diff --git a/lib/compress/zstd_compress.c b/lib/compress/zstd_compress.c index 508ce1fa5..765c8e34d 100644 --- a/lib/compress/zstd_compress.c +++ b/lib/compress/zstd_compress.c @@ -344,8 +344,12 @@ size_t ZSTD_copyCCtx(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx, unsigned long { if (srcCCtx->stage!=ZSTDcs_init) return ERROR(stage_wrong); + memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem)); - ZSTD_resetCCtx_advanced(dstCCtx, srcCCtx->params, pledgedSrcSize, ZSTDcrp_noMemset); + { ZSTD_parameters params = srcCCtx->params; + params.fParams.contentSizeFlag = (pledgedSrcSize > 0); + ZSTD_resetCCtx_advanced(dstCCtx, params, pledgedSrcSize, ZSTDcrp_noMemset); + } /* copy tables */ { size_t const chainSize = (srcCCtx->params.cParams.strategy == ZSTD_fast) ? 0 : (1 << srcCCtx->params.cParams.chainLog); @@ -2362,7 +2366,7 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity, U32 const dictIDSizeCode = (dictID>0) + (dictID>=256) + (dictID>=65536); /* 0-3 */ U32 const checksumFlag = params.fParams.checksumFlag>0; U32 const windowSize = 1U << params.cParams.windowLog; - U32 const singleSegment = params.fParams.contentSizeFlag && (windowSize > pledgedSrcSize); + U32 const singleSegment = params.fParams.contentSizeFlag && (windowSize >= pledgedSrcSize); BYTE const windowLogByte = (BYTE)((params.cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3); U32 const fcsCode = params.fParams.contentSizeFlag ? (pledgedSrcSize>=256) + (pledgedSrcSize>=65536+256) + (pledgedSrcSize>=0xFFFFFFFFU) : /* 0-3 */ @@ -2845,7 +2849,11 @@ static ZSTD_parameters ZSTD_getParamsFromCDict(const ZSTD_CDict* cdict) { size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict, unsigned long long pledgedSrcSize) { if (cdict->dictContentSize) CHECK_F(ZSTD_copyCCtx(cctx, cdict->refContext, pledgedSrcSize)) - else CHECK_F(ZSTD_compressBegin_advanced(cctx, NULL, 0, cdict->refContext->params, pledgedSrcSize)); + else { + ZSTD_parameters params = cdict->refContext->params; + params.fParams.contentSizeFlag = (pledgedSrcSize > 0); + CHECK_F(ZSTD_compressBegin_advanced(cctx, NULL, 0, params, pledgedSrcSize)); + } return 0; } @@ -2939,7 +2947,7 @@ size_t ZSTD_freeCStream(ZSTD_CStream* zcs) size_t ZSTD_CStreamInSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX; } size_t ZSTD_CStreamOutSize(void) { return ZSTD_compressBound(ZSTD_BLOCKSIZE_ABSOLUTEMAX) + ZSTD_blockHeaderSize + 4 /* 32-bits hash */ ; } -size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize) +static size_t ZSTD_resetCStream_internal(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize) { if (zcs->inBuffSize==0) return ERROR(stage_wrong); /* zcs has not been init at least once => can't reset */ @@ -2957,6 +2965,14 @@ size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize) return 0; /* ready to go */ } +size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize) +{ + + zcs->params.fParams.contentSizeFlag = (pledgedSrcSize > 0); + + return ZSTD_resetCStream_internal(zcs, pledgedSrcSize); +} + size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize) @@ -2988,7 +3004,7 @@ size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, zcs->checksum = params.fParams.checksumFlag > 0; zcs->params = params; - return ZSTD_resetCStream(zcs, pledgedSrcSize); + return ZSTD_resetCStream_internal(zcs, pledgedSrcSize); } /* note : cdict must outlive compression session */ diff --git a/lib/zstd.h b/lib/zstd.h index 5de11b012..900a4c0c5 100644 --- a/lib/zstd.h +++ b/lib/zstd.h @@ -88,44 +88,12 @@ ZSTDLIB_API size_t ZSTD_compress( void* dst, size_t dstCapacity, ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity, const void* src, size_t compressedSize); -#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) -#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) - -/*! ZSTD_getFrameContentSize() : -* `src` should point to the start of a ZSTD encoded frame -* @return : decompressed size of the frame pointed to be `src` if known, otherwise -* - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined -* - ZSTD_CONTENTSIZE_ERROR if an error occured (e.g. invalid magic number, srcSize too small) */ -ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); - -/*! ZSTD_findDecompressedSize() : -* `src` should point the start of a series of ZSTD encoded and/or skippable frames -* `srcSize` must be the _exact_ size of this series -* (i.e. there should be a frame boundary exactly `srcSize` bytes after `src`) -* @return : the decompressed size of all data in the contained frames, as a 64-bit value _if known_ -* - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN -* - if an error occurred: ZSTD_CONTENTSIZE_ERROR -* -* note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode. -* When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size. -* In