Scarfski/tracy
1
0
Fork 0
mirror of https://github.com/wolfpld/tracy.git synced 2026-11-09 01:15:25 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
3dced9c241ab0fed0c53a06c4e638bc99ff4a339
tracy/public/common/tracy_lz4.cpp
T
Bartosz Taudul 3dced9c241 Bump LZ4 to 1.11.0.
2026-11-05 00:58:54 +01:00

2945 lines
123 KiB
C++
Raw Blame History

/*
LZ4 - Fast LZ compression algorithm
Copyright (c) Yann Collet. All rights reserved.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following disclaimer
in the documentation and/or other materials provided with the
distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
You can contact the author at :
- LZ4 homepage : http://www.lz4.org
- LZ4 source repository : https://github.com/lz4/lz4
*/
/*-************************************
* Tuning parameters
**************************************/
/*
* LZ4_HEAPMODE :
* Select how stateless compression functions like `LZ4_compress_default()`
* allocate memory for their hash table,
* in memory stack (0:default, fastest), or in memory heap (1:requires malloc()).
*/
#ifndef LZ4_HEAPMODE
# define LZ4_HEAPMODE 0
#endif
/*-************************************
* CPU Feature Detection
**************************************/
/* LZ4_FORCE_MEMORY_ACCESS
* By default, access to unaligned memory is controlled by `memcpy()`, which is safe and portable.
* 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 (ie, 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 which assembly generation depends on alignment.
* But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6)
* See https://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details.
* Prefer these methods in priority order (0 > 1 > 2)
*/
#ifndef LZ4_FORCE_MEMORY_ACCESS /* can be defined externally */
# if defined(__GNUC__) && \
( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) \
|| defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) \
|| (defined(__riscv) && defined(__riscv_zicclsm)) )
# define LZ4_FORCE_MEMORY_ACCESS 2
# elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__) || defined(_MSC_VER)
# define LZ4_FORCE_MEMORY_ACCESS 1
# endif
#endif
/*
* LZ4_FORCE_SW_BITCOUNT
* Define this parameter if your target system or compiler does not support hardware bit count
*/
#if defined(_MSC_VER) && defined(_WIN32_WCE) /* Visual Studio for WinCE doesn't support Hardware bit count */
# undef LZ4_FORCE_SW_BITCOUNT /* avoid double def */
# define LZ4_FORCE_SW_BITCOUNT
#endif
/*-************************************
* Dependency
**************************************/
/*
* LZ4_SRC_INCLUDED:
* Amalgamation flag, whether lz4.c is included
*/
#ifndef LZ4_SRC_INCLUDED
# define LZ4_SRC_INCLUDED 1
#endif
#ifndef LZ4_DISABLE_DEPRECATE_WARNINGS
# define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */
#endif
#ifndef LZ4_STATIC_LINKING_ONLY
# define LZ4_STATIC_LINKING_ONLY
#endif
#include "tracy_lz4.hpp"
/* see also "memory routines" below */
/*-************************************
* Compiler Options
**************************************/
#if defined(_MSC_VER) && (_MSC_VER >= 1400) /* Visual Studio 2005+ */
# include <intrin.h> /* only present in VS2005+ */
# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
# pragma warning(disable : 6237) /* disable: C6237: conditional expression is always 0 */
# pragma warning(disable : 6239) /* disable: C6239: (<non-zero constant> && <expression>) always evaluates to the result of <expression> */
# pragma warning(disable : 6240) /* disable: C6240: (<expression> && <non-zero constant>) always evaluates to the result of <expression> */
# pragma warning(disable : 6326) /* disable: C6326: Potential comparison of a constant with another constant */
#endif /* _MSC_VER */
#ifndef LZ4_FORCE_INLINE
# if defined (_MSC_VER) && !defined (__clang__) /* MSVC */
# define LZ4_FORCE_INLINE static __forceinline
# else
# if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */
# if defined (__GNUC__) || defined (__clang__)
# define LZ4_FORCE_INLINE static inline __attribute__((always_inline))
# else
# define LZ4_FORCE_INLINE static inline
# endif
# else
# define LZ4_FORCE_INLINE static
# endif /* __STDC_VERSION__ */
# endif /* _MSC_VER */
#endif /* LZ4_FORCE_INLINE */
/* LZ4_FORCE_NOINLINE : keeps a rarely used function out of its callers' hot loops */
#ifndef LZ4_FORCE_NOINLINE
# if defined(_MSC_VER)
# define LZ4_FORCE_NOINLINE static __declspec(noinline)
# elif defined(__GNUC__) || defined(__clang__)
# define LZ4_FORCE_NOINLINE static __attribute__((noinline))
# else
# define LZ4_FORCE_NOINLINE static
# endif
#endif
/* LZ4_FORCE_O2 and LZ4_FORCE_INLINE
* gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy8,
* together with a simple 8-byte copy loop as a fall-back path.
* However, this optimization hurts the decompression speed by >30%,
* because the execution does not go to the optimized loop
* for typical compressible data, and all of the preamble checks
* before going to the fall-back path become useless overhead.
* This optimization happens only with the -O3 flag, and -O2 generates
* a simple 8-byte copy loop.
* With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy8
* functions are annotated with __attribute__((optimize("O2"))),
* and also LZ4_wildCopy8 is forcibly inlined, so that the O2 attribute
* of LZ4_wildCopy8 does not affect the compression speed.
*/
#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__) && !defined(__clang__)
# define LZ4_FORCE_O2 __attribute__((optimize("O2")))
# undef LZ4_FORCE_INLINE
# define LZ4_FORCE_INLINE static __inline __attribute__((optimize("O2"),always_inline))
#else
# define LZ4_FORCE_O2
#endif
#if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__)
# define expect(expr,value) (__builtin_expect ((expr),(value)) )
#else
# define expect(expr,value) (expr)
#endif
#ifndef likely
#define likely(expr) expect((expr) != 0, 1)
#endif
#ifndef unlikely
#define unlikely(expr) expect((expr) != 0, 0)
#endif
/* Should the alignment test prove unreliable, for some reason,
* it can be disabled by setting LZ4_ALIGN_TEST to 0 */
#ifndef LZ4_ALIGN_TEST /* can be externally provided */
# define LZ4_ALIGN_TEST 1
#endif
/*-************************************
* Memory routines
**************************************/
/*! LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION :
* Disable relatively high-level LZ4/HC functions that use dynamic memory
* allocation functions (malloc(), calloc(), free()).
*
* Note that this is a compile-time switch. And since it disables
* public/stable LZ4 v1 API functions, we don't recommend using this
* symbol to generate a library for distribution.
*
* The following public functions are removed when this symbol is defined.
* - lz4 : LZ4_createStream, LZ4_freeStream,
* LZ4_createStreamDecode, LZ4_freeStreamDecode, LZ4_create (deprecated)
* - lz4hc : LZ4_createStreamHC, LZ4_freeStreamHC,
* LZ4_createHC (deprecated), LZ4_freeHC (deprecated)
* - lz4frame, lz4file : All LZ4F_* functions
*/
#if defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
# define ALLOC(s) lz4_error_memory_allocation_is_disabled
# define ALLOC_AND_ZERO(s) lz4_error_memory_allocation_is_disabled
# define FREEMEM(p) lz4_error_memory_allocation_is_disabled
#elif defined(LZ4_USER_MEMORY_FUNCTIONS)
/* memory management functions can be customized by user project.
* Below functions must exist somewhere in the Project
* and be available at link time. */
void* LZ4_malloc(size_t s);
void* LZ4_calloc(size_t n, size_t s);
void LZ4_free(void* p);
# define ALLOC(s) LZ4_malloc(s)
# define ALLOC_AND_ZERO(s) LZ4_calloc(1,s)
# define FREEMEM(p) LZ4_free(p)
#else
# include <stdlib.h> /* malloc, calloc, free */
# define ALLOC(s) malloc(s)
# define ALLOC_AND_ZERO(s) calloc(1,s)
# define FREEMEM(p) free(p)
#endif
#if ! LZ4_FREESTANDING
# include <string.h> /* memset, memcpy */
#endif
#if !defined(LZ4_memset)
# define LZ4_memset(p,v,s) memset((p),(v),(s))
#endif
#define MEM_INIT(p,v,s) LZ4_memset((p),(v),(s))
/*-************************************
* Common Constants
**************************************/
#define MINMATCH 4
#define WILDCOPYLENGTH 8
#define LASTLITERALS 5 /* see ../doc/lz4_Block_format.md#parsing-restrictions */
#define MFLIMIT 12 /* see ../doc/lz4_Block_format.md#parsing-restrictions */
#define MATCH_SAFEGUARD_DISTANCE ((2*WILDCOPYLENGTH) - MINMATCH) /* ensure it's possible to write 2 x wildcopyLength without overflowing output buffer */
#define FASTLOOP_SAFE_DISTANCE 64
static const int LZ4_minLength = (MFLIMIT+1);
#define KB *(1 <<10)
#define MB *(1 <<20)
#define GB *(1U<<30)
#define LZ4_DISTANCE_ABSOLUTE_MAX 65535
#if (LZ4_DISTANCE_MAX > LZ4_DISTANCE_ABSOLUTE_MAX) /* max supported by LZ4 format */
# error "LZ4_DISTANCE_MAX is too big : must be <= 65535"
#endif
#define ML_BITS 4
#define ML_MASK ((1U<<ML_BITS)-1)
#define RUN_BITS (8-ML_BITS)
#define RUN_MASK ((1U<<RUN_BITS)-1)
/*-************************************
* Error detection
**************************************/
#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=1)
# include <assert.h>
#else
# ifndef assert
# define assert(condition) ((void)0)
# endif
#endif
#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(int)(!!(c)) }; } /* use after variable declarations */
#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2)
# include <stdio.h>
static int g_debuglog_enable = 1;
# define DEBUGLOG(l, ...) { \
if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) { \
fprintf(stderr, __FILE__ " %i: ", __LINE__); \
fprintf(stderr, __VA_ARGS__); \
fprintf(stderr, " \n"); \
} }
#else
# define DEBUGLOG(l, ...) {} /* disabled */
#endif
static int LZ4_isAligned(const void* ptr, size_t alignment)
{
return ((size_t)ptr & (alignment -1)) == 0;
}
/*-************************************
* Types
**************************************/
#include <limits.h>
#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
# include <stdint.h>
typedef unsigned char BYTE; /*uint8_t not necessarily blessed to alias arbitrary type*/
typedef uint16_t U16;
typedef uint32_t U32;
typedef int32_t S32;
typedef uint64_t U64;
typedef uintptr_t uptrval;
#else
# if UINT_MAX != 4294967295UL
# error "LZ4 code (when not C++ or C99) assumes that sizeof(int) == 4"
# endif
typedef unsigned char BYTE;
typedef unsigned short U16;
typedef unsigned int U32;
typedef signed int S32;
typedef unsigned long long U64;
typedef size_t uptrval; /* generally true, except OpenVMS-64 */
#endif
#if defined(__x86_64__)
typedef U64 reg_t; /* 64-bits in x32 mode */
#else
typedef size_t reg_t; /* 32-bits in x32 mode */
#endif
typedef enum {
notLimited = 0,
limitedOutput = 1,
fillOutput = 2
} limitedOutput_directive;
namespace tracy
{
/*-************************************
* Reading and writing into memory
**************************************/
/**
* LZ4 relies on memcpy with a constant size being inlined. In freestanding
* environments, the compiler can't assume the implementation of memcpy() is
* standard compliant, so it can't apply its specialized memcpy() inlining
* logic. When possible, use __builtin_memcpy() to tell the compiler to analyze
* memcpy() as if it were standard compliant, so it can inline it in freestanding
* environments. This is needed when decompressing the Linux Kernel, for example.
