength = LL_base[llCode] + ((llCode>15) ? BIT_readBitsFast(&seqState->DStream, llBits) : 0);    /* <=  16 bits */
-    if (MEM_32bits() ||
-       (totalBits > 64 - 7 - (LLFSELog+MLFSELog+OffFSELog)) ) BIT_reloadDStream(&seqState->DStream);
+    seq.litLength = LL_base[llCode]
+                  + ((llCode>15) ? BIT_readBitsFast(&seqState->DStream, llBits) : 0);    /* <=  16 bits */
+    if (  MEM_32bits()
+      || (totalBits > 64 - 7 - (LLFSELog+MLFSELog+OffFSELog)) )
+       BIT_reloadDStream(&seqState->DStream);
+
+    DEBUGLOG(6, "seq: litL=%u, matchL=%u, offset=%u",
+                (U32)seq.litLength, (U32)seq.matchLength, (U32)seq.offset);
 
     /* ANS state update */
     FSE_updateState(&seqState->stateLL, &seqState->DStream);    /* <=  9 bits */
@@ -909,7 +986,8 @@ size_t ZSTD_execSequence(BYTE* op,
     /* copy Match */
     if (sequence.offset > (size_t)(oLitEnd - base)) {
         /* offset beyond prefix -> go into extDict */
-        if (sequence.offset > (size_t)(oLitEnd - vBase)) return ERROR(corruption_detected);
+        if (sequence.offset > (size_t)(oLitEnd - vBase))
+            return ERROR(corruption_detected);
         match = dictEnd + (match - base);
         if (match + sequence.matchLength <= dictEnd) {
             memmove(oLitEnd, match, sequence.matchLength);
@@ -977,9 +1055,12 @@ static size_t ZSTD_decompressSequences(
     const BYTE* const vBase = (const BYTE*) (dctx->vBase);
     const BYTE* const dictEnd = (const BYTE*) (dctx->dictEnd);
     int nbSeq;
+    DEBUGLOG(5, "ZSTD_decompressSequences");
 
     /* Build Decoding Tables */
     {   size_t const seqHSize = ZSTD_decodeSeqHeaders(dctx, &nbSeq, ip, seqSize);
+        DEBUGLOG(5, "ZSTD_decodeSeqHeaders: size=%u, nbSeq=%i",
+                    (U32)seqHSize, nbSeq);
         if (ZSTD_isError(seqHSize)) return seqHSize;
         ip += seqHSize;
     }
@@ -998,11 +1079,13 @@ static size_t ZSTD_decompressSequences(
             nbSeq--;
             {   seq_t const sequence = ZSTD_decodeSequence(&seqState);
                 size_t const oneSeqSize = ZSTD_execSequence(op, oend, sequence, &litPtr, litEnd, base, vBase, dictEnd);
+                DEBUGLOG(6, "regenerated sequence size : %u", (U32)oneSeqSize);
                 if (ZSTD_isError(oneSeqSize)) return oneSeqSize;
                 op += oneSeqSize;
         }   }
 
         /* check if reached exact end */
+        DEBUGLOG(5, "after decode loop, remaining nbSeq : %i", nbSeq);
         if (nbSeq) return ERROR(corruption_detected);
         /* save reps for next block */
         { U32 i; for (i=0; i<ZSTD_REP_NUM; i++) dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]); }
@@ -1216,7 +1299,7 @@ static size_t ZSTD_decompressSequencesLong(
     const BYTE* const base = (const BYTE*) (dctx->base);
     const BYTE* const vBase = (const BYTE*) (dctx->vBase);
     const BYTE* const dictEnd = (const BYTE*) (dctx->dictEnd);
-    unsigned const windowSize = dctx->fParams.windowSize;
+    unsigned const windowSize32 = (unsigned)dctx->fParams.windowSize;
     int nbSeq;
 
     /* Build Decoding Tables */
@@ -1246,13 +1329,13 @@ static size_t ZSTD_decompressSequencesLong(
 
         /* prepare in advance */
         for (seqNb=0; (BIT_reloadDStream(&seqState.DStream) <= BIT_DStream_completed) && seqNb<seqAdvance; seqNb++) {
-            sequences[seqNb] = ZSTD_decodeSequenceLong(&seqState, windowSize);
+            sequences[seqNb] = ZSTD_decodeSequenceLong(&seqState, windowSize32);
         }
         if (seqNb<seqAdvance) return ERROR(corruption_detected);
 
         /* decode and decompress */
         for ( ; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && seqNb<nbSeq ; seqNb++) {
-            seq_t const sequence = ZSTD_decodeSequenceLong(&seqState, windowSize);
+            seq_t const sequence = ZSTD_decodeSequenceLong(&seqState, windowSize32);
             size_t const oneSeqSize = ZSTD_execSequenceLong(op, oend, sequences[(seqNb-ADVANCED_SEQS) & STOSEQ_MASK], &litPtr, litEnd, base, vBase, dictEnd);
             if (ZSTD_isError(oneSeqSize)) return oneSeqSize;
             ZSTD_PREFETCH(sequence.match);
@@ -1289,11 +1372,13 @@ static size_t ZSTD_decompressBlock_internal(ZSTD_DCtx* dctx,
                       const void* src, size_t srcSize)
 {   /* blockType == blockCompressed */
     const BYTE* ip = (const BYTE*)src;
+    DEBUGLOG(5, "ZSTD_decompressBlock_internal");
 
