diff --git a/polymer/eduke32/build/include/lz4.h b/polymer/eduke32/build/include/lz4.h index 0bfe44af4..3b0142214 100644 --- a/polymer/eduke32/build/include/lz4.h +++ b/polymer/eduke32/build/include/lz4.h @@ -1,7 +1,8 @@ /* LZ4 - Fast LZ compression algorithm Header File - Copyright (C) 2011-2013, Yann Collet. + Copyright (C) 2011-2015, Yann Collet. + BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) Redistribution and use in source and binary forms, with or without @@ -28,8 +29,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. You can contact the author at : - - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html - - LZ4 source repository : http://code.google.com/p/lz4/ + - LZ4 source repository : https://github.com/Cyan4973/lz4 + - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c */ #pragma once @@ -37,213 +38,321 @@ extern "C" { #endif +/* + * lz4.h provides block compression functions, and gives full buffer control to programmer. + * If you need to generate inter-operable compressed data (respecting LZ4 frame specification), + * and can let the library handle its own memory, please use lz4frame.h instead. +*/ -/************************************** - Version -**************************************/ -#define LZ4_VERSION_MAJOR 1 /* for major interface/format changes */ -#define LZ4_VERSION_MINOR 1 /* for minor interface/format changes */ -#define LZ4_VERSION_RELEASE 3 /* for tweaks, bug-fixes, or development */ +/************************************** +* Version +**************************************/ +#define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */ +#define LZ4_VERSION_MINOR 7 /* for new (non-breaking) interface capabilities */ +#define LZ4_VERSION_RELEASE 1 /* for tweaks, bug-fixes, or development */ +#define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE) +int LZ4_versionNumber (void); + +/************************************** +* Tuning parameter +**************************************/ +/* + * LZ4_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 LZ4_MEMORY_USAGE 14 /************************************** - Compiler Options -**************************************/ -#if (defined(__GNUC__) && defined(__STRICT_ANSI__)) || (defined(_MSC_VER) && !defined(__cplusplus)) /* Visual Studio */ -# define inline __inline /* Visual C is not C99, but supports some kind of inline */ -#endif - - -/************************************** - Simple Functions +* Simple Functions **************************************/ -int LZ4_compress (const char* source, char* dest, int inputSize); -int LZ4_decompress_safe (const char* source, char* dest, int inputSize, int maxOutputSize); +int LZ4_compress_default(const char* source, char* dest, int sourceSize, int maxDestSize); +int LZ4_decompress_safe (const char* source, char* dest, int compressedSize, int maxDecompressedSize); /* -LZ4_compress() : - Compresses 'inputSize' bytes from 'source' into 'dest'. - Destination buffer must be already allocated, - and must be sized to handle worst cases situations (input data not compressible) - Worst case size evaluation is provided by function LZ4_compressBound() - inputSize : Max supported value is LZ4_MAX_INPUT_VALUE - return : the number of bytes written in buffer dest - or 0 if the compression fails +LZ4_compress_default() : + Compresses 'sourceSize' bytes from buffer 'source' + into already allocated 'dest' buffer of size 'maxDestSize'. + Compression is guaranteed to succeed if 'maxDestSize' >= LZ4_compressBound(sourceSize). + It also runs faster, so it's a recommended setting. + If the function cannot compress 'source' into a more limited 'dest' budget, + compression stops *immediately*, and the function result is zero. + As a consequence, 'dest' content is not valid. + This function never writes outside 'dest' buffer, nor read outside 'source' buffer. + sourceSize : Max supported value is LZ4_MAX_INPUT_VALUE + maxDestSize : full or partial size of buffer 'dest' (which must be already allocated) + return : the number of bytes written into buffer 'dest' (necessarily <= maxOutputSize) + or 0 if compression fails LZ4_decompress_safe() : - maxOutputSize : is the size of the destination buffer (which must be already allocated) - return : the number of bytes decoded in the destination buffer (necessarily <= maxOutputSize) + compressedSize : is the precise full size of the compressed block. + maxDecompressedSize : is the size of destination buffer, which must be already allocated. + return : the number of bytes decompressed into destination buffer (necessarily <= maxDecompressedSize) + If destination buffer is not large enough, decoding will stop and output an error code (<0). If the source stream is detected malformed, the function will stop decoding and return a negative result. - This function is protected against buffer overflow exploits (never writes outside of output buffer, and never reads outside of input buffer). Therefore, it is protected against malicious data packets + This function is protected against buffer overflow exploits, including malicious data packets. + It never writes outside output buffer, nor reads outside input buffer. */ /************************************** - Advanced Functions +* Advanced Functions **************************************/ #define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */ -#define LZ4_COMPRESSBOUND(isize) ((unsigned int)(isize) > (unsigned int)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16) -static inline int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } +#define LZ4_COMPRESSBOUND(isize) ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16) /* LZ4_compressBound() : - Provides the maximum size that LZ4 may output in a "worst case" scenario (input data not compressible) - primarily useful for memory allocation of output buffer. - inline function is recommended for the general case, - macro is also provided when result needs to be evaluated at compilation (such as stack memory allocation). - - isize : is the input size. Max supported value is LZ4_MAX_INPUT_SIZE - return : maximum output size in a "worst case" scenario - or 0, if input size is too large ( > LZ4_MAX_INPUT_SIZE) + Provides the maximum size that LZ4 compression may output in a "worst case" scenario (input data not compressible) + This function is primarily useful for memory allocation purposes (destination buffer size). + Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example). + Note that LZ4_compress_default() compress faster when dest buffer size is >= LZ4_compressBound(srcSize) + inputSize : max supported value is LZ4_MAX_INPUT_SIZE + return : maximum output size in a "worst case" scenario + or 0, if input size is too large ( > LZ4_MAX_INPUT_SIZE) */ - - -int LZ4_compress_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize); +int LZ4_compressBound(int inputSize); /* -LZ4_compress_limitedOutput() : - Compress 'inputSize' bytes from 'source' into an output buffer 'dest' of maximum size 'maxOutputSize'. - If it cannot achieve it, compression will stop, and result of the function will be zero. - This function never writes outside of provided output buffer. - - inputSize : Max supported value is LZ4_MAX_INPUT_VALUE - maxOutputSize : is the size of the destination buffer (which must be already allocated) - return : the number of bytes written in buffer 'dest' - or 0 if the compression fails +LZ4_compress_fast() : + Same as LZ4_compress_default(), but allows to select an "acceleration" factor. + The larger the acceleration value, the faster the algorithm, but also the lesser the compression. + It's a trade-off. It can be fine tuned, with each successive value providing roughly +~3% to speed. + An acceleration value of "1" is the same as regular LZ4_compress_default() + Values <= 0 will be replaced by ACCELERATION_DEFAULT (see lz4.c), which is 1. */ +int LZ4_compress_fast (const char* source, char* dest, int sourceSize, int maxDestSize, int acceleration); -int LZ4_decompress_fast (const char* source, char* dest, int outputSize); +/* +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. +*/ +int LZ4_sizeofState(void); +int LZ4_compress_fast_extState (void* state, const char* source, char* dest, int inputSize, int maxDestSize, int acceleration); + + +/* +LZ4_compress_destSize() : + Reverse the logic, by compressing as much data as possible from 'source' buffer + into already allocated buffer 'dest' of size 'targetDestSize'. + This function either compresses the entire 'source' content into 'dest' if it's large