diff options
author | igorsolovyev <igorsolovyev@yandex-team.ru> | 2022-02-10 16:48:03 +0300 |
---|---|---|
committer | Daniil Cherednik <dcherednik@yandex-team.ru> | 2022-02-10 16:48:03 +0300 |
commit | 93dc653cf53bf7a9319b52b85a7c02edfd95463d (patch) | |
tree | b85de7682b5f10d28a798003716a65756425aa15 /contrib | |
parent | 6ab7e5f5ada0643a48d393717f443bd548706ffc (diff) | |
download | ydb-93dc653cf53bf7a9319b52b85a7c02edfd95463d.tar.gz |
Restoring authorship annotation for <igorsolovyev@yandex-team.ru>. Commit 1 of 2.
Diffstat (limited to 'contrib')
54 files changed, 9054 insertions, 9054 deletions
diff --git a/contrib/libs/zstd/lib/common/bitstream.h b/contrib/libs/zstd/lib/common/bitstream.h index 84b6062ff3..abbde06ca8 100644 --- a/contrib/libs/zstd/lib/common/bitstream.h +++ b/contrib/libs/zstd/lib/common/bitstream.h @@ -43,21 +43,21 @@ extern "C" { # endif #endif -#define STREAM_ACCUMULATOR_MIN_32 25 -#define STREAM_ACCUMULATOR_MIN_64 57 -#define STREAM_ACCUMULATOR_MIN ((U32)(MEM_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64)) - +#define STREAM_ACCUMULATOR_MIN_32 25 +#define STREAM_ACCUMULATOR_MIN_64 57 +#define STREAM_ACCUMULATOR_MIN ((U32)(MEM_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64)) + /*-****************************************** * bitStream encoding API (write forward) ********************************************/ /* bitStream can mix input from multiple sources. - * A critical property of these streams is that they encode and decode in **reverse** direction. - * So the first bit sequence you add will be the last to be read, like a LIFO stack. - */ + * A critical property of these streams is that they encode and decode in **reverse** direction. + * So the first bit sequence you add will be the last to be read, like a LIFO stack. + */ typedef struct { size_t bitContainer; - unsigned bitPos; + unsigned bitPos; char* startPtr; char* ptr; char* endPtr; @@ -94,7 +94,7 @@ typedef struct { unsigned bitsConsumed; const char* ptr; const char* start; - const char* limitPtr; + const char* limitPtr; } BIT_DStream_t; typedef enum { BIT_DStream_unfinished = 0, @@ -137,10 +137,10 @@ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits); /*-************************************************************** * Internal functions ****************************************************************/ -MEM_STATIC unsigned BIT_highbit32 (U32 val) +MEM_STATIC unsigned BIT_highbit32 (U32 val) { - assert(val != 0); - { + assert(val != 0); + { # if defined(_MSC_VER) /* Visual */ # if STATIC_BMI2 == 1 return _lzcnt_u32(val) ^ 31; @@ -159,59 +159,59 @@ MEM_STATIC unsigned BIT_highbit32 (U32 val) # elif defined(__ICCARM__) /* IAR Intrinsic */ return 31 - __CLZ(val); # else /* Software version */ - static const unsigned DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, - 11, 14, 16, 18, 22, 25, 3, 30, - 8, 12, 20, 28, 15, 17, 24, 7, - 19, 27, 23, 6, 26, 5, 4, 31 }; - U32 v = val; - v |= v >> 1; - v |= v >> 2; - v |= v >> 4; - v |= v >> 8; - v |= v >> 16; - return DeBruijnClz[ (U32) (v * 0x07C4ACDDU) >> 27]; + static const unsigned DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, + 11, 14, 16, 18, 22, 25, 3, 30, + 8, 12, 20, 28, 15, 17, 24, 7, + 19, 27, 23, 6, 26, 5, 4, 31 }; + U32 v = val; + v |= v >> 1; + v |= v >> 2; + v |= v >> 4; + v |= v >> 8; + v |= v >> 16; + return DeBruijnClz[ (U32) (v * 0x07C4ACDDU) >> 27]; # endif - } + } } /*===== Local Constants =====*/ -static const unsigned BIT_mask[] = { - 0, 1, 3, 7, 0xF, 0x1F, - 0x3F, 0x7F, 0xFF, 0x1FF, 0x3FF, 0x7FF, - 0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0x1FFFF, - 0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF, - 0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF, 0x7FFFFFF, 0xFFFFFFF, 0x1FFFFFFF, - 0x3FFFFFFF, 0x7FFFFFFF}; /* up to 31 bits */ -#define BIT_MASK_SIZE (sizeof(BIT_mask) / sizeof(BIT_mask[0])) +static const unsigned BIT_mask[] = { + 0, 1, 3, 7, 0xF, 0x1F, + 0x3F, 0x7F, 0xFF, 0x1FF, 0x3FF, 0x7FF, + 0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0x1FFFF, + 0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF, + 0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF, 0x7FFFFFF, 0xFFFFFFF, 0x1FFFFFFF, + 0x3FFFFFFF, 0x7FFFFFFF}; /* up to 31 bits */ +#define BIT_MASK_SIZE (sizeof(BIT_mask) / sizeof(BIT_mask[0])) /*-************************************************************** * bitStream encoding ****************************************************************/ /*! BIT_initCStream() : - * `dstCapacity` must be > sizeof(size_t) + * `dstCapacity` must be > sizeof(size_t) * @return : 0 if success, - * otherwise an error code (can be tested using ERR_isError()) */ -MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, - void* startPtr, size_t dstCapacity) + * otherwise an error code (can be tested using ERR_isError()) */ +MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, + void* startPtr, size_t dstCapacity) { bitC->bitContainer = 0; bitC->bitPos = 0; bitC->startPtr = (char*)startPtr; bitC->ptr = bitC->startPtr; - bitC->endPtr = bitC->startPtr + dstCapacity - sizeof(bitC->bitContainer); - if (dstCapacity <= sizeof(bitC->bitContainer)) return ERROR(dstSize_tooSmall); + bitC->endPtr = bitC->startPtr + dstCapacity - sizeof(bitC->bitContainer); + if (dstCapacity <= sizeof(bitC->bitContainer)) return ERROR(dstSize_tooSmall); return 0; } /*! BIT_addBits() : - * can add up to 31 bits into `bitC`. - * Note : does not check for register overflow ! */ -MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC, - size_t value, unsigned nbBits) + * can add up to 31 bits into `bitC`. + * Note : does not check for register overflow ! */ +MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC, + size_t value, unsigned nbBits) { DEBUG_STATIC_ASSERT(BIT_MASK_SIZE == 32); - assert(nbBits < BIT_MASK_SIZE); - assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8); + assert(nbBits < BIT_MASK_SIZE); + assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8); bitC->bitContainer |= (value & BIT_mask[nbBits]) << bitC->bitPos; bitC->bitPos += nbBits; } @@ -219,74 +219,74 @@ MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC, /*! BIT_addBitsFast() : * works only if `value` is _clean_, * meaning all high bits above nbBits are 0 */ -MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, - size_t value, unsigned nbBits) +MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, + size_t value, unsigned nbBits) { - assert((value>>nbBits) == 0); - assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8); + assert((value>>nbBits) == 0); + assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8); bitC->bitContainer |= value << bitC->bitPos; bitC->bitPos += nbBits; } /*! BIT_flushBitsFast() : - * assumption : bitContainer has not overflowed + * assumption : bitContainer has not overflowed * unsafe version; does not check buffer overflow */ MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC) { size_t const nbBytes = bitC->bitPos >> 3; - assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8); + assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8); assert(bitC->ptr <= bitC->endPtr); MEM_writeLEST(bitC->ptr, bitC->bitContainer); bitC->ptr += nbBytes; bitC->bitPos &= 7; - bitC->bitContainer >>= nbBytes*8; + bitC->bitContainer >>= nbBytes*8; } /*! BIT_flushBits() : - * assumption : bitContainer has not overflowed + * assumption : bitContainer has not overflowed * safe version; check for buffer overflow, and prevents it. - * note : does not signal buffer overflow. - * overflow will be revealed later on using BIT_closeCStream() */ + * note : does not signal buffer overflow. + * overflow will be revealed later on using BIT_closeCStream() */ MEM_STATIC void BIT_flushBits(BIT_CStream_t* bitC) { size_t const nbBytes = bitC->bitPos >> 3; - assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8); + assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8); assert(bitC->ptr <= bitC->endPtr); MEM_writeLEST(bitC->ptr, bitC->bitContainer); bitC->ptr += nbBytes; if (bitC->ptr > bitC->endPtr) bitC->ptr = bitC->endPtr; bitC->bitPos &= 7; - bitC->bitContainer >>= nbBytes*8; + bitC->bitContainer >>= nbBytes*8; } /*! BIT_closeCStream() : * @return : size of CStream, in bytes, - * or 0 if it could not fit into dstBuffer */ + * or 0 if it could not fit into dstBuffer */ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC) { BIT_addBitsFast(bitC, 1, 1); /* endMark */ BIT_flushBits(bitC); - if (bitC->ptr >= bitC->endPtr) return 0; /* overflow detected */ + if (bitC->ptr >= bitC->endPtr) return 0; /* overflow detected */ return (bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0); } /*-******************************************************** -* bitStream decoding +* bitStream decoding **********************************************************/ /*! BIT_initDStream() : - * Initialize a BIT_DStream_t. - * `bitD` : a pointer to an already allocated BIT_DStream_t structure. - * `srcSize` must be the *exact* size of the bitStream, in bytes. - * @return : size of stream (== srcSize), or an errorCode if a problem is detected - */ + * Initialize a BIT_DStream_t. + * `bitD` : a pointer to an already allocated BIT_DStream_t structure. + * `srcSize` must be the *exact* size of the bitStream, in bytes. + * @return : size of stream (== srcSize), or an errorCode if a problem is detected + */ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize) { if (srcSize < 1) { ZSTD_memset(bitD, 0, sizeof(*bitD)); return ERROR(srcSize_wrong); } - bitD->start = (const char*)srcBuffer; - bitD->limitPtr = bitD->start + sizeof(bitD->bitContainer); - + bitD->start = (const char*)srcBuffer; + bitD->limitPtr = bitD->start + sizeof(bitD->bitContainer); + if (srcSize >= sizeof(bitD->bitContainer)) { /* normal case */ bitD->ptr = (const char*)srcBuffer + srcSize - sizeof(bitD->bitContainer); bitD->bitContainer = MEM_readLEST(bitD->ptr); @@ -298,30 +298,30 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si bitD->bitContainer = *(const BYTE*)(bitD->start); switch(srcSize) { - case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16); + case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16); ZSTD_FALLTHROUGH; - - case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24); + + case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24); ZSTD_FALLTHROUGH; - - case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32); + + case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32); ZSTD_FALLTHROUGH; - - case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24; + + case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24; ZSTD_FALLTHROUGH; - - case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16; + + case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16; ZSTD_FALLTHROUGH; - - case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8; + + case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8; ZSTD_FALLTHROUGH; - - default: break; - } - { BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1]; - bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0; - if (lastByte == 0) return ERROR(corruption_detected); /* endMark not present */ + + default: break; } + { BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1]; + bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0; + if (lastByte == 0) return ERROR(corruption_detected); /* endMark not present */ + } bitD->bitsConsumed += (U32)(sizeof(bitD->bitContainer) - srcSize)*8; } @@ -337,7 +337,7 @@ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getMiddleBits(size_t bitContainer, U32 c { U32 const regMask = sizeof(bitContainer)*8 - 1; /* if start > regMask, bitstream is corrupted, and result is undefined */ - assert(nbBits < BIT_MASK_SIZE); + assert(nbBits < BIT_MASK_SIZE); /* x86 transform & ((1 << nbBits) - 1) to bzhi instruction, it is better * than accessing memory. When bmi2 instruction is not present, we consider * such cpus old (pre-Haswell, 2013) and their performance is not of that @@ -355,7 +355,7 @@ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getLowerBits(size_t bitContainer, U32 co #if defined(STATIC_BMI2) && STATIC_BMI2 == 1 return _bzhi_u64(bitContainer, nbBits); #else - assert(nbBits < BIT_MASK_SIZE); + assert(nbBits < BIT_MASK_SIZE); return bitContainer & BIT_mask[nbBits]; #endif } @@ -365,7 +365,7 @@ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getLowerBits(size_t bitContainer, U32 co * local register is not modified. * On 32-bits, maxNbBits==24. * On 64-bits, maxNbBits==56. - * @return : value extracted */ + * @return : value extracted */ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_lookBits(const BIT_DStream_t* bitD, U32 nbBits) { /* arbitrate between double-shift and shift+mask */ @@ -375,18 +375,18 @@ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_lookBits(const BIT_DStream_t* bitD, U3 return BIT_getMiddleBits(bitD->bitContainer, (sizeof(bitD->bitContainer)*8) - bitD->bitsConsumed - nbBits, nbBits); #else /* this code path is slower on my os-x laptop */ - U32 const regMask = sizeof(bitD->bitContainer)*8 - 1; - return ((bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> 1) >> ((regMask-nbBits) & regMask); + U32 const regMask = sizeof(bitD->bitContainer)*8 - 1; + return ((bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> 1) >> ((regMask-nbBits) & regMask); #endif } /*! BIT_lookBitsFast() : - * unsafe version; only works if nbBits >= 1 */ + * unsafe version; only works if nbBits >= 1 */ MEM_STATIC size_t BIT_lookBitsFast(const BIT_DStream_t* bitD, U32 nbBits) { - U32 const regMask = sizeof(bitD->bitContainer)*8 - 1; - assert(nbBits >= 1); - return (bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> (((regMask+1)-nbBits) & regMask); + U32 const regMask = sizeof(bitD->bitContainer)*8 - 1; + assert(nbBits >= 1); + return (bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> (((regMask+1)-nbBits) & regMask); } MEM_STATIC FORCE_INLINE_ATTR void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits) @@ -397,7 +397,7 @@ MEM_STATIC FORCE_INLINE_ATTR void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits) /*! BIT_readBits() : * Read (consume) next n bits from local register and update. * Pay attention to not read more than nbBits contained into local register. - * @return : extracted value. */ + * @return : extracted value. */ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits) { size_t const value = BIT_lookBits(bitD, nbBits); @@ -406,11 +406,11 @@ MEM_STATIC FORCE_INLINE_ATTR size_t BIT_readBits(BIT_DStream_t* bitD, unsigned n } /*! BIT_readBitsFast() : - * unsafe version; only works only if nbBits >= 1 */ + * unsafe version; only works only if nbBits >= 1 */ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits) { size_t const value = BIT_lookBitsFast(bitD, nbBits); - assert(nbBits >= 1); + assert(nbBits >= 1); BIT_skipBits(bitD, nbBits); return value; } @@ -433,23 +433,23 @@ MEM_STATIC BIT_DStream_status BIT_reloadDStreamFast(BIT_DStream_t* bitD) } /*! BIT_reloadDStream() : - * Refill `bitD` from buffer previously set in BIT_initDStream() . - * This function is safe, it guarantees it will not read beyond src buffer. - * @return : status of `BIT_DStream_t` internal register. - * when status == BIT_DStream_unfinished, internal register is filled with at least 25 or 57 bits */ + * Refill `bitD` from buffer previously set in BIT_initDStream() . + * This function is safe, it guarantees it will not read beyond src buffer. + * @return : status of `BIT_DStream_t` internal register. + * when status == BIT_DStream_unfinished, internal register is filled with at least 25 or 57 bits */ MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD) { - if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* overflow detected, like end of stream */ - return BIT_DStream_overflow; + if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* overflow detected, like end of stream */ + return BIT_DStream_overflow; - if (bitD->ptr >= bitD->limitPtr) { + if (bitD->ptr >= bitD->limitPtr) { return BIT_reloadDStreamFast(bitD); } if (bitD->ptr == bitD->start) { if (bitD->bitsConsumed < sizeof(bitD->bitContainer)*8) return BIT_DStream_endOfBuffer; return BIT_DStream_completed; } - /* start < ptr < limitPtr */ + /* start < ptr < limitPtr */ { U32 nbBytes = bitD->bitsConsumed >> 3; BIT_DStream_status result = BIT_DStream_unfinished; if (bitD->ptr - nbBytes < bitD->start) { @@ -458,14 +458,14 @@ MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD) } bitD->ptr -= nbBytes; bitD->bitsConsumed -= nbBytes*8; - bitD->bitContainer = MEM_readLEST(bitD->ptr); /* reminder : srcSize > sizeof(bitD->bitContainer), otherwise bitD->ptr == bitD->start */ + bitD->bitContainer = MEM_readLEST(bitD->ptr); /* reminder : srcSize > sizeof(bitD->bitContainer), otherwise bitD->ptr == bitD->start */ return result; } } /*! BIT_endOfDStream() : - * @return : 1 if DStream has _exactly_ reached its end (all bits consumed). - */ + * @return : 1 if DStream has _exactly_ reached its end (all bits consumed). + */ MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* DStream) { return ((DStream->ptr == DStream->start) && (DStream->bitsConsumed == sizeof(DStream->bitContainer)*8)); diff --git a/contrib/libs/zstd/lib/common/compiler.h b/contrib/libs/zstd/lib/common/compiler.h index 516930c01e..441b3586d2 100644 --- a/contrib/libs/zstd/lib/common/compiler.h +++ b/contrib/libs/zstd/lib/common/compiler.h @@ -1,38 +1,38 @@ -/* +/* * Copyright (c) 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_COMPILER_H -#define ZSTD_COMPILER_H - + * 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_COMPILER_H +#define ZSTD_COMPILER_H + #include "portability_macros.h" -/*-******************************************************* -* Compiler specifics -*********************************************************/ -/* force inlining */ +/*-******************************************************* +* Compiler specifics +*********************************************************/ +/* force inlining */ #if !defined(ZSTD_NO_INLINE) #if (defined(__GNUC__) && !defined(__STRICT_ANSI__)) || defined(__cplusplus) || defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */ -# define INLINE_KEYWORD inline -#else -# define INLINE_KEYWORD -#endif - +# define INLINE_KEYWORD inline +#else +# define INLINE_KEYWORD +#endif + #if defined(__GNUC__) || defined(__ICCARM__) -# define FORCE_INLINE_ATTR __attribute__((always_inline)) -#elif defined(_MSC_VER) -# define FORCE_INLINE_ATTR __forceinline -#else -# define FORCE_INLINE_ATTR -#endif - +# define FORCE_INLINE_ATTR __attribute__((always_inline)) +#elif defined(_MSC_VER) +# define FORCE_INLINE_ATTR __forceinline +#else +# define FORCE_INLINE_ATTR +#endif + #else #define INLINE_KEYWORD @@ -40,7 +40,7 @@ #endif -/** +/** On MSVC qsort requires that functions passed into it use the __cdecl calling conversion(CC). This explicitly marks such functions as __cdecl so that the code will still compile if a CC other than __cdecl has been made the default. @@ -52,28 +52,28 @@ #endif /** - * FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant + * FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant * parameters. They must be inlined for the compiler to eliminate the constant - * branches. - */ -#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR -/** - * HINT_INLINE is used to help the compiler generate better code. It is *not* - * used for "templates", so it can be tweaked based on the compilers - * performance. - * - * gcc-4.8 and gcc-4.9 have been shown to benefit from leaving off the - * always_inline attribute. - * - * clang up to 5.0.0 (trunk) benefit tremendously from the always_inline - * attribute. - */ -#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 4 && __GNUC_MINOR__ >= 8 && __GNUC__ < 5 -# define HINT_INLINE static INLINE_KEYWORD -#else -# define HINT_INLINE static INLINE_KEYWORD FORCE_INLINE_ATTR -#endif - + * branches. + */ +#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR +/** + * HINT_INLINE is used to help the compiler generate better code. It is *not* + * used for "templates", so it can be tweaked based on the compilers + * performance. + * + * gcc-4.8 and gcc-4.9 have been shown to benefit from leaving off the + * always_inline attribute. + * + * clang up to 5.0.0 (trunk) benefit tremendously from the always_inline + * attribute. + */ +#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 4 && __GNUC_MINOR__ >= 8 && __GNUC__ < 5 +# define HINT_INLINE static INLINE_KEYWORD +#else +# define HINT_INLINE static INLINE_KEYWORD FORCE_INLINE_ATTR +#endif + /* UNUSED_ATTR tells the compiler it is okay if the function is unused. */ #if defined(__GNUC__) # define UNUSED_ATTR __attribute__((unused)) @@ -81,37 +81,37 @@ # define UNUSED_ATTR #endif -/* force no inlining */ -#ifdef _MSC_VER -# define FORCE_NOINLINE static __declspec(noinline) -#else +/* force no inlining */ +#ifdef _MSC_VER +# define FORCE_NOINLINE static __declspec(noinline) +#else # if defined(__GNUC__) || defined(__ICCARM__) -# define FORCE_NOINLINE static __attribute__((__noinline__)) -# else -# define FORCE_NOINLINE static -# endif -#endif - - -/* target attribute */ +# define FORCE_NOINLINE static __attribute__((__noinline__)) +# else +# define FORCE_NOINLINE static +# endif +#endif + + +/* target attribute */ #if defined(__GNUC__) || defined(__ICCARM__) -# define TARGET_ATTRIBUTE(target) __attribute__((__target__(target))) -#else -# define TARGET_ATTRIBUTE(target) -#endif - +# define TARGET_ATTRIBUTE(target) __attribute__((__target__(target))) +#else +# define TARGET_ATTRIBUTE(target) +#endif + /* Target attribute for BMI2 dynamic dispatch. * Enable lzcnt, bmi, and bmi2. * We test for bmi1 & bmi2. lzcnt is included in bmi1. - */ + */ #define BMI2_TARGET_ATTRIBUTE TARGET_ATTRIBUTE("lzcnt,bmi,bmi2") - + /* prefetch * can be disabled, by declaring NO_PREFETCH build macro */ #if defined(NO_PREFETCH) # define PREFETCH_L1(ptr) (void)(ptr) /* disabled */ # define PREFETCH_L2(ptr) (void)(ptr) /* disabled */ -#else +#else # if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_I86)) /* _mm_prefetch() is not defined outside of x86/x64 */ # include <mmintrin.h> /* https://msdn.microsoft.com/fr-fr/library/84szxsww(v=vs.90).aspx */ # define PREFETCH_L1(ptr) _mm_prefetch((const char*)(ptr), _MM_HINT_T0) @@ -127,7 +127,7 @@ # define PREFETCH_L2(ptr) (void)(ptr) /* disabled */ # endif #endif /* NO_PREFETCH */ - + #define CACHELINE_SIZE 64 #define PREFETCH_AREA(p, s) { \ @@ -165,16 +165,16 @@ #define UNLIKELY(x) (x) #endif -/* disable warnings */ -#ifdef _MSC_VER /* Visual Studio */ -# include <intrin.h> /* For Visual 2005 */ -# pragma warning(disable : 4100) /* disable: C4100: unreferenced formal parameter */ -# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ -# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */ -# pragma warning(disable : 4214) /* disable: C4214: non-int bitfields */ -# pragma warning(disable : 4324) /* disable: C4324: padded structure */ -#endif - +/* disable warnings */ +#ifdef _MSC_VER /* Visual Studio */ +# include <intrin.h> /* For Visual 2005 */ +# pragma warning(disable : 4100) /* disable: C4100: unreferenced formal parameter */ +# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ +# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */ +# pragma warning(disable : 4214) /* disable: C4214: non-int bitfields */ +# pragma warning(disable : 4324) /* disable: C4324: padded structure */ +#endif + /*Like DYNAMIC_BMI2 but for compile time determination of BMI2 support*/ #ifndef STATIC_BMI2 # if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_I86)) @@ -332,4 +332,4 @@ void __asan_poison_memory_region(void const volatile *addr, size_t size); void __asan_unpoison_memory_region(void const volatile *addr, size_t size); #endif -#endif /* ZSTD_COMPILER_H */ +#endif /* ZSTD_COMPILER_H */ diff --git a/contrib/libs/zstd/lib/common/cpu.h b/contrib/libs/zstd/lib/common/cpu.h index 8acd33be3c..547cea7efd 100644 --- a/contrib/libs/zstd/lib/common/cpu.h +++ b/contrib/libs/zstd/lib/common/cpu.h @@ -1,213 +1,213 @@ -/* +/* * Copyright (c) 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_COMMON_CPU_H -#define ZSTD_COMMON_CPU_H - -/** - * Implementation taken from folly/CpuId.h - * https://github.com/facebook/folly/blob/master/folly/CpuId.h - */ - -#include "mem.h" - -#ifdef _MSC_VER -#include <intrin.h> -#endif - -typedef struct { - U32 f1c; - U32 f1d; - U32 f7b; - U32 f7c; -} ZSTD_cpuid_t; - -MEM_STATIC ZSTD_cpuid_t ZSTD_cpuid(void) { - U32 f1c = 0; - U32 f1d = 0; - U32 f7b = 0; - U32 f7c = 0; + * 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_COMMON_CPU_H +#define ZSTD_COMMON_CPU_H + +/** + * Implementation taken from folly/CpuId.h + * https://github.com/facebook/folly/blob/master/folly/CpuId.h + */ + +#include "mem.h" + +#ifdef _MSC_VER +#include <intrin.h> +#endif + +typedef struct { + U32 f1c; + U32 f1d; + U32 f7b; + U32 f7c; +} ZSTD_cpuid_t; + +MEM_STATIC ZSTD_cpuid_t ZSTD_cpuid(void) { + U32 f1c = 0; + U32 f1d = 0; + U32 f7b = 0; + U32 f7c = 0; #if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_IX86)) - int reg[4]; - __cpuid((int*)reg, 0); - { - int const n = reg[0]; - if (n >= 1) { - __cpuid((int*)reg, 1); - f1c = (U32)reg[2]; - f1d = (U32)reg[3]; - } - if (n >= 7) { - __cpuidex((int*)reg, 7, 0); - f7b = (U32)reg[1]; - f7c = (U32)reg[2]; - } - } -#elif defined(__i386__) && defined(__PIC__) && !defined(__clang__) && defined(__GNUC__) - /* The following block like the normal cpuid branch below, but gcc - * reserves ebx for use of its pic register so we must specially - * handle the save and restore to avoid clobbering the register - */ - U32 n; - __asm__( - "pushl %%ebx\n\t" - "cpuid\n\t" - "popl %%ebx\n\t" - : "=a"(n) - : "a"(0) - : "ecx", "edx"); - if (n >= 1) { - U32 f1a; - __asm__( - "pushl %%ebx\n\t" - "cpuid\n\t" - "popl %%ebx\n\t" - : "=a"(f1a), "=c"(f1c), "=d"(f1d) + int reg[4]; + __cpuid((int*)reg, 0); + { + int const n = reg[0]; + if (n >= 1) { + __cpuid((int*)reg, 1); + f1c = (U32)reg[2]; + f1d = (U32)reg[3]; + } + if (n >= 7) { + __cpuidex((int*)reg, 7, 0); + f7b = (U32)reg[1]; + f7c = (U32)reg[2]; + } + } +#elif defined(__i386__) && defined(__PIC__) && !defined(__clang__) && defined(__GNUC__) + /* The following block like the normal cpuid branch below, but gcc + * reserves ebx for use of its pic register so we must specially + * handle the save and restore to avoid clobbering the register + */ + U32 n; + __asm__( + "pushl %%ebx\n\t" + "cpuid\n\t" + "popl %%ebx\n\t" + : "=a"(n) + : "a"(0) + : "ecx", "edx"); + if (n >= 1) { + U32 f1a; + __asm__( + "pushl %%ebx\n\t" + "cpuid\n\t" + "popl %%ebx\n\t" + : "=a"(f1a), "=c"(f1c), "=d"(f1d) : "a"(1)); - } - if (n >= 7) { - __asm__( - "pushl %%ebx\n\t" - "cpuid\n\t" + } + if (n >= 7) { + __asm__( + "pushl %%ebx\n\t" + "cpuid\n\t" "movl %%ebx, %%eax\n\t" - "popl %%ebx" - : "=a"(f7b), "=c"(f7c) - : "a"(7), "c"(0) - : "edx"); - } -#elif defined(__x86_64__) || defined(_M_X64) || defined(__i386__) - U32 n; - __asm__("cpuid" : "=a"(n) : "a"(0) : "ebx", "ecx", "edx"); - if (n >= 1) { - U32 f1a; - __asm__("cpuid" : "=a"(f1a), "=c"(f1c), "=d"(f1d) : "a"(1) : "ebx"); - } - if (n >= 7) { - U32 f7a; - __asm__("cpuid" - : "=a"(f7a), "=b"(f7b), "=c"(f7c) - : "a"(7), "c"(0) - : "edx"); - } -#endif - { - ZSTD_cpuid_t cpuid; - cpuid.f1c = f1c; - cpuid.f1d = f1d; - cpuid.f7b = f7b; - cpuid.f7c = f7c; - return cpuid; - } -} - -#define X(name, r, bit) \ - MEM_STATIC int ZSTD_cpuid_##name(ZSTD_cpuid_t const cpuid) { \ - return ((cpuid.r) & (1U << bit)) != 0; \ - } - -/* cpuid(1): Processor Info and Feature Bits. */ -#define C(name, bit) X(name, f1c, bit) - C(sse3, 0) - C(pclmuldq, 1) - C(dtes64, 2) - C(monitor, 3) - C(dscpl, 4) - C(vmx, 5) - C(smx, 6) - C(eist, 7) - C(tm2, 8) - C(ssse3, 9) - C(cnxtid, 10) - C(fma, 12) - C(cx16, 13) - C(xtpr, 14) - C(pdcm, 15) - C(pcid, 17) - C(dca, 18) - C(sse41, 19) - C(sse42, 20) - C(x2apic, 21) - C(movbe, 22) - C(popcnt, 23) - C(tscdeadline, 24) - C(aes, 25) - C(xsave, 26) - C(osxsave, 27) - C(avx, 28) - C(f16c, 29) - C(rdrand, 30) -#undef C -#define D(name, bit) X(name, f1d, bit) - D(fpu, 0) - D(vme, 1) - D(de, 2) - D(pse, 3) - D(tsc, 4) - D(msr, 5) - D(pae, 6) - D(mce, 7) - D(cx8, 8) - D(apic, 9) - D(sep, 11) - D(mtrr, 12) - D(pge, 13) - D(mca, 14) - D(cmov, 15) - D(pat, 16) - D(pse36, 17) - D(psn, 18) - D(clfsh, 19) - D(ds, 21) - D(acpi, 22) - D(mmx, 23) - D(fxsr, 24) - D(sse, 25) - D(sse2, 26) - D(ss, 27) - D(htt, 28) - D(tm, 29) - D(pbe, 31) -#undef D - -/* cpuid(7): Extended Features. */ -#define B(name, bit) X(name, f7b, bit) - B(bmi1, 3) - B(hle, 4) - B(avx2, 5) - B(smep, 7) - B(bmi2, 8) - B(erms, 9) - B(invpcid, 10) - B(rtm, 11) - B(mpx, 14) - B(avx512f, 16) - B(avx512dq, 17) - B(rdseed, 18) - B(adx, 19) - B(smap, 20) - B(avx512ifma, 21) - B(pcommit, 22) - B(clflushopt, 23) - B(clwb, 24) - B(avx512pf, 26) - B(avx512er, 27) - B(avx512cd, 28) - B(sha, 29) - B(avx512bw, 30) - B(avx512vl, 31) -#undef B -#define C(name, bit) X(name, f7c, bit) - C(prefetchwt1, 0) - C(avx512vbmi, 1) -#undef C - -#undef X - -#endif /* ZSTD_COMMON_CPU_H */ + "popl %%ebx" + : "=a"(f7b), "=c"(f7c) + : "a"(7), "c"(0) + : "edx"); + } +#elif defined(__x86_64__) || defined(_M_X64) || defined(__i386__) + U32 n; + __asm__("cpuid" : "=a"(n) : "a"(0) : "ebx", "ecx", "edx"); + if (n >= 1) { + U32 f1a; + __asm__("cpuid" : "=a"(f1a), "=c"(f1c), "=d"(f1d) : "a"(1) : "ebx"); + } + if (n >= 7) { + U32 f7a; + __asm__("cpuid" + : "=a"(f7a), "=b"(f7b), "=c"(f7c) + : "a"(7), "c"(0) + : "edx"); + } +#endif + { + ZSTD_cpuid_t cpuid; + cpuid.f1c = f1c; + cpuid.f1d = f1d; + cpuid.f7b = f7b; + cpuid.f7c = f7c; + return cpuid; + } +} + +#define X(name, r, bit) \ + MEM_STATIC int ZSTD_cpuid_##name(ZSTD_cpuid_t const cpuid) { \ + return ((cpuid.r) & (1U << bit)) != 0; \ + } + +/* cpuid(1): Processor Info and Feature Bits. */ +#define C(name, bit) X(name, f1c, bit) + C(sse3, 0) + C(pclmuldq, 1) + C(dtes64, 2) + C(monitor, 3) + C(dscpl, 4) + C(vmx, 5) + C(smx, 6) + C(eist, 7) + C(tm2, 8) + C(ssse3, 9) + C(cnxtid, 10) + C(fma, 12) + C(cx16, 13) + C(xtpr, 14) + C(pdcm, 15) + C(pcid, 17) + C(dca, 18) + C(sse41, 19) + C(sse42, 20) + C(x2apic, 21) + C(movbe, 22) + C(popcnt, 23) + C(tscdeadline, 24) + C(aes, 25) + C(xsave, 26) + C(osxsave, 27) + C(avx, 28) + C(f16c, 29) + C(rdrand, 30) +#undef C +#define D(name, bit) X(name, f1d, bit) + D(fpu, 0) + D(vme, 1) + D(de, 2) + D(pse, 3) + D(tsc, 4) + D(msr, 5) + D(pae, 6) + D(mce, 7) + D(cx8, 8) + D(apic, 9) + D(sep, 11) + D(mtrr, 12) + D(pge, 13) + D(mca, 14) + D(cmov, 15) + D(pat, 16) + D(pse36, 17) + D(psn, 18) + D(clfsh, 19) + D(ds, 21) + D(acpi, 22) + D(mmx, 23) + D(fxsr, 24) + D(sse, 25) + D(sse2, 26) + D(ss, 27) + D(htt, 28) + D(tm, 29) + D(pbe, 31) +#undef D + +/* cpuid(7): Extended Features. */ +#define B(name, bit) X(name, f7b, bit) + B(bmi1, 3) + B(hle, 4) + B(avx2, 5) + B(smep, 7) + B(bmi2, 8) + B(erms, 9) + B(invpcid, 10) + B(rtm, 11) + B(mpx, 14) + B(avx512f, 16) + B(avx512dq, 17) + B(rdseed, 18) + B(adx, 19) + B(smap, 20) + B(avx512ifma, 21) + B(pcommit, 22) + B(clflushopt, 23) + B(clwb, 24) + B(avx512pf, 26) + B(avx512er, 27) + B(avx512cd, 28) + B(sha, 29) + B(avx512bw, 30) + B(avx512vl, 31) +#undef B +#define C(name, bit) X(name, f7c, bit) + C(prefetchwt1, 0) + C(avx512vbmi, 1) +#undef C + +#undef X + +#endif /* ZSTD_COMMON_CPU_H */ diff --git a/contrib/libs/zstd/lib/common/entropy_common.c b/contrib/libs/zstd/lib/common/entropy_common.c index 4229b40c5e..7734a6d40f 100644 --- a/contrib/libs/zstd/lib/common/entropy_common.c +++ b/contrib/libs/zstd/lib/common/entropy_common.c @@ -23,12 +23,12 @@ #include "huf.h" -/*=== Version ===*/ -unsigned FSE_versionNumber(void) { return FSE_VERSION_NUMBER; } - - -/*=== Error Management ===*/ -unsigned FSE_isError(size_t code) { return ERR_isError(code); } +/*=== Version ===*/ +unsigned FSE_versionNumber(void) { return FSE_VERSION_NUMBER; } + + +/*=== Error Management ===*/ +unsigned FSE_isError(size_t code) { return ERR_isError(code); } const char* FSE_getErrorName(size_t code) { return ERR_getErrorName(code); } unsigned HUF_isError(size_t code) { return ERR_isError(code); } @@ -158,15 +158,15 @@ size_t FSE_readNCount_body(short* normalizedCounter, unsigned* maxSVPtr, unsigne } { int const max = (2*threshold-1) - remaining; - int count; + int count; if ((bitStream & (threshold-1)) < (U32)max) { - count = bitStream & (threshold-1); - bitCount += nbBits-1; + count = bitStream & (threshold-1); + bitCount += nbBits-1; } else { - count = bitStream & (2*threshold-1); + count = bitStream & (2*threshold-1); if (count >= threshold) count -= max; - bitCount += nbBits; + bitCount += nbBits; } count--; /* extra accuracy */ @@ -179,7 +179,7 @@ size_t FSE_readNCount_body(short* normalizedCounter, unsigned* maxSVPtr, unsigne assert(count == -1); remaining += count; } - normalizedCounter[charnum++] = (short)count; + normalizedCounter[charnum++] = (short)count; previous0 = !count; assert(threshold > 1); diff --git a/contrib/libs/zstd/lib/common/error_private.c b/contrib/libs/zstd/lib/common/error_private.c index 6d1135f8c3..cd5eda3191 100644 --- a/contrib/libs/zstd/lib/common/error_private.c +++ b/contrib/libs/zstd/lib/common/error_private.c @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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. */ /* The purpose of this file is to have a single list of error strings embedded in binary */ @@ -27,26 +27,26 @@ const char* ERR_getErrorString(ERR_enum code) case PREFIX(version_unsupported): return "Version not supported"; case PREFIX(frameParameter_unsupported): return "Unsupported frame parameter"; case PREFIX(frameParameter_windowTooLarge): return "Frame requires too much memory for decoding"; - case PREFIX(corruption_detected): return "Corrupted block detected"; - case PREFIX(checksum_wrong): return "Restored data doesn't match checksum"; - case PREFIX(parameter_unsupported): return "Unsupported parameter"; - case PREFIX(parameter_outOfBound): return "Parameter is out of bound"; + case PREFIX(corruption_detected): return "Corrupted block detected"; + case PREFIX(checksum_wrong): return "Restored data doesn't match checksum"; + case PREFIX(parameter_unsupported): return "Unsupported parameter"; + case PREFIX(parameter_outOfBound): return "Parameter is out of bound"; case PREFIX(init_missing): return "Context should be init first"; case PREFIX(memory_allocation): return "Allocation error : not enough memory"; - case PREFIX(workSpace_tooSmall): return "workSpace buffer is not large enough"; + case PREFIX(workSpace_tooSmall): return "workSpace buffer is not large enough"; case PREFIX(stage_wrong): return "Operation not authorized at current processing stage"; case PREFIX(tableLog_tooLarge): return "tableLog requires too much memory : unsupported"; case PREFIX(maxSymbolValue_tooLarge): return "Unsupported max Symbol Value : too large"; case PREFIX(maxSymbolValue_tooSmall): return "Specified maxSymbolValue is too small"; case PREFIX(dictionary_corrupted): return "Dictionary is corrupted"; case PREFIX(dictionary_wrong): return "Dictionary mismatch"; - case PREFIX(dictionaryCreation_failed): return "Cannot create Dictionary from provided samples"; - case PREFIX(dstSize_tooSmall): return "Destination buffer is too small"; - case PREFIX(srcSize_wrong): return "Src size is incorrect"; + case PREFIX(dictionaryCreation_failed): return "Cannot create Dictionary from provided samples"; + case PREFIX(dstSize_tooSmall): return "Destination buffer is too small"; + case PREFIX(srcSize_wrong): return "Src size is incorrect"; case PREFIX(dstBuffer_null): return "Operation on NULL destination buffer"; - /* following error codes are not stable and may be removed or changed in a future version */ - case PREFIX(frameIndex_tooLarge): return "Frame index is too large"; - case PREFIX(seekableIO): return "An I/O error occurred when reading/seeking"; + /* following error codes are not stable and may be removed or changed in a future version */ + case PREFIX(frameIndex_tooLarge): return "Frame index is too large"; + case PREFIX(seekableIO): return "An I/O error occurred when reading/seeking"; case PREFIX(dstBuffer_wrong): return "Destination buffer is wrong"; case PREFIX(srcBuffer_wrong): return "Source buffer is wrong"; case PREFIX(maxCode): diff --git a/contrib/libs/zstd/lib/common/error_private.h b/contrib/libs/zstd/lib/common/error_private.h index 007d81066a..f61fc3b02f 100644 --- a/contrib/libs/zstd/lib/common/error_private.h +++ b/contrib/libs/zstd/lib/common/error_private.h @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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. */ /* Note : this module is expected to remain private, do not expose it */ @@ -52,8 +52,8 @@ typedef ZSTD_ErrorCode ERR_enum; * Error codes handling ******************************************/ #undef ERROR /* already defined on Visual Studio */ -#define ERROR(name) ZSTD_ERROR(name) -#define ZSTD_ERROR(name) ((size_t)-PREFIX(name)) +#define ERROR(name) ZSTD_ERROR(name) +#define ZSTD_ERROR(name) ((size_t)-PREFIX(name)) ERR_STATIC unsigned ERR_isError(size_t code) { return (code > ERROR(maxCode)); } diff --git a/contrib/libs/zstd/lib/common/fse.h b/contrib/libs/zstd/lib/common/fse.h index 714bfd3e7f..c35d3c6e11 100644 --- a/contrib/libs/zstd/lib/common/fse.h +++ b/contrib/libs/zstd/lib/common/fse.h @@ -16,42 +16,42 @@ extern "C" { #endif -#ifndef FSE_H -#define FSE_H - +#ifndef FSE_H +#define FSE_H + /*-***************************************** * Dependencies ******************************************/ #include "zstd_deps.h" /* size_t, ptrdiff_t */ -/*-***************************************** -* FSE_PUBLIC_API : control library symbols visibility -******************************************/ -#if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4) -# define FSE_PUBLIC_API __attribute__ ((visibility ("default"))) -#elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) /* Visual expected */ -# define FSE_PUBLIC_API __declspec(dllexport) -#elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1) -# define FSE_PUBLIC_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ -#else -# define FSE_PUBLIC_API -#endif - -/*------ Version ------*/ -#define FSE_VERSION_MAJOR 0 -#define FSE_VERSION_MINOR 9 -#define FSE_VERSION_RELEASE 0 - -#define FSE_LIB_VERSION FSE_VERSION_MAJOR.FSE_VERSION_MINOR.FSE_VERSION_RELEASE -#define FSE_QUOTE(str) #str -#define FSE_EXPAND_AND_QUOTE(str) FSE_QUOTE(str) -#define FSE_VERSION_STRING FSE_EXPAND_AND_QUOTE(FSE_LIB_VERSION) - -#define FSE_VERSION_NUMBER (FSE_VERSION_MAJOR *100*100 + FSE_VERSION_MINOR *100 + FSE_VERSION_RELEASE) -FSE_PUBLIC_API unsigned FSE_versionNumber(void); /**< library version number; to be used when checking dll version */ - +/*-***************************************** +* FSE_PUBLIC_API : control library symbols visibility +******************************************/ +#if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4) +# define FSE_PUBLIC_API __attribute__ ((visibility ("default"))) +#elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) /* Visual expected */ +# define FSE_PUBLIC_API __declspec(dllexport) +#elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1) +# define FSE_PUBLIC_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ +#else +# define FSE_PUBLIC_API +#endif + +/*------ Version ------*/ +#define FSE_VERSION_MAJOR 0 +#define FSE_VERSION_MINOR 9 +#define FSE_VERSION_RELEASE 0 + +#define FSE_LIB_VERSION FSE_VERSION_MAJOR.FSE_VERSION_MINOR.FSE_VERSION_RELEASE +#define FSE_QUOTE(str) #str +#define FSE_EXPAND_AND_QUOTE(str) FSE_QUOTE(str) +#define FSE_VERSION_STRING FSE_EXPAND_AND_QUOTE(FSE_LIB_VERSION) + +#define FSE_VERSION_NUMBER (FSE_VERSION_MAJOR *100*100 + FSE_VERSION_MINOR *100 + FSE_VERSION_RELEASE) +FSE_PUBLIC_API unsigned FSE_versionNumber(void); /**< library version number; to be used when checking dll version */ + /*-**************************************** * FSE simple functions @@ -64,8 +64,8 @@ FSE_PUBLIC_API unsigned FSE_versionNumber(void); /**< library version number; if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression instead. if FSE_isError(return), compression failed (more details using FSE_getErrorName()) */ -FSE_PUBLIC_API size_t FSE_compress(void* dst, size_t dstCapacity, - const void* src, size_t srcSize); +FSE_PUBLIC_API size_t FSE_compress(void* dst, size_t dstCapacity, + const void* src, size_t srcSize); /*! FSE_decompress(): Decompress FSE data from buffer 'cSrc', of size 'cSrcSize', @@ -77,18 +77,18 @@ FSE_PUBLIC_API size_t FSE_compress(void* dst, size_t dstCapacity, Why ? : making this distinction requires a header. Header management is intentionally delegated to the user layer, which can better manage special cases. */ -FSE_PUBLIC_API size_t FSE_decompress(void* dst, size_t dstCapacity, - const void* cSrc, size_t cSrcSize); +FSE_PUBLIC_API size_t FSE_decompress(void* dst, size_t dstCapacity, + const void* cSrc, size_t cSrcSize); /*-***************************************** * Tool functions ******************************************/ -FSE_PUBLIC_API size_t FSE_compressBound(size_t size); /* maximum compressed size */ +FSE_PUBLIC_API size_t FSE_compressBound(size_t size); /* maximum compressed size */ /* Error Management */ -FSE_PUBLIC_API unsigned FSE_isError(size_t code); /* tells if a return value is an error code */ -FSE_PUBLIC_API const char* FSE_getErrorName(size_t code); /* provides error code string (useful for debugging) */ +FSE_PUBLIC_API unsigned FSE_isError(size_t code); /* tells if a return value is an error code */ +FSE_PUBLIC_API const char* FSE_getErrorName(size_t code); /* provides error code string (useful for debugging) */ /*-***************************************** @@ -102,7 +102,7 @@ FSE_PUBLIC_API const char* FSE_getErrorName(size_t code); /* provides error co if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression. if FSE_isError(return), it's an error code. */ -FSE_PUBLIC_API size_t FSE_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog); +FSE_PUBLIC_API size_t FSE_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog); /*-***************************************** @@ -132,7 +132,7 @@ or to save and provide normalized distribution using external method. dynamically downsize 'tableLog' when conditions are met. It saves CPU time, by using smaller tables, while preserving or even improving compression ratio. @return : recommended tableLog (necessarily <= 'maxTableLog') */ -FSE_PUBLIC_API unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue); +FSE_PUBLIC_API unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue); /*! FSE_normalizeCount(): normalize counts so that sum(count[]) == Power_of_2 (2^tableLog) @@ -151,7 +151,7 @@ FSE_PUBLIC_API size_t FSE_normalizeCount(short* normalizedCounter, unsigned tabl /*! FSE_NCountWriteBound(): Provides the maximum possible size of an FSE normalized table, given 'maxSymbolValue' and 'tableLog'. Typically useful for allocation purpose. */ -FSE_PUBLIC_API size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog); +FSE_PUBLIC_API size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog); /*! FSE_writeNCount(): Compactly save 'normalizedCounter' into 'buffer'. @@ -164,20 +164,20 @@ FSE_PUBLIC_API size_t FSE_writeNCount (void* buffer, size_t bufferSize, /*! Constructor and Destructor of FSE_CTable. Note that FSE_CTable size depends on 'tableLog' and 'maxSymbolValue' */ typedef unsigned FSE_CTable; /* don't allocate that. It's only meant to be more restrictive than void* */ -FSE_PUBLIC_API FSE_CTable* FSE_createCTable (unsigned maxSymbolValue, unsigned tableLog); -FSE_PUBLIC_API void FSE_freeCTable (FSE_CTable* ct); +FSE_PUBLIC_API FSE_CTable* FSE_createCTable (unsigned maxSymbolValue, unsigned tableLog); +FSE_PUBLIC_API void FSE_freeCTable (FSE_CTable* ct); /*! FSE_buildCTable(): Builds `ct`, which must be already allocated, using FSE_createCTable(). @return : 0, or an errorCode, which can be tested using FSE_isError() */ -FSE_PUBLIC_API size_t FSE_buildCTable(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog); +FSE_PUBLIC_API size_t FSE_buildCTable(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog); /*! FSE_compress_usingCTable(): Compress `src` using `ct` into `dst` which must be already allocated. @return : size of compressed data (<= `dstCapacity`), or 0 if compressed data could not fit into `dst`, or an errorCode, which can be tested using FSE_isError() */ -FSE_PUBLIC_API size_t FSE_compress_usingCTable (void* dst, size_t dstCapacity, const void* src, size_t srcSize, const FSE_CTable* ct); +FSE_PUBLIC_API size_t FSE_compress_usingCTable (void* dst, size_t dstCapacity, const void* src, size_t srcSize, const FSE_CTable* ct); /*! Tutorial : @@ -244,20 +244,20 @@ FSE_PUBLIC_API size_t FSE_readNCount_bmi2(short* normalizedCounter, /*! Constructor and Destructor of FSE_DTable. Note that its size depends on 'tableLog' */ typedef unsigned FSE_DTable; /* don't allocate that. It's just a way to be more restrictive than void* */ -FSE_PUBLIC_API FSE_DTable* FSE_createDTable(unsigned tableLog); -FSE_PUBLIC_API void FSE_freeDTable(FSE_DTable* dt); +FSE_PUBLIC_API FSE_DTable* FSE_createDTable(unsigned tableLog); +FSE_PUBLIC_API void FSE_freeDTable(FSE_DTable* dt); /*! FSE_buildDTable(): Builds 'dt', which must be already allocated, using FSE_createDTable(). return : 0, or an errorCode, which can be tested using FSE_isError() */ -FSE_PUBLIC_API size_t FSE_buildDTable (FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog); +FSE_PUBLIC_API size_t FSE_buildDTable (FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog); /*! FSE_decompress_usingDTable(): Decompress compressed source `cSrc` of size `cSrcSize` using `dt` into `dst` which must be already allocated. @return : size of regenerated data (necessarily <= `dstCapacity`), or an errorCode, which can be tested using FSE_isError() */ -FSE_PUBLIC_API size_t FSE_decompress_usingDTable(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt); +FSE_PUBLIC_API size_t FSE_decompress_usingDTable(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt); /*! Tutorial : @@ -287,10 +287,10 @@ FSE_decompress_usingDTable() result will tell how many bytes were regenerated (< If there is an error, the function will return an error code, which can be tested using FSE_isError(). (ex: dst buffer too small) */ -#endif /* FSE_H */ +#endif /* FSE_H */ -#if defined(FSE_STATIC_LINKING_ONLY) && !defined(FSE_H_FSE_STATIC_LINKING_ONLY) -#define FSE_H_FSE_STATIC_LINKING_ONLY +#if defined(FSE_STATIC_LINKING_ONLY) && !defined(FSE_H_FSE_STATIC_LINKING_ONLY) +#define FSE_H_FSE_STATIC_LINKING_ONLY /* *** Dependency *** */ #include "bitstream.h" @@ -308,11 +308,11 @@ If there is an error, the function will return an error code, which can be teste #define FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) (1 + (1<<((maxTableLog)-1)) + (((maxSymbolValue)+1)*2)) #define FSE_DTABLE_SIZE_U32(maxTableLog) (1 + (1<<(maxTableLog))) -/* or use the size to malloc() space directly. Pay attention to alignment restrictions though */ -#define FSE_CTABLE_SIZE(maxTableLog, maxSymbolValue) (FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) * sizeof(FSE_CTable)) -#define FSE_DTABLE_SIZE(maxTableLog) (FSE_DTABLE_SIZE_U32(maxTableLog) * sizeof(FSE_DTable)) - +/* or use the size to malloc() space directly. Pay attention to alignment restrictions though */ +#define FSE_CTABLE_SIZE(maxTableLog, maxSymbolValue) (FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) * sizeof(FSE_CTable)) +#define FSE_DTABLE_SIZE(maxTableLog) (FSE_DTABLE_SIZE_U32(maxTableLog) * sizeof(FSE_DTable)) + /* ***************************************** * FSE advanced API ***************************************** */ @@ -361,11 +361,11 @@ size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size size_t FSE_decompress_wksp_bmi2(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize, int bmi2); /**< Same as FSE_decompress_wksp() but with dynamic BMI2 support. Pass 1 if your CPU supports BMI2 or 0 if it doesn't. */ -typedef enum { - FSE_repeat_none, /**< Cannot use the previous table */ - FSE_repeat_check, /**< Can use the previous table but it must be checked */ +typedef enum { + FSE_repeat_none, /**< Cannot use the previous table */ + FSE_repeat_check, /**< Can use the previous table but it must be checked */ FSE_repeat_valid /**< Can use the previous table and it is assumed to be valid */ - } FSE_repeat; + } FSE_repeat; /* ***************************************** * FSE symbol compression API @@ -539,9 +539,9 @@ MEM_STATIC void FSE_initCState2(FSE_CState_t* statePtr, const FSE_CTable* ct, U3 MEM_STATIC void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* statePtr, unsigned symbol) { - FSE_symbolCompressionTransform const symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol]; + FSE_symbolCompressionTransform const symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol]; const U16* const stateTable = (const U16*)(statePtr->stateTable); - U32 const nbBitsOut = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16); + U32 const nbBitsOut = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16); BIT_addBits(bitC, statePtr->value, nbBitsOut); statePtr->value = stateTable[ (statePtr->value >> nbBitsOut) + symbolTT.deltaFindState]; } diff --git a/contrib/libs/zstd/lib/common/fse_decompress.c b/contrib/libs/zstd/lib/common/fse_decompress.c index a5a358015f..f915ad58a2 100644 --- a/contrib/libs/zstd/lib/common/fse_decompress.c +++ b/contrib/libs/zstd/lib/common/fse_decompress.c @@ -18,10 +18,10 @@ ****************************************************************/ #include "debug.h" /* assert */ #include "bitstream.h" -#include "compiler.h" +#include "compiler.h" #define FSE_STATIC_LINKING_ONLY #include "fse.h" -#include "error_private.h" +#include "error_private.h" #define ZSTD_DEPS_NEED_MALLOC #include "zstd_deps.h" @@ -165,8 +165,8 @@ static size_t FSE_buildDTable_internal(FSE_DTable* dt, const short* normalizedCo { U32 u; for (u=0; u<tableSize; u++) { FSE_FUNCTION_TYPE const symbol = (FSE_FUNCTION_TYPE)(tableDecode[u].symbol); - U32 const nextState = symbolNext[symbol]++; - tableDecode[u].nbBits = (BYTE) (tableLog - BIT_highbit32(nextState) ); + U32 const nextState = symbolNext[symbol]++; + tableDecode[u].nbBits = (BYTE) (tableLog - BIT_highbit32(nextState) ); tableDecode[u].newState = (U16) ( (nextState << tableDecode[u].nbBits) - tableSize); } } @@ -228,7 +228,7 @@ size_t FSE_buildDTable_raw (FSE_DTable* dt, unsigned nbBits) return 0; } -FORCE_INLINE_TEMPLATE size_t FSE_decompress_usingDTable_generic( +FORCE_INLINE_TEMPLATE size_t FSE_decompress_usingDTable_generic( void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt, const unsigned fast) diff --git a/contrib/libs/zstd/lib/common/huf.h b/contrib/libs/zstd/lib/common/huf.h index 85518481ec..cc398f64c0 100644 --- a/contrib/libs/zstd/lib/common/huf.h +++ b/contrib/libs/zstd/lib/common/huf.h @@ -16,98 +16,98 @@ extern "C" { #endif -#ifndef HUF_H_298734234 -#define HUF_H_298734234 +#ifndef HUF_H_298734234 +#define HUF_H_298734234 /* *** Dependencies *** */ #include "zstd_deps.h" /* size_t */ -/* *** 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); - - +/* *** 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 */ +HUF_PUBLIC_API 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) */ +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) */ /* *** 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); + * 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`. + * 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 +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 */ @@ -117,9 +117,9 @@ HUF_PUBLIC_API size_t HUF_compress4X_wksp (void* dst, size_t dstCapacity, /* *** 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 - +#define HUF_TABLELOG_DEFAULT 11 /* default tableLog value when none specified */ +#define HUF_SYMBOLVALUE_MAX 255 + #define HUF_TABLELOG_ABSOLUTEMAX 12 /* absolute limit of HUF_MAX_TABLELOG. Beyond that value, code does not work */ #if (HUF_TABLELOG_MAX > HUF_TABLELOG_ABSOLUTEMAX) # error "HUF_TABLELOG_MAX is too large !" @@ -131,7 +131,7 @@ HUF_PUBLIC_API size_t HUF_compress4X_wksp (void* dst, size_t dstCapacity, ******************************************/ /* HUF buffer bounds */ #define HUF_CTABLEBOUND 129 -#define HUF_BLOCKBOUND(size) (size + (size>>8) + 8) /* only true when incompressible is pre-filtered with fast heuristic */ +#define HUF_BLOCKBOUND(size) (size + (size>>8) + 8) /* only true when incompressible is pre-filtered with fast heuristic */ #define HUF_COMPRESSBOUND(size) (HUF_CTABLEBOUND + HUF_BLOCKBOUND(size)) /* Macro version, useful for static allocation */ /* static allocation of HUF's Compression Table */ @@ -161,7 +161,7 @@ size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cS 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_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 @@ -171,22 +171,22 @@ size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, /* **************************************** - * HUF detailed API - * ****************************************/ - -/*! 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() - * 4. save Huffman table to memory buffer using HUF_writeCTable() - * 5. encode the data stream using HUF_compress4X_usingCTable() - * - * 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. - */ + * HUF detailed API + * ****************************************/ + +/*! 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() + * 4. save Huffman table to memory buffer using HUF_writeCTable() + * 5. encode the data stream using HUF_compress4X_usingCTable() + * + * 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_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); 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); @@ -194,40 +194,40 @@ size_t HUF_compress4X_usingCTable_bmi2(void* dst, size_t dstSize, const void* sr 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 */ +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. + } 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 */ +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_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. + * `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 (HUF_CTABLE_WORKSPACE_SIZE_U32 * sizeof(unsigned)) +#define HUF_CTABLE_WORKSPACE_SIZE_U32 (2*HUF_SYMBOLVALUE_MAX +1 +1) +#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); /*! HUF_readStats() : - * Read compact Huffman tree, saved by HUF_writeCTable(). - * `huffWeight` is destination buffer. - * @return : size read from `src` , or an error Code . - * Note : Needed by HUF_readCTable() and HUF_readDTableXn() . */ -size_t HUF_readStats(BYTE* huffWeight, size_t hwSize, - U32* rankStats, U32* nbSymbolsPtr, U32* tableLogPtr, + * Read compact Huffman tree, saved by HUF_writeCTable(). + * `huffWeight` is destination buffer. + * @return : size read from `src` , or an error Code . + * Note : Needed by HUF_readCTable() and HUF_readDTableXn() . */ +size_t HUF_readStats(BYTE* huffWeight, size_t hwSize, + U32* rankStats, U32* nbSymbolsPtr, U32* tableLogPtr, const void* src, size_t srcSize); /*! HUF_readStats_wksp() : @@ -244,7 +244,7 @@ size_t HUF_readStats_wksp(BYTE* huffWeight, size_t hwSize, int bmi2); /** HUF_readCTable() : - * Loading a CTable saved with HUF_writeCTable() */ + * Loading a CTable saved with HUF_writeCTable() */ size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize, unsigned *hasZeroWeights); /** HUF_getNbBitsFromCTable() : @@ -253,39 +253,39 @@ size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void U32 HUF_getNbBitsFromCTable(const HUF_CElt* symbolTable, U32 symbolValue); /* - * HUF_decompress() does the following: + * HUF_decompress() does the following: * 1. select the decompression algorithm (X1, X2) based on pre-computed heuristics - * 2. build Huffman table from save, using HUF_readDTableX?() - * 3. decode 1 or 4 segments in parallel using HUF_decompress?X?_usingDTable() - */ + * 2. build Huffman table from save, using HUF_readDTableX?() + * 3. decode 1 or 4 segments in parallel using HUF_decompress?X?_usingDTable() + */ /** HUF_selectDecoder() : - * Tells which decoder is likely to decode faster, - * based on a set of pre-computed metrics. + * Tells which decoder is likely to decode faster, + * based on a set of pre-computed metrics. * @return : 0==HUF_decompress4X1, 1==HUF_decompress4X2 . - * Assumption : 0 < dstSize <= 128 KB */ + * Assumption : 0 < dstSize <= 128 KB */ U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize); -/** - * The minimum workspace size for the `workSpace` used in +/** + * The minimum workspace size for the `workSpace` used in * HUF_readDTableX1_wksp() and HUF_readDTableX2_wksp(). - * - * The space used depends on HUF_TABLELOG_MAX, ranging from ~1500 bytes when - * HUF_TABLE_LOG_MAX=12 to ~1850 bytes when HUF_TABLE_LOG_MAX=15. - * Buffer overflow errors may potentially occur if code modifications result in - * a required workspace size greater than that specified in the following - * macro. - */ + * + * The space used depends on HUF_TABLELOG_MAX, ranging from ~1500 bytes when + * HUF_TABLE_LOG_MAX=12 to ~1850 bytes when HUF_TABLE_LOG_MAX=15. + * Buffer overflow errors may potentially occur if code modifications result in + * a required workspace size greater than that specified in the following + * macro. + */ #define HUF_DECOMPRESS_WORKSPACE_SIZE ((2 << 10) + (1 << 9)) -#define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32)) - +#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); +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); @@ -297,24 +297,24 @@ size_t HUF_decompress4X2_usingDTable(void* dst, size_t maxDstSize, const void* c #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); -/** 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. +/** 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 */ +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); size_t HUF_decompress1X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /* single-symbol decoder */ @@ -323,7 +323,7 @@ size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cS #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); +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 */ @@ -341,22 +341,22 @@ size_t HUF_decompress1X1_usingDTable(void* dst, size_t maxDstSize, const void* c 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); +/* 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); #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); #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_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); #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); #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); #endif - + #endif /* HUF_STATIC_LINKING_ONLY */ #if defined (__cplusplus) diff --git a/contrib/libs/zstd/lib/common/mem.h b/contrib/libs/zstd/lib/common/mem.h index 85581c3847..b46e47c00e 100644 --- a/contrib/libs/zstd/lib/common/mem.h +++ b/contrib/libs/zstd/lib/common/mem.h @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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 MEM_H_MODULE @@ -50,15 +50,15 @@ extern "C" { # else # include <stdint.h> /* intptr_t */ # endif - typedef uint8_t BYTE; + typedef uint8_t BYTE; typedef uint8_t U8; typedef int8_t S8; - typedef uint16_t U16; - typedef int16_t S16; - typedef uint32_t U32; - typedef int32_t S32; - typedef uint64_t U64; - typedef int64_t S64; + typedef uint16_t U16; + typedef int16_t S16; + typedef uint32_t U32; + typedef int32_t S32; + typedef uint64_t U64; + typedef int64_t S64; #else # include <limits.h> #if CHAR_BIT != 8 @@ -138,11 +138,11 @@ MEM_STATIC size_t MEM_swapST(size_t in); * Unfortunately, on some target/compiler combinations, the generated assembly is sub-optimal. * The below switch allow to select different access method for improved performance. * Method 0 (default) : use `memcpy()`. Safe and portable. - * Method 1 : `__packed` statement. It depends on compiler extension (i.e., not portable). + * Method 1 : `__packed` statement. It depends on compiler extension (i.e., not portable). * This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`. * Method 2 : direct access. This method is portable but violate C standard. * It can generate buggy code on targets depending on alignment. - * In some circumstances, it's the only known way to get the most performance (i.e. GCC + ARMv6) + * In some circumstances, it's the only known way to get the most performance (i.e. GCC + ARMv6) * See http://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details. * Prefer these methods in priority order (0 > 1 > 2) */ @@ -182,7 +182,7 @@ Only use if no other choice to achieve best performance on target platform */ MEM_STATIC U16 MEM_read16(const void* memPtr) { return *(const U16*) memPtr; } MEM_STATIC U32 MEM_read32(const void* memPtr) { return *(const U32*) memPtr; } MEM_STATIC U64 MEM_read64(const void* memPtr) { return *(const U64*) memPtr; } -MEM_STATIC size_t MEM_readST(const void* memPtr) { return *(const size_t*) memPtr; } +MEM_STATIC size_t MEM_readST(const void* memPtr) { return *(const size_t*) memPtr; } MEM_STATIC void MEM_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; } MEM_STATIC void MEM_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; } @@ -193,27 +193,27 @@ MEM_STATIC void MEM_write64(void* memPtr, U64 value) { *(U64*)memPtr = value; } /* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */ /* currently only defined for gcc and icc */ #if defined(_MSC_VER) || (defined(__INTEL_COMPILER) && defined(WIN32)) - __pragma( pack(push, 1) ) - typedef struct { U16 v; } unalign16; - typedef struct { U32 v; } unalign32; - typedef struct { U64 v; } unalign64; - typedef struct { size_t v; } unalignArch; + __pragma( pack(push, 1) ) + typedef struct { U16 v; } unalign16; + typedef struct { U32 v; } unalign32; + typedef struct { U64 v; } unalign64; + typedef struct { size_t v; } unalignArch; __pragma( pack(pop) ) #else - typedef struct { U16 v; } __attribute__((packed)) unalign16; - typedef struct { U32 v; } __attribute__((packed)) unalign32; - typedef struct { U64 v; } __attribute__((packed)) unalign64; - typedef struct { size_t v; } __attribute__((packed)) unalignArch; + typedef struct { U16 v; } __attribute__((packed)) unalign16; + typedef struct { U32 v; } __attribute__((packed)) unalign32; + typedef struct { U64 v; } __attribute__((packed)) unalign64; + typedef struct { size_t v; } __attribute__((packed)) unalignArch; #endif -MEM_STATIC U16 MEM_read16(const void* ptr) { return ((const unalign16*)ptr)->v; } -MEM_STATIC U32 MEM_read32(const void* ptr) { return ((const unalign32*)ptr)->v; } -MEM_STATIC U64 MEM_read64(const void* ptr) { return ((const unalign64*)ptr)->v; } -MEM_STATIC size_t MEM_readST(const void* ptr) { return ((const unalignArch*)ptr)->v; } +MEM_STATIC U16 MEM_read16(const void* ptr) { return ((const unalign16*)ptr)->v; } +MEM_STATIC U32 MEM_read32(const void* ptr) { return ((const unalign32*)ptr)->v; } +MEM_STATIC U64 MEM_read64(const void* ptr) { return ((const unalign64*)ptr)->v; } +MEM_STATIC size_t MEM_readST(const void* ptr) { return ((const unalignArch*)ptr)->v; } -MEM_STATIC void MEM_write16(void* memPtr, U16 value) { ((unalign16*)memPtr)->v = value; } -MEM_STATIC void MEM_write32(void* memPtr, U32 value) { ((unalign32*)memPtr)->v = value; } -MEM_STATIC void MEM_write64(void* memPtr, U64 value) { ((unalign64*)memPtr)->v = value; } +MEM_STATIC void MEM_write16(void* memPtr, U16 value) { ((unalign16*)memPtr)->v = value; } +MEM_STATIC void MEM_write32(void* memPtr, U32 value) { ((unalign32*)memPtr)->v = value; } +MEM_STATIC void MEM_write64(void* memPtr, U64 value) { ((unalign64*)memPtr)->v = value; } #else diff --git a/contrib/libs/zstd/lib/common/pool.c b/contrib/libs/zstd/lib/common/pool.c index 2e37cdd73c..7591a5f84c 100644 --- a/contrib/libs/zstd/lib/common/pool.c +++ b/contrib/libs/zstd/lib/common/pool.c @@ -1,76 +1,76 @@ -/* +/* * Copyright (c) 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 ======= */ + * 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_deps.h" /* size_t */ #include "debug.h" /* assert */ #include "zstd_internal.h" /* ZSTD_customMalloc, ZSTD_customFree */ -#include "pool.h" - -/* ====== Compiler specifics ====== */ -#if defined(_MSC_VER) -# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */ -#endif - - -#ifdef ZSTD_MULTITHREAD - -#include "threading.h" /* pthread adaptation */ - -/* A job is a function and an opaque argument */ -typedef struct POOL_job_s { - POOL_function function; - void *opaque; -} POOL_job; - -struct POOL_ctx_s { - ZSTD_customMem customMem; - /* Keep track of the threads */ +#include "pool.h" + +/* ====== Compiler specifics ====== */ +#if defined(_MSC_VER) +# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */ +#endif + + +#ifdef ZSTD_MULTITHREAD + +#include "threading.h" /* pthread adaptation */ + +/* A job is a function and an opaque argument */ +typedef struct POOL_job_s { + POOL_function function; + void *opaque; +} POOL_job; + +struct POOL_ctx_s { + ZSTD_customMem customMem; + /* Keep track of the threads */ ZSTD_pthread_t* threads; size_t threadCapacity; size_t threadLimit; - - /* The queue is a circular buffer */ - POOL_job *queue; - size_t queueHead; - size_t queueTail; - size_t queueSize; - - /* The number of threads working on jobs */ - size_t numThreadsBusy; - /* Indicates if the queue is empty */ - int queueEmpty; - - /* The mutex protects the queue */ - ZSTD_pthread_mutex_t queueMutex; - /* Condition variable for pushers to wait on when the queue is full */ - ZSTD_pthread_cond_t queuePushCond; - /* Condition variables for poppers to wait on when the queue is empty */ - ZSTD_pthread_cond_t queuePopCond; - /* Indicates if the queue is shutting down */ - int shutdown; -}; - -/* POOL_thread() : + + /* The queue is a circular buffer */ + POOL_job *queue; + size_t queueHead; + size_t queueTail; + size_t queueSize; + + /* The number of threads working on jobs */ + size_t numThreadsBusy; + /* Indicates if the queue is empty */ + int queueEmpty; + + /* The mutex protects the queue */ + ZSTD_pthread_mutex_t queueMutex; + /* Condition variable for pushers to wait on when the queue is full */ + ZSTD_pthread_cond_t queuePushCond; + /* Condition variables for poppers to wait on when the queue is empty */ + ZSTD_pthread_cond_t queuePopCond; + /* Indicates if the queue is shutting down */ + int shutdown; +}; + +/* POOL_thread() : * Work thread for the thread pool. * Waits for jobs and executes them. * @returns : NULL on failure else non-null. */ -static void* POOL_thread(void* opaque) { - POOL_ctx* const ctx = (POOL_ctx*)opaque; - if (!ctx) { return NULL; } - for (;;) { - /* Lock the mutex and wait for a non-empty queue or until shutdown */ - ZSTD_pthread_mutex_lock(&ctx->queueMutex); - +static void* POOL_thread(void* opaque) { + POOL_ctx* const ctx = (POOL_ctx*)opaque; + if (!ctx) { return NULL; } + for (;;) { + /* Lock the mutex and wait for a non-empty queue or until shutdown */ + ZSTD_pthread_mutex_lock(&ctx->queueMutex); + while ( ctx->queueEmpty || (ctx->numThreadsBusy >= ctx->threadLimit) ) { if (ctx->shutdown) { @@ -80,59 +80,59 @@ static void* POOL_thread(void* opaque) { ZSTD_pthread_mutex_unlock(&ctx->queueMutex); return opaque; } - ZSTD_pthread_cond_wait(&ctx->queuePopCond, &ctx->queueMutex); - } - /* Pop a job off the queue */ - { POOL_job const job = ctx->queue[ctx->queueHead]; - ctx->queueHead = (ctx->queueHead + 1) % ctx->queueSize; - ctx->numThreadsBusy++; + ZSTD_pthread_cond_wait(&ctx->queuePopCond, &ctx->queueMutex); + } + /* Pop a job off the queue */ + { POOL_job const job = ctx->queue[ctx->queueHead]; + ctx->queueHead = (ctx->queueHead + 1) % ctx->queueSize; + ctx->numThreadsBusy++; ctx->queueEmpty = (ctx->queueHead == ctx->queueTail); - /* Unlock the mutex, signal a pusher, and run the job */ + /* Unlock the mutex, signal a pusher, and run the job */ ZSTD_pthread_cond_signal(&ctx->queuePushCond); - ZSTD_pthread_mutex_unlock(&ctx->queueMutex); - - job.function(job.opaque); - - /* If the intended queue size was 0, signal after finishing job */ + ZSTD_pthread_mutex_unlock(&ctx->queueMutex); + + job.function(job.opaque); + + /* If the intended queue size was 0, signal after finishing job */ ZSTD_pthread_mutex_lock(&ctx->queueMutex); ctx->numThreadsBusy--; - if (ctx->queueSize == 1) { - ZSTD_pthread_cond_signal(&ctx->queuePushCond); + if (ctx->queueSize == 1) { + ZSTD_pthread_cond_signal(&ctx->queuePushCond); } ZSTD_pthread_mutex_unlock(&ctx->queueMutex); } - } /* for (;;) */ + } /* for (;;) */ assert(0); /* Unreachable */ -} - +} + /* ZSTD_createThreadPool() : public access point */ POOL_ctx* ZSTD_createThreadPool(size_t numThreads) { return POOL_create (numThreads, 0); } -POOL_ctx* POOL_create(size_t numThreads, size_t queueSize) { - return POOL_create_advanced(numThreads, queueSize, ZSTD_defaultCMem); -} - +POOL_ctx* POOL_create(size_t numThreads, size_t queueSize) { + return POOL_create_advanced(numThreads, queueSize, ZSTD_defaultCMem); +} + POOL_ctx* POOL_create_advanced(size_t numThreads, size_t queueSize, ZSTD_customMem customMem) { - POOL_ctx* ctx; + POOL_ctx* ctx; /* Check parameters */ - if (!numThreads) { return NULL; } - /* Allocate the context and zero initialize */ + if (!numThreads) { return NULL; } + /* Allocate the context and zero initialize */ ctx = (POOL_ctx*)ZSTD_customCalloc(sizeof(POOL_ctx), customMem); - if (!ctx) { return NULL; } - /* Initialize the job queue. + if (!ctx) { return NULL; } + /* Initialize the job queue. * It needs one extra space since one space is wasted to differentiate * empty and full queues. - */ - ctx->queueSize = queueSize + 1; + */ + ctx->queueSize = queueSize + 1; ctx->queue = (POOL_job*)ZSTD_customMalloc(ctx->queueSize * sizeof(POOL_job), customMem); - ctx->queueHead = 0; - ctx->queueTail = 0; - ctx->numThreadsBusy = 0; - ctx->queueEmpty = 1; + ctx->queueHead = 0; + ctx->queueTail = 0; + ctx->numThreadsBusy = 0; + ctx->queueEmpty = 1; { int error = 0; error |= ZSTD_pthread_mutex_init(&ctx->queueMutex, NULL); @@ -140,67 +140,67 @@ POOL_ctx* POOL_create_advanced(size_t numThreads, size_t queueSize, error |= ZSTD_pthread_cond_init(&ctx->queuePopCond, NULL); if (error) { POOL_free(ctx); return NULL; } } - ctx->shutdown = 0; - /* Allocate space for the thread handles */ + ctx->shutdown = 0; + /* Allocate space for the thread handles */ ctx->threads = (ZSTD_pthread_t*)ZSTD_customMalloc(numThreads * sizeof(ZSTD_pthread_t), customMem); ctx->threadCapacity = 0; - ctx->customMem = customMem; - /* Check for errors */ - if (!ctx->threads || !ctx->queue) { POOL_free(ctx); return NULL; } - /* Initialize the threads */ - { size_t i; - for (i = 0; i < numThreads; ++i) { - if (ZSTD_pthread_create(&ctx->threads[i], NULL, &POOL_thread, ctx)) { + ctx->customMem = customMem; + /* Check for errors */ + if (!ctx->threads || !ctx->queue) { POOL_free(ctx); return NULL; } + /* Initialize the threads */ + { size_t i; + for (i = 0; i < numThreads; ++i) { + if (ZSTD_pthread_create(&ctx->threads[i], NULL, &POOL_thread, ctx)) { ctx->threadCapacity = i; - POOL_free(ctx); - return NULL; - } } + POOL_free(ctx); + return NULL; + } } ctx->threadCapacity = numThreads; ctx->threadLimit = numThreads; - } - return ctx; -} - -/*! POOL_join() : - Shutdown the queue, wake any sleeping threads, and join all of the threads. -*/ -static void POOL_join(POOL_ctx* ctx) { - /* Shut down the queue */ - ZSTD_pthread_mutex_lock(&ctx->queueMutex); - ctx->shutdown = 1; - ZSTD_pthread_mutex_unlock(&ctx->queueMutex); - /* Wake up sleeping threads */ - ZSTD_pthread_cond_broadcast(&ctx->queuePushCond); - ZSTD_pthread_cond_broadcast(&ctx->queuePopCond); - /* Join all of the threads */ - { size_t i; + } + return ctx; +} + +/*! POOL_join() : + Shutdown the queue, wake any sleeping threads, and join all of the threads. +*/ +static void POOL_join(POOL_ctx* ctx) { + /* Shut down the queue */ + ZSTD_pthread_mutex_lock(&ctx->queueMutex); + ctx->shutdown = 1; + ZSTD_pthread_mutex_unlock(&ctx->queueMutex); + /* Wake up sleeping threads */ + ZSTD_pthread_cond_broadcast(&ctx->queuePushCond); + ZSTD_pthread_cond_broadcast(&ctx->queuePopCond); + /* Join all of the threads */ + { size_t i; for (i = 0; i < ctx->threadCapacity; ++i) { ZSTD_pthread_join(ctx->threads[i], NULL); /* note : could fail */ - } } -} - -void POOL_free(POOL_ctx *ctx) { - if (!ctx) { return; } - POOL_join(ctx); - ZSTD_pthread_mutex_destroy(&ctx->queueMutex); - ZSTD_pthread_cond_destroy(&ctx->queuePushCond); - ZSTD_pthread_cond_destroy(&ctx->queuePopCond); + } } +} + +void POOL_free(POOL_ctx *ctx) { + if (!ctx) { return; } + POOL_join(ctx); + ZSTD_pthread_mutex_destroy(&ctx->queueMutex); + ZSTD_pthread_cond_destroy(&ctx->queuePushCond); + ZSTD_pthread_cond_destroy(&ctx->queuePopCond); ZSTD_customFree(ctx->queue, ctx->customMem); ZSTD_customFree(ctx->threads, ctx->customMem); ZSTD_customFree(ctx, ctx->customMem); -} - +} + void ZSTD_freeThreadPool (ZSTD_threadPool* pool) { POOL_free (pool); } size_t POOL_sizeof(const POOL_ctx* ctx) { - if (ctx==NULL) return 0; /* supports sizeof NULL */ - return sizeof(*ctx) - + ctx->queueSize * sizeof(POOL_job) + if (ctx==NULL) return 0; /* supports sizeof NULL */ + return sizeof(*ctx) + + ctx->queueSize * sizeof(POOL_job) + ctx->threadCapacity * sizeof(ZSTD_pthread_t); -} - +} + /* @return : 0 on success, 1 on error */ static int POOL_resize_internal(POOL_ctx* ctx, size_t numThreads) @@ -243,113 +243,113 @@ int POOL_resize(POOL_ctx* ctx, size_t numThreads) return result; } -/** - * Returns 1 if the queue is full and 0 otherwise. - * +/** + * Returns 1 if the queue is full and 0 otherwise. + * * When queueSize is 1 (pool was created with an intended queueSize of 0), * then a queue is empty if there is a thread free _and_ no job is waiting. - */ -static int isQueueFull(POOL_ctx const* ctx) { - if (ctx->queueSize > 1) { - return ctx->queueHead == ((ctx->queueTail + 1) % ctx->queueSize); - } else { + */ +static int isQueueFull(POOL_ctx const* ctx) { + if (ctx->queueSize > 1) { + return ctx->queueHead == ((ctx->queueTail + 1) % ctx->queueSize); + } else { return (ctx->numThreadsBusy == ctx->threadLimit) || - !ctx->queueEmpty; - } -} - - + !ctx->queueEmpty; + } +} + + static void POOL_add_internal(POOL_ctx* ctx, POOL_function function, void *opaque) -{ - POOL_job const job = {function, opaque}; - assert(ctx != NULL); - if (ctx->shutdown) return; - - ctx->queueEmpty = 0; - ctx->queue[ctx->queueTail] = job; - ctx->queueTail = (ctx->queueTail + 1) % ctx->queueSize; - ZSTD_pthread_cond_signal(&ctx->queuePopCond); -} - -void POOL_add(POOL_ctx* ctx, POOL_function function, void* opaque) -{ - assert(ctx != NULL); - ZSTD_pthread_mutex_lock(&ctx->queueMutex); - /* Wait until there is space in the queue for the new job */ - while (isQueueFull(ctx) && (!ctx->shutdown)) { - ZSTD_pthread_cond_wait(&ctx->queuePushCond, &ctx->queueMutex); - } - POOL_add_internal(ctx, function, opaque); - ZSTD_pthread_mutex_unlock(&ctx->queueMutex); -} - - -int POOL_tryAdd(POOL_ctx* ctx, POOL_function function, void* opaque) -{ - assert(ctx != NULL); - ZSTD_pthread_mutex_lock(&ctx->queueMutex); - if (isQueueFull(ctx)) { - ZSTD_pthread_mutex_unlock(&ctx->queueMutex); - return 0; - } - POOL_add_internal(ctx, function, opaque); - ZSTD_pthread_mutex_unlock(&ctx->queueMutex); - return 1; -} - - -#else /* ZSTD_MULTITHREAD not defined */ - -/* ========================== */ -/* No multi-threading support */ -/* ========================== */ - - -/* We don't need any data, but if it is empty, malloc() might return NULL. */ -struct POOL_ctx_s { - int dummy; -}; +{ + POOL_job const job = {function, opaque}; + assert(ctx != NULL); + if (ctx->shutdown) return; + + ctx->queueEmpty = 0; + ctx->queue[ctx->queueTail] = job; + ctx->queueTail = (ctx->queueTail + 1) % ctx->queueSize; + ZSTD_pthread_cond_signal(&ctx->queuePopCond); +} + +void POOL_add(POOL_ctx* ctx, POOL_function function, void* opaque) +{ + assert(ctx != NULL); + ZSTD_pthread_mutex_lock(&ctx->queueMutex); + /* Wait until there is space in the queue for the new job */ + while (isQueueFull(ctx) && (!ctx->shutdown)) { + ZSTD_pthread_cond_wait(&ctx->queuePushCond, &ctx->queueMutex); + } + POOL_add_internal(ctx, function, opaque); + ZSTD_pthread_mutex_unlock(&ctx->queueMutex); +} + + +int POOL_tryAdd(POOL_ctx* ctx, POOL_function function, void* opaque) +{ + assert(ctx != NULL); + ZSTD_pthread_mutex_lock(&ctx->queueMutex); + if (isQueueFull(ctx)) { + ZSTD_pthread_mutex_unlock(&ctx->queueMutex); + return 0; + } + POOL_add_internal(ctx, function, opaque); + ZSTD_pthread_mutex_unlock(&ctx->queueMutex); + return 1; +} + + +#else /* ZSTD_MULTITHREAD not defined */ + +/* ========================== */ +/* No multi-threading support */ +/* ========================== */ + + +/* We don't need any data, but if it is empty, malloc() might return NULL. */ +struct POOL_ctx_s { + int dummy; +}; static POOL_ctx g_poolCtx; - -POOL_ctx* POOL_create(size_t numThreads, size_t queueSize) { - return POOL_create_advanced(numThreads, queueSize, ZSTD_defaultCMem); -} - + +POOL_ctx* POOL_create(size_t numThreads, size_t queueSize) { + return POOL_create_advanced(numThreads, queueSize, ZSTD_defaultCMem); +} + POOL_ctx* POOL_create_advanced(size_t numThreads, size_t queueSize, ZSTD_customMem customMem) { - (void)numThreads; - (void)queueSize; - (void)customMem; + (void)numThreads; + (void)queueSize; + (void)customMem; return &g_poolCtx; -} - -void POOL_free(POOL_ctx* ctx) { +} + +void POOL_free(POOL_ctx* ctx) { assert(!ctx || ctx == &g_poolCtx); - (void)ctx; -} - + (void)ctx; +} + int POOL_resize(POOL_ctx* ctx, size_t numThreads) { (void)ctx; (void)numThreads; return 0; } -void POOL_add(POOL_ctx* ctx, POOL_function function, void* opaque) { - (void)ctx; - function(opaque); -} - -int POOL_tryAdd(POOL_ctx* ctx, POOL_function function, void* opaque) { - (void)ctx; - function(opaque); - return 1; -} - +void POOL_add(POOL_ctx* ctx, POOL_function function, void* opaque) { + (void)ctx; + function(opaque); +} + +int POOL_tryAdd(POOL_ctx* ctx, POOL_function function, void* opaque) { + (void)ctx; + function(opaque); + return 1; +} + size_t POOL_sizeof(const POOL_ctx* ctx) { - if (ctx==NULL) return 0; /* supports sizeof NULL */ + if (ctx==NULL) return 0; /* supports sizeof NULL */ assert(ctx == &g_poolCtx); - return sizeof(*ctx); -} - -#endif /* ZSTD_MULTITHREAD */ + return sizeof(*ctx); +} + +#endif /* ZSTD_MULTITHREAD */ diff --git a/contrib/libs/zstd/lib/common/pool.h b/contrib/libs/zstd/lib/common/pool.h index 0ebde1805d..67feb6da6d 100644 --- a/contrib/libs/zstd/lib/common/pool.h +++ b/contrib/libs/zstd/lib/common/pool.h @@ -1,43 +1,43 @@ -/* +/* * Copyright (c) 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 POOL_H -#define POOL_H - -#if defined (__cplusplus) -extern "C" { -#endif - - + * 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 POOL_H +#define POOL_H + +#if defined (__cplusplus) +extern "C" { +#endif + + #include "zstd_deps.h" -#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_customMem */ +#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_customMem */ #include "../zstd.h" - -typedef struct POOL_ctx_s POOL_ctx; - -/*! POOL_create() : - * Create a thread pool with at most `numThreads` threads. - * `numThreads` must be at least 1. - * The maximum number of queued jobs before blocking is `queueSize`. - * @return : POOL_ctx pointer on success, else NULL. -*/ -POOL_ctx* POOL_create(size_t numThreads, size_t queueSize); - + +typedef struct POOL_ctx_s POOL_ctx; + +/*! POOL_create() : + * Create a thread pool with at most `numThreads` threads. + * `numThreads` must be at least 1. + * The maximum number of queued jobs before blocking is `queueSize`. + * @return : POOL_ctx pointer on success, else NULL. +*/ +POOL_ctx* POOL_create(size_t numThreads, size_t queueSize); + POOL_ctx* POOL_create_advanced(size_t numThreads, size_t queueSize, ZSTD_customMem customMem); - -/*! POOL_free() : + +/*! POOL_free() : * Free a thread pool returned by POOL_create(). */ -void POOL_free(POOL_ctx* ctx); - +void POOL_free(POOL_ctx* ctx); + /*! POOL_resize() : * Expands or shrinks pool's number of threads. * This is more efficient than releasing + creating a new context, @@ -49,36 +49,36 @@ void POOL_free(POOL_ctx* ctx); */ int POOL_resize(POOL_ctx* ctx, size_t numThreads); -/*! POOL_sizeof() : +/*! POOL_sizeof() : * @return threadpool memory usage * note : compatible with NULL (returns 0 in this case) */ size_t POOL_sizeof(const POOL_ctx* ctx); - -/*! POOL_function : + +/*! POOL_function : * The function type that can be added to a thread pool. */ -typedef void (*POOL_function)(void*); - -/*! POOL_add() : +typedef void (*POOL_function)(void*); + +/*! POOL_add() : * Add the job `function(opaque)` to the thread pool. `ctx` must be valid. * Possibly blocks until there is room in the queue. * Note : The function may be executed asynchronously, * therefore, `opaque` must live until function has been completed. */ -void POOL_add(POOL_ctx* ctx, POOL_function function, void* opaque); - - -/*! POOL_tryAdd() : +void POOL_add(POOL_ctx* ctx, POOL_function function, void* opaque); + + +/*! POOL_tryAdd() : * Add the job `function(opaque)` to thread pool _if_ a queue slot is available. * Returns immediately even if not (does not block). * @return : 1 if successful, 0 if not. */ -int POOL_tryAdd(POOL_ctx* ctx, POOL_function function, void* opaque); - - -#if defined (__cplusplus) -} -#endif - -#endif +int POOL_tryAdd(POOL_ctx* ctx, POOL_function function, void* opaque); + + +#if defined (__cplusplus) +} +#endif + +#endif diff --git a/contrib/libs/zstd/lib/common/threading.c b/contrib/libs/zstd/lib/common/threading.c index 92cf57c195..c0c2adb937 100644 --- a/contrib/libs/zstd/lib/common/threading.c +++ b/contrib/libs/zstd/lib/common/threading.c @@ -1,80 +1,80 @@ -/** - * Copyright (c) 2016 Tino Reichardt - * All rights reserved. - * +/** + * Copyright (c) 2016 Tino Reichardt + * All rights reserved. + * * You can contact the author at: * - zstdmt source repository: https://github.com/mcmilk/zstdmt * - * 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). + * 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. - */ - -/** - * This file will hold wrapper for systems, which do not support pthreads - */ - + */ + +/** + * This file will hold wrapper for systems, which do not support pthreads + */ + #include "threading.h" /* create fake symbol to avoid empty translation unit warning */ int g_ZSTD_threading_useless_symbol; - -#if defined(ZSTD_MULTITHREAD) && defined(_WIN32) - -/** - * Windows minimalist Pthread Wrapper, based on : - * http://www.cse.wustl.edu/~schmidt/win32-cv-1.html - */ - - -/* === Dependencies === */ -#include <process.h> -#include <errno.h> - - -/* === Implementation === */ - -static unsigned __stdcall worker(void *arg) -{ - ZSTD_pthread_t* const thread = (ZSTD_pthread_t*) arg; - thread->arg = thread->start_routine(thread->arg); - return 0; -} - -int ZSTD_pthread_create(ZSTD_pthread_t* thread, const void* unused, - void* (*start_routine) (void*), void* arg) -{ - (void)unused; - thread->arg = arg; - thread->start_routine = start_routine; - thread->handle = (HANDLE) _beginthreadex(NULL, 0, worker, thread, 0, NULL); - - if (!thread->handle) - return errno; - else - return 0; -} - -int ZSTD_pthread_join(ZSTD_pthread_t thread, void **value_ptr) -{ - DWORD result; - - if (!thread.handle) return 0; - - result = WaitForSingleObject(thread.handle, INFINITE); - switch (result) { - case WAIT_OBJECT_0: - if (value_ptr) *value_ptr = thread.arg; - return 0; - case WAIT_ABANDONED: - return EINVAL; - default: - return GetLastError(); - } -} - -#endif /* ZSTD_MULTITHREAD */ + +#if defined(ZSTD_MULTITHREAD) && defined(_WIN32) + +/** + * Windows minimalist Pthread Wrapper, based on : + * http://www.cse.wustl.edu/~schmidt/win32-cv-1.html + */ + + +/* === Dependencies === */ +#include <process.h> +#include <errno.h> + + +/* === Implementation === */ + +static unsigned __stdcall worker(void *arg) +{ + ZSTD_pthread_t* const thread = (ZSTD_pthread_t*) arg; + thread->arg = thread->start_routine(thread->arg); + return 0; +} + +int ZSTD_pthread_create(ZSTD_pthread_t* thread, const void* unused, + void* (*start_routine) (void*), void* arg) +{ + (void)unused; + thread->arg = arg; + thread->start_routine = start_routine; + thread->handle = (HANDLE) _beginthreadex(NULL, 0, worker, thread, 0, NULL); + + if (!thread->handle) + return errno; + else + return 0; +} + +int ZSTD_pthread_join(ZSTD_pthread_t thread, void **value_ptr) +{ + DWORD result; + + if (!thread.handle) return 0; + + result = WaitForSingleObject(thread.handle, INFINITE); + switch (result) { + case WAIT_OBJECT_0: + if (value_ptr) *value_ptr = thread.arg; + return 0; + case WAIT_ABANDONED: + return EINVAL; + default: + return GetLastError(); + } +} + +#endif /* ZSTD_MULTITHREAD */ #if defined(ZSTD_MULTITHREAD) && DEBUGLEVEL >= 1 && !defined(_WIN32) diff --git a/contrib/libs/zstd/lib/common/threading.h b/contrib/libs/zstd/lib/common/threading.h index fd0060d5aa..c5e303eedc 100644 --- a/contrib/libs/zstd/lib/common/threading.h +++ b/contrib/libs/zstd/lib/common/threading.h @@ -1,106 +1,106 @@ -/** - * Copyright (c) 2016 Tino Reichardt - * All rights reserved. - * +/** + * Copyright (c) 2016 Tino Reichardt + * All rights reserved. + * * You can contact the author at: * - zstdmt source repository: https://github.com/mcmilk/zstdmt * - * 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). + * 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 THREADING_H_938743 -#define THREADING_H_938743 - + */ + +#ifndef THREADING_H_938743 +#define THREADING_H_938743 + #include "debug.h" -#if defined (__cplusplus) -extern "C" { -#endif - -#if defined(ZSTD_MULTITHREAD) && defined(_WIN32) - -/** - * Windows minimalist Pthread Wrapper, based on : - * http://www.cse.wustl.edu/~schmidt/win32-cv-1.html - */ -#ifdef WINVER -# undef WINVER -#endif -#define WINVER 0x0600 - -#ifdef _WIN32_WINNT -# undef _WIN32_WINNT -#endif -#define _WIN32_WINNT 0x0600 - -#ifndef WIN32_LEAN_AND_MEAN -# define WIN32_LEAN_AND_MEAN -#endif - -#undef ERROR /* reported already defined on VS 2015 (Rich Geldreich) */ -#include <windows.h> -#undef ERROR -#define ERROR(name) ZSTD_ERROR(name) - - -/* mutex */ -#define ZSTD_pthread_mutex_t CRITICAL_SECTION -#define ZSTD_pthread_mutex_init(a, b) ((void)(b), InitializeCriticalSection((a)), 0) -#define ZSTD_pthread_mutex_destroy(a) DeleteCriticalSection((a)) -#define ZSTD_pthread_mutex_lock(a) EnterCriticalSection((a)) -#define ZSTD_pthread_mutex_unlock(a) LeaveCriticalSection((a)) - -/* condition variable */ -#define ZSTD_pthread_cond_t CONDITION_VARIABLE -#define ZSTD_pthread_cond_init(a, b) ((void)(b), InitializeConditionVariable((a)), 0) -#define ZSTD_pthread_cond_destroy(a) ((void)(a)) -#define ZSTD_pthread_cond_wait(a, b) SleepConditionVariableCS((a), (b), INFINITE) -#define ZSTD_pthread_cond_signal(a) WakeConditionVariable((a)) -#define ZSTD_pthread_cond_broadcast(a) WakeAllConditionVariable((a)) - -/* ZSTD_pthread_create() and ZSTD_pthread_join() */ -typedef struct { - HANDLE handle; - void* (*start_routine)(void*); - void* arg; -} ZSTD_pthread_t; - -int ZSTD_pthread_create(ZSTD_pthread_t* thread, const void* unused, - void* (*start_routine) (void*), void* arg); - -int ZSTD_pthread_join(ZSTD_pthread_t thread, void** value_ptr); - -/** - * add here more wrappers as required - */ - - +#if defined (__cplusplus) +extern "C" { +#endif + +#if defined(ZSTD_MULTITHREAD) && defined(_WIN32) + +/** + * Windows minimalist Pthread Wrapper, based on : + * http://www.cse.wustl.edu/~schmidt/win32-cv-1.html + */ +#ifdef WINVER +# undef WINVER +#endif +#define WINVER 0x0600 + +#ifdef _WIN32_WINNT +# undef _WIN32_WINNT +#endif +#define _WIN32_WINNT 0x0600 + +#ifndef WIN32_LEAN_AND_MEAN +# define WIN32_LEAN_AND_MEAN +#endif + +#undef ERROR /* reported already defined on VS 2015 (Rich Geldreich) */ +#include <windows.h> +#undef ERROR +#define ERROR(name) ZSTD_ERROR(name) + + +/* mutex */ +#define ZSTD_pthread_mutex_t CRITICAL_SECTION +#define ZSTD_pthread_mutex_init(a, b) ((void)(b), InitializeCriticalSection((a)), 0) +#define ZSTD_pthread_mutex_destroy(a) DeleteCriticalSection((a)) +#define ZSTD_pthread_mutex_lock(a) EnterCriticalSection((a)) +#define ZSTD_pthread_mutex_unlock(a) LeaveCriticalSection((a)) + +/* condition variable */ +#define ZSTD_pthread_cond_t CONDITION_VARIABLE +#define ZSTD_pthread_cond_init(a, b) ((void)(b), InitializeConditionVariable((a)), 0) +#define ZSTD_pthread_cond_destroy(a) ((void)(a)) +#define ZSTD_pthread_cond_wait(a, b) SleepConditionVariableCS((a), (b), INFINITE) +#define ZSTD_pthread_cond_signal(a) WakeConditionVariable((a)) +#define ZSTD_pthread_cond_broadcast(a) WakeAllConditionVariable((a)) + +/* ZSTD_pthread_create() and ZSTD_pthread_join() */ +typedef struct { + HANDLE handle; + void* (*start_routine)(void*); + void* arg; +} ZSTD_pthread_t; + +int ZSTD_pthread_create(ZSTD_pthread_t* thread, const void* unused, + void* (*start_routine) (void*), void* arg); + +int ZSTD_pthread_join(ZSTD_pthread_t thread, void** value_ptr); + +/** + * add here more wrappers as required + */ + + #elif defined(ZSTD_MULTITHREAD) /* posix assumed ; need a better detection method */ -/* === POSIX Systems === */ -# include <pthread.h> - +/* === POSIX Systems === */ +# include <pthread.h> + #if DEBUGLEVEL < 1 -#define ZSTD_pthread_mutex_t pthread_mutex_t -#define ZSTD_pthread_mutex_init(a, b) pthread_mutex_init((a), (b)) -#define ZSTD_pthread_mutex_destroy(a) pthread_mutex_destroy((a)) -#define ZSTD_pthread_mutex_lock(a) pthread_mutex_lock((a)) -#define ZSTD_pthread_mutex_unlock(a) pthread_mutex_unlock((a)) - -#define ZSTD_pthread_cond_t pthread_cond_t -#define ZSTD_pthread_cond_init(a, b) pthread_cond_init((a), (b)) -#define ZSTD_pthread_cond_destroy(a) pthread_cond_destroy((a)) -#define ZSTD_pthread_cond_wait(a, b) pthread_cond_wait((a), (b)) -#define ZSTD_pthread_cond_signal(a) pthread_cond_signal((a)) -#define ZSTD_pthread_cond_broadcast(a) pthread_cond_broadcast((a)) - -#define ZSTD_pthread_t pthread_t -#define ZSTD_pthread_create(a, b, c, d) pthread_create((a), (b), (c), (d)) -#define ZSTD_pthread_join(a, b) pthread_join((a),(b)) - +#define ZSTD_pthread_mutex_t pthread_mutex_t +#define ZSTD_pthread_mutex_init(a, b) pthread_mutex_init((a), (b)) +#define ZSTD_pthread_mutex_destroy(a) pthread_mutex_destroy((a)) +#define ZSTD_pthread_mutex_lock(a) pthread_mutex_lock((a)) +#define ZSTD_pthread_mutex_unlock(a) pthread_mutex_unlock((a)) + +#define ZSTD_pthread_cond_t pthread_cond_t +#define ZSTD_pthread_cond_init(a, b) pthread_cond_init((a), (b)) +#define ZSTD_pthread_cond_destroy(a) pthread_cond_destroy((a)) +#define ZSTD_pthread_cond_wait(a, b) pthread_cond_wait((a), (b)) +#define ZSTD_pthread_cond_signal(a) pthread_cond_signal((a)) +#define ZSTD_pthread_cond_broadcast(a) pthread_cond_broadcast((a)) + +#define ZSTD_pthread_t pthread_t +#define ZSTD_pthread_create(a, b, c, d) pthread_create((a), (b), (c), (d)) +#define ZSTD_pthread_join(a, b) pthread_join((a),(b)) + #else /* DEBUGLEVEL >= 1 */ /* Debug implementation of threading. @@ -128,28 +128,28 @@ int ZSTD_pthread_cond_destroy(ZSTD_pthread_cond_t* cond); #endif -#else /* ZSTD_MULTITHREAD not defined */ -/* No multithreading support */ - -typedef int ZSTD_pthread_mutex_t; -#define ZSTD_pthread_mutex_init(a, b) ((void)(a), (void)(b), 0) -#define ZSTD_pthread_mutex_destroy(a) ((void)(a)) -#define ZSTD_pthread_mutex_lock(a) ((void)(a)) -#define ZSTD_pthread_mutex_unlock(a) ((void)(a)) - -typedef int ZSTD_pthread_cond_t; -#define ZSTD_pthread_cond_init(a, b) ((void)(a), (void)(b), 0) -#define ZSTD_pthread_cond_destroy(a) ((void)(a)) -#define ZSTD_pthread_cond_wait(a, b) ((void)(a), (void)(b)) -#define ZSTD_pthread_cond_signal(a) ((void)(a)) -#define ZSTD_pthread_cond_broadcast(a) ((void)(a)) - -/* do not use ZSTD_pthread_t */ - -#endif /* ZSTD_MULTITHREAD */ - -#if defined (__cplusplus) -} -#endif - -#endif /* THREADING_H_938743 */ +#else /* ZSTD_MULTITHREAD not defined */ +/* No multithreading support */ + +typedef int ZSTD_pthread_mutex_t; +#define ZSTD_pthread_mutex_init(a, b) ((void)(a), (void)(b), 0) +#define ZSTD_pthread_mutex_destroy(a) ((void)(a)) +#define ZSTD_pthread_mutex_lock(a) ((void)(a)) +#define ZSTD_pthread_mutex_unlock(a) ((void)(a)) + +typedef int ZSTD_pthread_cond_t; +#define ZSTD_pthread_cond_init(a, b) ((void)(a), (void)(b), 0) +#define ZSTD_pthread_cond_destroy(a) ((void)(a)) +#define ZSTD_pthread_cond_wait(a, b) ((void)(a), (void)(b)) +#define ZSTD_pthread_cond_signal(a) ((void)(a)) +#define ZSTD_pthread_cond_broadcast(a) ((void)(a)) + +/* do not use ZSTD_pthread_t */ + +#endif /* ZSTD_MULTITHREAD */ + +#if defined (__cplusplus) +} +#endif + +#endif /* THREADING_H_938743 */ diff --git a/contrib/libs/zstd/lib/common/zstd_common.c b/contrib/libs/zstd/lib/common/zstd_common.c index 3d7e35b309..ea4e288daa 100644 --- a/contrib/libs/zstd/lib/common/zstd_common.c +++ b/contrib/libs/zstd/lib/common/zstd_common.c @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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. */ @@ -16,17 +16,17 @@ #define ZSTD_DEPS_NEED_MALLOC #include "zstd_deps.h" /* ZSTD_malloc, ZSTD_calloc, ZSTD_free, ZSTD_memset */ #include "error_private.h" -#include "zstd_internal.h" +#include "zstd_internal.h" /*-**************************************** * Version ******************************************/ -unsigned ZSTD_versionNumber(void) { return ZSTD_VERSION_NUMBER; } - -const char* ZSTD_versionString(void) { return ZSTD_VERSION_STRING; } +unsigned ZSTD_versionNumber(void) { return ZSTD_VERSION_NUMBER; } +const char* ZSTD_versionString(void) { return ZSTD_VERSION_STRING; } + /*-**************************************** * ZSTD Error Management ******************************************/ @@ -37,16 +37,16 @@ const char* ZSTD_versionString(void) { return ZSTD_VERSION_STRING; } unsigned ZSTD_isError(size_t code) { return ERR_isError(code); } /*! ZSTD_getErrorName() : - * provides error code string from function result (useful for debugging) */ + * provides error code string from function result (useful for debugging) */ const char* ZSTD_getErrorName(size_t code) { return ERR_getErrorName(code); } /*! ZSTD_getError() : - * convert a `size_t` function result into a proper ZSTD_errorCode enum */ + * convert a `size_t` function result into a proper ZSTD_errorCode enum */ ZSTD_ErrorCode ZSTD_getErrorCode(size_t code) { return ERR_getErrorCode(code); } /*! ZSTD_getErrorString() : - * provides error code string from enum */ -const char* ZSTD_getErrorString(ZSTD_ErrorCode code) { return ERR_getErrorString(code); } + * provides error code string from enum */ +const char* ZSTD_getErrorString(ZSTD_ErrorCode code) { return ERR_getErrorString(code); } @@ -55,29 +55,29 @@ const char* ZSTD_getErrorString(ZSTD_ErrorCode code) { return ERR_getErrorString ****************************************************************/ void* ZSTD_customMalloc(size_t size, ZSTD_customMem customMem) { - if (customMem.customAlloc) - return customMem.customAlloc(customMem.opaque, size); + if (customMem.customAlloc) + return customMem.customAlloc(customMem.opaque, size); return ZSTD_malloc(size); } void* ZSTD_customCalloc(size_t size, ZSTD_customMem customMem) { - if (customMem.customAlloc) { - /* calloc implemented as malloc+memset; - * not as efficient as calloc, but next best guess for custom malloc */ - void* const ptr = customMem.customAlloc(customMem.opaque, size); + if (customMem.customAlloc) { + /* calloc implemented as malloc+memset; + * not as efficient as calloc, but next best guess for custom malloc */ + void* const ptr = customMem.customAlloc(customMem.opaque, size); ZSTD_memset(ptr, 0, size); - return ptr; - } + return ptr; + } return ZSTD_calloc(1, size); } void ZSTD_customFree(void* ptr, ZSTD_customMem customMem) { - if (ptr!=NULL) { - if (customMem.customFree) - customMem.customFree(customMem.opaque, ptr); - else + if (ptr!=NULL) { + if (customMem.customFree) + customMem.customFree(customMem.opaque, ptr); + else ZSTD_free(ptr); - } + } } diff --git a/contrib/libs/zstd/lib/common/zstd_internal.h b/contrib/libs/zstd/lib/common/zstd_internal.h index 1dee37cdbe..e149b40943 100644 --- a/contrib/libs/zstd/lib/common/zstd_internal.h +++ b/contrib/libs/zstd/lib/common/zstd_internal.h @@ -1,38 +1,38 @@ -/* +/* * Copyright (c) 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. + * 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_CCOMMON_H_MODULE #define ZSTD_CCOMMON_H_MODULE -/* this module contains definitions which must be identical - * across compression, decompression and dictBuilder. - * It also contains a few functions useful to at least 2 of them - * and which benefit from being inlined */ +/* this module contains definitions which must be identical + * across compression, decompression and dictBuilder. + * It also contains a few functions useful to at least 2 of them + * and which benefit from being inlined */ /*-************************************* * Dependencies ***************************************/ -#include "compiler.h" +#include "compiler.h" #include "cpu.h" #include "mem.h" #include "debug.h" /* assert, DEBUGLOG, RAWLOG, g_debuglevel */ #include "error_private.h" #define ZSTD_STATIC_LINKING_ONLY #include "../zstd.h" -#define FSE_STATIC_LINKING_ONLY -#include "fse.h" -#define HUF_STATIC_LINKING_ONLY -#include "huf.h" -#ifndef XXH_STATIC_LINKING_ONLY -# define XXH_STATIC_LINKING_ONLY /* XXH64_state_t */ -#endif +#define FSE_STATIC_LINKING_ONLY +#include "fse.h" +#define HUF_STATIC_LINKING_ONLY +#include "huf.h" +#ifndef XXH_STATIC_LINKING_ONLY +# define XXH_STATIC_LINKING_ONLY /* XXH64_state_t */ +#endif #include <contrib/libs/xxhash/xxhash.h> /* XXH_reset, update, digest */ #ifndef ZSTD_NO_TRACE # include "zstd_trace.h" @@ -40,22 +40,22 @@ # define ZSTD_TRACE 0 #endif -#if defined (__cplusplus) -extern "C" { -#endif - +#if defined (__cplusplus) +extern "C" { +#endif + /* ---- static assert (debug) --- */ #define ZSTD_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c) #define ZSTD_isError ERR_isError /* for inlining */ #define FSE_isError ERR_isError #define HUF_isError ERR_isError - - -/*-************************************* + + +/*-************************************* * shared macros ***************************************/ -#undef MIN -#undef MAX +#undef MIN +#undef MAX #define MIN(a,b) ((a)<(b) ? (a) : (b)) #define MAX(a,b) ((a)>(b) ? (a) : (b)) #define BOUNDED(min,val,max) (MAX(min,MIN(val,max))) @@ -85,7 +85,7 @@ static UNUSED_ATTR const size_t ZSTD_fcs_fieldSize[4] = { 0, 2, 4, 8 }; static UNUSED_ATTR const size_t ZSTD_did_fieldSize[4] = { 0, 1, 2, 4 }; #define ZSTD_FRAMEIDSIZE 4 /* magic number size */ - + #define ZSTD_BLOCKHEADERSIZE 3 /* C standard doesn't allow `static const` variable to be init using another `static const` variable */ static UNUSED_ATTR const size_t ZSTD_blockHeaderSize = ZSTD_BLOCKHEADERSIZE; typedef enum { bt_raw, bt_rle, bt_compressed, bt_reserved } blockType_e; @@ -104,15 +104,15 @@ typedef enum { set_basic, set_rle, set_compressed, set_repeat } symbolEncodingTy #define Litbits 8 #define MaxLit ((1<<Litbits) - 1) -#define MaxML 52 -#define MaxLL 35 -#define DefaultMaxOff 28 -#define MaxOff 31 +#define MaxML 52 +#define MaxLL 35 +#define DefaultMaxOff 28 +#define MaxOff 31 #define MaxSeq MAX(MaxLL, MaxML) /* Assumption : MaxOff < MaxLL,MaxML */ #define MLFSELog 9 #define LLFSELog 9 #define OffFSELog 8 -#define MaxFSELog MAX(MAX(MLFSELog, LLFSELog), OffFSELog) +#define MaxFSELog MAX(MAX(MLFSELog, LLFSELog), OffFSELog) #define ZSTD_MAX_HUF_HEADER_SIZE 128 /* header + <= 127 byte tree description */ /* Each table cannot take more than #symbols * FSELog bits */ @@ -281,7 +281,7 @@ typedef enum { /*-******************************************* -* Private declarations +* Private declarations *********************************************/ typedef struct seqDef_s { U32 offBase; /* offBase == Offset + ZSTD_REP_NUM, or repcode 1,2,3 */ @@ -351,8 +351,8 @@ typedef struct { unsigned long long decompressedBound; } ZSTD_frameSizeInfo; /* decompress & legacy */ -const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx); /* compress & dictBuilder */ -void ZSTD_seqToCodes(const seqStore_t* seqStorePtr); /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */ +const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx); /* compress & dictBuilder */ +void ZSTD_seqToCodes(const seqStore_t* seqStorePtr); /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */ /* custom memory allocation functions */ void* ZSTD_customMalloc(size_t size, ZSTD_customMem customMem); @@ -360,10 +360,10 @@ void* ZSTD_customCalloc(size_t size, ZSTD_customMem customMem); void ZSTD_customFree(void* ptr, ZSTD_customMem customMem); -MEM_STATIC U32 ZSTD_highbit32(U32 val) /* compress, dictBuilder, decodeCorpus */ +MEM_STATIC U32 ZSTD_highbit32(U32 val) /* compress, dictBuilder, decodeCorpus */ { - assert(val != 0); - { + assert(val != 0); + { # if defined(_MSC_VER) /* Visual */ # if STATIC_BMI2 == 1 return _lzcnt_u32(val)^31; @@ -382,16 +382,16 @@ MEM_STATIC U32 ZSTD_highbit32(U32 val) /* compress, dictBuilder, decodeCorpus # elif defined(__ICCARM__) /* IAR Intrinsic */ return 31 - __CLZ(val); # else /* Software version */ - static const U32 DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, 11, 14, 16, 18, 22, 25, 3, 30, 8, 12, 20, 28, 15, 17, 24, 7, 19, 27, 23, 6, 26, 5, 4, 31 }; - U32 v = val; - v |= v >> 1; - v |= v >> 2; - v |= v >> 4; - v |= v >> 8; - v |= v >> 16; - return DeBruijnClz[(v * 0x07C4ACDDU) >> 27]; + static const U32 DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, 11, 14, 16, 18, 22, 25, 3, 30, 8, 12, 20, 28, 15, 17, 24, 7, 19, 27, 23, 6, 26, 5, 4, 31 }; + U32 v = val; + v |= v >> 1; + v |= v >> 2; + v |= v >> 4; + v |= v >> 8; + v |= v >> 16; + return DeBruijnClz[(v * 0x07C4ACDDU) >> 27]; # endif - } + } } /** @@ -452,25 +452,25 @@ MEM_STATIC unsigned ZSTD_countTrailingZeros(size_t val) } -/* ZSTD_invalidateRepCodes() : - * ensures next compression will not use repcodes from previous block. - * Note : only works with regular variant; - * do not use with extDict variant ! */ -void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx); /* zstdmt, adaptive_compression (shouldn't get this definition from here) */ - - -typedef struct { - blockType_e blockType; - U32 lastBlock; - U32 origSize; +/* ZSTD_invalidateRepCodes() : + * ensures next compression will not use repcodes from previous block. + * Note : only works with regular variant; + * do not use with extDict variant ! */ +void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx); /* zstdmt, adaptive_compression (shouldn't get this definition from here) */ + + +typedef struct { + blockType_e blockType; + U32 lastBlock; + U32 origSize; } blockProperties_t; /* declared here for decompress and fullbench */ - -/*! ZSTD_getcBlockSize() : - * Provides the size of compressed block from block header `src` */ -/* Used by: decompress, fullbench (does not get its definition from here) */ -size_t ZSTD_getcBlockSize(const void* src, size_t srcSize, - blockProperties_t* bpPtr); - + +/*! ZSTD_getcBlockSize() : + * Provides the size of compressed block from block header `src` */ +/* Used by: decompress, fullbench (does not get its definition from here) */ +size_t ZSTD_getcBlockSize(const void* src, size_t srcSize, + blockProperties_t* bpPtr); + /*! ZSTD_decodeSeqHeaders() : * decode sequence header from src */ /* Used by: decompress, fullbench (does not get its definition from here) */ @@ -486,8 +486,8 @@ MEM_STATIC int ZSTD_cpuSupportsBmi2(void) return ZSTD_cpuid_bmi1(cpuid) && ZSTD_cpuid_bmi2(cpuid); } -#if defined (__cplusplus) -} -#endif - +#if defined (__cplusplus) +} +#endif + #endif /* ZSTD_CCOMMON_H_MODULE */ diff --git a/contrib/libs/zstd/lib/compress/fse_compress.c b/contrib/libs/zstd/lib/compress/fse_compress.c index 5547b4ac09..95dbec2558 100644 --- a/contrib/libs/zstd/lib/compress/fse_compress.c +++ b/contrib/libs/zstd/lib/compress/fse_compress.c @@ -31,7 +31,7 @@ /* ************************************************************** * Error Management ****************************************************************/ -#define FSE_isError ERR_isError +#define FSE_isError ERR_isError /* ************************************************************** @@ -289,7 +289,7 @@ FSE_writeNCount_generic (void* header, size_t headerBufferSize, } } { int count = normalizedCounter[symbol++]; int const max = (2*threshold-1) - remaining; - remaining -= count < 0 ? -count : count; + remaining -= count < 0 ? -count : count; count++; /* +1 for extra accuracy */ if (count>=threshold) count += max; /* [0..max[ [max..threshold[ (...) [threshold+max 2*threshold[ */ @@ -297,8 +297,8 @@ FSE_writeNCount_generic (void* header, size_t headerBufferSize, bitCount += nbBits; bitCount -= (count<max); previousIs0 = (count==1); - if (remaining<1) return ERROR(GENERIC); - while (remaining<threshold) { nbBits--; threshold>>=1; } + if (remaining<1) return ERROR(GENERIC); + while (remaining<threshold) { nbBits--; threshold>>=1; } } if (bitCount>16) { if ((!writeIsSafe) && (out > oend - 2)) @@ -328,7 +328,7 @@ FSE_writeNCount_generic (void* header, size_t headerBufferSize, size_t FSE_writeNCount (void* buffer, size_t bufferSize, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog) { - if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge); /* Unsupported */ + if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge); /* Unsupported */ if (tableLog < FSE_MIN_TABLELOG) return ERROR(GENERIC); /* Unsupported */ if (bufferSize < FSE_NCountWriteBound(maxSymbolValue, tableLog)) @@ -356,21 +356,21 @@ void FSE_freeCTable (FSE_CTable* ct) { ZSTD_free(ct); } static unsigned FSE_minTableLog(size_t srcSize, unsigned maxSymbolValue) { U32 minBitsSrc = BIT_highbit32((U32)(srcSize)) + 1; - U32 minBitsSymbols = BIT_highbit32(maxSymbolValue) + 2; - U32 minBits = minBitsSrc < minBitsSymbols ? minBitsSrc : minBitsSymbols; - assert(srcSize > 1); /* Not supported, RLE should be used instead */ - return minBits; + U32 minBitsSymbols = BIT_highbit32(maxSymbolValue) + 2; + U32 minBits = minBitsSrc < minBitsSymbols ? minBitsSrc : minBitsSymbols; + assert(srcSize > 1); /* Not supported, RLE should be used instead */ + return minBits; } unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus) { - U32 maxBitsSrc = BIT_highbit32((U32)(srcSize - 1)) - minus; + U32 maxBitsSrc = BIT_highbit32((U32)(srcSize - 1)) - minus; U32 tableLog = maxTableLog; - U32 minBits = FSE_minTableLog(srcSize, maxSymbolValue); - assert(srcSize > 1); /* Not supported, RLE should be used instead */ + U32 minBits = FSE_minTableLog(srcSize, maxSymbolValue); + assert(srcSize > 1); /* Not supported, RLE should be used instead */ if (tableLog==0) tableLog = FSE_DEFAULT_TABLELOG; - if (maxBitsSrc < tableLog) tableLog = maxBitsSrc; /* Accuracy can be reduced */ - if (minBits > tableLog) tableLog = minBits; /* Need a minimum to safely represent all symbol values */ + if (maxBitsSrc < tableLog) tableLog = maxBitsSrc; /* Accuracy can be reduced */ + if (minBits > tableLog) tableLog = minBits; /* Need a minimum to safely represent all symbol values */ if (tableLog < FSE_MIN_TABLELOG) tableLog = FSE_MIN_TABLELOG; if (tableLog > FSE_MAX_TABLELOG) tableLog = FSE_MAX_TABLELOG; return tableLog; @@ -386,7 +386,7 @@ unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxS static size_t FSE_normalizeM2(short* norm, U32 tableLog, const unsigned* count, size_t total, U32 maxSymbolValue, short lowProbCount) { - short const NOT_YET_ASSIGNED = -2; + short const NOT_YET_ASSIGNED = -2; U32 s; U32 distributed = 0; U32 ToDistribute; @@ -412,8 +412,8 @@ static size_t FSE_normalizeM2(short* norm, U32 tableLog, const unsigned* count, total -= count[s]; continue; } - - norm[s]=NOT_YET_ASSIGNED; + + norm[s]=NOT_YET_ASSIGNED; } ToDistribute = (1 << tableLog) - distributed; @@ -424,7 +424,7 @@ static size_t FSE_normalizeM2(short* norm, U32 tableLog, const unsigned* count, /* risk of rounding to zero */ lowOne = (U32)((total * 3) / (ToDistribute * 2)); for (s=0; s<=maxSymbolValue; s++) { - if ((norm[s] == NOT_YET_ASSIGNED) && (count[s] <= lowOne)) { + if ((norm[s] == NOT_YET_ASSIGNED) && (count[s] <= lowOne)) { norm[s] = 1; distributed++; total -= count[s]; @@ -439,24 +439,24 @@ static size_t FSE_normalizeM2(short* norm, U32 tableLog, const unsigned* count, find max, then give all remaining points to max */ U32 maxV = 0, maxC = 0; for (s=0; s<=maxSymbolValue; s++) - if (count[s] > maxC) { maxV=s; maxC=count[s]; } + if (count[s] > maxC) { maxV=s; maxC=count[s]; } norm[maxV] += (short)ToDistribute; return 0; } - if (total == 0) { - /* all of the symbols were low enough for the lowOne or lowThreshold */ - for (s=0; ToDistribute > 0; s = (s+1)%(maxSymbolValue+1)) - if (norm[s] > 0) { ToDistribute--; norm[s]++; } - return 0; - } - + if (total == 0) { + /* all of the symbols were low enough for the lowOne or lowThreshold */ + for (s=0; ToDistribute > 0; s = (s+1)%(maxSymbolValue+1)) + if (norm[s] > 0) { ToDistribute--; norm[s]++; } + return 0; + } + { U64 const vStepLog = 62 - tableLog; U64 const mid = (1ULL << (vStepLog-1)) - 1; U64 const rStep = ZSTD_div64((((U64)1<<vStepLog) * ToDistribute) + mid, (U32)total); /* scale on remaining */ U64 tmpTotal = mid; for (s=0; s<=maxSymbolValue; s++) { - if (norm[s]==NOT_YET_ASSIGNED) { + if (norm[s]==NOT_YET_ASSIGNED) { U64 const end = tmpTotal + (count[s] * rStep); U32 const sStart = (U32)(tmpTotal >> vStepLog); U32 const sEnd = (U32)(end >> vStepLog); @@ -480,7 +480,7 @@ size_t FSE_normalizeCount (short* normalizedCounter, unsigned tableLog, if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge); /* Unsupported size */ if (tableLog < FSE_minTableLog(total, maxSymbolValue)) return ERROR(GENERIC); /* Too small tableLog, compression potentially impossible */ - { static U32 const rtbTable[] = { 0, 473195, 504333, 520860, 550000, 700000, 750000, 830000 }; + { static U32 const rtbTable[] = { 0, 473195, 504333, 520860, 550000, 700000, 750000, 830000 }; short const lowProbCount = useLowProbCount ? -1 : 1; U64 const scale = 62 - tableLog; U64 const step = ZSTD_div64((U64)1<<62, (U32)total); /* <== here, one division ! */ @@ -503,7 +503,7 @@ size_t FSE_normalizeCount (short* normalizedCounter, unsigned tableLog, U64 restToBeat = vStep * rtbTable[proba]; proba += (count[s]*step) - ((U64)proba<<scale) > restToBeat; } - if (proba > largestP) { largestP=proba; largest=s; } + if (proba > largestP) { largestP=proba; largest=s; } normalizedCounter[s] = proba; stillToDistribute -= proba; } } diff --git a/contrib/libs/zstd/lib/compress/huf_compress.c b/contrib/libs/zstd/lib/compress/huf_compress.c index 2b3d6adc2a..0de33e9408 100644 --- a/contrib/libs/zstd/lib/compress/huf_compress.c +++ b/contrib/libs/zstd/lib/compress/huf_compress.c @@ -37,7 +37,7 @@ /* ************************************************************** * Error Management ****************************************************************/ -#define HUF_isError ERR_isError +#define HUF_isError ERR_isError #define HUF_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c) /* use only *after* variable declarations */ @@ -232,7 +232,7 @@ size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void /* check result */ if (tableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge); - if (nbSymbols > *maxSymbolValuePtr+1) return ERROR(maxSymbolValue_tooSmall); + if (nbSymbols > *maxSymbolValuePtr+1) return ERROR(maxSymbolValue_tooSmall); CTable[0] = tableLog; @@ -266,7 +266,7 @@ size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void { U32 n; for (n=0; n<nbSymbols; n++) HUF_setValue(ct + n, valPerRank[HUF_getNbBits(ct[n])]++); } } - *maxSymbolValuePtr = nbSymbols - 1; + *maxSymbolValuePtr = nbSymbols - 1; return readSize; } @@ -369,8 +369,8 @@ static U32 HUF_setMaxHeight(nodeElt* huffNode, U32 lastNonNull, U32 maxNbBits) } } /* only triggered when no more rank 1 symbol left => find closest one (note : there is necessarily at least one !) */ assert(rankLast[nBitsToDecrease] != noSymbol || nBitsToDecrease == 1); - /* HUF_MAX_TABLELOG test just to please gcc 5+; but it should not be necessary */ - while ((nBitsToDecrease<=HUF_TABLELOG_MAX) && (rankLast[nBitsToDecrease] == noSymbol)) + /* HUF_MAX_TABLELOG test just to please gcc 5+; but it should not be necessary */ + while ((nBitsToDecrease<=HUF_TABLELOG_MAX) && (rankLast[nBitsToDecrease] == noSymbol)) nBitsToDecrease++; assert(rankLast[nBitsToDecrease] != noSymbol); /* Increase the number of bits to gain back half the rank cost. */ @@ -710,24 +710,24 @@ size_t HUF_buildCTable_wksp (HUF_CElt* CTable, const unsigned* count, U32 maxSym size_t HUF_estimateCompressedSize(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue) { HUF_CElt const* ct = CTable + 1; - size_t nbBits = 0; - int s; - for (s = 0; s <= (int)maxSymbolValue; ++s) { + size_t nbBits = 0; + int s; + for (s = 0; s <= (int)maxSymbolValue; ++s) { nbBits += HUF_getNbBits(ct[s]) * count[s]; - } - return nbBits >> 3; + } + return nbBits >> 3; } int HUF_validateCTable(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue) { HUF_CElt const* ct = CTable + 1; - int bad = 0; - int s; - for (s = 0; s <= (int)maxSymbolValue; ++s) { + int bad = 0; + int s; + for (s = 0; s <= (int)maxSymbolValue; ++s) { bad |= (count[s] != 0) & (HUF_getNbBits(ct[s]) == 0); - } - return !bad; -} - + } + return !bad; +} + size_t HUF_compressBound(size_t size) { return HUF_COMPRESSBOUND(size); } /** HUF_CStream_t: @@ -891,11 +891,11 @@ static size_t HUF_closeCStream(HUF_CStream_t* bitC) } } -FORCE_INLINE_TEMPLATE void +FORCE_INLINE_TEMPLATE void HUF_encodeSymbol(HUF_CStream_t* bitCPtr, U32 symbol, const HUF_CElt* CTable, int idx, int fast) -{ +{ HUF_addBits(bitCPtr, CTable[symbol], idx, fast); -} +} FORCE_INLINE_TEMPLATE void HUF_compress1X_usingCTable_internal_body_loop(HUF_CStream_t* bitC, @@ -913,7 +913,7 @@ HUF_compress1X_usingCTable_internal_body_loop(HUF_CStream_t* bitC, HUF_flushBits(bitC, kFastFlush); } assert(n % kUnroll == 0); - + /* Join to 2 * kUnroll */ if (n % (2 * kUnroll)) { int u; @@ -962,10 +962,10 @@ static size_t HUF_tightCompressBound(size_t srcSize, size_t tableLog) } -FORCE_INLINE_TEMPLATE size_t -HUF_compress1X_usingCTable_internal_body(void* dst, size_t dstSize, - const void* src, size_t srcSize, - const HUF_CElt* CTable) +FORCE_INLINE_TEMPLATE size_t +HUF_compress1X_usingCTable_internal_body(void* dst, size_t dstSize, + const void* src, size_t srcSize, + const HUF_CElt* CTable) { U32 const tableLog = (U32)CTable[0]; HUF_CElt const* ct = CTable + 1; @@ -1027,63 +1027,63 @@ HUF_compress1X_usingCTable_internal_body(void* dst, size_t dstSize, return HUF_closeCStream(&bitC); } -#if DYNAMIC_BMI2 +#if DYNAMIC_BMI2 static BMI2_TARGET_ATTRIBUTE size_t -HUF_compress1X_usingCTable_internal_bmi2(void* dst, size_t dstSize, - const void* src, size_t srcSize, - const HUF_CElt* CTable) -{ - return HUF_compress1X_usingCTable_internal_body(dst, dstSize, src, srcSize, CTable); -} - -static size_t -HUF_compress1X_usingCTable_internal_default(void* dst, size_t dstSize, - const void* src, size_t srcSize, - const HUF_CElt* CTable) -{ - return HUF_compress1X_usingCTable_internal_body(dst, dstSize, src, srcSize, CTable); -} - -static size_t -HUF_compress1X_usingCTable_internal(void* dst, size_t dstSize, - const void* src, size_t srcSize, - const HUF_CElt* CTable, const int bmi2) -{ - if (bmi2) { - return HUF_compress1X_usingCTable_internal_bmi2(dst, dstSize, src, srcSize, CTable); - } - return HUF_compress1X_usingCTable_internal_default(dst, dstSize, src, srcSize, CTable); -} - -#else - -static size_t -HUF_compress1X_usingCTable_internal(void* dst, size_t dstSize, - const void* src, size_t srcSize, - const HUF_CElt* CTable, const int bmi2) -{ - (void)bmi2; - return HUF_compress1X_usingCTable_internal_body(dst, dstSize, src, srcSize, CTable); -} - -#endif - -size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable) +HUF_compress1X_usingCTable_internal_bmi2(void* dst, size_t dstSize, + const void* src, size_t srcSize, + const HUF_CElt* CTable) { + return HUF_compress1X_usingCTable_internal_body(dst, dstSize, src, srcSize, CTable); +} + +static size_t +HUF_compress1X_usingCTable_internal_default(void* dst, size_t dstSize, + const void* src, size_t srcSize, + const HUF_CElt* CTable) +{ + return HUF_compress1X_usingCTable_internal_body(dst, dstSize, src, srcSize, CTable); +} + +static size_t +HUF_compress1X_usingCTable_internal(void* dst, size_t dstSize, + const void* src, size_t srcSize, + const HUF_CElt* CTable, const int bmi2) +{ + if (bmi2) { + return HUF_compress1X_usingCTable_internal_bmi2(dst, dstSize, src, srcSize, CTable); + } + return HUF_compress1X_usingCTable_internal_default(dst, dstSize, src, srcSize, CTable); +} + +#else + +static size_t +HUF_compress1X_usingCTable_internal(void* dst, size_t dstSize, + const void* src, size_t srcSize, + const HUF_CElt* CTable, const int bmi2) +{ + (void)bmi2; + return HUF_compress1X_usingCTable_internal_body(dst, dstSize, src, srcSize, CTable); +} + +#endif + +size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable) +{ return HUF_compress1X_usingCTable_bmi2(dst, dstSize, src, srcSize, CTable, /* bmi2 */ 0); -} - +} + size_t HUF_compress1X_usingCTable_bmi2(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable, int bmi2) { return HUF_compress1X_usingCTable_internal(dst, dstSize, src, srcSize, CTable, bmi2); } - -static size_t -HUF_compress4X_usingCTable_internal(void* dst, size_t dstSize, - const void* src, size_t srcSize, - const HUF_CElt* CTable, int bmi2) -{ + +static size_t +HUF_compress4X_usingCTable_internal(void* dst, size_t dstSize, + const void* src, size_t srcSize, + const HUF_CElt* CTable, int bmi2) +{ size_t const segmentSize = (srcSize+3)/4; /* first 3 segments */ const BYTE* ip = (const BYTE*) src; const BYTE* const iend = ip + srcSize; @@ -1129,10 +1129,10 @@ HUF_compress4X_usingCTable_internal(void* dst, size_t dstSize, return (size_t)(op-ostart); } -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(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable) +{ return HUF_compress4X_usingCTable_bmi2(dst, dstSize, src, srcSize, CTable, /* bmi2 */ 0); -} +} size_t HUF_compress4X_usingCTable_bmi2(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable, int bmi2) { @@ -1140,25 +1140,25 @@ size_t HUF_compress4X_usingCTable_bmi2(void* dst, size_t dstSize, const void* sr } typedef enum { HUF_singleStream, HUF_fourStreams } HUF_nbStreams_e; - -static size_t HUF_compressCTable_internal( - BYTE* const ostart, BYTE* op, BYTE* const oend, - const void* src, size_t srcSize, + +static size_t HUF_compressCTable_internal( + BYTE* const ostart, BYTE* op, BYTE* const oend, + const void* src, size_t srcSize, HUF_nbStreams_e nbStreams, const HUF_CElt* CTable, const int bmi2) -{ +{ size_t const cSize = (nbStreams==HUF_singleStream) ? HUF_compress1X_usingCTable_internal(op, (size_t)(oend - op), src, srcSize, CTable, bmi2) : HUF_compress4X_usingCTable_internal(op, (size_t)(oend - op), src, srcSize, CTable, bmi2); - if (HUF_isError(cSize)) { return cSize; } - if (cSize==0) { return 0; } /* uncompressible */ - op += cSize; - /* check compressibility */ + if (HUF_isError(cSize)) { return cSize; } + if (cSize==0) { return 0; } /* uncompressible */ + op += cSize; + /* check compressibility */ assert(op >= ostart); - if ((size_t)(op-ostart) >= srcSize-1) { return 0; } + if ((size_t)(op-ostart) >= srcSize-1) { return 0; } return (size_t)(op-ostart); -} - -typedef struct { +} + +typedef struct { unsigned count[HUF_SYMBOLVALUE_MAX + 1]; HUF_CElt CTable[HUF_CTABLE_SIZE_ST(HUF_SYMBOLVALUE_MAX)]; union { @@ -1166,12 +1166,12 @@ typedef struct { HUF_WriteCTableWksp writeCTable_wksp; U32 hist_wksp[HIST_WKSP_SIZE_U32]; } wksps; -} HUF_compress_tables_t; - +} HUF_compress_tables_t; + #define SUSPECT_INCOMPRESSIBLE_SAMPLE_SIZE 4096 #define SUSPECT_INCOMPRESSIBLE_SAMPLE_RATIO 10 /* Must be >= 2 */ -/* HUF_compress_internal() : +/* HUF_compress_internal() : * `workSpace_align4` must be aligned on 4-bytes boundaries, * and occupies the same space as a table of HUF_WORKSPACE_SIZE_U64 unsigned */ static size_t @@ -1192,21 +1192,21 @@ HUF_compress_internal (void* dst, size_t dstSize, /* checks & inits */ if (wkspSize < sizeof(*table)) return ERROR(workSpace_tooSmall); - if (!srcSize) return 0; /* Uncompressed */ - if (!dstSize) return 0; /* cannot fit anything within dst budget */ + if (!srcSize) return 0; /* Uncompressed */ + if (!dstSize) return 0; /* cannot fit anything within dst budget */ if (srcSize > HUF_BLOCKSIZE_MAX) return ERROR(srcSize_wrong); /* current block size limit */ if (huffLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge); - if (maxSymbolValue > HUF_SYMBOLVALUE_MAX) return ERROR(maxSymbolValue_tooLarge); + if (maxSymbolValue > HUF_SYMBOLVALUE_MAX) return ERROR(maxSymbolValue_tooLarge); if (!maxSymbolValue) maxSymbolValue = HUF_SYMBOLVALUE_MAX; if (!huffLog) huffLog = HUF_TABLELOG_DEFAULT; - /* Heuristic : If old table is valid, use it for small inputs */ - if (preferRepeat && repeat && *repeat == HUF_repeat_valid) { - return HUF_compressCTable_internal(ostart, op, oend, - src, srcSize, + /* Heuristic : If old table is valid, use it for small inputs */ + if (preferRepeat && repeat && *repeat == HUF_repeat_valid) { + return HUF_compressCTable_internal(ostart, op, oend, + src, srcSize, nbStreams, oldHufTable, bmi2); - } - + } + /* If uncompressible data is suspected, do a smaller sampling first */ DEBUG_STATIC_ASSERT(SUSPECT_INCOMPRESSIBLE_SAMPLE_RATIO >= 2); if (suspectUncompressible && srcSize >= (SUSPECT_INCOMPRESSIBLE_SAMPLE_SIZE * SUSPECT_INCOMPRESSIBLE_SAMPLE_RATIO)) { @@ -1228,19 +1228,19 @@ HUF_compress_internal (void* dst, size_t dstSize, if (largest <= (srcSize >> 7)+4) return 0; /* heuristic : probably not compressible enough */ } - /* Check validity of previous table */ - if ( repeat - && *repeat == HUF_repeat_check - && !HUF_validateCTable(oldHufTable, table->count, maxSymbolValue)) { - *repeat = HUF_repeat_none; - } - /* Heuristic : use existing table for small inputs */ - if (preferRepeat && repeat && *repeat != HUF_repeat_none) { - return HUF_compressCTable_internal(ostart, op, oend, - src, srcSize, + /* Check validity of previous table */ + if ( repeat + && *repeat == HUF_repeat_check + && !HUF_validateCTable(oldHufTable, table->count, maxSymbolValue)) { + *repeat = HUF_repeat_none; + } + /* Heuristic : use existing table for small inputs */ + if (preferRepeat && repeat && *repeat != HUF_repeat_none) { + return HUF_compressCTable_internal(ostart, op, oend, + src, srcSize, nbStreams, oldHufTable, bmi2); - } - + } + /* Build Huffman Tree */ huffLog = HUF_optimalTableLog(huffLog, srcSize, maxSymbolValue); { size_t const maxBits = HUF_buildCTable_wksp(table->CTable, table->count, @@ -1259,25 +1259,25 @@ HUF_compress_internal (void* dst, size_t dstSize, /* Write table description header */ { CHECK_V_F(hSize, HUF_writeCTable_wksp(op, dstSize, table->CTable, maxSymbolValue, huffLog, &table->wksps.writeCTable_wksp, sizeof(table->wksps.writeCTable_wksp)) ); - /* Check if using previous huffman table is beneficial */ - if (repeat && *repeat != HUF_repeat_none) { - size_t const oldSize = HUF_estimateCompressedSize(oldHufTable, table->count, maxSymbolValue); - size_t const newSize = HUF_estimateCompressedSize(table->CTable, table->count, maxSymbolValue); - if (oldSize <= hSize + newSize || hSize + 12 >= srcSize) { - return HUF_compressCTable_internal(ostart, op, oend, - src, srcSize, + /* Check if using previous huffman table is beneficial */ + if (repeat && *repeat != HUF_repeat_none) { + size_t const oldSize = HUF_estimateCompressedSize(oldHufTable, table->count, maxSymbolValue); + size_t const newSize = HUF_estimateCompressedSize(table->CTable, table->count, maxSymbolValue); + if (oldSize <= hSize + newSize || hSize + 12 >= srcSize) { + return HUF_compressCTable_internal(ostart, op, oend, + src, srcSize, nbStreams, oldHufTable, bmi2); - } } - - /* Use the new huffman table */ - if (hSize + 12ul >= srcSize) { return 0; } + } } + + /* Use the new huffman table */ + if (hSize + 12ul >= srcSize) { return 0; } op += hSize; - if (repeat) { *repeat = HUF_repeat_none; } - if (oldHufTable) + if (repeat) { *repeat = HUF_repeat_none; } + if (oldHufTable) ZSTD_memcpy(oldHufTable, table->CTable, sizeof(table->CTable)); /* Save new table */ } - return HUF_compressCTable_internal(ostart, op, oend, - src, srcSize, + return HUF_compressCTable_internal(ostart, op, oend, + src, srcSize, nbStreams, table->CTable, bmi2); } @@ -1287,55 +1287,55 @@ size_t HUF_compress1X_wksp (void* dst, size_t dstSize, unsigned maxSymbolValue, unsigned huffLog, void* workSpace, size_t wkspSize) { - return HUF_compress_internal(dst, dstSize, src, srcSize, + return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, HUF_singleStream, - workSpace, wkspSize, + workSpace, wkspSize, NULL, NULL, 0, 0 /*bmi2*/, 0); } -size_t HUF_compress1X_repeat (void* dst, size_t dstSize, - const void* src, size_t srcSize, - unsigned maxSymbolValue, unsigned huffLog, - void* workSpace, size_t wkspSize, +size_t HUF_compress1X_repeat (void* dst, size_t dstSize, + const void* src, size_t srcSize, + unsigned maxSymbolValue, unsigned huffLog, + void* workSpace, size_t wkspSize, HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2, unsigned suspectUncompressible) -{ - return HUF_compress_internal(dst, dstSize, src, srcSize, +{ + return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, HUF_singleStream, - workSpace, wkspSize, hufTable, + workSpace, wkspSize, hufTable, repeat, preferRepeat, bmi2, suspectUncompressible); -} - -/* HUF_compress4X_repeat(): - * compress input using 4 streams. - * provide workspace to generate compression tables */ +} + +/* HUF_compress4X_repeat(): + * compress input using 4 streams. + * provide workspace to generate compression tables */ size_t HUF_compress4X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void* workSpace, size_t wkspSize) { - return HUF_compress_internal(dst, dstSize, src, srcSize, + return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, HUF_fourStreams, - workSpace, wkspSize, + workSpace, wkspSize, NULL, NULL, 0, 0 /*bmi2*/, 0); } -/* HUF_compress4X_repeat(): - * compress input using 4 streams. +/* HUF_compress4X_repeat(): + * compress input using 4 streams. * consider skipping quickly - * re-use an existing huffman compression table */ -size_t HUF_compress4X_repeat (void* dst, size_t dstSize, - const void* src, size_t srcSize, - unsigned maxSymbolValue, unsigned huffLog, - void* workSpace, size_t wkspSize, + * re-use an existing huffman compression table */ +size_t HUF_compress4X_repeat (void* dst, size_t dstSize, + const void* src, size_t srcSize, + unsigned maxSymbolValue, unsigned huffLog, + void* workSpace, size_t wkspSize, HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2, unsigned suspectUncompressible) -{ - return HUF_compress_internal(dst, dstSize, src, srcSize, +{ + return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, HUF_fourStreams, - workSpace, wkspSize, + workSpace, wkspSize, hufTable, repeat, preferRepeat, bmi2, suspectUncompressible); -} - +} + #ifndef ZSTD_NO_UNUSED_FUNCTIONS /** HUF_buildCTable() : * @return : maxNbBits @@ -1365,6 +1365,6 @@ size_t HUF_compress2 (void* dst, size_t dstSize, size_t HUF_compress (void* dst, size_t maxDstSize, const void* src, size_t srcSize) { - return HUF_compress2(dst, maxDstSize, src, srcSize, 255, HUF_TABLELOG_DEFAULT); + return HUF_compress2(dst, maxDstSize, src, srcSize, 255, HUF_TABLELOG_DEFAULT); } #endif diff --git a/contrib/libs/zstd/lib/compress/zstd_compress.c b/contrib/libs/zstd/lib/compress/zstd_compress.c index f06456af92..a03dfab6bd 100644 --- a/contrib/libs/zstd/lib/compress/zstd_compress.c +++ b/contrib/libs/zstd/lib/compress/zstd_compress.c @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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. */ /*-************************************* @@ -18,14 +18,14 @@ #include "../common/fse.h" #define HUF_STATIC_LINKING_ONLY #include "../common/huf.h" -#include "zstd_compress_internal.