-    if (srcSize >= ZSTD_BLOCKSIZE_ABSOLUTEMAX) return ERROR(srcSize_wrong);
+    if (srcSize >= ZSTD_BLOCKSIZE_MAX) return ERROR(srcSize_wrong);
 
     /* Decode literals section */
     {   size_t const litCSize = ZSTD_decodeLiteralsBlock(dctx, src, srcSize);
+        DEBUGLOG(5, "ZSTD_decodeLiteralsBlock : %u", (U32)litCSize);
         if (ZSTD_isError(litCSize)) return litCSize;
         ip += litCSize;
         srcSize -= litCSize;
@@ -1364,13 +1449,13 @@ size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize)
         const BYTE* ip = (const BYTE*)src;
         const BYTE* const ipstart = ip;
         size_t remainingSize = srcSize;
-        ZSTD_frameParams fParams;
+        ZSTD_frameHeader fParams;
 
         size_t const headerSize = ZSTD_frameHeaderSize(ip, remainingSize);
         if (ZSTD_isError(headerSize)) return headerSize;
 
         /* Frame Header */
-        {   size_t const ret = ZSTD_getFrameParams(&fParams, ip, remainingSize);
+        {   size_t const ret = ZSTD_getFrameHeader(&fParams, ip, remainingSize);
             if (ZSTD_isError(ret)) return ret;
             if (ret > 0) return ERROR(srcSize_wrong);
         }
@@ -1505,6 +1590,8 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
             size_t decodedSize;
             size_t const frameSize = ZSTD_findFrameCompressedSizeLegacy(src, srcSize);
             if (ZSTD_isError(frameSize)) return frameSize;
+            /* legacy support is incompatible with static dctx */
+            if (dctx->staticSize) return ERROR(memory_allocation);
 
             decodedSize = ZSTD_decompressLegacy(dst, dstCapacity, src, frameSize, dict, dictSize);
 
@@ -1540,7 +1627,7 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
 
         if (ddict) {
             /* we were called from ZSTD_decompress_usingDDict */
-            ZSTD_refDDict(dctx, ddict);
+            CHECK_F(ZSTD_decompressBegin_usingDDict(dctx, ddict));
         } else {
             /* this will initialize correctly with no dict if dict == NULL, so
              * use this in all cases but ddict */
@@ -1580,7 +1667,7 @@ size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const
 
 size_t ZSTD_decompress(void* dst, size_t dstCapacity, const void* src, size_t srcSize)
 {
-#if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE==1)
+#if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE>=1)
     size_t regenSize;
     ZSTD_DCtx* const dctx = ZSTD_createDCtx();
     if (dctx==NULL) return ERROR(memory_allocation);
@@ -1604,6 +1691,7 @@ ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx) {
     switch(dctx->stage)
     {
     default:   /* should not happen */
+        assert(0);
     case ZSTDds_getFrameHeaderSize:
     case ZSTDds_decodeFrameHeader:
         return ZSTDnit_frameHeader;
@@ -1621,21 +1709,24 @@ ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx) {
     }
 }
 
-int ZSTD_isSkipFrame(ZSTD_DCtx* dctx) { return dctx->stage == ZSTDds_skipFrame; }   /* for zbuff */
+static int ZSTD_isSkipFrame(ZSTD_DCtx* dctx) { return dctx->stage == ZSTDds_skipFrame; }
 
 /** ZSTD_decompressContinue() :
-*   @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity)
-*             or an error code, which can be tested using ZSTD_isError() */
+ *  srcSize : must be the exact nb of bytes expected (see ZSTD_nextSrcSizeToDecompress())
+ *  @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity)
+ *            or an error code, which can be tested using ZSTD_isError() */
 size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
 {
+    DEBUGLOG(5, "ZSTD_decompressContinue");
     /* Sanity check */
-    if (srcSize != dctx->expected) return ERROR(srcSize_wrong);
+    if (srcSize != dctx->expected) return ERROR(srcSize_wrong);   /* unauthorized */
     if (dstCapacity) ZSTD_checkContinuity(dctx, dst);
 
     switch (dctx->stage)
     {
     case ZSTDds_getFrameHeaderSize :
-        if (srcSize != ZSTD_frameHeaderSize_prefix) return ERROR(srcSize_wrong);      /* impossible */
+        if (srcSize != ZSTD_frameHeaderSize_prefix) return ERROR(srcSize_wrong);      /* unauthorized */
+        assert(src != NULL);
         if ((MEM_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {        /* skippable frame */
             memcpy(dctx->headerBuffer, src, ZSTD_frameHeaderSize_prefix);
             dctx->expected = ZSTD_skippableHeaderSize - ZSTD_frameHeaderSize_prefix;  /* magic number + skippable frame length */
@@ -1653,6 +1744,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
         dctx->expected = 0;   /* not necessary to copy more */
 
