zstd-ruby 1.3.7.0 → 1.3.8.0

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

@@ -28,6 +28,16 @@
 #include "zstd.h"            /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTDLIB_API */
 
 
+/* ===   Constants   === */
+#ifndef ZSTDMT_NBWORKERS_MAX
+#  define ZSTDMT_NBWORKERS_MAX 200
+#endif
+#ifndef ZSTDMT_JOBSIZE_MIN
+#  define ZSTDMT_JOBSIZE_MIN (1 MB)
+#endif
+#define ZSTDMT_JOBSIZE_MAX  (MEM_32bits() ? (512 MB) : (1024 MB))
+
+
 /* ===   Memory management   === */
 typedef struct ZSTDMT_CCtx_s ZSTDMT_CCtx;
 ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers);
@@ -52,6 +62,7 @@ ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
 ZSTDLIB_API size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel);
 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 will change in the future to mean "empty" */
 
+ZSTDLIB_API size_t ZSTDMT_nextInputSizeHint(const ZSTDMT_CCtx* mtctx);
 ZSTDLIB_API size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
 
 ZSTDLIB_API size_t ZSTDMT_flushStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);   /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
@@ -60,16 +71,12 @@ ZSTDLIB_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);
 
 /* ===   Advanced functions and parameters  === */
 
-#ifndef ZSTDMT_JOBSIZE_MIN
-#  define ZSTDMT_JOBSIZE_MIN (1U << 20)   /* 1 MB - Minimum size of each compression job */
-#endif
-
 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 params,
-                                           unsigned overlapLog);
+                                           int 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 */
@@ -84,8 +91,9 @@ ZSTDLIB_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
 /* ZSTDMT_parameter :
  * List of parameters that can be set using ZSTDMT_setMTCtxParameter() */
 typedef enum {
-    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. This is a "sticky" parameter : its value will be re-used on next compression job */
+    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_overlapLog,  /* 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. This is a "sticky" parameter : its value will be re-used on next compression job */
+    ZSTDMT_p_rsyncable    /* Enables rsyncable mode. */
 } ZSTDMT_parameter;
 
 /* ZSTDMT_setMTCtxParameter() :
@@ -93,12 +101,12 @@ typedef enum {
  * 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, ZSTDMT_parameter parameter, unsigned value);
+ZSTDLIB_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int value);
 
 /* ZSTDMT_getMTCtxParameter() :
  * Query the ZSTDMT_CCtx for a parameter value.
  * @return : 0, or an error code (which can be tested using ZSTD_isError()) */
-ZSTDLIB_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, unsigned* value);
+ZSTDLIB_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int* value);
 
 
 /*! ZSTDMT_compressStream_generic() :
@@ -129,7 +137,7 @@ size_t ZSTDMT_toFlushNow(ZSTDMT_CCtx* mtctx);
 
 /*! ZSTDMT_CCtxParam_setMTCtxParameter()
  *  like ZSTDMT_setMTCtxParameter(), but into a ZSTD_CCtx_Params */
-size_t ZSTDMT_CCtxParam_setMTCtxParameter(ZSTD_CCtx_params* params, ZSTDMT_parameter parameter, unsigned value);
+size_t ZSTDMT_CCtxParam_setMTCtxParameter(ZSTD_CCtx_params* params, ZSTDMT_parameter parameter, int value);
 
 /*! ZSTDMT_CCtxParam_setNbWorkers()
  *  Set nbWorkers, and clamp it.