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" -#include "zstd_opt.h" -#include "zstd_ldm.h" +#include "zstd_fast.h" +#include "zstd_double_fast.h" +#include "zstd_lazy.h" +#include "zstd_opt.h" +#include "zstd_ldm.h" #include "zstd_compress_superblock.h" /* *************************************************************** @@ -64,34 +64,34 @@ * the overhead of headers can make the compressed data to be larger than the * return value of ZSTD_compressBound(). */ -size_t ZSTD_compressBound(size_t srcSize) { - return ZSTD_COMPRESSBOUND(srcSize); +size_t ZSTD_compressBound(size_t srcSize) { + return ZSTD_COMPRESSBOUND(srcSize); } /*-************************************* * Context memory management ***************************************/ -struct ZSTD_CDict_s { - const void* dictContent; - size_t dictContentSize; +struct ZSTD_CDict_s { + const void* dictContent; + size_t dictContentSize; ZSTD_dictContentType_e dictContentType; /* The dictContentType the CDict was created with */ U32* entropyWorkspace; /* entropy workspace of HUF_WORKSPACE_SIZE bytes */ ZSTD_cwksp workspace; - ZSTD_matchState_t matchState; - ZSTD_compressedBlockState_t cBlockState; + ZSTD_matchState_t matchState; + ZSTD_compressedBlockState_t cBlockState; ZSTD_customMem customMem; - U32 dictID; + U32 dictID; int compressionLevel; /* 0 indicates that advanced API was used to select CDict params */ ZSTD_paramSwitch_e useRowMatchFinder; /* Indicates whether the CDict was created with params that would use * row-based matchfinder. Unless the cdict is reloaded, we will use * the same greedy/lazy matchfinder at compression time. */ -}; /* typedef'd to ZSTD_CDict within "zstd.h" */ +}; /* typedef'd to ZSTD_CDict within "zstd.h" */ ZSTD_CCtx* ZSTD_createCCtx(void) { - return ZSTD_createCCtx_advanced(ZSTD_defaultCMem); + return ZSTD_createCCtx_advanced(ZSTD_defaultCMem); } static void ZSTD_initCCtx(ZSTD_CCtx* cctx, ZSTD_customMem memManager) @@ -108,22 +108,22 @@ static void ZSTD_initCCtx(ZSTD_CCtx* cctx, ZSTD_customMem memManager) ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem) { - ZSTD_STATIC_ASSERT(zcss_init==0); - ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN==(0ULL - 1)); + ZSTD_STATIC_ASSERT(zcss_init==0); + ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN==(0ULL - 1)); if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL; { ZSTD_CCtx* const cctx = (ZSTD_CCtx*)ZSTD_customMalloc(sizeof(ZSTD_CCtx), customMem); - if (!cctx) return NULL; + if (!cctx) return NULL; ZSTD_initCCtx(cctx, customMem); - return cctx; - } -} + return cctx; + } +} ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize) -{ +{ ZSTD_cwksp ws; ZSTD_CCtx* cctx; - if (workspaceSize <= sizeof(ZSTD_CCtx)) return NULL; /* minimum size */ - if ((size_t)workspace & 7) return NULL; /* must be 8-aligned */ + if (workspaceSize <= sizeof(ZSTD_CCtx)) return NULL; /* minimum size */ + if ((size_t)workspace & 7) return NULL; /* must be 8-aligned */ ZSTD_cwksp_init(&ws, workspace, workspaceSize, ZSTD_cwksp_static_alloc); cctx = (ZSTD_CCtx*)ZSTD_cwksp_reserve_object(&ws, sizeof(ZSTD_CCtx)); @@ -131,14 +131,14 @@ ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize) ZSTD_memset(cctx, 0, sizeof(ZSTD_CCtx)); ZSTD_cwksp_move(&cctx->workspace, &ws); - cctx->staticSize = workspaceSize; + cctx->staticSize = workspaceSize; - /* statically sized space. entropyWorkspace never moves (but prev/next block swap places) */ + /* statically sized space. entropyWorkspace never moves (but prev/next block swap places) */ if (!ZSTD_cwksp_check_available(&cctx->workspace, ENTROPY_WORKSPACE_SIZE + 2 * sizeof(ZSTD_compressedBlockState_t))) return NULL; cctx->blockState.prevCBlock = (ZSTD_compressedBlockState_t*)ZSTD_cwksp_reserve_object(&cctx->workspace, sizeof(ZSTD_compressedBlockState_t)); cctx->blockState.nextCBlock = (ZSTD_compressedBlockState_t*)ZSTD_cwksp_reserve_object(&cctx->workspace, sizeof(ZSTD_compressedBlockState_t)); cctx->entropyWorkspace = (U32*)ZSTD_cwksp_reserve_object(&cctx->workspace, ENTROPY_WORKSPACE_SIZE); - cctx->bmi2 = ZSTD_cpuid_bmi2(ZSTD_cpuid()); + cctx->bmi2 = ZSTD_cpuid_bmi2(ZSTD_cpuid()); return cctx; } @@ -166,9 +166,9 @@ static void ZSTD_freeCCtxContent(ZSTD_CCtx* cctx) assert(cctx != NULL); assert(cctx->staticSize == 0); ZSTD_clearAllDicts(cctx); -#ifdef ZSTD_MULTITHREAD - ZSTDMT_freeCCtx(cctx->mtctx); cctx->mtctx = NULL; -#endif +#ifdef ZSTD_MULTITHREAD + ZSTDMT_freeCCtx(cctx->mtctx); cctx->mtctx = NULL; +#endif ZSTD_cwksp_free(&cctx->workspace, cctx->customMem); } @@ -187,18 +187,18 @@ size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx) return 0; } - -static size_t ZSTD_sizeof_mtctx(const ZSTD_CCtx* cctx) -{ -#ifdef ZSTD_MULTITHREAD - return ZSTDMT_sizeof_CCtx(cctx->mtctx); -#else + +static size_t ZSTD_sizeof_mtctx(const ZSTD_CCtx* cctx) +{ +#ifdef ZSTD_MULTITHREAD + return ZSTDMT_sizeof_CCtx(cctx->mtctx); +#else (void)cctx; - return 0; -#endif -} - - + return 0; +#endif +} + + size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx) { if (cctx==NULL) return 0; /* support sizeof on NULL */ @@ -206,17 +206,17 @@ size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx) return (cctx->workspace.workspace == cctx ? 0 : sizeof(*cctx)) + ZSTD_cwksp_sizeof(&cctx->workspace) + ZSTD_sizeof_localDict(cctx->localDict) - + ZSTD_sizeof_mtctx(cctx); + + ZSTD_sizeof_mtctx(cctx); } -size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs) +size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs) { - return ZSTD_sizeof_CCtx(zcs); /* same object */ + return ZSTD_sizeof_CCtx(zcs); /* same object */ } -/* private API call, for dictBuilder only */ -const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx) { return &(ctx->seqStore); } - +/* private API call, for dictBuilder only */ +const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx) { return &(ctx->seqStore); } + /* Returns true if the strategy supports using a row based matchfinder */ static int ZSTD_rowMatchFinderSupported(const ZSTD_strategy strategy) { return (strategy >= ZSTD_greedy && strategy <= ZSTD_lazy2); @@ -277,13 +277,13 @@ static ZSTD_paramSwitch_e ZSTD_resolveEnableLdm(ZSTD_paramSwitch_e mode, return (cParams->strategy >= ZSTD_btopt && cParams->windowLog >= 27) ? ZSTD_ps_enable : ZSTD_ps_disable; } -static ZSTD_CCtx_params ZSTD_makeCCtxParamsFromCParams( - ZSTD_compressionParameters cParams) -{ - ZSTD_CCtx_params cctxParams; +static ZSTD_CCtx_params ZSTD_makeCCtxParamsFromCParams( + ZSTD_compressionParameters cParams) +{ + ZSTD_CCtx_params cctxParams; /* should not matter, as all cParams are presumed properly defined */ ZSTD_CCtxParams_init(&cctxParams, ZSTD_CLEVEL_DEFAULT); - cctxParams.cParams = cParams; + cctxParams.cParams = cParams; /* Adjust advanced params according to cParams */ cctxParams.ldmParams.enableLdm = ZSTD_resolveEnableLdm(cctxParams.ldmParams.enableLdm, &cParams); @@ -294,48 +294,48 @@ static ZSTD_CCtx_params ZSTD_makeCCtxParamsFromCParams( } cctxParams.useBlockSplitter = ZSTD_resolveBlockSplitterMode(cctxParams.useBlockSplitter, &cParams); cctxParams.useRowMatchFinder = ZSTD_resolveRowMatchFinderMode(cctxParams.useRowMatchFinder, &cParams); - assert(!ZSTD_checkCParams(cParams)); - return cctxParams; -} - -static ZSTD_CCtx_params* ZSTD_createCCtxParams_advanced( - ZSTD_customMem customMem) -{ - ZSTD_CCtx_params* params; + assert(!ZSTD_checkCParams(cParams)); + return cctxParams; +} + +static ZSTD_CCtx_params* ZSTD_createCCtxParams_advanced( + ZSTD_customMem customMem) +{ + ZSTD_CCtx_params* params; if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL; params = (ZSTD_CCtx_params*)ZSTD_customCalloc( - sizeof(ZSTD_CCtx_params), customMem); - if (!params) { return NULL; } + sizeof(ZSTD_CCtx_params), customMem); + if (!params) { return NULL; } ZSTD_CCtxParams_init(params, ZSTD_CLEVEL_DEFAULT); - params->customMem = customMem; - return params; -} - -ZSTD_CCtx_params* ZSTD_createCCtxParams(void) -{ - return ZSTD_createCCtxParams_advanced(ZSTD_defaultCMem); -} - -size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params) -{ - if (params == NULL) { return 0; } + params->customMem = customMem; + return params; +} + +ZSTD_CCtx_params* ZSTD_createCCtxParams(void) +{ + return ZSTD_createCCtxParams_advanced(ZSTD_defaultCMem); +} + +size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params) +{ + if (params == NULL) { return 0; } ZSTD_customFree(params, params->customMem); - return 0; -} - -size_t ZSTD_CCtxParams_reset(ZSTD_CCtx_params* params) -{ - return ZSTD_CCtxParams_init(params, ZSTD_CLEVEL_DEFAULT); -} - -size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel) { + return 0; +} + +size_t ZSTD_CCtxParams_reset(ZSTD_CCtx_params* params) +{ + return ZSTD_CCtxParams_init(params, ZSTD_CLEVEL_DEFAULT); +} + +size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel) { RETURN_ERROR_IF(!cctxParams, GENERIC, "NULL pointer!"); ZSTD_memset(cctxParams, 0, sizeof(*cctxParams)); - cctxParams->compressionLevel = compressionLevel; - cctxParams->fParams.contentSizeFlag = 1; - return 0; -} - + cctxParams->compressionLevel = compressionLevel; + cctxParams->fParams.contentSizeFlag = 1; + return 0; +} + #define ZSTD_NO_CLEVEL 0 /** @@ -359,21 +359,21 @@ static void ZSTD_CCtxParams_init_internal(ZSTD_CCtx_params* cctxParams, ZSTD_par cctxParams->useRowMatchFinder, cctxParams->useBlockSplitter, cctxParams->ldmParams.enableLdm); } -size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params) -{ +size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params) +{ RETURN_ERROR_IF(!cctxParams, GENERIC, "NULL pointer!"); FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) , ""); ZSTD_CCtxParams_init_internal(cctxParams, ¶ms, ZSTD_NO_CLEVEL); - return 0; -} - + return 0; +} + /** * Sets cctxParams' cParams and fParams from params, but otherwise leaves them alone. * @param param Validated zstd parameters. */ static void ZSTD_CCtxParams_setZstdParams( ZSTD_CCtx_params* cctxParams, const ZSTD_parameters* params) -{ +{ assert(!ZSTD_checkCParams(params->cParams)); cctxParams->cParams = params->cParams; cctxParams->fParams = params->fParams; @@ -381,19 +381,19 @@ static void ZSTD_CCtxParams_setZstdParams( * But, set it for tracing anyway. */ cctxParams->compressionLevel = ZSTD_NO_CLEVEL; -} - +} + ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param) { ZSTD_bounds bounds = { 0, 0, 0 }; - + switch(param) { case ZSTD_c_compressionLevel: bounds.lowerBound = ZSTD_minCLevel(); bounds.upperBound = ZSTD_maxCLevel(); return bounds; - + case ZSTD_c_windowLog: bounds.lowerBound = ZSTD_WINDOWLOG_MIN; bounds.upperBound = ZSTD_WINDOWLOG_MAX; @@ -596,10 +596,10 @@ static size_t ZSTD_cParam_clampBounds(ZSTD_cParameter cParam, int* value) } -static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param) -{ - switch(param) - { +static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param) +{ + switch(param) + { case ZSTD_c_compressionLevel: case ZSTD_c_hashLog: case ZSTD_c_chainLog: @@ -607,8 +607,8 @@ static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param) case ZSTD_c_minMatch: case ZSTD_c_targetLength: case ZSTD_c_strategy: - return 1; - + return 1; + case ZSTD_c_format: case ZSTD_c_windowLog: case ZSTD_c_contentSizeFlag: @@ -636,28 +636,28 @@ static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param) case ZSTD_c_useBlockSplitter: case ZSTD_c_useRowMatchFinder: case ZSTD_c_deterministicRefPrefix: - default: - return 0; - } -} - + default: + return 0; + } +} + size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value) -{ +{ DEBUGLOG(4, "ZSTD_CCtx_setParameter (%i, %i)", (int)param, value); - if (cctx->streamStage != zcss_init) { - if (ZSTD_isUpdateAuthorized(param)) { - cctx->cParamsChanged = 1; - } else { + if (cctx->streamStage != zcss_init) { + if (ZSTD_isUpdateAuthorized(param)) { + cctx->cParamsChanged = 1; + } else { RETURN_ERROR(stage_wrong, "can only set params in ctx init stage"); - } } - - switch(param) - { + } } + + switch(param) + { case ZSTD_c_nbWorkers: RETURN_ERROR_IF((value!=0) && cctx->staticSize, parameter_unsupported, "MT not compatible with static alloc"); break; - + case ZSTD_c_compressionLevel: case ZSTD_c_windowLog: case ZSTD_c_hashLog: @@ -692,23 +692,23 @@ size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value) case ZSTD_c_useRowMatchFinder: case ZSTD_c_deterministicRefPrefix: break; - + default: RETURN_ERROR(parameter_unsupported, "unknown parameter"); - } + } return ZSTD_CCtxParams_setParameter(&cctx->requestedParams, param, value); -} - +} + size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams, ZSTD_cParameter param, int value) -{ +{ DEBUGLOG(4, "ZSTD_CCtxParams_setParameter (%i, %i)", (int)param, value); - switch(param) - { + switch(param) + { case ZSTD_c_format : BOUNDCHECK(ZSTD_c_format, value); - CCtxParams->format = (ZSTD_format_e)value; - return (size_t)CCtxParams->format; - + CCtxParams->format = (ZSTD_format_e)value; + return (size_t)CCtxParams->format; + case ZSTD_c_compressionLevel : { FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value), ""); if (value == 0) @@ -716,70 +716,70 @@ size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams, else CCtxParams->compressionLevel = value; if (CCtxParams->compressionLevel >= 0) return (size_t)CCtxParams->compressionLevel; - return 0; /* return type (size_t) cannot represent negative values */ - } - + return 0; /* return type (size_t) cannot represent negative values */ + } + case ZSTD_c_windowLog : if (value!=0) /* 0 => use default */ BOUNDCHECK(ZSTD_c_windowLog, value); CCtxParams->cParams.windowLog = (U32)value; - return CCtxParams->cParams.windowLog; - + return CCtxParams->cParams.windowLog; + case ZSTD_c_hashLog : if (value!=0) /* 0 => use default */ BOUNDCHECK(ZSTD_c_hashLog, value); CCtxParams->cParams.hashLog = (U32)value; - return CCtxParams->cParams.hashLog; - + return CCtxParams->cParams.hashLog; + case ZSTD_c_chainLog : if (value!=0) /* 0 => use default */ BOUNDCHECK(ZSTD_c_chainLog, value); CCtxParams->cParams.chainLog = (U32)value; - return CCtxParams->cParams.chainLog; - + return CCtxParams->cParams.chainLog; + case ZSTD_c_searchLog : if (value!=0) /* 0 => use default */ BOUNDCHECK(ZSTD_c_searchLog, value); CCtxParams->cParams.searchLog = (U32)value; return (size_t)value; - + case ZSTD_c_minMatch : if (value!=0) /* 0 => use default */ BOUNDCHECK(ZSTD_c_minMatch, value); CCtxParams->cParams.minMatch = value; return CCtxParams->cParams.minMatch; - + case ZSTD_c_targetLength : BOUNDCHECK(ZSTD_c_targetLength, value); - CCtxParams->cParams.targetLength = value; - return CCtxParams->cParams.targetLength; - + CCtxParams->cParams.targetLength = value; + return CCtxParams->cParams.targetLength; + case ZSTD_c_strategy : if (value!=0) /* 0 => use default */ BOUNDCHECK(ZSTD_c_strategy, value); - CCtxParams->cParams.strategy = (ZSTD_strategy)value; - return (size_t)CCtxParams->cParams.strategy; - + CCtxParams->cParams.strategy = (ZSTD_strategy)value; + return (size_t)CCtxParams->cParams.strategy; + case ZSTD_c_contentSizeFlag : - /* Content size written in frame header _when known_ (default:1) */ + /* Content size written in frame header _when known_ (default:1) */ DEBUGLOG(4, "set content size flag = %u", (value!=0)); CCtxParams->fParams.contentSizeFlag = value != 0; - return CCtxParams->fParams.contentSizeFlag; - + return CCtxParams->fParams.contentSizeFlag; + case ZSTD_c_checksumFlag : - /* A 32-bits content checksum will be calculated and written at end of frame (default:0) */ + /* A 32-bits content checksum will be calculated and written at end of frame (default:0) */ CCtxParams->fParams.checksumFlag = value != 0; - return CCtxParams->fParams.checksumFlag; - + return CCtxParams->fParams.checksumFlag; + case ZSTD_c_dictIDFlag : /* When applicable, dictionary's dictID is provided in frame header (default:1) */ DEBUGLOG(4, "set dictIDFlag = %u", (value!=0)); - CCtxParams->fParams.noDictIDFlag = !value; - return !CCtxParams->fParams.noDictIDFlag; - + CCtxParams->fParams.noDictIDFlag = !value; + return !CCtxParams->fParams.noDictIDFlag; + case ZSTD_c_forceMaxWindow : CCtxParams->forceWindow = (value != 0); - return CCtxParams->forceWindow; - + return CCtxParams->forceWindow; + case ZSTD_c_forceAttachDict : { const ZSTD_dictAttachPref_e pref = (ZSTD_dictAttachPref_e)value; BOUNDCHECK(ZSTD_c_forceAttachDict, pref); @@ -795,20 +795,20 @@ size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams, } case ZSTD_c_nbWorkers : -#ifndef ZSTD_MULTITHREAD +#ifndef ZSTD_MULTITHREAD RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); - return 0; -#else + return 0; +#else FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value), ""); CCtxParams->nbWorkers = value; return CCtxParams->nbWorkers; -#endif - +#endif + case ZSTD_c_jobSize : -#ifndef ZSTD_MULTITHREAD +#ifndef ZSTD_MULTITHREAD RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); return 0; -#else +#else /* Adjust to the minimum non-default value. */ if (value != 0 && value < ZSTDMT_JOBSIZE_MIN) value = ZSTDMT_JOBSIZE_MIN; @@ -816,18 +816,18 @@ size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams, assert(value >= 0); CCtxParams->jobSize = value; return CCtxParams->jobSize; -#endif - +#endif + case ZSTD_c_overlapLog : -#ifndef ZSTD_MULTITHREAD +#ifndef ZSTD_MULTITHREAD RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); return 0; -#else +#else FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(ZSTD_c_overlapLog, &value), ""); CCtxParams->overlapLog = value; return CCtxParams->overlapLog; -#endif - +#endif + case ZSTD_c_rsyncable : #ifndef ZSTD_MULTITHREAD RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); @@ -844,32 +844,32 @@ size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams, case ZSTD_c_enableLongDistanceMatching : CCtxParams->ldmParams.enableLdm = (ZSTD_paramSwitch_e)value; - return CCtxParams->ldmParams.enableLdm; - + return CCtxParams->ldmParams.enableLdm; + case ZSTD_c_ldmHashLog : if (value!=0) /* 0 ==> auto */ BOUNDCHECK(ZSTD_c_ldmHashLog, value); - CCtxParams->ldmParams.hashLog = value; - return CCtxParams->ldmParams.hashLog; - + CCtxParams->ldmParams.hashLog = value; + return CCtxParams->ldmParams.hashLog; + case ZSTD_c_ldmMinMatch : if (value!=0) /* 0 ==> default */ BOUNDCHECK(ZSTD_c_ldmMinMatch, value); - CCtxParams->ldmParams.minMatchLength = value; - return CCtxParams->ldmParams.minMatchLength; - + CCtxParams->ldmParams.minMatchLength = value; + return CCtxParams->ldmParams.minMatchLength; + case ZSTD_c_ldmBucketSizeLog : if (value!=0) /* 0 ==> default */ BOUNDCHECK(ZSTD_c_ldmBucketSizeLog, value); - CCtxParams->ldmParams.bucketSizeLog = value; - return CCtxParams->ldmParams.bucketSizeLog; - + CCtxParams->ldmParams.bucketSizeLog = value; + return CCtxParams->ldmParams.bucketSizeLog; + case ZSTD_c_ldmHashRateLog : if (value!=0) /* 0 ==> default */ BOUNDCHECK(ZSTD_c_ldmHashRateLog, value); CCtxParams->ldmParams.hashRateLog = value; return CCtxParams->ldmParams.hashRateLog; - + case ZSTD_c_targetCBlockSize : if (value!=0) /* 0 ==> default */ BOUNDCHECK(ZSTD_c_targetCBlockSize, value); @@ -918,9 +918,9 @@ size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams, return CCtxParams->deterministicRefPrefix; default: RETURN_ERROR(parameter_unsupported, "unknown parameter"); - } -} - + } +} + size_t ZSTD_CCtx_getParameter(ZSTD_CCtx const* cctx, ZSTD_cParameter param, int* value) { return ZSTD_CCtxParams_getParameter(&cctx->requestedParams, param, value); @@ -1054,36 +1054,36 @@ size_t ZSTD_CCtxParams_getParameter( return 0; } -/** ZSTD_CCtx_setParametersUsingCCtxParams() : - * just applies `params` into `cctx` - * no action is performed, parameters are merely stored. - * If ZSTDMT is enabled, parameters are pushed to cctx->mtctx. - * This is possible even if a compression is ongoing. - * In which case, new parameters will be applied on the fly, starting with next compression job. - */ -size_t ZSTD_CCtx_setParametersUsingCCtxParams( - ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params) -{ +/** ZSTD_CCtx_setParametersUsingCCtxParams() : + * just applies `params` into `cctx` + * no action is performed, parameters are merely stored. + * If ZSTDMT is enabled, parameters are pushed to cctx->mtctx. + * This is possible even if a compression is ongoing. + * In which case, new parameters will be applied on the fly, starting with next compression job. + */ +size_t ZSTD_CCtx_setParametersUsingCCtxParams( + ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params) +{ DEBUGLOG(4, "ZSTD_CCtx_setParametersUsingCCtxParams"); RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, "The context is in the wrong stage!"); RETURN_ERROR_IF(cctx->cdict, stage_wrong, "Can't override parameters with cdict attached (some must " "be inherited from the cdict)."); - - cctx->requestedParams = *params; - return 0; -} - + + cctx->requestedParams = *params; + return 0; +} + size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize) -{ - DEBUGLOG(4, "ZSTD_CCtx_setPledgedSrcSize to %u bytes", (U32)pledgedSrcSize); +{ + DEBUGLOG(4, "ZSTD_CCtx_setPledgedSrcSize to %u bytes", (U32)pledgedSrcSize); RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, "Can't set pledgedSrcSize when not in init stage."); - cctx->pledgedSrcSizePlusOne = pledgedSrcSize+1; - return 0; -} - + cctx->pledgedSrcSizePlusOne = pledgedSrcSize+1; + return 0; +} + static ZSTD_compressionParameters ZSTD_dedicatedDictSearch_getCParams( int const compressionLevel, size_t const dictSize); @@ -1128,19 +1128,19 @@ static size_t ZSTD_initLocalDict(ZSTD_CCtx* cctx) return 0; } -size_t ZSTD_CCtx_loadDictionary_advanced( - ZSTD_CCtx* cctx, const void* dict, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType) -{ +size_t ZSTD_CCtx_loadDictionary_advanced( + ZSTD_CCtx* cctx, const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType) +{ RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, "Can't load a dictionary when ctx is not in init stage."); - DEBUGLOG(4, "ZSTD_CCtx_loadDictionary_advanced (size: %u)", (U32)dictSize); + DEBUGLOG(4, "ZSTD_CCtx_loadDictionary_advanced (size: %u)", (U32)dictSize); ZSTD_clearAllDicts(cctx); /* in case one already exists */ if (dict == NULL || dictSize == 0) /* no dictionary mode */ return 0; if (dictLoadMethod == ZSTD_dlm_byRef) { cctx->localDict.dict = dict; - } else { + } else { void* dictBuffer; RETURN_ERROR_IF(cctx->staticSize, memory_allocation, "no malloc for static CCtx"); @@ -1149,36 +1149,36 @@ size_t ZSTD_CCtx_loadDictionary_advanced( ZSTD_memcpy(dictBuffer, dict, dictSize); cctx->localDict.dictBuffer = dictBuffer; cctx->localDict.dict = dictBuffer; - } + } cctx->localDict.dictSize = dictSize; cctx->localDict.dictContentType = dictContentType; - return 0; -} - + return 0; +} + size_t ZSTD_CCtx_loadDictionary_byReference( - ZSTD_CCtx* cctx, const void* dict, size_t dictSize) -{ - return ZSTD_CCtx_loadDictionary_advanced( - cctx, dict, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto); -} - + ZSTD_CCtx* cctx, const void* dict, size_t dictSize) +{ + return ZSTD_CCtx_loadDictionary_advanced( + cctx, dict, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto); +} + size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize) -{ - return ZSTD_CCtx_loadDictionary_advanced( - cctx, dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto); -} - - -size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict) -{ +{ + return ZSTD_CCtx_loadDictionary_advanced( + cctx, dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto); +} + + +size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict) +{ RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, "Can't ref a dict when ctx not in init stage."); /* Free the existing local cdict (if any) to save memory. */ ZSTD_clearAllDicts(cctx); - cctx->cdict = cdict; - return 0; -} - + cctx->cdict = cdict; + return 0; +} + size_t ZSTD_CCtx_refThreadPool(ZSTD_CCtx* cctx, ZSTD_threadPool* pool) { RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, @@ -1187,14 +1187,14 @@ size_t ZSTD_CCtx_refThreadPool(ZSTD_CCtx* cctx, ZSTD_threadPool* pool) return 0; } -size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize) -{ - return ZSTD_CCtx_refPrefix_advanced(cctx, prefix, prefixSize, ZSTD_dct_rawContent); -} - -size_t ZSTD_CCtx_refPrefix_advanced( - ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType) -{ +size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize) +{ + return ZSTD_CCtx_refPrefix_advanced(cctx, prefix, prefixSize, ZSTD_dct_rawContent); +} + +size_t ZSTD_CCtx_refPrefix_advanced( + ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType) +{ RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, "Can't ref a prefix when ctx not in init stage."); ZSTD_clearAllDicts(cctx); @@ -1203,13 +1203,13 @@ size_t ZSTD_CCtx_refPrefix_advanced( cctx->prefixDict.dictSize = prefixSize; cctx->prefixDict.dictContentType = dictContentType; } - return 0; -} - -/*! ZSTD_CCtx_reset() : - * Also dumps dictionary */ + return 0; +} + +/*! ZSTD_CCtx_reset() : + * Also dumps dictionary */ size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset) -{ +{ if ( (reset == ZSTD_reset_session_only) || (reset == ZSTD_reset_session_and_parameters) ) { cctx->streamStage = zcss_init; @@ -1223,11 +1223,11 @@ size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset) return ZSTD_CCtxParams_reset(&cctx->requestedParams); } return 0; -} - +} + -/** ZSTD_checkCParams() : - control CParam values remain within authorized range. +/** ZSTD_checkCParams() : + control CParam values remain within authorized range. @return : 0, or an error code if one value is beyond authorized range */ size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams) { @@ -1241,17 +1241,17 @@ size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams) return 0; } -/** ZSTD_clampCParams() : - * make CParam values within valid range. - * @return : valid CParams */ +/** ZSTD_clampCParams() : + * make CParam values within valid range. + * @return : valid CParams */ static ZSTD_compressionParameters ZSTD_clampCParams(ZSTD_compressionParameters cParams) -{ +{ # define CLAMP_TYPE(cParam, val, type) { \ ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam); \ if ((int)val<bounds.lowerBound) val=(type)bounds.lowerBound; \ else if ((int)val>bounds.upperBound) val=(type)bounds.upperBound; \ - } + } # define CLAMP(cParam, val) CLAMP_TYPE(cParam, val, unsigned) CLAMP(ZSTD_c_windowLog, cParams.windowLog); CLAMP(ZSTD_c_chainLog, cParams.chainLog); @@ -1260,8 +1260,8 @@ ZSTD_clampCParams(ZSTD_compressionParameters cParams) CLAMP(ZSTD_c_minMatch, cParams.minMatch); CLAMP(ZSTD_c_targetLength,cParams.targetLength); CLAMP_TYPE(ZSTD_c_strategy,cParams.strategy, ZSTD_strategy); - return cParams; -} + return cParams; +} /** ZSTD_cycleLog() : * condition for correct operation : hashLog > 1 */ @@ -1305,7 +1305,7 @@ static U32 ZSTD_dictAndWindowLog(U32 windowLog, U64 srcSize, U64 dictSize) } } -/** ZSTD_adjustCParams_internal() : +/** ZSTD_adjustCParams_internal() : * optimize `cPar` for a specified input (`srcSize` and `dictSize`). * mostly downsize to reduce memory consumption and initialization latency. * `srcSize` can be ZSTD_CONTENTSIZE_UNKNOWN when not known. @@ -1320,7 +1320,7 @@ ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar, { const U64 minSrcSize = 513; /* (1<<9) + 1 */ const U64 maxWindowResize = 1ULL << (ZSTD_WINDOWLOG_MAX-1); - assert(ZSTD_checkCParams(cPar)==0); + assert(ZSTD_checkCParams(cPar)==0); switch (mode) { case ZSTD_cpm_unknown: @@ -1349,15 +1349,15 @@ ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar, break; } - /* resize windowLog if input is small enough, to use less memory */ - if ( (srcSize < maxWindowResize) - && (dictSize < maxWindowResize) ) { - U32 const tSize = (U32)(srcSize + dictSize); - static U32 const hashSizeMin = 1 << ZSTD_HASHLOG_MIN; - U32 const srcLog = (tSize < hashSizeMin) ? ZSTD_HASHLOG_MIN : - ZSTD_highbit32(tSize-1) + 1; - if (cPar.windowLog > srcLog) cPar.windowLog = srcLog; - } + /* resize windowLog if input is small enough, to use less memory */ + if ( (srcSize < maxWindowResize) + && (dictSize < maxWindowResize) ) { + U32 const tSize = (U32)(srcSize + dictSize); + static U32 const hashSizeMin = 1 << ZSTD_HASHLOG_MIN; + U32 const srcLog = (tSize < hashSizeMin) ? ZSTD_HASHLOG_MIN : + ZSTD_highbit32(tSize-1) + 1; + if (cPar.windowLog > srcLog) cPar.windowLog = srcLog; + } if (srcSize != ZSTD_CONTENTSIZE_UNKNOWN) { U32 const dictAndWindowLog = ZSTD_dictAndWindowLog(cPar.windowLog, (U64)srcSize, (U64)dictSize); U32 const cycleLog = ZSTD_cycleLog(cPar.chainLog, cPar.strategy); @@ -1366,7 +1366,7 @@ ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar, cPar.chainLog -= (cycleLog - dictAndWindowLog); } - if (cPar.windowLog < ZSTD_WINDOWLOG_ABSOLUTEMIN) + if (cPar.windowLog < ZSTD_WINDOWLOG_ABSOLUTEMIN) cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN; /* minimum wlog required for valid frame header */ return cPar; @@ -1376,12 +1376,12 @@ ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize) -{ +{ cPar = ZSTD_clampCParams(cPar); /* resulting cPar is necessarily valid (all parameters within range) */ if (srcSize == 0) srcSize = ZSTD_CONTENTSIZE_UNKNOWN; return ZSTD_adjustCParams_internal(cPar, srcSize, dictSize, ZSTD_cpm_unknown); -} - +} + static ZSTD_compressionParameters ZSTD_getCParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode); static ZSTD_parameters ZSTD_getParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode); @@ -1400,7 +1400,7 @@ static void ZSTD_overrideCParams( ZSTD_compressionParameters ZSTD_getCParamsFromCCtxParams( const ZSTD_CCtx_params* CCtxParams, U64 srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode) -{ +{ ZSTD_compressionParameters cParams; if (srcSizeHint == ZSTD_CONTENTSIZE_UNKNOWN && CCtxParams->srcSizeHint > 0) { srcSizeHint = CCtxParams->srcSizeHint; @@ -1423,7 +1423,7 @@ ZSTD_sizeof_matchState(const ZSTD_compressionParameters* const cParams, size_t const chainSize = ZSTD_allocateChainTable(cParams->strategy, useRowMatchFinder, enableDedicatedDictSearch && !forCCtx) ? ((size_t)1 << cParams->chainLog) : 0; - size_t const hSize = ((size_t)1) << cParams->hashLog; + size_t const hSize = ((size_t)1) << cParams->hashLog; U32 const hashLog3 = (forCCtx && cParams->minMatch==3) ? MIN(ZSTD_HASHLOG3_MAX, cParams->windowLog) : 0; size_t const h3Size = hashLog3 ? ((size_t)1) << hashLog3 : 0; /* We don't use ZSTD_cwksp_alloc_size() here because the tables aren't @@ -1442,18 +1442,18 @@ ZSTD_sizeof_matchState(const ZSTD_compressionParameters* const cParams, ? ZSTD_cwksp_aligned_alloc_size(hSize*sizeof(U16)) : 0; size_t const optSpace = (forCCtx && (cParams->strategy >= ZSTD_btopt)) - ? optPotentialSpace - : 0; + ? optPotentialSpace + : 0; size_t const slackSpace = ZSTD_cwksp_slack_space_required(); /* tables are guaranteed to be sized in multiples of 64 bytes (or 16 uint32_t) */ ZSTD_STATIC_ASSERT(ZSTD_HASHLOG_MIN >= 4 && ZSTD_WINDOWLOG_MIN >= 4 && ZSTD_CHAINLOG_MIN >= 4); assert(useRowMatchFinder != ZSTD_ps_auto); - DEBUGLOG(4, "chainSize: %u - hSize: %u - h3Size: %u", - (U32)chainSize, (U32)hSize, (U32)h3Size); + DEBUGLOG(4, "chainSize: %u - hSize: %u - h3Size: %u", + (U32)chainSize, (U32)hSize, (U32)h3Size); return tableSpace + optSpace + slackSpace + lazyAdditionalSpace; -} +} static size_t ZSTD_estimateCCtxSize_usingCCtxParams_internal( const ZSTD_compressionParameters* cParams, @@ -1463,7 +1463,7 @@ static size_t ZSTD_estimateCCtxSize_usingCCtxParams_internal( const size_t buffInSize, const size_t buffOutSize, const U64 pledgedSrcSize) -{ +{ size_t const windowSize = (size_t) BOUNDED(1ULL, 1ULL << cParams->windowLog, pledgedSrcSize); size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, windowSize); U32 const divider = (cParams->minMatch==3) ? 3 : 4; @@ -1479,11 +1479,11 @@ static size_t ZSTD_estimateCCtxSize_usingCCtxParams_internal( size_t const maxNbLdmSeq = ZSTD_ldm_getMaxNbSeq(*ldmParams, blockSize); size_t const ldmSeqSpace = ldmParams->enableLdm == ZSTD_ps_enable ? ZSTD_cwksp_aligned_alloc_size(maxNbLdmSeq * sizeof(rawSeq)) : 0; - + size_t const bufferSpace = ZSTD_cwksp_alloc_size(buffInSize) + ZSTD_cwksp_alloc_size(buffOutSize); - + size_t const cctxSpace = isStatic ? ZSTD_cwksp_alloc_size(sizeof(ZSTD_CCtx)) : 0; size_t const neededSpace = @@ -1515,8 +1515,8 @@ size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params) &cParams, ¶ms->ldmParams, 1, useRowMatchFinder, 0, 0, ZSTD_CONTENTSIZE_UNKNOWN); } -size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams) -{ +size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams) +{ ZSTD_CCtx_params initialParams = ZSTD_makeCCtxParamsFromCParams(cParams); if (ZSTD_rowMatchFinderSupported(cParams.strategy)) { /* Pick bigger of not using and using row-based matchfinder for greedy and lazy strategies */ @@ -1530,9 +1530,9 @@ size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams) } else { return ZSTD_estimateCCtxSize_usingCCtxParams(&initialParams); } -} +} -static size_t ZSTD_estimateCCtxSize_internal(int compressionLevel) +static size_t ZSTD_estimateCCtxSize_internal(int compressionLevel) { int tier = 0; size_t largestSize = 0; @@ -1545,20 +1545,20 @@ static size_t ZSTD_estimateCCtxSize_internal(int compressionLevel) return largestSize; } -size_t ZSTD_estimateCCtxSize(int compressionLevel) -{ - int level; - size_t memBudget = 0; +size_t ZSTD_estimateCCtxSize(int compressionLevel) +{ + int level; + size_t memBudget = 0; for (level=MIN(compressionLevel, 1); level<=compressionLevel; level++) { /* Ensure monotonically increasing memory usage as compression level increases */ - size_t const newMB = ZSTD_estimateCCtxSize_internal(level); - if (newMB > memBudget) memBudget = newMB; - } - return memBudget; -} - -size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params) -{ + size_t const newMB = ZSTD_estimateCCtxSize_internal(level); + if (newMB > memBudget) memBudget = newMB; + } + return memBudget; +} + +size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params) +{ RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only."); { ZSTD_compressionParameters const cParams = ZSTD_getCParamsFromCCtxParams(params, ZSTD_CONTENTSIZE_UNKNOWN, 0, ZSTD_cpm_noAttachDict); @@ -1570,15 +1570,15 @@ size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params) ? ZSTD_compressBound(blockSize) + 1 : 0; ZSTD_paramSwitch_e const useRowMatchFinder = ZSTD_resolveRowMatchFinderMode(params->useRowMatchFinder, ¶ms->cParams); - + return ZSTD_estimateCCtxSize_usingCCtxParams_internal( &cParams, ¶ms->ldmParams, 1, useRowMatchFinder, inBuffSize, outBuffSize, ZSTD_CONTENTSIZE_UNKNOWN); - } -} - -size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams) -{ + } +} + +size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams) +{ ZSTD_CCtx_params initialParams = ZSTD_makeCCtxParamsFromCParams(cParams); if (ZSTD_rowMatchFinderSupported(cParams.strategy)) { /* Pick bigger of not using and using row-based matchfinder for greedy and lazy strategies */ @@ -1592,50 +1592,50 @@ size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams) } else { return ZSTD_estimateCStreamSize_usingCCtxParams(&initialParams); } -} - +} + static size_t ZSTD_estimateCStreamSize_internal(int compressionLevel) { ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, 0, ZSTD_cpm_noAttachDict); - return ZSTD_estimateCStreamSize_usingCParams(cParams); -} - + return ZSTD_estimateCStreamSize_usingCParams(cParams); +} + size_t ZSTD_estimateCStreamSize(int compressionLevel) { - int level; - size_t memBudget = 0; + int level; + size_t memBudget = 0; for (level=MIN(compressionLevel, 1); level<=compressionLevel; level++) { - size_t const newMB = ZSTD_estimateCStreamSize_internal(level); - if (newMB > memBudget) memBudget = newMB; - } - return memBudget; -} - -/* ZSTD_getFrameProgression(): - * tells how much data has been consumed (input) and produced (output) for current frame. - * able to count progression inside worker threads (non-blocking mode). - */ -ZSTD_frameProgression ZSTD_getFrameProgression(const ZSTD_CCtx* cctx) -{ -#ifdef ZSTD_MULTITHREAD - if (cctx->appliedParams.nbWorkers > 0) { - return ZSTDMT_getFrameProgression(cctx->mtctx); - } -#endif - { ZSTD_frameProgression fp; - size_t const buffered = (cctx->inBuff == NULL) ? 0 : - cctx->inBuffPos - cctx->inToCompress; - if (buffered) assert(cctx->inBuffPos >= cctx->inToCompress); - assert(buffered <= ZSTD_BLOCKSIZE_MAX); - fp.ingested = cctx->consumedSrcSize + buffered; - fp.consumed = cctx->consumedSrcSize; - fp.produced = cctx->producedCSize; + size_t const newMB = ZSTD_estimateCStreamSize_internal(level); + if (newMB > memBudget) memBudget = newMB; + } + return memBudget; +} + +/* ZSTD_getFrameProgression(): + * tells how much data has been consumed (input) and produced (output) for current frame. + * able to count progression inside worker threads (non-blocking mode). + */ +ZSTD_frameProgression ZSTD_getFrameProgression(const ZSTD_CCtx* cctx) +{ +#ifdef ZSTD_MULTITHREAD + if (cctx->appliedParams.nbWorkers > 0) { + return ZSTDMT_getFrameProgression(cctx->mtctx); + } +#endif + { ZSTD_frameProgression fp; + size_t const buffered = (cctx->inBuff == NULL) ? 0 : + cctx->inBuffPos - cctx->inToCompress; + if (buffered) assert(cctx->inBuffPos >= cctx->inToCompress); + assert(buffered <= ZSTD_BLOCKSIZE_MAX); + fp.ingested = cctx->consumedSrcSize + buffered; + fp.consumed = cctx->consumedSrcSize; + fp.produced = cctx->producedCSize; fp.flushed = cctx->producedCSize; /* simplified; some data might still be left within streaming output buffer */ fp.currentJobID = 0; fp.nbActiveWorkers = 0; - return fp; -} } - + return fp; +} } + /*! ZSTD_toFlushNow() * Only useful for multithreading scenarios currently (nbWorkers >= 1). */ @@ -1649,7 +1649,7 @@ size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx) (void)cctx; return 0; /* over-simplification; could also check if context is currently running in streaming mode, and in which case, report how many bytes are left to be flushed within output buffer */ } - + static void ZSTD_assertEqualCParams(ZSTD_compressionParameters cParams1, ZSTD_compressionParameters cParams2) { @@ -1665,30 +1665,30 @@ static void ZSTD_assertEqualCParams(ZSTD_compressionParameters cParams1, } void ZSTD_reset_compressedBlockState(ZSTD_compressedBlockState_t* bs) -{ - int i; - for (i = 0; i < ZSTD_REP_NUM; ++i) - bs->rep[i] = repStartValue[i]; +{ + int i; + for (i = 0; i < ZSTD_REP_NUM; ++i) + bs->rep[i] = repStartValue[i]; bs->entropy.huf.repeatMode = HUF_repeat_none; bs->entropy.fse.offcode_repeatMode = FSE_repeat_none; bs->entropy.fse.matchlength_repeatMode = FSE_repeat_none; bs->entropy.fse.litlength_repeatMode = FSE_repeat_none; -} - -/*! ZSTD_invalidateMatchState() +} + +/*! ZSTD_invalidateMatchState() * Invalidate all the matches in the match finder tables. * Requires nextSrc and base to be set (can be NULL). - */ -static void ZSTD_invalidateMatchState(ZSTD_matchState_t* ms) -{ - ZSTD_window_clear(&ms->window); - + */ +static void ZSTD_invalidateMatchState(ZSTD_matchState_t* ms) +{ + ZSTD_window_clear(&ms->window); + ms->nextToUpdate = ms->window.dictLimit; - ms->loadedDictEnd = 0; - ms->opt.litLengthSum = 0; /* force reset of btopt stats */ + ms->loadedDictEnd = 0; + ms->opt.litLengthSum = 0; /* force reset of btopt stats */ ms->dictMatchState = NULL; -} - +} + /** * Controls, for this matchState reset, whether the tables need to be cleared / * prepared for the coming compression (ZSTDcrp_makeClean), or whether the @@ -1731,7 +1731,7 @@ ZSTD_reset_matchState(ZSTD_matchState_t* ms, ms->dedicatedDictSearch && (forWho == ZSTD_resetTarget_CDict)) ? ((size_t)1 << cParams->chainLog) : 0; - size_t const hSize = ((size_t)1) << cParams->hashLog; + size_t const hSize = ((size_t)1) << cParams->hashLog; U32 const hashLog3 = ((forWho == ZSTD_resetTarget_CCtx) && cParams->minMatch==3) ? MIN(ZSTD_HASHLOG3_MAX, cParams->windowLog) : 0; size_t const h3Size = hashLog3 ? ((size_t)1) << hashLog3 : 0; @@ -1741,11 +1741,11 @@ ZSTD_reset_matchState(ZSTD_matchState_t* ms, ZSTD_window_init(&ms->window); ZSTD_cwksp_mark_tables_dirty(ws); } + + ms->hashLog3 = hashLog3; - ms->hashLog3 = hashLog3; - - ZSTD_invalidateMatchState(ms); - + ZSTD_invalidateMatchState(ms); + assert(!ZSTD_cwksp_reserve_failed(ws)); /* check that allocation hasn't already failed */ ZSTD_cwksp_clear_tables(ws); @@ -1764,17 +1764,17 @@ ZSTD_reset_matchState(ZSTD_matchState_t* ms, ZSTD_cwksp_clean_tables(ws); } - /* opt parser space */ + /* opt parser space */ if ((forWho == ZSTD_resetTarget_CCtx) && (cParams->strategy >= ZSTD_btopt)) { - DEBUGLOG(4, "reserving optimal parser space"); + DEBUGLOG(4, "reserving optimal parser space"); ms->opt.litFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (1<<Litbits) * sizeof(unsigned)); ms->opt.litLengthFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (MaxLL+1) * sizeof(unsigned)); ms->opt.matchLengthFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (MaxML+1) * sizeof(unsigned)); ms->opt.offCodeFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (MaxOff+1) * sizeof(unsigned)); ms->opt.matchTable = (ZSTD_match_t*)ZSTD_cwksp_reserve_aligned(ws, (ZSTD_OPT_NUM+1) * sizeof(ZSTD_match_t)); ms->opt.priceTable = (ZSTD_optimal_t*)ZSTD_cwksp_reserve_aligned(ws, (ZSTD_OPT_NUM+1) * sizeof(ZSTD_optimal_t)); - } - + } + if (ZSTD_rowMatchFinderUsed(cParams->strategy, useRowMatchFinder)) { { /* Row match finder needs an additional table of hashes ("tags") */ size_t const tagTableSize = hSize*sizeof(U16); @@ -1793,8 +1793,8 @@ ZSTD_reset_matchState(ZSTD_matchState_t* ms, RETURN_ERROR_IF(ZSTD_cwksp_reserve_failed(ws), memory_allocation, "failed a workspace allocation in ZSTD_reset_matchState"); return 0; -} - +} + /* ZSTD_indexTooCloseToMax() : * minor optimization : prefer memset() rather than reduceIndex() * which is measurably slow in some circumstances (reported for Visual Studio). @@ -1818,26 +1818,26 @@ static int ZSTD_dictTooBig(size_t const loadedDictSize) return loadedDictSize > ZSTD_CHUNKSIZE_MAX; } -/*! ZSTD_resetCCtx_internal() : +/*! ZSTD_resetCCtx_internal() : * @param loadedDictSize The size of the dictionary to be loaded * into the context, if any. If no dictionary is used, or the * dictionary is being attached / copied, then pass 0. * note : `params` are assumed fully validated at this stage. */ -static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc, +static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc, ZSTD_CCtx_params const* params, U64 const pledgedSrcSize, size_t const loadedDictSize, - ZSTD_compResetPolicy_e const crp, - ZSTD_buffered_policy_e const zbuff) -{ + ZSTD_compResetPolicy_e const crp, + ZSTD_buffered_policy_e const zbuff) +{ ZSTD_cwksp* const ws = &zc->workspace; DEBUGLOG(4, "ZSTD_resetCCtx_internal: pledgedSrcSize=%u, wlog=%u, useRowMatchFinder=%d useBlockSplitter=%d", (U32)pledgedSrcSize, params->cParams.windowLog, (int)params->useRowMatchFinder, (int)params->useBlockSplitter); assert(!ZSTD_isError(ZSTD_checkCParams(params->cParams))); - + zc->isFirstBlock = 1; - + /* Set applied params early so we can modify them for LDM, * and point params at the applied params. */ @@ -1848,14 +1848,14 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc, assert(params->useBlockSplitter != ZSTD_ps_auto); assert(params->ldmParams.enableLdm != ZSTD_ps_auto); if (params->ldmParams.enableLdm == ZSTD_ps_enable) { - /* Adjust long distance matching parameters */ + /* Adjust long distance matching parameters */ ZSTD_ldm_adjustParameters(&zc->appliedParams.ldmParams, ¶ms->cParams); assert(params->ldmParams.hashLog >= params->ldmParams.bucketSizeLog); assert(params->ldmParams.hashRateLog < 32); - } - + } + { size_t const windowSize = MAX(1, (size_t)MIN(((U64)1 << params->cParams.windowLog), pledgedSrcSize)); - size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, windowSize); + size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, windowSize); U32 const divider = (params->cParams.minMatch==3) ? 3 : 4; size_t const maxNbSeq = blockSize / divider; size_t const buffOutSize = (zbuff == ZSTDb_buffered && params->outBufferMode == ZSTD_bm_buffered) @@ -1896,7 +1896,7 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc, RETURN_ERROR_IF(zc->staticSize, memory_allocation, "static cctx : no resize"); needsIndexReset = ZSTDirp_reset; - + ZSTD_cwksp_free(ws, zc->customMem); FORWARD_IF_ERROR(ZSTD_cwksp_create(ws, neededSpace, zc->customMem), ""); @@ -1915,23 +1915,23 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc, ZSTD_cwksp_clear(ws); - /* init params */ + /* init params */ zc->blockState.matchState.cParams = params->cParams; - zc->pledgedSrcSizePlusOne = pledgedSrcSize+1; - zc->consumedSrcSize = 0; - zc->producedCSize = 0; - if (pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN) - zc->appliedParams.fParams.contentSizeFlag = 0; - DEBUGLOG(4, "pledged content size : %u ; flag : %u", + zc->pledgedSrcSizePlusOne = pledgedSrcSize+1; + zc->consumedSrcSize = 0; + zc->producedCSize = 0; + if (pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN) + zc->appliedParams.fParams.contentSizeFlag = 0; + DEBUGLOG(4, "pledged content size : %u ; flag : %u", (unsigned)pledgedSrcSize, zc->appliedParams.fParams.contentSizeFlag); - zc->blockSize = blockSize; - + zc->blockSize = blockSize; + XXH64_reset(&zc->xxhState, 0); - zc->stage = ZSTDcs_init; - zc->dictID = 0; + zc->stage = ZSTDcs_init; + zc->dictID = 0; zc->dictContentSize = 0; - ZSTD_reset_compressedBlockState(zc->blockState.prevCBlock); + ZSTD_reset_compressedBlockState(zc->blockState.prevCBlock); /* ZSTD_wildcopy() is used to copy into the literals buffer, * so we have to oversize the buffer by WILDCOPY_OVERLENGTH bytes. @@ -1946,7 +1946,7 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc, zc->outBuffSize = buffOutSize; zc->outBuff = (char*)ZSTD_cwksp_reserve_buffer(ws, buffOutSize); - /* ldm bucketOffsets table */ + /* ldm bucketOffsets table */ if (params->ldmParams.enableLdm == ZSTD_ps_enable) { /* TODO: avoid memset? */ size_t const numBuckets = @@ -1954,10 +1954,10 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc, params->ldmParams.bucketSizeLog); zc->ldmState.bucketOffsets = ZSTD_cwksp_reserve_buffer(ws, numBuckets); ZSTD_memset(zc->ldmState.bucketOffsets, 0, numBuckets); - } + } /* sequences storage */ - ZSTD_referenceExternalSequences(zc, NULL, 0); + ZSTD_referenceExternalSequences(zc, NULL, 0); zc->seqStore.maxNbSeq = maxNbSeq; zc->seqStore.llCode = ZSTD_cwksp_reserve_buffer(ws, maxNbSeq * sizeof(BYTE)); zc->seqStore.mlCode = ZSTD_cwksp_reserve_buffer(ws, maxNbSeq * sizeof(BYTE)); @@ -1972,7 +1972,7 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc, crp, needsIndexReset, ZSTD_resetTarget_CCtx), ""); - + /* ldm hash table */ if (params->ldmParams.enableLdm == ZSTD_ps_enable) { /* TODO: avoid memset? */ @@ -1995,15 +1995,15 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc, } } -/* ZSTD_invalidateRepCodes() : - * ensures next compression will not use repcodes from previous block. - * Note : only works with regular variant; - * do not use with extDict variant ! */ -void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx) { - int i; - for (i=0; i<ZSTD_REP_NUM; i++) cctx->blockState.prevCBlock->rep[i] = 0; - assert(!ZSTD_window_hasExtDict(cctx->blockState.matchState.window)); -} +/* ZSTD_invalidateRepCodes() : + * ensures next compression will not use repcodes from previous block. + * Note : only works with regular variant; + * do not use with extDict variant ! */ +void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx) { + int i; + for (i=0; i<ZSTD_REP_NUM; i++) cctx->blockState.prevCBlock->rep[i] = 0; + assert(!ZSTD_window_hasExtDict(cctx->blockState.matchState.window)); +} /* These are the approximate sizes for each strategy past which copying the * dictionary tables into the working context is faster than using them @@ -2099,10 +2099,10 @@ ZSTD_resetCCtx_byAttachingCDict(ZSTD_CCtx* cctx, } static size_t ZSTD_resetCCtx_byCopyingCDict(ZSTD_CCtx* cctx, - const ZSTD_CDict* cdict, + const ZSTD_CDict* cdict, ZSTD_CCtx_params params, - U64 pledgedSrcSize, - ZSTD_buffered_policy_e zbuff) + U64 pledgedSrcSize, + ZSTD_buffered_policy_e zbuff) { const ZSTD_compressionParameters *cdict_cParams = &cdict->matchState.cParams; @@ -2112,7 +2112,7 @@ static size_t ZSTD_resetCCtx_byCopyingCDict(ZSTD_CCtx* cctx, { unsigned const windowLog = params.cParams.windowLog; assert(windowLog != 0); - /* Copy only compression parameters related to tables. */ + /* Copy only compression parameters related to tables. */ params.cParams = *cdict_cParams; params.cParams.windowLog = windowLog; params.useRowMatchFinder = cdict->useRowMatchFinder; @@ -2122,12 +2122,12 @@ static size_t ZSTD_resetCCtx_byCopyingCDict(ZSTD_CCtx* cctx, assert(cctx->appliedParams.cParams.strategy == cdict_cParams->strategy); assert(cctx->appliedParams.cParams.hashLog == cdict_cParams->hashLog); assert(cctx->appliedParams.cParams.chainLog == cdict_cParams->chainLog); - } - + } + ZSTD_cwksp_mark_tables_dirty(&cctx->workspace); assert(params.useRowMatchFinder != ZSTD_ps_auto); - /* copy tables */ + /* copy tables */ { size_t const chainSize = ZSTD_allocateChainTable(cdict_cParams->strategy, cdict->useRowMatchFinder, 0 /* DDS guaranteed disabled */) ? ((size_t)1 << cdict_cParams->chainLog) : 0; @@ -2149,34 +2149,34 @@ static size_t ZSTD_resetCCtx_byCopyingCDict(ZSTD_CCtx* cctx, cdict->matchState.tagTable, tagTableSize); } - } + } - /* Zero the hashTable3, since the cdict never fills it */ + /* Zero the hashTable3, since the cdict never fills it */ { int const h3log = cctx->blockState.matchState.hashLog3; size_t const h3Size = h3log ? ((size_t)1 << h3log) : 0; - assert(cdict->matchState.hashLog3 == 0); + assert(cdict->matchState.hashLog3 == 0); ZSTD_memset(cctx->blockState.matchState.hashTable3, 0, h3Size * sizeof(U32)); - } - + } + ZSTD_cwksp_mark_tables_clean(&cctx->workspace); - /* copy dictionary offsets */ + /* copy dictionary offsets */ { ZSTD_matchState_t const* srcMatchState = &cdict->matchState; - ZSTD_matchState_t* dstMatchState = &cctx->blockState.matchState; - dstMatchState->window = srcMatchState->window; - dstMatchState->nextToUpdate = srcMatchState->nextToUpdate; - dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd; - } + ZSTD_matchState_t* dstMatchState = &cctx->blockState.matchState; + dstMatchState->window = srcMatchState->window; + dstMatchState->nextToUpdate = srcMatchState->nextToUpdate; + dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd; + } - cctx->dictID = cdict->dictID; + cctx->dictID = cdict->dictID; cctx->dictContentSize = cdict->dictContentSize; - - /* copy block state */ + + /* copy block state */ ZSTD_memcpy(cctx->blockState.prevCBlock, &cdict->cBlockState, sizeof(cdict->cBlockState)); - - return 0; -} - + + return 0; +} + /* We have a choice between copying the dictionary context into the working * context, or referencing the dictionary context from the working context * in-place. We decide here which strategy to use. */ @@ -2199,42 +2199,42 @@ static size_t ZSTD_resetCCtx_usingCDict(ZSTD_CCtx* cctx, } } -/*! ZSTD_copyCCtx_internal() : - * Duplicate an existing context `srcCCtx` into another one `dstCCtx`. - * Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()). - * The "context", in this case, refers to the hash and chain tables, - * entropy tables, and dictionary references. - * `windowLog` value is enforced if != 0, otherwise value is copied from srcCCtx. - * @return : 0, or an error code */ -static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx, - const ZSTD_CCtx* srcCCtx, - ZSTD_frameParameters fParams, - U64 pledgedSrcSize, - ZSTD_buffered_policy_e zbuff) -{ +/*! ZSTD_copyCCtx_internal() : + * Duplicate an existing context `srcCCtx` into another one `dstCCtx`. + * Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()). + * The "context", in this case, refers to the hash and chain tables, + * entropy tables, and dictionary references. + * `windowLog` value is enforced if != 0, otherwise value is copied from srcCCtx. + * @return : 0, or an error code */ +static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx, + const ZSTD_CCtx* srcCCtx, + ZSTD_frameParameters fParams, + U64 pledgedSrcSize, + ZSTD_buffered_policy_e zbuff) +{ RETURN_ERROR_IF(srcCCtx->stage!=ZSTDcs_init, stage_wrong, "Can't copy a ctx that's not in init stage."); DEBUGLOG(5, "ZSTD_copyCCtx_internal"); ZSTD_memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem)); - { ZSTD_CCtx_params params = dstCCtx->requestedParams; - /* Copy only compression parameters related to tables. */ - params.cParams = srcCCtx->appliedParams.cParams; + { ZSTD_CCtx_params params = dstCCtx->requestedParams; + /* Copy only compression parameters related to tables. */ + params.cParams = srcCCtx->appliedParams.cParams; assert(srcCCtx->appliedParams.useRowMatchFinder != ZSTD_ps_auto); assert(srcCCtx->appliedParams.useBlockSplitter != ZSTD_ps_auto); assert(srcCCtx->appliedParams.ldmParams.enableLdm != ZSTD_ps_auto); params.useRowMatchFinder = srcCCtx->appliedParams.useRowMatchFinder; params.useBlockSplitter = srcCCtx->appliedParams.useBlockSplitter; params.ldmParams = srcCCtx->appliedParams.ldmParams; - params.fParams = fParams; + params.fParams = fParams; ZSTD_resetCCtx_internal(dstCCtx, ¶ms, pledgedSrcSize, /* loadedDictSize */ 0, ZSTDcrp_leaveDirty, zbuff); - assert(dstCCtx->appliedParams.cParams.windowLog == srcCCtx->appliedParams.cParams.windowLog); - assert(dstCCtx->appliedParams.cParams.strategy == srcCCtx->appliedParams.cParams.strategy); - assert(dstCCtx->appliedParams.cParams.hashLog == srcCCtx->appliedParams.cParams.hashLog); - assert(dstCCtx->appliedParams.cParams.chainLog == srcCCtx->appliedParams.cParams.chainLog); - assert(dstCCtx->blockState.matchState.hashLog3 == srcCCtx->blockState.matchState.hashLog3); - } + assert(dstCCtx->appliedParams.cParams.windowLog == srcCCtx->appliedParams.cParams.windowLog); + assert(dstCCtx->appliedParams.cParams.strategy == srcCCtx->appliedParams.cParams.strategy); + assert(dstCCtx->appliedParams.cParams.hashLog == srcCCtx->appliedParams.cParams.hashLog); + assert(dstCCtx->appliedParams.cParams.chainLog == srcCCtx->appliedParams.cParams.chainLog); + assert(dstCCtx->blockState.matchState.hashLog3 == srcCCtx->blockState.matchState.hashLog3); + } ZSTD_cwksp_mark_tables_dirty(&dstCCtx->workspace); @@ -2244,7 +2244,7 @@ static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx, 0 /* forDDSDict */) ? ((size_t)1 << srcCCtx->appliedParams.cParams.chainLog) : 0; - size_t const hSize = (size_t)1 << srcCCtx->appliedParams.cParams.hashLog; + size_t const hSize = (size_t)1 << srcCCtx->appliedParams.cParams.hashLog; int const h3log = srcCCtx->blockState.matchState.hashLog3; size_t const h3Size = h3log ? ((size_t)1 << h3log) : 0; @@ -2262,58 +2262,58 @@ static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx, ZSTD_cwksp_mark_tables_clean(&dstCCtx->workspace); /* copy dictionary offsets */ - { + { const ZSTD_matchState_t* srcMatchState = &srcCCtx->blockState.matchState; - ZSTD_matchState_t* dstMatchState = &dstCCtx->blockState.matchState; - dstMatchState->window = srcMatchState->window; - dstMatchState->nextToUpdate = srcMatchState->nextToUpdate; - dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd; + ZSTD_matchState_t* dstMatchState = &dstCCtx->blockState.matchState; + dstMatchState->window = srcMatchState->window; + dstMatchState->nextToUpdate = srcMatchState->nextToUpdate; + dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd; } - dstCCtx->dictID = srcCCtx->dictID; + dstCCtx->dictID = srcCCtx->dictID; dstCCtx->dictContentSize = srcCCtx->dictContentSize; - /* copy block state */ + /* copy block state */ ZSTD_memcpy(dstCCtx->blockState.prevCBlock, srcCCtx->blockState.prevCBlock, sizeof(*srcCCtx->blockState.prevCBlock)); - + return 0; } -/*! ZSTD_copyCCtx() : - * Duplicate an existing context `srcCCtx` into another one `dstCCtx`. - * Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()). - * pledgedSrcSize==0 means "unknown". -* @return : 0, or an error code */ -size_t ZSTD_copyCCtx(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx, unsigned long long pledgedSrcSize) -{ - ZSTD_frameParameters fParams = { 1 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ }; +/*! ZSTD_copyCCtx() : + * Duplicate an existing context `srcCCtx` into another one `dstCCtx`. + * Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()). + * pledgedSrcSize==0 means "unknown". +* @return : 0, or an error code */ +size_t ZSTD_copyCCtx(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx, unsigned long long pledgedSrcSize) +{ + ZSTD_frameParameters fParams = { 1 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ }; ZSTD_buffered_policy_e const zbuff = srcCCtx->bufferedPolicy; - ZSTD_STATIC_ASSERT((U32)ZSTDb_buffered==1); - if (pledgedSrcSize==0) pledgedSrcSize = ZSTD_CONTENTSIZE_UNKNOWN; - fParams.contentSizeFlag = (pledgedSrcSize != ZSTD_CONTENTSIZE_UNKNOWN); - - return ZSTD_copyCCtx_internal(dstCCtx, srcCCtx, - fParams, pledgedSrcSize, - zbuff); -} - - -#define ZSTD_ROWSIZE 16 + ZSTD_STATIC_ASSERT((U32)ZSTDb_buffered==1); + if (pledgedSrcSize==0) pledgedSrcSize = ZSTD_CONTENTSIZE_UNKNOWN; + fParams.contentSizeFlag = (pledgedSrcSize != ZSTD_CONTENTSIZE_UNKNOWN); + + return ZSTD_copyCCtx_internal(dstCCtx, srcCCtx, + fParams, pledgedSrcSize, + zbuff); +} + + +#define ZSTD_ROWSIZE 16 /*! ZSTD_reduceTable() : - * reduce table indexes by `reducerValue`, or squash to zero. - * PreserveMark preserves "unsorted mark" for btlazy2 strategy. - * It must be set to a clear 0/1 value, to remove branch during inlining. - * Presume table size is a multiple of ZSTD_ROWSIZE - * to help auto-vectorization */ -FORCE_INLINE_TEMPLATE void -ZSTD_reduceTable_internal (U32* const table, U32 const size, U32 const reducerValue, int const preserveMark) -{ - int const nbRows = (int)size / ZSTD_ROWSIZE; - int cellNb = 0; - int rowNb; + * reduce table indexes by `reducerValue`, or squash to zero. + * PreserveMark preserves "unsorted mark" for btlazy2 strategy. + * It must be set to a clear 0/1 value, to remove branch during inlining. + * Presume table size is a multiple of ZSTD_ROWSIZE + * to help auto-vectorization */ +FORCE_INLINE_TEMPLATE void +ZSTD_reduceTable_internal (U32* const table, U32 const size, U32 const reducerValue, int const preserveMark) +{ + int const nbRows = (int)size / ZSTD_ROWSIZE; + int cellNb = 0; + int rowNb; /* Protect special index values < ZSTD_WINDOW_START_INDEX. */ U32 const reducerThreshold = reducerValue + ZSTD_WINDOW_START_INDEX; - assert((size & (ZSTD_ROWSIZE-1)) == 0); /* multiple of ZSTD_ROWSIZE */ - assert(size < (1U<<31)); /* can be casted to int */ + assert((size & (ZSTD_ROWSIZE-1)) == 0); /* multiple of ZSTD_ROWSIZE */ + assert(size < (1U<<31)); /* can be casted to int */ #if ZSTD_MEMORY_SANITIZER && !defined (ZSTD_MSAN_DONT_POISON_WORKSPACE) /* To validate that the table re-use logic is sound, and that we don't @@ -2328,9 +2328,9 @@ ZSTD_reduceTable_internal (U32* const table, U32 const size, U32 const reducerVa __msan_unpoison(table, size * sizeof(U32)); #endif - for (rowNb=0 ; rowNb < nbRows ; rowNb++) { - int column; - for (column=0; column<ZSTD_ROWSIZE; column++) { + for (rowNb=0 ; rowNb < nbRows ; rowNb++) { + int column; + for (column=0; column<ZSTD_ROWSIZE; column++) { U32 newVal; if (preserveMark && table[cellNb] == ZSTD_DUBT_UNSORTED_MARK) { /* This write is pointless, but is required(?) for the compiler @@ -2340,42 +2340,42 @@ ZSTD_reduceTable_internal (U32* const table, U32 const size, U32 const reducerVa newVal = 0; } else { newVal = table[cellNb] - reducerValue; - } + } table[cellNb] = newVal; - cellNb++; - } } -} - -static void ZSTD_reduceTable(U32* const table, U32 const size, U32 const reducerValue) -{ - ZSTD_reduceTable_internal(table, size, reducerValue, 0); -} - -static void ZSTD_reduceTable_btlazy2(U32* const table, U32 const size, U32 const reducerValue) -{ - ZSTD_reduceTable_internal(table, size, reducerValue, 1); -} - + cellNb++; + } } +} + +static void ZSTD_reduceTable(U32* const table, U32 const size, U32 const reducerValue) +{ + ZSTD_reduceTable_internal(table, size, reducerValue, 0); +} + +static void ZSTD_reduceTable_btlazy2(U32* const table, U32 const size, U32 const reducerValue) +{ + ZSTD_reduceTable_internal(table, size, reducerValue, 1); +} + /*! ZSTD_reduceIndex() : * rescale all indexes to avoid future overflow (indexes are U32) */ static void ZSTD_reduceIndex (ZSTD_matchState_t* ms, ZSTD_CCtx_params const* params, const U32 reducerValue) { { U32 const hSize = (U32)1 << params->cParams.hashLog; - ZSTD_reduceTable(ms->hashTable, hSize, reducerValue); - } + ZSTD_reduceTable(ms->hashTable, hSize, reducerValue); + } if (ZSTD_allocateChainTable(params->cParams.strategy, params->useRowMatchFinder, (U32)ms->dedicatedDictSearch)) { U32 const chainSize = (U32)1 << params->cParams.chainLog; if (params->cParams.strategy == ZSTD_btlazy2) - ZSTD_reduceTable_btlazy2(ms->chainTable, chainSize, reducerValue); - else - ZSTD_reduceTable(ms->chainTable, chainSize, reducerValue); - } + ZSTD_reduceTable_btlazy2(ms->chainTable, chainSize, reducerValue); + else + ZSTD_reduceTable(ms->chainTable, chainSize, reducerValue); + } - if (ms->hashLog3) { - U32 const h3Size = (U32)1 << ms->hashLog3; - ZSTD_reduceTable(ms->hashTable3, h3Size, reducerValue); - } + if (ms->hashLog3) { + U32 const h3Size = (U32)1 << ms->hashLog3; + ZSTD_reduceTable(ms->hashTable3, h3Size, reducerValue); + } } @@ -2397,9 +2397,9 @@ void ZSTD_seqToCodes(const seqStore_t* seqStorePtr) for (u=0; u<nbSeq; u++) { U32 const llv = sequences[u].litLength; U32 const mlv = sequences[u].mlBase; - llCodeTable[u] = (BYTE)ZSTD_LLcode(llv); + llCodeTable[u] = (BYTE)ZSTD_LLcode(llv); ofCodeTable[u] = (BYTE)ZSTD_highbit32(sequences[u].offBase); - mlCodeTable[u] = (BYTE)ZSTD_MLcode(mlv); + mlCodeTable[u] = (BYTE)ZSTD_MLcode(mlv); } if (seqStorePtr->longLengthType==ZSTD_llt_literalLength) llCodeTable[seqStorePtr->longLengthPos] = MaxLL; @@ -2579,54 +2579,54 @@ ZSTD_entropyCompressSeqStore_internal(seqStore_t* seqStorePtr, void* entropyWorkspace, size_t entropyWkspSize, const int bmi2) { - const int longOffsets = cctxParams->cParams.windowLog > STREAM_ACCUMULATOR_MIN; + const int longOffsets = cctxParams->cParams.windowLog > STREAM_ACCUMULATOR_MIN; ZSTD_strategy const strategy = cctxParams->cParams.strategy; unsigned* count = (unsigned*)entropyWorkspace; FSE_CTable* CTable_LitLength = nextEntropy->fse.litlengthCTable; FSE_CTable* CTable_OffsetBits = nextEntropy->fse.offcodeCTable; FSE_CTable* CTable_MatchLength = nextEntropy->fse.matchlengthCTable; - const seqDef* const sequences = seqStorePtr->sequencesStart; + const seqDef* const sequences = seqStorePtr->sequencesStart; const size_t nbSeq = seqStorePtr->sequences - seqStorePtr->sequencesStart; - const BYTE* const ofCodeTable = seqStorePtr->ofCode; - const BYTE* const llCodeTable = seqStorePtr->llCode; - const BYTE* const mlCodeTable = seqStorePtr->mlCode; - BYTE* const ostart = (BYTE*)dst; - BYTE* const oend = ostart + dstCapacity; - BYTE* op = ostart; + const BYTE* const ofCodeTable = seqStorePtr->ofCode; + const BYTE* const llCodeTable = seqStorePtr->llCode; + const BYTE* const mlCodeTable = seqStorePtr->mlCode; + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + dstCapacity; + BYTE* op = ostart; size_t lastCountSize; entropyWorkspace = count + (MaxSeq + 1); entropyWkspSize -= (MaxSeq + 1) * sizeof(*count); DEBUGLOG(4, "ZSTD_entropyCompressSeqStore_internal (nbSeq=%zu)", nbSeq); - ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<<MAX(MLFSELog,LLFSELog))); + ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<<MAX(MLFSELog,LLFSELog))); assert(entropyWkspSize >= HUF_WORKSPACE_SIZE); - /* Compress literals */ - { const BYTE* const literals = seqStorePtr->litStart; + /* Compress literals */ + { const BYTE* const literals = seqStorePtr->litStart; size_t const numSequences = seqStorePtr->sequences - seqStorePtr->sequencesStart; size_t const numLiterals = seqStorePtr->lit - seqStorePtr->litStart; /* Base suspicion of uncompressibility on ratio of literals to sequences */ unsigned const suspectUncompressible = (numSequences == 0) || (numLiterals / numSequences >= SUSPECT_UNCOMPRESSIBLE_LITERAL_RATIO); size_t const litSize = (size_t)(seqStorePtr->lit - literals); - size_t const cSize = ZSTD_compressLiterals( + size_t const cSize = ZSTD_compressLiterals( &prevEntropy->huf, &nextEntropy->huf, cctxParams->cParams.strategy, ZSTD_literalsCompressionIsDisabled(cctxParams), - op, dstCapacity, - literals, litSize, + op, dstCapacity, + literals, litSize, entropyWorkspace, entropyWkspSize, bmi2, suspectUncompressible); FORWARD_IF_ERROR(cSize, "ZSTD_compressLiterals failed"); - assert(cSize <= dstCapacity); - op += cSize; - } + assert(cSize <= dstCapacity); + op += cSize; + } - /* Sequences Header */ + /* Sequences Header */ RETURN_ERROR_IF((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/, dstSize_tooSmall, "Can't fit seq hdr in output buf!"); if (nbSeq < 128) { - *op++ = (BYTE)nbSeq; + *op++ = (BYTE)nbSeq; } else if (nbSeq < LONGNBSEQ) { op[0] = (BYTE)((nbSeq>>8) + 0x80); op[1] = (BYTE)nbSeq; @@ -2637,11 +2637,11 @@ ZSTD_entropyCompressSeqStore_internal(seqStore_t* seqStorePtr, op+=3; } assert(op <= oend); - if (nbSeq==0) { + if (nbSeq==0) { /* Copy the old tables over as if we repeated them */ ZSTD_memcpy(&nextEntropy->fse, &prevEntropy->fse, sizeof(prevEntropy->fse)); return (size_t)(op - ostart); - } + } { ZSTD_symbolEncodingTypeStats_t stats; BYTE* seqHead = op++; @@ -2657,15 +2657,15 @@ ZSTD_entropyCompressSeqStore_internal(seqStore_t* seqStorePtr, op += stats.size; } - { size_t const bitstreamSize = ZSTD_encodeSequences( + { size_t const bitstreamSize = ZSTD_encodeSequences( op, (size_t)(oend - op), - CTable_MatchLength, mlCodeTable, - CTable_OffsetBits, ofCodeTable, - CTable_LitLength, llCodeTable, - sequences, nbSeq, - longOffsets, bmi2); + CTable_MatchLength, mlCodeTable, + CTable_OffsetBits, ofCodeTable, + CTable_LitLength, llCodeTable, + sequences, nbSeq, + longOffsets, bmi2); FORWARD_IF_ERROR(bitstreamSize, "ZSTD_encodeSequences failed"); - op += bitstreamSize; + op += bitstreamSize; assert(op <= oend); /* zstd versions <= 1.3.4 mistakenly report corruption when * FSE_readNCount() receives a buffer < 4 bytes. @@ -2682,12 +2682,12 @@ ZSTD_entropyCompressSeqStore_internal(seqStore_t* seqStorePtr, "emitting an uncompressed block."); return 0; } - } - + } + DEBUGLOG(5, "compressed block size : %u", (unsigned)(op - ostart)); return (size_t)(op - ostart); -} - +} + MEM_STATIC size_t ZSTD_entropyCompressSeqStore(seqStore_t* seqStorePtr, const ZSTD_entropyCTables_t* prevEntropy, @@ -2697,34 +2697,34 @@ ZSTD_entropyCompressSeqStore(seqStore_t* seqStorePtr, size_t srcSize, void* entropyWorkspace, size_t entropyWkspSize, int bmi2) -{ +{ size_t const cSize = ZSTD_entropyCompressSeqStore_internal( seqStorePtr, prevEntropy, nextEntropy, cctxParams, dst, dstCapacity, entropyWorkspace, entropyWkspSize, bmi2); if (cSize == 0) return 0; - /* When srcSize <= dstCapacity, there is enough space to write a raw uncompressed block. - * Since we ran out of space, block must be not compressible, so fall back to raw uncompressed block. - */ - if ((cSize == ERROR(dstSize_tooSmall)) & (srcSize <= dstCapacity)) - return 0; /* block not compressed */ + /* When srcSize <= dstCapacity, there is enough space to write a raw uncompressed block. + * Since we ran out of space, block must be not compressible, so fall back to raw uncompressed block. + */ + if ((cSize == ERROR(dstSize_tooSmall)) & (srcSize <= dstCapacity)) + return 0; /* block not compressed */ FORWARD_IF_ERROR(cSize, "ZSTD_entropyCompressSeqStore_internal failed"); - - /* Check compressibility */ + + /* Check compressibility */ { size_t const maxCSize = srcSize - ZSTD_minGain(srcSize, cctxParams->cParams.strategy); - if (cSize >= maxCSize) return 0; /* block not compressed */ - } + if (cSize >= maxCSize) return 0; /* block not compressed */ + } DEBUGLOG(4, "ZSTD_entropyCompressSeqStore() cSize: %zu", cSize); - return cSize; + return cSize; } -/* ZSTD_selectBlockCompressor() : - * Not static, but internal use only (used by long distance matcher) - * assumption : strat is a valid strategy */ +/* ZSTD_selectBlockCompressor() : + * Not static, but internal use only (used by long distance matcher) + * assumption : strat is a valid strategy */ ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, ZSTD_paramSwitch_e useRowMatchFinder, ZSTD_dictMode_e dictMode) { static const ZSTD_blockCompressor blockCompressor[4][ZSTD_STRATEGY_MAX+1] = { - { ZSTD_compressBlock_fast /* default for 0 */, + { ZSTD_compressBlock_fast /* default for 0 */, ZSTD_compressBlock_fast, ZSTD_compressBlock_doubleFast, ZSTD_compressBlock_greedy, @@ -2734,7 +2734,7 @@ ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, ZSTD_paramS ZSTD_compressBlock_btopt, ZSTD_compressBlock_btultra, ZSTD_compressBlock_btultra2 }, - { ZSTD_compressBlock_fast_extDict /* default for 0 */, + { ZSTD_compressBlock_fast_extDict /* default for 0 */, ZSTD_compressBlock_fast_extDict, ZSTD_compressBlock_doubleFast_extDict, ZSTD_compressBlock_greedy_extDict, @@ -2764,9 +2764,9 @@ ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, ZSTD_paramS NULL, NULL, NULL } - }; + }; ZSTD_blockCompressor selectedCompressor; - ZSTD_STATIC_ASSERT((unsigned)ZSTD_fast == 1); + ZSTD_STATIC_ASSERT((unsigned)ZSTD_fast == 1); assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat)); DEBUGLOG(4, "Selected block compressor: dictMode=%d strat=%d rowMatchfinder=%d", (int)dictMode, (int)strat, (int)useRowMatchFinder); @@ -2793,19 +2793,19 @@ ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, ZSTD_paramS } assert(selectedCompressor != NULL); return selectedCompressor; -} +} -static void ZSTD_storeLastLiterals(seqStore_t* seqStorePtr, - const BYTE* anchor, size_t lastLLSize) -{ +static void ZSTD_storeLastLiterals(seqStore_t* seqStorePtr, + const BYTE* anchor, size_t lastLLSize) +{ ZSTD_memcpy(seqStorePtr->lit, anchor, lastLLSize); - seqStorePtr->lit += lastLLSize; + seqStorePtr->lit += lastLLSize; } void ZSTD_resetSeqStore(seqStore_t* ssPtr) { - ssPtr->lit = ssPtr->litStart; - ssPtr->sequences = ssPtr->sequencesStart; + ssPtr->lit = ssPtr->litStart; + ssPtr->sequences = ssPtr->sequencesStart; ssPtr->longLengthType = ZSTD_llt_none; } @@ -2813,20 +2813,20 @@ typedef enum { ZSTDbss_compress, ZSTDbss_noCompress } ZSTD_buildSeqStore_e; static size_t ZSTD_buildSeqStore(ZSTD_CCtx* zc, const void* src, size_t srcSize) { - ZSTD_matchState_t* const ms = &zc->blockState.matchState; + ZSTD_matchState_t* const ms = &zc->blockState.matchState; DEBUGLOG(5, "ZSTD_buildSeqStore (srcSize=%zu)", srcSize); assert(srcSize <= ZSTD_BLOCKSIZE_MAX); /* Assert that we have correctly flushed the ctx params into the ms's copy */ ZSTD_assertEqualCParams(zc->appliedParams.cParams, ms->cParams); - if (srcSize < MIN_CBLOCK_SIZE+ZSTD_blockHeaderSize+1) { + if (srcSize < MIN_CBLOCK_SIZE+ZSTD_blockHeaderSize+1) { if (zc->appliedParams.cParams.strategy >= ZSTD_btopt) { ZSTD_ldm_skipRawSeqStoreBytes(&zc->externSeqStore, srcSize); } else { ZSTD_ldm_skipSequences(&zc->externSeqStore, srcSize, zc->appliedParams.cParams.minMatch); } return ZSTDbss_noCompress; /* don't even attempt compression below a certain srcSize */ - } - ZSTD_resetSeqStore(&(zc->seqStore)); + } + ZSTD_resetSeqStore(&(zc->seqStore)); /* required for optimal parser to read stats from dictionary */ ms->opt.symbolCosts = &zc->blockState.prevCBlock->entropy; /* tell the optimal parser how we expect to compress literals */ @@ -2836,62 +2836,62 @@ static size_t ZSTD_buildSeqStore(ZSTD_CCtx* zc, const void* src, size_t srcSize) * and when that stops being the case, the dict must be unset */ assert(ms->dictMatchState == NULL || ms->loadedDictEnd == ms->window.dictLimit); - /* limited update after a very long match */ - { const BYTE* const base = ms->window.base; - const BYTE* const istart = (const BYTE*)src; + /* limited update after a very long match */ + { const BYTE* const base = ms->window.base; + const BYTE* const istart = (const BYTE*)src; const U32 curr = (U32)(istart-base); if (sizeof(ptrdiff_t)==8) assert(istart - base < (ptrdiff_t)(U32)(-1)); /* ensure no overflow */ if (curr > ms->nextToUpdate + 384) ms->nextToUpdate = curr - MIN(192, (U32)(curr - ms->nextToUpdate - 384)); - } + } - /* select and store sequences */ + /* select and store sequences */ { ZSTD_dictMode_e const dictMode = ZSTD_matchState_dictMode(ms); - size_t lastLLSize; - { int i; - for (i = 0; i < ZSTD_REP_NUM; ++i) - zc->blockState.nextCBlock->rep[i] = zc->blockState.prevCBlock->rep[i]; - } - if (zc->externSeqStore.pos < zc->externSeqStore.size) { + size_t lastLLSize; + { int i; + for (i = 0; i < ZSTD_REP_NUM; ++i) + zc->blockState.nextCBlock->rep[i] = zc->blockState.prevCBlock->rep[i]; + } + if (zc->externSeqStore.pos < zc->externSeqStore.size) { assert(zc->appliedParams.ldmParams.enableLdm == ZSTD_ps_disable); - /* Updates ldmSeqStore.pos */ - lastLLSize = - ZSTD_ldm_blockCompress(&zc->externSeqStore, - ms, &zc->seqStore, - zc->blockState.nextCBlock->rep, + /* Updates ldmSeqStore.pos */ + lastLLSize = + ZSTD_ldm_blockCompress(&zc->externSeqStore, + ms, &zc->seqStore, + zc->blockState.nextCBlock->rep, zc->appliedParams.useRowMatchFinder, src, srcSize); - assert(zc->externSeqStore.pos <= zc->externSeqStore.size); + assert(zc->externSeqStore.pos <= zc->externSeqStore.size); } else if (zc->appliedParams.ldmParams.enableLdm == ZSTD_ps_enable) { rawSeqStore_t ldmSeqStore = kNullRawSeqStore; - - ldmSeqStore.seq = zc->ldmSequences; - ldmSeqStore.capacity = zc->maxNbLdmSequences; - /* Updates ldmSeqStore.size */ + + ldmSeqStore.seq = zc->ldmSequences; + ldmSeqStore.capacity = zc->maxNbLdmSequences; + /* Updates ldmSeqStore.size */ FORWARD_IF_ERROR(ZSTD_ldm_generateSequences(&zc->ldmState, &ldmSeqStore, - &zc->appliedParams.ldmParams, + &zc->appliedParams.ldmParams, src, srcSize), ""); - /* Updates ldmSeqStore.pos */ - lastLLSize = - ZSTD_ldm_blockCompress(&ldmSeqStore, - ms, &zc->seqStore, - zc->blockState.nextCBlock->rep, + /* Updates ldmSeqStore.pos */ + lastLLSize = + ZSTD_ldm_blockCompress(&ldmSeqStore, + ms, &zc->seqStore, + zc->blockState.nextCBlock->rep, zc->appliedParams.useRowMatchFinder, src, srcSize); - assert(ldmSeqStore.pos == ldmSeqStore.size); - } else { /* not long range mode */ + assert(ldmSeqStore.pos == ldmSeqStore.size); + } else { /* not long range mode */ ZSTD_blockCompressor const blockCompressor = ZSTD_selectBlockCompressor(zc->appliedParams.cParams.strategy, zc->appliedParams.useRowMatchFinder, dictMode); ms->ldmSeqStore = NULL; lastLLSize = blockCompressor(ms, &zc->seqStore, zc->blockState.nextCBlock->rep, src, srcSize); - } - { const BYTE* const lastLiterals = (const BYTE*)src + srcSize - lastLLSize; - ZSTD_storeLastLiterals(&zc->seqStore, lastLiterals, lastLLSize); - } } + } + { const BYTE* const lastLiterals = (const BYTE*)src + srcSize - lastLLSize; + ZSTD_storeLastLiterals(&zc->seqStore, lastLiterals, lastLLSize); + } } return ZSTDbss_compress; } - + static void ZSTD_copyBlockSequences(ZSTD_CCtx* zc) { const seqStore_t* seqStore = ZSTD_getSeqStore(zc); @@ -3787,7 +3787,7 @@ ZSTD_compressBlock_internal(ZSTD_CCtx* zc, return 0; } - /* encode sequences and literals */ + /* encode sequences and literals */ cSize = ZSTD_entropyCompressSeqStore(&zc->seqStore, &zc->blockState.prevCBlock->entropy, &zc->blockState.nextCBlock->entropy, &zc->appliedParams, @@ -3922,7 +3922,7 @@ static void ZSTD_overflowCorrectIfNeeded(ZSTD_matchState_t* ms, } } -/*! ZSTD_compress_frameChunk() : +/*! ZSTD_compress_frameChunk() : * Compress a chunk of data into one or multiple blocks. * All blocks will be terminated, all input will be consumed. * Function will issue an error if there is not enough `dstCapacity` to hold the compressed content. @@ -3939,16 +3939,16 @@ static size_t ZSTD_compress_frameChunk(ZSTD_CCtx* cctx, const BYTE* ip = (const BYTE*)src; BYTE* const ostart = (BYTE*)dst; BYTE* op = ostart; - U32 const maxDist = (U32)1 << cctx->appliedParams.cParams.windowLog; + U32 const maxDist = (U32)1 << cctx->appliedParams.cParams.windowLog; assert(cctx->appliedParams.cParams.windowLog <= ZSTD_WINDOWLOG_MAX); DEBUGLOG(4, "ZSTD_compress_frameChunk (blockSize=%u)", (unsigned)blockSize); - if (cctx->appliedParams.fParams.checksumFlag && srcSize) + if (cctx->appliedParams.fParams.checksumFlag && srcSize) XXH64_update(&cctx->xxhState, src, srcSize); while (remaining) { - ZSTD_matchState_t* const ms = &cctx->blockState.matchState; + ZSTD_matchState_t* const ms = &cctx->blockState.matchState; U32 const lastBlock = lastFrameChunk & (blockSize >= remaining); RETURN_ERROR_IF(dstCapacity < ZSTD_blockHeaderSize + MIN_CBLOCK_SIZE, @@ -3962,7 +3962,7 @@ static size_t ZSTD_compress_frameChunk(ZSTD_CCtx* cctx, ZSTD_window_enforceMaxDist(&ms->window, ip, maxDist, &ms->loadedDictEnd, &ms->dictMatchState); /* Ensure hash/chain table insertion resumes no sooner than lowlimit */ - if (ms->nextToUpdate < ms->window.lowLimit) ms->nextToUpdate = ms->window.lowLimit; + if (ms->nextToUpdate < ms->window.lowLimit) ms->nextToUpdate = ms->window.lowLimit; { size_t cSize; if (ZSTD_useTargetCBlockSize(&cctx->appliedParams)) { @@ -3974,7 +3974,7 @@ static size_t ZSTD_compress_frameChunk(ZSTD_CCtx* cctx, cSize = ZSTD_compressBlock_splitBlock(cctx, op, dstCapacity, ip, blockSize, lastBlock); FORWARD_IF_ERROR(cSize, "ZSTD_compressBlock_splitBlock failed"); assert(cSize > 0 || cctx->seqCollector.collectSequences == 1); - } else { + } else { cSize = ZSTD_compressBlock_internal(cctx, op+ZSTD_blockHeaderSize, dstCapacity-ZSTD_blockHeaderSize, ip, blockSize, 1 /* frame */); @@ -3990,19 +3990,19 @@ static size_t ZSTD_compress_frameChunk(ZSTD_CCtx* cctx, MEM_writeLE24(op, cBlockHeader); cSize += ZSTD_blockHeaderSize; } - } + } - ip += blockSize; - assert(remaining >= blockSize); - remaining -= blockSize; - op += cSize; - assert(dstCapacity >= cSize); - dstCapacity -= cSize; + ip += blockSize; + assert(remaining >= blockSize); + remaining -= blockSize; + op += cSize; + assert(dstCapacity >= cSize); + dstCapacity -= cSize; cctx->isFirstBlock = 0; - DEBUGLOG(5, "ZSTD_compress_frameChunk: adding a block of size %u", + DEBUGLOG(5, "ZSTD_compress_frameChunk: adding a block of size %u", (unsigned)cSize); - } } + } } if (lastFrameChunk && (op>ostart)) cctx->stage = ZSTDcs_ending; return (size_t)(op-ostart); @@ -4012,26 +4012,26 @@ static size_t ZSTD_compress_frameChunk(ZSTD_CCtx* cctx, static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity, const ZSTD_CCtx_params* params, U64 pledgedSrcSize, U32 dictID) { BYTE* const op = (BYTE*)dst; - U32 const dictIDSizeCodeLength = (dictID>0) + (dictID>=256) + (dictID>=65536); /* 0-3 */ + U32 const dictIDSizeCodeLength = (dictID>0) + (dictID>=256) + (dictID>=65536); /* 0-3 */ U32 const dictIDSizeCode = params->fParams.noDictIDFlag ? 0 : dictIDSizeCodeLength; /* 0-3 */ U32 const checksumFlag = params->fParams.checksumFlag>0; U32 const windowSize = (U32)1 << params->cParams.windowLog; U32 const singleSegment = params->fParams.contentSizeFlag && (windowSize >= pledgedSrcSize); BYTE const windowLogByte = (BYTE)((params->cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3); U32 const fcsCode = params->fParams.contentSizeFlag ? - (pledgedSrcSize>=256) + (pledgedSrcSize>=65536+256) + (pledgedSrcSize>=0xFFFFFFFFU) : 0; /* 0-3 */ + (pledgedSrcSize>=256) + (pledgedSrcSize>=65536+256) + (pledgedSrcSize>=0xFFFFFFFFU) : 0; /* 0-3 */ BYTE const frameHeaderDescriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag<<2) + (singleSegment<<5) + (fcsCode<<6) ); - size_t pos=0; + size_t pos=0; assert(!(params->fParams.contentSizeFlag && pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN)); RETURN_ERROR_IF(dstCapacity < ZSTD_FRAMEHEADERSIZE_MAX, dstSize_tooSmall, "dst buf is too small to fit worst-case frame header size."); - DEBUGLOG(4, "ZSTD_writeFrameHeader : dictIDFlag : %u ; dictID : %u ; dictIDSizeCode : %u", + DEBUGLOG(4, "ZSTD_writeFrameHeader : dictIDFlag : %u ; dictID : %u ; dictIDSizeCode : %u", !params->fParams.noDictIDFlag, (unsigned)dictID, (unsigned)dictIDSizeCode); if (params->format == ZSTD_f_zstd1) { - MEM_writeLE32(dst, ZSTD_MAGICNUMBER); - pos = 4; - } + MEM_writeLE32(dst, ZSTD_MAGICNUMBER); + pos = 4; + } op[pos++] = frameHeaderDescriptionByte; if (!singleSegment) op[pos++] = windowLogByte; switch(dictIDSizeCode) @@ -4077,37 +4077,37 @@ size_t ZSTD_writeSkippableFrame(void* dst, size_t dstCapacity, return srcSize + ZSTD_SKIPPABLEHEADERSIZE; } -/* ZSTD_writeLastEmptyBlock() : - * output an empty Block with end-of-frame mark to complete a frame - * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h)) +/* ZSTD_writeLastEmptyBlock() : + * output an empty Block with end-of-frame mark to complete a frame + * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h)) * or an error code if `dstCapacity` is too small (<ZSTD_blockHeaderSize) - */ -size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity) -{ + */ +size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity) +{ RETURN_ERROR_IF(dstCapacity < ZSTD_blockHeaderSize, dstSize_tooSmall, "dst buf is too small to write frame trailer empty block."); - { U32 const cBlockHeader24 = 1 /*lastBlock*/ + (((U32)bt_raw)<<1); /* 0 size */ - MEM_writeLE24(dst, cBlockHeader24); - return ZSTD_blockHeaderSize; - } -} - -size_t ZSTD_referenceExternalSequences(ZSTD_CCtx* cctx, rawSeq* seq, size_t nbSeq) -{ + { U32 const cBlockHeader24 = 1 /*lastBlock*/ + (((U32)bt_raw)<<1); /* 0 size */ + MEM_writeLE24(dst, cBlockHeader24); + return ZSTD_blockHeaderSize; + } +} + +size_t ZSTD_referenceExternalSequences(ZSTD_CCtx* cctx, rawSeq* seq, size_t nbSeq) +{ RETURN_ERROR_IF(cctx->stage != ZSTDcs_init, stage_wrong, "wrong cctx stage"); RETURN_ERROR_IF(cctx->appliedParams.ldmParams.enableLdm == ZSTD_ps_enable, parameter_unsupported, "incompatible with ldm"); - cctx->externSeqStore.seq = seq; - cctx->externSeqStore.size = nbSeq; - cctx->externSeqStore.capacity = nbSeq; - cctx->externSeqStore.pos = 0; + cctx->externSeqStore.seq = seq; + cctx->externSeqStore.size = nbSeq; + cctx->externSeqStore.capacity = nbSeq; + cctx->externSeqStore.pos = 0; cctx->externSeqStore.posInSequence = 0; - return 0; -} - - + return 0; +} + + static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, @@ -4116,14 +4116,14 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx, ZSTD_matchState_t* const ms = &cctx->blockState.matchState; size_t fhSize = 0; - DEBUGLOG(5, "ZSTD_compressContinue_internal, stage: %u, srcSize: %u", + DEBUGLOG(5, "ZSTD_compressContinue_internal, stage: %u, srcSize: %u", cctx->stage, (unsigned)srcSize); RETURN_ERROR_IF(cctx->stage==ZSTDcs_created, stage_wrong, "missing init (ZSTD_compressBegin)"); if (frame && (cctx->stage==ZSTDcs_init)) { fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, &cctx->appliedParams, - cctx->pledgedSrcSizePlusOne-1, cctx->dictID); + cctx->pledgedSrcSizePlusOne-1, cctx->dictID); FORWARD_IF_ERROR(fhSize, "ZSTD_writeFrameHeader failed"); assert(fhSize <= dstCapacity); dstCapacity -= fhSize; @@ -4131,11 +4131,11 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx, cctx->stage = ZSTDcs_ongoing; } - if (!srcSize) return fhSize; /* do not generate an empty block if no input */ + if (!srcSize) return fhSize; /* do not generate an empty block if no input */ if (!ZSTD_window_update(&ms->window, src, srcSize, ms->forceNonContiguous)) { ms->forceNonContiguous = 0; - ms->nextToUpdate = ms->window.dictLimit; + ms->nextToUpdate = ms->window.dictLimit; } if (cctx->appliedParams.ldmParams.enableLdm == ZSTD_ps_enable) { ZSTD_window_update(&cctx->ldmState.window, src, srcSize, /* forceNonContiguous */ 0); @@ -4150,11 +4150,11 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx, DEBUGLOG(5, "ZSTD_compressContinue_internal (blockSize=%u)", (unsigned)cctx->blockSize); { size_t const cSize = frame ? - ZSTD_compress_frameChunk (cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) : + ZSTD_compress_frameChunk (cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) : ZSTD_compressBlock_internal (cctx, dst, dstCapacity, src, srcSize, 0 /* frame */); FORWARD_IF_ERROR(cSize, "%s", frame ? "ZSTD_compress_frameChunk failed" : "ZSTD_compressBlock_internal failed"); - cctx->consumedSrcSize += srcSize; - cctx->producedCSize += (cSize + fhSize); + cctx->consumedSrcSize += srcSize; + cctx->producedCSize += (cSize + fhSize); assert(!(cctx->appliedParams.fParams.contentSizeFlag && cctx->pledgedSrcSizePlusOne == 0)); if (cctx->pledgedSrcSizePlusOne != 0) { /* control src size */ ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN == (unsigned long long)-1); @@ -4164,7 +4164,7 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx, "error : pledgedSrcSize = %u, while realSrcSize >= %u", (unsigned)cctx->pledgedSrcSizePlusOne-1, (unsigned)cctx->consumedSrcSize); - } + } return cSize + fhSize; } } @@ -4174,15 +4174,15 @@ size_t ZSTD_compressContinue (ZSTD_CCtx* cctx, const void* src, size_t srcSize) { DEBUGLOG(5, "ZSTD_compressContinue (srcSize=%u)", (unsigned)srcSize); - return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 1 /* frame mode */, 0 /* last chunk */); + return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 1 /* frame mode */, 0 /* last chunk */); } -size_t ZSTD_getBlockSize(const ZSTD_CCtx* cctx) +size_t ZSTD_getBlockSize(const ZSTD_CCtx* cctx) { - ZSTD_compressionParameters const cParams = cctx->appliedParams.cParams; - assert(!ZSTD_checkCParams(cParams)); - return MIN (ZSTD_BLOCKSIZE_MAX, (U32)1 << cParams.windowLog); + ZSTD_compressionParameters const cParams = cctx->appliedParams.cParams; + assert(!ZSTD_checkCParams(cParams)); + return MIN (ZSTD_BLOCKSIZE_MAX, (U32)1 << cParams.windowLog); } size_t ZSTD_compressBlock(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize) @@ -4191,12 +4191,12 @@ size_t ZSTD_compressBlock(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const { size_t const blockSizeMax = ZSTD_getBlockSize(cctx); RETURN_ERROR_IF(srcSize > blockSizeMax, srcSize_wrong, "input is larger than a block"); } - return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0 /* frame mode */, 0 /* last chunk */); + return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0 /* frame mode */, 0 /* last chunk */); } -/*! ZSTD_loadDictionaryContent() : - * @return : 0, or an error code - */ +/*! ZSTD_loadDictionaryContent() : + * @return : 0, or an error code + */ static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms, ldmState_t* ls, ZSTD_cwksp* ws, @@ -4231,7 +4231,7 @@ static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms, DEBUGLOG(4, "ZSTD_loadDictionaryContent(): useRowMatchFinder=%d", (int)params->useRowMatchFinder); ZSTD_window_update(&ms->window, src, srcSize, /* forceNonContiguous */ 0); - ms->loadedDictEnd = params->forceWindow ? 0 : (U32)(iend - ms->window.base); + ms->loadedDictEnd = params->forceWindow ? 0 : (U32)(iend - ms->window.base); ms->forceNonContiguous = params->deterministicRefPrefix; if (loadLdmDict) { @@ -4288,7 +4288,7 @@ static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms, assert(0); /* not possible : not a valid strategy id */ } - ms->nextToUpdate = (U32)(iend - ms->window.base); + ms->nextToUpdate = (U32)(iend - ms->window.base); return 0; } @@ -4325,12 +4325,12 @@ size_t ZSTD_loadCEntropy(ZSTD_compressedBlockState_t* bs, void* workspace, unsigned hasZeroWeights = 1; size_t const hufHeaderSize = HUF_readCTable((HUF_CElt*)bs->entropy.huf.CTable, &maxSymbolValue, dictPtr, dictEnd-dictPtr, &hasZeroWeights); - + /* We only set the loaded table as valid if it contains all non-zero * weights. Otherwise, we set it to check */ if (!hasZeroWeights) bs->entropy.huf.repeatMode = HUF_repeat_valid; - + RETURN_ERROR_IF(HUF_isError(hufHeaderSize), dictionary_corrupted, ""); RETURN_ERROR_IF(maxSymbolValue < 255, dictionary_corrupted, ""); dictPtr += hufHeaderSize; @@ -4379,9 +4379,9 @@ size_t ZSTD_loadCEntropy(ZSTD_compressedBlockState_t* bs, void* workspace, } RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted, ""); - bs->rep[0] = MEM_readLE32(dictPtr+0); - bs->rep[1] = MEM_readLE32(dictPtr+4); - bs->rep[2] = MEM_readLE32(dictPtr+8); + bs->rep[0] = MEM_readLE32(dictPtr+0); + bs->rep[1] = MEM_readLE32(dictPtr+4); + bs->rep[2] = MEM_readLE32(dictPtr+8); dictPtr += 12; { size_t const dictContentSize = (size_t)(dictEnd - dictPtr); @@ -4437,12 +4437,12 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs, size_t const dictContentSize = (size_t)(dictEnd - dictPtr); FORWARD_IF_ERROR(ZSTD_loadDictionaryContent( ms, NULL, ws, params, dictPtr, dictContentSize, dtlm), ""); - } + } return dictID; } /** ZSTD_compress_insertDictionary() : -* @return : dictID, or an error code */ +* @return : dictID, or an error code */ static size_t ZSTD_compress_insertDictionary(ZSTD_compressedBlockState_t* bs, ZSTD_matchState_t* ms, @@ -4454,29 +4454,29 @@ ZSTD_compress_insertDictionary(ZSTD_compressedBlockState_t* bs, ZSTD_dictTableLoadMethod_e dtlm, void* workspace) { - DEBUGLOG(4, "ZSTD_compress_insertDictionary (dictSize=%u)", (U32)dictSize); + DEBUGLOG(4, "ZSTD_compress_insertDictionary (dictSize=%u)", (U32)dictSize); if ((dict==NULL) || (dictSize<8)) { RETURN_ERROR_IF(dictContentType == ZSTD_dct_fullDict, dictionary_wrong, ""); return 0; } - ZSTD_reset_compressedBlockState(bs); + ZSTD_reset_compressedBlockState(bs); - /* dict restricted modes */ - if (dictContentType == ZSTD_dct_rawContent) + /* dict restricted modes */ + if (dictContentType == ZSTD_dct_rawContent) return ZSTD_loadDictionaryContent(ms, ls, ws, params, dict, dictSize, dtlm); - - if (MEM_readLE32(dict) != ZSTD_MAGIC_DICTIONARY) { - if (dictContentType == ZSTD_dct_auto) { - DEBUGLOG(4, "raw content dictionary detected"); + + if (MEM_readLE32(dict) != ZSTD_MAGIC_DICTIONARY) { + if (dictContentType == ZSTD_dct_auto) { + DEBUGLOG(4, "raw content dictionary detected"); return ZSTD_loadDictionaryContent( ms, ls, ws, params, dict, dictSize, dtlm); - } + } RETURN_ERROR_IF(dictContentType == ZSTD_dct_fullDict, dictionary_wrong, ""); - assert(0); /* impossible */ + assert(0); /* impossible */ } - - /* dict as full zstd dictionary */ + + /* dict as full zstd dictionary */ return ZSTD_loadZstdDictionary( bs, ms, ws, params, dict, dictSize, dtlm, workspace); } @@ -4485,7 +4485,7 @@ ZSTD_compress_insertDictionary(ZSTD_compressedBlockState_t* bs, #define ZSTD_USE_CDICT_PARAMS_DICTSIZE_MULTIPLIER (6ULL) /*! ZSTD_compressBegin_internal() : - * @return : 0, or an error code */ + * @return : 0, or an error code */ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_dictContentType_e dictContentType, @@ -4499,9 +4499,9 @@ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx, cctx->traceCtx = (ZSTD_trace_compress_begin != NULL) ? ZSTD_trace_compress_begin(cctx) : 0; #endif DEBUGLOG(4, "ZSTD_compressBegin_internal: wlog=%u", params->cParams.windowLog); - /* params are supposed to be fully validated at this point */ + /* params are supposed to be fully validated at this point */ assert(!ZSTD_isError(ZSTD_checkCParams(params->cParams))); - assert(!((dict) && (cdict))); /* either dict or cdict, not both */ + assert(!((dict) && (cdict))); /* either dict or cdict, not both */ if ( (cdict) && (cdict->dictContentSize > 0) && ( pledgedSrcSize < ZSTD_USE_CDICT_PARAMS_SRCSIZE_CUTOFF @@ -4510,8 +4510,8 @@ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx, || cdict->compressionLevel == 0) && (params->attachDictPref != ZSTD_dictForceLoad) ) { return ZSTD_resetCCtx_usingCDict(cctx, cdict, params, pledgedSrcSize, zbuff); - } - + } + FORWARD_IF_ERROR( ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize, dictContentSize, ZSTDcrp_makeClean, zbuff) , ""); @@ -4527,29 +4527,29 @@ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx, dictContentType, dtlm, cctx->entropyWorkspace); FORWARD_IF_ERROR(dictID, "ZSTD_compress_insertDictionary failed"); assert(dictID <= UINT_MAX); - cctx->dictID = (U32)dictID; + cctx->dictID = (U32)dictID; cctx->dictContentSize = dictContentSize; - } - return 0; + } + return 0; } -size_t ZSTD_compressBegin_advanced_internal(ZSTD_CCtx* cctx, - const void* dict, size_t dictSize, - ZSTD_dictContentType_e dictContentType, +size_t ZSTD_compressBegin_advanced_internal(ZSTD_CCtx* cctx, + const void* dict, size_t dictSize, + ZSTD_dictContentType_e dictContentType, ZSTD_dictTableLoadMethod_e dtlm, - const ZSTD_CDict* cdict, + const ZSTD_CDict* cdict, const ZSTD_CCtx_params* params, - unsigned long long pledgedSrcSize) -{ + unsigned long long pledgedSrcSize) +{ DEBUGLOG(4, "ZSTD_compressBegin_advanced_internal: wlog=%u", params->cParams.windowLog); - /* compression parameters verification and optimization */ + /* compression parameters verification and optimization */ FORWARD_IF_ERROR( ZSTD_checkCParams(params->cParams) , ""); - return ZSTD_compressBegin_internal(cctx, + return ZSTD_compressBegin_internal(cctx, dict, dictSize, dictContentType, dtlm, - cdict, - params, pledgedSrcSize, - ZSTDb_not_buffered); -} + cdict, + params, pledgedSrcSize, + ZSTDb_not_buffered); +} /*! ZSTD_compressBegin_advanced() : * @return : 0, or an error code */ @@ -4559,9 +4559,9 @@ size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, { ZSTD_CCtx_params cctxParams; ZSTD_CCtxParams_init_internal(&cctxParams, ¶ms, ZSTD_NO_CLEVEL); - return ZSTD_compressBegin_advanced_internal(cctx, + return ZSTD_compressBegin_advanced_internal(cctx, dict, dictSize, ZSTD_dct_auto, ZSTD_dtlm_fast, - NULL /*cdict*/, + NULL /*cdict*/, &cctxParams, pledgedSrcSize); } @@ -4577,9 +4577,9 @@ size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t di &cctxParams, ZSTD_CONTENTSIZE_UNKNOWN, ZSTDb_not_buffered); } -size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel) +size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel) { - return ZSTD_compressBegin_usingDict(cctx, NULL, 0, compressionLevel); + return ZSTD_compressBegin_usingDict(cctx, NULL, 0, compressionLevel); } @@ -4592,7 +4592,7 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity) BYTE* op = ostart; size_t fhSize = 0; - DEBUGLOG(4, "ZSTD_writeEpilogue"); + DEBUGLOG(4, "ZSTD_writeEpilogue"); RETURN_ERROR_IF(cctx->stage == ZSTDcs_created, stage_wrong, "init missing"); /* special case : empty frame */ @@ -4613,7 +4613,7 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity) dstCapacity -= ZSTD_blockHeaderSize; } - if (cctx->appliedParams.fParams.checksumFlag) { + if (cctx->appliedParams.fParams.checksumFlag) { U32 const checksum = (U32) XXH64_digest(&cctx->xxhState); RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall, "no room for checksum"); DEBUGLOG(4, "ZSTD_writeEpilogue: write checksum : %08X", (unsigned)checksum); @@ -4654,16 +4654,16 @@ size_t ZSTD_compressEnd (ZSTD_CCtx* cctx, const void* src, size_t srcSize) { size_t endResult; - size_t const cSize = ZSTD_compressContinue_internal(cctx, - dst, dstCapacity, src, srcSize, - 1 /* frame mode */, 1 /* last chunk */); + size_t const cSize = ZSTD_compressContinue_internal(cctx, + dst, dstCapacity, src, srcSize, + 1 /* frame mode */, 1 /* last chunk */); FORWARD_IF_ERROR(cSize, "ZSTD_compressContinue_internal failed"); endResult = ZSTD_writeEpilogue(cctx, (char*)dst + cSize, dstCapacity-cSize); FORWARD_IF_ERROR(endResult, "ZSTD_writeEpilogue failed"); assert(!(cctx->appliedParams.fParams.contentSizeFlag && cctx->pledgedSrcSizePlusOne == 0)); if (cctx->pledgedSrcSizePlusOne != 0) { /* control src size */ ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN == (unsigned long long)-1); - DEBUGLOG(4, "end of frame : controlling src size"); + DEBUGLOG(4, "end of frame : controlling src size"); RETURN_ERROR_IF( cctx->pledgedSrcSizePlusOne != cctx->consumedSrcSize+1, srcSize_wrong, @@ -4681,7 +4681,7 @@ size_t ZSTD_compress_advanced (ZSTD_CCtx* cctx, const void* dict,size_t dictSize, ZSTD_parameters params) { - DEBUGLOG(4, "ZSTD_compress_advanced"); + DEBUGLOG(4, "ZSTD_compress_advanced"); FORWARD_IF_ERROR(ZSTD_checkCParams(params.cParams), ""); ZSTD_CCtxParams_init_internal(&cctx->simpleApiParams, ¶ms, ZSTD_NO_CLEVEL); return ZSTD_compress_advanced_internal(cctx, @@ -4691,19 +4691,19 @@ size_t ZSTD_compress_advanced (ZSTD_CCtx* cctx, &cctx->simpleApiParams); } -/* Internal */ -size_t ZSTD_compress_advanced_internal( - ZSTD_CCtx* cctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const void* dict,size_t dictSize, +/* Internal */ +size_t ZSTD_compress_advanced_internal( + ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, const ZSTD_CCtx_params* params) { DEBUGLOG(4, "ZSTD_compress_advanced_internal (srcSize:%u)", (unsigned)srcSize); FORWARD_IF_ERROR( ZSTD_compressBegin_internal(cctx, dict, dictSize, ZSTD_dct_auto, ZSTD_dtlm_fast, NULL, params, srcSize, ZSTDb_not_buffered) , ""); - return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize); + return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize); } size_t ZSTD_compress_usingDict(ZSTD_CCtx* cctx, @@ -4725,12 +4725,12 @@ size_t ZSTD_compressCCtx(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, int compressionLevel) -{ +{ DEBUGLOG(4, "ZSTD_compressCCtx (srcSize=%u)", (unsigned)srcSize); assert(cctx != NULL); - return ZSTD_compress_usingDict(cctx, dst, dstCapacity, src, srcSize, NULL, 0, compressionLevel); -} - + return ZSTD_compress_usingDict(cctx, dst, dstCapacity, src, srcSize, NULL, 0, compressionLevel); +} + size_t ZSTD_compress(void* dst, size_t dstCapacity, const void* src, size_t srcSize, int compressionLevel) @@ -4753,12 +4753,12 @@ size_t ZSTD_compress(void* dst, size_t dstCapacity, /* ===== Dictionary API ===== */ -/*! ZSTD_estimateCDictSize_advanced() : - * Estimate amount of memory that will be needed to create a dictionary with following arguments */ -size_t ZSTD_estimateCDictSize_advanced( - size_t dictSize, ZSTD_compressionParameters cParams, - ZSTD_dictLoadMethod_e dictLoadMethod) -{ +/*! ZSTD_estimateCDictSize_advanced() : + * Estimate amount of memory that will be needed to create a dictionary with following arguments */ +size_t ZSTD_estimateCDictSize_advanced( + size_t dictSize, ZSTD_compressionParameters cParams, + ZSTD_dictLoadMethod_e dictLoadMethod) +{ DEBUGLOG(5, "sizeof(ZSTD_CDict) : %u", (unsigned)sizeof(ZSTD_CDict)); return ZSTD_cwksp_alloc_size(sizeof(ZSTD_CDict)) + ZSTD_cwksp_alloc_size(HUF_WORKSPACE_SIZE) @@ -4768,14 +4768,14 @@ size_t ZSTD_estimateCDictSize_advanced( /* enableDedicatedDictSearch */ 1, /* forCCtx */ 0) + (dictLoadMethod == ZSTD_dlm_byRef ? 