*/
#if !defined(LZ4_memcpy)
# if defined(__GNUC__) && (__GNUC__ >= 4)
# define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size)
# else
# define LZ4_memcpy(dst, src, size) memcpy(dst, src, size)
# endif
#endif
#if !defined(LZ4_memmove)
# if defined(__GNUC__) && (__GNUC__ >= 4)
# define LZ4_memmove __builtin_memmove
# else
# define LZ4_memmove memmove
# endif
#endif
static unsigned LZ4_isLittleEndian(void)
{
const union { U32 u; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */
return one.c[0];
}
#if defined(__GNUC__) || defined(__INTEL_COMPILER)
#define LZ4_PACK( __Declaration__ ) __Declaration__ __attribute__((__packed__))
#elif defined(_MSC_VER)
#define LZ4_PACK( __Declaration__ ) __pragma( pack(push, 1) ) __Declaration__ __pragma( pack(pop))
#endif
#if defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==2)
/* lie to the compiler about data alignment; use with caution */
static U16 LZ4_read16(const void* memPtr) { return *(const U16*) memPtr; }
static U32 LZ4_read32(const void* memPtr) { return *(const U32*) memPtr; }
static reg_t LZ4_read_ARCH(const void* memPtr) { return *(const reg_t*) memPtr; }
static void LZ4_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; }
static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; }
#elif defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==1)
/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */
/* currently only defined for gcc and icc */
LZ4_PACK(typedef struct { U16 u16; }) LZ4_unalign16;
LZ4_PACK(typedef struct { U32 u32; }) LZ4_unalign32;
LZ4_PACK(typedef struct { reg_t uArch; }) LZ4_unalignST;
static U16 LZ4_read16(const void* ptr) { return ((const LZ4_unalign16*)ptr)->u16; }
static U32 LZ4_read32(const void* ptr) { return ((const LZ4_unalign32*)ptr)->u32; }
static reg_t LZ4_read_ARCH(const void* ptr) { return ((const LZ4_unalignST*)ptr)->uArch; }
static void LZ4_write16(void* memPtr, U16 value) { ((LZ4_unalign16*)memPtr)->u16 = value; }
static void LZ4_write32(void* memPtr, U32 value) { ((LZ4_unalign32*)memPtr)->u32 = value; }
#else /* safe and portable access using memcpy() */
static U16 LZ4_read16(const void* memPtr)
{
U16 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val;
}
static U32 LZ4_read32(const void* memPtr)
{
U32 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val;
}
static reg_t LZ4_read_ARCH(const void* memPtr)
{
reg_t val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val;
}
static void LZ4_write16(void* memPtr, U16 value)
{
LZ4_memcpy(memPtr, &value, sizeof(value));
}
static void LZ4_write32(void* memPtr, U32 value)
{
LZ4_memcpy(memPtr, &value, sizeof(value));
}
#endif /* LZ4_FORCE_MEMORY_ACCESS */
static U16 LZ4_readLE16(const void* memPtr)
{
if (LZ4_isLittleEndian()) {
return LZ4_read16(memPtr);
} else {
const BYTE* p = (const BYTE*)memPtr;
return (U16)((U16)p[0] | (p[1]<<8));
}
}
#ifdef LZ4_STATIC_LINKING_ONLY_ENDIANNESS_INDEPENDENT_OUTPUT
static U32 LZ4_readLE32(const void* memPtr)
{
if (LZ4_isLittleEndian()) {
return LZ4_read32(memPtr);
} else {
const BYTE* p = (const BYTE*)memPtr;
return (U32)p[0] | (p[1]<<8) | (p[2]<<16) | (p[3]<<24);
}
}
#endif
static void LZ4_writeLE16(void* memPtr, U16 value)
{
if (LZ4_isLittleEndian()) {
LZ4_write16(memPtr, value);
} else {
BYTE* p = (BYTE*)memPtr;
p[0] = (BYTE) value;
p[1] = (BYTE)(value>>8);
}
}
/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */
LZ4_FORCE_INLINE
void LZ4_wildCopy8(void* dstPtr, const void* srcPtr, void* dstEnd)
{
BYTE* d = (BYTE*)dstPtr;
const BYTE* s = (const BYTE*)srcPtr;
BYTE* const e = (BYTE*)dstEnd;
do { LZ4_memcpy(d,s,8); d+=8; s+=8; } while (d<e);
}
static const unsigned inc32table[8] = {0, 1, 2, 1, 0, 4, 4, 4};
static const int dec64table[8] = {0, 0, 0, -1, -4, 1, 2, 3};
#ifndef LZ4_FAST_DEC_LOOP
# if defined __i386__ || defined _M_IX86 || defined __x86_64__ || defined _M_X64
# define LZ4_FAST_DEC_LOOP 1
# elif defined(__aarch64__)
# define LZ4_FAST_DEC_LOOP 1
# elif defined(__riscv) && (__riscv_xlen == 64) && defined(__riscv_misaligned_fast)
# define LZ4_FAST_DEC_LOOP 1 /* otherwise, unaligned memcpy() become byte copies, defeating the fast loop */
# else
# define LZ4_FAST_DEC_LOOP 0
# endif
#endif
/* LZ4_memcpy_using_offset_base() :
* copy a match of length >= MINMATCH (srcPtr + offset == dstPtr, overlap allowed),
* can overwrite up to 12 bytes beyond dstEnd */
LZ4_FORCE_INLINE void
LZ4_memcpy_using_offset_base(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset)
{
assert(srcPtr + offset == dstPtr);
if (unlikely(offset < 8)) {
LZ4_write32(dstPtr, 0); /* silence an msan warning when offset==0 */
dstPtr[0] = srcPtr[0];
dstPtr[1] = srcPtr[1];
dstPtr[2] = srcPtr[2];
dstPtr[3] = srcPtr[3];
srcPtr += inc32table[offset];
LZ4_memcpy(dstPtr+4, srcPtr, 4);
srcPtr -= dec64table[offset];
} else {
LZ4_memcpy(dstPtr, srcPtr, 8);
srcPtr += 8;
}
dstPtr += 8;
/* srcPtr is now at least 8 bytes behind dstPtr */
LZ4_memcpy(dstPtr, srcPtr, 8);
if (dstEnd > dstPtr + 8) { LZ4_wildCopy8(dstPtr + 8, srcPtr + 8, dstEnd); }
}
#if LZ4_FAST_DEC_LOOP
/* LZ4_wildCopy64 is faster on aarch64 and x86-64, but not on 32-bit x86.
* On wasm, it depends on the host cpu (faster on Apple silicon, slower on x86-64) :
* it's not enabled by default, but can be, with LZ4_FAST_DEC_LOOP, from the build command */
#ifndef LZ4_WILDCOPY64
# if defined(__aarch64__) || defined(__x86_64__) || defined(_M_X64)
# define LZ4_WILDCOPY64 1
# else
# define LZ4_WILDCOPY64 0
# endif
#endif
#if LZ4_WILDCOPY64
/* customized variant of memcpy, which can overwrite up to 64 bytes beyond dstEnd */
LZ4_FORCE_INLINE void
LZ4_wildCopy64(void* dstPtr, const void* srcPtr, void* dstEnd)
{
BYTE* d = (BYTE*)dstPtr;
const BYTE* s = (const BYTE*)srcPtr;
BYTE* const e = (BYTE*)dstEnd;
do { LZ4_memcpy(d,s,64); d+=64; s+=64; } while (d<e);
}
#endif
/* customized variant of memcpy, which can overwrite up to 32 bytes beyond dstEnd
* this version copies two times 16 bytes (instead of one time 32 bytes)
* because it must be compatible with offsets >= 16. */
LZ4_FORCE_INLINE void
LZ4_wildCopy32(void* dstPtr, const void* srcPtr, void* dstEnd)
{
BYTE* d = (BYTE*)dstPtr;
const BYTE* s = (const BYTE*)srcPtr;
BYTE* const e = (BYTE*)dstEnd;
do { LZ4_memcpy(d,s,16); LZ4_memcpy(d+16,s+16,16); d+=32; s+=32; } while (d<e);
}
/* LZ4_memcpy_using_offset() presumes :
* - dstEnd >= dstPtr + MINMATCH
* - there is at least 12 bytes available to write after dstEnd */
LZ4_FORCE_INLINE void
LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset)
{
BYTE v[8];
assert(dstEnd >= dstPtr + MINMATCH);
switch(offset) {
case 1:
MEM_INIT(v, *srcPtr, 8);
break;
case 2:
LZ4_memcpy(v, srcPtr, 2);
LZ4_memcpy(&v[2], srcPtr, 2);
#if defined(_MSC_VER) && (_MSC_VER <= 1937) /* MSVC 2022 ver 17.7 or earlier */
# pragma warning(push)
# pragma warning(disable : 6385) /* warning C6385: Reading invalid data from 'v'. */
#endif
LZ4_memcpy(&v[4], v, 4);
#if defined(_MSC_VER) && (_MSC_VER <= 1937) /* MSVC 2022 ver 17.7 or earlier */
# pragma warning(pop)
#endif
break;
case 4:
LZ4_memcpy(v, srcPtr, 4);
LZ4_memcpy(&v[4], srcPtr, 4);
break;
default:
LZ4_memcpy_using_offset_base(dstPtr, srcPtr, dstEnd, offset);
return;
}
LZ4_memcpy(dstPtr, v, 8);
dstPtr += 8;
while (dstPtr < dstEnd) {
LZ4_memcpy(dstPtr, v, 8);
dstPtr += 8;
}
}
#endif
/*-************************************
* Common functions
**************************************/
LZ4_FORCE_INLINE unsigned LZ4_NbCommonBytes (reg_t val)
{
assert(val != 0);
if (LZ4_isLittleEndian()) {
if (sizeof(val) == 8) {
# if defined(_MSC_VER) && (_MSC_VER >= 1800) && (defined(_M_AMD64) && !defined(_M_ARM64EC)) && !defined(LZ4_FORCE_SW_BITCOUNT)
/*-*************************************************************************************************
* ARM64EC is a Microsoft-designed ARM64 ABI compatible with AMD64 applications on ARM64 Windows 11.
* The ARM64EC ABI does not support AVX/AVX2/AVX512 instructions, nor their relevant intrinsics
* including _tzcnt_u64. Therefore, we need to neuter the _tzcnt_u64 code path for ARM64EC.
****************************************************************************************************/
# if defined(__clang__) && (__clang_major__ < 10)
/* Avoid undefined clang-cl intrinsics issue.
* See https://github.com/lz4/lz4/pull/1017 for details. */
return (unsigned)__builtin_ia32_tzcnt_u64(val) >> 3;
# else
/* x64 CPUS without BMI support interpret `TZCNT` as `REP BSF` */
return (unsigned)_tzcnt_u64(val) >> 3;
# endif
# elif defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
unsigned long r = 0;
_BitScanForward64(&r, (U64)val);
return (unsigned)r >> 3;
# elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
!defined(LZ4_FORCE_SW_BITCOUNT)
return (unsigned)__builtin_ctzll((U64)val) >> 3;
# else
const U64 m = 0x0101010101010101ULL;
val ^= val - 1;
return (unsigned)(((U64)((val & (m - 1)) * m)) >> 56);
# endif
} else /* 32 bits */ {
# if defined(_MSC_VER) && (_MSC_VER >= 1400) && !defined(LZ4_FORCE_SW_BITCOUNT)
unsigned long r;
_BitScanForward(&r, (U32)val);
return (unsigned)r >> 3;
# elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
!defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT)
return (unsigned)__builtin_ctz((U32)val) >> 3;
# else
const U32 m = 0x01010101;
return (unsigned)((((val - 1) ^ val) & (m - 1)) * m) >> 24;
# endif
}
} else /* Big Endian CPU */ {
if (sizeof(val)==8) {
# if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
!defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT)
return (unsigned)__builtin_clzll((U64)val) >> 3;
# else
#if 1
/* this method is probably faster,
* but adds a 128 bytes lookup table */
static const unsigned char ctz7_tab[128] = {
7, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
6, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
};
U64 const mask = 0x0101010101010101ULL;
U64 const t = (((val >> 8) - mask) | val) & mask;
return ctz7_tab[(t * 0x0080402010080402ULL) >> 57];
#else
/* this method doesn't consume memory space like the previous one,
* but it contains several branches,
* that may end up slowing execution */
static const U32 by32 = sizeof(val)*4; /* 32 on 64 bits (goal), 16 on 32 bits.
Just to avoid some static analyzer complaining about shift by 32 on 32-bits target.
Note that this code path is never triggered in 32-bits mode. */
unsigned r;
if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; }
if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
r += (!val);
return r;
#endif
# endif
} else /* 32 bits */ {
# if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
!defined(LZ4_FORCE_SW_BITCOUNT)
return (unsigned)__builtin_clz((U32)val) >> 3;
# else
val >>= 8;
val = ((((val + 0x00FFFF00) | 0x00FFFFFF) + val) |
(val + 0x00FF0000)) >> 24;
return (unsigned)val ^ 3;
# endif
}
}
}
#define STEPSIZE sizeof(reg_t)
LZ4_FORCE_INLINE
unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)
{
const BYTE* const pStart = pIn;
if (likely(pIn < pInLimit-(STEPSIZE-1))) {
reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
if (!diff) {
pIn+=STEPSIZE; pMatch+=STEPSIZE;
} else {
return LZ4_NbCommonBytes(diff);
} }
while (likely(pIn < pInLimit-(STEPSIZE-1))) {
reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; }
pIn += LZ4_NbCommonBytes(diff);
return (unsigned)(pIn - pStart);
}
if ((STEPSIZE==8) && (pIn<(pInLimit-3)) && (LZ4_read32(pMatch) == LZ4_read32(pIn))) { pIn+=4; pMatch+=4; }
if ((pIn<(pInLimit-1)) && (LZ4_read16(pMatch) == LZ4_read16(pIn))) { pIn+=2; pMatch+=2; }
if ((pIn<pInLimit) && (*pMatch == *pIn)) pIn++;
return (unsigned)(pIn - pStart);
}
#ifndef LZ4_COMMONDEFS_ONLY
/*-************************************
* Local Constants
**************************************/
static const int LZ4_64Klimit = ((64 KB) + (MFLIMIT-1));
static const U32 LZ4_skipTrigger = 6; /* Increase this value ==> compression run slower on incompressible data */
/*-************************************
* Local Structures and types
**************************************/
typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t;
/**
* This enum distinguishes several different modes of accessing previous
* content in the stream.
*
* - noDict : There is no preceding content.
* - withPrefix64k : Table entries up to ctx->dictSize before the current blob
* blob being compressed are valid and refer to the preceding
* content (of length ctx->dictSize), which is available
* contiguously preceding in memory the content currently
* being compressed.
* - usingExtDict : Like withPrefix64k, but the preceding content is somewhere
* else in memory, starting at ctx->dictionary with length
* ctx->dictSize.
* - usingDictCtx : Everything concerning the preceding content is
* in a separate context, pointed to by ctx->dictCtx.
* ctx->dictionary, ctx->dictSize, and table entries
* in the current context that refer to positions
* preceding the beginning of the current compression are
* ignored. Instead, ctx->dictCtx->dictionary and ctx->dictCtx
* ->dictSize describe the location and size of the preceding
* content, and matches are found by looking in the ctx
* ->dictCtx->hashTable.
