Update to ZStandard v1.2.0

mcmilk · May 12, 2017 · 9e50322 · 9e50322
1 parent dc355d6
commit 9e50322
Show file tree

Hide file tree

Showing 20 changed files with 840 additions and 655 deletions.
diff --git a/C/7zVersion.h b/C/7zVersion.h
@@ -1,7 +1,7 @@
 #define MY_VER_MAJOR 17
 #define MY_VER_MINOR 00
 #define MY_VER_BUILD 0
-#define MY_VERSION_NUMBERS "17.00 ZS v1.1.4 R2"
+#define MY_VERSION_NUMBERS "17.00 ZS v1.2.0"
 #define MY_VERSION MY_VERSION_NUMBERS
 
 #ifdef MY_CPU_NAME
@@ -10,7 +10,7 @@
   #define MY_VERSION_CPU MY_VERSION
 #endif
 
-#define MY_DATE "2017-05-10"
+#define MY_DATE "2017-05-12"
 #undef MY_COPYRIGHT
 #undef MY_VERSION_COPYRIGHT_DATE
 #define MY_AUTHOR_NAME "Igor Pavlov, Tino Reichardt"

diff --git a/C/7zVersionTr.h b/C/7zVersionTr.h
@@ -1,9 +1,9 @@
 #define MY_VER_MAJOR 1
-#define MY_VER_MINOR 1
-#define MY_VER_BUILD 4
-#define MY_VERSION_NUMBERS "1.1.4 R2"
-#define MY_VERSION         "1.1.4 R2"
-#define MY_DATE            "2017-05-10"
+#define MY_VER_MINOR 2
+#define MY_VER_BUILD 0
+#define MY_VERSION_NUMBERS "1.2.0"
+#define MY_VERSION         "1.2.0"
+#define MY_DATE            "2017-05-12"
 #undef MY_COPYRIGHT
 #undef MY_VERSION_COPYRIGHT_DATE
 #define MY_AUTHOR_NAME     "Tino Reichardt"

diff --git a/C/zstd/bitstream.h b/C/zstd/bitstream.h
@@ -2,7 +2,7 @@
    bitstream
    Part of FSE library
    header file (to include)
-   Copyright (C) 2013-2016, Yann Collet.
+   Copyright (C) 2013-2017, Yann Collet.
 
    BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
 
@@ -53,6 +53,16 @@ extern "C" {
 #include "error_private.h"  /* error codes and messages */
 
 
+/*-*************************************
+*  Debug
+***************************************/
+#if defined(BIT_DEBUG) && (BIT_DEBUG>=1)
+#  include <assert.h>
+#else
+#  define assert(condition) ((void)0)
+#endif
+
+
 /*=========================================
 *  Target specific
 =========================================*/
@@ -74,7 +84,7 @@ extern "C" {
 typedef struct
 {
     size_t bitContainer;
-    int    bitPos;
+    unsigned bitPos;
     char*  startPtr;
     char*  ptr;
     char*  endPtr;
@@ -112,6 +122,7 @@ typedef struct
     unsigned bitsConsumed;
     const char* ptr;
     const char* start;
+    const char* limitPtr;
 } BIT_DStream_t;
 
 typedef enum { BIT_DStream_unfinished = 0,
@@ -163,7 +174,10 @@ MEM_STATIC unsigned BIT_highbit32 (register U32 val)
 #   elif defined(__GNUC__) && (__GNUC__ >= 3)   /* Use GCC Intrinsic */
     return 31 - __builtin_clz (val);
 #   else   /* Software version */
-    static const unsigned DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, 11, 14, 16, 18, 22, 25, 3, 30, 8, 12, 20, 28, 15, 17, 24, 7, 19, 27, 23, 6, 26, 5, 4, 31 };
+    static const unsigned DeBruijnClz[32] = { 0,  9,  1, 10, 13, 21,  2, 29,
+                                             11, 14, 16, 18, 22, 25,  3, 30,
+                                              8, 12, 20, 28, 15, 17, 24,  7,
+                                             19, 27, 23,  6, 26,  5,  4, 31 };
     U32 v = val;
     v |= v >> 1;
     v |= v >> 2;
@@ -175,66 +189,79 @@ MEM_STATIC unsigned BIT_highbit32 (register U32 val)
 }
 