0 : ZSTD_cwksp_alloc_size(ZSTD_cwksp_align(dictSize, sizeof(void *)))); -} +} -size_t ZSTD_estimateCDictSize(size_t dictSize, int compressionLevel) -{ +size_t ZSTD_estimateCDictSize(size_t dictSize, int compressionLevel) +{ ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_createCDict); - return ZSTD_estimateCDictSize_advanced(dictSize, cParams, ZSTD_dlm_byCopy); -} - + return ZSTD_estimateCDictSize_advanced(dictSize, cParams, ZSTD_dlm_byCopy); +} + size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict) { if (cdict==NULL) return 0; /* support sizeof on NULL */ @@ -4785,33 +4785,33 @@ size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict) + ZSTD_cwksp_sizeof(&cdict->workspace); } -static size_t ZSTD_initCDict_internal( - ZSTD_CDict* cdict, - const void* dictBuffer, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, - ZSTD_dictContentType_e dictContentType, +static size_t ZSTD_initCDict_internal( + ZSTD_CDict* cdict, + const void* dictBuffer, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, ZSTD_CCtx_params params) { DEBUGLOG(3, "ZSTD_initCDict_internal (dictContentType:%u)", (unsigned)dictContentType); assert(!ZSTD_checkCParams(params.cParams)); cdict->matchState.cParams = params.cParams; cdict->matchState.dedicatedDictSearch = params.enableDedicatedDictSearch; - if ((dictLoadMethod == ZSTD_dlm_byRef) || (!dictBuffer) || (!dictSize)) { - cdict->dictContent = dictBuffer; - } else { + if ((dictLoadMethod == ZSTD_dlm_byRef) || (!dictBuffer) || (!dictSize)) { + cdict->dictContent = dictBuffer; + } else { void *internalBuffer = ZSTD_cwksp_reserve_object(&cdict->workspace, ZSTD_cwksp_align(dictSize, sizeof(void*))); RETURN_ERROR_IF(!internalBuffer, memory_allocation, "NULL pointer!"); - cdict->dictContent = internalBuffer; + cdict->dictContent = internalBuffer; ZSTD_memcpy(internalBuffer, dictBuffer, dictSize); - } - cdict->dictContentSize = dictSize; + } + cdict->dictContentSize = dictSize; cdict->dictContentType = dictContentType; cdict->entropyWorkspace = (U32*)ZSTD_cwksp_reserve_object(&cdict->workspace, HUF_WORKSPACE_SIZE); - /* Reset the state to no dictionary */ - ZSTD_reset_compressedBlockState(&cdict->cBlockState); + /* Reset the state to no dictionary */ + ZSTD_reset_compressedBlockState(&cdict->cBlockState); FORWARD_IF_ERROR(ZSTD_reset_matchState( &cdict->matchState, &cdict->workspace, @@ -4820,33 +4820,33 @@ static size_t ZSTD_initCDict_internal( ZSTDcrp_makeClean, ZSTDirp_reset, ZSTD_resetTarget_CDict), ""); - /* (Maybe) load the dictionary + /* (Maybe) load the dictionary * Skips loading the dictionary if it is < 8 bytes. - */ + */ { params.compressionLevel = ZSTD_CLEVEL_DEFAULT; - params.fParams.contentSizeFlag = 1; - { size_t const dictID = ZSTD_compress_insertDictionary( + params.fParams.contentSizeFlag = 1; + { size_t const dictID = ZSTD_compress_insertDictionary( &cdict->cBlockState, &cdict->matchState, NULL, &cdict->workspace, ¶ms, cdict->dictContent, cdict->dictContentSize, dictContentType, ZSTD_dtlm_full, cdict->entropyWorkspace); FORWARD_IF_ERROR(dictID, "ZSTD_compress_insertDictionary failed"); - assert(dictID <= (size_t)(U32)-1); - cdict->dictID = (U32)dictID; - } - } - - return 0; -} - + assert(dictID <= (size_t)(U32)-1); + cdict->dictID = (U32)dictID; + } + } + + return 0; +} + static ZSTD_CDict* ZSTD_createCDict_advanced_internal(size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_compressionParameters cParams, ZSTD_paramSwitch_e useRowMatchFinder, U32 enableDedicatedDictSearch, ZSTD_customMem customMem) -{ +{ if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL; - + { size_t const workspaceSize = ZSTD_cwksp_alloc_size(sizeof(ZSTD_CDict)) + ZSTD_cwksp_alloc_size(HUF_WORKSPACE_SIZE) + @@ -4856,7 +4856,7 @@ static ZSTD_CDict* ZSTD_createCDict_advanced_internal(size_t dictSize, void* const workspace = ZSTD_customMalloc(workspaceSize, customMem); ZSTD_cwksp ws; ZSTD_CDict* cdict; - + if (!workspace) { ZSTD_customFree(workspace, customMem); return NULL; @@ -4867,7 +4867,7 @@ static ZSTD_CDict* ZSTD_createCDict_advanced_internal(size_t dictSize, cdict = (ZSTD_CDict*)ZSTD_cwksp_reserve_object(&ws, sizeof(ZSTD_CDict)); assert(cdict != NULL); ZSTD_cwksp_move(&cdict->workspace, &ws); - cdict->customMem = customMem; + cdict->customMem = customMem; cdict->compressionLevel = ZSTD_NO_CLEVEL; /* signals advanced API usage */ cdict->useRowMatchFinder = useRowMatchFinder; return cdict; @@ -4952,21 +4952,21 @@ ZSTD_CDict* ZSTD_createCDict(const void* dict, size_t dictSize, int compressionL return cdict; } -ZSTD_CDict* ZSTD_createCDict_byReference(const void* dict, size_t dictSize, int compressionLevel) -{ +ZSTD_CDict* ZSTD_createCDict_byReference(const void* dict, size_t dictSize, int compressionLevel) +{ ZSTD_compressionParameters cParams = ZSTD_getCParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_createCDict); ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dict, dictSize, - ZSTD_dlm_byRef, ZSTD_dct_auto, - cParams, ZSTD_defaultCMem); + ZSTD_dlm_byRef, ZSTD_dct_auto, + cParams, ZSTD_defaultCMem); if (cdict) cdict->compressionLevel = (compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT : compressionLevel; return cdict; -} - +} + size_t ZSTD_freeCDict(ZSTD_CDict* cdict) { if (cdict==NULL) return 0; /* support free on NULL */ - { ZSTD_customMem const cMem = cdict->customMem; + { ZSTD_customMem const cMem = cdict->customMem; int cdictInWorkspace = ZSTD_cwksp_owns_buffer(&cdict->workspace, cdict); ZSTD_cwksp_free(&cdict->workspace, cMem); if (!cdictInWorkspace) { @@ -4976,26 +4976,26 @@ size_t ZSTD_freeCDict(ZSTD_CDict* cdict) } } -/*! ZSTD_initStaticCDict_advanced() : - * Generate a digested dictionary in provided memory area. - * workspace: The memory area to emplace the dictionary into. - * Provided pointer must 8-bytes aligned. - * It must outlive dictionary usage. - * workspaceSize: Use ZSTD_estimateCDictSize() - * to determine how large workspace must be. - * cParams : use ZSTD_getCParams() to transform a compression level - * into its relevants cParams. - * @return : pointer to ZSTD_CDict*, or NULL if error (size too small) - * Note : there is no corresponding "free" function. - * Since workspace was allocated externally, it must be freed externally. - */ -const ZSTD_CDict* ZSTD_initStaticCDict( - void* workspace, size_t workspaceSize, - const void* dict, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, - ZSTD_dictContentType_e dictContentType, - ZSTD_compressionParameters cParams) -{ +/*! ZSTD_initStaticCDict_advanced() : + * Generate a digested dictionary in provided memory area. + * workspace: The memory area to emplace the dictionary into. + * Provided pointer must 8-bytes aligned. + * It must outlive dictionary usage. + * workspaceSize: Use ZSTD_estimateCDictSize() + * to determine how large workspace must be. + * cParams : use ZSTD_getCParams() to transform a compression level + * into its relevants cParams. + * @return : pointer to ZSTD_CDict*, or NULL if error (size too small) + * Note : there is no corresponding "free" function. + * Since workspace was allocated externally, it must be freed externally. + */ +const ZSTD_CDict* ZSTD_initStaticCDict( + void* workspace, size_t workspaceSize, + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_compressionParameters cParams) +{ ZSTD_paramSwitch_e const useRowMatchFinder = ZSTD_resolveRowMatchFinderMode(ZSTD_ps_auto, &cParams); /* enableDedicatedDictSearch == 1 ensures matchstate is not too small in case this CDict will be used for DDS + row hash */ size_t const matchStateSize = ZSTD_sizeof_matchState(&cParams, useRowMatchFinder, /* enableDedicatedDictSearch */ 1, /* forCCtx */ 0); @@ -5007,7 +5007,7 @@ const ZSTD_CDict* ZSTD_initStaticCDict( ZSTD_CDict* cdict; ZSTD_CCtx_params params; - if ((size_t)workspace & 7) return NULL; /* 8-aligned */ + if ((size_t)workspace & 7) return NULL; /* 8-aligned */ { ZSTD_cwksp ws; @@ -5017,27 +5017,27 @@ const ZSTD_CDict* ZSTD_initStaticCDict( ZSTD_cwksp_move(&cdict->workspace, &ws); } - DEBUGLOG(4, "(workspaceSize < neededSize) : (%u < %u) => %u", + DEBUGLOG(4, "(workspaceSize < neededSize) : (%u < %u) => %u", (unsigned)workspaceSize, (unsigned)neededSize, (unsigned)(workspaceSize < neededSize)); - if (workspaceSize < neededSize) return NULL; - + if (workspaceSize < neededSize) return NULL; + ZSTD_CCtxParams_init(¶ms, 0); params.cParams = cParams; params.useRowMatchFinder = useRowMatchFinder; cdict->useRowMatchFinder = useRowMatchFinder; - if (ZSTD_isError( ZSTD_initCDict_internal(cdict, - dict, dictSize, + if (ZSTD_isError( ZSTD_initCDict_internal(cdict, + dict, dictSize, dictLoadMethod, dictContentType, params) )) - return NULL; - - return cdict; + return NULL; + + return cdict; } -ZSTD_compressionParameters ZSTD_getCParamsFromCDict(const ZSTD_CDict* cdict) +ZSTD_compressionParameters ZSTD_getCParamsFromCDict(const ZSTD_CDict* cdict) { - assert(cdict != NULL); + assert(cdict != NULL); return cdict->matchState.cParams; } @@ -5055,9 +5055,9 @@ unsigned ZSTD_getDictID_fromCDict(const ZSTD_CDict* cdict) * Implementation of various ZSTD_compressBegin_usingCDict* functions. */ static size_t ZSTD_compressBegin_usingCDict_internal( - ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, - ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize) -{ + ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, + ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize) +{ ZSTD_CCtx_params cctxParams; DEBUGLOG(4, "ZSTD_compressBegin_usingCDict_internal"); RETURN_ERROR_IF(cdict==NULL, dictionary_wrong, "NULL pointer!"); @@ -5074,7 +5074,7 @@ static size_t ZSTD_compressBegin_usingCDict_internal( pledgedSrcSize, cdict->dictContentSize); ZSTD_CCtxParams_init_internal(&cctxParams, ¶ms, cdict->compressionLevel); - } + } /* Increase window log to fit the entire dictionary and source if the * source size is known. Limit the increase to 19, which is the * window log for compression level 1 with the largest source size. @@ -5089,8 +5089,8 @@ static size_t ZSTD_compressBegin_usingCDict_internal( cdict, &cctxParams, pledgedSrcSize, ZSTDb_not_buffered); -} - +} + /* ZSTD_compressBegin_usingCDict_advanced() : * This function is DEPRECATED. @@ -5102,26 +5102,26 @@ size_t ZSTD_compressBegin_usingCDict_advanced( return ZSTD_compressBegin_usingCDict_internal(cctx, cdict, fParams, pledgedSrcSize); } -/* ZSTD_compressBegin_usingCDict() : +/* ZSTD_compressBegin_usingCDict() : * cdict must be != NULL */ -size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict) -{ - ZSTD_frameParameters const fParams = { 0 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ }; +size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict) +{ + ZSTD_frameParameters const fParams = { 0 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ }; return ZSTD_compressBegin_usingCDict_internal(cctx, cdict, fParams, ZSTD_CONTENTSIZE_UNKNOWN); -} - +} + /*! ZSTD_compress_usingCDict_internal(): * Implementation of various ZSTD_compress_usingCDict* functions. */ static size_t ZSTD_compress_usingCDict_internal(ZSTD_CCtx* cctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const ZSTD_CDict* cdict, ZSTD_frameParameters fParams) -{ + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_CDict* cdict, ZSTD_frameParameters fParams) +{ FORWARD_IF_ERROR(ZSTD_compressBegin_usingCDict_internal(cctx, cdict, fParams, srcSize), ""); /* will check if cdict != NULL */ - return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize); -} - + return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize); +} + /*! ZSTD_compress_usingCDict_advanced(): * This function is DEPRECATED. */ @@ -5134,16 +5134,16 @@ size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx, } /*! ZSTD_compress_usingCDict() : - * Compression using a digested Dictionary. - * Faster startup than ZSTD_compress_usingDict(), recommended when same dictionary is used multiple times. - * Note that compression parameters are decided at CDict creation time - * while frame parameters are hardcoded */ + * Compression using a digested Dictionary. + * Faster startup than ZSTD_compress_usingDict(), recommended when same dictionary is used multiple times. + * Note that compression parameters are decided at CDict creation time + * while frame parameters are hardcoded */ size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, const ZSTD_CDict* cdict) { - ZSTD_frameParameters const fParams = { 1 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ }; + ZSTD_frameParameters const fParams = { 1 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ }; return ZSTD_compress_usingCDict_internal(cctx, dst, dstCapacity, src, srcSize, cdict, fParams); } @@ -5155,46 +5155,46 @@ size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx, ZSTD_CStream* ZSTD_createCStream(void) { - DEBUGLOG(3, "ZSTD_createCStream"); - return ZSTD_createCStream_advanced(ZSTD_defaultCMem); + DEBUGLOG(3, "ZSTD_createCStream"); + return ZSTD_createCStream_advanced(ZSTD_defaultCMem); } -ZSTD_CStream* ZSTD_initStaticCStream(void *workspace, size_t workspaceSize) +ZSTD_CStream* ZSTD_initStaticCStream(void *workspace, size_t workspaceSize) { - return ZSTD_initStaticCCtx(workspace, workspaceSize); -} + return ZSTD_initStaticCCtx(workspace, workspaceSize); +} -ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem) -{ /* CStream and CCtx are now same object */ - return ZSTD_createCCtx_advanced(customMem); +ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem) +{ /* CStream and CCtx are now same object */ + return ZSTD_createCCtx_advanced(customMem); } size_t ZSTD_freeCStream(ZSTD_CStream* zcs) { - return ZSTD_freeCCtx(zcs); /* same object */ + return ZSTD_freeCCtx(zcs); /* same object */ } - + /*====== Initialization ======*/ -size_t ZSTD_CStreamInSize(void) { return ZSTD_BLOCKSIZE_MAX; } +size_t ZSTD_CStreamInSize(void) { return ZSTD_BLOCKSIZE_MAX; } -size_t ZSTD_CStreamOutSize(void) +size_t ZSTD_CStreamOutSize(void) { - return ZSTD_compressBound(ZSTD_BLOCKSIZE_MAX) + ZSTD_blockHeaderSize + 4 /* 32-bits hash */ ; -} + return ZSTD_compressBound(ZSTD_BLOCKSIZE_MAX) + ZSTD_blockHeaderSize + 4 /* 32-bits hash */ ; +} static ZSTD_cParamMode_e ZSTD_getCParamMode(ZSTD_CDict const* cdict, ZSTD_CCtx_params const* params, U64 pledgedSrcSize) -{ +{ if (cdict != NULL && ZSTD_shouldAttachDict(cdict, params, pledgedSrcSize)) return ZSTD_cpm_attachDict; else return ZSTD_cpm_noAttachDict; } -/* ZSTD_resetCStream(): - * pledgedSrcSize == 0 means "unknown" */ +/* ZSTD_resetCStream(): + * pledgedSrcSize == 0 means "unknown" */ size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pss) { /* temporary : 0 interpreted as "unknown" during transition period. @@ -5206,40 +5206,40 @@ size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pss) FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , ""); return 0; -} - -/*! ZSTD_initCStream_internal() : - * Note : for lib/compress only. Used by zstdmt_compress.c. - * Assumption 1 : params are valid - * Assumption 2 : either dict, or cdict, is defined, not both */ -size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs, - const void* dict, size_t dictSize, const ZSTD_CDict* cdict, +} + +/*! ZSTD_initCStream_internal() : + * Note : for lib/compress only. Used by zstdmt_compress.c. + * Assumption 1 : params are valid + * Assumption 2 : either dict, or cdict, is defined, not both */ +size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs, + const void* dict, size_t dictSize, const ZSTD_CDict* cdict, const ZSTD_CCtx_params* params, unsigned long long pledgedSrcSize) -{ - DEBUGLOG(4, "ZSTD_initCStream_internal"); +{ + DEBUGLOG(4, "ZSTD_initCStream_internal"); FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , ""); assert(!ZSTD_isError(ZSTD_checkCParams(params->cParams))); zcs->requestedParams = *params; - assert(!((dict) && (cdict))); /* either dict or cdict, not both */ + assert(!((dict) && (cdict))); /* either dict or cdict, not both */ if (dict) { FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) , ""); - } else { + } else { /* Dictionary is cleared if !cdict */ FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) , ""); - } + } return 0; -} - -/* ZSTD_initCStream_usingCDict_advanced() : - * same as ZSTD_initCStream_usingCDict(), with control over frame parameters */ -size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, - const ZSTD_CDict* cdict, - ZSTD_frameParameters fParams, - unsigned long long pledgedSrcSize) -{ - DEBUGLOG(4, "ZSTD_initCStream_usingCDict_advanced"); +} + +/* ZSTD_initCStream_usingCDict_advanced() : + * same as ZSTD_initCStream_usingCDict(), with control over frame parameters */ +size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, + const ZSTD_CDict* cdict, + ZSTD_frameParameters fParams, + unsigned long long pledgedSrcSize) +{ + DEBUGLOG(4, "ZSTD_initCStream_usingCDict_advanced"); FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , ""); zcs->requestedParams.fParams = fParams; @@ -5250,21 +5250,21 @@ size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, /* note : cdict must outlive compression session */ size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict) { - DEBUGLOG(4, "ZSTD_initCStream_usingCDict"); + DEBUGLOG(4, "ZSTD_initCStream_usingCDict"); FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) , ""); return 0; } - -/* ZSTD_initCStream_advanced() : - * pledgedSrcSize must be exact. - * if srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. + +/* ZSTD_initCStream_advanced() : + * pledgedSrcSize must be exact. + * if srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. * dict is loaded with default parameters ZSTD_dct_auto and ZSTD_dlm_byCopy. */ -size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, - const void* dict, size_t dictSize, +size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, + const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pss) -{ +{ /* for compatibility with older programs relying on this behavior. * Users should now specify ZSTD_CONTENTSIZE_UNKNOWN. * This line will be removed in the future. @@ -5277,8 +5277,8 @@ size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, ZSTD_CCtxParams_setZstdParams(&zcs->requestedParams, ¶ms); FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) , ""); return 0; -} - +} + size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel) { DEBUGLOG(4, "ZSTD_initCStream_usingDict"); @@ -5288,7 +5288,7 @@ size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t di return 0; } -size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pss) +size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pss) { /* temporary : 0 interpreted as "unknown" during transition period. * Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN. @@ -5305,7 +5305,7 @@ size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigne size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel) { - DEBUGLOG(4, "ZSTD_initCStream"); + DEBUGLOG(4, "ZSTD_initCStream"); FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, NULL) , ""); FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) , ""); @@ -5321,24 +5321,24 @@ static size_t ZSTD_nextInputSizeHint(const ZSTD_CCtx* cctx) return hintInSize; } -/** ZSTD_compressStream_generic(): +/** ZSTD_compressStream_generic(): * internal function for all *compressStream*() variants - * non-static, because can be called from zstdmt_compress.c - * @return : hint size for next input */ + * non-static, because can be called from zstdmt_compress.c + * @return : hint size for next input */ static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input, ZSTD_EndDirective const flushMode) { - const char* const istart = (const char*)input->src; + const char* const istart = (const char*)input->src; const char* const iend = input->size != 0 ? istart + input->size : istart; const char* ip = input->pos != 0 ? istart + input->pos : istart; - char* const ostart = (char*)output->dst; + char* const ostart = (char*)output->dst; char* const oend = output->size != 0 ? ostart + output->size : ostart; char* op = output->pos != 0 ? ostart + output->pos : ostart; U32 someMoreWork = 1; - /* check expectations */ + /* check expectations */ DEBUGLOG(5, "ZSTD_compressStream_generic, flush=%u", (unsigned)flushMode); if (zcs->appliedParams.inBufferMode == ZSTD_bm_buffered) { assert(zcs->inBuff != NULL); @@ -5348,54 +5348,54 @@ static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs, assert(zcs->outBuff != NULL); assert(zcs->outBuffSize > 0); } - assert(output->pos <= output->size); - assert(input->pos <= input->size); + assert(output->pos <= output->size); + assert(input->pos <= input->size); assert((U32)flushMode <= (U32)ZSTD_e_end); - + while (someMoreWork) { - switch(zcs->streamStage) + switch(zcs->streamStage) { - case zcss_init: + case zcss_init: RETURN_ERROR(init_missing, "call ZSTD_initCStream() first!"); case zcss_load: - if ( (flushMode == ZSTD_e_end) + if ( (flushMode == ZSTD_e_end) && ( (size_t)(oend-op) >= ZSTD_compressBound(iend-ip) /* Enough output space */ || zcs->appliedParams.outBufferMode == ZSTD_bm_stable) /* OR we are allowed to return dstSizeTooSmall */ - && (zcs->inBuffPos == 0) ) { - /* shortcut to compression pass directly into output buffer */ - size_t const cSize = ZSTD_compressEnd(zcs, - op, oend-op, ip, iend-ip); + && (zcs->inBuffPos == 0) ) { + /* shortcut to compression pass directly into output buffer */ + size_t const cSize = ZSTD_compressEnd(zcs, + op, oend-op, ip, iend-ip); DEBUGLOG(4, "ZSTD_compressEnd : cSize=%u", (unsigned)cSize); FORWARD_IF_ERROR(cSize, "ZSTD_compressEnd failed"); - ip = iend; - op += cSize; - zcs->frameEnded = 1; + ip = iend; + op += cSize; + zcs->frameEnded = 1; ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); - someMoreWork = 0; break; - } + someMoreWork = 0; break; + } /* complete loading into inBuffer in buffered mode */ if (zcs->appliedParams.inBufferMode == ZSTD_bm_buffered) { size_t const toLoad = zcs->inBuffTarget - zcs->inBuffPos; - size_t const loaded = ZSTD_limitCopy( - zcs->inBuff + zcs->inBuffPos, toLoad, - ip, iend-ip); + size_t const loaded = ZSTD_limitCopy( + zcs->inBuff + zcs->inBuffPos, toLoad, + ip, iend-ip); zcs->inBuffPos += loaded; if (loaded != 0) ip += loaded; - if ( (flushMode == ZSTD_e_continue) - && (zcs->inBuffPos < zcs->inBuffTarget) ) { - /* not enough input to fill full block : stop here */ - someMoreWork = 0; break; - } - if ( (flushMode == ZSTD_e_flush) - && (zcs->inBuffPos == zcs->inToCompress) ) { - /* empty */ - someMoreWork = 0; break; - } - } + if ( (flushMode == ZSTD_e_continue) + && (zcs->inBuffPos < zcs->inBuffTarget) ) { + /* not enough input to fill full block : stop here */ + someMoreWork = 0; break; + } + if ( (flushMode == ZSTD_e_flush) + && (zcs->inBuffPos == zcs->inToCompress) ) { + /* empty */ + someMoreWork = 0; break; + } + } /* compress current block (note : this stage cannot be stopped in the middle) */ - DEBUGLOG(5, "stream compression stage (flushMode==%u)", flushMode); + DEBUGLOG(5, "stream compression stage (flushMode==%u)", flushMode); { int const inputBuffered = (zcs->appliedParams.inBufferMode == ZSTD_bm_buffered); void* cDst; size_t cSize; @@ -5404,7 +5404,7 @@ static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs, ? zcs->inBuffPos - zcs->inToCompress : MIN((size_t)(iend - ip), zcs->blockSize); if (oSize >= ZSTD_compressBound(iSize) || zcs->appliedParams.outBufferMode == ZSTD_bm_stable) - cDst = op; /* compress into output buffer, to skip flush stage */ + cDst = op; /* compress into output buffer, to skip flush stage */ else cDst = zcs->outBuff, oSize = zcs->outBuffSize; if (inputBuffered) { @@ -5439,55 +5439,55 @@ static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs, if (lastBlock) assert(ip == iend); } - if (cDst == op) { /* no need to flush */ - op += cSize; - if (zcs->frameEnded) { - DEBUGLOG(5, "Frame completed directly in outBuffer"); - someMoreWork = 0; + if (cDst == op) { /* no need to flush */ + op += cSize; + if (zcs->frameEnded) { + DEBUGLOG(5, "Frame completed directly in outBuffer"); + someMoreWork = 0; ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); - } - break; - } + } + break; + } zcs->outBuffContentSize = cSize; zcs->outBuffFlushedSize = 0; - zcs->streamStage = zcss_flush; /* pass-through to flush stage */ + zcs->streamStage = zcss_flush; /* pass-through to flush stage */ } ZSTD_FALLTHROUGH; case zcss_flush: - DEBUGLOG(5, "flush stage"); + DEBUGLOG(5, "flush stage"); assert(zcs->appliedParams.outBufferMode == ZSTD_bm_buffered); { size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize; size_t const flushed = ZSTD_limitCopy(op, (size_t)(oend-op), - zcs->outBuff + zcs->outBuffFlushedSize, toFlush); - DEBUGLOG(5, "toFlush: %u into %u ==> flushed: %u", + zcs->outBuff + zcs->outBuffFlushedSize, toFlush); + DEBUGLOG(5, "toFlush: %u into %u ==> flushed: %u", (unsigned)toFlush, (unsigned)(oend-op), (unsigned)flushed); if (flushed) op += flushed; zcs->outBuffFlushedSize += flushed; - if (toFlush!=flushed) { - /* flush not fully completed, presumably because dst is too small */ - assert(op==oend); - someMoreWork = 0; - break; - } + if (toFlush!=flushed) { + /* flush not fully completed, presumably because dst is too small */ + assert(op==oend); + someMoreWork = 0; + break; + } zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0; - if (zcs->frameEnded) { - DEBUGLOG(5, "Frame completed on flush"); - someMoreWork = 0; + if (zcs->frameEnded) { + DEBUGLOG(5, "Frame completed on flush"); + someMoreWork = 0; ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); - break; - } - zcs->streamStage = zcss_load; + break; + } + zcs->streamStage = zcss_load; break; } - default: /* impossible */ - assert(0); + default: /* impossible */ + assert(0); } } - input->pos = ip - istart; - output->pos = op - ostart; + input->pos = ip - istart; + output->pos = op - ostart; if (zcs->frameEnded) return 0; return ZSTD_nextInputSizeHint(zcs); } @@ -5635,42 +5635,42 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input, ZSTD_EndDirective endOp) -{ +{ DEBUGLOG(5, "ZSTD_compressStream2, endOp=%u ", (unsigned)endOp); - /* check conditions */ + /* check conditions */ RETURN_ERROR_IF(output->pos > output->size, dstSize_tooSmall, "invalid output buffer"); RETURN_ERROR_IF(input->pos > input->size, srcSize_wrong, "invalid input buffer"); RETURN_ERROR_IF((U32)endOp > (U32)ZSTD_e_end, parameter_outOfBound, "invalid endDirective"); assert(cctx != NULL); - - /* transparent initialization stage */ - if (cctx->streamStage == zcss_init) { + + /* transparent initialization stage */ + if (cctx->streamStage == zcss_init) { FORWARD_IF_ERROR(ZSTD_CCtx_init_compressStream2(cctx, endOp, input->size), "CompressStream2 initialization failed"); ZSTD_setBufferExpectations(cctx, output, input); /* Set initial buffer expectations now that we've initialized */ } /* end of transparent initialization stage */ - + FORWARD_IF_ERROR(ZSTD_checkBufferStability(cctx, output, input, endOp), "invalid buffers"); - /* compression stage */ -#ifdef ZSTD_MULTITHREAD - if (cctx->appliedParams.nbWorkers > 0) { + /* compression stage */ +#ifdef ZSTD_MULTITHREAD + if (cctx->appliedParams.nbWorkers > 0) { size_t flushMin; - if (cctx->cParamsChanged) { - ZSTDMT_updateCParams_whileCompressing(cctx->mtctx, &cctx->requestedParams); - cctx->cParamsChanged = 0; - } + if (cctx->cParamsChanged) { + ZSTDMT_updateCParams_whileCompressing(cctx->mtctx, &cctx->requestedParams); + cctx->cParamsChanged = 0; + } for (;;) { size_t const ipos = input->pos; size_t const opos = output->pos; flushMin = ZSTDMT_compressStream_generic(cctx->mtctx, output, input, endOp); cctx->consumedSrcSize += (U64)(input->pos - ipos); cctx->producedCSize += (U64)(output->pos - opos); - if ( ZSTD_isError(flushMin) - || (endOp == ZSTD_e_end && flushMin == 0) ) { /* compression completed */ + if ( ZSTD_isError(flushMin) + || (endOp == ZSTD_e_end && flushMin == 0) ) { /* compression completed */ if (flushMin == 0) ZSTD_CCtx_trace(cctx, 0); ZSTD_CCtx_reset(cctx, ZSTD_reset_session_only); - } + } FORWARD_IF_ERROR(flushMin, "ZSTDMT_compressStream_generic failed"); if (endOp == ZSTD_e_continue) { @@ -5697,28 +5697,28 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, ZSTD_setBufferExpectations(cctx, output, input); return flushMin; } -#endif +#endif FORWARD_IF_ERROR( ZSTD_compressStream_generic(cctx, output, input, endOp) , ""); DEBUGLOG(5, "completed ZSTD_compressStream2"); ZSTD_setBufferExpectations(cctx, output, input); - return cctx->outBuffContentSize - cctx->outBuffFlushedSize; /* remaining to flush */ -} - + return cctx->outBuffContentSize - cctx->outBuffFlushedSize; /* remaining to flush */ +} + size_t ZSTD_compressStream2_simpleArgs ( - ZSTD_CCtx* cctx, - void* dst, size_t dstCapacity, size_t* dstPos, - const void* src, size_t srcSize, size_t* srcPos, - ZSTD_EndDirective endOp) -{ - ZSTD_outBuffer output = { dst, dstCapacity, *dstPos }; - ZSTD_inBuffer input = { src, srcSize, *srcPos }; + ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, size_t* dstPos, + const void* src, size_t srcSize, size_t* srcPos, + ZSTD_EndDirective endOp) +{ + ZSTD_outBuffer output = { dst, dstCapacity, *dstPos }; + ZSTD_inBuffer input = { src, srcSize, *srcPos }; /* ZSTD_compressStream2() will check validity of dstPos and srcPos */ size_t const cErr = ZSTD_compressStream2(cctx, &output, &input, endOp); - *dstPos = output.pos; - *srcPos = input.pos; - return cErr; -} - + *dstPos = output.pos; + *srcPos = input.pos; + return cErr; +} + size_t ZSTD_compress2(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize) @@ -5748,7 +5748,7 @@ size_t ZSTD_compress2(ZSTD_CCtx* cctx, return oPos; } } - + typedef struct { U32 idx; /* Index in array of ZSTD_Sequence */ U32 posInSequence; /* Position within sequence at idx */ @@ -6156,26 +6156,26 @@ size_t ZSTD_compressSequences(ZSTD_CCtx* const cctx, void* dst, size_t dstCapaci /*====== Finalize ======*/ /*! ZSTD_flushStream() : - * @return : amount of data remaining to flush */ + * @return : amount of data remaining to flush */ size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output) { - ZSTD_inBuffer input = { NULL, 0, 0 }; + ZSTD_inBuffer input = { NULL, 0, 0 }; return ZSTD_compressStream2(zcs, output, &input, ZSTD_e_flush); } size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output) { - ZSTD_inBuffer input = { NULL, 0, 0 }; + ZSTD_inBuffer input = { NULL, 0, 0 }; size_t const remainingToFlush = ZSTD_compressStream2(zcs, output, &input, ZSTD_e_end); FORWARD_IF_ERROR( remainingToFlush , "ZSTD_compressStream2 failed"); if (zcs->appliedParams.nbWorkers > 0) return remainingToFlush; /* minimal estimation */ /* single thread mode : attempt to calculate remaining to flush more precisely */ - { size_t const lastBlockSize = zcs->frameEnded ? 0 : ZSTD_BLOCKHEADERSIZE; + { size_t const lastBlockSize = zcs->frameEnded ? 0 : ZSTD_BLOCKHEADERSIZE; size_t const checksumSize = (size_t)(zcs->frameEnded ? 0 : zcs->appliedParams.fParams.checksumFlag * 4); size_t const toFlush = remainingToFlush + lastBlockSize + checksumSize; DEBUGLOG(4, "ZSTD_endStream : remaining to flush : %u", (unsigned)toFlush); - return toFlush; + return toFlush; } } @@ -6277,12 +6277,12 @@ static ZSTD_compressionParameters ZSTD_getCParams_internal(int compressionLevel, DEBUGLOG(5, "ZSTD_getCParams_internal (cLevel=%i)", compressionLevel); /* row */ - if (compressionLevel == 0) row = ZSTD_CLEVEL_DEFAULT; /* 0 == default */ + if (compressionLevel == 0) row = ZSTD_CLEVEL_DEFAULT; /* 0 == default */ else if (compressionLevel < 0) row = 0; /* entry 0 is baseline for fast mode */ else if (compressionLevel > ZSTD_MAX_CLEVEL) row = ZSTD_MAX_CLEVEL; else row = compressionLevel; - { ZSTD_compressionParameters cp = ZSTD_defaultCParameters[tableID][row]; + { ZSTD_compressionParameters cp = ZSTD_defaultCParameters[tableID][row]; DEBUGLOG(5, "ZSTD_getCParams_internal selected tableID: %u row: %u strat: %u", tableID, row, (U32)cp.strategy); /* acceleration factor */ if (compressionLevel < 0) { @@ -6310,10 +6310,10 @@ ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long l static ZSTD_parameters ZSTD_getParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode) { ZSTD_parameters params; ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, srcSizeHint, dictSize, mode); - DEBUGLOG(5, "ZSTD_getParams (cLevel=%i)", compressionLevel); + DEBUGLOG(5, "ZSTD_getParams (cLevel=%i)", compressionLevel); ZSTD_memset(¶ms, 0, sizeof(params)); params.cParams = cParams; - params.fParams.contentSizeFlag = 1; + params.fParams.contentSizeFlag = 1; return params; } diff --git a/contrib/libs/zstd/lib/compress/zstd_compress_internal.h b/contrib/libs/zstd/lib/compress/zstd_compress_internal.h index c406e794bd..4a493f015e 100644 --- a/contrib/libs/zstd/lib/compress/zstd_compress_internal.h +++ b/contrib/libs/zstd/lib/compress/zstd_compress_internal.h @@ -1,60 +1,60 @@ -/* +/* * Copyright (c) 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. - */ - -/* This header contains definitions - * that shall **only** be used by modules within lib/compress. - */ - -#ifndef ZSTD_COMPRESS_H -#define ZSTD_COMPRESS_H - -/*-************************************* -* Dependencies -***************************************/ + * 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. + */ + +/* This header contains definitions + * that shall **only** be used by modules within lib/compress. + */ + +#ifndef ZSTD_COMPRESS_H +#define ZSTD_COMPRESS_H + +/*-************************************* +* Dependencies +***************************************/ #include "../common/zstd_internal.h" #include "zstd_cwksp.h" -#ifdef ZSTD_MULTITHREAD -# include "zstdmt_compress.h" -#endif - -#if defined (__cplusplus) -extern "C" { -#endif - -/*-************************************* -* Constants -***************************************/ -#define kSearchStrength 8 -#define HASH_READ_SIZE 8 +#ifdef ZSTD_MULTITHREAD +# include "zstdmt_compress.h" +#endif + +#if defined (__cplusplus) +extern "C" { +#endif + +/*-************************************* +* Constants +***************************************/ +#define kSearchStrength 8 +#define HASH_READ_SIZE 8 #define ZSTD_DUBT_UNSORTED_MARK 1 /* For btlazy2 strategy, index ZSTD_DUBT_UNSORTED_MARK==1 means "unsorted". - It could be confused for a real successor at index "1", if sorted as larger than its predecessor. - It's not a big deal though : candidate will just be sorted again. + It could be confused for a real successor at index "1", if sorted as larger than its predecessor. + It's not a big deal though : candidate will just be sorted again. Additionally, candidate position 1 will be lost. - But candidate 1 cannot hide a large tree of candidates, so it's a minimal loss. + But candidate 1 cannot hide a large tree of candidates, so it's a minimal loss. The benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be mishandled after table re-use with a different strategy. This constant is required by ZSTD_compressBlock_btlazy2() and ZSTD_reduceTable_internal() */ - - -/*-************************************* -* Context memory management -***************************************/ -typedef enum { ZSTDcs_created=0, ZSTDcs_init, ZSTDcs_ongoing, ZSTDcs_ending } ZSTD_compressionStage_e; -typedef enum { zcss_init=0, zcss_load, zcss_flush } ZSTD_cStreamStage; - -typedef struct ZSTD_prefixDict_s { - const void* dict; - size_t dictSize; - ZSTD_dictContentType_e dictContentType; -} ZSTD_prefixDict; - -typedef struct { + + +/*-************************************* +* Context memory management +***************************************/ +typedef enum { ZSTDcs_created=0, ZSTDcs_init, ZSTDcs_ongoing, ZSTDcs_ending } ZSTD_compressionStage_e; +typedef enum { zcss_init=0, zcss_load, zcss_flush } ZSTD_cStreamStage; + +typedef struct ZSTD_prefixDict_s { + const void* dict; + size_t dictSize; + ZSTD_dictContentType_e dictContentType; +} ZSTD_prefixDict; + +typedef struct { void* dictBuffer; void const* dict; size_t dictSize; @@ -68,19 +68,19 @@ typedef struct { } ZSTD_hufCTables_t; typedef struct { - FSE_CTable offcodeCTable[FSE_CTABLE_SIZE_U32(OffFSELog, MaxOff)]; - FSE_CTable matchlengthCTable[FSE_CTABLE_SIZE_U32(MLFSELog, MaxML)]; - FSE_CTable litlengthCTable[FSE_CTABLE_SIZE_U32(LLFSELog, MaxLL)]; - FSE_repeat offcode_repeatMode; - FSE_repeat matchlength_repeatMode; - FSE_repeat litlength_repeatMode; + FSE_CTable offcodeCTable[FSE_CTABLE_SIZE_U32(OffFSELog, MaxOff)]; + FSE_CTable matchlengthCTable[FSE_CTABLE_SIZE_U32(MLFSELog, MaxML)]; + FSE_CTable litlengthCTable[FSE_CTABLE_SIZE_U32(LLFSELog, MaxLL)]; + FSE_repeat offcode_repeatMode; + FSE_repeat matchlength_repeatMode; + FSE_repeat litlength_repeatMode; } ZSTD_fseCTables_t; typedef struct { ZSTD_hufCTables_t huf; ZSTD_fseCTables_t fse; -} ZSTD_entropyCTables_t; - +} ZSTD_entropyCTables_t; + /*********************************************** * Entropy buffer statistics structs and funcs * ***********************************************/ @@ -89,7 +89,7 @@ typedef struct { * huffman tree description in hufDesBuffer. * hufDesSize refers to the size of huffman tree description in bytes. * This metadata is populated in ZSTD_buildBlockEntropyStats_literals() */ -typedef struct { +typedef struct { symbolEncodingType_e hType; BYTE hufDesBuffer[ZSTD_MAX_HUF_HEADER_SIZE]; size_t hufDesSize; @@ -131,9 +131,9 @@ size_t ZSTD_buildBlockEntropyStats(seqStore_t* seqStorePtr, typedef struct { U32 off; /* Offset sumtype code for the match, using ZSTD_storeSeq() format */ U32 len; /* Raw length of match */ -} ZSTD_match_t; - -typedef struct { +} ZSTD_match_t; + +typedef struct { U32 offset; /* Offset of sequence */ U32 litLength; /* Length of literals prior to match */ U32 matchLength; /* Raw length of match */ @@ -151,28 +151,28 @@ typedef struct { UNUSED_ATTR static const rawSeqStore_t kNullRawSeqStore = {NULL, 0, 0, 0, 0}; typedef struct { - int price; - U32 off; - U32 mlen; - U32 litlen; - U32 rep[ZSTD_REP_NUM]; -} ZSTD_optimal_t; - + int price; + U32 off; + U32 mlen; + U32 litlen; + U32 rep[ZSTD_REP_NUM]; +} ZSTD_optimal_t; + typedef enum { zop_dynamic=0, zop_predef } ZSTD_OptPrice_e; -typedef struct { - /* All tables are allocated inside cctx->workspace by ZSTD_resetCCtx_internal() */ +typedef struct { + /* All tables are allocated inside cctx->workspace by ZSTD_resetCCtx_internal() */ unsigned* litFreq; /* table of literals statistics, of size 256 */ unsigned* litLengthFreq; /* table of litLength statistics, of size (MaxLL+1) */ unsigned* matchLengthFreq; /* table of matchLength statistics, of size (MaxML+1) */ unsigned* offCodeFreq; /* table of offCode statistics, of size (MaxOff+1) */ ZSTD_match_t* matchTable; /* list of found matches, of size ZSTD_OPT_NUM+1 */ ZSTD_optimal_t* priceTable; /* All positions tracked by optimal parser, of size ZSTD_OPT_NUM+1 */ - - U32 litSum; /* nb of literals */ - U32 litLengthSum; /* nb of litLength codes */ - U32 matchLengthSum; /* nb of matchLength codes */ - U32 offCodeSum; /* nb of offset codes */ + + U32 litSum; /* nb of literals */ + U32 litLengthSum; /* nb of litLength codes */ + U32 matchLengthSum; /* nb of matchLength codes */ + U32 offCodeSum; /* nb of offset codes */ U32 litSumBasePrice; /* to compare to log2(litfreq) */ U32 litLengthSumBasePrice; /* to compare to log2(llfreq) */ U32 matchLengthSumBasePrice;/* to compare to log2(mlfreq) */ @@ -180,14 +180,14 @@ typedef struct { ZSTD_OptPrice_e priceType; /* prices can be determined dynamically, or follow a pre-defined cost structure */ const ZSTD_entropyCTables_t* symbolCosts; /* pre-calculated dictionary statistics */ ZSTD_paramSwitch_e literalCompressionMode; -} optState_t; - -typedef struct { - ZSTD_entropyCTables_t entropy; - U32 rep[ZSTD_REP_NUM]; -} ZSTD_compressedBlockState_t; - -typedef struct { +} optState_t; + +typedef struct { + ZSTD_entropyCTables_t entropy; + U32 rep[ZSTD_REP_NUM]; +} ZSTD_compressedBlockState_t; + +typedef struct { BYTE const* nextSrc; /* next block here to continue on current prefix */ BYTE const* base; /* All regular indexes relative to this position */ BYTE const* dictBase; /* extDict indexes relative to this position */ @@ -197,8 +197,8 @@ typedef struct { * ZSTD_window_init(). Useful for debugging coredumps * and for ZSTD_WINDOW_OVERFLOW_CORRECT_FREQUENTLY. */ -} ZSTD_window_t; - +} ZSTD_window_t; + #define ZSTD_WINDOW_START_INDEX 2 typedef struct ZSTD_matchState_t ZSTD_matchState_t; @@ -221,33 +221,33 @@ struct ZSTD_matchState_t { U16* tagTable; /* For row-based matchFinder: A row-based table containing the hashes and head index. */ U32 hashCache[ZSTD_ROW_HASH_CACHE_SIZE]; /* For row-based matchFinder: a cache of hashes to improve speed */ - U32* hashTable; - U32* hashTable3; - U32* chainTable; + U32* hashTable; + U32* hashTable3; + U32* chainTable; U32 forceNonContiguous; /* Non-zero if we should force non-contiguous load for the next window update. */ int dedicatedDictSearch; /* Indicates whether this matchState is using the * dedicated dictionary search structure. */ - optState_t opt; /* optimal parser state */ + optState_t opt; /* optimal parser state */ const ZSTD_matchState_t* dictMatchState; ZSTD_compressionParameters cParams; const rawSeqStore_t* ldmSeqStore; }; - -typedef struct { - ZSTD_compressedBlockState_t* prevCBlock; - ZSTD_compressedBlockState_t* nextCBlock; - ZSTD_matchState_t matchState; -} ZSTD_blockState_t; - -typedef struct { - U32 offset; - U32 checksum; -} ldmEntry_t; - -typedef struct { + +typedef struct { + ZSTD_compressedBlockState_t* prevCBlock; + ZSTD_compressedBlockState_t* nextCBlock; + ZSTD_matchState_t matchState; +} ZSTD_blockState_t; + +typedef struct { + U32 offset; + U32 checksum; +} ldmEntry_t; + +typedef struct { BYTE const* split; U32 hash; U32 checksum; @@ -257,57 +257,57 @@ typedef struct { #define LDM_BATCH_SIZE 64 typedef struct { - ZSTD_window_t window; /* State for the window round buffer management */ - ldmEntry_t* hashTable; + ZSTD_window_t window; /* State for the window round buffer management */ + ldmEntry_t* hashTable; U32 loadedDictEnd; - BYTE* bucketOffsets; /* Next position in bucket to insert entry */ + BYTE* bucketOffsets; /* Next position in bucket to insert entry */ size_t splitIndices[LDM_BATCH_SIZE]; ldmMatchCandidate_t matchCandidates[LDM_BATCH_SIZE]; -} ldmState_t; - -typedef struct { +} ldmState_t; + +typedef struct { ZSTD_paramSwitch_e enableLdm; /* ZSTD_ps_enable to enable LDM. ZSTD_ps_auto by default */ - U32 hashLog; /* Log size of hashTable */ - U32 bucketSizeLog; /* Log bucket size for collision resolution, at most 8 */ - U32 minMatchLength; /* Minimum match length */ + U32 hashLog; /* Log size of hashTable */ + U32 bucketSizeLog; /* Log bucket size for collision resolution, at most 8 */ + U32 minMatchLength; /* Minimum match length */ U32 hashRateLog; /* Log number of entries to skip */ - U32 windowLog; /* Window log for the LDM */ -} ldmParams_t; - -typedef struct { + U32 windowLog; /* Window log for the LDM */ +} ldmParams_t; + +typedef struct { int collectSequences; ZSTD_Sequence* seqStart; size_t seqIndex; size_t maxSequences; } SeqCollector; -struct ZSTD_CCtx_params_s { - ZSTD_format_e format; - ZSTD_compressionParameters cParams; - ZSTD_frameParameters fParams; - - int compressionLevel; - int forceWindow; /* force back-references to respect limit of - * 1<<wLog, even for dictionary */ +struct ZSTD_CCtx_params_s { + ZSTD_format_e format; + ZSTD_compressionParameters cParams; + ZSTD_frameParameters fParams; + + int compressionLevel; + int forceWindow; /* force back-references to respect limit of + * 1<<wLog, even for dictionary */ size_t targetCBlockSize; /* Tries to fit compressed block size to be around targetCBlockSize. * No target when targetCBlockSize == 0. * There is no guarantee on compressed block size */ int srcSizeHint; /* User's best guess of source size. * Hint is not valid when srcSizeHint == 0. * There is no guarantee that hint is close to actual source size */ - + ZSTD_dictAttachPref_e attachDictPref; ZSTD_paramSwitch_e literalCompressionMode; - /* Multithreading: used to pass parameters to mtctx */ + /* Multithreading: used to pass parameters to mtctx */ int nbWorkers; size_t jobSize; int overlapLog; int rsyncable; - - /* Long distance matching parameters */ - ldmParams_t ldmParams; - + + /* Long distance matching parameters */ + ldmParams_t ldmParams; + /* Dedicated dict search algorithm trigger */ int enableDedicatedDictSearch; @@ -328,10 +328,10 @@ struct ZSTD_CCtx_params_s { /* Always load a dictionary in ext-dict mode (not prefix mode)? */ int deterministicRefPrefix; - /* Internal use, for createCCtxParams() and freeCCtxParams() only */ - ZSTD_customMem customMem; -}; /* typedef'd to ZSTD_CCtx_params within "zstd.h" */ - + /* Internal use, for createCCtxParams() and freeCCtxParams() only */ + ZSTD_customMem customMem; +}; /* typedef'd to ZSTD_CCtx_params within "zstd.h" */ + #define COMPRESS_SEQUENCES_WORKSPACE_SIZE (sizeof(unsigned) * (MaxSeq + 2)) #define ENTROPY_WORKSPACE_SIZE (HUF_WORKSPACE_SIZE + COMPRESS_SEQUENCES_WORKSPACE_SIZE) @@ -361,66 +361,66 @@ typedef struct { ZSTD_entropyCTablesMetadata_t entropyMetadata; } ZSTD_blockSplitCtx; -struct ZSTD_CCtx_s { - ZSTD_compressionStage_e stage; - int cParamsChanged; /* == 1 if cParams(except wlog) or compression level are changed in requestedParams. Triggers transmission of new params to ZSTDMT (if available) then reset to 0. */ - int bmi2; /* == 1 if the CPU supports BMI2 and 0 otherwise. CPU support is determined dynamically once per context lifetime. */ - ZSTD_CCtx_params requestedParams; - ZSTD_CCtx_params appliedParams; +struct ZSTD_CCtx_s { + ZSTD_compressionStage_e stage; + int cParamsChanged; /* == 1 if cParams(except wlog) or compression level are changed in requestedParams. Triggers transmission of new params to ZSTDMT (if available) then reset to 0. */ + int bmi2; /* == 1 if the CPU supports BMI2 and 0 otherwise. CPU support is determined dynamically once per context lifetime. */ + ZSTD_CCtx_params requestedParams; + ZSTD_CCtx_params appliedParams; ZSTD_CCtx_params simpleApiParams; /* Param storage used by the simple API - not sticky. Must only be used in top-level simple API functions for storage. */ - U32 dictID; + U32 dictID; size_t dictContentSize; ZSTD_cwksp workspace; /* manages buffer for dynamic allocations */ - size_t blockSize; - unsigned long long pledgedSrcSizePlusOne; /* this way, 0 (default) == unknown */ - unsigned long long consumedSrcSize; - unsigned long long producedCSize; - XXH64_state_t xxhState; - ZSTD_customMem customMem; + size_t blockSize; + unsigned long long pledgedSrcSizePlusOne; /* this way, 0 (default) == unknown */ + unsigned long long consumedSrcSize; + unsigned long long producedCSize; + XXH64_state_t xxhState; + ZSTD_customMem customMem; ZSTD_threadPool* pool; - size_t staticSize; + size_t staticSize; SeqCollector seqCollector; int isFirstBlock; int initialized; - - seqStore_t seqStore; /* sequences storage ptrs */ - ldmState_t ldmState; /* long distance matching state */ - rawSeq* ldmSequences; /* Storage for the ldm output sequences */ - size_t maxNbLdmSequences; - rawSeqStore_t externSeqStore; /* Mutable reference to external sequences */ - ZSTD_blockState_t blockState; + + seqStore_t seqStore; /* sequences storage ptrs */ + ldmState_t ldmState; /* long distance matching state */ + rawSeq* ldmSequences; /* Storage for the ldm output sequences */ + size_t maxNbLdmSequences; + rawSeqStore_t externSeqStore; /* Mutable reference to external sequences */ + ZSTD_blockState_t blockState; U32* entropyWorkspace; /* entropy workspace of ENTROPY_WORKSPACE_SIZE bytes */ - + /* Whether we are streaming or not */ ZSTD_buffered_policy_e bufferedPolicy; - /* streaming */ - char* inBuff; - size_t inBuffSize; - size_t inToCompress; - size_t inBuffPos; - size_t inBuffTarget; - char* outBuff; - size_t outBuffSize; - size_t outBuffContentSize; - size_t outBuffFlushedSize; - ZSTD_cStreamStage streamStage; - U32 frameEnded; - + /* streaming */ + char* inBuff; + size_t inBuffSize; + size_t inToCompress; + size_t inBuffPos; + size_t inBuffTarget; + char* outBuff; + size_t outBuffSize; + size_t outBuffContentSize; + size_t outBuffFlushedSize; + ZSTD_cStreamStage streamStage; + U32 frameEnded; + /* Stable in/out buffer verification */ ZSTD_inBuffer expectedInBuffer; size_t expectedOutBufferSize; - /* Dictionary */ + /* Dictionary */ ZSTD_localDict localDict; - const ZSTD_CDict* cdict; - ZSTD_prefixDict prefixDict; /* single-usage dictionary */ - - /* Multi-threading */ -#ifdef ZSTD_MULTITHREAD - ZSTDMT_CCtx* mtctx; -#endif + const ZSTD_CDict* cdict; + ZSTD_prefixDict prefixDict; /* single-usage dictionary */ + + /* Multi-threading */ +#ifdef ZSTD_MULTITHREAD + ZSTDMT_CCtx* mtctx; +#endif /* Tracing */ #if ZSTD_TRACE @@ -429,10 +429,10 @@ struct ZSTD_CCtx_s { /* Workspace for block splitter */ ZSTD_blockSplitCtx blockSplitCtx; -}; - +}; + typedef enum { ZSTD_dtlm_fast, ZSTD_dtlm_full } ZSTD_dictTableLoadMethod_e; - + typedef enum { ZSTD_noDict = 0, ZSTD_extDict = 1, @@ -460,43 +460,43 @@ typedef enum { */ } ZSTD_cParamMode_e; -typedef size_t (*ZSTD_blockCompressor) ( - ZSTD_matchState_t* bs, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +typedef size_t (*ZSTD_blockCompressor) ( + ZSTD_matchState_t* bs, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, ZSTD_paramSwitch_e rowMatchfinderMode, ZSTD_dictMode_e dictMode); - - -MEM_STATIC U32 ZSTD_LLcode(U32 litLength) -{ - static const BYTE LL_Code[64] = { 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 16, 17, 17, 18, 18, 19, 19, - 20, 20, 20, 20, 21, 21, 21, 21, - 22, 22, 22, 22, 22, 22, 22, 22, - 23, 23, 23, 23, 23, 23, 23, 23, - 24, 24, 24, 24, 24, 24, 24, 24, - 24, 24, 24, 24, 24, 24, 24, 24 }; - static const U32 LL_deltaCode = 19; - return (litLength > 63) ? ZSTD_highbit32(litLength) + LL_deltaCode : LL_Code[litLength]; -} - -/* ZSTD_MLcode() : - * note : mlBase = matchLength - MINMATCH; - * because it's the format it's stored in seqStore->sequences */ -MEM_STATIC U32 ZSTD_MLcode(U32 mlBase) -{ - static const BYTE ML_Code[128] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, - 32, 32, 33, 33, 34, 34, 35, 35, 36, 36, 36, 36, 37, 37, 37, 37, - 38, 38, 38, 38, 38, 38, 38, 38, 39, 39, 39, 39, 39, 39, 39, 39, - 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, - 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, - 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, - 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42 }; - static const U32 ML_deltaCode = 36; - return (mlBase > 127) ? ZSTD_highbit32(mlBase) + ML_deltaCode : ML_Code[mlBase]; -} - + + +MEM_STATIC U32 ZSTD_LLcode(U32 litLength) +{ + static const BYTE LL_Code[64] = { 0, 1, 2, 3, 4, 5, 6, 7, + 8, 9, 10, 11, 12, 13, 14, 15, + 16, 16, 17, 17, 18, 18, 19, 19, + 20, 20, 20, 20, 21, 21, 21, 21, + 22, 22, 22, 22, 22, 22, 22, 22, + 23, 23, 23, 23, 23, 23, 23, 23, + 24, 24, 24, 24, 24, 24, 24, 24, + 24, 24, 24, 24, 24, 24, 24, 24 }; + static const U32 LL_deltaCode = 19; + return (litLength > 63) ? ZSTD_highbit32(litLength) + LL_deltaCode : LL_Code[litLength]; +} + +/* ZSTD_MLcode() : + * note : mlBase = matchLength - MINMATCH; + * because it's the format it's stored in seqStore->sequences */ +MEM_STATIC U32 ZSTD_MLcode(U32 mlBase) +{ + static const BYTE ML_Code[128] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, + 32, 32, 33, 33, 34, 34, 35, 35, 36, 36, 36, 36, 37, 37, 37, 37, + 38, 38, 38, 38, 38, 38, 38, 38, 39, 39, 39, 39, 39, 39, 39, 39, + 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, + 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, + 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, + 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42 }; + static const U32 ML_deltaCode = 36; + return (mlBase > 127) ? ZSTD_highbit32(mlBase) + ML_deltaCode : ML_Code[mlBase]; +} + /* ZSTD_cParam_withinBounds: * @return 1 if value is within cParam bounds, * 0 otherwise */ @@ -590,30 +590,30 @@ ZSTD_safecopyLiterals(BYTE* op, BYTE const* ip, BYTE const* const iend, BYTE con #define STORED_TO_OFFBASE(o) ((o)+1) #define OFFBASE_TO_STORED(o) ((o)-1) -/*! ZSTD_storeSeq() : +/*! ZSTD_storeSeq() : * Store a sequence (litlen, litPtr, offCode and matchLength) into seqStore_t. * @offBase_minus1 : Users should use employ macros STORE_REPCODE_X and STORE_OFFSET(). * @matchLength : must be >= MINMATCH * Allowed to overread literals up to litLimit. -*/ +*/ HINT_INLINE UNUSED_ATTR void ZSTD_storeSeq(seqStore_t* seqStorePtr, size_t litLength, const BYTE* literals, const BYTE* litLimit, U32 offBase_minus1, size_t matchLength) -{ +{ BYTE const* const litLimit_w = litLimit - WILDCOPY_OVERLENGTH; BYTE const* const litEnd = literals + litLength; #if defined(DEBUGLEVEL) && (DEBUGLEVEL >= 6) - static const BYTE* g_start = NULL; - if (g_start==NULL) g_start = (const BYTE*)literals; /* note : index only works for compression within a single segment */ - { U32 const pos = (U32)((const BYTE*)literals - g_start); + static const BYTE* g_start = NULL; + if (g_start==NULL) g_start = (const BYTE*)literals; /* note : index only works for compression within a single segment */ + { U32 const pos = (U32)((const BYTE*)literals - g_start); DEBUGLOG(6, "Cpos%7u :%3u literals, match%4u bytes at offCode%7u", pos, (U32)litLength, (U32)matchLength, (U32)offBase_minus1); - } -#endif + } +#endif assert((size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart) < seqStorePtr->maxNbSeq); - /* copy Literals */ + /* copy Literals */ assert(seqStorePtr->maxNbLit <= 128 KB); assert(seqStorePtr->lit + litLength <= seqStorePtr->litStart + seqStorePtr->maxNbLit); assert(literals + litLength <= litLimit); @@ -629,20 +629,20 @@ ZSTD_storeSeq(seqStore_t* seqStorePtr, } else { ZSTD_safecopyLiterals(seqStorePtr->lit, literals, litEnd, litLimit_w); } - seqStorePtr->lit += litLength; - - /* literal Length */ - if (litLength>0xFFFF) { + seqStorePtr->lit += litLength; + + /* literal Length */ + if (litLength>0xFFFF) { assert(seqStorePtr->longLengthType == ZSTD_llt_none); /* there can only be a single long length */ seqStorePtr->longLengthType = ZSTD_llt_literalLength; - seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart); - } - seqStorePtr->sequences[0].litLength = (U16)litLength; - - /* match offset */ + seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart); + } + seqStorePtr->sequences[0].litLength = (U16)litLength; + + /* match offset */ seqStorePtr->sequences[0].offBase = STORED_TO_OFFBASE(offBase_minus1); - - /* match Length */ + + /* match Length */ assert(matchLength >= MINMATCH); { size_t const mlBase = matchLength - MINMATCH; if (mlBase>0xFFFF) { @@ -651,11 +651,11 @@ ZSTD_storeSeq(seqStore_t* seqStorePtr, seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart); } seqStorePtr->sequences[0].mlBase = (U16)mlBase; - } - - seqStorePtr->sequences++; -} - + } + + seqStorePtr->sequences++; +} + /* ZSTD_updateRep() : * updates in-place @rep (array of repeat offsets) * @offBase_minus1 : sum-type, with same numeric representation as ZSTD_storeSeq() @@ -679,7 +679,7 @@ ZSTD_updateRep(U32 rep[ZSTD_REP_NUM], U32 const offBase_minus1, U32 const ll0) } } } - + typedef struct repcodes_s { U32 rep[3]; } repcodes_t; @@ -694,14 +694,14 @@ ZSTD_newRep(U32 const rep[ZSTD_REP_NUM], U32 const offBase_minus1, U32 const ll0 } -/*-************************************* -* Match length counter -***************************************/ -static unsigned ZSTD_NbCommonBytes (size_t val) -{ - if (MEM_isLittleEndian()) { - if (MEM_64bits()) { -# if defined(_MSC_VER) && defined(_WIN64) +/*-************************************* +* Match length counter +***************************************/ +static unsigned ZSTD_NbCommonBytes (size_t val) +{ + if (MEM_isLittleEndian()) { + if (MEM_64bits()) { +# if defined(_MSC_VER) && defined(_WIN64) # if STATIC_BMI2 return _tzcnt_u64(val) >> 3; # else @@ -714,21 +714,21 @@ static unsigned ZSTD_NbCommonBytes (size_t val) __assume(0); } # endif -# elif defined(__GNUC__) && (__GNUC__ >= 4) - return (__builtin_ctzll((U64)val) >> 3); -# else - static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, - 0, 3, 1, 3, 1, 4, 2, 7, - 0, 2, 3, 6, 1, 5, 3, 5, - 1, 3, 4, 4, 2, 5, 6, 7, - 7, 0, 1, 2, 3, 3, 4, 6, - 2, 6, 5, 5, 3, 4, 5, 6, - 7, 1, 2, 4, 6, 4, 4, 5, - 7, 2, 6, 5, 7, 6, 7, 7 }; - return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58]; -# endif - } else { /* 32 bits */ -# if defined(_MSC_VER) +# elif defined(__GNUC__) && (__GNUC__ >= 4) + return (__builtin_ctzll((U64)val) >> 3); +# else + static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, + 0, 3, 1, 3, 1, 4, 2, 7, + 0, 2, 3, 6, 1, 5, 3, 5, + 1, 3, 4, 4, 2, 5, 6, 7, + 7, 0, 1, 2, 3, 3, 4, 6, + 2, 6, 5, 5, 3, 4, 5, 6, + 7, 1, 2, 4, 6, 4, 4, 5, + 7, 2, 6, 5, 7, 6, 7, 7 }; + return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58]; +# endif + } else { /* 32 bits */ +# if defined(_MSC_VER) if (val != 0) { unsigned long r; _BitScanForward(&r, (U32)val); @@ -737,19 +737,19 @@ static unsigned ZSTD_NbCommonBytes (size_t val) /* Should not reach this code path */ __assume(0); } -# elif defined(__GNUC__) && (__GNUC__ >= 3) - return (__builtin_ctz((U32)val) >> 3); -# else - static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, - 3, 2, 2, 1, 3, 2, 0, 1, - 3, 3, 1, 2, 2, 2, 2, 0, - 3, 1, 2, 0, 1, 0, 1, 1 }; - return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27]; -# endif - } - } else { /* Big Endian CPU */ - if (MEM_64bits()) { -# if defined(_MSC_VER) && defined(_WIN64) +# elif defined(__GNUC__) && (__GNUC__ >= 3) + return (__builtin_ctz((U32)val) >> 3); +# else + static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, + 3, 2, 2, 1, 3, 2, 0, 1, + 3, 3, 1, 2, 2, 2, 2, 0, + 3, 1, 2, 0, 1, 0, 1, 1 }; + return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27]; +# endif + } + } else { /* Big Endian CPU */ + if (MEM_64bits()) { +# if defined(_MSC_VER) && defined(_WIN64) # if STATIC_BMI2 return _lzcnt_u64(val) >> 3; # else @@ -762,18 +762,18 @@ static unsigned ZSTD_NbCommonBytes (size_t val) __assume(0); } # endif -# elif defined(__GNUC__) && (__GNUC__ >= 4) - return (__builtin_clzll(val) >> 3); -# else - unsigned r; - const unsigned n32 = sizeof(size_t)*4; /* calculate this way due to compiler complaining in 32-bits mode */ - if (!(val>>n32)) { r=4; } else { r=0; val>>=n32; } - if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } - r += (!val); - return r; -# endif - } else { /* 32 bits */ -# if defined(_MSC_VER) +# elif defined(__GNUC__) && (__GNUC__ >= 4) + return (__builtin_clzll(val) >> 3); +# else + unsigned r; + const unsigned n32 = sizeof(size_t)*4; /* calculate this way due to compiler complaining in 32-bits mode */ + if (!(val>>n32)) { r=4; } else { r=0; val>>=n32; } + if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } + r += (!val); + return r; +# endif + } else { /* 32 bits */ +# if defined(_MSC_VER) if (val != 0) { unsigned long r; _BitScanReverse(&r, (unsigned long)val); @@ -782,100 +782,100 @@ static unsigned ZSTD_NbCommonBytes (size_t val) /* Should not reach this code path */ __assume(0); } -# elif defined(__GNUC__) && (__GNUC__ >= 3) - return (__builtin_clz((U32)val) >> 3); -# else - unsigned r; - if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } - r += (!val); - return r; -# endif - } } -} - - -MEM_STATIC size_t ZSTD_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* const pInLimit) -{ - const BYTE* const pStart = pIn; - const BYTE* const pInLoopLimit = pInLimit - (sizeof(size_t)-1); - - if (pIn < pInLoopLimit) { - { size_t const diff = MEM_readST(pMatch) ^ MEM_readST(pIn); - if (diff) return ZSTD_NbCommonBytes(diff); } - pIn+=sizeof(size_t); pMatch+=sizeof(size_t); - while (pIn < pInLoopLimit) { - size_t const diff = MEM_readST(pMatch) ^ MEM_readST(pIn); - if (!diff) { pIn+=sizeof(size_t); pMatch+=sizeof(size_t); continue; } - pIn += ZSTD_NbCommonBytes(diff); - return (size_t)(pIn - pStart); - } } - if (MEM_64bits() && (pIn<(pInLimit-3)) && (MEM_read32(pMatch) == MEM_read32(pIn))) { pIn+=4; pMatch+=4; } - if ((pIn<(pInLimit-1)) && (MEM_read16(pMatch) == MEM_read16(pIn))) { pIn+=2; pMatch+=2; } - if ((pIn<pInLimit) && (*pMatch == *pIn)) pIn++; - return (size_t)(pIn - pStart); -} - -/** ZSTD_count_2segments() : - * can count match length with `ip` & `match` in 2 different segments. - * convention : on reaching mEnd, match count continue starting from iStart - */ -MEM_STATIC size_t -ZSTD_count_2segments(const BYTE* ip, const BYTE* match, - const BYTE* iEnd, const BYTE* mEnd, const BYTE* iStart) -{ - const BYTE* const vEnd = MIN( ip + (mEnd - match), iEnd); - size_t const matchLength = ZSTD_count(ip, match, vEnd); - if (match + matchLength != mEnd) return matchLength; +# elif defined(__GNUC__) && (__GNUC__ >= 3) + return (__builtin_clz((U32)val) >> 3); +# else + unsigned r; + if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } + r += (!val); + return r; +# endif + } } +} + + +MEM_STATIC size_t ZSTD_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* const pInLimit) +{ + const BYTE* const pStart = pIn; + const BYTE* const pInLoopLimit = pInLimit - (sizeof(size_t)-1); + + if (pIn < pInLoopLimit) { + { size_t const diff = MEM_readST(pMatch) ^ MEM_readST(pIn); + if (diff) return ZSTD_NbCommonBytes(diff); } + pIn+=sizeof(size_t); pMatch+=sizeof(size_t); + while (pIn < pInLoopLimit) { + size_t const diff = MEM_readST(pMatch) ^ MEM_readST(pIn); + if (!diff) { pIn+=sizeof(size_t); pMatch+=sizeof(size_t); continue; } + pIn += ZSTD_NbCommonBytes(diff); + return (size_t)(pIn - pStart); + } } + if (MEM_64bits() && (pIn<(pInLimit-3)) && (MEM_read32(pMatch) == MEM_read32(pIn))) { pIn+=4; pMatch+=4; } + if ((pIn<(pInLimit-1)) && (MEM_read16(pMatch) == MEM_read16(pIn))) { pIn+=2; pMatch+=2; } + if ((pIn<pInLimit) && (*pMatch == *pIn)) pIn++; + return (size_t)(pIn - pStart); +} + +/** ZSTD_count_2segments() : + * can count match length with `ip` & `match` in 2 different segments. + * convention : on reaching mEnd, match count continue starting from iStart + */ +MEM_STATIC size_t +ZSTD_count_2segments(const BYTE* ip, const BYTE* match, + const BYTE* iEnd, const BYTE* mEnd, const BYTE* iStart) +{ + const BYTE* const vEnd = MIN( ip + (mEnd - match), iEnd); + size_t const matchLength = ZSTD_count(ip, match, vEnd); + if (match + matchLength != mEnd) return matchLength; DEBUGLOG(7, "ZSTD_count_2segments: found a 2-parts match (current length==%zu)", matchLength); DEBUGLOG(7, "distance from match beginning to end dictionary = %zi", mEnd - match); DEBUGLOG(7, "distance from current pos to end buffer = %zi", iEnd - ip); DEBUGLOG(7, "next byte : ip==%02X, istart==%02X", ip[matchLength], *iStart); DEBUGLOG(7, "final match length = %zu", matchLength + ZSTD_count(ip+matchLength, iStart, iEnd)); - return matchLength + ZSTD_count(ip+matchLength, iStart, iEnd); -} - - -/*-************************************* - * Hashes - ***************************************/ -static const U32 prime3bytes = 506832829U; -static U32 ZSTD_hash3(U32 u, U32 h) { return ((u << (32-24)) * prime3bytes) >> (32-h) ; } -MEM_STATIC size_t ZSTD_hash3Ptr(const void* ptr, U32 h) { return ZSTD_hash3(MEM_readLE32(ptr), h); } /* only in zstd_opt.h */ - -static const U32 prime4bytes = 2654435761U; -static U32 ZSTD_hash4(U32 u, U32 h) { return (u * prime4bytes) >> (32-h) ; } -static size_t ZSTD_hash4Ptr(const void* ptr, U32 h) { return ZSTD_hash4(MEM_read32(ptr), h); } - -static const U64 prime5bytes = 889523592379ULL; -static size_t ZSTD_hash5(U64 u, U32 h) { return (size_t)(((u << (64-40)) * prime5bytes) >> (64-h)) ; } -static size_t ZSTD_hash5Ptr(const void* p, U32 h) { return ZSTD_hash5(MEM_readLE64(p), h); } - -static const U64 prime6bytes = 227718039650203ULL; -static size_t ZSTD_hash6(U64 u, U32 h) { return (size_t)(((u << (64-48)) * prime6bytes) >> (64-h)) ; } -static size_t ZSTD_hash6Ptr(const void* p, U32 h) { return ZSTD_hash6(MEM_readLE64(p), h); } - -static const U64 prime7bytes = 58295818150454627ULL; -static size_t ZSTD_hash7(U64 u, U32 h) { return (size_t)(((u << (64-56)) * prime7bytes) >> (64-h)) ; } -static size_t ZSTD_hash7Ptr(const void* p, U32 h) { return ZSTD_hash7(MEM_readLE64(p), h); } - -static const U64 prime8bytes = 0xCF1BBCDCB7A56463ULL; -static size_t ZSTD_hash8(U64 u, U32 h) { return (size_t)(((u) * prime8bytes) >> (64-h)) ; } -static size_t ZSTD_hash8Ptr(const void* p, U32 h) { return ZSTD_hash8(MEM_readLE64(p), h); } - + return matchLength + ZSTD_count(ip+matchLength, iStart, iEnd); +} + + +/*-************************************* + * Hashes + ***************************************/ +static const U32 prime3bytes = 506832829U; +static U32 ZSTD_hash3(U32 u, U32 h) { return ((u << (32-24)) * prime3bytes) >> (32-h) ; } +MEM_STATIC size_t ZSTD_hash3Ptr(const void* ptr, U32 h) { return ZSTD_hash3(MEM_readLE32(ptr), h); } /* only in zstd_opt.h */ + +static const U32 prime4bytes = 2654435761U; +static U32 ZSTD_hash4(U32 u, U32 h) { return (u * prime4bytes) >> (32-h) ; } +static size_t ZSTD_hash4Ptr(const void* ptr, U32 h) { return ZSTD_hash4(MEM_read32(ptr), h); } + +static const U64 prime5bytes = 889523592379ULL; +static size_t ZSTD_hash5(U64 u, U32 h) { return (size_t)(((u << (64-40)) * prime5bytes) >> (64-h)) ; } +static size_t ZSTD_hash5Ptr(const void* p, U32 h) { return ZSTD_hash5(MEM_readLE64(p), h); } + +static const U64 prime6bytes = 227718039650203ULL; +static size_t ZSTD_hash6(U64 u, U32 h) { return (size_t)(((u << (64-48)) * prime6bytes) >> (64-h)) ; } +static size_t ZSTD_hash6Ptr(const void* p, U32 h) { return ZSTD_hash6(MEM_readLE64(p), h); } + +static const U64 prime7bytes = 58295818150454627ULL; +static size_t ZSTD_hash7(U64 u, U32 h) { return (size_t)(((u << (64-56)) * prime7bytes) >> (64-h)) ; } +static size_t ZSTD_hash7Ptr(const void* p, U32 h) { return ZSTD_hash7(MEM_readLE64(p), h); } + +static const U64 prime8bytes = 0xCF1BBCDCB7A56463ULL; +static size_t ZSTD_hash8(U64 u, U32 h) { return (size_t)(((u) * prime8bytes) >> (64-h)) ; } +static size_t ZSTD_hash8Ptr(const void* p, U32 h) { return ZSTD_hash8(MEM_readLE64(p), h); } + MEM_STATIC FORCE_INLINE_ATTR size_t ZSTD_hashPtr(const void* p, U32 hBits, U32 mls) -{ - switch(mls) - { - default: - case 4: return ZSTD_hash4Ptr(p, hBits); - case 5: return ZSTD_hash5Ptr(p, hBits); - case 6: return ZSTD_hash6Ptr(p, hBits); - case 7: return ZSTD_hash7Ptr(p, hBits); - case 8: return ZSTD_hash8Ptr(p, hBits); - } -} - +{ + switch(mls) + { + default: + case 4: return ZSTD_hash4Ptr(p, hBits); + case 5: return ZSTD_hash5Ptr(p, hBits); + case 6: return ZSTD_hash6Ptr(p, hBits); + case 7: return ZSTD_hash7Ptr(p, hBits); + case 8: return ZSTD_hash8Ptr(p, hBits); + } +} + /** ZSTD_ipow() : * Return base^exponent. */ @@ -934,32 +934,32 @@ MEM_STATIC U64 ZSTD_rollingHash_rotate(U64 hash, BYTE toRemove, BYTE toAdd, U64 return hash; } -/*-************************************* -* Round buffer management -***************************************/ +/*-************************************* +* Round buffer management +***************************************/ #if (ZSTD_WINDOWLOG_MAX_64 > 31) # error "ZSTD_WINDOWLOG_MAX is too large : would overflow ZSTD_CURRENT_MAX" #endif -/* Max current allowed */ -#define ZSTD_CURRENT_MAX ((3U << 29) + (1U << ZSTD_WINDOWLOG_MAX)) -/* Maximum chunk size before overflow correction needs to be called again */ -#define ZSTD_CHUNKSIZE_MAX \ - ( ((U32)-1) /* Maximum ending current index */ \ - - ZSTD_CURRENT_MAX) /* Maximum beginning lowLimit */ - -/** - * ZSTD_window_clear(): - * Clears the window containing the history by simply setting it to empty. - */ -MEM_STATIC void ZSTD_window_clear(ZSTD_window_t* window) -{ - size_t const endT = (size_t)(window->nextSrc - window->base); - U32 const end = (U32)endT; - - window->lowLimit = end; - window->dictLimit = end; -} - +/* Max current allowed */ +#define ZSTD_CURRENT_MAX ((3U << 29) + (1U << ZSTD_WINDOWLOG_MAX)) +/* Maximum chunk size before overflow correction needs to be called again */ +#define ZSTD_CHUNKSIZE_MAX \ + ( ((U32)-1) /* Maximum ending current index */ \ + - ZSTD_CURRENT_MAX) /* Maximum beginning lowLimit */ + +/** + * ZSTD_window_clear(): + * Clears the window containing the history by simply setting it to empty. + */ +MEM_STATIC void ZSTD_window_clear(ZSTD_window_t* window) +{ + size_t const endT = (size_t)(window->nextSrc - window->base); + U32 const end = (U32)endT; + + window->lowLimit = end; + window->dictLimit = end; +} + MEM_STATIC U32 ZSTD_window_isEmpty(ZSTD_window_t const window) { return window.dictLimit == ZSTD_WINDOW_START_INDEX && @@ -967,16 +967,16 @@ MEM_STATIC U32 ZSTD_window_isEmpty(ZSTD_window_t const window) (window.nextSrc - window.base) == ZSTD_WINDOW_START_INDEX; } -/** - * ZSTD_window_hasExtDict(): - * Returns non-zero if the window has a non-empty extDict. - */ -MEM_STATIC U32 ZSTD_window_hasExtDict(ZSTD_window_t const window) -{ - return window.lowLimit < window.dictLimit; -} - -/** +/** + * ZSTD_window_hasExtDict(): + * Returns non-zero if the window has a non-empty extDict. + */ +MEM_STATIC U32 ZSTD_window_hasExtDict(ZSTD_window_t const window) +{ + return window.lowLimit < window.dictLimit; +} + +/** * ZSTD_matchState_dictMode(): * Inspects the provided matchState and figures out what dictMode should be * passed to the compressor. @@ -1038,17 +1038,17 @@ MEM_STATIC U32 ZSTD_window_canOverflowCorrect(ZSTD_window_t const window, } /** - * ZSTD_window_needOverflowCorrection(): - * Returns non-zero if the indices are getting too large and need overflow - * protection. - */ -MEM_STATIC U32 ZSTD_window_needOverflowCorrection(ZSTD_window_t const window, + * ZSTD_window_needOverflowCorrection(): + * Returns non-zero if the indices are getting too large and need overflow + * protection. + */ +MEM_STATIC U32 ZSTD_window_needOverflowCorrection(ZSTD_window_t const window, U32 cycleLog, U32 maxDist, U32 loadedDictEnd, void const* src, - void const* srcEnd) -{ + void const* srcEnd) +{ U32 const curr = (U32)((BYTE const*)srcEnd - window.base); if (ZSTD_WINDOW_OVERFLOW_CORRECT_FREQUENTLY) { if (ZSTD_window_canOverflowCorrect(window, cycleLog, maxDist, loadedDictEnd, src)) { @@ -1056,39 +1056,39 @@ MEM_STATIC U32 ZSTD_window_needOverflowCorrection(ZSTD_window_t const window, } } return curr > ZSTD_CURRENT_MAX; -} - -/** - * ZSTD_window_correctOverflow(): - * Reduces the indices to protect from index overflow. - * Returns the correction made to the indices, which must be applied to every - * stored index. - * - * The least significant cycleLog bits of the indices must remain the same, - * which may be 0. Every index up to maxDist in the past must be valid. - */ -MEM_STATIC U32 ZSTD_window_correctOverflow(ZSTD_window_t* window, U32 cycleLog, - U32 maxDist, void const* src) -{ - /* preemptive overflow correction: - * 1. correction is large enough: - * lowLimit > (3<<29) ==> current > 3<<29 + 1<<windowLog - * 1<<windowLog <= newCurrent < 1<<chainLog + 1<<windowLog - * - * current - newCurrent - * > (3<<29 + 1<<windowLog) - (1<<windowLog + 1<<chainLog) - * > (3<<29) - (1<<chainLog) - * > (3<<29) - (1<<30) (NOTE: chainLog <= 30) - * > 1<<29 - * - * 2. (ip+ZSTD_CHUNKSIZE_MAX - cctx->base) doesn't overflow: - * After correction, current is less than (1<<chainLog + 1<<windowLog). - * In 64-bit mode we are safe, because we have 64-bit ptrdiff_t. - * In 32-bit mode we are safe, because (chainLog <= 29), so - * ip+ZSTD_CHUNKSIZE_MAX - cctx->base < 1<<32. - * 3. (cctx->lowLimit + 1<<windowLog) < 1<<32: - * windowLog <= 31 ==> 3<<29 + 1<<windowLog < 7<<29 < 1<<32. - */ +} + +/** + * ZSTD_window_correctOverflow(): + * Reduces the indices to protect from index overflow. + * Returns the correction made to the indices, which must be applied to every + * stored index. + * + * The least significant cycleLog bits of the indices must remain the same, + * which may be 0. Every index up to maxDist in the past must be valid. + */ +MEM_STATIC U32 ZSTD_window_correctOverflow(ZSTD_window_t* window, U32 cycleLog, + U32 maxDist, void const* src) +{ + /* preemptive overflow correction: + * 1. correction is large enough: + * lowLimit > (3<<29) ==> current > 3<<29 + 1<<windowLog + * 1<<windowLog <= newCurrent < 1<<chainLog + 1<<windowLog + * + * current - newCurrent + * > (3<<29 + 1<<windowLog) - (1<<windowLog + 1<<chainLog) + * > (3<<29) - (1<<chainLog) + * > (3<<29) - (1<<30) (NOTE: chainLog <= 30) + * > 1<<29 + * + * 2. (ip+ZSTD_CHUNKSIZE_MAX - cctx->base) doesn't overflow: + * After correction, current is less than (1<<chainLog + 1<<windowLog). + * In 64-bit mode we are safe, because we have 64-bit ptrdiff_t. + * In 32-bit mode we are safe, because (chainLog <= 29), so + * ip+ZSTD_CHUNKSIZE_MAX - cctx->base < 1<<32. + * 3. (cctx->lowLimit + 1<<windowLog) < 1<<32: + * windowLog <= 31 ==> 3<<29 + 1<<windowLog < 7<<29 < 1<<32. + */ U32 const cycleSize = 1u << cycleLog; U32 const cycleMask = cycleSize - 1; U32 const curr = (U32)((BYTE const*)src - window->base); @@ -1112,9 +1112,9 @@ MEM_STATIC U32 ZSTD_window_correctOverflow(ZSTD_window_t* window, U32 cycleLog, /* Loose bound, should be around 1<<29 (see above) */ assert(correction > 1<<28); } - - window->base += correction; - window->dictBase += correction; + + window->base += correction; + window->dictBase += correction; if (window->lowLimit < correction + ZSTD_WINDOW_START_INDEX) { window->lowLimit = ZSTD_WINDOW_START_INDEX; } else { @@ -1125,7 +1125,7 @@ MEM_STATIC U32 ZSTD_window_correctOverflow(ZSTD_window_t* window, U32 cycleLog, } else { window->dictLimit -= correction; } - + /* Ensure we can still reference the full window. */ assert(newCurrent >= maxDist); assert(newCurrent - maxDist >= ZSTD_WINDOW_START_INDEX); @@ -1135,15 +1135,15 @@ MEM_STATIC U32 ZSTD_window_correctOverflow(ZSTD_window_t* window, U32 cycleLog, ++window->nbOverflowCorrections; - DEBUGLOG(4, "Correction of 0x%x bytes to lowLimit=0x%x", correction, - window->lowLimit); - return correction; -} - -/** - * ZSTD_window_enforceMaxDist(): - * Updates lowLimit so that: - * (srcEnd - base) - lowLimit == maxDist + loadedDictEnd + DEBUGLOG(4, "Correction of 0x%x bytes to lowLimit=0x%x", correction, + window->lowLimit); + return correction; +} + +/** + * ZSTD_window_enforceMaxDist(): + * Updates lowLimit so that: + * (srcEnd - base) - lowLimit == maxDist + loadedDictEnd * * It ensures index is valid as long as index >= lowLimit. * This must be called before a block compression call. @@ -1162,14 +1162,14 @@ MEM_STATIC U32 ZSTD_window_correctOverflow(ZSTD_window_t* window, U32 cycleLog, * In dictMatchState mode, lowLimit and dictLimit are the same, * and the dictionary is below them. * forceWindow and dictMatchState are therefore incompatible. - */ + */ MEM_STATIC void ZSTD_window_enforceMaxDist(ZSTD_window_t* window, const void* blockEnd, U32 maxDist, U32* loadedDictEndPtr, const ZSTD_matchState_t** dictMatchStatePtr) -{ +{ U32 const blockEndIdx = (U32)((BYTE const*)blockEnd - window->base); U32 const loadedDictEnd = (loadedDictEndPtr != NULL) ? *loadedDictEndPtr : 0; DEBUGLOG(5, "ZSTD_window_enforceMaxDist: blockEndIdx=%u, maxDist=%u, loadedDictEnd=%u", @@ -1190,18 +1190,18 @@ ZSTD_window_enforceMaxDist(ZSTD_window_t* window, */ if (blockEndIdx > maxDist + loadedDictEnd) { U32 const newLowLimit = blockEndIdx - maxDist; - if (window->lowLimit < newLowLimit) window->lowLimit = newLowLimit; - if (window->dictLimit < window->lowLimit) { + if (window->lowLimit < newLowLimit) window->lowLimit = newLowLimit; + if (window->dictLimit < window->lowLimit) { DEBUGLOG(5, "Update dictLimit to match lowLimit, from %u to %u", (unsigned)window->dictLimit, (unsigned)window->lowLimit); - window->dictLimit = window->lowLimit; - } + window->dictLimit = window->lowLimit; + } /* On reaching window size, dictionaries are invalidated */ if (loadedDictEndPtr) *loadedDictEndPtr = 0; if (dictMatchStatePtr) *dictMatchStatePtr = NULL; - } -} - + } +} + /* Similar to ZSTD_window_enforceMaxDist(), * but only invalidates dictionary * when input progresses beyond window size. @@ -1248,50 +1248,50 @@ MEM_STATIC void ZSTD_window_init(ZSTD_window_t* window) { window->nbOverflowCorrections = 0; } -/** - * ZSTD_window_update(): - * Updates the window by appending [src, src + srcSize) to the window. - * If it is not contiguous, the current prefix becomes the extDict, and we - * forget about the extDict. Handles overlap of the prefix and extDict. - * Returns non-zero if the segment is contiguous. - */ -MEM_STATIC U32 ZSTD_window_update(ZSTD_window_t* window, +/** + * ZSTD_window_update(): + * Updates the window by appending [src, src + srcSize) to the window. + * If it is not contiguous, the current prefix becomes the extDict, and we + * forget about the extDict. Handles overlap of the prefix and extDict. + * Returns non-zero if the segment is contiguous. + */ +MEM_STATIC U32 ZSTD_window_update(ZSTD_window_t* window, void const* src, size_t srcSize, int forceNonContiguous) -{ - BYTE const* const ip = (BYTE const*)src; - U32 contiguous = 1; +{ + BYTE const* const ip = (BYTE const*)src; + U32 contiguous = 1; DEBUGLOG(5, "ZSTD_window_update"); if (srcSize == 0) return contiguous; assert(window->base != NULL); assert(window->dictBase != NULL); - /* Check if blocks follow each other */ + /* Check if blocks follow each other */ if (src != window->nextSrc || forceNonContiguous) { - /* not contiguous */ - size_t const distanceFromBase = (size_t)(window->nextSrc - window->base); + /* not contiguous */ + size_t const distanceFromBase = (size_t)(window->nextSrc - window->base); DEBUGLOG(5, "Non contiguous blocks, new segment starts at %u", window->dictLimit); - window->lowLimit = window->dictLimit; - assert(distanceFromBase == (size_t)(U32)distanceFromBase); /* should never overflow */ - window->dictLimit = (U32)distanceFromBase; - window->dictBase = window->base; - window->base = ip - distanceFromBase; + window->lowLimit = window->dictLimit; + assert(distanceFromBase == (size_t)(U32)distanceFromBase); /* should never overflow */ + window->dictLimit = (U32)distanceFromBase; + window->dictBase = window->base; + window->base = ip - distanceFromBase; /* ms->nextToUpdate = window->dictLimit; */ - if (window->dictLimit - window->lowLimit < HASH_READ_SIZE) window->lowLimit = window->dictLimit; /* too small extDict */ - contiguous = 0; - } - window->nextSrc = ip + srcSize; - /* if input and dictionary overlap : reduce dictionary (area presumed modified by input) */ - if ( (ip+srcSize > window->dictBase + window->lowLimit) - & (ip < window->dictBase + window->dictLimit)) { - ptrdiff_t const highInputIdx = (ip + srcSize) - window->dictBase; - U32 const lowLimitMax = (highInputIdx > (ptrdiff_t)window->dictLimit) ? window->dictLimit : (U32)highInputIdx; - window->lowLimit = lowLimitMax; + if (window->dictLimit - window->lowLimit < HASH_READ_SIZE) window->lowLimit = window->dictLimit; /* too small extDict */ + contiguous = 0; + } + window->nextSrc = ip + srcSize; + /* if input and dictionary overlap : reduce dictionary (area presumed modified by input) */ + if ( (ip+srcSize > window->dictBase + window->lowLimit) + & (ip < window->dictBase + window->dictLimit)) { + ptrdiff_t const highInputIdx = (ip + srcSize) - window->dictBase; + U32 const lowLimitMax = (highInputIdx > (ptrdiff_t)window->dictLimit) ? window->dictLimit : (U32)highInputIdx; + window->lowLimit = lowLimitMax; DEBUGLOG(5, "Overlapping extDict and input : new lowLimit = %u", window->lowLimit); - } - return contiguous; -} - + } + return contiguous; +} + /** * Returns the lowest allowed match index. It may either be in the ext-dict or the prefix. */ @@ -1359,15 +1359,15 @@ MEM_STATIC void ZSTD_debugTable(const U32* table, U32 max) #endif -#if defined (__cplusplus) -} -#endif - +#if defined (__cplusplus) +} +#endif + /* =============================================================== * Shared internal declarations * These prototypes may be called from sources not in lib/compress * =============================================================== */ - + /* ZSTD_loadCEntropy() : * dict : must point at beginning of a valid zstd dictionary. * return : size of dictionary header (size of magic number + dict ID + entropy tables) @@ -1378,81 +1378,81 @@ size_t ZSTD_loadCEntropy(ZSTD_compressedBlockState_t* bs, void* workspace, void ZSTD_reset_compressedBlockState(ZSTD_compressedBlockState_t* bs); -/* ============================================================== - * Private declarations - * These prototypes shall only be called from within lib/compress - * ============================================================== */ - -/* ZSTD_getCParamsFromCCtxParams() : +/* ============================================================== + * Private declarations + * These prototypes shall only be called from within lib/compress + * ============================================================== */ + +/* ZSTD_getCParamsFromCCtxParams() : * cParams are built depending on compressionLevel, src size hints, - * LDM and manually set compression parameters. + * LDM and manually set compression parameters. * Note: srcSizeHint == 0 means 0! - */ -ZSTD_compressionParameters ZSTD_getCParamsFromCCtxParams( + */ +ZSTD_compressionParameters ZSTD_getCParamsFromCCtxParams( const ZSTD_CCtx_params* CCtxParams, U64 srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode); - -/*! ZSTD_initCStream_internal() : - * Private use only. Init streaming operation. - * expects params to be valid. - * must receive dict, or cdict, or none, but not both. - * @return : 0, or an error code */ -size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs, - const void* dict, size_t dictSize, - const ZSTD_CDict* cdict, + +/*! ZSTD_initCStream_internal() : + * Private use only. Init streaming operation. + * expects params to be valid. + * must receive dict, or cdict, or none, but not both. + * @return : 0, or an error code */ +size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs, + const void* dict, size_t dictSize, + const ZSTD_CDict* cdict, const ZSTD_CCtx_params* params, unsigned long long pledgedSrcSize); - + void ZSTD_resetSeqStore(seqStore_t* ssPtr); - -/*! ZSTD_getCParamsFromCDict() : - * as the name implies */ -ZSTD_compressionParameters ZSTD_getCParamsFromCDict(const ZSTD_CDict* cdict); - -/* ZSTD_compressBegin_advanced_internal() : - * Private use only. To be called from zstdmt_compress.c. */ -size_t ZSTD_compressBegin_advanced_internal(ZSTD_CCtx* cctx, - const void* dict, size_t dictSize, - ZSTD_dictContentType_e dictContentType, + +/*! ZSTD_getCParamsFromCDict() : + * as the name implies */ +ZSTD_compressionParameters ZSTD_getCParamsFromCDict(const ZSTD_CDict* cdict); + +/* ZSTD_compressBegin_advanced_internal() : + * Private use only. To be called from zstdmt_compress.c. */ +size_t ZSTD_compressBegin_advanced_internal(ZSTD_CCtx* cctx, + const void* dict, size_t dictSize, + ZSTD_dictContentType_e dictContentType, ZSTD_dictTableLoadMethod_e dtlm, - const ZSTD_CDict* cdict, + const ZSTD_CDict* cdict, const ZSTD_CCtx_params* params, - unsigned long long pledgedSrcSize); - -/* ZSTD_compress_advanced_internal() : - * Private use only. To be called from zstdmt_compress.c. */ -size_t ZSTD_compress_advanced_internal(ZSTD_CCtx* cctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const void* dict,size_t dictSize, + unsigned long long pledgedSrcSize); + +/* ZSTD_compress_advanced_internal() : + * Private use only. To be called from zstdmt_compress.c. */ +size_t ZSTD_compress_advanced_internal(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, const ZSTD_CCtx_params* params); - - -/* ZSTD_writeLastEmptyBlock() : - * output an empty Block with end-of-frame mark to complete a frame - * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h)) + + +/* ZSTD_writeLastEmptyBlock() : + * output an empty Block with end-of-frame mark to complete a frame + * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h)) * or an error code if `dstCapacity` is too small (<ZSTD_blockHeaderSize) - */ -size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity); - - -/* ZSTD_referenceExternalSequences() : - * Must be called before starting a compression operation. - * seqs must parse a prefix of the source. - * This cannot be used when long range matching is enabled. - * Zstd will use these sequences, and pass the literals to a secondary block - * compressor. - * @return : An error code on failure. - * NOTE: seqs are not verified! Invalid sequences can cause out-of-bounds memory - * access and data corruption. - */ -size_t ZSTD_referenceExternalSequences(ZSTD_CCtx* cctx, rawSeq* seq, size_t nbSeq); - + */ +size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity); + + +/* ZSTD_referenceExternalSequences() : + * Must be called before starting a compression operation. + * seqs must parse a prefix of the source. + * This cannot be used when long range matching is enabled. + * Zstd will use these sequences, and pass the literals to a secondary block + * compressor. + * @return : An error code on failure. + * NOTE: seqs are not verified! Invalid sequences can cause out-of-bounds memory + * access and data corruption. + */ +size_t ZSTD_referenceExternalSequences(ZSTD_CCtx* cctx, rawSeq* seq, size_t nbSeq); + /** ZSTD_cycleLog() : * condition for correct operation : hashLog > 1 */ U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat); - + /** ZSTD_CCtx_trace() : * Trace the end of a compression call. */ void ZSTD_CCtx_trace(ZSTD_CCtx* cctx, size_t extraCSize); -#endif /* ZSTD_COMPRESS_H */ +#endif /* ZSTD_COMPRESS_H */ diff --git a/contrib/libs/zstd/lib/compress/zstd_double_fast.c b/contrib/libs/zstd/lib/compress/zstd_double_fast.c index 76933dea26..59f4ad5e05 100644 --- a/contrib/libs/zstd/lib/compress/zstd_double_fast.c +++ b/contrib/libs/zstd/lib/compress/zstd_double_fast.c @@ -1,55 +1,55 @@ -/* +/* * Copyright (c) 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. - */ - -#include "zstd_compress_internal.h" -#include "zstd_double_fast.h" - - -void ZSTD_fillDoubleHashTable(ZSTD_matchState_t* ms, + * 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. + */ + +#include "zstd_compress_internal.h" +#include "zstd_double_fast.h" + + +void ZSTD_fillDoubleHashTable(ZSTD_matchState_t* ms, void const* end, ZSTD_dictTableLoadMethod_e dtlm) -{ +{ const ZSTD_compressionParameters* const cParams = &ms->cParams; - U32* const hashLarge = ms->hashTable; - U32 const hBitsL = cParams->hashLog; + U32* const hashLarge = ms->hashTable; + U32 const hBitsL = cParams->hashLog; U32 const mls = cParams->minMatch; - U32* const hashSmall = ms->chainTable; - U32 const hBitsS = cParams->chainLog; - const BYTE* const base = ms->window.base; - const BYTE* ip = base + ms->nextToUpdate; - const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE; - const U32 fastHashFillStep = 3; - - /* Always insert every fastHashFillStep position into the hash tables. - * Insert the other positions into the large hash table if their entry - * is empty. - */ - for (; ip + fastHashFillStep - 1 <= iend; ip += fastHashFillStep) { + U32* const hashSmall = ms->chainTable; + U32 const hBitsS = cParams->chainLog; + const BYTE* const base = ms->window.base; + const BYTE* ip = base + ms->nextToUpdate; + const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE; + const U32 fastHashFillStep = 3; + + /* Always insert every fastHashFillStep position into the hash tables. + * Insert the other positions into the large hash table if their entry + * is empty. + */ + for (; ip + fastHashFillStep - 1 <= iend; ip += fastHashFillStep) { U32 const curr = (U32)(ip - base); - U32 i; - for (i = 0; i < fastHashFillStep; ++i) { - size_t const smHash = ZSTD_hashPtr(ip + i, hBitsS, mls); - size_t const lgHash = ZSTD_hashPtr(ip + i, hBitsL, 8); - if (i == 0) + U32 i; + for (i = 0; i < fastHashFillStep; ++i) { + size_t const smHash = ZSTD_hashPtr(ip + i, hBitsS, mls); + size_t const lgHash = ZSTD_hashPtr(ip + i, hBitsL, 8); + if (i == 0) hashSmall[smHash] = curr + i; - if (i == 0 || hashLarge[lgHash] == 0) + if (i == 0 || hashLarge[lgHash] == 0) hashLarge[lgHash] = curr + i; /* Only load extra positions for ZSTD_dtlm_full */ if (dtlm == ZSTD_dtlm_fast) break; } } -} - - -FORCE_INLINE_TEMPLATE +} + + +FORCE_INLINE_TEMPLATE size_t ZSTD_compressBlock_doubleFast_noDict_generic( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize, U32 const mls /* template */) { ZSTD_compressionParameters const* cParams = &ms->cParams; @@ -258,25 +258,25 @@ size_t ZSTD_compressBlock_doubleFast_dictMatchState_generic( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize, U32 const mls /* template */) -{ +{ ZSTD_compressionParameters const* cParams = &ms->cParams; - U32* const hashLong = ms->hashTable; - const U32 hBitsL = cParams->hashLog; - U32* const hashSmall = ms->chainTable; - const U32 hBitsS = cParams->chainLog; - const BYTE* const base = ms->window.base; - const BYTE* const istart = (const BYTE*)src; - const BYTE* ip = istart; - const BYTE* anchor = istart; + U32* const hashLong = ms->hashTable; + const U32 hBitsL = cParams->hashLog; + U32* const hashSmall = ms->chainTable; + const U32 hBitsS = cParams->chainLog; + const BYTE* const base = ms->window.base; + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; const U32 endIndex = (U32)((size_t)(istart - base) + srcSize); /* presumes that, if there is a dictionary, it must be using Attach mode */ const U32 prefixLowestIndex = ZSTD_getLowestPrefixIndex(ms, endIndex, cParams->windowLog); const BYTE* const prefixLowest = base + prefixLowestIndex; - const BYTE* const iend = istart + srcSize; - const BYTE* const ilimit = iend - HASH_READ_SIZE; - U32 offset_1=rep[0], offset_2=rep[1]; - U32 offsetSaved = 0; - + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - HASH_READ_SIZE; + U32 offset_1=rep[0], offset_2=rep[1]; + U32 offsetSaved = 0; + const ZSTD_matchState_t* const dms = ms->dictMatchState; const ZSTD_compressionParameters* const dictCParams = &dms->cParams; const U32* const dictHashLong = dms->hashTable; @@ -295,33 +295,33 @@ size_t ZSTD_compressBlock_doubleFast_dictMatchState_generic( /* if a dictionary is attached, it must be within window range */ assert(ms->window.dictLimit + (1U << cParams->windowLog) >= endIndex); - /* init */ + /* init */ ip += (dictAndPrefixLength == 0); - + /* dictMatchState repCode checks don't currently handle repCode == 0 * disabling. */ assert(offset_1 <= dictAndPrefixLength); assert(offset_2 <= dictAndPrefixLength); - /* Main Search Loop */ - while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */ - size_t mLength; + /* Main Search Loop */ + while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */ + size_t mLength; U32 offset; - size_t const h2 = ZSTD_hashPtr(ip, hBitsL, 8); - size_t const h = ZSTD_hashPtr(ip, hBitsS, mls); + size_t const h2 = ZSTD_hashPtr(ip, hBitsL, 8); + size_t const h = ZSTD_hashPtr(ip, hBitsS, mls); size_t const dictHL = ZSTD_hashPtr(ip, dictHBitsL, 8); size_t const dictHS = ZSTD_hashPtr(ip, dictHBitsS, mls); U32 const curr = (U32)(ip-base); - U32 const matchIndexL = hashLong[h2]; + U32 const matchIndexL = hashLong[h2]; U32 matchIndexS = hashSmall[h]; - const BYTE* matchLong = base + matchIndexL; - const BYTE* match = base + matchIndexS; + const BYTE* matchLong = base + matchIndexL; + const BYTE* match = base + matchIndexS; const U32 repIndex = curr + 1 - offset_1; const BYTE* repMatch = (repIndex < prefixLowestIndex) ? dictBase + (repIndex - dictIndexDelta) : base + repIndex; hashLong[h2] = hashSmall[h] = curr; /* update hash tables */ - + /* check repcode */ if (((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */) && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { @@ -335,8 +335,8 @@ size_t ZSTD_compressBlock_doubleFast_dictMatchState_generic( if (matchIndexL > prefixLowestIndex) { /* check prefix long match */ if (MEM_read64(matchLong) == MEM_read64(ip)) { - mLength = ZSTD_count(ip+8, matchLong+8, iend) + 8; - offset = (U32)(ip-matchLong); + mLength = ZSTD_count(ip+8, matchLong+8, iend) + 8; + offset = (U32)(ip-matchLong); while (((ip>anchor) & (matchLong>prefixLowest)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */ goto _match_found; } @@ -385,12 +385,12 @@ _search_next_long: /* check prefix long +1 match */ if (matchIndexL3 > prefixLowestIndex) { if (MEM_read64(matchL3) == MEM_read64(ip+1)) { - mLength = ZSTD_count(ip+9, matchL3+8, iend) + 8; - ip++; - offset = (U32)(ip-matchL3); + mLength = ZSTD_count(ip+9, matchL3+8, iend) + 8; + ip++; + offset = (U32)(ip-matchL3); while (((ip>anchor) & (matchL3>prefixLowest)) && (ip[-1] == matchL3[-1])) { ip--; matchL3--; mLength++; } /* catch up */ goto _match_found; - } + } } else { /* check dict long +1 match */ U32 const dictMatchIndexL3 = dictHashLong[dictHLNext]; @@ -403,7 +403,7 @@ _search_next_long: while (((ip>anchor) & (dictMatchL3>dictStart)) && (ip[-1] == dictMatchL3[-1])) { ip--; dictMatchL3--; mLength++; } /* catch up */ goto _match_found; } } } - + /* if no long +1 match, explore the short match we found */ if (matchIndexS < prefixLowestIndex) { mLength = ZSTD_count_2segments(ip+4, match+4, iend, dictEnd, prefixLowest) + 4; @@ -413,8 +413,8 @@ _search_next_long: mLength = ZSTD_count(ip+4, match+4, iend) + 4; offset = (U32)(ip - match); while (((ip>anchor) & (match>prefixLowest)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ - } - + } + _match_found: offset_2 = offset_1; offset_1 = offset; @@ -422,11 +422,11 @@ _match_found: ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, STORE_OFFSET(offset), mLength); _match_stored: - /* match found */ - ip += mLength; - anchor = ip; - - if (ip <= ilimit) { + /* match found */ + ip += mLength; + anchor = ip; + + if (ip <= ilimit) { /* Complementary insertion */ /* done after iLimit test, as candidates could be > iend-8 */ { U32 const indexToInsert = curr+2; @@ -435,8 +435,8 @@ _match_stored: hashSmall[ZSTD_hashPtr(base+indexToInsert, hBitsS, mls)] = indexToInsert; hashSmall[ZSTD_hashPtr(ip-1, hBitsS, mls)] = (U32)(ip-1-base); } - - /* check immediate repcode */ + + /* check immediate repcode */ while (ip <= ilimit) { U32 const current2 = (U32)(ip-base); U32 const repIndex2 = current2 - offset_2; @@ -460,14 +460,14 @@ _match_stored: } } /* while (ip < ilimit) */ - /* save reps for next block */ - rep[0] = offset_1 ? offset_1 : offsetSaved; - rep[1] = offset_2 ? offset_2 : offsetSaved; - - /* Return the last literals size */ + /* save reps for next block */ + rep[0] = offset_1 ? offset_1 : offsetSaved; + rep[1] = offset_2 ? offset_2 : offsetSaved; + + /* Return the last literals size */ return (size_t)(iend - anchor); -} - +} + #define ZSTD_GEN_DFAST_FN(dictMode, mls) \ static size_t ZSTD_compressBlock_doubleFast_##dictMode##_##mls( \ ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], \ @@ -475,7 +475,7 @@ _match_stored: { \ return ZSTD_compressBlock_doubleFast_##dictMode##_generic(ms, seqStore, rep, src, srcSize, mls); \ } - + ZSTD_GEN_DFAST_FN(noDict, 4) ZSTD_GEN_DFAST_FN(noDict, 5) ZSTD_GEN_DFAST_FN(noDict, 6) @@ -487,26 +487,26 @@ ZSTD_GEN_DFAST_FN(dictMatchState, 6) ZSTD_GEN_DFAST_FN(dictMatchState, 7) -size_t ZSTD_compressBlock_doubleFast( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_doubleFast( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) -{ +{ const U32 mls = ms->cParams.minMatch; - switch(mls) - { - default: /* includes case 3 */ - case 4 : + switch(mls) + { + default: /* includes case 3 */ + case 4 : return ZSTD_compressBlock_doubleFast_noDict_4(ms, seqStore, rep, src, srcSize); - case 5 : + case 5 : return ZSTD_compressBlock_doubleFast_noDict_5(ms, seqStore, rep, src, srcSize); - case 6 : + case 6 : return ZSTD_compressBlock_doubleFast_noDict_6(ms, seqStore, rep, src, srcSize); - case 7 : + case 7 : return ZSTD_compressBlock_doubleFast_noDict_7(ms, seqStore, rep, src, srcSize); - } -} - - + } +} + + size_t ZSTD_compressBlock_doubleFast_dictMatchState( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) @@ -527,21 +527,21 @@ size_t ZSTD_compressBlock_doubleFast_dictMatchState( } -static size_t ZSTD_compressBlock_doubleFast_extDict_generic( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +static size_t ZSTD_compressBlock_doubleFast_extDict_generic( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize, - U32 const mls /* template */) -{ + U32 const mls /* template */) +{ ZSTD_compressionParameters const* cParams = &ms->cParams; - U32* const hashLong = ms->hashTable; - U32 const hBitsL = cParams->hashLog; - U32* const hashSmall = ms->chainTable; - U32 const hBitsS = cParams->chainLog; - const BYTE* const istart = (const BYTE*)src; - const BYTE* ip = istart; - const BYTE* anchor = istart; - const BYTE* const iend = istart + srcSize; - const BYTE* const ilimit = iend - 8; + U32* const hashLong = ms->hashTable; + U32 const hBitsL = cParams->hashLog; + U32* const hashSmall = ms->chainTable; + U32 const hBitsS = cParams->chainLog; + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - 8; const BYTE* const base = ms->window.base; const U32 endIndex = (U32)((size_t)(istart - base) + srcSize); const U32 lowLimit = ZSTD_getLowestMatchIndex(ms, endIndex, cParams->windowLog); @@ -552,87 +552,87 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic( const BYTE* const dictBase = ms->window.dictBase; const BYTE* const dictStart = dictBase + dictStartIndex; const BYTE* const dictEnd = dictBase + prefixStartIndex; - U32 offset_1=rep[0], offset_2=rep[1]; - + U32 offset_1=rep[0], offset_2=rep[1]; + DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_extDict_generic (srcSize=%zu)", srcSize); /* if extDict is invalidated due to maxDistance, switch to "regular" variant */ if (prefixStartIndex == dictStartIndex) return ZSTD_compressBlock_doubleFast(ms, seqStore, rep, src, srcSize); - /* Search Loop */ - while (ip < ilimit) { /* < instead of <=, because (ip+1) */ - const size_t hSmall = ZSTD_hashPtr(ip, hBitsS, mls); - const U32 matchIndex = hashSmall[hSmall]; + /* Search Loop */ + while (ip < ilimit) { /* < instead of <=, because (ip+1) */ + const size_t hSmall = ZSTD_hashPtr(ip, hBitsS, mls); + const U32 matchIndex = hashSmall[hSmall]; const BYTE* const matchBase = matchIndex < prefixStartIndex ? dictBase : base; - const BYTE* match = matchBase + matchIndex; - - const size_t hLong = ZSTD_hashPtr(ip, hBitsL, 8); - const U32 matchLongIndex = hashLong[hLong]; + const BYTE* match = matchBase + matchIndex; + + const size_t hLong = ZSTD_hashPtr(ip, hBitsL, 8); + const U32 matchLongIndex = hashLong[hLong]; const BYTE* const matchLongBase = matchLongIndex < prefixStartIndex ? dictBase : base; - const BYTE* matchLong = matchLongBase + matchLongIndex; - + const BYTE* matchLong = matchLongBase + matchLongIndex; + const U32 curr = (U32)(ip-base); const U32 repIndex = curr + 1 - offset_1; /* offset_1 expected <= curr +1 */ const BYTE* const repBase = repIndex < prefixStartIndex ? dictBase : base; const BYTE* const repMatch = repBase + repIndex; - size_t mLength; + size_t mLength; hashSmall[hSmall] = hashLong[hLong] = curr; /* update hash table */ - + if ((((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex doesn't overlap dict + prefix */ & (offset_1 <= curr+1 - dictStartIndex)) /* note: we are searching at curr+1 */ && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { const BYTE* repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend; mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4; - ip++; + ip++; ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, STORE_REPCODE_1, mLength); - } else { + } else { if ((matchLongIndex > dictStartIndex) && (MEM_read64(matchLong) == MEM_read64(ip))) { const BYTE* const matchEnd = matchLongIndex < prefixStartIndex ? dictEnd : iend; const BYTE* const lowMatchPtr = matchLongIndex < prefixStartIndex ? dictStart : prefixStart; - U32 offset; + U32 offset; mLength = ZSTD_count_2segments(ip+8, matchLong+8, iend, matchEnd, prefixStart) + 8; offset = curr - matchLongIndex; - while (((ip>anchor) & (matchLong>lowMatchPtr)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */ - offset_2 = offset_1; - offset_1 = offset; + while (((ip>anchor) & (matchLong>lowMatchPtr)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */ + offset_2 = offset_1; + offset_1 = offset; ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, STORE_OFFSET(offset), mLength); - + } else if ((matchIndex > dictStartIndex) && (MEM_read32(match) == MEM_read32(ip))) { - size_t const h3 = ZSTD_hashPtr(ip+1, hBitsL, 8); - U32 const matchIndex3 = hashLong[h3]; + size_t const h3 = ZSTD_hashPtr(ip+1, hBitsL, 8); + U32 const matchIndex3 = hashLong[h3]; const BYTE* const match3Base = matchIndex3 < prefixStartIndex ? dictBase : base; - const BYTE* match3 = match3Base + matchIndex3; - U32 offset; + const BYTE* match3 = match3Base + matchIndex3; + U32 offset; hashLong[h3] = curr + 1; if ( (matchIndex3 > dictStartIndex) && (MEM_read64(match3) == MEM_read64(ip+1)) ) { const BYTE* const matchEnd = matchIndex3 < prefixStartIndex ? dictEnd : iend; const BYTE* const lowMatchPtr = matchIndex3 < prefixStartIndex ? dictStart : prefixStart; mLength = ZSTD_count_2segments(ip+9, match3+8, iend, matchEnd, prefixStart) + 8; - ip++; + ip++; offset = curr+1 - matchIndex3; - while (((ip>anchor) & (match3>lowMatchPtr)) && (ip[-1] == match3[-1])) { ip--; match3--; mLength++; } /* catch up */ - } else { + while (((ip>anchor) & (match3>lowMatchPtr)) && (ip[-1] == match3[-1])) { ip--; match3--; mLength++; } /* catch up */ + } else { const BYTE* const matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend; const BYTE* const lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart; mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4; offset = curr - matchIndex; - while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ - } - offset_2 = offset_1; - offset_1 = offset; + while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ + } + offset_2 = offset_1; + offset_1 = offset; ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, STORE_OFFSET(offset), mLength); - - } else { - ip += ((ip-anchor) >> kSearchStrength) + 1; - continue; - } } - + + } else { + ip += ((ip-anchor) >> kSearchStrength) + 1; + continue; + } } + /* move to next sequence start */ - ip += mLength; - anchor = ip; - - if (ip <= ilimit) { + ip += mLength; + anchor = ip; + + if (ip <= ilimit) { /* Complementary insertion */ /* done after iLimit test, as candidates could be > iend-8 */ { U32 const indexToInsert = curr+2; @@ -642,10 +642,10 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic( hashSmall[ZSTD_hashPtr(ip-1, hBitsS, mls)] = (U32)(ip-1-base); } - /* check immediate repcode */ - while (ip <= ilimit) { - U32 const current2 = (U32)(ip-base); - U32 const repIndex2 = current2 - offset_2; + /* check immediate repcode */ + while (ip <= ilimit) { + U32 const current2 = (U32)(ip-base); + U32 const repIndex2 = current2 - offset_2; const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2; if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3) /* intentional overflow : ensure repIndex2 doesn't overlap dict + prefix */ & (offset_2 <= current2 - dictStartIndex)) @@ -654,43 +654,43 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic( size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4; U32 const tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */ ZSTD_storeSeq(seqStore, 0, anchor, iend, STORE_REPCODE_1, repLength2); - hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = current2; - hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = current2; - ip += repLength2; - anchor = ip; - continue; - } - break; - } } } - - /* save reps for next block */ - rep[0] = offset_1; - rep[1] = offset_2; - - /* Return the last literals size */ + hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = current2; + hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = current2; + ip += repLength2; + anchor = ip; + continue; + } + break; + } } } + + /* save reps for next block */ + rep[0] = offset_1; + rep[1] = offset_2; + + /* Return the last literals size */ return (size_t)(iend - anchor); -} - +} + ZSTD_GEN_DFAST_FN(extDict, 4) ZSTD_GEN_DFAST_FN(extDict, 5) ZSTD_GEN_DFAST_FN(extDict, 6) ZSTD_GEN_DFAST_FN(extDict, 7) - -size_t ZSTD_compressBlock_doubleFast_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + +size_t ZSTD_compressBlock_doubleFast_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) -{ +{ U32 const mls = ms->cParams.minMatch; - switch(mls) - { - default: /* includes case 3 */ - case 4 : + switch(mls) + { + default: /* includes case 3 */ + case 4 : return ZSTD_compressBlock_doubleFast_extDict_4(ms, seqStore, rep, src, srcSize); - case 5 : + case 5 : return ZSTD_compressBlock_doubleFast_extDict_5(ms, seqStore, rep, src, srcSize); - case 6 : + case 6 : return ZSTD_compressBlock_doubleFast_extDict_6(ms, seqStore, rep, src, srcSize); - case 7 : + case 7 : return ZSTD_compressBlock_doubleFast_extDict_7(ms, seqStore, rep, src, srcSize); - } -} + } +} diff --git a/contrib/libs/zstd/lib/compress/zstd_double_fast.h b/contrib/libs/zstd/lib/compress/zstd_double_fast.h index e16b7b03a3..ddca837bff 100644 --- a/contrib/libs/zstd/lib/compress/zstd_double_fast.h +++ b/contrib/libs/zstd/lib/compress/zstd_double_fast.h @@ -1,38 +1,38 @@ -/* +/* * Copyright (c) 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_DOUBLE_FAST_H -#define ZSTD_DOUBLE_FAST_H - -#if defined (__cplusplus) -extern "C" { -#endif - + * 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_DOUBLE_FAST_H +#define ZSTD_DOUBLE_FAST_H + +#if defined (__cplusplus) +extern "C" { +#endif + #include "../common/mem.h" /* U32 */ -#include "zstd_compress_internal.h" /* ZSTD_CCtx, size_t */ - -void ZSTD_fillDoubleHashTable(ZSTD_matchState_t* ms, +#include "zstd_compress_internal.h" /* ZSTD_CCtx, size_t */ + +void ZSTD_fillDoubleHashTable(ZSTD_matchState_t* ms, void const* end, ZSTD_dictTableLoadMethod_e dtlm); -size_t ZSTD_compressBlock_doubleFast( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_doubleFast( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); size_t ZSTD_compressBlock_doubleFast_dictMatchState( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); -size_t ZSTD_compressBlock_doubleFast_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_doubleFast_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); - - -#if defined (__cplusplus) -} -#endif - -#endif /* ZSTD_DOUBLE_FAST_H */ + + +#if defined (__cplusplus) +} +#endif + +#endif /* ZSTD_DOUBLE_FAST_H */ diff --git a/contrib/libs/zstd/lib/compress/zstd_fast.c b/contrib/libs/zstd/lib/compress/zstd_fast.c index 802fc31579..7f6b333e5b 100644 --- a/contrib/libs/zstd/lib/compress/zstd_fast.c +++ b/contrib/libs/zstd/lib/compress/zstd_fast.c @@ -1,33 +1,33 @@ -/* +/* * Copyright (c) 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. - */ - + * 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. + */ + #include "zstd_compress_internal.h" /* ZSTD_hashPtr, ZSTD_count, ZSTD_storeSeq */ -#include "zstd_fast.h" - - -void ZSTD_fillHashTable(ZSTD_matchState_t* ms, +#include "zstd_fast.h" + + +void ZSTD_fillHashTable(ZSTD_matchState_t* ms, const void* const end, ZSTD_dictTableLoadMethod_e dtlm) -{ +{ const ZSTD_compressionParameters* const cParams = &ms->cParams; - U32* const hashTable = ms->hashTable; - U32 const hBits = cParams->hashLog; + U32* const hashTable = ms->hashTable; + U32 const hBits = cParams->hashLog; U32 const mls = cParams->minMatch; - const BYTE* const base = ms->window.base; - const BYTE* ip = base + ms->nextToUpdate; - const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE; - const U32 fastHashFillStep = 3; - - /* Always insert every fastHashFillStep position into the hash table. - * Insert the other positions if their hash entry is empty. - */ + const BYTE* const base = ms->window.base; + const BYTE* ip = base + ms->nextToUpdate; + const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE; + const U32 fastHashFillStep = 3; + + /* Always insert every fastHashFillStep position into the hash table. + * Insert the other positions if their hash entry is empty. + */ for ( ; ip + fastHashFillStep < iend + 2; ip += fastHashFillStep) { U32 const curr = (U32)(ip - base); size_t const hash0 = ZSTD_hashPtr(ip, hBits, mls); @@ -40,8 +40,8 @@ void ZSTD_fillHashTable(ZSTD_matchState_t* ms, if (hashTable[hash] == 0) { /* not yet filled */ hashTable[hash] = curr + p; } } } } -} - +} + /** * If you squint hard enough (and ignore repcodes), the search operation at any @@ -91,22 +91,22 @@ void ZSTD_fillHashTable(ZSTD_matchState_t* ms, */ FORCE_INLINE_TEMPLATE size_t ZSTD_compressBlock_fast_noDict_generic( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], - void const* src, size_t srcSize, + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize, U32 const mls, U32 const hasStep) -{ +{ const ZSTD_compressionParameters* const cParams = &ms->cParams; - U32* const hashTable = ms->hashTable; + U32* const hashTable = ms->hashTable; U32 const hlog = cParams->hashLog; /* support stepSize of 0 */ size_t const stepSize = hasStep ? (cParams->targetLength + !(cParams->targetLength) + 1) : 2; - const BYTE* const base = ms->window.base; - const BYTE* const istart = (const BYTE*)src; + const BYTE* const base = ms->window.base; + const BYTE* const istart = (const BYTE*)src; const U32 endIndex = (U32)((size_t)(istart - base) + srcSize); const U32 prefixStartIndex = ZSTD_getLowestPrefixIndex(ms, endIndex, cParams->windowLog); const BYTE* const prefixStart = base + prefixStartIndex; - const BYTE* const iend = istart + srcSize; - const BYTE* const ilimit = iend - HASH_READ_SIZE; + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - HASH_READ_SIZE; const BYTE* anchor = istart; const BYTE* ip0 = istart; @@ -117,8 +117,8 @@ ZSTD_compressBlock_fast_noDict_generic( U32 rep_offset1 = rep[0]; U32 rep_offset2 = rep[1]; - U32 offsetSaved = 0; - + U32 offsetSaved = 0; + size_t hash0; /* hash for ip0 */ size_t hash1; /* hash for ip1 */ U32 idx; /* match idx for ip0 */ @@ -143,8 +143,8 @@ ZSTD_compressBlock_fast_noDict_generic( U32 const maxRep = curr - windowLow; if (rep_offset2 > maxRep) offsetSaved = rep_offset2, rep_offset2 = 0; if (rep_offset1 > maxRep) offsetSaved = rep_offset1, rep_offset1 = 0; - } - + } + /* start each op */ _start: /* Requires: ip0 */ @@ -422,23 +422,23 @@ size_t ZSTD_compressBlock_fast_dictMatchState_generic( assert(offset_2 <= dictAndPrefixLength); /* Main Search Loop */ - while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */ - size_t mLength; - size_t const h = ZSTD_hashPtr(ip, hlog, mls); + while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */ + size_t mLength; + size_t const h = ZSTD_hashPtr(ip, hlog, mls); U32 const curr = (U32)(ip-base); - U32 const matchIndex = hashTable[h]; - const BYTE* match = base + matchIndex; + U32 const matchIndex = hashTable[h]; + const BYTE* match = base + matchIndex; const U32 repIndex = curr + 1 - offset_1; const BYTE* repMatch = (repIndex < prefixStartIndex) ? dictBase + (repIndex - dictIndexDelta) : base + repIndex; hashTable[h] = curr; /* update hash table */ - + if ( ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */ && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend; mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4; - ip++; + ip++; ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, STORE_REPCODE_1, mLength); } else if ( (matchIndex <= prefixStartIndex) ) { size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls); @@ -446,9 +446,9 @@ size_t ZSTD_compressBlock_fast_dictMatchState_generic( const BYTE* dictMatch = dictBase + dictMatchIndex; if (dictMatchIndex <= dictStartIndex || MEM_read32(dictMatch) != MEM_read32(ip)) { - assert(stepSize >= 1); - ip += ((ip-anchor) >> kSearchStrength) + stepSize; - continue; + assert(stepSize >= 1); + ip += ((ip-anchor) >> kSearchStrength) + stepSize; + continue; } else { /* found a dict match */ U32 const offset = (U32)(curr-dictMatchIndex-dictIndexDelta); @@ -457,8 +457,8 @@ size_t ZSTD_compressBlock_fast_dictMatchState_generic( && (ip[-1] == dictMatch[-1])) { ip--; dictMatch--; mLength++; } /* catch up */ - offset_2 = offset_1; - offset_1 = offset; + offset_2 = offset_1; + offset_1 = offset; ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, STORE_OFFSET(offset), mLength); } } else if (MEM_read32(match) != MEM_read32(ip)) { @@ -476,18 +476,18 @@ size_t ZSTD_compressBlock_fast_dictMatchState_generic( offset_1 = offset; ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, STORE_OFFSET(offset), mLength); } - - /* match found */ - ip += mLength; - anchor = ip; - - if (ip <= ilimit) { - /* Fill Table */ + + /* match found */ + ip += mLength; + anchor = ip; + + if (ip <= ilimit) { + /* Fill Table */ assert(base+curr+2 > istart); /* check base overflow */ hashTable[ZSTD_hashPtr(base+curr+2, hlog, mls)] = curr+2; /* here because curr+2 could be > iend-8 */ - hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base); + hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base); - /* check immediate repcode */ + /* check immediate repcode */ while (ip <= ilimit) { U32 const current2 = (U32)(ip-base); U32 const repIndex2 = current2 - offset_2; @@ -509,15 +509,15 @@ size_t ZSTD_compressBlock_fast_dictMatchState_generic( } } } - - /* save reps for next block */ - rep[0] = offset_1 ? offset_1 : offsetSaved; - rep[1] = offset_2 ? offset_2 : offsetSaved; - - /* Return the last literals size */ + + /* save reps for next block */ + rep[0] = offset_1 ? offset_1 : offsetSaved; + rep[1] = offset_2 ? offset_2 : offsetSaved; + + /* Return the last literals size */ return (size_t)(iend - anchor); -} - +} + ZSTD_GEN_FAST_FN(dictMatchState, 4, 0) ZSTD_GEN_FAST_FN(dictMatchState, 5, 0) @@ -525,40 +525,40 @@ ZSTD_GEN_FAST_FN(dictMatchState, 6, 0) ZSTD_GEN_FAST_FN(dictMatchState, 7, 0) size_t ZSTD_compressBlock_fast_dictMatchState( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) -{ +{ U32 const mls = ms->cParams.minMatch; assert(ms->dictMatchState != NULL); - switch(mls) - { - default: /* includes case 3 */ - case 4 : + switch(mls) + { + default: /* includes case 3 */ + case 4 : return ZSTD_compressBlock_fast_dictMatchState_4_0(ms, seqStore, rep, src, srcSize); - case 5 : + case 5 : return ZSTD_compressBlock_fast_dictMatchState_5_0(ms, seqStore, rep, src, srcSize); - case 6 : + case 6 : return ZSTD_compressBlock_fast_dictMatchState_6_0(ms, seqStore, rep, src, srcSize); - case 7 : + case 7 : return ZSTD_compressBlock_fast_dictMatchState_7_0(ms, seqStore, rep, src, srcSize); - } -} - - -static size_t ZSTD_compressBlock_fast_extDict_generic( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + } +} + + +static size_t ZSTD_compressBlock_fast_extDict_generic( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize, U32 const mls, U32 const hasStep) -{ +{ const ZSTD_compressionParameters* const cParams = &ms->cParams; U32* const hashTable = ms->hashTable; U32 const hlog = cParams->hashLog; /* support stepSize of 0 */ U32 const stepSize = cParams->targetLength + !