ext/zstdruby/libzstd/common/huf.h in zstd-ruby-1.5.2.3 vs ext/zstdruby/libzstd/common/huf.h in zstd-ruby-1.5.4.0
- old
+ new
@@ -1,9 +1,9 @@
/* ******************************************************************
* huff0 huffman codec,
* part of Finite State Entropy library
- * Copyright (c) Yann Collet, Facebook, Inc.
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
*
* You can contact the author at :
* - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
*
* This source code is licensed under both the BSD-style license (found in the
@@ -19,104 +19,27 @@
#ifndef HUF_H_298734234
#define HUF_H_298734234
/* *** Dependencies *** */
#include "zstd_deps.h" /* size_t */
+#include "mem.h" /* U32 */
+#define FSE_STATIC_LINKING_ONLY
+#include "fse.h"
-/* *** library symbols visibility *** */
-/* Note : when linking with -fvisibility=hidden on gcc, or by default on Visual,
- * HUF symbols remain "private" (internal symbols for library only).
- * Set macro FSE_DLL_EXPORT to 1 if you want HUF symbols visible on DLL interface */
-#if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4)
-# define HUF_PUBLIC_API __attribute__ ((visibility ("default")))
-#elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) /* Visual expected */
-# define HUF_PUBLIC_API __declspec(dllexport)
-#elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1)
-# define HUF_PUBLIC_API __declspec(dllimport) /* not required, just to generate faster code (saves a function pointer load from IAT and an indirect jump) */
-#else
-# define HUF_PUBLIC_API
-#endif
-
-
-/* ========================== */
-/* *** simple functions *** */
-/* ========================== */
-
-/** HUF_compress() :
- * Compress content from buffer 'src', of size 'srcSize', into buffer 'dst'.
- * 'dst' buffer must be already allocated.
- * Compression runs faster if `dstCapacity` >= HUF_compressBound(srcSize).
- * `srcSize` must be <= `HUF_BLOCKSIZE_MAX` == 128 KB.
- * @return : size of compressed data (<= `dstCapacity`).
- * Special values : if return == 0, srcData is not compressible => Nothing is stored within dst !!!
- * if HUF_isError(return), compression failed (more details using HUF_getErrorName())
- */
-HUF_PUBLIC_API size_t HUF_compress(void* dst, size_t dstCapacity,
- const void* src, size_t srcSize);
-
-/** HUF_decompress() :
- * Decompress HUF data from buffer 'cSrc', of size 'cSrcSize',
- * into already allocated buffer 'dst', of minimum size 'dstSize'.
- * `originalSize` : **must** be the ***exact*** size of original (uncompressed) data.
- * Note : in contrast with FSE, HUF_decompress can regenerate
- * RLE (cSrcSize==1) and uncompressed (cSrcSize==dstSize) data,
- * because it knows size to regenerate (originalSize).
- * @return : size of regenerated data (== originalSize),
- * or an error code, which can be tested using HUF_isError()
- */
-HUF_PUBLIC_API size_t HUF_decompress(void* dst, size_t originalSize,
- const void* cSrc, size_t cSrcSize);
-
-
/* *** Tool functions *** */
-#define HUF_BLOCKSIZE_MAX (128 * 1024) /**< maximum input size for a single block compressed with HUF_compress */
-HUF_PUBLIC_API size_t HUF_compressBound(size_t size); /**< maximum compressed size (worst case) */
+#define HUF_BLOCKSIZE_MAX (128 * 1024) /**< maximum input size for a single block compressed with HUF_compress */
+size_t HUF_compressBound(size_t size); /**< maximum compressed size (worst case) */
/* Error Management */
-HUF_PUBLIC_API unsigned HUF_isError(size_t code); /**< tells if a return value is an error code */
-HUF_PUBLIC_API const char* HUF_getErrorName(size_t code); /**< provides error code string (useful for debugging) */
+unsigned HUF_isError(size_t code); /**< tells if a return value is an error code */
+const char* HUF_getErrorName(size_t code); /**< provides error code string (useful for debugging) */
-/* *** Advanced function *** */
-
-/** HUF_compress2() :
- * Same as HUF_compress(), but offers control over `maxSymbolValue` and `tableLog`.
