multi_compress 0.3.2 → 0.3.3

data/ext/multi_compress/vendor/zstd/lib/compress/zstd_compress_literals.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -13,11 +13,36 @@
  ***************************************/
 #include "zstd_compress_literals.h"
 
+
+/* **************************************************************
+*  Debug Traces
+****************************************************************/
+#if DEBUGLEVEL >= 2
+
+static size_t showHexa(const void* src, size_t srcSize)
+{
+    const BYTE* const ip = (const BYTE*)src;
+    size_t u;
+    for (u=0; u<srcSize; u++) {
+        RAWLOG(5, " %02X", ip[u]); (void)ip;
+    }
+    RAWLOG(5, " \n");
+    return srcSize;
+}
+
+#endif
+
+
+/* **************************************************************
+*  Literals compression - special cases
+****************************************************************/
 size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
 {
     BYTE* const ostart = (BYTE*)dst;
     U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
 
+    DEBUGLOG(5, "ZSTD_noCompressLiterals: srcSize=%zu, dstCapacity=%zu", srcSize, dstCapacity);
+
     RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall, "");
 
     switch(flSize)
@@ -36,16 +61,30 @@ size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src,
     }
 
     ZSTD_memcpy(ostart + flSize, src, srcSize);
-    DEBUGLOG(5, "Raw literals: %u -> %u", (U32)srcSize, (U32)(srcSize + flSize));
+    DEBUGLOG(5, "Raw (uncompressed) literals: %u -> %u", (U32)srcSize, (U32)(srcSize + flSize));
     return srcSize + flSize;
 }
 
+static int allBytesIdentical(const void* src, size_t srcSize)
+{
+    assert(srcSize >= 1);
+    assert(src != NULL);
+    {   const BYTE b = ((const BYTE*)src)[0];
+        size_t p;
+        for (p=1; p<srcSize; p++) {
+            if (((const BYTE*)src)[p] != b) return 0;
+        }
+        return 1;
+    }
+}
+
 size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
 {
     BYTE* const ostart = (BYTE*)dst;
     U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
 
-    (void)dstCapacity;  /* dstCapacity already guaranteed to be >=4, hence large enough */
+    assert(dstCapacity >= 4); (void)dstCapacity;
+    assert(allBytesIdentical(src, srcSize));
 
     switch(flSize)
     {
@@ -63,28 +102,51 @@ size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void*
     }
 
     ostart[flSize] = *(const BYTE*)src;
-    DEBUGLOG(5, "RLE literals: %u -> %u", (U32)srcSize, (U32)flSize + 1);
+    DEBUGLOG(5, "RLE : Repeated Literal (%02X: %u times) -> %u bytes encoded", ((const BYTE*)src)[0], (U32)srcSize, (U32)flSize + 1);
     return flSize+1;
 }
 
-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,
-                        unsigned suspectUncompressible)
+/* ZSTD_minLiteralsToCompress() :
+ * returns minimal amount of literals
+ * for literal compression to even be attempted.
+ * Minimum is made tighter as compression strategy increases.
+ */
+static size_t
+ZSTD_minLiteralsToCompress(ZSTD_strategy strategy, HUF_repeat huf_repeat)
+{
+    assert((int)strategy >= 0);
+    assert((int)strategy <= 9);
+    /* btultra2 : min 8 bytes;
+     * then 2x larger for each successive compression strategy
+     * max threshold 64 bytes */
+    {   int const shift = MIN(9-(int)strategy, 3);
+        size_t const mintc = (huf_repeat == HUF_repeat_valid) ? 6 : (size_t)8 << shift;
+        DEBUGLOG(7, "minLiteralsToCompress = %zu", mintc);
+        return mintc;
+    }
+}
+
+size_t ZSTD_compressLiterals (
+                  void* dst, size_t dstCapacity,
+            const void* src, size_t srcSize,
+                  void* entropyWorkspace, size_t entropyWorkspaceSize,
+            const ZSTD_hufCTables_t* prevHuf,
+                  ZSTD_hufCTables_t* nextHuf,
+                  ZSTD_strategy strategy,
+                  int disableLiteralCompression,
+                  int suspectUncompressible,
+                  int bmi2)
 {
-    size_t const minGain = ZSTD_minGain(srcSize, strategy);
     size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
     BYTE*  const ostart = (BYTE*)dst;
     U32 singleStream = srcSize < 256;
-    symbolEncodingType_e hType = set_compressed;
+    SymbolEncodingType_e hType = set_compressed;
     size_t cLitSize;
 
-    DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i srcSize=%u)",
-                disableLiteralCompression, (U32)srcSize);
+    DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i, srcSize=%u, dstCapacity=%zu)",
+                disableLiteralCompression, (U32)srcSize, dstCapacity);
+
+    DEBUGLOG(6, "Completed literals listing (%zu bytes)", showHexa(src, srcSize));
 