(cParams->targetLength); - const BYTE* const base = ms->window.base; - const BYTE* const dictBase = ms->window.dictBase; - const BYTE* const istart = (const BYTE*)src; - const BYTE* ip = istart; - const BYTE* anchor = istart; + const BYTE* const base = ms->window.base; + const BYTE* const dictBase = ms->window.dictBase; + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; const U32 endIndex = (U32)((size_t)(istart - base) + srcSize); const U32 lowLimit = ZSTD_getLowestMatchIndex(ms, endIndex, cParams->windowLog); const U32 dictStartIndex = lowLimit; @@ -567,10 +567,10 @@ static size_t ZSTD_compressBlock_fast_extDict_generic( const U32 prefixStartIndex = dictLimit < lowLimit ? lowLimit : dictLimit; const BYTE* const prefixStart = base + prefixStartIndex; const BYTE* const dictEnd = dictBase + prefixStartIndex; - const BYTE* const iend = istart + srcSize; - const BYTE* const ilimit = iend - 8; - U32 offset_1=rep[0], offset_2=rep[1]; - + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - 8; + U32 offset_1=rep[0], offset_2=rep[1]; + (void)hasStep; /* not currently specialized on whether it's accelerated */ DEBUGLOG(5, "ZSTD_compressBlock_fast_extDict_generic (offset_1=%u)", offset_1); @@ -579,9 +579,9 @@ static size_t ZSTD_compressBlock_fast_extDict_generic( if (prefixStartIndex == dictStartIndex) return ZSTD_compressBlock_fast(ms, seqStore, rep, src, srcSize); - /* Search Loop */ - while (ip < ilimit) { /* < instead of <=, because (ip+1) */ - const size_t h = ZSTD_hashPtr(ip, hlog, mls); + /* Search Loop */ + while (ip < ilimit) { /* < instead of <=, because (ip+1) */ + const size_t h = ZSTD_hashPtr(ip, hlog, mls); const U32 matchIndex = hashTable[h]; const BYTE* const matchBase = matchIndex < prefixStartIndex ? dictBase : base; const BYTE* match = matchBase + matchIndex; @@ -591,85 +591,85 @@ static size_t ZSTD_compressBlock_fast_extDict_generic( const BYTE* const repMatch = repBase + repIndex; hashTable[h] = curr; /* update hash table */ DEBUGLOG(7, "offset_1 = %u , curr = %u", offset_1, curr); - + if ( ( ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow */ & (offset_1 <= curr+1 - dictStartIndex) ) /* note: we are searching at curr+1 */ - && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { + && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend; size_t const rLength = ZSTD_count_2segments(ip+1 +4, repMatch +4, iend, repMatchEnd, prefixStart) + 4; - ip++; + ip++; ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, STORE_REPCODE_1, rLength); ip += rLength; anchor = ip; - } else { + } else { if ( (matchIndex < dictStartIndex) || - (MEM_read32(match) != MEM_read32(ip)) ) { - assert(stepSize >= 1); - ip += ((ip-anchor) >> kSearchStrength) + stepSize; - continue; - } + (MEM_read32(match) != MEM_read32(ip)) ) { + assert(stepSize >= 1); + ip += ((ip-anchor) >> kSearchStrength) + stepSize; + continue; + } { const BYTE* const matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend; const BYTE* const lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart; U32 const offset = curr - matchIndex; size_t mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4; - while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ + while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ offset_2 = offset_1; offset_1 = offset; /* update offset history */ ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, STORE_OFFSET(offset), mLength); ip += mLength; anchor = ip; - } } - - if (ip <= ilimit) { - /* Fill Table */ + } } + + if (ip <= ilimit) { + /* Fill Table */ hashTable[ZSTD_hashPtr(base+curr+2, hlog, mls)] = curr+2; - hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base); - /* check immediate repcode */ - while (ip <= ilimit) { - U32 const current2 = (U32)(ip-base); - U32 const repIndex2 = current2 - offset_2; + hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base); + /* check immediate repcode */ + while (ip <= ilimit) { + U32 const current2 = (U32)(ip-base); + U32 const repIndex2 = current2 - offset_2; const BYTE* const repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2; if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3) & (offset_2 <= curr - dictStartIndex)) /* intentional overflow */ - && (MEM_read32(repMatch2) == MEM_read32(ip)) ) { + && (MEM_read32(repMatch2) == MEM_read32(ip)) ) { const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend; size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4; { U32 const tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; } /* swap offset_2 <=> offset_1 */ ZSTD_storeSeq(seqStore, 0 /*litlen*/, anchor, iend, STORE_REPCODE_1, repLength2); - hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2; - ip += repLength2; - anchor = ip; - continue; - } - break; - } } } - - /* save reps for next block */ - rep[0] = offset_1; - rep[1] = offset_2; - - /* Return the last literals size */ + hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2; + ip += repLength2; + anchor = ip; + continue; + } + break; + } } } + + /* save reps for next block */ + rep[0] = offset_1; + rep[1] = offset_2; + + /* Return the last literals size */ return (size_t)(iend - anchor); -} - +} + ZSTD_GEN_FAST_FN(extDict, 4, 0) ZSTD_GEN_FAST_FN(extDict, 5, 0) ZSTD_GEN_FAST_FN(extDict, 6, 0) ZSTD_GEN_FAST_FN(extDict, 7, 0) - -size_t ZSTD_compressBlock_fast_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + +size_t ZSTD_compressBlock_fast_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) -{ +{ U32 const mls = ms->cParams.minMatch; - switch(mls) - { - default: /* includes case 3 */ - case 4 : + switch(mls) + { + default: /* includes case 3 */ + case 4 : return ZSTD_compressBlock_fast_extDict_4_0(ms, seqStore, rep, src, srcSize); - case 5 : + case 5 : return ZSTD_compressBlock_fast_extDict_5_0(ms, seqStore, rep, src, srcSize); - case 6 : + case 6 : return ZSTD_compressBlock_fast_extDict_6_0(ms, seqStore, rep, src, srcSize); - case 7 : + case 7 : return ZSTD_compressBlock_fast_extDict_7_0(ms, seqStore, rep, src, srcSize); - } -} + } +} diff --git a/contrib/libs/zstd/lib/compress/zstd_fast.h b/contrib/libs/zstd/lib/compress/zstd_fast.h index 0d4a0c1090..1259a23629 100644 --- a/contrib/libs/zstd/lib/compress/zstd_fast.h +++ b/contrib/libs/zstd/lib/compress/zstd_fast.h @@ -1,37 +1,37 @@ -/* +/* * Copyright (c) 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_FAST_H -#define ZSTD_FAST_H - -#if defined (__cplusplus) -extern "C" { -#endif - + * 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_FAST_H +#define ZSTD_FAST_H + +#if defined (__cplusplus) +extern "C" { +#endif + #include "../common/mem.h" /* U32 */ -#include "zstd_compress_internal.h" - -void ZSTD_fillHashTable(ZSTD_matchState_t* ms, +#include "zstd_compress_internal.h" + +void ZSTD_fillHashTable(ZSTD_matchState_t* ms, void const* end, ZSTD_dictTableLoadMethod_e dtlm); -size_t ZSTD_compressBlock_fast( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_fast( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); size_t ZSTD_compressBlock_fast_dictMatchState( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); -size_t ZSTD_compressBlock_fast_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_fast_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); - -#if defined (__cplusplus) -} -#endif - -#endif /* ZSTD_FAST_H */ + +#if defined (__cplusplus) +} +#endif + +#endif /* ZSTD_FAST_H */ diff --git a/contrib/libs/zstd/lib/compress/zstd_lazy.c b/contrib/libs/zstd/lib/compress/zstd_lazy.c index 2e38dcb46d..d43ac04f95 100644 --- a/contrib/libs/zstd/lib/compress/zstd_lazy.c +++ b/contrib/libs/zstd/lib/compress/zstd_lazy.c @@ -1,154 +1,154 @@ -/* +/* * Copyright (c) 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. - */ - -#include "zstd_compress_internal.h" -#include "zstd_lazy.h" - - -/*-************************************* -* Binary Tree search -***************************************/ - + * 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. + */ + +#include "zstd_compress_internal.h" +#include "zstd_lazy.h" + + +/*-************************************* +* Binary Tree search +***************************************/ + static void ZSTD_updateDUBT(ZSTD_matchState_t* ms, - const BYTE* ip, const BYTE* iend, - U32 mls) -{ + const BYTE* ip, const BYTE* iend, + U32 mls) +{ const ZSTD_compressionParameters* const cParams = &ms->cParams; - U32* const hashTable = ms->hashTable; - U32 const hashLog = cParams->hashLog; - - U32* const bt = ms->chainTable; - U32 const btLog = cParams->chainLog - 1; - U32 const btMask = (1 << btLog) - 1; - - const BYTE* const base = ms->window.base; - U32 const target = (U32)(ip - base); - U32 idx = ms->nextToUpdate; - - if (idx != target) - DEBUGLOG(7, "ZSTD_updateDUBT, from %u to %u (dictLimit:%u)", - idx, target, ms->window.dictLimit); - assert(ip + 8 <= iend); /* condition for ZSTD_hashPtr */ - (void)iend; - - assert(idx >= ms->window.dictLimit); /* condition for valid base+idx */ - for ( ; idx < target ; idx++) { - size_t const h = ZSTD_hashPtr(base + idx, hashLog, mls); /* assumption : ip + 8 <= iend */ - U32 const matchIndex = hashTable[h]; - - U32* const nextCandidatePtr = bt + 2*(idx&btMask); - U32* const sortMarkPtr = nextCandidatePtr + 1; - - DEBUGLOG(8, "ZSTD_updateDUBT: insert %u", idx); - hashTable[h] = idx; /* Update Hash Table */ - *nextCandidatePtr = matchIndex; /* update BT like a chain */ - *sortMarkPtr = ZSTD_DUBT_UNSORTED_MARK; - } - ms->nextToUpdate = target; -} - - -/** ZSTD_insertDUBT1() : - * sort one already inserted but unsorted position + U32* const hashTable = ms->hashTable; + U32 const hashLog = cParams->hashLog; + + U32* const bt = ms->chainTable; + U32 const btLog = cParams->chainLog - 1; + U32 const btMask = (1 << btLog) - 1; + + const BYTE* const base = ms->window.base; + U32 const target = (U32)(ip - base); + U32 idx = ms->nextToUpdate; + + if (idx != target) + DEBUGLOG(7, "ZSTD_updateDUBT, from %u to %u (dictLimit:%u)", + idx, target, ms->window.dictLimit); + assert(ip + 8 <= iend); /* condition for ZSTD_hashPtr */ + (void)iend; + + assert(idx >= ms->window.dictLimit); /* condition for valid base+idx */ + for ( ; idx < target ; idx++) { + size_t const h = ZSTD_hashPtr(base + idx, hashLog, mls); /* assumption : ip + 8 <= iend */ + U32 const matchIndex = hashTable[h]; + + U32* const nextCandidatePtr = bt + 2*(idx&btMask); + U32* const sortMarkPtr = nextCandidatePtr + 1; + + DEBUGLOG(8, "ZSTD_updateDUBT: insert %u", idx); + hashTable[h] = idx; /* Update Hash Table */ + *nextCandidatePtr = matchIndex; /* update BT like a chain */ + *sortMarkPtr = ZSTD_DUBT_UNSORTED_MARK; + } + ms->nextToUpdate = target; +} + + +/** ZSTD_insertDUBT1() : + * sort one already inserted but unsorted position * assumption : curr >= btlow == (curr - btmask) - * doesn't fail */ + * doesn't fail */ static void ZSTD_insertDUBT1(const ZSTD_matchState_t* ms, U32 curr, const BYTE* inputEnd, U32 nbCompares, U32 btLow, const ZSTD_dictMode_e dictMode) -{ +{ const ZSTD_compressionParameters* const cParams = &ms->cParams; U32* const bt = ms->chainTable; U32 const btLog = cParams->chainLog - 1; U32 const btMask = (1 << btLog) - 1; - size_t commonLengthSmaller=0, commonLengthLarger=0; - const BYTE* const base = ms->window.base; - const BYTE* const dictBase = ms->window.dictBase; - const U32 dictLimit = ms->window.dictLimit; + size_t commonLengthSmaller=0, commonLengthLarger=0; + const BYTE* const base = ms->window.base; + const BYTE* const dictBase = ms->window.dictBase; + const U32 dictLimit = ms->window.dictLimit; const BYTE* const ip = (curr>=dictLimit) ? base + curr : dictBase + curr; const BYTE* const iend = (curr>=dictLimit) ? inputEnd : dictBase + dictLimit; - const BYTE* const dictEnd = dictBase + dictLimit; - const BYTE* const prefixStart = base + dictLimit; - const BYTE* match; + const BYTE* const dictEnd = dictBase + dictLimit; + const BYTE* const prefixStart = base + dictLimit; + const BYTE* match; U32* smallerPtr = bt + 2*(curr&btMask); - U32* largerPtr = smallerPtr + 1; + U32* largerPtr = smallerPtr + 1; U32 matchIndex = *smallerPtr; /* this candidate is unsorted : next sorted candidate is reached through *smallerPtr, while *largerPtr contains previous unsorted candidate (which is already saved and can be overwritten) */ - U32 dummy32; /* to be nullified at the end */ + U32 dummy32; /* to be nullified at the end */ U32 const windowValid = ms->window.lowLimit; U32 const maxDistance = 1U << cParams->windowLog; U32 const windowLow = (curr - windowValid > maxDistance) ? curr - maxDistance : windowValid; + - - DEBUGLOG(8, "ZSTD_insertDUBT1(%u) (dictLimit=%u, lowLimit=%u)", + DEBUGLOG(8, "ZSTD_insertDUBT1(%u) (dictLimit=%u, lowLimit=%u)", curr, dictLimit, windowLow); assert(curr >= btLow); - assert(ip < iend); /* condition for ZSTD_count */ - + assert(ip < iend); /* condition for ZSTD_count */ + for (; nbCompares && (matchIndex > windowLow); --nbCompares) { - U32* const nextPtr = bt + 2*(matchIndex & btMask); - size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ + U32* const nextPtr = bt + 2*(matchIndex & btMask); + size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ assert(matchIndex < curr); /* note : all candidates are now supposed sorted, * but it's still possible to have nextPtr[1] == ZSTD_DUBT_UNSORTED_MARK * when a real index has the same value as ZSTD_DUBT_UNSORTED_MARK */ - + if ( (dictMode != ZSTD_extDict) - || (matchIndex+matchLength >= dictLimit) /* both in current segment*/ + || (matchIndex+matchLength >= dictLimit) /* both in current segment*/ || (curr < dictLimit) /* both in extDict */) { const BYTE* const mBase = ( (dictMode != ZSTD_extDict) || (matchIndex+matchLength >= dictLimit)) ? base : dictBase; - assert( (matchIndex+matchLength >= dictLimit) /* might be wrong if extDict is incorrectly set to 0 */ + assert( (matchIndex+matchLength >= dictLimit) /* might be wrong if extDict is incorrectly set to 0 */ || (curr < dictLimit) ); - match = mBase + matchIndex; - matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend); - } else { - match = dictBase + matchIndex; - matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart); - if (matchIndex+matchLength >= dictLimit) + match = mBase + matchIndex; + matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend); + } else { + match = dictBase + matchIndex; + matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart); + if (matchIndex+matchLength >= dictLimit) match = base + matchIndex; /* preparation for next read of match[matchLength] */ - } - - DEBUGLOG(8, "ZSTD_insertDUBT1: comparing %u with %u : found %u common bytes ", + } + + DEBUGLOG(8, "ZSTD_insertDUBT1: comparing %u with %u : found %u common bytes ", curr, matchIndex, (U32)matchLength); - - if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */ - break; /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt tree */ - } - - if (match[matchLength] < ip[matchLength]) { /* necessarily within buffer */ - /* match is smaller than current */ - *smallerPtr = matchIndex; /* update smaller idx */ - commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ - if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop searching */ - DEBUGLOG(8, "ZSTD_insertDUBT1: %u (>btLow=%u) is smaller : next => %u", - matchIndex, btLow, nextPtr[1]); - smallerPtr = nextPtr+1; /* new "candidate" => larger than match, which was smaller than target */ - matchIndex = nextPtr[1]; /* new matchIndex, larger than previous and closer to current */ - } else { - /* match is larger than current */ - *largerPtr = matchIndex; - commonLengthLarger = matchLength; - if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop searching */ - DEBUGLOG(8, "ZSTD_insertDUBT1: %u (>btLow=%u) is larger => %u", - matchIndex, btLow, nextPtr[0]); - largerPtr = nextPtr; - matchIndex = nextPtr[0]; - } } - - *smallerPtr = *largerPtr = 0; -} - - + + if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */ + break; /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt tree */ + } + + if (match[matchLength] < ip[matchLength]) { /* necessarily within buffer */ + /* match is smaller than current */ + *smallerPtr = matchIndex; /* update smaller idx */ + commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ + if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop searching */ + DEBUGLOG(8, "ZSTD_insertDUBT1: %u (>btLow=%u) is smaller : next => %u", + matchIndex, btLow, nextPtr[1]); + smallerPtr = nextPtr+1; /* new "candidate" => larger than match, which was smaller than target */ + matchIndex = nextPtr[1]; /* new matchIndex, larger than previous and closer to current */ + } else { + /* match is larger than current */ + *largerPtr = matchIndex; + commonLengthLarger = matchLength; + if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop searching */ + DEBUGLOG(8, "ZSTD_insertDUBT1: %u (>btLow=%u) is larger => %u", + matchIndex, btLow, nextPtr[0]); + largerPtr = nextPtr; + matchIndex = nextPtr[0]; + } } + + *smallerPtr = *largerPtr = 0; +} + + static size_t ZSTD_DUBT_findBetterDictMatch ( const ZSTD_matchState_t* ms, @@ -158,7 +158,7 @@ ZSTD_DUBT_findBetterDictMatch ( U32 nbCompares, U32 const mls, const ZSTD_dictMode_e dictMode) -{ +{ const ZSTD_matchState_t * const dms = ms->dictMatchState; const ZSTD_compressionParameters* const dmsCParams = &dms->cParams; const U32 * const dictHashTable = dms->hashTable; @@ -235,128 +235,128 @@ ZSTD_DUBT_findBestMatch(ZSTD_matchState_t* ms, const ZSTD_dictMode_e dictMode) { const ZSTD_compressionParameters* const cParams = &ms->cParams; - U32* const hashTable = ms->hashTable; - U32 const hashLog = cParams->hashLog; - size_t const h = ZSTD_hashPtr(ip, hashLog, mls); - U32 matchIndex = hashTable[h]; - - const BYTE* const base = ms->window.base; + U32* const hashTable = ms->hashTable; + U32 const hashLog = cParams->hashLog; + size_t const h = ZSTD_hashPtr(ip, hashLog, mls); + U32 matchIndex = hashTable[h]; + + const BYTE* const base = ms->window.base; U32 const curr = (U32)(ip-base); U32 const windowLow = ZSTD_getLowestMatchIndex(ms, curr, cParams->windowLog); - - U32* const bt = ms->chainTable; - U32 const btLog = cParams->chainLog - 1; - U32 const btMask = (1 << btLog) - 1; + + U32* const bt = ms->chainTable; + U32 const btLog = cParams->chainLog - 1; + U32 const btMask = (1 << btLog) - 1; U32 const btLow = (btMask >= curr) ? 0 : curr - btMask; - U32 const unsortLimit = MAX(btLow, windowLow); - - U32* nextCandidate = bt + 2*(matchIndex&btMask); - U32* unsortedMark = bt + 2*(matchIndex&btMask) + 1; - U32 nbCompares = 1U << cParams->searchLog; - U32 nbCandidates = nbCompares; - U32 previousCandidate = 0; - + U32 const unsortLimit = MAX(btLow, windowLow); + + U32* nextCandidate = bt + 2*(matchIndex&btMask); + U32* unsortedMark = bt + 2*(matchIndex&btMask) + 1; + U32 nbCompares = 1U << cParams->searchLog; + U32 nbCandidates = nbCompares; + U32 previousCandidate = 0; + DEBUGLOG(7, "ZSTD_DUBT_findBestMatch (%u) ", curr); - assert(ip <= iend-8); /* required for h calculation */ + assert(ip <= iend-8); /* required for h calculation */ assert(dictMode != ZSTD_dedicatedDictSearch); - - /* reach end of unsorted candidates list */ - while ( (matchIndex > unsortLimit) - && (*unsortedMark == ZSTD_DUBT_UNSORTED_MARK) - && (nbCandidates > 1) ) { - DEBUGLOG(8, "ZSTD_DUBT_findBestMatch: candidate %u is unsorted", - matchIndex); + + /* reach end of unsorted candidates list */ + while ( (matchIndex > unsortLimit) + && (*unsortedMark == ZSTD_DUBT_UNSORTED_MARK) + && (nbCandidates > 1) ) { + DEBUGLOG(8, "ZSTD_DUBT_findBestMatch: candidate %u is unsorted", + matchIndex); *unsortedMark = previousCandidate; /* the unsortedMark becomes a reversed chain, to move up back to original position */ - previousCandidate = matchIndex; - matchIndex = *nextCandidate; - nextCandidate = bt + 2*(matchIndex&btMask); - unsortedMark = bt + 2*(matchIndex&btMask) + 1; - nbCandidates --; - } - + previousCandidate = matchIndex; + matchIndex = *nextCandidate; + nextCandidate = bt + 2*(matchIndex&btMask); + unsortedMark = bt + 2*(matchIndex&btMask) + 1; + nbCandidates --; + } + /* nullify last candidate if it's still unsorted * simplification, detrimental to compression ratio, beneficial for speed */ - if ( (matchIndex > unsortLimit) - && (*unsortedMark==ZSTD_DUBT_UNSORTED_MARK) ) { - DEBUGLOG(7, "ZSTD_DUBT_findBestMatch: nullify last unsorted candidate %u", - matchIndex); + if ( (matchIndex > unsortLimit) + && (*unsortedMark==ZSTD_DUBT_UNSORTED_MARK) ) { + DEBUGLOG(7, "ZSTD_DUBT_findBestMatch: nullify last unsorted candidate %u", + matchIndex); *nextCandidate = *unsortedMark = 0; - } - - /* batch sort stacked candidates */ - matchIndex = previousCandidate; - while (matchIndex) { /* will end on matchIndex == 0 */ - U32* const nextCandidateIdxPtr = bt + 2*(matchIndex&btMask) + 1; - U32 const nextCandidateIdx = *nextCandidateIdxPtr; + } + + /* batch sort stacked candidates */ + matchIndex = previousCandidate; + while (matchIndex) { /* will end on matchIndex == 0 */ + U32* const nextCandidateIdxPtr = bt + 2*(matchIndex&btMask) + 1; + U32 const nextCandidateIdx = *nextCandidateIdxPtr; ZSTD_insertDUBT1(ms, matchIndex, iend, nbCandidates, unsortLimit, dictMode); - matchIndex = nextCandidateIdx; - nbCandidates++; - } - - /* find longest match */ + matchIndex = nextCandidateIdx; + nbCandidates++; + } + + /* find longest match */ { size_t commonLengthSmaller = 0, commonLengthLarger = 0; - const BYTE* const dictBase = ms->window.dictBase; - const U32 dictLimit = ms->window.dictLimit; - const BYTE* const dictEnd = dictBase + dictLimit; - const BYTE* const prefixStart = base + dictLimit; + const BYTE* const dictBase = ms->window.dictBase; + const U32 dictLimit = ms->window.dictLimit; + const BYTE* const dictEnd = dictBase + dictLimit; + const BYTE* const prefixStart = base + dictLimit; U32* smallerPtr = bt + 2*(curr&btMask); U32* largerPtr = bt + 2*(curr&btMask) + 1; U32 matchEndIdx = curr + 8 + 1; - U32 dummy32; /* to be nullified at the end */ - size_t bestLength = 0; - - matchIndex = hashTable[h]; + U32 dummy32; /* to be nullified at the end */ + size_t bestLength = 0; + + matchIndex = hashTable[h]; hashTable[h] = curr; /* Update Hash Table */ - + for (; nbCompares && (matchIndex > windowLow); --nbCompares) { - U32* const nextPtr = bt + 2*(matchIndex & btMask); - size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ - const BYTE* match; - + U32* const nextPtr = bt + 2*(matchIndex & btMask); + size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ + const BYTE* match; + if ((dictMode != ZSTD_extDict) || (matchIndex+matchLength >= dictLimit)) { - match = base + matchIndex; - matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend); - } else { - match = dictBase + matchIndex; - matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart); - if (matchIndex+matchLength >= dictLimit) - match = base + matchIndex; /* to prepare for next usage of match[matchLength] */ - } - - if (matchLength > bestLength) { - if (matchLength > matchEndIdx - matchIndex) - matchEndIdx = matchIndex + (U32)matchLength; + match = base + matchIndex; + matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend); + } else { + match = dictBase + matchIndex; + matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart); + if (matchIndex+matchLength >= dictLimit) + match = base + matchIndex; /* to prepare for next usage of match[matchLength] */ + } + + if (matchLength > bestLength) { + if (matchLength > matchEndIdx - matchIndex) + matchEndIdx = matchIndex + (U32)matchLength; if ( (4*(int)(matchLength-bestLength)) > (int)(ZSTD_highbit32(curr-matchIndex+1) - ZSTD_highbit32((U32)offsetPtr[0]+1)) ) bestLength = matchLength, *offsetPtr = STORE_OFFSET(curr - matchIndex); - if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */ + if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */ if (dictMode == ZSTD_dictMatchState) { nbCompares = 0; /* in addition to avoiding checking any * further in this loop, make sure we * skip checking in the dictionary. */ } - break; /* drop, to guarantee consistency (miss a little bit of compression) */ - } - } - - if (match[matchLength] < ip[matchLength]) { - /* match is smaller than current */ - *smallerPtr = matchIndex; /* update smaller idx */ - commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ - if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop the search */ - smallerPtr = nextPtr+1; /* new "smaller" => larger of match */ - matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to current) */ - } else { - /* match is larger than current */ - *largerPtr = matchIndex; - commonLengthLarger = matchLength; - if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop the search */ - largerPtr = nextPtr; - matchIndex = nextPtr[0]; - } } - - *smallerPtr = *largerPtr = 0; - + break; /* drop, to guarantee consistency (miss a little bit of compression) */ + } + } + + if (match[matchLength] < ip[matchLength]) { + /* match is smaller than current */ + *smallerPtr = matchIndex; /* update smaller idx */ + commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ + if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop the search */ + smallerPtr = nextPtr+1; /* new "smaller" => larger of match */ + matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to current) */ + } else { + /* match is larger than current */ + *largerPtr = matchIndex; + commonLengthLarger = matchLength; + if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop the search */ + largerPtr = nextPtr; + matchIndex = nextPtr[0]; + } } + + *smallerPtr = *largerPtr = 0; + assert(nbCompares <= (1U << ZSTD_SEARCHLOG_MAX)); /* Check we haven't underflowed. */ if (dictMode == ZSTD_dictMatchState && nbCompares) { bestLength = ZSTD_DUBT_findBetterDictMatch( @@ -366,35 +366,35 @@ ZSTD_DUBT_findBestMatch(ZSTD_matchState_t* ms, } assert(matchEndIdx > curr+8); /* ensure nextToUpdate is increased */ - ms->nextToUpdate = matchEndIdx - 8; /* skip repetitive patterns */ - if (bestLength >= MINMATCH) { + ms->nextToUpdate = matchEndIdx - 8; /* skip repetitive patterns */ + if (bestLength >= MINMATCH) { U32 const mIndex = curr - (U32)STORED_OFFSET(*offsetPtr); (void)mIndex; - DEBUGLOG(8, "ZSTD_DUBT_findBestMatch(%u) : found match of length %u and offsetCode %u (pos %u)", + DEBUGLOG(8, "ZSTD_DUBT_findBestMatch(%u) : found match of length %u and offsetCode %u (pos %u)", curr, (U32)bestLength, (U32)*offsetPtr, mIndex); - } - return bestLength; - } -} - - -/** ZSTD_BtFindBestMatch() : Tree updater, providing best match */ + } + return bestLength; + } +} + + +/** ZSTD_BtFindBestMatch() : Tree updater, providing best match */ FORCE_INLINE_TEMPLATE size_t ZSTD_BtFindBestMatch( ZSTD_matchState_t* ms, const BYTE* const ip, const BYTE* const iLimit, size_t* offsetPtr, const U32 mls /* template */, const ZSTD_dictMode_e dictMode) -{ - DEBUGLOG(7, "ZSTD_BtFindBestMatch"); - if (ip < ms->window.base + ms->nextToUpdate) return 0; /* skipped area */ +{ + DEBUGLOG(7, "ZSTD_BtFindBestMatch"); + if (ip < ms->window.base + ms->nextToUpdate) return 0; /* skipped area */ ZSTD_updateDUBT(ms, ip, iLimit, mls); return ZSTD_DUBT_findBestMatch(ms, ip, iLimit, offsetPtr, mls, dictMode); -} - +} + /*********************************** * Dedicated dict search -***********************************/ - +***********************************/ + void ZSTD_dedicatedDictSearch_lazy_loadDictionary(ZSTD_matchState_t* ms, const BYTE* const ip) { const BYTE* const base = ms->window.base; @@ -408,7 +408,7 @@ void ZSTD_dedicatedDictSearch_lazy_loadDictionary(ZSTD_matchState_t* ms, const B U32 const cacheSize = bucketSize - 1; U32 const chainAttempts = (1 << ms->cParams.searchLog) - cacheSize; U32 const chainLimit = chainAttempts > 255 ? 255 : chainAttempts; - + /* We know the hashtable is oversized by a factor of `bucketSize`. * We are going to temporarily pretend `bucketSize == 1`, keeping only a * single entry. We will use the rest of the space to construct a temporary @@ -643,23 +643,23 @@ U32 ZSTD_insertAndFindFirstIndex(ZSTD_matchState_t* ms, const BYTE* ip) { return ZSTD_insertAndFindFirstIndex_internal(ms, cParams, ip, ms->cParams.minMatch); } -/* inlining is important to hardwire a hot branch (template emulation) */ -FORCE_INLINE_TEMPLATE +/* inlining is important to hardwire a hot branch (template emulation) */ +FORCE_INLINE_TEMPLATE size_t ZSTD_HcFindBestMatch( ZSTD_matchState_t* ms, - const BYTE* const ip, const BYTE* const iLimit, - size_t* offsetPtr, + const BYTE* const ip, const BYTE* const iLimit, + size_t* offsetPtr, const U32 mls, const ZSTD_dictMode_e dictMode) -{ +{ const ZSTD_compressionParameters* const cParams = &ms->cParams; - U32* const chainTable = ms->chainTable; - const U32 chainSize = (1 << cParams->chainLog); - const U32 chainMask = chainSize-1; - const BYTE* const base = ms->window.base; - const BYTE* const dictBase = ms->window.dictBase; - const U32 dictLimit = ms->window.dictLimit; - const BYTE* const prefixStart = base + dictLimit; - const BYTE* const dictEnd = dictBase + dictLimit; + U32* const chainTable = ms->chainTable; + const U32 chainSize = (1 << cParams->chainLog); + const U32 chainMask = chainSize-1; + const BYTE* const base = ms->window.base; + const BYTE* const dictBase = ms->window.dictBase; + const U32 dictLimit = ms->window.dictLimit; + const BYTE* const prefixStart = base + dictLimit; + const BYTE* const dictEnd = dictBase + dictLimit; const U32 curr = (U32)(ip-base); const U32 maxDistance = 1U << cParams->windowLog; const U32 lowestValid = ms->window.lowLimit; @@ -667,9 +667,9 @@ size_t ZSTD_HcFindBestMatch( const U32 isDictionary = (ms->loadedDictEnd != 0); const U32 lowLimit = isDictionary ? lowestValid : withinMaxDistance; const U32 minChain = curr > chainSize ? curr - chainSize : 0; - U32 nbAttempts = 1U << cParams->searchLog; - size_t ml=4-1; - + U32 nbAttempts = 1U << cParams->searchLog; + size_t ml=4-1; + const ZSTD_matchState_t* const dms = ms->dictMatchState; const U32 ddsHashLog = dictMode == ZSTD_dedicatedDictSearch ? dms->cParams.hashLog - ZSTD_LAZY_DDSS_BUCKET_LOG : 0; @@ -683,34 +683,34 @@ size_t ZSTD_HcFindBestMatch( PREFETCH_L1(entry); } - /* HC4 match finder */ + /* HC4 match finder */ matchIndex = ZSTD_insertAndFindFirstIndex_internal(ms, cParams, ip, mls); - + for ( ; (matchIndex>=lowLimit) & (nbAttempts>0) ; nbAttempts--) { - size_t currentMl=0; + size_t currentMl=0; if ((dictMode != ZSTD_extDict) || matchIndex >= dictLimit) { - const BYTE* const match = base + matchIndex; + const BYTE* const match = base + matchIndex; assert(matchIndex >= dictLimit); /* ensures this is true if dictMode != ZSTD_extDict */ - if (match[ml] == ip[ml]) /* potentially better */ - currentMl = ZSTD_count(ip, match, iLimit); - } else { - const BYTE* const match = dictBase + matchIndex; - assert(match+4 <= dictEnd); - if (MEM_read32(match) == MEM_read32(ip)) /* assumption : matchIndex <= dictLimit-4 (by table construction) */ - currentMl = ZSTD_count_2segments(ip+4, match+4, iLimit, dictEnd, prefixStart) + 4; - } - - /* save best solution */ - if (currentMl > ml) { - ml = currentMl; + if (match[ml] == ip[ml]) /* potentially better */ + currentMl = ZSTD_count(ip, match, iLimit); + } else { + const BYTE* const match = dictBase + matchIndex; + assert(match+4 <= dictEnd); + if (MEM_read32(match) == MEM_read32(ip)) /* assumption : matchIndex <= dictLimit-4 (by table construction) */ + currentMl = ZSTD_count_2segments(ip+4, match+4, iLimit, dictEnd, prefixStart) + 4; + } + + /* save best solution */ + if (currentMl > ml) { + ml = currentMl; *offsetPtr = STORE_OFFSET(curr - matchIndex); - if (ip+currentMl == iLimit) break; /* best possible, avoids read overflow on next attempt */ - } - - if (matchIndex <= minChain) break; - matchIndex = NEXT_IN_CHAIN(matchIndex, chainMask); - } - + if (ip+currentMl == iLimit) break; /* best possible, avoids read overflow on next attempt */ + } + + if (matchIndex <= minChain) break; + matchIndex = NEXT_IN_CHAIN(matchIndex, chainMask); + } + assert(nbAttempts <= (1U << ZSTD_SEARCHLOG_MAX)); /* Check we haven't underflowed. */ if (dictMode == ZSTD_dedicatedDictSearch) { ml = ZSTD_dedicatedDictSearch_lazy_search(offsetPtr, ml, nbAttempts, dms, @@ -749,9 +749,9 @@ size_t ZSTD_HcFindBestMatch( } } - return ml; -} - + return ml; +} + /* ********************************* * (SIMD) Row-based matchfinder ***********************************/ @@ -760,7 +760,7 @@ size_t ZSTD_HcFindBestMatch( #define ZSTD_ROW_HASH_TAG_BITS 8 /* nb bits to use for the tag */ #define ZSTD_ROW_HASH_TAG_MASK ((1u << ZSTD_ROW_HASH_TAG_BITS) - 1) #define ZSTD_ROW_HASH_MAX_ENTRIES 64 /* absolute maximum number of entries per row, for all configurations */ - + #define ZSTD_ROW_HASH_CACHE_MASK (ZSTD_ROW_HASH_CACHE_SIZE - 1) typedef U64 ZSTD_VecMask; /* Clarifies when we are interacting with a U64 representing a mask of matches */ @@ -1437,9 +1437,9 @@ ZSTD_FOR_EACH_DICT_MODE(ZSTD_FOR_EACH_MLS, GEN_ZSTD_HC_VTABLE) X(dedicatedDictSearch) \ } -/* ******************************* -* Common parser - lazy strategy -*********************************/ +/* ******************************* +* Common parser - lazy strategy +*********************************/ typedef enum { search_hashChain=0, search_binaryTree=1, search_rowHash=2 } searchMethod_e; /** @@ -1474,24 +1474,24 @@ ZSTD_selectLazyVTable(ZSTD_matchState_t const* ms, searchMethod_e searchMethod, FORCE_INLINE_TEMPLATE size_t ZSTD_compressBlock_lazy_generic( - ZSTD_matchState_t* ms, seqStore_t* seqStore, - U32 rep[ZSTD_REP_NUM], - const void* src, size_t srcSize, + ZSTD_matchState_t* ms, seqStore_t* seqStore, + U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize, const searchMethod_e searchMethod, const U32 depth, ZSTD_dictMode_e const dictMode) -{ - const BYTE* const istart = (const BYTE*)src; - const BYTE* ip = istart; - const BYTE* anchor = istart; - const BYTE* const iend = istart + srcSize; +{ + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; + const BYTE* const iend = istart + srcSize; const BYTE* const ilimit = (searchMethod == search_rowHash) ? iend - 8 - ZSTD_ROW_HASH_CACHE_SIZE : iend - 8; const BYTE* const base = ms->window.base; const U32 prefixLowestIndex = ms->window.dictLimit; const BYTE* const prefixLowest = base + prefixLowestIndex; - + searchMax_f const searchMax = ZSTD_selectLazyVTable(ms, searchMethod, dictMode)->searchMax; - U32 offset_1 = rep[0], offset_2 = rep[1], savedOffset=0; - + U32 offset_1 = rep[0], offset_2 = rep[1], savedOffset=0; + const int isDMS = dictMode == ZSTD_dictMatchState; const int isDDS = dictMode == ZSTD_dedicatedDictSearch; const int isDxS = isDMS || isDDS; @@ -1513,16 +1513,16 @@ ZSTD_compressBlock_lazy_generic( U32 const curr = (U32)(ip - base); U32 const windowLow = ZSTD_getLowestPrefixIndex(ms, curr, ms->cParams.windowLog); U32 const maxRep = curr - windowLow; - if (offset_2 > maxRep) savedOffset = offset_2, offset_2 = 0; - if (offset_1 > maxRep) savedOffset = offset_1, offset_1 = 0; - } + if (offset_2 > maxRep) savedOffset = offset_2, offset_2 = 0; + if (offset_1 > maxRep) savedOffset = offset_1, offset_1 = 0; + } if (isDxS) { /* dictMatchState repCode checks don't currently handle repCode == 0 * disabling. */ assert(offset_1 <= dictAndPrefixLength); assert(offset_2 <= dictAndPrefixLength); } - + if (searchMethod == search_rowHash) { const U32 rowLog = MAX(4, MIN(6, ms->cParams.searchLog)); ZSTD_row_fillHashCache(ms, base, rowLog, @@ -1530,20 +1530,20 @@ ZSTD_compressBlock_lazy_generic( ms->nextToUpdate, ilimit); } - /* Match Loop */ + /* Match Loop */ #if defined(__GNUC__) && defined(__x86_64__) /* I've measured random a 5% speed loss on levels 5 & 6 (greedy) when the * code alignment is perturbed. To fix the instability align the loop on 32-bytes. */ __asm__(".p2align 5"); #endif - while (ip < ilimit) { - size_t matchLength=0; + while (ip < ilimit) { + size_t matchLength=0; size_t offcode=STORE_REPCODE_1; - const BYTE* start=ip+1; + const BYTE* start=ip+1; DEBUGLOG(7, "search baseline (depth 0)"); - - /* check repCode */ + + /* check repCode */ if (isDxS) { const U32 repIndex = (U32)(ip - base) + 1 - offset_1; const BYTE* repMatch = ((dictMode == ZSTD_dictMatchState || dictMode == ZSTD_dedicatedDictSearch) @@ -1559,35 +1559,35 @@ ZSTD_compressBlock_lazy_generic( } if ( dictMode == ZSTD_noDict && ((offset_1 > 0) & (MEM_read32(ip+1-offset_1) == MEM_read32(ip+1)))) { - matchLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4; - if (depth==0) goto _storeSequence; - } - - /* first search (depth 0) */ + matchLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4; + if (depth==0) goto _storeSequence; + } + + /* first search (depth 0) */ { size_t offsetFound = 999999999; size_t const ml2 = searchMax(ms, ip, iend, &offsetFound); - if (ml2 > matchLength) + if (ml2 > matchLength) matchLength = ml2, start = ip, offcode=offsetFound; - } - - if (matchLength < 4) { - ip += ((ip-anchor) >> kSearchStrength) + 1; /* jump faster over incompressible sections */ - continue; - } - - /* let's try to find a better solution */ - if (depth>=1) - while (ip<ilimit) { + } + + if (matchLength < 4) { + ip += ((ip-anchor) >> kSearchStrength) + 1; /* jump faster over incompressible sections */ + continue; + } + + /* let's try to find a better solution */ + if (depth>=1) + while (ip<ilimit) { DEBUGLOG(7, "search depth 1"); - ip ++; + ip ++; if ( (dictMode == ZSTD_noDict) && (offcode) && ((offset_1>0) & (MEM_read32(ip) == MEM_read32(ip - offset_1)))) { - size_t const mlRep = ZSTD_count(ip+4, ip+4-offset_1, iend) + 4; - int const gain2 = (int)(mlRep * 3); + size_t const mlRep = ZSTD_count(ip+4, ip+4-offset_1, iend) + 4; + int const gain2 = (int)(mlRep * 3); int const gain1 = (int)(matchLength*3 - ZSTD_highbit32((U32)STORED_TO_OFFBASE(offcode)) + 1); - if ((mlRep >= 4) && (gain2 > gain1)) + if ((mlRep >= 4) && (gain2 > gain1)) matchLength = mlRep, offcode = STORE_REPCODE_1, start = ip; - } + } if (isDxS) { const U32 repIndex = (U32)(ip - base) - offset_1; const BYTE* repMatch = repIndex < prefixLowestIndex ? @@ -1607,15 +1607,15 @@ ZSTD_compressBlock_lazy_generic( size_t const ml2 = searchMax(ms, ip, iend, &offset2); int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)STORED_TO_OFFBASE(offset2))); /* raw approx */ int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)STORED_TO_OFFBASE(offcode)) + 4); - if ((ml2 >= 4) && (gain2 > gain1)) { + if ((ml2 >= 4) && (gain2 > gain1)) { matchLength = ml2, offcode = offset2, start = ip; - continue; /* search a better one */ - } } - - /* let's find an even better one */ - if ((depth==2) && (ip<ilimit)) { + continue; /* search a better one */ + } } + + /* let's find an even better one */ + if ((depth==2) && (ip<ilimit)) { DEBUGLOG(7, "search depth 2"); - ip ++; + ip ++; if ( (dictMode == ZSTD_noDict) && (offcode) && ((offset_1>0) & (MEM_read32(ip) == MEM_read32(ip - offset_1)))) { size_t const mlRep = ZSTD_count(ip+4, ip+4-offset_1, iend) + 4; @@ -1623,7 +1623,7 @@ ZSTD_compressBlock_lazy_generic( int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)STORED_TO_OFFBASE(offcode)) + 1); if ((mlRep >= 4) && (gain2 > gain1)) matchLength = mlRep, offcode = STORE_REPCODE_1, start = ip; - } + } if (isDxS) { const U32 repIndex = (U32)(ip - base) - offset_1; const BYTE* repMatch = repIndex < prefixLowestIndex ? @@ -1643,18 +1643,18 @@ ZSTD_compressBlock_lazy_generic( size_t const ml2 = searchMax(ms, ip, iend, &offset2); int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)STORED_TO_OFFBASE(offset2))); /* raw approx */ int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)STORED_TO_OFFBASE(offcode)) + 7); - if ((ml2 >= 4) && (gain2 > gain1)) { + if ((ml2 >= 4) && (gain2 > gain1)) { matchLength = ml2, offcode = offset2, start = ip; - continue; - } } } - break; /* nothing found : store previous solution */ - } - - /* NOTE: + continue; + } } } + break; /* nothing found : store previous solution */ + } + + /* NOTE: * Pay attention that `start[-value]` can lead to strange undefined behavior * notably if `value` is unsigned, resulting in a large positive `-value`. - */ - /* catch up */ + */ + /* catch up */ if (STORED_IS_OFFSET(offcode)) { if (dictMode == ZSTD_noDict) { while ( ((start > anchor) & (start - STORED_OFFSET(offcode) > prefixLowest)) @@ -1668,15 +1668,15 @@ ZSTD_compressBlock_lazy_generic( while ((start>anchor) && (match>mStart) && (start[-1] == match[-1])) { start--; match--; matchLength++; } /* catch up */ } offset_2 = offset_1; offset_1 = (U32)STORED_OFFSET(offcode); - } - /* store sequence */ -_storeSequence: + } + /* store sequence */ +_storeSequence: { size_t const litLength = (size_t)(start - anchor); ZSTD_storeSeq(seqStore, litLength, anchor, iend, (U32)offcode, matchLength); - anchor = ip = start + matchLength; - } - - /* check immediate repcode */ + anchor = ip = start + matchLength; + } + + /* check immediate repcode */ if (isDxS) { while (ip <= ilimit) { U32 const current2 = (U32)(ip-base); @@ -1697,7 +1697,7 @@ _storeSequence: break; } } - + if (dictMode == ZSTD_noDict) { while ( ((ip <= ilimit) & (offset_2>0)) && (MEM_read32(ip) == MEM_read32(ip - offset_2)) ) { @@ -1710,50 +1710,50 @@ _storeSequence: continue; /* faster when present ... (?) */ } } } - /* Save reps for next block */ - rep[0] = offset_1 ? offset_1 : savedOffset; - rep[1] = offset_2 ? offset_2 : savedOffset; - - /* Return the last literals size */ + /* Save reps for next block */ + rep[0] = offset_1 ? offset_1 : savedOffset; + rep[1] = offset_2 ? offset_2 : savedOffset; + + /* Return the last literals size */ return (size_t)(iend - anchor); -} - - -size_t ZSTD_compressBlock_btlazy2( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +} + + +size_t ZSTD_compressBlock_btlazy2( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) -{ +{ return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_binaryTree, 2, ZSTD_noDict); -} - -size_t ZSTD_compressBlock_lazy2( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +} + +size_t ZSTD_compressBlock_lazy2( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) -{ +{ return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2, ZSTD_noDict); -} - -size_t ZSTD_compressBlock_lazy( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +} + +size_t ZSTD_compressBlock_lazy( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) -{ +{ return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1, ZSTD_noDict); -} - -size_t ZSTD_compressBlock_greedy( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +} + +size_t ZSTD_compressBlock_greedy( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) -{ +{ return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0, ZSTD_noDict); -} - +} + size_t ZSTD_compressBlock_btlazy2_dictMatchState( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) { return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_binaryTree, 2, ZSTD_dictMatchState); } - + size_t ZSTD_compressBlock_lazy2_dictMatchState( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) @@ -1862,223 +1862,223 @@ size_t ZSTD_compressBlock_greedy_dedicatedDictSearch_row( return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_rowHash, 0, ZSTD_dedicatedDictSearch); } -FORCE_INLINE_TEMPLATE -size_t ZSTD_compressBlock_lazy_extDict_generic( - ZSTD_matchState_t* ms, seqStore_t* seqStore, - U32 rep[ZSTD_REP_NUM], - const void* src, size_t srcSize, +FORCE_INLINE_TEMPLATE +size_t ZSTD_compressBlock_lazy_extDict_generic( + ZSTD_matchState_t* ms, seqStore_t* seqStore, + U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize, const searchMethod_e searchMethod, const U32 depth) -{ - const BYTE* const istart = (const BYTE*)src; - const BYTE* ip = istart; - const BYTE* anchor = istart; - const BYTE* const iend = istart + srcSize; +{ + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; + const BYTE* const iend = istart + srcSize; const BYTE* const ilimit = searchMethod == search_rowHash ? iend - 8 - ZSTD_ROW_HASH_CACHE_SIZE : iend - 8; - const BYTE* const base = ms->window.base; - const U32 dictLimit = ms->window.dictLimit; - const BYTE* const prefixStart = base + dictLimit; - const BYTE* const dictBase = ms->window.dictBase; - const BYTE* const dictEnd = dictBase + dictLimit; + const BYTE* const base = ms->window.base; + const U32 dictLimit = ms->window.dictLimit; + const BYTE* const prefixStart = base + dictLimit; + const BYTE* const dictBase = ms->window.dictBase; + const BYTE* const dictEnd = dictBase + dictLimit; const BYTE* const dictStart = dictBase + ms->window.lowLimit; const U32 windowLog = ms->cParams.windowLog; const U32 rowLog = ms->cParams.searchLog < 5 ? 4 : 5; - + searchMax_f const searchMax = ZSTD_selectLazyVTable(ms, searchMethod, ZSTD_extDict)->searchMax; - U32 offset_1 = rep[0], offset_2 = rep[1]; - + U32 offset_1 = rep[0], offset_2 = rep[1]; + DEBUGLOG(5, "ZSTD_compressBlock_lazy_extDict_generic (searchFunc=%u)", (U32)searchMethod); - /* init */ - ip += (ip == prefixStart); + /* init */ + ip += (ip == prefixStart); if (searchMethod == search_rowHash) { ZSTD_row_fillHashCache(ms, base, rowLog, MIN(ms->cParams.minMatch, 6 /* mls caps out at 6 */), ms->nextToUpdate, ilimit); } - - /* Match Loop */ + + /* Match Loop */ #if defined(__GNUC__) && defined(__x86_64__) /* I've measured random a 5% speed loss on levels 5 & 6 (greedy) when the * code alignment is perturbed. To fix the instability align the loop on 32-bytes. */ __asm__(".p2align 5"); #endif - while (ip < ilimit) { - size_t matchLength=0; + while (ip < ilimit) { + size_t matchLength=0; size_t offcode=STORE_REPCODE_1; - const BYTE* start=ip+1; + const BYTE* start=ip+1; U32 curr = (U32)(ip-base); - - /* check repCode */ + + /* check repCode */ { const U32 windowLow = ZSTD_getLowestMatchIndex(ms, curr+1, windowLog); const U32 repIndex = (U32)(curr+1 - offset_1); - const BYTE* const repBase = repIndex < dictLimit ? dictBase : base; - const BYTE* const repMatch = repBase + repIndex; + const BYTE* const repBase = repIndex < dictLimit ? dictBase : base; + const BYTE* const repMatch = repBase + repIndex; if ( ((U32)((dictLimit-1) - repIndex) >= 3) /* intentional overflow */ & (offset_1 <= curr+1 - windowLow) ) /* note: we are searching at curr+1 */ - if (MEM_read32(ip+1) == MEM_read32(repMatch)) { - /* repcode detected we should take it */ - const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend; - matchLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repEnd, prefixStart) + 4; - if (depth==0) goto _storeSequence; - } } - - /* first search (depth 0) */ + if (MEM_read32(ip+1) == MEM_read32(repMatch)) { + /* repcode detected we should take it */ + const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend; + matchLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repEnd, prefixStart) + 4; + if (depth==0) goto _storeSequence; + } } + + /* first search (depth 0) */ { size_t offsetFound = 999999999; size_t const ml2 = searchMax(ms, ip, iend, &offsetFound); - if (ml2 > matchLength) + if (ml2 > matchLength) matchLength = ml2, start = ip, offcode=offsetFound; - } - + } + if (matchLength < 4) { - ip += ((ip-anchor) >> kSearchStrength) + 1; /* jump faster over incompressible sections */ - continue; - } - - /* let's try to find a better solution */ - if (depth>=1) - while (ip<ilimit) { - ip ++; + ip += ((ip-anchor) >> kSearchStrength) + 1; /* jump faster over incompressible sections */ + continue; + } + + /* let's try to find a better solution */ + if (depth>=1) + while (ip<ilimit) { + ip ++; curr++; - /* check repCode */ + /* check repCode */ if (offcode) { const U32 windowLow = ZSTD_getLowestMatchIndex(ms, curr, windowLog); const U32 repIndex = (U32)(curr - offset_1); - const BYTE* const repBase = repIndex < dictLimit ? dictBase : base; - const BYTE* const repMatch = repBase + repIndex; + const BYTE* const repBase = repIndex < dictLimit ? dictBase : base; + const BYTE* const repMatch = repBase + repIndex; if ( ((U32)((dictLimit-1) - repIndex) >= 3) /* intentional overflow : do not test positions overlapping 2 memory segments */ & (offset_1 <= curr - windowLow) ) /* equivalent to `curr > repIndex >= windowLow` */ - if (MEM_read32(ip) == MEM_read32(repMatch)) { - /* repcode detected */ - const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend; - size_t const repLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4; - int const gain2 = (int)(repLength * 3); + if (MEM_read32(ip) == MEM_read32(repMatch)) { + /* repcode detected */ + const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend; + size_t const repLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4; + int const gain2 = (int)(repLength * 3); int const gain1 = (int)(matchLength*3 - ZSTD_highbit32((U32)STORED_TO_OFFBASE(offcode)) + 1); - if ((repLength >= 4) && (gain2 > gain1)) + if ((repLength >= 4) && (gain2 > gain1)) matchLength = repLength, offcode = STORE_REPCODE_1, start = ip; - } } - - /* search match, depth 1 */ + } } + + /* search match, depth 1 */ { size_t offset2=999999999; size_t const ml2 = searchMax(ms, ip, iend, &offset2); int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)STORED_TO_OFFBASE(offset2))); /* raw approx */ int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)STORED_TO_OFFBASE(offcode)) + 4); - if ((ml2 >= 4) && (gain2 > gain1)) { + if ((ml2 >= 4) && (gain2 > gain1)) { matchLength = ml2, offcode = offset2, start = ip; - continue; /* search a better one */ - } } - - /* let's find an even better one */ - if ((depth==2) && (ip<ilimit)) { - ip ++; + continue; /* search a better one */ + } } + + /* let's find an even better one */ + if ((depth==2) && (ip<ilimit)) { + ip ++; curr++; - /* check repCode */ + /* check repCode */ if (offcode) { const U32 windowLow = ZSTD_getLowestMatchIndex(ms, curr, windowLog); const U32 repIndex = (U32)(curr - offset_1); - const BYTE* const repBase = repIndex < dictLimit ? dictBase : base; - const BYTE* const repMatch = repBase + repIndex; + const BYTE* const repBase = repIndex < dictLimit ? dictBase : base; + const BYTE* const repMatch = repBase + repIndex; if ( ((U32)((dictLimit-1) - repIndex) >= 3) /* intentional overflow : do not test positions overlapping 2 memory segments */ & (offset_1 <= curr - windowLow) ) /* equivalent to `curr > repIndex >= windowLow` */ - if (MEM_read32(ip) == MEM_read32(repMatch)) { - /* repcode detected */ - const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend; - size_t const repLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4; - int const gain2 = (int)(repLength * 4); + if (MEM_read32(ip) == MEM_read32(repMatch)) { + /* repcode detected */ + const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend; + size_t const repLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4; + int const gain2 = (int)(repLength * 4); int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)STORED_TO_OFFBASE(offcode)) + 1); - if ((repLength >= 4) && (gain2 > gain1)) + if ((repLength >= 4) && (gain2 > gain1)) matchLength = repLength, offcode = STORE_REPCODE_1, start = ip; - } } - - /* search match, depth 2 */ + } } + + /* search match, depth 2 */ { size_t offset2=999999999; size_t const ml2 = searchMax(ms, ip, iend, &offset2); int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)STORED_TO_OFFBASE(offset2))); /* raw approx */ int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)STORED_TO_OFFBASE(offcode)) + 7); - if ((ml2 >= 4) && (gain2 > gain1)) { + if ((ml2 >= 4) && (gain2 > gain1)) { matchLength = ml2, offcode = offset2, start = ip; - continue; - } } } - break; /* nothing found : store previous solution */ - } - - /* catch up */ + continue; + } } } + break; /* nothing found : store previous solution */ + } + + /* catch up */ if (STORED_IS_OFFSET(offcode)) { U32 const matchIndex = (U32)((size_t)(start-base) - STORED_OFFSET(offcode)); - const BYTE* match = (matchIndex < dictLimit) ? dictBase + matchIndex : base + matchIndex; - const BYTE* const mStart = (matchIndex < dictLimit) ? dictStart : prefixStart; - while ((start>anchor) && (match>mStart) && (start[-1] == match[-1])) { start--; match--; matchLength++; } /* catch up */ + const BYTE* match = (matchIndex < dictLimit) ? dictBase + matchIndex : base + matchIndex; + const BYTE* const mStart = (matchIndex < dictLimit) ? dictStart : prefixStart; + while ((start>anchor) && (match>mStart) && (start[-1] == match[-1])) { start--; match--; matchLength++; } /* catch up */ offset_2 = offset_1; offset_1 = (U32)STORED_OFFSET(offcode); - } - - /* store sequence */ -_storeSequence: + } + + /* store sequence */ +_storeSequence: { size_t const litLength = (size_t)(start - anchor); ZSTD_storeSeq(seqStore, litLength, anchor, iend, (U32)offcode, matchLength); - anchor = ip = start + matchLength; - } - - /* check immediate repcode */ - while (ip <= ilimit) { + anchor = ip = start + matchLength; + } + + /* check immediate repcode */ + while (ip <= ilimit) { const U32 repCurrent = (U32)(ip-base); const U32 windowLow = ZSTD_getLowestMatchIndex(ms, repCurrent, windowLog); const U32 repIndex = repCurrent - offset_2; - const BYTE* const repBase = repIndex < dictLimit ? dictBase : base; - const BYTE* const repMatch = repBase + repIndex; + const BYTE* const repBase = repIndex < dictLimit ? dictBase : base; + const BYTE* const repMatch = repBase + repIndex; if ( ((U32)((dictLimit-1) - repIndex) >= 3) /* intentional overflow : do not test positions overlapping 2 memory segments */ & (offset_2 <= repCurrent - windowLow) ) /* equivalent to `curr > repIndex >= windowLow` */ - if (MEM_read32(ip) == MEM_read32(repMatch)) { - /* repcode detected we should take it */ - const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend; - matchLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4; + if (MEM_read32(ip) == MEM_read32(repMatch)) { + /* repcode detected we should take it */ + const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend; + matchLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4; offcode = offset_2; offset_2 = offset_1; offset_1 = (U32)offcode; /* swap offset history */ ZSTD_storeSeq(seqStore, 0, anchor, iend, STORE_REPCODE_1, matchLength); - ip += matchLength; - anchor = ip; - continue; /* faster when present ... (?) */ - } - break; - } } - - /* Save reps for next block */ - rep[0] = offset_1; - rep[1] = offset_2; - - /* Return the last literals size */ + ip += matchLength; + anchor = ip; + continue; /* faster when present ... (?) */ + } + break; + } } + + /* Save reps for next block */ + rep[0] = offset_1; + rep[1] = offset_2; + + /* Return the last literals size */ return (size_t)(iend - anchor); -} - - -size_t ZSTD_compressBlock_greedy_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +} + + +size_t ZSTD_compressBlock_greedy_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) -{ +{ return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0); -} - -size_t ZSTD_compressBlock_lazy_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +} + +size_t ZSTD_compressBlock_lazy_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) - -{ + +{ return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1); -} - -size_t ZSTD_compressBlock_lazy2_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +} + +size_t ZSTD_compressBlock_lazy2_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) - -{ + +{ return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2); -} - -size_t ZSTD_compressBlock_btlazy2_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +} + +size_t ZSTD_compressBlock_btlazy2_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize) - -{ + +{ return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_binaryTree, 2); -} +} size_t ZSTD_compressBlock_greedy_extDict_row( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], diff --git a/contrib/libs/zstd/lib/compress/zstd_lazy.h b/contrib/libs/zstd/lib/compress/zstd_lazy.h index 150f7b390b..c98a4359f3 100644 --- a/contrib/libs/zstd/lib/compress/zstd_lazy.h +++ b/contrib/libs/zstd/lib/compress/zstd_lazy.h @@ -1,22 +1,22 @@ -/* +/* * Copyright (c) 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_LAZY_H -#define ZSTD_LAZY_H - -#if defined (__cplusplus) -extern "C" { -#endif - -#include "zstd_compress_internal.h" - + * 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_LAZY_H +#define ZSTD_LAZY_H + +#if defined (__cplusplus) +extern "C" { +#endif + +#include "zstd_compress_internal.h" + /** * Dedicated Dictionary Search Structure bucket log. In the * ZSTD_dedicatedDictSearch mode, the hashTable has @@ -27,22 +27,22 @@ extern "C" { U32 ZSTD_insertAndFindFirstIndex(ZSTD_matchState_t* ms, const BYTE* ip); void ZSTD_row_update(ZSTD_matchState_t* const ms, const BYTE* ip); - + void ZSTD_dedicatedDictSearch_lazy_loadDictionary(ZSTD_matchState_t* ms, const BYTE* const ip); void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue); /*! used in ZSTD_reduceIndex(). preemptively increase value of ZSTD_DUBT_UNSORTED_MARK */ - -size_t ZSTD_compressBlock_btlazy2( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + +size_t ZSTD_compressBlock_btlazy2( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); -size_t ZSTD_compressBlock_lazy2( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_lazy2( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); -size_t ZSTD_compressBlock_lazy( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_lazy( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); -size_t ZSTD_compressBlock_greedy( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_greedy( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); size_t ZSTD_compressBlock_lazy2_row( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], @@ -53,7 +53,7 @@ size_t ZSTD_compressBlock_lazy_row( size_t ZSTD_compressBlock_greedy_row( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); - + size_t ZSTD_compressBlock_btlazy2_dictMatchState( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); @@ -95,14 +95,14 @@ size_t ZSTD_compressBlock_greedy_dedicatedDictSearch_row( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); -size_t ZSTD_compressBlock_greedy_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_greedy_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); -size_t ZSTD_compressBlock_lazy_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_lazy_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); -size_t ZSTD_compressBlock_lazy2_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_lazy2_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); size_t ZSTD_compressBlock_greedy_extDict_row( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], @@ -113,13 +113,13 @@ size_t ZSTD_compressBlock_lazy_extDict_row( size_t ZSTD_compressBlock_lazy2_extDict_row( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); -size_t ZSTD_compressBlock_btlazy2_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_btlazy2_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); - -#if defined (__cplusplus) -} -#endif - -#endif /* ZSTD_LAZY_H */ + +#if defined (__cplusplus) +} +#endif + +#endif /* ZSTD_LAZY_H */ diff --git a/contrib/libs/zstd/lib/compress/zstd_ldm.c b/contrib/libs/zstd/lib/compress/zstd_ldm.c index 476b45746e..da14f7896b 100644 --- a/contrib/libs/zstd/lib/compress/zstd_ldm.c +++ b/contrib/libs/zstd/lib/compress/zstd_ldm.c @@ -1,25 +1,25 @@ -/* +/* * Copyright (c) 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). + * 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. - */ - -#include "zstd_ldm.h" - + */ + +#include "zstd_ldm.h" + #include "../common/debug.h" #include <contrib/libs/xxhash/xxhash.h> -#include "zstd_fast.h" /* ZSTD_fillHashTable() */ -#include "zstd_double_fast.h" /* ZSTD_fillDoubleHashTable() */ +#include "zstd_fast.h" /* ZSTD_fillHashTable() */ +#include "zstd_double_fast.h" /* ZSTD_fillDoubleHashTable() */ #include "zstd_ldm_geartab.h" - -#define LDM_BUCKET_SIZE_LOG 3 -#define LDM_MIN_MATCH_LENGTH 64 -#define LDM_HASH_RLOG 7 - + +#define LDM_BUCKET_SIZE_LOG 3 +#define LDM_MIN_MATCH_LENGTH 64 +#define LDM_HASH_RLOG 7 + typedef struct { U64 rolling; U64 stopMask; @@ -132,80 +132,80 @@ done: return n; } -void ZSTD_ldm_adjustParameters(ldmParams_t* params, - ZSTD_compressionParameters const* cParams) -{ +void ZSTD_ldm_adjustParameters(ldmParams_t* params, + ZSTD_compressionParameters const* cParams) +{ params->windowLog = cParams->windowLog; - ZSTD_STATIC_ASSERT(LDM_BUCKET_SIZE_LOG <= ZSTD_LDM_BUCKETSIZELOG_MAX); - DEBUGLOG(4, "ZSTD_ldm_adjustParameters"); - if (!params->bucketSizeLog) params->bucketSizeLog = LDM_BUCKET_SIZE_LOG; - if (!params->minMatchLength) params->minMatchLength = LDM_MIN_MATCH_LENGTH; - if (params->hashLog == 0) { + ZSTD_STATIC_ASSERT(LDM_BUCKET_SIZE_LOG <= ZSTD_LDM_BUCKETSIZELOG_MAX); + DEBUGLOG(4, "ZSTD_ldm_adjustParameters"); + if (!params->bucketSizeLog) params->bucketSizeLog = LDM_BUCKET_SIZE_LOG; + if (!params->minMatchLength) params->minMatchLength = LDM_MIN_MATCH_LENGTH; + if (params->hashLog == 0) { params->hashLog = MAX(ZSTD_HASHLOG_MIN, params->windowLog - LDM_HASH_RLOG); - assert(params->hashLog <= ZSTD_HASHLOG_MAX); - } + assert(params->hashLog <= ZSTD_HASHLOG_MAX); + } if (params->hashRateLog == 0) { params->hashRateLog = params->windowLog < params->hashLog ? 0 : params->windowLog - params->hashLog; - } - params->bucketSizeLog = MIN(params->bucketSizeLog, params->hashLog); -} - -size_t ZSTD_ldm_getTableSize(ldmParams_t params) -{ - size_t const ldmHSize = ((size_t)1) << params.hashLog; - size_t const ldmBucketSizeLog = MIN(params.bucketSizeLog, params.hashLog); + } + params->bucketSizeLog = MIN(params->bucketSizeLog, params->hashLog); +} + +size_t ZSTD_ldm_getTableSize(ldmParams_t params) +{ + size_t const ldmHSize = ((size_t)1) << params.hashLog; + size_t const ldmBucketSizeLog = MIN(params.bucketSizeLog, params.hashLog); size_t const ldmBucketSize = ((size_t)1) << (params.hashLog - ldmBucketSizeLog); size_t const totalSize = ZSTD_cwksp_alloc_size(ldmBucketSize) + ZSTD_cwksp_alloc_size(ldmHSize * sizeof(ldmEntry_t)); return params.enableLdm == ZSTD_ps_enable ? totalSize : 0; -} - -size_t ZSTD_ldm_getMaxNbSeq(ldmParams_t params, size_t maxChunkSize) -{ +} + +size_t ZSTD_ldm_getMaxNbSeq(ldmParams_t params, size_t maxChunkSize) +{ return params.enableLdm == ZSTD_ps_enable ? (maxChunkSize / params.minMatchLength) : 0; -} - -/** ZSTD_ldm_getBucket() : - * Returns a pointer to the start of the bucket associated with hash. */ -static ldmEntry_t* ZSTD_ldm_getBucket( - ldmState_t* ldmState, size_t hash, ldmParams_t const ldmParams) -{ - return ldmState->hashTable + (hash << ldmParams.bucketSizeLog); -} - -/** ZSTD_ldm_insertEntry() : - * Insert the entry with corresponding hash into the hash table */ -static void ZSTD_ldm_insertEntry(ldmState_t* ldmState, - size_t const hash, const ldmEntry_t entry, - ldmParams_t const ldmParams) -{ +} + +/** ZSTD_ldm_getBucket() : + * Returns a pointer to the start of the bucket associated with hash. */ +static ldmEntry_t* ZSTD_ldm_getBucket( + ldmState_t* ldmState, size_t hash, ldmParams_t const ldmParams) +{ + return ldmState->hashTable + (hash << ldmParams.bucketSizeLog); +} + +/** ZSTD_ldm_insertEntry() : + * Insert the entry with corresponding hash into the hash table */ +static void ZSTD_ldm_insertEntry(ldmState_t* ldmState, + size_t const hash, const ldmEntry_t entry, + ldmParams_t const ldmParams) +{ BYTE* const pOffset = ldmState->bucketOffsets + hash; unsigned const offset = *pOffset; - + *(ZSTD_ldm_getBucket(ldmState, hash, ldmParams) + offset) = entry; *pOffset = (BYTE)((offset + 1) & ((1u << ldmParams.bucketSizeLog) - 1)); -} - -/** ZSTD_ldm_countBackwardsMatch() : - * Returns the number of bytes that match backwards before pIn and pMatch. - * - * We count only bytes where pMatch >= pBase and pIn >= pAnchor. */ -static size_t ZSTD_ldm_countBackwardsMatch( - const BYTE* pIn, const BYTE* pAnchor, +} + +/** ZSTD_ldm_countBackwardsMatch() : + * Returns the number of bytes that match backwards before pIn and pMatch. + * + * We count only bytes where pMatch >= pBase and pIn >= pAnchor. */ +static size_t ZSTD_ldm_countBackwardsMatch( + const BYTE* pIn, const BYTE* pAnchor, const BYTE* pMatch, const BYTE* pMatchBase) -{ - size_t matchLength = 0; +{ + size_t matchLength = 0; while (pIn > pAnchor && pMatch > pMatchBase && pIn[-1] == pMatch[-1]) { - pIn--; - pMatch--; - matchLength++; - } - return matchLength; -} - + pIn--; + pMatch--; + matchLength++; + } + return matchLength; +} + /** ZSTD_ldm_countBackwardsMatch_2segments() : * Returns the number of bytes that match backwards from pMatch, * even with the backwards match spanning 2 different segments. @@ -227,43 +227,43 @@ static size_t ZSTD_ldm_countBackwardsMatch_2segments( return matchLength; } -/** ZSTD_ldm_fillFastTables() : - * - * Fills the relevant tables for the ZSTD_fast and ZSTD_dfast strategies. - * This is similar to ZSTD_loadDictionaryContent. - * - * The tables for the other strategies are filled within their - * block compressors. */ -static size_t ZSTD_ldm_fillFastTables(ZSTD_matchState_t* ms, - void const* end) -{ - const BYTE* const iend = (const BYTE*)end; - +/** ZSTD_ldm_fillFastTables() : + * + * Fills the relevant tables for the ZSTD_fast and ZSTD_dfast strategies. + * This is similar to ZSTD_loadDictionaryContent. + * + * The tables for the other strategies are filled within their + * block compressors. */ +static size_t ZSTD_ldm_fillFastTables(ZSTD_matchState_t* ms, + void const* end) +{ + const BYTE* const iend = (const BYTE*)end; + switch(ms->cParams.strategy) - { - case ZSTD_fast: + { + case ZSTD_fast: ZSTD_fillHashTable(ms, iend, ZSTD_dtlm_fast); - break; - - case ZSTD_dfast: + break; + + case ZSTD_dfast: ZSTD_fillDoubleHashTable(ms, iend, ZSTD_dtlm_fast); - break; - - case ZSTD_greedy: - case ZSTD_lazy: - case ZSTD_lazy2: - case ZSTD_btlazy2: - case ZSTD_btopt: - case ZSTD_btultra: + break; + + case ZSTD_greedy: + case ZSTD_lazy: + case ZSTD_lazy2: + case ZSTD_btlazy2: + case ZSTD_btopt: + case ZSTD_btultra: case ZSTD_btultra2: - break; - default: - assert(0); /* not possible : not a valid strategy id */ - } - - return 0; -} - + break; + default: + assert(0); /* not possible : not a valid strategy id */ + } + + return 0; +} + void ZSTD_ldm_fillHashTable( ldmState_t* ldmState, const BYTE* ip, const BYTE* iend, ldmParams_t const* params) @@ -302,53 +302,53 @@ void ZSTD_ldm_fillHashTable( ip += hashed; } } - - -/** ZSTD_ldm_limitTableUpdate() : - * - * Sets cctx->nextToUpdate to a position corresponding closer to anchor - * if it is far way - * (after a long match, only update tables a limited amount). */ -static void ZSTD_ldm_limitTableUpdate(ZSTD_matchState_t* ms, const BYTE* anchor) -{ + + +/** ZSTD_ldm_limitTableUpdate() : + * + * Sets cctx->nextToUpdate to a position corresponding closer to anchor + * if it is far way + * (after a long match, only update tables a limited amount). */ +static void ZSTD_ldm_limitTableUpdate(ZSTD_matchState_t* ms, const BYTE* anchor) +{ U32 const curr = (U32)(anchor - ms->window.base); if (curr > ms->nextToUpdate + 1024) { - ms->nextToUpdate = + ms->nextToUpdate = curr - MIN(512, curr - ms->nextToUpdate - 1024); - } -} - -static size_t ZSTD_ldm_generateSequences_internal( - ldmState_t* ldmState, rawSeqStore_t* rawSeqStore, - ldmParams_t const* params, void const* src, size_t srcSize) -{ - /* LDM parameters */ - int const extDict = ZSTD_window_hasExtDict(ldmState->window); - U32 const minMatchLength = params->minMatchLength; + } +} + +static size_t ZSTD_ldm_generateSequences_internal( + ldmState_t* ldmState, rawSeqStore_t* rawSeqStore, + ldmParams_t const* params, void const* src, size_t srcSize) +{ + /* LDM parameters */ + int const extDict = ZSTD_window_hasExtDict(ldmState->window); + U32 const minMatchLength = params->minMatchLength; U32 const entsPerBucket = 1U << params->bucketSizeLog; - U32 const hBits = params->hashLog - params->bucketSizeLog; - /* Prefix and extDict parameters */ - U32 const dictLimit = ldmState->window.dictLimit; - U32 const lowestIndex = extDict ? ldmState->window.lowLimit : dictLimit; - BYTE const* const base = ldmState->window.base; - BYTE const* const dictBase = extDict ? ldmState->window.dictBase : NULL; - BYTE const* const dictStart = extDict ? dictBase + lowestIndex : NULL; - BYTE const* const dictEnd = extDict ? dictBase + dictLimit : NULL; - BYTE const* const lowPrefixPtr = base + dictLimit; - /* Input bounds */ - BYTE const* const istart = (BYTE const*)src; - BYTE const* const iend = istart + srcSize; + U32 const hBits = params->hashLog - params->bucketSizeLog; + /* Prefix and extDict parameters */ + U32 const dictLimit = ldmState->window.dictLimit; + U32 const lowestIndex = extDict ? ldmState->window.lowLimit : dictLimit; + BYTE const* const base = ldmState->window.base; + BYTE const* const dictBase = extDict ? ldmState->window.dictBase : NULL; + BYTE const* const dictStart = extDict ? dictBase + lowestIndex : NULL; + BYTE const* const dictEnd = extDict ? dictBase + dictLimit : NULL; + BYTE const* const lowPrefixPtr = base + dictLimit; + /* Input bounds */ + BYTE const* const istart = (BYTE const*)src; + BYTE const* const iend = istart + srcSize; BYTE const* const ilimit = iend - HASH_READ_SIZE; - /* Input positions */ - BYTE const* anchor = istart; - BYTE const* ip = istart; + /* Input positions */ + BYTE const* anchor = istart; + BYTE const* ip = istart; /* Rolling hash state */ ldmRollingHashState_t hashState; /* Arrays for staged-processing */ size_t* const splits = ldmState->splitIndices; ldmMatchCandidate_t* const candidates = ldmState->matchCandidates; unsigned numSplits; - + if (srcSize < minMatchLength) return iend - anchor; @@ -375,8 +375,8 @@ static size_t ZSTD_ldm_generateSequences_internal( candidates[n].checksum = (U32)(xxhash >> 32); candidates[n].bucket = ZSTD_ldm_getBucket(ldmState, hash, *params); PREFETCH_L1(candidates[n].bucket); - } - + } + for (n = 0; n < numSplits; n++) { size_t forwardMatchLength = 0, backwardMatchLength = 0, bestMatchLength = 0, mLength; @@ -388,7 +388,7 @@ static size_t ZSTD_ldm_generateSequences_internal( ldmEntry_t const* cur; ldmEntry_t const* bestEntry = NULL; ldmEntry_t newEntry; - + newEntry.offset = (U32)(split - base); newEntry.checksum = checksum; @@ -401,58 +401,58 @@ static size_t ZSTD_ldm_generateSequences_internal( } for (cur = bucket; cur < bucket + entsPerBucket; cur++) { - size_t curForwardMatchLength, curBackwardMatchLength, - curTotalMatchLength; - if (cur->checksum != checksum || cur->offset <= lowestIndex) { - continue; - } - if (extDict) { - BYTE const* const curMatchBase = - cur->offset < dictLimit ? dictBase : base; - BYTE const* const pMatch = curMatchBase + cur->offset; - BYTE const* const matchEnd = - cur->offset < dictLimit ? dictEnd : iend; - BYTE const* const lowMatchPtr = - cur->offset < dictLimit ? dictStart : lowPrefixPtr; + size_t curForwardMatchLength, curBackwardMatchLength, + curTotalMatchLength; + if (cur->checksum != checksum || cur->offset <= lowestIndex) { + continue; + } + if (extDict) { + BYTE const* const curMatchBase = + cur->offset < dictLimit ? dictBase : base; + BYTE const* const pMatch = curMatchBase + cur->offset; + BYTE const* const matchEnd = + cur->offset < dictLimit ? dictEnd : iend; + BYTE const* const lowMatchPtr = + cur->offset < dictLimit ? dictStart : lowPrefixPtr; curForwardMatchLength = ZSTD_count_2segments(split, pMatch, iend, matchEnd, lowPrefixPtr); - if (curForwardMatchLength < minMatchLength) { - continue; - } + if (curForwardMatchLength < minMatchLength) { + continue; + } curBackwardMatchLength = ZSTD_ldm_countBackwardsMatch_2segments( split, anchor, pMatch, lowMatchPtr, dictStart, dictEnd); - } else { /* !extDict */ - BYTE const* const pMatch = base + cur->offset; + } else { /* !extDict */ + BYTE const* const pMatch = base + cur->offset; curForwardMatchLength = ZSTD_count(split, pMatch, iend); - if (curForwardMatchLength < minMatchLength) { - continue; - } - curBackwardMatchLength = + if (curForwardMatchLength < minMatchLength) { + continue; + } + curBackwardMatchLength = ZSTD_ldm_countBackwardsMatch(split, anchor, pMatch, lowPrefixPtr); - } + } curTotalMatchLength = curForwardMatchLength + curBackwardMatchLength; - - if (curTotalMatchLength > bestMatchLength) { - bestMatchLength = curTotalMatchLength; - forwardMatchLength = curForwardMatchLength; - backwardMatchLength = curBackwardMatchLength; - bestEntry = cur; - } - } - + + if (curTotalMatchLength > bestMatchLength) { + bestMatchLength = curTotalMatchLength; + forwardMatchLength = curForwardMatchLength; + backwardMatchLength = curBackwardMatchLength; + bestEntry = cur; + } + } + /* No match found -- insert an entry into the hash table * and process the next candidate match */ if (bestEntry == NULL) { ZSTD_ldm_insertEntry(ldmState, hash, newEntry, *params); continue; } - + /* Match found */ offset = (U32)(split - base) - bestEntry->offset; mLength = forwardMatchLength + backwardMatchLength; { rawSeq* const seq = rawSeqStore->seq + rawSeqStore->size; - + /* Out of sequence storage */ if (rawSeqStore->size == rawSeqStore->capacity) return ERROR(dstSize_tooSmall); @@ -461,7 +461,7 @@ static size_t ZSTD_ldm_generateSequences_internal( seq->offset = offset; rawSeqStore->size++; } - + /* Insert the current entry into the hash table --- it must be * done after the previous block to avoid clobbering bestEntry */ ZSTD_ldm_insertEntry(ldmState, hash, newEntry, *params); @@ -482,164 +482,164 @@ static size_t ZSTD_ldm_generateSequences_internal( ip = anchor - hashed; break; } - } - + } + ip += hashed; } - - return iend - anchor; -} - -/*! ZSTD_ldm_reduceTable() : - * reduce table indexes by `reducerValue` */ -static void ZSTD_ldm_reduceTable(ldmEntry_t* const table, U32 const size, - U32 const reducerValue) -{ - U32 u; - for (u = 0; u < size; u++) { - if (table[u].offset < reducerValue) table[u].offset = 0; - else table[u].offset -= reducerValue; - } -} - -size_t ZSTD_ldm_generateSequences( - ldmState_t* ldmState, rawSeqStore_t* sequences, - ldmParams_t const* params, void const* src, size_t srcSize) -{ - U32 const maxDist = 1U << params->windowLog; - BYTE const* const istart = (BYTE const*)src; - BYTE const* const iend = istart + srcSize; - size_t const kMaxChunkSize = 1 << 20; - size_t const nbChunks = (srcSize / kMaxChunkSize) + ((srcSize % kMaxChunkSize) != 0); - size_t chunk; - size_t leftoverSize = 0; - - assert(ZSTD_CHUNKSIZE_MAX >= kMaxChunkSize); - /* Check that ZSTD_window_update() has been called for this chunk prior - * to passing it to this function. - */ - assert(ldmState->window.nextSrc >= (BYTE const*)src + srcSize); - /* The input could be very large (in zstdmt), so it must be broken up into + + return iend - anchor; +} + +/*! ZSTD_ldm_reduceTable() : + * reduce table indexes by `reducerValue` */ +static void ZSTD_ldm_reduceTable(ldmEntry_t* const table, U32 const size, + U32 const reducerValue) +{ + U32 u; + for (u = 0; u < size; u++) { + if (table[u].offset < reducerValue) table[u].offset = 0; + else table[u].offset -= reducerValue; + } +} + +size_t ZSTD_ldm_generateSequences( + ldmState_t* ldmState, rawSeqStore_t* sequences, + ldmParams_t const* params, void const* src, size_t srcSize) +{ + U32 const maxDist = 1U << params->windowLog; + BYTE const* const istart = (BYTE const*)src; + BYTE const* const iend = istart + srcSize; + size_t const kMaxChunkSize = 1 << 20; + size_t const nbChunks = (srcSize / kMaxChunkSize) + ((srcSize % kMaxChunkSize) != 0); + size_t chunk; + size_t leftoverSize = 0; + + assert(ZSTD_CHUNKSIZE_MAX >= kMaxChunkSize); + /* Check that ZSTD_window_update() has been called for this chunk prior + * to passing it to this function. + */ + assert(ldmState->window.nextSrc >= (BYTE const*)src + srcSize); + /* The input could be very large (in zstdmt), so it must be broken up into * chunks to enforce the maximum distance and handle overflow correction. - */ - assert(sequences->pos <= sequences->size); - assert(sequences->size <= sequences->capacity); - for (chunk = 0; chunk < nbChunks && sequences->size < sequences->capacity; ++chunk) { - BYTE const* const chunkStart = istart + chunk * kMaxChunkSize; - size_t const remaining = (size_t)(iend - chunkStart); - BYTE const *const chunkEnd = - (remaining < kMaxChunkSize) ? iend : chunkStart + kMaxChunkSize; - size_t const chunkSize = chunkEnd - chunkStart; - size_t newLeftoverSize; - size_t const prevSize = sequences->size; - - assert(chunkStart < iend); - /* 1. Perform overflow correction if necessary. */ + */ + assert(sequences->pos <= sequences->size); + assert(sequences->size <= sequences->capacity); + for (chunk = 0; chunk < nbChunks && sequences->size < sequences->capacity; ++chunk) { + BYTE const* const chunkStart = istart + chunk * kMaxChunkSize; + size_t const remaining = (size_t)(iend - chunkStart); + BYTE const *const chunkEnd = + (remaining < kMaxChunkSize) ? iend : chunkStart + kMaxChunkSize; + size_t const chunkSize = chunkEnd - chunkStart; + size_t newLeftoverSize; + size_t const prevSize = sequences->size; + + assert(chunkStart < iend); + /* 1. Perform overflow correction if necessary. */ if (ZSTD_window_needOverflowCorrection(ldmState->window, 0, maxDist, ldmState->loadedDictEnd, chunkStart, chunkEnd)) { - U32 const ldmHSize = 1U << params->hashLog; - U32 const correction = ZSTD_window_correctOverflow( + U32 const ldmHSize = 1U << params->hashLog; + U32 const correction = ZSTD_window_correctOverflow( &ldmState->window, /* cycleLog */ 0, maxDist, chunkStart); - ZSTD_ldm_reduceTable(ldmState->hashTable, ldmHSize, correction); + ZSTD_ldm_reduceTable(ldmState->hashTable, ldmHSize, correction); /* invalidate dictionaries on overflow correction */ ldmState->loadedDictEnd = 0; - } - /* 2. We enforce the maximum offset allowed. - * - * kMaxChunkSize should be small enough that we don't lose too much of - * the window through early invalidation. - * TODO: * Test the chunk size. - * * Try invalidation after the sequence generation and test the - * the offset against maxDist directly. + } + /* 2. We enforce the maximum offset allowed. + * + * kMaxChunkSize should be small enough that we don't lose too much of + * the window through early invalidation. + * TODO: * Test the chunk size. + * * Try invalidation after the sequence generation and test the + * the offset against maxDist directly. * * NOTE: Because of dictionaries + sequence splitting we MUST make sure * that any offset used is valid at the END of the sequence, since it may * be split into two sequences. This condition holds when using * ZSTD_window_enforceMaxDist(), but if we move to checking offsets * against maxDist directly, we'll have to carefully handle that case. - */ + */ ZSTD_window_enforceMaxDist(&ldmState->window, chunkEnd, maxDist, &ldmState->loadedDictEnd, NULL); - /* 3. Generate the sequences for the chunk, and get newLeftoverSize. */ - newLeftoverSize = ZSTD_ldm_generateSequences_internal( - ldmState, sequences, params, chunkStart, chunkSize); - if (ZSTD_isError(newLeftoverSize)) - return newLeftoverSize; - /* 4. We add the leftover literals from previous iterations to the first - * newly generated sequence, or add the `newLeftoverSize` if none are - * generated. - */ - /* Prepend the leftover literals from the last call */ - if (prevSize < sequences->size) { - sequences->seq[prevSize].litLength += (U32)leftoverSize; - leftoverSize = newLeftoverSize; - } else { - assert(newLeftoverSize == chunkSize); - leftoverSize += chunkSize; - } - } - return 0; -} - + /* 3. Generate the sequences for the chunk, and get newLeftoverSize. */ + newLeftoverSize = ZSTD_ldm_generateSequences_internal( + ldmState, sequences, params, chunkStart, chunkSize); + if (ZSTD_isError(newLeftoverSize)) + return newLeftoverSize; + /* 4. We add the leftover literals from previous iterations to the first + * newly generated sequence, or add the `newLeftoverSize` if none are + * generated. + */ + /* Prepend the leftover literals from the last call */ + if (prevSize < sequences->size) { + sequences->seq[prevSize].litLength += (U32)leftoverSize; + leftoverSize = newLeftoverSize; + } else { + assert(newLeftoverSize == chunkSize); + leftoverSize += chunkSize; + } + } + return 0; +} + void ZSTD_ldm_skipSequences(rawSeqStore_t* rawSeqStore, size_t srcSize, U32 const minMatch) { - while (srcSize > 0 && rawSeqStore->pos < rawSeqStore->size) { - rawSeq* seq = rawSeqStore->seq + rawSeqStore->pos; - if (srcSize <= seq->litLength) { - /* Skip past srcSize literals */ - seq->litLength -= (U32)srcSize; - return; - } - srcSize -= seq->litLength; - seq->litLength = 0; - if (srcSize < seq->matchLength) { - /* Skip past the first srcSize of the match */ - seq->matchLength -= (U32)srcSize; - if (seq->matchLength < minMatch) { - /* The match is too short, omit it */ - if (rawSeqStore->pos + 1 < rawSeqStore->size) { - seq[1].litLength += seq[0].matchLength; - } - rawSeqStore->pos++; - } - return; - } - srcSize -= seq->matchLength; - seq->matchLength = 0; - rawSeqStore->pos++; - } -} - -/** - * If the sequence length is longer than remaining then the sequence is split - * between this block and the next. - * - * Returns the current sequence to handle, or if the rest of the block should - * be literals, it returns a sequence with offset == 0. - */ -static rawSeq maybeSplitSequence(rawSeqStore_t* rawSeqStore, - U32 const remaining, U32 const minMatch) -{ - rawSeq sequence = rawSeqStore->seq[rawSeqStore->pos]; - assert(sequence.offset > 0); - /* Likely: No partial sequence */ - if (remaining >= sequence.litLength + sequence.matchLength) { - rawSeqStore->pos++; - return sequence; - } - /* Cut the sequence short (offset == 0 ==> rest is literals). */ - if (remaining <= sequence.litLength) { - sequence.offset = 0; - } else if (remaining < sequence.litLength + sequence.matchLength) { - sequence.matchLength = remaining - sequence.litLength; - if (sequence.matchLength < minMatch) { - sequence.offset = 0; - } - } - /* Skip past `remaining` bytes for the future sequences. */ - ZSTD_ldm_skipSequences(rawSeqStore, remaining, minMatch); - return sequence; -} - + while (srcSize > 0 && rawSeqStore->pos < rawSeqStore->size) { + rawSeq* seq = rawSeqStore->seq + rawSeqStore->pos; + if (srcSize <= seq->litLength) { + /* Skip past srcSize literals */ + seq->litLength -= (U32)srcSize; + return; + } + srcSize -= seq->litLength; + seq->litLength = 0; + if (srcSize < seq->matchLength) { + /* Skip past the first srcSize of the match */ + seq->matchLength -= (U32)srcSize; + if (seq->matchLength < minMatch) { + /* The match is too short, omit it */ + if (rawSeqStore->pos + 1 < rawSeqStore->size) { + seq[1].litLength += seq[0].matchLength; + } + rawSeqStore->pos++; + } + return; + } + srcSize -= seq->matchLength; + seq->matchLength = 0; + rawSeqStore->pos++; + } +} + +/** + * If the sequence length is longer than remaining then the sequence is split + * between this block and the next. + * + * Returns the current sequence to handle, or if the rest of the block should + * be literals, it returns a sequence with offset == 0. + */ +static rawSeq maybeSplitSequence(rawSeqStore_t* rawSeqStore, + U32 const remaining, U32 const minMatch) +{ + rawSeq sequence = rawSeqStore->seq[rawSeqStore->pos]; + assert(sequence.offset > 0); + /* Likely: No partial sequence */ + if (remaining >= sequence.litLength + sequence.matchLength) { + rawSeqStore->pos++; + return sequence; + } + /* Cut the sequence short (offset == 0 ==> rest is literals). */ + if (remaining <= sequence.litLength) { + sequence.offset = 0; + } else if (remaining < sequence.litLength + sequence.matchLength) { + sequence.matchLength = remaining - sequence.litLength; + if (sequence.matchLength < minMatch) { + sequence.offset = 0; + } + } + /* Skip past `remaining` bytes for the future sequences. */ + ZSTD_ldm_skipSequences(rawSeqStore, remaining, minMatch); + return sequence; +} + void ZSTD_ldm_skipRawSeqStoreBytes(rawSeqStore_t* rawSeqStore, size_t nbBytes) { U32 currPos = (U32)(rawSeqStore->posInSequence + nbBytes); while (currPos && rawSeqStore->pos < rawSeqStore->size) { @@ -657,21 +657,21 @@ void ZSTD_ldm_skipRawSeqStoreBytes(rawSeqStore_t* rawSeqStore, size_t nbBytes) { } } -size_t ZSTD_ldm_blockCompress(rawSeqStore_t* rawSeqStore, - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_ldm_blockCompress(rawSeqStore_t* rawSeqStore, + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], ZSTD_paramSwitch_e useRowMatchFinder, void const* src, size_t srcSize) -{ +{ const ZSTD_compressionParameters* const cParams = &ms->cParams; unsigned const minMatch = cParams->minMatch; - ZSTD_blockCompressor const blockCompressor = + ZSTD_blockCompressor const blockCompressor = ZSTD_selectBlockCompressor(cParams->strategy, useRowMatchFinder, ZSTD_matchState_dictMode(ms)); - /* Input bounds */ - BYTE const* const istart = (BYTE const*)src; - BYTE const* const iend = istart + srcSize; - /* Input positions */ - BYTE const* ip = istart; - + /* Input bounds */ + BYTE const* const istart = (BYTE const*)src; + BYTE const* const iend = istart + srcSize; + /* Input positions */ + BYTE const* ip = istart; + DEBUGLOG(5, "ZSTD_ldm_blockCompress: srcSize=%zu", srcSize); /* If using opt parser, use LDMs only as candidates rather than always accepting them */ if (cParams->strategy >= ZSTD_btopt) { @@ -682,43 +682,43 @@ size_t ZSTD_ldm_blockCompress(rawSeqStore_t* rawSeqStore, return lastLLSize; } - assert(rawSeqStore->pos <= rawSeqStore->size); - assert(rawSeqStore->size <= rawSeqStore->capacity); + assert(rawSeqStore->pos <= rawSeqStore->size); + assert(rawSeqStore->size <= rawSeqStore->capacity); /* Loop through each sequence and apply the block compressor to the literals */ - while (rawSeqStore->pos < rawSeqStore->size && ip < iend) { - /* maybeSplitSequence updates rawSeqStore->pos */ - rawSeq const sequence = maybeSplitSequence(rawSeqStore, - (U32)(iend - ip), minMatch); - int i; - /* End signal */ - if (sequence.offset == 0) - break; - - assert(ip + sequence.litLength + sequence.matchLength <= iend); - - /* Fill tables for block compressor */ - ZSTD_ldm_limitTableUpdate(ms, ip); + while (rawSeqStore->pos < rawSeqStore->size && ip < iend) { + /* maybeSplitSequence updates rawSeqStore->pos */ + rawSeq const sequence = maybeSplitSequence(rawSeqStore, + (U32)(iend - ip), minMatch); + int i; + /* End signal */ + if (sequence.offset == 0) + break; + + assert(ip + sequence.litLength + sequence.matchLength <= iend); + + /* Fill tables for block compressor */ + ZSTD_ldm_limitTableUpdate(ms, ip); ZSTD_ldm_fillFastTables(ms, ip); - /* Run the block compressor */ + /* Run the block compressor */ DEBUGLOG(5, "pos %u : calling block compressor on segment of size %u", (unsigned)(ip-istart), sequence.litLength); - { - size_t const newLitLength = + { + size_t const newLitLength = blockCompressor(ms, seqStore, rep, ip, sequence.litLength); - ip += sequence.litLength; - /* Update the repcodes */ - for (i = ZSTD_REP_NUM - 1; i > 0; i--) - rep[i] = rep[i-1]; - rep[0] = sequence.offset; - /* Store the sequence */ + ip += sequence.litLength; + /* Update the repcodes */ + for (i = ZSTD_REP_NUM - 1; i > 0; i--) + rep[i] = rep[i-1]; + rep[0] = sequence.offset; + /* Store the sequence */ ZSTD_storeSeq(seqStore, newLitLength, ip - newLitLength, iend, STORE_OFFSET(sequence.offset), sequence.matchLength); - ip += sequence.matchLength; - } - } - /* Fill the tables for the block compressor */ - ZSTD_ldm_limitTableUpdate(ms, ip); + ip += sequence.matchLength; + } + } + /* Fill the tables for the block compressor */ + ZSTD_ldm_limitTableUpdate(ms, ip); ZSTD_ldm_fillFastTables(ms, ip); - /* Compress the last literals */ + /* Compress the last literals */ return blockCompressor(ms, seqStore, rep, ip, iend - ip); -} +} diff --git a/contrib/libs/zstd/lib/compress/zstd_ldm.h b/contrib/libs/zstd/lib/compress/zstd_ldm.h index 4e68dbf52e..9432096183 100644 --- a/contrib/libs/zstd/lib/compress/zstd_ldm.h +++ b/contrib/libs/zstd/lib/compress/zstd_ldm.h @@ -1,117 +1,117 @@ -/* +/* * Copyright (c) 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). + * 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_LDM_H -#define ZSTD_LDM_H - -#if defined (__cplusplus) -extern "C" { -#endif - -#include "zstd_compress_internal.h" /* ldmParams_t, U32 */ + */ + +#ifndef ZSTD_LDM_H +#define ZSTD_LDM_H + +#if defined (__cplusplus) +extern "C" { +#endif + +#include "zstd_compress_internal.h" /* ldmParams_t, U32 */ #include "../zstd.h" /* ZSTD_CCtx, size_t */ - -/*-************************************* -* Long distance matching -***************************************/ - + +/*-************************************* +* Long distance matching +***************************************/ + #define ZSTD_LDM_DEFAULT_WINDOW_LOG ZSTD_WINDOWLOG_LIMIT_DEFAULT - + void ZSTD_ldm_fillHashTable( ldmState_t* state, const BYTE* ip, const BYTE* iend, ldmParams_t const* params); -/** - * ZSTD_ldm_generateSequences(): - * - * Generates the sequences using the long distance match finder. - * Generates long range matching sequences in `sequences`, which parse a prefix - * of the source. `sequences` must be large enough to store every sequence, - * which can be checked with `ZSTD_ldm_getMaxNbSeq()`. - * @returns 0 or an error code. - * - * NOTE: The user must have called ZSTD_window_update() for all of the input - * they have, even if they pass it to ZSTD_ldm_generateSequences() in chunks. - * NOTE: This function returns an error if it runs out of space to store - * sequences. - */ -size_t ZSTD_ldm_generateSequences( - ldmState_t* ldms, rawSeqStore_t* sequences, - ldmParams_t const* params, void const* src, size_t srcSize); - -/** - * ZSTD_ldm_blockCompress(): - * - * Compresses a block using the predefined sequences, along with a secondary - * block compressor. The literals section of every sequence is passed to the - * secondary block compressor, and those sequences are interspersed with the - * predefined sequences. Returns the length of the last literals. - * Updates `rawSeqStore.pos` to indicate how many sequences have been consumed. - * `rawSeqStore.seq` may also be updated to split the last sequence between two - * blocks. - * @return The length of the last literals. - * - * NOTE: The source must be at most the maximum block size, but the predefined - * sequences can be any size, and may be longer than the block. In the case that - * they are longer than the block, the last sequences may need to be split into - * two. We handle that case correctly, and update `rawSeqStore` appropriately. - * NOTE: This function does not return any errors. - */ -size_t ZSTD_ldm_blockCompress(rawSeqStore_t* rawSeqStore, - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +/** + * ZSTD_ldm_generateSequences(): + * + * Generates the sequences using the long distance match finder. + * Generates long range matching sequences in `sequences`, which parse a prefix + * of the source. `sequences` must be large enough to store every sequence, + * which can be checked with `ZSTD_ldm_getMaxNbSeq()`. + * @returns 0 or an error code. + * + * NOTE: The user must have called ZSTD_window_update() for all of the input + * they have, even if they pass it to ZSTD_ldm_generateSequences() in chunks. + * NOTE: This function returns an error if it runs out of space to store + * sequences. + */ +size_t ZSTD_ldm_generateSequences( + ldmState_t* ldms, rawSeqStore_t* sequences, + ldmParams_t const* params, void const* src, size_t srcSize); + +/** + * ZSTD_ldm_blockCompress(): + * + * Compresses a block using the predefined sequences, along with a secondary + * block compressor. The literals section of every sequence is passed to the + * secondary block compressor, and those sequences are interspersed with the + * predefined sequences. Returns the length of the last literals. + * Updates `rawSeqStore.pos` to indicate how many sequences have been consumed. + * `rawSeqStore.seq` may also be updated to split the last sequence between two + * blocks. + * @return The length of the last literals. + * + * NOTE: The source must be at most the maximum block size, but the predefined + * sequences can be any size, and may be longer than the block. In the case that + * they are longer than the block, the last sequences may need to be split into + * two. We handle that case correctly, and update `rawSeqStore` appropriately. + * NOTE: This function does not return any errors. + */ +size_t ZSTD_ldm_blockCompress(rawSeqStore_t* rawSeqStore, + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], ZSTD_paramSwitch_e useRowMatchFinder, void const* src, size_t srcSize); - -/** - * ZSTD_ldm_skipSequences(): - * - * Skip past `srcSize` bytes worth of sequences in `rawSeqStore`. - * Avoids emitting matches less than `minMatch` bytes. + +/** + * ZSTD_ldm_skipSequences(): + * + * Skip past `srcSize` bytes worth of sequences in `rawSeqStore`. + * Avoids emitting matches less than `minMatch` bytes. * Must be called for data that is not passed to ZSTD_ldm_blockCompress(). - */ -void ZSTD_ldm_skipSequences(rawSeqStore_t* rawSeqStore, size_t srcSize, - U32 const minMatch); - + */ +void ZSTD_ldm_skipSequences(rawSeqStore_t* rawSeqStore, size_t srcSize, + U32 const minMatch); + /* ZSTD_ldm_skipRawSeqStoreBytes(): * Moves forward in rawSeqStore by nbBytes, updating fields 'pos' and 'posInSequence'. * Not to be used in conjunction with ZSTD_ldm_skipSequences(). * Must be called for data with is not passed to ZSTD_ldm_blockCompress(). */ void ZSTD_ldm_skipRawSeqStoreBytes(rawSeqStore_t* rawSeqStore, size_t nbBytes); - -/** ZSTD_ldm_getTableSize() : - * Estimate the space needed for long distance matching tables or 0 if LDM is - * disabled. - */ -size_t ZSTD_ldm_getTableSize(ldmParams_t params); - -/** ZSTD_ldm_getSeqSpace() : - * Return an upper bound on the number of sequences that can be produced by - * the long distance matcher, or 0 if LDM is disabled. - */ -size_t ZSTD_ldm_getMaxNbSeq(ldmParams_t params, size_t maxChunkSize); - -/** ZSTD_ldm_adjustParameters() : + +/** ZSTD_ldm_getTableSize() : + * Estimate the space needed for long distance matching tables or 0 if LDM is + * disabled. + */ +size_t ZSTD_ldm_getTableSize(ldmParams_t params); + +/** ZSTD_ldm_getSeqSpace() : + * Return an upper bound on the number of sequences that can be produced by + * the long distance matcher, or 0 if LDM is disabled. + */ +size_t ZSTD_ldm_getMaxNbSeq(ldmParams_t params, size_t maxChunkSize); + +/** ZSTD_ldm_adjustParameters() : * If the params->hashRateLog is not set, set it to its default value based on - * windowLog and params->hashLog. - * - * Ensures that params->bucketSizeLog is <= params->hashLog (setting it to - * params->hashLog if it is not). - * - * Ensures that the minMatchLength >= targetLength during optimal parsing. - */ -void ZSTD_ldm_adjustParameters(ldmParams_t* params, - ZSTD_compressionParameters const* cParams); - -#if defined (__cplusplus) -} -#endif - -#endif /* ZSTD_FAST_H */ + * windowLog and params->hashLog. + * + * Ensures that params->bucketSizeLog is <= params->hashLog (setting it to + * params->hashLog if it is not). + * + * Ensures that the minMatchLength >= targetLength during optimal parsing. + */ +void ZSTD_ldm_adjustParameters(ldmParams_t* params, + ZSTD_compressionParameters const* cParams); + +#if defined (__cplusplus) +} +#endif + +#endif /* ZSTD_FAST_H */ diff --git a/contrib/libs/zstd/lib/compress/zstd_opt.c b/contrib/libs/zstd/lib/compress/zstd_opt.c index 1b1ddad428..794af785dd 100644 --- a/contrib/libs/zstd/lib/compress/zstd_opt.c +++ b/contrib/libs/zstd/lib/compress/zstd_opt.c @@ -1,27 +1,27 @@ -/* +/* * Copyright (c) Przemyslaw Skibinski, 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. - */ - -#include "zstd_compress_internal.h" + * 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. + */ + +#include "zstd_compress_internal.h" #include "hist.h" -#include "zstd_opt.h" - - +#include "zstd_opt.h" + + #define ZSTD_LITFREQ_ADD 2 /* scaling factor for litFreq, so that frequencies adapt faster to new stats */ -#define ZSTD_MAX_PRICE (1<<30) - +#define ZSTD_MAX_PRICE (1<<30) + #define ZSTD_PREDEF_THRESHOLD 1024 /* if srcSize < ZSTD_PREDEF_THRESHOLD, symbols' cost is assumed static, directly determined by pre-defined distributions */ + - -/*-************************************* -* Price functions for optimal parser -***************************************/ +/*-************************************* +* Price functions for optimal parser +***************************************/ #if 0 /* approximation at bit level (for tests) */ # define BITCOST_ACCURACY 0 @@ -38,10 +38,10 @@ #endif MEM_STATIC U32 ZSTD_bitWeight(U32 stat) -{ +{ return (ZSTD_highbit32(stat+1) * BITCOST_MULTIPLIER); -} - +} + MEM_STATIC U32 ZSTD_fracWeight(U32 rawStat) { U32 const stat = rawStat + 1; @@ -52,22 +52,22 @@ MEM_STATIC U32 ZSTD_fracWeight(U32 rawStat) assert(hb + BITCOST_ACCURACY < 31); return weight; } - + #if (DEBUGLEVEL>=2) /* debugging function, * @return price in bytes as fractional value * for debug messages only */ MEM_STATIC double ZSTD_fCost(U32 price) -{ +{ return (double)price / (BITCOST_MULTIPLIER*8); } #endif - + static int ZSTD_compressedLiterals(optState_t const* const optPtr) { return optPtr->literalCompressionMode != ZSTD_ps_disable; } - + static void ZSTD_setBasePrices(optState_t* optPtr, int optLevel) { if (ZSTD_compressedLiterals(optPtr)) @@ -133,13 +133,13 @@ ZSTD_rescaleFreqs(optState_t* const optPtr, if (srcSize <= ZSTD_PREDEF_THRESHOLD) { /* heuristic */ DEBUGLOG(5, "(srcSize <= ZSTD_PREDEF_THRESHOLD) => zop_predef"); optPtr->priceType = zop_predef; - } - + } + assert(optPtr->symbolCosts != NULL); if (optPtr->symbolCosts->huf.repeatMode == HUF_repeat_valid) { /* huffman table presumed generated by dictionary */ optPtr->priceType = zop_dynamic; - + if (compressedLiterals) { unsigned lit; assert(optPtr->litFreq != NULL); @@ -151,7 +151,7 @@ ZSTD_rescaleFreqs(optState_t* const optPtr, optPtr->litFreq[lit] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/; optPtr->litSum += optPtr->litFreq[lit]; } } - + { unsigned ll; FSE_CState_t llstate; FSE_initCState(&llstate, optPtr->symbolCosts->fse.litlengthCTable); @@ -225,7 +225,7 @@ ZSTD_rescaleFreqs(optState_t* const optPtr, } - } + } } else { /* new block : re-use previous statistics, scaled down */ @@ -234,20 +234,20 @@ ZSTD_rescaleFreqs(optState_t* const optPtr, optPtr->litLengthSum = ZSTD_scaleStats(optPtr->litLengthFreq, MaxLL, 11); optPtr->matchLengthSum = ZSTD_scaleStats(optPtr->matchLengthFreq, MaxML, 11); optPtr->offCodeSum = ZSTD_scaleStats(optPtr->offCodeFreq, MaxOff, 11); - } - + } + ZSTD_setBasePrices(optPtr, optLevel); -} - -/* ZSTD_rawLiteralsCost() : +} + +/* ZSTD_rawLiteralsCost() : * price of literals (only) in specified segment (which length can be 0). * does not include price of literalLength symbol */ -static U32 ZSTD_rawLiteralsCost(const BYTE* const literals, U32 const litLength, +static U32 ZSTD_rawLiteralsCost(const BYTE* const literals, U32 const litLength, const optState_t* const optPtr, int optLevel) -{ - if (litLength == 0) return 0; - +{ + if (litLength == 0) return 0; + if (!ZSTD_compressedLiterals(optPtr)) return (litLength << 3) * BITCOST_MULTIPLIER; /* Uncompressed - 8 bytes per literal. */ @@ -262,13 +262,13 @@ static U32 ZSTD_rawLiteralsCost(const BYTE* const literals, U32 const litLength, price -= WEIGHT(optPtr->litFreq[literals[u]], optLevel); } return price; - } -} - -/* ZSTD_litLengthPrice() : - * cost of literalLength symbol */ + } +} + +/* ZSTD_litLengthPrice() : + * cost of literalLength symbol */ static U32 ZSTD_litLengthPrice(U32 const litLength, const optState_t* const optPtr, int optLevel) -{ +{ assert(litLength <= ZSTD_BLOCKSIZE_MAX); if (optPtr->priceType == zop_predef) return WEIGHT(litLength, optLevel); @@ -279,18 +279,18 @@ static U32 ZSTD_litLengthPrice(U32 const litLength, const optState_t* const optP */ if (litLength == ZSTD_BLOCKSIZE_MAX) return BITCOST_MULTIPLIER + ZSTD_litLengthPrice(ZSTD_BLOCKSIZE_MAX - 1, optPtr, optLevel); - + /* dynamic statistics */ - { U32 const llCode = ZSTD_LLcode(litLength); + { U32 const llCode = ZSTD_LLcode(litLength); return (LL_bits[llCode] * BITCOST_MULTIPLIER) + optPtr->litLengthSumBasePrice - WEIGHT(optPtr->litLengthFreq[llCode], optLevel); - } -} - -/* ZSTD_getMatchPrice() : - * Provides the cost of the match part (offset + matchLength) of a sequence - * Must be combined with ZSTD_fullLiteralsCost() to get the full cost of a sequence. + } +} + +/* ZSTD_getMatchPrice() : + * Provides the cost of the match part (offset + matchLength) of a sequence + * Must be combined with ZSTD_fullLiteralsCost() to get the full cost of a sequence. * @offcode : expects a scale where 0,1,2 are repcodes 1-3, and 3+ are real_offsets+2 * @optLevel: when <2, favors small offset for decompression speed (improved cache efficiency) */ @@ -299,245 +299,245 @@ ZSTD_getMatchPrice(U32 const offcode, U32 const matchLength, const optState_t* const optPtr, int const optLevel) -{ - U32 price; +{ + U32 price; U32 const offCode = ZSTD_highbit32(STORED_TO_OFFBASE(offcode)); - U32 const mlBase = matchLength - MINMATCH; - assert(matchLength >= MINMATCH); - + U32 const mlBase = matchLength - MINMATCH; + assert(matchLength >= MINMATCH); + if (optPtr->priceType == zop_predef) /* fixed scheme, do not use statistics */ return WEIGHT(mlBase, optLevel) + ((16 + offCode) * BITCOST_MULTIPLIER); - + /* dynamic statistics */ price = (offCode * BITCOST_MULTIPLIER) + (optPtr->offCodeSumBasePrice - WEIGHT(optPtr->offCodeFreq[offCode], optLevel)); if ((optLevel<2) /*static*/ && offCode >= 20) price += (offCode-19)*2 * BITCOST_MULTIPLIER; /* handicap for long distance offsets, favor decompression speed */ - - /* match Length */ - { U32 const mlCode = ZSTD_MLcode(mlBase); + + /* match Length */ + { U32 const mlCode = ZSTD_MLcode(mlBase); price += (ML_bits[mlCode] * BITCOST_MULTIPLIER) + (optPtr->matchLengthSumBasePrice - WEIGHT(optPtr->matchLengthFreq[mlCode], optLevel)); - } - + } + price += BITCOST_MULTIPLIER / 5; /* heuristic : make matches a bit more costly to favor less sequences -> faster decompression speed */ - DEBUGLOG(8, "ZSTD_getMatchPrice(ml:%u) = %u", matchLength, price); - return price; -} - + DEBUGLOG(8, "ZSTD_getMatchPrice(ml:%u) = %u", matchLength, price); + return price; +} + /* ZSTD_updateStats() : * assumption : literals + litLengtn <= iend */ -static void ZSTD_updateStats(optState_t* const optPtr, - U32 litLength, const BYTE* literals, - U32 offsetCode, U32 matchLength) -{ - /* literals */ +static void ZSTD_updateStats(optState_t* const optPtr, + U32 litLength, const BYTE* literals, + U32 offsetCode, U32 matchLength) +{ + /* literals */ if (ZSTD_compressedLiterals(optPtr)) { U32 u; - for (u=0; u < litLength; u++) - optPtr->litFreq[literals[u]] += ZSTD_LITFREQ_ADD; - optPtr->litSum += litLength*ZSTD_LITFREQ_ADD; - } - - /* literal Length */ - { U32 const llCode = ZSTD_LLcode(litLength); - optPtr->litLengthFreq[llCode]++; - optPtr->litLengthSum++; - } - + for (u=0; u < litLength; u++) + optPtr->litFreq[literals[u]] += ZSTD_LITFREQ_ADD; + optPtr->litSum += litLength*ZSTD_LITFREQ_ADD; + } + + /* literal Length */ + { U32 const llCode = ZSTD_LLcode(litLength); + optPtr->litLengthFreq[llCode]++; + optPtr->litLengthSum++; + } + /* offset code : expected to follow storeSeq() numeric representation */ { U32 const offCode = ZSTD_highbit32(STORED_TO_OFFBASE(offsetCode)); - assert(offCode <= MaxOff); - optPtr->offCodeFreq[offCode]++; - optPtr->offCodeSum++; - } - - /* match Length */ - { U32 const mlBase = matchLength - MINMATCH; - U32 const mlCode = ZSTD_MLcode(mlBase); - optPtr->matchLengthFreq[mlCode]++; - optPtr->matchLengthSum++; - } -} - - -/* ZSTD_readMINMATCH() : - * function safe only for comparisons - * assumption : memPtr must be at least 4 bytes before end of buffer */ -MEM_STATIC U32 ZSTD_readMINMATCH(const void* memPtr, U32 length) -{ - switch (length) - { - default : - case 4 : return MEM_read32(memPtr); - case 3 : if (MEM_isLittleEndian()) - return MEM_read32(memPtr)<<8; - else - return MEM_read32(memPtr)>>8; - } -} - - -/* Update hashTable3 up to ip (excluded) - Assumption : always within prefix (i.e. not within extDict) */ + assert(offCode <= MaxOff); + optPtr->offCodeFreq[offCode]++; + optPtr->offCodeSum++; + } + + /* match Length */ + { U32 const mlBase = matchLength - MINMATCH; + U32 const mlCode = ZSTD_MLcode(mlBase); + optPtr->matchLengthFreq[mlCode]++; + optPtr->matchLengthSum++; + } +} + + +/* ZSTD_readMINMATCH() : + * function safe only for comparisons + * assumption : memPtr must be at least 4 bytes before end of buffer */ +MEM_STATIC U32 ZSTD_readMINMATCH(const void* memPtr, U32 length) +{ + switch (length) + { + default : + case 4 : return MEM_read32(memPtr); + case 3 : if (MEM_isLittleEndian()) + return MEM_read32(memPtr)<<8; + else + return MEM_read32(memPtr)>>8; + } +} + + +/* Update hashTable3 up to ip (excluded) + Assumption : always within prefix (i.e. not within extDict) */ static U32 ZSTD_insertAndFindFirstIndexHash3 (const ZSTD_matchState_t* ms, U32* nextToUpdate3, const BYTE* const ip) -{ - U32* const hashTable3 = ms->hashTable3; - U32 const hashLog3 = ms->hashLog3; - const BYTE* const base = ms->window.base; +{ + U32* const hashTable3 = ms->hashTable3; + U32 const hashLog3 = ms->hashLog3; + const BYTE* const base = ms->window.base; U32 idx = *nextToUpdate3; U32 const target = (U32)(ip - base); - size_t const hash3 = ZSTD_hash3Ptr(ip, hashLog3); - assert(hashLog3 > 0); - - while(idx < target) { - hashTable3[ZSTD_hash3Ptr(base+idx, hashLog3)] = idx; - idx++; - } - + size_t const hash3 = ZSTD_hash3Ptr(ip, hashLog3); + assert(hashLog3 > 0); + + while(idx < target) { + hashTable3[ZSTD_hash3Ptr(base+idx, hashLog3)] = idx; + idx++; + } + *nextToUpdate3 = target; - return hashTable3[hash3]; -} - - -/*-************************************* -* Binary Tree search -***************************************/ -/** ZSTD_insertBt1() : add one or multiple positions to tree. + return hashTable3[hash3]; +} + + +/*-************************************* +* Binary Tree search +***************************************/ +/** ZSTD_insertBt1() : add one or multiple positions to tree. * @param ip assumed <= iend-8 . * @param target The target of ZSTD_updateTree_internal() - we are filling to this position - * @return : nb of positions added */ -static U32 ZSTD_insertBt1( + * @return : nb of positions added */ +static U32 ZSTD_insertBt1( const ZSTD_matchState_t* ms, - const BYTE* const ip, const BYTE* const iend, + const BYTE* const ip, const BYTE* const iend, U32 const target, U32 const mls, const int extDict) -{ +{ const ZSTD_compressionParameters* const cParams = &ms->cParams; - U32* const hashTable = ms->hashTable; - U32 const hashLog = cParams->hashLog; - size_t const h = ZSTD_hashPtr(ip, hashLog, mls); - U32* const bt = ms->chainTable; - U32 const btLog = cParams->chainLog - 1; - U32 const btMask = (1 << btLog) - 1; - U32 matchIndex = hashTable[h]; - size_t commonLengthSmaller=0, commonLengthLarger=0; - const BYTE* const base = ms->window.base; - const BYTE* const dictBase = ms->window.dictBase; - const U32 dictLimit = ms->window.dictLimit; - const BYTE* const dictEnd = dictBase + dictLimit; - const BYTE* const prefixStart = base + dictLimit; - const BYTE* match; + U32* const hashTable = ms->hashTable; + U32 const hashLog = cParams->hashLog; + size_t const h = ZSTD_hashPtr(ip, hashLog, mls); + U32* const bt = ms->chainTable; + U32 const btLog = cParams->chainLog - 1; + U32 const btMask = (1 << btLog) - 1; + U32 matchIndex = hashTable[h]; + size_t commonLengthSmaller=0, commonLengthLarger=0; + const BYTE* const base = ms->window.base; + const BYTE* const dictBase = ms->window.dictBase; + const U32 dictLimit = ms->window.dictLimit; + const BYTE* const dictEnd = dictBase + dictLimit; + const BYTE* const prefixStart = base + dictLimit; + const BYTE* match; const U32 curr = (U32)(ip-base); const U32 btLow = btMask >= curr ? 0 : curr - btMask; U32* smallerPtr = bt + 2*(curr&btMask); - U32* largerPtr = smallerPtr + 1; - U32 dummy32; /* to be nullified at the end */ + U32* largerPtr = smallerPtr + 1; + U32 dummy32; /* to be nullified at the end */ /* windowLow is based on target because * we only need positions that will be in the window at the end of the tree update. */ U32 const windowLow = ZSTD_getLowestMatchIndex(ms, target, cParams->windowLog); U32 matchEndIdx = curr+8+1; - size_t bestLength = 8; - U32 nbCompares = 1U << cParams->searchLog; -#ifdef ZSTD_C_PREDICT + size_t bestLength = 8; + U32 nbCompares = 1U << cParams->searchLog; +#ifdef ZSTD_C_PREDICT U32 predictedSmall = *(bt + 2*((curr-1)&btMask) + 0); U32 predictedLarge = *(bt + 2*((curr-1)&btMask) + 1); - predictedSmall += (predictedSmall>0); - predictedLarge += (predictedLarge>0); -#endif /* ZSTD_C_PREDICT */ - + predictedSmall += (predictedSmall>0); + predictedLarge += (predictedLarge>0); +#endif /* ZSTD_C_PREDICT */ + DEBUGLOG(8, "ZSTD_insertBt1 (%u)", curr); - + assert(curr <= target); - assert(ip <= iend-8); /* required for h calculation */ + assert(ip <= iend-8); /* required for h calculation */ hashTable[h] = curr; /* Update Hash Table */ - + assert(windowLow > 0); for (; nbCompares && (matchIndex >= windowLow); --nbCompares) { - U32* const nextPtr = bt + 2*(matchIndex & btMask); - size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ + U32* const nextPtr = bt + 2*(matchIndex & btMask); + size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ assert(matchIndex < curr); - -#ifdef ZSTD_C_PREDICT /* note : can create issues when hlog small <= 11 */ - const U32* predictPtr = bt + 2*((matchIndex-1) & btMask); /* written this way, as bt is a roll buffer */ - if (matchIndex == predictedSmall) { - /* no need to check length, result known */ - *smallerPtr = matchIndex; - if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop the search */ - smallerPtr = nextPtr+1; /* new "smaller" => larger of match */ - matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to current) */ - predictedSmall = predictPtr[1] + (predictPtr[1]>0); - continue; - } - if (matchIndex == predictedLarge) { - *largerPtr = matchIndex; - if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop the search */ - largerPtr = nextPtr; - matchIndex = nextPtr[0]; - predictedLarge = predictPtr[0] + (predictPtr[0]>0); - continue; - } -#endif - + +#ifdef ZSTD_C_PREDICT /* note : can create issues when hlog small <= 11 */ + const U32* predictPtr = bt + 2*((matchIndex-1) & btMask); /* written this way, as bt is a roll buffer */ + if (matchIndex == predictedSmall) { + /* no need to check length, result known */ + *smallerPtr = matchIndex; + if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop the search */ + smallerPtr = nextPtr+1; /* new "smaller" => larger of match */ + matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to current) */ + predictedSmall = predictPtr[1] + (predictPtr[1]>0); + continue; + } + if (matchIndex == predictedLarge) { + *largerPtr = matchIndex; + if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop the search */ + largerPtr = nextPtr; + matchIndex = nextPtr[0]; + predictedLarge = predictPtr[0] + (predictPtr[0]>0); + continue; + } +#endif + if (!extDict || (matchIndex+matchLength >= dictLimit)) { assert(matchIndex+matchLength >= dictLimit); /* might be wrong if actually extDict */ - match = base + matchIndex; - matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend); - } else { - match = dictBase + matchIndex; - matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart); - if (matchIndex+matchLength >= dictLimit) - match = base + matchIndex; /* to prepare for next usage of match[matchLength] */ - } - - if (matchLength > bestLength) { - bestLength = matchLength; - if (matchLength > matchEndIdx - matchIndex) - matchEndIdx = matchIndex + (U32)matchLength; - } - - if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */ - break; /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt tree */ - } - - if (match[matchLength] < ip[matchLength]) { /* necessarily within buffer */ - /* match is smaller than current */ - *smallerPtr = matchIndex; /* update smaller idx */ - commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ - if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop searching */ - smallerPtr = nextPtr+1; /* new "candidate" => larger than match, which was smaller than target */ - matchIndex = nextPtr[1]; /* new matchIndex, larger than previous and closer to current */ - } else { - /* match is larger than current */ - *largerPtr = matchIndex; - commonLengthLarger = matchLength; - if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop searching */ - largerPtr = nextPtr; - matchIndex = nextPtr[0]; - } } - - *smallerPtr = *largerPtr = 0; + match = base + matchIndex; + matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend); + } else { + match = dictBase + matchIndex; + matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart); + if (matchIndex+matchLength >= dictLimit) + match = base + matchIndex; /* to prepare for next usage of match[matchLength] */ + } + + if (matchLength > bestLength) { + bestLength = matchLength; + if (matchLength > matchEndIdx - matchIndex) + matchEndIdx = matchIndex + (U32)matchLength; + } + + if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */ + break; /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt tree */ + } + + if (match[matchLength] < ip[matchLength]) { /* necessarily within buffer */ + /* match is smaller than current */ + *smallerPtr = matchIndex; /* update smaller idx */ + commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ + if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop searching */ + smallerPtr = nextPtr+1; /* new "candidate" => larger than match, which was smaller than target */ + matchIndex = nextPtr[1]; /* new matchIndex, larger than previous and closer to current */ + } else { + /* match is larger than current */ + *largerPtr = matchIndex; + commonLengthLarger = matchLength; + if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop searching */ + largerPtr = nextPtr; + matchIndex = nextPtr[0]; + } } + + *smallerPtr = *largerPtr = 0; { U32 positions = 0; if (bestLength > 384) positions = MIN(192, (U32)(bestLength - 384)); /* speed optimization */ assert(matchEndIdx > curr + 8); return MAX(positions, matchEndIdx - (curr + 8)); } -} - -FORCE_INLINE_TEMPLATE -void ZSTD_updateTree_internal( +} + +FORCE_INLINE_TEMPLATE +void ZSTD_updateTree_internal( ZSTD_matchState_t* ms, - const BYTE* const ip, const BYTE* const iend, + const BYTE* const ip, const BYTE* const iend, const U32 mls, const ZSTD_dictMode_e dictMode) -{ - const BYTE* const base = ms->window.base; - U32 const target = (U32)(ip - base); - U32 idx = ms->nextToUpdate; +{ + const BYTE* const base = ms->window.base; + U32 const target = (U32)(ip - base); + U32 idx = ms->nextToUpdate; DEBUGLOG(6, "ZSTD_updateTree_internal, from %u to %u (dictMode:%u)", idx, target, dictMode); - + while(idx < target) { U32 const forward = ZSTD_insertBt1(ms, base+idx, iend, target, mls, dictMode == ZSTD_extDict); assert(idx < (U32)(idx + forward)); @@ -545,15 +545,15 @@ void ZSTD_updateTree_internal( } assert((size_t)(ip - base) <= (size_t)(U32)(-1)); assert((size_t)(iend - base) <= (size_t)(U32)(-1)); - ms->nextToUpdate = target; -} - + ms->nextToUpdate = target; +} + void ZSTD_updateTree(ZSTD_matchState_t* ms, const BYTE* ip, const BYTE* iend) { ZSTD_updateTree_internal(ms, ip, iend, ms->cParams.minMatch, ZSTD_noDict); -} - -FORCE_INLINE_TEMPLATE -U32 ZSTD_insertBtAndGetAllMatches ( +} + +FORCE_INLINE_TEMPLATE +U32 ZSTD_insertBtAndGetAllMatches ( ZSTD_match_t* matches, /* store result (found matches) in this table (presumed large enough) */ ZSTD_matchState_t* ms, U32* nextToUpdate3, @@ -562,34 +562,34 @@ U32 ZSTD_insertBtAndGetAllMatches ( U32 const ll0, /* tells if associated literal length is 0 or not. This value must be 0 or 1 */ const U32 lengthToBeat, U32 const mls /* template */) -{ +{ const ZSTD_compressionParameters* const cParams = &ms->cParams; - U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1); - const BYTE* const base = ms->window.base; + U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1); + const BYTE* const base = ms->window.base; U32 const curr = (U32)(ip-base); - U32 const hashLog = cParams->hashLog; - U32 const minMatch = (mls==3) ? 3 : 4; - U32* const hashTable = ms->hashTable; - size_t const h = ZSTD_hashPtr(ip, hashLog, mls); - U32 matchIndex = hashTable[h]; - U32* const bt = ms->chainTable; - U32 const btLog = cParams->chainLog - 1; - U32 const btMask= (1U << btLog) - 1; - size_t commonLengthSmaller=0, commonLengthLarger=0; - const BYTE* const dictBase = ms->window.dictBase; - U32 const dictLimit = ms->window.dictLimit; - const BYTE* const dictEnd = dictBase + dictLimit; - const BYTE* const prefixStart = base + dictLimit; + U32 const hashLog = cParams->hashLog; + U32 const minMatch = (mls==3) ? 