diff --git a/build/VS2008/fullbench/fullbench.vcproj b/build/VS2008/fullbench/fullbench.vcproj
index 2246262d..cd9391ec 100644
--- a/build/VS2008/fullbench/fullbench.vcproj
+++ b/build/VS2008/fullbench/fullbench.vcproj
@@ -364,6 +364,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.c"
>
+
+
+
+
@@ -494,6 +502,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.h"
>
+
+
+
+
diff --git a/build/VS2008/fuzzer/fuzzer.vcproj b/build/VS2008/fuzzer/fuzzer.vcproj
index c81791f4..5f10bbe7 100644
--- a/build/VS2008/fuzzer/fuzzer.vcproj
+++ b/build/VS2008/fuzzer/fuzzer.vcproj
@@ -412,6 +412,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.c"
>
+
+
+
+
@@ -530,6 +538,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.h"
>
+
+
+
+
diff --git a/build/VS2008/zstd/zstd.vcproj b/build/VS2008/zstd/zstd.vcproj
index 745f2e87..34ccb6f4 100644
--- a/build/VS2008/zstd/zstd.vcproj
+++ b/build/VS2008/zstd/zstd.vcproj
@@ -424,6 +424,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.c"
>
+
+
+
+
@@ -610,6 +618,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.h"
>
+
+
+
+
diff --git a/build/VS2008/zstdlib/zstdlib.vcproj b/build/VS2008/zstdlib/zstdlib.vcproj
index 4dc91516..be46d351 100644
--- a/build/VS2008/zstdlib/zstdlib.vcproj
+++ b/build/VS2008/zstdlib/zstdlib.vcproj
@@ -396,6 +396,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.c"
>
+
+
+
+
@@ -542,6 +550,14 @@
RelativePath="..\..\..\lib\compress\zstd_compress.h"
>
+
+
+
+
diff --git a/build/VS2010/fullbench/fullbench.vcxproj b/build/VS2010/fullbench/fullbench.vcxproj
index 57ee3371..105c692b 100644
--- a/build/VS2010/fullbench/fullbench.vcxproj
+++ b/build/VS2010/fullbench/fullbench.vcxproj
@@ -167,6 +167,8 @@
+
+
@@ -193,6 +195,8 @@
+
+
diff --git a/build/VS2010/fuzzer/fuzzer.vcxproj b/build/VS2010/fuzzer/fuzzer.vcxproj
index de649de1..7f7e404d 100644
--- a/build/VS2010/fuzzer/fuzzer.vcxproj
+++ b/build/VS2010/fuzzer/fuzzer.vcxproj
@@ -167,6 +167,8 @@
+
+
@@ -196,6 +198,8 @@
+
+
diff --git a/build/VS2010/libzstd-dll/libzstd-dll.vcxproj b/build/VS2010/libzstd-dll/libzstd-dll.vcxproj
index bcde584b..840d1ec3 100644
--- a/build/VS2010/libzstd-dll/libzstd-dll.vcxproj
+++ b/build/VS2010/libzstd-dll/libzstd-dll.vcxproj
@@ -31,6 +31,8 @@
+
+
@@ -78,6 +80,8 @@
+
+
diff --git a/build/VS2010/libzstd/libzstd.vcxproj b/build/VS2010/libzstd/libzstd.vcxproj
index 6b985baf..b84d45b9 100644
--- a/build/VS2010/libzstd/libzstd.vcxproj
+++ b/build/VS2010/libzstd/libzstd.vcxproj
@@ -31,6 +31,8 @@
+
+
@@ -78,6 +80,8 @@
+
+
diff --git a/build/VS2010/zstd/zstd.vcxproj b/build/VS2010/zstd/zstd.vcxproj
index 6e7ddca1..d65f55b3 100644
--- a/build/VS2010/zstd/zstd.vcxproj
+++ b/build/VS2010/zstd/zstd.vcxproj
@@ -32,6 +32,8 @@
+
+
@@ -75,6 +77,8 @@
+
+
diff --git a/build/cmake/lib/CMakeLists.txt b/build/cmake/lib/CMakeLists.txt
index e415c159..5c0802bc 100644
--- a/build/cmake/lib/CMakeLists.txt
+++ b/build/cmake/lib/CMakeLists.txt
@@ -20,62 +20,32 @@ endif()
# Define library directory, where sources and header files are located
include_directories(${LIBRARY_DIR} ${LIBRARY_DIR}/common)
+file(GLOB CommonSources ${LIBRARY_DIR}/common/*.c)
+file(GLOB CompressSources ${LIBRARY_DIR}/compress/*.c)
+file(GLOB DecompressSources ${LIBRARY_DIR}/decompress/*.c)
+file(GLOB DictBuilderSources ${LIBRARY_DIR}/dictBuilder/*.c)
+file(GLOB DeprecatedSources ${LIBRARY_DIR}/deprecated/*.c)
+
set(Sources
- ${LIBRARY_DIR}/common/entropy_common.c
- ${LIBRARY_DIR}/common/fse_decompress.c
- ${LIBRARY_DIR}/common/threading.c
- ${LIBRARY_DIR}/common/pool.c
- ${LIBRARY_DIR}/common/zstd_common.c
- ${LIBRARY_DIR}/common/error_private.c
- ${LIBRARY_DIR}/common/xxhash.c
- ${LIBRARY_DIR}/compress/hist.c
- ${LIBRARY_DIR}/compress/fse_compress.c
- ${LIBRARY_DIR}/compress/huf_compress.c
- ${LIBRARY_DIR}/compress/zstd_compress.c
- ${LIBRARY_DIR}/compress/zstdmt_compress.c
- ${LIBRARY_DIR}/compress/zstd_fast.c
- ${LIBRARY_DIR}/compress/zstd_double_fast.c
- ${LIBRARY_DIR}/compress/zstd_lazy.c
- ${LIBRARY_DIR}/compress/zstd_opt.c
- ${LIBRARY_DIR}/compress/zstd_ldm.c
- ${LIBRARY_DIR}/decompress/huf_decompress.c
- ${LIBRARY_DIR}/decompress/zstd_decompress.c
- ${LIBRARY_DIR}/decompress/zstd_decompress_block.c
- ${LIBRARY_DIR}/decompress/zstd_ddict.c
- ${LIBRARY_DIR}/dictBuilder/cover.c
- ${LIBRARY_DIR}/dictBuilder/fastcover.c
- ${LIBRARY_DIR}/dictBuilder/divsufsort.c
- ${LIBRARY_DIR}/dictBuilder/zdict.c
- ${LIBRARY_DIR}/deprecated/zbuff_common.c
- ${LIBRARY_DIR}/deprecated/zbuff_compress.c
- ${LIBRARY_DIR}/deprecated/zbuff_decompress.c)
+ ${CommonSources}
+ ${CompressSources}
+ ${DecompressSources}
+ ${DictBuilderSources}
+ ${DeprecatedSources})
+
+file(GLOB CommonHeaders ${LIBRARY_DIR}/common/*.h)
+file(GLOB CompressHeaders ${LIBRARY_DIR}/compress/*.h)
