diff options
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Makefile | 147 | ||||
-rw-r--r-- | lib/README.md | 56 | ||||
-rw-r--r-- | lib/lz4.c | 1488 | ||||
-rw-r--r-- | lib/lz4.h | 490 | ||||
-rw-r--r-- | lib/lz4frame.c | 1457 | ||||
-rw-r--r-- | lib/lz4frame.h | 461 | ||||
-rw-r--r-- | lib/lz4frame_static.h | 45 | ||||
-rw-r--r-- | lib/lz4hc.c | 1204 | ||||
-rw-r--r-- | lib/lz4hc.h | 253 | ||||
-rw-r--r-- | lib/lz4opt.h | 363 | ||||
-rw-r--r-- | lib/xxhash.c | 49 |
11 files changed, 3857 insertions, 2156 deletions
diff --git a/lib/Makefile b/lib/Makefile index 2d9c8f38..88d9b4f2 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -3,6 +3,8 @@ # Copyright (C) Yann Collet 2011-2016 # All rights reserved. # +# This Makefile is validated for Linux, macOS, *BSD, Hurd, Solaris, MSYS2 targets +# # BSD license # Redistribution and use in source and binary forms, with or without modification, # are permitted provided that the following conditions are met: @@ -40,25 +42,28 @@ LIBVER_MINOR := $(shell echo $(LIBVER_MINOR_SCRIPT)) LIBVER_PATCH := $(shell echo $(LIBVER_PATCH_SCRIPT)) LIBVER := $(shell echo $(LIBVER_SCRIPT)) -BUILD_STATIC:= yes +BUILD_SHARED:=yes +BUILD_STATIC:=yes +OS ?= $(shell uname) CPPFLAGS+= -DXXH_NAMESPACE=LZ4_ CFLAGS ?= -O3 -DEBUGFLAGS:=-g -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \ - -Wswitch-enum -Wdeclaration-after-statement -Wstrict-prototypes -Wundef \ - -Wpointer-arith -Wstrict-aliasing=1 -CFLAGS += $(MOREFLAGS) +DEBUGFLAGS:= -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \ + -Wswitch-enum -Wdeclaration-after-statement -Wstrict-prototypes \ + -Wundef -Wpointer-arith -Wstrict-aliasing=1 +CFLAGS += $(DEBUGFLAGS) $(MOREFLAGS) FLAGS = $(CPPFLAGS) $(CFLAGS) $(LDFLAGS) +SRCFILES := $(sort $(wildcard *.c)) # OS X linker doesn't support -soname, and use different extension # see : https://developer.apple.com/library/mac/documentation/DeveloperTools/Conceptual/DynamicLibraries/100-Articles/DynamicLibraryDesignGuidelines.html -ifeq ($(shell uname), Darwin) +ifeq ($(OS), Darwin) SHARED_EXT = dylib SHARED_EXT_MAJOR = $(LIBVER_MAJOR).$(SHARED_EXT) SHARED_EXT_VER = $(LIBVER).$(SHARED_EXT) - SONAME_FLAGS = -install_name $(PREFIX)/lib/liblz4.$(SHARED_EXT_MAJOR) -compatibility_version $(LIBVER_MAJOR) -current_version $(LIBVER) + SONAME_FLAGS = -install_name $(libdir)/liblz4.$(SHARED_EXT_MAJOR) -compatibility_version $(LIBVER_MAJOR) -current_version $(LIBVER) else SONAME_FLAGS = -Wl,-soname=liblz4.$(SHARED_EXT).$(LIBVER_MAJOR) SHARED_EXT = so @@ -68,103 +73,129 @@ endif LIBLZ4 = liblz4.$(SHARED_EXT_VER) +.PHONY: default default: lib-release -lib-release: liblz4.a liblz4 +lib-release: DEBUGFLAGS := +lib-release: lib -lib: CFLAGS += $(DEBUGFLAGS) -lib: lib-release +lib: liblz4.a liblz4 all: lib all32: CFLAGS+=-m32 all32: all -liblz4.a: *.c -ifeq ($(BUILD_STATIC),yes) +ifeq ($(V), 1) +Q = +else +Q = @ +endif + +liblz4.a: $(SRCFILES) +ifeq ($(BUILD_STATIC),yes) # can be disabled on command line @echo compiling static library - @$(CC) $(CPPFLAGS) $(CFLAGS) -c $^ - @$(AR) rcs $@ *.o + $(Q)$(CC) $(CPPFLAGS) $(CFLAGS) -c $^ + $(Q)$(AR) rcs $@ *.o endif -$(LIBLZ4): *.c +$(LIBLZ4): $(SRCFILES) +ifeq ($(BUILD_SHARED),yes) # can be disabled on command line @echo compiling dynamic library $(LIBVER) ifneq (,$(filter Windows%,$(OS))) - @$(CC) $(FLAGS) -DLZ4_DLL_EXPORT=1 -shared $^ -o dll\$@.dll + $(Q)$(CC) $(FLAGS) -DLZ4_DLL_EXPORT=1 -shared $^ -o dll\$@.dll dlltool -D dll\liblz4.dll -d dll\liblz4.def -l dll\liblz4.lib else - @$(CC) $(FLAGS) -shared $^ -fPIC $(SONAME_FLAGS) -o $@ + $(Q)$(CC) $(FLAGS) -shared $^ -fPIC -fvisibility=hidden $(SONAME_FLAGS) -o $@ @echo creating versioned links - @ln -sf $@ liblz4.$(SHARED_EXT_MAJOR) - @ln -sf $@ liblz4.$(SHARED_EXT) + $(Q)ln -sf $@ liblz4.$(SHARED_EXT_MAJOR) + $(Q)ln -sf $@ liblz4.$(SHARED_EXT) +endif endif liblz4: $(LIBLZ4) clean: - @$(RM) core *.o liblz4.pc dll/liblz4.dll dll/liblz4.lib - @$(RM) *.a *.$(SHARED_EXT) *.$(SHARED_EXT_MAJOR) *.$(SHARED_EXT_VER) + $(Q)$(RM) core *.o liblz4.pc dll/liblz4.dll dll/liblz4.lib + $(Q)$(RM) *.a *.$(SHARED_EXT) *.$(SHARED_EXT_MAJOR) *.$(SHARED_EXT_VER) @echo Cleaning library completed #----------------------------------------------------------------------------- # make install is validated only for Linux, OSX, BSD, Hurd and Solaris targets #----------------------------------------------------------------------------- -ifneq (,$(filter $(shell uname),Linux Darwin GNU/kFreeBSD GNU OpenBSD FreeBSD NetBSD DragonFly SunOS)) - -ifneq (,$(filter $(shell uname),SunOS)) -INSTALL ?= ginstall +ifneq (,$(filter $(shell uname),Linux Darwin GNU/kFreeBSD GNU OpenBSD FreeBSD NetBSD DragonFly SunOS Haiku MidnightBSD)) + +.PHONY: listL120 +listL120: # extract lines >= 120 characters in *.{c,h}, by Takayuki Matsuoka (note : $$, for Makefile compatibility) + find . -type f -name '*.c' -o -name '*.h' | while read -r filename; do awk 'length > 120 {print FILENAME "(" FNR "): " $$0}' $$filename; done + +DESTDIR ?= +# directory variables : GNU conventions prefer lowercase +# see https://www.gnu.org/prep/standards/html_node/Makefile-Conventions.html +# support both lower and uppercase (BSD), use lower in script +PREFIX ?= /usr/local +prefix ?= $(PREFIX) +EXEC_PREFIX ?= $(prefix) +exec_prefix ?= $(EXEC_PREFIX) +LIBDIR ?= $(exec_prefix)/lib +libdir ?= $(LIBDIR) +INCLUDEDIR ?= $(prefix)/include +includedir ?= $(INCLUDEDIR) + +ifneq (,$(filter $(OS),OpenBSD FreeBSD NetBSD DragonFly)) +PKGCONFIGDIR ?= $(prefix)/libdata/pkgconfig else -INSTALL ?= install +PKGCONFIGDIR ?= $(libdir)/pkgconfig endif +pkgconfigdir ?= $(PKGCONFIGDIR) -PREFIX ?= /usr/local -DESTDIR ?= -LIBDIR ?= $(PREFIX)/lib -INCLUDEDIR ?= $(PREFIX)/include - -ifneq (,$(filter $(shell uname),OpenBSD FreeBSD NetBSD DragonFly)) -PKGCONFIGDIR ?= $(PREFIX)/libdata/pkgconfig +ifneq (,$(filter $(OS),SunOS)) +INSTALL ?= ginstall else -PKGCONFIGDIR ?= $(LIBDIR)/pkgconfig +INSTALL ?= install endif -INSTALL_LIB ?= $(INSTALL) -m 755 -INSTALL_DATA ?= $(INSTALL) -m 644 +INSTALL_PROGRAM ?= $(INSTALL) +INSTALL_DATA ?= $(INSTALL) -m 644 liblz4.pc: liblz4.pc.in Makefile @echo creating pkgconfig - @sed -e 's|@PREFIX@|$(PREFIX)|' \ - -e 's|@LIBDIR@|$(LIBDIR)|' \ - -e 's|@INCLUDEDIR@|$(INCLUDEDIR)|' \ + $(Q)sed -e 's|@PREFIX@|$(prefix)|' \ + -e 's|@LIBDIR@|$(libdir)|' \ + -e 's|@INCLUDEDIR@|$(includedir)|' \ -e 's|@VERSION@|$(LIBVER)|' \ $< >$@ install: lib liblz4.pc - @$(INSTALL) -d -m 755 $(DESTDIR)$(PKGCONFIGDIR)/ $(DESTDIR)$(INCLUDEDIR)/ - @$(INSTALL_DATA) liblz4.pc $(DESTDIR)$(PKGCONFIGDIR)/ + $(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(pkgconfigdir)/ $(DESTDIR)$(includedir)/ $(DESTDIR)$(libdir)/ + $(Q)$(INSTALL_DATA) liblz4.pc $(DESTDIR)$(pkgconfigdir)/ @echo Installing libraries ifeq ($(BUILD_STATIC),yes) - @$(INSTALL_LIB) liblz4.a $(DESTDIR)$(LIBDIR)/liblz4.a + $(Q)$(INSTALL_DATA) liblz4.a $(DESTDIR)$(libdir)/liblz4.a + $(Q)$(INSTALL_DATA) lz4frame_static.h $(DESTDIR)$(includedir)/lz4frame_static.h +endif +ifeq ($(BUILD_SHARED),yes) + $(Q)$(INSTALL_PROGRAM) liblz4.$(SHARED_EXT_VER) $(DESTDIR)$(libdir) + $(Q)ln -sf liblz4.$(SHARED_EXT_VER) $(DESTDIR)$(libdir)/liblz4.$(SHARED_EXT_MAJOR) + $(Q)ln -sf liblz4.$(SHARED_EXT_VER) $(DESTDIR)$(libdir)/liblz4.$(SHARED_EXT) endif - @$(INSTALL_LIB) liblz4.$(SHARED_EXT_VER) $(DESTDIR)$(LIBDIR) - @ln -sf liblz4.$(SHARED_EXT_VER) $(DESTDIR)$(LIBDIR)/liblz4.$(SHARED_EXT_MAJOR) - @ln -sf liblz4.$(SHARED_EXT_VER) $(DESTDIR)$(LIBDIR)/liblz4.$(SHARED_EXT) - @echo Installing includes - @$(INSTALL_DATA) lz4.h $(DESTDIR)$(INCLUDEDIR)/lz4.h - @$(INSTALL_DATA) lz4hc.h $(DESTDIR)$(INCLUDEDIR)/lz4hc.h - @$(INSTALL_DATA) lz4frame.h $(DESTDIR)$(INCLUDEDIR)/lz4frame.h - @echo lz4 static and shared libraries installed + @echo Installing headers in $(includedir) + $(Q)$(INSTALL_DATA) lz4.h $(DESTDIR)$(includedir)/lz4.h + $(Q)$(INSTALL_DATA) lz4hc.h $(DESTDIR)$(includedir)/lz4hc.h + $(Q)$(INSTALL_DATA) lz4frame.h $(DESTDIR)$(includedir)/lz4frame.h + @echo lz4 libraries installed uninstall: - @$(RM) $(DESTDIR)$(LIBDIR)/pkgconfig/liblz4.pc - @$(RM) $(DESTDIR)$(LIBDIR)/liblz4.