*/
typedef enum { noDict = 0, withPrefix64k, usingExtDict, usingDictCtx } dict_directive;
typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
/*-************************************
* Local Utils
**************************************/
int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; }
const char* LZ4_versionString(void) { return LZ4_VERSION_STRING; }
int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); }
int LZ4_sizeofState(void) { return sizeof(LZ4_stream_t); }
/*-****************************************
* Internal Definitions, used only in Tests
*******************************************/
int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize);
int LZ4_decompress_safe_forceExtDict(const char* source, char* dest,
int compressedSize, int maxOutputSize,
const void* dictStart, size_t dictSize);
int LZ4_decompress_safe_partial_forceExtDict(const char* source, char* dest,
int compressedSize, int targetOutputSize, int dstCapacity,
const void* dictStart, size_t dictSize);
/*-****************************************
* Obsolete functions, removed from lz4.h (v1.11.0)
* still exported, for programs linked to previous versions
*******************************************/
LZ4LIB_API int LZ4_compress (const char* src, char* dest, int srcSize);
LZ4LIB_API int LZ4_compress_limitedOutput (const char* src, char* dest, int srcSize, int maxOutputSize);
LZ4LIB_API int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize);
LZ4LIB_API int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
LZ4LIB_API int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize);
LZ4LIB_API int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize);
LZ4LIB_API int LZ4_uncompress (const char* source, char* dest, int outputSize);
LZ4LIB_API int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize);
LZ4LIB_API void* LZ4_create (char* inputBuffer);
LZ4LIB_API int LZ4_sizeofStreamState(void);
LZ4LIB_API int LZ4_resetStreamState(void* state, char* inputBuffer);
LZ4LIB_API char* LZ4_slideInputBuffer (void* state);
LZ4LIB_API int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize);
LZ4LIB_API int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize);
/*-******************************
* Compression functions
********************************/
LZ4_FORCE_INLINE U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
{
const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG;
return ((sequence * 2654435761U) >> ((MINMATCH*8)-hashLog));
}
LZ4_FORCE_INLINE U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
{
const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG;
if (LZ4_isLittleEndian()) {
const U64 prime5bytes = 889523592379ULL;
return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog));
} else {
const U64 prime8bytes = 11400714785074694791ULL;
return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog));
}
}
LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType)
{
if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType);
#ifdef LZ4_STATIC_LINKING_ONLY_ENDIANNESS_INDEPENDENT_OUTPUT
return LZ4_hash4(LZ4_readLE32(p), tableType);
#else
return LZ4_hash4(LZ4_read32(p), tableType);
#endif
}
LZ4_FORCE_INLINE void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType)
{
switch (tableType)
{
default: /* fallthrough */
case clearedTable: { /* illegal! */ assert(0); return; }
case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = NULL; return; }
case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = 0; return; }
case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = 0; return; }
}
}
LZ4_FORCE_INLINE void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType)
{
switch (tableType)
{
default: /* fallthrough */
case clearedTable: /* fallthrough */
case byPtr: { /* illegal! */ assert(0); return; }
case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; }
case byU16: { U16* hashTable = (U16*) tableBase; assert(idx < 65536); hashTable[h] = (U16)idx; return; }
}
}
/* LZ4_putPositionOnHash() : only used in byPtr mode */
LZ4_FORCE_INLINE void LZ4_putPositionOnHash(const BYTE* p, U32 h,
void* tableBase, tableType_t const tableType)
{
const BYTE** const hashTable = (const BYTE**)tableBase;
assert(tableType == byPtr); (void)tableType;
hashTable[h] = p;
}
/* LZ4_putPosition() :
* register position p : by pointer (byPtr), or by index relative to base (byU32, byU16) */
LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* base)
{
U32 const h = LZ4_hashPosition(p, tableType);
if (tableType == byPtr) {
LZ4_putPositionOnHash(p, h, tableBase, byPtr);
} else {
LZ4_putIndexOnHash((U32)(p - base), h, tableBase, tableType);
}
}
/* LZ4_getIndexOnHash() :
* Index of match position registered in hash table.
* hash position must be calculated by using base+index, or dictBase+index.
* Assumption 1 : only valid if tableType == byU32 or byU16.
* Assumption 2 : h is presumed valid (within limits of hash table)
*/
LZ4_FORCE_INLINE U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType)
{
LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2);
if (tableType == byU32) {
const U32* const hashTable = (const U32*) tableBase;
assert(h < (1U << (LZ4_MEMORY_USAGE-2)));
return hashTable[h];
}
if (tableType == byU16) {
const U16* const hashTable = (const U16*) tableBase;
assert(h < (1U << (LZ4_MEMORY_USAGE-1)));
return hashTable[h];
}
assert(0); return 0; /* forbidden case */
}
static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType_t tableType)
{
assert(tableType == byPtr); (void)tableType;
{ const BYTE* const* hashTable = (const BYTE* const*) tableBase; return hashTable[h]; }
}
/* beyond this input size (1 KB by default),
* clearing the table is faster than rejecting its stale entries */
#define LZ4_CLEAR_TABLE_THRESHOLD (LZ4_HASHTABLESIZE / 16)
LZ4_FORCE_INLINE void
LZ4_prepareTable(LZ4_stream_t_internal* const cctx,
const int inputSize,
const tableType_t tableType) {
/* If the table hasn't been used, it's guaranteed to be zeroed out, and is
* therefore safe to use no matter what mode we're in. Otherwise, we figure
* out if it's safe to leave as is or whether it needs to be reset.
*/
if ((tableType_t)cctx->tableType != clearedTable) {
assert(inputSize >= 0);
if ((tableType_t)cctx->tableType != tableType
|| ((tableType == byU16) && cctx->currentOffset + (unsigned)inputSize >= 0xFFFFU)
|| ((tableType == byU32) && cctx->currentOffset > 1 GB)
|| tableType == byPtr
|| inputSize >= LZ4_CLEAR_TABLE_THRESHOLD)
{
DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", (void*)cctx);
MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE);
cctx->currentOffset = 0;
cctx->tableType = (U32)clearedTable;
} else {
DEBUGLOG(4, "LZ4_prepareTable: Re-use hash table (no reset)");
}
}
/* Adding a gap, so all previous entries are > LZ4_DISTANCE_MAX back,
* is faster than compressing without a gap.
* However, compressing with currentOffset == 0 is faster still,
* so we preserve that case.
*/
if (cctx->currentOffset != 0 && tableType == byU32) {
DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset");
cctx->currentOffset += 64 KB;
}
/* Finally, clear history */
cctx->dictCtx = NULL;
cctx->dictionary = NULL;
cctx->dictSize = 0;
}
/* LZ4_match8() : the 8 bytes at p and q are equal */
LZ4_FORCE_INLINE int LZ4_match8(const void* p, const void* q)
{
if (sizeof(reg_t) == 8) return LZ4_read_ARCH(p) == LZ4_read_ARCH(q);
return (LZ4_read32(p) == LZ4_read32(q))
&& (LZ4_read32((const BYTE*)p + 4) == LZ4_read32((const BYTE*)q + 4));
}
/* state of an extDict compression which resumes in prefix mode (see LZ4_compress_generic()) */
typedef struct {
const BYTE* ip; /* end of a match : resumes at the test of the next position */
BYTE* op;
U32 startIndex;
} LZ4_resume_t;
/** LZ4_compress_generic_validated() :
* inlined, to ensure branches are decided at compilation time.
* The following conditions are presumed already validated:
* - source != NULL
* - inputSize > 0
*/
LZ4_FORCE_INLINE int LZ4_compress_generic_validated(
LZ4_stream_t_internal* const cctx,
const char* const source,
char* const dest,
const int inputSize,
int* inputConsumed, /* only written when outputDirective == fillOutput */
const int maxOutputSize,
const limitedOutput_directive outputDirective,
const tableType_t tableType,
const dict_directive dictDirective,
const dictIssue_directive dictIssue,
const int acceleration,
LZ4_resume_t* const suspend, /* usingExtDict : stops when the dictionary is out of reach, saving its state */
const LZ4_resume_t* const resume) /* withPrefix64k : resumes such a compression */
{
int result;
const BYTE* ip = resume ? resume->ip : (const BYTE*)source;
U32 const startIndex = resume ? resume->startIndex : cctx->currentOffset;
const BYTE* base = (const BYTE*)source - startIndex;
const BYTE* lowLimit;
const LZ4_stream_t_internal* dictCtx = (const LZ4_stream_t_internal*) cctx->dictCtx;
const BYTE* const dictionary =
dictDirective == usingDictCtx ? dictCtx->dictionary : cctx->dictionary;
const U32 dictSize =
dictDirective == usingDictCtx ? dictCtx->dictSize : cctx->dictSize;
const U32 dictDelta =
(dictDirective == usingDictCtx) ? startIndex - dictCtx->currentOffset : 0; /* make indexes in dictCtx comparable with indexes in current context */
int const maybe_extMem = (dictDirective == usingExtDict) || (dictDirective == usingDictCtx);
U32 const prefixIdxLimit = startIndex - dictSize; /* used when dictDirective == dictSmall */
const BYTE* const dictEnd = dictionary ? dictionary + dictSize : dictionary;
const BYTE* anchor = resume ? resume->ip : (const BYTE*)source;
const BYTE* const iend = (const BYTE*)source + inputSize;
const BYTE* mflimitPlusOne; /* set after the size check : would precede a small input */
const BYTE* matchlimit;
const BYTE* seqLimit; /* suspend : mflimitPlusOne, or earlier, where the dictionary gets out of reach */
/* the dictCtx currentOffset is indexed on the start of the dictionary,
* while a dictionary in the current context precedes the currentOffset */
const BYTE* dictBase = (dictionary == NULL) ? NULL :
(dictDirective == usingDictCtx) ?
dictionary + dictSize - dictCtx->currentOffset :
dictionary + dictSize - startIndex;
BYTE* op = resume ? resume->op : (BYTE*)dest;
BYTE* const olimit = (BYTE*)dest + maxOutputSize;
U32 offset = 0;
U32 forwardH;
const BYTE* filledIp = NULL; /* fillOutput only ; set by catch up (resume : never with fillOutput) */
DEBUGLOG(5, "LZ4_compress_generic_validated: srcSize=%i, tableType=%u", inputSize, tableType);
assert(ip != NULL);
if (tableType == byU16) assert(inputSize<LZ4_64Klimit); /* Size too large (not within 64K limit) */
if (tableType == byPtr) assert(dictDirective==noDict); /* only supported use case with byPtr */
/* If init conditions are not met, we don't have to mark stream
* as having dirty context, since no action was taken yet */
if (outputDirective == fillOutput && maxOutputSize < 1) { return 0; } /* Impossible to store anything */
assert(acceleration >= 1);
/* resume : candidates are within source (see LZ4_compress_generic()) */
lowLimit = (const BYTE*)source - ((dictDirective == withPrefix64k) && !resume ? dictSize : 0);
if (!resume) { /* resume : context state already updated */
/* Update context state */
if (dictDirective == usingDictCtx) {
/* Subsequent linked blocks can't use the dictionary. */
/* Instead, they use the block we just compressed. */
cctx->dictCtx = NULL;
cctx->dictSize = (U32)inputSize;
} else {
cctx->dictSize += (U32)inputSize;
}
cctx->currentOffset += (U32)inputSize;
cctx->tableType = (U32)tableType;
if (inputSize<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */
}
mflimitPlusOne = iend - MFLIMIT + 1;
matchlimit = iend - LASTLITERALS;
seqLimit = mflimitPlusOne;
if ((suspend != NULL) && (inputSize > LZ4_DISTANCE_MAX + MFLIMIT - 1)) /* source + LZ4_DISTANCE_MAX < mflimitPlusOne */
seqLimit = (const BYTE*)source + LZ4_DISTANCE_MAX;
if (resume) goto _resume;
/* First Byte */
LZ4_putPosition(ip, cctx->hashTable, tableType, base);
ip++; forwardH = LZ4_hashPosition(ip, tableType);
/* Main Loop */
for ( ; ; ) {
const BYTE* match;
BYTE* token;
/* Find a match */
if (tableType == byPtr) {
const BYTE* forwardIp = ip;
int step = 1;
int searchMatchNb = acceleration << LZ4_skipTrigger;
do {
U32 const h = forwardH;
ip = forwardIp;
forwardIp += step;
step = (searchMatchNb++ >> LZ4_skipTrigger);
if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;
assert(ip < mflimitPlusOne);
match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType);
forwardH = LZ4_hashPosition(forwardIp, tableType);
LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType);
} while ( (match+LZ4_DISTANCE_MAX < ip)
|| (LZ4_read32(match) != LZ4_read32(ip)) );
} else { /* byU32, byU16 */
const BYTE* forwardIp = ip;
int step = 1;
int searchMatchNb = acceleration << LZ4_skipTrigger;
do {
U32 const h = forwardH;
U32 const current = (U32)(forwardIp - base);
U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
assert(matchIndex <= current);
assert(forwardIp - base < (ptrdiff_t)(2 GB - 1));
ip = forwardIp;
forwardIp += step;
step = (searchMatchNb++ >> LZ4_skipTrigger);
if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;
assert(ip < mflimitPlusOne);
if (dictDirective == usingDictCtx) {
if (matchIndex < startIndex) {
/* there was no match, try the dictionary */
assert(tableType == byU32);
matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
match = dictBase + matchIndex;
matchIndex += dictDelta; /* make dictCtx index comparable with current context */
lowLimit = dictionary;
} else {
match = base + matchIndex;
lowLimit = (const BYTE*)source;
}
} else if (dictDirective == usingExtDict) {
/* select without branch : dictionary and prefix candidates alternate unpredictably.