+file(GLOB DecompressHeaders ${LIBRARY_DIR}/decompress/*.h)
+file(GLOB DictBuilderHeaders ${LIBRARY_DIR}/dictBuilder/*.h)
+file(GLOB DeprecatedHeaders ${LIBRARY_DIR}/deprecated/*.h)
set(Headers
${LIBRARY_DIR}/zstd.h
- ${LIBRARY_DIR}/common/debug.h
- ${LIBRARY_DIR}/common/pool.h
- ${LIBRARY_DIR}/common/threading.h
- ${LIBRARY_DIR}/common/bitstream.h
- ${LIBRARY_DIR}/common/error_private.h
- ${LIBRARY_DIR}/common/zstd_errors.h
- ${LIBRARY_DIR}/common/fse.h
- ${LIBRARY_DIR}/common/huf.h
- ${LIBRARY_DIR}/common/mem.h
- ${LIBRARY_DIR}/common/zstd_internal.h
- ${LIBRARY_DIR}/compress/hist.h
- ${LIBRARY_DIR}/compress/zstd_compress_internal.h
- ${LIBRARY_DIR}/compress/zstd_fast.h
- ${LIBRARY_DIR}/compress/zstd_double_fast.h
- ${LIBRARY_DIR}/compress/zstd_lazy.h
- ${LIBRARY_DIR}/compress/zstd_opt.h
- ${LIBRARY_DIR}/compress/zstd_ldm.h
- ${LIBRARY_DIR}/compress/zstdmt_compress.h
- ${LIBRARY_DIR}/decompress/zstd_decompress_internal.h
- ${LIBRARY_DIR}/decompress/zstd_decompress_block.h
- ${LIBRARY_DIR}/decompress/zstd_ddict.h
- ${LIBRARY_DIR}/dictBuilder/zdict.h
- ${LIBRARY_DIR}/dictBuilder/cover.h
- ${LIBRARY_DIR}/deprecated/zbuff.h)
+ ${CommonHeaders}
+ ${CompressHeaders}
+ ${DecompressHeaders}
+ ${DictBuilderHeaders}
+ ${DeprecatedHeaders})
if (ZSTD_LEGACY_SUPPORT)
set(LIBRARY_LEGACY_DIR ${LIBRARY_DIR}/legacy)
diff --git a/build/meson/lib/meson.build b/build/meson/lib/meson.build
index f8014c62..ef669327 100644
--- a/build/meson/lib/meson.build
+++ b/build/meson/lib/meson.build
@@ -28,6 +28,8 @@ libzstd_sources = [join_paths(zstd_rootdir, 'lib/common/entropy_common.c'),
join_paths(zstd_rootdir, 'lib/compress/fse_compress.c'),
join_paths(zstd_rootdir, 'lib/compress/huf_compress.c'),
join_paths(zstd_rootdir, 'lib/compress/zstd_compress.c'),
+ join_paths(zstd_rootdir, 'lib/compress/zstd_compress_literals.c'),
+ join_paths(zstd_rootdir, 'lib/compress/zstd_compress_sequences.c'),
join_paths(zstd_rootdir, 'lib/compress/zstdmt_compress.c'),
join_paths(zstd_rootdir, 'lib/compress/zstd_fast.c'),
join_paths(zstd_rootdir, 'lib/compress/zstd_double_fast.c'),
diff --git a/lib/compress/zstd_compress.c b/lib/compress/zstd_compress.c
index 14765125..8ad15e1c 100644
--- a/lib/compress/zstd_compress.c
+++ b/lib/compress/zstd_compress.c
@@ -21,6 +21,8 @@
#define HUF_STATIC_LINKING_ONLY
#include "huf.h"
#include "zstd_compress_internal.h"
+#include "zstd_compress_sequences.h"
+#include "zstd_compress_literals.h"
#include "zstd_fast.h"
#include "zstd_double_fast.h"
#include "zstd_lazy.h"
@@ -397,18 +399,6 @@ ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param)
}
}
-/* ZSTD_cParam_withinBounds:
- * @return 1 if value is within cParam bounds,
- * 0 otherwise */
-static int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value)
-{
- ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam);
- if (ZSTD_isError(bounds.error)) return 0;
- if (value < bounds.lowerBound) return 0;
- if (value > bounds.upperBound) return 0;
- return 1;
-}
-
/* ZSTD_cParam_clampBounds:
* Clamps the value into the bounded range.
*/
@@ -1903,155 +1893,6 @@ static size_t ZSTD_noCompressBlock (void* dst, size_t dstCapacity, const void* s
return ZSTD_blockHeaderSize + srcSize;
}
-static size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
-{
- BYTE* const ostart = (BYTE* const)dst;
- U32 const flSize = 1 + (srcSize>31) + (srcSize>4095);
-
- RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall);
-
- switch(flSize)
- {
- case 1: /* 2 - 1 - 5 */
- ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3));
- break;
- case 2: /* 2 - 2 - 12 */
- MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
- break;
- case 3: /* 2 - 2 - 20 */
- MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
- break;
- default: /* not necessary : flSize is {1,2,3} */
- assert(0);
- }
-
- memcpy(ostart + flSize, src, srcSize);
- return srcSize + flSize;
-}
-
-static size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
-{
- BYTE* const ostart = (BYTE* const)dst;
- U32 const flSize = 1 + (srcSize>31) + (srcSize>4095);
-
- (void)dstCapacity; /* dstCapacity already guaranteed to be >=4, hence large enough */
-
- switch(flSize)
- {
- case 1: /* 2 - 1 - 5 */
- ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3));
- break;
- case 2: /* 2 - 2 - 12 */
- MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
- break;
- case 3: /* 2 - 2 - 20 */
- MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
- break;
- default: /* not necessary : flSize is {1,2,3} */
- assert(0);
- }
-
- ostart[flSize] = *(const BYTE*)src;
- return flSize+1;
-}
-
-
-/* ZSTD_minGain() :
- * minimum compression required
- * to generate a compress block or a compressed literals section.
