diff options
Diffstat (limited to 'lz4.c')
| -rwxr-xr-x[-rw-r--r--] | lz4.c | 585 |
1 files changed, 379 insertions, 206 deletions
@@ -35,15 +35,6 @@ Tuning parameters **************************************/ /* - * MEMORY_USAGE : - * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.) - * Increasing memory usage improves compression ratio - * Reduced memory usage can improve speed, due to cache effect - * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache - */ -#define MEMORY_USAGE 14 - -/* * HEAPMODE : * Select how default compression functions will allocate memory for their hash table, * in memory stack (0:default, fastest), or in memory heap (1:requires memory allocation (malloc)). @@ -56,8 +47,9 @@ **************************************/ /* 32 or 64 bits ? */ #if (defined(__x86_64__) || defined(_M_X64) || defined(_WIN64) \ - || defined(__powerpc64__) || defined(__ppc64__) || defined(__PPC64__) \ - || defined(__64BIT__) || defined(_LP64) || defined(__LP64__) \ + || defined(__powerpc64__) || defined(__powerpc64le__) \ + || defined(__ppc64__) || defined(__ppc64le__) \ + || defined(__PPC64__) || defined(__PPC64LE__) \ || defined(__ia64) || defined(__itanium__) || defined(_M_IA64) ) /* Detects 64 bits mode */ # define LZ4_ARCH64 1 #else @@ -68,6 +60,7 @@ * Little Endian or Big Endian ? * Overwrite the #define below if you know your architecture endianess */ +#include <stdlib.h> /* Apparently required to detect endianess */ #if defined (__GLIBC__) # include <endian.h> # if (__BYTE_ORDER == __BIG_ENDIAN) @@ -118,7 +111,6 @@ #endif #ifdef _MSC_VER /* Visual Studio */ -# define FORCE_INLINE static __forceinline # include <intrin.h> /* For Visual 2005 */ # if LZ4_ARCH64 /* 64-bits */ # pragma intrinsic(_BitScanForward64) /* For Visual 2005 */ @@ -128,15 +120,6 @@ # pragma intrinsic(_BitScanReverse) /* For Visual 2005 */ # endif # pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ -#else -# ifdef __GNUC__ -# define FORCE_INLINE static inline __attribute__((always_inline)) -# else -# define FORCE_INLINE static inline -# endif -#endif - -#ifdef _MSC_VER /* Visual Studio */ # define lz4_bswap16(x) _byteswap_ushort(x) #else # define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8))) @@ -224,9 +207,9 @@ typedef struct {size_t v;} _PACKED size_t_S; /************************************** Constants **************************************/ -#define LZ4_HASHLOG (MEMORY_USAGE-2) -#define HASHTABLESIZE (1 << MEMORY_USAGE) -#define HASHNBCELLS4 (1 << LZ4_HASHLOG) +#define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2) +#define HASHTABLESIZE (1 << LZ4_MEMORY_USAGE) +#define HASH_SIZE_U32 (1 << LZ4_HASHLOG) #define MINMATCH 4 @@ -255,16 +238,18 @@ static const int LZ4_minLength = (MFLIMIT+1); Structures and local types **************************************/ typedef struct { - U32 hashTable[HASHNBCELLS4]; + U32 hashTable[HASH_SIZE_U32]; + U32 currentOffset; + U32 initCheck; + const BYTE* dictionary; const BYTE* bufferStart; - const BYTE* base; - const BYTE* nextBlock; -} LZ4_Data_Structure; + U32 dictSize; +} LZ4_dict_t_internal; -typedef enum { notLimited = 0, limited = 1 } limitedOutput_directive; +typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive; typedef enum { byPtr, byU32, byU16 } tableType_t; -typedef enum { noDict = 0, withPrefix64k = 1, withExtDict=2 } dict_directive; +typedef enum { noDict = 0, withPrefix64k = 1, usingExtDict = 2 } dict_directive; typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; typedef enum { full = 0, partial = 1 } earlyEnd_directive; @@ -289,12 +274,12 @@ typedef enum { full = 0, partial = 1 } earlyEnd_directive; /************************************** Macros **************************************/ +#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(!!