* relative to dictEnd or source, within their buffers (base can be NULL) */
ptrdiff_t const relIdx = (ptrdiff_t)matchIndex - (ptrdiff_t)startIndex; /* < 0 : within dictionary */
match = ((relIdx < 0) ? dictEnd : (const BYTE*)source) + relIdx;
} else { /* single continuous memory segment */
match = base + matchIndex;
}
forwardH = LZ4_hashPosition(forwardIp, tableType);
LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
DEBUGLOG(7, "candidate at pos=%u (offset=%u \n", matchIndex, current - matchIndex);
if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) { continue; } /* match outside of valid area */
assert(matchIndex < current);
/* noDict : the candidate is within input, so it is compared before checking its distance :
* this order is faster (better branch prediction) */
assert((dictDirective != noDict) || (match >= (const BYTE*)source));
if ( (dictDirective != noDict)
&& ((tableType != byU16) || (LZ4_DISTANCE_MAX < LZ4_DISTANCE_ABSOLUTE_MAX))
&& (matchIndex+LZ4_DISTANCE_MAX < current)) {
continue;
} /* too far */
if (LZ4_read32(match) == LZ4_read32(ip)) {
if ( (dictDirective == noDict)
&& ((tableType != byU16) || (LZ4_DISTANCE_MAX < LZ4_DISTANCE_ABSOLUTE_MAX))
&& (matchIndex+LZ4_DISTANCE_MAX < current)) {
continue;
} /* too far */
assert((current - matchIndex) <= LZ4_DISTANCE_MAX); /* match now expected within distance */
if (maybe_extMem) offset = current - matchIndex;
if (dictDirective == usingExtDict) /* lowLimit : only needed once a match is found */
lowLimit = (matchIndex < startIndex) ? dictionary : (const BYTE*)source;
break; /* match found */
}
} while(1);
}
/* Catch up */
filledIp = ip;
assert(ip > anchor); /* this is always true as ip has been advanced before entering the main loop */
if ((match > lowLimit) && unlikely(ip[-1] == match[-1])) {
do { ip--; match--; } while (((ip > anchor) & (match > lowLimit)) && (unlikely(ip[-1] == match[-1])));
}
/* Encode Literals */
{ unsigned const litLength = (unsigned)(ip - anchor);
token = op++;
if ((outputDirective == limitedOutput) && /* Check output buffer overflow */
(unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)) ) {
return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
}
if ((outputDirective == fillOutput) &&
(unlikely(op + (litLength+240)/255 /* litlen */ + litLength /* literals */ + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit))) {
op--;
goto _last_literals;
}
if (litLength >= RUN_MASK) {
unsigned len = litLength - RUN_MASK;
*token = (RUN_MASK<<ML_BITS);
for(; len >= 255 ; len-=255) *op++ = 255;
*op++ = (BYTE)len;
}
else *token = (BYTE)(litLength<<ML_BITS);
/* Copy Literals */
LZ4_wildCopy8(op, anchor, op+litLength);
op+=litLength;
DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
(int)(anchor-(const BYTE*)source), litLength, (int)(ip-(const BYTE*)source));
}
_next_match:
/* at this stage, the following variables must be correctly set :
* - ip : at start of LZ operation
* - match : at start of previous pattern occurrence; can be within current prefix, or within extDict
* - offset : if maybe_ext_memSegment==1 (constant)
* - lowLimit : must be == dictionary to mean "match is within extDict"; must be == source otherwise
* - token and *token : position to write 4-bits for match length; higher 4-bits for literal length supposed already written
*/
if ((outputDirective == fillOutput) &&
(op + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit)) {
/* the match was too close to the end, rewind and go to last literals */
op = token;
goto _last_literals;
}
/* Encode Offset */
if (maybe_extMem) { /* static test */
DEBUGLOG(6, " with offset=%u (ext if > %i)", offset, (int)(ip - (const BYTE*)source));
assert(offset <= LZ4_DISTANCE_MAX && offset > 0);
LZ4_writeLE16(op, (U16)offset); op+=2;
} else {
DEBUGLOG(6, " with offset=%u (same segment)", (U32)(ip - match));
assert(ip-match <= LZ4_DISTANCE_MAX);
LZ4_writeLE16(op, (U16)(ip - match)); op+=2;
}
/* Encode MatchLength */
{ unsigned matchCode;
if ( (dictDirective==usingExtDict || dictDirective==usingDictCtx)
&& (lowLimit==dictionary) /* match within extDict */ ) {
const BYTE* limit = ip + (dictEnd-match);
assert(dictEnd > match);
if (limit > matchlimit) limit = matchlimit;
matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
ip += (size_t)matchCode + MINMATCH;
if (ip==limit) {
unsigned const more = LZ4_count(limit, (const BYTE*)source, matchlimit);
matchCode += more;
ip += more;
}
DEBUGLOG(6, " with matchLength=%u starting in extDict", matchCode+MINMATCH);
} else {
matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
ip += (size_t)matchCode + MINMATCH;
DEBUGLOG(6, " with matchLength=%u", matchCode+MINMATCH);
}
if ((outputDirective) && /* Check output buffer overflow */
(unlikely(op + (1 + LASTLITERALS) + (matchCode+240)/255 > olimit)) ) {
if (outputDirective == fillOutput) {
/* Match description too long : reduce it */
U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 1 - LASTLITERALS) * 255;
ip -= matchCode - newMatchCode;
assert(newMatchCode < matchCode);
matchCode = newMatchCode;
if (unlikely(ip <= filledIp)) {
/* We have already filled up to filledIp so if ip ends up less than filledIp
* we have positions in the hash table beyond the current position. This is
* a problem if we reuse the hash table. So we have to remove these positions
* from the hash table.
*/
const BYTE* ptr;
DEBUGLOG(5, "Clearing %u positions", (U32)(filledIp - ip));
for (ptr = ip; ptr <= filledIp; ++ptr) {
U32 const h = LZ4_hashPosition(ptr, tableType);
LZ4_clearHash(h, cctx->hashTable, tableType);
}
}
} else {
assert(outputDirective == limitedOutput);
return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
}
}
if (matchCode >= ML_MASK) {
*token += ML_MASK;
matchCode -= ML_MASK;
LZ4_write32(op, 0xFFFFFFFF);
while (matchCode >= 4*255) {
op+=4;
LZ4_write32(op, 0xFFFFFFFF);
matchCode -= 4*255;
}
op += matchCode / 255;
*op++ = (BYTE)(matchCode % 255);
} else
*token += (BYTE)(matchCode);
}
/* Ensure we have enough space for the last literals. */
assert(!(outputDirective == fillOutput && op + 1 + LASTLITERALS > olimit));
anchor = ip;
/* Test end of chunk */
if (ip >= seqLimit) {
if ((suspend == NULL) || (ip >= mflimitPlusOne)) break;
/* extDict : from ip, all candidates (and catch up) are beyond reach of the dictionary :
* stop, to resume in prefix mode, which is faster */
suspend->ip = ip;
suspend->op = op;
suspend->startIndex = startIndex;
return 0;
}
_resume:
/* Fill table, and test next position.
* First, the position after the previous occurrence of ip-1, if it matches 8+ bytes :
* it breaks chains of short matches, which the table alone can produce on periodic data. */
if (tableType == byPtr) {
U32 const hPrev = LZ4_hashPosition(ip-1, tableType);
const BYTE* const prev = LZ4_getPositionOnHash(hPrev, cctx->hashTable, tableType);
U32 const h = LZ4_hashPosition(ip, tableType);
LZ4_putPositionOnHash(ip-1, hPrev, cctx->hashTable, tableType);
match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType);
if ((prev+1+LZ4_DISTANCE_MAX >= ip) && LZ4_match8(prev+1, ip)) match = prev+1;
LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType);
if ( (match+LZ4_DISTANCE_MAX >= ip)
&& (LZ4_read32(match) == LZ4_read32(ip)) )
{ token=op++; *token=0; goto _next_match; }
} else { /* byU32, byU16 */
U32 const h = LZ4_hashPosition(ip, tableType);
U32 const current = (U32)(ip-base);
U32 const hPrev = LZ4_hashPosition(ip-1, tableType);
U32 prevIndex = LZ4_getIndexOnHash(hPrev, cctx->hashTable, tableType);
U32 matchIndex;
LZ4_putIndexOnHash(current-1, hPrev, cctx->hashTable, tableType);
if ((dictDirective == usingDictCtx) && (prevIndex < startIndex)) {
/* no occurrence in the current context : try the dictionary */
prevIndex = LZ4_getIndexOnHash(hPrev, dictCtx->hashTable, byU32) + dictDelta;
}
{ /* used table (small block, see LZ4_prepareTable()) : a stale entry yields the candidate of an empty slot
* of a cleared table (0), the position after the first one : the output doesn't depend on the table's history */
int const usedTable = (dictDirective == noDict) && (dictIssue == dictSmall);
U32 const ctxIndex = ((usedTable && (prevIndex < startIndex)) ? startIndex : prevIndex) + 1;
int const inDict = (dictDirective == usingExtDict || dictDirective == usingDictCtx) && (ctxIndex < startIndex);
if ( ((dictIssue==dictSmall) ? (ctxIndex >= prefixIdxLimit) : 1)
&& (((tableType==byU16) && (LZ4_DISTANCE_MAX == LZ4_DISTANCE_ABSOLUTE_MAX)) ? 1 : (ctxIndex+LZ4_DISTANCE_MAX >= current))
&& (!inDict || (ctxIndex + 8 <= startIndex)) /* the 8 compared bytes are within the dictionary */
&& LZ4_match8(inDict ? dictBase + (ctxIndex - dictDelta) : base + ctxIndex, ip) ) {
matchIndex = ctxIndex;
} else {
matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
if ((dictDirective == usingDictCtx) && (matchIndex < startIndex))
matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32) + dictDelta;
}
}
assert(matchIndex < current);
if (dictDirective == usingExtDict) { /* select without branch */
ptrdiff_t const relIdx = (ptrdiff_t)matchIndex - (ptrdiff_t)startIndex; /* < 0 : within dictionary */
match = ((relIdx < 0) ? dictEnd : (const BYTE*)source) + relIdx;
} else if ((dictDirective == usingDictCtx) && (matchIndex < startIndex)) {
match = dictBase + (matchIndex - dictDelta);
lowLimit = dictionary; /* required for match length counter */
} else {
match = base + matchIndex;
if (dictDirective == usingDictCtx)
lowLimit = (const BYTE*)source; /* required for match length counter */
}
LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
assert(matchIndex < current);
if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1)
&& (((tableType==byU16) && (LZ4_DISTANCE_MAX == LZ4_DISTANCE_ABSOLUTE_MAX)) ? 1 : (matchIndex+LZ4_DISTANCE_MAX >= current))
&& (LZ4_read32(match) == LZ4_read32(ip)) ) {
token=op++;
*token=0;
if (maybe_extMem) offset = current - matchIndex;
if (dictDirective == usingExtDict)
lowLimit = (matchIndex < startIndex) ? dictionary : (const BYTE*)source; /* required for match length counter */
DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
(int)(anchor-(const BYTE*)source), 0, (int)(ip-(const BYTE*)source));
goto _next_match;
}
}
/* Prepare next loop */
forwardH = LZ4_hashPosition(++ip, tableType);
}
_last_literals:
/* Encode Last Literals */
{ size_t lastRun = (size_t)(iend - anchor);
if ( (outputDirective) && /* Check output buffer overflow */
(op + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > olimit)) {
if (outputDirective == fillOutput) {
/* adapt lastRun to fill 'dst' */
assert(olimit >= op);
lastRun = (size_t)(olimit-op) - 1/*token*/;
lastRun -= (lastRun + 256 - RUN_MASK) / 256; /*additional length tokens*/
} else {
assert(outputDirective == limitedOutput);
return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
}
}
DEBUGLOG(6, "Final literal run : %i literals", (int)lastRun);
if (lastRun >= RUN_MASK) {
size_t accumulator = lastRun - RUN_MASK;
*op++ = RUN_MASK << ML_BITS;
for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
*op++ = (BYTE) accumulator;
} else {
*op++ = (BYTE)(lastRun<<ML_BITS);
}
LZ4_memcpy(op, anchor, lastRun);
ip = anchor + lastRun;
op += lastRun;
}
if (outputDirective == fillOutput) {
*inputConsumed = (int) (((const char*)ip)-source);
}
result = (int)(((char*)op) - dest);
assert(result > 0);
DEBUGLOG(5, "LZ4_compress_generic: compressed %i bytes into %i bytes", inputSize, result);
return result;
}
/* second part of an extDict compression, in prefix mode (see LZ4_compress_generic()).