- * note : use same formula for both situations */
-static size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat)
-{
- U32 const minlog = (strat>=ZSTD_btultra) ? (U32)(strat) - 1 : 6;
- ZSTD_STATIC_ASSERT(ZSTD_btultra == 8);
- assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat));
- return (srcSize >> minlog) + 2;
-}
-
-static 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* workspace, size_t wkspSize,
- const 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;
- size_t cLitSize;
-
- DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i)",
- disableLiteralCompression);
-
- /* Prepare nextEntropy assuming reusing the existing table */
- memcpy(nextHuf, prevHuf, sizeof(*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);
- }
-
- 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;
- if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
- cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
- workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2)
- : HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
- workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
- if (repeat != HUF_repeat_none) {
- /* reused the existing table */
- hType = set_repeat;
- }
- }
-
- if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
- memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
- return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
- }
- if (cLitSize==1) {
- memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
- return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
- }
-
- if (hType == set_compressed) {
- /* using a newly constructed table */
- nextHuf->repeatMode = HUF_repeat_check;
- }
-
- /* Build header */
- switch(lhSize)
- {
- case 3: /* 2 - 2 - 10 - 10 */
- { U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
- MEM_writeLE24(ostart, lhc);
- break;
- }
- case 4: /* 2 - 2 - 14 - 14 */
- { U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18);
- MEM_writeLE32(ostart, lhc);
- break;
- }
- case 5: /* 2 - 2 - 18 - 18 */
- { U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
- MEM_writeLE32(ostart, lhc);
- ostart[4] = (BYTE)(cLitSize >> 10);
- break;
- }
- default: /* not possible : lhSize is {3,4,5} */
- assert(0);
- }
- return lhSize+cLitSize;
-}
-
-
void ZSTD_seqToCodes(const seqStore_t* seqStorePtr)
{
const seqDef* const sequences = seqStorePtr->sequencesStart;
@@ -2074,418 +1915,6 @@ void ZSTD_seqToCodes(const seqStore_t* seqStorePtr)
mlCodeTable[seqStorePtr->longLengthPos] = MaxML;
}
-
-/**
- * -log2(x / 256) lookup table for x in [0, 256).
- * If x == 0: Return 0
- * Else: Return floor(-log2(x / 256) * 256)
- */
-static unsigned const kInverseProbabilityLog256[256] = {
- 0, 2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162,
- 1130, 1100, 1073, 1047, 1024, 1001, 980, 960, 941, 923, 906, 889,
- 874, 859, 844, 830, 817, 804, 791, 779, 768, 756, 745, 734,
- 724, 714, 704, 694, 685, 676, 667, 658, 650, 642, 633, 626,
- 618, 610, 603, 595, 588, 581, 574, 567, 561, 554, 548, 542,
- 535, 529, 523, 517, 512, 506, 500, 495, 489, 484, 478, 473,
- 468, 463, 458, 453, 448, 443, 438, 434, 429, 424, 420, 415,
- 411, 407, 402, 398, 394, 390, 386, 382, 377, 373, 370, 366,
- 362, 358, 354, 350, 347, 343, 339, 336, 332, 329, 325, 322,
- 318, 315, 311, 308, 305, 302, 298, 295, 292, 289, 286, 282,
- 279, 276, 273, 270, 267, 264, 261, 258, 256, 253, 250, 247,
- 244, 241, 239, 236, 233, 230, 228, 225, 222, 220, 217, 215,
- 212, 209, 207, 204, 202, 199, 197, 194, 192, 190, 187, 185,
- 182, 180, 178, 175, 173, 171, 168, 166, 164, 162, 159, 157,
- 155, 153, 151, 149, 146, 144, 142, 140, 138, 136, 134, 132,
- 130, 128, 126, 123, 121, 119, 117, 115, 114, 112, 110, 108,
- 106, 104, 102, 100, 98, 96, 94, 93, 91, 89, 87, 85,
- 83, 82, 80, 78, 76, 74, 73, 71, 69, 67, 66, 64,
- 62, 61, 59, 57, 55, 54, 52, 50, 49, 47, 46, 44,
- 42, 41, 39, 37, 36, 34, 33, 31, 30, 28, 26, 25,
- 23, 22, 20, 19, 17, 16, 14, 13, 11, 10, 8, 7,
- 5, 4, 2, 1,
-};
-
-
-/**
- * Returns the cost in bits of encoding the distribution described by count
- * using the entropy bound.
- */
-static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t const total)
-{
- unsigned cost = 0;
- unsigned s;
- for (s = 0; s <= max; ++s) {
- unsigned norm = (unsigned)((256 * count[s]) / total);
- if (count[s] != 0 && norm == 0)
- norm = 1;
- assert(count[s] < total);
- cost += count[s] * kInverseProbabilityLog256[norm];
- }
- return cost >> 8;
-}
-
-
-/**
- * Returns the cost in bits of encoding the distribution in count using the
- * table described by norm. The max symbol support by norm is assumed >= max.
- * norm must be valid for every symbol with non-zero probability in count.
- */
-static size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
- unsigned const* count, unsigned const max)
-{
- unsigned const shift = 8 - accuracyLog;
- size_t cost = 0;
- unsigned s;
- assert(accuracyLog <= 8);
- for (s = 0; s <= max; ++s) {
- unsigned const normAcc = norm[s] != -1 ? norm[s] : 1;
- unsigned const norm256 = normAcc << shift;
- assert(norm256 > 0);
- assert(norm256 < 256);
- cost += count[s] * kInverseProbabilityLog256[norm256];
- }
- return cost >> 8;
-}
-
-
-static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) {
- void const* ptr = ctable;
- U16 const* u16ptr = (U16 const*)ptr;
- U32 const maxSymbolValue = MEM_read16(u16ptr + 1);
- return maxSymbolValue;
-}
-
-
-/**
- * Returns the cost in bits of encoding the distribution in count using ctable.
- * Returns an error if ctable cannot represent all the symbols in count.
- */
-static size_t ZSTD_fseBitCost(
- FSE_CTable const* ctable,
- unsigned const* count,
- unsigned const max)
-{
- unsigned const kAccuracyLog = 8;
- size_t cost = 0;
- unsigned s;
- FSE_CState_t cstate;
- FSE_initCState(&cstate, ctable);
- RETURN_ERROR_IF(ZSTD_getFSEMaxSymbolValue(ctable) < max, GENERIC,
- "Repeat FSE_CTable has maxSymbolValue %u < %u",
- ZSTD_getFSEMaxSymbolValue(ctable), max);
- for (s = 0; s <= max; ++s) {
- unsigned const tableLog = cstate.stateLog;
- unsigned const badCost = (tableLog + 1) << kAccuracyLog;
- unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog);
- if (count[s] == 0)
- continue;
- RETURN_ERROR_IF(bitCost >= badCost, GENERIC,
- "Repeat FSE_CTable has Prob[%u] == 0", s);
- cost += count[s] * bitCost;
- }
- return cost >> kAccuracyLog;
-}
-
-/**
- * Returns the cost in bytes of encoding the normalized count header.
- * Returns an error if any of the helper functions return an error.