(c)) }; } /* use only *after* variable declarations */ #if LZ4_ARCH64 || !defined(__GNUC__) -# define LZ4_WILDCOPY(d,s,e) { do { LZ4_COPY8(d,s) } while (d<e); } /* at the end, d>=e; */ +# define LZ4_WILDCOPY(d,s,e) { do { LZ4_COPY8(d,s) } while (d<e); } /* at the end, d>=e; */ #else -# define LZ4_WILDCOPY(d,s,e) { if (likely(e-d <= 8)) LZ4_COPY8(d,s) else do { LZ4_COPY8(d,s) } while (d<e); } +# define LZ4_WILDCOPY(d,s,e) { if (likely(e-d <= 8)) LZ4_COPY8(d,s) else do { LZ4_COPY8(d,s) } while (d<e); } #endif -#define LZ4_SECURECOPY(d,s,e) { if (d<e) LZ4_WILDCOPY(d,s,e); } /**************************** @@ -302,7 +287,7 @@ typedef enum { full = 0, partial = 1 } earlyEnd_directive; ****************************/ #if LZ4_ARCH64 -FORCE_INLINE int LZ4_NbCommonBytes (register U64 val) +int LZ4_NbCommonBytes (register U64 val) { # if defined(LZ4_BIG_ENDIAN) # if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) @@ -334,7 +319,7 @@ FORCE_INLINE int LZ4_NbCommonBytes (register U64 val) #else -FORCE_INLINE int LZ4_NbCommonBytes (register U32 val) +int LZ4_NbCommonBytes (register U32 val) { # if defined(LZ4_BIG_ENDIAN) # if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) @@ -371,7 +356,7 @@ FORCE_INLINE int LZ4_NbCommonBytes (register U32 val) ****************************/ int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } -FORCE_INLINE int LZ4_hashSequence(U32 sequence, tableType_t tableType) +static int LZ4_hashSequence(U32 sequence, tableType_t tableType) { if (tableType == byU16) return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1))); @@ -379,9 +364,9 @@ FORCE_INLINE int LZ4_hashSequence(U32 sequence, tableType_t tableType) return (((sequence) * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG)); } -FORCE_INLINE int LZ4_hashPosition(const BYTE* p, tableType_t tableType) { return LZ4_hashSequence(A32(p), tableType); } +static int LZ4_hashPosition(const BYTE* p, tableType_t tableType) { return LZ4_hashSequence(A32(p), tableType); } -FORCE_INLINE void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) +static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) { switch (tableType) { @@ -391,58 +376,96 @@ FORCE_INLINE void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, t } } -FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) +static void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) { U32 h = LZ4_hashPosition(p, tableType); LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase); } -FORCE_INLINE const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) +static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) { if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; } if (tableType == byU32) { U32* hashTable = (U32*) tableBase; return hashTable[h] + srcBase; } { U16* hashTable = (U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */ } -FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) +static const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) { U32 h = LZ4_hashPosition(p, tableType); return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase); } +static unsigned LZ4_count(const BYTE* pIn, const BYTE* pRef, const BYTE* pInLimit) +{ + const BYTE* const pStart = pIn; + + while (likely(pIn<pInLimit-(STEPSIZE-1))) + { + size_t diff = AARCH(pRef) ^ AARCH(pIn); + if (!diff) { pIn+=STEPSIZE; pRef+=STEPSIZE; continue; } + pIn += LZ4_NbCommonBytes(diff); + return (unsigned)(pIn - pStart); + } + if (LZ4_ARCH64) if ((pIn<(pInLimit-3)) && (A32(pRef) == A32(pIn))) { pIn+=4; pRef+=4; } + if ((pIn<(pInLimit-1)) && (A16(pRef) == A16(pIn))) { pIn+=2; pRef+=2; } + if ((pIn<pInLimit) && (*pRef == *pIn)) pIn++; + + return (unsigned)(pIn - pStart); +} + -FORCE_INLINE int LZ4_compress_generic( +static int LZ4_compress_generic( void* ctx, const char* source, char* dest, int inputSize, int maxOutputSize, - limitedOutput_directive limitedOutput, + limitedOutput_directive outputLimited, tableType_t tableType, dict_directive dict) { + LZ4_dict_t_internal* const dictPtr = (LZ4_dict_t_internal*)ctx; + const BYTE* ip = (const BYTE*) source; - const