* not inlined : a single instance serves all invocations */
LZ4_FORCE_NOINLINE int LZ4_compress_resumeWithPrefix(LZ4_stream_t_internal* cctx,
const char* src, char* dst, int srcSize, int dstCapacity, int acceleration,
const LZ4_resume_t* state)
{
return LZ4_compress_generic_validated(cctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput,
byU32, withPrefix64k, noDictIssue, acceleration, NULL, state);
}
/** LZ4_compress_generic() :
* inlined, to ensure branches are decided at compilation time;
* takes care of src == (NULL, 0)
* and forward the rest to LZ4_compress_generic_validated */
LZ4_FORCE_INLINE int LZ4_compress_generic(
LZ4_stream_t_internal* const cctx,
const char* const src,
char* const dst,
const int srcSize,
int *inputConsumed, /* only written when outputDirective == fillOutput */
const int dstCapacity,
const limitedOutput_directive outputDirective,
const tableType_t tableType,
const dict_directive dictDirective,
const dictIssue_directive dictIssue,
const int acceleration)
{
DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, dstCapacity=%i",
srcSize, dstCapacity);
if ((U32)srcSize > (U32)LZ4_MAX_INPUT_SIZE) { return 0; } /* Unsupported srcSize, too large (or negative) */
if (srcSize == 0) { /* src == NULL supported if srcSize == 0 */
if (outputDirective != notLimited && dstCapacity <= 0) return 0; /* no output, can't write anything */
DEBUGLOG(5, "Generating an empty block");
assert(outputDirective == notLimited || dstCapacity >= 1);
assert(dst != NULL);
dst[0] = 0;
if (outputDirective == fillOutput) {
assert (inputConsumed != NULL);
*inputConsumed = 0;
}
return 1;
}
assert(src != NULL);
if ((dictDirective == usingExtDict) && (dictIssue == noDictIssue)) {
/* beyond LZ4_DISTANCE_MAX, the dictionary is out of reach : the rest of the input is compressed in prefix mode */
LZ4_resume_t state;
int result;
assert(tableType == byU32);
assert(outputDirective != fillOutput);
state.ip = NULL;
result = LZ4_compress_generic_validated(cctx, src, dst, srcSize, inputConsumed, dstCapacity, outputDirective,
tableType, usingExtDict, noDictIssue, acceleration, &state, NULL);
if (state.ip == NULL) return result; /* completed (or failed) in extDict mode */
/* notLimited : dst is presumed large enough for LZ4_compressBound() */
return LZ4_compress_resumeWithPrefix(cctx, src, dst, srcSize,
(outputDirective == notLimited) ? LZ4_COMPRESSBOUND(srcSize) : dstCapacity,
acceleration, &state);
}
return LZ4_compress_generic_validated(cctx, src, dst, srcSize,
inputConsumed, /* only written into if outputDirective == fillOutput */
dstCapacity, outputDirective,
tableType, dictDirective, dictIssue, acceleration, NULL, NULL);
}
/* values < 1 select the default, values > LZ4_ACCELERATION_MAX are capped */
static int LZ4_clampAcceleration(int acceleration)
{
if (acceleration < 1) return LZ4_ACCELERATION_DEFAULT;
if (acceleration > LZ4_ACCELERATION_MAX) return LZ4_ACCELERATION_MAX;
return acceleration;
}
/* table type for inputs too large for byU16.
* byPtr (32-bit only) requires src > LZ4_DISTANCE_MAX,
* so that empty (NULL) entries are always beyond the maximum distance */
static tableType_t LZ4_largeInputTableType(const char* src)
{
(void)src; /* unused on 64-bit systems */
return ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
}
/* outputDirective must be a compile-time constant */
LZ4_FORCE_INLINE int LZ4_compress_fastReset_generic(
LZ4_stream_t_internal* const ctx,
const char* const src,
char* const dst,
const int srcSize,
const int dstCapacity,
const limitedOutput_directive outputDirective,
const int acceleration)
{
if (srcSize < LZ4_64Klimit) {
LZ4_prepareTable(ctx, srcSize, byU16);
if (ctx->currentOffset) { /* table re-used : stale entries must be rejected */
return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, outputDirective, byU16, noDict, dictSmall, acceleration);
} else {
return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, outputDirective, byU16, noDict, noDictIssue, acceleration);
}
} else {
const tableType_t tableType = LZ4_largeInputTableType(src);
LZ4_prepareTable(ctx, srcSize, tableType);
return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, outputDirective, tableType, noDict, noDictIssue, acceleration);
}
}
int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
{
/* a freshly initialized state is valid for _fastReset() */
LZ4_stream_t* const s = LZ4_initStream(state, sizeof(LZ4_stream_t));
assert(s != NULL);
return LZ4_compress_fast_extState_fastReset(s, source, dest, inputSize, maxOutputSize, acceleration);
}
/**
* LZ4_compress_fast_extState_fastReset() :
* A variant of LZ4_compress_fast_extState().
*
* Using this variant avoids an expensive initialization step. It is only safe
* to call if the state buffer is known to be correctly initialized already
* (see comment in lz4.h on LZ4_resetStream_fast() for a definition of
* "correctly initialized").
*/
int LZ4_compress_fast_extState_fastReset(void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration)
{
LZ4_stream_t_internal* const ctx = &((LZ4_stream_t*)state)->internal_donotuse;
acceleration = LZ4_clampAcceleration(acceleration);
assert(ctx != NULL);
if (dstCapacity >= LZ4_compressBound(srcSize)) {
return LZ4_compress_fastReset_generic(ctx, src, dst, srcSize, 0, notLimited, acceleration);
} else {
return LZ4_compress_fastReset_generic(ctx, src, dst, srcSize, dstCapacity, limitedOutput, acceleration);
}
}
int LZ4_compress_fast(const char* src, char* dest, int srcSize, int dstCapacity, int acceleration)
{
int result;
#if (LZ4_HEAPMODE)
LZ4_stream_t* const ctxPtr = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */
if (ctxPtr == NULL) return 0;
#else
LZ4_stream_t ctx;
LZ4_stream_t* const ctxPtr = &ctx;
#endif
result = LZ4_compress_fast_extState(ctxPtr, src, dest, srcSize, dstCapacity, acceleration);
#if (LZ4_HEAPMODE)
FREEMEM(ctxPtr);
#endif
return result;
}
int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity)
{
return LZ4_compress_fast(src, dst, srcSize, dstCapacity, 1);
}
/* Note!: This function leaves the stream in an unclean/broken state!
* It is not safe to subsequently use the same state with a _fastReset() or
* _continue() call without resetting it. */
static int LZ4_compress_destSize_extState_internal(LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize, int acceleration)
{
void* const s = LZ4_initStream(state, sizeof (*state));
assert(s != NULL); (void)s;
acceleration = LZ4_clampAcceleration(acceleration);
if (targetDstSize >= LZ4_compressBound(*srcSizePtr)) { /* compression success is guaranteed */
return LZ4_compress_fast_extState_fastReset(state, src, dst, *srcSizePtr, targetDstSize, acceleration);
} else {
if (*srcSizePtr < LZ4_64Klimit) {
return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, byU16, noDict, noDictIssue, acceleration);
} else {
return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, LZ4_largeInputTableType(src), noDict, noDictIssue, acceleration);
} }
}
int LZ4_compress_destSize_extState(void* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize, int acceleration)
{
int const r = LZ4_compress_destSize_extState_internal((LZ4_stream_t*)state, src, dst, srcSizePtr, targetDstSize, acceleration);
/* clean the state on exit */
LZ4_initStream(state, sizeof (LZ4_stream_t));
return r;
}
int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize)
{
int result;
#if (LZ4_HEAPMODE)
LZ4_stream_t* const ctx = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */
if (ctx == NULL) return 0;
#else
LZ4_stream_t ctxBody;
LZ4_stream_t* const ctx = &ctxBody;
#endif
result = LZ4_compress_destSize_extState_internal(ctx, src, dst, srcSizePtr, targetDstSize, 1);
#if (LZ4_HEAPMODE)
FREEMEM(ctx);
#endif
return result;
}
/*-******************************
* Streaming functions
********************************/
#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
LZ4_stream_t* LZ4_createStream(void)
{
LZ4_stream_t* const lz4s = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));
LZ4_STATIC_ASSERT(sizeof(LZ4_stream_t) >= sizeof(LZ4_stream_t_internal));
DEBUGLOG(4, "LZ4_createStream %p", (void*)lz4s);
if (lz4s == NULL) return NULL;
LZ4_initStream(lz4s, sizeof(*lz4s));
return lz4s;
}
#endif
static size_t LZ4_stream_t_alignment(void)
{
#if LZ4_ALIGN_TEST
typedef struct { char c; LZ4_stream_t t; } t_a;
return sizeof(t_a) - sizeof(LZ4_stream_t);
#else
return 1; /* effectively disabled */
#endif
}
LZ4_stream_t* LZ4_initStream (void* buffer, size_t size)
{
DEBUGLOG(5, "LZ4_initStream");
if (buffer == NULL) { return NULL; }
if (size < sizeof(LZ4_stream_t)) { return NULL; }
if (!LZ4_isAligned(buffer, LZ4_stream_t_alignment())) return NULL;
MEM_INIT(buffer, 0, sizeof(LZ4_stream_t_internal));
return (LZ4_stream_t*)buffer;
}
/* resetStream is now deprecated,
* prefer initStream() which is more general */
void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
{
DEBUGLOG(5, "LZ4_resetStream (ctx:%p)", (void*)LZ4_stream);
MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t_internal));
}
void LZ4_resetStream_fast(LZ4_stream_t* ctx) {
LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32);
}
#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
{
if (!LZ4_stream) return 0; /* support free on NULL */
DEBUGLOG(5, "LZ4_freeStream %p", (void*)LZ4_stream);
FREEMEM(LZ4_stream);
return (0);
}
#endif
typedef enum { _ld_fast, _ld_slow } LoadDict_mode_e;
#define HASH_UNIT sizeof(reg_t)
static int LZ4_loadDict_internal(LZ4_stream_t* LZ4_dict,
const char* dictionary, int dictSize,
LoadDict_mode_e _ld)
{
LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse;
const tableType_t tableType = byU32;
const BYTE* p = (const BYTE*)dictionary;
const BYTE* const dictEnd = p + dictSize;
U32 idx32;
DEBUGLOG(4, "LZ4_loadDict (%i bytes from %p into %p)", dictSize, (void*)dictionary, (void*)LZ4_dict);
/* It's necessary to reset the context,
* and not just continue it with prepareTable()
* to avoid any risk of generating overflowing matchIndex
* when compressing using this dictionary */
LZ4_resetStream(LZ4_dict);
/* We always increment the offset by 64 KB, since, if the dict is longer,
* we truncate it to the last 64k, and if it's shorter, we still want to
* advance by a whole window length so we can provide the guarantee that
* there are only valid offsets in the window, which allows an optimization
* in LZ4_compress_fast_continue() where it uses noDictIssue even when the
* dictionary isn't a full 64k. */
dict->currentOffset += 64 KB;
/* no longer a cleared table : LZ4_prepareTable() must check it,
* even when the dictionary is too small to be used */
dict->tableType = (U32)tableType;
if (dictSize < (int)HASH_UNIT) {
return 0;
}
if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB;
dict->dictionary = p;
dict->dictSize = (U32)(dictEnd - p);
idx32 = dict->currentOffset - dict->dictSize;
while (p <= dictEnd-HASH_UNIT) {
U32 const h = LZ4_hashPosition(p, tableType);
/* Note: overwriting => favors positions end of dictionary */
LZ4_putIndexOnHash(idx32, h, dict->hashTable, tableType);
p+=3; idx32+=3;
}
if (_ld == _ld_slow) {
/* Fill hash table with additional references, to improve compression capability */
p = dict->dictionary;
idx32 = dict->currentOffset - dict->dictSize;
while (p <= dictEnd-HASH_UNIT) {
U32 const h = LZ4_hashPosition(p, tableType);
U32 const limit = dict->currentOffset - 64 KB;
if (LZ4_getIndexOnHash(h, dict->hashTable, tableType) <= limit) {
/* Note: not overwriting => favors positions beginning of dictionary */
LZ4_putIndexOnHash(idx32, h, dict->hashTable, tableType);
}
p++; idx32++;
}
}
return (int)dict->dictSize;
}
int LZ4_loadDict(LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
{
return LZ4_loadDict_internal(LZ4_dict, dictionary, dictSize, _ld_fast);
}
int LZ4_loadDictSlow(LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
{
return LZ4_loadDict_internal(LZ4_dict, dictionary, dictSize, _ld_slow);
}
void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream)
{
const LZ4_stream_t_internal* dictCtx = (dictionaryStream == NULL) ? NULL :
&(dictionaryStream->internal_donotuse);
DEBUGLOG(4, "LZ4_attach_dictionary (%p, %p, size %u)",
(void*)workingStream, (void*)dictionaryStream,
dictCtx != NULL ? dictCtx->dictSize : 0);
if (dictCtx != NULL) {
/* If the current offset is zero, we will never look in the
* external dictionary context, since there is no value a table
* entry can take that indicate a miss. In that case, we need
* to bump the offset to something non-zero.
*/
if (workingStream->internal_donotuse.currentOffset == 0) {
workingStream->internal_donotuse.currentOffset = 64 KB;
/* no longer a cleared table : LZ4_prepareTable() must check it */
workingStream->internal_donotuse.tableType = (U32)byU32;
}
/* Don't actually attach an empty dictionary.
*/
if (dictCtx->dictSize == 0) {
dictCtx = NULL;
}
}
workingStream->internal_donotuse.dictCtx = dictCtx;
}
static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, int nextSize)
{
assert(nextSize >= 0);
if (LZ4_dict->currentOffset + (unsigned)nextSize > 0x80000000) { /* potential ptrdiff_t overflow (32-bits mode) */
/* rescale hash table */
U32 const delta = LZ4_dict->currentOffset - 64 KB;
const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
int i;
DEBUGLOG(4, "LZ4_renormDictT");
for (i=0; i<LZ4_HASH_SIZE_U32; i++) {
if (LZ4_dict->hashTable[i] < delta) LZ4_dict->hashTable[i]=0;
else LZ4_dict->hashTable[i] -= delta;
}
LZ4_dict->currentOffset = 64 KB;
if (LZ4_dict->dictSize > 64 KB) LZ4_dict->dictSize = 64 KB;
LZ4_dict->dictionary = dictEnd - LZ4_dict->dictSize;
}
}
/* The history covers neither the full window (64 KB) nor all positions since the start of indexes :
* the table may contain stale entries, from before the history, which must be rejected (dictSmall). */
static int LZ4_isDictSmall(const LZ4_stream_t_internal* streamPtr)
{
return (streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset);
}
/* from this input size (2 KB by default, at most 4 KB),
* copying the tables of an attached dictionary is faster than looking into both tables.