- */
-static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max,
- size_t const nbSeq, unsigned const FSELog)
-{
- 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));
- return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog);
-}
-
-
-typedef enum {
- ZSTD_defaultDisallowed = 0,
- ZSTD_defaultAllowed = 1
-} ZSTD_defaultPolicy_e;
-
-MEM_STATIC 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_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,
- * since RLE uses 1 byte, but set_basic uses 5-6 bits per symbol.
- * If basic encoding isn't possible, always choose RLE.
- */
- DEBUGLOG(5, "Selected set_basic");
- return set_basic;
- }
- DEBUGLOG(5, "Selected set_rle");
- return set_rle;
- }
- if (strategy < ZSTD_lazy) {
- if (isDefaultAllowed) {
- size_t const staticFse_nbSeq_max = 1000;
- size_t const mult = 10 - strategy;
- size_t const baseLog = 3;
- size_t const dynamicFse_nbSeq_min = (((size_t)1 << defaultNormLog) * mult) >> baseLog; /* 28-36 for offset, 56-72 for lengths */
- assert(defaultNormLog >= 5 && defaultNormLog <= 6); /* xx_DEFAULTNORMLOG */
- assert(mult <= 9 && mult >= 7);
- if ( (*repeatMode == FSE_repeat_valid)
- && (nbSeq < staticFse_nbSeq_max) ) {
- DEBUGLOG(5, "Selected set_repeat");
- return set_repeat;
- }
- if ( (nbSeq < dynamicFse_nbSeq_min)
- || (mostFrequent < (nbSeq >> (defaultNormLog-1))) ) {
- DEBUGLOG(5, "Selected set_basic");
- /* The format allows default tables to be repeated, but it isn't useful.
- * When using simple heuristics to select encoding type, we don't want
- * to confuse these tables with dictionaries. When running more careful
- * analysis, we don't need to waste time checking both repeating tables
- * and default tables.
- */
- *repeatMode = FSE_repeat_none;
- return set_basic;
- }
- }
- } else {
- size_t const basicCost = isDefaultAllowed ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, count, max) : ERROR(GENERIC);
- size_t const repeatCost = *repeatMode != FSE_repeat_none ? ZSTD_fseBitCost(prevCTable, count, max) : ERROR(GENERIC);
- size_t const NCountCost = ZSTD_NCountCost(count, max, nbSeq, FSELog);
- size_t const compressedCost = (NCountCost << 3) + ZSTD_entropyCost(count, max, nbSeq);
-
- if (isDefaultAllowed) {
- assert(!ZSTD_isError(basicCost));
- assert(!(*repeatMode == FSE_repeat_valid && ZSTD_isError(repeatCost)));
- }
- assert(!ZSTD_isError(NCountCost));
- assert(compressedCost < ERROR(maxCode));
- DEBUGLOG(5, "Estimated bit costs: basic=%u\trepeat=%u\tcompressed=%u",
- (unsigned)basicCost, (unsigned)repeatCost, (unsigned)compressedCost);
- if (basicCost <= repeatCost && basicCost <= compressedCost) {
- DEBUGLOG(5, "Selected set_basic");
- assert(isDefaultAllowed);
- *repeatMode = FSE_repeat_none;
- return set_basic;
- }
- if (repeatCost <= compressedCost) {
- DEBUGLOG(5, "Selected set_repeat");
- assert(!ZSTD_isError(repeatCost));
- return set_repeat;
- }
- assert(compressedCost < basicCost && compressedCost < repeatCost);
- }
- DEBUGLOG(5, "Selected set_compressed");
- *repeatMode = FSE_repeat_check;
- return set_compressed;
-}
-
-MEM_STATIC size_t
-ZSTD_buildCTable(void* dst, size_t dstCapacity,
- 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,
- const FSE_CTable* prevCTable, size_t prevCTableSize,
- void* workspace, size_t workspaceSize)
-{
- BYTE* op = (BYTE*)dst;
- const BYTE* const oend = op + dstCapacity;
- DEBUGLOG(6, "ZSTD_buildCTable (dstCapacity=%u)", (unsigned)dstCapacity);
-
- switch (type) {
- case set_rle:
- FORWARD_IF_ERROR(FSE_buildCTable_rle(nextCTable, (BYTE)max));
- RETURN_ERROR_IF(dstCapacity==0, dstSize_tooSmall);
- *op = codeTable[0];
- return 1;
- case set_repeat:
- memcpy(nextCTable, prevCTable, prevCTableSize);
- return 0;
- case set_basic:
- FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize)); /* note : could be pre-calculated */
- return 0;
- case set_compressed: {
- S16 norm[MaxSeq + 1];
- size_t nbSeq_1 = nbSeq;
- const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
- if (count[codeTable[nbSeq-1]] > 1) {
- count[codeTable[nbSeq-1]]--;
- 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 */
- FORWARD_IF_ERROR(NCountSize);
- FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize));
- return NCountSize;
- }
- }
- default: assert(0); RETURN_ERROR(GENERIC);
- }
-}
-
-FORCE_INLINE_TEMPLATE size_t
-ZSTD_encodeSequences_body(
- void* dst, size_t dstCapacity,
- 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)
-{
- BIT_CStream_t blockStream;
- FSE_CState_t stateMatchLength;
- FSE_CState_t stateOffsetBits;
- FSE_CState_t stateLitLength;
-
- RETURN_ERROR_IF(
- ERR_isError(BIT_initCStream(&blockStream, dst, dstCapacity)),
- dstSize_tooSmall, "not enough space remaining");
- DEBUGLOG(6, "available space for bitstream : %i (dstCapacity=%u)",
- (int)(blockStream.endPtr - blockStream.startPtr),
- (unsigned)dstCapacity);
-
- /* first symbols */
- FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]);
- FSE_initCState2(&stateOffsetBits, CTable_OffsetBits, ofCodeTable[nbSeq-1]);
- FSE_initCState2(&stateLitLength, CTable_LitLength, llCodeTable[nbSeq-1]);
- BIT_addBits(&blockStream, sequences[nbSeq-1].litLength, LL_bits[llCodeTable[nbSeq-1]]);
- if (MEM_32bits()) BIT_flushBits(&blockStream);