BYTE* const base = (dict==withPrefix64k) ? ((LZ4_Data_Structure*)ctx)->base : (const BYTE*) source; - const BYTE* const lowLimit = ((dict==withPrefix64k) ? ((LZ4_Data_Structure*)ctx)->bufferStart : (const BYTE*)source); + const BYTE* base; + const BYTE* lowLimit; + const BYTE* const dictionary = dictPtr->dictionary; + const BYTE* const dictEnd = dictionary + dictPtr->dictSize; + const size_t dictDelta = dictEnd - (const BYTE*)source; const BYTE* anchor = (const BYTE*) source; const BYTE* const iend = ip + inputSize; const BYTE* const mflimit = iend - MFLIMIT; const BYTE* const matchlimit = iend - LASTLITERALS; BYTE* op = (BYTE*) dest; - BYTE* const oend = op + maxOutputSize; + BYTE* const olimit = op + maxOutputSize; - int length; const int skipStrength = SKIPSTRENGTH; U32 forwardH; + size_t refDelta=0; /* Init conditions */ - if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size, too large (or negative) */ - if ((dict==withPrefix64k) && (ip != ((LZ4_Data_Structure*)ctx)->nextBlock)) return 0; /* must continue from end of previous block */ - if (dict==withPrefix64k) ((LZ4_Data_Structure*)ctx)->nextBlock=iend; /* do it now, due to potential early exit */ - if ((tableType == byU16) && (inputSize>=(int)LZ4_64KLIMIT)) return 0; /* Size too large (not within 64K limit) */ - if (inputSize<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ + if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size, too large (or negative) */ + switch(dict) + { + case noDict: + default: + base = (const BYTE*)source; + lowLimit = (const BYTE*)source; + break; + case withPrefix64k: + base = (const BYTE*)source - dictPtr->currentOffset; + lowLimit = (const BYTE*)source - dictPtr->dictSize; + if (lowLimit < base) lowLimit = base; + break; + case usingExtDict: + base = (const BYTE*)source - dictPtr->currentOffset; + lowLimit = (const BYTE*)source; + break; + } + if ((tableType == byU16) && (inputSize>=(int)LZ4_64KLIMIT)) return 0; /* Size too large (not within 64K limit) */ + if (inputSize<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ /* First Byte */ LZ4_putPosition(ip, ctx, tableType, base); @@ -451,98 +474,139 @@ FORCE_INLINE int LZ4_compress_generic( /* Main Loop */ for ( ; ; ) { - int findMatchAttempts = (1U << skipStrength) + 3; const BYTE* forwardIp = ip; const BYTE* ref; BYTE* token; + { + int step=1; + int searchMatchNb = (1U << skipStrength) + 3; - /* Find a match */ - do { - U32 h = forwardH; - int step = findMatchAttempts++ >> skipStrength; - ip = forwardIp; - forwardIp = ip + step; + /* Find a match */ + do { + U32 h = forwardH; + ip = forwardIp; + forwardIp += step; + step = searchMatchNb++ >> skipStrength; + if (unlikely (step>8)) step=8; // slows down uncompressible data; required for valid forwardIp - if (unlikely(forwardIp > mflimit)) { goto _last_literals; } + if (unlikely(ip > mflimit)) goto _last_literals; - forwardH = LZ4_hashPosition(forwardIp, tableType); - ref = LZ4_getPositionOnHash(h, ctx, tableType, base); - LZ4_putPositionOnHash(ip, h, ctx, tableType, base); + ref = LZ4_getPositionOnHash(h, ctx, tableType, base); + if (dict==usingExtDict) + { + if (ref<(const BYTE*)source) + { + refDelta = dictDelta; + lowLimit = dictionary; + } + else + { + refDelta = 0; + lowLimit = (const BYTE*)source; + } + } + forwardH = LZ4_hashPosition(forwardIp, tableType); + LZ4_putPositionOnHash(ip, h, ctx, tableType, base); - } while ((ref + MAX_DISTANCE < ip) || (A32(ref) != A32(ip))); + } while ( ((tableType==byU16)? 