diff options
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Makefile | 9 | ||||
-rw-r--r-- | lib/lz4.c | 178 | ||||
-rw-r--r-- | lib/lz4.h | 128 | ||||
-rw-r--r-- | lib/lz4frame.c | 4 | ||||
-rw-r--r-- | lib/lz4frame.h | 29 | ||||
-rw-r--r-- | lib/lz4hc.c | 3 | ||||
-rw-r--r-- | lib/lz4hc.h | 8 |
7 files changed, 229 insertions, 130 deletions
diff --git a/lib/Makefile b/lib/Makefile index abb6c07..88d9b4f 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -45,6 +45,7 @@ LIBVER := $(shell echo $(LIBVER_SCRIPT)) BUILD_SHARED:=yes BUILD_STATIC:=yes +OS ?= $(shell uname) CPPFLAGS+= -DXXH_NAMESPACE=LZ4_ CFLAGS ?= -O3 DEBUGFLAGS:= -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \ @@ -58,7 +59,7 @@ SRCFILES := $(sort $(wildcard *.c)) # OS X linker doesn't support -soname, and use different extension # see : https://developer.apple.com/library/mac/documentation/DeveloperTools/Conceptual/DynamicLibraries/100-Articles/DynamicLibraryDesignGuidelines.html -ifeq ($(shell uname), Darwin) +ifeq ($(OS), Darwin) SHARED_EXT = dylib SHARED_EXT_MAJOR = $(LIBVER_MAJOR).$(SHARED_EXT) SHARED_EXT_VER = $(LIBVER).$(SHARED_EXT) @@ -123,7 +124,7 @@ clean: #----------------------------------------------------------------------------- # make install is validated only for Linux, OSX, BSD, Hurd and Solaris targets #----------------------------------------------------------------------------- -ifneq (,$(filter $(shell uname),Linux Darwin GNU/kFreeBSD GNU OpenBSD FreeBSD NetBSD DragonFly SunOS)) +ifneq (,$(filter $(shell uname),Linux Darwin GNU/kFreeBSD GNU OpenBSD FreeBSD NetBSD DragonFly SunOS Haiku MidnightBSD)) .PHONY: listL120 listL120: # extract lines >= 120 characters in *.{c,h}, by Takayuki Matsuoka (note : $$, for Makefile compatibility) @@ -142,14 +143,14 @@ libdir ?= $(LIBDIR) INCLUDEDIR ?= $(prefix)/include includedir ?= $(INCLUDEDIR) -ifneq (,$(filter $(shell uname),OpenBSD FreeBSD NetBSD DragonFly)) +ifneq (,$(filter $(OS),OpenBSD FreeBSD NetBSD DragonFly)) PKGCONFIGDIR ?= $(prefix)/libdata/pkgconfig else PKGCONFIGDIR ?= $(libdir)/pkgconfig endif pkgconfigdir ?= $(PKGCONFIGDIR) -ifneq (,$(filter $(shell uname),SunOS)) +ifneq (,$(filter $(OS),SunOS)) INSTALL ?= ginstall else INSTALL ?= install @@ -1,6 +1,6 @@ /* LZ4 - Fast LZ compression algorithm - Copyright (C) 2011-2017, Yann Collet. + Copyright (C) 2011-present, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -297,8 +297,9 @@ void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd) #define MINMATCH 4 #define WILDCOPYLENGTH 8 -#define LASTLITERALS 5 -#define MFLIMIT (WILDCOPYLENGTH+MINMATCH) +#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 */ static const int LZ4_minLength = (MFLIMIT+1); #define KB *(1 <<10) @@ -483,9 +484,6 @@ typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t; typedef enum { noDict = 0, withPrefix64k, usingExtDict, usingDictCtx } dict_directive; typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive; -typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; -typedef enum { full = 0, partial = 1 } earlyEnd_directive; - /*-************************************ * Local Utils @@ -496,6 +494,21 @@ int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } int LZ4_sizeofState() { return LZ4_STREAMSIZE; } +/*-************************************ +* Internal Definitions used in Tests +**************************************/ +#if defined (__cplusplus) +extern "C" { +#endif + +int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize); + +int LZ4_decompress_safe_forceExtDict(const char* in, char* out, int inSize, int outSize, const void* dict, size_t dictSize); + +#if defined (__cplusplus) +} +#endif + /*-****************************** * Compression functions ********************************/ @@ -669,9 +682,9 @@ LZ4_FORCE_INLINE int LZ4_compress_generic( /* the dictCtx currentOffset is indexed on the start of the dictionary, * while a dictionary in the current context precedes the currentOffset */ - const BYTE* dictBase = dictDirective == usingDictCtx ? - dictionary + dictSize - dictCtx->currentOffset : - dictionary + dictSize - startIndex; + const BYTE* dictBase = (dictDirective == usingDictCtx) ? + dictionary + dictSize - dictCtx->currentOffset : + dictionary + dictSize - startIndex; BYTE* op = (BYTE*) dest; BYTE* const olimit = op + maxOutputSize; @@ -699,7 +712,7 @@ LZ4_FORCE_INLINE int LZ4_compress_generic( cctx->dictSize += (U32)inputSize; } cctx->currentOffset += (U32)inputSize; - cctx->tableType = tableType; + cctx->tableType = (U16)tableType; if (inputSize<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ @@ -1370,26 +1383,32 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize) -/*-***************************** -* Decompression functions -*******************************/ +/*-******************************* + * Decompression functions + ********************************/ + +typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; +typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive; + +#undef MIN +#define MIN(a,b) ( (a) < (b) ? (a) : (b) ) + /*! 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_O2_GCC_PPC64LE -LZ4_FORCE_INLINE int LZ4_decompress_generic( +LZ4_FORCE_INLINE int +LZ4_decompress_generic( const char* const src, char* const dst, int srcSize, int outputSize, /* If endOnInput==endOnInputSize, this value is `dstCapacity` */ - int endOnInput, /* endOnOutputSize, endOnInputSize */ - int partialDecoding, /* full, partial */ - int targetOutputSize, /* only used if partialDecoding==partial */ - int dict, /* noDict, withPrefix64k, usingExtDict */ + endCondition_directive endOnInput, /* endOnOutputSize, endOnInputSize */ + 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 */ @@ -1401,7 +1420,6 @@ LZ4_FORCE_INLINE int LZ4_decompress_generic( BYTE* op = (BYTE*) dst; BYTE* const oend = op + outputSize; BYTE* cpy; - BYTE* oexit = op + targetOutputSize; const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize; const unsigned inc32table[8] = {0, 1, 2, 1, 0, 4, 4, 4}; @@ -1414,12 +1432,13 @@ LZ4_FORCE_INLINE int LZ4_decompress_generic( const BYTE* const shortiend = iend - (endOnInput ? 14 : 8) /*maxLL*/ - 2 /*offset*/; const BYTE* const shortoend = oend - (endOnInput ? 14 : 8) /*maxLL*/ - 18 /*maxML*/; - DEBUGLOG(5, "LZ4_decompress_generic (srcSize:%i)", srcSize); + DEBUGLOG(5, "LZ4_decompress_generic (srcSize:%i, dstSize:%i)", srcSize, outputSize); /* Special cases */ - if ((partialDecoding) && (oexit > oend-MFLIMIT)) oexit = oend-MFLIMIT; /* targetOutputSize too high => just decode everything */ + assert(lowPrefix <= op); + assert(src != NULL); if ((endOnInput) && (unlikely(outputSize==0))) return ((srcSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */ - if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1); + if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0 ? 1 : -1); if ((endOnInput) && unlikely(srcSize==0)) return -1; /* Main Loop : decode sequences */ @@ -1428,7 +1447,7 @@ LZ4_FORCE_INLINE int LZ4_decompress_generic( size_t offset; unsigned const token = *ip++; - size_t length = token >> ML_BITS; /* literal length */ + size_t length = token >> ML_BITS; /* literal length */ assert(!endOnInput || ip <= iend); /* ip < iend before the increment */ @@ -1453,6 +1472,7 @@ LZ4_FORCE_INLINE int LZ4_decompress_generic( length = token & ML_MASK; /* match length */ offset = LZ4_readLE16(ip); ip += 2; match = op - offset; + assert(match <= op); /* check overflow */ /* Do not deal with overlapping matches. */ if ( (length != ML_MASK) @@ -1486,11 +1506,12 @@ LZ4_FORCE_INLINE int LZ4_decompress_generic( /* copy literals */ cpy = op+length; - if ( ((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) ) - || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) ) + LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH); + if ( ((endOnInput) && ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) ) + || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) ) { if (partialDecoding) { - if (cpy > oend) goto _output_error; /* Error : write attempt beyond end of output buffer */ + if (cpy > oend) { cpy = oend; length = oend-op; } /* Partial decoding : stop in the middle of literal segment */ if ((endOnInput) && (ip+length > iend)) goto _output_error; /* Error : read attempt beyond end of input buffer */ } else { if ((!endOnInput) && (cpy != oend)) goto _output_error; /* Error : block decoding must stop exactly there */ @@ -1499,10 +1520,15 @@ LZ4_FORCE_INLINE int LZ4_decompress_generic( memcpy(op, ip, length); ip += length; op += length; - break; /* Necessarily EOF, due to parsing restrictions */ + if (!partialDecoding || (cpy == oend)) { + /* Necessarily EOF, due to parsing restrictions */ + break; + } + + } else { + LZ4_wildCopy(op, ip, cpy); /* may overwrite up to WILDCOPYLENGTH beyond cpy */ + ip += length; op = cpy; } - LZ4_wildCopy(op, ip, cpy); - ip += length; op = cpy; /* get offset */ offset = LZ4_readLE16(ip); ip+=2; @@ -1513,7 +1539,11 @@ LZ4_FORCE_INLINE int LZ4_decompress_generic( _copy_match: if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */ - LZ4_write32(op, (U32)offset); /* costs ~1%; silence an msan warning when offset==0 */ + if (!partialDecoding) { + assert(oend > op); + assert(oend - op >= 4); + LZ4_write32(op, 0); /* silence an msan warning when offset==0; costs <1%; */ + } /* note : when partialDecoding, there is no guarantee that at least 4 bytes remain available in output buffer */ if (length == ML_MASK) { unsigned s; @@ -1526,21 +1556,24 @@ _copy_match: } length += MINMATCH; - /* check external dictionary */ + /* match starting within external dictionary */ if ((dict==usingExtDict) && (match < lowPrefix)) { - if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error; /* doesn't respect parsing restriction */ + if (unlikely(op+length > oend-LASTLITERALS)) { + if (partialDecoding) length = MIN(length, (size_t)(oend-op)); + else goto _output_error; /* doesn't respect parsing restriction */ + } if (length <= (size_t)(lowPrefix-match)) { - /* match can be copied as a single segment from external dictionary */ + /* match fits entirely within external dictionary : just copy */ memmove(op, dictEnd - (lowPrefix-match), length); op += length; } else { - /* match encompass external dictionary and current block */ - size_t const copySize = (size_t)(lowPrefix-match); + /* match stretches into both external dictionary and current block */ + size_t const copySize = (size_t)(lowPrefix - match); size_t const restSize = length - copySize; memcpy(op, dictEnd - copySize, copySize); op += copySize; - if (restSize > (size_t)(op-lowPrefix)) { /* overlap copy */ + if (restSize > (size_t)(op - lowPrefix)) { /* overlap copy */ BYTE* const endOfMatch = op + restSize; const BYTE* copyFrom = lowPrefix; while (op < endOfMatch) *op++ = *copyFrom++; @@ -1553,6 +1586,23 @@ _copy_match: /* copy match within block */ cpy = op + length; + + /* partialDecoding : may not respect endBlock parsing restrictions */ + assert(op<=oend); + if (partialDecoding && (cpy > oend-MATCH_SAFEGUARD_DISTANCE)) { + size_t const mlen = MIN(length, (size_t)(oend-op)); + const BYTE* const matchEnd = match + mlen; + BYTE* const copyEnd = op + mlen; + if (matchEnd > op) { /* overlap copy */ + while (op < copyEnd) *op++ = *match++; + } else { + memcpy(op, match, mlen); + } + op = copyEnd; + if (op==oend) break; + continue; + } + if (unlikely(offset<8)) { op[0] = match[0]; op[1] = match[1]; @@ -1561,23 +1611,26 @@ _copy_match: match += inc32table[offset]; memcpy(op+4, match, 4); match -= dec64table[offset]; - } else { memcpy(op, match, 8); match+=8; } + } else { + memcpy(op, match, 8); + match += 8; + } op += 8; - if (unlikely(cpy>oend-12)) { - BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1); + if (unlikely(cpy > oend-MATCH_SAFEGUARD_DISTANCE)) { + BYTE* const oCopyLimit = oend - (WILDCOPYLENGTH-1); if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last LASTLITERALS bytes must be literals (uncompressed) */ if (op < oCopyLimit) { LZ4_wildCopy(op, match, oCopyLimit); match += oCopyLimit - op; op = oCopyLimit; } - while (op<cpy) *op++ = *match++; + while (op < cpy) *op++ = *match++; } else { memcpy(op, match, 8); - if (length>16) LZ4_wildCopy(op+8, match+8, cpy); + if (length > 16) LZ4_wildCopy(op+8, match+8, cpy); } - op = cpy; /* correction */ + op = cpy; /* wildcopy correction */ } /* end of decoding */ @@ -1598,23 +1651,24 @@ LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, - endOnInputSize, full, 0, noDict, + endOnInputSize, decode_full_block, noDict, (BYTE*)dest, NULL, 