which case, it's necessary to use streaming mode to decompress data. -* Optionally, application can still use ZSTD_decompress() while relying on implied limits. -* (For example, data may be necessarily cut into blocks <= 16 KB). -* note 2 : decompressed size is always present when compression is done with ZSTD_compress() -* note 3 : decompressed size can be very large (64-bits value), -* potentially larger than what local system can handle as a single memory segment. -* In which case, it's necessary to use streaming mode to decompress data. -* note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified. -* Always ensure result fits within application's authorized limits. -* Each application can set its own limits. -* note 5 : ZSTD_findDecompressedSize handles multiple frames, and so it must traverse the input to -* read each contained frame header. This is efficient as most of the data is skipped, -* however it does mean that all frame data must be present and valid. */ -ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize); - /*! ZSTD_getDecompressedSize() : -* WARNING: This function is now obsolete. ZSTD_findDecompressedSize should be used, -* or if only exactly one ZSTD frame is needed, ZSTD_getFrameContentSize can be used. +* NOTE: This function is planned to be obsolete, in favour of ZSTD_findDecompressedSize, +* or for single frames, ZSTD_getFrameContentSize. Both of the new functions return more +* descriptive return values, disambiguating empty frames from size unknown or errors. +* Additionally, ZSTD_findDecompressedSize handles multi-frame inputs, returning the total +* size of all frames put together. * * 'src' is the start of a zstd compressed frame. * @return : content size to be decompressed, as a 64-bits value _if known_, 0 otherwise. @@ -369,6 +337,9 @@ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output #define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */ #define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U +#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) + #define ZSTD_WINDOWLOG_MAX_32 25 #define ZSTD_WINDOWLOG_MAX_64 27 #define ZSTD_WINDOWLOG_MAX ((U32)(MEM_32bits() ? ZSTD_WINDOWLOG_MAX_32 : ZSTD_WINDOWLOG_MAX_64)) @@ -422,6 +393,41 @@ typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size); typedef void (*ZSTD_freeFunction) (void* opaque, void* address); typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem; +/*************************************** +* Decompressed size functions +***************************************/ +/*! ZSTD_getFrameContentSize() : +* `src` should point to the start of a ZSTD encoded frame +* @return : decompressed size of the frame pointed to be `src` if known, otherwise +* - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined +* - ZSTD_CONTENTSIZE_ERROR if an error occured (e.g. invalid magic number, srcSize too small) */ +ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); + +/*! ZSTD_findDecompressedSize() : +* `src` should point the start of a series of ZSTD encoded and/or skippable frames +* `srcSize` must be the _exact_ size of this series +* (i.e. there should be a frame boundary exactly `srcSize` bytes after `src`) +* @return : the decompressed size of all data in the contained frames, as a 64-bit value _if known_ +* - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN +* - if an error occurred: ZSTD_CONTENTSIZE_ERROR +* +* note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode. +* When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size. +* In which case, it's necessary to use streaming mode to decompress data. +* Optionally, application can still use ZSTD_decompress() while relying on implied limits. +* (For example, data may be necessarily cut into blocks <= 16 KB). +* note 2 : decompressed size is always present when compression is done with ZSTD_compress() +* note 3 : decompressed size can be very large (64-bits value), +* potentially larger than what local system can handle as a single memory segment. +* In which case, it's necessary to use streaming mode to decompress data. +* note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified. +* Always ensure result fits within application's authorized limits. +* Each application can set its own limits. +* note 5 : ZSTD_findDecompressedSize handles multiple frames, and so it must traverse the input to +* read each contained frame header. This is efficient as most of the data is skipped, +* however it does mean that all frame data must be present and valid. */ +ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize); + /*************************************** * Advanced compression functions @@ -555,12 +561,12 @@ ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); /*===== Advanced