Merge pull request #5 from SpringMT/update-zstd-for-v1.1.4

Update zstd version to v1.1.4

Author: SpringMT

ext/zstdruby/libzstd/Makefile

@@ -24,19 +24,22 @@ CPPFLAGS+= -I. -I./common -DXXH_NAMESPACE=ZSTD_
 CFLAGS  ?= -O3
 DEBUGFLAGS = -g -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
            -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
-           -Wstrict-prototypes -Wundef -Wpointer-arith
+           -Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security
 CFLAGS  += $(DEBUGFLAGS) $(MOREFLAGS)
 FLAGS    = $(CPPFLAGS) $(CFLAGS)
 
 
 ZSTD_FILES := $(wildcard common/*.c compress/*.c decompress/*.c dictBuilder/*.c deprecated/*.c)
 
-ifeq ($(ZSTD_LEGACY_SUPPORT), 0)
-CPPFLAGS  += -DZSTD_LEGACY_SUPPORT=0
-else
-CPPFLAGS  += -I./legacy -DZSTD_LEGACY_SUPPORT=1
-ZSTD_FILES+= $(wildcard legacy/*.c)
+ZSTD_LEGACY_SUPPORT ?= 4
+
+ifneq ($(ZSTD_LEGACY_SUPPORT), 0)
+ifeq ($(shell test $(ZSTD_LEGACY_SUPPORT) -lt 8; echo $$?), 0)
+	ZSTD_FILES += $(shell ls legacy/*.c | grep 'v0[$(ZSTD_LEGACY_SUPPORT)-7]')
+endif
+	CPPFLAGS += -I./legacy
 endif
+CPPFLAGS  += -DZSTD_LEGACY_SUPPORT=$(ZSTD_LEGACY_SUPPORT)
 
 ZSTD_OBJ   := $(patsubst %.c,%.o,$(ZSTD_FILES))
 

ext/zstdruby/libzstd/common/bitstream.h

@@ -60,6 +60,9 @@ extern "C" {
 #  include <immintrin.h>   /* support for bextr (experimental) */
 #endif
 
+#define STREAM_ACCUMULATOR_MIN_32  25
+#define STREAM_ACCUMULATOR_MIN_64  57
+#define STREAM_ACCUMULATOR_MIN    ((U32)(MEM_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64))
 
 /*-******************************************
 *  bitStream encoding API (write forward)

ext/zstdruby/libzstd/common/entropy_common.c

@@ -43,27 +43,21 @@
 #include "huf.h"
 
 
-/*-****************************************
-*  FSE Error Management
-******************************************/
-unsigned FSE_isError(size_t code) { return ERR_isError(code); }
+/*===   Version   ===*/
+unsigned FSE_versionNumber(void) { return FSE_VERSION_NUMBER; }
 
-const char* FSE_getErrorName(size_t code) { return ERR_getErrorName(code); }
 
+/*===   Error Management   ===*/
+unsigned FSE_isError(size_t code) { return ERR_isError(code); }
+const char* FSE_getErrorName(size_t code) { return ERR_getErrorName(code); }
 
-/* **************************************************************
-*  HUF Error Management
-****************************************************************/
 unsigned HUF_isError(size_t code) { return ERR_isError(code); }
-
 const char* HUF_getErrorName(size_t code) { return ERR_getErrorName(code); }
 
 
 /*-**************************************************************
 *  FSE NCount encoding-decoding
 ****************************************************************/
-static short FSE_abs(short a) { return (short)(a<0 ? -a : a); }
-
 size_t FSE_readNCount (short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr,
                  const void* headerBuffer, size_t hbSize)
 {
@@ -117,21 +111,21 @@ size_t FSE_readNCount (short* normalizedCounter, unsigned* maxSVPtr, unsigned* t
             } else {
                 bitStream >>= 2;
         }   }
-        {   short const max = (short)((2*threshold-1)-remaining);
-            short count;
+        {   int const max = (2*threshold-1) - remaining;
+            int count;
 
             if ((bitStream & (threshold-1)) < (U32)max) {
-                count = (short)(bitStream & (threshold-1));
-                bitCount   += nbBits-1;
+                count = bitStream & (threshold-1);
+                bitCount += nbBits-1;
             } else {
-                count = (short)(bitStream & (2*threshold-1));
+                count = bitStream & (2*threshold-1);
                 if (count >= threshold) count -= max;
-                bitCount   += nbBits;
+                bitCount += nbBits;
             }
 
             count--;   /* extra accuracy */
-            remaining -= FSE_abs(count);
-            normalizedCounter[charnum++] = count;
+            remaining -= count < 0 ? -count : count;   /* -1 means +1 */
+            normalizedCounter[charnum++] = (short)count;
             previous0 = !count;
             while (remaining < threshold) {
                 nbBits--;