     case ZSTDds_decodeFrameHeader:
+        assert(src != NULL);
         memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected);
         CHECK_F(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize));
         dctx->expected = ZSTD_blockHeaderSize;
@@ -1680,17 +1772,19 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
                     dctx->stage = ZSTDds_getFrameHeaderSize;
                 }
             } else {
-                dctx->expected = 3;  /* go directly to next header */
+                dctx->expected = ZSTD_blockHeaderSize;  /* jump to next header */
                 dctx->stage = ZSTDds_decodeBlockHeader;
             }
             return 0;
         }
     case ZSTDds_decompressLastBlock:
     case ZSTDds_decompressBlock:
+        DEBUGLOG(5, "case ZSTDds_decompressBlock");
         {   size_t rSize;
             switch(dctx->bType)
             {
             case bt_compressed:
+                DEBUGLOG(5, "case bt_compressed");
                 rSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize);
                 break;
             case bt_raw :
@@ -1730,7 +1824,8 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
             return 0;
         }
     case ZSTDds_decodeSkippableHeader:
-        {   memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected);
+        {   assert(src != NULL);
+            memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected);
             dctx->expected = MEM_readLE32(dctx->headerBuffer + 4);
             dctx->stage = ZSTDds_skipFrame;
             return 0;
@@ -1767,7 +1862,9 @@ static size_t ZSTD_loadEntropy(ZSTD_entropyTables_t* entropy, const void* const
     dictPtr += 8;   /* skip header = magic + dictID */
 
 
-    {   size_t const hSize = HUF_readDTableX4(entropy->hufTable, dictPtr, dictEnd-dictPtr);
+    {   size_t const hSize = HUF_readDTableX4_wksp(
+            entropy->hufTable, dictPtr, dictEnd - dictPtr,
+            entropy->workspace, sizeof(entropy->workspace));
         if (HUF_isError(hSize)) return ERROR(dictionary_corrupted);
         dictPtr += hSize;
     }
@@ -1815,7 +1912,7 @@ static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx* dctx, const void* dict
 {
     if (dictSize < 8) return ZSTD_refDictContent(dctx, dict, dictSize);
     {   U32 const magic = MEM_readLE32(dict);
-        if (magic != ZSTD_DICT_MAGIC) {
+        if (magic != ZSTD_MAGIC_DICTIONARY) {
             return ZSTD_refDictContent(dctx, dict, dictSize);   /* pure content mode */
     }   }
     dctx->dictID = MEM_readLE32((const char*)dict + 4);
@@ -1862,10 +1959,10 @@ static size_t ZSTD_DDictDictSize(const ZSTD_DDict* ddict)
     return ddict->dictSize;
 }
 
-static void ZSTD_refDDict(ZSTD_DCtx* dstDCtx, const ZSTD_DDict* ddict)
+size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dstDCtx, const ZSTD_DDict* ddict)
 {
-    ZSTD_decompressBegin(dstDCtx);  /* init */
-    if (ddict) {   /* support refDDict on NULL */
+    CHECK_F(ZSTD_decompressBegin(dstDCtx));
+    if (ddict) {   /* support begin on NULL */
         dstDCtx->dictID = ddict->dictID;
         dstDCtx->base = ddict->dictContent;
         dstDCtx->vBase = ddict->dictContent;
@@ -1886,6 +1983,7 @@ static void ZSTD_refDDict(ZSTD_DCtx* dstDCtx, const ZSTD_DDict* ddict)
             dstDCtx->fseEntropy = 0;
         }
     }
+    return 0;
 }
 
 static size_t ZSTD_loadEntropy_inDDict(ZSTD_DDict* ddict)
@@ -1894,7 +1992,7 @@ static size_t ZSTD_loadEntropy_inDDict(ZSTD_DDict* ddict)
     ddict->entropyPresent = 0;
     if (ddict->dictSize < 8) return 0;
     {   U32 const magic = MEM_readLE32(ddict->dictContent);
-        if (magic != ZSTD_DICT_MAGIC) return 0;   /* pure content mode */
+        if (magic != ZSTD_MAGIC_DICTIONARY) return 0;   /* pure content mode */
     }
     ddict->dictID = MEM_readLE32((const char*)ddict->dictContent + 4);
 
@@ -1905,33 +2003,39 @@ static size_t ZSTD_loadEntropy_inDDict(ZSTD_DDict* ddict)
 }
 