enough, + or fill 'dest' buffer completely with as much data as possible from 'source'. + *sourceSizePtr : will be modified to indicate how many bytes where read from 'source' to fill 'dest'. + New value is necessarily <= old value. + return : Nb bytes written into 'dest' (necessarily <= targetDestSize) + or 0 if compression fails +*/ +int LZ4_compress_destSize (const char* source, char* dest, int* sourceSizePtr, int targetDestSize); + /* LZ4_decompress_fast() : - outputSize : is the original (uncompressed) size + originalSize : is the original and therefore uncompressed size return : the number of bytes read from the source buffer (in other words, the compressed size) - If the source stream is malformed, the function will stop decoding and return a negative result. - note : This function is a bit faster than LZ4_decompress_safe() - This function never writes outside of output buffers, but may read beyond input buffer in case of malicious data packet. - Use this function preferably into a trusted environment (data to decode comes from a trusted source). - Destination buffer must be already allocated. Its size must be a minimum of 'outputSize' bytes. + If the source stream is detected malformed, the function will stop decoding and return a negative result. + Destination buffer must be already allocated. Its size must be a minimum of 'originalSize' bytes. + note : This function fully respect memory boundaries for properly formed compressed data. + It is a bit faster than LZ4_decompress_safe(). + However, it does not provide any protection against intentionally modified data stream (malicious input). + Use this function in trusted environment only (data to decode comes from a trusted source). */ - -int LZ4_decompress_safe_partial (const char* source, char* dest, int inputSize, int targetOutputSize, int maxOutputSize); +int LZ4_decompress_fast (const char* source, char* dest, int originalSize); /* LZ4_decompress_safe_partial() : - This function decompress a compressed block of size 'inputSize' at position 'source' - into output buffer 'dest' of size 'maxOutputSize'. + This function decompress a compressed block of size 'compressedSize' at position 'source' + into destination buffer 'dest' of size 'maxDecompressedSize'. The function tries to stop decompressing operation as soon as 'targetOutputSize' has been reached, reducing decompression time. - return : the number of bytes decoded in the destination buffer (necessarily <= maxOutputSize) + return : the number of bytes decoded in the destination buffer (necessarily <= maxDecompressedSize) Note : this number can be < 'targetOutputSize' should the compressed block to decode be smaller. Always control how many bytes were decoded. If the source stream is detected malformed, the function will stop decoding and return a negative result. This function never writes outside of output buffer, and never reads outside of input buffer. It is therefore protected against malicious data packets */ +int LZ4_decompress_safe_partial (const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize); -int LZ4_sizeofState(); +/*********************************************** +* Streaming Compression Functions +***********************************************/ +#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4) +#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U64 * sizeof(long long)) +/* + * LZ4_stream_t + * information structure to track an LZ4 stream. + * important : init this structure content before first use ! + * note : only allocated directly the structure if you are statically linking LZ4 + * If you are using liblz4 as a DLL, please use below construction methods instead. + */ +typedef struct { long long table[LZ4_STREAMSIZE_U64]; } LZ4_stream_t; + +/* + * LZ4_resetStream + * Use this function to init an allocated LZ4_stream_t structure + */ +void LZ4_resetStream (LZ4_stream_t* streamPtr); + +/* + * LZ4_createStream will allocate and initialize an LZ4_stream_t structure + * LZ4_freeStream releases its memory. + * In the context of a DLL (liblz4), please use these methods rather than the static struct. + * They are more future proof, in case of a change of LZ4_stream_t size. + */ +LZ4_stream_t* LZ4_createStream(void); +int LZ4_freeStream (LZ4_stream_t* streamPtr); + +/* + * LZ4_loadDict + * Use this function to load a static dictionary into LZ4_stream. + * Any previous data will be forgotten, only 'dictionary' will remain in memory. + * Loading a size of 0 is allowed. + * Return : dictionary size, in bytes (necessarily <= 64 KB) + */ +int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize); + +/* + * LZ4_compress_fast_continue + * Compress buffer content 'src', using data from previously compressed blocks as dictionary to improve compression ratio. + * Important : Previous data blocks are assumed to still be present and unmodified ! + * 'dst' buffer must be already allocated. + * If maxDstSize >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster. + * If not, and if compressed data cannot fit into 'dst' buffer size, compression stops, and function returns a zero. + */ +int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int maxDstSize, int acceleration); + +/* + * 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 : you don't need to call LZ4_loadDict() afterwards, + * dictionary is immediately usable, you can therefore call LZ4_compress_fast_continue() + * Return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error + */ +int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int dictSize); + + +/************************************************ +* Streaming Decompression Functions +************************************************/ + +#define LZ4_STREAMDECODESIZE_U64 4 +#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U64 * sizeof(unsigned long long)) +typedef struct { unsigned long long table[LZ4_STREAMDECODESIZE_U64]; } LZ4_streamDecode_t; +/* + * LZ4_streamDecode_t + * information structure to track an LZ4 stream. + * init this structure content using LZ4_setStreamDecode or memset() before first use ! + * + * In the context of a DLL (liblz4) please prefer usage of construction methods below. + * They are more future proof, in case of a change of LZ4_streamDecode_t size in the future. + * LZ4_createStreamDecode will allocate and initialize an LZ4_streamDecode_t structure + * LZ4_freeStreamDecode releases its memory. + */ +LZ4_streamDecode_t* LZ4_createStreamDecode(void); +int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream); + +/* + * LZ4_setStreamDecode + * Use this function to instruct where to find the dictionary. + * Setting a size of 0 is allowed (same effect as reset). + * Return : 1 if OK, 0 if error + */ +int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize); + +/* +*_continue() : + These decoding functions allow decompression of multiple blocks in "streaming" mode. + Previously decoded blocks *must* remain available at the memory position where they were decoded (up to 64 KB) + In the case of a ring buffers, decoding buffer must be either : + - Exactly same size as encoding buffer, with same update rule (block boundaries at same positions) + In which case, the decoding & encoding ring buffer can have any size, including very small ones ( < 64 KB). + - Larger than encoding buffer, by a minimum of maxBlockSize more bytes. + maxBlockSize is implementation dependent. It's the maximum size you intend to compress into a single block. + In which case, encoding and decoding buffers do not need to be synchronized, + and encoding ring buffer can have any size, including small ones ( < 64 KB). + - _At least_ 64 KB + 8 bytes + maxBlockSize. + In which case, encoding and decoding buffers do not need to be synchronized, + and encoding ring buffer can have any size, including larger than decoding buffer. + Whenever these conditions are not possible, save the last 64KB of decoded data into a safe buffer, + and indicate where it is saved using LZ4_setStreamDecode() +*/ +int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxDecompressedSize); +int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize); + + +/* +Advanced decoding functions : +*_usingDict() : + These decoding functions work the same as + a combination of LZ4_setStreamDecode() followed by LZ4_decompress_x_continue() + They are stand-alone. They don't need nor update an LZ4_streamDecode_t structure. +*/ +int LZ4_decompress_safe_usingDict (const char* source, char* dest, int compressedSize, int maxDecompressedSize, const