 /*=====    Local Constants   =====*/
-static const unsigned BIT_mask[] = { 0, 1, 3, 7, 0xF, 0x1F, 0x3F, 0x7F, 0xFF, 0x1FF, 0x3FF, 0x7FF, 0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0x1FFFF, 0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF,  0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF };   /* up to 26 bits */
+static const unsigned BIT_mask[] = { 0, 1, 3, 7, 0xF, 0x1F, 0x3F, 0x7F,
+                                    0xFF, 0x1FF, 0x3FF, 0x7FF, 0xFFF, 0x1FFF, 0x3FFF, 0x7FFF,
+                                    0xFFFF, 0x1FFFF, 0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF,
+                                    0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF };   /* up to 26 bits */
 
 
 /*-**************************************************************
 *  bitStream encoding
 ****************************************************************/
 /*! BIT_initCStream() :
- *  `dstCapacity` must be > sizeof(void*)
+ *  `dstCapacity` must be > sizeof(size_t)
  *  @return : 0 if success,
               otherwise an error code (can be tested using ERR_isError() ) */
-MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, void* startPtr, size_t dstCapacity)
+MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC,
+                                  void* startPtr, size_t dstCapacity)
 {
     bitC->bitContainer = 0;
     bitC->bitPos = 0;
     bitC->startPtr = (char*)startPtr;
     bitC->ptr = bitC->startPtr;
-    bitC->endPtr = bitC->startPtr + dstCapacity - sizeof(bitC->ptr);
-    if (dstCapacity <= sizeof(bitC->ptr)) return ERROR(dstSize_tooSmall);
+    bitC->endPtr = bitC->startPtr + dstCapacity - sizeof(bitC->bitContainer);
+    if (dstCapacity <= sizeof(bitC->bitContainer)) return ERROR(dstSize_tooSmall);
     return 0;
 }
 
 /*! BIT_addBits() :
     can add up to 26 bits into `bitC`.
     Does not check for register overflow ! */
-MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC, size_t value, unsigned nbBits)
+MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC,
+                            size_t value, unsigned nbBits)
 {
     bitC->bitContainer |= (value & BIT_mask[nbBits]) << bitC->bitPos;
     bitC->bitPos += nbBits;
 }
 
 /*! BIT_addBitsFast() :
  *  works only if `value` is _clean_, meaning all high bits above nbBits are 0 */
-MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, size_t value, unsigned nbBits)
+MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC,
+                                size_t value, unsigned nbBits)
 {
+    assert((value>>nbBits) == 0);
     bitC->bitContainer |= value << bitC->bitPos;
     bitC->bitPos += nbBits;
 }
 
 /*! BIT_flushBitsFast() :
+ *  assumption : bitContainer has not overflowed
  *  unsafe version; does not check buffer overflow */
 MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC)
 {
     size_t const nbBytes = bitC->bitPos >> 3;
+    assert( bitC->bitPos <= (sizeof(bitC->bitContainer)*8) );
     MEM_writeLEST(bitC->ptr, bitC->bitContainer);
     bitC->ptr += nbBytes;
+    assert(bitC->ptr <= bitC->endPtr);
     bitC->bitPos &= 7;
-    bitC->bitContainer >>= nbBytes*8;   /* if bitPos >= sizeof(bitContainer)*8 --> undefined behavior */
+    bitC->bitContainer >>= nbBytes*8;
 }
 
 /*! BIT_flushBits() :
+ *  assumption : bitContainer has not overflowed
  *  safe version; check for buffer overflow, and prevents it.
- *  note : does not signal buffer overflow. This will be revealed later on using BIT_closeCStream() */
+ *  note : does not signal buffer overflow.
+ *  overflow will be revealed later on using BIT_closeCStream() */
 MEM_STATIC void BIT_flushBits(BIT_CStream_t* bitC)
 {
     size_t const nbBytes = bitC->bitPos >> 3;
+    assert( bitC->bitPos <= (sizeof(bitC->bitContainer)*8) );
     MEM_writeLEST(bitC->ptr, bitC->bitContainer);
     bitC->ptr += nbBytes;
     if (bitC->ptr > bitC->endPtr) bitC->ptr = bitC->endPtr;
     bitC->bitPos &= 7;
-    bitC->bitContainer >>= nbBytes*8;   /* if bitPos >= sizeof(bitContainer)*8 --> undefined behavior */
+    bitC->bitContainer >>= nbBytes*8;
 }
 
