zstd-ruby 1.4.5.0 → 1.5.1.1

data/ext/zstdruby/libzstd/compress/zstd_compress_literals.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc.
+ * Copyright (c) Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -15,7 +15,7 @@
 
 size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
 {
-    BYTE* const ostart = (BYTE* const)dst;
+    BYTE* const ostart = (BYTE*)dst;
     U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
 
     RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall, "");
@@ -35,14 +35,14 @@ size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src,
             assert(0);
     }
 
-    memcpy(ostart + flSize, src, srcSize);
+    ZSTD_memcpy(ostart + flSize, src, srcSize);
     DEBUGLOG(5, "Raw literals: %u -> %u", (U32)srcSize, (U32)(srcSize + flSize));
     return srcSize + flSize;
 }
 
 size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
 {
-    BYTE* const ostart = (BYTE* const)dst;
+    BYTE* const ostart = (BYTE*)dst;
     U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
 
     (void)dstCapacity;  /* dstCapacity already guaranteed to be >=4, hence large enough */
@@ -73,7 +73,8 @@ size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
                               void* dst, size_t dstCapacity,
                         const void* src, size_t srcSize,
                               void* entropyWorkspace, size_t entropyWorkspaceSize,
-                        const int bmi2)
+                        const int bmi2,
+                        unsigned suspectUncompressible)
 {
     size_t const minGain = ZSTD_minGain(srcSize, strategy);
     size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
@@ -86,7 +87,7 @@ size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
                 disableLiteralCompression, (U32)srcSize);
 
     /* Prepare nextEntropy assuming reusing the existing table */
-    memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+    ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
 
     if (disableLiteralCompression)
         return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
@@ -105,11 +106,11 @@ size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
             HUF_compress1X_repeat(
                 ostart+lhSize, dstCapacity-lhSize, src, srcSize,
                 HUF_SYMBOLVALUE_MAX, HUF_TABLELOG_DEFAULT, entropyWorkspace, entropyWorkspaceSize,
-                (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2) :
+                (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2, suspectUncompressible) :
             HUF_compress4X_repeat(
                 ostart+lhSize, dstCapacity-lhSize, src, srcSize,
                 HUF_SYMBOLVALUE_MAX, HUF_TABLELOG_DEFAULT, entropyWorkspace, entropyWorkspaceSize,
-                (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
+                (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2, suspectUncompressible);
         if (repeat != HUF_repeat_none) {
             /* reused the existing table */
             DEBUGLOG(5, "Reusing previous huffman table");
@@ -117,12 +118,12 @@ size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
         }
     }
 
-    if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
-        memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+    if ((cLitSize==0) || (cLitSize >= srcSize - minGain) || ERR_isError(cLitSize)) {
+        ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
         return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
     }
     if (cLitSize==1) {
-        memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+        ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
         return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
     }
 

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

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc.
+ * Copyright (c) Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -18,12 +18,14 @@ size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src,
 
 size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
 
+/* If suspectUncompressible then some sampling checks will be run to potentially skip huffman coding */
 size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
                               ZSTD_hufCTables_t* nextHuf,
                               ZSTD_strategy strategy, int disableLiteralCompression,
                               void* dst, size_t dstCapacity,
                         const void* src, size_t srcSize,
                               void* entropyWorkspace, size_t entropyWorkspaceSize,
-                        const int bmi2);
+                        const int bmi2,
+                        unsigned suspectUncompressible);
 
 #endif /* ZSTD_COMPRESS_LITERALS_H */

data/ext/zstdruby/libzstd/compress/zstd_compress_sequences.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc.
+ * Copyright (c) Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -50,6 +50,19 @@ static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) {
   return maxSymbolValue;
 }
 
+/**
+ * Returns true if we should use ncount=-1 else we should
+ * use ncount=1 for low probability symbols instead.
+ */
+static unsigned ZSTD_useLowProbCount(size_t const nbSeq)
+{
+    /* Heuristic: This should cover most blocks <= 16K and
+     * start to fade out after 16K to about 32K depending on
+     * comprssibility.
+     */
+    return nbSeq >= 2048;
+}
+
 /**
  * Returns the cost in bytes of encoding the normalized count header.
  * Returns an error if any of the helper functions return an error.
@@ -60,7 +73,7 @@ static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max,
     BYTE wksp[FSE_NCOUNTBOUND];
     S16 norm[MaxSeq + 1];
     const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
-    FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max), "");
+    FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max, ZSTD_useLowProbCount(nbSeq)), "");
     return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog);
 }
 