$(SHARED_EXT) - @$(RM) $(DESTDIR)$(LIBDIR)/liblz4.$(SHARED_EXT_MAJOR) - @$(RM) $(DESTDIR)$(LIBDIR)/liblz4.$(SHARED_EXT_VER) - @$(RM) $(DESTDIR)$(LIBDIR)/liblz4.a - @$(RM) $(DESTDIR)$(INCLUDEDIR)/lz4.h - @$(RM) $(DESTDIR)$(INCLUDEDIR)/lz4hc.h - @$(RM) $(DESTDIR)$(INCLUDEDIR)/lz4frame.h + $(Q)$(RM) $(DESTDIR)$(pkgconfigdir)/liblz4.pc + $(Q)$(RM) $(DESTDIR)$(libdir)/liblz4.$(SHARED_EXT) + $(Q)$(RM) $(DESTDIR)$(libdir)/liblz4.$(SHARED_EXT_MAJOR) + $(Q)$(RM) $(DESTDIR)$(libdir)/liblz4.$(SHARED_EXT_VER) + $(Q)$(RM) $(DESTDIR)$(libdir)/liblz4.a + $(Q)$(RM) $(DESTDIR)$(includedir)/lz4.h + $(Q)$(RM) $(DESTDIR)$(includedir)/lz4hc.h + $(Q)$(RM) $(DESTDIR)$(includedir)/lz4frame.h + $(Q)$(RM) $(DESTDIR)$(includedir)/lz4frame_static.h @echo lz4 libraries successfully uninstalled endif diff --git a/lib/README.md b/lib/README.md index b40442c4..7082fe3e 100644 --- a/lib/README.md +++ b/lib/README.md @@ -1,44 +1,43 @@ LZ4 - Library Files ================================ -The directory contains many files, but depending on project's objectives, +The `/lib` directory contains many files, but depending on project's objectives, not all of them are necessary. #### Minimal LZ4 build The minimum required is **`lz4.c`** and **`lz4.h`**, -which will provide the fast compression and decompression algorithm. +which provides the fast compression and decompression algorithm. +They generate and decode data using [LZ4 block format]. -#### The High Compression variant of LZ4 +#### High Compression variant -For more compression at the cost of compression speed, -the High Compression variant **lz4hc** is available. -It's necessary to add **`lz4hc.c`** and **`lz4hc.h`**. -The variant still depends on regular `lz4` source files. -In particular, the decompression is still provided by `lz4.c`. +For more compression ratio at the cost of compression speed, +the High Compression variant called **lz4hc** is available. +Add files **`lz4hc.c`** and **`lz4hc.h`**. +The variant still depends on regular `lib/lz4.*` source files. -#### Compatibility issues +#### Frame variant, for interoperability -In order to produce files or streams compatible with `lz4` command line utility, +In order to produce compressed data compatible with `lz4` command line utility, it's necessary to encode lz4-compressed blocks using the [official interoperable frame format]. This format is generated and decoded automatically by the **lz4frame** library. -In order to work properly, lz4frame needs lz4 and lz4hc, and also **xxhash**, -which provides error detection. -(_Advanced stuff_ : It's possible to hide xxhash symbols into a local namespace. -This is what `liblz4` does, to avoid symbol duplication -in case a user program would link to several libraries containing xxhash symbols.) +Its public API is described in `lib/lz4frame.h`. +In order to work properly, lz4frame needs all other modules present in `/lib`, +including, lz4 and lz4hc, and also **xxhash**. +So it's necessary to include all `*.c` and `*.h` files present in `/lib`. -#### Advanced API +#### Advanced / Experimental API -A more complex `lz4frame_static.h` is also provided. -It contains definitions which are not guaranteed to remain stable within future versions. -It must be used with static linking ***only***. +A complex API defined in `lz4frame_static.h` contains definitions +which are not guaranteed to remain stable in future versions. +As a consequence, it must be used with static linking ***only***. -#### Using MinGW+MSYS to create DLL +#### Windows : using MinGW+MSYS to create DLL DLL can be created using MinGW+MSYS with the `make liblz4` command. This command creates `dll\liblz4.dll` and the import library `dll\liblz4.lib`. @@ -51,23 +50,24 @@ file it should be linked with `dll\liblz4.dll`. For example: ``` gcc $(CFLAGS) -Iinclude/ test-dll.c -o test-dll dll\liblz4.dll ``` -The compiled executable will require LZ4 DLL which is available at `dll\liblz4.dll`. +The compiled executable will require LZ4 DLL which is available at `dll\liblz4.dll`. -#### Miscellaneous +#### Miscellaneous Other files present in the directory are not source code. There are : - - LICENSE : contains the BSD license text - - Makefile : script to compile or install lz4 library (static or dynamic) - - liblz4.pc.in : for pkg-config (make install) - - README.md : this file + - `LICENSE` : contains the BSD license text + - `Makefile` : `make` script to compile and install lz4 library (static and dynamic) + - `liblz4.pc.in` : for `pkg-config` (used in `make install`) + - `README.md` : this file [official interoperable frame format]: ../doc/lz4_Frame_format.md +[LZ4 block format]: ../doc/lz4_Block_format.md -#### License +#### License All source material within __lib__ directory are BSD 2-Clause licensed. See [LICENSE](LICENSE) for details. -The license is also repeated at the top of each source file. +The license is also reminded at the top of each source file. @@ -1,6 +1,6 @@ /* LZ4 - Fast LZ compression algorithm - Copyright (C) 2011-2016, Yann Collet. + Copyright (C) 2011-present, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -37,12 +37,12 @@ * Tuning parameters **************************************/ /* - * HEAPMODE : + * LZ4_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 malloc()). */ -#ifndef HEAPMODE -# define HEAPMODE 0 +#ifndef LZ4_HEAPMODE +# define LZ4_HEAPMODE 0 #endif /* @@ -63,16 +63,17 @@ * Method 1 : `__packed` statement. It depends on compiler extension (ie, not portable). * This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`. * Method 2 : direct access. This method is portable but violate C standard. - * It can generate buggy code on targets which generate assembly depending on alignment. + * It can generate buggy code on targets which assembly generation depends on alignment. * But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6) * See https://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details. * Prefer these methods in priority order (0 > 1 > 2) */ -#ifndef LZ4_FORCE_MEMORY_ACCESS /* can be defined externally, on command line for example */ -# if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) ) +#ifndef LZ4_FORCE_MEMORY_ACCESS /* can be defined externally */ +# if defined(__GNUC__) && \ + ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) \ + || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) ) # define LZ4_FORCE_MEMORY_ACCESS 2 -# elif defined(__INTEL_COMPILER) || \ - (defined(__GNUC__) && ( defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) || defined(__ARM_ARCH_7S__) )) +# elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__) # define LZ4_FORCE_MEMORY_ACCESS 1 # endif #endif @@ -81,14 +82,17 @@ * LZ4_FORCE_SW_BITCOUNT * Define this parameter if your target system or compiler does not support hardware bit count */ -#if defined(_MSC_VER) && defined(_WIN32_WCE) /* Visual Studio for Windows CE does not support Hardware bit count */ +#if defined(_MSC_VER) && defined(_WIN32_WCE) /* Visual Studio for WinCE doesn't support Hardware bit count */ # define LZ4_FORCE_SW_BITCOUNT #endif + /*-************************************ * Dependency **************************************/ +#define LZ4_STATIC_LINKING_ONLY +#define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */ #include "lz4.h" /* see also "memory routines" below */ @@ -97,38 +101,72 @@ * Compiler Options **************************************/ #ifdef _MSC_VER /* Visual Studio */ -# define FORCE_INLINE static __forceinline # include <intrin.h> # pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ # pragma warning(disable : 4293) /* disable: C4293: too large shift (32-bits) */ -#else -# if defined(__GNUC__) || defined(__clang__) -# define FORCE_INLINE static inline __attribute__((always_inline)) -# elif defined(__cplusplus) || (defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) -# define FORCE_INLINE static inline -# else -# define FORCE_INLINE static -# endif #endif /* _MSC_VER */ +#ifndef LZ4_FORCE_INLINE +# ifdef _MSC_VER /* Visual Studio */ +# define LZ4_FORCE_INLINE static __forceinline +# else +# if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */ +# ifdef __GNUC__ +# define LZ4_FORCE_INLINE static inline __attribute__((always_inline)) +# else +# define LZ4_FORCE_INLINE static inline +# endif +# else +# define LZ4_FORCE_INLINE static +# endif /* __STDC_VERSION__ */ +# endif /* _MSC_VER */ +#endif /* LZ4_FORCE_INLINE */ + +/* LZ4_FORCE_O2_GCC_PPC64LE and LZ4_FORCE_O2_INLINE_GCC_PPC64LE + * Gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy, + * together with a simple 8-byte copy loop as a fall-back path. + * However, this optimization hurts the decompression speed by >30%, + * because the execution does not go to the optimized loop + * for typical compressible data, and all of the preamble checks + * before going to the fall-back path become useless overhead. + * This optimization happens only with the -O3 flag, and -O2 generates + * a simple 8-byte copy loop. + * With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy + * functions are annotated with __attribute__((optimize("O2"))), + * and also LZ4_wildCopy is forcibly inlined, so that the O2 attribute + * of LZ4_wildCopy does not affect the compression speed. + */ +#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__) +# define LZ4_FORCE_O2_GCC_PPC64LE __attribute__((optimize("O2"))) +# define LZ4_FORCE_O2_INLINE_GCC_PPC64LE __attribute__((optimize("O2"))) LZ4_FORCE_INLINE +#else +# define LZ4_FORCE_O2_GCC_PPC64LE +# define LZ4_FORCE_O2_INLINE_GCC_PPC64LE static +#endif + #if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__) # define expect(expr,value) (__builtin_expect ((expr),(value)) ) #else # define expect(expr,value) (expr) #endif +#ifndef likely #define likely(expr) expect((expr) != 0, 1) +#endif +#ifndef unlikely #define unlikely(expr) expect((expr) != 0, 0) +#endif /*-************************************ * Memory routines **************************************/ #include <stdlib.h> /* malloc, calloc, free */ -#define ALLOCATOR(n,s) calloc(n,s) -#define FREEMEM free +#define ALLOC(s) malloc(s) +#define ALLOC_AND_ZERO(s) calloc(1,s) +#define FREEMEM(p) free(p) #include <string.h> /* memset, memcpy */ -#define MEM_INIT memset +#define MEM_INIT(p,v,s) memset((p),(v),(s)) /*-************************************ @@ -241,19 +279,15 @@ static void LZ4_writeLE16(void* memPtr, U16 value) } } -static void LZ4_copy8(void* dst, const void* src) -{ - memcpy(dst,src,8); -} - /* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */ -static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd) +LZ4_FORCE_O2_INLINE_GCC_PPC64LE +void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd) { BYTE* d = (BYTE*)dstPtr; const BYTE* s = (const BYTE*)srcPtr; BYTE* const e = (BYTE*)dstEnd; - do { LZ4_copy8(d,s); d+=8; s+=8; } while (d<e); + do { memcpy(d,s,8); d+=8; s+=8; } while (d<e); } @@ -263,8 +297,9 @@ static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd) #define MINMATCH 4 #define WILDCOPYLENGTH 8 -#define LASTLITERALS 5 -#define MFLIMIT (WILDCOPYLENGTH+MINMATCH) +#define LASTLITERALS 5 /* see ../doc/lz4_Block_format.md#parsing-restrictions */ +#define MFLIMIT 12 /* see ../doc/lz4_Block_format.md#parsing-restrictions */ +#define MATCH_SAFEGUARD_DISTANCE ((2*WILDCOPYLENGTH) - MINMATCH) /* ensure it's possible to write 2 x wildcopyLength without overflowing output buffer */ static const int LZ4_minLength = (MFLIMIT+1); #define KB *(1 <<10) @@ -281,15 +316,36 @@ static const int LZ4_minLength = (MFLIMIT+1); /*-************************************ -* Common Utils +* Error detection **************************************/ -#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(int)(!!(c)) }; } /* use only *after* variable declarations */ +#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=1) +# include <assert.h> +#else +# ifndef assert +# define assert(condition) ((void)0) +# endif +#endif + +#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(int)(!!(c)) }; } /* use after variable declarations */ + +#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2) +# include <stdio.h> +static int g_debuglog_enable = 1; +# define DEBUGLOG(l, ...) { \ + if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) { \ + fprintf(stderr, __FILE__ ": "); \ + fprintf(stderr, __VA_ARGS__); \ + fprintf(stderr, " \n"); \ + } } +#else +# define DEBUGLOG(l, ...) {} /* disabled */ +#endif /*-************************************ * Common functions **************************************/ -static unsigned LZ4_NbCommonBytes (register reg_t val) +static unsigned LZ4_NbCommonBytes (reg_t val) { if (LZ4_isLittleEndian()) { if (sizeof(val)==8) { @@ -300,7 +356,14 @@ static unsigned LZ4_NbCommonBytes (register reg_t val) # elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !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 }; + 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 */ { @@ -311,12 +374,15 @@ static unsigned LZ4_NbCommonBytes (register reg_t val) # elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !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 }; + 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 (sizeof(val)==8) { + if (sizeof(val)==8) { /* 64-bits */ # if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) unsigned long r = 0; _BitScanReverse64( &r, val ); @@ -324,8 +390,11 @@ static unsigned LZ4_NbCommonBytes (register reg_t val) # elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) return (__builtin_clzll((U64)val) >> 3); # else + static const U32 by32 = sizeof(val)*4; /* 32 on 64 bits (goal), 16 on 32 bits. + Just to avoid some static analyzer complaining about shift by 32 on 32-bits target. + Note that this code path is never triggered in 32-bits mode. */ unsigned r; - if (!(val>>32)) { r=4; } else { r=0; val>>=32; } + if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; } if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } r += (!val); return r; @@ -348,11 +417,20 @@ static unsigned LZ4_NbCommonBytes (register reg_t val) } #define STEPSIZE sizeof(reg_t) -static unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit) +LZ4_FORCE_INLINE +unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit) { const BYTE* const pStart = pIn; - while (likely(pIn<pInLimit-(STEPSIZE-1))) { + if (likely(pIn < pInLimit-(STEPSIZE-1))) { + reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn); + if (!diff) { + pIn+=STEPSIZE; pMatch+=STEPSIZE; + } else { + return LZ4_NbCommonBytes(diff); + } } + + while (likely(pIn < pInLimit-(STEPSIZE-1))) { reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn); if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; } pIn += LZ4_NbCommonBytes(diff); @@ -377,15 +455,35 @@ static const U32 LZ4_skipTrigger = 6; /* Increase this value ==> compression ru /*-************************************ * Local Structures and types **************************************/ -typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive; -typedef enum { byPtr, byU32, byU16 } tableType_t; - -typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive; +typedef enum { notLimited = 0, limitedOutput = 1, fillOutput = 2 } limitedOutput_directive; +typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t; + +/** + * This enum distinguishes several