 /*! BIT_closeCStream() :
@@ -244,9 +271,7 @@ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC)
 {
     BIT_addBitsFast(bitC, 1, 1);   /* endMark */
     BIT_flushBits(bitC);
-
-    if (bitC->ptr >= bitC->endPtr) return 0; /* doesn't fit within authorized budget : cancel */
-
+    if (bitC->ptr >= bitC->endPtr) return 0; /* overflow detected */
     return (bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0);
 }
 
@@ -264,15 +289,16 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si
 {
     if (srcSize < 1) { memset(bitD, 0, sizeof(*bitD)); return ERROR(srcSize_wrong); }
 
+    bitD->start = (const char*)srcBuffer;
+    bitD->limitPtr = bitD->start + sizeof(bitD->bitContainer);
+
     if (srcSize >=  sizeof(bitD->bitContainer)) {  /* normal case */
-        bitD->start = (const char*)srcBuffer;
         bitD->ptr   = (const char*)srcBuffer + srcSize - sizeof(bitD->bitContainer);
         bitD->bitContainer = MEM_readLEST(bitD->ptr);
         { BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
           bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0;  /* ensures bitsConsumed is always set */
           if (lastByte == 0) return ERROR(GENERIC); /* endMark not present */ }
     } else {
-        bitD->start = (const char*)srcBuffer;
         bitD->ptr   = bitD->start;
         bitD->bitContainer = *(const BYTE*)(bitD->start);
         switch(srcSize)
@@ -330,17 +356,18 @@ MEM_STATIC size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits)
 #if defined(__BMI__) && defined(__GNUC__)   /* experimental; fails if bitD->bitsConsumed + nbBits > sizeof(bitD->bitContainer)*8 */
     return BIT_getMiddleBits(bitD->bitContainer, (sizeof(bitD->bitContainer)*8) - bitD->bitsConsumed - nbBits, nbBits);
 #else
-    U32 const bitMask = sizeof(bitD->bitContainer)*8 - 1;
-    return ((bitD->bitContainer << (bitD->bitsConsumed & bitMask)) >> 1) >> ((bitMask-nbBits) & bitMask);
+    U32 const regMask = sizeof(bitD->bitContainer)*8 - 1;
+    return ((bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> 1) >> ((regMask-nbBits) & regMask);
 #endif
 }
 
 /*! BIT_lookBitsFast() :
-*   unsafe version; only works only if nbBits >= 1 */
+ *  unsafe version; only works if nbBits >= 1 */
 MEM_STATIC size_t BIT_lookBitsFast(const BIT_DStream_t* bitD, U32 nbBits)
 {
-    U32 const bitMask = sizeof(bitD->bitContainer)*8 - 1;
-    return (bitD->bitContainer << (bitD->bitsConsumed & bitMask)) >> (((bitMask+1)-nbBits) & bitMask);
+    U32 const regMask = sizeof(bitD->bitContainer)*8 - 1;
+    assert(nbBits >= 1);
+    return (bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> (((regMask+1)-nbBits) & regMask);
 }
 
 MEM_STATIC void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits)
@@ -365,6 +392,7 @@ MEM_STATIC size_t BIT_readBits(BIT_DStream_t* bitD, U32 nbBits)
 MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, U32 nbBits)
 {
     size_t const value = BIT_lookBitsFast(bitD, nbBits);
+    assert(nbBits >= 1);
     BIT_skipBits(bitD, nbBits);
     return value;
 }
@@ -376,10 +404,10 @@ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, U32 nbBits)
               if status == BIT_DStream_unfinished, internal register is filled with >= (sizeof(bitD->bitContainer)*8 - 7) bits */
 MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD)
 {
-	if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8))  /* should not happen => corruption detected */
-		return BIT_DStream_overflow;
+    if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8))  /* overflow detected, like end of stream */
+        return BIT_DStream_overflow;
 