@@ -72,6 +85,8 @@ static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t
 {
     unsigned cost = 0;
     unsigned s;
+
+    assert(total > 0);
     for (s = 0; s <= max; ++s) {
         unsigned norm = (unsigned)((256 * count[s]) / total);
         if (count[s] != 0 && norm == 0)
@@ -219,6 +234,11 @@ ZSTD_selectEncodingType(
     return set_compressed;
 }
 
+typedef struct {
+    S16 norm[MaxSeq + 1];
+    U32 wksp[FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(MaxSeq, MaxFSELog)];
+} ZSTD_BuildCTableWksp;
+
 size_t
 ZSTD_buildCTable(void* dst, size_t dstCapacity,
                 FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
@@ -239,13 +259,13 @@ ZSTD_buildCTable(void* dst, size_t dstCapacity,
         *op = codeTable[0];
         return 1;
     case set_repeat:
-        memcpy(nextCTable, prevCTable, prevCTableSize);
+        ZSTD_memcpy(nextCTable, prevCTable, prevCTableSize);
         return 0;
     case set_basic:
         FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, entropyWorkspace, entropyWorkspaceSize), "");  /* note : could be pre-calculated */
         return 0;
     case set_compressed: {
-        S16 norm[MaxSeq + 1];
+        ZSTD_BuildCTableWksp* wksp = (ZSTD_BuildCTableWksp*)entropyWorkspace;
         size_t nbSeq_1 = nbSeq;
         const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
         if (count[codeTable[nbSeq-1]] > 1) {
@@ -253,10 +273,13 @@ ZSTD_buildCTable(void* dst, size_t dstCapacity,
             nbSeq_1--;
         }
         assert(nbSeq_1 > 1);
-        FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max), "");
-        {   size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog);   /* overflow protected */
+        assert(entropyWorkspaceSize >= sizeof(ZSTD_BuildCTableWksp));
+        (void)entropyWorkspaceSize;
+        FORWARD_IF_ERROR(FSE_normalizeCount(wksp->norm, tableLog, count, nbSeq_1, max, ZSTD_useLowProbCount(nbSeq_1)), "FSE_normalizeCount failed");
+        assert(oend >= op);
+        {   size_t const NCountSize = FSE_writeNCount(op, (size_t)(oend - op), wksp->norm, max, tableLog);   /* overflow protected */
             FORWARD_IF_ERROR(NCountSize, "FSE_writeNCount failed");
-            FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, entropyWorkspace, entropyWorkspaceSize), "");
+            FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, wksp->norm, max, tableLog, wksp->wksp, sizeof(wksp->wksp)), "FSE_buildCTable_wksp failed");
             return NCountSize;
         }
     }
@@ -376,7 +399,7 @@ ZSTD_encodeSequences_default(
 
 #if DYNAMIC_BMI2
 
-static TARGET_ATTRIBUTE("bmi2") size_t
+static BMI2_TARGET_ATTRIBUTE size_t
 ZSTD_encodeSequences_bmi2(
             void* dst, size_t dstCapacity,
             FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,

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

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc.
+ * Copyright (c) Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the

data/ext/zstdruby/libzstd/compress/zstd_compress_superblock.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc.
+ * Copyright (c) Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -15,288 +15,10 @@
 
 #include "../common/zstd_internal.h"  /* ZSTD_getSequenceLength */
 #include "hist.h"                     /* HIST_countFast_wksp */
-#include "zstd_compress_internal.h"
+#include "zstd_compress_internal.h"   /* ZSTD_[huf|fse|entropy]CTablesMetadata_t */
 #include "zstd_compress_sequences.h"
 #include "zstd_compress_literals.h"
 