char* dictStart, int dictSize); +int LZ4_decompress_fast_usingDict (const char* source, char* dest, int originalSize, const char* dictStart, int dictSize); + + + +/************************************** +* Obsolete Functions +**************************************/ +/* Deprecate Warnings */ +/* Should these warnings messages be a problem, + it is generally possible to disable them, + with -Wno-deprecated-declarations for gcc + or _CRT_SECURE_NO_WARNINGS in Visual for example. + You can also define LZ4_DEPRECATE_WARNING_DEFBLOCK. */ +#ifndef LZ4_DEPRECATE_WARNING_DEFBLOCK +# define LZ4_DEPRECATE_WARNING_DEFBLOCK +# define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) +# if (LZ4_GCC_VERSION >= 405) || defined(__clang__) +# define LZ4_DEPRECATED(message) __attribute__((deprecated(message))) +# elif (LZ4_GCC_VERSION >= 301) +# define LZ4_DEPRECATED(message) __attribute__((deprecated)) +# elif defined(_MSC_VER) +# define LZ4_DEPRECATED(message) __declspec(deprecated(message)) +# else +# pragma message("WARNING: You need to implement LZ4_DEPRECATED for this compiler") +# define LZ4_DEPRECATED(message) +# endif +#endif /* LZ4_DEPRECATE_WARNING_DEFBLOCK */ + +/* Obsolete compression functions */ +/* These functions are planned to start generate warnings by r131 approximately */ +int LZ4_compress (const char* source, char* dest, int sourceSize); +int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize); int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize); int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); +int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize); +int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize); -/* -These functions are provided should you prefer to allocate memory for compression tables with your own allocation methods. -To know how much memory must be allocated for the compression tables, use : -int LZ4_sizeofState(); +/* Obsolete decompression functions */ +/* These function names are completely deprecated and must no longer be used. + They are only provided here for compatibility with older programs. + - LZ4_uncompress is the same as LZ4_decompress_fast + - LZ4_uncompress_unknownOutputSize is the same as LZ4_decompress_safe + These function prototypes are now disabled; uncomment them only if you really need them. + It is highly recommended to stop using these prototypes and migrate to maintained ones */ +/* int LZ4_uncompress (const char* source, char* dest, int outputSize); */ +/* int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize); */ -Note that tables must be aligned on 4-bytes boundaries, otherwise compression will fail (return code 0). - -The allocated memory can be provided to the compressions functions using 'void* state' parameter. -LZ4_compress_withState() and LZ4_compress_limitedOutput_withState() are equivalent to previously described functions. -They just use the externally allocated memory area instead of allocating their own (on stack, or on heap). -*/ - - -/************************************** - Streaming Functions -**************************************/ -void* LZ4_create (const char* inputBuffer); -int LZ4_compress_continue (void* LZ4_Data, const char* source, char* dest, int inputSize); -int LZ4_compress_limitedOutput_continue (void* LZ4_Data, const char* source, char* dest, int inputSize, int maxOutputSize); -char* LZ4_slideInputBuffer (void* LZ4_Data); -int LZ4_free (void* LZ4_Data); - -/* -These functions allow the compression of dependent blocks, where each block benefits from prior 64 KB within preceding blocks. -In order to achieve this, it is necessary to start creating the LZ4 Data Structure, thanks to the function : - -void* LZ4_create (const char* inputBuffer); -The result of the function is the (void*) pointer on the LZ4 Data Structure. -This pointer will be needed in all other functions. -If the pointer returned is NULL, then the allocation has failed, and compression must be aborted. -The only parameter 'const char* inputBuffer' must, obviously, point at the beginning of input buffer. -The input buffer must be already allocated, and size at least 192KB. -'inputBuffer' will also be the 'const char* source' of the first block. - -All blocks are expected to lay next to each other within the input buffer, starting from 'inputBuffer'. -To compress each block, use either LZ4_compress_continue() or LZ4_compress_limitedOutput_continue(). -Their behavior are identical to LZ4_compress() or LZ4_compress_limitedOutput(), -but require the LZ4 Data Structure as their first argument, and check that each block starts right after the previous one. -If next block does not begin immediately after the previous one, the compression will fail (return 0). - -When it's no longer possible to lay the next block after the previous one (not enough space left into input buffer), a call to : -char* LZ4_slideInputBuffer(void* LZ4_Data); -must be performed. It will typically copy the latest 64KB of input at the beginning of input buffer. -Note that, for this function to work properly, minimum size of an input buffer must be 192KB. -==> The memory position where the next input data block must start is provided as the result of the function. - -Compression can then resume, using LZ4_compress_continue() or LZ4_compress_limitedOutput_continue(), as usual. - -When compression is completed, a call to LZ4_free() will release the memory used by the LZ4 Data Structure. -*/ - -int LZ4_sizeofStreamState(); -int LZ4_resetStreamState(void* state, const char* inputBuffer); - -/* -These functions achieve the same result as : -void* LZ4_create (const char* inputBuffer); - -They are provided here to allow the user program to allocate memory using its own routines. - -To know how much space must be allocated, use LZ4_sizeofStreamState(); -Note also that space must be 4-bytes aligned. - -Once space is allocated, you must initialize it using : LZ4_resetStreamState(void* state, const char* inputBuffer); -void* state is a pointer to the space allocated. -It must be aligned on 4-bytes boundaries, and be large enough. -The parameter 'const char* inputBuffer' must, obviously, point at the beginning of input buffer. -The input buffer must be already allocated, and size at least 192KB. -'inputBuffer' will also be the 'const char* source' of the first block. - -The same space can be re-used multiple times, just by initializing it each time with LZ4_resetStreamState(). -return value of LZ4_resetStreamState() must be 0 is OK. -Any other value means there was an error (typically, pointer is not aligned on 4-bytes boundaries). -*/ - - -int LZ4_decompress_safe_withPrefix64k (const char* source, char* dest, int inputSize, int maxOutputSize); -int LZ4_decompress_fast_withPrefix64k (const char* source, char* dest, int outputSize); - -/* -*_withPrefix64k() : - These decoding functions work the same as their "normal name" versions, - but can use up to 64KB of data in front of 'char* dest'. - These functions are necessary to decode inter-dependant blocks. -*/ - - -/************************************** - Obsolete Functions -**************************************/ -/* -These functions are deprecated and should no longer be used. -They are provided here for compatibility with existing user programs. -*/ -static inline int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); } -static inline int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); } +/* Obsolete streaming functions; use new streaming interface whenever possible */ +LZ4_DEPRECATED("use LZ4_createStream() instead") void* LZ4_create (char* inputBuffer); +LZ4_DEPRECATED("use LZ4_createStream() instead") int LZ4_sizeofStreamState(void); +LZ4_DEPRECATED("use LZ4_resetStream() instead") int LZ4_resetStreamState(void* state, char* inputBuffer); +LZ4_DEPRECATED("use LZ4_saveDict() instead") char* LZ4_slideInputBuffer (void* state); +/* Obsolete streaming decoding functions */ +LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize); +LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize); #if defined (__cplusplus) diff --git a/polymer/eduke32/build/include/texcache.h b/polymer/eduke32/build/include/texcache.h index 1f68275b6..f3051edbf 100644 --- a/polymer/eduke32/build/include/texcache.h +++ b/polymer/eduke32/build/include/texcache.h @@ -7,7 +7,7 @@ extern "C" { #ifdef USE_OPENGL -#define TEXCACHEMAGIC "LZ40" +#define TEXCACHEMAGIC "LZ41" #define GLTEXCACHEADSIZ 8192 #define TEXCACHEHASHSIZE 1024 diff --git a/polymer/eduke32/build/src/engine.c b/polymer/eduke32/build/src/engine.c