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

@@ -43,6 +43,19 @@
 #include "huf.h"
 #include "error_private.h"
 
+/* **************************************************************
+*  Macros
+****************************************************************/
+
+/* These two optional macros force the use one way or another of the two
+ * Huffman decompression implementations. You can't force in both directions
+ * at the same time.
+ */
+#if defined(HUF_FORCE_DECOMPRESS_X1) && \
+    defined(HUF_FORCE_DECOMPRESS_X2)
+#error "Cannot force the use of the X1 and X2 decoders at the same time!"
+#endif
+
 
 /* **************************************************************
 *  Error Management
@@ -58,6 +71,51 @@
 #define HUF_ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask))
 
 
+/* **************************************************************
+*  BMI2 Variant Wrappers
+****************************************************************/
+#if DYNAMIC_BMI2
+
+#define HUF_DGEN(fn)                                                        \
+                                                                            \
+    static size_t fn##_default(                                             \
+                  void* dst,  size_t dstSize,                               \
+            const void* cSrc, size_t cSrcSize,                              \
+            const HUF_DTable* DTable)                                       \
+    {                                                                       \
+        return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable);             \
+    }                                                                       \
+                                                                            \
+    static TARGET_ATTRIBUTE("bmi2") size_t fn##_bmi2(                       \
+                  void* dst,  size_t dstSize,                               \
+            const void* cSrc, size_t cSrcSize,                              \
+            const HUF_DTable* DTable)                                       \
+    {                                                                       \
+        return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable);             \
+    }                                                                       \
+                                                                            \
+    static size_t fn(void* dst, size_t dstSize, void const* cSrc,           \
+                     size_t cSrcSize, HUF_DTable const* DTable, int bmi2)   \
+    {                                                                       \
+        if (bmi2) {                                                         \
+            return fn##_bmi2(dst, dstSize, cSrc, cSrcSize, DTable);         \
+        }                                                                   \
+        return fn##_default(dst, dstSize, cSrc, cSrcSize, DTable);          \
+    }
+
+#else
+
+#define HUF_DGEN(fn)                                                        \
+    static size_t fn(void* dst, size_t dstSize, void const* cSrc,           \
+                     size_t cSrcSize, HUF_DTable const* DTable, int bmi2)   \
+    {                                                                       \
+        (void)bmi2;                                                         \
+        return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable);             \
+    }
+
+#endif
+
+
 /*-***************************/
 /*  generic DTableDesc       */
 /*-***************************/
@@ -71,6 +129,8 @@ static DTableDesc HUF_getDTableDesc(const HUF_DTable* table)
 }
 
 
+#ifndef HUF_FORCE_DECOMPRESS_X2
+
 /*-***************************/
 /*  single-symbol decoding   */
 /*-***************************/
@@ -307,46 +367,6 @@ typedef size_t (*HUF_decompress_usingDTable_t)(void *dst, size_t dstSize,
                                                const void *cSrc,
                                                size_t cSrcSize,
                                                const HUF_DTable *DTable);
-#if DYNAMIC_BMI2
-
-#define HUF_DGEN(fn)                                                               \
-                                                                            \
-    static size_t fn##_default(                                             \
-                  void* dst,  size_t dstSize,                               \
-            const void* cSrc, size_t cSrcSize,                              \
-            const HUF_DTable* DTable)                                       \
-    {                                                                       \
-        return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable);             \
-    }                                                                       \
-                                                                            \
-    static TARGET_ATTRIBUTE("bmi2") size_t fn##_bmi2(                       \
-                  void* dst,  size_t dstSize,                               \
-            const void* cSrc, size_t cSrcSize,                              \
-            const HUF_DTable* DTable)                                       \
-    {                                                                       \
-        return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable);             \
-    }                                                                       \
-                                                                            \
-    static size_t fn(void* dst, size_t dstSize, void const* cSrc,           \
-                     size_t cSrcSize, HUF_DTable const* DTable, int bmi2)   \
-    {                                                                       \
-        if (bmi2) {                                                         \
-            return fn##_bmi2(dst, dstSize, cSrc, cSrcSize, DTable);         \
-        }                                                                   \
-        return fn##_default(dst, dstSize, cSrc, cSrcSize, DTable);          \
-    }
-
-#else
-
-#define HUF_DGEN(fn)                                                               \
-    static size_t fn(void* dst, size_t dstSize, void const* cSrc,           \
-                     size_t cSrcSize, HUF_DTable const* DTable, int bmi2)   \
-    {                                                                       \
-        (void)bmi2;                                                         \
-        return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable);             \
-    }
-
-#endif
 