-    if (bitD->ptr >= bitD->start + sizeof(bitD->bitContainer)) {
+    if (bitD->ptr >= bitD->limitPtr) {
         bitD->ptr -= bitD->bitsConsumed >> 3;
         bitD->bitsConsumed &= 7;
         bitD->bitContainer = MEM_readLEST(bitD->ptr);
@@ -389,6 +417,7 @@ MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD)
         if (bitD->bitsConsumed < sizeof(bitD->bitContainer)*8) return BIT_DStream_endOfBuffer;
         return BIT_DStream_completed;
     }
+    /* start < ptr < limitPtr */
     {   U32 nbBytes = bitD->bitsConsumed >> 3;
         BIT_DStream_status result = BIT_DStream_unfinished;
         if (bitD->ptr - nbBytes < bitD->start) {
@@ -397,7 +426,7 @@ MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD)
         }
         bitD->ptr -= nbBytes;
         bitD->bitsConsumed -= nbBytes*8;
-        bitD->bitContainer = MEM_readLEST(bitD->ptr);   /* reminder : srcSize > sizeof(bitD) */
+        bitD->bitContainer = MEM_readLEST(bitD->ptr);   /* reminder : srcSize > sizeof(bitD->bitContainer), otherwise bitD->ptr == bitD->start */
         return result;
     }
 }

diff --git a/C/zstd/error_private.c b/C/zstd/error_private.c
@@ -29,14 +29,15 @@ const char* ERR_getErrorString(ERR_enum code)
     case PREFIX(memory_allocation): return "Allocation error : not enough memory";
     case PREFIX(stage_wrong): return "Operation not authorized at current processing stage";
     case PREFIX(dstSize_tooSmall): return "Destination buffer is too small";
-    case PREFIX(srcSize_wrong): return "Src size incorrect";
+    case PREFIX(srcSize_wrong): return "Src size is incorrect";
     case PREFIX(corruption_detected): return "Corrupted block detected";
     case PREFIX(checksum_wrong): return "Restored data doesn't match checksum";
     case PREFIX(tableLog_tooLarge): return "tableLog requires too much memory : unsupported";
     case PREFIX(maxSymbolValue_tooLarge): return "Unsupported max Symbol Value : too large";
     case PREFIX(maxSymbolValue_tooSmall): return "Specified maxSymbolValue is too small";
     case PREFIX(dictionary_corrupted): return "Dictionary is corrupted";
     case PREFIX(dictionary_wrong): return "Dictionary mismatch";
+    case PREFIX(dictionaryCreation_failed): return "Cannot create Dictionary from provided samples";
     case PREFIX(maxCode):
     default: return notErrorCode;
     }

diff --git a/C/zstd/fse.h b/C/zstd/fse.h
@@ -316,6 +316,10 @@ If there is an error, the function will return an error code, which can be teste
 #define FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue)   (1 + (1<<(maxTableLog-1)) + ((maxSymbolValue+1)*2))
 #define FSE_DTABLE_SIZE_U32(maxTableLog)                   (1 + (1<<maxTableLog))
 
+/* or use the size to malloc() space directly. Pay attention to alignment restrictions though */
+#define FSE_CTABLE_SIZE(maxTableLog, maxSymbolValue)   (FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) * sizeof(FSE_CTable))
+#define FSE_DTABLE_SIZE(maxTableLog)                   (FSE_DTABLE_SIZE_U32(maxTableLog) * sizeof(FSE_DTable))
+
 
 /* *****************************************
 *  FSE advanced API
@@ -353,7 +357,7 @@ unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsi
  * Same as FSE_compress2(), but using an externally allocated scratch buffer (`workSpace`).
  * FSE_WKSP_SIZE_U32() provides the minimum size required for `workSpace` as a table of FSE_CTable.
  */
-#define FSE_WKSP_SIZE_U32(maxTableLog, maxSymbolValue)   ( FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) + (1<<((maxTableLog>2)?(maxTableLog-2):0)) )
+#define FSE_WKSP_SIZE_U32(maxTableLog, maxSymbolValue)   ( FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) + ((maxTableLog > 12) ? (1 << (maxTableLog - 2)) : 1024) )
 size_t FSE_compress_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
 
 size_t FSE_buildCTable_raw (FSE_CTable* ct, unsigned nbBits);
@@ -550,9 +554,9 @@ MEM_STATIC void FSE_initCState2(FSE_CState_t* statePtr, const FSE_CTable* ct, U3
 