 
+static size_t ZSTD_initDDict_internal(ZSTD_DDict* ddict, const void* dict, size_t dictSize, unsigned byReference)
+{
+    if ((byReference) || (!dict) || (!dictSize)) {
+        ddict->dictBuffer = NULL;
+        ddict->dictContent = dict;
+    } else {
+        void* const internalBuffer = ZSTD_malloc(dictSize, ddict->cMem);
+        ddict->dictBuffer = internalBuffer;
+        ddict->dictContent = internalBuffer;
+        if (!internalBuffer) return ERROR(memory_allocation);
+        memcpy(internalBuffer, dict, dictSize);
+    }
+    ddict->dictSize = dictSize;
+    ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001);  /* cover both little and big endian */
+
+    /* parse dictionary content */
+    CHECK_F( ZSTD_loadEntropy_inDDict(ddict) );
+
+    return 0;
+}
+
 ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize, unsigned byReference, ZSTD_customMem customMem)
 {
-    if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
-    if (!customMem.customAlloc || !customMem.customFree) return NULL;
+    if (!customMem.customAlloc ^ !customMem.customFree) return NULL;
 
     {   ZSTD_DDict* const ddict = (ZSTD_DDict*) ZSTD_malloc(sizeof(ZSTD_DDict), customMem);
         if (!ddict) return NULL;
         ddict->cMem = customMem;
 
-        if ((byReference) || (!dict) || (!dictSize)) {
-            ddict->dictBuffer = NULL;
-            ddict->dictContent = dict;
-        } else {
-            void* const internalBuffer = ZSTD_malloc(dictSize, customMem);
-            if (!internalBuffer) { ZSTD_freeDDict(ddict); return NULL; }
-            memcpy(internalBuffer, dict, dictSize);
-            ddict->dictBuffer = internalBuffer;
-            ddict->dictContent = internalBuffer;
+        if (ZSTD_isError( ZSTD_initDDict_internal(ddict, dict, dictSize, byReference) )) {
+            ZSTD_freeDDict(ddict);
+            return NULL;
         }
-        ddict->dictSize = dictSize;
-        ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001);  /* cover both little and big endian */
-        /* parse dictionary content */
-        {   size_t const errorCode = ZSTD_loadEntropy_inDDict(ddict);
-            if (ZSTD_isError(errorCode)) {
-                ZSTD_freeDDict(ddict);
-                return NULL;
-        }   }
 
         return ddict;
     }
@@ -1947,7 +2051,6 @@ ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize)
     return ZSTD_createDDict_advanced(dict, dictSize, 0, allocator);
 }
 
-
 /*! ZSTD_createDDict_byReference() :
  *  Create a digested dictionary, to start decompression without startup delay.
  *  Dictionary content is simply referenced, it will be accessed during decompression.
@@ -1959,6 +2062,26 @@ ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize
 }
 
 
+ZSTD_DDict* ZSTD_initStaticDDict(void* workspace, size_t workspaceSize,
+                                 const void* dict, size_t dictSize,
+                                 unsigned byReference)
+{
+    size_t const neededSpace = sizeof(ZSTD_DDict) + (byReference ? 0 : dictSize);
+    ZSTD_DDict* const ddict = (ZSTD_DDict*)workspace;
+    assert(workspace != NULL);
+    assert(dict != NULL);
+    if ((size_t)workspace & 7) return NULL;  /* 8-aligned */
+    if (workspaceSize < neededSpace) return NULL;
+    if (!byReference) {
+        memcpy(ddict+1, dict, dictSize);  /* local copy */
+        dict = ddict+1;
+    }
+    if (ZSTD_isError( ZSTD_initDDict_internal(ddict, dict, dictSize, 1 /* byRef */) ))
+        return NULL;
+    return ddict;
+}
+
+
 size_t ZSTD_freeDDict(ZSTD_DDict* ddict)
 {
     if (ddict==NULL) return 0;   /* support free on NULL */
@@ -1969,6 +2092,14 @@ size_t ZSTD_freeDDict(ZSTD_DDict* ddict)
     }
 }
 
+/*! ZSTD_estimateDDictSize() :
+ *  Estimate amount of memory that will be needed to create a dictionary for decompression.
+ *  Note : dictionary created "byReference" are smaller */
+size_t ZSTD_estimateDDictSize(size_t dictSize, unsigned byReference)
+{
+    return sizeof(ZSTD_DDict) + (byReference ? 0 : dictSize);
+}
+
 size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict)
 {
     if (ddict==NULL) return 0;   /* support sizeof on NULL */
@@ -1982,7 +2113,7 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict)
 unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize)
 {
     if (dictSize < 8) return 0;
-    if (MEM_readLE32(dict) != ZSTD_DICT_MAGIC) return 0;
+    if (MEM_readLE32(dict) != ZSTD_MAGIC_DICTIONARY) return 0;
     return MEM_readLE32((const char*)dict + 4);
 }
 