 HUF_DGEN(HUF_decompress1X1_usingDTable_internal)
 HUF_DGEN(HUF_decompress4X1_usingDTable_internal)
@@ -437,6 +457,10 @@ size_t HUF_decompress4X1 (void* dst, size_t dstSize, const void* cSrc, size_t cS
     return HUF_decompress4X1_DCtx(DTable, dst, dstSize, cSrc, cSrcSize);
 }
 
+#endif /* HUF_FORCE_DECOMPRESS_X2 */
+
+
+#ifndef HUF_FORCE_DECOMPRESS_X1
 
 /* *************************/
 /* double-symbols decoding */
@@ -911,6 +935,8 @@ size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cS
     return HUF_decompress4X2_DCtx(DTable, dst, dstSize, cSrc, cSrcSize);
 }
 
+#endif /* HUF_FORCE_DECOMPRESS_X1 */
+
 
 /* ***********************************/
 /* Universal decompression selectors */
@@ -921,8 +947,18 @@ size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize,
                                     const HUF_DTable* DTable)
 {
     DTableDesc const dtd = HUF_getDTableDesc(DTable);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dtd;
+    assert(dtd.tableType == 0);
+    return HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dtd;
+    assert(dtd.tableType == 1);
+    return HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#else
     return dtd.tableType ? HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0) :
                            HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#endif
 }
 
 size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize,
@@ -930,11 +966,22 @@ size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize,
                                     const HUF_DTable* DTable)
 {
     DTableDesc const dtd = HUF_getDTableDesc(DTable);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dtd;
+    assert(dtd.tableType == 0);
+    return HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dtd;
+    assert(dtd.tableType == 1);
+    return HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#else
     return dtd.tableType ? HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0) :
                            HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#endif
 }
 
 
+#if !defined(HUF_FORCE_DECOMPRESS_X1) && !defined(HUF_FORCE_DECOMPRESS_X2)
 typedef struct { U32 tableTime; U32 decode256Time; } algo_time_t;
 static const algo_time_t algoTime[16 /* Quantization */][3 /* single, double, quad */] =
 {
@@ -956,6 +1003,7 @@ static const algo_time_t algoTime[16 /* Quantization */][3 /* single, double, qu
     {{1455,128}, {2422,124}, {4174,124}},   /* Q ==14 : 87-93% */
     {{ 722,128}, {1891,145}, {1936,146}},   /* Q ==15 : 93-99% */
 };
+#endif
 
 /** HUF_selectDecoder() :
  *  Tells which decoder is likely to decode faster,
@@ -966,6 +1014,15 @@ U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize)
 {
     assert(dstSize > 0);
     assert(dstSize <= 128*1024);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dstSize;
+    (void)cSrcSize;
+    return 0;
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dstSize;
+    (void)cSrcSize;
+    return 1;
+#else
     /* decoder timing evaluation */
     {   U32 const Q = (cSrcSize >= dstSize) ? 15 : (U32)(cSrcSize * 16 / dstSize);   /* Q < 16 */
         U32 const D256 = (U32)(dstSize >> 8);
@@ -973,14 +1030,18 @@ U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize)
         U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256);
         DTime1 += DTime1 >> 3;  /* advantage to algorithm using less memory, to reduce cache eviction */
         return DTime1 < DTime0;
-}   }
+    }
+#endif
+}
 
 
 typedef size_t (*decompressionAlgo)(void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);
 
 size_t HUF_decompress (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
 {
+#if !defined(HUF_FORCE_DECOMPRESS_X1) && !defined(HUF_FORCE_DECOMPRESS_X2)
     static const decompressionAlgo decompress[2] = { HUF_decompress4X1, HUF_decompress4X2 };
+#endif
 