 MEM_STATIC void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* statePtr, U32 symbol)
 {
-    const FSE_symbolCompressionTransform symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol];
+    FSE_symbolCompressionTransform const symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol];
     const U16* const stateTable = (const U16*)(statePtr->stateTable);
-    U32 nbBitsOut  = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16);
+    U32 const nbBitsOut  = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16);
     BIT_addBits(bitC, statePtr->value, nbBitsOut);
     statePtr->value = stateTable[ (statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
 }

diff --git a/C/zstd/fse_compress.c b/C/zstd/fse_compress.c
@@ -291,7 +291,7 @@ static size_t FSE_writeNCount_generic (void* header, size_t headerBufferSize,
 
 size_t FSE_writeNCount (void* buffer, size_t bufferSize, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog)
 {
-    if (tableLog > FSE_MAX_TABLELOG) return ERROR(GENERIC);   /* Unsupported */
+    if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge);   /* Unsupported */
     if (tableLog < FSE_MIN_TABLELOG) return ERROR(GENERIC);   /* Unsupported */
 
     if (bufferSize < FSE_NCountWriteBound(maxSymbolValue, tableLog))
@@ -476,20 +476,20 @@ void FSE_freeCTable (FSE_CTable* ct) { free(ct); }
 /* provides the minimum logSize to safely represent a distribution */
 static unsigned FSE_minTableLog(size_t srcSize, unsigned maxSymbolValue)
 {
-	U32 minBitsSrc = BIT_highbit32((U32)(srcSize - 1)) + 1;
-	U32 minBitsSymbols = BIT_highbit32(maxSymbolValue) + 2;
-	U32 minBits = minBitsSrc < minBitsSymbols ? minBitsSrc : minBitsSymbols;
-	return minBits;
+    U32 minBitsSrc = BIT_highbit32((U32)(srcSize - 1)) + 1;
+    U32 minBitsSymbols = BIT_highbit32(maxSymbolValue) + 2;
+    U32 minBits = minBitsSrc < minBitsSymbols ? minBitsSrc : minBitsSymbols;
+    return minBits;
 }
 
 unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus)
 {
-	U32 maxBitsSrc = BIT_highbit32((U32)(srcSize - 1)) - minus;
+    U32 maxBitsSrc = BIT_highbit32((U32)(srcSize - 1)) - minus;
     U32 tableLog = maxTableLog;
-	U32 minBits = FSE_minTableLog(srcSize, maxSymbolValue);
+    U32 minBits = FSE_minTableLog(srcSize, maxSymbolValue);
     if (tableLog==0) tableLog = FSE_DEFAULT_TABLELOG;
-	if (maxBitsSrc < tableLog) tableLog = maxBitsSrc;   /* Accuracy can be reduced */
-	if (minBits > tableLog) tableLog = minBits;   /* Need a minimum to safely represent all symbol values */
+    if (maxBitsSrc < tableLog) tableLog = maxBitsSrc;   /* Accuracy can be reduced */
+    if (minBits > tableLog) tableLog = minBits;   /* Need a minimum to safely represent all symbol values */
     if (tableLog < FSE_MIN_TABLELOG) tableLog = FSE_MIN_TABLELOG;
     if (tableLog > FSE_MAX_TABLELOG) tableLog = FSE_MAX_TABLELOG;
     return tableLog;
@@ -808,7 +808,7 @@ size_t FSE_compress_wksp (void* dst, size_t dstSize, const void* src, size_t src
     if (!tableLog) tableLog = FSE_DEFAULT_TABLELOG;
 
     /* Scan input and build symbol stats */
-    {   CHECK_V_F(maxCount, FSE_count(count, &maxSymbolValue, src, srcSize) );
+    {   CHECK_V_F(maxCount, FSE_count_wksp(count, &maxSymbolValue, src, srcSize, (unsigned*)scratchBuffer) );
         if (maxCount == srcSize) return 1;   /* only a single symbol in src : rle */
         if (maxCount == 1) return 0;         /* each symbol present maximum once => not compressible */
         if (maxCount < (srcSize >> 7)) return 0;   /* Heuristic : not compressible enough */