-/*-*************************************
-*  Superblock entropy buffer structs
-***************************************/
-/** ZSTD_hufCTablesMetadata_t :
- *  Stores Literals Block Type for a super-block in hType, and
- *  huffman tree description in hufDesBuffer.
- *  hufDesSize refers to the size of huffman tree description in bytes.
- *  This metadata is populated in ZSTD_buildSuperBlockEntropy_literal() */
-typedef struct {
-    symbolEncodingType_e hType;
-    BYTE hufDesBuffer[500]; /* TODO give name to this value */
-    size_t hufDesSize;
-} ZSTD_hufCTablesMetadata_t;
-
-/** ZSTD_fseCTablesMetadata_t :
- *  Stores symbol compression modes for a super-block in {ll, ol, ml}Type, and
- *  fse tables in fseTablesBuffer.
- *  fseTablesSize refers to the size of fse tables in bytes.
- *  This metadata is populated in ZSTD_buildSuperBlockEntropy_sequences() */
-typedef struct {
-    symbolEncodingType_e llType;
-    symbolEncodingType_e ofType;
-    symbolEncodingType_e mlType;
-    BYTE fseTablesBuffer[500]; /* TODO give name to this value */
-    size_t fseTablesSize;
-    size_t lastCountSize; /* This is to account for bug in 1.3.4. More detail in ZSTD_compressSubBlock_sequences() */
-} ZSTD_fseCTablesMetadata_t;
-
-typedef struct {
-    ZSTD_hufCTablesMetadata_t hufMetadata;
-    ZSTD_fseCTablesMetadata_t fseMetadata;
-} ZSTD_entropyCTablesMetadata_t;
-
-
-/** ZSTD_buildSuperBlockEntropy_literal() :
- *  Builds entropy for the super-block literals.
- *  Stores literals block type (raw, rle, compressed, repeat) and
- *  huffman description table to hufMetadata.
- *  @return : size of huffman description table or error code */
-static size_t ZSTD_buildSuperBlockEntropy_literal(void* const src, size_t srcSize,
-                                            const ZSTD_hufCTables_t* prevHuf,
-                                                  ZSTD_hufCTables_t* nextHuf,
-                                                  ZSTD_hufCTablesMetadata_t* hufMetadata,
-                                                  const int disableLiteralsCompression,
-                                                  void* workspace, size_t wkspSize)
-{
-    BYTE* const wkspStart = (BYTE*)workspace;
-    BYTE* const wkspEnd = wkspStart + wkspSize;
-    BYTE* const countWkspStart = wkspStart;
-    unsigned* const countWksp = (unsigned*)workspace;
-    const size_t countWkspSize = (HUF_SYMBOLVALUE_MAX + 1) * sizeof(unsigned);
-    BYTE* const nodeWksp = countWkspStart + countWkspSize;
-    const size_t nodeWkspSize = wkspEnd-nodeWksp;
-    unsigned maxSymbolValue = 255;
-    unsigned huffLog = HUF_TABLELOG_DEFAULT;
-    HUF_repeat repeat = prevHuf->repeatMode;
-
-    DEBUGLOG(5, "ZSTD_buildSuperBlockEntropy_literal (srcSize=%zu)", srcSize);
-
-    /* Prepare nextEntropy assuming reusing the existing table */
-    memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
-
-    if (disableLiteralsCompression) {
-        DEBUGLOG(5, "set_basic - disabled");
-        hufMetadata->hType = set_basic;
-        return 0;
-    }
-
-    /* small ? don't even attempt compression (speed opt) */
-#   define COMPRESS_LITERALS_SIZE_MIN 63
-    {   size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
-        if (srcSize <= minLitSize) {
-            DEBUGLOG(5, "set_basic - too small");
-            hufMetadata->hType = set_basic;
-            return 0;
-        }
-    }
-
-    /* Scan input and build symbol stats */
-    {   size_t const largest = HIST_count_wksp (countWksp, &maxSymbolValue, (const BYTE*)src, srcSize, workspace, wkspSize);
-        FORWARD_IF_ERROR(largest, "HIST_count_wksp failed");
-        if (largest == srcSize) {
-            DEBUGLOG(5, "set_rle");
-            hufMetadata->hType = set_rle;
-            return 0;
-        }
-        if (largest <= (srcSize >> 7)+4) {
-            DEBUGLOG(5, "set_basic - no gain");
-            hufMetadata->hType = set_basic;
-            return 0;
-        }
-    }
-
-    /* Validate the previous Huffman table */