- BIT_addBits(&blockStream, sequences[nbSeq-1].matchLength, ML_bits[mlCodeTable[nbSeq-1]]);
- if (MEM_32bits()) BIT_flushBits(&blockStream);
- if (longOffsets) {
- U32 const ofBits = ofCodeTable[nbSeq-1];
- int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
- if (extraBits) {
- BIT_addBits(&blockStream, sequences[nbSeq-1].offset, extraBits);
- BIT_flushBits(&blockStream);
- }
- BIT_addBits(&blockStream, sequences[nbSeq-1].offset >> extraBits,
- ofBits - extraBits);
- } else {
- BIT_addBits(&blockStream, sequences[nbSeq-1].offset, ofCodeTable[nbSeq-1]);
- }
- BIT_flushBits(&blockStream);
-
- { size_t n;
- for (n=nbSeq-2 ; n= 64-7-(LLFSELog+MLFSELog+OffFSELog)))
- BIT_flushBits(&blockStream); /* (7)*/
- BIT_addBits(&blockStream, sequences[n].litLength, llBits);
- if (MEM_32bits() && ((llBits+mlBits)>24)) BIT_flushBits(&blockStream);
- BIT_addBits(&blockStream, sequences[n].matchLength, mlBits);
- if (MEM_32bits() || (ofBits+mlBits+llBits > 56)) BIT_flushBits(&blockStream);
- if (longOffsets) {
- int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
- if (extraBits) {
- BIT_addBits(&blockStream, sequences[n].offset, extraBits);
- BIT_flushBits(&blockStream); /* (7)*/
- }
- BIT_addBits(&blockStream, sequences[n].offset >> extraBits,
- ofBits - extraBits); /* 31 */
- } else {
- BIT_addBits(&blockStream, sequences[n].offset, ofBits); /* 31 */
- }
- BIT_flushBits(&blockStream); /* (7)*/
- DEBUGLOG(7, "remaining space : %i", (int)(blockStream.endPtr - blockStream.ptr));
- } }
-
- DEBUGLOG(6, "ZSTD_encodeSequences: flushing ML state with %u bits", stateMatchLength.stateLog);
- FSE_flushCState(&blockStream, &stateMatchLength);
- DEBUGLOG(6, "ZSTD_encodeSequences: flushing Off state with %u bits", stateOffsetBits.stateLog);
- FSE_flushCState(&blockStream, &stateOffsetBits);
- DEBUGLOG(6, "ZSTD_encodeSequences: flushing LL state with %u bits", stateLitLength.stateLog);
- FSE_flushCState(&blockStream, &stateLitLength);
-
- { size_t const streamSize = BIT_closeCStream(&blockStream);
- RETURN_ERROR_IF(streamSize==0, dstSize_tooSmall, "not enough space");
- return streamSize;
- }
-}
-
-static size_t
-ZSTD_encodeSequences_default(
- void* dst, size_t dstCapacity,
- 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)
-{
- return ZSTD_encodeSequences_body(dst, dstCapacity,
- CTable_MatchLength, mlCodeTable,
- CTable_OffsetBits, ofCodeTable,
- CTable_LitLength, llCodeTable,
- sequences, nbSeq, longOffsets);
-}
-
-
-#if DYNAMIC_BMI2
-
-static TARGET_ATTRIBUTE("bmi2") size_t
-ZSTD_encodeSequences_bmi2(
- void* dst, size_t dstCapacity,
- 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)
-{
- return ZSTD_encodeSequences_body(dst, dstCapacity,
- CTable_MatchLength, mlCodeTable,
- CTable_OffsetBits, ofCodeTable,
- CTable_LitLength, llCodeTable,
- sequences, nbSeq, longOffsets);
-}
-
-#endif
-
-static size_t ZSTD_encodeSequences(
- void* dst, size_t dstCapacity,
- 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)
-{
- DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
-#if DYNAMIC_BMI2
- if (bmi2) {
- return ZSTD_encodeSequences_bmi2(dst, dstCapacity,
- CTable_MatchLength, mlCodeTable,
- CTable_OffsetBits, ofCodeTable,
- CTable_LitLength, llCodeTable,
- sequences, nbSeq, longOffsets);
- }
-#endif
- (void)bmi2;
- return ZSTD_encodeSequences_default(dst, dstCapacity,
- CTable_MatchLength, mlCodeTable,
- CTable_OffsetBits, ofCodeTable,
- CTable_LitLength, llCodeTable,
- sequences, nbSeq, longOffsets);
-}
-
static int ZSTD_disableLiteralsCompression(const ZSTD_CCtx_params* cctxParams)
{
switch (cctxParams->literalCompressionMode) {
@@ -2530,8 +1959,8 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
BYTE* seqHead;
BYTE* lastNCount = NULL;
+ DEBUGLOG(5, "ZSTD_compressSequences_internal (nbSeq=%zu)", nbSeq);
ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<litStart;
diff --git a/lib/compress/zstd_compress_internal.h b/lib/compress/zstd_compress_internal.h
index 5495899b..10b59d39 100644
--- a/lib/compress/zstd_compress_internal.h
+++ b/lib/compress/zstd_compress_internal.h
@@ -307,6 +307,30 @@ MEM_STATIC U32 ZSTD_MLcode(U32 mlBase)
return (mlBase > 127) ? ZSTD_highbit32(mlBase) + ML_deltaCode : ML_Code[mlBase];
}
+/* ZSTD_cParam_withinBounds:
+ * @return 1 if value is within cParam bounds,
+ * 0 otherwise */
+MEM_STATIC int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value)
+{
+ ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam);
+ if (ZSTD_isError(bounds.error)) return 0;
+ if (value < bounds.lowerBound) return 0;
+ if (value > bounds.upperBound) return 0;
+ return 1;
+}
+
+/* ZSTD_minGain() :
+ * minimum compression required
+ * to generate a compress block or a compressed literals section.
+ * note : use same formula for both situations */
+MEM_STATIC size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat)
+{
+ U32 const minlog = (strat>=ZSTD_btultra) ? (U32)(strat) - 1 : 6;
+ ZSTD_STATIC_ASSERT(ZSTD_btultra == 8);
+ assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat));
+ return (srcSize >> minlog) + 2;
+}
+
/*! ZSTD_storeSeq() :
* Store a sequence (literal length, literals, offset code and match length code) into seqStore_t.
* `offsetCode` : distance to match + 3 (values 1-3 are repCodes).