* The copy cost follows the table size. */
#define LZ4_DICTCTX_COPY_THRESHOLD ((LZ4_HASHTABLESIZE / 8 < 4 KB) ? (LZ4_HASHTABLESIZE / 8) : 4 KB)
int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream,
const char* source, char* dest,
int inputSize, int maxOutputSize,
int acceleration)
{
const tableType_t tableType = byU32;
LZ4_stream_t_internal* const streamPtr = &LZ4_stream->internal_donotuse;
const char* dictEnd = streamPtr->dictSize ? (const char*)streamPtr->dictionary + streamPtr->dictSize : NULL;
DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i, dictSize=%u)", inputSize, streamPtr->dictSize);
/* new stream (no history) : clear the table beyond LZ4_CLEAR_TABLE_THRESHOLD */
if ((streamPtr->dictSize == 0) && (streamPtr->dictCtx == NULL) && (inputSize >= LZ4_CLEAR_TABLE_THRESHOLD))
LZ4_prepareTable(streamPtr, inputSize, byU32);
LZ4_renormDictT(streamPtr, inputSize); /* fix index overflow */
acceleration = LZ4_clampAcceleration(acceleration);
/* invalidate tiny dictionaries */
if ( (streamPtr->dictSize < 4) /* tiny dictionary : not enough for a hash */
&& (dictEnd != source) /* prefix mode */
&& (inputSize > 0) /* tolerance : don't lose history, in case next invocation would use prefix mode */
&& (streamPtr->dictCtx == NULL) /* usingDictCtx */
) {
DEBUGLOG(5, "LZ4_compress_fast_continue: dictSize(%u) at addr:%p is too small", streamPtr->dictSize, (void*)streamPtr->dictionary);
/* remove dictionary existence from history, to employ faster prefix mode */
streamPtr->dictSize = 0;
streamPtr->dictionary = (const BYTE*)source;
dictEnd = source;
}
/* Check overlapping input/dictionary space */
{ const char* const sourceEnd = source + inputSize;
if ((sourceEnd > (const char*)streamPtr->dictionary) && (source < dictEnd)) {
/* only the part of the dictionary beyond input remains */
streamPtr->dictSize = (sourceEnd < dictEnd) ? (U32)(dictEnd - sourceEnd) : 0;
if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB;
if (streamPtr->dictSize < 4) streamPtr->dictSize = 0;
streamPtr->dictionary = (const BYTE*)dictEnd - streamPtr->dictSize;
}
}
/* prefix mode : source data follows dictionary */
if (dictEnd == source) {
if (LZ4_isDictSmall(streamPtr))
return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration);
else
return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, noDictIssue, acceleration);
}
/* external dictionary mode */
{ int result;
if (streamPtr->dictCtx) {
/* We depend here on the fact that dictCtx'es (produced by
* LZ4_loadDict) guarantee that their tables contain no references
* to offsets between dictCtx->currentOffset - 64 KB and
* dictCtx->currentOffset - dictCtx->dictSize. This makes it safe
* to use noDictIssue even when the dict isn't a full 64 KB.
*/
if (inputSize >= LZ4_DICTCTX_COPY_THRESHOLD) {
/* For compressing large blobs, it is faster to pay the setup
* cost to copy the dictionary's tables into the active context,
* so that the compression loop is only looking into one table.
*/
LZ4_memcpy(streamPtr, streamPtr->dictCtx, sizeof(*streamPtr));
result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
} else {
result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration);
}
} else { /* external dictionary in the current context */
if (LZ4_isDictSmall(streamPtr)) {
result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration);
} else {
result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
}
}
streamPtr->dictionary = (const BYTE*)source;
streamPtr->dictSize = (U32)inputSize;
return result;
}
}
/* Hidden debug function, to force-test external dictionary mode */
int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize)
{
LZ4_stream_t_internal* const streamPtr = &LZ4_dict->internal_donotuse;
int result;
LZ4_renormDictT(streamPtr, srcSize);
if (LZ4_isDictSmall(streamPtr)) {
result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, dictSmall, 1);
} else {
result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
}
streamPtr->dictionary = (const BYTE*)source;
streamPtr->dictSize = (U32)srcSize;
return result;
}
/*! LZ4_saveDict() :
* If previously compressed data block is not guaranteed to remain available at its memory location,
* save it into a safer place (char* safeBuffer).
* Note : no need to call LZ4_loadDict() afterwards, dictionary is immediately usable,
* one can therefore call LZ4_compress_fast_continue() right after.
* @return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error.
*/
int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
{
LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse;
DEBUGLOG(5, "LZ4_saveDict : dictSize=%i, safeBuffer=%p", dictSize, (void*)safeBuffer);
if (dictSize < 0) dictSize = 0; /* invalid : save nothing, like LZ4_saveDictHC() */
if ((U32)dictSize > 64 KB) { dictSize = 64 KB; } /* useless to define a dictionary > 64 KB */
if ((U32)dictSize > dict->dictSize) { dictSize = (int)dict->dictSize; }
if (safeBuffer == NULL) assert(dictSize == 0);
if (dictSize > 0) {
const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize;
assert(dict->dictionary);
LZ4_memmove(safeBuffer, previousDictEnd - dictSize, (size_t)dictSize);
}
dict->dictionary = (const BYTE*)safeBuffer;
dict->dictSize = (U32)dictSize;
return dictSize;
}
/*-*******************************
* Decompression functions
********************************/
typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive;
#undef MIN
#define MIN(a,b) ( (a) < (b) ? (a) : (b) )
/* variant for decompress_unsafe()
* does not know end of input
* presumes input is well formed
* note : will consume at least one byte */
static size_t read_long_length_no_check(const BYTE** pp)
{
size_t b, l = 0;
do { b = **pp; (*pp)++; l += b; } while (b==255);
DEBUGLOG(6, "read_long_length_no_check: +length=%zu using %zu input bytes", l, l/255 + 1)
return l;
}
/* core decoder variant for LZ4_decompress_fast*()
* for legacy support only : these entry points are deprecated.
* - Presumes input is correctly formed (no defense vs malformed inputs)
* - Does not know input size (presume input buffer is "large enough")
* - Decompress a full block (only)
* @return : nb of bytes read from input.
* Note : this variant is not optimized for speed, just for maintenance.
* the goal is to remove support of decompress_fast*() variants by v2.0
**/
LZ4_FORCE_INLINE int
LZ4_decompress_unsafe_generic(
const BYTE* const istart,
BYTE* const ostart,
int decompressedSize,
size_t prefixSize,
const BYTE* const dictStart, /* only if dict==usingExtDict */
const size_t dictSize /* note: =0 if dictStart==NULL */
)
{
const BYTE* ip = istart;
BYTE* op = (BYTE*)ostart;
BYTE* oend;
const BYTE* const prefixStart = ostart - prefixSize;
DEBUGLOG(5, "LZ4_decompress_unsafe_generic");
if (dictStart == NULL) assert(dictSize == 0);
if (decompressedSize < 0) return -1;
oend = ostart + decompressedSize;
while (1) {
/* start new sequence */
unsigned token = *ip++;
/* literals */
{ size_t ll = token >> ML_BITS;
if (ll==15) {
/* long literal length */
ll += read_long_length_no_check(&ip);
}
if ((size_t)(oend-op) < ll) return -1; /* output buffer overflow */
LZ4_memmove(op, ip, ll); /* support in-place decompression */
op += ll;
ip += ll;
if ((size_t)(oend-op) < MFLIMIT) {
if (op==oend) break; /* end of block */
DEBUGLOG(5, "invalid: literals end at distance %zi from end of block", oend-op);
/* incorrect end of block :
* last match must start at least MFLIMIT==12 bytes before end of output block */
return -1;
} }
/* match */
{ size_t ml = token & 15;
size_t const offset = LZ4_readLE16(ip);
ip+=2;
if (ml==15) {
/* long literal length */
ml += read_long_length_no_check(&ip);
}
ml += MINMATCH;
if ((size_t)(oend-op) < ml) return -1; /* output buffer overflow */
{ const BYTE* match = op - offset;
/* out of range */
if (offset > (size_t)(op - prefixStart) + dictSize) {
DEBUGLOG(6, "offset out of range");
return -1;
}
/* check special case : extDict */
if (offset > (size_t)(op - prefixStart)) {
/* extDict scenario */
const BYTE* const dictEnd = dictStart + dictSize;
const BYTE* extMatch = dictEnd - (offset - (size_t)(op-prefixStart));
size_t const extml = (size_t)(dictEnd - extMatch);
if (extml > ml) {
/* match entirely within extDict */
LZ4_memmove(op, extMatch, ml);
op += ml;
ml = 0;
} else {
/* match split between extDict & prefix */
LZ4_memmove(op, extMatch, extml);
op += extml;
ml -= extml;
}
match = prefixStart;
}
/* match copy - slow variant, supporting overlap copy */
{ size_t u;
for (u=0; u<ml; u++) {
op[u] = match[u];
} } }
op += ml;
if ((size_t)(oend-op) < LASTLITERALS) {
DEBUGLOG(5, "invalid: match ends at distance %zi from end of block", oend-op);
/* incorrect end of block :
* last match must stop at least LASTLITERALS==5 bytes before end of output block */
return -1;
}
} /* match */
} /* main loop */
return (int)(ip - istart);
}
/* Read the variable-length literal or match length.
*
* @ipPtr : pointer to input pointer, will be advanced
* @ilimit : read is forbidden beyond this position (must be within input buffer)
**/
typedef size_t Rvl_t;
static const Rvl_t rvl_error = (Rvl_t)(-1);
LZ4_FORCE_INLINE Rvl_t
read_variable_length(const BYTE** ipPtr, const BYTE* ilimit)
{
Rvl_t s, length = 0;
assert(ipPtr != NULL);
assert(*ipPtr != NULL);
assert(ilimit != NULL);
if (unlikely((*ipPtr) >= ilimit)) { /* read limit reached */
return rvl_error;
}
s = **ipPtr;
(*ipPtr)++;
length += s;
if (likely(s != 255)) return length;
do {
if (unlikely((*ipPtr) >= ilimit)) { /* read limit reached */
return rvl_error;
}
s = **ipPtr;
(*ipPtr)++;
length += s;
/* accumulator overflow detection (32-bit mode only) */
if ((sizeof(length) < 8) && unlikely(length > ((Rvl_t)(-1)/2)) ) {
return rvl_error;
}
} while (s == 255);
return length;
}
/* LZ4_copyMatchExact() :
* copy a match of length bytes from match to op (match < op, overlap allowed),
* writing nothing beyond op+length. Invalid offset 0 (match == op) produces 0 bytes.
* Not inlined : rarely used, its memcpy() calls would burden the decoder's hot loops.
* @return : output position after the match */
LZ4_FORCE_NOINLINE BYTE*
LZ4_copyMatchExact(BYTE* op, const BYTE* match, size_t length)
{
if (unlikely(match == op)) { /* invalid offset 0 : clear the match segment, see doc/lz4_Block_format.md */
MEM_INIT(op, 0, length);
return op + length;
}
/* bytes from match to op repeat with period (op-match) :
* copy all of them, so the distance doubles at each round.
* Beyond 2 KB, keep the distance : larger copies of just written data are slower */
while (length > (size_t)(op - match)) {
size_t const available = (size_t)(op - match);
LZ4_memcpy(op, match, available);
op += available;
length -= available;
if (available >= 2048) match += available;
}
LZ4_memcpy(op, match, length);
return op + length;
}
/* LZ4_copyExtDictMatch() :
* copy a match starting within the external dictionary (match < lowPrefix),
* possibly stretching into the current block.
* @return : output position after the match */
LZ4_FORCE_INLINE BYTE*
LZ4_copyExtDictMatch(BYTE* op, const BYTE* match, size_t length,
const BYTE* lowPrefix, const BYTE* dictEnd)
{
if (length <= (size_t)(lowPrefix-match)) {
/* match fits entirely within external dictionary : just copy */
LZ4_memmove(op, dictEnd - (lowPrefix-match), length);
return op + length;
} else {
/* match stretches into both external dictionary and current block */
size_t const copySize = (size_t)(lowPrefix - match);
LZ4_memcpy(op, dictEnd - copySize, copySize);
return LZ4_copyMatchExact(op + copySize, lowPrefix, length - copySize);
}
}
/*! LZ4_decompress_generic() :
* This generic decompression function covers all use cases.
* It shall be instantiated several times, using different sets of directives.
* Note that it is important for performance that this function really get inlined,
* in order to remove useless branches during compilation optimization.