     /* Prepare nextEntropy assuming reusing the existing table */
     ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
@@ -92,40 +154,51 @@ size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
     if (disableLiteralCompression)
         return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
 
-    /* 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) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
-    }
+    /* if too small, don't even attempt compression (speed opt) */
+    if (srcSize < ZSTD_minLiteralsToCompress(strategy, prevHuf->repeatMode))
+        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
 
     RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression");
     {   HUF_repeat repeat = prevHuf->repeatMode;
-        int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
+        int const flags = 0
+            | (bmi2 ? HUF_flags_bmi2 : 0)
+            | (strategy < ZSTD_lazy && srcSize <= 1024 ? HUF_flags_preferRepeat : 0)
+            | (strategy >= HUF_OPTIMAL_DEPTH_THRESHOLD ? HUF_flags_optimalDepth : 0)
+            | (suspectUncompressible ? HUF_flags_suspectUncompressible : 0);
+
+        typedef size_t (*huf_compress_f)(void*, size_t, const void*, size_t, unsigned, unsigned, void*, size_t, HUF_CElt*, HUF_repeat*, int);
+        huf_compress_f huf_compress;
         if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
-        cLitSize = singleStream ?
-            HUF_compress1X_repeat(
-                ostart+lhSize, dstCapacity-lhSize, src, srcSize,
-                HUF_SYMBOLVALUE_MAX, HUF_TABLELOG_DEFAULT, entropyWorkspace, entropyWorkspaceSize,
-                (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, suspectUncompressible);
+        huf_compress = singleStream ? HUF_compress1X_repeat : HUF_compress4X_repeat;
+        cLitSize = huf_compress(ostart+lhSize, dstCapacity-lhSize,
+                                src, srcSize,
+                                HUF_SYMBOLVALUE_MAX, LitHufLog,
+                                entropyWorkspace, entropyWorkspaceSize,
+                                (HUF_CElt*)nextHuf->CTable,
+                                &repeat, flags);
+        DEBUGLOG(5, "%zu literals compressed into %zu bytes (before header)", srcSize, cLitSize);
         if (repeat != HUF_repeat_none) {
             /* reused the existing table */
-            DEBUGLOG(5, "Reusing previous huffman table");
+            DEBUGLOG(5, "reusing statistics from previous huffman block");
             hType = set_repeat;
         }
     }
 
-    if ((cLitSize==0) || (cLitSize >= srcSize - minGain) || ERR_isError(cLitSize)) {
-        ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
-        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
-    }
+    {   size_t const minGain = ZSTD_minGain(srcSize, strategy);
+        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) {
-        ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
-        return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
-    }
+        /* A return value of 1 signals that the alphabet consists of a single symbol.
+         * However, in some rare circumstances, it could be the compressed size (a single byte).
+         * For that outcome to have a chance to happen, it's necessary that `srcSize < 8`.
+         * (it's also necessary to not generate statistics).
+         * Therefore, in such a case, actively check that all bytes are identical. */
+        if ((srcSize >= 8) || allBytesIdentical(src, srcSize)) {
+            ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+            return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
+    }   }
 
     if (hType == set_compressed) {
         /* using a newly constructed table */
@@ -136,16 +209,19 @@ size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
     switch(lhSize)
     {
     case 3: /* 2 - 2 - 10 - 10 */
-        {   U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
+        if (!singleStream) assert(srcSize >= MIN_LITERALS_FOR_4_STREAMS);
+        {   U32 const lhc = hType + ((U32)(!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
             MEM_writeLE24(ostart, lhc);
             break;
         }
     case 4: /* 2 - 2 - 14 - 14 */
+        assert(srcSize >= MIN_LITERALS_FOR_4_STREAMS);
         {   U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18);
             MEM_writeLE32(ostart, lhc);
             break;
         }
     case 5: /* 2 - 2 - 18 - 18 */
+        assert(srcSize >= MIN_LITERALS_FOR_4_STREAMS);
         {   U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
             MEM_writeLE32(ostart, lhc);
             ostart[4] = (BYTE)(cLitSize >> 10);

data/ext/multi_compress/vendor/zstd/lib/compress/zstd_compress_literals.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -16,16 +16,24 @@
 
 size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
 
+/* ZSTD_compressRleLiteralsBlock() :
+ * Conditions :
+ * - All bytes in @src are identical
+ * - dstCapacity >= 4 */
 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,
+/* ZSTD_compressLiterals():
+ * @entropyWorkspace: must be aligned on 4-bytes boundaries
+ * @entropyWorkspaceSize : must be >= HUF_WORKSPACE_SIZE
+ * @suspectUncompressible: sampling checks, to potentially skip huffman coding
+ */
+size_t ZSTD_compressLiterals (void* dst, size_t dstCapacity,
                         const void* src, size_t srcSize,
                               void* entropyWorkspace, size_t entropyWorkspaceSize,
-                        const int bmi2,
-                        unsigned suspectUncompressible);
+                        const ZSTD_hufCTables_t* prevHuf,
+                              ZSTD_hufCTables_t* nextHuf,
+                              ZSTD_strategy strategy, int disableLiteralCompression,
+                              int suspectUncompressible,
+                              int bmi2);
 