diff --git a/lib/compress/zstd_compress_literals.c b/lib/compress/zstd_compress_literals.c
new file mode 100644
index 00000000..eb3e5a44
--- /dev/null
+++ b/lib/compress/zstd_compress_literals.c
@@ -0,0 +1,149 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+ /*-*************************************
+ * Dependencies
+ ***************************************/
+#include "zstd_compress_literals.h"
+
+size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+ BYTE* const ostart = (BYTE* const)dst;
+ U32 const flSize = 1 + (srcSize>31) + (srcSize>4095);
+
+ RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall);
+
+ switch(flSize)
+ {
+ case 1: /* 2 - 1 - 5 */
+ ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3));
+ break;
+ case 2: /* 2 - 2 - 12 */
+ MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
+ break;
+ case 3: /* 2 - 2 - 20 */
+ MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
+ break;
+ default: /* not necessary : flSize is {1,2,3} */
+ assert(0);
+ }
+
+ memcpy(ostart + flSize, src, srcSize);
+ return srcSize + flSize;
+}
+
+size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+ BYTE* const ostart = (BYTE* const)dst;
+ U32 const flSize = 1 + (srcSize>31) + (srcSize>4095);
+
+ (void)dstCapacity; /* dstCapacity already guaranteed to be >=4, hence large enough */
+
+ switch(flSize)
+ {
+ case 1: /* 2 - 1 - 5 */
+ ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3));
+ break;
+ case 2: /* 2 - 2 - 12 */
+ MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
+ break;
+ case 3: /* 2 - 2 - 20 */
+ MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
+ break;
+ default: /* not necessary : flSize is {1,2,3} */
+ assert(0);
+ }
+
+ ostart[flSize] = *(const BYTE*)src;
+ 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* workspace, size_t wkspSize,
+ const 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;
+ size_t cLitSize;
+
+ DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i)",
+ disableLiteralCompression);
+
+ /* Prepare nextEntropy assuming reusing the existing table */
+ memcpy(nextHuf, prevHuf, sizeof(*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);
+ }
+
+ 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;
+ if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
+ cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
+ workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2)
+ : HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
+ workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
+ if (repeat != HUF_repeat_none) {
+ /* reused the existing table */
+ hType = set_repeat;
+ }
+ }
+
+ if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
+ memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+ return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
+ }
+ if (cLitSize==1) {
+ memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+ return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
+ }
+
+ if (hType == set_compressed) {
+ /* using a newly constructed table */
+ nextHuf->repeatMode = HUF_repeat_check;
+ }
+
+ /* Build header */
+ switch(lhSize)
+ {
+ case 3: /* 2 - 2 - 10 - 10 */
+ { U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
+ MEM_writeLE24(ostart, lhc);
+ break;
+ }
+ case 4: /* 2 - 2 - 14 - 14 */
+ { U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18);
+ MEM_writeLE32(ostart, lhc);
+ break;
+ }
+ case 5: /* 2 - 2 - 18 - 18 */
+ { U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
+ MEM_writeLE32(ostart, lhc);
+ ostart[4] = (BYTE)(cLitSize >> 10);
+ break;
+ }
+ default: /* not possible : lhSize is {3,4,5} */
+ assert(0);
+ }
+ return lhSize+cLitSize;
+}
diff --git a/lib/compress/zstd_compress_literals.h b/lib/compress/zstd_compress_literals.h
new file mode 100644
index 00000000..7adbecc0
--- /dev/null
+++ b/lib/compress/zstd_compress_literals.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_COMPRESS_LITERALS_H
+#define ZSTD_COMPRESS_LITERALS_H
+
+#include "zstd_compress_internal.h" /* ZSTD_hufCTables_t, ZSTD_minGain() */
+
+
+size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+
+size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+
+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* workspace, size_t wkspSize,
+ const int bmi2);
+
+#endif /* ZSTD_COMPRESS_LITERALS_H */
diff --git a/lib/compress/zstd_compress_sequences.c b/lib/compress/zstd_compress_sequences.c
new file mode 100644
index 00000000..3c3deae0
--- /dev/null
+++ b/lib/compress/zstd_compress_sequences.c
@@ -0,0 +1,415 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+ /*-*************************************
+ * Dependencies
+ ***************************************/
+#include "zstd_compress_sequences.h"
+
+/**
+ * -log2(x / 256) lookup table for x in [0, 256).
+ * If x == 0: Return 0
+ * Else: Return floor(-log2(x / 256) * 256)
+ */
+static unsigned const kInverseProbabilityLog256[256] = {
+ 0, 2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162,
+ 1130, 1100, 1073, 1047, 1024, 1001, 980, 960, 941, 923, 906, 889,
+ 874, 859, 844, 830, 817, 804, 791, 779, 768, 756, 745, 734,
+ 724, 714, 704, 694, 685, 676, 667, 658, 650, 642, 633, 626,
+ 618, 610, 603, 595, 588, 581, 574, 567, 561, 554, 548, 542,
+ 535, 529, 523, 517, 512, 506, 500, 495, 489, 484, 478, 473,
+ 468, 463, 458, 453, 448, 443, 438, 434, 429, 424, 420, 415,
+ 411, 407, 402, 398, 394, 390, 386, 382, 377, 373, 370, 366,
+ 362, 358, 354, 350, 347, 343, 339, 336, 332, 329, 325, 322,
+ 318, 315, 311, 308, 305, 302, 298, 295, 292, 289, 286, 282,
+ 279, 276, 273, 270, 267, 264, 261, 258, 256, 253, 250, 247,
+ 244, 241, 239, 236, 233, 230, 228, 225, 222, 220, 217, 215,
+ 212, 209, 207, 204, 202, 199, 197, 194, 192, 190, 187, 185,
+ 182, 180, 178, 175, 173, 171, 168, 166, 164, 162, 159, 157,
+ 155, 153, 151, 149, 146, 144, 142, 140, 138, 136, 134, 132,
+ 130, 128, 126, 123, 121, 119, 117, 115, 114, 112, 110, 108,
+ 106, 104, 102, 100, 98, 96, 94, 93, 91, 89, 87, 85,
+ 83, 82, 80, 78, 76, 74, 73, 71, 69, 67, 66, 64,
+ 62, 61, 59, 57, 55, 54, 52, 50, 49, 47, 46, 44,
+ 42, 41, 39, 37, 36, 34, 33, 31, 30, 28, 26, 25,
+ 23, 22, 20, 19, 17, 16, 14, 13, 11, 10, 8, 7,
+ 5, 4, 2, 1,
+};
+
+static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) {
+ void const* ptr = ctable;
+ U16 const* u16ptr = (U16 const*)ptr;
+ U32 const maxSymbolValue = MEM_read16(u16ptr + 1);
+ return maxSymbolValue;
+}
+
+/**
+ * Returns the cost in bytes of encoding the normalized count header.
+ * Returns an error if any of the helper functions return an error.
+ */
+static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max,
+ size_t const nbSeq, unsigned const FSELog)
+{
+ 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));
+ return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog);
+}
+
+/**
+ * Returns the cost in bits of encoding the distribution described by count
+ * using the entropy bound.
+ */
+static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t const total)
+{
+ unsigned cost = 0;
+ unsigned s;
+ for (s = 0; s <= max; ++s) {
+ unsigned norm = (unsigned)((256 * count[s]) / total);
+ if (count[s] != 0 && norm == 0)
+ norm = 1;
+ assert(count[s] < total);
+ cost += count[s] * kInverseProbabilityLog256[norm];
+ }
+ return cost >> 8;
+}
+
+/**
+ * Returns the cost in bits of encoding the distribution in count using ctable.
+ * Returns an error if ctable cannot represent all the symbols in count.