- * `maxSymbolValue` must be <= HUF_SYMBOLVALUE_MAX .
- * `tableLog` must be `<= HUF_TABLELOG_MAX` . */
-HUF_PUBLIC_API size_t HUF_compress2 (void* dst, size_t dstCapacity,
- const void* src, size_t srcSize,
- unsigned maxSymbolValue, unsigned tableLog);
-
-/** HUF_compress4X_wksp() :
- * Same as HUF_compress2(), but uses externally allocated `workSpace`.
- * `workspace` must be at least as large as HUF_WORKSPACE_SIZE */
#define HUF_WORKSPACE_SIZE ((8 << 10) + 512 /* sorting scratch space */)
#define HUF_WORKSPACE_SIZE_U64 (HUF_WORKSPACE_SIZE / sizeof(U64))
-HUF_PUBLIC_API size_t HUF_compress4X_wksp (void* dst, size_t dstCapacity,
- const void* src, size_t srcSize,
- unsigned maxSymbolValue, unsigned tableLog,
- void* workSpace, size_t wkspSize);
-#endif /* HUF_H_298734234 */
-
-/* ******************************************************************
- * WARNING !!
- * The following section contains advanced and experimental definitions
- * which shall never be used in the context of a dynamic library,
- * because they are not guaranteed to remain stable in the future.
- * Only consider them in association with static linking.
- * *****************************************************************/
-#if defined(HUF_STATIC_LINKING_ONLY) && !defined(HUF_H_HUF_STATIC_LINKING_ONLY)
-#define HUF_H_HUF_STATIC_LINKING_ONLY
-
-/* *** Dependencies *** */
-#include "mem.h" /* U32 */
-#define FSE_STATIC_LINKING_ONLY
-#include "fse.h"
-
-
/* *** Constants *** */
#define HUF_TABLELOG_MAX 12 /* max runtime value of tableLog (due to static allocation); can be modified up to HUF_TABLELOG_ABSOLUTEMAX */
#define HUF_TABLELOG_DEFAULT 11 /* default tableLog value when none specified */
#define HUF_SYMBOLVALUE_MAX 255
@@ -152,29 +75,53 @@
/* ****************************************
* Advanced decompression functions
******************************************/
-size_t HUF_decompress4X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< single-symbol decoder */
-#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< double-symbols decoder */
-#endif
-size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< decodes RLE and uncompressed */
-size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< considers RLE and uncompressed as errors */
-size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< considers RLE and uncompressed as errors */
-size_t HUF_decompress4X1_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< single-symbol decoder */
-size_t HUF_decompress4X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< single-symbol decoder */
-#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_decompress4X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< double-symbols decoder */
-size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< double-symbols decoder */
-#endif
+/**
+ * Huffman flags bitset.
+ * For all flags, 0 is the default value.
+ */
+typedef enum {
+ /**
+ * If compiled with DYNAMIC_BMI2: Set flag only if the CPU supports BMI2 at runtime.
+ * Otherwise: Ignored.
+ */
+ HUF_flags_bmi2 = (1 << 0),
+ /**
+ * If set: Test possible table depths to find the one that produces the smallest header + encoded size.
+ * If unset: Use heuristic to find the table depth.
+ */
+ HUF_flags_optimalDepth = (1 << 1),
+ /**
+ * If set: If the previous table can encode the input, always reuse the previous table.
+ * If unset: If the previous table can encode the input, reuse the previous table if it results in a smaller output.
+ */
+ HUF_flags_preferRepeat = (1 << 2),
+ /**
+ * If set: Sample the input and check if the sample is uncompressible, if it is then don't attempt to compress.
+ * If unset: Always histogram the entire input.