-    if (repeat == HUF_repeat_check && !HUF_validateCTable((HUF_CElt const*)prevHuf->CTable, countWksp, maxSymbolValue)) {
-        repeat = HUF_repeat_none;
-    }
-
-    /* Build Huffman Tree */
-    memset(nextHuf->CTable, 0, sizeof(nextHuf->CTable));
-    huffLog = HUF_optimalTableLog(huffLog, srcSize, maxSymbolValue);
-    {   size_t const maxBits = HUF_buildCTable_wksp((HUF_CElt*)nextHuf->CTable, countWksp,
-                                                    maxSymbolValue, huffLog,
-                                                    nodeWksp, nodeWkspSize);
-        FORWARD_IF_ERROR(maxBits, "HUF_buildCTable_wksp");
-        huffLog = (U32)maxBits;
-        {   /* Build and write the CTable */
-            size_t const newCSize = HUF_estimateCompressedSize(
-                    (HUF_CElt*)nextHuf->CTable, countWksp, maxSymbolValue);
-            size_t const hSize = HUF_writeCTable(
-                    hufMetadata->hufDesBuffer, sizeof(hufMetadata->hufDesBuffer),
-                    (HUF_CElt*)nextHuf->CTable, maxSymbolValue, huffLog);
-            /* Check against repeating the previous CTable */
-            if (repeat != HUF_repeat_none) {
-                size_t const oldCSize = HUF_estimateCompressedSize(
-                        (HUF_CElt const*)prevHuf->CTable, countWksp, maxSymbolValue);
-                if (oldCSize < srcSize && (oldCSize <= hSize + newCSize || hSize + 12 >= srcSize)) {
-                    DEBUGLOG(5, "set_repeat - smaller");
-                    memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
-                    hufMetadata->hType = set_repeat;
-                    return 0;
-                }
-            }
-            if (newCSize + hSize >= srcSize) {
-                DEBUGLOG(5, "set_basic - no gains");
-                memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
-                hufMetadata->hType = set_basic;
-                return 0;
-            }
-            DEBUGLOG(5, "set_compressed (hSize=%u)", (U32)hSize);
-            hufMetadata->hType = set_compressed;
-            nextHuf->repeatMode = HUF_repeat_check;
-            return hSize;
-        }
-    }
-}
-
-/** ZSTD_buildSuperBlockEntropy_sequences() :
- *  Builds entropy for the super-block sequences.
- *  Stores symbol compression modes and fse table to fseMetadata.
- *  @return : size of fse tables or error code */
-static size_t ZSTD_buildSuperBlockEntropy_sequences(seqStore_t* seqStorePtr,
-                                              const ZSTD_fseCTables_t* prevEntropy,
-                                                    ZSTD_fseCTables_t* nextEntropy,
-                                              const ZSTD_CCtx_params* cctxParams,
-                                                    ZSTD_fseCTablesMetadata_t* fseMetadata,
-                                                    void* workspace, size_t wkspSize)
-{
-    BYTE* const wkspStart = (BYTE*)workspace;
-    BYTE* const wkspEnd = wkspStart + wkspSize;
-    BYTE* const countWkspStart = wkspStart;
-    unsigned* const countWksp = (unsigned*)workspace;
-    const size_t countWkspSize = (MaxSeq + 1) * sizeof(unsigned);
-    BYTE* const cTableWksp = countWkspStart + countWkspSize;
-    const size_t cTableWkspSize = wkspEnd-cTableWksp;
-    ZSTD_strategy const strategy = cctxParams->cParams.strategy;
-    FSE_CTable* CTable_LitLength = nextEntropy->litlengthCTable;
-    FSE_CTable* CTable_OffsetBits = nextEntropy->offcodeCTable;
-    FSE_CTable* CTable_MatchLength = nextEntropy->matchlengthCTable;
-    const BYTE* const ofCodeTable = seqStorePtr->ofCode;
-    const BYTE* const llCodeTable = seqStorePtr->llCode;
-    const BYTE* const mlCodeTable = seqStorePtr->mlCode;
-    size_t const nbSeq = seqStorePtr->sequences - seqStorePtr->sequencesStart;
-    BYTE* const ostart = fseMetadata->fseTablesBuffer;
-    BYTE* const oend = ostart + sizeof(fseMetadata->fseTablesBuffer);
-    BYTE* op = ostart;
-
-    assert(cTableWkspSize >= (1 << MaxFSELog) * sizeof(FSE_FUNCTION_TYPE));
-    DEBUGLOG(5, "ZSTD_buildSuperBlockEntropy_sequences (nbSeq=%zu)", nbSeq);