+ */
+static size_t ZSTD_fseBitCost(
+ FSE_CTable const* ctable,
+ unsigned const* count,
+ unsigned const max)
+{
+ unsigned const kAccuracyLog = 8;
+ size_t cost = 0;
+ unsigned s;
+ FSE_CState_t cstate;
+ FSE_initCState(&cstate, ctable);
+ RETURN_ERROR_IF(ZSTD_getFSEMaxSymbolValue(ctable) < max, GENERIC,
+ "Repeat FSE_CTable has maxSymbolValue %u < %u",
+ ZSTD_getFSEMaxSymbolValue(ctable), max);
+ for (s = 0; s <= max; ++s) {
+ unsigned const tableLog = cstate.stateLog;
+ unsigned const badCost = (tableLog + 1) << kAccuracyLog;
+ unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog);
+ if (count[s] == 0)
+ continue;
+ RETURN_ERROR_IF(bitCost >= badCost, GENERIC,
+ "Repeat FSE_CTable has Prob[%u] == 0", s);
+ cost += count[s] * bitCost;
+ }
+ return cost >> kAccuracyLog;
+}
+
+/**
+ * Returns the cost in bits of encoding the distribution in count using the
+ * table described by norm. The max symbol support by norm is assumed >= max.
+ * norm must be valid for every symbol with non-zero probability in count.
+ */
+static size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
+ unsigned const* count, unsigned const max)
+{
+ unsigned const shift = 8 - accuracyLog;
+ size_t cost = 0;
+ unsigned s;
+ assert(accuracyLog <= 8);
+ for (s = 0; s <= max; ++s) {
+ unsigned const normAcc = norm[s] != -1 ? norm[s] : 1;
+ unsigned const norm256 = normAcc << shift;
+ assert(norm256 > 0);
+ assert(norm256 < 256);
+ cost += count[s] * kInverseProbabilityLog256[norm256];
+ }
+ return cost >> 8;
+}
+
+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_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,
+ * since RLE uses 1 byte, but set_basic uses 5-6 bits per symbol.
+ * If basic encoding isn't possible, always choose RLE.
+ */
+ DEBUGLOG(5, "Selected set_basic");
+ return set_basic;
+ }
+ DEBUGLOG(5, "Selected set_rle");
+ return set_rle;
+ }
+ if (strategy < ZSTD_lazy) {
+ if (isDefaultAllowed) {
+ size_t const staticFse_nbSeq_max = 1000;
+ size_t const mult = 10 - strategy;
+ size_t const baseLog = 3;
+ size_t const dynamicFse_nbSeq_min = (((size_t)1 << defaultNormLog) * mult) >> baseLog; /* 28-36 for offset, 56-72 for lengths */
+ assert(defaultNormLog >= 5 && defaultNormLog <= 6); /* xx_DEFAULTNORMLOG */
+ assert(mult <= 9 && mult >= 7);
+ if ( (*repeatMode == FSE_repeat_valid)
+ && (nbSeq < staticFse_nbSeq_max) ) {
+ DEBUGLOG(5, "Selected set_repeat");
+ return set_repeat;
+ }
+ if ( (nbSeq < dynamicFse_nbSeq_min)
+ || (mostFrequent < (nbSeq >> (defaultNormLog-1))) ) {
+ DEBUGLOG(5, "Selected set_basic");
+ /* The format allows default tables to be repeated, but it isn't useful.
+ * When using simple heuristics to select encoding type, we don't want
+ * to confuse these tables with dictionaries. When running more careful
+ * analysis, we don't need to waste time checking both repeating tables
+ * and default tables.
+ */
+ *repeatMode = FSE_repeat_none;
+ return set_basic;
+ }
+ }
+ } else {
+ size_t const basicCost = isDefaultAllowed ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, count, max) : ERROR(GENERIC);
+ size_t const repeatCost = *repeatMode != FSE_repeat_none ? ZSTD_fseBitCost(prevCTable, count, max) : ERROR(GENERIC);
+ size_t const NCountCost = ZSTD_NCountCost(count, max, nbSeq, FSELog);
+ size_t const compressedCost = (NCountCost << 3) + ZSTD_entropyCost(count, max, nbSeq);
+
+ if (isDefaultAllowed) {
+ assert(!ZSTD_isError(basicCost));
+ assert(!(*repeatMode == FSE_repeat_valid && ZSTD_isError(repeatCost)));
+ }
+ assert(!ZSTD_isError(NCountCost));
+ assert(compressedCost < ERROR(maxCode));
+ DEBUGLOG(5, "Estimated bit costs: basic=%u\trepeat=%u\tcompressed=%u",
+ (unsigned)basicCost, (unsigned)repeatCost, (unsigned)compressedCost);
+ if (basicCost <= repeatCost && basicCost <= compressedCost) {
+ DEBUGLOG(5, "Selected set_basic");
+ assert(isDefaultAllowed);
+ *repeatMode = FSE_repeat_none;
+ return set_basic;
+ }
+ if (repeatCost <= compressedCost) {
+ DEBUGLOG(5, "Selected set_repeat");
+ assert(!ZSTD_isError(repeatCost));
+ return set_repeat;
+ }
+ assert(compressedCost < basicCost && compressedCost < repeatCost);
+ }
+ DEBUGLOG(5, "Selected set_compressed");
+ *repeatMode = FSE_repeat_check;
+ return set_compressed;
+}
+
+size_t
+ZSTD_buildCTable(void* dst, size_t dstCapacity,
+ 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,
+ const FSE_CTable* prevCTable, size_t prevCTableSize,
+ void* workspace, size_t workspaceSize)
+{
+ BYTE* op = (BYTE*)dst;
+ const BYTE* const oend = op + dstCapacity;
+ DEBUGLOG(6, "ZSTD_buildCTable (dstCapacity=%u)", (unsigned)dstCapacity);
+
+ switch (type) {
+ case set_rle:
+ FORWARD_IF_ERROR(FSE_buildCTable_rle(nextCTable, (BYTE)max));
+ RETURN_ERROR_IF(dstCapacity==0, dstSize_tooSmall);
+ *op = codeTable[0];
+ return 1;
+ case set_repeat:
+ memcpy(nextCTable, prevCTable, prevCTableSize);
+ return 0;
+ case set_basic:
+ FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize)); /* note : could be pre-calculated */
+ return 0;
+ case set_compressed: {
+ S16 norm[MaxSeq + 1];
+ size_t nbSeq_1 = nbSeq;
+ const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
+ if (count[codeTable[nbSeq-1]] > 1) {
+ count[codeTable[nbSeq-1]]--;
+ 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 */
+ FORWARD_IF_ERROR(NCountSize);
+ FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize));
+ return NCountSize;
+ }
+ }
+ default: assert(0); RETURN_ERROR(GENERIC);