*/
LZ4_FORCE_INLINE int
LZ4_decompress_generic(
const char* const src,
char* const dst,
int srcSize,
int outputSize, /* dstCapacity, or MIN(targetOutputSize, dstCapacity) when partialDecoding */
earlyEnd_directive partialDecoding, /* full, partial */
dict_directive dict, /* noDict, withPrefix64k, usingExtDict */
const BYTE* const lowPrefix, /* always <= dst, == dst when no prefix */
const BYTE* const dictStart, /* only if dict==usingExtDict */
const size_t dictSize /* note : = 0 if noDict */
)
{
if ((src == NULL) || (outputSize < 0)) { return -1; }
{ const BYTE* ip = (const BYTE*) src;
const BYTE* const iend = ip + srcSize;
BYTE* op = (BYTE*) dst;
BYTE* const oend = op + outputSize;
const BYTE* const dictEnd = (dictStart == NULL) ? NULL : dictStart + dictSize;
/* withPrefix64k : offset <= 65535 can't reach beyond the 64 KB prefix */
const int checkOffset = (dict != withPrefix64k) && (dictSize < (int)(64 KB));
/* Set up the "end" pointers for the shortcut. */
const BYTE* const shortiend = iend - 14 /*maxLL*/ - 2 /*offset*/;
const BYTE* const shortoend = oend - 14 /*maxLL*/ - 18 /*maxML*/;
/* shared by both loops : the fast loop can hand over a decoded match (safe_match_copy) */
const BYTE* match;
size_t offset;
size_t ml; /* match length */
DEBUGLOG(5, "LZ4_decompress_generic (srcSize:%i, dstSize:%i)", srcSize, outputSize);
/* Special cases */
assert(lowPrefix <= op);
if (unlikely(outputSize==0)) {
/* Empty output buffer */
if (partialDecoding) return 0;
if ((srcSize==1) && (*ip==0)) return 0; /* empty block */
return (srcSize > 1) ? -2 : -1; /* -2 : output buffer too small */
}
if (unlikely(srcSize<=0)) { return -1; }
/* LZ4_FAST_DEC_LOOP:
* designed for modern OoO performance cpus,
* where copying reliably 32-bytes is preferable to an unpredictable branch.
* note : fast loop may show a regression for some client arm chips. */
#if LZ4_FAST_DEC_LOOP
if ((oend - op) < FASTLOOP_SAFE_DISTANCE) {
DEBUGLOG(6, "move to safe decode loop");
goto safe_decode;
}
/* Ring buffer restarting at its beginning : the oldest referenced history (max distance behind op)
* lies in the external dictionary, ahead of op, always at the same distance.
* Rings sized with the former LZ4_DECODER_RING_BUFFER_SIZE() (margin 14, up to v1.10.0)
* still work, but leave as little as 16 bytes :
* the fast loop's wide copies could overwrite it, the safe loop's can't. */
if ( (dict==usingExtDict)
&& ((uptrval)dictEnd - (uptrval)lowPrefix - LZ4_DISTANCE_ABSOLUTE_MAX < FASTLOOP_SAFE_DISTANCE) ) {
DEBUGLOG(6, "history just ahead : move to safe decode loop");
goto safe_decode;
}
/* Fast loop : decode sequences as long as output < oend-FASTLOOP_SAFE_DISTANCE,
* and input is not too close to iend.
* It hands over to the safe loop either at a sequence start (break),
* or once a match is fully decoded (goto safe_match_copy). */
DEBUGLOG(6, "using fast decode loop");
while (1) {
unsigned token;
size_t ll; /* literal length */
BYTE* cpy;
/* Main fastloop assertion: We can always wildcopy FASTLOOP_SAFE_DISTANCE */
assert(oend - op >= FASTLOOP_SAFE_DISTANCE);
assert(ip < iend);
token = *ip++;
ll = token >> ML_BITS;
DEBUGLOG(7, "blockPos%6u: litLength token = %u", (unsigned)(op-(BYTE*)dst), (unsigned)ll);
/* too close to input end : the safe loop restarts this sequence */
if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) { ip--; break; }
/* decode literal length */
if (ll == RUN_MASK) {
/* literal length >= RUN_MASK means >= RUN_MASK literal bytes follow the extension bytes,
* so extension bytes cannot reach the last RUN_MASK bytes of input */
const BYTE* const tokenPos = ip-1;
size_t const addl = read_variable_length(&ip, iend - RUN_MASK);
if (addl == rvl_error) {
DEBUGLOG(6, "error reading long literal length");
goto _output_error;
}
ll += addl;
if (unlikely((uptrval)(op)+ll<(uptrval)(op))) { goto _output_error; } /* overflow detection */
if (unlikely((uptrval)(ip)+ll<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
/* copy literals, unless too close to the end for a wild copy :
* nothing is written yet, so the safe loop can restart this sequence */
cpy = op+ll;
LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
#if LZ4_WILDCOPY64
if ((cpy>oend-64) || (ip+ll>iend-64)) { ip = tokenPos; break; }
LZ4_wildCopy64(op, ip, cpy);
#else
if ((cpy>oend-32) || (ip+ll>iend-32)) { ip = tokenPos; break; }
LZ4_wildCopy32(op, ip, cpy);
#endif
ip += ll; op = cpy;
} else {
DEBUGLOG(7, "copy %u bytes in a 16-bytes stripe", (unsigned)ll);
/* Literals can only be <= 14, but hope compilers optimize better when copy by a register size */
LZ4_memcpy(op, ip, 16);
ip += ll; op += ll;
}
/* get offset */
offset = LZ4_readLE16(ip); ip+=2;
DEBUGLOG(6, "blockPos%6u: offset = %u", (unsigned)(op-(BYTE*)dst), (unsigned)offset);
match = op - offset;
assert(match <= op); /* overflow check */
/* get matchlength */
ml = token & ML_MASK;
DEBUGLOG(7, " match length token = %u (len==%u)", (unsigned)ml, (unsigned)ml+MINMATCH);
if (ml == ML_MASK) {
/* after match length extension bytes, at least 1 token + LASTLITERALS literals must remain */
size_t const addl = read_variable_length(&ip, iend - (1 + LASTLITERALS));
if (addl == rvl_error) {
DEBUGLOG(5, "error reading long match length");
goto _output_error;
}
ml += addl;
DEBUGLOG(7, " long match length == %u", (unsigned)ml + MINMATCH);
if (unlikely((uptrval)(op)+ml<(uptrval)op)) { goto _output_error; } /* overflow detection */
}
ml += MINMATCH;
if (op + ml >= oend - FASTLOOP_SAFE_DISTANCE) {
DEBUGLOG(7, "moving to safe_match_copy (ml==%u)", (unsigned)ml);
goto safe_match_copy;
}
/* match length from token only (<= 18), no overlap, within prefix : copy 18 bytes */
if ( ((token & ML_MASK) != ML_MASK) && (offset >= 8)
&& ((dict == withPrefix64k) || (match >= lowPrefix)) ) {
assert(match >= lowPrefix);
assert(match <= op);
assert(op + 18 <= oend);
LZ4_memcpy(op, match, 8);
LZ4_memcpy(op+8, match+8, 8);
LZ4_memcpy(op+16, match+16, 2);
op += ml;
continue;
}
/* match ends far from oend : no end-of-block condition to check */
assert(op + ml < oend - FASTLOOP_SAFE_DISTANCE);
if ( checkOffset && (unlikely(match + dictSize < lowPrefix)) ) {
DEBUGLOG(5, "Error : pos=%zi, offset=%zi => outside buffers", op-lowPrefix, op-match);
goto _offset_error;
}
/* match starting within external dictionary */
if ((dict==usingExtDict) && (match < lowPrefix)) {
assert(dictEnd != NULL);
op = LZ4_copyExtDictMatch(op, match, ml, lowPrefix, dictEnd);
continue;
}
/* copy match within block */
cpy = op + ml;
assert((op <= oend) && (oend-op >= 64));
if (unlikely(offset<16)) {
LZ4_memcpy_using_offset(op, match, cpy, offset);
#if LZ4_WILDCOPY64
} else if (offset >= 64) {
LZ4_wildCopy64(op, match, cpy);
#endif
} else {
LZ4_wildCopy32(op, match, cpy);
}
op = cpy; /* wildcopy correction */
}
safe_decode:
#endif
/* Safe loop : decode remaining sequences, without writing beyond oend nor reading beyond iend.
* With LZ4_FAST_DEC_LOOP, that's the end of the block (or a block too small for the fast loop),
* entered at a sequence start, or at safe_match_copy with a decoded match.
* Without it, that's the whole block. */
DEBUGLOG(6, "using safe decode loop");
while (1) {
unsigned token;
size_t ll; /* literal length */
BYTE* cpy;
assert(ip < iend);
token = *ip++;
ll = token >> ML_BITS;
DEBUGLOG(7, "blockPos%6u: litLength token = %u", (unsigned)(op-(BYTE*)dst), (unsigned)ll);
/* A two-stage shortcut for the most common case:
* 1) If the literal length is 0..14, and there is enough space,
* enter the shortcut and copy 16 bytes on behalf of the literals.
* 2) Further if the match length is 4..18, copy 18 bytes in a similar
* manner; but we ensure that there's enough space in the output for
* those 18 bytes earlier, upon entering the shortcut (in other words,
* there is a combined check for both stages).
*/
if ( (ll != RUN_MASK)
/* strictly "less than" on input, to re-enter the loop with at least one byte */
&& likely((ip < shortiend) & (op <= shortoend)) ) {
/* Copy the literals */
LZ4_memcpy(op, ip, 16);
op += ll; ip += ll;
/* The second stage: prepare for match copying, decode full info.
* If it doesn't work out, the info won't be wasted. */
offset = LZ4_readLE16(ip); ip += 2;
match = op - offset;
assert(match <= op); /* check overflow */
ml = token & ML_MASK;
DEBUGLOG(7, "blockPos%6u: matchLength token = %u (len=%u)", (unsigned)(op-(BYTE*)dst), (unsigned)ml, (unsigned)ml + 4);
/* Do not deal with overlapping matches. */
if ( (ml != ML_MASK)
&& (offset >= 8)
&& (dict==withPrefix64k || match >= lowPrefix) ) {
/* Copy the match. */
LZ4_memcpy(op + 0, match + 0, 8);
LZ4_memcpy(op + 8, match + 8, 8);
LZ4_memcpy(op +16, match +16, 2);
op += ml + MINMATCH;
/* Both stages worked, load the next token. */
continue;
}
/* The second stage didn't work out, but the info is ready for the match copy below. */
} else {
/* decode literal length */
if (ll == RUN_MASK) {
/* literal length >= RUN_MASK means >= RUN_MASK literal bytes follow the extension bytes,
* so extension bytes cannot reach the last RUN_MASK bytes of input */
size_t const addl = read_variable_length(&ip, iend-RUN_MASK);
if (addl == rvl_error) { goto _output_error; }
ll += addl;
if (unlikely((uptrval)(op)+ll<(uptrval)(op))) { goto _output_error; } /* overflow detection */
if (unlikely((uptrval)(ip)+ll<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
}
/* copy literals */
cpy = op+ll;
LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
if ((cpy>oend-MFLIMIT) || (ip+ll>iend-(2+1+LASTLITERALS))) {
/* close to input or output end : these must be the last literals of the block,
* except with partialDecoding, which can also stop within them */
if (partialDecoding) {
/* stop at input end, or when output is full */
ll = MIN(ll, (size_t)(iend-ip));
ll = MIN(ll, (size_t)(oend-op));
} else if ((ip+ll != iend) || (cpy > oend)) {
/* last literals must end exactly at input end, within output */
DEBUGLOG(5, "invalid last literals : they end at iend%+zi and oend%+zi", (ip+ll)-iend, cpy-oend);
if ((ip+ll <= iend) && (cpy > oend-MFLIMIT)) goto _dst_too_small; /* output full, input left */
goto _output_error;
}
LZ4_memmove(op, ip, ll); /* supports overlapping memory regions, for in-place decompression scenarios */
ip += ll;
op += ll;
/* end of block, unless partialDecoding can go on : output not full, input left for a match */
if (!partialDecoding || (op == oend) || (ip >= (iend-2))) {
break;
}
} else {
LZ4_wildCopy8(op, ip, cpy); /* can overwrite up to 8 bytes beyond cpy */
ip += ll; op = cpy;
}
/* get offset */
offset = LZ4_readLE16(ip); ip+=2;
match = op - offset;
/* get matchlength */
ml = token & ML_MASK;
DEBUGLOG(7, "blockPos%6u: matchLength token = %u", (unsigned)(op-(BYTE*)dst), (unsigned)ml);
}
/* literals copied, offset decoded, ml == match length token */
if (ml == ML_MASK) {
/* after match length extension bytes, at least 1 token + LASTLITERALS literals must remain */
size_t const addl = read_variable_length(&ip, iend - (1 + LASTLITERALS));
if (addl == rvl_error) { goto _output_error; }
ml += addl;
if (unlikely((uptrval)(op)+ml<(uptrval)op)) goto _output_error; /* overflow detection */
}
ml += MINMATCH;
#if LZ4_FAST_DEC_LOOP
safe_match_copy:
#endif
/* literals copied, match fully decoded (ml includes MINMATCH), offset not validated yet */
if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _offset_error; /* Error : offset outside buffers */
/* end of block : the last LASTLITERALS bytes must be literals */
assert(op <= oend);
if (unlikely(op+ml > oend-LASTLITERALS)) {
if (partialDecoding) ml = MIN(ml, (size_t)(oend-op)); /* partialDecoding : may end anywhere */
else goto _dst_too_small;
}
/* match starting within external dictionary */
if ((dict==usingExtDict) && (match < lowPrefix)) {
assert(dictEnd != NULL);
op = LZ4_copyExtDictMatch(op, match, ml, lowPrefix, dictEnd);
continue;
}
assert(match >= lowPrefix);
/* close to block end : no wild copy */
if (unlikely(op+ml > oend-MATCH_SAFEGUARD_DISTANCE)) {
op = LZ4_copyMatchExact(op, match, ml);
if (op == oend) { break; } /* partialDecoding : output buffer full */
continue;
}
/* copy match within block */
cpy = op + ml;
LZ4_memcpy_using_offset_base(op, match, cpy, offset);
op = cpy; /* wildcopy correction */
}
/* end of decoding */
DEBUGLOG(5, "decoded %i bytes", (int) (((char*)op)-dst));
return (int) (((char*)op)-dst); /* Nb of output bytes decoded */
/* errors : see LZ4_decompress_safe() in lz4.h */
_output_error:
return -1;
_dst_too_small:
return -2;
_offset_error:
return -3;
}
}
/*===== Instantiate the API decoding functions. =====*/
LZ4_FORCE_O2
int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize)
{
return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize,
decode_full_block, noDict,
(BYTE*)dest, NULL, 0);
}
LZ4_FORCE_O2
int LZ4_decompress_safe_partial(const char* src, char* dst, int compressedSize, int targetOutputSize, int dstCapacity)
{