+ */
+ HUF_flags_suspectUncompressible = (1 << 3),
+ /**
+ * If set: Don't use assembly implementations
+ * If unset: Allow using assembly implementations
+ */
+ HUF_flags_disableAsm = (1 << 4),
+ /**
+ * If set: Don't use the fast decoding loop, always use the fallback decoding loop.
+ * If unset: Use the fast decoding loop when possible.
+ */
+ HUF_flags_disableFast = (1 << 5)
+} HUF_flags_e;
/* ****************************************
* HUF detailed API
* ****************************************/
+#define HUF_OPTIMAL_DEPTH_THRESHOLD ZSTD_btultra
/*! HUF_compress() does the following:
* 1. count symbol occurrence from source[] into table count[] using FSE_count() (exposed within "fse.h")
* 2. (optional) refine tableLog using HUF_optimalTableLog()
* 3. build Huffman table from count using HUF_buildCTable()
@@ -183,41 +130,42 @@
*
* The following API allows targeting specific sub-functions for advanced tasks.
* For example, it's possible to compress several blocks using the same 'CTable',
* or to save and regenerate 'CTable' using external methods.
*/
-unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
-size_t HUF_buildCTable (HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue, unsigned maxNbBits); /* @return : maxNbBits; CTable and count can overlap. In which case, CTable will overwrite count content */
-size_t HUF_writeCTable (void* dst, size_t maxDstSize, const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog);
+unsigned HUF_minTableLog(unsigned symbolCardinality);
+unsigned HUF_cardinality(const unsigned* count, unsigned maxSymbolValue);
+unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, void* workSpace,
+ size_t wkspSize, HUF_CElt* table, const unsigned* count, int flags); /* table is used as scratch space for building and testing tables, not a return value */
size_t HUF_writeCTable_wksp(void* dst, size_t maxDstSize, const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog, void* workspace, size_t workspaceSize);
-size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
-size_t HUF_compress4X_usingCTable_bmi2(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable, int bmi2);
+size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable, int flags);
size_t HUF_estimateCompressedSize(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue);
int HUF_validateCTable(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue);
typedef enum {
HUF_repeat_none, /**< Cannot use the previous table */
HUF_repeat_check, /**< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1, 4}X_repeat */
HUF_repeat_valid /**< Can use the previous table and it is assumed to be valid */
} HUF_repeat;
+
/** HUF_compress4X_repeat() :
* Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
* If it uses hufTable it does not modify hufTable or repeat.
* If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
* If preferRepeat then the old table will always be used if valid.
* If suspectUncompressible then some sampling checks will be run to potentially skip huffman coding */
size_t HUF_compress4X_repeat(void* dst, size_t dstSize,
const void* src, size_t srcSize,
unsigned maxSymbolValue, unsigned tableLog,
void* workSpace, size_t wkspSize, /**< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */
- HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2, unsigned suspectUncompressible);
+ HUF_CElt* hufTable, HUF_repeat* repeat, int flags);
/** HUF_buildCTable_wksp() :
* Same as HUF_buildCTable(), but using externally allocated scratch buffer.
* `workSpace` must be aligned on 4-bytes boundaries, and its size must be >= HUF_CTABLE_WORKSPACE_SIZE.
*/
-#define HUF_CTABLE_WORKSPACE_SIZE_U32 (2*HUF_SYMBOLVALUE_MAX +1 +1)
+#define HUF_CTABLE_WORKSPACE_SIZE_U32 ((4 * (HUF_SYMBOLVALUE_MAX + 1)) + 192)
#define HUF_CTABLE_WORKSPACE_SIZE (HUF_CTABLE_WORKSPACE_SIZE_U32 * sizeof(unsigned))
size_t HUF_buildCTable_wksp (HUF_CElt* tree,
const unsigned* count, U32 maxSymbolValue, U32 maxNbBits,
void* workSpace, size_t wkspSize);
@@ -239,11 +187,11 @@
#define HUF_READ_STATS_WORKSPACE_SIZE (HUF_READ_STATS_WORKSPACE_SIZE_U32 * sizeof(unsigned))
size_t HUF_readStats_wksp(BYTE* huffWeight, size_t hwSize,
U32* rankStats, U32* nbSymbolsPtr, U32* tableLogPtr,
const void* src, size_t srcSize,
void* workspace, size_t wkspSize,
- int bmi2);
+ int flags);
/** HUF_readCTable() :
* Loading a CTable saved with HUF_writeCTable() */
size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize, unsigned *hasZeroWeights);
@@ -277,88 +225,49 @@
* macro.