-    memset(workspace, 0, wkspSize);
-
-    fseMetadata->lastCountSize = 0;
-    /* convert length/distances into codes */
-    ZSTD_seqToCodes(seqStorePtr);
-    /* build CTable for Literal Lengths */
-    {   U32 LLtype;
-        unsigned max = MaxLL;
-        size_t const mostFrequent = HIST_countFast_wksp(countWksp, &max, llCodeTable, nbSeq, workspace, wkspSize);  /* can't fail */
-        DEBUGLOG(5, "Building LL table");
-        nextEntropy->litlength_repeatMode = prevEntropy->litlength_repeatMode;
-        LLtype = ZSTD_selectEncodingType(&nextEntropy->litlength_repeatMode,
-                                        countWksp, max, mostFrequent, nbSeq,
-                                        LLFSELog, prevEntropy->litlengthCTable,
-                                        LL_defaultNorm, LL_defaultNormLog,
-                                        ZSTD_defaultAllowed, strategy);
-        assert(set_basic < set_compressed && set_rle < set_compressed);
-        assert(!(LLtype < set_compressed && nextEntropy->litlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */
-        {   size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_LitLength, LLFSELog, (symbolEncodingType_e)LLtype,
-                                                    countWksp, max, llCodeTable, nbSeq, LL_defaultNorm, LL_defaultNormLog, MaxLL,
-                                                    prevEntropy->litlengthCTable, sizeof(prevEntropy->litlengthCTable),
-                                                    cTableWksp, cTableWkspSize);
-            FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for LitLens failed");
-            if (LLtype == set_compressed)
-                fseMetadata->lastCountSize = countSize;
-            op += countSize;
-            fseMetadata->llType = (symbolEncodingType_e) LLtype;
-    }   }
-    /* build CTable for Offsets */
-    {   U32 Offtype;
-        unsigned max = MaxOff;
-        size_t const mostFrequent = HIST_countFast_wksp(countWksp, &max, ofCodeTable, nbSeq, workspace, wkspSize);  /* can't fail */
-        /* We can only use the basic table if max <= DefaultMaxOff, otherwise the offsets are too large */
-        ZSTD_defaultPolicy_e const defaultPolicy = (max <= DefaultMaxOff) ? ZSTD_defaultAllowed : ZSTD_defaultDisallowed;
-        DEBUGLOG(5, "Building OF table");
-        nextEntropy->offcode_repeatMode = prevEntropy->offcode_repeatMode;
-        Offtype = ZSTD_selectEncodingType(&nextEntropy->offcode_repeatMode,
-                                        countWksp, max, mostFrequent, nbSeq,
-                                        OffFSELog, prevEntropy->offcodeCTable,
-                                        OF_defaultNorm, OF_defaultNormLog,
-                                        defaultPolicy, strategy);
-        assert(!(Offtype < set_compressed && nextEntropy->offcode_repeatMode != FSE_repeat_none)); /* We don't copy tables */
-        {   size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_OffsetBits, OffFSELog, (symbolEncodingType_e)Offtype,
-                                                    countWksp, max, ofCodeTable, nbSeq, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff,
-                                                    prevEntropy->offcodeCTable, sizeof(prevEntropy->offcodeCTable),
-                                                    cTableWksp, cTableWkspSize);
-            FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for Offsets failed");
-            if (Offtype == set_compressed)
-                fseMetadata->lastCountSize = countSize;
-            op += countSize;
-            fseMetadata->ofType = (symbolEncodingType_e) Offtype;
-    }   }
-    /* build CTable for MatchLengths */
-    {   U32 MLtype;
-        unsigned max = MaxML;
-        size_t const mostFrequent = HIST_countFast_wksp(countWksp, &max, mlCodeTable, nbSeq, workspace, wkspSize);   /* can't fail */
-        DEBUGLOG(5, "Building ML table (remaining space : %i)", (int)(oend-op));