3 : 4; + U32* const hashTable = ms->hashTable; + size_t const h = ZSTD_hashPtr(ip, hashLog, mls); + U32 matchIndex = hashTable[h]; + U32* const bt = ms->chainTable; + U32 const btLog = cParams->chainLog - 1; + U32 const btMask= (1U << btLog) - 1; + size_t commonLengthSmaller=0, commonLengthLarger=0; + const BYTE* const dictBase = ms->window.dictBase; + U32 const dictLimit = ms->window.dictLimit; + const BYTE* const dictEnd = dictBase + dictLimit; + const BYTE* const prefixStart = base + dictLimit; U32 const btLow = (btMask >= curr) ? 0 : curr - btMask; U32 const windowLow = ZSTD_getLowestMatchIndex(ms, curr, cParams->windowLog); U32 const matchLow = windowLow ? windowLow : 1; U32* smallerPtr = bt + 2*(curr&btMask); U32* largerPtr = bt + 2*(curr&btMask) + 1; U32 matchEndIdx = curr+8+1; /* farthest referenced position of any match => detects repetitive patterns */ - U32 dummy32; /* to be nullified at the end */ - U32 mnum = 0; - U32 nbCompares = 1U << cParams->searchLog; - + U32 dummy32; /* to be nullified at the end */ + U32 mnum = 0; + U32 nbCompares = 1U << cParams->searchLog; + const ZSTD_matchState_t* dms = dictMode == ZSTD_dictMatchState ? ms->dictMatchState : NULL; const ZSTD_compressionParameters* const dmsCParams = dictMode == ZSTD_dictMatchState ? &dms->cParams : NULL; @@ -603,25 +603,25 @@ U32 ZSTD_insertBtAndGetAllMatches ( U32 const dmsBtMask = dictMode == ZSTD_dictMatchState ? (1U << dmsBtLog) - 1 : 0; U32 const dmsBtLow = dictMode == ZSTD_dictMatchState && dmsBtMask < dmsHighLimit - dmsLowLimit ? dmsHighLimit - dmsBtMask : dmsLowLimit; - size_t bestLength = lengthToBeat-1; + size_t bestLength = lengthToBeat-1; DEBUGLOG(8, "ZSTD_insertBtAndGetAllMatches: current=%u", curr); - - /* check repCode */ + + /* check repCode */ assert(ll0 <= 1); /* necessarily 1 or 0 */ - { U32 const lastR = ZSTD_REP_NUM + ll0; - U32 repCode; - for (repCode = ll0; repCode < lastR; repCode++) { - U32 const repOffset = (repCode==ZSTD_REP_NUM) ? (rep[0] - 1) : rep[repCode]; + { U32 const lastR = ZSTD_REP_NUM + ll0; + U32 repCode; + for (repCode = ll0; repCode < lastR; repCode++) { + U32 const repOffset = (repCode==ZSTD_REP_NUM) ? (rep[0] - 1) : rep[repCode]; U32 const repIndex = curr - repOffset; - U32 repLen = 0; + U32 repLen = 0; assert(curr >= dictLimit); if (repOffset-1 /* intentional overflow, discards 0 and -1 */ < curr-dictLimit) { /* equivalent to `curr > repIndex >= dictLimit` */ /* We must validate the repcode offset because when we're using a dictionary the * valid offset range shrinks when the dictionary goes out of bounds. */ if ((repIndex >= windowLow) & (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(ip - repOffset, minMatch))) { - repLen = (U32)ZSTD_count(ip+minMatch, ip+minMatch-repOffset, iLimit) + minMatch; - } + repLen = (U32)ZSTD_count(ip+minMatch, ip+minMatch-repOffset, iLimit) + minMatch; + } } else { /* repIndex < dictLimit || repIndex >= curr */ const BYTE* const repMatch = dictMode == ZSTD_dictMatchState ? dmsBase + repIndex - dmsIndexDelta : @@ -629,115 +629,115 @@ U32 ZSTD_insertBtAndGetAllMatches ( assert(curr >= windowLow); if ( dictMode == ZSTD_extDict && ( ((repOffset-1) /*intentional overflow*/ < curr - windowLow) /* equivalent to `curr > repIndex >= windowLow` */ - & (((U32)((dictLimit-1) - repIndex) >= 3) ) /* intentional overflow : do not test positions overlapping 2 memory segments */) - && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) { - repLen = (U32)ZSTD_count_2segments(ip+minMatch, repMatch+minMatch, iLimit, dictEnd, prefixStart) + minMatch; + & (((U32)((dictLimit-1) - repIndex) >= 3) ) /* intentional overflow : do not test positions overlapping 2 memory segments */) + && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) { + repLen = (U32)ZSTD_count_2segments(ip+minMatch, repMatch+minMatch, iLimit, dictEnd, prefixStart) + minMatch; } if (dictMode == ZSTD_dictMatchState && ( ((repOffset-1) /*intentional overflow*/ < curr - (dmsLowLimit + dmsIndexDelta)) /* equivalent to `curr > repIndex >= dmsLowLimit` */ & ((U32)((dictLimit-1) - repIndex) >= 3) ) /* intentional overflow : do not test positions overlapping 2 memory segments */ && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) { repLen = (U32)ZSTD_count_2segments(ip+minMatch, repMatch+minMatch, iLimit, dmsEnd, prefixStart) + minMatch; - } } - /* save longer solution */ - if (repLen > bestLength) { + } } + /* save longer solution */ + if (repLen > bestLength) { DEBUGLOG(8, "found repCode %u (ll0:%u, offset:%u) of length %u", repCode, ll0, repOffset, repLen); - bestLength = repLen; + bestLength = repLen; matches[mnum].off = STORE_REPCODE(repCode - ll0 + 1); /* expect value between 1 and 3 */ - matches[mnum].len = (U32)repLen; - mnum++; - if ( (repLen > sufficient_len) - | (ip+repLen == iLimit) ) { /* best possible */ - return mnum; - } } } } - - /* HC3 match finder */ - if ((mls == 3) /*static*/ && (bestLength < mls)) { + matches[mnum].len = (U32)repLen; + mnum++; + if ( (repLen > sufficient_len) + | (ip+repLen == iLimit) ) { /* best possible */ + return mnum; + } } } } + + /* HC3 match finder */ + if ((mls == 3) /*static*/ && (bestLength < mls)) { U32 const matchIndex3 = ZSTD_insertAndFindFirstIndexHash3(ms, nextToUpdate3, ip); if ((matchIndex3 >= matchLow) & (curr - matchIndex3 < (1<<18)) /*heuristic : longer distance likely too expensive*/ ) { - size_t mlen; + size_t mlen; if ((dictMode == ZSTD_noDict) /*static*/ || (dictMode == ZSTD_dictMatchState) /*static*/ || (matchIndex3 >= dictLimit)) { - const BYTE* const match = base + matchIndex3; - mlen = ZSTD_count(ip, match, iLimit); - } else { - const BYTE* const match = dictBase + matchIndex3; - mlen = ZSTD_count_2segments(ip, match, iLimit, dictEnd, prefixStart); - } - - /* save best solution */ - if (mlen >= mls /* == 3 > bestLength */) { - DEBUGLOG(8, "found small match with hlog3, of length %u", - (U32)mlen); - bestLength = mlen; + const BYTE* const match = base + matchIndex3; + mlen = ZSTD_count(ip, match, iLimit); + } else { + const BYTE* const match = dictBase + matchIndex3; + mlen = ZSTD_count_2segments(ip, match, iLimit, dictEnd, prefixStart); + } + + /* save best solution */ + if (mlen >= mls /* == 3 > bestLength */) { + DEBUGLOG(8, "found small match with hlog3, of length %u", + (U32)mlen); + bestLength = mlen; assert(curr > matchIndex3); - assert(mnum==0); /* no prior solution */ + assert(mnum==0); /* no prior solution */ matches[0].off = STORE_OFFSET(curr - matchIndex3); - matches[0].len = (U32)mlen; - mnum = 1; - if ( (mlen > sufficient_len) | - (ip+mlen == iLimit) ) { /* best possible length */ + matches[0].len = (U32)mlen; + mnum = 1; + if ( (mlen > sufficient_len) | + (ip+mlen == iLimit) ) { /* best possible length */ ms->nextToUpdate = curr+1; /* skip insertion */ - return 1; + return 1; } } } /* no dictMatchState lookup: dicts don't have a populated HC3 table */ } /* if (mls == 3) */ - + hashTable[h] = curr; /* Update Hash Table */ - + for (; nbCompares && (matchIndex >= matchLow); --nbCompares) { - U32* const nextPtr = bt + 2*(matchIndex & btMask); + U32* const nextPtr = bt + 2*(matchIndex & btMask); const BYTE* match; - size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ + size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ assert(curr > matchIndex); - + if ((dictMode == ZSTD_noDict) || (dictMode == ZSTD_dictMatchState) || (matchIndex+matchLength >= dictLimit)) { - assert(matchIndex+matchLength >= dictLimit); /* ensure the condition is correct when !extDict */ - match = base + matchIndex; + assert(matchIndex+matchLength >= dictLimit); /* ensure the condition is correct when !extDict */ + match = base + matchIndex; if (matchIndex >= dictLimit) assert(memcmp(match, ip, matchLength) == 0); /* ensure early section of match is equal as expected */ - matchLength += ZSTD_count(ip+matchLength, match+matchLength, iLimit); - } else { - match = dictBase + matchIndex; + matchLength += ZSTD_count(ip+matchLength, match+matchLength, iLimit); + } else { + match = dictBase + matchIndex; assert(memcmp(match, ip, matchLength) == 0); /* ensure early section of match is equal as expected */ - matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iLimit, dictEnd, prefixStart); - if (matchIndex+matchLength >= dictLimit) + matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iLimit, dictEnd, prefixStart); + if (matchIndex+matchLength >= dictLimit) match = base + matchIndex; /* prepare for match[matchLength] read */ - } - - if (matchLength > bestLength) { + } + + if (matchLength > bestLength) { DEBUGLOG(8, "found match of length %u at distance %u (offCode=%u)", (U32)matchLength, curr - matchIndex, STORE_OFFSET(curr - matchIndex)); - assert(matchEndIdx > matchIndex); - if (matchLength > matchEndIdx - matchIndex) - matchEndIdx = matchIndex + (U32)matchLength; - bestLength = matchLength; + assert(matchEndIdx > matchIndex); + if (matchLength > matchEndIdx - matchIndex) + matchEndIdx = matchIndex + (U32)matchLength; + bestLength = matchLength; matches[mnum].off = STORE_OFFSET(curr - matchIndex); - matches[mnum].len = (U32)matchLength; - mnum++; + matches[mnum].len = (U32)matchLength; + mnum++; if ( (matchLength > ZSTD_OPT_NUM) | (ip+matchLength == iLimit) /* equal : no way to know if inf or sup */) { if (dictMode == ZSTD_dictMatchState) nbCompares = 0; /* break should also skip searching dms */ break; /* drop, to preserve bt consistency (miss a little bit of compression) */ } } - - if (match[matchLength] < ip[matchLength]) { - /* match smaller than current */ - *smallerPtr = matchIndex; /* update smaller idx */ - commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ - if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop the search */ - smallerPtr = nextPtr+1; /* new candidate => larger than match, which was smaller than current */ - matchIndex = nextPtr[1]; /* new matchIndex, larger than previous, closer to current */ - } else { - *largerPtr = matchIndex; - commonLengthLarger = matchLength; - if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop the search */ - largerPtr = nextPtr; - matchIndex = nextPtr[0]; - } } - - *smallerPtr = *largerPtr = 0; - + + if (match[matchLength] < ip[matchLength]) { + /* match smaller than current */ + *smallerPtr = matchIndex; /* update smaller idx */ + commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ + if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop the search */ + smallerPtr = nextPtr+1; /* new candidate => larger than match, which was smaller than current */ + matchIndex = nextPtr[1]; /* new matchIndex, larger than previous, closer to current */ + } else { + *largerPtr = matchIndex; + commonLengthLarger = matchLength; + if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop the search */ + largerPtr = nextPtr; + matchIndex = nextPtr[0]; + } } + + *smallerPtr = *largerPtr = 0; + assert(nbCompares <= (1U << ZSTD_SEARCHLOG_MAX)); /* Check we haven't underflowed. */ if (dictMode == ZSTD_dictMatchState && nbCompares) { size_t const dmsH = ZSTD_hashPtr(ip, dmsHashLog, mls); @@ -778,10 +778,10 @@ U32 ZSTD_insertBtAndGetAllMatches ( } } } /* if (dictMode == ZSTD_dictMatchState) */ assert(matchEndIdx > curr+8); - ms->nextToUpdate = matchEndIdx - 8; /* skip repetitive patterns */ - return mnum; -} - + ms->nextToUpdate = matchEndIdx - 8; /* skip repetitive patterns */ + return mnum; +} + typedef U32 (*ZSTD_getAllMatchesFn)( ZSTD_match_t*, ZSTD_matchState_t*, @@ -791,7 +791,7 @@ typedef U32 (*ZSTD_getAllMatchesFn)( const U32 rep[ZSTD_REP_NUM], U32 const ll0, U32 const lengthToBeat); - + FORCE_INLINE_TEMPLATE U32 ZSTD_btGetAllMatches_internal( ZSTD_match_t* matches, ZSTD_matchState_t* ms, @@ -803,7 +803,7 @@ FORCE_INLINE_TEMPLATE U32 ZSTD_btGetAllMatches_internal( U32 const lengthToBeat, const ZSTD_dictMode_e dictMode, const U32 mls) -{ +{ assert(BOUNDED(3, ms->cParams.minMatch, 6) == mls); DEBUGLOG(8, "ZSTD_BtGetAllMatches(dictMode=%d, mls=%u)", (int)dictMode, mls); if (ip < ms->window.base + ms->nextToUpdate) @@ -828,7 +828,7 @@ FORCE_INLINE_TEMPLATE U32 ZSTD_btGetAllMatches_internal( return ZSTD_btGetAllMatches_internal( \ matches, ms, nextToUpdate3, ip, iHighLimit, \ rep, ll0, lengthToBeat, ZSTD_##dictMode, mls); \ - } + } #define GEN_ZSTD_BT_GET_ALL_MATCHES(dictMode) \ GEN_ZSTD_BT_GET_ALL_MATCHES_(dictMode, 3) \ @@ -860,12 +860,12 @@ ZSTD_selectBtGetAllMatches(ZSTD_matchState_t const* ms, ZSTD_dictMode_e const di assert((U32)dictMode < 3); assert(mls - 3 < 4); return getAllMatchesFns[(int)dictMode][mls - 3]; -} - +} + /************************* * LDM helper functions * *************************/ - + /* Struct containing info needed to make decision about ldm inclusion */ typedef struct { rawSeqStore_t seqStore; /* External match candidates store for this block */ @@ -1007,17 +1007,17 @@ ZSTD_optLdm_processMatchCandidate(ZSTD_optLdm_t* optLdm, } -/*-******************************* -* Optimal parser -*********************************/ - +/*-******************************* +* Optimal parser +*********************************/ + static U32 ZSTD_totalLen(ZSTD_optimal_t sol) -{ +{ return sol.litlen + sol.mlen; } - + #if 0 /* debug */ - + static void listStats(const U32* table, int lastEltID) { @@ -1027,12 +1027,12 @@ listStats(const U32* table, int lastEltID) (void)table; /* RAWLOG(2, "%3i:%3i, ", enb, table[enb]); */ RAWLOG(2, "%4i,", table[enb]); - } + } RAWLOG(2, " \n"); -} - +} + #endif - + FORCE_INLINE_TEMPLATE size_t ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms, seqStore_t* seqStore, @@ -1040,132 +1040,132 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms, const void* src, size_t srcSize, const int optLevel, const ZSTD_dictMode_e dictMode) -{ - optState_t* const optStatePtr = &ms->opt; - const BYTE* const istart = (const BYTE*)src; - const BYTE* ip = istart; - const BYTE* anchor = istart; - const BYTE* const iend = istart + srcSize; - const BYTE* const ilimit = iend - 8; - const BYTE* const base = ms->window.base; - const BYTE* const prefixStart = base + ms->window.dictLimit; +{ + optState_t* const optStatePtr = &ms->opt; + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - 8; + const BYTE* const base = ms->window.base; + const BYTE* const prefixStart = base + ms->window.dictLimit; const ZSTD_compressionParameters* const cParams = &ms->cParams; - + ZSTD_getAllMatchesFn getAllMatches = ZSTD_selectBtGetAllMatches(ms, dictMode); - U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1); + U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1); U32 const minMatch = (cParams->minMatch == 3) ? 3 : 4; U32 nextToUpdate3 = ms->nextToUpdate; - - ZSTD_optimal_t* const opt = optStatePtr->priceTable; - ZSTD_match_t* const matches = optStatePtr->matchTable; + + ZSTD_optimal_t* const opt = optStatePtr->priceTable; + ZSTD_match_t* const matches = optStatePtr->matchTable; ZSTD_optimal_t lastSequence; ZSTD_optLdm_t optLdm; - + optLdm.seqStore = ms->ldmSeqStore ? *ms->ldmSeqStore : kNullRawSeqStore; optLdm.endPosInBlock = optLdm.startPosInBlock = optLdm.offset = 0; ZSTD_opt_getNextMatchAndUpdateSeqStore(&optLdm, (U32)(ip-istart), (U32)(iend-ip)); - /* init */ + /* init */ DEBUGLOG(5, "ZSTD_compressBlock_opt_generic: current=%u, prefix=%u, nextToUpdate=%u", (U32)(ip - base), ms->window.dictLimit, ms->nextToUpdate); assert(optLevel <= 2); ZSTD_rescaleFreqs(optStatePtr, (const BYTE*)src, srcSize, optLevel); - ip += (ip==prefixStart); - - /* Match Loop */ - while (ip < ilimit) { - U32 cur, last_pos = 0; - - /* find first match */ - { U32 const litlen = (U32)(ip - anchor); - U32 const ll0 = !litlen; + ip += (ip==prefixStart); + + /* Match Loop */ + while (ip < ilimit) { + U32 cur, last_pos = 0; + + /* find first match */ + { U32 const litlen = (U32)(ip - anchor); + U32 const ll0 = !litlen; U32 nbMatches = getAllMatches(matches, ms, &nextToUpdate3, ip, iend, rep, ll0, minMatch); ZSTD_optLdm_processMatchCandidate(&optLdm, matches, &nbMatches, (U32)(ip-istart), (U32)(iend - ip)); - if (!nbMatches) { ip++; continue; } - - /* initialize opt[0] */ - { U32 i ; for (i=0; i<ZSTD_REP_NUM; i++) opt[0].rep[i] = rep[i]; } + if (!nbMatches) { ip++; continue; } + + /* initialize opt[0] */ + { U32 i ; for (i=0; i<ZSTD_REP_NUM; i++) opt[0].rep[i] = rep[i]; } opt[0].mlen = 0; /* means is_a_literal */ - opt[0].litlen = litlen; + opt[0].litlen = litlen; /* We don't need to include the actual price of the literals because * it is static for the duration of the forward pass, and is included * in every price. We include the literal length to avoid negative * prices when we subtract the previous literal length. */ opt[0].price = (int)ZSTD_litLengthPrice(litlen, optStatePtr, optLevel); - - /* large match -> immediate encoding */ - { U32 const maxML = matches[nbMatches-1].len; + + /* large match -> immediate encoding */ + { U32 const maxML = matches[nbMatches-1].len; U32 const maxOffcode = matches[nbMatches-1].off; DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffCode=%u at cPos=%u => start new series", nbMatches, maxML, maxOffcode, (U32)(ip-prefixStart)); - - if (maxML > sufficient_len) { + + if (maxML > sufficient_len) { lastSequence.litlen = litlen; lastSequence.mlen = maxML; lastSequence.off = maxOffcode; DEBUGLOG(6, "large match (%u>%u), immediate encoding", maxML, sufficient_len); - cur = 0; + cur = 0; last_pos = ZSTD_totalLen(lastSequence); - goto _shortestPath; - } } - - /* set prices for first matches starting position == 0 */ + goto _shortestPath; + } } + + /* set prices for first matches starting position == 0 */ assert(opt[0].price >= 0); { U32 const literalsPrice = (U32)opt[0].price + ZSTD_litLengthPrice(0, optStatePtr, optLevel); - U32 pos; - U32 matchNb; + U32 pos; + U32 matchNb; for (pos = 1; pos < minMatch; pos++) { opt[pos].price = ZSTD_MAX_PRICE; /* mlen, litlen and price will be fixed during forward scanning */ - } - for (matchNb = 0; matchNb < nbMatches; matchNb++) { + } + for (matchNb = 0; matchNb < nbMatches; matchNb++) { U32 const offcode = matches[matchNb].off; - U32 const end = matches[matchNb].len; - for ( ; pos <= end ; pos++ ) { + U32 const end = matches[matchNb].len; + for ( ; pos <= end ; pos++ ) { U32 const matchPrice = ZSTD_getMatchPrice(offcode, pos, optStatePtr, optLevel); U32 const sequencePrice = literalsPrice + matchPrice; DEBUGLOG(7, "rPos:%u => set initial price : %.2f", pos, ZSTD_fCost(sequencePrice)); - opt[pos].mlen = pos; + opt[pos].mlen = pos; opt[pos].off = offcode; - opt[pos].litlen = litlen; + opt[pos].litlen = litlen; opt[pos].price = (int)sequencePrice; - } } - last_pos = pos-1; - } - } - - /* check further positions */ - for (cur = 1; cur <= last_pos; cur++) { - const BYTE* const inr = ip + cur; - assert(cur < ZSTD_OPT_NUM); + } } + last_pos = pos-1; + } + } + + /* check further positions */ + for (cur = 1; cur <= last_pos; cur++) { + const BYTE* const inr = ip + cur; + assert(cur < ZSTD_OPT_NUM); DEBUGLOG(7, "cPos:%zi==rPos:%u", inr-istart, cur) - - /* Fix current position with one literal if cheaper */ + + /* Fix current position with one literal if cheaper */ { U32 const litlen = (opt[cur-1].mlen == 0) ? opt[cur-1].litlen + 1 : 1; int const price = opt[cur-1].price + (int)ZSTD_rawLiteralsCost(ip+cur-1, 1, optStatePtr, optLevel) + (int)ZSTD_litLengthPrice(litlen, optStatePtr, optLevel) - (int)ZSTD_litLengthPrice(litlen-1, optStatePtr, optLevel); - assert(price < 1000000000); /* overflow check */ - if (price <= opt[cur].price) { + assert(price < 1000000000); /* overflow check */ + if (price <= opt[cur].price) { DEBUGLOG(7, "cPos:%zi==rPos:%u : better price (%.2f<=%.2f) using literal (ll==%u) (hist:%u,%u,%u)", inr-istart, cur, ZSTD_fCost(price), ZSTD_fCost(opt[cur].price), litlen, opt[cur-1].rep[0], opt[cur-1].rep[1], opt[cur-1].rep[2]); opt[cur].mlen = 0; - opt[cur].off = 0; - opt[cur].litlen = litlen; - opt[cur].price = price; + opt[cur].off = 0; + opt[cur].litlen = litlen; + opt[cur].price = price; } else { DEBUGLOG(7, "cPos:%zi==rPos:%u : literal would cost more (%.2f>%.2f) (hist:%u,%u,%u)", inr-istart, cur, ZSTD_fCost(price), ZSTD_fCost(opt[cur].price), opt[cur].rep[0], opt[cur].rep[1], opt[cur].rep[2]); } } - + /* Set the repcodes of the current position. We must do it here * because we rely on the repcodes of the 2nd to last sequence being * correct to set the next chunks repcodes during the backward @@ -1181,24 +1181,24 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms, ZSTD_memcpy(opt[cur].rep, opt[cur - 1].rep, sizeof(repcodes_t)); } - /* last match must start at a minimum distance of 8 from oend */ - if (inr > ilimit) continue; - - if (cur == last_pos) break; - + /* last match must start at a minimum distance of 8 from oend */ + if (inr > ilimit) continue; + + if (cur == last_pos) break; + if ( (optLevel==0) /*static_test*/ && (opt[cur+1].price <= opt[cur].price + (BITCOST_MULTIPLIER/2)) ) { DEBUGLOG(7, "move to next rPos:%u : price is <=", cur+1); - continue; /* skip unpromising positions; about ~+6% speed, -0.01 ratio */ + continue; /* skip unpromising positions; about ~+6% speed, -0.01 ratio */ } - + assert(opt[cur].price >= 0); { U32 const ll0 = (opt[cur].mlen != 0); U32 const litlen = (opt[cur].mlen == 0) ? opt[cur].litlen : 0; U32 const previousPrice = (U32)opt[cur].price; U32 const basePrice = previousPrice + ZSTD_litLengthPrice(0, optStatePtr, optLevel); U32 nbMatches = getAllMatches(matches, ms, &nextToUpdate3, inr, iend, opt[cur].rep, ll0, minMatch); - U32 matchNb; + U32 matchNb; ZSTD_optLdm_processMatchCandidate(&optLdm, matches, &nbMatches, (U32)(inr-istart), (U32)(iend-inr)); @@ -1207,12 +1207,12 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms, DEBUGLOG(7, "rPos:%u : no match found", cur); continue; } - - { U32 const maxML = matches[nbMatches-1].len; + + { U32 const maxML = matches[nbMatches-1].len; DEBUGLOG(7, "cPos:%zi==rPos:%u, found %u matches, of maxLength=%u", inr-istart, cur, nbMatches, maxML); - - if ( (maxML > sufficient_len) + + if ( (maxML > sufficient_len) || (cur + maxML >= ZSTD_OPT_NUM) ) { lastSequence.mlen = maxML; lastSequence.off = matches[nbMatches-1].off; @@ -1220,46 +1220,46 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms, cur -= (opt[cur].mlen==0) ? opt[cur].litlen : 0; /* last sequence is actually only literals, fix cur to last match - note : may underflow, in which case, it's first sequence, and it's okay */ last_pos = cur + ZSTD_totalLen(lastSequence); if (cur > ZSTD_OPT_NUM) cur = 0; /* underflow => first match */ - goto _shortestPath; + goto _shortestPath; } } - - /* set prices using matches found at position == cur */ - for (matchNb = 0; matchNb < nbMatches; matchNb++) { - U32 const offset = matches[matchNb].off; - U32 const lastML = matches[matchNb].len; - U32 const startML = (matchNb>0) ? matches[matchNb-1].len+1 : minMatch; - U32 mlen; - + + /* set prices using matches found at position == cur */ + for (matchNb = 0; matchNb < nbMatches; matchNb++) { + U32 const offset = matches[matchNb].off; + U32 const lastML = matches[matchNb].len; + U32 const startML = (matchNb>0) ? matches[matchNb-1].len+1 : minMatch; + U32 mlen; + DEBUGLOG(7, "testing match %u => offCode=%4u, mlen=%2u, llen=%2u", - matchNb, matches[matchNb].off, lastML, litlen); - + matchNb, matches[matchNb].off, lastML, litlen); + for (mlen = lastML; mlen >= startML; mlen--) { /* scan downward */ - U32 const pos = cur + mlen; + U32 const pos = cur + mlen; int const price = (int)basePrice + (int)ZSTD_getMatchPrice(offset, mlen, optStatePtr, optLevel); - - if ((pos > last_pos) || (price < opt[pos].price)) { + + if ((pos > last_pos) || (price < opt[pos].price)) { DEBUGLOG(7, "rPos:%u (ml=%2u) => new better price (%.2f<%.2f)", pos, mlen, ZSTD_fCost(price), ZSTD_fCost(opt[pos].price)); while (last_pos < pos) { opt[last_pos+1].price = ZSTD_MAX_PRICE; last_pos++; } /* fill empty positions */ - opt[pos].mlen = mlen; - opt[pos].off = offset; - opt[pos].litlen = litlen; - opt[pos].price = price; - } else { + opt[pos].mlen = mlen; + opt[pos].off = offset; + opt[pos].litlen = litlen; + opt[pos].price = price; + } else { DEBUGLOG(7, "rPos:%u (ml=%2u) => new price is worse (%.2f>=%.2f)", pos, mlen, ZSTD_fCost(price), ZSTD_fCost(opt[pos].price)); if (optLevel==0) break; /* early update abort; gets ~+10% speed for about -0.01 ratio loss */ - } - } } } - } /* for (cur = 1; cur <= last_pos; cur++) */ - + } + } } } + } /* for (cur = 1; cur <= last_pos; cur++) */ + lastSequence = opt[last_pos]; cur = last_pos > ZSTD_totalLen(lastSequence) ? last_pos - ZSTD_totalLen(lastSequence) : 0; /* single sequence, and it starts before `ip` */ assert(cur < ZSTD_OPT_NUM); /* control overflow*/ - -_shortestPath: /* cur, last_pos, best_mlen, best_off have to be set */ + +_shortestPath: /* cur, last_pos, best_mlen, best_off have to be set */ assert(opt[0].mlen == 0); - + /* Set the next chunk's repcodes based on the repcodes of the beginning * of the last match, and the last sequence. This avoids us having to * update them while traversing the sequences. @@ -1274,7 +1274,7 @@ _shortestPath: /* cur, last_pos, best_mlen, best_off have to be set */ { U32 const storeEnd = cur + 1; U32 storeStart = storeEnd; U32 seqPos = cur; - + DEBUGLOG(6, "start reverse traversal (last_pos:%u, cur:%u)", last_pos, cur); (void)last_pos; assert(storeEnd < ZSTD_OPT_NUM); @@ -1289,7 +1289,7 @@ _shortestPath: /* cur, last_pos, best_mlen, best_off have to be set */ opt[storeStart] = opt[seqPos]; seqPos = (seqPos > backDist) ? seqPos - backDist : 0; } - + /* save sequences */ DEBUGLOG(6, "sending selected sequences into seqStore") { U32 storePos; @@ -1305,8 +1305,8 @@ _shortestPath: /* cur, last_pos, best_mlen, best_off have to be set */ assert(storePos == storeEnd); /* must be last sequence */ ip = anchor + llen; /* last "sequence" is a bunch of literals => don't progress anchor */ continue; /* will finish */ - } - + } + assert(anchor + llen <= iend); ZSTD_updateStats(optStatePtr, llen, anchor, offCode, mlen); ZSTD_storeSeq(seqStore, llen, anchor, iend, offCode, mlen); @@ -1315,19 +1315,19 @@ _shortestPath: /* cur, last_pos, best_mlen, best_off have to be set */ } } ZSTD_setBasePrices(optStatePtr, optLevel); } - } /* while (ip < ilimit) */ - - /* Return the last literals size */ + } /* while (ip < ilimit) */ + + /* Return the last literals size */ return (size_t)(iend - anchor); -} - +} + static size_t ZSTD_compressBlock_opt0( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], const void* src, size_t srcSize, const ZSTD_dictMode_e dictMode) { return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 0 /* optLevel */, dictMode); } - + static size_t ZSTD_compressBlock_opt2( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], const void* src, size_t srcSize, const ZSTD_dictMode_e dictMode) @@ -1335,14 +1335,14 @@ static size_t ZSTD_compressBlock_opt2( return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 2 /* optLevel */, dictMode); } -size_t ZSTD_compressBlock_btopt( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_btopt( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], const void* src, size_t srcSize) -{ - DEBUGLOG(5, "ZSTD_compressBlock_btopt"); +{ + DEBUGLOG(5, "ZSTD_compressBlock_btopt"); return ZSTD_compressBlock_opt0(ms, seqStore, rep, src, srcSize, ZSTD_noDict); -} - +} + @@ -1377,14 +1377,14 @@ ZSTD_initStats_ultra(ZSTD_matchState_t* ms, } -size_t ZSTD_compressBlock_btultra( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_btultra( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], const void* src, size_t srcSize) -{ +{ DEBUGLOG(5, "ZSTD_compressBlock_btultra (srcSize=%zu)", srcSize); return ZSTD_compressBlock_opt2(ms, seqStore, rep, src, srcSize, ZSTD_noDict); -} - +} + size_t ZSTD_compressBlock_btultra2( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], const void* src, size_t srcSize) @@ -1427,19 +1427,19 @@ size_t ZSTD_compressBlock_btultra_dictMatchState( return ZSTD_compressBlock_opt2(ms, seqStore, rep, src, srcSize, ZSTD_dictMatchState); } -size_t ZSTD_compressBlock_btopt_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_btopt_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], const void* src, size_t srcSize) -{ +{ return ZSTD_compressBlock_opt0(ms, seqStore, rep, src, srcSize, ZSTD_extDict); -} - -size_t ZSTD_compressBlock_btultra_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +} + +size_t ZSTD_compressBlock_btultra_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], const void* src, size_t srcSize) -{ +{ return ZSTD_compressBlock_opt2(ms, seqStore, rep, src, srcSize, ZSTD_extDict); -} +} /* note : no btultra2 variant for extDict nor dictMatchState, * because btultra2 is not meant to work with dictionaries diff --git a/contrib/libs/zstd/lib/compress/zstd_opt.h b/contrib/libs/zstd/lib/compress/zstd_opt.h index 627255f53d..f7bab711f7 100644 --- a/contrib/libs/zstd/lib/compress/zstd_opt.h +++ b/contrib/libs/zstd/lib/compress/zstd_opt.h @@ -1,30 +1,30 @@ -/* +/* * Copyright (c) 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. + * 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_OPT_H -#define ZSTD_OPT_H +#ifndef ZSTD_OPT_H +#define ZSTD_OPT_H -#if defined (__cplusplus) -extern "C" { -#endif +#if defined (__cplusplus) +extern "C" { +#endif -#include "zstd_compress_internal.h" +#include "zstd_compress_internal.h" /* used in ZSTD_loadDictionaryContent() */ void ZSTD_updateTree(ZSTD_matchState_t* ms, const BYTE* ip, const BYTE* iend); -size_t ZSTD_compressBlock_btopt( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_btopt( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); -size_t ZSTD_compressBlock_btultra( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_btultra( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); size_t ZSTD_compressBlock_btultra2( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], @@ -38,19 +38,19 @@ size_t ZSTD_compressBlock_btultra_dictMatchState( ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); -size_t ZSTD_compressBlock_btopt_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_btopt_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); -size_t ZSTD_compressBlock_btultra_extDict( - ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], +size_t ZSTD_compressBlock_btultra_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], void const* src, size_t srcSize); /* note : no btultra2 variant for extDict nor dictMatchState, * because btultra2 is not meant to work with dictionaries * and is only specific for the first block (no prefix) */ -#if defined (__cplusplus) +#if defined (__cplusplus) } -#endif +#endif -#endif /* ZSTD_OPT_H */ +#endif /* ZSTD_OPT_H */ diff --git a/contrib/libs/zstd/lib/compress/zstdmt_compress.c b/contrib/libs/zstd/lib/compress/zstdmt_compress.c index 6bc14b035e..30cb698dff 100644 --- a/contrib/libs/zstd/lib/compress/zstdmt_compress.c +++ b/contrib/libs/zstd/lib/compress/zstdmt_compress.c @@ -1,163 +1,163 @@ -/* +/* * Copyright (c) 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. - */ - - -/* ====== Compiler specifics ====== */ -#if defined(_MSC_VER) -# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */ -#endif - - + * 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. + */ + + +/* ====== Compiler specifics ====== */ +#if defined(_MSC_VER) +# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */ +#endif + + /* ====== Constants ====== */ #define ZSTDMT_OVERLAPLOG_DEFAULT 0 -/* ====== Dependencies ====== */ +/* ====== Dependencies ====== */ #include "../common/zstd_deps.h" /* ZSTD_memcpy, ZSTD_memset, INT_MAX, UINT_MAX */ #include "../common/mem.h" /* MEM_STATIC */ #include "../common/pool.h" /* threadpool */ #include "../common/threading.h" /* mutex */ -#include "zstd_compress_internal.h" /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */ -#include "zstd_ldm.h" -#include "zstdmt_compress.h" - -/* Guards code to support resizing the SeqPool. - * We will want to resize the SeqPool to save memory in the future. - * Until then, comment the code out since it is unused. - */ -#define ZSTD_RESIZE_SEQPOOL 0 - -/* ====== Debug ====== */ +#include "zstd_compress_internal.h" /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */ +#include "zstd_ldm.h" +#include "zstdmt_compress.h" + +/* Guards code to support resizing the SeqPool. + * We will want to resize the SeqPool to save memory in the future. + * Until then, comment the code out since it is unused. + */ +#define ZSTD_RESIZE_SEQPOOL 0 + +/* ====== Debug ====== */ #if defined(DEBUGLEVEL) && (DEBUGLEVEL>=2) \ && !defined(_MSC_VER) \ && !defined(__MINGW32__) - -# include <stdio.h> -# include <unistd.h> -# include <sys/times.h> - -# define DEBUG_PRINTHEX(l,p,n) { \ - unsigned debug_u; \ - for (debug_u=0; debug_u<(n); debug_u++) \ + +# include <stdio.h> +# include <unistd.h> +# include <sys/times.h> + +# define DEBUG_PRINTHEX(l,p,n) { \ + unsigned debug_u; \ + for (debug_u=0; debug_u<(n); debug_u++) \ RAWLOG(l, "%02X ", ((const unsigned char*)(p))[debug_u]); \ RAWLOG(l, " \n"); \ -} - -static unsigned long long GetCurrentClockTimeMicroseconds(void) -{ - static clock_t _ticksPerSecond = 0; - if (_ticksPerSecond <= 0) _ticksPerSecond = sysconf(_SC_CLK_TCK); - +} + +static unsigned long long GetCurrentClockTimeMicroseconds(void) +{ + static clock_t _ticksPerSecond = 0; + if (_ticksPerSecond <= 0) _ticksPerSecond = sysconf(_SC_CLK_TCK); + { struct tms junk; clock_t newTicks = (clock_t) times(&junk); return ((((unsigned long long)newTicks)*(1000000))/_ticksPerSecond); } } - -#define MUTEX_WAIT_TIME_DLEVEL 6 -#define ZSTD_PTHREAD_MUTEX_LOCK(mutex) { \ + +#define MUTEX_WAIT_TIME_DLEVEL 6 +#define ZSTD_PTHREAD_MUTEX_LOCK(mutex) { \ if (DEBUGLEVEL >= MUTEX_WAIT_TIME_DLEVEL) { \ - unsigned long long const beforeTime = GetCurrentClockTimeMicroseconds(); \ - ZSTD_pthread_mutex_lock(mutex); \ - { unsigned long long const afterTime = GetCurrentClockTimeMicroseconds(); \ - unsigned long long const elapsedTime = (afterTime-beforeTime); \ - if (elapsedTime > 1000) { /* or whatever threshold you like; I'm using 1 millisecond here */ \ - DEBUGLOG(MUTEX_WAIT_TIME_DLEVEL, "Thread took %llu microseconds to acquire mutex %s \n", \ - elapsedTime, #mutex); \ - } } \ - } else { \ - ZSTD_pthread_mutex_lock(mutex); \ - } \ -} - -#else - -# define ZSTD_PTHREAD_MUTEX_LOCK(m) ZSTD_pthread_mutex_lock(m) -# define DEBUG_PRINTHEX(l,p,n) {} - -#endif - - -/* ===== Buffer Pool ===== */ -/* a single Buffer Pool can be invoked from multiple threads in parallel */ - -typedef struct buffer_s { - void* start; - size_t capacity; -} buffer_t; - -static const buffer_t g_nullBuffer = { NULL, 0 }; - -typedef struct ZSTDMT_bufferPool_s { - ZSTD_pthread_mutex_t poolMutex; - size_t bufferSize; - unsigned totalBuffers; - unsigned nbBuffers; - ZSTD_customMem cMem; - buffer_t bTable[1]; /* variable size */ -} ZSTDMT_bufferPool; - + unsigned long long const beforeTime = GetCurrentClockTimeMicroseconds(); \ + ZSTD_pthread_mutex_lock(mutex); \ + { unsigned long long const afterTime = GetCurrentClockTimeMicroseconds(); \ + unsigned long long const elapsedTime = (afterTime-beforeTime); \ + if (elapsedTime > 1000) { /* or whatever threshold you like; I'm using 1 millisecond here */ \ + DEBUGLOG(MUTEX_WAIT_TIME_DLEVEL, "Thread took %llu microseconds to acquire mutex %s \n", \ + elapsedTime, #mutex); \ + } } \ + } else { \ + ZSTD_pthread_mutex_lock(mutex); \ + } \ +} + +#else + +# define ZSTD_PTHREAD_MUTEX_LOCK(m) ZSTD_pthread_mutex_lock(m) +# define DEBUG_PRINTHEX(l,p,n) {} + +#endif + + +/* ===== Buffer Pool ===== */ +/* a single Buffer Pool can be invoked from multiple threads in parallel */ + +typedef struct buffer_s { + void* start; + size_t capacity; +} buffer_t; + +static const buffer_t g_nullBuffer = { NULL, 0 }; + +typedef struct ZSTDMT_bufferPool_s { + ZSTD_pthread_mutex_t poolMutex; + size_t bufferSize; + unsigned totalBuffers; + unsigned nbBuffers; + ZSTD_customMem cMem; + buffer_t bTable[1]; /* variable size */ +} ZSTDMT_bufferPool; + static ZSTDMT_bufferPool* ZSTDMT_createBufferPool(unsigned maxNbBuffers, ZSTD_customMem cMem) -{ +{ ZSTDMT_bufferPool* const bufPool = (ZSTDMT_bufferPool*)ZSTD_customCalloc( - sizeof(ZSTDMT_bufferPool) + (maxNbBuffers-1) * sizeof(buffer_t), cMem); - if (bufPool==NULL) return NULL; - if (ZSTD_pthread_mutex_init(&bufPool->poolMutex, NULL)) { + sizeof(ZSTDMT_bufferPool) + (maxNbBuffers-1) * sizeof(buffer_t), cMem); + if (bufPool==NULL) return NULL; + if (ZSTD_pthread_mutex_init(&bufPool->poolMutex, NULL)) { ZSTD_customFree(bufPool, cMem); - return NULL; - } - bufPool->bufferSize = 64 KB; - bufPool->totalBuffers = maxNbBuffers; - bufPool->nbBuffers = 0; - bufPool->cMem = cMem; - return bufPool; -} - -static void ZSTDMT_freeBufferPool(ZSTDMT_bufferPool* bufPool) -{ - unsigned u; - DEBUGLOG(3, "ZSTDMT_freeBufferPool (address:%08X)", (U32)(size_t)bufPool); - if (!bufPool) return; /* compatibility with free on NULL */ - for (u=0; u<bufPool->totalBuffers; u++) { - DEBUGLOG(4, "free buffer %2u (address:%08X)", u, (U32)(size_t)bufPool->bTable[u].start); + return NULL; + } + bufPool->bufferSize = 64 KB; + bufPool->totalBuffers = maxNbBuffers; + bufPool->nbBuffers = 0; + bufPool->cMem = cMem; + return bufPool; +} + +static void ZSTDMT_freeBufferPool(ZSTDMT_bufferPool* bufPool) +{ + unsigned u; + DEBUGLOG(3, "ZSTDMT_freeBufferPool (address:%08X)", (U32)(size_t)bufPool); + if (!bufPool) return; /* compatibility with free on NULL */ + for (u=0; u<bufPool->totalBuffers; u++) { + DEBUGLOG(4, "free buffer %2u (address:%08X)", u, (U32)(size_t)bufPool->bTable[u].start); ZSTD_customFree(bufPool->bTable[u].start, bufPool->cMem); - } - ZSTD_pthread_mutex_destroy(&bufPool->poolMutex); + } + ZSTD_pthread_mutex_destroy(&bufPool->poolMutex); ZSTD_customFree(bufPool, bufPool->cMem); -} - -/* only works at initialization, not during compression */ -static size_t ZSTDMT_sizeof_bufferPool(ZSTDMT_bufferPool* bufPool) -{ - size_t const poolSize = sizeof(*bufPool) - + (bufPool->totalBuffers - 1) * sizeof(buffer_t); - unsigned u; - size_t totalBufferSize = 0; - ZSTD_pthread_mutex_lock(&bufPool->poolMutex); - for (u=0; u<bufPool->totalBuffers; u++) - totalBufferSize += bufPool->bTable[u].capacity; - ZSTD_pthread_mutex_unlock(&bufPool->poolMutex); - - return poolSize + totalBufferSize; -} - -/* ZSTDMT_setBufferSize() : - * all future buffers provided by this buffer pool will have _at least_ this size - * note : it's better for all buffers to have same size, - * as they become freely interchangeable, reducing malloc/free usages and memory fragmentation */ -static void ZSTDMT_setBufferSize(ZSTDMT_bufferPool* const bufPool, size_t const bSize) -{ - ZSTD_pthread_mutex_lock(&bufPool->poolMutex); - DEBUGLOG(4, "ZSTDMT_setBufferSize: bSize = %u", (U32)bSize); - bufPool->bufferSize = bSize; - ZSTD_pthread_mutex_unlock(&bufPool->poolMutex); -} - +} + +/* only works at initialization, not during compression */ +static size_t ZSTDMT_sizeof_bufferPool(ZSTDMT_bufferPool* bufPool) +{ + size_t const poolSize = sizeof(*bufPool) + + (bufPool->totalBuffers - 1) * sizeof(buffer_t); + unsigned u; + size_t totalBufferSize = 0; + ZSTD_pthread_mutex_lock(&bufPool->poolMutex); + for (u=0; u<bufPool->totalBuffers; u++) + totalBufferSize += bufPool->bTable[u].capacity; + ZSTD_pthread_mutex_unlock(&bufPool->poolMutex); + + return poolSize + totalBufferSize; +} + +/* ZSTDMT_setBufferSize() : + * all future buffers provided by this buffer pool will have _at least_ this size + * note : it's better for all buffers to have same size, + * as they become freely interchangeable, reducing malloc/free usages and memory fragmentation */ +static void ZSTDMT_setBufferSize(ZSTDMT_bufferPool* const bufPool, size_t const bSize) +{ + ZSTD_pthread_mutex_lock(&bufPool->poolMutex); + DEBUGLOG(4, "ZSTDMT_setBufferSize: bSize = %u", (U32)bSize); + bufPool->bufferSize = bSize; + ZSTD_pthread_mutex_unlock(&bufPool->poolMutex); +} + static ZSTDMT_bufferPool* ZSTDMT_expandBufferPool(ZSTDMT_bufferPool* srcBufPool, unsigned maxNbBuffers) { @@ -176,214 +176,214 @@ static ZSTDMT_bufferPool* ZSTDMT_expandBufferPool(ZSTDMT_bufferPool* srcBufPool, } } -/** ZSTDMT_getBuffer() : - * assumption : bufPool must be valid - * @return : a buffer, with start pointer and size - * note: allocation may fail, in this case, start==NULL and size==0 */ -static buffer_t ZSTDMT_getBuffer(ZSTDMT_bufferPool* bufPool) -{ - size_t const bSize = bufPool->bufferSize; - DEBUGLOG(5, "ZSTDMT_getBuffer: bSize = %u", (U32)bufPool->bufferSize); - ZSTD_pthread_mutex_lock(&bufPool->poolMutex); - if (bufPool->nbBuffers) { /* try to use an existing buffer */ - buffer_t const buf = bufPool->bTable[--(bufPool->nbBuffers)]; - size_t const availBufferSize = buf.capacity; - bufPool->bTable[bufPool->nbBuffers] = g_nullBuffer; - if ((availBufferSize >= bSize) & ((availBufferSize>>3) <= bSize)) { - /* large enough, but not too much */ - DEBUGLOG(5, "ZSTDMT_getBuffer: provide buffer %u of size %u", - bufPool->nbBuffers, (U32)buf.capacity); - ZSTD_pthread_mutex_unlock(&bufPool->poolMutex); - return buf; - } - /* size conditions not respected : scratch this buffer, create new one */ - DEBUGLOG(5, "ZSTDMT_getBuffer: existing buffer does not meet size conditions => freeing"); +/** ZSTDMT_getBuffer() : + * assumption : bufPool must be valid + * @return : a buffer, with start pointer and size + * note: allocation may fail, in this case, start==NULL and size==0 */ +static buffer_t ZSTDMT_getBuffer(ZSTDMT_bufferPool* bufPool) +{ + size_t const bSize = bufPool->bufferSize; + DEBUGLOG(5, "ZSTDMT_getBuffer: bSize = %u", (U32)bufPool->bufferSize); + ZSTD_pthread_mutex_lock(&bufPool->poolMutex); + if (bufPool->nbBuffers) { /* try to use an existing buffer */ + buffer_t const buf = bufPool->bTable[--(bufPool->nbBuffers)]; + size_t const availBufferSize = buf.capacity; + bufPool->bTable[bufPool->nbBuffers] = g_nullBuffer; + if ((availBufferSize >= bSize) & ((availBufferSize>>3) <= bSize)) { + /* large enough, but not too much */ + DEBUGLOG(5, "ZSTDMT_getBuffer: provide buffer %u of size %u", + bufPool->nbBuffers, (U32)buf.capacity); + ZSTD_pthread_mutex_unlock(&bufPool->poolMutex); + return buf; + } + /* size conditions not respected : scratch this buffer, create new one */ + DEBUGLOG(5, "ZSTDMT_getBuffer: existing buffer does not meet size conditions => freeing"); ZSTD_customFree(buf.start, bufPool->cMem); - } - ZSTD_pthread_mutex_unlock(&bufPool->poolMutex); - /* create new buffer */ - DEBUGLOG(5, "ZSTDMT_getBuffer: create a new buffer"); - { buffer_t buffer; + } + ZSTD_pthread_mutex_unlock(&bufPool->poolMutex); + /* create new buffer */ + DEBUGLOG(5, "ZSTDMT_getBuffer: create a new buffer"); + { buffer_t buffer; void* const start = ZSTD_customMalloc(bSize, bufPool->cMem); - buffer.start = start; /* note : start can be NULL if malloc fails ! */ - buffer.capacity = (start==NULL) ? 0 : bSize; - if (start==NULL) { - DEBUGLOG(5, "ZSTDMT_getBuffer: buffer allocation failure !!"); - } else { - DEBUGLOG(5, "ZSTDMT_getBuffer: created buffer of size %u", (U32)bSize); - } - return buffer; - } -} - -#if ZSTD_RESIZE_SEQPOOL -/** ZSTDMT_resizeBuffer() : - * assumption : bufPool must be valid - * @return : a buffer that is at least the buffer pool buffer size. - * If a reallocation happens, the data in the input buffer is copied. - */ -static buffer_t ZSTDMT_resizeBuffer(ZSTDMT_bufferPool* bufPool, buffer_t buffer) -{ - size_t const bSize = bufPool->bufferSize; - if (buffer.capacity < bSize) { + buffer.start = start; /* note : start can be NULL if malloc fails ! */ + buffer.capacity = (start==NULL) ? 0 : bSize; + if (start==NULL) { + DEBUGLOG(5, "ZSTDMT_getBuffer: buffer allocation failure !!"); + } else { + DEBUGLOG(5, "ZSTDMT_getBuffer: created buffer of size %u", (U32)bSize); + } + return buffer; + } +} + +#if ZSTD_RESIZE_SEQPOOL +/** ZSTDMT_resizeBuffer() : + * assumption : bufPool must be valid + * @return : a buffer that is at least the buffer pool buffer size. + * If a reallocation happens, the data in the input buffer is copied. + */ +static buffer_t ZSTDMT_resizeBuffer(ZSTDMT_bufferPool* bufPool, buffer_t buffer) +{ + size_t const bSize = bufPool->bufferSize; + if (buffer.capacity < bSize) { void* const start = ZSTD_customMalloc(bSize, bufPool->cMem); - buffer_t newBuffer; - newBuffer.start = start; - newBuffer.capacity = start == NULL ? 0 : bSize; - if (start != NULL) { - assert(newBuffer.capacity >= buffer.capacity); + buffer_t newBuffer; + newBuffer.start = start; + newBuffer.capacity = start == NULL ? 0 : bSize; + if (start != NULL) { + assert(newBuffer.capacity >= buffer.capacity); ZSTD_memcpy(newBuffer.start, buffer.start, buffer.capacity); - DEBUGLOG(5, "ZSTDMT_resizeBuffer: created buffer of size %u", (U32)bSize); - return newBuffer; - } - DEBUGLOG(5, "ZSTDMT_resizeBuffer: buffer allocation failure !!"); - } - return buffer; -} -#endif - -/* store buffer for later re-use, up to pool capacity */ -static void ZSTDMT_releaseBuffer(ZSTDMT_bufferPool* bufPool, buffer_t buf) -{ + DEBUGLOG(5, "ZSTDMT_resizeBuffer: created buffer of size %u", (U32)bSize); + return newBuffer; + } + DEBUGLOG(5, "ZSTDMT_resizeBuffer: buffer allocation failure !!"); + } + return buffer; +} +#endif + +/* store buffer for later re-use, up to pool capacity */ +static void ZSTDMT_releaseBuffer(ZSTDMT_bufferPool* bufPool, buffer_t buf) +{ DEBUGLOG(5, "ZSTDMT_releaseBuffer"); - if (buf.start == NULL) return; /* compatible with release on NULL */ - ZSTD_pthread_mutex_lock(&bufPool->poolMutex); - if (bufPool->nbBuffers < bufPool->totalBuffers) { - bufPool->bTable[bufPool->nbBuffers++] = buf; /* stored for later use */ - DEBUGLOG(5, "ZSTDMT_releaseBuffer: stored buffer of size %u in slot %u", - (U32)buf.capacity, (U32)(bufPool->nbBuffers-1)); - ZSTD_pthread_mutex_unlock(&bufPool->poolMutex); - return; - } - ZSTD_pthread_mutex_unlock(&bufPool->poolMutex); - /* Reached bufferPool capacity (should not happen) */ - DEBUGLOG(5, "ZSTDMT_releaseBuffer: pool capacity reached => freeing "); + if (buf.start == NULL) return; /* compatible with release on NULL */ + ZSTD_pthread_mutex_lock(&bufPool->poolMutex); + if (bufPool->nbBuffers < bufPool->totalBuffers) { + bufPool->bTable[bufPool->nbBuffers++] = buf; /* stored for later use */ + DEBUGLOG(5, "ZSTDMT_releaseBuffer: stored buffer of size %u in slot %u", + (U32)buf.capacity, (U32)(bufPool->nbBuffers-1)); + ZSTD_pthread_mutex_unlock(&bufPool->poolMutex); + return; + } + ZSTD_pthread_mutex_unlock(&bufPool->poolMutex); + /* Reached bufferPool capacity (should not happen) */ + DEBUGLOG(5, "ZSTDMT_releaseBuffer: pool capacity reached => freeing "); ZSTD_customFree(buf.start, bufPool->cMem); -} - +} + /* We need 2 output buffers per worker since each dstBuff must be flushed after it is released. * The 3 additional buffers are as follows: * 1 buffer for input loading * 1 buffer for "next input" when submitting current one * 1 buffer stuck in queue */ #define BUF_POOL_MAX_NB_BUFFERS(nbWorkers) 2*nbWorkers + 3 - + /* After a worker releases its rawSeqStore, it is immediately ready for reuse. * So we only need one seq buffer per worker. */ #define SEQ_POOL_MAX_NB_BUFFERS(nbWorkers) nbWorkers -/* ===== Seq Pool Wrapper ====== */ - -typedef ZSTDMT_bufferPool ZSTDMT_seqPool; - -static size_t ZSTDMT_sizeof_seqPool(ZSTDMT_seqPool* seqPool) -{ - return ZSTDMT_sizeof_bufferPool(seqPool); -} - -static rawSeqStore_t bufferToSeq(buffer_t buffer) -{ +/* ===== Seq Pool Wrapper ====== */ + +typedef ZSTDMT_bufferPool ZSTDMT_seqPool; + +static size_t ZSTDMT_sizeof_seqPool(ZSTDMT_seqPool* seqPool) +{ + return ZSTDMT_sizeof_bufferPool(seqPool); +} + +static rawSeqStore_t bufferToSeq(buffer_t buffer) +{ rawSeqStore_t seq = kNullRawSeqStore; - seq.seq = (rawSeq*)buffer.start; - seq.capacity = buffer.capacity / sizeof(rawSeq); - return seq; -} - -static buffer_t seqToBuffer(rawSeqStore_t seq) -{ - buffer_t buffer; - buffer.start = seq.seq; - buffer.capacity = seq.capacity * sizeof(rawSeq); - return buffer; -} - -static rawSeqStore_t ZSTDMT_getSeq(ZSTDMT_seqPool* seqPool) -{ - if (seqPool->bufferSize == 0) { - return kNullRawSeqStore; - } - return bufferToSeq(ZSTDMT_getBuffer(seqPool)); -} - -#if ZSTD_RESIZE_SEQPOOL -static rawSeqStore_t ZSTDMT_resizeSeq(ZSTDMT_seqPool* seqPool, rawSeqStore_t seq) -{ - return bufferToSeq(ZSTDMT_resizeBuffer(seqPool, seqToBuffer(seq))); -} -#endif - -static void ZSTDMT_releaseSeq(ZSTDMT_seqPool* seqPool, rawSeqStore_t seq) -{ - ZSTDMT_releaseBuffer(seqPool, seqToBuffer(seq)); -} - -static void ZSTDMT_setNbSeq(ZSTDMT_seqPool* const seqPool, size_t const nbSeq) -{ - ZSTDMT_setBufferSize(seqPool, nbSeq * sizeof(rawSeq)); -} - -static ZSTDMT_seqPool* ZSTDMT_createSeqPool(unsigned nbWorkers, ZSTD_customMem cMem) -{ + seq.seq = (rawSeq*)buffer.start; + seq.capacity = buffer.capacity / sizeof(rawSeq); + return seq; +} + +static buffer_t seqToBuffer(rawSeqStore_t seq) +{ + buffer_t buffer; + buffer.start = seq.seq; + buffer.capacity = seq.capacity * sizeof(rawSeq); + return buffer; +} + +static rawSeqStore_t ZSTDMT_getSeq(ZSTDMT_seqPool* seqPool) +{ + if (seqPool->bufferSize == 0) { + return kNullRawSeqStore; + } + return bufferToSeq(ZSTDMT_getBuffer(seqPool)); +} + +#if ZSTD_RESIZE_SEQPOOL +static rawSeqStore_t ZSTDMT_resizeSeq(ZSTDMT_seqPool* seqPool, rawSeqStore_t seq) +{ + return bufferToSeq(ZSTDMT_resizeBuffer(seqPool, seqToBuffer(seq))); +} +#endif + +static void ZSTDMT_releaseSeq(ZSTDMT_seqPool* seqPool, rawSeqStore_t seq) +{ + ZSTDMT_releaseBuffer(seqPool, seqToBuffer(seq)); +} + +static void ZSTDMT_setNbSeq(ZSTDMT_seqPool* const seqPool, size_t const nbSeq) +{ + ZSTDMT_setBufferSize(seqPool, nbSeq * sizeof(rawSeq)); +} + +static ZSTDMT_seqPool* ZSTDMT_createSeqPool(unsigned nbWorkers, ZSTD_customMem cMem) +{ ZSTDMT_seqPool* const seqPool = ZSTDMT_createBufferPool(SEQ_POOL_MAX_NB_BUFFERS(nbWorkers), cMem); if (seqPool == NULL) return NULL; - ZSTDMT_setNbSeq(seqPool, 0); - return seqPool; -} - -static void ZSTDMT_freeSeqPool(ZSTDMT_seqPool* seqPool) -{ - ZSTDMT_freeBufferPool(seqPool); -} - + ZSTDMT_setNbSeq(seqPool, 0); + return seqPool; +} + +static void ZSTDMT_freeSeqPool(ZSTDMT_seqPool* seqPool) +{ + ZSTDMT_freeBufferPool(seqPool); +} + static ZSTDMT_seqPool* ZSTDMT_expandSeqPool(ZSTDMT_seqPool* pool, U32 nbWorkers) { return ZSTDMT_expandBufferPool(pool, SEQ_POOL_MAX_NB_BUFFERS(nbWorkers)); } - - -/* ===== CCtx Pool ===== */ -/* a single CCtx Pool can be invoked from multiple threads in parallel */ - -typedef struct { - ZSTD_pthread_mutex_t poolMutex; + + +/* ===== CCtx Pool ===== */ +/* a single CCtx Pool can be invoked from multiple threads in parallel */ + +typedef struct { + ZSTD_pthread_mutex_t poolMutex; int totalCCtx; int availCCtx; - ZSTD_customMem cMem; - ZSTD_CCtx* cctx[1]; /* variable size */ -} ZSTDMT_CCtxPool; - -/* note : all CCtx borrowed from the pool should be released back to the pool _before_ freeing the pool */ -static void ZSTDMT_freeCCtxPool(ZSTDMT_CCtxPool* pool) -{ + ZSTD_customMem cMem; + ZSTD_CCtx* cctx[1]; /* variable size */ +} ZSTDMT_CCtxPool; + +/* note : all CCtx borrowed from the pool should be released back to the pool _before_ freeing the pool */ +static void ZSTDMT_freeCCtxPool(ZSTDMT_CCtxPool* pool) +{ int cid; for (cid=0; cid<pool->totalCCtx; cid++) ZSTD_freeCCtx(pool->cctx[cid]); /* note : compatible with free on NULL */ - ZSTD_pthread_mutex_destroy(&pool->poolMutex); + ZSTD_pthread_mutex_destroy(&pool->poolMutex); ZSTD_customFree(pool, pool->cMem); -} - -/* ZSTDMT_createCCtxPool() : - * implies nbWorkers >= 1 , checked by caller ZSTDMT_createCCtx() */ +} + +/* ZSTDMT_createCCtxPool() : + * implies nbWorkers >= 1 , checked by caller ZSTDMT_createCCtx() */ static ZSTDMT_CCtxPool* ZSTDMT_createCCtxPool(int nbWorkers, - ZSTD_customMem cMem) -{ + ZSTD_customMem cMem) +{ ZSTDMT_CCtxPool* const cctxPool = (ZSTDMT_CCtxPool*) ZSTD_customCalloc( - sizeof(ZSTDMT_CCtxPool) + (nbWorkers-1)*sizeof(ZSTD_CCtx*), cMem); - assert(nbWorkers > 0); - if (!cctxPool) return NULL; - if (ZSTD_pthread_mutex_init(&cctxPool->poolMutex, NULL)) { + sizeof(ZSTDMT_CCtxPool) + (nbWorkers-1)*sizeof(ZSTD_CCtx*), cMem); + assert(nbWorkers > 0); + if (!cctxPool) return NULL; + if (ZSTD_pthread_mutex_init(&cctxPool->poolMutex, NULL)) { ZSTD_customFree(cctxPool, cMem); - return NULL; - } - cctxPool->cMem = cMem; - cctxPool->totalCCtx = nbWorkers; - cctxPool->availCCtx = 1; /* at least one cctx for single-thread mode */ - cctxPool->cctx[0] = ZSTD_createCCtx_advanced(cMem); - if (!cctxPool->cctx[0]) { ZSTDMT_freeCCtxPool(cctxPool); return NULL; } - DEBUGLOG(3, "cctxPool created, with %u workers", nbWorkers); - return cctxPool; -} - + return NULL; + } + cctxPool->cMem = cMem; + cctxPool->totalCCtx = nbWorkers; + cctxPool->availCCtx = 1; /* at least one cctx for single-thread mode */ + cctxPool->cctx[0] = ZSTD_createCCtx_advanced(cMem); + if (!cctxPool->cctx[0]) { ZSTDMT_freeCCtxPool(cctxPool); return NULL; } + DEBUGLOG(3, "cctxPool created, with %u workers", nbWorkers); + return cctxPool; +} + static ZSTDMT_CCtxPool* ZSTDMT_expandCCtxPool(ZSTDMT_CCtxPool* srcPool, int nbWorkers) { @@ -396,76 +396,76 @@ static ZSTDMT_CCtxPool* ZSTDMT_expandCCtxPool(ZSTDMT_CCtxPool* srcPool, } } -/* only works during initialization phase, not during compression */ -static size_t ZSTDMT_sizeof_CCtxPool(ZSTDMT_CCtxPool* cctxPool) -{ - ZSTD_pthread_mutex_lock(&cctxPool->poolMutex); - { unsigned const nbWorkers = cctxPool->totalCCtx; - size_t const poolSize = sizeof(*cctxPool) - + (nbWorkers-1) * sizeof(ZSTD_CCtx*); - unsigned u; - size_t totalCCtxSize = 0; - for (u=0; u<nbWorkers; u++) { - totalCCtxSize += ZSTD_sizeof_CCtx(cctxPool->cctx[u]); - } - ZSTD_pthread_mutex_unlock(&cctxPool->poolMutex); - assert(nbWorkers > 0); - return poolSize + totalCCtxSize; - } -} - -static ZSTD_CCtx* ZSTDMT_getCCtx(ZSTDMT_CCtxPool* cctxPool) -{ - DEBUGLOG(5, "ZSTDMT_getCCtx"); - ZSTD_pthread_mutex_lock(&cctxPool->poolMutex); - if (cctxPool->availCCtx) { - cctxPool->availCCtx--; - { ZSTD_CCtx* const cctx = cctxPool->cctx[cctxPool->availCCtx]; - ZSTD_pthread_mutex_unlock(&cctxPool->poolMutex); - return cctx; - } } - ZSTD_pthread_mutex_unlock(&cctxPool->poolMutex); - DEBUGLOG(5, "create one more CCtx"); - return ZSTD_createCCtx_advanced(cctxPool->cMem); /* note : can be NULL, when creation fails ! */ -} - -static void ZSTDMT_releaseCCtx(ZSTDMT_CCtxPool* pool, ZSTD_CCtx* cctx) -{ - if (cctx==NULL) return; /* compatibility with release on NULL */ - ZSTD_pthread_mutex_lock(&pool->poolMutex); - if (pool->availCCtx < pool->totalCCtx) - pool->cctx[pool->availCCtx++] = cctx; - else { - /* pool overflow : should not happen, since totalCCtx==nbWorkers */ - DEBUGLOG(4, "CCtx pool overflow : free cctx"); - ZSTD_freeCCtx(cctx); - } - ZSTD_pthread_mutex_unlock(&pool->poolMutex); -} - -/* ==== Serial State ==== */ - -typedef struct { - void const* start; - size_t size; -} range_t; - -typedef struct { - /* All variables in the struct are protected by mutex. */ - ZSTD_pthread_mutex_t mutex; - ZSTD_pthread_cond_t cond; - ZSTD_CCtx_params params; - ldmState_t ldmState; - XXH64_state_t xxhState; - unsigned nextJobID; - /* Protects ldmWindow. - * Must be acquired after the main mutex when acquiring both. - */ - ZSTD_pthread_mutex_t ldmWindowMutex; +/* only works during initialization phase, not during compression */ +static size_t ZSTDMT_sizeof_CCtxPool(ZSTDMT_CCtxPool* cctxPool) +{ + ZSTD_pthread_mutex_lock(&cctxPool->poolMutex); + { unsigned const nbWorkers = cctxPool->totalCCtx; + size_t const poolSize = sizeof(*cctxPool) + + (nbWorkers-1) * sizeof(ZSTD_CCtx*); + unsigned u; + size_t totalCCtxSize = 0; + for (u=0; u<nbWorkers; u++) { + totalCCtxSize += ZSTD_sizeof_CCtx(cctxPool->cctx[u]); + } + ZSTD_pthread_mutex_unlock(&cctxPool->poolMutex); + assert(nbWorkers > 0); + return poolSize + totalCCtxSize; + } +} + +static ZSTD_CCtx* ZSTDMT_getCCtx(ZSTDMT_CCtxPool* cctxPool) +{ + DEBUGLOG(5, "ZSTDMT_getCCtx"); + ZSTD_pthread_mutex_lock(&cctxPool->poolMutex); + if (cctxPool->availCCtx) { + cctxPool->availCCtx--; + { ZSTD_CCtx* const cctx = cctxPool->cctx[cctxPool->availCCtx]; + ZSTD_pthread_mutex_unlock(&cctxPool->poolMutex); + return cctx; + } } + ZSTD_pthread_mutex_unlock(&cctxPool->poolMutex); + DEBUGLOG(5, "create one more CCtx"); + return ZSTD_createCCtx_advanced(cctxPool->cMem); /* note : can be NULL, when creation fails ! */ +} + +static void ZSTDMT_releaseCCtx(ZSTDMT_CCtxPool* pool, ZSTD_CCtx* cctx) +{ + if (cctx==NULL) return; /* compatibility with release on NULL */ + ZSTD_pthread_mutex_lock(&pool->poolMutex); + if (pool->availCCtx < pool->totalCCtx) + pool->cctx[pool->availCCtx++] = cctx; + else { + /* pool overflow : should not happen, since totalCCtx==nbWorkers */ + DEBUGLOG(4, "CCtx pool overflow : free cctx"); + ZSTD_freeCCtx(cctx); + } + ZSTD_pthread_mutex_unlock(&pool->poolMutex); +} + +/* ==== Serial State ==== */ + +typedef struct { + void const* start; + size_t size; +} range_t; + +typedef struct { + /* All variables in the struct are protected by mutex. */ + ZSTD_pthread_mutex_t mutex; + ZSTD_pthread_cond_t cond; + ZSTD_CCtx_params params; + ldmState_t ldmState; + XXH64_state_t xxhState; + unsigned nextJobID; + /* Protects ldmWindow. + * Must be acquired after the main mutex when acquiring both. + */ + ZSTD_pthread_mutex_t ldmWindowMutex; ZSTD_pthread_cond_t ldmWindowCond; /* Signaled when ldmWindow is updated */ - ZSTD_window_t ldmWindow; /* A thread-safe copy of ldmState.window */ -} serialState_t; - + ZSTD_window_t ldmWindow; /* A thread-safe copy of ldmState.window */ +} serialState_t; + static int ZSTDMT_serialState_reset(serialState_t* serialState, ZSTDMT_seqPool* seqPool, @@ -473,45 +473,45 @@ ZSTDMT_serialState_reset(serialState_t* serialState, size_t jobSize, const void* dict, size_t const dictSize, ZSTD_dictContentType_e dictContentType) -{ - /* Adjust parameters */ +{ + /* Adjust parameters */ if (params.ldmParams.enableLdm == ZSTD_ps_enable) { - DEBUGLOG(4, "LDM window size = %u KB", (1U << params.cParams.windowLog) >> 10); - ZSTD_ldm_adjustParameters(¶ms.ldmParams, ¶ms.cParams); - assert(params.ldmParams.hashLog >= params.ldmParams.bucketSizeLog); + DEBUGLOG(4, "LDM window size = %u KB", (1U << params.cParams.windowLog) >> 10); + ZSTD_ldm_adjustParameters(¶ms.ldmParams, ¶ms.cParams); + assert(params.ldmParams.hashLog >= params.ldmParams.bucketSizeLog); assert(params.ldmParams.hashRateLog < 32); - } else { + } else { ZSTD_memset(¶ms.ldmParams, 0, sizeof(params.ldmParams)); - } - serialState->nextJobID = 0; - if (params.fParams.checksumFlag) - XXH64_reset(&serialState->xxhState, 0); + } + serialState->nextJobID = 0; + if (params.fParams.checksumFlag) + XXH64_reset(&serialState->xxhState, 0); if (params.ldmParams.enableLdm == ZSTD_ps_enable) { - ZSTD_customMem cMem = params.customMem; - unsigned const hashLog = params.ldmParams.hashLog; - size_t const hashSize = ((size_t)1 << hashLog) * sizeof(ldmEntry_t); - unsigned const bucketLog = - params.ldmParams.hashLog - params.ldmParams.bucketSizeLog; - unsigned const prevBucketLog = - serialState->params.ldmParams.hashLog - - serialState->params.ldmParams.bucketSizeLog; + ZSTD_customMem cMem = params.customMem; + unsigned const hashLog = params.ldmParams.hashLog; + size_t const hashSize = ((size_t)1 << hashLog) * sizeof(ldmEntry_t); + unsigned const bucketLog = + params.ldmParams.hashLog - params.ldmParams.bucketSizeLog; + unsigned const prevBucketLog = + serialState->params.ldmParams.hashLog - + serialState->params.ldmParams.bucketSizeLog; size_t const numBuckets = (size_t)1 << bucketLog; - /* Size the seq pool tables */ + /* Size the seq pool tables */ ZSTDMT_setNbSeq(seqPool, ZSTD_ldm_getMaxNbSeq(params.ldmParams, jobSize)); - /* Reset the window */ + /* Reset the window */ ZSTD_window_init(&serialState->ldmState.window); - /* Resize tables and output space if necessary. */ - if (serialState->ldmState.hashTable == NULL || serialState->params.ldmParams.hashLog < hashLog) { + /* Resize tables and output space if necessary. */ + if (serialState->ldmState.hashTable == NULL || serialState->params.ldmParams.hashLog < hashLog) { ZSTD_customFree(serialState->ldmState.hashTable, cMem); serialState->ldmState.hashTable = (ldmEntry_t*)ZSTD_customMalloc(hashSize, cMem); - } - if (serialState->ldmState.bucketOffsets == NULL || prevBucketLog < bucketLog) { + } + if (serialState->ldmState.bucketOffsets == NULL || prevBucketLog < bucketLog) { ZSTD_customFree(serialState->ldmState.bucketOffsets, cMem); serialState->ldmState.bucketOffsets = (BYTE*)ZSTD_customMalloc(numBuckets, cMem); - } - if (!serialState->ldmState.hashTable || !serialState->ldmState.bucketOffsets) - return 1; - /* Zero the tables */ + } + if (!serialState->ldmState.hashTable || !serialState->ldmState.bucketOffsets) + return 1; + /* Zero the tables */ ZSTD_memset(serialState->ldmState.hashTable, 0, hashSize); ZSTD_memset(serialState->ldmState.bucketOffsets, 0, numBuckets); @@ -530,132 +530,132 @@ ZSTDMT_serialState_reset(serialState_t* serialState, /* Initialize serialState's copy of ldmWindow. */ serialState->ldmWindow = serialState->ldmState.window; - } + } - serialState->params = params; + serialState->params = params; serialState->params.jobSize = (U32)jobSize; - return 0; -} - -static int ZSTDMT_serialState_init(serialState_t* serialState) -{ - int initError = 0; + return 0; +} + +static int ZSTDMT_serialState_init(serialState_t* serialState) +{ + int initError = 0; ZSTD_memset(serialState, 0, sizeof(*serialState)); - initError |= ZSTD_pthread_mutex_init(&serialState->mutex, NULL); - initError |= ZSTD_pthread_cond_init(&serialState->cond, NULL); - initError |= ZSTD_pthread_mutex_init(&serialState->ldmWindowMutex, NULL); - initError |= ZSTD_pthread_cond_init(&serialState->ldmWindowCond, NULL); - return initError; -} - -static void ZSTDMT_serialState_free(serialState_t* serialState) -{ - ZSTD_customMem cMem = serialState->params.customMem; - ZSTD_pthread_mutex_destroy(&serialState->mutex); - ZSTD_pthread_cond_destroy(&serialState->cond); - ZSTD_pthread_mutex_destroy(&serialState->ldmWindowMutex); - ZSTD_pthread_cond_destroy(&serialState->ldmWindowCond); + initError |= ZSTD_pthread_mutex_init(&serialState->mutex, NULL); + initError |= ZSTD_pthread_cond_init(&serialState->cond, NULL); + initError |= ZSTD_pthread_mutex_init(&serialState->ldmWindowMutex, NULL); + initError |= ZSTD_pthread_cond_init(&serialState->ldmWindowCond, NULL); + return initError; +} + +static void ZSTDMT_serialState_free(serialState_t* serialState) +{ + ZSTD_customMem cMem = serialState->params.customMem; + ZSTD_pthread_mutex_destroy(&serialState->mutex); + ZSTD_pthread_cond_destroy(&serialState->cond); + ZSTD_pthread_mutex_destroy(&serialState->ldmWindowMutex); + ZSTD_pthread_cond_destroy(&serialState->ldmWindowCond); ZSTD_customFree(serialState->ldmState.hashTable, cMem); ZSTD_customFree(serialState->ldmState.bucketOffsets, cMem); -} - -static void ZSTDMT_serialState_update(serialState_t* serialState, - ZSTD_CCtx* jobCCtx, rawSeqStore_t seqStore, - range_t src, unsigned jobID) -{ - /* Wait for our turn */ - ZSTD_PTHREAD_MUTEX_LOCK(&serialState->mutex); - while (serialState->nextJobID < jobID) { +} + +static void ZSTDMT_serialState_update(serialState_t* serialState, + ZSTD_CCtx* jobCCtx, rawSeqStore_t seqStore, + range_t src, unsigned jobID) +{ + /* Wait for our turn */ + ZSTD_PTHREAD_MUTEX_LOCK(&serialState->mutex); + while (serialState->nextJobID < jobID) { DEBUGLOG(5, "wait for serialState->cond"); - ZSTD_pthread_cond_wait(&serialState->cond, &serialState->mutex); - } - /* A future job may error and skip our job */ - if (serialState->nextJobID == jobID) { - /* It is now our turn, do any processing necessary */ + ZSTD_pthread_cond_wait(&serialState->cond, &serialState->mutex); + } + /* A future job may error and skip our job */ + if (serialState->nextJobID == jobID) { + /* It is now our turn, do any processing necessary */ if (serialState->params.ldmParams.enableLdm == ZSTD_ps_enable) { - size_t error; - assert(seqStore.seq != NULL && seqStore.pos == 0 && - seqStore.size == 0 && seqStore.capacity > 0); + size_t error; + assert(seqStore.seq != NULL && seqStore.pos == 0 && + seqStore.size == 0 && seqStore.capacity > 0); assert(src.size <= serialState->params.jobSize); ZSTD_window_update(&serialState->ldmState.window, src.start, src.size, /* forceNonContiguous */ 0); - error = ZSTD_ldm_generateSequences( - &serialState->ldmState, &seqStore, - &serialState->params.ldmParams, src.start, src.size); - /* We provide a large enough buffer to never fail. */ - assert(!ZSTD_isError(error)); (void)error; - /* Update ldmWindow to match the ldmState.window and signal the main - * thread if it is waiting for a buffer. - */ - ZSTD_PTHREAD_MUTEX_LOCK(&serialState->ldmWindowMutex); - serialState->ldmWindow = serialState->ldmState.window; - ZSTD_pthread_cond_signal(&serialState->ldmWindowCond); - ZSTD_pthread_mutex_unlock(&serialState->ldmWindowMutex); - } - if (serialState->params.fParams.checksumFlag && src.size > 0) - XXH64_update(&serialState->xxhState, src.start, src.size); - } - /* Now it is the next jobs turn */ - serialState->nextJobID++; - ZSTD_pthread_cond_broadcast(&serialState->cond); - ZSTD_pthread_mutex_unlock(&serialState->mutex); - - if (seqStore.size > 0) { - size_t const err = ZSTD_referenceExternalSequences( - jobCCtx, seqStore.seq, seqStore.size); + error = ZSTD_ldm_generateSequences( + &serialState->ldmState, &seqStore, + &serialState->params.ldmParams, src.start, src.size); + /* We provide a large enough buffer to never fail. */ + assert(!ZSTD_isError(error)); (void)error; + /* Update ldmWindow to match the ldmState.window and signal the main + * thread if it is waiting for a buffer. + */ + ZSTD_PTHREAD_MUTEX_LOCK(&serialState->ldmWindowMutex); + serialState->ldmWindow = serialState->ldmState.window; + ZSTD_pthread_cond_signal(&serialState->ldmWindowCond); + ZSTD_pthread_mutex_unlock(&serialState->ldmWindowMutex); + } + if (serialState->params.fParams.checksumFlag && src.size > 0) + XXH64_update(&serialState->xxhState, src.start, src.size); + } + /* Now it is the next jobs turn */ + serialState->nextJobID++; + ZSTD_pthread_cond_broadcast(&serialState->cond); + ZSTD_pthread_mutex_unlock(&serialState->mutex); + + if (seqStore.size > 0) { + size_t const err = ZSTD_referenceExternalSequences( + jobCCtx, seqStore.seq, seqStore.size); assert(serialState->params.ldmParams.enableLdm == ZSTD_ps_enable); - assert(!ZSTD_isError(err)); - (void)err; - } -} - -static void ZSTDMT_serialState_ensureFinished(serialState_t* serialState, - unsigned jobID, size_t cSize) -{ - ZSTD_PTHREAD_MUTEX_LOCK(&serialState->mutex); - if (serialState->nextJobID <= jobID) { - assert(ZSTD_isError(cSize)); (void)cSize; - DEBUGLOG(5, "Skipping past job %u because of error", jobID); - serialState->nextJobID = jobID + 1; - ZSTD_pthread_cond_broadcast(&serialState->cond); - - ZSTD_PTHREAD_MUTEX_LOCK(&serialState->ldmWindowMutex); - ZSTD_window_clear(&serialState->ldmWindow); - ZSTD_pthread_cond_signal(&serialState->ldmWindowCond); - ZSTD_pthread_mutex_unlock(&serialState->ldmWindowMutex); - } - ZSTD_pthread_mutex_unlock(&serialState->mutex); - -} - - -/* ------------------------------------------ */ -/* ===== Worker thread ===== */ -/* ------------------------------------------ */ - -static const range_t kNullRange = { NULL, 0 }; - -typedef struct { - size_t consumed; /* SHARED - set0 by mtctx, then modified by worker AND read by mtctx */ - size_t cSize; /* SHARED - set0 by mtctx, then modified by worker AND read by mtctx, then set0 by mtctx */ - ZSTD_pthread_mutex_t job_mutex; /* Thread-safe - used by mtctx and worker */ - ZSTD_pthread_cond_t job_cond; /* Thread-safe - used by mtctx and worker */ - ZSTDMT_CCtxPool* cctxPool; /* Thread-safe - used by mtctx and (all) workers */ - ZSTDMT_bufferPool* bufPool; /* Thread-safe - used by mtctx and (all) workers */ - ZSTDMT_seqPool* seqPool; /* Thread-safe - used by mtctx and (all) workers */ - serialState_t* serial; /* Thread-safe - used by mtctx and (all) workers */ - buffer_t dstBuff; /* set by worker (or mtctx), then read by worker & mtctx, then modified by mtctx => no barrier */ - range_t prefix; /* set by mtctx, then read by worker & mtctx => no barrier */ - range_t src; /* set by mtctx, then read by worker & mtctx => no barrier */ - unsigned jobID; /* set by mtctx, then read by worker => no barrier */ - unsigned firstJob; /* set by mtctx, then read by worker => no barrier */ - unsigned lastJob; /* set by mtctx, then read by worker => no barrier */ - ZSTD_CCtx_params params; /* set by mtctx, then read by worker => no barrier */ - const ZSTD_CDict* cdict; /* set by mtctx, then read by worker => no barrier */ - unsigned long long fullFrameSize; /* set by mtctx, then read by worker => no barrier */ - size_t dstFlushed; /* used only by mtctx */ - unsigned frameChecksumNeeded; /* used only by mtctx */ -} ZSTDMT_jobDescription; - + assert(!ZSTD_isError(err)); + (void)err; + } +} + +static void ZSTDMT_serialState_ensureFinished(serialState_t* serialState, + unsigned jobID, size_t cSize) +{ + ZSTD_PTHREAD_MUTEX_LOCK(&serialState->mutex); + if (serialState->nextJobID <= jobID) { + assert(ZSTD_isError(cSize)); (void)cSize; + DEBUGLOG(5, "Skipping past job %u because of error", jobID); + serialState->nextJobID = jobID + 1; + ZSTD_pthread_cond_broadcast(&serialState->cond); + + ZSTD_PTHREAD_MUTEX_LOCK(&serialState->ldmWindowMutex); + ZSTD_window_clear(&serialState->ldmWindow); + ZSTD_pthread_cond_signal(&serialState->ldmWindowCond); + ZSTD_pthread_mutex_unlock(&serialState->ldmWindowMutex); + } + ZSTD_pthread_mutex_unlock(&serialState->mutex); + +} + + +/* ------------------------------------------ */ +/* ===== Worker thread ===== */ +/* ------------------------------------------ */ + +static const range_t kNullRange = { NULL, 0 }; + +typedef struct { + size_t consumed; /* SHARED - set0 by mtctx, then modified by worker AND read by mtctx */ + size_t cSize; /* SHARED - set0 by mtctx, then modified by worker AND read by mtctx, then set0 by mtctx */ + ZSTD_pthread_mutex_t job_mutex; /* Thread-safe - used by mtctx and worker */ + ZSTD_pthread_cond_t job_cond; /* Thread-safe - used by mtctx and worker */ + ZSTDMT_CCtxPool* cctxPool; /* Thread-safe - used by mtctx and (all) workers */ + ZSTDMT_bufferPool* bufPool; /* Thread-safe - used by mtctx and (all) workers */ + ZSTDMT_seqPool* seqPool; /* Thread-safe - used by mtctx and (all) workers */ + serialState_t* serial; /* Thread-safe - used by mtctx and (all) workers */ + buffer_t dstBuff; /* set by worker (or mtctx), then read by worker & mtctx, then modified by mtctx => no barrier */ + range_t prefix; /* set by mtctx, then read by worker & mtctx => no barrier */ + range_t src; /* set by mtctx, then read by worker & mtctx => no barrier */ + unsigned jobID; /* set by mtctx, then read by worker => no barrier */ + unsigned firstJob; /* set by mtctx, then read by worker => no barrier */ + unsigned lastJob; /* set by mtctx, then read by worker => no barrier */ + ZSTD_CCtx_params params; /* set by mtctx, then read by worker => no barrier */ + const ZSTD_CDict* cdict; /* set by mtctx, then read by worker => no barrier */ + unsigned long long fullFrameSize; /* set by mtctx, then read by worker => no barrier */ + size_t dstFlushed; /* used only by mtctx */ + unsigned frameChecksumNeeded; /* used only by mtctx */ +} ZSTDMT_jobDescription; + #define JOB_ERROR(e) { \ ZSTD_PTHREAD_MUTEX_LOCK(&job->job_mutex); \ job->cSize = e; \ @@ -663,16 +663,16 @@ typedef struct { goto _endJob; \ } -/* ZSTDMT_compressionJob() is a POOL_function type */ +/* ZSTDMT_compressionJob() is a POOL_function type */ static void ZSTDMT_compressionJob(void* jobDescription) -{ - ZSTDMT_jobDescription* const job = (ZSTDMT_jobDescription*)jobDescription; - ZSTD_CCtx_params jobParams = job->params; /* do not modify job->params ! copy it, modify the copy */ - ZSTD_CCtx* const cctx = ZSTDMT_getCCtx(job->cctxPool); - rawSeqStore_t rawSeqStore = ZSTDMT_getSeq(job->seqPool); - buffer_t dstBuff = job->dstBuff; +{ + ZSTDMT_jobDescription* const job = (ZSTDMT_jobDescription*)jobDescription; + ZSTD_CCtx_params jobParams = job->params; /* do not modify job->params ! copy it, modify the copy */ + ZSTD_CCtx* const cctx = ZSTDMT_getCCtx(job->cctxPool); + rawSeqStore_t rawSeqStore = ZSTDMT_getSeq(job->seqPool); + buffer_t dstBuff = job->dstBuff; size_t lastCBlockSize = 0; - + /* resources */ if (cctx==NULL) JOB_ERROR(ERROR(memory_allocation)); if (dstBuff.start == NULL) { /* streaming job : doesn't provide a dstBuffer */ @@ -683,23 +683,23 @@ static void ZSTDMT_compressionJob(void* jobDescription) if (jobParams.ldmParams.enableLdm == ZSTD_ps_enable && rawSeqStore.seq == NULL) JOB_ERROR(ERROR(memory_allocation)); - /* Don't compute the checksum for chunks, since we compute it externally, - * but write it in the header. - */ - if (job->jobID != 0) jobParams.fParams.checksumFlag = 0; - /* Don't run LDM for the chunks, since we handle it externally */ + /* Don't compute the checksum for chunks, since we compute it externally, + * but write it in the header. + */ + if (job->jobID != 0) jobParams.fParams.checksumFlag = 0; + /* Don't run LDM for the chunks, since we handle it externally */ jobParams.ldmParams.enableLdm = ZSTD_ps_disable; /* Correct nbWorkers to 0. */ jobParams.nbWorkers = 0; - - - /* init */ - if (job->cdict) { + + + /* init */ + if (job->cdict) { size_t const initError = ZSTD_compressBegin_advanced_internal(cctx, NULL, 0, ZSTD_dct_auto, ZSTD_dtlm_fast, job->cdict, &jobParams, job->fullFrameSize); - assert(job->firstJob); /* only allowed for first job */ + assert(job->firstJob); /* only allowed for first job */ if (ZSTD_isError(initError)) JOB_ERROR(initError); - } else { /* srcStart points at reloaded section */ - U64 const pledgedSrcSize = job->firstJob ? job->fullFrameSize : job->src.size; + } else { /* srcStart points at reloaded section */ + U64 const pledgedSrcSize = job->firstJob ? job->fullFrameSize : job->src.size; { size_t const forceWindowError = ZSTD_CCtxParams_setParameter(&jobParams, ZSTD_c_forceMaxWindow, !job->firstJob); if (ZSTD_isError(forceWindowError)) JOB_ERROR(forceWindowError); } @@ -707,61 +707,61 @@ static void ZSTDMT_compressionJob(void* jobDescription) size_t const err = ZSTD_CCtxParams_setParameter(&jobParams, ZSTD_c_deterministicRefPrefix, 0); if (ZSTD_isError(err)) JOB_ERROR(err); } - { size_t const initError = ZSTD_compressBegin_advanced_internal(cctx, - job->prefix.start, job->prefix.size, ZSTD_dct_rawContent, /* load dictionary in "content-only" mode (no header analysis) */ + { size_t const initError = ZSTD_compressBegin_advanced_internal(cctx, + job->prefix.start, job->prefix.size, ZSTD_dct_rawContent, /* load dictionary in "content-only" mode (no header analysis) */ ZSTD_dtlm_fast, - NULL, /*cdict*/ + NULL, /*cdict*/ &jobParams, pledgedSrcSize); if (ZSTD_isError(initError)) JOB_ERROR(initError); } } - - /* Perform serial step as early as possible, but after CCtx initialization */ - ZSTDMT_serialState_update(job->serial, cctx, rawSeqStore, job->src, job->jobID); - - if (!job->firstJob) { /* flush and overwrite frame header when it's not first job */ - size_t const hSize = ZSTD_compressContinue(cctx, dstBuff.start, dstBuff.capacity, job->src.start, 0); + + /* Perform serial step as early as possible, but after CCtx initialization */ + ZSTDMT_serialState_update(job->serial, cctx, rawSeqStore, job->src, job->jobID); + + if (!job->firstJob) { /* flush and overwrite frame header when it's not first job */ + size_t const hSize = ZSTD_compressContinue(cctx, dstBuff.start, dstBuff.capacity, job->src.start, 0); if (ZSTD_isError(hSize)) JOB_ERROR(hSize); - DEBUGLOG(5, "ZSTDMT_compressionJob: flush and overwrite %u bytes of frame header (not first job)", (U32)hSize); - ZSTD_invalidateRepCodes(cctx); - } - - /* compress */ - { size_t const chunkSize = 4*ZSTD_BLOCKSIZE_MAX; - int const nbChunks = (int)((job->src.size + (chunkSize-1)) / chunkSize); - const BYTE* ip = (const BYTE*) job->src.start; - BYTE* const ostart = (BYTE*)dstBuff.start; - BYTE* op = ostart; - BYTE* oend = op + dstBuff.capacity; - int chunkNb; - if (sizeof(size_t) > sizeof(int)) assert(job->src.size < ((size_t)INT_MAX) * chunkSize); /* check overflow */ - DEBUGLOG(5, "ZSTDMT_compressionJob: compress %u bytes in %i blocks", (U32)job->src.size, nbChunks); - assert(job->cSize == 0); - for (chunkNb = 1; chunkNb < nbChunks; chunkNb++) { - size_t const cSize = ZSTD_compressContinue(cctx, op, oend-op, ip, chunkSize); + DEBUGLOG(5, "ZSTDMT_compressionJob: flush and overwrite %u bytes of frame header (not first job)", (U32)hSize); + ZSTD_invalidateRepCodes(cctx); + } + + /* compress */ + { size_t const chunkSize = 4*ZSTD_BLOCKSIZE_MAX; + int const nbChunks = (int)((job->src.size + (chunkSize-1)) / chunkSize); + const BYTE* ip = (const BYTE*) job->src.start; + BYTE* const ostart = (BYTE*)dstBuff.start; + BYTE* op = ostart; + BYTE* oend = op + dstBuff.capacity; + int chunkNb; + if (sizeof(size_t) > sizeof(int)) assert(job->src.size < ((size_t)INT_MAX) * chunkSize); /* check overflow */ + DEBUGLOG(5, "ZSTDMT_compressionJob: compress %u bytes in %i blocks", (U32)job->src.size, nbChunks); + assert(job->cSize == 0); + for (chunkNb = 1; chunkNb < nbChunks; chunkNb++) { + size_t const cSize = ZSTD_compressContinue(cctx, op, oend-op, ip, chunkSize); if (ZSTD_isError(cSize)) JOB_ERROR(cSize); - ip += chunkSize; - op += cSize; assert(op < oend); - /* stats */ - ZSTD_PTHREAD_MUTEX_LOCK(&job->job_mutex); - job->cSize += cSize; - job->consumed = chunkSize * chunkNb; - DEBUGLOG(5, "ZSTDMT_compressionJob: compress new block : cSize==%u bytes (total: %u)", - (U32)cSize, (U32)job->cSize); - ZSTD_pthread_cond_signal(&job->job_cond); /* warns some more data is ready to be flushed */ - ZSTD_pthread_mutex_unlock(&job->job_mutex); - } - /* last block */ + ip += chunkSize; + op += cSize; assert(op < oend); + /* stats */ + ZSTD_PTHREAD_MUTEX_LOCK(&job->job_mutex); + job->cSize += cSize; + job->consumed = chunkSize * chunkNb; + DEBUGLOG(5, "ZSTDMT_compressionJob: compress new block : cSize==%u bytes (total: %u)", + (U32)cSize, (U32)job->cSize); + ZSTD_pthread_cond_signal(&job->job_cond); /* warns some more data is ready to be flushed */ + ZSTD_pthread_mutex_unlock(&job->job_mutex); + } + /* last block */ assert(chunkSize > 0); assert((chunkSize & (chunkSize - 1)) == 0); /* chunkSize must be power of 2 for mask==(chunkSize-1) to work */ - if ((nbChunks > 0) | job->lastJob /*must output a "last block" flag*/ ) { - size_t const lastBlockSize1 = job->src.size & (chunkSize-1); - size_t const lastBlockSize = ((lastBlockSize1==0) & (job->src.size>=chunkSize)) ? chunkSize : lastBlockSize1; - size_t const cSize = (job->lastJob) ? - ZSTD_compressEnd (cctx, op, oend-op, ip, lastBlockSize) : - ZSTD_compressContinue(cctx, op, oend-op, ip, lastBlockSize); + if ((nbChunks > 0) | job->lastJob /*must output a "last block" flag*/ ) { + size_t const lastBlockSize1 = job->src.size & (chunkSize-1); + size_t const lastBlockSize = ((lastBlockSize1==0) & (job->src.size>=chunkSize)) ? chunkSize : lastBlockSize1; + size_t const cSize = (job->lastJob) ? + ZSTD_compressEnd (cctx, op, oend-op, ip, lastBlockSize) : + ZSTD_compressContinue(cctx, op, oend-op, ip, lastBlockSize); if (ZSTD_isError(cSize)) JOB_ERROR(cSize); lastCBlockSize = cSize; - } } + } } if (!job->firstJob) { /* Double check that we don't have an ext-dict, because then our * repcode invalidation doesn't work. @@ -769,51 +769,51 @@ static void ZSTDMT_compressionJob(void* jobDescription) assert(!ZSTD_window_hasExtDict(cctx->blockState.matchState.window)); } ZSTD_CCtx_trace(cctx, 0); - -_endJob: - ZSTDMT_serialState_ensureFinished(job->serial, job->jobID, job->cSize); - if (job->prefix.size > 0) - DEBUGLOG(5, "Finished with prefix: %zx", (size_t)job->prefix.start); - DEBUGLOG(5, "Finished with source: %zx", (size_t)job->src.start); - /* release resources */ - ZSTDMT_releaseSeq(job->seqPool, rawSeqStore); - ZSTDMT_releaseCCtx(job->cctxPool, cctx); - /* report */ - ZSTD_PTHREAD_MUTEX_LOCK(&job->job_mutex); + +_endJob: + ZSTDMT_serialState_ensureFinished(job->serial, job->jobID, job->cSize); + if (job->prefix.size > 0) + DEBUGLOG(5, "Finished with prefix: %zx", (size_t)job->prefix.start); + DEBUGLOG(5, "Finished with source: %zx", (size_t)job->src.start); + /* release resources */ + ZSTDMT_releaseSeq(job->seqPool, rawSeqStore); + ZSTDMT_releaseCCtx(job->cctxPool, cctx); + /* report */ + ZSTD_PTHREAD_MUTEX_LOCK(&job->job_mutex); if (ZSTD_isError(job->cSize)) assert(lastCBlockSize == 0); job->cSize += lastCBlockSize; job->consumed = job->src.size; /* when job->consumed == job->src.size , compression job is presumed completed */ - ZSTD_pthread_cond_signal(&job->job_cond); - ZSTD_pthread_mutex_unlock(&job->job_mutex); -} - - -/* ------------------------------------------ */ -/* ===== Multi-threaded compression ===== */ -/* ------------------------------------------ */ - -typedef struct { - range_t prefix; /* read-only non-owned prefix buffer */ - buffer_t buffer; - size_t filled; -} inBuff_t; - -typedef struct { - BYTE* buffer; /* The round input buffer. All jobs get references - * to pieces of the buffer. ZSTDMT_tryGetInputRange() - * handles handing out job input buffers, and makes - * sure it doesn't overlap with any pieces still in use. - */ - size_t capacity; /* The capacity of buffer. */ - size_t pos; /* The position of the current inBuff in the round - * buffer. Updated past the end if the inBuff once - * the inBuff is sent to the worker thread. - * pos <= capacity. - */ -} roundBuff_t; - -static const roundBuff_t kNullRoundBuff = {NULL, 0, 0}; - + ZSTD_pthread_cond_signal(&job->job_cond); + ZSTD_pthread_mutex_unlock(&job->job_mutex); +} + + +/* ------------------------------------------ */ +/* ===== Multi-threaded compression ===== */ +/* ------------------------------------------ */ + +typedef struct { + range_t prefix; /* read-only non-owned prefix buffer */ + buffer_t buffer; + size_t filled; +} inBuff_t; + +typedef struct { + BYTE* buffer; /* The round input buffer. All jobs get references + * to pieces of the buffer. ZSTDMT_tryGetInputRange() + * handles handing out job input buffers, and makes + * sure it doesn't overlap with any pieces still in use. + */ + size_t capacity; /* The capacity of buffer. */ + size_t pos; /* The position of the current inBuff in the round + * buffer. Updated past the end if the inBuff once + * the inBuff is sent to the worker thread. + * pos <= capacity. + */ +} roundBuff_t; + +static const roundBuff_t kNullRoundBuff = {NULL, 0, 0}; + #define RSYNC_LENGTH 32 /* Don't create chunks smaller than the zstd block size. * This stops us from regressing compression ratio too much, @@ -831,69 +831,69 @@ typedef struct { U64 primePower; } rsyncState_t; -struct ZSTDMT_CCtx_s { - POOL_ctx* factory; - ZSTDMT_jobDescription* jobs; - ZSTDMT_bufferPool* bufPool; - ZSTDMT_CCtxPool* cctxPool; - ZSTDMT_seqPool* seqPool; - ZSTD_CCtx_params params; - size_t targetSectionSize; - size_t targetPrefixSize; +struct ZSTDMT_CCtx_s { + POOL_ctx* factory; + ZSTDMT_jobDescription* jobs; + ZSTDMT_bufferPool* bufPool; + ZSTDMT_CCtxPool* cctxPool; + ZSTDMT_seqPool* seqPool; + ZSTD_CCtx_params params; + size_t targetSectionSize; + size_t targetPrefixSize; int jobReady; /* 1 => one job is already prepared, but pool has shortage of workers. Don't create a new job. */ inBuff_t inBuff; - roundBuff_t roundBuff; - serialState_t serial; + roundBuff_t roundBuff; + serialState_t serial; rsyncState_t rsync; - unsigned jobIDMask; - unsigned doneJobID; - unsigned nextJobID; - unsigned frameEnded; - unsigned allJobsCompleted; - unsigned long long frameContentSize; - unsigned long long consumed; - unsigned long long produced; - ZSTD_customMem cMem; - ZSTD_CDict* cdictLocal; - const ZSTD_CDict* cdict; + unsigned jobIDMask; + unsigned doneJobID; + unsigned nextJobID; + unsigned frameEnded; + unsigned allJobsCompleted; + unsigned long long frameContentSize; + unsigned long long consumed; + unsigned long long produced; + ZSTD_customMem cMem; + ZSTD_CDict* cdictLocal; + const ZSTD_CDict* cdict; unsigned providedFactory: 1; -}; - -static void ZSTDMT_freeJobsTable(ZSTDMT_jobDescription* jobTable, U32 nbJobs, ZSTD_customMem cMem) -{ - U32 jobNb; - if (jobTable == NULL) return; - for (jobNb=0; jobNb<nbJobs; jobNb++) { - ZSTD_pthread_mutex_destroy(&jobTable[jobNb].job_mutex); - ZSTD_pthread_cond_destroy(&jobTable[jobNb].job_cond); - } +}; + +static void ZSTDMT_freeJobsTable(ZSTDMT_jobDescription* jobTable, U32 nbJobs, ZSTD_customMem cMem) +{ + U32 jobNb; + if (jobTable == NULL) return; + for (jobNb=0; jobNb<nbJobs; jobNb++) { + ZSTD_pthread_mutex_destroy(&jobTable[jobNb].job_mutex); + ZSTD_pthread_cond_destroy(&jobTable[jobNb].job_cond); + } ZSTD_customFree(jobTable, cMem); -} - -/* ZSTDMT_allocJobsTable() - * allocate and init a job table. - * update *nbJobsPtr to next power of 2 value, as size of table */ -static ZSTDMT_jobDescription* ZSTDMT_createJobsTable(U32* nbJobsPtr, ZSTD_customMem cMem) -{ - U32 const nbJobsLog2 = ZSTD_highbit32(*nbJobsPtr) + 1; - U32 const nbJobs = 1 << nbJobsLog2; - U32 jobNb; - ZSTDMT_jobDescription* const jobTable = (ZSTDMT_jobDescription*) +} + +/* ZSTDMT_allocJobsTable() + * allocate and init a job table. + * update *nbJobsPtr to next power of 2 value, as size of table */ +static ZSTDMT_jobDescription* ZSTDMT_createJobsTable(U32* nbJobsPtr, ZSTD_customMem cMem) +{ + U32 const nbJobsLog2 = ZSTD_highbit32(*nbJobsPtr) + 1; + U32 const nbJobs = 1 << nbJobsLog2; + U32 jobNb; + ZSTDMT_jobDescription* const jobTable = (ZSTDMT_jobDescription*) ZSTD_customCalloc(nbJobs * sizeof(ZSTDMT_jobDescription), cMem); - int initError = 0; - if (jobTable==NULL) return NULL; - *nbJobsPtr = nbJobs; - for (jobNb=0; jobNb<nbJobs; jobNb++) { - initError |= ZSTD_pthread_mutex_init(&jobTable[jobNb].job_mutex, NULL); - initError |= ZSTD_pthread_cond_init(&jobTable[jobNb].job_cond, NULL); - } - if (initError != 0) { - ZSTDMT_freeJobsTable(jobTable, nbJobs, cMem); - return NULL; - } - return jobTable; -} - + int initError = 0; + if (jobTable==NULL) return NULL; + *nbJobsPtr = nbJobs; + for (jobNb=0; jobNb<nbJobs; jobNb++) { + initError |= ZSTD_pthread_mutex_init(&jobTable[jobNb].job_mutex, NULL); + initError |= ZSTD_pthread_cond_init(&jobTable[jobNb].job_cond, NULL); + } + if (initError != 0) { + ZSTDMT_freeJobsTable(jobTable, nbJobs, cMem); + return NULL; + } + return jobTable; +} + static size_t ZSTDMT_expandJobsTable (ZSTDMT_CCtx* mtctx, U32 nbWorkers) { U32 nbJobs = nbWorkers + 2; if (nbJobs > mtctx->jobIDMask+1) { /* need more job capacity */ @@ -908,31 +908,31 @@ static size_t ZSTDMT_expandJobsTable (ZSTDMT_CCtx* mtctx, U32 nbWorkers) { } -/* ZSTDMT_CCtxParam_setNbWorkers(): - * Internal use only */ +/* ZSTDMT_CCtxParam_setNbWorkers(): + * Internal use only */ static size_t ZSTDMT_CCtxParam_setNbWorkers(ZSTD_CCtx_params* params, unsigned nbWorkers) -{ +{ return ZSTD_CCtxParams_setParameter(params, ZSTD_c_nbWorkers, (int)nbWorkers); -} - +} + MEM_STATIC ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced_internal(unsigned nbWorkers, ZSTD_customMem cMem, ZSTD_threadPool* pool) -{ - ZSTDMT_CCtx* mtctx; - U32 nbJobs = nbWorkers + 2; - int initError; - DEBUGLOG(3, "ZSTDMT_createCCtx_advanced (nbWorkers = %u)", nbWorkers); - - if (nbWorkers < 1) return NULL; - nbWorkers = MIN(nbWorkers , ZSTDMT_NBWORKERS_MAX); - if ((cMem.customAlloc!=NULL) ^ (cMem.customFree!=NULL)) - /* invalid custom allocator */ - return NULL; - +{ + ZSTDMT_CCtx* mtctx; + U32 nbJobs = nbWorkers + 2; + int initError; + DEBUGLOG(3, "ZSTDMT_createCCtx_advanced (nbWorkers = %u)", nbWorkers); + + if (nbWorkers < 1) return NULL; + nbWorkers = MIN(nbWorkers , ZSTDMT_NBWORKERS_MAX); + if ((cMem.customAlloc!=NULL) ^ (cMem.customFree!=NULL)) + /* invalid custom allocator */ + return NULL; + mtctx = (ZSTDMT_CCtx*) ZSTD_customCalloc(sizeof(ZSTDMT_CCtx), cMem); - if (!mtctx) return NULL; - ZSTDMT_CCtxParam_setNbWorkers(&mtctx->params, nbWorkers); - mtctx->cMem = cMem; - mtctx->allJobsCompleted = 1; + if (!mtctx) return NULL; + ZSTDMT_CCtxParam_setNbWorkers(&mtctx->params, nbWorkers); + mtctx->cMem = cMem; + mtctx->allJobsCompleted = 1; if (pool != NULL) { mtctx->factory = pool; mtctx->providedFactory = 1; @@ -941,22 +941,22 @@ MEM_STATIC ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced_internal(unsigned nbWorkers, mtctx->factory = POOL_create_advanced(nbWorkers, 0, cMem); mtctx->providedFactory = 0; } - mtctx->jobs = ZSTDMT_createJobsTable(&nbJobs, cMem); - assert(nbJobs > 0); assert((nbJobs & (nbJobs - 1)) == 0); /* ensure nbJobs is a power of 2 */ - mtctx->jobIDMask = nbJobs - 1; + mtctx->jobs = ZSTDMT_createJobsTable(&nbJobs, cMem); + assert(nbJobs > 0); assert((nbJobs & (nbJobs - 1)) == 0); /* ensure nbJobs is a power of 2 */ + mtctx->jobIDMask = nbJobs - 1; mtctx->bufPool = ZSTDMT_createBufferPool(BUF_POOL_MAX_NB_BUFFERS(nbWorkers), cMem); - mtctx->cctxPool = ZSTDMT_createCCtxPool(nbWorkers, cMem); - mtctx->seqPool = ZSTDMT_createSeqPool(nbWorkers, cMem); - initError = ZSTDMT_serialState_init(&mtctx->serial); - mtctx->roundBuff = kNullRoundBuff; - if (!mtctx->factory | !mtctx->jobs | !mtctx->bufPool | !mtctx->cctxPool | !mtctx->seqPool | initError) { - ZSTDMT_freeCCtx(mtctx); - return NULL; - } - DEBUGLOG(3, "mt_cctx created, for %u threads", nbWorkers); - return mtctx; -} - + mtctx->cctxPool = ZSTDMT_createCCtxPool(nbWorkers, cMem); + mtctx->seqPool = ZSTDMT_createSeqPool(nbWorkers, cMem); + initError = ZSTDMT_serialState_init(&mtctx->serial); + mtctx->roundBuff = kNullRoundBuff; + if (!mtctx->factory | !mtctx->jobs | !mtctx->bufPool | !mtctx->cctxPool | !mtctx->seqPool | initError) { + ZSTDMT_freeCCtx(mtctx); + return NULL; + } + DEBUGLOG(3, "mt_cctx created, for %u threads", nbWorkers); + return mtctx; +} + ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem, ZSTD_threadPool* pool) { #ifdef ZSTD_MULTITHREAD @@ -969,78 +969,78 @@ ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem, #endif } - -/* ZSTDMT_releaseAllJobResources() : - * note : ensure all workers are killed first ! */ -static void ZSTDMT_releaseAllJobResources(ZSTDMT_CCtx* mtctx) -{ - unsigned jobID; - DEBUGLOG(3, "ZSTDMT_releaseAllJobResources"); - for (jobID=0; jobID <= mtctx->jobIDMask; jobID++) { + +/* ZSTDMT_releaseAllJobResources() : + * note : ensure all workers are killed first ! */ +static void ZSTDMT_releaseAllJobResources(ZSTDMT_CCtx* mtctx) +{ + unsigned jobID; + DEBUGLOG(3, "ZSTDMT_releaseAllJobResources"); + for (jobID=0; jobID <= mtctx->jobIDMask; jobID++) { /* Copy the mutex/cond out */ ZSTD_pthread_mutex_t const mutex = mtctx->jobs[jobID].job_mutex; ZSTD_pthread_cond_t const cond = mtctx->jobs[jobID].job_cond; - DEBUGLOG(4, "job%02u: release dst address %08X", jobID, (U32)(size_t)mtctx->jobs[jobID].dstBuff.start); - ZSTDMT_releaseBuffer(mtctx->bufPool, mtctx->jobs[jobID].dstBuff); + DEBUGLOG(4, "job%02u: release dst address %08X", jobID, (U32)(size_t)mtctx->jobs[jobID].dstBuff.start); + ZSTDMT_releaseBuffer(mtctx->bufPool, mtctx->jobs[jobID].dstBuff); /* Clear the job description, but keep the mutex/cond */ ZSTD_memset(&mtctx->jobs[jobID], 0, sizeof(mtctx->jobs[jobID])); mtctx->jobs[jobID].job_mutex = mutex; mtctx->jobs[jobID].job_cond = cond; - } - mtctx->inBuff.buffer = g_nullBuffer; - mtctx->inBuff.filled = 0; - mtctx->allJobsCompleted = 1; -} - -static void ZSTDMT_waitForAllJobsCompleted(ZSTDMT_CCtx* mtctx) -{ - DEBUGLOG(4, "ZSTDMT_waitForAllJobsCompleted"); - while (mtctx->doneJobID < mtctx->nextJobID) { - unsigned const jobID = mtctx->doneJobID & mtctx->jobIDMask; - ZSTD_PTHREAD_MUTEX_LOCK(&mtctx->jobs[jobID].job_mutex); - while (mtctx->jobs[jobID].consumed < mtctx->jobs[jobID].src.size) { + } + mtctx->inBuff.buffer = g_nullBuffer; + mtctx->inBuff.filled = 0; + mtctx->allJobsCompleted = 1; +} + +static void ZSTDMT_waitForAllJobsCompleted(ZSTDMT_CCtx* mtctx) +{ + DEBUGLOG(4, "ZSTDMT_waitForAllJobsCompleted"); + while (mtctx->doneJobID < mtctx->nextJobID) { + unsigned const jobID = mtctx->doneJobID & mtctx->jobIDMask; + ZSTD_PTHREAD_MUTEX_LOCK(&mtctx->jobs[jobID].job_mutex); + while (mtctx->jobs[jobID].consumed < mtctx->jobs[jobID].src.size) { DEBUGLOG(4, "waiting for jobCompleted signal from job %u", mtctx->doneJobID); /* we want to block when waiting for data to flush */ - ZSTD_pthread_cond_wait(&mtctx->jobs[jobID].job_cond, &mtctx->jobs[jobID].job_mutex); - } - ZSTD_pthread_mutex_unlock(&mtctx->jobs[jobID].job_mutex); - mtctx->doneJobID++; - } -} - -size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx) -{ - if (mtctx==NULL) return 0; /* compatible with free on NULL */ + ZSTD_pthread_cond_wait(&mtctx->jobs[jobID].job_cond, &mtctx->jobs[jobID].job_mutex); + } + ZSTD_pthread_mutex_unlock(&mtctx->jobs[jobID].job_mutex); + mtctx->doneJobID++; + } +} + +size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx) +{ + if (mtctx==NULL) return 0; /* compatible with free on NULL */ if (!mtctx->providedFactory) POOL_free(mtctx->factory); /* stop and free worker threads */ - ZSTDMT_releaseAllJobResources(mtctx); /* release job resources into pools first */ - ZSTDMT_freeJobsTable(mtctx->jobs, mtctx->jobIDMask+1, mtctx->cMem); - ZSTDMT_freeBufferPool(mtctx->bufPool); - ZSTDMT_freeCCtxPool(mtctx->cctxPool); - ZSTDMT_freeSeqPool(mtctx->seqPool); - ZSTDMT_serialState_free(&mtctx->serial); - ZSTD_freeCDict(mtctx->cdictLocal); - if (mtctx->roundBuff.buffer) + ZSTDMT_releaseAllJobResources(mtctx); /* release job resources into pools first */ + ZSTDMT_freeJobsTable(mtctx->jobs, mtctx->jobIDMask+1, mtctx->cMem); + ZSTDMT_freeBufferPool(mtctx->bufPool); + ZSTDMT_freeCCtxPool(mtctx->cctxPool); + ZSTDMT_freeSeqPool(mtctx->seqPool); + ZSTDMT_serialState_free(&mtctx->serial); + ZSTD_freeCDict(mtctx->cdictLocal); + if (mtctx->roundBuff.buffer) ZSTD_customFree(mtctx->roundBuff.buffer, mtctx->cMem); ZSTD_customFree(mtctx, mtctx->cMem); - return 0; -} - -size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx) -{ - if (mtctx == NULL) return 0; /* supports sizeof NULL */ - return sizeof(*mtctx) - + POOL_sizeof(mtctx->factory) - + ZSTDMT_sizeof_bufferPool(mtctx->bufPool) - + (mtctx->jobIDMask+1) * sizeof(ZSTDMT_jobDescription) - + ZSTDMT_sizeof_CCtxPool(mtctx->cctxPool) - + ZSTDMT_sizeof_seqPool(mtctx->seqPool) - + ZSTD_sizeof_CDict(mtctx->cdictLocal) - + mtctx->roundBuff.capacity; -} - - + return 0; +} + +size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx) +{ + if (mtctx == NULL) return 0; /* supports sizeof NULL */ + return sizeof(*mtctx) + + POOL_sizeof(mtctx->factory) + + ZSTDMT_sizeof_bufferPool(mtctx->bufPool) + + (mtctx->jobIDMask+1) * sizeof(ZSTDMT_jobDescription) + + ZSTDMT_sizeof_CCtxPool(mtctx->cctxPool) + + ZSTDMT_sizeof_seqPool(mtctx->seqPool) + + ZSTD_sizeof_CDict(mtctx->cdictLocal) + + mtctx->roundBuff.capacity; +} + + /* ZSTDMT_resize() : * @return : error code if fails, 0 on success */ static size_t ZSTDMT_resize(ZSTDMT_CCtx* mtctx, unsigned nbWorkers) @@ -1055,63 +1055,63 @@ static size_t ZSTDMT_resize(ZSTDMT_CCtx* mtctx, unsigned nbWorkers) if (mtctx->seqPool == NULL) return ERROR(memory_allocation); ZSTDMT_CCtxParam_setNbWorkers(&mtctx->params, nbWorkers); return 0; -} - +} + -/*! ZSTDMT_updateCParams_whileCompressing() : +/*! ZSTDMT_updateCParams_whileCompressing() : * Updates a selected set of compression parameters, remaining compatible with currently active frame. - * New parameters will be applied to next compression job. */ -void ZSTDMT_updateCParams_whileCompressing(ZSTDMT_CCtx* mtctx, const ZSTD_CCtx_params* cctxParams) -{ - U32 const saved_wlog = mtctx->params.cParams.windowLog; /* Do not modify windowLog while compressing */ - int const compressionLevel = cctxParams->compressionLevel; - DEBUGLOG(5, "ZSTDMT_updateCParams_whileCompressing (level:%i)", - compressionLevel); - mtctx->params.compressionLevel = compressionLevel; + * New parameters will be applied to next compression job. */ +void ZSTDMT_updateCParams_whileCompressing(ZSTDMT_CCtx* mtctx, const ZSTD_CCtx_params* cctxParams) +{ + U32 const saved_wlog = mtctx->params.cParams.windowLog; /* Do not modify windowLog while compressing */ + int const compressionLevel = cctxParams->compressionLevel; + DEBUGLOG(5, "ZSTDMT_updateCParams_whileCompressing (level:%i)", + compressionLevel); + mtctx->params.compressionLevel = compressionLevel; { ZSTD_compressionParameters cParams = ZSTD_getCParamsFromCCtxParams(cctxParams, ZSTD_CONTENTSIZE_UNKNOWN, 0, ZSTD_cpm_noAttachDict); - cParams.windowLog = saved_wlog; - mtctx->params.cParams = cParams; - } -} - -/* ZSTDMT_getFrameProgression(): - * tells how much data has been consumed (input) and produced (output) for current frame. - * able to count progression inside worker threads. + cParams.windowLog = saved_wlog; + mtctx->params.cParams = cParams; + } +} + +/* ZSTDMT_getFrameProgression(): + * tells how much data has been consumed (input) and produced (output) for current frame. + * able to count progression inside worker threads. * Note : mutex will be acquired during statistics collection inside workers. */ -ZSTD_frameProgression ZSTDMT_getFrameProgression(ZSTDMT_CCtx* mtctx) -{ - ZSTD_frameProgression fps; +ZSTD_frameProgression ZSTDMT_getFrameProgression(ZSTDMT_CCtx* mtctx) +{ + ZSTD_frameProgression fps; DEBUGLOG(5, "ZSTDMT_getFrameProgression"); fps.ingested = mtctx->consumed + mtctx->inBuff.filled; - fps.consumed = mtctx->consumed; + fps.consumed = mtctx->consumed; fps.produced = fps.flushed = mtctx->produced; fps.currentJobID = mtctx->nextJobID; fps.nbActiveWorkers = 0; - { unsigned jobNb; - unsigned lastJobNb = mtctx->nextJobID + mtctx->jobReady; assert(mtctx->jobReady <= 1); - DEBUGLOG(6, "ZSTDMT_getFrameProgression: jobs: from %u to <%u (jobReady:%u)", - mtctx->doneJobID, lastJobNb, mtctx->jobReady) - for (jobNb = mtctx->doneJobID ; jobNb < lastJobNb ; jobNb++) { - unsigned const wJobID = jobNb & mtctx->jobIDMask; + { unsigned jobNb; + unsigned lastJobNb = mtctx->nextJobID + mtctx->jobReady; assert(mtctx->jobReady <= 1); + DEBUGLOG(6, "ZSTDMT_getFrameProgression: jobs: from %u to <%u (jobReady:%u)", + mtctx->doneJobID, lastJobNb, mtctx->jobReady) + for (jobNb = mtctx->doneJobID ; jobNb < lastJobNb ; jobNb++) { + unsigned const wJobID = jobNb & mtctx->jobIDMask; ZSTDMT_jobDescription* jobPtr = &mtctx->jobs[wJobID]; ZSTD_pthread_mutex_lock(&jobPtr->job_mutex); { size_t const cResult = jobPtr->cSize; - size_t const produced = ZSTD_isError(cResult) ? 0 : cResult; + size_t const produced = ZSTD_isError(cResult) ? 0 : cResult; size_t const flushed = ZSTD_isError(cResult) ? 0 : jobPtr->dstFlushed; assert(flushed <= produced); fps.ingested += jobPtr->src.size; fps.consumed += jobPtr->consumed; - fps.produced += produced; + fps.produced += produced; fps.flushed += flushed; fps.nbActiveWorkers += (jobPtr->consumed < jobPtr->src.size); - } - ZSTD_pthread_mutex_unlock(&mtctx->jobs[wJobID].job_mutex); - } - } - return fps; -} - - + } + ZSTD_pthread_mutex_unlock(&mtctx->jobs[wJobID].job_mutex); + } + } + return fps; +} + + size_t ZSTDMT_toFlushNow(ZSTDMT_CCtx* mtctx) { size_t toFlush; @@ -1145,12 +1145,12 @@ size_t ZSTDMT_toFlushNow(ZSTDMT_CCtx* mtctx) } -/* ------------------------------------------ */ -/* ===== Multi-threaded compression ===== */ -/* ------------------------------------------ */ - +/* ------------------------------------------ */ +/* ===== Multi-threaded compression ===== */ +/* ------------------------------------------ */ + static unsigned ZSTDMT_computeTargetJobLog(const ZSTD_CCtx_params* params) -{ +{ unsigned jobLog; if (params->ldmParams.enableLdm == ZSTD_ps_enable) { /* In Long Range Mode, the windowLog is typically oversized. @@ -1161,10 +1161,10 @@ static unsigned ZSTDMT_computeTargetJobLog(const ZSTD_CCtx_params* params) jobLog = MAX(20, params->cParams.windowLog + 2); } return MIN(jobLog, (unsigned)ZSTDMT_JOBLOG_MAX); -} - +} + static int ZSTDMT_overlapLog_default(ZSTD_strategy strat) -{ +{ switch(strat) { case ZSTD_btultra2: @@ -1182,8 +1182,8 @@ static int ZSTDMT_overlapLog_default(ZSTD_strategy strat) default:; } return 6; -} - +} + static int ZSTDMT_overlapLog(int ovlog, ZSTD_strategy strat) { assert(0 <= ovlog && ovlog <= 9); @@ -1210,56 +1210,56 @@ static size_t ZSTDMT_computeOverlapSize(const ZSTD_CCtx_params* params) return (ovLog==0) ? 0 : (size_t)1 << ovLog; } -/* ====================================== */ -/* ======= Streaming API ======= */ -/* ====================================== */ - -size_t ZSTDMT_initCStream_internal( - ZSTDMT_CCtx* mtctx, - const void* dict, size_t dictSize, ZSTD_dictContentType_e dictContentType, - const ZSTD_CDict* cdict, ZSTD_CCtx_params params, - unsigned long long pledgedSrcSize) -{ +/* ====================================== */ +/* ======= Streaming API ======= */ +/* ====================================== */ + +size_t ZSTDMT_initCStream_internal( + ZSTDMT_CCtx* mtctx, + const void* dict, size_t dictSize, ZSTD_dictContentType_e dictContentType, + const ZSTD_CDict* cdict, ZSTD_CCtx_params params, + unsigned long long pledgedSrcSize) +{ DEBUGLOG(4, "ZSTDMT_initCStream_internal (pledgedSrcSize=%u, nbWorkers=%u, cctxPool=%u)", (U32)pledgedSrcSize, params.nbWorkers, mtctx->cctxPool->totalCCtx); /* params supposed partially fully validated at this point */ - assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams))); - assert(!((dict) && (cdict))); /* either dict or cdict, not both */ - - /* init */ + assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams))); + assert(!