@@ -2008,11 +2139,11 @@ unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict)
  *    Note : possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`.
  *  - This is not a Zstandard frame.
  *  When identifying the exact failure cause, it's possible to use
- *  ZSTD_getFrameParams(), which will provide a more precise error code. */
+ *  ZSTD_getFrameHeader(), which will provide a more precise error code. */
 unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize)
 {
-    ZSTD_frameParams zfp = { 0 , 0 , 0 , 0 };
-    size_t const hError = ZSTD_getFrameParams(&zfp, src, srcSize);
+    ZSTD_frameHeader zfp = { 0 , 0 , 0 , 0 };
+    size_t const hError = ZSTD_getFrameHeader(&zfp, src, srcSize);
     if (ZSTD_isError(hError)) return 0;
     return zfp.dictID;
 }
@@ -2037,88 +2168,35 @@ size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
 *   Streaming decompression
 *====================================*/
 
-typedef enum { zdss_init, zdss_loadHeader,
-               zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage;
-
-/* *** Resource management *** */
-struct ZSTD_DStream_s {
-    ZSTD_DCtx* dctx;
-    ZSTD_DDict* ddictLocal;
-    const ZSTD_DDict* ddict;
-    ZSTD_frameParams fParams;
-    ZSTD_dStreamStage stage;
-    char*  inBuff;
-    size_t inBuffSize;
-    size_t inPos;
-    size_t maxWindowSize;
-    char*  outBuff;
-    size_t outBuffSize;
-    size_t outStart;
-    size_t outEnd;
-    size_t blockSize;
-    BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX];   /* tmp buffer to store frame header */
-    size_t lhSize;
-    ZSTD_customMem customMem;
-    void* legacyContext;
-    U32 previousLegacyVersion;
-    U32 legacyVersion;
-    U32 hostageByte;
-};   /* typedef'd to ZSTD_DStream within "zstd.h" */
-
-
 ZSTD_DStream* ZSTD_createDStream(void)
 {
-    return ZSTD_createDStream_advanced(defaultCustomMem);
+    return ZSTD_createDStream_advanced(ZSTD_defaultCMem);
 }
 
-ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem)
+ZSTD_DStream* ZSTD_initStaticDStream(void *workspace, size_t workspaceSize)
 {
-    ZSTD_DStream* zds;
-
-    if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
-    if (!customMem.customAlloc || !customMem.customFree) return NULL;
+    return ZSTD_initStaticDCtx(workspace, workspaceSize);
+}
 
-    zds = (ZSTD_DStream*) ZSTD_malloc(sizeof(ZSTD_DStream), customMem);
-    if (zds==NULL) return NULL;
-    memset(zds, 0, sizeof(ZSTD_DStream));
-    memcpy(&zds->customMem, &customMem, sizeof(ZSTD_customMem));
-    zds->dctx = ZSTD_createDCtx_advanced(customMem);
-    if (zds->dctx == NULL) { ZSTD_freeDStream(zds); return NULL; }
-    zds->stage = zdss_init;
-    zds->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
-    return zds;
+ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem)
+{
+    return ZSTD_createDCtx_advanced(customMem);
 }
 
 size_t ZSTD_freeDStream(ZSTD_DStream* zds)
 {
-    if (zds==NULL) return 0;   /* support free on null */
-    {   ZSTD_customMem const cMem = zds->customMem;
-        ZSTD_freeDCtx(zds->dctx);
-        zds->dctx = NULL;
-        ZSTD_freeDDict(zds->ddictLocal);
-        zds->ddictLocal = NULL;
-        ZSTD_free(zds->inBuff, cMem);
-        zds->inBuff = NULL;
-        ZSTD_free(zds->outBuff, cMem);
-        zds->outBuff = NULL;
-#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
-        if (zds->legacyContext)
-            ZSTD_freeLegacyStreamContext(zds->legacyContext, zds->previousLegacyVersion);
-#endif
-        ZSTD_free(zds, cMem);
-        return 0;
-    }
+    return ZSTD_freeDCtx(zds);
 }
 
 
 /* *** Initialization *** */
 
-size_t ZSTD_DStreamInSize(void)  { return ZSTD_BLOCKSIZE_ABSOLUTEMAX + ZSTD_blockHeaderSize; }
-size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX; }
+size_t ZSTD_DStreamInSize(void)  { return ZSTD_BLOCKSIZE_MAX + ZSTD_blockHeaderSize; }
+size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_MAX; }
 
 size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize)
 {
-    zds->stage = zdss_loadHeader;
+    zds->streamStage = zdss_loadHeader;
     zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
     ZSTD_freeDDict(zds->ddictLocal);
     if (dict && dictSize >= 8) {
@@ -2147,7 +2225,7 @@ size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict)
 
 size_t ZSTD_resetDStream(ZSTD_DStream* zds)
 {
-    zds->stage = zdss_loadHeader;
+    zds->streamStage = zdss_loadHeader;
     zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
     zds->legacyVersion = 0;
     zds->hostageByte = 0;
@@ -2168,11 +2246,24 @@ size_t ZSTD_setDStreamParameter(ZSTD_DStream* zds,
 