-        nextEntropy->matchlength_repeatMode = prevEntropy->matchlength_repeatMode;
-        MLtype = ZSTD_selectEncodingType(&nextEntropy->matchlength_repeatMode,
-                                        countWksp, max, mostFrequent, nbSeq,
-                                        MLFSELog, prevEntropy->matchlengthCTable,
-                                        ML_defaultNorm, ML_defaultNormLog,
-                                        ZSTD_defaultAllowed, strategy);
-        assert(!(MLtype < set_compressed && nextEntropy->matchlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */
-        {   size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_MatchLength, MLFSELog, (symbolEncodingType_e)MLtype,
-                                                    countWksp, max, mlCodeTable, nbSeq, ML_defaultNorm, ML_defaultNormLog, MaxML,
-                                                    prevEntropy->matchlengthCTable, sizeof(prevEntropy->matchlengthCTable),
-                                                    cTableWksp, cTableWkspSize);
-            FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for MatchLengths failed");
-            if (MLtype == set_compressed)
-                fseMetadata->lastCountSize = countSize;
-            op += countSize;
-            fseMetadata->mlType = (symbolEncodingType_e) MLtype;
-    }   }
-    assert((size_t) (op-ostart) <= sizeof(fseMetadata->fseTablesBuffer));
-    return op-ostart;
-}
-
-
-/** ZSTD_buildSuperBlockEntropy() :
- *  Builds entropy for the super-block.
- *  @return : 0 on success or error code */
-static size_t
-ZSTD_buildSuperBlockEntropy(seqStore_t* seqStorePtr,
-                      const ZSTD_entropyCTables_t* prevEntropy,
-                            ZSTD_entropyCTables_t* nextEntropy,
-                      const ZSTD_CCtx_params* cctxParams,
-                            ZSTD_entropyCTablesMetadata_t* entropyMetadata,
-                            void* workspace, size_t wkspSize)
-{
-    size_t const litSize = seqStorePtr->lit - seqStorePtr->litStart;
-    DEBUGLOG(5, "ZSTD_buildSuperBlockEntropy");
-    entropyMetadata->hufMetadata.hufDesSize =
-        ZSTD_buildSuperBlockEntropy_literal(seqStorePtr->litStart, litSize,
-                                            &prevEntropy->huf, &nextEntropy->huf,
-                                            &entropyMetadata->hufMetadata,
-                                            ZSTD_disableLiteralsCompression(cctxParams),
-                                            workspace, wkspSize);
-    FORWARD_IF_ERROR(entropyMetadata->hufMetadata.hufDesSize, "ZSTD_buildSuperBlockEntropy_literal failed");
-    entropyMetadata->fseMetadata.fseTablesSize =
-        ZSTD_buildSuperBlockEntropy_sequences(seqStorePtr,
-                                              &prevEntropy->fse, &nextEntropy->fse,
-                                              cctxParams,
-                                              &entropyMetadata->fseMetadata,
-                                              workspace, wkspSize);
-    FORWARD_IF_ERROR(entropyMetadata->fseMetadata.fseTablesSize, "ZSTD_buildSuperBlockEntropy_sequences failed");
-    return 0;
-}
-
 /** ZSTD_compressSubBlock_literal() :
  *  Compresses literals section for a sub-block.
  *  When we have to write the Huffman table we will sometimes choose a header
@@ -304,7 +26,7 @@ ZSTD_buildSuperBlockEntropy(seqStore_t* seqStorePtr,
  *  before we know the table size + compressed size, so we have a bound on the
  *  table size. If we guessed incorrectly, we fall back to uncompressed literals.
  *
- *  We write the header when writeEntropy=1 and set entropyWrriten=1 when we succeeded
+ *  We write the header when writeEntropy=1 and set entropyWritten=1 when we succeeded
  *  in writing the header, otherwise it is set to 0.
  *
  *  hufMetadata->hType has literals block type info.
@@ -348,7 +70,7 @@ static size_t ZSTD_compressSubBlock_literal(const HUF_CElt* hufTable,
     assert(hufMetadata->hType == set_compressed || hufMetadata->hType == set_repeat);
 