0); } LZ4_FORCE_O2_GCC_PPC64LE -int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize) +int LZ4_decompress_safe_partial(const char* src, char* dst, int compressedSize, int targetOutputSize, int dstCapacity) { - return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, - endOnInputSize, partial, targetOutputSize, - noDict, (BYTE*)dest, NULL, 0); + dstCapacity = MIN(targetOutputSize, dstCapacity); + return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity, + endOnInputSize, partial_decode, + noDict, (BYTE*)dst, NULL, 0); } LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_fast(const char* source, char* dest, int originalSize) { return LZ4_decompress_generic(source, dest, 0, originalSize, - endOnOutputSize, full, 0, withPrefix64k, + endOnOutputSize, decode_full_block, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 0); } @@ -1624,7 +1678,7 @@ LZ4_FORCE_O2_GCC_PPC64LE /* 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, - endOnInputSize, full, 0, withPrefix64k, + endOnInputSize, decode_full_block, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 0); } @@ -1641,17 +1695,17 @@ static int LZ4_decompress_safe_withSmallPrefix(const char* source, char* dest, i size_t prefixSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, full, 0, noDict, + endOnInputSize, decode_full_block, noDict, (BYTE*)dest-prefixSize, NULL, 0); } -LZ4_FORCE_O2_GCC_PPC64LE /* Exported under another name, for tests/fullbench.c */ -#define LZ4_decompress_safe_extDict LZ4_decompress_safe_forceExtDict -int LZ4_decompress_safe_extDict(const char* source, char* dest, int compressedSize, int maxOutputSize, - const void* dictStart, size_t dictSize) +LZ4_FORCE_O2_GCC_PPC64LE +int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, + int compressedSize, int maxOutputSize, + const void* dictStart, size_t dictSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, full, 0, usingExtDict, + endOnInputSize, decode_full_block, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize); } @@ -1660,7 +1714,7 @@ static int LZ4_decompress_fast_extDict(const char* source, char* dest, int origi const void* dictStart, size_t dictSize) { return LZ4_decompress_generic(source, dest, 0, originalSize, - endOnOutputSize, full, 0, usingExtDict, + endOnOutputSize, decode_full_block, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize); } @@ -1673,7 +1727,7 @@ int LZ4_decompress_safe_doubleDict(const char* source, char* dest, int compresse size_t prefixSize, const void* dictStart, size_t dictSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, full, 0, usingExtDict, + endOnInputSize, decode_full_block, usingExtDict, (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize); } @@ -1682,7 +1736,7 @@ int LZ4_decompress_fast_doubleDict(const char* source, char* dest, int originalS size_t prefixSize, const void* dictStart, size_t dictSize) { return LZ4_decompress_generic(source, dest, 0, originalSize, - endOnOutputSize, full, 0, usingExtDict, + endOnOutputSize, decode_full_block, usingExtDict, (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize); } @@ -1773,8 +1827,8 @@ int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const ch /* 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_extDict(source, dest, compressedSize, maxOutputSize, - lz4sd->externalDict, lz4sd->extDictSize); + result = LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, + lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; lz4sd->prefixSize = result; lz4sd->prefixEnd = (BYTE*)dest + result; @@ -1834,7 +1888,7 @@ int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressed return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize); return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, dictSize); } - return LZ4_decompress_safe_extDict(source, dest, compressedSize, maxOutputSize, dictStart, dictSize); + return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, dictSize); } int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize) @@ -1,7 +1,7 @@ /* * LZ4 - Fast LZ compression algorithm * Header File - * Copyright (C) 2011-2017, Yann Collet. + * Copyright (C) 2011-present, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -46,7 +46,7 @@ extern "C" { /** Introduction - LZ4 is lossless compression algorithm, providing compression speed at 400 MB/s per core, + LZ4 is lossless compression algorithm, providing compression speed at 500 MB/s per core, scalable with multi-cores CPU. It features an extremely fast decoder, with speed in multiple GB/s per core, typically reaching RAM speed limits on multi-core systems. @@ -62,8 +62,8 @@ extern "C" { An additional format, called LZ4 frame specification (doc/lz4_Frame_format.md), take care of encoding standard metadata alongside LZ4-compressed blocks. - If your application requires interoperability, it's recommended to use it. - A library is provided to take care of it, see lz4frame.h. + Frame format is required for interoperability. + It is delivered through a companion API, declared in lz4frame.h. */ /*^*************************************************************** @@ -93,7 +93,7 @@ extern "C" { /*------ Version ------*/ #define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */ #define LZ4_VERSION_MINOR 8 /* for new (non-breaking) interface capabilities */ -#define LZ4_VERSION_RELEASE 2 /* for tweaks, bug-fixes, or development */ +#define LZ4_VERSION_RELEASE 3 /* for tweaks, bug-fixes, or development */ #define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE) @@ -183,55 +183,72 @@ LZ4_compress_fast_extState() : Same compression function, just using an externally allocated memory space to store compression state. Use LZ4_sizeofState() to know how much memory must be allocated, and allocate it on 8-bytes boundaries (using malloc() typically). - Then, provide it as 'void* state' to compression function. + Then, provide this buffer as 'void* state' to compression function. */ LZ4LIB_API int LZ4_sizeofState(void); LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); -/*! -LZ4_compress_destSize() : - Reverse the logic : compresses as much data as possible from 'src' buffer - into already allocated buffer 'dst' of size 'targetDestSize'. - This function either compresses the entire 'src' content into 'dst' if it's large enough, - or fill 'dst' buffer completely with as much data as possible from 'src'. - *srcSizePtr : will be modified to indicate how many bytes where read from 'src' to fill 'dst'. - New value is necessarily <= old value. - return : Nb bytes written into 'dst' (necessarily <= targetDestSize) - or 0 if compression fails +/*! LZ4_compress_destSize() : + * Reverse the logic : compresses as much data as possible from 'src' buffer + * into already allocated buffer 'dst', of size >= 'targetDestSize'. + * This function either compresses the entire 'src' content into 'dst' if it's large enough, + * or fill 'dst' buffer completely with as much data as possible from 'src'. + * note: acceleration parameter is fixed to "default". + * + * *srcSizePtr : will be modified to indicate how many bytes where read from 'src' to fill 'dst'. + * New value is necessarily <= input value. + * @return : Nb bytes written into 'dst' (necessarily <= targetDestSize) + * or 0 if compression fails. */ LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePtr, int targetDstSize); -/*! -LZ4_decompress_fast() : **unsafe!** -This function is a bit faster than LZ4_decompress_safe(), -but it may misbehave on malformed input because it doesn't perform full validation of compressed data. - originalSize : is the uncompressed size to regenerate - Destination buffer must be already allocated, and its size must be >= 'originalSize' bytes. - return : number of bytes read from source buffer (== compressed size). - If the source stream is detected malformed, the function stops decoding and return a negative result. - note : This function is only usable if the originalSize of uncompressed data is known in advance. - The caller should also check that all the compressed input has been consumed properly, - i.e. that the return value matches the size of the buffer with compressed input. - The function never writes past the output buffer. However, since it doesn't know its 'src' size, - it may read past the intended input. Also, because match offsets are not validated during decoding, - reads from 'src' may underflow. Use this function in trusted environment **only**. -*/ +/*! LZ4_decompress_fast() : **unsafe!