((dict) && (cdict))); /* either dict or cdict, not both */ + + /* init */ if (params.nbWorkers != mtctx->params.nbWorkers) FORWARD_IF_ERROR( ZSTDMT_resize(mtctx, params.nbWorkers) , ""); - + if (params.jobSize != 0 && params.jobSize < ZSTDMT_JOBSIZE_MIN) params.jobSize = ZSTDMT_JOBSIZE_MIN; if (params.jobSize > (size_t)ZSTDMT_JOBSIZE_MAX) params.jobSize = (size_t)ZSTDMT_JOBSIZE_MAX; - DEBUGLOG(4, "ZSTDMT_initCStream_internal: %u workers", params.nbWorkers); - - if (mtctx->allJobsCompleted == 0) { /* previous compression not correctly finished */ - ZSTDMT_waitForAllJobsCompleted(mtctx); - ZSTDMT_releaseAllJobResources(mtctx); - mtctx->allJobsCompleted = 1; - } - - mtctx->params = params; - mtctx->frameContentSize = pledgedSrcSize; - if (dict) { - ZSTD_freeCDict(mtctx->cdictLocal); - mtctx->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize, - ZSTD_dlm_byCopy, dictContentType, /* note : a loadPrefix becomes an internal CDict */ - params.cParams, mtctx->cMem); - mtctx->cdict = mtctx->cdictLocal; - if (mtctx->cdictLocal == NULL) return ERROR(memory_allocation); - } else { - ZSTD_freeCDict(mtctx->cdictLocal); - mtctx->cdictLocal = NULL; - mtctx->cdict = cdict; - } - + DEBUGLOG(4, "ZSTDMT_initCStream_internal: %u workers", params.nbWorkers); + + if (mtctx->allJobsCompleted == 0) { /* previous compression not correctly finished */ + ZSTDMT_waitForAllJobsCompleted(mtctx); + ZSTDMT_releaseAllJobResources(mtctx); + mtctx->allJobsCompleted = 1; + } + + mtctx->params = params; + mtctx->frameContentSize = pledgedSrcSize; + if (dict) { + ZSTD_freeCDict(mtctx->cdictLocal); + mtctx->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize, + ZSTD_dlm_byCopy, dictContentType, /* note : a loadPrefix becomes an internal CDict */ + params.cParams, mtctx->cMem); + mtctx->cdict = mtctx->cdictLocal; + if (mtctx->cdictLocal == NULL) return ERROR(memory_allocation); + } else { + ZSTD_freeCDict(mtctx->cdictLocal); + mtctx->cdictLocal = NULL; + mtctx->cdict = cdict; + } + mtctx->targetPrefixSize = ZSTDMT_computeOverlapSize(¶ms); DEBUGLOG(4, "overlapLog=%i => %u KB", params.overlapLog, (U32)(mtctx->targetPrefixSize>>10)); - mtctx->targetSectionSize = params.jobSize; + mtctx->targetSectionSize = params.jobSize; if (mtctx->targetSectionSize == 0) { mtctx->targetSectionSize = 1ULL << ZSTDMT_computeTargetJobLog(¶ms); } @@ -1277,292 +1277,292 @@ size_t ZSTDMT_initCStream_internal( mtctx->rsync.hitMask = (1ULL << rsyncBits) - 1; mtctx->rsync.primePower = ZSTD_rollingHash_primePower(RSYNC_LENGTH); } - if (mtctx->targetSectionSize < mtctx->targetPrefixSize) mtctx->targetSectionSize = mtctx->targetPrefixSize; /* job size must be >= overlap size */ + if (mtctx->targetSectionSize < mtctx->targetPrefixSize) mtctx->targetSectionSize = mtctx->targetPrefixSize; /* job size must be >= overlap size */ DEBUGLOG(4, "Job Size : %u KB (note : set to %u)", (U32)(mtctx->targetSectionSize>>10), (U32)params.jobSize); - DEBUGLOG(4, "inBuff Size : %u KB", (U32)(mtctx->targetSectionSize>>10)); - ZSTDMT_setBufferSize(mtctx->bufPool, ZSTD_compressBound(mtctx->targetSectionSize)); - { - /* If ldm is enabled we need windowSize space. */ + DEBUGLOG(4, "inBuff Size : %u KB", (U32)(mtctx->targetSectionSize>>10)); + ZSTDMT_setBufferSize(mtctx->bufPool, ZSTD_compressBound(mtctx->targetSectionSize)); + { + /* If ldm is enabled we need windowSize space. */ size_t const windowSize = mtctx->params.ldmParams.enableLdm == ZSTD_ps_enable ? (1U << mtctx->params.cParams.windowLog) : 0; - /* Two buffers of slack, plus extra space for the overlap - * This is the minimum slack that LDM works with. One extra because - * flush might waste up to targetSectionSize-1 bytes. Another extra - * for the overlap (if > 0), then one to fill which doesn't overlap - * with the LDM window. - */ - size_t const nbSlackBuffers = 2 + (mtctx->targetPrefixSize > 0); - size_t const slackSize = mtctx->targetSectionSize * nbSlackBuffers; - /* Compute the total size, and always have enough slack */ - size_t const nbWorkers = MAX(mtctx->params.nbWorkers, 1); - size_t const sectionsSize = mtctx->targetSectionSize * nbWorkers; - size_t const capacity = MAX(windowSize, sectionsSize) + slackSize; - if (mtctx->roundBuff.capacity < capacity) { - if (mtctx->roundBuff.buffer) + /* Two buffers of slack, plus extra space for the overlap + * This is the minimum slack that LDM works with. One extra because + * flush might waste up to targetSectionSize-1 bytes. Another extra + * for the overlap (if > 0), then one to fill which doesn't overlap + * with the LDM window. + */ + size_t const nbSlackBuffers = 2 + (mtctx->targetPrefixSize > 0); + size_t const slackSize = mtctx->targetSectionSize * nbSlackBuffers; + /* Compute the total size, and always have enough slack */ + size_t const nbWorkers = MAX(mtctx->params.nbWorkers, 1); + size_t const sectionsSize = mtctx->targetSectionSize * nbWorkers; + size_t const capacity = MAX(windowSize, sectionsSize) + slackSize; + if (mtctx->roundBuff.capacity < capacity) { + if (mtctx->roundBuff.buffer) ZSTD_customFree(mtctx->roundBuff.buffer, mtctx->cMem); mtctx->roundBuff.buffer = (BYTE*)ZSTD_customMalloc(capacity, mtctx->cMem); - if (mtctx->roundBuff.buffer == NULL) { - mtctx->roundBuff.capacity = 0; - return ERROR(memory_allocation); - } - mtctx->roundBuff.capacity = capacity; - } - } - DEBUGLOG(4, "roundBuff capacity : %u KB", (U32)(mtctx->roundBuff.capacity>>10)); - mtctx->roundBuff.pos = 0; - mtctx->inBuff.buffer = g_nullBuffer; - mtctx->inBuff.filled = 0; - mtctx->inBuff.prefix = kNullRange; - mtctx->doneJobID = 0; - mtctx->nextJobID = 0; - mtctx->frameEnded = 0; - mtctx->allJobsCompleted = 0; - mtctx->consumed = 0; - mtctx->produced = 0; + if (mtctx->roundBuff.buffer == NULL) { + mtctx->roundBuff.capacity = 0; + return ERROR(memory_allocation); + } + mtctx->roundBuff.capacity = capacity; + } + } + DEBUGLOG(4, "roundBuff capacity : %u KB", (U32)(mtctx->roundBuff.capacity>>10)); + mtctx->roundBuff.pos = 0; + mtctx->inBuff.buffer = g_nullBuffer; + mtctx->inBuff.filled = 0; + mtctx->inBuff.prefix = kNullRange; + mtctx->doneJobID = 0; + mtctx->nextJobID = 0; + mtctx->frameEnded = 0; + mtctx->allJobsCompleted = 0; + mtctx->consumed = 0; + mtctx->produced = 0; if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params, mtctx->targetSectionSize, dict, dictSize, dictContentType)) - return ERROR(memory_allocation); - return 0; -} - - -/* ZSTDMT_writeLastEmptyBlock() - * Write a single empty block with an end-of-frame to finish a frame. - * Job must be created from streaming variant. + return ERROR(memory_allocation); + return 0; +} + + +/* ZSTDMT_writeLastEmptyBlock() + * Write a single empty block with an end-of-frame to finish a frame. + * Job must be created from streaming variant. * This function is always successful if expected conditions are fulfilled. - */ -static void ZSTDMT_writeLastEmptyBlock(ZSTDMT_jobDescription* job) -{ - assert(job->lastJob == 1); - assert(job->src.size == 0); /* last job is empty -> will be simplified into a last empty block */ - assert(job->firstJob == 0); /* cannot be first job, as it also needs to create frame header */ - assert(job->dstBuff.start == NULL); /* invoked from streaming variant only (otherwise, dstBuff might be user's output) */ - job->dstBuff = ZSTDMT_getBuffer(job->bufPool); - if (job->dstBuff.start == NULL) { - job->cSize = ERROR(memory_allocation); - return; - } - assert(job->dstBuff.capacity >= ZSTD_blockHeaderSize); /* no buffer should ever be that small */ - job->src = kNullRange; - job->cSize = ZSTD_writeLastEmptyBlock(job->dstBuff.start, job->dstBuff.capacity); - assert(!ZSTD_isError(job->cSize)); - assert(job->consumed == 0); -} - -static size_t ZSTDMT_createCompressionJob(ZSTDMT_CCtx* mtctx, size_t srcSize, ZSTD_EndDirective endOp) -{ - unsigned const jobID = mtctx->nextJobID & mtctx->jobIDMask; - int const endFrame = (endOp == ZSTD_e_end); - - if (mtctx->nextJobID > mtctx->doneJobID + mtctx->jobIDMask) { - DEBUGLOG(5, "ZSTDMT_createCompressionJob: will not create new job : table is full"); - assert((mtctx->nextJobID & mtctx->jobIDMask) == (mtctx->doneJobID & mtctx->jobIDMask)); - return 0; - } - - if (!mtctx->jobReady) { - BYTE const* src = (BYTE const*)mtctx->inBuff.buffer.start; - DEBUGLOG(5, "ZSTDMT_createCompressionJob: preparing job %u to compress %u bytes with %u preload ", - mtctx->nextJobID, (U32)srcSize, (U32)mtctx->inBuff.prefix.size); - mtctx->jobs[jobID].src.start = src; - mtctx->jobs[jobID].src.size = srcSize; - assert(mtctx->inBuff.filled >= srcSize); - mtctx->jobs[jobID].prefix = mtctx->inBuff.prefix; - mtctx->jobs[jobID].consumed = 0; - mtctx->jobs[jobID].cSize = 0; - mtctx->jobs[jobID].params = mtctx->params; - mtctx->jobs[jobID].cdict = mtctx->nextJobID==0 ? mtctx->cdict : NULL; - mtctx->jobs[jobID].fullFrameSize = mtctx->frameContentSize; - mtctx->jobs[jobID].dstBuff = g_nullBuffer; - mtctx->jobs[jobID].cctxPool = mtctx->cctxPool; - mtctx->jobs[jobID].bufPool = mtctx->bufPool; - mtctx->jobs[jobID].seqPool = mtctx->seqPool; - mtctx->jobs[jobID].serial = &mtctx->serial; - mtctx->jobs[jobID].jobID = mtctx->nextJobID; - mtctx->jobs[jobID].firstJob = (mtctx->nextJobID==0); - mtctx->jobs[jobID].lastJob = endFrame; + */ +static void ZSTDMT_writeLastEmptyBlock(ZSTDMT_jobDescription* job) +{ + assert(job->lastJob == 1); + assert(job->src.size == 0); /* last job is empty -> will be simplified into a last empty block */ + assert(job->firstJob == 0); /* cannot be first job, as it also needs to create frame header */ + assert(job->dstBuff.start == NULL); /* invoked from streaming variant only (otherwise, dstBuff might be user's output) */ + job->dstBuff = ZSTDMT_getBuffer(job->bufPool); + if (job->dstBuff.start == NULL) { + job->cSize = ERROR(memory_allocation); + return; + } + assert(job->dstBuff.capacity >= ZSTD_blockHeaderSize); /* no buffer should ever be that small */ + job->src = kNullRange; + job->cSize = ZSTD_writeLastEmptyBlock(job->dstBuff.start, job->dstBuff.capacity); + assert(!ZSTD_isError(job->cSize)); + assert(job->consumed == 0); +} + +static size_t ZSTDMT_createCompressionJob(ZSTDMT_CCtx* mtctx, size_t srcSize, ZSTD_EndDirective endOp) +{ + unsigned const jobID = mtctx->nextJobID & mtctx->jobIDMask; + int const endFrame = (endOp == ZSTD_e_end); + + if (mtctx->nextJobID > mtctx->doneJobID + mtctx->jobIDMask) { + DEBUGLOG(5, "ZSTDMT_createCompressionJob: will not create new job : table is full"); + assert((mtctx->nextJobID & mtctx->jobIDMask) == (mtctx->doneJobID & mtctx->jobIDMask)); + return 0; + } + + if (!mtctx->jobReady) { + BYTE const* src = (BYTE const*)mtctx->inBuff.buffer.start; + DEBUGLOG(5, "ZSTDMT_createCompressionJob: preparing job %u to compress %u bytes with %u preload ", + mtctx->nextJobID, (U32)srcSize, (U32)mtctx->inBuff.prefix.size); + mtctx->jobs[jobID].src.start = src; + mtctx->jobs[jobID].src.size = srcSize; + assert(mtctx->inBuff.filled >= srcSize); + mtctx->jobs[jobID].prefix = mtctx->inBuff.prefix; + mtctx->jobs[jobID].consumed = 0; + mtctx->jobs[jobID].cSize = 0; + mtctx->jobs[jobID].params = mtctx->params; + mtctx->jobs[jobID].cdict = mtctx->nextJobID==0 ? mtctx->cdict : NULL; + mtctx->jobs[jobID].fullFrameSize = mtctx->frameContentSize; + mtctx->jobs[jobID].dstBuff = g_nullBuffer; + mtctx->jobs[jobID].cctxPool = mtctx->cctxPool; + mtctx->jobs[jobID].bufPool = mtctx->bufPool; + mtctx->jobs[jobID].seqPool = mtctx->seqPool; + mtctx->jobs[jobID].serial = &mtctx->serial; + mtctx->jobs[jobID].jobID = mtctx->nextJobID; + mtctx->jobs[jobID].firstJob = (mtctx->nextJobID==0); + mtctx->jobs[jobID].lastJob = endFrame; mtctx->jobs[jobID].frameChecksumNeeded = mtctx->params.fParams.checksumFlag && endFrame && (mtctx->nextJobID>0); - mtctx->jobs[jobID].dstFlushed = 0; - - /* Update the round buffer pos and clear the input buffer to be reset */ - mtctx->roundBuff.pos += srcSize; - mtctx->inBuff.buffer = g_nullBuffer; - mtctx->inBuff.filled = 0; - /* Set the prefix */ - if (!endFrame) { - size_t const newPrefixSize = MIN(srcSize, mtctx->targetPrefixSize); - mtctx->inBuff.prefix.start = src + srcSize - newPrefixSize; - mtctx->inBuff.prefix.size = newPrefixSize; - } else { /* endFrame==1 => no need for another input buffer */ - mtctx->inBuff.prefix = kNullRange; - mtctx->frameEnded = endFrame; - if (mtctx->nextJobID == 0) { - /* single job exception : checksum is already calculated directly within worker thread */ - mtctx->params.fParams.checksumFlag = 0; - } } - - if ( (srcSize == 0) - && (mtctx->nextJobID>0)/*single job must also write frame header*/ ) { - DEBUGLOG(5, "ZSTDMT_createCompressionJob: creating a last empty block to end frame"); - assert(endOp == ZSTD_e_end); /* only possible case : need to end the frame with an empty last block */ - ZSTDMT_writeLastEmptyBlock(mtctx->jobs + jobID); - mtctx->nextJobID++; - return 0; - } - } - - DEBUGLOG(5, "ZSTDMT_createCompressionJob: posting job %u : %u bytes (end:%u, jobNb == %u (mod:%u))", - mtctx->nextJobID, - (U32)mtctx->jobs[jobID].src.size, - mtctx->jobs[jobID].lastJob, - mtctx->nextJobID, - jobID); - if (POOL_tryAdd(mtctx->factory, ZSTDMT_compressionJob, &mtctx->jobs[jobID])) { - mtctx->nextJobID++; - mtctx->jobReady = 0; - } else { - DEBUGLOG(5, "ZSTDMT_createCompressionJob: no worker available for job %u", mtctx->nextJobID); - mtctx->jobReady = 1; - } - return 0; -} - - -/*! ZSTDMT_flushProduced() : + mtctx->jobs[jobID].dstFlushed = 0; + + /* Update the round buffer pos and clear the input buffer to be reset */ + mtctx->roundBuff.pos += srcSize; + mtctx->inBuff.buffer = g_nullBuffer; + mtctx->inBuff.filled = 0; + /* Set the prefix */ + if (!endFrame) { + size_t const newPrefixSize = MIN(srcSize, mtctx->targetPrefixSize); + mtctx->inBuff.prefix.start = src + srcSize - newPrefixSize; + mtctx->inBuff.prefix.size = newPrefixSize; + } else { /* endFrame==1 => no need for another input buffer */ + mtctx->inBuff.prefix = kNullRange; + mtctx->frameEnded = endFrame; + if (mtctx->nextJobID == 0) { + /* single job exception : checksum is already calculated directly within worker thread */ + mtctx->params.fParams.checksumFlag = 0; + } } + + if ( (srcSize == 0) + && (mtctx->nextJobID>0)/*single job must also write frame header*/ ) { + DEBUGLOG(5, "ZSTDMT_createCompressionJob: creating a last empty block to end frame"); + assert(endOp == ZSTD_e_end); /* only possible case : need to end the frame with an empty last block */ + ZSTDMT_writeLastEmptyBlock(mtctx->jobs + jobID); + mtctx->nextJobID++; + return 0; + } + } + + DEBUGLOG(5, "ZSTDMT_createCompressionJob: posting job %u : %u bytes (end:%u, jobNb == %u (mod:%u))", + mtctx->nextJobID, + (U32)mtctx->jobs[jobID].src.size, + mtctx->jobs[jobID].lastJob, + mtctx->nextJobID, + jobID); + if (POOL_tryAdd(mtctx->factory, ZSTDMT_compressionJob, &mtctx->jobs[jobID])) { + mtctx->nextJobID++; + mtctx->jobReady = 0; + } else { + DEBUGLOG(5, "ZSTDMT_createCompressionJob: no worker available for job %u", mtctx->nextJobID); + mtctx->jobReady = 1; + } + return 0; +} + + +/*! ZSTDMT_flushProduced() : * flush whatever data has been produced but not yet flushed in current job. * move to next job if current one is fully flushed. - * `output` : `pos` will be updated with amount of data flushed . - * `blockToFlush` : if >0, the function will block and wait if there is no data available to flush . - * @return : amount of data remaining within internal buffer, 0 if no more, 1 if unknown but > 0, or an error code */ -static size_t ZSTDMT_flushProduced(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, unsigned blockToFlush, ZSTD_EndDirective end) -{ - unsigned const wJobID = mtctx->doneJobID & mtctx->jobIDMask; - DEBUGLOG(5, "ZSTDMT_flushProduced (blocking:%u , job %u <= %u)", - blockToFlush, mtctx->doneJobID, mtctx->nextJobID); - assert(output->size >= output->pos); - - ZSTD_PTHREAD_MUTEX_LOCK(&mtctx->jobs[wJobID].job_mutex); - if ( blockToFlush - && (mtctx->doneJobID < mtctx->nextJobID) ) { - assert(mtctx->jobs[wJobID].dstFlushed <= mtctx->jobs[wJobID].cSize); - while (mtctx->jobs[wJobID].dstFlushed == mtctx->jobs[wJobID].cSize) { /* nothing to flush */ - if (mtctx->jobs[wJobID].consumed == mtctx->jobs[wJobID].src.size) { - DEBUGLOG(5, "job %u is completely consumed (%u == %u) => don't wait for cond, there will be none", - mtctx->doneJobID, (U32)mtctx->jobs[wJobID].consumed, (U32)mtctx->jobs[wJobID].src.size); - break; - } - DEBUGLOG(5, "waiting for something to flush from job %u (currently flushed: %u bytes)", - mtctx->doneJobID, (U32)mtctx->jobs[wJobID].dstFlushed); - ZSTD_pthread_cond_wait(&mtctx->jobs[wJobID].job_cond, &mtctx->jobs[wJobID].job_mutex); /* block when nothing to flush but some to come */ - } } - - /* try to flush something */ - { size_t cSize = mtctx->jobs[wJobID].cSize; /* shared */ - size_t const srcConsumed = mtctx->jobs[wJobID].consumed; /* shared */ + * `output` : `pos` will be updated with amount of data flushed . + * `blockToFlush` : if >0, the function will block and wait if there is no data available to flush . + * @return : amount of data remaining within internal buffer, 0 if no more, 1 if unknown but > 0, or an error code */ +static size_t ZSTDMT_flushProduced(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, unsigned blockToFlush, ZSTD_EndDirective end) +{ + unsigned const wJobID = mtctx->doneJobID & mtctx->jobIDMask; + DEBUGLOG(5, "ZSTDMT_flushProduced (blocking:%u , job %u <= %u)", + blockToFlush, mtctx->doneJobID, mtctx->nextJobID); + assert(output->size >= output->pos); + + ZSTD_PTHREAD_MUTEX_LOCK(&mtctx->jobs[wJobID].job_mutex); + if ( blockToFlush + && (mtctx->doneJobID < mtctx->nextJobID) ) { + assert(mtctx->jobs[wJobID].dstFlushed <= mtctx->jobs[wJobID].cSize); + while (mtctx->jobs[wJobID].dstFlushed == mtctx->jobs[wJobID].cSize) { /* nothing to flush */ + if (mtctx->jobs[wJobID].consumed == mtctx->jobs[wJobID].src.size) { + DEBUGLOG(5, "job %u is completely consumed (%u == %u) => don't wait for cond, there will be none", + mtctx->doneJobID, (U32)mtctx->jobs[wJobID].consumed, (U32)mtctx->jobs[wJobID].src.size); + break; + } + DEBUGLOG(5, "waiting for something to flush from job %u (currently flushed: %u bytes)", + mtctx->doneJobID, (U32)mtctx->jobs[wJobID].dstFlushed); + ZSTD_pthread_cond_wait(&mtctx->jobs[wJobID].job_cond, &mtctx->jobs[wJobID].job_mutex); /* block when nothing to flush but some to come */ + } } + + /* try to flush something */ + { size_t cSize = mtctx->jobs[wJobID].cSize; /* shared */ + size_t const srcConsumed = mtctx->jobs[wJobID].consumed; /* shared */ size_t const srcSize = mtctx->jobs[wJobID].src.size; /* read-only, could be done after mutex lock, but no-declaration-after-statement */ - ZSTD_pthread_mutex_unlock(&mtctx->jobs[wJobID].job_mutex); - if (ZSTD_isError(cSize)) { - DEBUGLOG(5, "ZSTDMT_flushProduced: job %u : compression error detected : %s", - mtctx->doneJobID, ZSTD_getErrorName(cSize)); - ZSTDMT_waitForAllJobsCompleted(mtctx); - ZSTDMT_releaseAllJobResources(mtctx); - return cSize; - } - /* add frame checksum if necessary (can only happen once) */ - assert(srcConsumed <= srcSize); - if ( (srcConsumed == srcSize) /* job completed -> worker no longer active */ - && mtctx->jobs[wJobID].frameChecksumNeeded ) { - U32 const checksum = (U32)XXH64_digest(&mtctx->serial.xxhState); - DEBUGLOG(4, "ZSTDMT_flushProduced: writing checksum : %08X \n", checksum); - MEM_writeLE32((char*)mtctx->jobs[wJobID].dstBuff.start + mtctx->jobs[wJobID].cSize, checksum); - cSize += 4; - mtctx->jobs[wJobID].cSize += 4; /* can write this shared value, as worker is no longer active */ - mtctx->jobs[wJobID].frameChecksumNeeded = 0; - } - - if (cSize > 0) { /* compression is ongoing or completed */ - size_t const toFlush = MIN(cSize - mtctx->jobs[wJobID].dstFlushed, output->size - output->pos); - DEBUGLOG(5, "ZSTDMT_flushProduced: Flushing %u bytes from job %u (completion:%u/%u, generated:%u)", - (U32)toFlush, mtctx->doneJobID, (U32)srcConsumed, (U32)srcSize, (U32)cSize); - assert(mtctx->doneJobID < mtctx->nextJobID); - assert(cSize >= mtctx->jobs[wJobID].dstFlushed); - assert(mtctx->jobs[wJobID].dstBuff.start != NULL); + ZSTD_pthread_mutex_unlock(&mtctx->jobs[wJobID].job_mutex); + if (ZSTD_isError(cSize)) { + DEBUGLOG(5, "ZSTDMT_flushProduced: job %u : compression error detected : %s", + mtctx->doneJobID, ZSTD_getErrorName(cSize)); + ZSTDMT_waitForAllJobsCompleted(mtctx); + ZSTDMT_releaseAllJobResources(mtctx); + return cSize; + } + /* add frame checksum if necessary (can only happen once) */ + assert(srcConsumed <= srcSize); + if ( (srcConsumed == srcSize) /* job completed -> worker no longer active */ + && mtctx->jobs[wJobID].frameChecksumNeeded ) { + U32 const checksum = (U32)XXH64_digest(&mtctx->serial.xxhState); + DEBUGLOG(4, "ZSTDMT_flushProduced: writing checksum : %08X \n", checksum); + MEM_writeLE32((char*)mtctx->jobs[wJobID].dstBuff.start + mtctx->jobs[wJobID].cSize, checksum); + cSize += 4; + mtctx->jobs[wJobID].cSize += 4; /* can write this shared value, as worker is no longer active */ + mtctx->jobs[wJobID].frameChecksumNeeded = 0; + } + + if (cSize > 0) { /* compression is ongoing or completed */ + size_t const toFlush = MIN(cSize - mtctx->jobs[wJobID].dstFlushed, output->size - output->pos); + DEBUGLOG(5, "ZSTDMT_flushProduced: Flushing %u bytes from job %u (completion:%u/%u, generated:%u)", + (U32)toFlush, mtctx->doneJobID, (U32)srcConsumed, (U32)srcSize, (U32)cSize); + assert(mtctx->doneJobID < mtctx->nextJobID); + assert(cSize >= mtctx->jobs[wJobID].dstFlushed); + assert(mtctx->jobs[wJobID].dstBuff.start != NULL); if (toFlush > 0) { ZSTD_memcpy((char*)output->dst + output->pos, (const char*)mtctx->jobs[wJobID].dstBuff.start + mtctx->jobs[wJobID].dstFlushed, toFlush); } - output->pos += toFlush; - mtctx->jobs[wJobID].dstFlushed += toFlush; /* can write : this value is only used by mtctx */ - + output->pos += toFlush; + mtctx->jobs[wJobID].dstFlushed += toFlush; /* can write : this value is only used by mtctx */ + if ( (srcConsumed == srcSize) /* job is completed */ - && (mtctx->jobs[wJobID].dstFlushed == cSize) ) { /* output buffer fully flushed => free this job position */ - DEBUGLOG(5, "Job %u completed (%u bytes), moving to next one", - mtctx->doneJobID, (U32)mtctx->jobs[wJobID].dstFlushed); - ZSTDMT_releaseBuffer(mtctx->bufPool, mtctx->jobs[wJobID].dstBuff); + && (mtctx->jobs[wJobID].dstFlushed == cSize) ) { /* output buffer fully flushed => free this job position */ + DEBUGLOG(5, "Job %u completed (%u bytes), moving to next one", + mtctx->doneJobID, (U32)mtctx->jobs[wJobID].dstFlushed); + ZSTDMT_releaseBuffer(mtctx->bufPool, mtctx->jobs[wJobID].dstBuff); DEBUGLOG(5, "dstBuffer released"); - mtctx->jobs[wJobID].dstBuff = g_nullBuffer; - mtctx->jobs[wJobID].cSize = 0; /* ensure this job slot is considered "not started" in future check */ - mtctx->consumed += srcSize; - mtctx->produced += cSize; - mtctx->doneJobID++; - } } - - /* return value : how many bytes left in buffer ; fake it to 1 when unknown but >0 */ - if (cSize > mtctx->jobs[wJobID].dstFlushed) return (cSize - mtctx->jobs[wJobID].dstFlushed); - if (srcSize > srcConsumed) return 1; /* current job not completely compressed */ - } - if (mtctx->doneJobID < mtctx->nextJobID) return 1; /* some more jobs ongoing */ - if (mtctx->jobReady) return 1; /* one job is ready to push, just not yet in the list */ - if (mtctx->inBuff.filled > 0) return 1; /* input is not empty, and still needs to be converted into a job */ - mtctx->allJobsCompleted = mtctx->frameEnded; /* all jobs are entirely flushed => if this one is last one, frame is completed */ - if (end == ZSTD_e_end) return !mtctx->frameEnded; /* for ZSTD_e_end, question becomes : is frame completed ? instead of : are internal buffers fully flushed ? */ - return 0; /* internal buffers fully flushed */ -} - -/** - * Returns the range of data used by the earliest job that is not yet complete. - * If the data of the first job is broken up into two segments, we cover both - * sections. - */ -static range_t ZSTDMT_getInputDataInUse(ZSTDMT_CCtx* mtctx) -{ - unsigned const firstJobID = mtctx->doneJobID; - unsigned const lastJobID = mtctx->nextJobID; - unsigned jobID; - - for (jobID = firstJobID; jobID < lastJobID; ++jobID) { - unsigned const wJobID = jobID & mtctx->jobIDMask; - size_t consumed; - - ZSTD_PTHREAD_MUTEX_LOCK(&mtctx->jobs[wJobID].job_mutex); - consumed = mtctx->jobs[wJobID].consumed; - ZSTD_pthread_mutex_unlock(&mtctx->jobs[wJobID].job_mutex); - - if (consumed < mtctx->jobs[wJobID].src.size) { - range_t range = mtctx->jobs[wJobID].prefix; - if (range.size == 0) { - /* Empty prefix */ - range = mtctx->jobs[wJobID].src; - } - /* Job source in multiple segments not supported yet */ - assert(range.start <= mtctx->jobs[wJobID].src.start); - return range; - } - } - return kNullRange; -} - -/** - * Returns non-zero iff buffer and range overlap. - */ -static int ZSTDMT_isOverlapped(buffer_t buffer, range_t range) -{ - BYTE const* const bufferStart = (BYTE const*)buffer.start; - BYTE const* const rangeStart = (BYTE const*)range.start; - - if (rangeStart == NULL || bufferStart == NULL) - return 0; - + mtctx->jobs[wJobID].dstBuff = g_nullBuffer; + mtctx->jobs[wJobID].cSize = 0; /* ensure this job slot is considered "not started" in future check */ + mtctx->consumed += srcSize; + mtctx->produced += cSize; + mtctx->doneJobID++; + } } + + /* return value : how many bytes left in buffer ; fake it to 1 when unknown but >0 */ + if (cSize > mtctx->jobs[wJobID].dstFlushed) return (cSize - mtctx->jobs[wJobID].dstFlushed); + if (srcSize > srcConsumed) return 1; /* current job not completely compressed */ + } + if (mtctx->doneJobID < mtctx->nextJobID) return 1; /* some more jobs ongoing */ + if (mtctx->jobReady) return 1; /* one job is ready to push, just not yet in the list */ + if (mtctx->inBuff.filled > 0) return 1; /* input is not empty, and still needs to be converted into a job */ + mtctx->allJobsCompleted = mtctx->frameEnded; /* all jobs are entirely flushed => if this one is last one, frame is completed */ + if (end == ZSTD_e_end) return !mtctx->frameEnded; /* for ZSTD_e_end, question becomes : is frame completed ? instead of : are internal buffers fully flushed ? */ + return 0; /* internal buffers fully flushed */ +} + +/** + * Returns the range of data used by the earliest job that is not yet complete. + * If the data of the first job is broken up into two segments, we cover both + * sections. + */ +static range_t ZSTDMT_getInputDataInUse(ZSTDMT_CCtx* mtctx) +{ + unsigned const firstJobID = mtctx->doneJobID; + unsigned const lastJobID = mtctx->nextJobID; + unsigned jobID; + + for (jobID = firstJobID; jobID < lastJobID; ++jobID) { + unsigned const wJobID = jobID & mtctx->jobIDMask; + size_t consumed; + + ZSTD_PTHREAD_MUTEX_LOCK(&mtctx->jobs[wJobID].job_mutex); + consumed = mtctx->jobs[wJobID].consumed; + ZSTD_pthread_mutex_unlock(&mtctx->jobs[wJobID].job_mutex); + + if (consumed < mtctx->jobs[wJobID].src.size) { + range_t range = mtctx->jobs[wJobID].prefix; + if (range.size == 0) { + /* Empty prefix */ + range = mtctx->jobs[wJobID].src; + } + /* Job source in multiple segments not supported yet */ + assert(range.start <= mtctx->jobs[wJobID].src.start); + return range; + } + } + return kNullRange; +} + +/** + * Returns non-zero iff buffer and range overlap. + */ +static int ZSTDMT_isOverlapped(buffer_t buffer, range_t range) +{ + BYTE const* const bufferStart = (BYTE const*)buffer.start; + BYTE const* const rangeStart = (BYTE const*)range.start; + + if (rangeStart == NULL || bufferStart == NULL) + return 0; + { BYTE const* const bufferEnd = bufferStart + buffer.capacity; BYTE const* const rangeEnd = rangeStart + range.size; @@ -1573,112 +1573,112 @@ static int ZSTDMT_isOverlapped(buffer_t buffer, range_t range) return bufferStart < rangeEnd && rangeStart < bufferEnd; } -} - -static int ZSTDMT_doesOverlapWindow(buffer_t buffer, ZSTD_window_t window) -{ - range_t extDict; - range_t prefix; - +} + +static int ZSTDMT_doesOverlapWindow(buffer_t buffer, ZSTD_window_t window) +{ + range_t extDict; + range_t prefix; + DEBUGLOG(5, "ZSTDMT_doesOverlapWindow"); - extDict.start = window.dictBase + window.lowLimit; - extDict.size = window.dictLimit - window.lowLimit; - - prefix.start = window.base + window.dictLimit; - prefix.size = window.nextSrc - (window.base + window.dictLimit); - DEBUGLOG(5, "extDict [0x%zx, 0x%zx)", - (size_t)extDict.start, - (size_t)extDict.start + extDict.size); - DEBUGLOG(5, "prefix [0x%zx, 0x%zx)", - (size_t)prefix.start, - (size_t)prefix.start + prefix.size); - - return ZSTDMT_isOverlapped(buffer, extDict) - || ZSTDMT_isOverlapped(buffer, prefix); -} - -static void ZSTDMT_waitForLdmComplete(ZSTDMT_CCtx* mtctx, buffer_t buffer) -{ + extDict.start = window.dictBase + window.lowLimit; + extDict.size = window.dictLimit - window.lowLimit; + + prefix.start = window.base + window.dictLimit; + prefix.size = window.nextSrc - (window.base + window.dictLimit); + DEBUGLOG(5, "extDict [0x%zx, 0x%zx)", + (size_t)extDict.start, + (size_t)extDict.start + extDict.size); + DEBUGLOG(5, "prefix [0x%zx, 0x%zx)", + (size_t)prefix.start, + (size_t)prefix.start + prefix.size); + + return ZSTDMT_isOverlapped(buffer, extDict) + || ZSTDMT_isOverlapped(buffer, prefix); +} + +static void ZSTDMT_waitForLdmComplete(ZSTDMT_CCtx* mtctx, buffer_t buffer) +{ if (mtctx->params.ldmParams.enableLdm == ZSTD_ps_enable) { - ZSTD_pthread_mutex_t* mutex = &mtctx->serial.ldmWindowMutex; + ZSTD_pthread_mutex_t* mutex = &mtctx->serial.ldmWindowMutex; DEBUGLOG(5, "ZSTDMT_waitForLdmComplete"); - DEBUGLOG(5, "source [0x%zx, 0x%zx)", - (size_t)buffer.start, - (size_t)buffer.start + buffer.capacity); - ZSTD_PTHREAD_MUTEX_LOCK(mutex); - while (ZSTDMT_doesOverlapWindow(buffer, mtctx->serial.ldmWindow)) { + DEBUGLOG(5, "source [0x%zx, 0x%zx)", + (size_t)buffer.start, + (size_t)buffer.start + buffer.capacity); + ZSTD_PTHREAD_MUTEX_LOCK(mutex); + while (ZSTDMT_doesOverlapWindow(buffer, mtctx->serial.ldmWindow)) { DEBUGLOG(5, "Waiting for LDM to finish..."); - ZSTD_pthread_cond_wait(&mtctx->serial.ldmWindowCond, mutex); - } - DEBUGLOG(6, "Done waiting for LDM to finish"); - ZSTD_pthread_mutex_unlock(mutex); - } -} - -/** - * Attempts to set the inBuff to the next section to fill. - * If any part of the new section is still in use we give up. - * Returns non-zero if the buffer is filled. - */ -static int ZSTDMT_tryGetInputRange(ZSTDMT_CCtx* mtctx) -{ - range_t const inUse = ZSTDMT_getInputDataInUse(mtctx); - size_t const spaceLeft = mtctx->roundBuff.capacity - mtctx->roundBuff.pos; - size_t const target = mtctx->targetSectionSize; - buffer_t buffer; - + ZSTD_pthread_cond_wait(&mtctx->serial.ldmWindowCond, mutex); + } + DEBUGLOG(6, "Done waiting for LDM to finish"); + ZSTD_pthread_mutex_unlock(mutex); + } +} + +/** + * Attempts to set the inBuff to the next section to fill. + * If any part of the new section is still in use we give up. + * Returns non-zero if the buffer is filled. + */ +static int ZSTDMT_tryGetInputRange(ZSTDMT_CCtx* mtctx) +{ + range_t const inUse = ZSTDMT_getInputDataInUse(mtctx); + size_t const spaceLeft = mtctx->roundBuff.capacity - mtctx->roundBuff.pos; + size_t const target = mtctx->targetSectionSize; + buffer_t buffer; + DEBUGLOG(5, "ZSTDMT_tryGetInputRange"); - assert(mtctx->inBuff.buffer.start == NULL); - assert(mtctx->roundBuff.capacity >= target); - - if (spaceLeft < target) { - /* ZSTD_invalidateRepCodes() doesn't work for extDict variants. - * Simply copy the prefix to the beginning in that case. - */ - BYTE* const start = (BYTE*)mtctx->roundBuff.buffer; - size_t const prefixSize = mtctx->inBuff.prefix.size; - - buffer.start = start; - buffer.capacity = prefixSize; - if (ZSTDMT_isOverlapped(buffer, inUse)) { + assert(mtctx->inBuff.buffer.start == NULL); + assert(mtctx->roundBuff.capacity >= target); + + if (spaceLeft < target) { + /* ZSTD_invalidateRepCodes() doesn't work for extDict variants. + * Simply copy the prefix to the beginning in that case. + */ + BYTE* const start = (BYTE*)mtctx->roundBuff.buffer; + size_t const prefixSize = mtctx->inBuff.prefix.size; + + buffer.start = start; + buffer.capacity = prefixSize; + if (ZSTDMT_isOverlapped(buffer, inUse)) { DEBUGLOG(5, "Waiting for buffer..."); - return 0; - } - ZSTDMT_waitForLdmComplete(mtctx, buffer); + return 0; + } + ZSTDMT_waitForLdmComplete(mtctx, buffer); ZSTD_memmove(start, mtctx->inBuff.prefix.start, prefixSize); - mtctx->inBuff.prefix.start = start; - mtctx->roundBuff.pos = prefixSize; - } - buffer.start = mtctx->roundBuff.buffer + mtctx->roundBuff.pos; - buffer.capacity = target; - - if (ZSTDMT_isOverlapped(buffer, inUse)) { + mtctx->inBuff.prefix.start = start; + mtctx->roundBuff.pos = prefixSize; + } + buffer.start = mtctx->roundBuff.buffer + mtctx->roundBuff.pos; + buffer.capacity = target; + + if (ZSTDMT_isOverlapped(buffer, inUse)) { DEBUGLOG(5, "Waiting for buffer..."); - return 0; - } - assert(!ZSTDMT_isOverlapped(buffer, mtctx->inBuff.prefix)); - - ZSTDMT_waitForLdmComplete(mtctx, buffer); - - DEBUGLOG(5, "Using prefix range [%zx, %zx)", - (size_t)mtctx->inBuff.prefix.start, - (size_t)mtctx->inBuff.prefix.start + mtctx->inBuff.prefix.size); - DEBUGLOG(5, "Using source range [%zx, %zx)", - (size_t)buffer.start, - (size_t)buffer.start + buffer.capacity); - - - mtctx->inBuff.buffer = buffer; - mtctx->inBuff.filled = 0; - assert(mtctx->roundBuff.pos + buffer.capacity <= mtctx->roundBuff.capacity); - return 1; -} - + return 0; + } + assert(!ZSTDMT_isOverlapped(buffer, mtctx->inBuff.prefix)); + + ZSTDMT_waitForLdmComplete(mtctx, buffer); + + DEBUGLOG(5, "Using prefix range [%zx, %zx)", + (size_t)mtctx->inBuff.prefix.start, + (size_t)mtctx->inBuff.prefix.start + mtctx->inBuff.prefix.size); + DEBUGLOG(5, "Using source range [%zx, %zx)", + (size_t)buffer.start, + (size_t)buffer.start + buffer.capacity); + + + mtctx->inBuff.buffer = buffer; + mtctx->inBuff.filled = 0; + assert(mtctx->roundBuff.pos + buffer.capacity <= mtctx->roundBuff.capacity); + return 1; +} + typedef struct { size_t toLoad; /* The number of bytes to load from the input. */ int flush; /* Boolean declaring if we must flush because we found a synchronization point. */ } syncPoint_t; - + /** * Searches through the input for a synchronization point. If one is found, we * will instruct the caller to flush, and return the number of bytes to load. @@ -1782,54 +1782,54 @@ size_t ZSTDMT_nextInputSizeHint(const ZSTDMT_CCtx* mtctx) return hintInSize; } -/** ZSTDMT_compressStream_generic() : - * internal use only - exposed to be invoked from zstd_compress.c - * assumption : output and input are valid (pos <= size) - * @return : minimum amount of data remaining to flush, 0 if none */ -size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx, - ZSTD_outBuffer* output, - ZSTD_inBuffer* input, - ZSTD_EndDirective endOp) -{ - unsigned forwardInputProgress = 0; - DEBUGLOG(5, "ZSTDMT_compressStream_generic (endOp=%u, srcSize=%u)", - (U32)endOp, (U32)(input->size - input->pos)); - assert(output->pos <= output->size); - assert(input->pos <= input->size); - - if ((mtctx->frameEnded) && (endOp==ZSTD_e_continue)) { - /* current frame being ended. Only flush/end are allowed */ - return ERROR(stage_wrong); - } - - /* fill input buffer */ - if ( (!mtctx->jobReady) - && (input->size > input->pos) ) { /* support NULL input */ - if (mtctx->inBuff.buffer.start == NULL) { - assert(mtctx->inBuff.filled == 0); /* Can't fill an empty buffer */ - if (!ZSTDMT_tryGetInputRange(mtctx)) { - /* It is only possible for this operation to fail if there are - * still compression jobs ongoing. - */ +/** ZSTDMT_compressStream_generic() : + * internal use only - exposed to be invoked from zstd_compress.c + * assumption : output and input are valid (pos <= size) + * @return : minimum amount of data remaining to flush, 0 if none */ +size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx, + ZSTD_outBuffer* output, + ZSTD_inBuffer* input, + ZSTD_EndDirective endOp) +{ + unsigned forwardInputProgress = 0; + DEBUGLOG(5, "ZSTDMT_compressStream_generic (endOp=%u, srcSize=%u)", + (U32)endOp, (U32)(input->size - input->pos)); + assert(output->pos <= output->size); + assert(input->pos <= input->size); + + if ((mtctx->frameEnded) && (endOp==ZSTD_e_continue)) { + /* current frame being ended. Only flush/end are allowed */ + return ERROR(stage_wrong); + } + + /* fill input buffer */ + if ( (!mtctx->jobReady) + && (input->size > input->pos) ) { /* support NULL input */ + if (mtctx->inBuff.buffer.start == NULL) { + assert(mtctx->inBuff.filled == 0); /* Can't fill an empty buffer */ + if (!ZSTDMT_tryGetInputRange(mtctx)) { + /* It is only possible for this operation to fail if there are + * still compression jobs ongoing. + */ DEBUGLOG(5, "ZSTDMT_tryGetInputRange failed"); - assert(mtctx->doneJobID != mtctx->nextJobID); + assert(mtctx->doneJobID != mtctx->nextJobID); } else DEBUGLOG(5, "ZSTDMT_tryGetInputRange completed successfully : mtctx->inBuff.buffer.start = %p", mtctx->inBuff.buffer.start); - } - if (mtctx->inBuff.buffer.start != NULL) { + } + if (mtctx->inBuff.buffer.start != NULL) { syncPoint_t const syncPoint = findSynchronizationPoint(mtctx, *input); if (syncPoint.flush && endOp == ZSTD_e_continue) { endOp = ZSTD_e_flush; } - assert(mtctx->inBuff.buffer.capacity >= mtctx->targetSectionSize); - DEBUGLOG(5, "ZSTDMT_compressStream_generic: adding %u bytes on top of %u to buffer of size %u", + assert(mtctx->inBuff.buffer.capacity >= mtctx->targetSectionSize); + DEBUGLOG(5, "ZSTDMT_compressStream_generic: adding %u bytes on top of %u to buffer of size %u", (U32)syncPoint.toLoad, (U32)mtctx->inBuff.filled, (U32)mtctx->targetSectionSize); ZSTD_memcpy((char*)mtctx->inBuff.buffer.start + mtctx->inBuff.filled, (const char*)input->src + input->pos, syncPoint.toLoad); input->pos += syncPoint.toLoad; mtctx->inBuff.filled += syncPoint.toLoad; forwardInputProgress = syncPoint.toLoad>0; - } - } + } + } if ((input->pos < input->size) && (endOp == ZSTD_e_end)) { /* Can't end yet because the input is not fully consumed. * We are in one of these cases: @@ -1840,20 +1840,20 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx, assert(mtctx->inBuff.filled == 0 || mtctx->inBuff.filled == mtctx->targetSectionSize || mtctx->params.rsyncable); endOp = ZSTD_e_flush; } - - if ( (mtctx->jobReady) - || (mtctx->inBuff.filled >= mtctx->targetSectionSize) /* filled enough : let's compress */ - || ((endOp != ZSTD_e_continue) && (mtctx->inBuff.filled > 0)) /* something to flush : let's go */ - || ((endOp == ZSTD_e_end) && (!mtctx->frameEnded)) ) { /* must finish the frame with a zero-size block */ - size_t const jobSize = mtctx->inBuff.filled; - assert(mtctx->inBuff.filled <= mtctx->targetSectionSize); + + if ( (mtctx->jobReady) + || (mtctx->inBuff.filled >= mtctx->targetSectionSize) /* filled enough : let's compress */ + || ((endOp != ZSTD_e_continue) && (mtctx->inBuff.filled > 0)) /* something to flush : let's go */ + || ((endOp == ZSTD_e_end) && (!mtctx->frameEnded)) ) { /* must finish the frame with a zero-size block */ + size_t const jobSize = mtctx->inBuff.filled; + assert(mtctx->inBuff.filled <= mtctx->targetSectionSize); FORWARD_IF_ERROR( ZSTDMT_createCompressionJob(mtctx, jobSize, endOp) , ""); - } - - /* check for potential compressed data ready to be flushed */ - { size_t const remainingToFlush = ZSTDMT_flushProduced(mtctx, output, !forwardInputProgress, endOp); /* block if there was no forward input progress */ - if (input->pos < input->size) return MAX(remainingToFlush, 1); /* input not consumed : do not end flush yet */ + } + + /* check for potential compressed data ready to be flushed */ + { size_t const remainingToFlush = ZSTDMT_flushProduced(mtctx, output, !forwardInputProgress, endOp); /* block if there was no forward input progress */ + if (input->pos < input->size) return MAX(remainingToFlush, 1); /* input not consumed : do not end flush yet */ DEBUGLOG(5, "end of ZSTDMT_compressStream_generic: remainingToFlush = %u", (U32)remainingToFlush); - return remainingToFlush; - } -} + return remainingToFlush; + } +} diff --git a/contrib/libs/zstd/lib/compress/zstdmt_compress.h b/contrib/libs/zstd/lib/compress/zstdmt_compress.h index 271eb1ac71..c0bea93148 100644 --- a/contrib/libs/zstd/lib/compress/zstdmt_compress.h +++ b/contrib/libs/zstd/lib/compress/zstdmt_compress.h @@ -1,36 +1,36 @@ -/* +/* * Copyright (c) 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 ZSTDMT_COMPRESS_H - #define ZSTDMT_COMPRESS_H - - #if defined (__cplusplus) - extern "C" { - #endif - - -/* Note : This is an internal API. + * 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 ZSTDMT_COMPRESS_H + #define ZSTDMT_COMPRESS_H + + #if defined (__cplusplus) + extern "C" { + #endif + + +/* Note : This is an internal API. * These APIs used to be exposed with ZSTDLIB_API, - * because it used to be the only way to invoke MT compression. + * because it used to be the only way to invoke MT compression. * Now, you must use ZSTD_compress2 and ZSTD_compressStream2() instead. * * This API requires ZSTD_MULTITHREAD to be defined during compilation, * otherwise ZSTDMT_createCCtx*() will fail. */ - -/* === Dependencies === */ + +/* === Dependencies === */ #include "../common/zstd_deps.h" /* size_t */ -#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_parameters */ +#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_parameters */ #include "../zstd.h" /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTDLIB_API */ - - + + /* === Constants === */ #ifndef ZSTDMT_NBWORKERS_MAX /* a different value can be selected at compile time */ # define ZSTDMT_NBWORKERS_MAX ((sizeof(void*)==4) /*32-bit*/ ? 64 : 256) @@ -47,20 +47,20 @@ * === Not exposed in libzstd. Never invoke directly === * ======================================================== */ -/* === Memory management === */ -typedef struct ZSTDMT_CCtx_s ZSTDMT_CCtx; +/* === Memory management === */ +typedef struct ZSTDMT_CCtx_s ZSTDMT_CCtx; /* Requires ZSTD_MULTITHREAD to be defined during compilation, otherwise it will return NULL. */ ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem, ZSTD_threadPool *pool); size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx); - + size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx); - -/* === Streaming functions === */ - + +/* === Streaming functions === */ + size_t ZSTDMT_nextInputSizeHint(const ZSTDMT_CCtx* mtctx); - + /*! ZSTDMT_initCStream_internal() : * Private use only. Init streaming operation. * expects params to be valid. @@ -73,19 +73,19 @@ size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* mtctx, const void* dict, size_t dictSize, ZSTD_dictContentType_e dictContentType, const ZSTD_CDict* cdict, ZSTD_CCtx_params params, unsigned long long pledgedSrcSize); - -/*! ZSTDMT_compressStream_generic() : - * Combines ZSTDMT_compressStream() with optional ZSTDMT_flushStream() or ZSTDMT_endStream() - * depending on flush directive. - * @return : minimum amount of data still to be flushed - * 0 if fully flushed - * or an error code - * note : needs to be init using any ZSTD_initCStream*() variant */ + +/*! ZSTDMT_compressStream_generic() : + * Combines ZSTDMT_compressStream() with optional ZSTDMT_flushStream() or ZSTDMT_endStream() + * depending on flush directive. + * @return : minimum amount of data still to be flushed + * 0 if fully flushed + * or an error code + * note : needs to be init using any ZSTD_initCStream*() variant */ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input, ZSTD_EndDirective endOp); - + /*! ZSTDMT_toFlushNow() * Tell how many bytes are ready to be flushed immediately. * Probe the oldest active job (not yet entirely flushed) and check its output buffer. @@ -93,21 +93,21 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx, * or, it means oldest job is still active, but everything produced has been flushed so far, * therefore flushing is limited by speed of oldest job. */ size_t ZSTDMT_toFlushNow(ZSTDMT_CCtx* mtctx); - -/*! ZSTDMT_updateCParams_whileCompressing() : - * Updates only a selected set of compression parameters, to remain compatible with current frame. - * New parameters will be applied to next compression job. */ -void ZSTDMT_updateCParams_whileCompressing(ZSTDMT_CCtx* mtctx, const ZSTD_CCtx_params* cctxParams); - + +/*! ZSTDMT_updateCParams_whileCompressing() : + * Updates only a selected set of compression parameters, to remain compatible with current frame. + * New parameters will be applied to next compression job. */ +void ZSTDMT_updateCParams_whileCompressing(ZSTDMT_CCtx* mtctx, const ZSTD_CCtx_params* cctxParams); + /*! ZSTDMT_getFrameProgression(): * tells how much data has been consumed (input) and produced (output) for current frame. * able to count progression inside worker threads. - */ -ZSTD_frameProgression ZSTDMT_getFrameProgression(ZSTDMT_CCtx* mtctx); - - -#if defined (__cplusplus) -} -#endif - -#endif /* ZSTDMT_COMPRESS_H */ + */ +ZSTD_frameProgression ZSTDMT_getFrameProgression(ZSTDMT_CCtx* mtctx); + + +#if defined (__cplusplus) +} +#endif + +#endif /* ZSTDMT_COMPRESS_H */ diff --git a/contrib/libs/zstd/lib/decompress/huf_decompress.c b/contrib/libs/zstd/lib/decompress/huf_decompress.c index 2027188255..275ccf88d5 100644 --- a/contrib/libs/zstd/lib/decompress/huf_decompress.c +++ b/contrib/libs/zstd/lib/decompress/huf_decompress.c @@ -71,16 +71,16 @@ /* ************************************************************** * Error Management ****************************************************************/ -#define HUF_isError ERR_isError - - -/* ************************************************************** -* Byte alignment for workSpace management -****************************************************************/ -#define HUF_ALIGN(x, a) HUF_ALIGN_MASK((x), (a) - 1) -#define HUF_ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask)) +#define HUF_isError ERR_isError +/* ************************************************************** +* Byte alignment for workSpace management +****************************************************************/ +#define HUF_ALIGN(x, a) HUF_ALIGN_MASK((x), (a) - 1) +#define HUF_ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask)) + + /* ************************************************************** * BMI2 Variant Wrappers ****************************************************************/ @@ -350,7 +350,7 @@ size_t HUF_readDTableX1_wksp_bmi2(HUF_DTable* DTable, const void* src, size_t sr DEBUG_STATIC_ASSERT(HUF_DECOMPRESS_WORKSPACE_SIZE >= sizeof(*wksp)); if (sizeof(*wksp) > wkspSize) return ERROR(tableLog_tooLarge); - + DEBUG_STATIC_ASSERT(sizeof(DTableDesc) == sizeof(HUF_DTable)); /* ZSTD_memset(huffWeight, 0, sizeof(huffWeight)); */ /* is not necessary, even though some analyzer complain ... */ @@ -363,7 +363,7 @@ size_t HUF_readDTableX1_wksp_bmi2(HUF_DTable* DTable, const void* src, size_t sr U32 const maxTableLog = dtd.maxTableLog + 1; U32 const targetTableLog = MIN(maxTableLog, HUF_DECODER_FAST_TABLELOG); tableLog = HUF_rescaleStats(wksp->huffWeight, wksp->rankVal, nbSymbols, tableLog, targetTableLog); - if (tableLog > (U32)(dtd.maxTableLog+1)) return ERROR(tableLog_tooLarge); /* DTable too small, Huffman tree cannot fit in */ + if (tableLog > (U32)(dtd.maxTableLog+1)) return ERROR(tableLog_tooLarge); /* DTable too small, Huffman tree cannot fit in */ dtd.tableType = 0; dtd.tableLog = (BYTE)tableLog; ZSTD_memcpy(DTable, &dtd, sizeof(dtd)); @@ -477,7 +477,7 @@ size_t HUF_readDTableX1_wksp_bmi2(HUF_DTable* DTable, const void* src, size_t sr return iSize; } -FORCE_INLINE_TEMPLATE BYTE +FORCE_INLINE_TEMPLATE BYTE HUF_decodeSymbolX1(BIT_DStream_t* Dstream, const HUF_DEltX1* dt, const U32 dtLog) { size_t const val = BIT_lookBitsFast(Dstream, dtLog); /* note : dtLog >= 1 */ @@ -497,7 +497,7 @@ HUF_decodeSymbolX1(BIT_DStream_t* Dstream, const HUF_DEltX1* dt, const U32 dtLog if (MEM_64bits()) \ HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr) -HINT_INLINE size_t +HINT_INLINE size_t HUF_decodeStreamX1(BYTE* p, BIT_DStream_t* const bitDPtr, BYTE* const pEnd, const HUF_DEltX1* const dt, const U32 dtLog) { BYTE* const pStart = p; @@ -514,19 +514,19 @@ HUF_decodeStreamX1(BYTE* p, BIT_DStream_t* const bitDPtr, BYTE* const pEnd, cons BIT_reloadDStream(bitDPtr); } - /* [0-3] symbols remaining */ - if (MEM_32bits()) - while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd)) + /* [0-3] symbols remaining */ + if (MEM_32bits()) + while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd)) HUF_DECODE_SYMBOLX1_0(p, bitDPtr); - /* no more data to retrieve from bitstream, no need to reload */ + /* no more data to retrieve from bitstream, no need to reload */ while (p < pEnd) HUF_DECODE_SYMBOLX1_0(p, bitDPtr); return pEnd-pStart; } -FORCE_INLINE_TEMPLATE size_t +FORCE_INLINE_TEMPLATE size_t HUF_decompress1X1_usingDTable_internal_body( void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, @@ -540,7 +540,7 @@ HUF_decompress1X1_usingDTable_internal_body( DTableDesc const dtd = HUF_getDTableDesc(DTable); U32 const dtLog = dtd.tableLog; - CHECK_F( BIT_initDStream(&bitD, cSrc, cSrcSize) ); + CHECK_F( BIT_initDStream(&bitD, cSrc, cSrcSize) ); HUF_decodeStreamX1(op, &bitD, oend, dt, dtLog); @@ -549,7 +549,7 @@ HUF_decompress1X1_usingDTable_internal_body( return dstSize; } -FORCE_INLINE_TEMPLATE size_t +FORCE_INLINE_TEMPLATE size_t HUF_decompress4X1_usingDTable_internal_body( void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, @@ -592,12 +592,12 @@ HUF_decompress4X1_usingDTable_internal_body( if (length4 > cSrcSize) return ERROR(corruption_detected); /* overflow */ if (opStart4 > oend) return ERROR(corruption_detected); /* overflow */ - CHECK_F( BIT_initDStream(&bitD1, istart1, length1) ); - CHECK_F( BIT_initDStream(&bitD2, istart2, length2) ); - CHECK_F( BIT_initDStream(&bitD3, istart3, length3) ); - CHECK_F( BIT_initDStream(&bitD4, istart4, length4) ); + CHECK_F( BIT_initDStream(&bitD1, istart1, length1) ); + CHECK_F( BIT_initDStream(&bitD2, istart2, length2) ); + CHECK_F( BIT_initDStream(&bitD3, istart3, length3) ); + CHECK_F( BIT_initDStream(&bitD4, istart4, length4) ); - /* up to 16 symbols per loop (4 symbols per stream) in 64-bit mode */ + /* up to 16 symbols per loop (4 symbols per stream) in 64-bit mode */ if ((size_t)(oend - op4) >= sizeof(size_t)) { for ( ; (endSignal) & (op4 < olimit) ; ) { HUF_DECODE_SYMBOLX1_2(op1, &bitD1); @@ -624,8 +624,8 @@ HUF_decompress4X1_usingDTable_internal_body( } /* check corruption */ - /* note : should not be necessary : op# advance in lock step, and we control op4. - * but curiously, binary generated by gcc 7.2 & 7.3 with -mbmi2 runs faster when >=1 test is present */ + /* note : should not be necessary : op# advance in lock step, and we control op4. + * but curiously, binary generated by gcc 7.2 & 7.3 with -mbmi2 runs faster when >=1 test is present */ if (op1 > opStart2) return ERROR(corruption_detected); if (op2 > opStart3) return ERROR(corruption_detected); if (op3 > opStart4) return ERROR(corruption_detected); @@ -638,8 +638,8 @@ HUF_decompress4X1_usingDTable_internal_body( HUF_decodeStreamX1(op4, &bitD4, oend, dt, dtLog); /* check */ - { U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4); - if (!endCheck) return ERROR(corruption_detected); } + { U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4); + if (!endCheck) return ERROR(corruption_detected); } /* decoded size */ return dstSize; @@ -720,13 +720,13 @@ HUF_decompress4X1_usingDTable_internal_bmi2_asm( } #endif /* ZSTD_ENABLE_ASM_X86_64_BMI2 */ -typedef size_t (*HUF_decompress_usingDTable_t)(void *dst, size_t dstSize, - const void *cSrc, - size_t cSrcSize, - const HUF_DTable *DTable); - +typedef size_t (*HUF_decompress_usingDTable_t)(void *dst, size_t dstSize, + const void *cSrc, + size_t cSrcSize, + const HUF_DTable *DTable); + HUF_DGEN(HUF_decompress1X1_usingDTable_internal) - + static size_t HUF_decompress4X1_usingDTable_internal(void* dst, size_t dstSize, void const* cSrc, size_t cSrcSize, HUF_DTable const* DTable, int bmi2) { @@ -741,54 +741,54 @@ static size_t HUF_decompress4X1_usingDTable_internal(void* dst, size_t dstSize, #else (void)bmi2; #endif - + #if ZSTD_ENABLE_ASM_X86_64_BMI2 && defined(__BMI2__) return HUF_decompress4X1_usingDTable_internal_bmi2_asm(dst, dstSize, cSrc, cSrcSize, DTable); #else return HUF_decompress4X1_usingDTable_internal_default(dst, dstSize, cSrc, cSrcSize, DTable); #endif } - + size_t HUF_decompress1X1_usingDTable( - void* dst, size_t dstSize, - const void* cSrc, size_t cSrcSize, - const HUF_DTable* DTable) -{ + void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + const HUF_DTable* DTable) +{ DTableDesc dtd = HUF_getDTableDesc(DTable); if (dtd.tableType != 0) return ERROR(GENERIC); return HUF_decompress1X1_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0); } 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) -{ - const BYTE* ip = (const BYTE*) cSrc; + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize) +{ + const BYTE* ip = (const BYTE*) cSrc; size_t const hSize = HUF_readDTableX1_wksp(DCtx, cSrc, cSrcSize, workSpace, wkspSize); - if (HUF_isError(hSize)) return hSize; - if (hSize >= cSrcSize) return ERROR(srcSize_wrong); - ip += hSize; cSrcSize -= hSize; - + if (HUF_isError(hSize)) return hSize; + if (hSize >= cSrcSize) return ERROR(srcSize_wrong); + ip += hSize; cSrcSize -= hSize; + return HUF_decompress1X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, /* bmi2 */ 0); -} - - +} + + size_t HUF_decompress4X1_usingDTable( - void* dst, size_t dstSize, - const void* cSrc, size_t cSrcSize, - const HUF_DTable* DTable) -{ - DTableDesc dtd = HUF_getDTableDesc(DTable); - if (dtd.tableType != 0) return ERROR(GENERIC); + void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + const HUF_DTable* DTable) +{ + DTableDesc dtd = HUF_getDTableDesc(DTable); + if (dtd.tableType != 0) return ERROR(GENERIC); return HUF_decompress4X1_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0); -} - +} + static size_t HUF_decompress4X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, - const void* cSrc, size_t cSrcSize, - void* workSpace, size_t wkspSize, int bmi2) -{ + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize, int bmi2) +{ const BYTE* ip = (const BYTE*) cSrc; size_t const hSize = HUF_readDTableX1_wksp_bmi2(dctx, cSrc, cSrcSize, workSpace, wkspSize, bmi2); @@ -800,13 +800,13 @@ static size_t HUF_decompress4X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size } 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) -{ + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize) +{ return HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, 0); -} - - +} + + #endif /* HUF_FORCE_DECOMPRESS_X2 */ @@ -1059,16 +1059,16 @@ size_t HUF_readDTableX2_wksp_bmi2(HUF_DTable* DTable, size_t iSize; void* dtPtr = DTable+1; /* force compiler to avoid strict-aliasing */ HUF_DEltX2* const dt = (HUF_DEltX2*)dtPtr; - U32 *rankStart; + U32 *rankStart; HUF_ReadDTableX2_Workspace* const wksp = (HUF_ReadDTableX2_Workspace*)workSpace; - + if (sizeof(*wksp) > wkspSize) return ERROR(GENERIC); - + rankStart = wksp->rankStart0 + 1; ZSTD_memset(wksp->rankStats, 0, sizeof(wksp->rankStats)); ZSTD_memset(wksp->rankStart0, 0, sizeof(wksp->rankStart0)); - + DEBUG_STATIC_ASSERT(sizeof(HUF_DEltX2) == sizeof(HUF_DTable)); /* if compiler fails here, assertion is wrong */ if (maxTableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge); /* ZSTD_memset(weightList, 0, sizeof(weightList)); */ /* is not necessary, even though some analyzer complain ... */ @@ -1467,13 +1467,13 @@ size_t HUF_decompress1X2_usingDTable( } 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) + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize) { const BYTE* ip = (const BYTE*) cSrc; size_t const hSize = HUF_readDTableX2_wksp(DCtx, cSrc, cSrcSize, - workSpace, wkspSize); + workSpace, wkspSize); if (HUF_isError(hSize)) return hSize; if (hSize >= cSrcSize) return ERROR(srcSize_wrong); ip += hSize; cSrcSize -= hSize; @@ -1481,7 +1481,7 @@ size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize, return HUF_decompress1X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, /* bmi2 */ 0); } - + size_t HUF_decompress4X2_usingDTable( void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, @@ -1493,13 +1493,13 @@ size_t HUF_decompress4X2_usingDTable( } static size_t HUF_decompress4X2_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, - const void* cSrc, size_t cSrcSize, - void* workSpace, size_t wkspSize, int bmi2) + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize, int bmi2) { const BYTE* ip = (const BYTE*) cSrc; size_t hSize = HUF_readDTableX2_wksp(dctx, cSrc, cSrcSize, - workSpace, wkspSize); + workSpace, wkspSize); if (HUF_isError(hSize)) return hSize; if (hSize >= cSrcSize) return ERROR(srcSize_wrong); ip += hSize; cSrcSize -= hSize; @@ -1508,13 +1508,13 @@ static size_t HUF_decompress4X2_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size } 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) -{ + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize) +{ return HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, /* bmi2 */ 0); -} - - +} + + #endif /* HUF_FORCE_DECOMPRESS_X1 */ @@ -1586,13 +1586,13 @@ static const algo_time_t algoTime[16 /* Quantization */][2 /* single, double */] #endif /** HUF_selectDecoder() : - * Tells which decoder is likely to decode faster, - * based on a set of pre-computed metrics. + * Tells which decoder is likely to decode faster, + * based on a set of pre-computed metrics. * @return : 0==HUF_decompress4X1, 1==HUF_decompress4X2 . - * Assumption : 0 < dstSize <= 128 KB */ + * Assumption : 0 < dstSize <= 128 KB */ U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize) { - assert(dstSize > 0); + assert(dstSize > 0); assert(dstSize <= 128*1024); #if defined(HUF_FORCE_DECOMPRESS_X1) (void)dstSize; @@ -1604,25 +1604,25 @@ U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize) return 1; #else /* decoder timing evaluation */ - { U32 const Q = (cSrcSize >= dstSize) ? 15 : (U32)(cSrcSize * 16 / dstSize); /* Q < 16 */ - U32 const D256 = (U32)(dstSize >> 8); - U32 const DTime0 = algoTime[Q][0].tableTime + (algoTime[Q][0].decode256Time * D256); - U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256); + { U32 const Q = (cSrcSize >= dstSize) ? 15 : (U32)(cSrcSize * 16 / dstSize); /* Q < 16 */ + U32 const D256 = (U32)(dstSize >> 8); + U32 const DTime0 = algoTime[Q][0].tableTime + (algoTime[Q][0].decode256Time * D256); + U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256); DTime1 += DTime1 >> 5; /* small advantage to algorithm using less memory, to reduce cache eviction */ - return DTime1 < DTime0; + return DTime1 < DTime0; } #endif } -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) -{ +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) +{ /* validation checks */ if (dstSize == 0) return ERROR(dstSize_tooSmall); - if (cSrcSize == 0) return ERROR(corruption_detected); + if (cSrcSize == 0) return ERROR(corruption_detected); { U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize); #if defined(HUF_FORCE_DECOMPRESS_X1) @@ -1641,9 +1641,9 @@ size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, } } -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) +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) { /* validation checks */ if (dstSize == 0) return ERROR(dstSize_tooSmall); @@ -1664,17 +1664,17 @@ size_t HUF_decompress1X_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, cSrcSize, workSpace, wkspSize); #else return algoNb ? HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc, - cSrcSize, workSpace, wkspSize): + cSrcSize, workSpace, wkspSize): HUF_decompress1X1_DCtx_wksp(dctx, dst, dstSize, cSrc, - cSrcSize, workSpace, wkspSize); + cSrcSize, workSpace, wkspSize); #endif } } - - -size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2) -{ - DTableDesc const dtd = HUF_getDTableDesc(DTable); + + +size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2) +{ + DTableDesc const dtd = HUF_getDTableDesc(DTable); #if defined(HUF_FORCE_DECOMPRESS_X1) (void)dtd; assert(dtd.tableType == 0); @@ -1687,25 +1687,25 @@ size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const voi return dtd.tableType ? HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) : HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2); #endif -} - +} + #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) -{ - const BYTE* ip = (const BYTE*) cSrc; - +{ + const BYTE* ip = (const BYTE*) cSrc; + size_t const hSize = HUF_readDTableX1_wksp_bmi2(dctx, cSrc, cSrcSize, workSpace, wkspSize, bmi2); - if (HUF_isError(hSize)) return hSize; - if (hSize >= cSrcSize) return ERROR(srcSize_wrong); - ip += hSize; cSrcSize -= hSize; - + if (HUF_isError(hSize)) return hSize; + if (hSize >= cSrcSize) return ERROR(srcSize_wrong); + ip += hSize; cSrcSize -= hSize; + return HUF_decompress1X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2); -} +} #endif - -size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2) -{ - DTableDesc const dtd = HUF_getDTableDesc(DTable); + +size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2) +{ + DTableDesc const dtd = HUF_getDTableDesc(DTable); #if defined(HUF_FORCE_DECOMPRESS_X1) (void)dtd; assert(dtd.tableType == 0); @@ -1718,15 +1718,15 @@ size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const voi return dtd.tableType ? HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) : HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2); #endif -} - -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) -{ - /* validation checks */ - if (dstSize == 0) return ERROR(dstSize_tooSmall); - if (cSrcSize == 0) return ERROR(corruption_detected); - - { U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize); +} + +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) +{ + /* validation checks */ + if (dstSize == 0) return ERROR(dstSize_tooSmall); + if (cSrcSize == 0) return ERROR(corruption_detected); + + { U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize); #if defined(HUF_FORCE_DECOMPRESS_X1) (void)algoNb; assert(algoNb == 0); @@ -1739,8 +1739,8 @@ size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t ds return algoNb ? HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2) : HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2); #endif - } -} + } +} #ifndef ZSTD_NO_UNUSED_FUNCTIONS #ifndef HUF_FORCE_DECOMPRESS_X2 diff --git a/contrib/libs/zstd/lib/decompress/zstd_decompress.c b/contrib/libs/zstd/lib/decompress/zstd_decompress.c index b8bbefd538..15fee21c23 100644 --- a/contrib/libs/zstd/lib/decompress/zstd_decompress.c +++ b/contrib/libs/zstd/lib/decompress/zstd_decompress.c @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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. */ @@ -14,9 +14,9 @@ *****************************************************************/ /*! * HEAPMODE : - * Select how default decompression function ZSTD_decompress() allocates its context, - * on stack (0), or into heap (1, default; requires malloc()). - * Note that functions with explicit context such as ZSTD_decompressDCtx() are unaffected. + * Select how default decompression function ZSTD_decompress() allocates its context, + * on stack (0), or into heap (1, default; requires malloc()). + * Note that functions with explicit context such as ZSTD_decompressDCtx() are unaffected. */ #ifndef ZSTD_HEAPMODE # define ZSTD_HEAPMODE 1 @@ -24,18 +24,18 @@ /*! * LEGACY_SUPPORT : -* if set to 1+, ZSTD_decompress() can decode older formats (v0.1+) +* if set to 1+, ZSTD_decompress() can decode older formats (v0.1+) */ #ifndef ZSTD_LEGACY_SUPPORT # define ZSTD_LEGACY_SUPPORT 0 #endif /*! - * MAXWINDOWSIZE_DEFAULT : - * maximum window size accepted by DStream __by default__. - * Frames requiring more memory will be rejected. - * It's possible to set a different limit using ZSTD_DCtx_setMaxWindowSize(). - */ + * MAXWINDOWSIZE_DEFAULT : + * maximum window size accepted by DStream __by default__. + * Frames requiring more memory will be rejected. + * It's possible to set a different limit using ZSTD_DCtx_setMaxWindowSize(). + */ #ifndef ZSTD_MAXWINDOWSIZE_DEFAULT # define ZSTD_MAXWINDOWSIZE_DEFAULT (((U32)1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT) + 1) #endif @@ -216,23 +216,23 @@ static size_t ZSTD_DDictHashSet_addDDict(ZSTD_DDictHashSet* hashSet, const ZSTD_ /*-************************************************************* * Context management ***************************************************************/ -size_t ZSTD_sizeof_DCtx (const ZSTD_DCtx* dctx) -{ - if (dctx==NULL) return 0; /* support sizeof NULL */ - return sizeof(*dctx) - + ZSTD_sizeof_DDict(dctx->ddictLocal) - + dctx->inBuffSize + dctx->outBuffSize; -} +size_t ZSTD_sizeof_DCtx (const ZSTD_DCtx* dctx) +{ + if (dctx==NULL) return 0; /* support sizeof NULL */ + return sizeof(*dctx) + + ZSTD_sizeof_DDict(dctx->ddictLocal) + + dctx->inBuffSize + dctx->outBuffSize; +} size_t ZSTD_estimateDCtxSize(void) { return sizeof(ZSTD_DCtx); } - -static size_t ZSTD_startingInputLength(ZSTD_format_e format) + +static size_t ZSTD_startingInputLength(ZSTD_format_e format) { size_t const startingInputLength = ZSTD_FRAMEHEADERSIZE_PREFIX(format); - /* only supports formats ZSTD_f_zstd1 and ZSTD_f_zstd1_magicless */ - assert( (format == ZSTD_f_zstd1) || (format == ZSTD_f_zstd1_magicless) ); - return startingInputLength; + /* only supports formats ZSTD_f_zstd1 and ZSTD_f_zstd1_magicless */ + assert( (format == ZSTD_f_zstd1) || (format == ZSTD_f_zstd1_magicless) ); + return startingInputLength; } static void ZSTD_DCtx_resetParameters(ZSTD_DCtx* dctx) @@ -245,18 +245,18 @@ static void ZSTD_DCtx_resetParameters(ZSTD_DCtx* dctx) dctx->refMultipleDDicts = ZSTD_rmd_refSingleDDict; } -static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx) +static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx) { - dctx->staticSize = 0; - dctx->ddict = NULL; - dctx->ddictLocal = NULL; + dctx->staticSize = 0; + dctx->ddict = NULL; + dctx->ddictLocal = NULL; dctx->dictEnd = NULL; dctx->ddictIsCold = 0; dctx->dictUses = ZSTD_dont_use; - dctx->inBuff = NULL; - dctx->inBuffSize = 0; - dctx->outBuffSize = 0; - dctx->streamStage = zdss_init; + dctx->inBuff = NULL; + dctx->inBuffSize = 0; + dctx->outBuffSize = 0; + dctx->streamStage = zdss_init; #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1) dctx->legacyContext = NULL; dctx->previousLegacyVersion = 0; @@ -271,32 +271,32 @@ static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx) #ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION dctx->dictContentEndForFuzzing = NULL; #endif -} - -ZSTD_DCtx* ZSTD_initStaticDCtx(void *workspace, size_t workspaceSize) -{ - ZSTD_DCtx* const dctx = (ZSTD_DCtx*) workspace; - - if ((size_t)workspace & 7) return NULL; /* 8-aligned */ - if (workspaceSize < sizeof(ZSTD_DCtx)) return NULL; /* minimum size */ - - ZSTD_initDCtx_internal(dctx); - dctx->staticSize = workspaceSize; - dctx->inBuff = (char*)(dctx+1); +} + +ZSTD_DCtx* ZSTD_initStaticDCtx(void *workspace, size_t workspaceSize) +{ + ZSTD_DCtx* const dctx = (ZSTD_DCtx*) workspace; + + if ((size_t)workspace & 7) return NULL; /* 8-aligned */ + if (workspaceSize < sizeof(ZSTD_DCtx)) return NULL; /* minimum size */ + + ZSTD_initDCtx_internal(dctx); + dctx->staticSize = workspaceSize; + dctx->inBuff = (char*)(dctx+1); return dctx; } static ZSTD_DCtx* ZSTD_createDCtx_internal(ZSTD_customMem customMem) { if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL; - + { ZSTD_DCtx* const dctx = (ZSTD_DCtx*)ZSTD_customMalloc(sizeof(*dctx), customMem); - if (!dctx) return NULL; - dctx->customMem = customMem; - ZSTD_initDCtx_internal(dctx); - return dctx; - } -} - + if (!dctx) return NULL; + dctx->customMem = customMem; + ZSTD_initDCtx_internal(dctx); + return dctx; + } +} + ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem) { return ZSTD_createDCtx_internal(customMem); @@ -304,7 +304,7 @@ ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem) ZSTD_DCtx* ZSTD_createDCtx(void) { - DEBUGLOG(3, "ZSTD_createDCtx"); + DEBUGLOG(3, "ZSTD_createDCtx"); return ZSTD_createDCtx_internal(ZSTD_defaultCMem); } @@ -320,27 +320,27 @@ size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx) { if (dctx==NULL) return 0; /* support free on NULL */ RETURN_ERROR_IF(dctx->staticSize, memory_allocation, "not compatible with static DCtx"); - { ZSTD_customMem const cMem = dctx->customMem; + { ZSTD_customMem const cMem = dctx->customMem; ZSTD_clearDict(dctx); ZSTD_customFree(dctx->inBuff, cMem); - dctx->inBuff = NULL; -#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1) - if (dctx->legacyContext) - ZSTD_freeLegacyStreamContext(dctx->legacyContext, dctx->previousLegacyVersion); -#endif + dctx->inBuff = NULL; +#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1) + if (dctx->legacyContext) + ZSTD_freeLegacyStreamContext(dctx->legacyContext, dctx->previousLegacyVersion); +#endif if (dctx->ddictSet) { ZSTD_freeDDictHashSet(dctx->ddictSet, cMem); dctx->ddictSet = NULL; } ZSTD_customFree(dctx, cMem); - return 0; - } + return 0; + } } -/* no longer useful */ +/* no longer useful */ void ZSTD_copyDCtx(ZSTD_DCtx* dstDCtx, const ZSTD_DCtx* srcDCtx) { - size_t const toCopy = (size_t)((char*)(&dstDCtx->inBuff) - (char*)dstDCtx); + size_t const toCopy = (size_t)((char*)(&dstDCtx->inBuff) - (char*)dstDCtx); ZSTD_memcpy(dstDCtx, srcDCtx, toCopy); /* no need to copy workspace */ } @@ -369,8 +369,8 @@ static void ZSTD_DCtx_selectFrameDDict(ZSTD_DCtx* dctx) { /*-************************************************************* - * Frame header decoding - ***************************************************************/ + * Frame header decoding + ***************************************************************/ /*! ZSTD_isFrame() : * Tells if the content of `buffer` starts with a valid Frame Identifier. @@ -403,88 +403,88 @@ unsigned ZSTD_isSkippableFrame(const void* buffer, size_t size) return 0; } -/** ZSTD_frameHeaderSize_internal() : - * srcSize must be large enough to reach header size fields. - * note : only works for formats ZSTD_f_zstd1 and ZSTD_f_zstd1_magicless. - * @return : size of the Frame Header - * or an error code, which can be tested with ZSTD_isError() */ -static size_t ZSTD_frameHeaderSize_internal(const void* src, size_t srcSize, ZSTD_format_e format) -{ - size_t const minInputSize = ZSTD_startingInputLength(format); +/** ZSTD_frameHeaderSize_internal() : + * srcSize must be large enough to reach header size fields. + * note : only works for formats ZSTD_f_zstd1 and ZSTD_f_zstd1_magicless. + * @return : size of the Frame Header + * or an error code, which can be tested with ZSTD_isError() */ +static size_t ZSTD_frameHeaderSize_internal(const void* src, size_t srcSize, ZSTD_format_e format) +{ + size_t const minInputSize = ZSTD_startingInputLength(format); RETURN_ERROR_IF(srcSize < minInputSize, srcSize_wrong, ""); - - { BYTE const fhd = ((const BYTE*)src)[minInputSize-1]; + + { BYTE const fhd = ((const BYTE*)src)[minInputSize-1]; U32 const dictID= fhd & 3; U32 const singleSegment = (fhd >> 5) & 1; U32 const fcsId = fhd >> 6; - return minInputSize + !singleSegment - + ZSTD_did_fieldSize[dictID] + ZSTD_fcs_fieldSize[fcsId] - + (singleSegment && !fcsId); + return minInputSize + !singleSegment + + ZSTD_did_fieldSize[dictID] + ZSTD_fcs_fieldSize[fcsId] + + (singleSegment && !fcsId); } } -/** ZSTD_frameHeaderSize() : - * srcSize must be >= ZSTD_frameHeaderSize_prefix. +/** ZSTD_frameHeaderSize() : + * srcSize must be >= ZSTD_frameHeaderSize_prefix. * @return : size of the Frame Header, * or an error code (if srcSize is too small) */ -size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize) -{ - return ZSTD_frameHeaderSize_internal(src, srcSize, ZSTD_f_zstd1); -} - +size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize) +{ + return ZSTD_frameHeaderSize_internal(src, srcSize, ZSTD_f_zstd1); +} + /** ZSTD_getFrameHeader_advanced() : - * decode Frame Header, or require larger `srcSize`. - * note : only works for formats ZSTD_f_zstd1 and ZSTD_f_zstd1_magicless - * @return : 0, `zfhPtr` is correctly filled, - * >0, `srcSize` is too small, value is wanted `srcSize` amount, - * or an error code, which can be tested using ZSTD_isError() */ + * decode Frame Header, or require larger `srcSize`. + * note : only works for formats ZSTD_f_zstd1 and ZSTD_f_zstd1_magicless + * @return : 0, `zfhPtr` is correctly filled, + * >0, `srcSize` is too small, value is wanted `srcSize` amount, + * or an error code, which can be tested using ZSTD_isError() */ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format) { const BYTE* ip = (const BYTE*)src; - size_t const minInputSize = ZSTD_startingInputLength(format); + size_t const minInputSize = ZSTD_startingInputLength(format); ZSTD_memset(zfhPtr, 0, sizeof(*zfhPtr)); /* not strictly necessary, but static analyzer do not understand that zfhPtr is only going to be read only if return value is zero, since they are 2 different signals */ - if (srcSize < minInputSize) return minInputSize; + if (srcSize < minInputSize) return minInputSize; RETURN_ERROR_IF(src==NULL, GENERIC, "invalid parameter"); - - if ( (format != ZSTD_f_zstd1_magicless) - && (MEM_readLE32(src) != ZSTD_MAGICNUMBER) ) { + + if ( (format != ZSTD_f_zstd1_magicless) + && (MEM_readLE32(src) != ZSTD_MAGICNUMBER) ) { if ((MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { - /* skippable frame */ + /* skippable frame */ if (srcSize < ZSTD_SKIPPABLEHEADERSIZE) return ZSTD_SKIPPABLEHEADERSIZE; /* magic number + frame length */ ZSTD_memset(zfhPtr, 0, sizeof(*zfhPtr)); zfhPtr->frameContentSize = MEM_readLE32((const char *)src + ZSTD_FRAMEIDSIZE); - zfhPtr->frameType = ZSTD_skippableFrame; + zfhPtr->frameType = ZSTD_skippableFrame; return 0; } RETURN_ERROR(prefix_unknown, ""); } /* ensure there is enough `srcSize` to fully read/decode frame header */ - { size_t const fhsize = ZSTD_frameHeaderSize_internal(src, srcSize, format); - if (srcSize < fhsize) return fhsize; - zfhPtr->headerSize = (U32)fhsize; - } + { size_t const fhsize = ZSTD_frameHeaderSize_internal(src, srcSize, format); + if (srcSize < fhsize) return fhsize; + zfhPtr->headerSize = (U32)fhsize; + } - { BYTE const fhdByte = ip[minInputSize-1]; - size_t pos = minInputSize; + { BYTE const fhdByte = ip[minInputSize-1]; + size_t pos = minInputSize; U32 const dictIDSizeCode = fhdByte&3; U32 const checksumFlag = (fhdByte>>2)&1; U32 const singleSegment = (fhdByte>>5)&1; U32 const fcsID = fhdByte>>6; - U64 windowSize = 0; + U64 windowSize = 0; U32 dictID = 0; - U64 frameContentSize = ZSTD_CONTENTSIZE_UNKNOWN; + U64 frameContentSize = ZSTD_CONTENTSIZE_UNKNOWN; RETURN_ERROR_IF((fhdByte & 0x08) != 0, frameParameter_unsupported, "reserved bits, must be zero"); - + if (!singleSegment) { BYTE const wlByte = ip[pos++]; U32 const windowLog = (wlByte >> 3) + ZSTD_WINDOWLOG_ABSOLUTEMIN; RETURN_ERROR_IF(windowLog > ZSTD_WINDOWLOG_MAX, frameParameter_windowTooLarge, ""); - windowSize = (1ULL << windowLog); + windowSize = (1ULL << windowLog); windowSize += (windowSize >> 3) * (wlByte&7); } switch(dictIDSizeCode) @@ -507,52 +507,52 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s case 2 : frameContentSize = MEM_readLE32(ip+pos); break; case 3 : frameContentSize = MEM_readLE64(ip+pos); break; } - if (singleSegment) windowSize = frameContentSize; - - zfhPtr->frameType = ZSTD_frame; - zfhPtr->frameContentSize = frameContentSize; - zfhPtr->windowSize = windowSize; - zfhPtr->blockSizeMax = (unsigned) MIN(windowSize, ZSTD_BLOCKSIZE_MAX); - zfhPtr->dictID = dictID; - zfhPtr->checksumFlag = checksumFlag; + if (singleSegment) windowSize = frameContentSize; + + zfhPtr->frameType = ZSTD_frame; + zfhPtr->frameContentSize = frameContentSize; + zfhPtr->windowSize = windowSize; + zfhPtr->blockSizeMax = (unsigned) MIN(windowSize, ZSTD_BLOCKSIZE_MAX); + zfhPtr->dictID = dictID; + zfhPtr->checksumFlag = checksumFlag; } return 0; } -/** ZSTD_getFrameHeader() : - * decode Frame Header, or require larger `srcSize`. - * note : this function does not consume input, it only reads it. - * @return : 0, `zfhPtr` is correctly filled, - * >0, `srcSize` is too small, value is wanted `srcSize` amount, - * or an error code, which can be tested using ZSTD_isError() */ -size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize) -{ +/** ZSTD_getFrameHeader() : + * decode Frame Header, or require larger `srcSize`. + * note : this function does not consume input, it only reads it. + * @return : 0, `zfhPtr` is correctly filled, + * >0, `srcSize` is too small, value is wanted `srcSize` amount, + * or an error code, which can be tested using ZSTD_isError() */ +size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize) +{ return ZSTD_getFrameHeader_advanced(zfhPtr, src, srcSize, ZSTD_f_zstd1); -} - -/** ZSTD_getFrameContentSize() : - * compatible with legacy mode - * @return : decompressed size of the single frame pointed to be `src` if known, otherwise - * - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined - * - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) */ -unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize) -{ -#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1) - if (ZSTD_isLegacy(src, srcSize)) { - unsigned long long const ret = ZSTD_getDecompressedSize_legacy(src, srcSize); - return ret == 0 ? ZSTD_CONTENTSIZE_UNKNOWN : ret; - } -#endif - { ZSTD_frameHeader zfh; - if (ZSTD_getFrameHeader(&zfh, src, srcSize) != 0) - return ZSTD_CONTENTSIZE_ERROR; - if (zfh.frameType == ZSTD_skippableFrame) { - return 0; - } else { - return zfh.frameContentSize; - } } -} - +} + +/** ZSTD_getFrameContentSize() : + * compatible with legacy mode + * @return : decompressed size of the single frame pointed to be `src` if known, otherwise + * - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined + * - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) */ +unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize) +{ +#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1) + if (ZSTD_isLegacy(src, srcSize)) { + unsigned long long const ret = ZSTD_getDecompressedSize_legacy(src, srcSize); + return ret == 0 ? ZSTD_CONTENTSIZE_UNKNOWN : ret; + } +#endif + { ZSTD_frameHeader zfh; + if (ZSTD_getFrameHeader(&zfh, src, srcSize) != 0) + return ZSTD_CONTENTSIZE_ERROR; + if (zfh.frameType == ZSTD_skippableFrame) { + return 0; + } else { + return zfh.frameContentSize; + } } +} + static size_t readSkippableFrameSize(void const* src, size_t srcSize) { size_t const skippableHeaderSize = ZSTD_SKIPPABLEHEADERSIZE; @@ -601,65 +601,65 @@ ZSTDLIB_API size_t ZSTD_readSkippableFrame(void* dst, size_t dstCapacity, unsign return skippableContentSize; } -/** ZSTD_findDecompressedSize() : - * compatible with legacy mode - * `srcSize` must be the exact length of some number of ZSTD compressed and/or - * skippable frames - * @return : decompressed size of the frames contained */ -unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize) -{ - unsigned long long totalDstSize = 0; - +/** ZSTD_findDecompressedSize() : + * compatible with legacy mode + * `srcSize` must be the exact length of some number of ZSTD compressed and/or + * skippable frames + * @return : decompressed size of the frames contained */ +unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize) +{ + unsigned long long totalDstSize = 0; + while (srcSize >= ZSTD_startingInputLength(ZSTD_f_zstd1)) { - U32 const magicNumber = MEM_readLE32(src); - + U32 const magicNumber = MEM_readLE32(src); + if ((magicNumber & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { size_t const skippableSize = readSkippableFrameSize(src, srcSize); if (ZSTD_isError(skippableSize)) { - return ZSTD_CONTENTSIZE_ERROR; - } + return ZSTD_CONTENTSIZE_ERROR; + } assert(skippableSize <= srcSize); - - src = (const BYTE *)src + skippableSize; - srcSize -= skippableSize; - continue; - } - - { unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize); - if (ret >= ZSTD_CONTENTSIZE_ERROR) return ret; - - /* check for overflow */ - if (totalDstSize + ret < totalDstSize) return ZSTD_CONTENTSIZE_ERROR; - totalDstSize += ret; - } - { size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize); - if (ZSTD_isError(frameSrcSize)) { - return ZSTD_CONTENTSIZE_ERROR; - } - - src = (const BYTE *)src + frameSrcSize; - srcSize -= frameSrcSize; - } - } /* while (srcSize >= ZSTD_frameHeaderSize_prefix) */ - - if (srcSize) return ZSTD_CONTENTSIZE_ERROR; - - return totalDstSize; -} - + + src = (const BYTE *)src + skippableSize; + srcSize -= skippableSize; + continue; + } + + { unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize); + if (ret >= ZSTD_CONTENTSIZE_ERROR) return ret; + + /* check for overflow */ + if (totalDstSize + ret < totalDstSize) return ZSTD_CONTENTSIZE_ERROR; + totalDstSize += ret; + } + { size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize); + if (ZSTD_isError(frameSrcSize)) { + return ZSTD_CONTENTSIZE_ERROR; + } + + src = (const BYTE *)src + frameSrcSize; + srcSize -= frameSrcSize; + } + } /* while (srcSize >= ZSTD_frameHeaderSize_prefix) */ + + if (srcSize) return ZSTD_CONTENTSIZE_ERROR; + + return totalDstSize; +} + /** ZSTD_getDecompressedSize() : * compatible with legacy mode * @return : decompressed size if known, 0 otherwise note : 0 can mean any of the following : - - frame content is empty - - decompressed size field is not present in frame header + - frame content is empty + - decompressed size field is not present in frame header - frame header unknown / not supported - frame header not complete (`srcSize` too small) */ unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize) { - unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize); - ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_ERROR < ZSTD_CONTENTSIZE_UNKNOWN); - return (ret >= ZSTD_CONTENTSIZE_ERROR) ? 0 : ret; + unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize); + ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_ERROR < ZSTD_CONTENTSIZE_UNKNOWN); + return (ret >= ZSTD_CONTENTSIZE_ERROR) ? 0 : ret; } @@ -670,7 +670,7 @@ unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize) static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t headerSize) { size_t const result = ZSTD_getFrameHeader_advanced(&(dctx->fParams), src, headerSize, dctx->format); - if (ZSTD_isError(result)) return result; /* invalid header */ + if (ZSTD_isError(result)) return result; /* invalid header */ RETURN_ERROR_IF(result>0, srcSize_wrong, "headerSize too small"); /* Reference DDict requested by frame if dctx references multiple ddicts */ @@ -742,13 +742,13 @@ static ZSTD_frameSizeInfo ZSTD_findFrameSizeInfo(const void* src, size_t srcSize if (ZSTD_blockHeaderSize + cBlockSize > remainingSize) return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong)); - + ip += ZSTD_blockHeaderSize + cBlockSize; remainingSize -= ZSTD_blockHeaderSize + cBlockSize; nbBlocks++; - + if (blockProperties.lastBlock) break; - } + } /* Final frame content checksum */ if (zfh.checksumFlag) { @@ -781,9 +781,9 @@ size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize) * `src` must point to the start of a ZSTD frame or a skippeable frame * `srcSize` must be at least as large as the frame contained * @return : the maximum decompressed size of the compressed source - */ + */ unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize) -{ +{ unsigned long long bound = 0; /* Iterate over each frame */ while (srcSize > 0) { @@ -796,10 +796,10 @@ unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize) src = (const BYTE*)src + compressedSize; srcSize -= compressedSize; bound += decompressedBound; - } + } return bound; -} - +} + /*-************************************************************* * Frame decoding @@ -832,16 +832,16 @@ static size_t ZSTD_copyRawBlock(void* dst, size_t dstCapacity, static size_t ZSTD_setRleBlock(void* dst, size_t dstCapacity, BYTE b, size_t regenSize) -{ +{ RETURN_ERROR_IF(regenSize > dstCapacity, dstSize_tooSmall, ""); if (dst == NULL) { if (regenSize == 0) return 0; RETURN_ERROR(dstBuffer_null, ""); - } + } ZSTD_memset(dst, b, regenSize); return regenSize; -} - +} + static void ZSTD_DCtx_trace_end(ZSTD_DCtx const* dctx, U64 uncompressedSize, U64 compressedSize, unsigned streaming) { #if ZSTD_TRACE @@ -874,8 +874,8 @@ static void ZSTD_DCtx_trace_end(ZSTD_DCtx const* dctx, U64 uncompressedSize, U64 * will update *srcPtr and *srcSizePtr, * to make *srcPtr progress by one frame. */ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx, - void* dst, size_t dstCapacity, - const void** srcPtr, size_t *srcSizePtr) + void* dst, size_t dstCapacity, + const void** srcPtr, size_t *srcSizePtr) { const BYTE* const istart = (const BYTE*)(*srcPtr); const BYTE* ip = istart; @@ -930,7 +930,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx, if (ZSTD_isError(decodedSize)) return decodedSize; if (dctx->validateChecksum) - XXH64_update(&dctx->xxhState, op, decodedSize); + XXH64_update(&dctx->xxhState, op, decodedSize); if (decodedSize != 0) op += decodedSize; assert(ip != NULL); @@ -939,11 +939,11 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx, if (blockProperties.lastBlock) break; } - if (dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) { + if (dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) { RETURN_ERROR_IF((U64)(op-ostart) != dctx->fParams.frameContentSize, corruption_detected, ""); } - if (dctx->fParams.checksumFlag) { /* Frame content checksum verification */ + if (dctx->fParams.checksumFlag) { /* Frame content checksum verification */ RETURN_ERROR_IF(remainingSrcSize<4, checksum_wrong, ""); if (!dctx->forceIgnoreChecksum) { U32 const checkCalc = (U32)XXH64_digest(&dctx->xxhState); @@ -951,57 +951,57 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx, checkRead = MEM_readLE32(ip); RETURN_ERROR_IF(checkRead != checkCalc, checksum_wrong, ""); } - ip += 4; + ip += 4; remainingSrcSize -= 4; } ZSTD_DCtx_trace_end(dctx, (U64)(op-ostart), (U64)(ip-istart), /* streaming */ 0); - /* Allow caller to get size read */ - *srcPtr = ip; + /* Allow caller to get size read */ + *srcPtr = ip; *srcSizePtr = remainingSrcSize; return (size_t)(op-ostart); } -static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - const void* dict, size_t dictSize, - const ZSTD_DDict* ddict) -{ - void* const dststart = dst; +static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict, size_t dictSize, + const ZSTD_DDict* ddict) +{ + void* const dststart = dst; int moreThan1Frame = 0; DEBUGLOG(5, "ZSTD_decompressMultiFrame"); - assert(dict==NULL || ddict==NULL); /* either dict or ddict set, not both */ - - if (ddict) { + assert(dict==NULL || ddict==NULL); /* either dict or ddict set, not both */ + + if (ddict) { dict = ZSTD_DDict_dictContent(ddict); dictSize = ZSTD_DDict_dictSize(ddict); - } - + } + while (srcSize >= ZSTD_startingInputLength(dctx->format)) { - -#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1) - if (ZSTD_isLegacy(src, srcSize)) { - size_t decodedSize; - size_t const frameSize = ZSTD_findFrameCompressedSizeLegacy(src, srcSize); - if (ZSTD_isError(frameSize)) return frameSize; + +#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1) + if (ZSTD_isLegacy(src, srcSize)) { + size_t decodedSize; + size_t const frameSize = ZSTD_findFrameCompressedSizeLegacy(src, srcSize); + if (ZSTD_isError(frameSize)) return frameSize; RETURN_ERROR_IF(dctx->staticSize, memory_allocation, "legacy support is not compatible with static dctx"); - - decodedSize = ZSTD_decompressLegacy(dst, dstCapacity, src, frameSize, dict, dictSize); + + decodedSize = ZSTD_decompressLegacy(dst, dstCapacity, src, frameSize, dict, dictSize); if (ZSTD_isError(decodedSize)) return decodedSize; - + assert(decodedSize <= dstCapacity); - dst = (BYTE*)dst + decodedSize; - dstCapacity -= decodedSize; - - src = (const BYTE*)src + frameSize; - srcSize -= frameSize; - - continue; - } -#endif - + dst = (BYTE*)dst + decodedSize; + dstCapacity -= decodedSize; + + src = (const BYTE*)src + frameSize; + srcSize -= frameSize; + + continue; + } +#endif + { U32 const magicNumber = MEM_readLE32(src); DEBUGLOG(4, "reading magic number %08X (expecting %08X)", (unsigned)magicNumber, ZSTD_MAGICNUMBER); @@ -1009,24 +1009,24 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx, size_t const skippableSize = readSkippableFrameSize(src, srcSize); FORWARD_IF_ERROR(skippableSize, "readSkippableFrameSize failed"); assert(skippableSize <= srcSize); - - src = (const BYTE *)src + skippableSize; - srcSize -= skippableSize; - continue; + + src = (const BYTE *)src + skippableSize; + srcSize -= skippableSize; + continue; } } - - if (ddict) { - /* we were called from ZSTD_decompress_usingDDict */ + + if (ddict) { + /* we were called from ZSTD_decompress_usingDDict */ FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(dctx, ddict), ""); - } else { - /* this will initialize correctly with no dict if dict == NULL, so - * use this in all cases but ddict */ + } else { + /* this will initialize correctly with no dict if dict == NULL, so + * use this in all cases but ddict */ FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize), ""); - } + } ZSTD_checkContinuity(dctx, dst, dstCapacity); - - { const size_t res = ZSTD_decompressFrame(dctx, dst, dstCapacity, - &src, &srcSize); + + { const size_t res = ZSTD_decompressFrame(dctx, dst, dstCapacity, + &src, &srcSize); RETURN_ERROR_IF( (ZSTD_getErrorCode(res) == ZSTD_error_prefix_unknown) && (moreThan1Frame==1), @@ -1038,26 +1038,26 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx, "Note: one could be unlucky, it might be a corruption error instead, " "happening right at the place where we expect zstd magic bytes. " "But this is _much_ less likely than a srcSize field error."); - if (ZSTD_isError(res)) return res; + if (ZSTD_isError(res)) return res; assert(res <= dstCapacity); if (res != 0) dst = (BYTE*)dst + res; - dstCapacity -= res; - } + dstCapacity -= res; + } moreThan1Frame = 1; - } /* while (srcSize >= ZSTD_frameHeaderSize_prefix) */ - + } /* while (srcSize >= ZSTD_frameHeaderSize_prefix) */ + RETURN_ERROR_IF(srcSize, srcSize_wrong, "input not entirely consumed"); - + return (size_t)((BYTE*)dst - (BYTE*)dststart); -} - +} + size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, const void* dict, size_t dictSize) { - return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, dict, dictSize, NULL); + return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, dict, dictSize, NULL); } @@ -1086,7 +1086,7 @@ size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const size_t ZSTD_decompress(void* dst, size_t dstCapacity, const void* src, size_t srcSize) { -#if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE>=1) +#if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE>=1) size_t regenSize; ZSTD_DCtx* const dctx = ZSTD_createDCtx_internal(ZSTD_defaultCMem); RETURN_ERROR_IF(dctx==NULL, memory_allocation, "NULL pointer!"); @@ -1129,7 +1129,7 @@ ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx) { switch(dctx->stage) { default: /* should not happen */ - assert(0); + assert(0); ZSTD_FALLTHROUGH; case ZSTDds_getFrameHeaderSize: ZSTD_FALLTHROUGH; @@ -1150,12 +1150,12 @@ ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx) { } } -static int ZSTD_isSkipFrame(ZSTD_DCtx* dctx) { return dctx->stage == ZSTDds_skipFrame; } +static int ZSTD_isSkipFrame(ZSTD_DCtx* dctx) { return dctx->stage == ZSTDds_skipFrame; } /** ZSTD_decompressContinue() : - * srcSize : must be the exact nb of bytes expected (see ZSTD_nextSrcSizeToDecompress()) - * @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity) - * or an error code, which can be tested using ZSTD_isError() */ + * srcSize : must be the exact nb of bytes expected (see ZSTD_nextSrcSizeToDecompress()) + * @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity) + * or an error code, which can be tested using ZSTD_isError() */ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize) { DEBUGLOG(5, "ZSTD_decompressContinue (srcSize:%u)", (unsigned)srcSize); @@ -1168,24 +1168,24 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c switch (dctx->stage) { case ZSTDds_getFrameHeaderSize : - assert(src != NULL); - if (dctx->format == ZSTD_f_zstd1) { /* allows header */ + assert(src != NULL); + if (dctx->format == ZSTD_f_zstd1) { /* allows header */ assert(srcSize >= ZSTD_FRAMEIDSIZE); /* to read skippable magic number */ if ((MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */ ZSTD_memcpy(dctx->headerBuffer, src, srcSize); dctx->expected = ZSTD_SKIPPABLEHEADERSIZE - srcSize; /* remaining to load to get full skippable frame header */ - dctx->stage = ZSTDds_decodeSkippableHeader; - return 0; - } } - dctx->headerSize = ZSTD_frameHeaderSize_internal(src, srcSize, dctx->format); + dctx->stage = ZSTDds_decodeSkippableHeader; + return 0; + } } + dctx->headerSize = ZSTD_frameHeaderSize_internal(src, srcSize, dctx->format); if (ZSTD_isError(dctx->headerSize)) return dctx->headerSize; ZSTD_memcpy(dctx->headerBuffer, src, srcSize); - dctx->expected = dctx->headerSize - srcSize; - dctx->stage = ZSTDds_decodeFrameHeader; - return 0; + dctx->expected = dctx->headerSize - srcSize; + dctx->stage = ZSTDds_decodeFrameHeader; + return 0; case ZSTDds_decodeFrameHeader: - assert(src != NULL); + assert(src != NULL); ZSTD_memcpy(dctx->headerBuffer + (dctx->headerSize - srcSize), src, srcSize); FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize), ""); dctx->expected = ZSTD_blockHeaderSize; @@ -1214,20 +1214,20 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c dctx->stage = ZSTDds_getFrameHeaderSize; } } else { - dctx->expected = ZSTD_blockHeaderSize; /* jump to next header */ + dctx->expected = ZSTD_blockHeaderSize; /* jump to next header */ dctx->stage = ZSTDds_decodeBlockHeader; } return 0; } - + case ZSTDds_decompressLastBlock: case ZSTDds_decompressBlock: - DEBUGLOG(5, "ZSTD_decompressContinue: case ZSTDds_decompressBlock"); + DEBUGLOG(5, "ZSTD_decompressContinue: case ZSTDds_decompressBlock"); { size_t rSize; switch(dctx->bType) { case bt_compressed: - DEBUGLOG(5, "ZSTD_decompressContinue: case bt_compressed"); + DEBUGLOG(5, "ZSTD_decompressContinue: case bt_compressed"); rSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize, /* frame */ 1, is_streaming); dctx->expected = 0; /* Streaming not supported */ break; @@ -1249,7 +1249,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c FORWARD_IF_ERROR(rSize, ""); RETURN_ERROR_IF(rSize > dctx->fParams.blockSizeMax, corruption_detected, "Decompressed Block Size Exceeds Maximum"); DEBUGLOG(5, "ZSTD_decompressContinue: decoded size from block : %u", (unsigned)rSize); - dctx->decodedSize += rSize; + dctx->decodedSize += rSize; if (dctx->validateChecksum) XXH64_update(&dctx->xxhState, dst, rSize); dctx->previousDstEnd = (char*)dst + rSize; @@ -1278,9 +1278,9 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c } return rSize; } - + case ZSTDds_checkChecksum: - assert(srcSize == 4); /* guaranteed by dctx->expected */ + assert(srcSize == 4); /* guaranteed by dctx->expected */ { if (dctx->validateChecksum) { U32 const h32 = (U32)XXH64_digest(&dctx->xxhState); @@ -1293,20 +1293,20 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c dctx->stage = ZSTDds_getFrameHeaderSize; return 0; } - + case ZSTDds_decodeSkippableHeader: - assert(src != NULL); + assert(src != NULL); assert(srcSize <= ZSTD_SKIPPABLEHEADERSIZE); ZSTD_memcpy(dctx->headerBuffer + (ZSTD_SKIPPABLEHEADERSIZE - srcSize), src, srcSize); /* complete skippable header */ dctx->expected = MEM_readLE32(dctx->headerBuffer + ZSTD_FRAMEIDSIZE); /* note : dctx->expected can grow seriously large, beyond local buffer size */ - dctx->stage = ZSTDds_skipFrame; - return 0; - + dctx->stage = ZSTDds_skipFrame; + return 0; + case ZSTDds_skipFrame: - dctx->expected = 0; - dctx->stage = ZSTDds_getFrameHeaderSize; - return 0; - + dctx->expected = 0; + dctx->stage = ZSTDds_getFrameHeaderSize; + return 0; + default: assert(0); /* impossible */ RETURN_ERROR(GENERIC, "impossible to reach"); /* some compiler require default to do something */ @@ -1329,7 +1329,7 @@ static size_t ZSTD_refDictContent(ZSTD_DCtx* dctx, const void* dict, size_t dict /*! ZSTD_loadDEntropy() : * dict : must point at beginning of a valid zstd dictionary. - * @return : size of entropy tables read */ + * @return : size of entropy tables read */ size_t ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, const void* const dict, size_t const dictSize) @@ -1339,8 +1339,8 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, RETURN_ERROR_IF(dictSize <= 8, dictionary_corrupted, "dict is too small"); assert(MEM_readLE32(dict) == ZSTD_MAGIC_DICTIONARY); /* dict must be valid */ - dictPtr += 8; /* skip header = magic + dictID */ - + dictPtr += 8; /* skip header = magic + dictID */ + ZSTD_STATIC_ASSERT(offsetof(ZSTD_entropyDTables_t, OFTable) == offsetof(ZSTD_entropyDTables_t, LLTable) + sizeof(entropy->LLTable)); ZSTD_STATIC_ASSERT(offsetof(ZSTD_entropyDTables_t, MLTable) == offsetof(ZSTD_entropyDTables_t, OFTable) + sizeof(entropy->OFTable)); ZSTD_STATIC_ASSERT(sizeof(entropy->LLTable) + sizeof(entropy->OFTable) + sizeof(entropy->MLTable) >= HUF_DECOMPRESS_WORKSPACE_SIZE); @@ -1367,8 +1367,8 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, RETURN_ERROR_IF(offcodeMaxValue > MaxOff, dictionary_corrupted, ""); RETURN_ERROR_IF(offcodeLog > OffFSELog, dictionary_corrupted, ""); ZSTD_buildFSETable( entropy->OFTable, - offcodeNCount, offcodeMaxValue, - OF_base, OF_bits, + offcodeNCount, offcodeMaxValue, + OF_base, OF_bits, offcodeLog, entropy->workspace, sizeof(entropy->workspace), /* bmi2 */0); @@ -1382,8 +1382,8 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, RETURN_ERROR_IF(matchlengthMaxValue > MaxML, dictionary_corrupted, ""); RETURN_ERROR_IF(matchlengthLog > MLFSELog, dictionary_corrupted, ""); ZSTD_buildFSETable( entropy->MLTable, - matchlengthNCount, matchlengthMaxValue, - ML_base, ML_bits, + matchlengthNCount, matchlengthMaxValue, + ML_base, ML_bits, matchlengthLog, entropy->workspace, sizeof(entropy->workspace), /* bmi2 */ 0); @@ -1397,8 +1397,8 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, RETURN_ERROR_IF(litlengthMaxValue > MaxLL, dictionary_corrupted, ""); RETURN_ERROR_IF(litlengthLog > LLFSELog, dictionary_corrupted, ""); ZSTD_buildFSETable( entropy->LLTable, - litlengthNCount, litlengthMaxValue, - LL_base, LL_bits, + litlengthNCount, litlengthMaxValue, + LL_base, LL_bits, litlengthLog, entropy->workspace, sizeof(entropy->workspace), /* bmi2 */ 0); @@ -1406,14 +1406,14 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, } RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted, ""); - { int i; - size_t const dictContentSize = (size_t)(dictEnd - (dictPtr+12)); - for (i=0; i<3; i++) { - U32 const rep = MEM_readLE32(dictPtr); dictPtr += 4; + { int i; + size_t const dictContentSize = (size_t)(dictEnd - (dictPtr+12)); + for (i=0; i<3; i++) { + U32 const rep = MEM_readLE32(dictPtr); dictPtr += 4; RETURN_ERROR_IF(rep==0 || rep > dictContentSize, dictionary_corrupted, ""); - entropy->rep[i] = rep; - } } + entropy->rep[i] = rep; + } } return (size_t)(dictPtr - (const BYTE*)dict); } @@ -1422,7 +1422,7 @@ static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx* dctx, const void* dict { if (dictSize < 8) return ZSTD_refDictContent(dctx, dict, dictSize); { U32 const magic = MEM_readLE32(dict); - if (magic != ZSTD_MAGIC_DICTIONARY) { + if (magic != ZSTD_MAGIC_DICTIONARY) { return ZSTD_refDictContent(dctx, dict, dictSize); /* pure content mode */ } } dctx->dictID = MEM_readLE32((const char*)dict + ZSTD_FRAMEIDSIZE); @@ -1433,43 +1433,43 @@ static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx* dctx, const void* dict dict = (const char*)dict + eSize; dictSize -= eSize; } - dctx->litEntropy = dctx->fseEntropy = 1; + dctx->litEntropy = dctx->fseEntropy = 1; /* reference dictionary content */ return ZSTD_refDictContent(dctx, dict, dictSize); } -size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx) -{ - assert(dctx != NULL); +size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx) +{ + assert(dctx != NULL); #if ZSTD_TRACE dctx->traceCtx = (ZSTD_trace_decompress_begin != NULL) ? ZSTD_trace_decompress_begin(dctx) : 0; #endif - dctx->expected = ZSTD_startingInputLength(dctx->format); /* dctx->format must be properly set */ - dctx->stage = ZSTDds_getFrameHeaderSize; + dctx->expected = ZSTD_startingInputLength(dctx->format); /* dctx->format must be properly set */ + dctx->stage = ZSTDds_getFrameHeaderSize; dctx->processedCSize = 0; - dctx->decodedSize = 0; - dctx->previousDstEnd = NULL; + dctx->decodedSize = 0; + dctx->previousDstEnd = NULL; dctx->prefixStart = NULL; dctx->virtualStart = NULL; - dctx->dictEnd = NULL; - dctx->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */ - dctx->litEntropy = dctx->fseEntropy = 0; - dctx->dictID = 0; + dctx->dictEnd = NULL; + dctx->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */ + dctx->litEntropy = dctx->fseEntropy = 0; + dctx->dictID = 0; dctx->bType = bt_reserved; - ZSTD_STATIC_ASSERT(sizeof(dctx->entropy.rep) == sizeof(repStartValue)); + ZSTD_STATIC_ASSERT(sizeof(dctx->entropy.rep) == sizeof(repStartValue)); ZSTD_memcpy(dctx->entropy.rep, repStartValue, sizeof(repStartValue)); /* initial repcodes */ - dctx->LLTptr = dctx->entropy.LLTable; - dctx->MLTptr = dctx->entropy.MLTable; - dctx->OFTptr = dctx->entropy.OFTable; - dctx->HUFptr = dctx->entropy.hufTable; - return 0; -} - + dctx->LLTptr = dctx->entropy.LLTable; + dctx->MLTptr = dctx->entropy.MLTable; + dctx->OFTptr = dctx->entropy.OFTable; + dctx->HUFptr = dctx->entropy.hufTable; + return 0; +} + size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize) { FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) , ""); - if (dict && dictSize) + if (dict && dictSize) RETURN_ERROR_IF( ZSTD_isError(ZSTD_decompress_insertDictionary(dctx, dict, dictSize)), dictionary_corrupted, ""); @@ -1490,14 +1490,14 @@ size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict) dctx->ddictIsCold = (dctx->dictEnd != dictEnd); DEBUGLOG(4, "DDict is %s", dctx->ddictIsCold ? "~cold~" : "hot!"); - } + } FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) , ""); if (ddict) { /* NULL ddict is equivalent to no dictionary */ ZSTD_copyDDictParameters(dctx, ddict); - } - return 0; -} - + } + return 0; +} + /*! ZSTD_getDictID_fromDict() : * Provides the dictID stored within dictionary. * if @return == 0, the dictionary is not conformant with Zstandard specification. @@ -1505,7 +1505,7 @@ size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict) unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize) { if (dictSize < 8) return 0; - if (MEM_readLE32(dict) != ZSTD_MAGIC_DICTIONARY) return 0; + if (MEM_readLE32(dict) != ZSTD_MAGIC_DICTIONARY) return 0; return MEM_readLE32((const char*)dict + ZSTD_FRAMEIDSIZE); } @@ -1513,19 +1513,19 @@ unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize) * Provides the dictID required to decompress frame stored within `src`. * If @return == 0, the dictID could not be decoded. * This could for one of the following reasons : - * - The frame does not require a dictionary (most common case). - * - The frame was built with dictID intentionally removed. - * Needed dictionary is a hidden information. + * - The frame does not require a dictionary (most common case). + * - The frame was built with dictID intentionally removed. + * Needed dictionary is a hidden information. * Note : this use case also happens when using a non-conformant dictionary. - * - `srcSize` is too small, and as a result, frame header could not be decoded. - * Note : possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`. + * - `srcSize` is too small, and as a result, frame header could not be decoded. + * Note : possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`. * - This is not a Zstandard frame. - * When identifying the exact failure cause, it's possible to use - * ZSTD_getFrameHeader(), which will provide a more precise error code. */ + * When identifying the exact failure cause, it's possible to use + * ZSTD_getFrameHeader(), which will provide a more precise error code. */ unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize) { - ZSTD_frameHeader zfp = { 0, 0, 0, ZSTD_frame, 0, 0, 0 }; - size_t const hError = ZSTD_getFrameHeader(&zfp, src, srcSize); + ZSTD_frameHeader zfp = { 0, 0, 0, ZSTD_frame, 0, 0, 0 }; + size_t const hError = ZSTD_getFrameHeader(&zfp, src, srcSize); if (ZSTD_isError(hError)) return 0; return zfp.dictID; } @@ -1539,10 +1539,10 @@ size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, const void* src, size_t srcSize, const ZSTD_DDict* ddict) { - /* pass content and size in case legacy frames are encountered */ - return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, - NULL, 0, - ddict); + /* pass content and size in case legacy frames are encountered */ + return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, + NULL, 0, + ddict); } @@ -1550,104 +1550,104 @@ size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, * Streaming decompression *====================================*/ -ZSTD_DStream* ZSTD_createDStream(void) -{ - DEBUGLOG(3, "ZSTD_createDStream"); +ZSTD_DStream* ZSTD_createDStream(void) +{ + DEBUGLOG(3, "ZSTD_createDStream"); return ZSTD_createDCtx_internal(ZSTD_defaultCMem); -} - -ZSTD_DStream* ZSTD_initStaticDStream(void *workspace, size_t workspaceSize) -{ - return ZSTD_initStaticDCtx(workspace, workspaceSize); -} - -ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem) -{ +} + +ZSTD_DStream* ZSTD_initStaticDStream(void *workspace, size_t workspaceSize) +{ + return ZSTD_initStaticDCtx(workspace, workspaceSize); +} + +ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem) +{ return ZSTD_createDCtx_internal(customMem); -} - -size_t ZSTD_freeDStream(ZSTD_DStream* zds) -{ - return ZSTD_freeDCtx(zds); -} - - +} + +size_t ZSTD_freeDStream(ZSTD_DStream* zds) +{ + return ZSTD_freeDCtx(zds); +} + + /* *** Initialization *** */ - -size_t ZSTD_DStreamInSize(void) { return ZSTD_BLOCKSIZE_MAX + ZSTD_blockHeaderSize; } -size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_MAX; } - + +size_t ZSTD_DStreamInSize(void) { return ZSTD_BLOCKSIZE_MAX + ZSTD_blockHeaderSize; } +size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_MAX; } + size_t ZSTD_DCtx_loadDictionary_advanced(ZSTD_DCtx* dctx, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType) -{ +{ RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong, ""); ZSTD_clearDict(dctx); if (dict && dictSize != 0) { - dctx->ddictLocal = ZSTD_createDDict_advanced(dict, dictSize, dictLoadMethod, dictContentType, dctx->customMem); + dctx->ddictLocal = ZSTD_createDDict_advanced(dict, dictSize, dictLoadMethod, dictContentType, dctx->customMem); RETURN_ERROR_IF(dctx->ddictLocal == NULL, memory_allocation, "NULL pointer!"); dctx->ddict = dctx->ddictLocal; dctx->dictUses = ZSTD_use_indefinitely; - } - return 0; -} - -size_t ZSTD_DCtx_loadDictionary_byReference(ZSTD_DCtx* dctx, const void* dict, size_t dictSize) -{ - return ZSTD_DCtx_loadDictionary_advanced(dctx, dict, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto); -} - -size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize) -{ - return ZSTD_DCtx_loadDictionary_advanced(dctx, dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto); -} - -size_t ZSTD_DCtx_refPrefix_advanced(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType) + } + return 0; +} + +size_t ZSTD_DCtx_loadDictionary_byReference(ZSTD_DCtx* dctx, const void* dict, size_t dictSize) +{ + return ZSTD_DCtx_loadDictionary_advanced(dctx, dict, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto); +} + +size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize) +{ + return ZSTD_DCtx_loadDictionary_advanced(dctx, dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto); +} + +size_t ZSTD_DCtx_refPrefix_advanced(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType) { FORWARD_IF_ERROR(ZSTD_DCtx_loadDictionary_advanced(dctx, prefix, prefixSize, ZSTD_dlm_byRef, dictContentType), ""); dctx->dictUses = ZSTD_use_once; return 0; } -size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize) -{ - return ZSTD_DCtx_refPrefix_advanced(dctx, prefix, prefixSize, ZSTD_dct_rawContent); -} - - -/* ZSTD_initDStream_usingDict() : +size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize) +{ + return ZSTD_DCtx_refPrefix_advanced(dctx, prefix, prefixSize, ZSTD_dct_rawContent); +} + + +/* ZSTD_initDStream_usingDict() : * return : expected size, aka ZSTD_startingInputLength(). - * this function cannot fail */ + * this function cannot fail */ size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize) { - DEBUGLOG(4, "ZSTD_initDStream_usingDict"); + DEBUGLOG(4, "ZSTD_initDStream_usingDict"); FORWARD_IF_ERROR( ZSTD_DCtx_reset(zds, ZSTD_reset_session_only) , ""); FORWARD_IF_ERROR( ZSTD_DCtx_loadDictionary(zds, dict, dictSize) , ""); return ZSTD_startingInputLength(zds->format); } -/* note : this variant can't fail */ +/* note : this variant can't fail */ size_t ZSTD_initDStream(ZSTD_DStream* zds) { - DEBUGLOG(4, "ZSTD_initDStream"); + DEBUGLOG(4, "ZSTD_initDStream"); return ZSTD_initDStream_usingDDict(zds, NULL); } -/* ZSTD_initDStream_usingDDict() : - * ddict will just be referenced, and must outlive decompression session - * this function cannot fail */ -size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict) -{ +/* ZSTD_initDStream_usingDDict() : + * ddict will just be referenced, and must outlive decompression session + * this function cannot fail */ +size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict) +{ FORWARD_IF_ERROR( ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only) , ""); FORWARD_IF_ERROR( ZSTD_DCtx_refDDict(dctx, ddict) , ""); return ZSTD_startingInputLength(dctx->format); } -/* ZSTD_resetDStream() : +/* ZSTD_resetDStream() : * return : expected size, aka ZSTD_startingInputLength(). - * this function cannot fail */ -size_t ZSTD_resetDStream(ZSTD_DStream* dctx) + * this function cannot fail */ +size_t ZSTD_resetDStream(ZSTD_DStream* dctx) { FORWARD_IF_ERROR(ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only), ""); return ZSTD_startingInputLength(dctx->format); @@ -1678,19 +1678,19 @@ size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict) /* ZSTD_DCtx_setMaxWindowSize() : * note : no direct equivalence in ZSTD_DCtx_setParameter, * since this version sets windowSize, and the other sets windowLog */ -size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize) -{ +size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize) +{ ZSTD_bounds const bounds = ZSTD_dParam_getBounds(ZSTD_d_windowLogMax); size_t const min = (size_t)1 << bounds.lowerBound; size_t const max = (size_t)1 << bounds.upperBound; RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong, ""); RETURN_ERROR_IF(maxWindowSize < min, parameter_outOfBound, ""); RETURN_ERROR_IF(maxWindowSize > max, parameter_outOfBound, ""); - dctx->maxWindowSize = maxWindowSize; - return 0; -} + dctx->maxWindowSize = maxWindowSize; + return 0; +} -size_t ZSTD_DCtx_setFormat(ZSTD_DCtx* dctx, ZSTD_format_e format) +size_t ZSTD_DCtx_setFormat(ZSTD_DCtx* dctx, ZSTD_format_e format) { return ZSTD_DCtx_setParameter(dctx, ZSTD_d_format, (int)format); } @@ -1811,48 +1811,48 @@ size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset) ZSTD_clearDict(dctx); ZSTD_DCtx_resetParameters(dctx); } - return 0; + return 0; } -size_t ZSTD_sizeof_DStream(const ZSTD_DStream* dctx) -{ - return ZSTD_sizeof_DCtx(dctx); -} - -size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long long frameContentSize) -{ - size_t const blockSize = (size_t) MIN(windowSize, ZSTD_BLOCKSIZE_MAX); +size_t ZSTD_sizeof_DStream(const ZSTD_DStream* dctx) +{ + return ZSTD_sizeof_DCtx(dctx); +} + +size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long long frameContentSize) +{ + size_t const blockSize = (size_t) MIN(windowSize, ZSTD_BLOCKSIZE_MAX); /* space is needed to store the litbuffer after the output of a given block without stomping the extDict of a previous run, as well as to cover both windows against wildcopy*/ unsigned long long const neededRBSize = windowSize + blockSize + ZSTD_BLOCKSIZE_MAX + (WILDCOPY_OVERLENGTH * 2); - unsigned long long const neededSize = MIN(frameContentSize, neededRBSize); - size_t const minRBSize = (size_t) neededSize; + unsigned long long const neededSize = MIN(frameContentSize, neededRBSize); + size_t const minRBSize = (size_t) neededSize; RETURN_ERROR_IF((unsigned long long)minRBSize != neededSize, frameParameter_windowTooLarge, ""); - return minRBSize; -} - -size_t ZSTD_estimateDStreamSize(size_t windowSize) -{ - size_t const blockSize = MIN(windowSize, ZSTD_BLOCKSIZE_MAX); - size_t const inBuffSize = blockSize; /* no block can be larger */ - size_t const outBuffSize = ZSTD_decodingBufferSize_min(windowSize, ZSTD_CONTENTSIZE_UNKNOWN); - return ZSTD_estimateDCtxSize() + inBuffSize + outBuffSize; -} - -size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize) -{ + return minRBSize; +} + +size_t ZSTD_estimateDStreamSize(size_t windowSize) +{ + size_t const blockSize = MIN(windowSize, ZSTD_BLOCKSIZE_MAX); + size_t const inBuffSize = blockSize; /* no block can be larger */ + size_t const outBuffSize = ZSTD_decodingBufferSize_min(windowSize, ZSTD_CONTENTSIZE_UNKNOWN); + return ZSTD_estimateDCtxSize() + inBuffSize + outBuffSize; +} + +size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize) +{ U32 const windowSizeMax = 1U << ZSTD_WINDOWLOG_MAX; /* note : should be user-selectable, but requires an additional parameter (or a dctx) */ - ZSTD_frameHeader zfh; - size_t const err = ZSTD_getFrameHeader(&zfh, src, srcSize); - if (ZSTD_isError(err)) return err; + ZSTD_frameHeader zfh; + size_t const err = ZSTD_getFrameHeader(&zfh, src, srcSize); + if (ZSTD_isError(err)) return err; RETURN_ERROR_IF(err>0, srcSize_wrong, ""); RETURN_ERROR_IF(zfh.windowSize > windowSizeMax, frameParameter_windowTooLarge, ""); - return ZSTD_estimateDStreamSize((size_t)zfh.windowSize); -} - - + return ZSTD_estimateDStreamSize((size_t)zfh.windowSize); +} + + /* ***** Decompression ***** */ static int ZSTD_DCtx_isOverflow(ZSTD_DStream* zds, size_t const neededInBuffSize, size_t const neededOutBuffSize) @@ -1937,7 +1937,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB char* op = ostart; U32 someMoreWork = 1; - DEBUGLOG(5, "ZSTD_decompressStream"); + DEBUGLOG(5, "ZSTD_decompressStream"); RETURN_ERROR_IF( input->pos > input->size, srcSize_wrong, @@ -1948,14 +1948,14 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB dstSize_tooSmall, "forbidden. out: pos: %u vs size: %u", (U32)output->pos, (U32)output->size); - DEBUGLOG(5, "input size : %u", (U32)(input->size - input->pos)); + DEBUGLOG(5, "input size : %u", (U32)(input->size - input->pos)); FORWARD_IF_ERROR(ZSTD_checkOutBuffer(zds, output), ""); while (someMoreWork) { - switch(zds->streamStage) + switch(zds->streamStage) { case zdss_init : - DEBUGLOG(5, "stage zdss_init => transparent reset "); + DEBUGLOG(5, "stage zdss_init => transparent reset "); zds->streamStage = zdss_loadHeader; zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0; #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1) @@ -1966,75 +1966,75 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB ZSTD_FALLTHROUGH; case zdss_loadHeader : - DEBUGLOG(5, "stage zdss_loadHeader (srcSize : %u)", (U32)(iend - ip)); + DEBUGLOG(5, "stage zdss_loadHeader (srcSize : %u)", (U32)(iend - ip)); #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1) - if (zds->legacyVersion) { + if (zds->legacyVersion) { RETURN_ERROR_IF(zds->staticSize, memory_allocation, "legacy support is incompatible with static dctx"); - { size_t const hint = ZSTD_decompressLegacyStream(zds->legacyContext, zds->legacyVersion, output, input); - if (hint==0) zds->streamStage = zdss_init; - return hint; - } } -#endif + { size_t const hint = ZSTD_decompressLegacyStream(zds->legacyContext, zds->legacyVersion, output, input); + if (hint==0) zds->streamStage = zdss_init; + return hint; + } } +#endif { size_t const hSize = ZSTD_getFrameHeader_advanced(&zds->fParams, zds->headerBuffer, zds->lhSize, zds->format); if (zds->refMultipleDDicts && zds->ddictSet) { ZSTD_DCtx_selectFrameDDict(zds); } - DEBUGLOG(5, "header size : %u", (U32)hSize); - if (ZSTD_isError(hSize)) { -#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1) - U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart); + DEBUGLOG(5, "header size : %u", (U32)hSize); + if (ZSTD_isError(hSize)) { +#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1) + U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart); if (legacyVersion) { ZSTD_DDict const* const ddict = ZSTD_getDDict(zds); const void* const dict = ddict ? ZSTD_DDict_dictContent(ddict) : NULL; size_t const dictSize = ddict ? ZSTD_DDict_dictSize(ddict) : 0; - DEBUGLOG(5, "ZSTD_decompressStream: detected legacy version v0.%u", legacyVersion); + DEBUGLOG(5, "ZSTD_decompressStream: detected legacy version v0.%u", legacyVersion); RETURN_ERROR_IF(zds->staticSize, memory_allocation, "legacy support is incompatible with static dctx"); FORWARD_IF_ERROR(ZSTD_initLegacyStream(&zds->legacyContext, - zds->previousLegacyVersion, legacyVersion, + zds->previousLegacyVersion, legacyVersion, dict, dictSize), ""); zds->legacyVersion = zds->previousLegacyVersion = legacyVersion; - { size_t const hint = ZSTD_decompressLegacyStream(zds->legacyContext, legacyVersion, output, input); - if (hint==0) zds->streamStage = zdss_init; /* or stay in stage zdss_loadHeader */ - return hint; - } } + { size_t const hint = ZSTD_decompressLegacyStream(zds->legacyContext, legacyVersion, output, input); + if (hint==0) zds->streamStage = zdss_init; /* or stay in stage zdss_loadHeader */ + return hint; + } } #endif - return hSize; /* error */ - } + return hSize; /* error */ + } if (hSize != 0) { /* need more input */ size_t const toLoad = hSize - zds->lhSize; /* if hSize!