     if (writeEntropy && hufMetadata->hType == set_compressed) {
-        memcpy(op, hufMetadata->hufDesBuffer, hufMetadata->hufDesSize);
+        ZSTD_memcpy(op, hufMetadata->hufDesBuffer, hufMetadata->hufDesSize);
         op += hufMetadata->hufDesSize;
         cLitSize += hufMetadata->hufDesSize;
         DEBUGLOG(5, "ZSTD_compressSubBlock_literal (hSize=%zu)", hufMetadata->hufDesSize);
@@ -410,6 +132,7 @@ static size_t ZSTD_seqDecompressedSize(seqStore_t const* seqStore, const seqDef*
     const seqDef* sp = sstart;
     size_t matchLengthSum = 0;
     size_t litLengthSum = 0;
+    (void)(litLengthSum); /* suppress unused variable warning on some environments */
     while (send-sp > 0) {
         ZSTD_sequenceLength const seqLen = ZSTD_getSequenceLength(seqStore, sp);
         litLengthSum += seqLen.litLength;
@@ -474,7 +197,7 @@ static size_t ZSTD_compressSubBlock_sequences(const ZSTD_fseCTables_t* fseTables
         const U32 MLtype = fseMetadata->mlType;
         DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (fseTablesSize=%zu)", fseMetadata->fseTablesSize);
         *seqHead = (BYTE)((LLtype<<6) + (Offtype<<4) + (MLtype<<2));
-        memcpy(op, fseMetadata->fseTablesBuffer, fseMetadata->fseTablesSize);
+        ZSTD_memcpy(op, fseMetadata->fseTablesBuffer, fseMetadata->fseTablesSize);
         op += fseMetadata->fseTablesSize;
     } else {
         const U32 repeat = set_repeat;
@@ -602,8 +325,8 @@ static size_t ZSTD_estimateSubBlockSize_literal(const BYTE* literals, size_t lit
 static size_t ZSTD_estimateSubBlockSize_symbolType(symbolEncodingType_e type,
                         const BYTE* codeTable, unsigned maxCode,
                         size_t nbSeq, const FSE_CTable* fseCTable,
-                        const U32* additionalBits,
-                        short const* defaultNorm, U32 defaultNormLog,
+                        const U8* additionalBits,
+                        short const* defaultNorm, U32 defaultNormLog, U32 defaultMax,
                         void* workspace, size_t wkspSize)
 {
     unsigned* const countWksp = (unsigned*)workspace;
@@ -615,7 +338,11 @@ static size_t ZSTD_estimateSubBlockSize_symbolType(symbolEncodingType_e type,
 