different modes of accessing previous + * content in the stream. + * + * - noDict : There is no preceding content. + * - withPrefix64k : Table entries up to ctx->dictSize before the current blob + * blob being compressed are valid and refer to the preceding + * content (of length ctx->dictSize), which is available + * contiguously preceding in memory the content currently + * being compressed. + * - usingExtDict : Like withPrefix64k, but the preceding content is somewhere + * else in memory, starting at ctx->dictionary with length + * ctx->dictSize. + * - usingDictCtx : Like usingExtDict, but everything concerning the preceding + * content is in a separate context, pointed to by + * ctx->dictCtx. ctx->dictionary, ctx->dictSize, and table + * entries in the current context that refer to positions + * preceding the beginning of the current compression are + * ignored. Instead, ctx->dictCtx->dictionary and ctx->dictCtx + * ->dictSize describe the location and size of the preceding + * content, and matches are found by looking in the ctx + * ->dictCtx->hashTable. + */ +typedef enum { noDict = 0, withPrefix64k, usingExtDict, usingDictCtx } dict_directive; typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive; -typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; -typedef enum { full = 0, partial = 1 } earlyEnd_directive; - /*-************************************ * Local Utils @@ -396,6 +494,21 @@ int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } int LZ4_sizeofState() { return LZ4_STREAMSIZE; } +/*-************************************ +* Internal Definitions used in Tests +**************************************/ +#if defined (__cplusplus) +extern "C" { +#endif + +int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize); + +int LZ4_decompress_safe_forceExtDict(const char* in, char* out, int inSize, int outSize, const void* dict, size_t dictSize); + +#if defined (__cplusplus) +} +#endif + /*-****************************** * Compression functions ********************************/ @@ -418,93 +531,190 @@ static U32 LZ4_hash5(U64 sequence, tableType_t const tableType) return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog)); } -FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType) +LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType) { if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType); return LZ4_hash4(LZ4_read32(p), tableType); } -static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase) +static void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType) { switch (tableType) { + default: /* fallthrough */ + case clearedTable: /* fallthrough */ + case byPtr: { /* illegal! */ assert(0); return; } + case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; } + case byU16: { U16* hashTable = (U16*) tableBase; assert(idx < 65536); hashTable[h] = (U16)idx; return; } + } +} + +static void LZ4_putPositionOnHash(const BYTE* p, U32 h, + void* tableBase, tableType_t const tableType, + const BYTE* srcBase) +{ + switch (tableType) + { + case clearedTable: { /* illegal! */ assert(0); return; } 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) +LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) { U32 const h = LZ4_hashPosition(p, tableType); LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase); } -static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) +/* LZ4_getIndexOnHash() : + * Index of match position registered in hash table. + * hash position must be calculated by using base+index, or dictBase+index. + * Assumption 1 : only valid if tableType == byU32 or byU16. + * Assumption 2 : h is presumed valid (within limits of hash table) + */ +static U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType) +{ + LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2); + if (tableType == byU32) { + const U32* const hashTable = (const U32*) tableBase; + assert(h < (1U << (LZ4_MEMORY_USAGE-2))); + return hashTable[h]; + } + if (tableType == byU16) { + const U16* const hashTable = (const U16*) tableBase; + assert(h < (1U << (LZ4_MEMORY_USAGE-1))); + return hashTable[h]; + } + assert(0); return 0; /* forbidden case */ +} + +static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType_t tableType, const BYTE* srcBase) { - if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; } - if (tableType == byU32) { const U32* const hashTable = (U32*) tableBase; return hashTable[h] + srcBase; } - { const U16* const hashTable = (U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */ + if (tableType == byPtr) { const BYTE* const* hashTable = (const BYTE* const*) tableBase; return hashTable[h]; } + if (tableType == byU32) { const U32* const hashTable = (const U32*) tableBase; return hashTable[h] + srcBase; } + { const U16* const hashTable = (const 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) +LZ4_FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, + const void* tableBase, tableType_t tableType, + const BYTE* srcBase) { U32 const h = LZ4_hashPosition(p, tableType); return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase); } +LZ4_FORCE_INLINE void LZ4_prepareTable( + LZ4_stream_t_internal* const cctx, + const int inputSize, + const tableType_t tableType) { + /* If the table hasn't been used, it's guaranteed to be zeroed out, and is + * therefore safe to use no matter what mode we're in. Otherwise, we figure + * out if it's safe to leave as is or whether it needs to be reset. + */ + if (cctx->tableType != clearedTable) { + if (cctx->tableType != tableType + || (tableType == byU16 && cctx->currentOffset + inputSize >= 0xFFFFU) + || (tableType == byU32 && cctx->currentOffset > 1 GB) + || tableType == byPtr + || inputSize >= 4 KB) + { + DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", cctx); + MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE); + cctx->currentOffset = 0; + cctx->tableType = clearedTable; + } else { + DEBUGLOG(4, "LZ4_prepareTable: Re-use hash table (no reset)"); + } + } + + /* Adding a gap, so all previous entries are > MAX_DISTANCE back, is faster + * than compressing without a gap. However, compressing with + * currentOffset == 0 is faster still, so we preserve that case. + */ + if (cctx->currentOffset != 0 && tableType == byU32) { + DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset"); + cctx->currentOffset += 64 KB; + } + + /* Finally, clear history */ + cctx->dictCtx = NULL; + cctx->dictionary = NULL; + cctx->dictSize = 0; +} /** LZ4_compress_generic() : inlined, to ensure branches are decided at compilation time */ -FORCE_INLINE int LZ4_compress_generic( +LZ4_FORCE_INLINE int LZ4_compress_generic( LZ4_stream_t_internal* const cctx, const char* const source, char* const dest, const int inputSize, + int *inputConsumed, /* only written when outputLimited == fillOutput */ const int maxOutputSize, const limitedOutput_directive outputLimited, const tableType_t tableType, - const dict_directive dict, + const dict_directive dictDirective, const dictIssue_directive dictIssue, const U32 acceleration) { const BYTE* ip = (const BYTE*) source; - const BYTE* base; + + U32 const startIndex = cctx->currentOffset; + const BYTE* base = (const BYTE*) source - startIndex; const BYTE* lowLimit; - const BYTE* const lowRefLimit = ip - cctx->dictSize; - const BYTE* const dictionary = cctx->dictionary; - const BYTE* const dictEnd = dictionary + cctx->dictSize; - const ptrdiff_t dictDelta = dictEnd - (const BYTE*)source; + + const LZ4_stream_t_internal* dictCtx = (const LZ4_stream_t_internal*) cctx->dictCtx; + const BYTE* const dictionary = + dictDirective == usingDictCtx ? dictCtx->dictionary : cctx->dictionary; + const U32 dictSize = + dictDirective == usingDictCtx ? dictCtx->dictSize : cctx->dictSize; + const U32 dictDelta = (dictDirective == usingDictCtx) ? startIndex - dictCtx->currentOffset : 0; /* make indexes in dictCtx comparable with index in current context */ + + int const maybe_extMem = (dictDirective == usingExtDict) || (dictDirective == usingDictCtx); + U32 const prefixIdxLimit = startIndex - dictSize; /* used when dictDirective == dictSmall */ + const BYTE* const dictEnd = dictionary + dictSize; const BYTE* anchor = (const BYTE*) source; const BYTE* const iend = ip + inputSize; - const BYTE* const mflimit = iend - MFLIMIT; + const BYTE* const mflimitPlusOne = iend - MFLIMIT + 1; const BYTE* const matchlimit = iend - LASTLITERALS; + /* the dictCtx currentOffset is indexed on the start of the dictionary, + * while a dictionary in the current context precedes the currentOffset */ + const BYTE* dictBase = (dictDirective == usingDictCtx) ? + dictionary + dictSize - dictCtx->currentOffset : + dictionary + dictSize - startIndex; + BYTE* op = (BYTE*) dest; BYTE* const olimit = op + maxOutputSize; + U32 offset = 0; U32 forwardH; + DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, tableType=%u", inputSize, tableType); /* Init conditions */ + if (outputLimited == fillOutput && maxOutputSize < 1) return 0; /* Impossible to store anything */ if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported inputSize, too large (or negative) */ - switch(dict) - { - case noDict: - default: - base = (const BYTE*)source; - lowLimit = (const BYTE*)source; - break; - case withPrefix64k: - base = (const BYTE*)source - cctx->currentOffset; - lowLimit = (const BYTE*)source - cctx->dictSize; - break; - case usingExtDict: - base = (const BYTE*)source - cctx->currentOffset; - lowLimit = (const BYTE*)source; - break; + if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */ + if (tableType==byPtr) assert(dictDirective==noDict); /* only supported use case with byPtr */ + assert(acceleration >= 1); + + lowLimit = (const BYTE*)source - (dictDirective == withPrefix64k ? dictSize : 0); + + /* Update context state */ + if (dictDirective == usingDictCtx) { + /* Subsequent linked blocks can't use the dictionary. */ + /* Instead, they use the block we just compressed. */ + cctx->dictCtx = NULL; + cctx->dictSize = (U32)inputSize; + } else { + cctx->dictSize += (U32)inputSize; } - if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */ - if (inputSize<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ + cctx->currentOffset += (U32)inputSize; + cctx->tableType = (U16)tableType; + + if (inputSize<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ /* First Byte */ LZ4_putPosition(ip, cctx->hashTable, tableType, base); @@ -512,12 +722,12 @@ FORCE_INLINE int LZ4_compress_generic( /* Main Loop */ for ( ; ; ) { - ptrdiff_t refDelta = 0; const BYTE* match; BYTE* token; /* Find a match */ - { const BYTE* forwardIp = ip; + if (tableType == byPtr) { + const BYTE* forwardIp = ip; unsigned step = 1; unsigned searchMatchNb = acceleration << LZ4_skipTrigger; do { @@ -526,34 +736,89 @@ FORCE_INLINE int LZ4_compress_generic( forwardIp += step; step = (searchMatchNb++ >> LZ4_skipTrigger); - if (unlikely(forwardIp > mflimit)) goto _last_literals; + if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals; + assert(ip < mflimitPlusOne); match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base); - if (dict==usingExtDict) { - if (match < (const BYTE*)source) { - refDelta = dictDelta; + forwardH = LZ4_hashPosition(forwardIp, tableType); + LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base); + + } while ( (match+MAX_DISTANCE < ip) + || (LZ4_read32(match) != LZ4_read32(ip)) ); + + } else { /* byU32, byU16 */ + + const BYTE* forwardIp = ip; + unsigned step = 1; + unsigned searchMatchNb = acceleration << LZ4_skipTrigger; + do { + U32 const h = forwardH; + U32 const current = (U32)(forwardIp - base); + U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType); + assert(matchIndex <= current); + assert(forwardIp - base < (ptrdiff_t)(2 GB - 1)); + ip = forwardIp; + forwardIp += step; + step = (searchMatchNb++ >> LZ4_skipTrigger); + + if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals; + assert(ip < mflimitPlusOne); + + if (dictDirective == usingDictCtx) { + if (matchIndex < startIndex) { + /* there was no match, try the dictionary */ + assert(tableType == byU32); + matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32); + match = dictBase + matchIndex; + matchIndex += dictDelta; /* make dictCtx index comparable with current context */ lowLimit = dictionary; } else { - refDelta = 0; + match = base + matchIndex; lowLimit = (const BYTE*)source; - } } + } + } else if (dictDirective==usingExtDict) { + if (matchIndex < startIndex) { + DEBUGLOG(7, "extDict candidate: matchIndex=%5u < startIndex=%5u", matchIndex, startIndex); + assert(startIndex - matchIndex >= MINMATCH); + match = dictBase + matchIndex; + lowLimit = dictionary; + } else { + match = base + matchIndex; + lowLimit = (const BYTE*)source; + } + } else { /* single continuous memory segment */ + match = base + matchIndex; + } forwardH = LZ4_hashPosition(forwardIp, tableType); - LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base); + LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType); + + if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) continue; /* match outside of valid area */ + assert(matchIndex < current); + if ((tableType != byU16) && (matchIndex+MAX_DISTANCE < current)) continue; /* too far */ + if (tableType == byU16) assert((current - matchIndex) <= MAX_DISTANCE); /* too_far presumed impossible with byU16 */ - } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0) - || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip)) - || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) ); + if (LZ4_read32(match) == LZ4_read32(ip)) { + if (maybe_extMem) offset = current - matchIndex; + break; /* match found */ + } + + } while(1); } /* Catch up */ - while (((ip>anchor) & (match+refDelta > lowLimit)) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; } + while (((ip>anchor) & (match > lowLimit)) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; } /* Encode Literals */ { unsigned const litLength = (unsigned)(ip - anchor); token = op++; - if ((outputLimited) && /* Check output buffer overflow */ + if ((outputLimited == limitedOutput) && /* Check output buffer overflow */ (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit))) return 0; + if ((outputLimited == fillOutput) && + (unlikely(op + (litLength+240)/255 /* litlen */ + litLength /* literals */ + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit))) { + op--; + goto _last_literals; + } if (litLength >= RUN_MASK) { int len = (int)litLength-RUN_MASK; *token = (RUN_MASK<<ML_BITS); @@ -565,40 +830,79 @@ FORCE_INLINE int LZ4_compress_generic( /* Copy Literals */ LZ4_wildCopy(op, anchor, op+litLength); op+=litLength; + DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i", + (int)(anchor-(const BYTE*)source), litLength, (int)(ip-(const BYTE*)source)); } _next_match: + /* at this stage, the following variables must be correctly set : + * - ip : at start of LZ operation + * - match : at start of previous pattern occurence; can be within current prefix, or within extDict + * - offset : if maybe_ext_memSegment==1 (constant) + * - lowLimit : must be == dictionary to mean "match is within extDict"; must be == source otherwise + * - token and *token : position to write 4-bits for match length; higher 4-bits for literal length supposed already written + */ + + if ((outputLimited == fillOutput) && + (op + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit)) { + /* the match was too close to the end, rewind and go to last literals */ + op = token; + goto _last_literals; + } + /* Encode Offset */ - LZ4_writeLE16(op, (U16)(ip-match)); op+=2; + if (maybe_extMem) { /* static test */ + DEBUGLOG(6, " with offset=%u (ext if > %i)", offset, (int)(ip - (const BYTE*)source)); + assert(offset <= MAX_DISTANCE && offset > 0); + LZ4_writeLE16(op, (U16)offset); op+=2; + } else { + DEBUGLOG(6, " with offset=%u (same segment)", (U32)(ip - match)); + assert(ip-match <= MAX_DISTANCE); + LZ4_writeLE16(op, (U16)(ip - match)); op+=2; + } /* Encode MatchLength */ { unsigned matchCode; - if ((dict==usingExtDict) && (lowLimit==dictionary)) { - const BYTE* limit; - match += refDelta; - limit = ip + (dictEnd-match); + if ( (dictDirective==usingExtDict || dictDirective==usingDictCtx) + && (lowLimit==dictionary) /* match within extDict */ ) { + const BYTE* limit = ip + (dictEnd-match); + assert(dictEnd > match); if (limit > matchlimit) limit = matchlimit; matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit); ip += MINMATCH + matchCode; if (ip==limit) { - unsigned const more = LZ4_count(ip, (const BYTE*)source, matchlimit); + unsigned const more = LZ4_count(limit, (const BYTE*)source, matchlimit); matchCode += more; ip += more; } + DEBUGLOG(6, " with matchLength=%u starting in extDict", matchCode+MINMATCH); } else { matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit); ip += MINMATCH + matchCode; + DEBUGLOG(6, " with matchLength=%u", matchCode+MINMATCH); } - if ( outputLimited && /* Check output buffer overflow */ - (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) ) - return 0; + if ((outputLimited) && /* Check output buffer overflow */ + (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) ) { + if (outputLimited == limitedOutput) + return 0; + if (outputLimited == fillOutput) { + /* Match description too long : reduce it */ + U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 2 - 1 - LASTLITERALS) * 255; + ip -= matchCode - newMatchCode; + matchCode = newMatchCode; + } + } if (matchCode >= ML_MASK) { *token += ML_MASK; matchCode -= ML_MASK; LZ4_write32(op, 0xFFFFFFFF); - while (matchCode >= 4*255) op+=4, LZ4_write32(op, 0xFFFFFFFF), matchCode -= 4*255; + while (matchCode >= 4*255) { + op+=4; + LZ4_write32(op, 0xFFFFFFFF); + matchCode -= 4*255; + } op += matchCode / 255; *op++ = (BYTE)(matchCode % 255); } else @@ -608,37 +912,80 @@ _next_match: anchor = ip; /* Test end of chunk */ - if (ip > mflimit) break; + if (ip >= mflimitPlusOne) break; /* Fill table */ LZ4_putPosition(ip-2, cctx->hashTable, tableType, base); /* Test next position */ - match = LZ4_getPosition(ip, cctx->hashTable, tableType, base); - if (dict==usingExtDict) { - if (match < (const BYTE*)source) { - refDelta = dictDelta; - lowLimit = dictionary; - } else { - refDelta = 0; - lowLimit = (const BYTE*)source; - } } - LZ4_putPosition(ip, cctx->hashTable, tableType, base); - if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1) - && (match+MAX_DISTANCE>=ip) - && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) ) - { token=op++; *token=0; goto _next_match; } + if (tableType == byPtr) { + + match = LZ4_getPosition(ip, cctx->hashTable, tableType, base); + LZ4_putPosition(ip, cctx->hashTable, tableType, base); + if ( (match+MAX_DISTANCE >= ip) + && (LZ4_read32(match) == LZ4_read32(ip)) ) + { token=op++; *token=0; goto _next_match; } + + } else { /* byU32, byU16 */ + + U32 const h = LZ4_hashPosition(ip, tableType); + U32 const current = (U32)(ip-base); + U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType); + assert(matchIndex < current); + if (dictDirective == usingDictCtx) { + if (matchIndex < startIndex) { + /* there was no match, try the dictionary */ + matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32); + match = dictBase + matchIndex; + lowLimit = dictionary; /* required for match length counter */ + matchIndex += dictDelta; + } else { + match = base + matchIndex; + lowLimit = (const BYTE*)source; /* required for match length counter */ + } + } else if (dictDirective==usingExtDict) { + if (matchIndex < startIndex) { + match = dictBase + matchIndex; + lowLimit = dictionary; /* required for match length counter */ + } else { + match = base + matchIndex; + lowLimit = (const BYTE*)source; /* required for match length counter */ + } + } else { /* single memory segment */ + match = base + matchIndex; + } + LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType); + assert(matchIndex < current); + if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1) + && ((tableType==byU16) ? 1 : (matchIndex+MAX_DISTANCE >= current)) + && (LZ4_read32(match) == LZ4_read32(ip)) ) { + token=op++; + *token=0; + if (maybe_extMem) offset = current - matchIndex; + DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i", + (int)(anchor-(const BYTE*)source), 0, (int)(ip-(const BYTE*)source)); + goto _next_match; + } + } /* Prepare next loop */ forwardH = LZ4_hashPosition(++ip, tableType); + } _last_literals: /* Encode Last Literals */ - { size_t const lastRun = (size_t)(iend - anchor); + { size_t lastRun = (size_t)(iend - anchor); if ( (outputLimited) && /* Check output buffer overflow */ - ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) ) - return 0; + (op + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > olimit)) { + if (outputLimited == fillOutput) { + /* adapt lastRun to fill 'dst' */ + lastRun = (olimit-op) - 1; + lastRun -= (lastRun+240)/255; + } + if (outputLimited == limitedOutput) + return 0; + } if (lastRun >= RUN_MASK) { size_t accumulator = lastRun - RUN_MASK; *op++ = RUN_MASK << ML_BITS; @@ -648,46 +995,99 @@ _last_literals: *op++ = (BYTE)(lastRun<<ML_BITS); } memcpy(op, anchor, lastRun); + ip = anchor + lastRun; op += lastRun; } - /* End */ - return (int) (((char*)op)-dest); + if (outputLimited == fillOutput) { + *inputConsumed = (int) (((const char*)ip)-source); + } + DEBUGLOG(5, "LZ4_compress_generic: compressed %i bytes into %i bytes", inputSize, (int)(((char*)op) - dest)); + return (int)(((char*)op) - dest); } int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) { LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse; + if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; LZ4_resetStream((LZ4_stream_t*)state); + if (maxOutputSize >= LZ4_compressBound(inputSize)) { + if (inputSize < LZ4_64Klimit) { + return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, byU16, noDict, noDictIssue, acceleration); + } else { + const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > MAX_DISTANCE)) ? byPtr : byU32; + return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); + } + } else { + if (inputSize < LZ4_64Klimit) {; + return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); + } else { + const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > MAX_DISTANCE)) ? byPtr : byU32; + return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration); + } + } +} + +/** + * LZ4_compress_fast_extState_fastReset() : + * A variant of LZ4_compress_fast_extState(). + * + * Using this variant avoids an expensive initialization step. It is only safe + * to call if the state buffer is known to be correctly initialized already + * (see comment in lz4.h on LZ4_resetStream_fast() for a definition of + * "correctly initialized"). + */ +int LZ4_compress_fast_extState_fastReset(void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration) +{ + LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse; if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; - if (maxOutputSize >= LZ4_compressBound(inputSize)) { - if (inputSize < LZ4_64Klimit) - return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue, acceleration); - else - return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration); + if (dstCapacity >= LZ4_compressBound(srcSize)) { + if (srcSize < LZ4_64Klimit) { + const tableType_t tableType = byU16; + LZ4_prepareTable(ctx, srcSize, tableType); + if (ctx->currentOffset) { + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, dictSmall, acceleration); + } else { + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); + } + } else { + const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32; + LZ4_prepareTable(ctx, srcSize, tableType); + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); + } } else { - 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, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration); + if (srcSize < LZ4_64Klimit) { + const tableType_t tableType = byU16; + LZ4_prepareTable(ctx, srcSize, tableType); + if (ctx->currentOffset) { + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, dictSmall, acceleration); + } else { + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration); + } + } else { + const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32; + LZ4_prepareTable(ctx, srcSize, tableType); + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration); + } } } int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) { -#if (HEAPMODE) - void* ctxPtr = ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ + int result; +#if (LZ4_HEAPMODE) + LZ4_stream_t* ctxPtr = ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ + if (ctxPtr == NULL) return 0; #else LZ4_stream_t ctx; - void* const ctxPtr = &ctx; + LZ4_stream_t* const ctxPtr = &ctx; #endif + result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration); - int const result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration); - -#if (HEAPMODE) +#if (LZ4_HEAPMODE) FREEMEM(ctxPtr); #endif return result; @@ -708,172 +1108,15 @@ int LZ4_compress_fast_force(const char* source, char* dest, int inputSize, int m LZ4_resetStream(&ctx); if (inputSize < LZ4_64Klimit) - return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); + return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); else - return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, sizeof(void*)==8 ? byU32 : byPtr, noDict, noDictIssue, acceleration); -} - - -/*-****************************** -* *_destSize() variant -********************************/ - -static int LZ4_compress_destSize_generic( - LZ4_stream_t_internal* 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_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ - - /* First Byte */ - *srcSizePtr = 0; - LZ4_putPosition(ip, ctx->hashTable, tableType, base); - ip++; forwardH = LZ4_hashPosition(ip, tableType); - - /* Main Loop */ - for ( ; ; ) { - const BYTE* match; - BYTE* token; - - /* Find a match */ - { const BYTE* forwardIp = ip; - unsigned step = 1; - unsigned searchMatchNb = 1 << LZ4_skipTrigger; - - do { - U32 h = forwardH; - ip = forwardIp; - forwardIp += step; - step = (searchMatchNb++ >> LZ4_skipTrigger); - - if (unlikely(forwardIp > mflimit)) goto _last_literals; - - match = LZ4_getPositionOnHash(h, ctx->hashTable, tableType, base); - forwardH = LZ4_hashPosition(forwardIp, tableType); - LZ4_putPositionOnHash(ip, h, ctx->hashTable, 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<<ML_BITS); - for(; len >= 255 ; len-=255) *op++ = 255; - *op++ = (BYTE)len; - } - else *token = (BYTE)(litLength<<ML_BITS); - - /* Copy Literals */ - LZ4_wildCopy(op, anchor, op+litLength); - op += litLength; - } - -_next_match: - /* Encode Offset */ - LZ4_writeLE16(op, (U16)(ip-match)); op+=2; - - /* Encode MatchLength */ - { size_t matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit); - - if (op + ((matchLength+240)/255) > oMaxMatch) { - /* Match description too long : reduce it */ - matchLength = (15-1) + (oMaxMatch-op) * 255; - } - 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->hashTable, tableType, base); - - /* Test next position */ - match = LZ4_getPosition(ip, ctx->hashTable, tableType, base); - LZ4_putPosition(ip, ctx->hashTable, 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<<ML_BITS); - } - memcpy(op, anchor, lastRunSize); - op += lastRunSize; - } - - /* End */ - *srcSizePtr = (int) (((const char*)ip)-src); - return (int) (((char*)op)-dst); + return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, sizeof(void*)==8 ? byU32 : byPtr, noDict, noDictIssue, acceleration); } +/* Note!: This function leaves the stream in an unclean/broken state! + * It is not safe to subsequently use the same state with a _fastReset() or + * _continue() call without resetting it. */ static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize) { LZ4_resetStream(state); @@ -881,18 +1124,20 @@ static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, if (targetDstSize >= 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->internal_donotuse, src, dst, srcSizePtr, targetDstSize, byU16); - else - return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, sizeof(void*)==8 ? byU32 : byPtr); - } + if (*srcSizePtr < LZ4_64Klimit) { + return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, byU16, noDict, noDictIssue, 1); + } else { + tableType_t const tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32; + return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, tableType, noDict, noDictIssue, 1); + } } } int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize) { -#if (HEAPMODE) - LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ +#if (LZ4_HEAPMODE) + LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ + if (ctx == NULL) return 0; #else LZ4_stream_t ctxBody; LZ4_stream_t* ctx = &ctxBody; @@ -900,7 +1145,7 @@ int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targe int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize); -#if (HEAPMODE) +#if (LZ4_HEAPMODE) FREEMEM(ctx); #endif return result; @@ -914,19 +1159,28 @@ int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targe LZ4_stream_t* LZ4_createStream(void) { - LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(8, LZ4_STREAMSIZE_U64); + LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal)); /* A compilation error here means LZ4_STREAMSIZE is not large enough */ + DEBUGLOG(4, "LZ4_createStream %p", lz4s); + if (lz4s == NULL) return NULL; LZ4_resetStream(lz4s); return lz4s; } void LZ4_resetStream (LZ4_stream_t* LZ4_stream) { + DEBUGLOG(5, "LZ4_resetStream (ctx:%p)", LZ4_stream); MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t)); } +void LZ4_resetStream_fast(LZ4_stream_t* ctx) { + LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32); +} + int LZ4_freeStream (LZ4_stream_t* LZ4_stream) { + if (!LZ4_stream) return 0; /* support free on NULL */ + DEBUGLOG(5, "LZ4_freeStream %p", LZ4_stream); FREEMEM(LZ4_stream); return (0); } @@ -936,43 +1190,70 @@ int LZ4_freeStream (LZ4_stream_t* LZ4_stream) int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) { LZ4_stream_t_internal* dict = &LZ4_dict->internal_donotuse; + const tableType_t tableType = byU32; const BYTE* p = (const BYTE*)dictionary; const BYTE* const dictEnd = p + dictSize; const BYTE* base; - if ((dict->initCheck) || (dict->currentOffset > 1 GB)) /* Uninitialized structure, or reuse overflow */ - LZ4_resetStream(LZ4_dict); + DEBUGLOG(4, "LZ4_loadDict (%i bytes from %p into %p)", dictSize, dictionary, LZ4_dict); - if (dictSize < (int)HASH_UNIT) { - dict->dictionary = NULL; - dict->dictSize = 0; - return 0; - } + /* It's necessary to reset the context, + * and not just continue it with prepareTable() + * to avoid any risk of generating overflowing matchIndex + * when compressing using this dictionary */ + LZ4_resetStream(LZ4_dict); + + /* We always increment the offset by 64 KB, since, if the dict is longer, + * we truncate it to the last 64k, and if it's shorter, we still want to + * advance by a whole window length so we can provide the guarantee that + * there are only valid offsets in the window, which allows an optimization + * in LZ4_compress_fast_continue() where it uses