=0, hSize > zds->lhSize */ - size_t const remainingInput = (size_t)(iend-ip); - assert(iend >= ip); - if (toLoad > remainingInput) { /* not enough input to load full header */ - if (remainingInput > 0) { + size_t const remainingInput = (size_t)(iend-ip); + assert(iend >= ip); + if (toLoad > remainingInput) { /* not enough input to load full header */ + if (remainingInput > 0) { ZSTD_memcpy(zds->headerBuffer + zds->lhSize, ip, remainingInput); - zds->lhSize += remainingInput; - } + zds->lhSize += remainingInput; + } input->pos = input->size; return (MAX((size_t)ZSTD_FRAMEHEADERSIZE_MIN(zds->format), hSize) - zds->lhSize) + ZSTD_blockHeaderSize; /* remaining header bytes + next block header */ } - assert(ip != NULL); + assert(ip != NULL); ZSTD_memcpy(zds->headerBuffer + zds->lhSize, ip, toLoad); zds->lhSize = hSize; ip += toLoad; break; } } - /* check for single-pass mode opportunity */ + /* check for single-pass mode opportunity */ if (zds->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN && zds->fParams.frameType != ZSTD_skippableFrame - && (U64)(size_t)(oend-op) >= zds->fParams.frameContentSize) { + && (U64)(size_t)(oend-op) >= zds->fParams.frameContentSize) { size_t const cSize = ZSTD_findFrameCompressedSize(istart, (size_t)(iend-istart)); - if (cSize <= (size_t)(iend-istart)) { - /* shortcut : using single-pass mode */ + if (cSize <= (size_t)(iend-istart)) { + /* shortcut : using single-pass mode */ size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, (size_t)(oend-op), istart, cSize, ZSTD_getDDict(zds)); - if (ZSTD_isError(decompressedSize)) return decompressedSize; - DEBUGLOG(4, "shortcut to single-pass ZSTD_decompress_usingDDict()") - ip = istart + cSize; - op += decompressedSize; - zds->expected = 0; - zds->streamStage = zdss_init; - someMoreWork = 0; - break; + if (ZSTD_isError(decompressedSize)) return decompressedSize; + DEBUGLOG(4, "shortcut to single-pass ZSTD_decompress_usingDDict()") + ip = istart + cSize; + op += decompressedSize; + zds->expected = 0; + zds->streamStage = zdss_init; + someMoreWork = 0; + break; } } /* Check output buffer is large enough for ZSTD_odm_stable. */ @@ -2045,29 +2045,29 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB RETURN_ERROR(dstSize_tooSmall, "ZSTD_obm_stable passed but ZSTD_outBuffer is too small"); } - /* Consume header (see ZSTDds_decodeFrameHeader) */ - DEBUGLOG(4, "Consume header"); + /* Consume header (see ZSTDds_decodeFrameHeader) */ + DEBUGLOG(4, "Consume header"); FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(zds, ZSTD_getDDict(zds)), ""); - + if ((MEM_readLE32(zds->headerBuffer) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */ zds->expected = MEM_readLE32(zds->headerBuffer + ZSTD_FRAMEIDSIZE); - zds->stage = ZSTDds_skipFrame; - } else { + zds->stage = ZSTDds_skipFrame; + } else { FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize), ""); - zds->expected = ZSTD_blockHeaderSize; - zds->stage = ZSTDds_decodeBlockHeader; - } - - /* control buffer memory usage */ - DEBUGLOG(4, "Control max memory usage (%u KB <= max %u KB)", - (U32)(zds->fParams.windowSize >>10), - (U32)(zds->maxWindowSize >> 10) ); + zds->expected = ZSTD_blockHeaderSize; + zds->stage = ZSTDds_decodeBlockHeader; + } + + /* control buffer memory usage */ + DEBUGLOG(4, "Control max memory usage (%u KB <= max %u KB)", + (U32)(zds->fParams.windowSize >>10), + (U32)(zds->maxWindowSize >> 10) ); zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN); RETURN_ERROR_IF(zds->fParams.windowSize > zds->maxWindowSize, frameParameter_windowTooLarge, ""); /* Adapt buffer sizes to frame header instructions */ - { size_t const neededInBuffSize = MAX(zds->fParams.blockSizeMax, 4 /* frame checksum */); + { size_t const neededInBuffSize = MAX(zds->fParams.blockSizeMax, 4 /* frame checksum */); size_t const neededOutBuffSize = zds->outBufferMode == ZSTD_bm_buffered ? ZSTD_decodingBufferSize_min(zds->fParams.windowSize, zds->fParams.frameContentSize) : 0; @@ -2100,15 +2100,15 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB zds->outBuff = zds->inBuff + zds->inBuffSize; zds->outBuffSize = neededOutBuffSize; } } } - zds->streamStage = zdss_read; + zds->streamStage = zdss_read; ZSTD_FALLTHROUGH; case zdss_read: - DEBUGLOG(5, "stage zdss_read"); + DEBUGLOG(5, "stage zdss_read"); { size_t const neededInSize = ZSTD_nextSrcSizeToDecompressWithInputSize(zds, (size_t)(iend - ip)); - DEBUGLOG(5, "neededInSize = %u", (U32)neededInSize); + DEBUGLOG(5, "neededInSize = %u", (U32)neededInSize); if (neededInSize==0) { /* end of frame */ - zds->streamStage = zdss_init; + zds->streamStage = zdss_init; someMoreWork = 0; break; } @@ -2117,26 +2117,26 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB ip += neededInSize; /* Function modifies the stage so we must break */ break; - } } - if (ip==iend) { someMoreWork = 0; break; } /* no more input */ - zds->streamStage = zdss_load; + } } + if (ip==iend) { someMoreWork = 0; break; } /* no more input */ + zds->streamStage = zdss_load; ZSTD_FALLTHROUGH; case zdss_load: - { size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds); - size_t const toLoad = neededInSize - zds->inPos; - int const isSkipFrame = ZSTD_isSkipFrame(zds); + { size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds); + size_t const toLoad = neededInSize - zds->inPos; + int const isSkipFrame = ZSTD_isSkipFrame(zds); size_t loadedSize; /* At this point we shouldn't be decompressing a block that we can stream. */ assert(neededInSize == ZSTD_nextSrcSizeToDecompressWithInputSize(zds, iend - ip)); - if (isSkipFrame) { - loadedSize = MIN(toLoad, (size_t)(iend-ip)); - } else { + if (isSkipFrame) { + loadedSize = MIN(toLoad, (size_t)(iend-ip)); + } else { RETURN_ERROR_IF(toLoad > zds->inBuffSize - zds->inPos, corruption_detected, "should never happen"); loadedSize = ZSTD_limitCopy(zds->inBuff + zds->inPos, toLoad, ip, (size_t)(iend-ip)); - } + } ip += loadedSize; zds->inPos += loadedSize; if (loadedSize < toLoad) { someMoreWork = 0; break; } /* not enough input, wait for more */ @@ -2153,20 +2153,20 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB op += flushedSize; zds->outStart += flushedSize; if (flushedSize == toFlushSize) { /* flush completed */ - zds->streamStage = zdss_read; - if ( (zds->outBuffSize < zds->fParams.frameContentSize) - && (zds->outStart + zds->fParams.blockSizeMax > zds->outBuffSize) ) { - DEBUGLOG(5, "restart filling outBuff from beginning (left:%i, needed:%u)", - (int)(zds->outBuffSize - zds->outStart), - (U32)zds->fParams.blockSizeMax); + zds->streamStage = zdss_read; + if ( (zds->outBuffSize < zds->fParams.frameContentSize) + && (zds->outStart + zds->fParams.blockSizeMax > zds->outBuffSize) ) { + DEBUGLOG(5, "restart filling outBuff from beginning (left:%i, needed:%u)", + (int)(zds->outBuffSize - zds->outStart), + (U32)zds->fParams.blockSizeMax); zds->outStart = zds->outEnd = 0; - } + } break; - } } - /* cannot complete flush */ - someMoreWork = 0; - break; - + } } + /* cannot complete flush */ + someMoreWork = 0; + break; + default: assert(0); /* impossible */ RETURN_ERROR(GENERIC, "impossible to reach"); /* some compiler require default to do something */ @@ -2189,42 +2189,42 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB } else { zds->noForwardProgress = 0; } - { size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds); + { size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds); if (!nextSrcSizeHint) { /* frame fully decoded */ if (zds->outEnd == zds->outStart) { /* output fully flushed */ if (zds->hostageByte) { - if (input->pos >= input->size) { - /* can't release hostage (not present) */ - zds->streamStage = zdss_read; - return 1; - } + if (input->pos >= input->size) { + /* can't release hostage (not present) */ + zds->streamStage = zdss_read; + return 1; + } input->pos++; /* release hostage */ - } /* zds->hostageByte */ + } /* zds->hostageByte */ return 0; - } /* zds->outEnd == zds->outStart */ + } /* zds->outEnd == zds->outStart */ if (!zds->hostageByte) { /* output not fully flushed; keep last byte as hostage; will be released when all output is flushed */ input->pos--; /* note : pos > 0, otherwise, impossible to finish reading last block */ zds->hostageByte=1; } return 1; - } /* nextSrcSizeHint==0 */ - nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds) == ZSTDnit_block); /* preload header of next block */ - assert(zds->inPos <= nextSrcSizeHint); - nextSrcSizeHint -= zds->inPos; /* part already loaded*/ + } /* nextSrcSizeHint==0 */ + nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds) == ZSTDnit_block); /* preload header of next block */ + assert(zds->inPos <= nextSrcSizeHint); + nextSrcSizeHint -= zds->inPos; /* part already loaded*/ return nextSrcSizeHint; } } - + size_t ZSTD_decompressStream_simpleArgs ( - ZSTD_DCtx* dctx, - void* dst, size_t dstCapacity, size_t* dstPos, - const void* src, size_t srcSize, size_t* srcPos) -{ - ZSTD_outBuffer output = { dst, dstCapacity, *dstPos }; - ZSTD_inBuffer input = { src, srcSize, *srcPos }; - /* ZSTD_compress_generic() will check validity of dstPos and srcPos */ + ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, size_t* dstPos, + const void* src, size_t srcSize, size_t* srcPos) +{ + ZSTD_outBuffer output = { dst, dstCapacity, *dstPos }; + ZSTD_inBuffer input = { src, srcSize, *srcPos }; + /* ZSTD_compress_generic() will check validity of dstPos and srcPos */ size_t const cErr = ZSTD_decompressStream(dctx, &output, &input); - *dstPos = output.pos; - *srcPos = input.pos; - return cErr; -} + *dstPos = output.pos; + *srcPos = input.pos; + return cErr; +} diff --git a/contrib/libs/zstd/lib/dictBuilder/cover.c b/contrib/libs/zstd/lib/dictBuilder/cover.c index 028802a1b0..336cacf122 100644 --- a/contrib/libs/zstd/lib/dictBuilder/cover.c +++ b/contrib/libs/zstd/lib/dictBuilder/cover.c @@ -1,31 +1,31 @@ -/* +/* * Copyright (c) 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. - */ - -/* ***************************************************************************** - * Constructs a dictionary using a heuristic based on the following paper: - * - * Liao, Petri, Moffat, Wirth - * Effective Construction of Relative Lempel-Ziv Dictionaries - * Published in WWW 2016. - * - * Adapted from code originally written by @ot (Giuseppe Ottaviano). - ******************************************************************************/ - -/*-************************************* -* Dependencies -***************************************/ -#include <stdio.h> /* fprintf */ -#include <stdlib.h> /* malloc, free, qsort */ -#include <string.h> /* memset */ -#include <time.h> /* clock */ - + * 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. + */ + +/* ***************************************************************************** + * Constructs a dictionary using a heuristic based on the following paper: + * + * Liao, Petri, Moffat, Wirth + * Effective Construction of Relative Lempel-Ziv Dictionaries + * Published in WWW 2016. + * + * Adapted from code originally written by @ot (Giuseppe Ottaviano). + ******************************************************************************/ + +/*-************************************* +* Dependencies +***************************************/ +#include <stdio.h> /* fprintf */ +#include <stdlib.h> /* malloc, free, qsort */ +#include <string.h> /* memset */ +#include <time.h> /* clock */ + #ifndef ZDICT_STATIC_LINKING_ONLY # define ZDICT_STATIC_LINKING_ONLY #endif @@ -36,10 +36,10 @@ #include "../common/zstd_internal.h" /* includes zstd.h */ #include "../zdict.h" #include "cover.h" - -/*-************************************* -* Constants -***************************************/ + +/*-************************************* +* Constants +***************************************/ /** * There are 32bit indexes used to ref samples, so limit samples size to 4GB * on 64bit builds. @@ -49,520 +49,520 @@ */ #define COVER_MAX_SAMPLES_SIZE (sizeof(size_t) == 8 ? ((unsigned)-1) : ((unsigned)1 GB)) #define COVER_DEFAULT_SPLITPOINT 1.0 - -/*-************************************* -* Console display -***************************************/ + +/*-************************************* +* Console display +***************************************/ #ifndef LOCALDISPLAYLEVEL static int g_displayLevel = 0; #endif #undef DISPLAY -#define DISPLAY(...) \ - { \ - fprintf(stderr, __VA_ARGS__); \ - fflush(stderr); \ - } +#define DISPLAY(...) \ + { \ + fprintf(stderr, __VA_ARGS__); \ + fflush(stderr); \ + } #undef LOCALDISPLAYLEVEL -#define LOCALDISPLAYLEVEL(displayLevel, l, ...) \ - if (displayLevel >= l) { \ - DISPLAY(__VA_ARGS__); \ - } /* 0 : no display; 1: errors; 2: default; 3: details; 4: debug */ +#define LOCALDISPLAYLEVEL(displayLevel, l, ...) \ + if (displayLevel >= l) { \ + DISPLAY(__VA_ARGS__); \ + } /* 0 : no display; 1: errors; 2: default; 3: details; 4: debug */ #undef DISPLAYLEVEL -#define DISPLAYLEVEL(l, ...) LOCALDISPLAYLEVEL(g_displayLevel, l, __VA_ARGS__) - +#define DISPLAYLEVEL(l, ...) LOCALDISPLAYLEVEL(g_displayLevel, l, __VA_ARGS__) + #ifndef LOCALDISPLAYUPDATE static const clock_t g_refreshRate = CLOCKS_PER_SEC * 15 / 100; static clock_t g_time = 0; #endif #undef LOCALDISPLAYUPDATE -#define LOCALDISPLAYUPDATE(displayLevel, l, ...) \ - if (displayLevel >= l) { \ +#define LOCALDISPLAYUPDATE(displayLevel, l, ...) \ + if (displayLevel >= l) { \ if ((clock() - g_time > g_refreshRate) || (displayLevel >= 4)) { \ - g_time = clock(); \ - DISPLAY(__VA_ARGS__); \ - } \ - } + g_time = clock(); \ + DISPLAY(__VA_ARGS__); \ + } \ + } #undef DISPLAYUPDATE -#define DISPLAYUPDATE(l, ...) LOCALDISPLAYUPDATE(g_displayLevel, l, __VA_ARGS__) - -/*-************************************* -* Hash table -*************************************** -* A small specialized hash map for storing activeDmers. -* The map does not resize, so if it becomes full it will loop forever. -* Thus, the map must be large enough to store every value. -* The map implements linear probing and keeps its load less than 0.5. -*/ - -#define MAP_EMPTY_VALUE ((U32)-1) -typedef struct COVER_map_pair_t_s { - U32 key; - U32 value; -} COVER_map_pair_t; - -typedef struct COVER_map_s { - COVER_map_pair_t *data; - U32 sizeLog; - U32 size; - U32 sizeMask; -} COVER_map_t; - -/** - * Clear the map. - */ -static void COVER_map_clear(COVER_map_t *map) { - memset(map->data, MAP_EMPTY_VALUE, map->size * sizeof(COVER_map_pair_t)); -} - -/** - * Initializes a map of the given size. - * Returns 1 on success and 0 on failure. - * The map must be destroyed with COVER_map_destroy(). - * The map is only guaranteed to be large enough to hold size elements. - */ -static int COVER_map_init(COVER_map_t *map, U32 size) { - map->sizeLog = ZSTD_highbit32(size) + 2; - map->size = (U32)1 << map->sizeLog; - map->sizeMask = map->size - 1; - map->data = (COVER_map_pair_t *)malloc(map->size * sizeof(COVER_map_pair_t)); - if (!map->data) { - map->sizeLog = 0; - map->size = 0; - return 0; - } - COVER_map_clear(map); - return 1; -} - -/** - * Internal hash function - */ +#define DISPLAYUPDATE(l, ...) LOCALDISPLAYUPDATE(g_displayLevel, l, __VA_ARGS__) + +/*-************************************* +* Hash table +*************************************** +* A small specialized hash map for storing activeDmers. +* The map does not resize, so if it becomes full it will loop forever. +* Thus, the map must be large enough to store every value. +* The map implements linear probing and keeps its load less than 0.5. +*/ + +#define MAP_EMPTY_VALUE ((U32)-1) +typedef struct COVER_map_pair_t_s { + U32 key; + U32 value; +} COVER_map_pair_t; + +typedef struct COVER_map_s { + COVER_map_pair_t *data; + U32 sizeLog; + U32 size; + U32 sizeMask; +} COVER_map_t; + +/** + * Clear the map. + */ +static void COVER_map_clear(COVER_map_t *map) { + memset(map->data, MAP_EMPTY_VALUE, map->size * sizeof(COVER_map_pair_t)); +} + +/** + * Initializes a map of the given size. + * Returns 1 on success and 0 on failure. + * The map must be destroyed with COVER_map_destroy(). + * The map is only guaranteed to be large enough to hold size elements. + */ +static int COVER_map_init(COVER_map_t *map, U32 size) { + map->sizeLog = ZSTD_highbit32(size) + 2; + map->size = (U32)1 << map->sizeLog; + map->sizeMask = map->size - 1; + map->data = (COVER_map_pair_t *)malloc(map->size * sizeof(COVER_map_pair_t)); + if (!map->data) { + map->sizeLog = 0; + map->size = 0; + return 0; + } + COVER_map_clear(map); + return 1; +} + +/** + * Internal hash function + */ static const U32 COVER_prime4bytes = 2654435761U; -static U32 COVER_map_hash(COVER_map_t *map, U32 key) { +static U32 COVER_map_hash(COVER_map_t *map, U32 key) { return (key * COVER_prime4bytes) >> (32 - map->sizeLog); -} - -/** - * Helper function that returns the index that a key should be placed into. - */ -static U32 COVER_map_index(COVER_map_t *map, U32 key) { - const U32 hash = COVER_map_hash(map, key); - U32 i; - for (i = hash;; i = (i + 1) & map->sizeMask) { - COVER_map_pair_t *pos = &map->data[i]; - if (pos->value == MAP_EMPTY_VALUE) { - return i; - } - if (pos->key == key) { - return i; - } - } -} - -/** - * Returns the pointer to the value for key. - * If key is not in the map, it is inserted and the value is set to 0. - * The map must not be full. - */ -static U32 *COVER_map_at(COVER_map_t *map, U32 key) { - COVER_map_pair_t *pos = &map->data[COVER_map_index(map, key)]; - if (pos->value == MAP_EMPTY_VALUE) { - pos->key = key; - pos->value = 0; - } - return &pos->value; -} - -/** - * Deletes key from the map if present. - */ -static void COVER_map_remove(COVER_map_t *map, U32 key) { - U32 i = COVER_map_index(map, key); - COVER_map_pair_t *del = &map->data[i]; - U32 shift = 1; - if (del->value == MAP_EMPTY_VALUE) { - return; - } - for (i = (i + 1) & map->sizeMask;; i = (i + 1) & map->sizeMask) { - COVER_map_pair_t *const pos = &map->data[i]; - /* If the position is empty we are done */ - if (pos->value == MAP_EMPTY_VALUE) { - del->value = MAP_EMPTY_VALUE; - return; - } - /* If pos can be moved to del do so */ - if (((i - COVER_map_hash(map, pos->key)) & map->sizeMask) >= shift) { - del->key = pos->key; - del->value = pos->value; - del = pos; - shift = 1; - } else { - ++shift; - } - } -} - -/** +} + +/** + * Helper function that returns the index that a key should be placed into. + */ +static U32 COVER_map_index(COVER_map_t *map, U32 key) { + const U32 hash = COVER_map_hash(map, key); + U32 i; + for (i = hash;; i = (i + 1) & map->sizeMask) { + COVER_map_pair_t *pos = &map->data[i]; + if (pos->value == MAP_EMPTY_VALUE) { + return i; + } + if (pos->key == key) { + return i; + } + } +} + +/** + * Returns the pointer to the value for key. + * If key is not in the map, it is inserted and the value is set to 0. + * The map must not be full. + */ +static U32 *COVER_map_at(COVER_map_t *map, U32 key) { + COVER_map_pair_t *pos = &map->data[COVER_map_index(map, key)]; + if (pos->value == MAP_EMPTY_VALUE) { + pos->key = key; + pos->value = 0; + } + return &pos->value; +} + +/** + * Deletes key from the map if present. + */ +static void COVER_map_remove(COVER_map_t *map, U32 key) { + U32 i = COVER_map_index(map, key); + COVER_map_pair_t *del = &map->data[i]; + U32 shift = 1; + if (del->value == MAP_EMPTY_VALUE) { + return; + } + for (i = (i + 1) & map->sizeMask;; i = (i + 1) & map->sizeMask) { + COVER_map_pair_t *const pos = &map->data[i]; + /* If the position is empty we are done */ + if (pos->value == MAP_EMPTY_VALUE) { + del->value = MAP_EMPTY_VALUE; + return; + } + /* If pos can be moved to del do so */ + if (((i - COVER_map_hash(map, pos->key)) & map->sizeMask) >= shift) { + del->key = pos->key; + del->value = pos->value; + del = pos; + shift = 1; + } else { + ++shift; + } + } +} + +/** * Destroys a map that is inited with COVER_map_init(). - */ -static void COVER_map_destroy(COVER_map_t *map) { - if (map->data) { - free(map->data); - } - map->data = NULL; - map->size = 0; -} - -/*-************************************* -* Context -***************************************/ - -typedef struct { - const BYTE *samples; - size_t *offsets; - const size_t *samplesSizes; - size_t nbSamples; + */ +static void COVER_map_destroy(COVER_map_t *map) { + if (map->data) { + free(map->data); + } + map->data = NULL; + map->size = 0; +} + +/*-************************************* +* Context +***************************************/ + +typedef struct { + const BYTE *samples; + size_t *offsets; + const size_t *samplesSizes; + size_t nbSamples; size_t nbTrainSamples; size_t nbTestSamples; - U32 *suffix; - size_t suffixSize; - U32 *freqs; - U32 *dmerAt; - unsigned d; -} COVER_ctx_t; - -/* We need a global context for qsort... */ + U32 *suffix; + size_t suffixSize; + U32 *freqs; + U32 *dmerAt; + unsigned d; +} COVER_ctx_t; + +/* We need a global context for qsort... */ static COVER_ctx_t *g_coverCtx = NULL; - -/*-************************************* -* Helper functions -***************************************/ - -/** - * Returns the sum of the sample sizes. - */ + +/*-************************************* +* Helper functions +***************************************/ + +/** + * Returns the sum of the sample sizes. + */ size_t COVER_sum(const size_t *samplesSizes, unsigned nbSamples) { - size_t sum = 0; + size_t sum = 0; unsigned i; - for (i = 0; i < nbSamples; ++i) { - sum += samplesSizes[i]; - } - return sum; -} - -/** - * Returns -1 if the dmer at lp is less than the dmer at rp. - * Return 0 if the dmers at lp and rp are equal. - * Returns 1 if the dmer at lp is greater than the dmer at rp. - */ -static int COVER_cmp(COVER_ctx_t *ctx, const void *lp, const void *rp) { - U32 const lhs = *(U32 const *)lp; - U32 const rhs = *(U32 const *)rp; - return memcmp(ctx->samples + lhs, ctx->samples + rhs, ctx->d); -} -/** - * Faster version for d <= 8. - */ -static int COVER_cmp8(COVER_ctx_t *ctx, const void *lp, const void *rp) { - U64 const mask = (ctx->d == 8) ? (U64)-1 : (((U64)1 << (8 * ctx->d)) - 1); - U64 const lhs = MEM_readLE64(ctx->samples + *(U32 const *)lp) & mask; - U64 const rhs = MEM_readLE64(ctx->samples + *(U32 const *)rp) & mask; - if (lhs < rhs) { - return -1; - } - return (lhs > rhs); -} - -/** - * Same as COVER_cmp() except ties are broken by pointer value + for (i = 0; i < nbSamples; ++i) { + sum += samplesSizes[i]; + } + return sum; +} + +/** + * Returns -1 if the dmer at lp is less than the dmer at rp. + * Return 0 if the dmers at lp and rp are equal. + * Returns 1 if the dmer at lp is greater than the dmer at rp. + */ +static int COVER_cmp(COVER_ctx_t *ctx, const void *lp, const void *rp) { + U32 const lhs = *(U32 const *)lp; + U32 const rhs = *(U32 const *)rp; + return memcmp(ctx->samples + lhs, ctx->samples + rhs, ctx->d); +} +/** + * Faster version for d <= 8. + */ +static int COVER_cmp8(COVER_ctx_t *ctx, const void *lp, const void *rp) { + U64 const mask = (ctx->d == 8) ? (U64)-1 : (((U64)1 << (8 * ctx->d)) - 1); + U64 const lhs = MEM_readLE64(ctx->samples + *(U32 const *)lp) & mask; + U64 const rhs = MEM_readLE64(ctx->samples + *(U32 const *)rp) & mask; + if (lhs < rhs) { + return -1; + } + return (lhs > rhs); +} + +/** + * Same as COVER_cmp() except ties are broken by pointer value * NOTE: g_coverCtx must be set to call this function. A global is required because - * qsort doesn't take an opaque pointer. - */ + * qsort doesn't take an opaque pointer. + */ static int WIN_CDECL COVER_strict_cmp(const void *lp, const void *rp) { int result = COVER_cmp(g_coverCtx, lp, rp); - if (result == 0) { - result = lp < rp ? -1 : 1; - } - return result; -} -/** - * Faster version for d <= 8. - */ + if (result == 0) { + result = lp < rp ? -1 : 1; + } + return result; +} +/** + * Faster version for d <= 8. + */ static int WIN_CDECL COVER_strict_cmp8(const void *lp, const void *rp) { int result = COVER_cmp8(g_coverCtx, lp, rp); - if (result == 0) { - result = lp < rp ? -1 : 1; - } - return result; -} - -/** - * Returns the first pointer in [first, last) whose element does not compare - * less than value. If no such element exists it returns last. - */ -static const size_t *COVER_lower_bound(const size_t *first, const size_t *last, - size_t value) { - size_t count = last - first; - while (count != 0) { - size_t step = count / 2; - const size_t *ptr = first; - ptr += step; - if (*ptr < value) { - first = ++ptr; - count -= step + 1; - } else { - count = step; - } - } - return first; -} - -/** - * Generic groupBy function. - * Groups an array sorted by cmp into groups with equivalent values. - * Calls grp for each group. - */ -static void -COVER_groupBy(const void *data, size_t count, size_t size, COVER_ctx_t *ctx, - int (*cmp)(COVER_ctx_t *, const void *, const void *), - void (*grp)(COVER_ctx_t *, const void *, const void *)) { - const BYTE *ptr = (const BYTE *)data; - size_t num = 0; - while (num < count) { - const BYTE *grpEnd = ptr + size; - ++num; - while (num < count && cmp(ctx, ptr, grpEnd) == 0) { - grpEnd += size; - ++num; - } - grp(ctx, ptr, grpEnd); - ptr = grpEnd; - } -} - -/*-************************************* -* Cover functions -***************************************/ - -/** - * Called on each group of positions with the same dmer. - * Counts the frequency of each dmer and saves it in the suffix array. - * Fills `ctx->dmerAt`. - */ -static void COVER_group(COVER_ctx_t *ctx, const void *group, - const void *groupEnd) { - /* The group consists of all the positions with the same first d bytes. */ - const U32 *grpPtr = (const U32 *)group; - const U32 *grpEnd = (const U32 *)groupEnd; - /* The dmerId is how we will reference this dmer. - * This allows us to map the whole dmer space to a much smaller space, the - * size of the suffix array. - */ - const U32 dmerId = (U32)(grpPtr - ctx->suffix); - /* Count the number of samples this dmer shows up in */ - U32 freq = 0; - /* Details */ - const size_t *curOffsetPtr = ctx->offsets; - const size_t *offsetsEnd = ctx->offsets + ctx->nbSamples; - /* Once *grpPtr >= curSampleEnd this occurrence of the dmer is in a - * different sample than the last. - */ - size_t curSampleEnd = ctx->offsets[0]; - for (; grpPtr != grpEnd; ++grpPtr) { - /* Save the dmerId for this position so we can get back to it. */ - ctx->dmerAt[*grpPtr] = dmerId; - /* Dictionaries only help for the first reference to the dmer. - * After that zstd can reference the match from the previous reference. - * So only count each dmer once for each sample it is in. - */ - if (*grpPtr < curSampleEnd) { - continue; - } - freq += 1; - /* Binary search to find the end of the sample *grpPtr is in. - * In the common case that grpPtr + 1 == grpEnd we can skip the binary - * search because the loop is over. - */ - if (grpPtr + 1 != grpEnd) { - const size_t *sampleEndPtr = - COVER_lower_bound(curOffsetPtr, offsetsEnd, *grpPtr); - curSampleEnd = *sampleEndPtr; - curOffsetPtr = sampleEndPtr + 1; - } - } - /* At this point we are never going to look at this segment of the suffix - * array again. We take advantage of this fact to save memory. - * We store the frequency of the dmer in the first position of the group, - * which is dmerId. - */ - ctx->suffix[dmerId] = freq; -} - - -/** - * Selects the best segment in an epoch. - * Segments of are scored according to the function: - * - * Let F(d) be the frequency of dmer d. - * Let S_i be the dmer at position i of segment S which has length k. - * - * Score(S) = F(S_1) + F(S_2) + ... + F(S_{k-d+1}) - * + if (result == 0) { + result = lp < rp ? -1 : 1; + } + return result; +} + +/** + * Returns the first pointer in [first, last) whose element does not compare + * less than value. If no such element exists it returns last. + */ +static const size_t *COVER_lower_bound(const size_t *first, const size_t *last, + size_t value) { + size_t count = last - first; + while (count != 0) { + size_t step = count / 2; + const size_t *ptr = first; + ptr += step; + if (*ptr < value) { + first = ++ptr; + count -= step + 1; + } else { + count = step; + } + } + return first; +} + +/** + * Generic groupBy function. + * Groups an array sorted by cmp into groups with equivalent values. + * Calls grp for each group. + */ +static void +COVER_groupBy(const void *data, size_t count, size_t size, COVER_ctx_t *ctx, + int (*cmp)(COVER_ctx_t *, const void *, const void *), + void (*grp)(COVER_ctx_t *, const void *, const void *)) { + const BYTE *ptr = (const BYTE *)data; + size_t num = 0; + while (num < count) { + const BYTE *grpEnd = ptr + size; + ++num; + while (num < count && cmp(ctx, ptr, grpEnd) == 0) { + grpEnd += size; + ++num; + } + grp(ctx, ptr, grpEnd); + ptr = grpEnd; + } +} + +/*-************************************* +* Cover functions +***************************************/ + +/** + * Called on each group of positions with the same dmer. + * Counts the frequency of each dmer and saves it in the suffix array. + * Fills `ctx->dmerAt`. + */ +static void COVER_group(COVER_ctx_t *ctx, const void *group, + const void *groupEnd) { + /* The group consists of all the positions with the same first d bytes. */ + const U32 *grpPtr = (const U32 *)group; + const U32 *grpEnd = (const U32 *)groupEnd; + /* The dmerId is how we will reference this dmer. + * This allows us to map the whole dmer space to a much smaller space, the + * size of the suffix array. + */ + const U32 dmerId = (U32)(grpPtr - ctx->suffix); + /* Count the number of samples this dmer shows up in */ + U32 freq = 0; + /* Details */ + const size_t *curOffsetPtr = ctx->offsets; + const size_t *offsetsEnd = ctx->offsets + ctx->nbSamples; + /* Once *grpPtr >= curSampleEnd this occurrence of the dmer is in a + * different sample than the last. + */ + size_t curSampleEnd = ctx->offsets[0]; + for (; grpPtr != grpEnd; ++grpPtr) { + /* Save the dmerId for this position so we can get back to it. */ + ctx->dmerAt[*grpPtr] = dmerId; + /* Dictionaries only help for the first reference to the dmer. + * After that zstd can reference the match from the previous reference. + * So only count each dmer once for each sample it is in. + */ + if (*grpPtr < curSampleEnd) { + continue; + } + freq += 1; + /* Binary search to find the end of the sample *grpPtr is in. + * In the common case that grpPtr + 1 == grpEnd we can skip the binary + * search because the loop is over. + */ + if (grpPtr + 1 != grpEnd) { + const size_t *sampleEndPtr = + COVER_lower_bound(curOffsetPtr, offsetsEnd, *grpPtr); + curSampleEnd = *sampleEndPtr; + curOffsetPtr = sampleEndPtr + 1; + } + } + /* At this point we are never going to look at this segment of the suffix + * array again. We take advantage of this fact to save memory. + * We store the frequency of the dmer in the first position of the group, + * which is dmerId. + */ + ctx->suffix[dmerId] = freq; +} + + +/** + * Selects the best segment in an epoch. + * Segments of are scored according to the function: + * + * Let F(d) be the frequency of dmer d. + * Let S_i be the dmer at position i of segment S which has length k. + * + * Score(S) = F(S_1) + F(S_2) + ... + F(S_{k-d+1}) + * * Once the dmer d is in the dictionary we set F(d) = 0. - */ -static COVER_segment_t COVER_selectSegment(const COVER_ctx_t *ctx, U32 *freqs, - COVER_map_t *activeDmers, U32 begin, - U32 end, - ZDICT_cover_params_t parameters) { - /* Constants */ - const U32 k = parameters.k; - const U32 d = parameters.d; - const U32 dmersInK = k - d + 1; - /* Try each segment (activeSegment) and save the best (bestSegment) */ - COVER_segment_t bestSegment = {0, 0, 0}; - COVER_segment_t activeSegment; - /* Reset the activeDmers in the segment */ - COVER_map_clear(activeDmers); - /* The activeSegment starts at the beginning of the epoch. */ - activeSegment.begin = begin; - activeSegment.end = begin; - activeSegment.score = 0; - /* Slide the activeSegment through the whole epoch. - * Save the best segment in bestSegment. - */ - while (activeSegment.end < end) { - /* The dmerId for the dmer at the next position */ - U32 newDmer = ctx->dmerAt[activeSegment.end]; - /* The entry in activeDmers for this dmerId */ - U32 *newDmerOcc = COVER_map_at(activeDmers, newDmer); - /* If the dmer isn't already present in the segment add its score. */ - if (*newDmerOcc == 0) { - /* The paper suggest using the L-0.5 norm, but experiments show that it - * doesn't help. - */ - activeSegment.score += freqs[newDmer]; - } - /* Add the dmer to the segment */ - activeSegment.end += 1; - *newDmerOcc += 1; - - /* If the window is now too large, drop the first position */ - if (activeSegment.end - activeSegment.begin == dmersInK + 1) { - U32 delDmer = ctx->dmerAt[activeSegment.begin]; - U32 *delDmerOcc = COVER_map_at(activeDmers, delDmer); - activeSegment.begin += 1; - *delDmerOcc -= 1; + */ +static COVER_segment_t COVER_selectSegment(const COVER_ctx_t *ctx, U32 *freqs, + COVER_map_t *activeDmers, U32 begin, + U32 end, + ZDICT_cover_params_t parameters) { + /* Constants */ + const U32 k = parameters.k; + const U32 d = parameters.d; + const U32 dmersInK = k - d + 1; + /* Try each segment (activeSegment) and save the best (bestSegment) */ + COVER_segment_t bestSegment = {0, 0, 0}; + COVER_segment_t activeSegment; + /* Reset the activeDmers in the segment */ + COVER_map_clear(activeDmers); + /* The activeSegment starts at the beginning of the epoch. */ + activeSegment.begin = begin; + activeSegment.end = begin; + activeSegment.score = 0; + /* Slide the activeSegment through the whole epoch. + * Save the best segment in bestSegment. + */ + while (activeSegment.end < end) { + /* The dmerId for the dmer at the next position */ + U32 newDmer = ctx->dmerAt[activeSegment.end]; + /* The entry in activeDmers for this dmerId */ + U32 *newDmerOcc = COVER_map_at(activeDmers, newDmer); + /* If the dmer isn't already present in the segment add its score. */ + if (*newDmerOcc == 0) { + /* The paper suggest using the L-0.5 norm, but experiments show that it + * doesn't help. + */ + activeSegment.score += freqs[newDmer]; + } + /* Add the dmer to the segment */ + activeSegment.end += 1; + *newDmerOcc += 1; + + /* If the window is now too large, drop the first position */ + if (activeSegment.end - activeSegment.begin == dmersInK + 1) { + U32 delDmer = ctx->dmerAt[activeSegment.begin]; + U32 *delDmerOcc = COVER_map_at(activeDmers, delDmer); + activeSegment.begin += 1; + *delDmerOcc -= 1; /* If this is the last occurrence of the dmer, subtract its score */ - if (*delDmerOcc == 0) { - COVER_map_remove(activeDmers, delDmer); - activeSegment.score -= freqs[delDmer]; - } - } - - /* If this segment is the best so far save it */ - if (activeSegment.score > bestSegment.score) { - bestSegment = activeSegment; - } - } - { - /* Trim off the zero frequency head and tail from the segment. */ - U32 newBegin = bestSegment.end; - U32 newEnd = bestSegment.begin; - U32 pos; - for (pos = bestSegment.begin; pos != bestSegment.end; ++pos) { - U32 freq = freqs[ctx->dmerAt[pos]]; - if (freq != 0) { - newBegin = MIN(newBegin, pos); - newEnd = pos + 1; - } - } - bestSegment.begin = newBegin; - bestSegment.end = newEnd; - } - { - /* Zero out the frequency of each dmer covered by the chosen segment. */ - U32 pos; - for (pos = bestSegment.begin; pos != bestSegment.end; ++pos) { - freqs[ctx->dmerAt[pos]] = 0; - } - } - return bestSegment; -} - -/** - * Check the validity of the parameters. - * Returns non-zero if the parameters are valid and 0 otherwise. - */ -static int COVER_checkParameters(ZDICT_cover_params_t parameters, - size_t maxDictSize) { - /* k and d are required parameters */ - if (parameters.d == 0 || parameters.k == 0) { - return 0; - } - /* k <= maxDictSize */ - if (parameters.k > maxDictSize) { - return 0; - } - /* d <= k */ - if (parameters.d > parameters.k) { - return 0; - } + if (*delDmerOcc == 0) { + COVER_map_remove(activeDmers, delDmer); + activeSegment.score -= freqs[delDmer]; + } + } + + /* If this segment is the best so far save it */ + if (activeSegment.score > bestSegment.score) { + bestSegment = activeSegment; + } + } + { + /* Trim off the zero frequency head and tail from the segment. */ + U32 newBegin = bestSegment.end; + U32 newEnd = bestSegment.begin; + U32 pos; + for (pos = bestSegment.begin; pos != bestSegment.end; ++pos) { + U32 freq = freqs[ctx->dmerAt[pos]]; + if (freq != 0) { + newBegin = MIN(newBegin, pos); + newEnd = pos + 1; + } + } + bestSegment.begin = newBegin; + bestSegment.end = newEnd; + } + { + /* Zero out the frequency of each dmer covered by the chosen segment. */ + U32 pos; + for (pos = bestSegment.begin; pos != bestSegment.end; ++pos) { + freqs[ctx->dmerAt[pos]] = 0; + } + } + return bestSegment; +} + +/** + * Check the validity of the parameters. + * Returns non-zero if the parameters are valid and 0 otherwise. + */ +static int COVER_checkParameters(ZDICT_cover_params_t parameters, + size_t maxDictSize) { + /* k and d are required parameters */ + if (parameters.d == 0 || parameters.k == 0) { + return 0; + } + /* k <= maxDictSize */ + if (parameters.k > maxDictSize) { + return 0; + } + /* d <= k */ + if (parameters.d > parameters.k) { + return 0; + } /* 0 < splitPoint <= 1 */ if (parameters.splitPoint <= 0 || parameters.splitPoint > 1){ return 0; } - return 1; -} - -/** - * Clean up a context initialized with `COVER_ctx_init()`. - */ -static void COVER_ctx_destroy(COVER_ctx_t *ctx) { - if (!ctx) { - return; - } - if (ctx->suffix) { - free(ctx->suffix); - ctx->suffix = NULL; - } - if (ctx->freqs) { - free(ctx->freqs); - ctx->freqs = NULL; - } - if (ctx->dmerAt) { - free(ctx->dmerAt); - ctx->dmerAt = NULL; - } - if (ctx->offsets) { - free(ctx->offsets); - ctx->offsets = NULL; - } -} - -/** - * Prepare a context for dictionary building. - * The context is only dependent on the parameter `d` and can used multiple - * times. + return 1; +} + +/** + * Clean up a context initialized with `COVER_ctx_init()`. + */ +static void COVER_ctx_destroy(COVER_ctx_t *ctx) { + if (!ctx) { + return; + } + if (ctx->suffix) { + free(ctx->suffix); + ctx->suffix = NULL; + } + if (ctx->freqs) { + free(ctx->freqs); + ctx->freqs = NULL; + } + if (ctx->dmerAt) { + free(ctx->dmerAt); + ctx->dmerAt = NULL; + } + if (ctx->offsets) { + free(ctx->offsets); + ctx->offsets = NULL; + } +} + +/** + * Prepare a context for dictionary building. + * The context is only dependent on the parameter `d` and can used multiple + * times. * Returns 0 on success or error code on error. - * The context must be destroyed with `COVER_ctx_destroy()`. - */ + * The context must be destroyed with `COVER_ctx_destroy()`. + */ static size_t COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer, - const size_t *samplesSizes, unsigned nbSamples, + const size_t *samplesSizes, unsigned nbSamples, unsigned d, double splitPoint) { - const BYTE *const samples = (const BYTE *)samplesBuffer; - const size_t totalSamplesSize = COVER_sum(samplesSizes, nbSamples); + const BYTE *const samples = (const BYTE *)samplesBuffer; + const size_t totalSamplesSize = COVER_sum(samplesSizes, nbSamples); /* Split samples into testing and training sets */ const unsigned nbTrainSamples = splitPoint < 1.0 ? (unsigned)((double)nbSamples * splitPoint) : nbSamples; const unsigned nbTestSamples = splitPoint < 1.0 ? nbSamples - nbTrainSamples : nbSamples; const size_t trainingSamplesSize = splitPoint < 1.0 ? COVER_sum(samplesSizes, nbTrainSamples) : totalSamplesSize; const size_t testSamplesSize = splitPoint < 1.0 ? COVER_sum(samplesSizes + nbTrainSamples, nbTestSamples) : totalSamplesSize; - /* Checks */ - if (totalSamplesSize < MAX(d, sizeof(U64)) || - totalSamplesSize >= (size_t)COVER_MAX_SAMPLES_SIZE) { - DISPLAYLEVEL(1, "Total samples size is too large (%u MB), maximum size is %u MB\n", + /* Checks */ + if (totalSamplesSize < MAX(d, sizeof(U64)) || + totalSamplesSize >= (size_t)COVER_MAX_SAMPLES_SIZE) { + DISPLAYLEVEL(1, "Total samples size is too large (%u MB), maximum size is %u MB\n", (unsigned)(totalSamplesSize>>20), (COVER_MAX_SAMPLES_SIZE >> 20)); return ERROR(srcSize_wrong); - } + } /* Check if there are at least 5 training samples */ if (nbTrainSamples < 5) { DISPLAYLEVEL(1, "Total number of training samples is %u and is invalid.", nbTrainSamples); @@ -573,50 +573,50 @@ static size_t COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer, DISPLAYLEVEL(1, "Total number of testing samples is %u and is invalid.", nbTestSamples); return ERROR(srcSize_wrong); } - /* Zero the context */ - memset(ctx, 0, sizeof(*ctx)); + /* Zero the context */ + memset(ctx, 0, sizeof(*ctx)); DISPLAYLEVEL(2, "Training on %u samples of total size %u\n", nbTrainSamples, (unsigned)trainingSamplesSize); DISPLAYLEVEL(2, "Testing on %u samples of total size %u\n", nbTestSamples, (unsigned)testSamplesSize); - ctx->samples = samples; - ctx->samplesSizes = samplesSizes; - ctx->nbSamples = nbSamples; + ctx->samples = samples; + ctx->samplesSizes = samplesSizes; + ctx->nbSamples = nbSamples; ctx->nbTrainSamples = nbTrainSamples; ctx->nbTestSamples = nbTestSamples; - /* Partial suffix array */ + /* Partial suffix array */ ctx->suffixSize = trainingSamplesSize - MAX(d, sizeof(U64)) + 1; - ctx->suffix = (U32 *)malloc(ctx->suffixSize * sizeof(U32)); - /* Maps index to the dmerID */ - ctx->dmerAt = (U32 *)malloc(ctx->suffixSize * sizeof(U32)); - /* The offsets of each file */ - ctx->offsets = (size_t *)malloc((nbSamples + 1) * sizeof(size_t)); - if (!ctx->suffix || !ctx->dmerAt || !ctx->offsets) { - DISPLAYLEVEL(1, "Failed to allocate scratch buffers\n"); - COVER_ctx_destroy(ctx); + ctx->suffix = (U32 *)malloc(ctx->suffixSize * sizeof(U32)); + /* Maps index to the dmerID */ + ctx->dmerAt = (U32 *)malloc(ctx->suffixSize * sizeof(U32)); + /* The offsets of each file */ + ctx->offsets = (size_t *)malloc((nbSamples + 1) * sizeof(size_t)); + if (!ctx->suffix || !ctx->dmerAt || !ctx->offsets) { + DISPLAYLEVEL(1, "Failed to allocate scratch buffers\n"); + COVER_ctx_destroy(ctx); return ERROR(memory_allocation); - } - ctx->freqs = NULL; - ctx->d = d; - + } + ctx->freqs = NULL; + ctx->d = d; + /* Fill offsets from the samplesSizes */ - { - U32 i; - ctx->offsets[0] = 0; - for (i = 1; i <= nbSamples; ++i) { - ctx->offsets[i] = ctx->offsets[i - 1] + samplesSizes[i - 1]; - } - } - DISPLAYLEVEL(2, "Constructing partial suffix array\n"); - { - /* suffix is a partial suffix array. - * It only sorts suffixes by their first parameters.d bytes. - * The sort is stable, so each dmer group is sorted by position in input. - */ - U32 i; - for (i = 0; i < ctx->suffixSize; ++i) { - ctx->suffix[i] = i; - } + { + U32 i; + ctx->offsets[0] = 0; + for (i = 1; i <= nbSamples; ++i) { + ctx->offsets[i] = ctx->offsets[i - 1] + samplesSizes[i - 1]; + } + } + DISPLAYLEVEL(2, "Constructing partial suffix array\n"); + { + /* suffix is a partial suffix array. + * It only sorts suffixes by their first parameters.d bytes. + * The sort is stable, so each dmer group is sorted by position in input. + */ + U32 i; + for (i = 0; i < ctx->suffixSize; ++i) { + ctx->suffix[i] = i; + } /* qsort doesn't take an opaque pointer, so pass as a global. * On OpenBSD qsort() is not guaranteed to be stable, their mergesort() is. */ @@ -625,25 +625,25 @@ static size_t COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer, mergesort(ctx->suffix, ctx->suffixSize, sizeof(U32), (ctx->d <= 8 ? &COVER_strict_cmp8 : &COVER_strict_cmp)); #else - qsort(ctx->suffix, ctx->suffixSize, sizeof(U32), - (ctx->d <= 8 ? &COVER_strict_cmp8 : &COVER_strict_cmp)); + qsort(ctx->suffix, ctx->suffixSize, sizeof(U32), + (ctx->d <= 8 ? &COVER_strict_cmp8 : &COVER_strict_cmp)); #endif - } - DISPLAYLEVEL(2, "Computing frequencies\n"); - /* For each dmer group (group of positions with the same first d bytes): - * 1. For each position we set dmerAt[position] = dmerID. The dmerID is - * (groupBeginPtr - suffix). This allows us to go from position to - * dmerID so we can look up values in freq. - * 2. We calculate how many samples the dmer occurs in and save it in - * freqs[dmerId]. - */ - COVER_groupBy(ctx->suffix, ctx->suffixSize, sizeof(U32), ctx, - (ctx->d <= 8 ? &COVER_cmp8 : &COVER_cmp), &COVER_group); - ctx->freqs = ctx->suffix; - ctx->suffix = NULL; + } + DISPLAYLEVEL(2, "Computing frequencies\n"); + /* For each dmer group (group of positions with the same first d bytes): + * 1. For each position we set dmerAt[position] = dmerID. The dmerID is + * (groupBeginPtr - suffix). This allows us to go from position to + * dmerID so we can look up values in freq. + * 2. We calculate how many samples the dmer occurs in and save it in + * freqs[dmerId]. + */ + COVER_groupBy(ctx->suffix, ctx->suffixSize, sizeof(U32), ctx, + (ctx->d <= 8 ? &COVER_cmp8 : &COVER_cmp), &COVER_group); + ctx->freqs = ctx->suffix; + ctx->suffix = NULL; return 0; -} - +} + void COVER_warnOnSmallCorpus(size_t maxDictSize, size_t nbDmers, int displayLevel) { const double ratio = (double)nbDmers / maxDictSize; @@ -677,120 +677,120 @@ COVER_epoch_info_t COVER_computeEpochs(U32 maxDictSize, return epochs; } -/** - * Given the prepared context build the dictionary. - */ -static size_t COVER_buildDictionary(const COVER_ctx_t *ctx, U32 *freqs, - COVER_map_t *activeDmers, void *dictBuffer, - size_t dictBufferCapacity, - ZDICT_cover_params_t parameters) { - BYTE *const dict = (BYTE *)dictBuffer; - size_t tail = dictBufferCapacity; +/** + * Given the prepared context build the dictionary. + */ +static size_t COVER_buildDictionary(const COVER_ctx_t *ctx, U32 *freqs, + COVER_map_t *activeDmers, void *dictBuffer, + size_t dictBufferCapacity, + ZDICT_cover_params_t parameters) { + BYTE *const dict = (BYTE *)dictBuffer; + size_t tail = dictBufferCapacity; /* Divide the data into epochs. We will select one segment from each epoch. */ const COVER_epoch_info_t epochs = COVER_computeEpochs( (U32)dictBufferCapacity, (U32)ctx->suffixSize, parameters.k, 4); const size_t maxZeroScoreRun = MAX(10, MIN(100, epochs.num >> 3)); size_t zeroScoreRun = 0; - size_t epoch; + size_t epoch; DISPLAYLEVEL(2, "Breaking content into %u epochs of size %u\n", (U32)epochs.num, (U32)epochs.size); - /* Loop through the epochs until there are no more segments or the dictionary - * is full. - */ + /* Loop through the epochs until there are no more segments or the dictionary + * is full. + */ for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs.num) { const U32 epochBegin = (U32)(epoch * epochs.size); const U32 epochEnd = epochBegin + epochs.size; - size_t segmentSize; - /* Select a segment */ - COVER_segment_t segment = COVER_selectSegment( - ctx, freqs, activeDmers, epochBegin, epochEnd, parameters); + size_t segmentSize; + /* Select a segment */ + COVER_segment_t segment = COVER_selectSegment( + ctx, freqs, activeDmers, epochBegin, epochEnd, parameters); /* If the segment covers no dmers, then we are out of content. * There may be new content in other epochs, for continue for some time. */ - if (segment.score == 0) { + if (segment.score == 0) { if (++zeroScoreRun >= maxZeroScoreRun) { break; } continue; - } + } zeroScoreRun = 0; - /* Trim the segment if necessary and if it is too small then we are done */ - segmentSize = MIN(segment.end - segment.begin + parameters.d - 1, tail); - if (segmentSize < parameters.d) { - break; - } - /* We fill the dictionary from the back to allow the best segments to be - * referenced with the smallest offsets. - */ - tail -= segmentSize; - memcpy(dict + tail, ctx->samples + segment.begin, segmentSize); - DISPLAYUPDATE( - 2, "\r%u%% ", + /* Trim the segment if necessary and if it is too small then we are done */ + segmentSize = MIN(segment.end - segment.begin + parameters.d - 1, tail); + if (segmentSize < parameters.d) { + break; + } + /* We fill the dictionary from the back to allow the best segments to be + * referenced with the smallest offsets. + */ + tail -= segmentSize; + memcpy(dict + tail, ctx->samples + segment.begin, segmentSize); + DISPLAYUPDATE( + 2, "\r%u%% ", (unsigned)(((dictBufferCapacity - tail) * 100) / dictBufferCapacity)); - } - DISPLAYLEVEL(2, "\r%79s\r", ""); - return tail; -} - -ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover( - void *dictBuffer, size_t dictBufferCapacity, - const void *samplesBuffer, const size_t *samplesSizes, unsigned nbSamples, - ZDICT_cover_params_t parameters) -{ - BYTE* const dict = (BYTE*)dictBuffer; - COVER_ctx_t ctx; - COVER_map_t activeDmers; + } + DISPLAYLEVEL(2, "\r%79s\r", ""); + return tail; +} + +ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover( + void *dictBuffer, size_t dictBufferCapacity, + const void *samplesBuffer, const size_t *samplesSizes, unsigned nbSamples, + ZDICT_cover_params_t parameters) +{ + BYTE* const dict = (BYTE*)dictBuffer; + COVER_ctx_t ctx; + COVER_map_t activeDmers; parameters.splitPoint = 1.0; - /* Initialize global data */ + /* Initialize global data */ g_displayLevel = (int)parameters.zParams.notificationLevel; - /* Checks */ - if (!COVER_checkParameters(parameters, dictBufferCapacity)) { - DISPLAYLEVEL(1, "Cover parameters incorrect\n"); + /* Checks */ + if (!COVER_checkParameters(parameters, dictBufferCapacity)) { + DISPLAYLEVEL(1, "Cover parameters incorrect\n"); return ERROR(parameter_outOfBound); - } - if (nbSamples == 0) { - DISPLAYLEVEL(1, "Cover must have at least one input file\n"); + } + if (nbSamples == 0) { + DISPLAYLEVEL(1, "Cover must have at least one input file\n"); return ERROR(srcSize_wrong); - } - if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) { - DISPLAYLEVEL(1, "dictBufferCapacity must be at least %u\n", - ZDICT_DICTSIZE_MIN); - return ERROR(dstSize_tooSmall); - } - /* Initialize context and activeDmers */ + } + if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) { + DISPLAYLEVEL(1, "dictBufferCapacity must be at least %u\n", + ZDICT_DICTSIZE_MIN); + return ERROR(dstSize_tooSmall); + } + /* Initialize context and activeDmers */ { size_t const initVal = COVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples, parameters.d, parameters.splitPoint); if (ZSTD_isError(initVal)) { return initVal; } - } + } COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.suffixSize, g_displayLevel); - if (!COVER_map_init(&activeDmers, parameters.k - parameters.d + 1)) { - DISPLAYLEVEL(1, "Failed to allocate dmer map: out of memory\n"); - COVER_ctx_destroy(&ctx); + if (!COVER_map_init(&activeDmers, parameters.k - parameters.d + 1)) { + DISPLAYLEVEL(1, "Failed to allocate dmer map: out of memory\n"); + COVER_ctx_destroy(&ctx); return ERROR(memory_allocation); - } - - DISPLAYLEVEL(2, "Building dictionary\n"); - { - const size_t tail = - COVER_buildDictionary(&ctx, ctx.freqs, &activeDmers, dictBuffer, - dictBufferCapacity, parameters); - const size_t dictionarySize = ZDICT_finalizeDictionary( - dict, dictBufferCapacity, dict + tail, dictBufferCapacity - tail, - samplesBuffer, samplesSizes, nbSamples, parameters.zParams); - if (!ZSTD_isError(dictionarySize)) { - DISPLAYLEVEL(2, "Constructed dictionary of size %u\n", + } + + DISPLAYLEVEL(2, "Building dictionary\n"); + { + const size_t tail = + COVER_buildDictionary(&ctx, ctx.freqs, &activeDmers, dictBuffer, + dictBufferCapacity, parameters); + const size_t dictionarySize = ZDICT_finalizeDictionary( + dict, dictBufferCapacity, dict + tail, dictBufferCapacity - tail, + samplesBuffer, samplesSizes, nbSamples, parameters.zParams); + if (!ZSTD_isError(dictionarySize)) { + DISPLAYLEVEL(2, "Constructed dictionary of size %u\n", (unsigned)dictionarySize); - } - COVER_ctx_destroy(&ctx); - COVER_map_destroy(&activeDmers); - return dictionarySize; - } -} - - + } + COVER_ctx_destroy(&ctx); + COVER_map_destroy(&activeDmers); + return dictionarySize; + } +} + + size_t COVER_checkTotalCompressedSize(const ZDICT_cover_params_t parameters, const size_t *samplesSizes, const BYTE *samples, @@ -845,111 +845,111 @@ _compressCleanup: } -/** - * Initialize the `COVER_best_t`. - */ +/** + * Initialize the `COVER_best_t`. + */ void COVER_best_init(COVER_best_t *best) { - if (best==NULL) return; /* compatible with init on NULL */ - (void)ZSTD_pthread_mutex_init(&best->mutex, NULL); - (void)ZSTD_pthread_cond_init(&best->cond, NULL); - best->liveJobs = 0; - best->dict = NULL; - best->dictSize = 0; - best->compressedSize = (size_t)-1; - memset(&best->parameters, 0, sizeof(best->parameters)); -} - -/** - * Wait until liveJobs == 0. - */ + if (best==NULL) return; /* compatible with init on NULL */ + (void)ZSTD_pthread_mutex_init(&best->mutex, NULL); + (void)ZSTD_pthread_cond_init(&best->cond, NULL); + best->liveJobs = 0; + best->dict = NULL; + best->dictSize = 0; + best->compressedSize = (size_t)-1; + memset(&best->parameters, 0, sizeof(best->parameters)); +} + +/** + * Wait until liveJobs == 0. + */ void COVER_best_wait(COVER_best_t *best) { - if (!best) { - return; - } - ZSTD_pthread_mutex_lock(&best->mutex); - while (best->liveJobs != 0) { - ZSTD_pthread_cond_wait(&best->cond, &best->mutex); - } - ZSTD_pthread_mutex_unlock(&best->mutex); -} - -/** - * Call COVER_best_wait() and then destroy the COVER_best_t. - */ + if (!best) { + return; + } + ZSTD_pthread_mutex_lock(&best->mutex); + while (best->liveJobs != 0) { + ZSTD_pthread_cond_wait(&best->cond, &best->mutex); + } + ZSTD_pthread_mutex_unlock(&best->mutex); +} + +/** + * Call COVER_best_wait() and then destroy the COVER_best_t. + */ void COVER_best_destroy(COVER_best_t *best) { - if (!best) { - return; - } - COVER_best_wait(best); - if (best->dict) { - free(best->dict); - } - ZSTD_pthread_mutex_destroy(&best->mutex); - ZSTD_pthread_cond_destroy(&best->cond); -} - -/** - * Called when a thread is about to be launched. - * Increments liveJobs. - */ + if (!best) { + return; + } + COVER_best_wait(best); + if (best->dict) { + free(best->dict); + } + ZSTD_pthread_mutex_destroy(&best->mutex); + ZSTD_pthread_cond_destroy(&best->cond); +} + +/** + * Called when a thread is about to be launched. + * Increments liveJobs. + */ void COVER_best_start(COVER_best_t *best) { - if (!best) { - return; - } - ZSTD_pthread_mutex_lock(&best->mutex); - ++best->liveJobs; - ZSTD_pthread_mutex_unlock(&best->mutex); -} - -/** - * Called when a thread finishes executing, both on error or success. - * Decrements liveJobs and signals any waiting threads if liveJobs == 0. - * If this dictionary is the best so far save it and its parameters. - */ + if (!best) { + return; + } + ZSTD_pthread_mutex_lock(&best->mutex); + ++best->liveJobs; + ZSTD_pthread_mutex_unlock(&best->mutex); +} + +/** + * Called when a thread finishes executing, both on error or success. + * Decrements liveJobs and signals any waiting threads if liveJobs == 0. + * If this dictionary is the best so far save it and its parameters. + */ void COVER_best_finish(COVER_best_t *best, ZDICT_cover_params_t parameters, COVER_dictSelection_t selection) { void* dict = selection.dictContent; size_t compressedSize = selection.totalCompressedSize; size_t dictSize = selection.dictSize; - if (!best) { - return; - } - { - size_t liveJobs; - ZSTD_pthread_mutex_lock(&best->mutex); - --best->liveJobs; - liveJobs = best->liveJobs; - /* If the new dictionary is better */ - if (compressedSize < best->compressedSize) { - /* Allocate space if necessary */ - if (!best->dict || best->dictSize < dictSize) { - if (best->dict) { - free(best->dict); - } - best->dict = malloc(dictSize); - if (!best->dict) { - best->compressedSize = ERROR(GENERIC); - best->dictSize = 0; + if (!best) { + return; + } + { + size_t liveJobs; + ZSTD_pthread_mutex_lock(&best->mutex); + --best->liveJobs; + liveJobs = best->liveJobs; + /* If the new dictionary is better */ + if (compressedSize < best->compressedSize) { + /* Allocate space if necessary */ + if (!best->dict || best->dictSize < dictSize) { + if (best->dict) { + free(best->dict); + } + best->dict = malloc(dictSize); + if (!best->dict) { + best->compressedSize = ERROR(GENERIC); + best->dictSize = 0; ZSTD_pthread_cond_signal(&best->cond); ZSTD_pthread_mutex_unlock(&best->mutex); - return; - } - } - /* Save the dictionary, parameters, and size */ + return; + } + } + /* Save the dictionary, parameters, and size */ if (dict) { memcpy(best->dict, dict, dictSize); best->dictSize = dictSize; best->parameters = parameters; best->compressedSize = compressedSize; } - } - if (liveJobs == 0) { - ZSTD_pthread_cond_broadcast(&best->cond); - } + } + if (liveJobs == 0) { + ZSTD_pthread_cond_broadcast(&best->cond); + } ZSTD_pthread_mutex_unlock(&best->mutex); - } -} - + } +} + COVER_dictSelection_t COVER_dictSelectionError(size_t error) { COVER_dictSelection_t selection = { NULL, 0, error }; return selection; @@ -1055,128 +1055,128 @@ COVER_dictSelection_t COVER_selectDict(BYTE* customDictContent, size_t dictBuffe } } -/** - * Parameters for COVER_tryParameters(). - */ -typedef struct COVER_tryParameters_data_s { - const COVER_ctx_t *ctx; - COVER_best_t *best; - size_t dictBufferCapacity; - ZDICT_cover_params_t parameters; -} COVER_tryParameters_data_t; - -/** +/** + * Parameters for COVER_tryParameters(). + */ +typedef struct COVER_tryParameters_data_s { + const COVER_ctx_t *ctx; + COVER_best_t *best; + size_t dictBufferCapacity; + ZDICT_cover_params_t parameters; +} COVER_tryParameters_data_t; + +/** * Tries a set of parameters and updates the COVER_best_t with the results. - * This function is thread safe if zstd is compiled with multithreaded support. - * It takes its parameters as an *OWNING* opaque pointer to support threading. - */ + * This function is thread safe if zstd is compiled with multithreaded support. + * It takes its parameters as an *OWNING* opaque pointer to support threading. + */ static void COVER_tryParameters(void *opaque) { - /* Save parameters as local variables */ + /* Save parameters as local variables */ COVER_tryParameters_data_t *const data = (COVER_tryParameters_data_t*)opaque; - const COVER_ctx_t *const ctx = data->ctx; - const ZDICT_cover_params_t parameters = data->parameters; - size_t dictBufferCapacity = data->dictBufferCapacity; - size_t totalCompressedSize = ERROR(GENERIC); - /* Allocate space for hash table, dict, and freqs */ - COVER_map_t activeDmers; + const COVER_ctx_t *const ctx = data->ctx; + const ZDICT_cover_params_t parameters = data->parameters; + size_t dictBufferCapacity = data->dictBufferCapacity; + size_t totalCompressedSize = ERROR(GENERIC); + /* Allocate space for hash table, dict, and freqs */ + COVER_map_t activeDmers; BYTE* const dict = (BYTE*)malloc(dictBufferCapacity); COVER_dictSelection_t selection = COVER_dictSelectionError(ERROR(GENERIC)); U32* const freqs = (U32*)malloc(ctx->suffixSize * sizeof(U32)); - if (!COVER_map_init(&activeDmers, parameters.k - parameters.d + 1)) { - DISPLAYLEVEL(1, "Failed to allocate dmer map: out of memory\n"); - goto _cleanup; - } - if (!dict || !freqs) { - DISPLAYLEVEL(1, "Failed to allocate buffers: out of memory\n"); - goto _cleanup; - } - /* Copy the frequencies because we need to modify them */ - memcpy(freqs, ctx->freqs, ctx->suffixSize * sizeof(U32)); - /* Build the dictionary */ - { - const size_t tail = COVER_buildDictionary(ctx, freqs, &activeDmers, dict, - dictBufferCapacity, parameters); + if (!COVER_map_init(&activeDmers, parameters.k - parameters.d + 1)) { + DISPLAYLEVEL(1, "Failed to allocate dmer map: out of memory\n"); + goto _cleanup; + } + if (!dict || !freqs) { + DISPLAYLEVEL(1, "Failed to allocate buffers: out of memory\n"); + goto _cleanup; + } + /* Copy the frequencies because we need to modify them */ + memcpy(freqs, ctx->freqs, ctx->suffixSize * sizeof(U32)); + /* Build the dictionary */ + { + const size_t tail = COVER_buildDictionary(ctx, freqs, &activeDmers, dict, + dictBufferCapacity, parameters); selection = COVER_selectDict(dict + tail, dictBufferCapacity, dictBufferCapacity - tail, ctx->samples, ctx->samplesSizes, (unsigned)ctx->nbTrainSamples, ctx->nbTrainSamples, ctx->nbSamples, parameters, ctx->offsets, totalCompressedSize); if (COVER_dictSelectionIsError(selection)) { DISPLAYLEVEL(1, "Failed to select dictionary\n"); - goto _cleanup; - } - } -_cleanup: + goto _cleanup; + } + } +_cleanup: free(dict); COVER_best_finish(data->best, parameters, selection); - free(data); - COVER_map_destroy(&activeDmers); + free(data); + COVER_map_destroy(&activeDmers); COVER_dictSelectionFree(selection); free(freqs); -} - -ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover( +} + +ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover( void* dictBuffer, size_t dictBufferCapacity, const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, ZDICT_cover_params_t* parameters) { - /* constants */ - const unsigned nbThreads = parameters->nbThreads; + /* constants */ + const unsigned nbThreads = parameters->nbThreads; const double splitPoint = parameters->splitPoint <= 0.0 ? COVER_DEFAULT_SPLITPOINT : parameters->splitPoint; - const unsigned kMinD = parameters->d == 0 ? 6 : parameters->d; - const unsigned kMaxD = parameters->d == 0 ? 8 : parameters->d; - const unsigned kMinK = parameters->k == 0 ? 50 : parameters->k; - const unsigned kMaxK = parameters->k == 0 ? 2000 : parameters->k; - const unsigned kSteps = parameters->steps == 0 ? 40 : parameters->steps; - const unsigned kStepSize = MAX((kMaxK - kMinK) / kSteps, 1); - const unsigned kIterations = - (1 + (kMaxD - kMinD) / 2) * (1 + (kMaxK - kMinK) / kStepSize); + const unsigned kMinD = parameters->d == 0 ? 6 : parameters->d; + const unsigned kMaxD = parameters->d == 0 ? 8 : parameters->d; + const unsigned kMinK = parameters->k == 0 ? 50 : parameters->k; + const unsigned kMaxK = parameters->k == 0 ? 2000 : parameters->k; + const unsigned kSteps = parameters->steps == 0 ? 40 : parameters->steps; + const unsigned kStepSize = MAX((kMaxK - kMinK) / kSteps, 1); + const unsigned kIterations = + (1 + (kMaxD - kMinD) / 2) * (1 + (kMaxK - kMinK) / kStepSize); const unsigned shrinkDict = 0; - /* Local variables */ - const int displayLevel = parameters->zParams.notificationLevel; - unsigned iteration = 1; - unsigned d; - unsigned k; - COVER_best_t best; - POOL_ctx *pool = NULL; + /* Local variables */ + const int displayLevel = parameters->zParams.notificationLevel; + unsigned iteration = 1; + unsigned d; + unsigned k; + COVER_best_t best; + POOL_ctx *pool = NULL; int warned = 0; - - /* Checks */ + + /* Checks */ if (splitPoint <= 0 || splitPoint > 1) { LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect parameters\n"); return ERROR(parameter_outOfBound); } - if (kMinK < kMaxD || kMaxK < kMinK) { - LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect parameters\n"); + if (kMinK < kMaxD || kMaxK < kMinK) { + LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect parameters\n"); return ERROR(parameter_outOfBound); - } - if (nbSamples == 0) { - DISPLAYLEVEL(1, "Cover must have at least one input file\n"); + } + if (nbSamples == 0) { + DISPLAYLEVEL(1, "Cover must have at least one input file\n"); return ERROR(srcSize_wrong); - } - if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) { - DISPLAYLEVEL(1, "dictBufferCapacity must be at least %u\n", - ZDICT_DICTSIZE_MIN); - return ERROR(dstSize_tooSmall); - } - if (nbThreads > 1) { - pool = POOL_create(nbThreads, 1); - if (!pool) { - return ERROR(memory_allocation); - } - } - /* Initialization */ - COVER_best_init(&best); - /* Turn down global display level to clean up display at level 2 and below */ - g_displayLevel = displayLevel == 0 ? 0 : displayLevel - 1; - /* Loop through d first because each new value needs a new context */ - LOCALDISPLAYLEVEL(displayLevel, 2, "Trying %u different sets of parameters\n", - kIterations); - for (d = kMinD; d <= kMaxD; d += 2) { - /* Initialize the context for this value of d */ - COVER_ctx_t ctx; - LOCALDISPLAYLEVEL(displayLevel, 3, "d=%u\n", d); + } + if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) { + DISPLAYLEVEL(1, "dictBufferCapacity must be at least %u\n", + ZDICT_DICTSIZE_MIN); + return ERROR(dstSize_tooSmall); + } + if (nbThreads > 1) { + pool = POOL_create(nbThreads, 1); + if (!pool) { + return ERROR(memory_allocation); + } + } + /* Initialization */ + COVER_best_init(&best); + /* Turn down global display level to clean up display at level 2 and below */ + g_displayLevel = displayLevel == 0 ? 0 : displayLevel - 1; + /* Loop through d first because each new value needs a new context */ + LOCALDISPLAYLEVEL(displayLevel, 2, "Trying %u different sets of parameters\n", + kIterations); + for (d = kMinD; d <= kMaxD; d += 2) { + /* Initialize the context for this value of d */ + COVER_ctx_t ctx; + LOCALDISPLAYLEVEL(displayLevel, 3, "d=%u\n", d); { const size_t initVal = COVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples, d, splitPoint); if (ZSTD_isError(initVal)) { @@ -1185,69 +1185,69 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover( POOL_free(pool); return initVal; } - } + } if (!warned) { COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.suffixSize, displayLevel); warned = 1; } - /* Loop through k reusing the same context */ - for (k = kMinK; k <= kMaxK; k += kStepSize) { - /* Prepare the arguments */ - COVER_tryParameters_data_t *data = (COVER_tryParameters_data_t *)malloc( - sizeof(COVER_tryParameters_data_t)); - LOCALDISPLAYLEVEL(displayLevel, 3, "k=%u\n", k); - if (!data) { - LOCALDISPLAYLEVEL(displayLevel, 1, "Failed to allocate parameters\n"); - COVER_best_destroy(&best); - COVER_ctx_destroy(&ctx); - POOL_free(pool); + /* Loop through k reusing the same context */ + for (k = kMinK; k <= kMaxK; k += kStepSize) { + /* Prepare the arguments */ + COVER_tryParameters_data_t *data = (COVER_tryParameters_data_t *)malloc( + sizeof(COVER_tryParameters_data_t)); + LOCALDISPLAYLEVEL(displayLevel, 3, "k=%u\n", k); + if (!data) { + LOCALDISPLAYLEVEL(displayLevel, 1, "Failed to allocate parameters\n"); + COVER_best_destroy(&best); + COVER_ctx_destroy(&ctx); + POOL_free(pool); return ERROR(memory_allocation); - } - data->ctx = &ctx; - data->best = &best; - data->dictBufferCapacity = dictBufferCapacity; - data->parameters = *parameters; - data->parameters.k = k; - data->parameters.d = d; + } + data->ctx = &ctx; + data->best = &best; + data->dictBufferCapacity = dictBufferCapacity; + data->parameters = *parameters; + data->parameters.k = k; + data->parameters.d = d; data->parameters.splitPoint = splitPoint; - data->parameters.steps = kSteps; + data->parameters.steps = kSteps; data->parameters.shrinkDict = shrinkDict; - data->parameters.zParams.notificationLevel = g_displayLevel; - /* Check the parameters */ - if (!COVER_checkParameters(data->parameters, dictBufferCapacity)) { - DISPLAYLEVEL(1, "Cover parameters incorrect\n"); - free(data); - continue; - } - /* Call the function and pass ownership of data to it */ - COVER_best_start(&best); - if (pool) { - POOL_add(pool, &COVER_tryParameters, data); - } else { - COVER_tryParameters(data); - } - /* Print status */ - LOCALDISPLAYUPDATE(displayLevel, 2, "\r%u%% ", + data->parameters.zParams.notificationLevel = g_displayLevel; + /* Check the parameters */ + if (!COVER_checkParameters(data->parameters, dictBufferCapacity)) { + DISPLAYLEVEL(1, "Cover parameters incorrect\n"); + free(data); + continue; + } + /* Call the function and pass ownership of data to it */ + COVER_best_start(&best); + if (pool) { + POOL_add(pool, &COVER_tryParameters, data); + } else { + COVER_tryParameters(data); + } + /* Print status */ + LOCALDISPLAYUPDATE(displayLevel, 2, "\r%u%% ", (unsigned)((iteration * 100) / kIterations)); - ++iteration; - } - COVER_best_wait(&best); - COVER_ctx_destroy(&ctx); - } - LOCALDISPLAYLEVEL(displayLevel, 2, "\r%79s\r", ""); - /* Fill the output buffer and parameters with output of the best parameters */ - { - const size_t dictSize = best.dictSize; - if (ZSTD_isError(best.compressedSize)) { - const size_t compressedSize = best.compressedSize; - COVER_best_destroy(&best); - POOL_free(pool); - return compressedSize; - } - *parameters = best.parameters; - memcpy(dictBuffer, best.dict, dictSize); - COVER_best_destroy(&best); - POOL_free(pool); - return dictSize; - } -} + ++iteration; + } + COVER_best_wait(&best); + COVER_ctx_destroy(&ctx); + } + LOCALDISPLAYLEVEL(displayLevel, 2, "\r%79s\r", ""); + /* Fill the output buffer and parameters with output of the best parameters */ + { + const size_t dictSize = best.dictSize; + if (ZSTD_isError(best.compressedSize)) { + const size_t compressedSize = best.compressedSize; + COVER_best_destroy(&best); + POOL_free(pool); + return compressedSize; + } + *parameters = best.parameters; + memcpy(dictBuffer, best.dict, dictSize); + COVER_best_destroy(&best); + POOL_free(pool); + return dictSize; + } +} diff --git a/contrib/libs/zstd/lib/dictBuilder/zdict.c b/contrib/libs/zstd/lib/dictBuilder/zdict.c index 587df6b861..9a02f360bc 100644 --- a/contrib/libs/zstd/lib/dictBuilder/zdict.c +++ b/contrib/libs/zstd/lib/dictBuilder/zdict.c @@ -1,20 +1,20 @@ -/* +/* * Copyright (c) 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. + * 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. */ /*-************************************** * Tuning parameters ****************************************/ -#define MINRATIO 4 /* minimum nb of apparition to be selected in dictionary */ +#define MINRATIO 4 /* minimum nb of apparition to be selected in dictionary */ #define ZDICT_MAX_SAMPLES_SIZE (2000U << 20) -#define ZDICT_MIN_SAMPLES_SIZE (ZDICT_CONTENTSIZE_MIN * MINRATIO) +#define ZDICT_MIN_SAMPLES_SIZE (ZDICT_CONTENTSIZE_MIN * MINRATIO) /*-************************************** @@ -102,7 +102,7 @@ const char* ZDICT_getErrorName(size_t errorCode) { return ERR_getErrorName(error unsigned ZDICT_getDictID(const void* dictBuffer, size_t dictSize) { if (dictSize < 8) return 0; - if (MEM_readLE32(dictBuffer) != ZSTD_MAGIC_DICTIONARY) return 0; + if (MEM_readLE32(dictBuffer) != ZSTD_MAGIC_DICTIONARY) return 0; return MEM_readLE32((const char*)dictBuffer + 4); } @@ -130,7 +130,7 @@ size_t ZDICT_getDictHeaderSize(const void* dictBuffer, size_t dictSize) /*-******************************************************** * Dictionary training functions **********************************************************/ -static unsigned ZDICT_NbCommonBytes (size_t val) +static unsigned ZDICT_NbCommonBytes (size_t val) { if (MEM_isLittleEndian()) { if (MEM_64bits()) { @@ -268,30 +268,30 @@ static dictItem ZDICT_analyzePos( ||(MEM_read16(b+pos+1) == MEM_read16(b+pos+3)) ||(MEM_read16(b+pos+2) == MEM_read16(b+pos+4)) ) { /* skip and mark segment */ - U16 const pattern16 = MEM_read16(b+pos+4); - U32 u, patternEnd = 6; - while (MEM_read16(b+pos+patternEnd) == pattern16) patternEnd+=2 ; - if (b[pos+patternEnd] == b[pos+patternEnd-1]) patternEnd++; - for (u=1; u<patternEnd; u++) + U16 const pattern16 = MEM_read16(b+pos+4); + U32 u, patternEnd = 6; + while (MEM_read16(b+pos+patternEnd) == pattern16) patternEnd+=2 ; + if (b[pos+patternEnd] == b[pos+patternEnd-1]) patternEnd++; + for (u=1; u<patternEnd; u++) doneMarks[pos+u] = 1; return solution; } /* look forward */ - { size_t length; - do { - end++; - length = ZDICT_count(b + pos, b + suffix[end]); - } while (length >= MINMATCHLENGTH); - } + { size_t length; + do { + end++; + length = ZDICT_count(b + pos, b + suffix[end]); + } while (length >= MINMATCHLENGTH); + } /* look backward */ - { size_t length; - do { - length = ZDICT_count(b + pos, b + *(suffix+start-1)); - if (length >=MINMATCHLENGTH) start--; - } while(length >= MINMATCHLENGTH); - } + { size_t length; + do { + length = ZDICT_count(b + pos, b + *(suffix+start-1)); + if (length >=MINMATCHLENGTH) start--; + } while(length >= MINMATCHLENGTH); + } /* exit if not found a minimum nb of repetitions */ if (end-start < minRatio) { @@ -347,24 +347,24 @@ static dictItem ZDICT_analyzePos( memset(lengthList, 0, sizeof(lengthList)); /* look forward */ - { size_t length; - do { - end++; - length = ZDICT_count(b + pos, b + suffix[end]); - if (length >= LLIMIT) length = LLIMIT-1; - lengthList[length]++; - } while (length >=MINMATCHLENGTH); - } + { size_t length; + do { + end++; + length = ZDICT_count(b + pos, b + suffix[end]); + if (length >= LLIMIT) length = LLIMIT-1; + lengthList[length]++; + } while (length >=MINMATCHLENGTH); + } /* look backward */ - { size_t length = MINMATCHLENGTH; - while ((length >= MINMATCHLENGTH) & (start > 0)) { - length = ZDICT_count(b + pos, b + suffix[start - 1]); - if (length >= LLIMIT) length = LLIMIT - 1; - lengthList[length]++; - if (length >= MINMATCHLENGTH) start--; - } - } + { size_t length = MINMATCHLENGTH; + while ((length >= MINMATCHLENGTH) & (start > 0)) { + length = ZDICT_count(b + pos, b + suffix[start - 1]); + if (length >= LLIMIT) length = LLIMIT - 1; + lengthList[length]++; + if (length >= MINMATCHLENGTH) start--; + } + } /* largest useful length */ memset(cumulLength, 0, sizeof(cumulLength)); @@ -398,12 +398,12 @@ static dictItem ZDICT_analyzePos( /* mark positions done */ { U32 id; for (id=start; id<end; id++) { - U32 p, pEnd, length; + U32 p, pEnd, length; U32 const testedPos = (U32)suffix[id]; if (testedPos == pos) length = solution.length; else { - length = (U32)ZDICT_count(b+pos, b+testedPos); + length = (U32)ZDICT_count(b+pos, b+testedPos); if (length > solution.length) length = solution.length; } pEnd = (U32)(testedPos + length); @@ -415,35 +415,35 @@ static dictItem ZDICT_analyzePos( } -static int isIncluded(const void* in, const void* container, size_t length) -{ - const char* const ip = (const char*) in; - const char* const into = (const char*) container; - size_t u; - - for (u=0; u<length; u++) { /* works because end of buffer is a noisy guard band */ - if (ip[u] != into[u]) break; - } - - return u==length; -} - -/*! ZDICT_tryMerge() : +static int isIncluded(const void* in, const void* container, size_t length) +{ + const char* const ip = (const char*) in; + const char* const into = (const char*) container; + size_t u; + + for (u=0; u<length; u++) { /* works because end of buffer is a noisy guard band */ + if (ip[u] != into[u]) break; + } + + return u==length; +} + +/*! ZDICT_tryMerge() : check if dictItem can be merged, do it if possible @return : id of destination elt, 0 if not merged */ -static U32 ZDICT_tryMerge(dictItem* table, dictItem elt, U32 eltNbToSkip, const void* buffer) +static U32 ZDICT_tryMerge(dictItem* table, dictItem elt, U32 eltNbToSkip, const void* buffer) { const U32 tableSize = table->pos; const U32 eltEnd = elt.pos + elt.length; - const char* const buf = (const char*) buffer; + const char* const buf = (const char*) buffer; /* tail overlap */ U32 u; for (u=1; u<tableSize; u++) { if (u==eltNbToSkip) continue; if ((table[u].pos > elt.pos) && (table[u].pos <= eltEnd)) { /* overlap, existing > new */ /* append */ - U32 const addedLength = table[u].pos - elt.pos; + U32 const addedLength = table[u].pos - elt.pos; table[u].length += addedLength; table[u].pos = elt.pos; table[u].savings += elt.savings * addedLength / elt.length; /* rough approx */ @@ -459,7 +459,7 @@ static U32 ZDICT_tryMerge(dictItem* table, dictItem elt, U32 eltNbToSkip, const /* front overlap */ for (u=1; u<tableSize; u++) { if (u==eltNbToSkip) continue; - + if ((table[u].pos + table[u].length >= elt.pos) && (table[u].pos < elt.pos)) { /* overlap, existing < new */ /* append */ int const addedLength = (int)eltEnd - (int)(table[u].pos + table[u].length); @@ -474,27 +474,27 @@ static U32 ZDICT_tryMerge(dictItem* table, dictItem elt, U32 eltNbToSkip, const table[u] = table[u-1], u--; table[u] = elt; return u; - } - - if (MEM_read64(buf + table[u].pos) == MEM_read64(buf + elt.pos + 1)) { - if (isIncluded(buf + table[u].pos, buf + elt.pos + 1, table[u].length)) { - size_t const addedLength = MAX( (int)elt.length - (int)table[u].length , 1 ); - table[u].pos = elt.pos; - table[u].savings += (U32)(elt.savings * addedLength / elt.length); - table[u].length = MIN(elt.length, table[u].length + 1); - return u; - } - } - } - + } + + if (MEM_read64(buf + table[u].pos) == MEM_read64(buf + elt.pos + 1)) { + if (isIncluded(buf + table[u].pos, buf + elt.pos + 1, table[u].length)) { + size_t const addedLength = MAX( (int)elt.length - (int)table[u].length , 1 ); + table[u].pos = elt.pos; + table[u].savings += (U32)(elt.savings * addedLength / elt.length); + table[u].length = MIN(elt.length, table[u].length + 1); + return u; + } + } + } + return 0; } static void ZDICT_removeDictItem(dictItem* table, U32 id) { - /* convention : table[0].pos stores nb of elts */ - U32 const max = table[0].pos; + /* convention : table[0].pos stores nb of elts */ + U32 const max = table[0].pos; U32 u; if (!id) return; /* protection, should never happen */ for (u=id; u<max-1; u++) @@ -503,14 +503,14 @@ static void ZDICT_removeDictItem(dictItem* table, U32 id) } -static void ZDICT_insertDictItem(dictItem* table, U32 maxSize, dictItem elt, const void* buffer) +static void ZDICT_insertDictItem(dictItem* table, U32 maxSize, dictItem elt, const void* buffer) { /* merge if possible */ - U32 mergeId = ZDICT_tryMerge(table, elt, 0, buffer); + U32 mergeId = ZDICT_tryMerge(table, elt, 0, buffer); if (mergeId) { U32 newMerge = 1; while (newMerge) { - newMerge = ZDICT_tryMerge(table, table[mergeId], mergeId, buffer); + newMerge = ZDICT_tryMerge(table, table[mergeId], mergeId, buffer); if (newMerge) ZDICT_removeDictItem(table, mergeId); mergeId = newMerge; } @@ -541,7 +541,7 @@ static U32 ZDICT_dictSize(const dictItem* dictList) } -static size_t ZDICT_trainBuffer_legacy(dictItem* dictList, U32 dictListSize, +static size_t ZDICT_trainBuffer_legacy(dictItem* dictList, U32 dictListSize, const void* const buffer, size_t bufferSize, /* buffer must end with noisy guard band */ const size_t* fileSizes, unsigned nbFiles, unsigned minRatio, U32 notificationLevel) @@ -559,7 +559,7 @@ static size_t ZDICT_trainBuffer_legacy(dictItem* dictList, U32 dictListSize, # define DISPLAYUPDATE(l, ...) if (notificationLevel>=l) { \ if (ZDICT_clockSpan(displayClock) > refreshRate) \ { displayClock = clock(); DISPLAY(__VA_ARGS__); \ - if (notificationLevel>=4) fflush(stderr); } } + if (notificationLevel>=4) fflush(stderr); } } /* init */ DISPLAYLEVEL(2, "\r%70s\r", ""); /* clean display line */ @@ -600,7 +600,7 @@ static size_t ZDICT_trainBuffer_legacy(dictItem* dictList, U32 dictListSize, if (doneMarks[cursor]) { cursor++; continue; } solution = ZDICT_analyzePos(doneMarks, suffix, reverseSuffix[cursor], buffer, minRatio, notificationLevel); if (solution.length==0) { cursor++; continue; } - ZDICT_insertDictItem(dictList, dictListSize, solution, buffer); + ZDICT_insertDictItem(dictList, dictListSize, solution, buffer); cursor += solution.length; DISPLAYUPDATE(2, "\r%4.2f %% \r", (double)cursor / bufferSize * 100); } } @@ -630,16 +630,16 @@ static void ZDICT_fillNoise(void* buffer, size_t length) typedef struct { ZSTD_CDict* dict; /* dictionary */ - ZSTD_CCtx* zc; /* working context */ - void* workPlace; /* must be ZSTD_BLOCKSIZE_MAX allocated */ + ZSTD_CCtx* zc; /* working context */ + void* workPlace; /* must be ZSTD_BLOCKSIZE_MAX allocated */ } EStats_ress_t; #define MAXREPOFFSET 1024 static void ZDICT_countEStats(EStats_ress_t esr, const ZSTD_parameters* params, unsigned* countLit, unsigned* offsetcodeCount, unsigned* matchlengthCount, unsigned* litlengthCount, U32* repOffsets, - const void* src, size_t srcSize, - U32 notificationLevel) + const void* src, size_t srcSize, + U32 notificationLevel) { size_t const blockSizeMax = MIN (ZSTD_BLOCKSIZE_MAX, 1 << params->cParams.windowLog); size_t cSize; @@ -649,11 +649,11 @@ static void ZDICT_countEStats(EStats_ress_t esr, const ZSTD_parameters* params, if (ZSTD_isError(errorCode)) { DISPLAYLEVEL(1, "warning : ZSTD_compressBegin_usingCDict failed \n"); return; } } - cSize = ZSTD_compressBlock(esr.zc, esr.workPlace, ZSTD_BLOCKSIZE_MAX, src, srcSize); + cSize = ZSTD_compressBlock(esr.zc, esr.workPlace, ZSTD_BLOCKSIZE_MAX, src, srcSize); if (ZSTD_isError(cSize)) { DISPLAYLEVEL(3, "warning : could not compress sample size %u \n", (unsigned)srcSize); return; } if (cSize) { /* if == 0; block is not compressible */ - const seqStore_t* const seqStorePtr = ZSTD_getSeqStore(esr.zc); + const seqStore_t* const seqStorePtr = ZSTD_getSeqStore(esr.zc); /* literals stats */ { const BYTE* bytePtr; @@ -715,18 +715,18 @@ static void ZDICT_insertSortCount(offsetCount_t table[ZSTD_REP_NUM+1], U32 val, } } -/* ZDICT_flatLit() : - * rewrite `countLit` to contain a mostly flat but still compressible distribution of literals. - * necessary to avoid generating a non-compressible distribution that HUF_writeCTable() cannot encode. - */ +/* ZDICT_flatLit() : + * rewrite `countLit` to contain a mostly flat but still compressible distribution of literals. + * necessary to avoid generating a non-compressible distribution that HUF_writeCTable() cannot encode. + */ static void ZDICT_flatLit(unsigned* countLit) -{ - int u; - for (u=1; u<256; u++) countLit[u] = 2; - countLit[0] = 4; - countLit[253] = 1; - countLit[254] = 1; -} +{ + int u; + for (u=1; u<256; u++) countLit[u] = 2; + countLit[0] = 4; + countLit[253] = 1; + countLit[254] = 1; +} #define OFFCODE_MAX 30 /* only applicable to first block */ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize, @@ -756,12 +756,12 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize, BYTE* dstPtr = (BYTE*)dstBuffer; /* init */ - DEBUGLOG(4, "ZDICT_analyzeEntropy"); - if (offcodeMax>OFFCODE_MAX) { eSize = ERROR(dictionaryCreation_failed); goto _cleanup; } /* too large dictionary */ - for (u=0; u<256; u++) countLit[u] = 1; /* any character must be described */ - for (u=0; u<=offcodeMax; u++) offcodeCount[u] = 1; - for (u=0; u<=MaxML; u++) matchLengthCount[u] = 1; - for (u=0; u<=MaxLL; u++) litLengthCount[u] = 1; + DEBUGLOG(4, "ZDICT_analyzeEntropy"); + if (offcodeMax>OFFCODE_MAX) { eSize = ERROR(dictionaryCreation_failed); goto _cleanup; } /* too large dictionary */ + for (u=0; u<256; u++) countLit[u] = 1; /* any character must be described */ + for (u=0; u<=offcodeMax; u++) offcodeCount[u] = 1; + for (u=0; u<=MaxML; u++) matchLengthCount[u] = 1; + for (u=0; u<=MaxLL; u++) litLengthCount[u] = 1; memset(repOffset, 0, sizeof(repOffset)); repOffset[1] = repOffset[4] = repOffset[8] = 1; memset(bestRepOffset, 0, sizeof(bestRepOffset)); @@ -777,7 +777,7 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize, goto _cleanup; } - /* collect stats on all samples */ + /* collect stats on all samples */ for (u=0; u<nbFiles; u++) { ZDICT_countEStats(esr, ¶ms, countLit, offcodeCount, matchLengthCount, litLengthCount, repOffset, @@ -793,20 +793,20 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize, DISPLAYLEVEL(4, "%2u :%7u \n", u, offcodeCount[u]); } } - /* analyze, build stats, starting with literals */ - { size_t maxNbBits = HUF_buildCTable (hufTable, countLit, 255, huffLog); - if (HUF_isError(maxNbBits)) { + /* analyze, build stats, starting with literals */ + { size_t maxNbBits = HUF_buildCTable (hufTable, countLit, 255, huffLog); + if (HUF_isError(maxNbBits)) { eSize = maxNbBits; - DISPLAYLEVEL(1, " HUF_buildCTable error \n"); - goto _cleanup; - } - if (maxNbBits==8) { /* not compressible : will fail on HUF_writeCTable() */ - DISPLAYLEVEL(2, "warning : pathological dataset : literals are not compressible : samples are noisy or too regular \n"); - ZDICT_flatLit(countLit); /* replace distribution by a fake "mostly flat but still compressible" distribution, that HUF_writeCTable() can encode */ - maxNbBits = HUF_buildCTable (hufTable, countLit, 255, huffLog); - assert(maxNbBits==9); - } - huffLog = (U32)maxNbBits; + DISPLAYLEVEL(1, " HUF_buildCTable error \n"); + goto _cleanup; + } + if (maxNbBits==8) { /* not compressible : will fail on HUF_writeCTable() */ + DISPLAYLEVEL(2, "warning : pathological dataset : literals are not compressible : samples are noisy or too regular \n"); + ZDICT_flatLit(countLit); /* replace distribution by a fake "mostly flat but still compressible" distribution, that HUF_writeCTable() can encode */ + maxNbBits = HUF_buildCTable (hufTable, countLit, 255, huffLog); + assert(maxNbBits==9); + } + huffLog = (U32)maxNbBits; } /* looking for most common first offsets */ @@ -926,47 +926,47 @@ static U32 ZDICT_maxRep(U32 const reps[ZSTD_REP_NUM]) maxRep = MAX(maxRep, reps[r]); return maxRep; } - -size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity, - const void* customDictContent, size_t dictContentSize, + +size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity, + const void* customDictContent, size_t dictContentSize, const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, ZDICT_params_t params) { size_t hSize; -#define HBUFFSIZE 256 /* should prove large enough for all entropy headers */ - BYTE header[HBUFFSIZE]; +#define HBUFFSIZE 256 /* should prove large enough for all entropy headers */ + BYTE header[HBUFFSIZE]; int const compressionLevel = (params.compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT : params.compressionLevel; U32 const notificationLevel = params.notificationLevel; /* The final dictionary content must be at least as large as the largest repcode */ size_t const minContentSize = (size_t)ZDICT_maxRep(repStartValue); size_t paddingSize; - /* check conditions */ - DEBUGLOG(4, "ZDICT_finalizeDictionary"); - if (dictBufferCapacity < dictContentSize) return ERROR(dstSize_tooSmall); - if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) return ERROR(dstSize_tooSmall); - + /* check conditions */ + DEBUGLOG(4, "ZDICT_finalizeDictionary"); + if (dictBufferCapacity < dictContentSize) return ERROR(dstSize_tooSmall); + if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) return ERROR(dstSize_tooSmall); + /* dictionary header */ - MEM_writeLE32(header, ZSTD_MAGIC_DICTIONARY); - { U64 const randomID = XXH64(customDictContent, dictContentSize, 0); + MEM_writeLE32(header, ZSTD_MAGIC_DICTIONARY); + { U64 const randomID = XXH64(customDictContent, dictContentSize, 0); U32 const compliantID = (randomID % ((1U<<31)-32768)) + 32768; U32 const dictID = params.dictID ? params.dictID : compliantID; - MEM_writeLE32(header+4, dictID); + MEM_writeLE32(header+4, dictID); } hSize = 8; /* entropy tables */ DISPLAYLEVEL(2, "\r%70s\r", ""); /* clean display line */ DISPLAYLEVEL(2, "statistics ... \n"); - { size_t const eSize = ZDICT_analyzeEntropy(header+hSize, HBUFFSIZE-hSize, - compressionLevel, - samplesBuffer, samplesSizes, nbSamples, - customDictContent, dictContentSize, - notificationLevel); - if (ZDICT_isError(eSize)) return eSize; - hSize += eSize; - } - + { size_t const eSize = ZDICT_analyzeEntropy(header+hSize, HBUFFSIZE-hSize, + compressionLevel, + samplesBuffer, samplesSizes, nbSamples, + customDictContent, dictContentSize, + notificationLevel); + if (ZDICT_isError(eSize)) return eSize; + hSize += eSize; + } + /* Shrink the content size if it doesn't fit in the buffer */ if (hSize + dictContentSize > dictBufferCapacity) { dictContentSize = dictBufferCapacity - hSize; @@ -1004,23 +1004,23 @@ size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity, memcpy(outDictHeader, header, hSize); memset(outDictPadding, 0, paddingSize); - return dictSize; - } -} - - + return dictSize; + } +} + + static size_t ZDICT_addEntropyTablesFromBuffer_advanced( void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity, const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, ZDICT_params_t params) -{ +{ int const compressionLevel = (params.compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT : params.compressionLevel; - U32 const notificationLevel = params.notificationLevel; - size_t hSize = 8; - - /* calculate entropy tables */ - DISPLAYLEVEL(2, "\r%70s\r", ""); /* clean display line */ - DISPLAYLEVEL(2, "statistics ... \n"); + U32 const notificationLevel = params.notificationLevel; + size_t hSize = 8; + + /* calculate entropy tables */ + DISPLAYLEVEL(2, "\r%70s\r", ""); /* clean display line */ + DISPLAYLEVEL(2, "statistics ... \n"); { size_t const eSize = ZDICT_analyzeEntropy((char*)dictBuffer+hSize, dictBufferCapacity-hSize, compressionLevel, samplesBuffer, samplesSizes, nbSamples, @@ -1030,27 +1030,27 @@ static size_t ZDICT_addEntropyTablesFromBuffer_advanced( hSize += eSize; } - /* add dictionary header (after entropy tables) */ - MEM_writeLE32(dictBuffer, ZSTD_MAGIC_DICTIONARY); - { U64 const randomID = XXH64((char*)dictBuffer + dictBufferCapacity - dictContentSize, dictContentSize, 0); - U32 const compliantID = (randomID % ((1U<<31)-32768)) + 32768; - U32 const dictID = params.dictID ? params.dictID : compliantID; - MEM_writeLE32((char*)dictBuffer+4, dictID); - } + /* add dictionary header (after entropy tables) */ + MEM_writeLE32(dictBuffer, ZSTD_MAGIC_DICTIONARY); + { U64 const randomID = XXH64((char*)dictBuffer + dictBufferCapacity - dictContentSize, dictContentSize, 0); + U32 const compliantID = (randomID % ((1U<<31)-32768)) + 32768; + U32 const dictID = params.dictID ? params.dictID : compliantID; + MEM_writeLE32((char*)dictBuffer+4, dictID); + } if (hSize + dictContentSize < dictBufferCapacity) memmove((char*)dictBuffer + hSize, (char*)dictBuffer + dictBufferCapacity - dictContentSize, dictContentSize); return MIN(dictBufferCapacity, hSize+dictContentSize); } -/*! ZDICT_trainFromBuffer_unsafe_legacy() : +/*! ZDICT_trainFromBuffer_unsafe_legacy() : * Warning : `samplesBuffer` must be followed by noisy guard band !!! * @return : size of dictionary, or an error code which can be tested with ZDICT_isError() */ static size_t ZDICT_trainFromBuffer_unsafe_legacy( void* dictBuffer, size_t maxDictSize, const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, - ZDICT_legacy_params_t params) + ZDICT_legacy_params_t params) { U32 const dictListSize = MAX(MAX(DICTLISTSIZE_DEFAULT, nbSamples), (U32)(maxDictSize/16)); dictItem* const dictList = (dictItem*)malloc(dictListSize * sizeof(*dictList)); @@ -1059,24 +1059,24 @@ static size_t ZDICT_trainFromBuffer_unsafe_legacy( size_t const targetDictSize = maxDictSize; size_t const samplesBuffSize = ZDICT_totalSampleSize(samplesSizes, nbSamples); size_t dictSize = 0; - U32 const notificationLevel = params.zParams.notificationLevel; + U32 const notificationLevel = params.zParams.notificationLevel; /* checks */ if (!dictList) return ERROR(memory_allocation); - if (maxDictSize < ZDICT_DICTSIZE_MIN) { free(dictList); return ERROR(dstSize_tooSmall); } /* requested dictionary size is too small */ - if (samplesBuffSize < ZDICT_MIN_SAMPLES_SIZE) { free(dictList); return ERROR(dictionaryCreation_failed); } /* not enough source to create dictionary */ + if (maxDictSize < ZDICT_DICTSIZE_MIN) { free(dictList); return ERROR(dstSize_tooSmall); } /* requested dictionary size is too small */ + if (samplesBuffSize < ZDICT_MIN_SAMPLES_SIZE) { free(dictList); return ERROR(dictionaryCreation_failed); } /* not enough source to create dictionary */ /* init */ ZDICT_initDictItem(dictList); /* build dictionary */ - ZDICT_trainBuffer_legacy(dictList, dictListSize, - samplesBuffer, samplesBuffSize, - samplesSizes, nbSamples, - minRep, notificationLevel); + ZDICT_trainBuffer_legacy(dictList, dictListSize, + samplesBuffer, samplesBuffSize, + samplesSizes, nbSamples, + minRep, notificationLevel); /* display best matches */ - if (params.zParams.notificationLevel>= 3) { + if (params.zParams.notificationLevel>= 3) { unsigned const nb = MIN(25, dictList[0].pos); unsigned const dictContentSize = ZDICT_dictSize(dictList); unsigned u; @@ -1099,10 +1099,10 @@ static size_t ZDICT_trainFromBuffer_unsafe_legacy( /* create dictionary */ { unsigned dictContentSize = ZDICT_dictSize(dictList); - if (dictContentSize < ZDICT_CONTENTSIZE_MIN) { free(dictList); return ERROR(dictionaryCreation_failed); } /* dictionary content too small */ - if (dictContentSize < targetDictSize/4) { + if (dictContentSize < ZDICT_CONTENTSIZE_MIN) { free(dictList); return ERROR(dictionaryCreation_failed); } /* dictionary content too small */ + if (dictContentSize < targetDictSize/4) { DISPLAYLEVEL(2, "! warning : selected content significantly smaller than requested (%u < %u) \n", dictContentSize, (unsigned)maxDictSize); - if (samplesBuffSize < 10 * targetDictSize) + if (samplesBuffSize < 10 * targetDictSize) DISPLAYLEVEL(2, "! consider increasing the number of samples (total size : %u MB)\n", (unsigned)(samplesBuffSize>>20)); if (minRep > MINRATIO) { DISPLAYLEVEL(2, "! consider increasing selectivity to produce larger dictionary (-s%u) \n", selectivity+1); @@ -1115,7 +1115,7 @@ static size_t ZDICT_trainFromBuffer_unsafe_legacy( while ((nbSamples >> proposedSelectivity) <= MINRATIO) { proposedSelectivity--; } DISPLAYLEVEL(2, "! note : calculated dictionary significantly larger than requested (%u > %u) \n", dictContentSize, (unsigned)maxDictSize); DISPLAYLEVEL(2, "! consider increasing dictionary size, or produce denser dictionary (-s%u) \n", proposedSelectivity); - DISPLAYLEVEL(2, "! always test dictionary efficiency on real samples \n"); + DISPLAYLEVEL(2, "! always test dictionary efficiency on real samples \n"); } /* limit dictionary size */ @@ -1141,7 +1141,7 @@ static size_t ZDICT_trainFromBuffer_unsafe_legacy( dictSize = ZDICT_addEntropyTablesFromBuffer_advanced(dictBuffer, dictContentSize, maxDictSize, samplesBuffer, samplesSizes, nbSamples, - params.zParams); + params.zParams); } /* clean up */ @@ -1150,12 +1150,12 @@ static size_t ZDICT_trainFromBuffer_unsafe_legacy( } -/* ZDICT_trainFromBuffer_legacy() : - * issue : samplesBuffer need to be followed by a noisy guard band. - * work around : duplicate the buffer, and add the noise */ -size_t ZDICT_trainFromBuffer_legacy(void* dictBuffer, size_t dictBufferCapacity, - const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, - ZDICT_legacy_params_t params) +/* ZDICT_trainFromBuffer_legacy() : + * issue : samplesBuffer need to be followed by a noisy guard band. + * work around : duplicate the buffer, and add the noise */ +size_t ZDICT_trainFromBuffer_legacy(void* dictBuffer, size_t dictBufferCapacity, + const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, + ZDICT_legacy_params_t params) { size_t result; void* newBuff; @@ -1168,9 +1168,9 @@ size_t ZDICT_trainFromBuffer_legacy(void* dictBuffer, size_t dictBufferCapacity, memcpy(newBuff, samplesBuffer, sBuffSize); ZDICT_fillNoise((char*)newBuff + sBuffSize, NOISELENGTH); /* guard band, for end of buffer condition */ - result = - ZDICT_trainFromBuffer_unsafe_legacy(dictBuffer, dictBufferCapacity, newBuff, - samplesSizes, nbSamples, params); + result = + ZDICT_trainFromBuffer_unsafe_legacy(dictBuffer, dictBufferCapacity, newBuff, + samplesSizes, nbSamples, params); free(newBuff); return result; } @@ -1180,22 +1180,22 @@ size_t ZDICT_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity, const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples) { ZDICT_fastCover_params_t params; - DEBUGLOG(3, "ZDICT_trainFromBuffer"); + DEBUGLOG(3, "ZDICT_trainFromBuffer"); memset(¶ms, 0, sizeof(params)); - params.d = 8; - params.steps = 4; + params.d = 8; + params.steps = 4; /* Use default level since no compression level information is available */ params.zParams.compressionLevel = ZSTD_CLEVEL_DEFAULT; #if defined(DEBUGLEVEL) && (DEBUGLEVEL>=1) params.zParams.notificationLevel = DEBUGLEVEL; -#endif +#endif return ZDICT_optimizeTrainFromBuffer_fastCover(dictBuffer, dictBufferCapacity, - samplesBuffer, samplesSizes, nbSamples, - ¶ms); + samplesBuffer, samplesSizes, nbSamples, + ¶ms); } size_t ZDICT_addEntropyTablesFromBuffer(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity, - const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples) + const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples) { ZDICT_params_t params; memset(¶ms, 0, sizeof(params)); diff --git a/contrib/libs/zstd/lib/legacy/zstd_legacy.h b/contrib/libs/zstd/lib/legacy/zstd_legacy.h index a6f1174b82..cde5ef5c5f 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_legacy.h +++ b/contrib/libs/zstd/lib/legacy/zstd_legacy.h @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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_LEGACY_H @@ -22,33 +22,33 @@ extern "C" { #include "../common/error_private.h" /* ERROR */ #include "../common/zstd_internal.h" /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTD_frameSizeInfo */ -#if !defined (ZSTD_LEGACY_SUPPORT) || (ZSTD_LEGACY_SUPPORT == 0) -# undef ZSTD_LEGACY_SUPPORT -# define ZSTD_LEGACY_SUPPORT 8 -#endif - -#if (ZSTD_LEGACY_SUPPORT <= 1) -# include "zstd_v01.h" -#endif -#if (ZSTD_LEGACY_SUPPORT <= 2) -# include "zstd_v02.h" -#endif -#if (ZSTD_LEGACY_SUPPORT <= 3) -# include "zstd_v03.h" -#endif -#if (ZSTD_LEGACY_SUPPORT <= 4) -# include "zstd_v04.h" -#endif -#if (ZSTD_LEGACY_SUPPORT <= 5) -# include "zstd_v05.h" -#endif -#if (ZSTD_LEGACY_SUPPORT <= 6) -# include "zstd_v06.h" -#endif -#if (ZSTD_LEGACY_SUPPORT <= 7) -# include "zstd_v07.h" -#endif +#if !defined (ZSTD_LEGACY_SUPPORT) || (ZSTD_LEGACY_SUPPORT == 0) +# undef ZSTD_LEGACY_SUPPORT +# define ZSTD_LEGACY_SUPPORT 8 +#endif +#if (ZSTD_LEGACY_SUPPORT <= 1) +# include "zstd_v01.h" +#endif +#if (ZSTD_LEGACY_SUPPORT <= 2) +# include "zstd_v02.h" +#endif +#if (ZSTD_LEGACY_SUPPORT <= 3) +# include "zstd_v03.h" +#endif +#if (ZSTD_LEGACY_SUPPORT <= 4) +# include "zstd_v04.h" +#endif +#if (ZSTD_LEGACY_SUPPORT <= 5) +# include "zstd_v05.h" +#endif +#if (ZSTD_LEGACY_SUPPORT <= 6) +# include "zstd_v06.h" +#endif +#if (ZSTD_LEGACY_SUPPORT <= 7) +# include "zstd_v07.h" +#endif + /** ZSTD_isLegacy() : @return : > 0 if supported by legacy decoder. 0 otherwise. return value is the version. @@ -60,27 +60,27 @@ MEM_STATIC unsigned ZSTD_isLegacy(const void* src, size_t srcSize) magicNumberLE = MEM_readLE32(src); switch(magicNumberLE) { -#if (ZSTD_LEGACY_SUPPORT <= 1) +#if (ZSTD_LEGACY_SUPPORT <= 1) case ZSTDv01_magicNumberLE:return 1; -#endif -#if (ZSTD_LEGACY_SUPPORT <= 2) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 2) case ZSTDv02_magicNumber : return 2; -#endif -#if (ZSTD_LEGACY_SUPPORT <= 3) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 3) case ZSTDv03_magicNumber : return 3; -#endif -#if (ZSTD_LEGACY_SUPPORT <= 4) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 4) case ZSTDv04_magicNumber : return 4; -#endif -#if (ZSTD_LEGACY_SUPPORT <= 5) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 5) case ZSTDv05_MAGICNUMBER : return 5; -#endif -#if (ZSTD_LEGACY_SUPPORT <= 6) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 6) case ZSTDv06_MAGICNUMBER : return 6; -#endif -#if (ZSTD_LEGACY_SUPPORT <= 7) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 7) case ZSTDv07_MAGICNUMBER : return 7; -#endif +#endif default : return 0; } } @@ -90,30 +90,30 @@ MEM_STATIC unsigned long long ZSTD_getDecompressedSize_legacy(const void* src, s { U32 const version = ZSTD_isLegacy(src, srcSize); if (version < 5) return 0; /* no decompressed size in frame header, or not a legacy format */ -#if (ZSTD_LEGACY_SUPPORT <= 5) +#if (ZSTD_LEGACY_SUPPORT <= 5) if (version==5) { ZSTDv05_parameters fParams; size_t const frResult = ZSTDv05_getFrameParams(&fParams, src, srcSize); if (frResult != 0) return 0; return fParams.srcSize; } -#endif -#if (ZSTD_LEGACY_SUPPORT <= 6) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 6) if (version==6) { ZSTDv06_frameParams fParams; size_t const frResult = ZSTDv06_getFrameParams(&fParams, src, srcSize); if (frResult != 0) return 0; return fParams.frameContentSize; } -#endif -#if (ZSTD_LEGACY_SUPPORT <= 7) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 7) if (version==7) { ZSTDv07_frameParams fParams; size_t const frResult = ZSTDv07_getFrameParams(&fParams, src, srcSize); if (frResult != 0) return 0; return fParams.frameContentSize; } -#endif +#endif return 0; /* should not be possible */ } @@ -124,26 +124,26 @@ MEM_STATIC size_t ZSTD_decompressLegacy( const void* dict,size_t dictSize) { U32 const version = ZSTD_isLegacy(src, compressedSize); - (void)dst; (void)dstCapacity; (void)dict; (void)dictSize; /* unused when ZSTD_LEGACY_SUPPORT >= 8 */ + (void)dst; (void)dstCapacity; (void)dict; (void)dictSize; /* unused when ZSTD_LEGACY_SUPPORT >= 8 */ switch(version) { -#if (ZSTD_LEGACY_SUPPORT <= 1) +#if (ZSTD_LEGACY_SUPPORT <= 1) case 1 : return ZSTDv01_decompress(dst, dstCapacity, src, compressedSize); -#endif -#if (ZSTD_LEGACY_SUPPORT <= 2) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 2) case 2 : return ZSTDv02_decompress(dst, dstCapacity, src, compressedSize); -#endif -#if (ZSTD_LEGACY_SUPPORT <= 3) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 3) case 3 : return ZSTDv03_decompress(dst, dstCapacity, src, compressedSize); -#endif -#if (ZSTD_LEGACY_SUPPORT <= 4) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 4) case 4 : return ZSTDv04_decompress(dst, dstCapacity, src, compressedSize); -#endif -#if (ZSTD_LEGACY_SUPPORT <= 5) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 5) case 5 : { size_t result; ZSTDv05_DCtx* const zd = ZSTDv05_createDCtx(); @@ -152,8 +152,8 @@ MEM_STATIC size_t ZSTD_decompressLegacy( ZSTDv05_freeDCtx(zd); return result; } -#endif -#if (ZSTD_LEGACY_SUPPORT <= 6) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 6) case 6 : { size_t result; ZSTDv06_DCtx* const zd = ZSTDv06_createDCtx(); @@ -162,8 +162,8 @@ MEM_STATIC size_t ZSTD_decompressLegacy( ZSTDv06_freeDCtx(zd); return result; } -#endif -#if (ZSTD_LEGACY_SUPPORT <= 7) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 7) case 7 : { size_t result; ZSTDv07_DCtx* const zd = ZSTDv07_createDCtx(); @@ -172,78 +172,78 @@ MEM_STATIC size_t ZSTD_decompressLegacy( ZSTDv07_freeDCtx(zd); return result; } -#endif +#endif default : return ERROR(prefix_unknown); } } MEM_STATIC ZSTD_frameSizeInfo ZSTD_findFrameSizeInfoLegacy(const void *src, size_t srcSize) -{ +{ ZSTD_frameSizeInfo frameSizeInfo; U32 const version = ZSTD_isLegacy(src, srcSize); - switch(version) - { -#if (ZSTD_LEGACY_SUPPORT <= 1) - case 1 : + switch(version) + { +#if (ZSTD_LEGACY_SUPPORT <= 1) + case 1 : ZSTDv01_findFrameSizeInfoLegacy(src, srcSize, &frameSizeInfo.compressedSize, &frameSizeInfo.decompressedBound); break; -#endif -#if (ZSTD_LEGACY_SUPPORT <= 2) - case 2 : +#endif +#if (ZSTD_LEGACY_SUPPORT <= 2) + case 2 : ZSTDv02_findFrameSizeInfoLegacy(src, srcSize, &frameSizeInfo.compressedSize, &frameSizeInfo.decompressedBound); break; -#endif -#if (ZSTD_LEGACY_SUPPORT <= 3) - case 3 : +#endif +#if (ZSTD_LEGACY_SUPPORT <= 3) + case 3 : ZSTDv03_findFrameSizeInfoLegacy(src, srcSize, &frameSizeInfo.compressedSize, &frameSizeInfo.decompressedBound); break; -#endif -#if (ZSTD_LEGACY_SUPPORT <= 4) - case 4 : +#endif +#if (ZSTD_LEGACY_SUPPORT <= 4) + case 4 : ZSTDv04_findFrameSizeInfoLegacy(src, srcSize, &frameSizeInfo.compressedSize, &frameSizeInfo.decompressedBound); break; -#endif -#if (ZSTD_LEGACY_SUPPORT <= 5) - case 5 : +#endif +#if (ZSTD_LEGACY_SUPPORT <= 5) + case 5 : ZSTDv05_findFrameSizeInfoLegacy(src, srcSize, &frameSizeInfo.compressedSize, &frameSizeInfo.decompressedBound); break; -#endif -#if (ZSTD_LEGACY_SUPPORT <= 6) - case 6 : +#endif +#if (ZSTD_LEGACY_SUPPORT <= 6) + case 6 : ZSTDv06_findFrameSizeInfoLegacy(src, srcSize, &frameSizeInfo.compressedSize, &frameSizeInfo.decompressedBound); break; -#endif -#if (ZSTD_LEGACY_SUPPORT <= 7) - case 7 : +#endif +#if (ZSTD_LEGACY_SUPPORT <= 7) + case 7 : ZSTDv07_findFrameSizeInfoLegacy(src, srcSize, &frameSizeInfo.compressedSize, &frameSizeInfo.decompressedBound); break; -#endif - default : +#endif + default : frameSizeInfo.compressedSize = ERROR(prefix_unknown); frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR; break; - } + } if (!ZSTD_isError(frameSizeInfo.compressedSize) && frameSizeInfo.compressedSize > srcSize) { frameSizeInfo.compressedSize = ERROR(srcSize_wrong); frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR; } return frameSizeInfo; -} +} MEM_STATIC size_t ZSTD_findFrameCompressedSizeLegacy(const void *src, size_t srcSize) { @@ -259,20 +259,20 @@ MEM_STATIC size_t ZSTD_freeLegacyStreamContext(void* legacyContext, U32 version) case 1 : case 2 : case 3 : - (void)legacyContext; + (void)legacyContext; return ERROR(version_unsupported); -#if (ZSTD_LEGACY_SUPPORT <= 4) +#if (ZSTD_LEGACY_SUPPORT <= 4) case 4 : return ZBUFFv04_freeDCtx((ZBUFFv04_DCtx*)legacyContext); -#endif -#if (ZSTD_LEGACY_SUPPORT <= 5) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 5) case 5 : return ZBUFFv05_freeDCtx((ZBUFFv05_DCtx*)legacyContext); -#endif -#if (ZSTD_LEGACY_SUPPORT <= 6) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 6) case 6 : return ZBUFFv06_freeDCtx((ZBUFFv06_DCtx*)legacyContext); -#endif -#if (ZSTD_LEGACY_SUPPORT <= 7) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 7) case 7 : return ZBUFFv07_freeDCtx((ZBUFFv07_DCtx*)legacyContext); -#endif +#endif } } @@ -280,7 +280,7 @@ MEM_STATIC size_t ZSTD_freeLegacyStreamContext(void* legacyContext, U32 version) MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U32 newVersion, const void* dict, size_t dictSize) { - DEBUGLOG(5, "ZSTD_initLegacyStream for v0.%u", newVersion); + DEBUGLOG(5, "ZSTD_initLegacyStream for v0.%u", newVersion); if (prevVersion != newVersion) ZSTD_freeLegacyStreamContext(*legacyContext, prevVersion); switch(newVersion) { @@ -288,9 +288,9 @@ MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U case 1 : case 2 : case 3 : - (void)dict; (void)dictSize; + (void)dict; (void)dictSize; return 0; -#if (ZSTD_LEGACY_SUPPORT <= 4) +#if (ZSTD_LEGACY_SUPPORT <= 4) case 4 : { ZBUFFv04_DCtx* dctx = (prevVersion != newVersion) ? ZBUFFv04_createDCtx() : (ZBUFFv04_DCtx*)*legacyContext; @@ -300,8 +300,8 @@ MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U *legacyContext = dctx; return 0; } -#endif -#if (ZSTD_LEGACY_SUPPORT <= 5) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 5) case 5 : { ZBUFFv05_DCtx* dctx = (prevVersion != newVersion) ? ZBUFFv05_createDCtx() : (ZBUFFv05_DCtx*)*legacyContext; @@ -310,8 +310,8 @@ MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U *legacyContext = dctx; return 0; } -#endif -#if (ZSTD_LEGACY_SUPPORT <= 6) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 6) case 6 : { ZBUFFv06_DCtx* dctx = (prevVersion != newVersion) ? ZBUFFv06_createDCtx() : (ZBUFFv06_DCtx*)*legacyContext; @@ -320,8 +320,8 @@ MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U *legacyContext = dctx; return 0; } -#endif -#if (ZSTD_LEGACY_SUPPORT <= 7) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 7) case 7 : { ZBUFFv07_DCtx* dctx = (prevVersion != newVersion) ? ZBUFFv07_createDCtx() : (ZBUFFv07_DCtx*)*legacyContext; @@ -330,7 +330,7 @@ MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U *legacyContext = dctx; return 0; } -#endif +#endif } } @@ -339,16 +339,16 @@ MEM_STATIC size_t ZSTD_initLegacyStream(void** legacyContext, U32 prevVersion, U MEM_STATIC size_t ZSTD_decompressLegacyStream(void* legacyContext, U32 version, ZSTD_outBuffer* output, ZSTD_inBuffer* input) { - DEBUGLOG(5, "ZSTD_decompressLegacyStream for v0.%u", version); + DEBUGLOG(5, "ZSTD_decompressLegacyStream for v0.%u", version); switch(version) { default : case 1 : case 2 : case 3 : - (void)legacyContext; (void)output; (void)input; + (void)legacyContext; (void)output; (void)input; return ERROR(version_unsupported); -#if (ZSTD_LEGACY_SUPPORT <= 4) +#if (ZSTD_LEGACY_SUPPORT <= 4) case 4 : { ZBUFFv04_DCtx* dctx = (ZBUFFv04_DCtx*) legacyContext; @@ -361,8 +361,8 @@ MEM_STATIC size_t ZSTD_decompressLegacyStream(void* legacyContext, U32 version, input->pos += readSize; return hintSize; } -#endif -#if (ZSTD_LEGACY_SUPPORT <= 5) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 5) case 5 : { ZBUFFv05_DCtx* dctx = (ZBUFFv05_DCtx*) legacyContext; @@ -375,8 +375,8 @@ MEM_STATIC size_t ZSTD_decompressLegacyStream(void* legacyContext, U32 version, input->pos += readSize; return hintSize; } -#endif -#if (ZSTD_LEGACY_SUPPORT <= 6) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 6) case 6 : { ZBUFFv06_DCtx* dctx = (ZBUFFv06_DCtx*) legacyContext; @@ -389,8 +389,8 @@ MEM_STATIC size_t ZSTD_decompressLegacyStream(void* legacyContext, U32 version, input->pos += readSize; return hintSize; } -#endif -#if (ZSTD_LEGACY_SUPPORT <= 7) +#endif +#if (ZSTD_LEGACY_SUPPORT <= 7) case 7 : { ZBUFFv07_DCtx* dctx = (ZBUFFv07_DCtx*) legacyContext; @@ -403,7 +403,7 @@ MEM_STATIC size_t ZSTD_decompressLegacyStream(void* legacyContext, U32 version, input->pos += readSize; return hintSize; } -#endif +#endif } } diff --git a/contrib/libs/zstd/lib/legacy/zstd_v01.c b/contrib/libs/zstd/lib/legacy/zstd_v01.c index 23caaef564..43955848db 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v01.c +++ b/contrib/libs/zstd/lib/legacy/zstd_v01.c @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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. */ @@ -336,7 +336,7 @@ typedef U32 DTable_max_t[FSE_DTABLE_SIZE_U32(FSE_MAX_TABLELOG)]; /**************************************************************** * Internal functions ****************************************************************/ -FORCE_INLINE unsigned FSE_highbit32 (U32 val) +FORCE_INLINE unsigned FSE_highbit32 (U32 val) { # if defined(_MSC_VER) /* Visual */ unsigned long r; @@ -1435,7 +1435,7 @@ typedef struct ZSTD_Cctx_s #else U32 hashTable[HASH_TABLESIZE]; #endif - BYTE buffer[WORKPLACESIZE]; + BYTE buffer[WORKPLACESIZE]; } cctxi_t; @@ -2004,58 +2004,58 @@ size_t ZSTDv01_decompress(void* dst, size_t maxDstSize, const void* src, size_t /* ZSTD_errorFrameSizeInfoLegacy() : assumes `cSize` and `dBound` are _not_ NULL */ static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) -{ +{ *cSize = ret; *dBound = ZSTD_CONTENTSIZE_ERROR; } void ZSTDv01_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { - const BYTE* ip = (const BYTE*)src; - size_t remainingSize = srcSize; + const BYTE* ip = (const BYTE*)src; + size_t remainingSize = srcSize; size_t nbBlocks = 0; - U32 magicNumber; - blockProperties_t blockProperties; + U32 magicNumber; + blockProperties_t blockProperties; - /* Frame Header */ + /* Frame Header */ if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - magicNumber = ZSTD_readBE32(src); + magicNumber = ZSTD_readBE32(src); if (magicNumber != ZSTD_magicNumber) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown)); return; } - ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize; - - /* Loop on each block */ - while (1) - { - size_t blockSize = ZSTDv01_getcBlockSize(ip, remainingSize, &blockProperties); + ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize; + + /* Loop on each block */ + while (1) + { + size_t blockSize = ZSTDv01_getcBlockSize(ip, remainingSize, &blockProperties); if (ZSTDv01_isError(blockSize)) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, blockSize); return; } - - ip += ZSTD_blockHeaderSize; - remainingSize -= ZSTD_blockHeaderSize; + + ip += ZSTD_blockHeaderSize; + remainingSize -= ZSTD_blockHeaderSize; if (blockSize > remainingSize) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - - if (blockSize == 0) break; /* bt_end */ - - ip += blockSize; - remainingSize -= blockSize; + + if (blockSize == 0) break; /* bt_end */ + + ip += blockSize; + remainingSize -= blockSize; nbBlocks++; - } - + } + *cSize = ip - (const BYTE*)src; *dBound = nbBlocks * BLOCKSIZE; -} - +} + /******************************* * Streaming Decompression API *******************************/ diff --git a/contrib/libs/zstd/lib/legacy/zstd_v01.h b/contrib/libs/zstd/lib/legacy/zstd_v01.h index f777eb6e4c..0f8c05d5e1 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v01.h +++ b/contrib/libs/zstd/lib/legacy/zstd_v01.h @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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_V01_H_28739879432 @@ -42,13 +42,13 @@ size_t ZSTDv01_decompress( void* dst, size_t maxOriginalSize, or an error code if it fails (which can be tested using ZSTDv01_isError()) dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame or ZSTD_CONTENTSIZE_ERROR if an error occurs - + note : assumes `cSize` and `dBound` are _not_ NULL. */ void ZSTDv01_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound); -/** +/** ZSTDv01_isError() : tells if the result of ZSTDv01_decompress() is an error */ unsigned ZSTDv01_isError(size_t code); diff --git a/contrib/libs/zstd/lib/legacy/zstd_v02.c b/contrib/libs/zstd/lib/legacy/zstd_v02.c index 2f473a7573..21d2e61673 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v02.c +++ b/contrib/libs/zstd/lib/legacy/zstd_v02.c @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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. */ @@ -347,7 +347,7 @@ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits); /**************************************************************** * Helper functions ****************************************************************/ -MEM_STATIC unsigned BIT_highbit32 (U32 val) +MEM_STATIC unsigned BIT_highbit32 (U32 val) { # if defined(_MSC_VER) /* Visual */ unsigned long r; @@ -463,8 +463,8 @@ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, U32 nbBits) MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD) { - if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* should never happen */ - return BIT_DStream_overflow; + if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* should never happen */ + return BIT_DStream_overflow; if (bitD->ptr >= bitD->start + sizeof(bitD->bitContainer)) { @@ -1273,8 +1273,8 @@ static size_t FSE_readNCount (short* normalizedCounter, unsigned* maxSVPtr, unsi else { bitCount -= (int)(8 * (iend - 4 - ip)); - ip = iend - 4; - } + ip = iend - 4; + } bitStream = MEM_readLE32(ip) >> (bitCount & 31); } } @@ -1979,7 +1979,7 @@ static size_t HUF_readDTableX4 (U32* DTable, const void* src, size_t srcSize) rankStart[0] = 0; /* forget 0w symbols; this is beginning of weight(1) */ } - /* Build rankVal */ + /* Build rankVal */ { const U32 minBits = tableLog+1 - maxW; U32 nextRankVal = 0; @@ -2313,7 +2313,7 @@ static size_t HUF_readDTableX6 (U32* DTable, const void* src, size_t srcSize) rankStart[0] = 0; /* forget 0w symbols; this is beginning of weight(1) */ } - /* Build rankVal */ + /* Build rankVal */ { const U32 minBits = tableLog+1 - maxW; U32 nextRankVal = 0; @@ -2892,14 +2892,14 @@ static size_t ZSTD_decodeLiteralsBlock(void* ctx, if (litSize > srcSize-11) /* risk of reading too far with wildcopy */ { if (litSize > BLOCKSIZE) return ERROR(corruption_detected); - if (litSize > srcSize-3) return ERROR(corruption_detected); - memcpy(dctx->litBuffer, istart, litSize); - dctx->litPtr = dctx->litBuffer; - dctx->litSize = litSize; - memset(dctx->litBuffer + dctx->litSize, 0, 8); - return litSize+3; - } - /* direct reference into compressed stream */ + if (litSize > srcSize-3) return ERROR(corruption_detected); + memcpy(dctx->litBuffer, istart, litSize); + dctx->litPtr = dctx->litBuffer; + dctx->litSize = litSize; + memset(dctx->litBuffer + dctx->litSize, 0, 8); + return litSize+3; + } + /* direct reference into compressed stream */ dctx->litPtr = istart+3; dctx->litSize = litSize; return litSize+3; @@ -3327,58 +3327,58 @@ static size_t ZSTD_decompress(void* dst, size_t maxDstSize, const void* src, siz /* ZSTD_errorFrameSizeInfoLegacy() : assumes `cSize` and `dBound` are _not_ NULL */ static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) -{ +{ *cSize = ret; *dBound = ZSTD_CONTENTSIZE_ERROR; } void ZSTDv02_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { - const BYTE* ip = (const BYTE*)src; - size_t remainingSize = srcSize; + const BYTE* ip = (const BYTE*)src; + size_t remainingSize = srcSize; size_t nbBlocks = 0; - U32 magicNumber; - blockProperties_t blockProperties; - - /* Frame Header */ + U32 magicNumber; + blockProperties_t blockProperties; + + /* Frame Header */ if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - magicNumber = MEM_readLE32(src); + magicNumber = MEM_readLE32(src); if (magicNumber != ZSTD_magicNumber) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown)); return; } - ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize; - - /* Loop on each block */ - while (1) - { - size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); + ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize; + + /* Loop on each block */ + while (1) + { + size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); if (ZSTD_isError(cBlockSize)) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize); return; } - - ip += ZSTD_blockHeaderSize; - remainingSize -= ZSTD_blockHeaderSize; + + ip += ZSTD_blockHeaderSize; + remainingSize -= ZSTD_blockHeaderSize; if (cBlockSize > remainingSize) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - - if (cBlockSize == 0) break; /* bt_end */ - - ip += cBlockSize; - remainingSize -= cBlockSize; + + if (cBlockSize == 0) break; /* bt_end */ + + ip += cBlockSize; + remainingSize -= cBlockSize; nbBlocks++; - } - + } + *cSize = ip - (const BYTE*)src; *dBound = nbBlocks * BLOCKSIZE; -} - +} + /******************************* * Streaming Decompression API *******************************/ @@ -3483,36 +3483,36 @@ static size_t ZSTD_decompressContinue(ZSTD_DCtx* ctx, void* dst, size_t maxDstSi unsigned ZSTDv02_isError(size_t code) { - return ZSTD_isError(code); + return ZSTD_isError(code); } size_t ZSTDv02_decompress( void* dst, size_t maxOriginalSize, const void* src, size_t compressedSize) { - return ZSTD_decompress(dst, maxOriginalSize, src, compressedSize); + return ZSTD_decompress(dst, maxOriginalSize, src, compressedSize); } ZSTDv02_Dctx* ZSTDv02_createDCtx(void) { - return (ZSTDv02_Dctx*)ZSTD_createDCtx(); + return (ZSTDv02_Dctx*)ZSTD_createDCtx(); } size_t ZSTDv02_freeDCtx(ZSTDv02_Dctx* dctx) { - return ZSTD_freeDCtx((ZSTD_DCtx*)dctx); + return ZSTD_freeDCtx((ZSTD_DCtx*)dctx); } size_t ZSTDv02_resetDCtx(ZSTDv02_Dctx* dctx) { - return ZSTD_resetDCtx((ZSTD_DCtx*)dctx); + return ZSTD_resetDCtx((ZSTD_DCtx*)dctx); } size_t ZSTDv02_nextSrcSizeToDecompress(ZSTDv02_Dctx* dctx) { - return ZSTD_nextSrcSizeToDecompress((ZSTD_DCtx*)dctx); + return ZSTD_nextSrcSizeToDecompress((ZSTD_DCtx*)dctx); } size_t ZSTDv02_decompressContinue(ZSTDv02_Dctx* dctx, void* dst, size_t maxDstSize, const void* src, size_t srcSize) { - return ZSTD_decompressContinue((ZSTD_DCtx*)dctx, dst, maxDstSize, src, srcSize); + return ZSTD_decompressContinue((ZSTD_DCtx*)dctx, dst, maxDstSize, src, srcSize); } diff --git a/contrib/libs/zstd/lib/legacy/zstd_v02.h b/contrib/libs/zstd/lib/legacy/zstd_v02.h index 1b371953b7..d5e35b0c40 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v02.h +++ b/contrib/libs/zstd/lib/legacy/zstd_v02.h @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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_V02_H_4174539423 @@ -42,13 +42,13 @@ size_t ZSTDv02_decompress( void* dst, size_t maxOriginalSize, or an error code if it fails (which can be tested using ZSTDv01_isError()) dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame or ZSTD_CONTENTSIZE_ERROR if an error occurs - + note : assumes `cSize` and `dBound` are _not_ NULL. */ void ZSTDv02_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound); -/** +/** ZSTDv02_isError() : tells if the result of ZSTDv02_decompress() is an error */ unsigned ZSTDv02_isError(size_t code); diff --git a/contrib/libs/zstd/lib/legacy/zstd_v03.c b/contrib/libs/zstd/lib/legacy/zstd_v03.c index 6625f4df1c..50ac225538 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v03.c +++ b/contrib/libs/zstd/lib/legacy/zstd_v03.c @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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. */ @@ -350,7 +350,7 @@ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits); /**************************************************************** * Helper functions ****************************************************************/ -MEM_STATIC unsigned BIT_highbit32 (U32 val) +MEM_STATIC unsigned BIT_highbit32 (U32 val) { # if defined(_MSC_VER) /* Visual */ unsigned long r; @@ -465,8 +465,8 @@ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, U32 nbBits) MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD) { - if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* should never happen */ - return BIT_DStream_overflow; + if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* should never happen */ + return BIT_DStream_overflow; if (bitD->ptr >= bitD->start + sizeof(bitD->bitContainer)) { @@ -1274,8 +1274,8 @@ static size_t FSE_readNCount (short* normalizedCounter, unsigned* maxSVPtr, unsi else { bitCount -= (int)(8 * (iend - 4 - ip)); - ip = iend - 4; - } + ip = iend - 4; + } bitStream = MEM_readLE32(ip) >> (bitCount & 31); } } @@ -1976,7 +1976,7 @@ static size_t HUF_readDTableX4 (U32* DTable, const void* src, size_t srcSize) rankStart[0] = 0; /* forget 0w symbols; this is beginning of weight(1) */ } - /* Build rankVal */ + /* Build rankVal */ { const U32 minBits = tableLog+1 - maxW; U32 nextRankVal = 0; @@ -2533,14 +2533,14 @@ static size_t ZSTD_decodeLiteralsBlock(void* ctx, if (litSize > srcSize-11) /* risk of reading too far with wildcopy */ { if (litSize > BLOCKSIZE) return ERROR(corruption_detected); - if (litSize > srcSize-3) return ERROR(corruption_detected); - memcpy(dctx->litBuffer, istart, litSize); - dctx->litPtr = dctx->litBuffer; - dctx->litSize = litSize; - memset(dctx->litBuffer + dctx->litSize, 0, 8); - return litSize+3; - } - /* direct reference into compressed stream */ + if (litSize > srcSize-3) return ERROR(corruption_detected); + memcpy(dctx->litBuffer, istart, litSize); + dctx->litPtr = dctx->litBuffer; + dctx->litSize = litSize; + memset(dctx->litBuffer + dctx->litSize, 0, 8); + return litSize+3; + } + /* direct reference into compressed stream */ dctx->litPtr = istart+3; dctx->litSize = litSize; return litSize+3; @@ -2968,59 +2968,59 @@ static size_t ZSTD_decompress(void* dst, size_t maxDstSize, const void* src, siz /* ZSTD_errorFrameSizeInfoLegacy() : assumes `cSize` and `dBound` are _not_ NULL */ MEM_STATIC void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) -{ +{ *cSize = ret; *dBound = ZSTD_CONTENTSIZE_ERROR; } void ZSTDv03_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { - const BYTE* ip = (const BYTE*)src; - size_t remainingSize = srcSize; + const BYTE* ip = (const BYTE*)src; + size_t remainingSize = srcSize; size_t nbBlocks = 0; - U32 magicNumber; - blockProperties_t blockProperties; + U32 magicNumber; + blockProperties_t blockProperties; - /* Frame Header */ + /* Frame Header */ if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - magicNumber = MEM_readLE32(src); + magicNumber = MEM_readLE32(src); if (magicNumber != ZSTD_magicNumber) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown)); return; } - ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize; - - /* Loop on each block */ - while (1) - { - size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); + ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize; + + /* Loop on each block */ + while (1) + { + size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); if (ZSTD_isError(cBlockSize)) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize); return; } - - ip += ZSTD_blockHeaderSize; - remainingSize -= ZSTD_blockHeaderSize; + + ip += ZSTD_blockHeaderSize; + remainingSize -= ZSTD_blockHeaderSize; if (cBlockSize > remainingSize) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - - if (cBlockSize == 0) break; /* bt_end */ - - ip += cBlockSize; - remainingSize -= cBlockSize; + + if (cBlockSize == 0) break; /* bt_end */ + + ip += cBlockSize; + remainingSize -= cBlockSize; nbBlocks++; - } - + } + *cSize = ip - (const BYTE*)src; *dBound = nbBlocks * BLOCKSIZE; -} - - +} + + /******************************* * Streaming Decompression API *******************************/ @@ -3125,36 +3125,36 @@ static size_t ZSTD_decompressContinue(ZSTD_DCtx* ctx, void* dst, size_t maxDstSi unsigned ZSTDv03_isError(size_t code) { - return ZSTD_isError(code); + return ZSTD_isError(code); } size_t ZSTDv03_decompress( void* dst, size_t maxOriginalSize, const void* src, size_t compressedSize) { - return ZSTD_decompress(dst, maxOriginalSize, src, compressedSize); + return ZSTD_decompress(dst, maxOriginalSize, src, compressedSize); } ZSTDv03_Dctx* ZSTDv03_createDCtx(void) { - return (ZSTDv03_Dctx*)ZSTD_createDCtx(); + return (ZSTDv03_Dctx*)ZSTD_createDCtx(); } size_t ZSTDv03_freeDCtx(ZSTDv03_Dctx* dctx) { - return ZSTD_freeDCtx((ZSTD_DCtx*)dctx); + return ZSTD_freeDCtx((ZSTD_DCtx*)dctx); } size_t ZSTDv03_resetDCtx(ZSTDv03_Dctx* dctx) { - return