     /* validation checks */
     if (dstSize == 0) return ERROR(dstSize_tooSmall);
@@ -989,7 +1050,17 @@ size_t HUF_decompress (void* dst, size_t dstSize, const void* cSrc, size_t cSrcS
     if (cSrcSize == 1) { memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; }   /* RLE */
 
     {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress4X1(dst, dstSize, cSrc, cSrcSize);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress4X2(dst, dstSize, cSrc, cSrcSize);
+#else
         return decompress[algoNb](dst, dstSize, cSrc, cSrcSize);
+#endif
     }
 }
 
@@ -1002,8 +1073,18 @@ size_t HUF_decompress4X_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);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress4X1_DCtx(dctx, dst, dstSize, cSrc, cSrcSize);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress4X2_DCtx(dctx, dst, dstSize, cSrc, cSrcSize);
+#else
         return algoNb ? HUF_decompress4X2_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) :
                         HUF_decompress4X1_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) ;
+#endif
     }
 }
 
@@ -1025,8 +1106,19 @@ size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst,
     if (cSrcSize == 0) return ERROR(corruption_detected);
 
     {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
-        return algoNb ? HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize):
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress4X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
+#else
+        return algoNb ? HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                            cSrcSize, workSpace, wkspSize):
                         HUF_decompress4X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
+#endif
     }
 }
 
@@ -1041,10 +1133,22 @@ size_t HUF_decompress1X_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
     if (cSrcSize == 1) { memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; }   /* RLE */
 
     {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress1X1_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize);
+#else
         return algoNb ? HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
                                 cSrcSize, workSpace, wkspSize):
                         HUF_decompress1X1_DCtx_wksp(dctx, dst, dstSize, cSrc,
                                 cSrcSize, workSpace, wkspSize);
+#endif
     }
 }
 
@@ -1060,10 +1164,21 @@ size_t HUF_decompress1X_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize,
 size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2)
 {
     DTableDesc const dtd = HUF_getDTableDesc(DTable);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dtd;
+    assert(dtd.tableType == 0);
+    return HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dtd;
+    assert(dtd.tableType == 1);
+    return HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#else
     return dtd.tableType ? HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) :
                            HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#endif
 }
 
+#ifndef HUF_FORCE_DECOMPRESS_X2
 size_t HUF_decompress1X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2)
 {
     const BYTE* ip = (const BYTE*) cSrc;
@@ -1075,12 +1190,23 @@ size_t HUF_decompress1X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstS
 
     return HUF_decompress1X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
 }
+#endif
 
 size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2)
 {
     DTableDesc const dtd = HUF_getDTableDesc(DTable);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dtd;
+    assert(dtd.tableType == 0);
+    return HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dtd;
+    assert(dtd.tableType == 1);
+    return HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#else
     return dtd.tableType ? HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) :
                            HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#endif
 }
 
 size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2)
@@ -1090,7 +1216,17 @@ size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t ds
     if (cSrcSize == 0) return ERROR(corruption_detected);
 
     {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2);
+#else
         return algoNb ? HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2) :
                         HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2);
+#endif
     }
 }