Streaming compression functions =====*/ ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem); -ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); /**< pledgedSrcSize must be correct */ +ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); /**< pledgedSrcSize must be correct, a size of 0 means unknown. for a frame size of 0 use initCStream_advanced */ ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< note: a dict will not be used if dict == NULL or dictSize < 8 */ ZSTDLIB_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize is optional and can be 0 (meaning unknown). note: if the contentSizeFlag is set, pledgedSrcSize == 0 means the source size is actually 0 */ ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); /**< note : cdict will just be referenced, and must outlive compression session */ -ZSTDLIB_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize); /**< re-use compression parameters from previous init; skip dictionary loading stage; zcs must be init at least once before */ +ZSTDLIB_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize); /**< re-use compression parameters from previous init; skip dictionary loading stage; zcs must be init at least once before. note: pledgedSrcSize must be correct, a size of 0 means unknown. for a frame size of 0 use initCStream_advanced */ ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs); @@ -617,8 +623,8 @@ ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds); ZSTDLIB_API size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel); ZSTDLIB_API size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel); ZSTDLIB_API size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize is optional and can be 0 (meaning unknown). note: if the contentSizeFlag is set, pledgedSrcSize == 0 means the source size is actually 0 */ -ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); -ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict, unsigned long long pledgedSrcSize); +ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); /**< note: if pledgedSrcSize can be 0, indicating unknown size. if it is non-zero, it must be accurate. for 0 size frames, use compressBegin_advanced */ +ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict, unsigned long long pledgedSrcSize); /**< note: if pledgedSrcSize can be 0, indicating unknown size. if it is non-zero, it must be accurate. for 0 size frames, use compressBegin_advanced */ ZSTDLIB_API size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); diff --git a/tests/Makefile b/tests/Makefile index 83e10ad7c..5c966534c 100644 --- a/tests/Makefile +++ b/tests/Makefile @@ -27,7 +27,7 @@ TESTARTEFACT := versionsTest namespaceTest CPPFLAGS+= -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(ZSTDDIR)/compress -I$(ZSTDDIR)/dictBuilder -I$(ZSTDDIR)/deprecated -I$(PRGDIR) -CFLAGS ?= -g +CFLAGS ?= -O3 CFLAGS += -g -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow -Wstrict-aliasing=1 \ -Wswitch-enum -Wdeclaration-after-statement -Wstrict-prototypes -Wundef CFLAGS += $(MOREFLAGS) diff --git a/tests/zstreamtest.c b/tests/zstreamtest.c index 747e9a445..5680d27c1 100644 --- a/tests/zstreamtest.c +++ b/tests/zstreamtest.c @@ -438,6 +438,34 @@ static int basicUnitTests(U32 seed, double compressibility, ZSTD_customMem custo if (!ZSTD_isError(r)) goto _output_error; /* must fail : frame requires > 100 bytes */ DISPLAYLEVEL(3, "OK (%s)\n", ZSTD_getErrorName(r)); } + /* Unknown srcSize */ + DISPLAYLEVEL(3, "test%3i : pledgedSrcSize == 0 behaves properly : ", testNb++); + { ZSTD_parameters params = ZSTD_getParams(5, 0, 0); + params.fParams.contentSizeFlag = 1; + ZSTD_initCStream_advanced(zc, NULL, 0, params, 0); } /* cstream advanced should write the 0 size field */ + inBuff.src = CNBuffer; + inBuff.size = 0; + inBuff.pos = 0; + outBuff.dst = compressedBuffer; + outBuff.size = compressedBufferSize; + outBuff.pos = 0; + if (ZSTD_isError(ZSTD_compressStream(zc, &outBuff, &inBuff))) goto _output_error; + if (ZSTD_endStream(zc, &outBuff) != 0) goto _output_error; + cSize = outBuff.pos; + if (ZSTD_findDecompressedSize(compressedBuffer, cSize) != 0) goto _output_error; + + ZSTD_resetCStream(zc, 0); /* resetCStream should treat 0 as unknown */ + inBuff.src = CNBuffer; + inBuff.size = 0; + inBuff.pos = 0; + outBuff.dst = compressedBuffer; + outBuff.size = compressedBufferSize; + outBuff.pos = 0; + if (ZSTD_isError(ZSTD_compressStream(zc, &outBuff, &inBuff))) goto _output_error; + if (ZSTD_endStream(zc, &outBuff) != 0) goto _output_error; + cSize = outBuff.pos; + if (ZSTD_findDecompressedSize(compressedBuffer, cSize) != ZSTD_CONTENTSIZE_UNKNOWN) goto _output_error; + DISPLAYLEVEL(3, "OK \n"); _end: FUZ_freeDictionary(dictionary);