 #endif /* ZSTD_COMPRESS_LITERALS_H */

data/ext/multi_compress/vendor/zstd/lib/compress/zstd_compress_sequences.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -58,7 +58,7 @@ 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.
+     * compressibility.
      */
     return nbSeq >= 2048;
 }
@@ -153,20 +153,20 @@ size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
     return cost >> 8;
 }
 
-symbolEncodingType_e
+SymbolEncodingType_e
 ZSTD_selectEncodingType(
         FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
         size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
         FSE_CTable const* prevCTable,
         short const* defaultNorm, U32 defaultNormLog,
-        ZSTD_defaultPolicy_e const isDefaultAllowed,
+        ZSTD_DefaultPolicy_e const isDefaultAllowed,
         ZSTD_strategy const strategy)
 {
     ZSTD_STATIC_ASSERT(ZSTD_defaultDisallowed == 0 && ZSTD_defaultAllowed != 0);
     if (mostFrequent == nbSeq) {
         *repeatMode = FSE_repeat_none;
         if (isDefaultAllowed && nbSeq <= 2) {
-            /* Prefer set_basic over set_rle when there are 2 or less symbols,
+            /* Prefer set_basic over set_rle when there are 2 or fewer symbols,
              * since RLE uses 1 byte, but set_basic uses 5-6 bits per symbol.
              * If basic encoding isn't possible, always choose RLE.
              */
@@ -241,7 +241,7 @@ typedef struct {
 
 size_t
 ZSTD_buildCTable(void* dst, size_t dstCapacity,
-                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
+                FSE_CTable* nextCTable, U32 FSELog, SymbolEncodingType_e type,
                 unsigned* count, U32 max,
                 const BYTE* codeTable, size_t nbSeq,
                 const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
@@ -293,7 +293,7 @@ ZSTD_encodeSequences_body(
             FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
             FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
             FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets)
+            SeqDef const* sequences, size_t nbSeq, int longOffsets)
 {
     BIT_CStream_t blockStream;
     FSE_CState_t  stateMatchLength;
@@ -387,7 +387,7 @@ ZSTD_encodeSequences_default(
             FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
             FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
             FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets)
+            SeqDef const* sequences, size_t nbSeq, int longOffsets)
 {
     return ZSTD_encodeSequences_body(dst, dstCapacity,
                                     CTable_MatchLength, mlCodeTable,
@@ -405,7 +405,7 @@ ZSTD_encodeSequences_bmi2(
             FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
             FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
             FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets)
+            SeqDef const* sequences, size_t nbSeq, int longOffsets)
 {
     return ZSTD_encodeSequences_body(dst, dstCapacity,
                                     CTable_MatchLength, mlCodeTable,
@@ -421,7 +421,7 @@ size_t ZSTD_encodeSequences(
             FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
             FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
             FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
+            SeqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
 {
     DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
 #if DYNAMIC_BMI2

data/ext/multi_compress/vendor/zstd/lib/compress/zstd_compress_sequences.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -11,26 +11,27 @@
 #ifndef ZSTD_COMPRESS_SEQUENCES_H
 #define ZSTD_COMPRESS_SEQUENCES_H
 
+#include "zstd_compress_internal.h" /* SeqDef */
 #include "../common/fse.h" /* FSE_repeat, FSE_CTable */
-#include "../common/zstd_internal.h" /* symbolEncodingType_e, ZSTD_strategy */
+#include "../common/zstd_internal.h" /* SymbolEncodingType_e, ZSTD_strategy */
 
 typedef enum {
     ZSTD_defaultDisallowed = 0,
     ZSTD_defaultAllowed = 1
-} ZSTD_defaultPolicy_e;
+} ZSTD_DefaultPolicy_e;
 
-symbolEncodingType_e
+SymbolEncodingType_e
 ZSTD_selectEncodingType(
         FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
         size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
         FSE_CTable const* prevCTable,
         short const* defaultNorm, U32 defaultNormLog,
-        ZSTD_defaultPolicy_e const isDefaultAllowed,
+        ZSTD_DefaultPolicy_e const isDefaultAllowed,
         ZSTD_strategy const strategy);
 
 size_t
 ZSTD_buildCTable(void* dst, size_t dstCapacity,
-                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
+                FSE_CTable* nextCTable, U32 FSELog, SymbolEncodingType_e type,
                 unsigned* count, U32 max,
                 const BYTE* codeTable, size_t nbSeq,
                 const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
@@ -42,7 +43,7 @@ size_t ZSTD_encodeSequences(
             FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
             FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
             FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2);
+            SeqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2);
 
 size_t ZSTD_fseBitCost(
     FSE_CTable const* ctable,