 size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds)
 {
-    if (zds==NULL) return 0;   /* support sizeof NULL */
-    return sizeof(*zds)
-           + ZSTD_sizeof_DCtx(zds->dctx)
-           + ZSTD_sizeof_DDict(zds->ddictLocal)
-           + zds->inBuffSize + zds->outBuffSize;
+    return ZSTD_sizeof_DCtx(zds);
+}
+
+size_t ZSTD_estimateDStreamSize(size_t windowSize)
+{
+    size_t const blockSize = MIN(windowSize, ZSTD_BLOCKSIZE_MAX);
+    size_t const inBuffSize = blockSize;  /* no block can be larger */
+    size_t const outBuffSize = windowSize + blockSize + (WILDCOPY_OVERLENGTH * 2);
+    return sizeof(ZSTD_DStream) + ZSTD_estimateDCtxSize() + inBuffSize + outBuffSize;
+}
+
+ZSTDLIB_API size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize)
+{
+    ZSTD_frameHeader fh;
+    size_t const err = ZSTD_getFrameHeader(&fh, src, srcSize);
+    if (ZSTD_isError(err)) return err;
+    if (err>0) return ERROR(srcSize_wrong);
+    return ZSTD_estimateDStreamSize(fh.windowSize);
 }
 
 
@@ -2196,44 +2287,55 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
     char* op = ostart;
     U32 someMoreWork = 1;
 
+    DEBUGLOG(5, "ZSTD_decompressStream");
+    DEBUGLOG(5, "input size : %u", (U32)(input->size - input->pos));
 #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
-    if (zds->legacyVersion)
+    if (zds->legacyVersion) {
+        /* legacy support is incompatible with static dctx */
+        if (zds->staticSize) return ERROR(memory_allocation);
         return ZSTD_decompressLegacyStream(zds->legacyContext, zds->legacyVersion, output, input);
+    }
 #endif
 
     while (someMoreWork) {
-        switch(zds->stage)
+        switch(zds->streamStage)
         {
         case zdss_init :
             ZSTD_resetDStream(zds);   /* transparent reset on starting decoding a new frame */
             /* fall-through */
 
         case zdss_loadHeader :
-            {   size_t const hSize = ZSTD_getFrameParams(&zds->fParams, zds->headerBuffer, zds->lhSize);
-                if (ZSTD_isError(hSize))
+            {   size_t const hSize = ZSTD_getFrameHeader(&zds->fParams, zds->headerBuffer, zds->lhSize);
+                if (ZSTD_isError(hSize)) {
 #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
-                {   U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart);
+                    U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart);
                     if (legacyVersion) {
                         const void* const dict = zds->ddict ? zds->ddict->dictContent : NULL;
                         size_t const dictSize = zds->ddict ? zds->ddict->dictSize : 0;
+                        /* legacy support is incompatible with static dctx */
+                        if (zds->staticSize) return ERROR(memory_allocation);
                         CHECK_F(ZSTD_initLegacyStream(&zds->legacyContext, zds->previousLegacyVersion, legacyVersion,
                                                        dict, dictSize));
                         zds->legacyVersion = zds->previousLegacyVersion = legacyVersion;
                         return ZSTD_decompressLegacyStream(zds->legacyContext, zds->legacyVersion, output, input);
                     } else {
                         return hSize; /* error */
-                }   }
+                    }
 #else
-                return hSize;
+                    return hSize;
 #endif
+                }
                 if (hSize != 0) {   /* need more input */
                     size_t const toLoad = hSize - zds->lhSize;   /* if hSize!=0, hSize > zds->lhSize */
                     if (toLoad > (size_t)(iend-ip)) {   /* not enough input to load full header */
-                        memcpy(zds->headerBuffer + zds->lhSize, ip, iend-ip);
-                        zds->lhSize += iend-ip;
+                        if (iend-ip > 0) {
+                            memcpy(zds->headerBuffer + zds->lhSize, ip, iend-ip);
+                            zds->lhSize += iend-ip;
+                        }
                         input->pos = input->size;
                         return (MAX(ZSTD_frameHeaderSize_min, hSize) - zds->lhSize) + ZSTD_blockHeaderSize;   /* remaining header bytes + next block header */
                     }
+                    assert(ip != NULL);
                     memcpy(zds->headerBuffer + zds->lhSize, ip, toLoad); zds->lhSize = hSize; ip += toLoad;
                     break;
             }   }
@@ -2243,74 +2345,90 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
                 && (U64)(size_t)(oend-op) >= zds->fParams.frameContentSize) {
                 size_t const cSize = ZSTD_findFrameCompressedSize(istart, iend-istart);
                 if (cSize <= (size_t)(iend-istart)) {
-                    size_t const decompressedSize = ZSTD_decompress_usingDDict(zds->dctx, op, oend-op, istart, cSize, zds->ddict);
+                    size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, oend-op, istart, cSize, zds->ddict);
                     if (ZSTD_isError(decompressedSize)) return decompressedSize;
                     ip = istart + cSize;
                     op += decompressedSize;
-                    zds->dctx->expected = 0;
-                    zds->stage = zdss_init;
+                    zds->expected = 0;
+                    zds->streamStage = zdss_init;
                     someMoreWork = 0;
                     break;
             }   }
 