ZSTD_resetDCtx((ZSTD_DCtx*)dctx); + return ZSTD_resetDCtx((ZSTD_DCtx*)dctx); } size_t ZSTDv03_nextSrcSizeToDecompress(ZSTDv03_Dctx* dctx) { - return ZSTD_nextSrcSizeToDecompress((ZSTD_DCtx*)dctx); + return ZSTD_nextSrcSizeToDecompress((ZSTD_DCtx*)dctx); } size_t ZSTDv03_decompressContinue(ZSTDv03_Dctx* dctx, void* dst, size_t maxDstSize, const void* src, size_t srcSize) { - return ZSTD_decompressContinue((ZSTD_DCtx*)dctx, dst, maxDstSize, src, srcSize); + return ZSTD_decompressContinue((ZSTD_DCtx*)dctx, dst, maxDstSize, src, srcSize); } diff --git a/contrib/libs/zstd/lib/legacy/zstd_v03.h b/contrib/libs/zstd/lib/legacy/zstd_v03.h index 7a00d4304b..1e4377b63b 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v03.h +++ b/contrib/libs/zstd/lib/legacy/zstd_v03.h @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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_V03_H_298734209782 @@ -42,13 +42,13 @@ size_t ZSTDv03_decompress( void* dst, size_t maxOriginalSize, or an error code if it fails (which can be tested using ZSTDv01_isError()) dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame or ZSTD_CONTENTSIZE_ERROR if an error occurs - + note : assumes `cSize` and `dBound` are _not_ NULL. */ void ZSTDv03_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound); - /** + /** ZSTDv03_isError() : tells if the result of ZSTDv03_decompress() is an error */ unsigned ZSTDv03_isError(size_t code); diff --git a/contrib/libs/zstd/lib/legacy/zstd_v04.c b/contrib/libs/zstd/lib/legacy/zstd_v04.c index 8d305c7eae..605c931fdc 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v04.c +++ b/contrib/libs/zstd/lib/legacy/zstd_v04.c @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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. */ @@ -75,15 +75,15 @@ extern "C" { #endif -/*-************************************* -* Debug -***************************************/ +/*-************************************* +* Debug +***************************************/ #include "../common/debug.h" #ifndef assert # define assert(condition) ((void)0) -#endif - - +#endif + + /**************************************************************** * Memory I/O *****************************************************************/ @@ -621,7 +621,7 @@ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits); /**************************************************************** * Helper functions ****************************************************************/ -MEM_STATIC unsigned BIT_highbit32 (U32 val) +MEM_STATIC unsigned BIT_highbit32 (U32 val) { # if defined(_MSC_VER) /* Visual */ unsigned long r; @@ -676,13 +676,13 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si bitD->bitContainer = *(const BYTE*)(bitD->start); switch(srcSize) { - case 7: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[6]) << (sizeof(size_t)*8 - 16);/* fall-through */ - case 6: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[5]) << (sizeof(size_t)*8 - 24);/* fall-through */ - case 5: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[4]) << (sizeof(size_t)*8 - 32);/* fall-through */ - case 4: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[3]) << 24; /* fall-through */ - case 3: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[2]) << 16; /* fall-through */ - case 2: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[1]) << 8; /* fall-through */ - default: break; + case 7: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[6]) << (sizeof(size_t)*8 - 16);/* fall-through */ + case 6: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[5]) << (sizeof(size_t)*8 - 24);/* fall-through */ + case 5: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[4]) << (sizeof(size_t)*8 - 32);/* fall-through */ + case 4: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[3]) << 24; /* fall-through */ + case 3: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[2]) << 16; /* fall-through */ + case 2: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[1]) << 8; /* fall-through */ + default: break; } contain32 = ((const BYTE*)srcBuffer)[srcSize-1]; if (contain32 == 0) return ERROR(GENERIC); /* endMark not present */ @@ -730,8 +730,8 @@ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, U32 nbBits) MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD) { - if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* should never happen */ - return BIT_DStream_overflow; + if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* should never happen */ + return BIT_DStream_overflow; if (bitD->ptr >= bitD->start + sizeof(bitD->bitContainer)) { @@ -1251,8 +1251,8 @@ static size_t FSE_readNCount (short* normalizedCounter, unsigned* maxSVPtr, unsi else { bitCount -= (int)(8 * (iend - 4 - ip)); - ip = iend - 4; - } + ip = iend - 4; + } bitStream = MEM_readLE32(ip) >> (bitCount & 31); } } @@ -2576,7 +2576,7 @@ static size_t ZSTD_decodeFrameHeader_Part2(ZSTD_DCtx* zc, const void* src, size_ size_t result; if (srcSize != zc->headerSize) return ERROR(srcSize_wrong); result = ZSTD_getFrameParams(&(zc->params), src, srcSize); - if ((MEM_32bits()) && (zc->params.windowLog > 25)) return ERROR(frameParameter_unsupported); + if ((MEM_32bits()) && (zc->params.windowLog > 25)) return ERROR(frameParameter_unsupported); return result; } @@ -2815,18 +2815,18 @@ static void ZSTD_decodeSequence(seq_t* seq, seqState_t* seqState) /* Literal length */ litLength = FSE_decodeSymbol(&(seqState->stateLL), &(seqState->DStream)); prevOffset = litLength ? seq->offset : seqState->prevOffset; - if (litLength == MaxLL) { + if (litLength == MaxLL) { const U32 add = dumps<de ? *dumps++ : 0; if (add < 255) litLength += add; else if (dumps + 3 <= de) { litLength = MEM_readLE24(dumps); dumps += 3; } - if (dumps >= de) { dumps = de-1; } /* late correction, to avoid read overflow (data is now corrupted anyway) */ + if (dumps >= de) { dumps = de-1; } /* late correction, to avoid read overflow (data is now corrupted anyway) */ } /* Offset */ - { static const U32 offsetPrefix[MaxOff+1] = { + { static const U32 offsetPrefix[MaxOff+1] = { 1 /*fake*/, 1, 2, 4, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8192, 16384, 32768, 65536, 131072, 262144, 524288, 1048576, 2097152, 4194304, 8388608, 16777216, 33554432, /*fake*/ 1, 1, 1, 1, 1 }; @@ -2843,14 +2843,14 @@ static void ZSTD_decodeSequence(seq_t* seq, seqState_t* seqState) /* MatchLength */ matchLength = FSE_decodeSymbol(&(seqState->stateML), &(seqState->DStream)); - if (matchLength == MaxML) { + if (matchLength == MaxML) { const U32 add = dumps<de ? *dumps++ : 0; if (add < 255) matchLength += add; else if (dumps + 3 <= de){ matchLength = MEM_readLE24(dumps); dumps += 3; } - if (dumps >= de) { dumps = de-1; } /* late correction, to avoid read overflow (data is now corrupted anyway) */ + if (dumps >= de) { dumps = de-1; } /* late correction, to avoid read overflow (data is now corrupted anyway) */ } matchLength += MINMATCH; @@ -2914,7 +2914,7 @@ static size_t ZSTD_execSequence(BYTE* op, /* Requirement: op <= oend_8 */ /* match within prefix */ - if (sequence.offset < 8) { + if (sequence.offset < 8) { /* close range match, overlap */ const int sub2 = dec64table[sequence.offset]; op[0] = match[0]; @@ -2924,7 +2924,7 @@ static size_t ZSTD_execSequence(BYTE* op, match += dec32table[sequence.offset]; ZSTD_copy4(op+4, match); match -= sub2; - } else { + } else { ZSTD_copy8(op, match); } op += 8; match += 8; @@ -3135,19 +3135,19 @@ static size_t ZSTD_decompress_usingDict(ZSTD_DCtx* ctx, /* ZSTD_errorFrameSizeInfoLegacy() : assumes `cSize` and `dBound` are _not_ NULL */ static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) -{ +{ *cSize = ret; *dBound = ZSTD_CONTENTSIZE_ERROR; } void ZSTDv04_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { - const BYTE* ip = (const BYTE*)src; - size_t remainingSize = srcSize; + const BYTE* ip = (const BYTE*)src; + size_t remainingSize = srcSize; size_t nbBlocks = 0; - blockProperties_t blockProperties; + blockProperties_t blockProperties; - /* Frame Header */ + /* Frame Header */ if (srcSize < ZSTD_frameHeaderSize_min) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; @@ -3156,35 +3156,35 @@ void ZSTDv04_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cS ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown)); return; } - ip += ZSTD_frameHeaderSize_min; remainingSize -= ZSTD_frameHeaderSize_min; - - /* Loop on each block */ - while (1) - { - size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); + ip += ZSTD_frameHeaderSize_min; remainingSize -= ZSTD_frameHeaderSize_min; + + /* Loop on each block */ + while (1) + { + size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); if (ZSTD_isError(cBlockSize)) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize); return; } - - ip += ZSTD_blockHeaderSize; - remainingSize -= ZSTD_blockHeaderSize; + + ip += ZSTD_blockHeaderSize; + remainingSize -= ZSTD_blockHeaderSize; if (cBlockSize > remainingSize) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - - if (cBlockSize == 0) break; /* bt_end */ - - ip += cBlockSize; - remainingSize -= cBlockSize; + + if (cBlockSize == 0) break; /* bt_end */ + + ip += cBlockSize; + remainingSize -= cBlockSize; nbBlocks++; - } - + } + *cSize = ip - (const BYTE*)src; *dBound = nbBlocks * BLOCKSIZE; -} - +} + /* ****************************** * Streaming Decompression API ********************************/ @@ -3429,14 +3429,14 @@ static size_t ZBUFF_decompressContinue(ZBUFF_DCtx* zbc, void* dst, size_t* maxDs char* const oend = ostart + *maxDstSizePtr; U32 notDone = 1; - DEBUGLOG(5, "ZBUFF_decompressContinue"); + DEBUGLOG(5, "ZBUFF_decompressContinue"); while (notDone) { switch(zbc->stage) { case ZBUFFds_init : - DEBUGLOG(5, "ZBUFF_decompressContinue: stage==ZBUFFds_init => ERROR(init_missing)"); + DEBUGLOG(5, "ZBUFF_decompressContinue: stage==ZBUFFds_init => ERROR(init_missing)"); return ERROR(init_missing); case ZBUFFds_readHeader : @@ -3498,7 +3498,7 @@ static size_t ZBUFF_decompressContinue(ZBUFF_DCtx* zbc, void* dst, size_t* maxDs break; } zbc->stage = ZBUFFds_read; - /* fall-through */ + /* fall-through */ case ZBUFFds_read: { size_t neededInSize = ZSTD_nextSrcSizeToDecompress(zbc->zc); @@ -3524,7 +3524,7 @@ static size_t ZBUFF_decompressContinue(ZBUFF_DCtx* zbc, void* dst, size_t* maxDs if (ip==iend) { notDone = 0; break; } /* no more input */ zbc->stage = ZBUFFds_load; } - /* fall-through */ + /* fall-through */ case ZBUFFds_load: { size_t neededInSize = ZSTD_nextSrcSizeToDecompress(zbc->zc); @@ -3544,10 +3544,10 @@ static size_t ZBUFF_decompressContinue(ZBUFF_DCtx* zbc, void* dst, size_t* maxDs if (!decodedSize) { zbc->stage = ZBUFFds_read; break; } /* this was just a header */ zbc->outEnd = zbc->outStart + decodedSize; zbc->stage = ZBUFFds_flush; - /* ZBUFFds_flush follows */ + /* ZBUFFds_flush follows */ } } - /* fall-through */ + /* fall-through */ case ZBUFFds_flush: { size_t toFlushSize = zbc->outEnd - zbc->outStart; @@ -3631,7 +3631,7 @@ size_t ZSTDv04_decompressContinue(ZSTDv04_Dctx* dctx, void* dst, size_t maxDstSi ZBUFFv04_DCtx* ZBUFFv04_createDCtx(void) { return ZBUFF_createDCtx(); } -size_t ZBUFFv04_freeDCtx(ZBUFFv04_DCtx* dctx) { return ZBUFF_freeDCtx(dctx); } +size_t ZBUFFv04_freeDCtx(ZBUFFv04_DCtx* dctx) { return ZBUFF_freeDCtx(dctx); } size_t ZBUFFv04_decompressInit(ZBUFFv04_DCtx* dctx) { return ZBUFF_decompressInit(dctx); } size_t ZBUFFv04_decompressWithDictionary(ZBUFFv04_DCtx* dctx, const void* src, size_t srcSize) @@ -3639,7 +3639,7 @@ size_t ZBUFFv04_decompressWithDictionary(ZBUFFv04_DCtx* dctx, const void* src, s size_t ZBUFFv04_decompressContinue(ZBUFFv04_DCtx* dctx, void* dst, size_t* maxDstSizePtr, const void* src, size_t* srcSizePtr) { - DEBUGLOG(5, "ZBUFFv04_decompressContinue"); + DEBUGLOG(5, "ZBUFFv04_decompressContinue"); return ZBUFF_decompressContinue(dctx, dst, maxDstSizePtr, src, srcSizePtr); } diff --git a/contrib/libs/zstd/lib/legacy/zstd_v04.h b/contrib/libs/zstd/lib/legacy/zstd_v04.h index 66b97ab8e6..688c131574 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v04.h +++ b/contrib/libs/zstd/lib/legacy/zstd_v04.h @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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_V04_H_91868324769238 @@ -42,13 +42,13 @@ size_t ZSTDv04_decompress( void* dst, size_t maxOriginalSize, or an error code if it fails (which can be tested using ZSTDv01_isError()) dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame or ZSTD_CONTENTSIZE_ERROR if an error occurs - + note : assumes `cSize` and `dBound` are _not_ NULL. */ void ZSTDv04_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound); -/** +/** ZSTDv04_isError() : tells if the result of ZSTDv04_decompress() is an error */ unsigned ZSTDv04_isError(size_t code); diff --git a/contrib/libs/zstd/lib/legacy/zstd_v05.c b/contrib/libs/zstd/lib/legacy/zstd_v05.c index 795dfb410c..700e33efaf 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v05.c +++ b/contrib/libs/zstd/lib/legacy/zstd_v05.c @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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. */ @@ -750,7 +750,7 @@ MEM_STATIC size_t BITv05_readBitsFast(BITv05_DStream_t* bitD, unsigned nbBits); /*-************************************************************** * Helper functions ****************************************************************/ -MEM_STATIC unsigned BITv05_highbit32 (U32 val) +MEM_STATIC unsigned BITv05_highbit32 (U32 val) { # if defined(_MSC_VER) /* Visual */ unsigned long r; @@ -802,13 +802,13 @@ MEM_STATIC size_t BITv05_initDStream(BITv05_DStream_t* bitD, const void* srcBuff bitD->bitContainer = *(const BYTE*)(bitD->start); switch(srcSize) { - case 7: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[6]) << (sizeof(size_t)*8 - 16);/* fall-through */ - case 6: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[5]) << (sizeof(size_t)*8 - 24);/* fall-through */ - case 5: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[4]) << (sizeof(size_t)*8 - 32);/* fall-through */ - case 4: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[3]) << 24; /* fall-through */ - case 3: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[2]) << 16; /* fall-through */ - case 2: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[1]) << 8; /* fall-through */ - default: break; + case 7: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[6]) << (sizeof(size_t)*8 - 16);/* fall-through */ + case 6: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[5]) << (sizeof(size_t)*8 - 24);/* fall-through */ + case 5: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[4]) << (sizeof(size_t)*8 - 32);/* fall-through */ + case 4: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[3]) << 24; /* fall-through */ + case 3: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[2]) << 16; /* fall-through */ + case 2: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[1]) << 8; /* fall-through */ + default: break; } contain32 = ((const BYTE*)srcBuffer)[srcSize-1]; if (contain32 == 0) return ERROR(GENERIC); /* endMark not present */ @@ -856,8 +856,8 @@ MEM_STATIC size_t BITv05_readBitsFast(BITv05_DStream_t* bitD, unsigned nbBits) MEM_STATIC BITv05_DStream_status BITv05_reloadDStream(BITv05_DStream_t* bitD) { - if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* should never happen */ - return BITv05_DStream_overflow; + if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* should never happen */ + return BITv05_DStream_overflow; if (bitD->ptr >= bitD->start + sizeof(bitD->bitContainer)) { bitD->ptr -= bitD->bitsConsumed >> 3; @@ -2822,7 +2822,7 @@ static size_t ZSTDv05_decodeFrameHeader_Part2(ZSTDv05_DCtx* zc, const void* src, if (srcSize != zc->headerSize) return ERROR(srcSize_wrong); result = ZSTDv05_getFrameParams(&(zc->params), src, srcSize); - if ((MEM_32bits()) && (zc->params.windowLog > 25)) return ERROR(frameParameter_unsupported); + if ((MEM_32bits()) && (zc->params.windowLog > 25)) return ERROR(frameParameter_unsupported); return result; } @@ -3162,7 +3162,7 @@ static void ZSTDv05_decodeSequence(seq_t* seq, seqState_t* seqState) } litLength>>=1; } - if (dumps >= de) { dumps = de-1; } /* late correction, to avoid read overflow (data is now corrupted anyway) */ + if (dumps >= de) { dumps = de-1; } /* late correction, to avoid read overflow (data is now corrupted anyway) */ } /* Offset */ @@ -3199,7 +3199,7 @@ static void ZSTDv05_decodeSequence(seq_t* seq, seqState_t* seqState) } matchLength >>= 1; } - if (dumps >= de) { dumps = de-1; } /* late correction, to avoid read overflow (data is now corrupted anyway) */ + if (dumps >= de) { dumps = de-1; } /* late correction, to avoid read overflow (data is now corrupted anyway) */ } matchLength += MINMATCH; @@ -3522,19 +3522,19 @@ size_t ZSTDv05_decompress(void* dst, size_t maxDstSize, const void* src, size_t /* ZSTD_errorFrameSizeInfoLegacy() : assumes `cSize` and `dBound` are _not_ NULL */ static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) -{ +{ *cSize = ret; *dBound = ZSTD_CONTENTSIZE_ERROR; } void ZSTDv05_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { - const BYTE* ip = (const BYTE*)src; - size_t remainingSize = srcSize; + const BYTE* ip = (const BYTE*)src; + size_t remainingSize = srcSize; size_t nbBlocks = 0; - blockProperties_t blockProperties; + blockProperties_t blockProperties; - /* Frame Header */ + /* Frame Header */ if (srcSize < ZSTDv05_frameHeaderSize_min) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; @@ -3543,35 +3543,35 @@ void ZSTDv05_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cS ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown)); return; } - ip += ZSTDv05_frameHeaderSize_min; remainingSize -= ZSTDv05_frameHeaderSize_min; - - /* Loop on each block */ - while (1) - { - size_t cBlockSize = ZSTDv05_getcBlockSize(ip, remainingSize, &blockProperties); + ip += ZSTDv05_frameHeaderSize_min; remainingSize -= ZSTDv05_frameHeaderSize_min; + + /* Loop on each block */ + while (1) + { + size_t cBlockSize = ZSTDv05_getcBlockSize(ip, remainingSize, &blockProperties); if (ZSTDv05_isError(cBlockSize)) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize); return; } - - ip += ZSTDv05_blockHeaderSize; - remainingSize -= ZSTDv05_blockHeaderSize; + + ip += ZSTDv05_blockHeaderSize; + remainingSize -= ZSTDv05_blockHeaderSize; if (cBlockSize > remainingSize) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - - if (cBlockSize == 0) break; /* bt_end */ - - ip += cBlockSize; - remainingSize -= cBlockSize; + + if (cBlockSize == 0) break; /* bt_end */ + + ip += cBlockSize; + remainingSize -= cBlockSize; nbBlocks++; - } - + } + *cSize = ip - (const BYTE*)src; *dBound = nbBlocks * BLOCKSIZE; -} - +} + /* ****************************** * Streaming Decompression API ********************************/ @@ -3916,7 +3916,7 @@ size_t ZBUFFv05_decompressContinue(ZBUFFv05_DCtx* zbc, void* dst, size_t* maxDst zbc->stage = ZBUFFv05ds_decodeHeader; break; } - /* fall-through */ + /* fall-through */ case ZBUFFv05ds_loadHeader: /* complete header from src */ { @@ -3934,7 +3934,7 @@ size_t ZBUFFv05_decompressContinue(ZBUFFv05_DCtx* zbc, void* dst, size_t* maxDst } /* zbc->stage = ZBUFFv05ds_decodeHeader; break; */ /* useless : stage follows */ } - /* fall-through */ + /* fall-through */ case ZBUFFv05ds_decodeHeader: /* apply header to create / resize buffers */ { @@ -3961,7 +3961,7 @@ size_t ZBUFFv05_decompressContinue(ZBUFFv05_DCtx* zbc, void* dst, size_t* maxDst break; } zbc->stage = ZBUFFv05ds_read; - /* fall-through */ + /* fall-through */ case ZBUFFv05ds_read: { size_t neededInSize = ZSTDv05_nextSrcSizeToDecompress(zbc->zc); @@ -3985,7 +3985,7 @@ size_t ZBUFFv05_decompressContinue(ZBUFFv05_DCtx* zbc, void* dst, size_t* maxDst if (ip==iend) { notDone = 0; break; } /* no more input */ zbc->stage = ZBUFFv05ds_load; } - /* fall-through */ + /* fall-through */ case ZBUFFv05ds_load: { size_t neededInSize = ZSTDv05_nextSrcSizeToDecompress(zbc->zc); @@ -4006,9 +4006,9 @@ size_t ZBUFFv05_decompressContinue(ZBUFFv05_DCtx* zbc, void* dst, size_t* maxDst zbc->outEnd = zbc->outStart + decodedSize; zbc->stage = ZBUFFv05ds_flush; /* break; */ /* ZBUFFv05ds_flush follows */ - } - } - /* fall-through */ + } + } + /* fall-through */ case ZBUFFv05ds_flush: { size_t toFlushSize = zbc->outEnd - zbc->outStart; diff --git a/contrib/libs/zstd/lib/legacy/zstd_v05.h b/contrib/libs/zstd/lib/legacy/zstd_v05.h index bd423bfc1b..ad45c53255 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v05.h +++ b/contrib/libs/zstd/lib/legacy/zstd_v05.h @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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 ZSTDv05_H diff --git a/contrib/libs/zstd/lib/legacy/zstd_v06.c b/contrib/libs/zstd/lib/legacy/zstd_v06.c index ead213c484..3239144a8b 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v06.c +++ b/contrib/libs/zstd/lib/legacy/zstd_v06.c @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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. */ @@ -190,7 +190,7 @@ MEM_STATIC U32 MEM_swap32(U32 in) { #if defined(_MSC_VER) /* Visual Studio */ return _byteswap_ulong(in); -#elif defined (__GNUC__) && (__GNUC__ * 100 + __GNUC_MINOR__ >= 403) +#elif defined (__GNUC__) && (__GNUC__ * 100 + __GNUC_MINOR__ >= 403) return __builtin_bswap32(in); #else return ((in << 24) & 0xff000000 ) | @@ -204,7 +204,7 @@ MEM_STATIC U64 MEM_swap64(U64 in) { #if defined(_MSC_VER) /* Visual Studio */ return _byteswap_uint64(in); -#elif defined (__GNUC__) && (__GNUC__ * 100 + __GNUC_MINOR__ >= 403) +#elif defined (__GNUC__) && (__GNUC__ * 100 + __GNUC_MINOR__ >= 403) return __builtin_bswap64(in); #else return ((in << 56) & 0xff00000000000000ULL) | @@ -854,7 +854,7 @@ MEM_STATIC size_t BITv06_readBitsFast(BITv06_DStream_t* bitD, unsigned nbBits); /*-************************************************************** * Internal functions ****************************************************************/ -MEM_STATIC unsigned BITv06_highbit32 ( U32 val) +MEM_STATIC unsigned BITv06_highbit32 ( U32 val) { # if defined(_MSC_VER) /* Visual */ unsigned long r; @@ -903,13 +903,13 @@ MEM_STATIC size_t BITv06_initDStream(BITv06_DStream_t* bitD, const void* srcBuff bitD->bitContainer = *(const BYTE*)(bitD->start); switch(srcSize) { - case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);/* fall-through */ - case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);/* fall-through */ - case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);/* fall-through */ - case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24; /* fall-through */ - case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16; /* fall-through */ - case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8; /* fall-through */ - default: break; + case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);/* fall-through */ + case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);/* fall-through */ + case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);/* fall-through */ + case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24; /* fall-through */ + case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16; /* fall-through */ + case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8; /* fall-through */ + default: break; } { BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1]; if (lastByte == 0) return ERROR(GENERIC); /* endMark not present */ @@ -958,8 +958,8 @@ MEM_STATIC size_t BITv06_readBitsFast(BITv06_DStream_t* bitD, U32 nbBits) MEM_STATIC BITv06_DStream_status BITv06_reloadDStream(BITv06_DStream_t* bitD) { - if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* should never happen */ - return BITv06_DStream_overflow; + if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* should never happen */ + return BITv06_DStream_overflow; if (bitD->ptr >= bitD->start + sizeof(bitD->bitContainer)) { bitD->ptr -= bitD->bitsConsumed >> 3; @@ -3010,7 +3010,7 @@ size_t ZSTDv06_getFrameParams(ZSTDv06_frameParams* fparamsPtr, const void* src, static size_t ZSTDv06_decodeFrameHeader(ZSTDv06_DCtx* zc, const void* src, size_t srcSize) { size_t const result = ZSTDv06_getFrameParams(&(zc->fParams), src, srcSize); - if ((MEM_32bits()) && (zc->fParams.windowLog > 25)) return ERROR(frameParameter_unsupported); + if ((MEM_32bits()) && (zc->fParams.windowLog > 25)) return ERROR(frameParameter_unsupported); return result; } @@ -3659,19 +3659,19 @@ size_t ZSTDv06_decompress(void* dst, size_t dstCapacity, const void* src, size_t /* ZSTD_errorFrameSizeInfoLegacy() : assumes `cSize` and `dBound` are _not_ NULL */ static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) -{ +{ *cSize = ret; *dBound = ZSTD_CONTENTSIZE_ERROR; } void ZSTDv06_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { - const BYTE* ip = (const BYTE*)src; - size_t remainingSize = srcSize; + const BYTE* ip = (const BYTE*)src; + size_t remainingSize = srcSize; size_t nbBlocks = 0; - blockProperties_t blockProperties = { bt_compressed, 0 }; + blockProperties_t blockProperties = { bt_compressed, 0 }; - /* Frame Header */ + /* Frame Header */ { size_t const frameHeaderSize = ZSTDv06_frameHeaderSize(src, srcSize); if (ZSTDv06_isError(frameHeaderSize)) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, frameHeaderSize); @@ -3685,35 +3685,35 @@ void ZSTDv06_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cS ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - ip += frameHeaderSize; remainingSize -= frameHeaderSize; - } - - /* Loop on each block */ - while (1) { - size_t const cBlockSize = ZSTDv06_getcBlockSize(ip, remainingSize, &blockProperties); + ip += frameHeaderSize; remainingSize -= frameHeaderSize; + } + + /* Loop on each block */ + while (1) { + size_t const cBlockSize = ZSTDv06_getcBlockSize(ip, remainingSize, &blockProperties); if (ZSTDv06_isError(cBlockSize)) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize); return; } - - ip += ZSTDv06_blockHeaderSize; - remainingSize -= ZSTDv06_blockHeaderSize; + + ip += ZSTDv06_blockHeaderSize; + remainingSize -= ZSTDv06_blockHeaderSize; if (cBlockSize > remainingSize) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - - if (cBlockSize == 0) break; /* bt_end */ - - ip += cBlockSize; - remainingSize -= cBlockSize; + + if (cBlockSize == 0) break; /* bt_end */ + + ip += cBlockSize; + remainingSize -= cBlockSize; nbBlocks++; - } - + } + *cSize = ip - (const BYTE*)src; *dBound = nbBlocks * ZSTDv06_BLOCKSIZE_MAX; -} - +} + /*_****************************** * Streaming Decompression API ********************************/ @@ -3742,7 +3742,7 @@ size_t ZSTDv06_decompressContinue(ZSTDv06_DCtx* dctx, void* dst, size_t dstCapac return 0; } dctx->expected = 0; /* not necessary to copy more */ - /* fall-through */ + /* fall-through */ case ZSTDds_decodeFrameHeader: { size_t result; memcpy(dctx->headerBuffer + ZSTDv06_frameHeaderSize_min, src, dctx->expected); @@ -4063,7 +4063,7 @@ size_t ZBUFFv06_decompressContinue(ZBUFFv06_DCtx* zbd, zbd->inBuff = (char*)malloc(blockSize); if (zbd->inBuff == NULL) return ERROR(memory_allocation); } - { size_t const neededOutSize = ((size_t)1 << zbd->fParams.windowLog) + blockSize + WILDCOPY_OVERLENGTH * 2; + { size_t const neededOutSize = ((size_t)1 << zbd->fParams.windowLog) + blockSize + WILDCOPY_OVERLENGTH * 2; if (zbd->outBuffSize < neededOutSize) { free(zbd->outBuff); zbd->outBuffSize = neededOutSize; @@ -4071,7 +4071,7 @@ size_t ZBUFFv06_decompressContinue(ZBUFFv06_DCtx* zbd, if (zbd->outBuff == NULL) return ERROR(memory_allocation); } } } zbd->stage = ZBUFFds_read; - /* fall-through */ + /* fall-through */ case ZBUFFds_read: { size_t const neededInSize = ZSTDv06_nextSrcSizeToDecompress(zbd->zd); if (neededInSize==0) { /* end of frame */ @@ -4093,7 +4093,7 @@ size_t ZBUFFv06_decompressContinue(ZBUFFv06_DCtx* zbd, if (ip==iend) { notDone = 0; break; } /* no more input */ zbd->stage = ZBUFFds_load; } - /* fall-through */ + /* fall-through */ case ZBUFFds_load: { size_t const neededInSize = ZSTDv06_nextSrcSizeToDecompress(zbd->zd); size_t const toLoad = neededInSize - zbd->inPos; /* should always be <= remaining space within inBuff */ @@ -4114,9 +4114,9 @@ size_t ZBUFFv06_decompressContinue(ZBUFFv06_DCtx* zbd, zbd->outEnd = zbd->outStart + decodedSize; zbd->stage = ZBUFFds_flush; /* break; */ /* ZBUFFds_flush follows */ - } - } - /* fall-through */ + } + } + /* fall-through */ case ZBUFFds_flush: { size_t const toFlushSize = zbd->outEnd - zbd->outStart; size_t const flushedSize = ZBUFFv06_limitCopy(op, oend-op, zbd->outBuff + zbd->outStart, toFlushSize); diff --git a/contrib/libs/zstd/lib/legacy/zstd_v06.h b/contrib/libs/zstd/lib/legacy/zstd_v06.h index 9e32b76e08..802326e6f0 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v06.h +++ b/contrib/libs/zstd/lib/legacy/zstd_v06.h @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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 ZSTDv06_H @@ -42,7 +42,7 @@ extern "C" { ZSTDLIBv06_API size_t ZSTDv06_decompress( void* dst, size_t dstCapacity, const void* src, size_t compressedSize); -/** +/** ZSTDv06_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.6.x format srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' cSize (output parameter) : the number of bytes that would be read to decompress this frame @@ -51,7 +51,7 @@ ZSTDv06_findFrameSizeInfoLegacy() : get the source length and decompressed bound or ZSTD_CONTENTSIZE_ERROR if an error occurs note : assumes `cSize` and `dBound` are _not_ NULL. -*/ +*/ void ZSTDv06_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound); diff --git a/contrib/libs/zstd/lib/legacy/zstd_v07.c b/contrib/libs/zstd/lib/legacy/zstd_v07.c index 189f6ede69..25d234fe0c 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v07.c +++ b/contrib/libs/zstd/lib/legacy/zstd_v07.c @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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. */ @@ -14,14 +14,14 @@ #include <string.h> /* memcpy */ #include <stdlib.h> /* malloc, free, qsort */ -#ifndef XXH_STATIC_LINKING_ONLY -# define XXH_STATIC_LINKING_ONLY /* XXH64_state_t */ -#endif +#ifndef XXH_STATIC_LINKING_ONLY +# define XXH_STATIC_LINKING_ONLY /* XXH64_state_t */ +#endif #include <contrib/libs/xxhash/xxhash.h> /* XXH64_* */ #include "zstd_v07.h" -#define FSEv07_STATIC_LINKING_ONLY /* FSEv07_MIN_TABLELOG */ -#define HUFv07_STATIC_LINKING_ONLY /* HUFv07_TABLELOG_ABSOLUTEMAX */ +#define FSEv07_STATIC_LINKING_ONLY /* FSEv07_MIN_TABLELOG */ +#define HUFv07_STATIC_LINKING_ONLY /* HUFv07_TABLELOG_ABSOLUTEMAX */ #define ZSTDv07_STATIC_LINKING_ONLY #include "../common/error_private.h" @@ -349,7 +349,7 @@ MEM_STATIC U32 MEM_swap32(U32 in) { #if defined(_MSC_VER) /* Visual Studio */ return _byteswap_ulong(in); -#elif defined (__GNUC__) && (__GNUC__ * 100 + __GNUC_MINOR__ >= 403) +#elif defined (__GNUC__) && (__GNUC__ * 100 + __GNUC_MINOR__ >= 403) return __builtin_bswap32(in); #else return ((in << 24) & 0xff000000 ) | @@ -363,7 +363,7 @@ MEM_STATIC U64 MEM_swap64(U64 in) { #if defined(_MSC_VER) /* Visual Studio */ return _byteswap_uint64(in); -#elif defined (__GNUC__) && (__GNUC__ * 100 + __GNUC_MINOR__ >= 403) +#elif defined (__GNUC__) && (__GNUC__ * 100 + __GNUC_MINOR__ >= 403) return __builtin_bswap64(in); #else return ((in << 56) & 0xff00000000000000ULL) | @@ -524,7 +524,7 @@ MEM_STATIC size_t BITv07_readBitsFast(BITv07_DStream_t* bitD, unsigned nbBits); /*-************************************************************** * Internal functions ****************************************************************/ -MEM_STATIC unsigned BITv07_highbit32 (U32 val) +MEM_STATIC unsigned BITv07_highbit32 (U32 val) { # if defined(_MSC_VER) /* Visual */ unsigned long r; @@ -571,13 +571,13 @@ MEM_STATIC size_t BITv07_initDStream(BITv07_DStream_t* bitD, const void* srcBuff bitD->bitContainer = *(const BYTE*)(bitD->start); switch(srcSize) { - case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);/* fall-through */ - case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);/* fall-through */ - case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);/* fall-through */ - case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24; /* fall-through */ - case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16; /* fall-through */ - case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8; /* fall-through */ - default: break; + case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);/* fall-through */ + case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);/* fall-through */ + case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);/* fall-through */ + case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24; /* fall-through */ + case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16; /* fall-through */ + case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8; /* fall-through */ + default: break; } { BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1]; bitD->bitsConsumed = lastByte ? 8 - BITv07_highbit32(lastByte) : 0; @@ -3904,24 +3904,24 @@ size_t ZSTDv07_decompress(void* dst, size_t dstCapacity, const void* src, size_t /* ZSTD_errorFrameSizeInfoLegacy() : assumes `cSize` and `dBound` are _not_ NULL */ static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret) -{ +{ *cSize = ret; *dBound = ZSTD_CONTENTSIZE_ERROR; } void ZSTDv07_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound) { - const BYTE* ip = (const BYTE*)src; - size_t remainingSize = srcSize; + const BYTE* ip = (const BYTE*)src; + size_t remainingSize = srcSize; size_t nbBlocks = 0; - /* check */ + /* check */ if (srcSize < ZSTDv07_frameHeaderSize_min+ZSTDv07_blockHeaderSize) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - - /* Frame Header */ + + /* Frame Header */ { size_t const frameHeaderSize = ZSTDv07_frameHeaderSize(src, srcSize); if (ZSTDv07_isError(frameHeaderSize)) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, frameHeaderSize); @@ -3935,37 +3935,37 @@ void ZSTDv07_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cS ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - ip += frameHeaderSize; remainingSize -= frameHeaderSize; - } - - /* Loop on each block */ - while (1) { - blockProperties_t blockProperties; - size_t const cBlockSize = ZSTDv07_getcBlockSize(ip, remainingSize, &blockProperties); + ip += frameHeaderSize; remainingSize -= frameHeaderSize; + } + + /* Loop on each block */ + while (1) { + blockProperties_t blockProperties; + size_t const cBlockSize = ZSTDv07_getcBlockSize(ip, remainingSize, &blockProperties); if (ZSTDv07_isError(cBlockSize)) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize); return; } - - ip += ZSTDv07_blockHeaderSize; - remainingSize -= ZSTDv07_blockHeaderSize; - - if (blockProperties.blockType == bt_end) break; - + + ip += ZSTDv07_blockHeaderSize; + remainingSize -= ZSTDv07_blockHeaderSize; + + if (blockProperties.blockType == bt_end) break; + if (cBlockSize > remainingSize) { ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong)); return; } - - ip += cBlockSize; - remainingSize -= cBlockSize; + + ip += cBlockSize; + remainingSize -= cBlockSize; nbBlocks++; - } - + } + *cSize = ip - (const BYTE*)src; *dBound = nbBlocks * ZSTDv07_BLOCKSIZE_ABSOLUTEMAX; -} - +} + /*_****************************** * Streaming Decompression API ********************************/ @@ -4007,7 +4007,7 @@ size_t ZSTDv07_decompressContinue(ZSTDv07_DCtx* dctx, void* dst, size_t dstCapac return 0; } dctx->expected = 0; /* not necessary to copy more */ - /* fall-through */ + /* fall-through */ case ZSTDds_decodeFrameHeader: { size_t result; memcpy(dctx->headerBuffer + ZSTDv07_frameHeaderSize_min, src, dctx->expected); @@ -4131,9 +4131,9 @@ static size_t ZSTDv07_loadEntropy(ZSTDv07_DCtx* dctx, const void* const dict, si } if (dictPtr+12 > dictEnd) return ERROR(dictionary_corrupted); - dctx->rep[0] = MEM_readLE32(dictPtr+0); if (dctx->rep[0] == 0 || dctx->rep[0] >= dictSize) return ERROR(dictionary_corrupted); - dctx->rep[1] = MEM_readLE32(dictPtr+4); if (dctx->rep[1] == 0 || dctx->rep[1] >= dictSize) return ERROR(dictionary_corrupted); - dctx->rep[2] = MEM_readLE32(dictPtr+8); if (dctx->rep[2] == 0 || dctx->rep[2] >= dictSize) return ERROR(dictionary_corrupted); + dctx->rep[0] = MEM_readLE32(dictPtr+0); if (dctx->rep[0] == 0 || dctx->rep[0] >= dictSize) return ERROR(dictionary_corrupted); + dctx->rep[1] = MEM_readLE32(dictPtr+4); if (dctx->rep[1] == 0 || dctx->rep[1] >= dictSize) return ERROR(dictionary_corrupted); + dctx->rep[2] = MEM_readLE32(dictPtr+8); if (dctx->rep[2] == 0 || dctx->rep[2] >= dictSize) return ERROR(dictionary_corrupted); dictPtr += 12; dctx->litEntropy = dctx->fseEntropy = 1; @@ -4447,7 +4447,7 @@ size_t ZBUFFv07_decompressContinue(ZBUFFv07_DCtx* zbd, zbd->inBuff = (char*)zbd->customMem.customAlloc(zbd->customMem.opaque, blockSize); if (zbd->inBuff == NULL) return ERROR(memory_allocation); } - { size_t const neededOutSize = zbd->fParams.windowSize + blockSize + WILDCOPY_OVERLENGTH * 2; + { size_t const neededOutSize = zbd->fParams.windowSize + blockSize + WILDCOPY_OVERLENGTH * 2; if (zbd->outBuffSize < neededOutSize) { zbd->customMem.customFree(zbd->customMem.opaque, zbd->outBuff); zbd->outBuffSize = neededOutSize; @@ -4456,7 +4456,7 @@ size_t ZBUFFv07_decompressContinue(ZBUFFv07_DCtx* zbd, } } } zbd->stage = ZBUFFds_read; /* pass-through */ - /* fall-through */ + /* fall-through */ case ZBUFFds_read: { size_t const neededInSize = ZSTDv07_nextSrcSizeToDecompress(zbd->zd); if (neededInSize==0) { /* end of frame */ @@ -4479,7 +4479,7 @@ size_t ZBUFFv07_decompressContinue(ZBUFFv07_DCtx* zbd, if (ip==iend) { notDone = 0; break; } /* no more input */ zbd->stage = ZBUFFds_load; } - /* fall-through */ + /* fall-through */ case ZBUFFds_load: { size_t const neededInSize = ZSTDv07_nextSrcSizeToDecompress(zbd->zd); size_t const toLoad = neededInSize - zbd->inPos; /* should always be <= remaining space within inBuff */ @@ -4500,11 +4500,11 @@ size_t ZBUFFv07_decompressContinue(ZBUFFv07_DCtx* zbd, if (!decodedSize && !isSkipFrame) { zbd->stage = ZBUFFds_read; break; } /* this was just a header */ zbd->outEnd = zbd->outStart + decodedSize; zbd->stage = ZBUFFds_flush; - /* break; */ - /* pass-through */ - } - } - /* fall-through */ + /* break; */ + /* pass-through */ + } + } + /* fall-through */ case ZBUFFds_flush: { size_t const toFlushSize = zbd->outEnd - zbd->outStart; size_t const flushedSize = ZBUFFv07_limitCopy(op, oend-op, zbd->outBuff + zbd->outStart, toFlushSize); diff --git a/contrib/libs/zstd/lib/legacy/zstd_v07.h b/contrib/libs/zstd/lib/legacy/zstd_v07.h index bc35cfa6a3..1b60da5ced 100644 --- a/contrib/libs/zstd/lib/legacy/zstd_v07.h +++ b/contrib/libs/zstd/lib/legacy/zstd_v07.h @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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 ZSTDv07_H_235446 @@ -49,7 +49,7 @@ unsigned long long ZSTDv07_getDecompressedSize(const void* src, size_t srcSize); ZSTDLIBv07_API size_t ZSTDv07_decompress( void* dst, size_t dstCapacity, const void* src, size_t compressedSize); -/** +/** ZSTDv07_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.7.x format srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src' cSize (output parameter) : the number of bytes that would be read to decompress this frame @@ -58,10 +58,10 @@ ZSTDv07_findFrameSizeInfoLegacy() : get the source length and decompressed bound or ZSTD_CONTENTSIZE_ERROR if an error occurs note : assumes `cSize` and `dBound` are _not_ NULL. -*/ +*/ void ZSTDv07_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound); - + /*====== Helper functions ======*/ ZSTDLIBv07_API unsigned ZSTDv07_isError(size_t code); /*!< tells if a `size_t` function result is an error code */ ZSTDLIBv07_API const char* ZSTDv07_getErrorName(size_t code); /*!< provides readable string from an error code */ diff --git a/contrib/libs/zstd/lib/zdict.h b/contrib/libs/zstd/lib/zdict.h index f1e139a40d..07c3ca5ba8 100644 --- a/contrib/libs/zstd/lib/zdict.h +++ b/contrib/libs/zstd/lib/zdict.h @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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 DICTBUILDER_H_001 @@ -20,20 +20,20 @@ extern "C" { #include <stddef.h> /* size_t */ -/* ===== ZDICTLIB_API : control library symbols visibility ===== */ -#ifndef ZDICTLIB_VISIBILITY -# if defined(__GNUC__) && (__GNUC__ >= 4) -# define ZDICTLIB_VISIBILITY __attribute__ ((visibility ("default"))) -# else -# define ZDICTLIB_VISIBILITY -# endif -#endif -#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) -# define ZDICTLIB_API __declspec(dllexport) ZDICTLIB_VISIBILITY -#elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1) -# define ZDICTLIB_API __declspec(dllimport) ZDICTLIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ +/* ===== ZDICTLIB_API : control library symbols visibility ===== */ +#ifndef ZDICTLIB_VISIBILITY +# if defined(__GNUC__) && (__GNUC__ >= 4) +# define ZDICTLIB_VISIBILITY __attribute__ ((visibility ("default"))) +# else +# define ZDICTLIB_VISIBILITY +# endif +#endif +#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) +# define ZDICTLIB_API __declspec(dllexport) ZDICTLIB_VISIBILITY +#elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1) +# define ZDICTLIB_API __declspec(dllimport) ZDICTLIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ #else -# define ZDICTLIB_API ZDICTLIB_VISIBILITY +# define ZDICTLIB_API ZDICTLIB_VISIBILITY #endif /******************************************************************************* @@ -176,26 +176,26 @@ extern "C" { ******************************************************************************/ -/*! ZDICT_trainFromBuffer(): - * Train a dictionary from an array of samples. +/*! ZDICT_trainFromBuffer(): + * Train a dictionary from an array of samples. * Redirect towards ZDICT_optimizeTrainFromBuffer_fastCover() single-threaded, with d=8, steps=4, * f=20, and accel=1. - * Samples must be stored concatenated in a single flat buffer `samplesBuffer`, - * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order. - * The resulting dictionary will be saved into `dictBuffer`. - * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) - * or an error code, which can be tested with ZDICT_isError(). + * Samples must be stored concatenated in a single flat buffer `samplesBuffer`, + * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order. + * The resulting dictionary will be saved into `dictBuffer`. + * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) + * or an error code, which can be tested with ZDICT_isError(). * Note: Dictionary training will fail if there are not enough samples to construct a * dictionary, or if most of the samples are too small (< 8 bytes being the lower limit). * If dictionary training fails, you should use zstd without a dictionary, as the dictionary * would've been ineffective anyways. If you believe your samples would benefit from a dictionary * please open an issue with details, and we can look into it. * Note: ZDICT_trainFromBuffer()'s memory usage is about 6 MB. - * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. - * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. - * In general, it's recommended to provide a few thousands samples, though this can vary a lot. - * It's recommended that total size of all samples be about ~x100 times the target size of dictionary. - */ + * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. + * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. + * In general, it's recommended to provide a few thousands samples, though this can vary a lot. + * It's recommended that total size of all samples be about ~x100 times the target size of dictionary. + */ ZDICTLIB_API size_t ZDICT_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity, const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples); @@ -275,20 +275,20 @@ ZDICTLIB_API const char* ZDICT_getErrorName(size_t errorCode); /* Deprecated: Remove in v1.6.0 */ #define ZDICT_CONTENTSIZE_MIN 128 -/*! ZDICT_cover_params_t: - * k and d are the only required parameters. - * For others, value 0 means default. - */ -typedef struct { - unsigned k; /* Segment size : constraint: 0 < k : Reasonable range [16, 2048+] */ - unsigned d; /* dmer size : constraint: 0 < d <= k : Reasonable range [6, 16] */ +/*! ZDICT_cover_params_t: + * k and d are the only required parameters. + * For others, value 0 means default. + */ +typedef struct { + unsigned k; /* Segment size : constraint: 0 < k : Reasonable range [16, 2048+] */ + unsigned d; /* dmer size : constraint: 0 < d <= k : Reasonable range [6, 16] */ unsigned steps; /* Number of steps : Only used for optimization : 0 means default (40) : Higher means more parameters checked */ - unsigned nbThreads; /* Number of threads : constraint: 0 < nbThreads : 1 means single-threaded : Only used for optimization : Ignored if ZSTD_MULTITHREAD is not defined */ + unsigned nbThreads; /* Number of threads : constraint: 0 < nbThreads : 1 means single-threaded : Only used for optimization : Ignored if ZSTD_MULTITHREAD is not defined */ double splitPoint; /* Percentage of samples used for training: Only used for optimization : the first nbSamples * splitPoint samples will be used to training, the last nbSamples * (1 - splitPoint) samples will be used for testing, 0 means default (1.0), 1.0 when all samples are used for both training and testing */ unsigned shrinkDict; /* Train dictionaries to shrink in size starting from the minimum size and selects the smallest dictionary that is shrinkDictMaxRegression% worse than the largest dictionary. 0 means no shrinking and 1 means shrinking */ unsigned shrinkDictMaxRegression; /* Sets shrinkDictMaxRegression so that a smaller dictionary can be at worse shrinkDictMaxRegression% worse than the max dict size dictionary. */ - ZDICT_params_t zParams; -} ZDICT_cover_params_t; + ZDICT_params_t zParams; +} ZDICT_cover_params_t; typedef struct { unsigned k; /* Segment size : constraint: 0 < k : Reasonable range [16, 2048+] */ @@ -303,48 +303,48 @@ typedef struct { ZDICT_params_t zParams; } ZDICT_fastCover_params_t; - -/*! ZDICT_trainFromBuffer_cover(): - * Train a dictionary from an array of samples using the COVER algorithm. - * Samples must be stored concatenated in a single flat buffer `samplesBuffer`, - * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order. - * The resulting dictionary will be saved into `dictBuffer`. - * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) - * or an error code, which can be tested with ZDICT_isError(). + +/*! ZDICT_trainFromBuffer_cover(): + * Train a dictionary from an array of samples using the COVER algorithm. + * Samples must be stored concatenated in a single flat buffer `samplesBuffer`, + * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order. + * The resulting dictionary will be saved into `dictBuffer`. + * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) + * or an error code, which can be tested with ZDICT_isError(). * See ZDICT_trainFromBuffer() for details on failure modes. - * Note: ZDICT_trainFromBuffer_cover() requires about 9 bytes of memory for each input byte. - * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. - * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. - * In general, it's recommended to provide a few thousands samples, though this can vary a lot. - * It's recommended that total size of all samples be about ~x100 times the target size of dictionary. - */ -ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover( - void *dictBuffer, size_t dictBufferCapacity, - const void *samplesBuffer, const size_t *samplesSizes, unsigned nbSamples, - ZDICT_cover_params_t parameters); - -/*! ZDICT_optimizeTrainFromBuffer_cover(): - * The same requirements as above hold for all the parameters except `parameters`. - * This function tries many parameter combinations and picks the best parameters. - * `*parameters` is filled with the best parameters found, - * dictionary constructed with those parameters is stored in `dictBuffer`. - * - * All of the parameters d, k, steps are optional. + * Note: ZDICT_trainFromBuffer_cover() requires about 9 bytes of memory for each input byte. + * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. + * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. + * In general, it's recommended to provide a few thousands samples, though this can vary a lot. + * It's recommended that total size of all samples be about ~x100 times the target size of dictionary. + */ +ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover( + void *dictBuffer, size_t dictBufferCapacity, + const void *samplesBuffer, const size_t *samplesSizes, unsigned nbSamples, + ZDICT_cover_params_t parameters); + +/*! ZDICT_optimizeTrainFromBuffer_cover(): + * The same requirements as above hold for all the parameters except `parameters`. + * This function tries many parameter combinations and picks the best parameters. + * `*parameters` is filled with the best parameters found, + * dictionary constructed with those parameters is stored in `dictBuffer`. + * + * All of the parameters d, k, steps are optional. * If d is non-zero then we don't check multiple values of d, otherwise we check d = {6, 8}. - * if steps is zero it defaults to its default value. + * if steps is zero it defaults to its default value. * If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [50, 2000]. - * - * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) + * + * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) * or an error code, which can be tested with ZDICT_isError(). * On success `*parameters` contains the parameters selected. * See ZDICT_trainFromBuffer() for details on failure modes. - * Note: ZDICT_optimizeTrainFromBuffer_cover() requires about 8 bytes of memory for each input byte and additionally another 5 bytes of memory for each byte of memory for each thread. - */ -ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover( - void* dictBuffer, size_t dictBufferCapacity, - const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, - ZDICT_cover_params_t* parameters); - + * Note: ZDICT_optimizeTrainFromBuffer_cover() requires about 8 bytes of memory for each input byte and additionally another 5 bytes of memory for each byte of memory for each thread. + */ +ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover( + void* dictBuffer, size_t dictBufferCapacity, + const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, + ZDICT_cover_params_t* parameters); + /*! ZDICT_trainFromBuffer_fastCover(): * Train a dictionary from an array of samples using a modified version of COVER algorithm. * Samples must be stored concatenated in a single flat buffer `samplesBuffer`, @@ -389,58 +389,58 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_fastCover(void* dictBuffer, const size_t* samplesSizes, unsigned nbSamples, ZDICT_fastCover_params_t* parameters); -typedef struct { - unsigned selectivityLevel; /* 0 means default; larger => select more => larger dictionary */ - ZDICT_params_t zParams; -} ZDICT_legacy_params_t; - -/*! ZDICT_trainFromBuffer_legacy(): - * Train a dictionary from an array of samples. - * Samples must be stored concatenated in a single flat buffer `samplesBuffer`, - * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order. - * The resulting dictionary will be saved into `dictBuffer`. - * `parameters` is optional and can be provided with values set to 0 to mean "default". - * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) - * or an error code, which can be tested with ZDICT_isError(). +typedef struct { + unsigned selectivityLevel; /* 0 means default; larger => select more => larger dictionary */ + ZDICT_params_t zParams; +} ZDICT_legacy_params_t; + +/*! ZDICT_trainFromBuffer_legacy(): + * Train a dictionary from an array of samples. + * Samples must be stored concatenated in a single flat buffer `samplesBuffer`, + * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order. + * The resulting dictionary will be saved into `dictBuffer`. + * `parameters` is optional and can be provided with values set to 0 to mean "default". + * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) + * or an error code, which can be tested with ZDICT_isError(). * See ZDICT_trainFromBuffer() for details on failure modes. - * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. - * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. - * In general, it's recommended to provide a few thousands samples, though this can vary a lot. - * It's recommended that total size of all samples be about ~x100 times the target size of dictionary. - * Note: ZDICT_trainFromBuffer_legacy() will send notifications into stderr if instructed to, using notificationLevel>0. - */ -ZDICTLIB_API size_t ZDICT_trainFromBuffer_legacy( + * Tips: In general, a reasonable dictionary has a size of ~ 100 KB. + * It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`. + * In general, it's recommended to provide a few thousands samples, though this can vary a lot. + * It's recommended that total size of all samples be about ~x100 times the target size of dictionary. + * Note: ZDICT_trainFromBuffer_legacy() will send notifications into stderr if instructed to, using notificationLevel>0. + */ +ZDICTLIB_API size_t ZDICT_trainFromBuffer_legacy( void* dictBuffer, size_t dictBufferCapacity, const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, - ZDICT_legacy_params_t parameters); - - -/* Deprecation warnings */ -/* It is generally possible to disable deprecation warnings from compiler, - for example with -Wno-deprecated-declarations for gcc - or _CRT_SECURE_NO_WARNINGS in Visual. - Otherwise, it's also possible to manually define ZDICT_DISABLE_DEPRECATE_WARNINGS */ -#ifdef ZDICT_DISABLE_DEPRECATE_WARNINGS -# define ZDICT_DEPRECATED(message) ZDICTLIB_API /* disable deprecation warnings */ -#else -# define ZDICT_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) -# if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */ -# define ZDICT_DEPRECATED(message) [[deprecated(message)]] ZDICTLIB_API + ZDICT_legacy_params_t parameters); + + +/* Deprecation warnings */ +/* It is generally possible to disable deprecation warnings from compiler, + for example with -Wno-deprecated-declarations for gcc + or _CRT_SECURE_NO_WARNINGS in Visual. + Otherwise, it's also possible to manually define ZDICT_DISABLE_DEPRECATE_WARNINGS */ +#ifdef ZDICT_DISABLE_DEPRECATE_WARNINGS +# define ZDICT_DEPRECATED(message) ZDICTLIB_API /* disable deprecation warnings */ +#else +# define ZDICT_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) +# if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */ +# define ZDICT_DEPRECATED(message) [[deprecated(message)]] ZDICTLIB_API # elif defined(__clang__) || (ZDICT_GCC_VERSION >= 405) -# define ZDICT_DEPRECATED(message) ZDICTLIB_API __attribute__((deprecated(message))) -# elif (ZDICT_GCC_VERSION >= 301) -# define ZDICT_DEPRECATED(message) ZDICTLIB_API __attribute__((deprecated)) -# elif defined(_MSC_VER) -# define ZDICT_DEPRECATED(message) ZDICTLIB_API __declspec(deprecated(message)) -# else -# pragma message("WARNING: You need to implement ZDICT_DEPRECATED for this compiler") -# define ZDICT_DEPRECATED(message) ZDICTLIB_API -# endif -#endif /* ZDICT_DISABLE_DEPRECATE_WARNINGS */ - -ZDICT_DEPRECATED("use ZDICT_finalizeDictionary() instead") +# define ZDICT_DEPRECATED(message) ZDICTLIB_API __attribute__((deprecated(message))) +# elif (ZDICT_GCC_VERSION >= 301) +# define ZDICT_DEPRECATED(message) ZDICTLIB_API __attribute__((deprecated)) +# elif defined(_MSC_VER) +# define ZDICT_DEPRECATED(message) ZDICTLIB_API __declspec(deprecated(message)) +# else +# pragma message("WARNING: You need to implement ZDICT_DEPRECATED for this compiler") +# define ZDICT_DEPRECATED(message) ZDICTLIB_API +# endif +#endif /* ZDICT_DISABLE_DEPRECATE_WARNINGS */ + +ZDICT_DEPRECATED("use ZDICT_finalizeDictionary() instead") size_t ZDICT_addEntropyTablesFromBuffer(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity, - const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples); + const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples); #endif /* ZDICT_STATIC_LINKING_ONLY */ diff --git a/contrib/libs/zstd/lib/zstd.h b/contrib/libs/zstd/lib/zstd.h index a88ae7bf8e..8d25f23bfe 100644 --- a/contrib/libs/zstd/lib/zstd.h +++ b/contrib/libs/zstd/lib/zstd.h @@ -2,10 +2,10 @@ * Copyright (c) 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. + * 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. */ #if defined (__cplusplus) extern "C" { @@ -24,12 +24,12 @@ extern "C" { # if defined(__GNUC__) && (__GNUC__ >= 4) && !defined(__MINGW32__) # define ZSTDLIB_VISIBLE __attribute__ ((visibility ("default"))) # define ZSTDLIB_HIDDEN __attribute__ ((visibility ("hidden"))) -# else +# else # define ZSTDLIB_VISIBLE # define ZSTDLIB_HIDDEN -# endif -#endif -#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) +# endif +#endif +#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) # define ZSTDLIB_API __declspec(dllexport) ZSTDLIB_VISIBLE #elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1) # define ZSTDLIB_API __declspec(dllimport) ZSTDLIB_VISIBLE /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ @@ -54,7 +54,7 @@ extern "C" { Compression can be done in: - a single step (described as Simple API) - - a single step, reusing a context (described as Explicit context) + - a single step, reusing a context (described as Explicit context) - unbounded multiple steps (described as Streaming compression) The compression ratio achievable on small data can be highly improved using @@ -75,8 +75,8 @@ extern "C" { #define ZSTD_VERSION_MAJOR 1 #define ZSTD_VERSION_MINOR 5 #define ZSTD_VERSION_RELEASE 2 -#define ZSTD_VERSION_NUMBER (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE) - +#define ZSTD_VERSION_NUMBER (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE) + /*! ZSTD_versionNumber() : * Return runtime library version, the value is (MAJOR*100*100 + MINOR*100 + RELEASE). */ ZSTDLIB_API unsigned ZSTD_versionNumber(void); @@ -115,55 +115,55 @@ ZSTDLIB_API const char* ZSTD_versionString(void); * Simple API ***************************************/ /*! ZSTD_compress() : - * Compresses `src` content as a single zstd compressed frame into already allocated `dst`. - * Hint : compression runs faster if `dstCapacity` >= `ZSTD_compressBound(srcSize)`. - * @return : compressed size written into `dst` (<= `dstCapacity), - * or an error code if it fails (which can be tested using ZSTD_isError()). */ + * Compresses `src` content as a single zstd compressed frame into already allocated `dst`. + * Hint : compression runs faster if `dstCapacity` >= `ZSTD_compressBound(srcSize)`. + * @return : compressed size written into `dst` (<= `dstCapacity), + * or an error code if it fails (which can be tested using ZSTD_isError()). */ ZSTDLIB_API size_t ZSTD_compress( void* dst, size_t dstCapacity, const void* src, size_t srcSize, int compressionLevel); /*! ZSTD_decompress() : - * `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames. - * `dstCapacity` is an upper bound of originalSize to regenerate. - * If user cannot imply a maximum upper bound, it's better to use streaming mode to decompress data. - * @return : the number of bytes decompressed into `dst` (<= `dstCapacity`), - * or an errorCode if it fails (which can be tested using ZSTD_isError()). */ + * `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames. + * `dstCapacity` is an upper bound of originalSize to regenerate. + * If user cannot imply a maximum upper bound, it's better to use streaming mode to decompress data. + * @return : the number of bytes decompressed into `dst` (<= `dstCapacity`), + * or an errorCode if it fails (which can be tested using ZSTD_isError()). */ ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity, const void* src, size_t compressedSize); /*! ZSTD_getFrameContentSize() : requires v1.3.0+ - * `src` should point to the start of a ZSTD encoded frame. - * `srcSize` must be at least as large as the frame header. - * hint : any size >= `ZSTD_frameHeaderSize_max` is large enough. + * `src` should point to the start of a ZSTD encoded frame. + * `srcSize` must be at least as large as the frame header. + * hint : any size >= `ZSTD_frameHeaderSize_max` is large enough. * @return : - decompressed size of `src` frame content, if known - * - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined - * - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) - * note 1 : a 0 return value means the frame is valid but "empty". - * note 2 : decompressed size is an optional field, it may not be present, typically in streaming mode. - * When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size. - * In which case, it's necessary to use streaming mode to decompress data. - * Optionally, application can rely on some implicit limit, - * as ZSTD_decompress() only needs an upper bound of decompressed size. - * (For example, data could be necessarily cut into blocks <= 16 KB). + * - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined + * - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) + * note 1 : a 0 return value means the frame is valid but "empty". + * note 2 : decompressed size is an optional field, it may not be present, typically in streaming mode. + * When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size. + * In which case, it's necessary to use streaming mode to decompress data. + * Optionally, application can rely on some implicit limit, + * as ZSTD_decompress() only needs an upper bound of decompressed size. + * (For example, data could be necessarily cut into blocks <= 16 KB). * note 3 : decompressed size is always present when compression is completed using single-pass functions, * such as ZSTD_compress(), ZSTD_compressCCtx() ZSTD_compress_usingDict() or ZSTD_compress_usingCDict(). - * note 4 : decompressed size can be very large (64-bits value), - * potentially larger than what local system can handle as a single memory segment. - * In which case, it's necessary to use streaming mode to decompress data. - * note 5 : If source is untrusted, decompressed size could be wrong or intentionally modified. - * Always ensure return value fits within application's authorized limits. - * Each application can set its own limits. - * note 6 : This function replaces ZSTD_getDecompressedSize() */ -#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) -#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) -ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); - + * note 4 : decompressed size can be very large (64-bits value), + * potentially larger than what local system can handle as a single memory segment. + * In which case, it's necessary to use streaming mode to decompress data. + * note 5 : If source is untrusted, decompressed size could be wrong or intentionally modified. + * Always ensure return value fits within application's authorized limits. + * Each application can set its own limits. + * note 6 : This function replaces ZSTD_getDecompressedSize() */ +#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) +ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); + /*! ZSTD_getDecompressedSize() : - * NOTE: This function is now obsolete, in favor of ZSTD_getFrameContentSize(). - * Both functions work the same way, but ZSTD_getDecompressedSize() blends - * "empty", "unknown" and "error" results to the same return value (0), - * while ZSTD_getFrameContentSize() gives them separate return values. + * NOTE: This function is now obsolete, in favor of ZSTD_getFrameContentSize(). + * Both functions work the same way, but ZSTD_getDecompressedSize() blends + * "empty", "unknown" and "error" results to the same return value (0), + * while ZSTD_getFrameContentSize() gives them separate return values. * @return : decompressed size of `src` frame content _if known and not empty_, 0 otherwise. */ ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize); @@ -177,23 +177,23 @@ ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize) /*====== Helper functions ======*/ -#define ZSTD_COMPRESSBOUND(srcSize) ((srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11) /* margin, from 64 to 0 */ : 0)) /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */ -ZSTDLIB_API size_t ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case single-pass scenario */ +#define ZSTD_COMPRESSBOUND(srcSize) ((srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11) /* margin, from 64 to 0 */ : 0)) /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */ +ZSTDLIB_API size_t ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case single-pass scenario */ ZSTDLIB_API unsigned ZSTD_isError(size_t code); /*!< tells if a `size_t` function result is an error code */ ZSTDLIB_API const char* ZSTD_getErrorName(size_t code); /*!< provides readable string from an error code */ ZSTDLIB_API int ZSTD_minCLevel(void); /*!< minimum negative compression level allowed, requires v1.4.0+ */ -ZSTDLIB_API int ZSTD_maxCLevel(void); /*!< maximum compression level available */ +ZSTDLIB_API int ZSTD_maxCLevel(void); /*!< maximum compression level available */ ZSTDLIB_API int ZSTD_defaultCLevel(void); /*!< default compression level, specified by ZSTD_CLEVEL_DEFAULT, requires v1.5.0+ */ /*************************************** -* Explicit context +* Explicit context ***************************************/ /*= Compression context - * When compressing many times, + * When compressing many times, * it is recommended to allocate a context just once, * and re-use it for each successive compression operation. - * This will make workload friendlier for system's memory. + * This will make workload friendlier for system's memory. * Note : re-using context is just a speed / resource optimization. * It doesn't change the compression ratio, which remains identical. * Note 2 : In multi-threaded environments, @@ -212,16 +212,16 @@ ZSTDLIB_API size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx); /* accept NULL pointer * * they will all be reset. Only `compressionLevel` remains. */ ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* cctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - int compressionLevel); - -/*= Decompression context - * When decompressing many times, - * it is recommended to allocate a context only once, - * and re-use it for each successive compression operation. - * This will make workload friendlier for system's memory. - * Use one context per thread for parallel execution. */ + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + int compressionLevel); + +/*= Decompression context + * When decompressing many times, + * it is recommended to allocate a context only once, + * and re-use it for each successive compression operation. + * This will make workload friendlier for system's memory. + * Use one context per thread for parallel execution. */ typedef struct ZSTD_DCtx_s ZSTD_DCtx; ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx(void); ZSTDLIB_API size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx); /* accept NULL pointer */ @@ -232,8 +232,8 @@ ZSTDLIB_API size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx); /* accept NULL pointer * * Compatible with sticky parameters. */ ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize); + void* dst, size_t dstCapacity, + const void* src, size_t srcSize); /********************************************* @@ -662,19 +662,19 @@ typedef struct ZSTD_outBuffer_s { * start a new frame. * note: ZSTD_e_end will flush as much output as possible, meaning when compressing with multiple threads, it will * block until the flush is complete or the output buffer is full. -* @return : 0 if frame fully completed and fully flushed, +* @return : 0 if frame fully completed and fully flushed, * >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), * or an error code, which can be tested using ZSTD_isError(). * * *******************************************************************/ -typedef ZSTD_CCtx ZSTD_CStream; /**< CCtx and CStream are now effectively same object (>= v1.3.0) */ +typedef ZSTD_CCtx ZSTD_CStream; /**< CCtx and CStream are now effectively same object (>= v1.3.0) */ /* Continue to distinguish them for compatibility with older versions <= v1.2.0 */ -/*===== ZSTD_CStream management functions =====*/ +/*===== ZSTD_CStream management functions =====*/ ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void); ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs); /* accept NULL pointer */ -/*===== Streaming compression functions =====*/ +/*===== Streaming compression functions =====*/ typedef enum { ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */ ZSTD_e_flush=1, /* flush any data provided so far, @@ -789,13 +789,13 @@ ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); * that will never request more than the remaining frame size. * *******************************************************************************/ -typedef ZSTD_DCtx ZSTD_DStream; /**< DCtx and DStream are now effectively same object (>= v1.3.0) */ +typedef ZSTD_DCtx ZSTD_DStream; /**< DCtx and DStream are now effectively same object (>= v1.3.0) */ /* For compatibility with versions <= v1.2.0, prefer differentiating them. */ -/*===== ZSTD_DStream management functions =====*/ +/*===== ZSTD_DStream management functions =====*/ ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void); ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds); /* accept NULL pointer */ -/*===== Streaming decompression functions =====*/ +/*===== Streaming decompression functions =====*/ /* This function is redundant with the advanced API and equivalent to: * @@ -1068,13 +1068,13 @@ ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); **************************************************************************************** * The definitions in the following section are considered experimental. * They are provided for advanced scenarios. - * They should never be used with a dynamic library, as prototypes may change in the future. + * They should never be used with a dynamic library, as prototypes may change in the future. * Use them only in association with static linking. * ***************************************************************************************/ -#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY) -#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY - +#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY) +#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY + /* This can be overridden externally to hide static symbols. */ #ifndef ZSTDLIB_STATIC_API # if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) @@ -1233,24 +1233,24 @@ typedef struct { ZSTD_frameParameters fParams; } ZSTD_parameters; -typedef enum { +typedef enum { ZSTD_dct_auto = 0, /* dictionary is "full" when starting with ZSTD_MAGIC_DICTIONARY, otherwise it is "rawContent" */ ZSTD_dct_rawContent = 1, /* ensures dictionary is always loaded as rawContent, even if it starts with ZSTD_MAGIC_DICTIONARY */ ZSTD_dct_fullDict = 2 /* refuses to load a dictionary if it does not respect Zstandard's specification, starting with ZSTD_MAGIC_DICTIONARY */ -} ZSTD_dictContentType_e; +} ZSTD_dictContentType_e; -typedef enum { +typedef enum { ZSTD_dlm_byCopy = 0, /**< Copy dictionary content internally */ ZSTD_dlm_byRef = 1 /**< Reference dictionary content -- the dictionary buffer must outlive its users. */ -} ZSTD_dictLoadMethod_e; - +} ZSTD_dictLoadMethod_e; + typedef enum { ZSTD_f_zstd1 = 0, /* zstd frame format, specified in zstd_compression_format.md (default) */ ZSTD_f_zstd1_magicless = 1 /* Variant of zstd frame format, without initial 4-bytes magic number. * Useful to save 4 bytes per generated frame. * Decoder cannot recognise automatically this format, requiring this instruction. */ } ZSTD_format_e; - + typedef enum { /* Note: this enum controls ZSTD_d_forceIgnoreChecksum */ ZSTD_d_validateChecksum = 0, @@ -1301,7 +1301,7 @@ typedef enum { ZSTD_dictForceCopy = 2, /* Always copy the dictionary. */ ZSTD_dictForceLoad = 3 /* Always reload the dictionary */ } ZSTD_dictAttachPref_e; - + typedef enum { ZSTD_lcm_auto = 0, /**< Automatically determine the compression mode based on the compression level. * Negative compression levels will be uncompressed, and positive compression @@ -1322,32 +1322,32 @@ typedef enum { } ZSTD_paramSwitch_e; /*************************************** -* Frame size functions +* Frame size functions ***************************************/ -/*! ZSTD_findDecompressedSize() : +/*! ZSTD_findDecompressedSize() : * `src` should point to the start of a series of ZSTD encoded and/or skippable frames - * `srcSize` must be the _exact_ size of this series + * `srcSize` must be the _exact_ size of this series * (i.e. there should be a frame boundary at `src + srcSize`) - * @return : - decompressed size of all data in all successive frames - * - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN - * - if an error occurred: ZSTD_CONTENTSIZE_ERROR - * - * note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode. - * When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size. - * In which case, it's necessary to use streaming mode to decompress data. - * note 2 : decompressed size is always present when compression is done with ZSTD_compress() - * note 3 : decompressed size can be very large (64-bits value), - * potentially larger than what local system can handle as a single memory segment. - * In which case, it's necessary to use streaming mode to decompress data. - * note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified. - * Always ensure result fits within application's authorized limits. - * Each application can set its own limits. - * note 5 : ZSTD_findDecompressedSize handles multiple frames, and so it must traverse the input to - * read each contained frame header. This is fast as most of the data is skipped, - * however it does mean that all frame data must be present and valid. */ + * @return : - decompressed size of all data in all successive frames + * - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN + * - if an error occurred: ZSTD_CONTENTSIZE_ERROR + * + * note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode. + * When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size. + * In which case, it's necessary to use streaming mode to decompress data. + * note 2 : decompressed size is always present when compression is done with ZSTD_compress() + * note 3 : decompressed size can be very large (64-bits value), + * potentially larger than what local system can handle as a single memory segment. + * In which case, it's necessary to use streaming mode to decompress data. + * note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified. + * Always ensure result fits within application's authorized limits. + * Each application can set its own limits. + * note 5 : ZSTD_findDecompressedSize handles multiple frames, and so it must traverse the input to + * read each contained frame header. This is fast as most of the data is skipped, + * however it does mean that all frame data must be present and valid. */ ZSTDLIB_STATIC_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize); - + /*! ZSTD_decompressBound() : * `src` should point to the start of a series of ZSTD encoded and/or skippable frames * `srcSize` must be the _exact_ size of this series @@ -1363,12 +1363,12 @@ ZSTDLIB_STATIC_API unsigned long long ZSTD_findDecompressedSize(const void* src, */ ZSTDLIB_STATIC_API unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize); -/*! ZSTD_frameHeaderSize() : +/*! ZSTD_frameHeaderSize() : * srcSize must be >= ZSTD_FRAMEHEADERSIZE_PREFIX. * @return : size of the Frame Header, * or an error code (if srcSize is too small) */ ZSTDLIB_STATIC_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize); - + typedef enum { ZSTD_sf_noBlockDelimiters = 0, /* Representation of ZSTD_Sequence has no block delimiters, sequences only */ ZSTD_sf_explicitBlockDelimiters = 1 /* Representation of ZSTD_Sequence contains explicit block delimiters */ @@ -1389,7 +1389,7 @@ typedef enum { * setting of ZSTD_c_blockDelimiters as ZSTD_sf_explicitBlockDelimiters * @return : number of sequences generated */ - + ZSTDLIB_STATIC_API size_t ZSTD_generateSequences(ZSTD_CCtx* zc, ZSTD_Sequence* outSeqs, size_t outSeqsSize, const void* src, size_t srcSize); @@ -1476,11 +1476,11 @@ ZSTDLIB_API unsigned ZSTD_isSkippableFrame(const void* buffer, size_t size); -/*************************************** -* Memory management -***************************************/ - -/*! ZSTD_estimate*() : +/*************************************** +* Memory management +***************************************/ + +/*! ZSTD_estimate*() : * These functions make it possible to estimate memory usage * of a future {D,C}Ctx, before its creation. * @@ -1507,100 +1507,100 @@ ZSTDLIB_STATIC_API size_t ZSTD_estimateCCtxSize(int compressionLevel); ZSTDLIB_STATIC_API size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams); ZSTDLIB_STATIC_API size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params); ZSTDLIB_STATIC_API size_t ZSTD_estimateDCtxSize(void); - -/*! ZSTD_estimateCStreamSize() : - * ZSTD_estimateCStreamSize() will provide a budget large enough for any compression level up to selected one. - * It will also consider src size to be arbitrarily "large", which is worst case. - * If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation. - * ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. + +/*! ZSTD_estimateCStreamSize() : + * ZSTD_estimateCStreamSize() will provide a budget large enough for any compression level up to selected one. + * It will also consider src size to be arbitrarily "large", which is worst case. + * If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation. + * ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. * ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. - * Note : CStream size estimation is only correct for single-threaded compression. - * ZSTD_DStream memory budget depends on window Size. - * This information can be passed manually, using ZSTD_estimateDStreamSize, - * or deducted from a valid frame Header, using ZSTD_estimateDStreamSize_fromFrame(); - * Note : if streaming is init with function ZSTD_init?Stream_usingDict(), - * an internal ?Dict will be created, which additional size is not estimated here. - * In this case, get total size by adding ZSTD_estimate?DictSize */ + * Note : CStream size estimation is only correct for single-threaded compression. + * ZSTD_DStream memory budget depends on window Size. + * This information can be passed manually, using ZSTD_estimateDStreamSize, + * or deducted from a valid frame Header, using ZSTD_estimateDStreamSize_fromFrame(); + * Note : if streaming is init with function ZSTD_init?Stream_usingDict(), + * an internal ?Dict will be created, which additional size is not estimated here. + * In this case, get total size by adding ZSTD_estimate?DictSize */ ZSTDLIB_STATIC_API size_t ZSTD_estimateCStreamSize(int compressionLevel); ZSTDLIB_STATIC_API size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams); ZSTDLIB_STATIC_API size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params); ZSTDLIB_STATIC_API size_t ZSTD_estimateDStreamSize(size_t windowSize); ZSTDLIB_STATIC_API size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize); - -/*! ZSTD_estimate?DictSize() : - * ZSTD_estimateCDictSize() will bet that src size is relatively "small", and content is copied, like ZSTD_createCDict(). - * ZSTD_estimateCDictSize_advanced() makes it possible to control compression parameters precisely, like ZSTD_createCDict_advanced(). - * Note : dictionaries created by reference (`ZSTD_dlm_byRef`) are logically smaller. - */ + +/*! ZSTD_estimate?DictSize() : + * ZSTD_estimateCDictSize() will bet that src size is relatively "small", and content is copied, like ZSTD_createCDict(). + * ZSTD_estimateCDictSize_advanced() makes it possible to control compression parameters precisely, like ZSTD_createCDict_advanced(). + * Note : dictionaries created by reference (`ZSTD_dlm_byRef`) are logically smaller. + */ ZSTDLIB_STATIC_API size_t ZSTD_estimateCDictSize(size_t dictSize, int compressionLevel); ZSTDLIB_STATIC_API size_t ZSTD_estimateCDictSize_advanced(size_t dictSize, ZSTD_compressionParameters cParams, ZSTD_dictLoadMethod_e dictLoadMethod); ZSTDLIB_STATIC_API size_t ZSTD_estimateDDictSize(size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod); - -/*! ZSTD_initStatic*() : - * Initialize an object using a pre-allocated fixed-size buffer. - * workspace: The memory area to emplace the object into. - * Provided pointer *must be 8-bytes aligned*. - * Buffer must outlive object. - * workspaceSize: Use ZSTD_estimate*Size() to determine - * how large workspace must be to support target scenario. - * @return : pointer to object (same address as workspace, just different type), - * or NULL if error (size too small, incorrect alignment, etc.) - * Note : zstd will never resize nor malloc() when using a static buffer. - * If the object requires more memory than available, - * zstd will just error out (typically ZSTD_error_memory_allocation). - * Note 2 : there is no corresponding "free" function. - * Since workspace is allocated externally, it must be freed externally too. - * Note 3 : cParams : use ZSTD_getCParams() to convert a compression level - * into its associated cParams. - * Limitation 1 : currently not compatible with internal dictionary creation, triggered by - * ZSTD_CCtx_loadDictionary(), ZSTD_initCStream_usingDict() or ZSTD_initDStream_usingDict(). - * Limitation 2 : static cctx currently not compatible with multi-threading. - * Limitation 3 : static dctx is incompatible with legacy support. - */ + +/*! ZSTD_initStatic*() : + * Initialize an object using a pre-allocated fixed-size buffer. + * workspace: The memory area to emplace the object into. + * Provided pointer *must be 8-bytes aligned*. + * Buffer must outlive object. + * workspaceSize: Use ZSTD_estimate*Size() to determine + * how large workspace must be to support target scenario. + * @return : pointer to object (same address as workspace, just different type), + * or NULL if error (size too small, incorrect alignment, etc.) + * Note : zstd will never resize nor malloc() when using a static buffer. + * If the object requires more memory than available, + * zstd will just error out (typically ZSTD_error_memory_allocation). + * Note 2 : there is no corresponding "free" function. + * Since workspace is allocated externally, it must be freed externally too. + * Note 3 : cParams : use ZSTD_getCParams() to convert a compression level + * into its associated cParams. + * Limitation 1 : currently not compatible with internal dictionary creation, triggered by + * ZSTD_CCtx_loadDictionary(), ZSTD_initCStream_usingDict() or ZSTD_initDStream_usingDict(). + * Limitation 2 : static cctx currently not compatible with multi-threading. + * Limitation 3 : static dctx is incompatible with legacy support. + */ ZSTDLIB_STATIC_API ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize); ZSTDLIB_STATIC_API ZSTD_CStream* ZSTD_initStaticCStream(void* workspace, size_t workspaceSize); /**< same as ZSTD_initStaticCCtx() */ - + ZSTDLIB_STATIC_API ZSTD_DCtx* ZSTD_initStaticDCtx(void* workspace, size_t workspaceSize); ZSTDLIB_STATIC_API ZSTD_DStream* ZSTD_initStaticDStream(void* workspace, size_t workspaceSize); /**< same as ZSTD_initStaticDCtx() */ - + ZSTDLIB_STATIC_API const ZSTD_CDict* ZSTD_initStaticCDict( - void* workspace, size_t workspaceSize, - const void* dict, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, - ZSTD_dictContentType_e dictContentType, - ZSTD_compressionParameters cParams); - + void* workspace, size_t workspaceSize, + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_compressionParameters cParams); + ZSTDLIB_STATIC_API const ZSTD_DDict* ZSTD_initStaticDDict( - void* workspace, size_t workspaceSize, - const void* dict, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, - ZSTD_dictContentType_e dictContentType); - - -/*! Custom memory allocation : - * These prototypes make it possible to pass your own allocation/free functions. - * ZSTD_customMem is provided at creation time, using ZSTD_create*_advanced() variants listed below. - * All allocation/free operations will be completed using these custom variants instead of regular <stdlib.h> ones. - */ -typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size); -typedef void (*ZSTD_freeFunction) (void* opaque, void* address); -typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem; + void* workspace, size_t workspaceSize, + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType); + + +/*! Custom memory allocation : + * These prototypes make it possible to pass your own allocation/free functions. + * ZSTD_customMem is provided at creation time, using ZSTD_create*_advanced() variants listed below. + * All allocation/free operations will be completed using these custom variants instead of regular <stdlib.h> ones. + */ +typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size); +typedef void (*ZSTD_freeFunction) (void* opaque, void* address); +typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem; static #ifdef __GNUC__ __attribute__((__unused__)) #endif ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL }; /**< this constant defers to stdlib's functions */ - + ZSTDLIB_STATIC_API ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem); ZSTDLIB_STATIC_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem); ZSTDLIB_STATIC_API ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem); ZSTDLIB_STATIC_API ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem); - + ZSTDLIB_STATIC_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, - ZSTD_dictLoadMethod_e dictLoadMethod, - ZSTD_dictContentType_e dictContentType, - ZSTD_compressionParameters cParams, - ZSTD_customMem customMem); + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_compressionParameters cParams, + ZSTD_customMem customMem); /*! Thread pool : * These prototypes make it possible to share a thread pool among multiple compression contexts. @@ -1635,18 +1635,18 @@ ZSTDLIB_STATIC_API ZSTD_DDict* ZSTD_createDDict_advanced( ZSTD_customMem customMem); -/*************************************** -* Advanced compression functions -***************************************/ - -/*! ZSTD_createCDict_byReference() : - * Create a digested dictionary for compression +/*************************************** +* Advanced compression functions +***************************************/ + +/*! ZSTD_createCDict_byReference() : + * Create a digested dictionary for compression * Dictionary content is just referenced, not duplicated. * As a consequence, `dictBuffer` **must** outlive CDict, * and its content must remain unmodified throughout the lifetime of CDict. * note: equivalent to ZSTD_createCDict_advanced(), with dictLoadMethod==ZSTD_dlm_byRef */ ZSTDLIB_STATIC_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel); - + /*! ZSTD_getCParams() : * @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize. * `estimatedSrcSize` value is optional, select 0 if not known */ @@ -1663,7 +1663,7 @@ ZSTDLIB_STATIC_API ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned ZSTDLIB_STATIC_API size_t ZSTD_checkCParams(ZSTD_compressionParameters params); /*! ZSTD_adjustCParams() : - * optimize params for a given `srcSize` and `dictSize`. + * optimize params for a given `srcSize` and `dictSize`. * `srcSize` can be unknown, in which case use ZSTD_CONTENTSIZE_UNKNOWN. * `dictSize` must be `0` when there is no dictionary. * cPar can be invalid : all parameters will be clamped within valid range in the @return struct. @@ -1681,7 +1681,7 @@ size_t ZSTD_compress_advanced(ZSTD_CCtx* cctx, const void* dict,size_t dictSize, ZSTD_parameters params); -/*! ZSTD_compress_usingCDict_advanced() : +/*! ZSTD_compress_usingCDict_advanced() : * Note : this function is now DEPRECATED. * It can be replaced by ZSTD_compress2(), in combination with ZSTD_CCtx_loadDictionary() and other parameter setters. * This prototype will generate compilation warnings. */ @@ -1692,7 +1692,7 @@ size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams); - + /*! ZSTD_CCtx_loadDictionary_byReference() : * Same as ZSTD_CCtx_loadDictionary(), but dictionary content is referenced, instead of being copied into CCtx. * It saves some memory, but also requires that `dict` outlives its usage within `cctx` */ @@ -2045,11 +2045,11 @@ ZSTDLIB_STATIC_API size_t ZSTD_compressStream2_simpleArgs ( * Note 3 : Skippable Frame Identifiers are considered valid. */ ZSTDLIB_STATIC_API unsigned ZSTD_isFrame(const void* buffer, size_t size); -/*! ZSTD_createDDict_byReference() : - * Create a digested dictionary, ready to start decompression operation without startup delay. - * Dictionary content is referenced, and therefore stays in dictBuffer. - * It is important that dictBuffer outlives DDict, - * it must remain read accessible throughout the lifetime of DDict */ +/*! ZSTD_createDDict_byReference() : + * Create a digested dictionary, ready to start decompression operation without startup delay. + * Dictionary content is referenced, and therefore stays in dictBuffer. + * It is important that dictBuffer outlives DDict, + * it must remain read accessible throughout the lifetime of DDict */ ZSTDLIB_STATIC_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize); /*! ZSTD_DCtx_loadDictionary_byReference() : @@ -2276,7 +2276,7 @@ size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize); -/*! ZSTD_resetCStream() : +/*! ZSTD_resetCStream() : * This function is DEPRECATED, and is equivalent to: * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); @@ -2286,35 +2286,35 @@ size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, * * start a new frame, using same parameters from previous frame. * This is typically useful to skip dictionary loading stage, since it will re-use it in-place. - * Note that zcs must be init at least once before using ZSTD_resetCStream(). - * If pledgedSrcSize is not known at reset time, use macro ZSTD_CONTENTSIZE_UNKNOWN. - * If pledgedSrcSize > 0, its value must be correct, as it will be written in header, and controlled at the end. - * For the time being, pledgedSrcSize==0 is interpreted as "srcSize unknown" for compatibility with older programs, - * but it will change to mean "empty" in future version, so use macro ZSTD_CONTENTSIZE_UNKNOWN instead. + * Note that zcs must be init at least once before using ZSTD_resetCStream(). + * If pledgedSrcSize is not known at reset time, use macro ZSTD_CONTENTSIZE_UNKNOWN. + * If pledgedSrcSize > 0, its value must be correct, as it will be written in header, and controlled at the end. + * For the time being, pledgedSrcSize==0 is interpreted as "srcSize unknown" for compatibility with older programs, + * but it will change to mean "empty" in future version, so use macro ZSTD_CONTENTSIZE_UNKNOWN instead. * @return : 0, or an error code (which can be tested using ZSTD_isError()) * This prototype will generate compilation warnings. */ ZSTD_DEPRECATED("use ZSTD_CCtx_reset, see zstd.h for detailed instructions") size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize); - -typedef struct { + +typedef struct { unsigned long long ingested; /* nb input bytes read and buffered */ unsigned long long consumed; /* nb input bytes actually compressed */ unsigned long long produced; /* nb of compressed bytes generated and buffered */ unsigned long long flushed; /* nb of compressed bytes flushed : not provided; can be tracked from caller side */ unsigned currentJobID; /* MT only : latest started job nb */ unsigned nbActiveWorkers; /* MT only : nb of workers actively compressing at probe time */ -} ZSTD_frameProgression; - +} ZSTD_frameProgression; + /* ZSTD_getFrameProgression() : - * tells how much data has been ingested (read from input) - * consumed (input actually compressed) and produced (output) for current frame. + * tells how much data has been ingested (read from input) + * consumed (input actually compressed) and produced (output) for current frame. * Note : (ingested - consumed) is amount of input data buffered internally, not yet compressed. * Aggregates progression inside active worker threads. - */ + */ ZSTDLIB_STATIC_API ZSTD_frameProgression ZSTD_getFrameProgression(const ZSTD_CCtx* cctx); - + /*! ZSTD_toFlushNow() : * Tell how many bytes are ready to be flushed immediately. * Useful for multithreading scenarios (nbWorkers >= 1). @@ -2329,8 +2329,8 @@ ZSTDLIB_STATIC_API ZSTD_frameProgression ZSTD_getFrameProgression(const ZSTD_CCt * irrespective of the speed of concurrent (and newer) jobs. */ ZSTDLIB_STATIC_API size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx); - - + + /*===== Advanced Streaming decompression functions =====*/ /*! @@ -2370,8 +2370,8 @@ ZSTDLIB_STATIC_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); * Buffer-less and synchronous inner streaming functions * * This is an advanced API, giving full control over buffer management, for users which need direct control over memory. -* But it's also a complex one, with several restrictions, documented below. -* Prefer normal streaming API for an easier experience. +* But it's also a complex one, with several restrictions, documented below. +* Prefer normal streaming API for an easier experience. ********************************************************************* */ /** @@ -2387,8 +2387,8 @@ ZSTDLIB_STATIC_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); Then, consume your input using ZSTD_compressContinue(). There are some important considerations to keep in mind when using this advanced function : - - ZSTD_compressContinue() has no internal buffer. It uses externally provided buffers only. - - Interface is synchronous : input is consumed entirely and produces 1+ compressed blocks. + - ZSTD_compressContinue() has no internal buffer. It uses externally provided buffers only. + - Interface is synchronous : input is consumed entirely and produces 1+ compressed blocks. - Caller must ensure there is enough space in `dst` to store compressed data under worst case scenario. Worst case evaluation is provided by ZSTD_compressBound(). ZSTD_compressContinue() doesn't guarantee recover after a failed compression. @@ -2398,10 +2398,10 @@ ZSTDLIB_STATIC_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); In which case, it will "discard" the relevant memory section from its history. Finish a frame with ZSTD_compressEnd(), which will write the last block(s) and optional checksum. - It's possible to use srcSize==0, in which case, it will write a final empty block to end the frame. - Without last block mark, frames are considered unfinished (hence corrupted) by compliant decoders. + It's possible to use srcSize==0, in which case, it will write a final empty block to end the frame. + Without last block mark, frames are considered unfinished (hence corrupted) by compliant decoders. - `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress again. + `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress again. */ /*===== Buffer-less streaming compression functions =====*/ @@ -2409,7 +2409,7 @@ ZSTDLIB_STATIC_API size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLev ZSTDLIB_STATIC_API size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel); ZSTDLIB_STATIC_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); /**< note: fails if cdict==NULL */ ZSTDLIB_STATIC_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); /**< note: if pledgedSrcSize is not known, use ZSTD_CONTENTSIZE_UNKNOWN */ - + ZSTDLIB_STATIC_API size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); ZSTDLIB_STATIC_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); @@ -2425,52 +2425,52 @@ size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_ Use ZSTD_createDCtx() / ZSTD_freeDCtx() to manage it. A ZSTD_DCtx object can be re-used multiple times. - First typical operation is to retrieve frame parameters, using ZSTD_getFrameHeader(). - Frame header is extracted from the beginning of compressed frame, so providing only the frame's beginning is enough. - Data fragment must be large enough to ensure successful decoding. - `ZSTD_frameHeaderSize_max` bytes is guaranteed to always be large enough. - @result : 0 : successful decoding, the `ZSTD_frameHeader` structure is correctly filled. + First typical operation is to retrieve frame parameters, using ZSTD_getFrameHeader(). + Frame header is extracted from the beginning of compressed frame, so providing only the frame's beginning is enough. + Data fragment must be large enough to ensure successful decoding. + `ZSTD_frameHeaderSize_max` bytes is guaranteed to always be large enough. + @result : 0 : successful decoding, the `ZSTD_frameHeader` structure is correctly filled. >0 : `srcSize` is too small, please provide at least @result bytes on next attempt. errorCode, which can be tested using ZSTD_isError(). - It fills a ZSTD_frameHeader structure with important information to correctly decode the frame, - such as the dictionary ID, content size, or maximum back-reference distance (`windowSize`). - Note that these values could be wrong, either because of data corruption, or because a 3rd party deliberately spoofs false information. - As a consequence, check that values remain within valid application range. - For example, do not allocate memory blindly, check that `windowSize` is within expectation. - Each application can set its own limits, depending on local restrictions. - For extended interoperability, it is recommended to support `windowSize` of at least 8 MB. - - ZSTD_decompressContinue() needs previous data blocks during decompression, up to `windowSize` bytes. - ZSTD_decompressContinue() is very sensitive to contiguity, - if 2 blocks don't follow each other, make sure that either the compressor breaks contiguity at the same place, - or that previous contiguous segment is large enough to properly handle maximum back-reference distance. - There are multiple ways to guarantee this condition. - - The most memory efficient way is to use a round buffer of sufficient size. - Sufficient size is determined by invoking ZSTD_decodingBufferSize_min(), - which can @return an error code if required value is too large for current system (in 32-bits mode). - In a round buffer methodology, ZSTD_decompressContinue() decompresses each block next to previous one, - up to the moment there is not enough room left in the buffer to guarantee decoding another full block, - which maximum size is provided in `ZSTD_frameHeader` structure, field `blockSizeMax`. - At which point, decoding can resume from the beginning of the buffer. - Note that already decoded data stored in the buffer should be flushed before being overwritten. - - There are alternatives possible, for example using two or more buffers of size `windowSize` each, though they consume more memory. - - Finally, if you control the compression process, you can also ignore all buffer size rules, - as long as the encoder and decoder progress in "lock-step", - aka use exactly the same buffer sizes, break contiguity at the same place, etc. - - Once buffers are setup, start decompression, with ZSTD_decompressBegin(). - If decompression requires a dictionary, use ZSTD_decompressBegin_usingDict() or ZSTD_decompressBegin_usingDDict(). - + It fills a ZSTD_frameHeader structure with important information to correctly decode the frame, + such as the dictionary ID, content size, or maximum back-reference distance (`windowSize`). + Note that these values could be wrong, either because of data corruption, or because a 3rd party deliberately spoofs false information. + As a consequence, check that values remain within valid application range. + For example, do not allocate memory blindly, check that `windowSize` is within expectation. + Each application can set its own limits, depending on local restrictions. + For extended interoperability, it is recommended to support `windowSize` of at least 8 MB. + + ZSTD_decompressContinue() needs previous data blocks during decompression, up to `windowSize` bytes. + ZSTD_decompressContinue() is very sensitive to contiguity, + if 2 blocks don't follow each other, make sure that either the compressor breaks contiguity at the same place, + or that previous contiguous segment is large enough to properly handle maximum back-reference distance. + There are multiple ways to guarantee this condition. + + The most memory efficient way is to use a round buffer of sufficient size. + Sufficient size is determined by invoking ZSTD_decodingBufferSize_min(), + which can @return an error code if required value is too large for current system (in 32-bits mode). + In a round buffer methodology, ZSTD_decompressContinue() decompresses each block next to previous one, + up to the moment there is not enough room left in the buffer to guarantee decoding another full block, + which maximum size is provided in `ZSTD_frameHeader` structure, field `blockSizeMax`. + At which point, decoding can resume from the beginning of the buffer. + Note that already decoded data stored in the buffer should be flushed before being overwritten. + + There are alternatives possible, for example using two or more buffers of size `windowSize` each, though they consume more memory. + + Finally, if you control the compression process, you can also ignore all buffer size rules, + as long as the encoder and decoder progress in "lock-step", + aka use exactly the same buffer sizes, break contiguity at the same place, etc. + + Once buffers are setup, start decompression, with ZSTD_decompressBegin(). + If decompression requires a dictionary, use ZSTD_decompressBegin_usingDict() or ZSTD_decompressBegin_usingDDict(). + Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() alternatively. ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' to ZSTD_decompressContinue(). ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will fail. - @result of ZSTD_decompressContinue() is the number of bytes regenerated within 'dst' (necessarily <= dstCapacity). - It can be zero : it just means ZSTD_decompressContinue() has decoded some metadata item. + @result of ZSTD_decompressContinue() is the number of bytes regenerated within 'dst' (necessarily <= dstCapacity). + It can be zero : it just means ZSTD_decompressContinue() has decoded some metadata item. It can also be an error code, which can be tested with ZSTD_isError(). A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero. @@ -2482,26 +2482,26 @@ size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_ == Special case : skippable frames == Skippable frames allow integration of user-defined data into a flow of concatenated frames. - Skippable frames will be ignored (skipped) by decompressor. - The format of skippable frames is as follows : + Skippable frames will be ignored (skipped) by decompressor. + The format of skippable frames is as follows : a) Skippable frame ID - 4 Bytes, Little endian format, any value from 0x184D2A50 to 0x184D2A5F b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits c) Frame Content - any content (User Data) of length equal to Frame Size - For skippable frames ZSTD_getFrameHeader() returns zfhPtr->frameType==ZSTD_skippableFrame. - For skippable frames ZSTD_decompressContinue() always returns 0 : it only skips the content. + For skippable frames ZSTD_getFrameHeader() returns zfhPtr->frameType==ZSTD_skippableFrame. + For skippable frames ZSTD_decompressContinue() always returns 0 : it only skips the content. */ -/*===== Buffer-less streaming decompression functions =====*/ -typedef enum { ZSTD_frame, ZSTD_skippableFrame } ZSTD_frameType_e; +/*===== Buffer-less streaming decompression functions =====*/ +typedef enum { ZSTD_frame, ZSTD_skippableFrame } ZSTD_frameType_e; typedef struct { - unsigned long long frameContentSize; /* if == ZSTD_CONTENTSIZE_UNKNOWN, it means this field is not available. 0 means "empty" */ - unsigned long long windowSize; /* can be very large, up to <= frameContentSize */ - unsigned blockSizeMax; - ZSTD_frameType_e frameType; /* if == ZSTD_skippableFrame, frameContentSize is the size of skippable content */ - unsigned headerSize; + unsigned long long frameContentSize; /* if == ZSTD_CONTENTSIZE_UNKNOWN, it means this field is not available. 0 means "empty" */ + unsigned long long windowSize; /* can be very large, up to <= frameContentSize */ + unsigned blockSizeMax; + ZSTD_frameType_e frameType; /* if == ZSTD_skippableFrame, frameContentSize is the size of skippable content */ + unsigned headerSize; unsigned dictID; unsigned checksumFlag; -} ZSTD_frameHeader; +} ZSTD_frameHeader; /*! ZSTD_getFrameHeader() : * decode Frame Header, or requires larger `srcSize`. @@ -2518,23 +2518,23 @@ ZSTDLIB_STATIC_API size_t ZSTD_decodingBufferSize_min(unsigned long long windowS ZSTDLIB_STATIC_API size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx); ZSTDLIB_STATIC_API size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); ZSTDLIB_STATIC_API size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); - + ZSTDLIB_STATIC_API size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx); ZSTDLIB_STATIC_API size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); - -/* misc */ + +/* misc */ ZSTDLIB_STATIC_API void ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx); typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e; ZSTDLIB_STATIC_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); - - -/* ============================ */ -/** Block level API */ -/* ============================ */ - -/*! + + +/* ============================ */ +/** Block level API */ +/* ============================ */ + +/*! Block functions produce and decode raw zstd blocks, without frame metadata. Frame metadata cost is typically ~12 bytes, which can be non-negligible for very small blocks (< 100 bytes). But users will have to take in charge needed metadata to regenerate data, such as compressed and content sizes. @@ -2543,11 +2543,11 @@ ZSTDLIB_STATIC_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); - Compressing and decompressing require a context structure + Use ZSTD_createCCtx() and ZSTD_createDCtx() - It is necessary to init context before starting - + compression : any ZSTD_compressBegin*() variant, including with dictionary - + decompression : any ZSTD_decompressBegin*() variant, including with dictionary - + copyCCtx() and copyDCtx() can be used too - - Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX == 128 KB - + If input is larger than a block size, it's necessary to split input data into multiple blocks + + compression : any ZSTD_compressBegin*() variant, including with dictionary + + decompression : any ZSTD_decompressBegin*() variant, including with dictionary + + copyCCtx() and copyDCtx() can be used too + - Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX == 128 KB + + If input is larger than a block size, it's necessary to split input data into multiple blocks + For inputs larger than a single block, consider using regular ZSTD_compress() instead. Frame metadata is not that costly, and quickly becomes negligible as source size grows larger than a block. - When a block is considered not compressible enough, ZSTD_compressBlock() result will be 0 (zero) ! @@ -2556,9 +2556,9 @@ ZSTDLIB_STATIC_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); + A block cannot be declared incompressible if ZSTD_compressBlock() return value was != 0. Doing so would mess up with statistics history, leading to potential data corruption. + ZSTD_decompressBlock() _doesn't accept uncompressed data as input_ !! - + In case of multiple successive blocks, should some of them be uncompressed, - decoder must be informed of their existence in order to follow proper history. - Use ZSTD_insertBlock() for such a case. + + In case of multiple successive blocks, should some of them be uncompressed, + decoder must be informed of their existence in order to follow proper history. + Use ZSTD_insertBlock() for such a case. */ /*===== Raw zstd block functions =====*/ diff --git a/contrib/libs/zstd/lib/zstd_errors.h b/contrib/libs/zstd/lib/zstd_errors.h index fa3686b772..f5c7c43d0b 100644 --- a/contrib/libs/zstd/lib/zstd_errors.h +++ b/contrib/libs/zstd/lib/zstd_errors.h @@ -1,11 +1,11 @@ -/* +/* * Copyright (c) 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. + * 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_ERRORS_H_398273423 @@ -19,73 +19,73 @@ extern "C" { #include <stddef.h> /* size_t */ -/* ===== ZSTDERRORLIB_API : control library symbols visibility ===== */ -#ifndef ZSTDERRORLIB_VISIBILITY -# if defined(__GNUC__) && (__GNUC__ >= 4) -# define ZSTDERRORLIB_VISIBILITY __attribute__ ((visibility ("default"))) -# else -# define ZSTDERRORLIB_VISIBILITY -# endif -#endif -#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) -# define ZSTDERRORLIB_API __declspec(dllexport) ZSTDERRORLIB_VISIBILITY -#elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1) -# define ZSTDERRORLIB_API __declspec(dllimport) ZSTDERRORLIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ -#else -# define ZSTDERRORLIB_API ZSTDERRORLIB_VISIBILITY -#endif - -/*-********************************************* - * Error codes list - *-********************************************* - * Error codes _values_ are pinned down since v1.3.1 only. - * Therefore, don't rely on values if you may link to any version < v1.3.1. - * - * Only values < 100 are considered stable. - * - * note 1 : this API shall be used with static linking only. - * dynamic linking is not yet officially supported. - * note 2 : Prefer relying on the enum than on its value whenever possible - * This is the only supported way to use the error list < v1.3.1 - * note 3 : ZSTD_isError() is always correct, whatever the library version. - **********************************************/ +/* ===== ZSTDERRORLIB_API : control library symbols visibility ===== */ +#ifndef ZSTDERRORLIB_VISIBILITY +# if defined(__GNUC__) && (__GNUC__ >= 4) +# define ZSTDERRORLIB_VISIBILITY __attribute__ ((visibility ("default"))) +# else +# define ZSTDERRORLIB_VISIBILITY +# endif +#endif +#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) +# define ZSTDERRORLIB_API __declspec(dllexport) ZSTDERRORLIB_VISIBILITY +#elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1) +# define ZSTDERRORLIB_API __declspec(dllimport) ZSTDERRORLIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ +#else +# define ZSTDERRORLIB_API ZSTDERRORLIB_VISIBILITY +#endif + +/*-********************************************* + * Error codes list + *-********************************************* + * Error codes _values_ are pinned down since v1.3.1 only. + * Therefore, don't rely on values if you may link to any version < v1.3.1. + * + * Only values < 100 are considered stable. + * + * note 1 : this API shall be used with static linking only. + * dynamic linking is not yet officially supported. + * note 2 : Prefer relying on the enum than on its value whenever possible + * This is the only supported way to use the error list < v1.3.1 + * note 3 : ZSTD_isError() is always correct, whatever the library version. + **********************************************/ typedef enum { - ZSTD_error_no_error = 0, - ZSTD_error_GENERIC = 1, - ZSTD_error_prefix_unknown = 10, - ZSTD_error_version_unsupported = 12, - ZSTD_error_frameParameter_unsupported = 14, - ZSTD_error_frameParameter_windowTooLarge = 16, - ZSTD_error_corruption_detected = 20, - ZSTD_error_checksum_wrong = 22, - ZSTD_error_dictionary_corrupted = 30, - ZSTD_error_dictionary_wrong = 32, - ZSTD_error_dictionaryCreation_failed = 34, - ZSTD_error_parameter_unsupported = 40, - ZSTD_error_parameter_outOfBound = 42, - ZSTD_error_tableLog_tooLarge = 44, - ZSTD_error_maxSymbolValue_tooLarge = 46, - ZSTD_error_maxSymbolValue_tooSmall = 48, - ZSTD_error_stage_wrong = 60, - ZSTD_error_init_missing = 62, - ZSTD_error_memory_allocation = 64, - ZSTD_error_workSpace_tooSmall= 66, - ZSTD_error_dstSize_tooSmall = 70, - ZSTD_error_srcSize_wrong = 72, + ZSTD_error_no_error = 0, + ZSTD_error_GENERIC = 1, + ZSTD_error_prefix_unknown = 10, + ZSTD_error_version_unsupported = 12, + ZSTD_error_frameParameter_unsupported = 14, + ZSTD_error_frameParameter_windowTooLarge = 16, + ZSTD_error_corruption_detected = 20, + ZSTD_error_checksum_wrong = 22, + ZSTD_error_dictionary_corrupted = 30, + ZSTD_error_dictionary_wrong = 32, + ZSTD_error_dictionaryCreation_failed = 34, + ZSTD_error_parameter_unsupported = 40, + ZSTD_error_parameter_outOfBound = 42, + ZSTD_error_tableLog_tooLarge = 44, + ZSTD_error_maxSymbolValue_tooLarge = 46, + ZSTD_error_maxSymbolValue_tooSmall = 48, + ZSTD_error_stage_wrong = 60, + ZSTD_error_init_missing = 62, + ZSTD_error_memory_allocation = 64, + ZSTD_error_workSpace_tooSmall= 66, + ZSTD_error_dstSize_tooSmall = 70, + ZSTD_error_srcSize_wrong = 72, ZSTD_error_dstBuffer_null = 74, - /* following error codes are __NOT STABLE__, they can be removed or changed in future versions */ - ZSTD_error_frameIndex_tooLarge = 100, - ZSTD_error_seekableIO = 102, + /* following error codes are __NOT STABLE__, they can be removed or changed in future versions */ + ZSTD_error_frameIndex_tooLarge = 100, + ZSTD_error_seekableIO = 102, ZSTD_error_dstBuffer_wrong = 104, ZSTD_error_srcBuffer_wrong = 105, - ZSTD_error_maxCode = 120 /* never EVER use this value directly, it can change in future versions! Use ZSTD_isError() instead */ + ZSTD_error_maxCode = 120 /* never EVER use this value directly, it can change in future versions! Use ZSTD_isError() instead */ } ZSTD_ErrorCode; /*! ZSTD_getErrorCode() : convert a `size_t` function result into a `ZSTD_ErrorCode` enum type, - which can be used to compare with enum list published above */ -ZSTDERRORLIB_API ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult); -ZSTDERRORLIB_API const char* ZSTD_getErrorString(ZSTD_ErrorCode code); /**< Same as ZSTD_getErrorName, but using a `ZSTD_ErrorCode` enum argument */ + which can be used to compare with enum list published above */ +ZSTDERRORLIB_API ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult); +ZSTDERRORLIB_API const char* ZSTD_getErrorString(ZSTD_ErrorCode code); /**< Same as ZSTD_getErrorName, but using a `ZSTD_ErrorCode` enum argument */ #if defined (__cplusplus) |