0 : (ref + MAX_DISTANCE < ip)) || (A32(ref+refDelta) != A32(ip)) ); + } /* Catch up */ - while ((ip>anchor) && (ref > lowLimit) && (unlikely(ip[-1]==ref[-1]))) { ip--; ref--; } + while ((ip>anchor) && (ref+refDelta > lowLimit) && (unlikely(ip[-1]==ref[refDelta-1]))) { ip--; ref--; } - /* Encode Literal length */ - length = (int)(ip - anchor); - token = op++; - if ((limitedOutput) && (unlikely(op + length + (2 + 1 + LASTLITERALS) + (length/255) > oend))) return 0; /* Check output limit */ - if (length>=(int)RUN_MASK) { - int len = length-RUN_MASK; - *token=(RUN_MASK<<ML_BITS); - for(; len >= 255 ; len-=255) *op++ = 255; - *op++ = (BYTE)len; - } - else *token = (BYTE)(length<<ML_BITS); + /* Encode Literal length */ + unsigned litLength = (unsigned)(ip - anchor); + token = op++; + if ((outputLimited) && (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit))) return 0; /* Check output limit */ + if (litLength>=RUN_MASK) + { + int len = (int)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 */ - { BYTE* end=(op)+(length); LZ4_WILDCOPY(op,anchor,end); op=end; } + /* Copy Literals */ + { BYTE* end=(op)+(litLength); LZ4_WILDCOPY(op,anchor,end); op=end; } + } _next_match: /* Encode Offset */ LZ4_WRITE_LITTLEENDIAN_16(op,(U16)(ip-ref)); - /* Start Counting */ - ip+=MINMATCH; ref+=MINMATCH; /* MinMatch already verified */ - anchor = ip; - while (likely(ip<matchlimit-(STEPSIZE-1))) - { - size_t diff = AARCH(ref) ^ AARCH(ip); - if (!diff) { ip+=STEPSIZE; ref+=STEPSIZE; continue; } - ip += LZ4_NbCommonBytes(diff); - goto _endCount; - } - if (LZ4_ARCH64) if ((ip<(matchlimit-3)) && (A32(ref) == A32(ip))) { ip+=4; ref+=4; } - if ((ip<(matchlimit-1)) && (A16(ref) == A16(ip))) { ip+=2; ref+=2; } - if ((ip<matchlimit) && (*ref == *ip)) ip++; -_endCount: - /* Encode MatchLength */ - length = (int)(ip - anchor); - if ((limitedOutput) && (unlikely(op + (1 + LASTLITERALS) + (length>>8) > oend))) return 0; /* Check output limit */ - if (length>=(int)ML_MASK) + ref += refDelta; { - *token += ML_MASK; - length -= ML_MASK; - for (; length > 509 ; length-=510) { *op++ = 255; *op++ = 255; } - if (length >= 255) { length-=255; *op++ = 255; } - *op++ = (BYTE)length; + unsigned matchLength; + + if ((dict==usingExtDict) && (lowLimit==dictionary)) + { + const BYTE* limit = ip + (dictEnd-ref); + if (limit > matchlimit) limit = matchlimit; + matchLength = LZ4_count(ip+MINMATCH, ref+MINMATCH, limit); + ip += MINMATCH + matchLength; + if (ip==limit) + { + unsigned more = LZ4_count(ip, (const BYTE*)source, matchlimit); + matchLength += more; + ip += more; + } + } + else + { + matchLength = LZ4_count(ip+MINMATCH, ref+MINMATCH, matchlimit); + ip += MINMATCH + matchLength; + } + + if (matchLength>=ML_MASK) + { + if ((outputLimited) && (unlikely(op + (1 + LASTLITERALS) + (matchLength>>8) > olimit))) return 0; /* Check output limit */ + *token += ML_MASK; + matchLength -= ML_MASK; + for (; matchLength >= 510 ; matchLength-=510) { *op++ = 255; *op++ = 255; } + if (matchLength >= 255) { matchLength-=255; *op++ = 255; } + *op++ = (BYTE)matchLength; + } + else *token += (BYTE)(matchLength); } - else *token += (BYTE)(length); + + anchor = ip; /* Test end of chunk */ - if (ip > mflimit) { anchor = ip; break; } + if (ip > mflimit) break; /* Fill table */ LZ4_putPosition(ip-2, ctx, tableType, base); /* Test next position */ ref = LZ4_getPosition(ip, ctx, tableType, base); + if (dict==usingExtDict) + { + if (ref<(const BYTE*)source) + { + refDelta = dictDelta; + lowLimit = dictionary; + } + else + { + refDelta = 0; + lowLimit = (const BYTE*)source; + } + } LZ4_putPosition(ip, ctx, tableType, base); - if ((ref + MAX_DISTANCE >= ip) && (A32(ref) == A32(ip))) { token = op++; *token=0; goto _next_match; } + if ( (ref+MAX_DISTANCE>=ip) && (A32(ref+refDelta)==A32(ip)) ) { token=op++; *token=0; goto _next_match; } /* Prepare next loop */ - anchor = ip++; - forwardH = LZ4_hashPosition(ip, tableType); + forwardH = LZ4_hashPosition(++ip, tableType); } _last_literals: /* Encode Last Literals */ { int lastRun = (int)(iend - anchor); - if ((limitedOutput) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize)) return 0; /* Check output limit */ + if ((outputLimited) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize)) return 0; /* Check output limit */ if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun >= 255 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; } else *op++ = (BYTE)(lastRun<<ML_BITS); memcpy(op, anchor, iend - anchor); @@ -557,9 +621,9 @@ _last_literals: int LZ4_compress(const char* source, char* dest, int inputSize) { #if (HEAPMODE) - void* ctx = ALLOCATOR(HASHNBCELLS4, 4); /* Aligned on 4-bytes boundaries */ + void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U32, 4); /* Aligned on 4-bytes boundaries */ #else - U32 ctx[1U<<(MEMORY_USAGE-2)] = {0}; /* Ensure data is aligned on 4-bytes boundaries */ + U32 ctx[LZ4_STREAMSIZE_U32] = {0}; /* Ensure data is aligned on 4-bytes boundaries */ #endif int result; @@ -577,16 +641,16 @@ int LZ4_compress(const char* source, char* dest, int inputSize) int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) { #if (HEAPMODE) - void* ctx = ALLOCATOR(HASHNBCELLS4, 4); /* Aligned on 4-bytes boundaries */ + void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U32, 4); /* Aligned on 4-bytes boundaries */ #else - U32 ctx[1U<<(MEMORY_USAGE-2)] = {0}; /* Ensure data is aligned on 4-bytes boundaries */ + U32 ctx[LZ4_STREAMSIZE_U32] = {0}; /* Ensure data is aligned on 4-bytes boundaries */ #endif int result; if (inputSize < (int)LZ4_64KLIMIT) - result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limited, byU16, noDict); + result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict); else - result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limited, (sizeof(void*)==8) ? byU32 : byPtr, noDict); + result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limitedOutput, (sizeof(void*)==8) ? byU32 : byPtr, noDict); #if (HEAPMODE) FREEMEM(ctx); @@ -595,118 +659,169 @@ int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, in } -/***************************** - Using external allocation -*****************************/ - -int LZ4_sizeofState() { return 1 << MEMORY_USAGE; } - +/***************************************** + Experimental : Streaming functions +*****************************************/ -int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize) +void* LZ4_createStream() { - if (((size_t)(state)&3) != 0) return 0; /* Error : state is not aligned on 4-bytes boundary */ - MEM_INIT(state, 0, LZ4_sizeofState()); + void* lz4s = ALLOCATOR(4, LZ4_STREAMSIZE_U32); + MEM_INIT(lz4s, 0, LZ4_STREAMSIZE); + return lz4s; +} - if (inputSize < (int)LZ4_64KLIMIT) - return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, byU16, noDict); - else - return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict); +int LZ4_free (void* LZ4_stream) +{ + FREEMEM(LZ4_stream); + return (0); } -int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize) +int LZ4_loadDict (void* LZ4_dict, const char* dictionary, int dictSize) { - if (((size_t)(state)&3) != 0) return 0; /* Error : state is not aligned on 4-bytes boundary */ - MEM_INIT(state, 0, LZ4_sizeofState()); + LZ4_dict_t_internal* dict = (LZ4_dict_t_internal*) LZ4_dict; + const BYTE* p = (const BYTE*)dictionary; + const BYTE* const dictEnd = p + dictSize; + const BYTE* base; - if (inputSize < (int)LZ4_64KLIMIT) - return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limited, byU16, noDict); - else - return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limited, (sizeof(void*)==8) ? byU32 : byPtr, noDict); -} + LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_dict_t_internal)); /* A compilation error here means LZ4_STREAMSIZE is not large enough */ + if (dict->initCheck) MEM_INIT(dict, 0, sizeof(LZ4_dict_t_internal)); + if (dictSize < MINMATCH) + { + dict->dictionary = NULL; + dict->dictSize = 0; + return 1; + } -/**************************** - Stream functions -****************************/ + if (p <= dictEnd - 64 KB) p = dictEnd - 64 KB; + base = p - dict->currentOffset; + dict->dictionary = p; + dict->dictSize = (U32)(dictEnd - p); + dict->currentOffset += dict->dictSize; -int LZ4_sizeofStreamState() -{ - return sizeof(LZ4_Data_Structure); -} + while (p <= dictEnd-MINMATCH) + { + LZ4_putPosition(p, dict, byU32, base); + p+=3; + } -FORCE_INLINE void LZ4_init(LZ4_Data_Structure* lz4ds, const BYTE* base) -{ - MEM_INIT(lz4ds->hashTable, 0, sizeof(lz4ds->hashTable)); - lz4ds->bufferStart = base; - lz4ds->base = base; - lz4ds->nextBlock = base; + return 1; } -int LZ4_resetStreamState(void* state, const char* inputBuffer) -{ - if ((((size_t)state) & 3) != 0) return 1; /* Error : pointer is not aligned on 4-bytes boundary */ - LZ4_init((LZ4_Data_Structure*)state, (const BYTE*)inputBuffer); - return 0; -} -void* LZ4_create (const char* inputBuffer) +void LZ4_renormDictT(LZ4_dict_t_internal* LZ4_dict, const BYTE* src) { - void* lz4ds = ALLOCATOR(1, sizeof(LZ4_Data_Structure)); - LZ4_init ((LZ4_Data_Structure*)lz4ds, (const BYTE*)inputBuffer); - return lz4ds; + if ((LZ4_dict->currentOffset > 0x80000000) || + ((size_t)LZ4_dict->currentOffset > (size_t)src)) /* address space overflow */ + { + /* rescale hash table */ + U32 delta = LZ4_dict->currentOffset - 64 KB; + int i; + for (i=0; i<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; + LZ4_dict->dictionary = LZ4_dict->dictionary + LZ4_dict->dictSize - 64 KB; + LZ4_dict->dictSize = 64 KB; + } } -int LZ4_free (void* LZ4_Data) +int LZ4_compress_continue (void* LZ4_stream, const char* source, char* dest, int inputSize) { - FREEMEM(LZ4_Data); - return (0); -} - + LZ4_dict_t_internal* streamPtr = (LZ4_dict_t_internal*)LZ4_stream; + const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; -char* LZ4_slideInputBuffer (void* LZ4_Data) -{ - LZ4_Data_Structure* lz4ds = (LZ4_Data_Structure*)LZ4_Data; - size_t delta = lz4ds->nextBlock - (lz4ds->bufferStart + 64 KB); + const BYTE* smallest = (const BYTE*) source; + if ((streamPtr->dictSize>0) && (smallest > dictEnd)) smallest = dictEnd; + LZ4_renormDictT(streamPtr, smallest); - if ( (lz4ds->base - delta > lz4ds->base) /* underflow control */ - || ((size_t)(lz4ds->nextBlock - lz4ds->base) > 0xE0000000) ) /* close to 32-bits limit */ + if (dictEnd == (const BYTE*)source) { - size_t deltaLimit = (lz4ds->nextBlock - 64 KB) - lz4ds->base; - int nH; + int result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, 0, notLimited, byU32, withPrefix64k); + streamPtr->dictSize += (U32)inputSize; + streamPtr->currentOffset += (U32)inputSize; + return result; + } - for (nH=0; nH < HASHNBCELLS4; nH++) - { - if ((size_t)(lz4ds->hashTable[nH]) < deltaLimit) lz4ds->hashTable[nH] = 0; - else lz4ds->hashTable[nH] -= (U32)deltaLimit; - } - memcpy((void*)(lz4ds->bufferStart), (const void*)(lz4ds->nextBlock - 64 KB), 64 KB); - lz4ds->base = lz4ds->bufferStart; - lz4ds->nextBlock = lz4ds->base + 64 KB; + { + int result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, 0, notLimited, byU32, usingExtDict); + streamPtr->dictionary = (const BYTE*)source; + streamPtr->dictSize = (U32)inputSize; + streamPtr->currentOffset += (U32)inputSize; + return result; } - else +} + +int LZ4_compress_limitedOutput_continue (void* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize) +{ + LZ4_dict_t_internal* streamPtr = (LZ4_dict_t_internal*)LZ4_stream; + const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; + + const BYTE* smallest = (const BYTE*) source; + if ((streamPtr->dictSize>0) && (smallest>dictEnd)) smallest = dictEnd; + LZ4_renormDictT(streamPtr, smallest); + + if (dictEnd == (const BYTE*)source) { - memcpy((void*)(lz4ds->bufferStart), (const void*)(lz4ds->nextBlock - 64 KB), 64 KB); - lz4ds->nextBlock -= delta; - lz4ds->base -= delta; + int result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k); + streamPtr->dictSize += (U32)inputSize; + streamPtr->currentOffset += (U32)inputSize; + return result; } - return (char*)(lz4ds->nextBlock); + { + int result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict); + streamPtr->dictionary = (const BYTE*)source; + streamPtr->dictSize = (U32)inputSize; + streamPtr->currentOffset += (U32)inputSize; + return result; + } } -int LZ4_compress_continue (void* LZ4_Data, const char* source, char* dest, int inputSize) +// Hidden debug function, to force separate dictionary mode +int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize) { - return LZ4_compress_generic(LZ4_Data, source, dest, inputSize, 0, notLimited, byU32, withPrefix64k); + LZ4_dict_t_internal* streamPtr = (LZ4_dict_t_internal*)LZ4_dict; + int result; + const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; + + const BYTE* smallest = dictEnd; + if (smallest > (const BYTE*) source) smallest = (const BYTE*) source; + LZ4_renormDictT((LZ4_dict_t_internal*)LZ4_dict, smallest); + + result = LZ4_compress_generic(LZ4_dict, source, dest, inputSize, 0, notLimited, byU32, usingExtDict); + + streamPtr->dictionary = (const BYTE*)source; + streamPtr->dictSize = (U32)inputSize; + streamPtr->currentOffset += (U32)inputSize; + + return result; } -int LZ4_compress_limitedOutput_continue (void* LZ4_Data, const char* source, char* dest, int inputSize, int maxOutputSize) + +int LZ4_moveDict (void* LZ4_dict, char* safeBuffer, int dictSize) { - return LZ4_compress_generic(LZ4_Data, source, dest, inputSize, maxOutputSize, limited, byU32, withPrefix64k); + LZ4_dict_t_internal* dict = (LZ4_dict_t_internal*) LZ4_dict; + const BYTE* previousDictEnd = dict->dictionary + dict->dictSize; + + if ((U32)dictSize > 64 KB) dictSize = 64 KB; /* useless to define a dictionary > 64 KB */ + if ((U32)dictSize > dict->dictSize) dictSize = dict->dictSize; + + memcpy(safeBuffer, previousDictEnd - dictSize, dictSize); + + dict->dictionary = (const BYTE*)safeBuffer; + dict->dictSize = (U32)dictSize; + + return 1; } + /**************************** Decompression functions ****************************/ @@ -716,7 +831,7 @@ int LZ4_compress_limitedOutput_continue (void* LZ4_Data, const char* source, cha * Note that it is essential this generic function is really inlined, * in order to remove useless branches during compilation optimisation. */ -FORCE_INLINE int LZ4_decompress_generic( +static int LZ4_decompress_generic( const char* source, char* dest, int inputSize, @@ -725,9 +840,9 @@ FORCE_INLINE int LZ4_decompress_generic( int endOnInput, /* endOnOutputSize, endOnInputSize */ int partialDecoding, /* full, partial */ int targetOutputSize, /* only used if partialDecoding==partial */ - int dict, /* noDict, withPrefix64k, withExtDict */ - const char* dictStart, /* only if dict==withExtDict */ - int dictSize /* only if dict==withExtDict */ + int dict, /* noDict, withPrefix64k, usingExtDict */ + const char* dictStart, /* only if dict==usingExtDict */ + int dictSize /* only if dict==usingExtDict */ ) { /* Local Variables */ @@ -740,7 +855,7 @@ FORCE_INLINE int LZ4_decompress_generic( BYTE* cpy; BYTE* oexit = op + targetOutputSize; - const BYTE* const dictEnd = (dict==withExtDict) ? (const BYTE*)dictStart + dictSize : NULL; + const BYTE* const dictEnd = (dict==usingExtDict) ? (const BYTE*)dictStart + dictSize : NULL; const size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0}; /* static reduces speed for LZ4_decompress_safe() on GCC64 */ static const size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3}; @@ -748,11 +863,10 @@ FORCE_INLINE int LZ4_decompress_generic( /* Special cases */ (void)dictStart; (void)dictSize; - if ((partialDecoding) && (oexit> oend-MFLIMIT)) oexit = oend-MFLIMIT; /* targetOutputSize too high => decode everything */ + if ((partialDecoding) && (oexit> oend-MFLIMIT)) oexit = oend-MFLIMIT; /* targetOutputSize too high => decode everything */ if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */ if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1); - /* Main Loop */ while (1) { @@ -764,11 +878,7 @@ FORCE_INLINE int LZ4_decompress_generic( if ((length=(token>>ML_BITS)) == RUN_MASK) { unsigned s=255; - while (((endOnInput)?ip<iend:1) && (s==255)) - { - s = *ip++; - length += s; - } + while (((endOnInput)?ip<iend:1) && (s==255)) { s = *ip++; length += s; } } /* copy literals */ @@ -814,7 +924,7 @@ FORCE_INLINE int LZ4_decompress_generic( } /* check external dictionary */ - if ((dict==withExtDict) && (unlikely(ref < (BYTE* const)dest))) + if ((dict==usingExtDict) && (ref < (BYTE* const)dest)) { if (unlikely(op+length+MINMATCH > oend-LASTLITERALS)) goto _output_error; @@ -830,7 +940,7 @@ FORCE_INLINE int LZ4_decompress_generic( memcpy(op, dictEnd - copySize, copySize); op += copySize; copySize = length+MINMATCH - copySize; - if (copySize > (size_t)((char*)op-dest)) + if (copySize > (size_t)((char*)op-dest)) /* overlap */ { BYTE* const cpy = op + copySize; const BYTE* ref = (BYTE*)dest; @@ -862,7 +972,7 @@ FORCE_INLINE int LZ4_decompress_generic( if (unlikely(cpy>oend-COPYLENGTH-(STEPSIZE-4))) { if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last 5 bytes must be literals */ - LZ4_SECURECOPY(op, ref, (oend-COPYLENGTH)); + if (op<oend-COPYLENGTH) LZ4_WILDCOPY(op, ref, (oend-COPYLENGTH)); while(op<cpy) *op++=*ref++; op=cpy; continue; @@ -895,7 +1005,7 @@ int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compre int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize) { - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, withExtDict, dictStart, dictSize); + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, dictStart, dictSize); } int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxOutputSize) @@ -919,7 +1029,7 @@ int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int origin int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize) { - return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withExtDict, dictStart, dictSize); + return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, usingExtDict, dictStart, dictSize); } @@ -927,8 +1037,71 @@ int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSi Obsolete Functions **************************************/ /* -These functions are deprecated and should no longer be used. -They are provided here for compatibility with existing user programs. +These function names 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() { return LZ4_STREAMSIZE; } + +void LZ4_init(LZ4_dict_t_internal* lz4ds, const BYTE* base) +{ + MEM_INIT(lz4ds->hashTable, 0, LZ4_STREAMSIZE); + lz4ds->bufferStart = base; +} + +int LZ4_resetStreamState(void* state, const char* inputBuffer) +{ + if ((((size_t)state) & 3) != 0) return 1; /* Error : pointer is not aligned on 4-bytes boundary */ + LZ4_init((LZ4_dict_t_internal*)state, (const BYTE*)inputBuffer); + return 0; +} + +void* LZ4_create (const char* inputBuffer) +{ + void* lz4ds = ALLOCATOR(4, LZ4_STREAMSIZE_U32); + LZ4_init ((LZ4_dict_t_internal*)lz4ds, (const BYTE*)inputBuffer); + return lz4ds; +} + +char* LZ4_slideInputBuffer (void* LZ4_Data) +{ + LZ4_dict_t_internal* lz4ds = (LZ4_dict_t_internal*)LZ4_Data; + + LZ4_moveDict((LZ4_stream_t*)LZ4_Data, (char*)lz4ds->bufferStart, 64 KB); + + return (char*)(lz4ds->bufferStart + 64 KB); +} + +/* User-allocated state */ + +int LZ4_sizeofState() { return LZ4_STREAMSIZE; } + +int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize) +{ + if (((size_t)(state)&3) != 0) return 0; /* Error : state is not aligned on 4-bytes boundary */ + MEM_INIT(state, 0, LZ4_sizeofState()); + + if (inputSize < (int)LZ4_64KLIMIT) + return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, byU16, noDict); + else + return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict); +} + +int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize) +{ + if (((size_t)(state)&3) != 0) return 0; /* Error : state is not aligned on 4-bytes boundary */ + MEM_INIT(state, 0, LZ4_sizeofState()); + + if (inputSize < (int)LZ4_64KLIMIT) + return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict); + else + return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, (sizeof(void*)==8) ? byU32 : byPtr, noDict); +} + |