ext/zstdruby/libzstd/common/fse.h

@@ -45,6 +45,32 @@ extern "C" {
 #include <stddef.h>    /* size_t, ptrdiff_t */
 
 
+/*-*****************************************
+*  FSE_PUBLIC_API : control library symbols visibility
+******************************************/
+#if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4)
+#  define FSE_PUBLIC_API __attribute__ ((visibility ("default")))
+#elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1)   /* Visual expected */
+#  define FSE_PUBLIC_API __declspec(dllexport)
+#elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1)
+#  define FSE_PUBLIC_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
+#else
+#  define FSE_PUBLIC_API
+#endif
+
+/*------   Version   ------*/
+#define FSE_VERSION_MAJOR    0
+#define FSE_VERSION_MINOR    9
+#define FSE_VERSION_RELEASE  0
+
+#define FSE_LIB_VERSION FSE_VERSION_MAJOR.FSE_VERSION_MINOR.FSE_VERSION_RELEASE
+#define FSE_QUOTE(str) #str
+#define FSE_EXPAND_AND_QUOTE(str) FSE_QUOTE(str)
+#define FSE_VERSION_STRING FSE_EXPAND_AND_QUOTE(FSE_LIB_VERSION)
+
+#define FSE_VERSION_NUMBER  (FSE_VERSION_MAJOR *100*100 + FSE_VERSION_MINOR *100 + FSE_VERSION_RELEASE)
+FSE_PUBLIC_API unsigned FSE_versionNumber(void);   /**< library version number; to be used when checking dll version */
+
 /*-****************************************
 *  FSE simple functions
 ******************************************/
@@ -56,8 +82,8 @@ extern "C" {
                      if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression instead.
                      if FSE_isError(return), compression failed (more details using FSE_getErrorName())
 */
-size_t FSE_compress(void* dst, size_t dstCapacity,
-              const void* src, size_t srcSize);
+FSE_PUBLIC_API size_t FSE_compress(void* dst, size_t dstCapacity,
+                             const void* src, size_t srcSize);
 
 /*! FSE_decompress():
     Decompress FSE data from buffer 'cSrc', of size 'cSrcSize',
@@ -69,18 +95,18 @@ size_t FSE_compress(void* dst, size_t dstCapacity,
     Why ? : making this distinction requires a header.
     Header management is intentionally delegated to the user layer, which can better manage special cases.
 */
-size_t FSE_decompress(void* dst,  size_t dstCapacity,
-                const void* cSrc, size_t cSrcSize);
+FSE_PUBLIC_API size_t FSE_decompress(void* dst,  size_t dstCapacity,
+                               const void* cSrc, size_t cSrcSize);
 
 
 /*-*****************************************
 *  Tool functions
 ******************************************/
-size_t FSE_compressBound(size_t size);       /* maximum compressed size */
+FSE_PUBLIC_API size_t FSE_compressBound(size_t size);       /* maximum compressed size */
 
 /* Error Management */
-unsigned    FSE_isError(size_t code);        /* tells if a return value is an error code */
-const char* FSE_getErrorName(size_t code);   /* provides error code string (useful for debugging) */
+FSE_PUBLIC_API unsigned    FSE_isError(size_t code);        /* tells if a return value is an error code */
+FSE_PUBLIC_API const char* FSE_getErrorName(size_t code);   /* provides error code string (useful for debugging) */
 
 
 /*-*****************************************
@@ -94,7 +120,7 @@ const char* FSE_getErrorName(size_t code);   /* provides error code string (usef
                      if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression.
                      if FSE_isError(return), it's an error code.
 */
-size_t FSE_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
+FSE_PUBLIC_API size_t FSE_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
 
 
 /*-*****************************************
@@ -127,50 +153,50 @@ or to save and provide normalized distribution using external method.
     @return : the count of the most frequent symbol (which is not identified).
               if return == srcSize, there is only one symbol.
               Can also return an error code, which can be tested with FSE_isError(). */
-size_t FSE_count(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize);
+FSE_PUBLIC_API size_t FSE_count(unsigned* count, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize);
 
 /*! FSE_optimalTableLog():
     dynamically downsize 'tableLog' when conditions are met.
     It saves CPU time, by using smaller tables, while preserving or even improving compression ratio.
     @return : recommended tableLog (necessarily <= 'maxTableLog') */
-unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
+FSE_PUBLIC_API unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
 