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

@@ -0,0 +1,240 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * 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.
+ */
+
+/* zstd_ddict.c :
+ * concentrates all logic that needs to know the internals of ZSTD_DDict object */
+
+/*-*******************************************************
+*  Dependencies
+*********************************************************/
+#include <string.h>      /* memcpy, memmove, memset */
+#include "cpu.h"         /* bmi2 */
+#include "mem.h"         /* low level memory routines */
+#define FSE_STATIC_LINKING_ONLY
+#include "fse.h"
+#define HUF_STATIC_LINKING_ONLY
+#include "huf.h"
+#include "zstd_decompress_internal.h"
+#include "zstd_ddict.h"
+
+#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
+#  include "zstd_legacy.h"
+#endif
+
+
+
+/*-*******************************************************
+*  Types
+*********************************************************/
+struct ZSTD_DDict_s {
+    void* dictBuffer;
+    const void* dictContent;
+    size_t dictSize;
+    ZSTD_entropyDTables_t entropy;
+    U32 dictID;
+    U32 entropyPresent;
+    ZSTD_customMem cMem;
+};  /* typedef'd to ZSTD_DDict within "zstd.h" */
+
+const void* ZSTD_DDict_dictContent(const ZSTD_DDict* ddict)
+{
+    assert(ddict != NULL);
+    return ddict->dictContent;
+}
+
+size_t ZSTD_DDict_dictSize(const ZSTD_DDict* ddict)
+{
+    assert(ddict != NULL);
+    return ddict->dictSize;
+}
+
+void ZSTD_copyDDictParameters(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict)
+{
+    DEBUGLOG(4, "ZSTD_copyDDictParameters");
+    assert(dctx != NULL);
+    assert(ddict != NULL);
+    dctx->dictID = ddict->dictID;
+    dctx->prefixStart = ddict->dictContent;
+    dctx->virtualStart = ddict->dictContent;
+    dctx->dictEnd = (const BYTE*)ddict->dictContent + ddict->dictSize;
+    dctx->previousDstEnd = dctx->dictEnd;
+    if (ddict->entropyPresent) {
+        dctx->litEntropy = 1;
+        dctx->fseEntropy = 1;
+        dctx->LLTptr = ddict->entropy.LLTable;
+        dctx->MLTptr = ddict->entropy.MLTable;
+        dctx->OFTptr = ddict->entropy.OFTable;
+        dctx->HUFptr = ddict->entropy.hufTable;
+        dctx->entropy.rep[0] = ddict->entropy.rep[0];
+        dctx->entropy.rep[1] = ddict->entropy.rep[1];
+        dctx->entropy.rep[2] = ddict->entropy.rep[2];
+    } else {
+        dctx->litEntropy = 0;
+        dctx->fseEntropy = 0;
+    }
+}
+
+
+static size_t
+ZSTD_loadEntropy_intoDDict(ZSTD_DDict* ddict,
+                           ZSTD_dictContentType_e dictContentType)
+{
+    ddict->dictID = 0;
+    ddict->entropyPresent = 0;
+    if (dictContentType == ZSTD_dct_rawContent) return 0;
+
+    if (ddict->dictSize < 8) {
+        if (dictContentType == ZSTD_dct_fullDict)
+            return ERROR(dictionary_corrupted);   /* only accept specified dictionaries */
+        return 0;   /* pure content mode */
+    }
+    {   U32 const magic = MEM_readLE32(ddict->dictContent);
+        if (magic != ZSTD_MAGIC_DICTIONARY) {
+            if (dictContentType == ZSTD_dct_fullDict)
+                return ERROR(dictionary_corrupted);   /* only accept specified dictionaries */
+            return 0;   /* pure content mode */
+        }
+    }
+    ddict->dictID = MEM_readLE32((const char*)ddict->dictContent + ZSTD_FRAMEIDSIZE);
+
+    /* load entropy tables */
+    CHECK_E( ZSTD_loadDEntropy(&ddict->entropy,
+                                ddict->dictContent, ddict->dictSize),
+             dictionary_corrupted );
+    ddict->entropyPresent = 1;
+    return 0;
+}
+
+
+static size_t ZSTD_initDDict_internal(ZSTD_DDict* ddict,
+                                      const void* dict, size_t dictSize,
+                                      ZSTD_dictLoadMethod_e dictLoadMethod,
+                                      ZSTD_dictContentType_e dictContentType)
+{
+    if ((dictLoadMethod == ZSTD_dlm_byRef) || (!dict) || (!dictSize)) {
+        ddict->dictBuffer = NULL;
+        ddict->dictContent = dict;
+        if (!dict) dictSize = 0;
+    } 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_intoDDict(ddict, dictContentType) );