-            /* Consume header */
-            ZSTD_refDDict(zds->dctx, zds->ddict);
-            {   size_t const h1Size = ZSTD_nextSrcSizeToDecompress(zds->dctx);  /* == ZSTD_frameHeaderSize_prefix */
-                CHECK_F(ZSTD_decompressContinue(zds->dctx, NULL, 0, zds->headerBuffer, h1Size));
-                {   size_t const h2Size = ZSTD_nextSrcSizeToDecompress(zds->dctx);
-                    CHECK_F(ZSTD_decompressContinue(zds->dctx, NULL, 0, zds->headerBuffer+h1Size, h2Size));
-            }   }
+            /* Consume header (see ZSTDds_decodeFrameHeader) */
+            DEBUGLOG(4, "Consume header");
+            CHECK_F(ZSTD_decompressBegin_usingDDict(zds, zds->ddict));
+
+            if ((MEM_readLE32(zds->headerBuffer) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {  /* skippable frame */
+                zds->expected = MEM_readLE32(zds->headerBuffer + 4);
+                zds->stage = ZSTDds_skipFrame;
+            } else {
+                CHECK_F(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize));
+                zds->expected = ZSTD_blockHeaderSize;
+                zds->stage = ZSTDds_decodeBlockHeader;
+            }
 
+            /* control buffer memory usage */
+            DEBUGLOG(4, "Control max buffer memory usage");
             zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN);
             if (zds->fParams.windowSize > zds->maxWindowSize) return ERROR(frameParameter_windowTooLarge);
 
             /* Adapt buffer sizes to frame header instructions */
-            {   size_t const blockSize = MIN(zds->fParams.windowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX);
+            {   size_t const blockSize = MIN(zds->fParams.windowSize, ZSTD_BLOCKSIZE_MAX);
                 size_t const neededOutSize = zds->fParams.windowSize + blockSize + WILDCOPY_OVERLENGTH * 2;
                 zds->blockSize = blockSize;
-                if (zds->inBuffSize < blockSize) {
-                    ZSTD_free(zds->inBuff, zds->customMem);
-                    zds->inBuffSize = 0;
-                    zds->inBuff = (char*)ZSTD_malloc(blockSize, zds->customMem);
-                    if (zds->inBuff == NULL) return ERROR(memory_allocation);
+                if ((zds->inBuffSize < blockSize) || (zds->outBuffSize < neededOutSize)) {
+                    size_t const bufferSize = blockSize + neededOutSize;
+                    DEBUGLOG(4, "inBuff  : from %u to %u",
+                                (U32)zds->inBuffSize, (U32)blockSize);
+                    DEBUGLOG(4, "outBuff : from %u to %u",
+                                (U32)zds->outBuffSize, (U32)neededOutSize);
+                    if (zds->staticSize) {  /* static DCtx */
+                        DEBUGLOG(4, "staticSize : %u", (U32)zds->staticSize);
+                        assert(zds->staticSize >= sizeof(ZSTD_DCtx));  /* controlled at init */
+                        if (bufferSize > zds->staticSize - sizeof(ZSTD_DCtx))
+                            return ERROR(memory_allocation);
+                    } else {
+                        ZSTD_free(zds->inBuff, zds->customMem);
+                        zds->inBuffSize = 0;
+                        zds->outBuffSize = 0;
+                        zds->inBuff = (char*)ZSTD_malloc(bufferSize, zds->customMem);
+                        if (zds->inBuff == NULL) return ERROR(memory_allocation);
+                    }
                     zds->inBuffSize = blockSize;
-                }
-                if (zds->outBuffSize < neededOutSize) {
-                    ZSTD_free(zds->outBuff, zds->customMem);
-                    zds->outBuffSize = 0;
-                    zds->outBuff = (char*)ZSTD_malloc(neededOutSize, zds->customMem);
-                    if (zds->outBuff == NULL) return ERROR(memory_allocation);
+                    zds->outBuff = zds->inBuff + zds->inBuffSize;
                     zds->outBuffSize = neededOutSize;
             }   }
-            zds->stage = zdss_read;
+            zds->streamStage = zdss_read;
             /* pass-through */
 