 /*! FSE_normalizeCount():
     normalize counts so that sum(count[]) == Power_of_2 (2^tableLog)
     'normalizedCounter' is a table of short, of minimum size (maxSymbolValue+1).
     @return : tableLog,
               or an errorCode, which can be tested using FSE_isError() */
-size_t FSE_normalizeCount(short* normalizedCounter, unsigned tableLog, const unsigned* count, size_t srcSize, unsigned maxSymbolValue);
+FSE_PUBLIC_API size_t FSE_normalizeCount(short* normalizedCounter, unsigned tableLog, const unsigned* count, size_t srcSize, unsigned maxSymbolValue);
 
 /*! FSE_NCountWriteBound():
     Provides the maximum possible size of an FSE normalized table, given 'maxSymbolValue' and 'tableLog'.
     Typically useful for allocation purpose. */
-size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog);
+FSE_PUBLIC_API size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog);
 
 /*! FSE_writeNCount():
     Compactly save 'normalizedCounter' into 'buffer'.
     @return : size of the compressed table,
               or an errorCode, which can be tested using FSE_isError(). */
-size_t FSE_writeNCount (void* buffer, size_t bufferSize, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
+FSE_PUBLIC_API size_t FSE_writeNCount (void* buffer, size_t bufferSize, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
 
 
 /*! Constructor and Destructor of FSE_CTable.
     Note that FSE_CTable size depends on 'tableLog' and 'maxSymbolValue' */
 typedef unsigned FSE_CTable;   /* don't allocate that. It's only meant to be more restrictive than void* */
-FSE_CTable* FSE_createCTable (unsigned tableLog, unsigned maxSymbolValue);
-void        FSE_freeCTable (FSE_CTable* ct);
+FSE_PUBLIC_API FSE_CTable* FSE_createCTable (unsigned tableLog, unsigned maxSymbolValue);
+FSE_PUBLIC_API void        FSE_freeCTable (FSE_CTable* ct);
 
 /*! FSE_buildCTable():
     Builds `ct`, which must be already allocated, using FSE_createCTable().
     @return : 0, or an errorCode, which can be tested using FSE_isError() */
-size_t FSE_buildCTable(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
+FSE_PUBLIC_API size_t FSE_buildCTable(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
 
 /*! FSE_compress_usingCTable():
     Compress `src` using `ct` into `dst` which must be already allocated.
     @return : size of compressed data (<= `dstCapacity`),
               or 0 if compressed data could not fit into `dst`,
               or an errorCode, which can be tested using FSE_isError() */
-size_t FSE_compress_usingCTable (void* dst, size_t dstCapacity, const void* src, size_t srcSize, const FSE_CTable* ct);
+FSE_PUBLIC_API size_t FSE_compress_usingCTable (void* dst, size_t dstCapacity, const void* src, size_t srcSize, const FSE_CTable* ct);
 
 /*!
 Tutorial :
@@ -223,25 +249,25 @@ If there is an error, the function will return an ErrorCode (which can be tested
     @return : size read from 'rBuffer',
               or an errorCode, which can be tested using FSE_isError().
               maxSymbolValuePtr[0] and tableLogPtr[0] will also be updated with their respective values */
-size_t FSE_readNCount (short* normalizedCounter, unsigned* maxSymbolValuePtr, unsigned* tableLogPtr, const void* rBuffer, size_t rBuffSize);
+FSE_PUBLIC_API size_t FSE_readNCount (short* normalizedCounter, unsigned* maxSymbolValuePtr, unsigned* tableLogPtr, const void* rBuffer, size_t rBuffSize);
 
 /*! Constructor and Destructor of FSE_DTable.
     Note that its size depends on 'tableLog' */
 typedef unsigned FSE_DTable;   /* don't allocate that. It's just a way to be more restrictive than void* */
-FSE_DTable* FSE_createDTable(unsigned tableLog);
-void        FSE_freeDTable(FSE_DTable* dt);
+FSE_PUBLIC_API FSE_DTable* FSE_createDTable(unsigned tableLog);
+FSE_PUBLIC_API void        FSE_freeDTable(FSE_DTable* dt);
 
 /*! FSE_buildDTable():
     Builds 'dt', which must be already allocated, using FSE_createDTable().
     return : 0, or an errorCode, which can be tested using FSE_isError() */
-size_t FSE_buildDTable (FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
+FSE_PUBLIC_API size_t FSE_buildDTable (FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
 
 /*! FSE_decompress_usingDTable():
     Decompress compressed source `cSrc` of size `cSrcSize` using `dt`
     into `dst` which must be already allocated.
     @return : size of regenerated data (necessarily <= `dstCapacity`),
               or an errorCode, which can be tested using FSE_isError() */
-size_t FSE_decompress_usingDTable(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt);
+FSE_PUBLIC_API size_t FSE_decompress_usingDTable(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt);
 