+
+    return 0;
+}
+
+ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize,
+                                      ZSTD_dictLoadMethod_e dictLoadMethod,
+                                      ZSTD_dictContentType_e dictContentType,
+                                      ZSTD_customMem customMem)
+{
+    if (!customMem.customAlloc ^ !customMem.customFree) return NULL;
+
+    {   ZSTD_DDict* const ddict = (ZSTD_DDict*) ZSTD_malloc(sizeof(ZSTD_DDict), customMem);
+        if (ddict == NULL) return NULL;
+        ddict->cMem = customMem;
+        {   size_t const initResult = ZSTD_initDDict_internal(ddict,
+                                            dict, dictSize,
+                                            dictLoadMethod, dictContentType);
+            if (ZSTD_isError(initResult)) {
+                ZSTD_freeDDict(ddict);
+                return NULL;
+        }   }
+        return ddict;
+    }
+}
+
+/*! ZSTD_createDDict() :
+*   Create a digested dictionary, to start decompression without startup delay.
+*   `dict` content is copied inside DDict.
+*   Consequently, `dict` can be released after `ZSTD_DDict` creation */
+ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize)
+{
+    ZSTD_customMem const allocator = { NULL, NULL, NULL };
+    return ZSTD_createDDict_advanced(dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto, 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.
+ *  Warning : dictBuffer must outlive DDict (DDict must be freed before dictBuffer) */
+ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize)
+{
+    ZSTD_customMem const allocator = { NULL, NULL, NULL };
+    return ZSTD_createDDict_advanced(dictBuffer, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto, allocator);
+}
+
+
+const ZSTD_DDict* ZSTD_initStaticDDict(
+                                void* sBuffer, size_t sBufferSize,
+                                const void* dict, size_t dictSize,
+                                ZSTD_dictLoadMethod_e dictLoadMethod,
+                                ZSTD_dictContentType_e dictContentType)
+{
+    size_t const neededSpace = sizeof(ZSTD_DDict)
+                             + (dictLoadMethod == ZSTD_dlm_byRef ? 0 : dictSize);
+    ZSTD_DDict* const ddict = (ZSTD_DDict*)sBuffer;
+    assert(sBuffer != NULL);
+    assert(dict != NULL);
+    if ((size_t)sBuffer & 7) return NULL;   /* 8-aligned */
+    if (sBufferSize < neededSpace) return NULL;
+    if (dictLoadMethod == ZSTD_dlm_byCopy) {
+        memcpy(ddict+1, dict, dictSize);  /* local copy */
+        dict = ddict+1;
+    }
+    if (ZSTD_isError( ZSTD_initDDict_internal(ddict,
+                                              dict, dictSize,
+                                              ZSTD_dlm_byRef, dictContentType) ))
+        return NULL;
+    return ddict;
+}
+
+
+size_t ZSTD_freeDDict(ZSTD_DDict* ddict)
+{
+    if (ddict==NULL) return 0;   /* support free on NULL */
+    {   ZSTD_customMem const cMem = ddict->cMem;
+        ZSTD_free(ddict->dictBuffer, cMem);
+        ZSTD_free(ddict, cMem);
+        return 0;
+    }
+}
+
+/*! ZSTD_estimateDDictSize() :
+ *  Estimate amount of memory that will be needed to create a dictionary for decompression.
+ *  Note : dictionary created by reference using ZSTD_dlm_byRef are smaller */
+size_t ZSTD_estimateDDictSize(size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod)
+{
+    return sizeof(ZSTD_DDict) + (dictLoadMethod == ZSTD_dlm_byRef ? 0 : dictSize);
+}
+
+size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict)
+{
+    if (ddict==NULL) return 0;   /* support sizeof on NULL */
+    return sizeof(*ddict) + (ddict->dictBuffer ? ddict->dictSize : 0) ;
+}
+
+/*! ZSTD_getDictID_fromDDict() :
+ *  Provides the dictID of the dictionary loaded into `ddict`.
+ *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
+ *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
+unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict)
+{
+    if (ddict==NULL) return 0;
+    return ZSTD_getDictID_fromDict(ddict->dictContent, ddict->dictSize);
+}