** + * This function used to be a bit faster than LZ4_decompress_safe(), + * though situation has changed in recent versions, + * and now `LZ4_decompress_safe()` can be as fast and sometimes faster than `LZ4_decompress_fast()`. + * Moreover, LZ4_decompress_fast() is not protected vs malformed input, as it doesn't perform full validation of compressed data. + * As a consequence, this function is no longer recommended, and may be deprecated in future versions. + * It's only remaining specificity is that it can decompress data without knowing its compressed size. + * + * originalSize : is the uncompressed size to regenerate. + * `dst` must be already allocated, its size must be >= 'originalSize' bytes. + * @return : number of bytes read from source buffer (== compressed size). + * If the source stream is detected malformed, the function stops decoding and returns a negative result. + * note : This function requires uncompressed originalSize to be known in advance. + * The function never writes past the output buffer. + * However, since it doesn't know its 'src' size, it may read past the intended input. + * Also, because match offsets are not validated during decoding, + * reads from 'src' may underflow. + * Use this function in trusted environment **only**. + */ LZ4LIB_API int LZ4_decompress_fast (const char* src, char* dst, int originalSize); -/*! -LZ4_decompress_safe_partial() : - This function decompress a compressed block of size 'srcSize' at position 'src' - into destination buffer 'dst' of size 'dstCapacity'. - The function will decompress a minimum of 'targetOutputSize' bytes, and stop after that. - However, it's not accurate, and may write more than 'targetOutputSize' (but always <= dstCapacity). - @return : the number of bytes decoded in the destination buffer (necessarily <= dstCapacity) - Note : this number can also be < targetOutputSize, if compressed block contains less data. - Therefore, always control how many bytes were decoded. - If source stream is detected malformed, function returns a negative result. - This function is protected against malicious data packets. -*/ +/*! LZ4_decompress_safe_partial() : + * Decompress an LZ4 compressed block, of size 'srcSize' at position 'src', + * into destination buffer 'dst' of size 'dstCapacity'. + * Up to 'targetOutputSize' bytes will be decoded. + * The function stops decoding on reaching this objective, + * which can boost performance when only the beginning of a block is required. + * + * @return : the number of bytes decoded in `dst` (necessarily <= dstCapacity) + * If source stream is detected malformed, function returns a negative result. + * + * Note : @return can be < targetOutputSize, if compressed block contains less data. + * + * Note 2 : this function features 2 parameters, targetOutputSize and dstCapacity, + * and expects targetOutputSize <= dstCapacity. + * It effectively stops decoding on reaching targetOutputSize, + * so dstCapacity is kind of redundant. + * This is because in a previous version of this function, + * decoding operation would not "break" a sequence in the middle. + * As a consequence, there was no guarantee that decoding would stop at exactly targetOutputSize, + * it could write more bytes, though only up to dstCapacity. + * Some "margin" used to be required for this operation to work properly. + * This is no longer necessary. + * The function nonetheless keeps its signature, in an effort to not break API. + */ LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcSize, int targetOutputSize, int dstCapacity); @@ -266,16 +283,23 @@ LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, in * 'dst' buffer must be already allocated. * If dstCapacity >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster. * - * Important : The previous 64KB of compressed data is assumed to remain present and unmodified in memory! - * - * Special 1 : When input is a double-buffer, they can have any size, including < 64 KB. - * Make sure that buffers are separated by at least one byte. - * This way, each