 /*!
 Tutorial :

ext/zstdruby/libzstd/common/fse_decompress.c

@@ -59,7 +59,6 @@
 ****************************************************************/
 #include <stdlib.h>     /* malloc, free, qsort */
 #include <string.h>     /* memcpy, memset */
-#include <stdio.h>      /* printf (debug) */
 #include "bitstream.h"
 #define FSE_STATIC_LINKING_ONLY
 #include "fse.h"

ext/zstdruby/libzstd/common/huf.h

@@ -91,7 +91,7 @@ size_t HUF_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize
 
 /** HUF_compress4X_wksp() :
 *   Same as HUF_compress2(), but uses externally allocated `workSpace`, which must be a table of >= 1024 unsigned */
-size_t HUF_compress4X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);  /**< `workSpace` must be a table of at least 1024 unsigned */
+size_t HUF_compress4X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);  /**< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */
 
 
 
@@ -102,10 +102,11 @@ size_t HUF_compress4X_wksp (void* dst, size_t dstSize, const void* src, size_t s
 
 
 /* *** Constants *** */
-#define HUF_TABLELOG_ABSOLUTEMAX  15   /* absolute limit of HUF_MAX_TABLELOG. Beyond that value, code does not work */
-#define HUF_TABLELOG_MAX  12           /* max configured tableLog (for static allocation); can be modified up to HUF_ABSOLUTEMAX_TABLELOG */
+#define HUF_TABLELOG_MAX      12       /* max configured tableLog (for static allocation); can be modified up to HUF_ABSOLUTEMAX_TABLELOG */
 #define HUF_TABLELOG_DEFAULT  11       /* tableLog by default, when not specified */
-#define HUF_SYMBOLVALUE_MAX 255
+#define HUF_SYMBOLVALUE_MAX  255
+
+#define HUF_TABLELOG_ABSOLUTEMAX  15   /* absolute limit of HUF_MAX_TABLELOG. Beyond that value, code does not work */
 #if (HUF_TABLELOG_MAX > HUF_TABLELOG_ABSOLUTEMAX)
 #  error "HUF_TABLELOG_MAX is too large !"
 #endif
@@ -133,6 +134,10 @@ typedef U32 HUF_DTable;
 #define HUF_CREATE_STATIC_DTABLEX4(DTable, maxTableLog) \
         HUF_DTable DTable[HUF_DTABLE_SIZE(maxTableLog)] = { ((U32)(maxTableLog) * 0x01000001) }
 
+/* The workspace must have alignment at least 4 and be at least this large */
+#define HUF_WORKSPACE_SIZE (6 << 10)
+#define HUF_WORKSPACE_SIZE_U32 (HUF_WORKSPACE_SIZE / sizeof(U32))
+
 
 /* ****************************************
 *  Advanced decompression functions
@@ -168,6 +173,17 @@ size_t HUF_buildCTable (HUF_CElt* CTable, const unsigned* count, unsigned maxSym
 size_t HUF_writeCTable (void* dst, size_t maxDstSize, const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog);
 size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
 
+typedef enum {
+   HUF_repeat_none,  /**< Cannot use the previous table */
+   HUF_repeat_check, /**< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1, 4}X_repeat */
+   HUF_repeat_valid  /**< Can use the previous table and it is asumed to be valid */
+ } HUF_repeat;
+/** HUF_compress4X_repeat() :
+*   Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
+*   If it uses hufTable it does not modify hufTable or repeat.
+*   If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
+*   If preferRepeat then the old table will always be used if valid. */
+size_t HUF_compress4X_repeat(void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize, HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat);  /**< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */
 
 /** HUF_buildCTable_wksp() :
  *  Same as HUF_buildCTable(), but using externally allocated scratch buffer.
@@ -214,8 +230,14 @@ size_t HUF_decompress4X4_usingDTable(void* dst, size_t maxDstSize, const void* c
 /* single stream variants */
 
 size_t HUF_compress1X (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
-size_t HUF_compress1X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);  /**< `workSpace` must be a table of at least 1024 unsigned */
+size_t HUF_compress1X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);  /**< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */
 size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
+/** HUF_compress1X_repeat() :
+*   Same as HUF_compress1X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
+*   If it uses hufTable it does not modify hufTable or repeat.
+*   If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
+*   If preferRepeat then the old table will always be used if valid. */
+size_t HUF_compress1X_repeat(void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize, HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat);  /**< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */
 
 size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* single-symbol decoder */
 size_t HUF_decompress1X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* double-symbol decoder */