*/
#define HUF_DECOMPRESS_WORKSPACE_SIZE ((2 << 10) + (1 << 9))
#define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32))
-#ifndef HUF_FORCE_DECOMPRESS_X2
-size_t HUF_readDTableX1 (HUF_DTable* DTable, const void* src, size_t srcSize);
-size_t HUF_readDTableX1_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
-#endif
-#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize);
-size_t HUF_readDTableX2_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
-#endif
-size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
-#ifndef HUF_FORCE_DECOMPRESS_X2
-size_t HUF_decompress4X1_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
-#endif
-#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_decompress4X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
-#endif
-
-
/* ====================== */
/* single stream variants */
/* ====================== */
-size_t HUF_compress1X (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
-size_t HUF_compress1X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize); /**< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U64 U64 */
-size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
-size_t HUF_compress1X_usingCTable_bmi2(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable, int bmi2);
+size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable, int flags);
/** HUF_compress1X_repeat() :
* Same as HUF_compress1X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
* If it uses hufTable it does not modify hufTable or repeat.
* If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
* If preferRepeat then the old table will always be used if valid.
* If suspectUncompressible then some sampling checks will be run to potentially skip huffman coding */
size_t HUF_compress1X_repeat(void* dst, size_t dstSize,
const void* src, size_t srcSize,
unsigned maxSymbolValue, unsigned tableLog,
void* workSpace, size_t wkspSize, /**< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */
- HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2, unsigned suspectUncompressible);
+ HUF_CElt* hufTable, HUF_repeat* repeat, int flags);
-size_t HUF_decompress1X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /* single-symbol decoder */
+size_t HUF_decompress1X_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags);
#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /* double-symbol decoder */
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags); /**< double-symbols decoder */
#endif
-size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);
-size_t HUF_decompress1X_DCtx_wksp (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);
-#ifndef HUF_FORCE_DECOMPRESS_X2
-size_t HUF_decompress1X1_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< single-symbol decoder */
-size_t HUF_decompress1X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< single-symbol decoder */
-#endif
-#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_decompress1X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< double-symbols decoder */
-size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< double-symbols decoder */
-#endif
-
-size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); /**< automatic selection of sing or double symbol decoder, based on DTable */
-#ifndef HUF_FORCE_DECOMPRESS_X2
-size_t HUF_decompress1X1_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
-#endif
-#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_decompress1X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
-#endif
-
/* BMI2 variants.
* If the CPU has BMI2 support, pass bmi2=1, otherwise pass bmi2=0.
*/
-size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2);
+size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int flags);
#ifndef HUF_FORCE_DECOMPRESS_X2
-size_t HUF_decompress1X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2);
+size_t HUF_decompress1X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags);
#endif
-size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2);
-size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2);
+size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int flags);
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags);
#ifndef HUF_FORCE_DECOMPRESS_X2
-size_t HUF_readDTableX1_wksp_bmi2(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int bmi2);
+size_t HUF_readDTableX1_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int flags);
#endif
#ifndef HUF_FORCE_DECOMPRESS_X1
-size_t HUF_readDTableX2_wksp_bmi2(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int bmi2);
+size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int flags);
#endif
-#endif /* HUF_STATIC_LINKING_ONLY */
+#endif /* HUF_H_298734234 */
#if defined (__cplusplus)
}
#endif