index 71119f29b..11dc5df26 100644 --- a/polymer/eduke32/build/src/engine.c +++ b/polymer/eduke32/build/src/engine.c @@ -11852,7 +11852,7 @@ void E_CreateDummyTile(int32_t const tile) void E_CreateFakeTile(int32_t const tile, int32_t tsiz, char const * const buffer) { - faketiledata[tile] = (char *)Xrealloc(faketiledata[tile], tsiz + 32); + faketiledata[tile] = (char *)Xrealloc(faketiledata[tile], LZ4_compressBound(tsiz)); if ((tsiz = LZ4_compress(buffer, faketiledata[tile], tsiz)) != -1) { diff --git a/polymer/eduke32/build/src/lz4.c b/polymer/eduke32/build/src/lz4.c index 0f01a098d..08cf6b5cd 100644 --- a/polymer/eduke32/build/src/lz4.c +++ b/polymer/eduke32/build/src/lz4.c @@ -1,6 +1,7 @@ /* LZ4 - Fast LZ compression algorithm - Copyright (C) 2011-2014, Yann Collet. + Copyright (C) 2011-2015, Yann Collet. + BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) Redistribution and use in source and binary forms, with or without @@ -27,124 +28,68 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. You can contact the author at : - - LZ4 source repository : http://code.google.com/p/lz4/ + - LZ4 source repository : https://github.com/Cyan4973/lz4 - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c */ -/************************************** - 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 +/************************************** +* Tuning parameters +**************************************/ /* * 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)). + * in memory stack (0:default, fastest), or in memory heap (1:requires malloc()). */ #define HEAPMODE 0 +/* + * ACCELERATION_DEFAULT : + * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0 + */ +#define ACCELERATION_DEFAULT 1 + /************************************** - CPU Feature Detection +* CPU Feature Detection **************************************/ -/* 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(__ia64) || defined(__itanium__) || defined(_M_IA64) ) /* Detects 64 bits mode */ -# define LZ4_ARCH64 1 -#else -# define LZ4_ARCH64 0 -#endif - /* - * Little Endian or Big Endian ? - * Overwrite the #define below if you know your architecture endianess + * LZ4_FORCE_SW_BITCOUNT + * Define this parameter if your target system or compiler does not support hardware bit count */ -#if defined (__GLIBC__) -# include -# if (__BYTE_ORDER == __BIG_ENDIAN) -# define LZ4_BIG_ENDIAN 1 -# endif -#elif (defined(__BIG_ENDIAN__) || defined(__BIG_ENDIAN) || defined(_BIG_ENDIAN)) && !(defined(__LITTLE_ENDIAN__) || defined(__LITTLE_ENDIAN) || defined(_LITTLE_ENDIAN)) -# define LZ4_BIG_ENDIAN 1 -#elif defined(__sparc) || defined(__sparc__) \ - || defined(__powerpc__) || defined(__ppc__) || defined(__PPC__) \ - || defined(__hpux) || defined(__hppa) \ - || defined(_MIPSEB) || defined(__s390__) -# define LZ4_BIG_ENDIAN 1 -#else -/* Little Endian assumed. PDP Endian and other very rare endian format are unsupported. */ -#endif - -/* - * Unaligned memory access is automatically enabled for "common" CPU, such as x86. - * For others CPU, such as ARM, the compiler may be more cautious, inserting unnecessary extra code to ensure aligned access property - * If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance - */ -#if defined(__ARM_FEATURE_UNALIGNED) -# define LZ4_FORCE_UNALIGNED_ACCESS 1 -#endif - -/* 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 Windows CE does not support Hardware bit count */ # define LZ4_FORCE_SW_BITCOUNT #endif -/* - * BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE : - * This option may provide a small boost to performance for some big endian cpu, although probably modest. - * You may set this option to 1 if data will remain within closed environment. - * This option is useless on Little_Endian CPU (such as x86) - */ -/* #define BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE 1 */ +/************************************** +* Includes +**************************************/ +#include "lz4.h" /************************************** - Compiler Options +* Compiler Options **************************************/ -#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */ -/* "restrict" is a known keyword */ -#else -# define restrict /* Disable restrict */ -#endif - #ifdef _MSC_VER /* Visual Studio */ # define FORCE_INLINE static __forceinline -# include /* For Visual 2005 */ -# if LZ4_ARCH64 /* 64-bits */ -# pragma intrinsic(_BitScanForward64) /* For Visual 2005 */ -# pragma intrinsic(_BitScanReverse64) /* For Visual 2005 */ -# else /* 32-bits */ -# pragma intrinsic(_BitScanForward) /* For Visual 2005 */ -# pragma intrinsic(_BitScanReverse) /* For Visual 2005 */ -# endif +# include # pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ +# pragma warning(disable : 4293) /* disable: C4293: too large shift (32-bits) */ #else -# ifdef __GNUC__ -# define FORCE_INLINE static inline __attribute__((always_inline)) +# if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */ +# if defined(__GNUC__) || defined(__clang__) +# define FORCE_INLINE static inline __attribute__((always_inline)) +# else +# define FORCE_INLINE static inline +# endif # else -# define FORCE_INLINE static inline -# endif -#endif +# define FORCE_INLINE static +# endif /* __STDC_VERSION__ */ +#endif /* _MSC_VER */ -#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))) -#endif - -#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) - -#if (GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__) +/* LZ4_GCC_VERSION is defined into lz4.h */ +#if (LZ4_GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__) # define expect(expr,value) (__builtin_expect ((expr),(value)) ) #else # define expect(expr,value) (expr) @@ -155,24 +100,17 @@ /************************************** - Memory routines +* Memory routines **************************************/ -#include "compat.h" #include /* malloc, calloc, free */ -#define ALLOCATOR(n,s) Xcalloc(n,s) -#define FREEMEM Bfree +#define ALLOCATOR(n,s) calloc(n,s) +#define FREEMEM free #include /* memset, memcpy */ -#define MEM_INIT Bmemset +#define MEM_INIT memset /************************************** - Includes -**************************************/ -#include "lz4.h" - - -/************************************** - Basic Types +* Basic Types **************************************/ #if defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */ # include @@ -189,46 +127,95 @@ typedef unsigned long long U64; #endif -#if defined(__GNUC__) && !defined(LZ4_FORCE_UNALIGNED_ACCESS) -# define _PACKED __attribute__ ((packed)) -#else -# define _PACKED -#endif -#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__) -# if defined(__IBMC__) || defined(__SUNPRO_C) || defined(__SUNPRO_CC) -# pragma pack(1) -# else -# pragma pack(push, 1) -# endif -#endif +/************************************** +* Reading and writing into memory +**************************************/ +#define STEPSIZE sizeof(size_t) -typedef struct { U16 v; } _PACKED U16_S; -typedef struct { U32 v; } _PACKED U32_S; -typedef struct { U64 v; } _PACKED U64_S; -typedef struct {size_t v;} _PACKED size_t_S; +static unsigned LZ4_64bits(void) { return sizeof(void*)==8; } -#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__) -# if defined(__SUNPRO_C) || defined(__SUNPRO_CC) -# pragma pack(0) -# else -# pragma pack(pop) -# endif -#endif +static unsigned LZ4_isLittleEndian(void) +{ + const union { U32 i; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */ + return one.c[0]; +} -#define A16(x) (((U16_S *)(x))->v) -#define A32(x) (((U32_S *)(x))->v) -#define A64(x) (((U64_S *)(x))->v) -#define AARCH(x) (((size_t_S *)(x))->v) + +static U16 LZ4_read16(const void* memPtr) +{ + U16 val16; + memcpy(&val16, memPtr, 2); + return val16; +} + +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)); + } +} + +static void LZ4_writeLE16(void* memPtr, U16 value) +{ + if (LZ4_isLittleEndian()) + { + memcpy(memPtr, &value, 2); + } + else + { + BYTE* p = (BYTE*)memPtr; + p[0] = (BYTE) value; + p[1] = (BYTE)(value>>8); + } +} + +static U32 LZ4_read32(const void* memPtr) +{ + U32 val32; + memcpy(&val32, memPtr, 4); + return val32; +} + +static U64 LZ4_read64(const void* memPtr) +{ + U64 val64; + memcpy(&val64, memPtr, 8); + return val64; +} + +static size_t LZ4_read_ARCH(const void* p) +{ + if (LZ4_64bits()) + return (size_t)LZ4_read64(p); + else + return (size_t)LZ4_read32(p); +} + + +static void LZ4_copy4(void* dstPtr, const void* srcPtr) { memcpy(dstPtr, srcPtr, 4); } + +static void LZ4_copy8(void* dstPtr, const void* srcPtr) { memcpy(dstPtr, srcPtr, 8); } + +/* customized version of memcpy, which may overwrite up to 7 bytes beyond dstEnd */ +static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd) +{ + BYTE* d = (BYTE*)dstPtr; + const BYTE* s = (const BYTE*)srcPtr; + BYTE* e = (BYTE*)dstEnd; + do { LZ4_copy8(d,s); d+=8; s+=8; } while (d>3); +# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_ctzll((U64)val) >> 3); +# else + static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 }; + return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58]; +# endif + } + else /* 32 bits */ + { +# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r; + _BitScanForward( &r, (U32)val ); + return (int)(r>>3); +# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_ctz((U32)val) >> 3); +# else + static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 }; + return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27]; +# endif + } + } + else /* Big Endian CPU */ + { + if (LZ4_64bits()) + { +# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r = 0; + _BitScanReverse64( &r, val ); + return (unsigned)(r>>3); +# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_clzll((U64)val) >> 3); +# else + unsigned r; + if (!