dstCapacity = MIN(targetOutputSize, dstCapacity);
return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity,
partial_decode,
noDict, (BYTE*)dst, NULL, 0);
}
LZ4_FORCE_O2
int LZ4_decompress_fast(const char* source, char* dest, int originalSize)
{
DEBUGLOG(5, "LZ4_decompress_fast");
return LZ4_decompress_unsafe_generic(
(const BYTE*)source, (BYTE*)dest, originalSize,
0, NULL, 0);
}
/*===== Instantiate a few more decoding cases, used more than once. =====*/
LZ4_FORCE_O2 /* Exported, an obsolete API function. */
int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
{
return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
decode_full_block, withPrefix64k,
(BYTE*)dest - 64 KB, NULL, 0);
}
LZ4_FORCE_O2
static int LZ4_decompress_safe_partial_withPrefix64k(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity)
{
dstCapacity = MIN(targetOutputSize, dstCapacity);
return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity,
partial_decode, withPrefix64k,
(BYTE*)dest - 64 KB, NULL, 0);
}
/* Another obsolete API function, paired with the previous one. */
int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
{
return LZ4_decompress_unsafe_generic(
(const BYTE*)source, (BYTE*)dest, originalSize,
64 KB, NULL, 0);
}
LZ4_FORCE_O2
static int LZ4_decompress_safe_withSmallPrefix(const char* source, char* dest, int compressedSize, int maxOutputSize,
size_t prefixSize)
{
return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
decode_full_block, noDict,
(BYTE*)dest-prefixSize, NULL, 0);
}
LZ4_FORCE_O2
static int LZ4_decompress_safe_partial_withSmallPrefix(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity,
size_t prefixSize)
{
dstCapacity = MIN(targetOutputSize, dstCapacity);
return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity,
partial_decode, noDict,
(BYTE*)dest-prefixSize, NULL, 0);
}
LZ4_FORCE_O2
int LZ4_decompress_safe_forceExtDict(const char* source, char* dest,
int compressedSize, int maxOutputSize,
const void* dictStart, size_t dictSize)
{
DEBUGLOG(5, "LZ4_decompress_safe_forceExtDict");
return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
decode_full_block, usingExtDict,
(BYTE*)dest, (const BYTE*)dictStart, dictSize);
}
LZ4_FORCE_O2
int LZ4_decompress_safe_partial_forceExtDict(const char* source, char* dest,
int compressedSize, int targetOutputSize, int dstCapacity,
const void* dictStart, size_t dictSize)
{
dstCapacity = MIN(targetOutputSize, dstCapacity);
return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity,
partial_decode, usingExtDict,
(BYTE*)dest, (const BYTE*)dictStart, dictSize);
}
LZ4_FORCE_O2
static int LZ4_decompress_fast_extDict(const char* source, char* dest, int originalSize,
const void* dictStart, size_t dictSize)
{
return LZ4_decompress_unsafe_generic(
(const BYTE*)source, (BYTE*)dest, originalSize,
0, (const BYTE*)dictStart, dictSize);
}
/* The "double dictionary" mode, for use with e.g. ring buffers: the first part
* of the dictionary is passed as prefix, and the second via dictStart + dictSize.
* These routines are used only once, in LZ4_decompress_*_continue().
*/
LZ4_FORCE_INLINE
int LZ4_decompress_safe_doubleDict(const char* source, char* dest, int compressedSize, int maxOutputSize,
size_t prefixSize, const void* dictStart, size_t dictSize)
{
return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
decode_full_block, usingExtDict,
(BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize);
}
/*===== streaming decompression functions =====*/
#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
LZ4_streamDecode_t* LZ4_createStreamDecode(void)
{
LZ4_STATIC_ASSERT(sizeof(LZ4_streamDecode_t) >= sizeof(LZ4_streamDecode_t_internal));
return (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t));
}
int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
{
if (LZ4_stream == NULL) { return 0; } /* support free on NULL */
FREEMEM(LZ4_stream);
return 0;
}
#endif
/*! LZ4_setStreamDecode() :
* Use this function to instruct where to find the dictionary.
* This function is not necessary if previous data is still available where it was decoded.
* Loading a size of 0 is allowed (same effect as no dictionary).
* @return : 1 if OK, 0 if error
*/
int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize)
{
LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
if (dictSize < 0) return 0;
lz4sd->prefixSize = (size_t)dictSize;
if (dictSize) {
assert(dictionary != NULL);
lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize;
} else {
lz4sd->prefixEnd = (const BYTE*) dictionary;
}
lz4sd->externalDict = NULL;
lz4sd->extDictSize = 0;
return 1;
}
/*! LZ4_decoderRingBufferSize() :
* when setting a ring buffer for streaming decompression (optional scenario),
* provides the minimum size of this ring buffer
* to be compatible with any source respecting maxBlockSize condition.
* Note : in a ring buffer scenario,
* blocks are presumed decompressed next to each other.
* When not enough space remains for next block (remainingSize < maxBlockSize),
* decoding resumes from beginning of ring buffer.
* @return : minimum ring buffer size,
* or 0 if there is an error (invalid maxBlockSize).
*/
int LZ4_decoderRingBufferSize(int maxBlockSize)
{
/* the margin must cover the widest write beyond a copy of the safe loop (16 bytes), minus 2 :
* LZ4_decompress_generic() avoids the fast loop when history is closer than FASTLOOP_SAFE_DISTANCE,
* which the current margin (64) never is. The former margin (14) remains valid. */
LZ4_STATIC_ASSERT(LZ4_DECODER_RING_BUFFER_SIZE(0) - 65536 >= 16 - 2);
if (maxBlockSize < 0) return 0;
if (maxBlockSize > LZ4_MAX_INPUT_SIZE) return 0;
if (maxBlockSize < 16) maxBlockSize = 16;
return LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize);
}
/*
*_continue() :
These decoding functions allow decompression of multiple blocks in "streaming" mode.
Previously decoded blocks must still be available at the memory position where they were decoded.
If it's not possible, save the relevant part of decoded data into a safe buffer,
and indicate where it stands using LZ4_setStreamDecode()
*/
LZ4_FORCE_O2
int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize)
{
LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
int result;
if (lz4sd->prefixSize == 0) {
/* The first call, no dictionary yet. */
assert(lz4sd->extDictSize == 0);
result = LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize);
if (result <= 0) return result;
lz4sd->prefixSize = (size_t)result;
lz4sd->prefixEnd = (BYTE*)dest + result;
} else if (lz4sd->prefixEnd == (BYTE*)dest) {
/* They're rolling the current segment. */
if (lz4sd->prefixSize >= 64 KB - 1)
result = LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize);
else if (lz4sd->extDictSize == 0)
result = LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize,
lz4sd->prefixSize);
else
result = LZ4_decompress_safe_doubleDict(source, dest, compressedSize, maxOutputSize,
lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
if (result <= 0) return result;
lz4sd->prefixSize += (size_t)result;
lz4sd->prefixEnd += result;
} else {
/* The buffer wraps around, or they're switching to another buffer. */
lz4sd->extDictSize = lz4sd->prefixSize;
lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
result = LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize,
lz4sd->externalDict, lz4sd->extDictSize);
if (result <= 0) return result;
lz4sd->prefixSize = (size_t)result;
lz4sd->prefixEnd = (BYTE*)dest + result;
}
return result;
}
LZ4_FORCE_O2 int
LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode,
const char* source, char* dest, int originalSize)
{
LZ4_streamDecode_t_internal* const lz4sd =
(assert(LZ4_streamDecode!=NULL), &LZ4_streamDecode->internal_donotuse);
int result;
DEBUGLOG(5, "LZ4_decompress_fast_continue (toDecodeSize=%i)", originalSize);
assert(originalSize >= 0);
if (lz4sd->prefixSize == 0) {
DEBUGLOG(5, "first invocation : no prefix nor extDict");
assert(lz4sd->extDictSize == 0);
result = LZ4_decompress_fast(source, dest, originalSize);
if (result <= 0) return result;
lz4sd->prefixSize = (size_t)originalSize;
lz4sd->prefixEnd = (BYTE*)dest + originalSize;
} else if (lz4sd->prefixEnd == (BYTE*)dest) {
DEBUGLOG(5, "continue using existing prefix");
result = LZ4_decompress_unsafe_generic(
(const BYTE*)source, (BYTE*)dest, originalSize,
lz4sd->prefixSize,
lz4sd->externalDict, lz4sd->extDictSize);
if (result <= 0) return result;
lz4sd->prefixSize += (size_t)originalSize;
lz4sd->prefixEnd += originalSize;
} else {
DEBUGLOG(5, "prefix becomes extDict");
lz4sd->extDictSize = lz4sd->prefixSize;
lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
result = LZ4_decompress_fast_extDict(source, dest, originalSize,
lz4sd->externalDict, lz4sd->extDictSize);
if (result <= 0) return result;
lz4sd->prefixSize = (size_t)originalSize;
lz4sd->prefixEnd = (BYTE*)dest + originalSize;
}
return result;
}
/*
Advanced decoding functions :
*_usingDict() :
These decoding functions work the same as "_continue" ones,
the dictionary must be explicitly provided within parameters
*/
int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
{
if (dictSize < 0) return -1;
if (dictSize==0)
return LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize);
if (dictStart+dictSize == dest) {
if (dictSize >= 64 KB - 1) {
return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize);
}
assert(dictSize >= 0);
return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, (size_t)dictSize);
}
assert(dictSize >= 0);
return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, (size_t)dictSize);
}
int LZ4_decompress_safe_partial_usingDict(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity, const char* dictStart, int dictSize)
{
if (dictSize < 0) return -1;
if (dictSize==0)
return LZ4_decompress_safe_partial(source, dest, compressedSize, targetOutputSize, dstCapacity);
if (dictStart+dictSize == dest) {
if (dictSize >= 64 KB - 1) {
return LZ4_decompress_safe_partial_withPrefix64k(source, dest, compressedSize, targetOutputSize, dstCapacity);
}
assert(dictSize >= 0);
return LZ4_decompress_safe_partial_withSmallPrefix(source, dest, compressedSize, targetOutputSize, dstCapacity, (size_t)dictSize);
}
assert(dictSize >= 0);
return LZ4_decompress_safe_partial_forceExtDict(source, dest, compressedSize, targetOutputSize, dstCapacity, dictStart, (size_t)dictSize);
}
int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
{
if (dictSize < 0) return -1;
if (dictSize==0 || dictStart+dictSize == dest)
return LZ4_decompress_unsafe_generic(
(const BYTE*)source, (BYTE*)dest, originalSize,
(size_t)dictSize, NULL, 0);
assert(dictSize >= 0);
return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, (size_t)dictSize);
}
/*=*************************************************
* Obsolete Functions
***************************************************/
/* obsolete compression functions */
int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize)
{
return LZ4_compress_default(source, dest, inputSize, maxOutputSize);
}
int LZ4_compress(const char* src, char* dest, int srcSize)
{
return LZ4_compress_default(src, dest, srcSize, LZ4_compressBound(srcSize));
}
int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize)
{
return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1);
}
int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize)
{
return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1);
}
int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int dstCapacity)
{
return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, dstCapacity, 1);
}
int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize)
{
return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1);
}
/*
These decompression functions are deprecated and should no longer be used.
They are only provided here for compatibility with older user programs.
- LZ4_uncompress is totally equivalent to LZ4_decompress_fast
- LZ4_uncompress_unknownOutputSize is totally equivalent to LZ4_decompress_safe
*/
int LZ4_uncompress (const char* source, char* dest, int outputSize)
{
return LZ4_decompress_fast(source, dest, outputSize);
}
int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize)
{
return LZ4_decompress_safe(source, dest, isize, maxOutputSize);
}
/* Obsolete Streaming functions */
int LZ4_sizeofStreamState(void) { return sizeof(LZ4_stream_t); }
int LZ4_resetStreamState(void* state, char* inputBuffer)
{
(void)inputBuffer;
LZ4_resetStream((LZ4_stream_t*)state);
return 0;
}
#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
void* LZ4_create (char* inputBuffer)
{
(void)inputBuffer;
return LZ4_createStream();
}
#endif
char* LZ4_slideInputBuffer (void* state)
{
/* avoid const char * -> char * conversion warning */
return (char *)(uptrval)((LZ4_stream_t*)state)->internal_donotuse.dictionary;
}
#endif /* LZ4_COMMONDEFS_ONLY */
}
Reference in New Issue View Git Blame Copy Permalink