     HIST_countFast_wksp(countWksp, &max, codeTable, nbSeq, workspace, wkspSize);  /* can't fail */
     if (type == set_basic) {
-        cSymbolTypeSizeEstimateInBits = ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, countWksp, max);
+        /* We selected this encoding type, so it must be valid. */
+        assert(max <= defaultMax);
+        cSymbolTypeSizeEstimateInBits = max <= defaultMax
+                ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, countWksp, max)
+                : ERROR(GENERIC);
     } else if (type == set_rle) {
         cSymbolTypeSizeEstimateInBits = 0;
     } else if (type == set_compressed || type == set_repeat) {
@@ -639,19 +366,20 @@ static size_t ZSTD_estimateSubBlockSize_sequences(const BYTE* ofCodeTable,
                                                   void* workspace, size_t wkspSize,
                                                   int writeEntropy)
 {
-    size_t sequencesSectionHeaderSize = 3; /* Use hard coded size of 3 bytes */
+    size_t const sequencesSectionHeaderSize = 3; /* Use hard coded size of 3 bytes */
     size_t cSeqSizeEstimate = 0;
+    if (nbSeq == 0) return sequencesSectionHeaderSize;
     cSeqSizeEstimate += ZSTD_estimateSubBlockSize_symbolType(fseMetadata->ofType, ofCodeTable, MaxOff,
                                          nbSeq, fseTables->offcodeCTable, NULL,
-                                         OF_defaultNorm, OF_defaultNormLog,
+                                         OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff,
                                          workspace, wkspSize);
     cSeqSizeEstimate += ZSTD_estimateSubBlockSize_symbolType(fseMetadata->llType, llCodeTable, MaxLL,
                                          nbSeq, fseTables->litlengthCTable, LL_bits,
-                                         LL_defaultNorm, LL_defaultNormLog,
+                                         LL_defaultNorm, LL_defaultNormLog, MaxLL,
                                          workspace, wkspSize);
     cSeqSizeEstimate += ZSTD_estimateSubBlockSize_symbolType(fseMetadata->mlType, mlCodeTable, MaxML,
                                          nbSeq, fseTables->matchlengthCTable, ML_bits,
-                                         ML_defaultNorm, ML_defaultNormLog,
+                                         ML_defaultNorm, ML_defaultNormLog, MaxML,
                                          workspace, wkspSize);
     if (writeEntropy) cSeqSizeEstimate += fseMetadata->fseTablesSize;
     return cSeqSizeEstimate + sequencesSectionHeaderSize;
@@ -747,7 +475,7 @@ static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr,
         /* I think there is an optimization opportunity here.
          * Calling ZSTD_estimateSubBlockSize for every sequence can be wasteful
          * since it recalculates estimate from scratch.
-         * For example, it would recount literal distribution and symbol codes everytime.
+         * For example, it would recount literal distribution and symbol codes every time.
          */
         cBlockSizeEstimate = ZSTD_estimateSubBlockSize(lp, litSize, ofCodePtr, llCodePtr, mlCodePtr, seqCount,
                                                        &nextCBlock->entropy, entropyMetadata,
@@ -790,7 +518,7 @@ static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr,
     } while (!lastSequence);
     if (writeLitEntropy) {
         DEBUGLOG(5, "ZSTD_compressSubBlock_multi has literal entropy tables unwritten");
-        memcpy(&nextCBlock->entropy.huf, &prevCBlock->entropy.huf, sizeof(prevCBlock->entropy.huf));
+        ZSTD_memcpy(&nextCBlock->entropy.huf, &prevCBlock->entropy.huf, sizeof(prevCBlock->entropy.huf));
     }
     if (writeSeqEntropy && ZSTD_needSequenceEntropyTables(&entropyMetadata->fseMetadata)) {
         /* If we haven't written our entropy tables, then we've violated our contract and
@@ -809,11 +537,11 @@ static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr,
         if (sp < send) {
             seqDef const* seq;
             repcodes_t rep;
-            memcpy(&rep, prevCBlock->rep, sizeof(rep)); 
+            ZSTD_memcpy(&rep, prevCBlock->rep, sizeof(rep));
             for (seq = sstart; seq < sp; ++seq) {
                 rep = ZSTD_updateRep(rep.rep, seq->offset - 1, ZSTD_getSequenceLength(seqStorePtr, seq).litLength == 0);
             }
-            memcpy(nextCBlock->rep, &rep, sizeof(rep));
+            ZSTD_memcpy(nextCBlock->rep, &rep, sizeof(rep));
         }
     }
     DEBUGLOG(5, "ZSTD_compressSubBlock_multi compressed");
@@ -826,12 +554,12 @@ size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc,
                                unsigned lastBlock) {
     ZSTD_entropyCTablesMetadata_t entropyMetadata;
 
-    FORWARD_IF_ERROR(ZSTD_buildSuperBlockEntropy(&zc->seqStore,
+    FORWARD_IF_ERROR(ZSTD_buildBlockEntropyStats(&zc->seqStore,
           &zc->blockState.prevCBlock->entropy,
           &zc->blockState.nextCBlock->entropy,
           &zc->appliedParams,
           &entropyMetadata,
-          zc->entropyWorkspace, HUF_WORKSPACE_SIZE /* statically allocated in resetCCtx */), "");
+          zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */), "");
 
     return ZSTD_compressSubBlock_multi(&zc->seqStore,
             zc->blockState.prevCBlock,
@@ -841,5 +569,5 @@ size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc,
             dst, dstCapacity,
             src, srcSize,
             zc->bmi2, lastBlock,
-            zc->entropyWorkspace, HUF_WORKSPACE_SIZE /* statically allocated in resetCCtx */);
+            zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */);
 }

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

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc.
+ * Copyright (c) Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the