(val>>32)) { r=4; } else { r=0; val>>=32; } + if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } + r += (!val); + return r; +# endif + } + else /* 32 bits */ + { +# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r = 0; + _BitScanReverse( &r, (unsigned long)val ); + return (unsigned)(r>>3); +# elif (defined(__clang__) || (LZ4_GCC_VERSION >= 304)) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (__builtin_clz((U32)val) >> 3); +# else + unsigned r; + if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } + r += (!val); + return r; +# endif + } + } +} + +static unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit) +{ + const BYTE* const pStart = pIn; + + while (likely(pIn compression run slower on incompressible data */ + + +/************************************** +* Local Structures and types **************************************/ typedef struct { - U32 hashTable[HASHNBCELLS4]; - const BYTE* bufferStart; - const BYTE* base; - const BYTE* nextBlock; -} LZ4_Data_Structure; + U32 hashTable[HASH_SIZE_U32]; + U32 currentOffset; + U32 initCheck; + const BYTE* dictionary; + BYTE* bufferStart; /* obsolete, used for slideInputBuffer */ + U32 dictSize; +} LZ4_stream_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 { noPrefix = 0, withPrefix = 1 } prefix64k_directive; +typedef enum { noDict = 0, withPrefix64k, usingExtDict } 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; /************************************** - Architecture-specific macros +* Local Utils **************************************/ -#define STEPSIZE sizeof(size_t) -#define LZ4_COPYSTEP(d,s) { AARCH(d) = AARCH(s); d+=STEPSIZE; s+=STEPSIZE; } -#define LZ4_COPY8(d,s) { LZ4_COPYSTEP(d,s); if (STEPSIZE<8) LZ4_COPYSTEP(d,s); } - -#if (defined(LZ4_BIG_ENDIAN) && !defined(BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE)) -# define LZ4_READ_LITTLEENDIAN_16(d,s,p) { U16 v = A16(p); v = lz4_bswap16(v); d = (s) - v; } -# define LZ4_WRITE_LITTLEENDIAN_16(p,i) { U16 v = (U16)(i); v = lz4_bswap16(v); A16(p) = v; p+=2; } -#else /* Little Endian */ -# define LZ4_READ_LITTLEENDIAN_16(d,s,p) { d = (s) - A16(p); } -# define LZ4_WRITE_LITTLEENDIAN_16(p,v) { A16(p) = v; p+=2; } -#endif +int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; } +int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } +int LZ4_sizeofState() { return LZ4_STREAMSIZE; } -/************************************** - Macros -**************************************/ -#if LZ4_ARCH64 || !defined(__GNUC__) -# define LZ4_WILDCOPY(d,s,e) { do { LZ4_COPY8(d,s) } while (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>3); -# elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_clzll(val) >> 3); -# else - int r; - if (!(val>>32)) { r=4; } else { r=0; val>>=32; } - if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } - r += (!val); - return r; -# endif -# else -# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r = 0; - _BitScanForward64( &r, val ); - return (int)(r>>3); -# elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_ctzll(val) >> 3); -# else - static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 }; - return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58]; -# endif -# endif -} - -#else - -FORCE_INLINE int LZ4_NbCommonBytes (register U32 val) -{ -# if defined(LZ4_BIG_ENDIAN) -# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r = 0; - _BitScanReverse( &r, val ); - return (int)(r>>3); -# elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_clz(val) >> 3); -# else - int r; - if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } - r += (!val); - return r; -# endif -# else -# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r; - _BitScanForward( &r, val ); - return (int)(r>>3); -# elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_ctz(val) >> 3); -# else - static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 }; - return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27]; -# endif -# endif -} - -#endif - - -/**************************** - Compression functions -****************************/ -FORCE_INLINE int LZ4_hashSequence(U32 sequence, tableType_t tableType) +static U32 LZ4_hashSequence(U32 sequence, tableType_t const tableType) { if (tableType == byU16) return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1))); @@ -378,70 +386,104 @@ 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 const U64 prime5bytes = 889523592379ULL; +static U32 LZ4_hashSequence64(size_t sequence, tableType_t const tableType) +{ + const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG; + const U32 hashMask = (1<> (40 - hashLog)) & hashMask; +} -FORCE_INLINE void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) +static U32 LZ4_hashSequenceT(size_t sequence, tableType_t const tableType) +{ + if (LZ4_64bits()) + return LZ4_hashSequence64(sequence, tableType); + return LZ4_hashSequence((U32)sequence, tableType); +} + +static U32 LZ4_hashPosition(const void* p, tableType_t tableType) { return LZ4_hashSequenceT(LZ4_read_ARCH(p), tableType); } + +static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase) { switch (tableType) { - case byPtr: { const BYTE** hashTable = (const BYTE**) tableBase; hashTable[h] = p; break; } - case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); break; } - case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); break; } + case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = p; return; } + case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); return; } + case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); return; } } } -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); } - FORCE_INLINE int LZ4_compress_generic( - void* ctx, - const char* source, - char* dest, - int inputSize, - int maxOutputSize, - - limitedOutput_directive limitedOutput, - tableType_t tableType, - prefix64k_directive prefix) + void* const ctx, + const char* const source, + char* const dest, + const int inputSize, + const int maxOutputSize, + const limitedOutput_directive outputLimited, + const tableType_t tableType, + const dict_directive dict, + const dictIssue_directive dictIssue, + const U32 acceleration) { + LZ4_stream_t_internal* const dictPtr = (LZ4_stream_t_internal*)ctx; + const BYTE* ip = (const BYTE*) source; - const BYTE* const base = (prefix==withPrefix) ? ((LZ4_Data_Structure*)ctx)->base : (const BYTE*) source; - const BYTE* const lowLimit = ((prefix==withPrefix) ? ((LZ4_Data_Structure*)ctx)->bufferStart : (const BYTE*)source); + const BYTE* base; + const BYTE* lowLimit; + const BYTE* const lowRefLimit = ip - dictPtr->dictSize; + 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 ((prefix==withPrefix) && (ip != ((LZ4_Data_Structure*)ctx)->nextBlock)) return 0; /* must continue from end of previous block */ - if (prefix==withPrefix) ((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 (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; + break; + case usingExtDict: + base = (const BYTE*)source - dictPtr->currentOffset; + lowLimit = (const BYTE*)source; + break; + } + if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */ + if (inputSize> skipStrength; - ip = forwardIp; - forwardIp = ip + step; + /* Find a match */ + do { + U32 h = forwardH; + ip = forwardIp; + forwardIp += step; + step = (searchMatchNb++ >> LZ4_skipTrigger); - if (unlikely(forwardIp > mflimit)) { goto _last_literals; } + if (unlikely(forwardIp > mflimit)) goto _last_literals; - forwardH = LZ4_hashPosition(forwardIp, tableType); - ref = LZ4_getPositionOnHash(h, ctx, tableType, base); - LZ4_putPositionOnHash(ip, h, ctx, tableType, base); + match = LZ4_getPositionOnHash(h, ctx, tableType, base); + if (dict==usingExtDict) + { + if (match<(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 ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0) + || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip)) + || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) ); + } /* Catch up */ - while ((ip>anchor) && (ref > lowLimit) && (unlikely(ip[-1]==ref[-1]))) { ip--; ref--; } + while ((ip>anchor) && (match+refDelta > lowLimit) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; } - /* 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<= 255 ; len-=255) *op++ = 255; - *op++ = (BYTE)len; - } - else *token = (BYTE)(length< olimit))) + return 0; /* Check output limit */ + if (litLength>=RUN_MASK) + { + int len = (int)litLength-RUN_MASK; + *token=(RUN_MASK<= 255 ; len-=255) *op++ = 255; + *op++ = (BYTE)len; + } + else *token = (BYTE)(litLength<>8) > oend))) return 0; /* Check output limit */ - if (length>=(int)ML_MASK) { - *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; + match += refDelta; + limit = ip + (dictEnd-match); + if (limit > matchlimit) limit = matchlimit; + matchLength = LZ4_count(ip+MINMATCH, match+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, match+MINMATCH, matchlimit); + ip += MINMATCH + matchLength; + } + + if ((outputLimited) && (unlikely(op + (1 + LASTLITERALS) + (matchLength>>8) > olimit))) + return 0; /* Check output limit */ + if (matchLength>=ML_MASK) + { + *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); + match = LZ4_getPosition(ip, ctx, tableType, base); + if (dict==usingExtDict) + { + if (match<(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 ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1) + && (match+MAX_DISTANCE>=ip) + && (LZ4_read32(match+refDelta)==LZ4_read32(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 (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<= 255 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; } - else *op++ = (BYTE)(lastRun< (U32)maxOutputSize)) + return 0; /* Check output limit */ + 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<= LZ4_compressBound(inputSize)) + { + if (inputSize < LZ4_64Klimit) + return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue, acceleration); + else + return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration); + } + else + { + if (inputSize < LZ4_64Klimit) + return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); + else + return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration); + } +} + + +int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) { #if (HEAPMODE) - void* ctx = ALLOCATOR(HASHNBCELLS4, 4); /* Aligned on 4-bytes boundaries */ + void* ctxPtr = ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ #else - U32 ctx[1U<<(MEMORY_USAGE-2)] = {0}; /* Ensure data is aligned on 4-bytes boundaries */ + LZ4_stream_t ctx; + void* ctxPtr = &ctx; #endif - int result; - if (inputSize < (int)LZ4_64KLIMIT) - result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, byU16, noPrefix); - else - result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noPrefix); + int result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration); #if (HEAPMODE) - FREEMEM(ctx); + FREEMEM(ctxPtr); #endif return result; } -int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) + +int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxOutputSize) +{ + return LZ4_compress_fast(source, dest, inputSize, maxOutputSize, 1); +} + + +/* hidden debug function */ +/* strangely enough, gcc generates faster code when this function is uncommented, even if unused */ +int LZ4_compress_fast_force(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) +{ + LZ4_stream_t ctx; + + LZ4_resetStream(&ctx); + + if (inputSize < LZ4_64Klimit) + return LZ4_compress_generic(&ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); + else + return LZ4_compress_generic(&ctx, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration); +} + + +/******************************** +* destSize variant +********************************/ + +static int LZ4_compress_destSize_generic( + void* const ctx, + const char* const src, + char* const dst, + int* const srcSizePtr, + const int targetDstSize, + const tableType_t tableType) +{ + const BYTE* ip = (const BYTE*) src; + const BYTE* base = (const BYTE*) src; + const BYTE* lowLimit = (const BYTE*) src; + const BYTE* anchor = ip; + const BYTE* const iend = ip + *srcSizePtr; + const BYTE* const mflimit = iend - MFLIMIT; + const BYTE* const matchlimit = iend - LASTLITERALS; + + BYTE* op = (BYTE*) dst; + BYTE* const oend = op + targetDstSize; + BYTE* const oMaxLit = op + targetDstSize - 2 /* offset */ - 8 /* because 8+MINMATCH==MFLIMIT */ - 1 /* token */; + BYTE* const oMaxMatch = op + targetDstSize - (LASTLITERALS + 1 /* token */); + BYTE* const oMaxSeq = oMaxLit - 1 /* token */; + + U32 forwardH; + + + /* Init conditions */ + if (targetDstSize < 1) return 0; /* Impossible to store anything */ + if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size, too large (or negative) */ + if ((tableType == byU16) && (*srcSizePtr>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */ + if (*srcSizePtr> LZ4_skipTrigger); + + if (unlikely(forwardIp > mflimit)) + goto _last_literals; + + match = LZ4_getPositionOnHash(h, ctx, tableType, base); + forwardH = LZ4_hashPosition(forwardIp, tableType); + LZ4_putPositionOnHash(ip, h, ctx, tableType, base); + + } while ( ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip)) + || (LZ4_read32(match) != LZ4_read32(ip)) ); + } + + /* Catch up */ + while ((ip>anchor) && (match > lowLimit) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; } + + { + /* Encode Literal length */ + unsigned litLength = (unsigned)(ip - anchor); + token = op++; + if (op + ((litLength+240)/255) + litLength > oMaxLit) + { + /* Not enough space for a last match */ + op--; + goto _last_literals; + } + if (litLength>=RUN_MASK) + { + unsigned len = litLength - RUN_MASK; + *token=(RUN_MASK<= 255 ; len-=255) *op++ = 255; + *op++ = (BYTE)len; + } + else *token = (BYTE)(litLength< oMaxMatch) + { + /* Match description too long : reduce it */ + matchLength = (15-1) + (oMaxMatch-op) * 255; + } + //printf("offset %5i, matchLength%5i \n", (int)(ip-match), matchLength + MINMATCH); + ip += MINMATCH + matchLength; + + if (matchLength>=ML_MASK) + { + *token += ML_MASK; + matchLength -= ML_MASK; + while (matchLength >= 255) { matchLength-=255; *op++ = 255; } + *op++ = (BYTE)matchLength; + } + else *token += (BYTE)(matchLength); + } + + anchor = ip; + + /* Test end of block */ + if (ip > mflimit) break; + if (op > oMaxSeq) break; + + /* Fill table */ + LZ4_putPosition(ip-2, ctx, tableType, base); + + /* Test next position */ + match = LZ4_getPosition(ip, ctx, tableType, base); + LZ4_putPosition(ip, ctx, tableType, base); + if ( (match+MAX_DISTANCE>=ip) + && (LZ4_read32(match)==LZ4_read32(ip)) ) + { token=op++; *token=0; goto _next_match; } + + /* Prepare next loop */ + forwardH = LZ4_hashPosition(++ip, tableType); + } + +_last_literals: + /* Encode Last Literals */ + { + size_t lastRunSize = (size_t)(iend - anchor); + if (op + 1 /* token */ + ((lastRunSize+240)/255) /* litLength */ + lastRunSize /* literals */ > oend) + { + /* adapt lastRunSize to fill 'dst' */ + lastRunSize = (oend-op) - 1; + lastRunSize -= (lastRunSize+240)/255; + } + ip = anchor + lastRunSize; + + if (lastRunSize >= RUN_MASK) + { + size_t accumulator = lastRunSize - RUN_MASK; + *op++ = RUN_MASK << ML_BITS; + for(; accumulator >= 255 ; accumulator-=255) *op++ = 255; + *op++ = (BYTE) accumulator; + } + else + { + *op++ = (BYTE)(lastRunSize<= LZ4_compressBound(*srcSizePtr)) /* compression success is guaranteed */ + { + return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1); + } + else + { + if (*srcSizePtr < LZ4_64Klimit) + return LZ4_compress_destSize_generic(state, src, dst, srcSizePtr, targetDstSize, byU16); + else + return LZ4_compress_destSize_generic(state, src, dst, srcSizePtr, targetDstSize, LZ4_64bits() ? byU32 : byPtr); + } +} + + +int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize) { #if (HEAPMODE) - void* ctx = ALLOCATOR(HASHNBCELLS4, 4); /* Aligned on 4-bytes boundaries */ + void* ctx = ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ #else - U32 ctx[1U<<(MEMORY_USAGE-2)] = {0}; /* Ensure data is aligned on 4-bytes boundaries */ + LZ4_stream_t ctxBody; + void* ctx = &ctxBody; #endif - int result; - if (inputSize < (int)LZ4_64KLIMIT) - result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limited, byU16, noPrefix); - else - result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limited, (sizeof(void*)==8) ? byU32 : byPtr, noPrefix); + int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize); #if (HEAPMODE) FREEMEM(ctx); @@ -594,159 +927,222 @@ int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, in } -/***************************** - Using external allocation -*****************************/ -int LZ4_sizeofState() { return 1 << MEMORY_USAGE; } +/******************************** +* Streaming functions +********************************/ - -int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize) +LZ4_stream_t* LZ4_createStream(void) { - 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, noPrefix); - else - return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noPrefix); + LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(8, LZ4_STREAMSIZE_U64); + LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal)); /* A compilation error here means LZ4_STREAMSIZE is not large enough */ + LZ4_resetStream(lz4s); + return lz4s; } - -int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize) +void LZ4_resetStream (LZ4_stream_t* LZ4_stream) { - 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, limited, byU16, noPrefix); - else - return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limited, (sizeof(void*)==8) ? byU32 : byPtr, noPrefix); + MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t)); } - -/**************************** - Stream functions -****************************/ - -int LZ4_sizeofStreamState() +int LZ4_freeStream (LZ4_stream_t* LZ4_stream) { - return sizeof(LZ4_Data_Structure); -} - -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; -} - -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* lz4ds = ALLOCATOR(1, sizeof(LZ4_Data_Structure)); - LZ4_init ((LZ4_Data_Structure*)lz4ds, (const BYTE*)inputBuffer); - return lz4ds; -} - - -int LZ4_free (void* LZ4_Data) -{ - FREEMEM(LZ4_Data); + FREEMEM(LZ4_stream); return (0); } -char* LZ4_slideInputBuffer (void* LZ4_Data) +#define HASH_UNIT sizeof(size_t) +int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) { - LZ4_Data_Structure* lz4ds = (LZ4_Data_Structure*)LZ4_Data; - size_t delta = lz4ds->nextBlock - (lz4ds->bufferStart + 64 KB); + LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict; + const BYTE* p = (const BYTE*)dictionary; + const BYTE* const dictEnd = p + dictSize; + const BYTE* base; - if ( (lz4ds->base - delta > lz4ds->base) /* underflow control */ - || ((size_t)(lz4ds->nextBlock - lz4ds->base) > 0xE0000000) ) /* close to 32-bits limit */ + if ((dict->initCheck) || (dict->currentOffset > 1 GB)) /* Uninitialized structure, or reuse overflow */ + LZ4_resetStream(LZ4_dict); + + if (dictSize < (int)HASH_UNIT) { - size_t deltaLimit = (lz4ds->nextBlock - 64 KB) - lz4ds->base; - int nH; + dict->dictionary = NULL; + dict->dictSize = 0; + return 0; + } - for (nH=0; nH < HASHNBCELLS4; nH++) + if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB; + dict->currentOffset += 64 KB; + base = p - dict->currentOffset; + dict->dictionary = p; + dict->dictSize = (U32)(dictEnd - p); + dict->currentOffset += dict->dictSize; + + while (p <= dictEnd-HASH_UNIT) + { + LZ4_putPosition(p, dict->hashTable, byU32, base); + p+=3; + } + + return dict->dictSize; +} + + +static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src) +{ + 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; + const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize; + int i; + for (i=0; ihashTable[nH]) < deltaLimit) lz4ds->hashTable[nH] = 0; - else lz4ds->hashTable[nH] -= (U32)deltaLimit; + if (LZ4_dict->hashTable[i] < delta) LZ4_dict->hashTable[i]=0; + else LZ4_dict->hashTable[i] -= delta; } - memcpy((void*)(lz4ds->bufferStart), (const void*)(lz4ds->nextBlock - 64 KB), 64 KB); - lz4ds->base = lz4ds->bufferStart; - lz4ds->nextBlock = lz4ds->base + 64 KB; + LZ4_dict->currentOffset = 64 KB; + if (LZ4_dict->dictSize > 64 KB) LZ4_dict->dictSize = 64 KB; + LZ4_dict->dictionary = dictEnd - LZ4_dict->dictSize; } - else +} + + +int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) +{ + LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_stream; + const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; + + const BYTE* smallest = (const BYTE*) source; + if (streamPtr->initCheck) return 0; /* Uninitialized structure detected */ + if ((streamPtr->dictSize>0) && (smallest>dictEnd)) smallest = dictEnd; + LZ4_renormDictT(streamPtr, smallest); + if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; + + /* Check overlapping input/dictionary space */ { - memcpy((void*)(lz4ds->bufferStart), (const void*)(lz4ds->nextBlock - 64 KB), 64 KB); - lz4ds->nextBlock -= delta; - lz4ds->base -= delta; + const BYTE* sourceEnd = (const BYTE*) source + inputSize; + if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) + { + streamPtr->dictSize = (U32)(dictEnd - sourceEnd); + if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB; + if (streamPtr->dictSize < 4) streamPtr->dictSize = 0; + streamPtr->dictionary = dictEnd - streamPtr->dictSize; + } } - return (char*)(lz4ds->nextBlock); + /* prefix mode : source data follows dictionary */ + if (dictEnd == (const BYTE*)source) + { + int result; + if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) + result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration); + else + result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration); + streamPtr->dictSize += (U32)inputSize; + streamPtr->currentOffset += (U32)inputSize; + return result; + } + + /* external dictionary mode */ + { + int result; + if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) + result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration); + else + result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration); + 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 external 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, withPrefix); + LZ4_stream_t_internal* streamPtr = (LZ4_stream_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_stream_t_internal*)LZ4_dict, smallest); + + result = LZ4_compress_generic(LZ4_dict, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1); + + 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_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize) { - return LZ4_compress_generic(LZ4_Data, source, dest, inputSize, maxOutputSize, limited, byU32, withPrefix); + LZ4_stream_t_internal* dict = (LZ4_stream_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; + + memmove(safeBuffer, previousDictEnd - dictSize, dictSize); + + dict->dictionary = (const BYTE*)safeBuffer; + dict->dictSize = (U32)dictSize; + + return dictSize; } -/**************************** - Decompression functions -****************************/ +/******************************* +* Decompression functions +*******************************/ /* * This generic decompression function cover all use cases. - * It shall be instanciated several times, using different sets of directives + * It shall be instantiated several times, using different sets of directives * Note that it is essential this generic function is really inlined, - * in order to remove useless branches during compilation optimisation. + * in order to remove useless branches during compilation optimization. */ FORCE_INLINE int LZ4_decompress_generic( - const char* source, - char* dest, + const char* const source, + char* const dest, int inputSize, int outputSize, /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */ int endOnInput, /* endOnOutputSize, endOnInputSize */ - int prefix64k, /* noPrefix, withPrefix */ int partialDecoding, /* full, partial */ - int targetOutputSize /* only used if partialDecoding==partial */ + int targetOutputSize, /* only used if partialDecoding==partial */ + int dict, /* noDict, withPrefix64k, usingExtDict */ + const BYTE* const lowPrefix, /* == dest if dict == noDict */ + const BYTE* const dictStart, /* only if dict==usingExtDict */ + const size_t dictSize /* note : = 0 if noDict */ ) { /* Local Variables */ - const BYTE* restrict ip = (const BYTE*) source; - const BYTE* ref; + const BYTE* ip = (const BYTE*) source; const BYTE* const iend = ip + inputSize; BYTE* op = (BYTE*) dest; BYTE* const oend = op + outputSize; BYTE* cpy; BYTE* oexit = op + targetOutputSize; + const BYTE* const lowLimit = lowPrefix - dictSize; - /*const size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0}; / static reduces speed for LZ4_decompress_safe() on GCC64 */ - const size_t dec32table[] = {4-0, 4-3, 4-2, 4-3, 4-0, 4-0, 4-0, 4-0}; /* static reduces speed for LZ4_decompress_safe() on GCC64 */ - static const size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3}; + const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize; + const size_t dec32table[] = {4, 1, 2, 1, 4, 4, 4, 4}; + const size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3}; + + const int safeDecode = (endOnInput==endOnInputSize); + const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB))); /* Special cases */ - 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 ((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); @@ -755,17 +1151,21 @@ FORCE_INLINE int LZ4_decompress_generic( { unsigned token; size_t length; + const BYTE* match; - /* get runlength */ + /* get literal length */ token = *ip++; if ((length=(token>>ML_BITS)) == RUN_MASK) { - unsigned s=255; - while (((endOnInput)?ip iend-LASTLITERALS)) goto _output_error; + s = *ip++; length += s; - if (s==255) continue; - break; + } while (s==255); + if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)op)) goto _output_error; /* overflow detection */ + } + length += MINMATCH; + + /* check external dictionary */ + if ((dict==usingExtDict) && (match < lowPrefix)) + { + if (unlikely(op+length > oend-LASTLITERALS)) 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 = dictEnd - (lowPrefix-match); + memmove(op, match, length); op += length; } + else + { + /* match encompass external dictionary and current segment */ + size_t copySize = (size_t)(lowPrefix-match); + memcpy(op, dictEnd - copySize, copySize); + op += copySize; + copySize = length - copySize; + if (copySize > (size_t)(op-lowPrefix)) /* overlap within current segment */ + { + BYTE* const endOfMatch = op + copySize; + const BYTE* copyFrom = lowPrefix; + while (op < endOfMatch) *op++ = *copyFrom++; + } + else + { + memcpy(op, lowPrefix, copySize); + op += copySize; + } + } + continue; } /* copy repeated sequence */ - if (unlikely((op-ref)<(int)STEPSIZE)) + cpy = op + length; + if (unlikely((op-match)<8)) { - const size_t dec64 = dec64table[(sizeof(void*)==4) ? 0 : op-ref]; - op[0] = ref[0]; - op[1] = ref[1]; - op[2] = ref[2]; - op[3] = ref[3]; - /*op += 4, ref += 4; ref -= dec32table[op-ref]; - A32(op) = A32(ref); - op += STEPSIZE-4; ref -= dec64;*/ - ref += dec32table[op-ref]; - A32(op+4) = A32(ref); - op += STEPSIZE; ref -= dec64; - } else { LZ4_COPYSTEP(op,ref); } - cpy = op + length - (STEPSIZE-4); + const size_t dec64 = dec64table[op-match]; + op[0] = match[0]; + op[1] = match[1]; + op[2] = match[2]; + op[3] = match[3]; + match += dec32table[op-match]; + LZ4_copy4(op+4, match); + op += 8; match -= dec64; + } else { LZ4_copy8(op, match); op+=8; match+=8; } - if (unlikely(cpy>oend-COPYLENGTH-(STEPSIZE-4))) + if (unlikely(cpy>oend-12)) { - if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last 5 bytes must be literals */ - LZ4_SECURECOPY(op, ref, (oend-COPYLENGTH)); - while(op oend-LASTLITERALS) goto _output_error; /* Error : last LASTLITERALS bytes must be literals */ + if (op < oend-8) + { + LZ4_wildCopy(op, match, oend-8); + match += (oend-8) - op; + op = oend-8; + } + while (opprefixSize = (size_t) dictSize; + lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize; + lz4sd->externalDict = NULL; + lz4sd->extDictSize = 0; + return 1; +} + +/* +*_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() +*/ +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_t_internal*) LZ4_streamDecode; + int result; + + if (lz4sd->prefixEnd == (BYTE*)dest) + { + result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + endOnInputSize, full, 0, + usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize += result; + lz4sd->prefixEnd += result; + } + else + { + lz4sd->extDictSize = lz4sd->prefixSize; + lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; + result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + endOnInputSize, full, 0, + usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize = result; + lz4sd->prefixEnd = (BYTE*)dest + result; + } + + return result; +} + +int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize) +{ + LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode; + int result; + + if (lz4sd->prefixEnd == (BYTE*)dest) + { + result = LZ4_decompress_generic(source, dest, 0, originalSize, + endOnOutputSize, full, 0, + usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize += originalSize; + lz4sd->prefixEnd += originalSize; + } + else + { + lz4sd->extDictSize = lz4sd->prefixSize; + lz4sd->externalDict = (BYTE*)dest - lz4sd->extDictSize; + result = LZ4_decompress_generic(source, dest, 0, originalSize, + endOnOutputSize, full, 0, + usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize = 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 +*/ + +FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest, int compressedSize, int maxOutputSize, int safe, const char* dictStart, int dictSize) +{ + if (dictSize==0) + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest, NULL, 0); + if (dictStart+dictSize == dest) + { + if (dictSize >= (int)(64 KB - 1)) + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, withPrefix64k, (BYTE*)dest-64 KB, NULL, 0); + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest-dictSize, NULL, 0); + } + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize); +} + +int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize) +{ + return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize); +} + +int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize) +{ + return LZ4_decompress_usingDict_generic(source, dest, 0, originalSize, 0, dictStart, dictSize); +} + +/* debug function */ +int LZ4_decompress_safe_forceExtDict(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, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, 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* source, char* dest, int inputSize) { return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize)); } +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 maxDstSize) { return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, maxDstSize, 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 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; } + +static void LZ4_init(LZ4_stream_t_internal* lz4ds, BYTE* base) +{ + MEM_INIT(lz4ds, 0, LZ4_STREAMSIZE); + lz4ds->bufferStart = base; +} + +int LZ4_resetStreamState(void* state, char* inputBuffer) +{ + if ((((size_t)state) & 3) != 0) return 1; /* Error : pointer is not aligned on 4-bytes boundary */ + LZ4_init((LZ4_stream_t_internal*)state, (BYTE*)inputBuffer); + return 0; +} + +void* LZ4_create (char* inputBuffer) +{ + void* lz4ds = ALLOCATOR(8, LZ4_STREAMSIZE_U64); + LZ4_init ((LZ4_stream_t_internal*)lz4ds, (BYTE*)inputBuffer); + return lz4ds; +} + +char* LZ4_slideInputBuffer (void* LZ4_Data) +{ + LZ4_stream_t_internal* ctx = (LZ4_stream_t_internal*)LZ4_Data; + int dictSize = LZ4_saveDict((LZ4_stream_t*)LZ4_Data, (char*)ctx->bufferStart, 64 KB); + return (char*)(ctx->bufferStart + dictSize); +} + +/* Obsolete streaming decompression functions */ + +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, (BYTE*)dest - 64 KB, NULL, 64 KB); +} + +int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize) +{ + return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB); +} + +#endif /* LZ4_COMMONDEFS_ONLY */ + diff --git a/polymer/eduke32/source/m32common.c b/polymer/eduke32/source/m32common.c index 66f9bbd3b..0dd9291ff 100644 --- a/polymer/eduke32/source/m32common.c +++ b/polymer/eduke32/source/m32common.c @@ -337,9 +337,6 @@ mapundo_t *mapstate = NULL; int32_t map_revision = 1; -#define QADDNSZ 400 - - static int32_t try_match_with_prev(int32_t idx, int32_t numsthgs, uint32_t crc) { if (mapstate->prev && mapstate->prev->num[idx]==numsthgs && mapstate->prev->crc[idx]==crc) @@ -359,7 +356,7 @@ static void create_compressed_block(int32_t idx, const void *srcdata, uint32_t s uint32_t j; // allocate - mapstate->sws[idx] = (char *)Xmalloc(4 + size + QADDNSZ); + mapstate->sws[idx] = (char *)Xmalloc(4 + LZ4_compressBound(size)); // compress & realloc j = LZ4_compress((const char*)srcdata, mapstate->sws[idx]+4, size);