         case zdss_read:
-            {   size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
+            DEBUGLOG(5, "stage zdss_read");
+            {   size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds);
+                DEBUGLOG(5, "neededInSize = %u", (U32)neededInSize);
                 if (neededInSize==0) {  /* end of frame */
-                    zds->stage = zdss_init;
+                    zds->streamStage = zdss_init;
                     someMoreWork = 0;
                     break;
                 }
                 if ((size_t)(iend-ip) >= neededInSize) {  /* decode directly from src */
-                    const int isSkipFrame = ZSTD_isSkipFrame(zds->dctx);
-                    size_t const decodedSize = ZSTD_decompressContinue(zds->dctx,
+                    int const isSkipFrame = ZSTD_isSkipFrame(zds);
+                    size_t const decodedSize = ZSTD_decompressContinue(zds,
                         zds->outBuff + zds->outStart, (isSkipFrame ? 0 : zds->outBuffSize - zds->outStart),
                         ip, neededInSize);
                     if (ZSTD_isError(decodedSize)) return decodedSize;
                     ip += neededInSize;
                     if (!decodedSize && !isSkipFrame) break;   /* this was just a header */
                     zds->outEnd = zds->outStart + decodedSize;
-                    zds->stage = zdss_flush;
+                    zds->streamStage = zdss_flush;
                     break;
-                }
-                if (ip==iend) { someMoreWork = 0; break; }   /* no more input */
-                zds->stage = zdss_load;
-                /* pass-through */
-            }
+            }   }
+            if (ip==iend) { someMoreWork = 0; break; }   /* no more input */
+            zds->streamStage = zdss_load;
+            /* pass-through */
 
         case zdss_load:
-            {   size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
+            {   size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds);
                 size_t const toLoad = neededInSize - zds->inPos;   /* should always be <= remaining space within inBuff */
                 size_t loadedSize;
                 if (toLoad > zds->inBuffSize - zds->inPos) return ERROR(corruption_detected);   /* should never happen */
@@ -2320,17 +2438,17 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
                 if (loadedSize < toLoad) { someMoreWork = 0; break; }   /* not enough input, wait for more */
 
                 /* decode loaded input */
-                {  const int isSkipFrame = ZSTD_isSkipFrame(zds->dctx);
-                   size_t const decodedSize = ZSTD_decompressContinue(zds->dctx,
+                {  const int isSkipFrame = ZSTD_isSkipFrame(zds);
+                   size_t const decodedSize = ZSTD_decompressContinue(zds,
                         zds->outBuff + zds->outStart, zds->outBuffSize - zds->outStart,
                         zds->inBuff, neededInSize);
                     if (ZSTD_isError(decodedSize)) return decodedSize;
                     zds->inPos = 0;   /* input is consumed */
-                    if (!decodedSize && !isSkipFrame) { zds->stage = zdss_read; break; }   /* this was just a header */
+                    if (!decodedSize && !isSkipFrame) { zds->streamStage = zdss_read; break; }   /* this was just a header */
                     zds->outEnd = zds->outStart +  decodedSize;
-                    zds->stage = zdss_flush;
-                    /* pass-through */
             }   }
+            zds->streamStage = zdss_flush;
+            /* pass-through */
 
         case zdss_flush:
             {   size_t const toFlushSize = zds->outEnd - zds->outStart;
@@ -2338,37 +2456,41 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
                 op += flushedSize;
                 zds->outStart += flushedSize;
                 if (flushedSize == toFlushSize) {  /* flush completed */
-                    zds->stage = zdss_read;
+                    zds->streamStage = zdss_read;
                     if (zds->outStart + zds->blockSize > zds->outBuffSize)
                         zds->outStart = zds->outEnd = 0;
                     break;
-                }
-                /* cannot complete flush */
-                someMoreWork = 0;
-                break;
-            }
+            }   }
+            /* cannot complete flush */
+            someMoreWork = 0;
+            break;
+
         default: return ERROR(GENERIC);   /* impossible */
     }   }
 
     /* result */
     input->pos += (size_t)(ip-istart);
     output->pos += (size_t)(op-ostart);
-    {   size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds->dctx);
+    {   size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds);
         if (!nextSrcSizeHint) {   /* frame fully decoded */
             if (zds->outEnd == zds->outStart) {  /* output fully flushed */
                 if (zds->hostageByte) {
-                    if (input->pos >= input->size) { zds->stage = zdss_read; return 1; }  /* can't release hostage (not present) */
+                    if (input->pos >= input->size) {
+                        /* can't release hostage (not present) */
+                        zds->streamStage = zdss_read;
+                        return 1;
+                    }
                     input->pos++;  /* release hostage */
-                }
+                }   /* zds->hostageByte */
                 return 0;
-            }
+            }  /* zds->outEnd == zds->outStart */
             if (!zds->hostageByte) { /* output not fully flushed; keep last byte as hostage; will be released when all output is flushed */
                 input->pos--;   /* note : pos > 0, otherwise, impossible to finish reading last block */
                 zds->hostageByte=1;
             }
             return 1;
-        }
-        nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds->dctx) == ZSTDnit_block);   /* preload header of next block */
+        }  /* nextSrcSizeHint==0 */
+        nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds) == ZSTDnit_block);   /* preload header of next block */
         if (zds->inPos > nextSrcSizeHint) return ERROR(GENERIC);   /* should never happen */
         nextSrcSizeHint -= zds->inPos;   /* already loaded*/
         return nextSrcSizeHint;