block only depends on previous block. - * Special 2 : If input buffer is a ring-buffer, it can have any size, including < 64 KB. - * * @return : size of compressed block * or 0 if there is an error (typically, cannot fit into 'dst'). - * After an error, the stream status is invalid, it can only be reset or freed. + * + * Note 1 : Each invocation to LZ4_compress_fast_continue() generates a new block. + * Each block has precise boundaries. + * It's not possible to append blocks together and expect a single invocation of LZ4_decompress_*() to decompress them together. + * Each block must be decompressed separately, calling LZ4_decompress_*() with associated metadata. + * + * Note 2 : The previous 64KB of source data is __assumed__ to remain present, unmodified, at same address in memory! + * + * Note 3 : When input is structured as a double-buffer, each buffer can have any size, including < 64 KB. + * Make sure that buffers are separated, by at least one byte. + * This construction ensures that each block only depends on previous block. + * + * Note 4 : If input buffer is a ring-buffer, it can have any size, including < 64 KB. + * + * Note 5 : After an error, the stream status is invalid, it can only be reset or freed. */ LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); @@ -305,7 +329,7 @@ LZ4LIB_API int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_str /*! LZ4_setStreamDecode() : * An LZ4_streamDecode_t context can be allocated once and re-used multiple times. * Use this function to start decompression of a new stream of blocks. - * A dictionary can optionnally be set. Use NULL or size 0 for a reset order. + * A dictionary can optionally be set. Use NULL or size 0 for a reset order. * Dictionary is presumed stable : it must remain accessible and unmodified during next decompression. * @return : 1 if OK, 0 if error */ diff --git a/lib/lz4frame.c b/lib/lz4frame.c index e1d0b1d..08bf0fa 100644 --- a/lib/lz4frame.c +++ b/lib/lz4frame.c @@ -738,7 +738,7 @@ static size_t LZ4F_makeBlock(void* dst, const void* src, size_t srcSize, static int LZ4F_compressBlock(void* ctx, const char* src, char* dst, int srcSize, int dstCapacity, int level, const LZ4F_CDict* cdict) { - int const acceleration = (level < -1) ? -level : 1; + int const acceleration = (level < 0) ? -level + 1 : 1; LZ4F_initStream(ctx, cdict, level, LZ4F_blockIndependent); if (cdict) { return LZ4_compress_fast_continue((LZ4_stream_t*)ctx, src, dst, srcSize, dstCapacity, acceleration); @@ -749,7 +749,7 @@ static int LZ4F_compressBlock(void* ctx, const char* src, char* dst, int srcSize static int LZ4F_compressBlock_continue(void* ctx, const char* src, char* dst, int srcSize, int dstCapacity, int level, const LZ4F_CDict* cdict) { - int const acceleration = (level < -1) ? -level : 1; + int const acceleration = (level < 0) ? -level + 1 : 1; (void)cdict; /* init once at beginning of frame */ return LZ4_compress_fast_continue((LZ4_stream_t*)ctx, src, dst, srcSize, dstCapacity, acceleration); } diff --git a/lib/lz4frame.h b/lib/lz4frame.h index fb434ff..75f1fd9 100644 --- a/lib/lz4frame.h +++ b/lib/lz4frame.h @@ -33,9 +33,10 @@ */ /* LZ4F is a stand-alone API to create LZ4-compressed frames - * conformant with specification v1.5.1. + * conformant with specification v1.6.1. * It also offers streaming capabilities. - * lz4.h is not required when using lz4frame.h. + * lz4.h is not required when using lz4frame.h, + * except to get constant such as LZ4_VERSION_NUMBER. * */ #ifndef LZ4F_H_09782039843 @@ -159,8 +160,9 @@ typedef LZ4F_contentChecksum_t contentChecksum_t; /*! LZ4F_frameInfo_t : * makes it possible to set or read frame parameters. - * It's not required to set all fields, as long as the structure was initially memset() to zero. - * For all fields, 0 sets it to default value */ + * Structure must be first init to 0, using memset() or LZ4F_INIT_FRAMEINFO, + * setting all parameters to default. + * It's then possible to update selectively some parameters */ typedef struct { LZ4F_blockSizeID_t blockSizeID; /* max64KB, max256KB, max1MB, max4MB; 0 == default */ LZ4F_blockMode_t blockMode; /* LZ4F_blockLinked, LZ4F_blockIndependent; 0 == default */ @@ -171,24 +173,30 @@ typedef struct { LZ4F_blockChecksum_t blockChecksumFlag; /* 1: each block followed by a checksum of block's compressed data; 0: disabled (default) */ } LZ4F_frameInfo_t; +#define LZ4F_INIT_FRAMEINFO { 0, 0, 0, 0, 0, 0, 0 } /* v1.8.3+ */ + /*! LZ4F_preferences_t : - * makes it possible to supply detailed compression parameters to the stream interface. - * Structure is presumed initially memset() to zero, representing default settings. + * makes it possible to supply advanced compression instructions to streaming interface. + * Structure must be first init to 0, using memset() or LZ4F_INIT_PREFERENCES, + * setting all parameters to default. * All reserved fields must be set to zero. */ typedef struct { LZ4F_frameInfo_t frameInfo; int compressionLevel; /* 0: default (fast mode); values > LZ4HC_CLEVEL_MAX count as LZ4HC_CLEVEL_MAX; values < 0 trigger "fast acceleration" */ - unsigned autoFlush; /* 1: always flush, to reduce usage of internal buffers */ - unsigned favorDecSpeed; /* 1: parser favors decompression speed vs compression ratio. Only works for high compression modes (>= LZ4LZ4HC_CLEVEL_OPT_MIN) */ /* >= v1.8.2 */ + unsigned autoFlush; /* 1: always flush; reduces usage of internal buffers */ + unsigned favorDecSpeed; /* 1: parser favors decompression speed vs compression ratio. Only works for high compression modes (>= LZ4HC_CLEVEL_OPT_MIN) */ /* v1.8.2+ */ unsigned reserved[3]; /* must be zero for forward compatibility */ } LZ4F_preferences_t; -LZ4FLIB_API int LZ4F_compressionLevel_max(void); +#define LZ4F_INIT_PREFERENCES { LZ4F_INIT_FRAMEINFO, 0, 0, 0, { 0, 0, 0 } } /* v1.8.3+ */ /*-********************************* * Simple compression function ***********************************/ + +LZ4FLIB_API int LZ4F_compressionLevel_max(void); + /*! LZ4F_compressFrameBound() : * Returns the maximum possible compressed size with LZ4F_compressFrame() given srcSize and preferences. * `preferencesPtr` is optional. It can be replaced by NULL, in which case, the function will assume default preferences. @@ -222,8 +230,9 @@ typedef struct { /*--- Resource Management ---*/ -#define LZ4F_VERSION 100 +#define LZ4F_VERSION 100 /* This number can be used to check for an incompatible API breaking change */ LZ4FLIB_API unsigned LZ4F_getVersion(void); + /*! LZ4F_createCompressionContext() : * The first thing to do is to create a compressionContext object, which will be used in all compression operations. * This is achieved using LZ4F_createCompressionContext(), which takes as argument a version. diff --git a/lib/lz4hc.c b/lib/lz4hc.c index 8108ea0..e913ee7 100644 --- a/lib/lz4hc.c +++ b/lib/lz4hc.c @@ -327,6 +327,8 @@ LZ4HC_InsertAndGetWiderMatch ( if (lookBackLength==0) { /* no back possible */ size_t const maxML = MIN(currentSegmentLength, srcPatternLength); if ((size_t)longest < maxML) { + assert(base + matchIndex < ip); + if (ip - (base+matchIndex) > MAX_DISTANCE) break; assert(maxML < 2 GB); longest = (int)maxML; *matchpos = base + matchIndex; /* virtual pos, relative to ip, to retrieve offset */ @@ -450,6 +452,7 @@ LZ4_FORCE_INLINE int LZ4HC_encodeSequence ( *op += length; /* Encode Offset */ + assert( (*ip - match) <= MAX_DISTANCE ); /* note : consider providing offset as a value, rather than as a pointer difference */ LZ4_writeLE16(*op, (U16)(*ip-match)); *op += 2; /* Encode MatchLength */ diff --git a/lib/lz4hc.h b/lib/lz4hc.h index bb5e073..970fa39 100644 --- a/lib/lz4hc.h +++ b/lib/lz4hc.h @@ -246,6 +246,10 @@ LZ4_DEPRECATED("use LZ4_resetStreamHC() instead") LZ4LIB_API int LZ4_resetStr #ifndef LZ4_HC_SLO_098092834 #define LZ4_HC_SLO_098092834 +#if defined (__cplusplus) +extern "C" { +#endif + /*! LZ4_compress_HC_destSize() : v1.8.0 (experimental) * Will try to compress as much data from `src` as possible * that can fit into `targetDstSize` budget. @@ -343,5 +347,9 @@ int LZ4_compress_HC_extStateHC_fastReset (void* state, const char* src, char* ds */ LZ4LIB_API void LZ4_attach_HC_dictionary(LZ4_streamHC_t *working_stream, const LZ4_streamHC_t *dictionary_stream); +#if defined (__cplusplus) +} +#endif + #endif /* LZ4_HC_SLO_098092834 */ #endif /* LZ4_HC_STATIC_LINKING_ONLY */ |