+ }
+}
+
+FORCE_INLINE_TEMPLATE size_t
+ZSTD_encodeSequences_body(
+ void* dst, size_t dstCapacity,
+ 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)
+{
+ BIT_CStream_t blockStream;
+ FSE_CState_t stateMatchLength;
+ FSE_CState_t stateOffsetBits;
+ FSE_CState_t stateLitLength;
+
+ RETURN_ERROR_IF(
+ ERR_isError(BIT_initCStream(&blockStream, dst, dstCapacity)),
+ dstSize_tooSmall, "not enough space remaining");
+ DEBUGLOG(6, "available space for bitstream : %i (dstCapacity=%u)",
+ (int)(blockStream.endPtr - blockStream.startPtr),
+ (unsigned)dstCapacity);
+
+ /* first symbols */
+ FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]);
+ FSE_initCState2(&stateOffsetBits, CTable_OffsetBits, ofCodeTable[nbSeq-1]);
+ FSE_initCState2(&stateLitLength, CTable_LitLength, llCodeTable[nbSeq-1]);
+ BIT_addBits(&blockStream, sequences[nbSeq-1].litLength, LL_bits[llCodeTable[nbSeq-1]]);
+ if (MEM_32bits()) BIT_flushBits(&blockStream);
+ BIT_addBits(&blockStream, sequences[nbSeq-1].matchLength, ML_bits[mlCodeTable[nbSeq-1]]);
+ if (MEM_32bits()) BIT_flushBits(&blockStream);
+ if (longOffsets) {
+ U32 const ofBits = ofCodeTable[nbSeq-1];
+ int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
+ if (extraBits) {
+ BIT_addBits(&blockStream, sequences[nbSeq-1].offset, extraBits);
+ BIT_flushBits(&blockStream);
+ }
+ BIT_addBits(&blockStream, sequences[nbSeq-1].offset >> extraBits,
+ ofBits - extraBits);
+ } else {
+ BIT_addBits(&blockStream, sequences[nbSeq-1].offset, ofCodeTable[nbSeq-1]);
+ }
+ BIT_flushBits(&blockStream);
+
+ { size_t n;
+ for (n=nbSeq-2 ; n= 64-7-(LLFSELog+MLFSELog+OffFSELog)))
+ BIT_flushBits(&blockStream); /* (7)*/
+ BIT_addBits(&blockStream, sequences[n].litLength, llBits);
+ if (MEM_32bits() && ((llBits+mlBits)>24)) BIT_flushBits(&blockStream);
+ BIT_addBits(&blockStream, sequences[n].matchLength, mlBits);
+ if (MEM_32bits() || (ofBits+mlBits+llBits > 56)) BIT_flushBits(&blockStream);
+ if (longOffsets) {
+ int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
+ if (extraBits) {
+ BIT_addBits(&blockStream, sequences[n].offset, extraBits);
+ BIT_flushBits(&blockStream); /* (7)*/
+ }
+ BIT_addBits(&blockStream, sequences[n].offset >> extraBits,
+ ofBits - extraBits); /* 31 */
+ } else {
+ BIT_addBits(&blockStream, sequences[n].offset, ofBits); /* 31 */
+ }
+ BIT_flushBits(&blockStream); /* (7)*/
+ DEBUGLOG(7, "remaining space : %i", (int)(blockStream.endPtr - blockStream.ptr));
+ } }
+
+ DEBUGLOG(6, "ZSTD_encodeSequences: flushing ML state with %u bits", stateMatchLength.stateLog);
+ FSE_flushCState(&blockStream, &stateMatchLength);
+ DEBUGLOG(6, "ZSTD_encodeSequences: flushing Off state with %u bits", stateOffsetBits.stateLog);
+ FSE_flushCState(&blockStream, &stateOffsetBits);
+ DEBUGLOG(6, "ZSTD_encodeSequences: flushing LL state with %u bits", stateLitLength.stateLog);
+ FSE_flushCState(&blockStream, &stateLitLength);
+
+ { size_t const streamSize = BIT_closeCStream(&blockStream);
+ RETURN_ERROR_IF(streamSize==0, dstSize_tooSmall, "not enough space");
+ return streamSize;
+ }
+}
+
+static size_t
+ZSTD_encodeSequences_default(
+ void* dst, size_t dstCapacity,
+ 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)
+{
+ return ZSTD_encodeSequences_body(dst, dstCapacity,
+ CTable_MatchLength, mlCodeTable,
+ CTable_OffsetBits, ofCodeTable,
+ CTable_LitLength, llCodeTable,
+ sequences, nbSeq, longOffsets);
+}
+
+
+#if DYNAMIC_BMI2
+
+static TARGET_ATTRIBUTE("bmi2") size_t
+ZSTD_encodeSequences_bmi2(
+ void* dst, size_t dstCapacity,
+ 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)
+{
+ return ZSTD_encodeSequences_body(dst, dstCapacity,
+ CTable_MatchLength, mlCodeTable,
+ CTable_OffsetBits, ofCodeTable,
+ CTable_LitLength, llCodeTable,
+ sequences, nbSeq, longOffsets);
+}
+
+#endif
+
+size_t ZSTD_encodeSequences(
+ void* dst, size_t dstCapacity,
+ 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)
+{
+ DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
+#if DYNAMIC_BMI2
+ if (bmi2) {
+ return ZSTD_encodeSequences_bmi2(dst, dstCapacity,
+ CTable_MatchLength, mlCodeTable,
+ CTable_OffsetBits, ofCodeTable,
+ CTable_LitLength, llCodeTable,
+ sequences, nbSeq, longOffsets);
+ }
+#endif
+ (void)bmi2;
+ return ZSTD_encodeSequences_default(dst, dstCapacity,
+ CTable_MatchLength, mlCodeTable,
+ CTable_OffsetBits, ofCodeTable,
+ CTable_LitLength, llCodeTable,
+ sequences, nbSeq, longOffsets);
+}
diff --git a/lib/compress/zstd_compress_sequences.h b/lib/compress/zstd_compress_sequences.h
new file mode 100644
index 00000000..f5234d94
--- /dev/null
+++ b/lib/compress/zstd_compress_sequences.h
@@ -0,0 +1,47 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_COMPRESS_SEQUENCES_H
+#define ZSTD_COMPRESS_SEQUENCES_H
+
+#include "fse.h" /* FSE_repeat, FSE_CTable */
+#include "zstd_internal.h" /* symbolEncodingType_e, ZSTD_strategy */
+
+typedef enum {
+ ZSTD_defaultDisallowed = 0,
+ ZSTD_defaultAllowed = 1
+} ZSTD_defaultPolicy_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_strategy const strategy);
+
+size_t
+ZSTD_buildCTable(void* dst, size_t dstCapacity,
+ 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,
+ const FSE_CTable* prevCTable, size_t prevCTableSize,
+ void* workspace, size_t workspaceSize);
+
+size_t ZSTD_encodeSequences(
+ void* dst, size_t dstCapacity,
+ 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);
+
+#endif /* ZSTD_COMPRESS_SEQUENCES_H */