noDictIssue even when the + * dictionary isn't a full 64k. */ if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB; - dict->currentOffset += 64 KB; - base = p - dict->currentOffset; + base = dictEnd - 64 KB - dict->currentOffset; dict->dictionary = p; dict->dictSize = (U32)(dictEnd - p); - dict->currentOffset += dict->dictSize; + dict->currentOffset += 64 KB; + dict->tableType = tableType; + + if (dictSize < (int)HASH_UNIT) { + return 0; + } while (p <= dictEnd-HASH_UNIT) { - LZ4_putPosition(p, dict->hashTable, byU32, base); + LZ4_putPosition(p, dict->hashTable, tableType, base); p+=3; } return dict->dictSize; } +void LZ4_attach_dictionary(LZ4_stream_t *working_stream, const LZ4_stream_t *dictionary_stream) { + if (dictionary_stream != NULL) { + /* If the current offset is zero, we will never look in the + * external dictionary context, since there is no value a table + * entry can take that indicate a miss. In that case, we need + * to bump the offset to something non-zero. + */ + if (working_stream->internal_donotuse.currentOffset == 0) { + working_stream->internal_donotuse.currentOffset = 64 KB; + } + working_stream->internal_donotuse.dictCtx = &(dictionary_stream->internal_donotuse); + } else { + working_stream->internal_donotuse.dictCtx = NULL; + } +} -static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src) + +static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, int nextSize) { - if ((LZ4_dict->currentOffset > 0x80000000) || - ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) { /* address space overflow */ + if (LZ4_dict->currentOffset + nextSize > 0x80000000) { /* potential ptrdiff_t overflow (32-bits mode) */ /* rescale hash table */ U32 const delta = LZ4_dict->currentOffset - 64 KB; const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize; int i; + DEBUGLOG(4, "LZ4_renormDictT"); for (i=0; i<LZ4_HASH_SIZE_U32; i++) { if (LZ4_dict->hashTable[i] < delta) LZ4_dict->hashTable[i]=0; else LZ4_dict->hashTable[i] -= delta; @@ -986,15 +1267,25 @@ static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src) int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) { + const tableType_t tableType = byU32; LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse; - const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; + const BYTE* dictEnd = streamPtr->dictionary + streamPtr->dictSize; + + DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i)", inputSize); - 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); + LZ4_renormDictT(streamPtr, inputSize); /* avoid index overflow */ if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; + /* invalidate tiny dictionaries */ + if ( (streamPtr->dictSize-1 < 4) /* intentional underflow */ + && (dictEnd != (const BYTE*)source) ) { + DEBUGLOG(5, "LZ4_compress_fast_continue: dictSize(%u) at addr:%p is too small", streamPtr->dictSize, streamPtr->dictionary); + streamPtr->dictSize = 0; + streamPtr->dictionary = (const BYTE*)source; + dictEnd = (const BYTE*)source; + } + /* Check overlapping input/dictionary space */ { const BYTE* sourceEnd = (const BYTE*) source + inputSize; if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) { @@ -1007,46 +1298,61 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, ch /* 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(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration); + return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration); else - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration); - streamPtr->dictSize += (U32)inputSize; - streamPtr->currentOffset += (U32)inputSize; - return result; + return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, noDictIssue, acceleration); } /* external dictionary mode */ { int result; - if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration); - else - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration); + if (streamPtr->dictCtx) { + /* We depend here on the fact that dictCtx'es (produced by + * LZ4_loadDict) guarantee that their tables contain no references + * to offsets between dictCtx->currentOffset - 64 KB and + * dictCtx->currentOffset - dictCtx->dictSize. This makes it safe + * to use noDictIssue even when the dict isn't a full 64 KB. + */ + if (inputSize > 4 KB) { + /* For compressing large blobs, it is faster to pay the setup + * cost to copy the dictionary's tables into the active context, + * so that the compression loop is only looking into one table. + */ + memcpy(streamPtr, streamPtr->dictCtx, sizeof(LZ4_stream_t)); + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration); + } else { + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration); + } + } else { + if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) { + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration); + } else { + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration); + } + } streamPtr->dictionary = (const BYTE*)source; streamPtr->dictSize = (U32)inputSize; - streamPtr->currentOffset += (U32)inputSize; return result; } } -/* Hidden debug function, to force external dictionary mode */ -int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize) +/* Hidden debug function, to force-test external dictionary mode */ +int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize) { LZ4_stream_t_internal* streamPtr = &LZ4_dict->internal_donotuse; 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(streamPtr, smallest); + LZ4_renormDictT(streamPtr, srcSize); - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1); + if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) { + result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, dictSmall, 1); + } else { + result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, noDictIssue, 1); + } streamPtr->dictionary = (const BYTE*)source; - streamPtr->dictSize = (U32)inputSize; - streamPtr->currentOffset += (U32)inputSize; + streamPtr->dictSize = (U32)srcSize; return result; } @@ -1077,63 +1383,119 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize) -/*-***************************** -* Decompression functions -*******************************/ +/*-******************************* + * Decompression functions + ********************************/ + +typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; +typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive; + +#undef MIN +#define MIN(a,b) ( (a) < (b) ? (a) : (b) ) + /*! LZ4_decompress_generic() : - * This generic decompression function cover all use cases. - * It shall be instantiated several times, using different sets of directives - * Note that it is important this generic function is really inlined, + * This generic decompression function covers all use cases. + * It shall be instantiated several times, using different sets of directives. + * Note that it is important for performance that this function really get inlined, * in order to remove useless branches during compilation optimization. */ -FORCE_INLINE int LZ4_decompress_generic( - 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 partialDecoding, /* full, partial */ - int targetOutputSize, /* only used if partialDecoding==partial */ - int dict, /* noDict, withPrefix64k, usingExtDict */ - const BYTE* const lowPrefix, /* == dest when no prefix */ +LZ4_FORCE_INLINE int +LZ4_decompress_generic( + const char* const src, + char* const dst, + int srcSize, + int outputSize, /* If endOnInput==endOnInputSize, this value is `dstCapacity` */ + + endCondition_directive endOnInput, /* endOnOutputSize, endOnInputSize */ + earlyEnd_directive partialDecoding, /* full, partial */ + dict_directive dict, /* noDict, withPrefix64k, usingExtDict */ + const BYTE* const lowPrefix, /* always <= dst, == dst when no prefix */ const BYTE* const dictStart, /* only if dict==usingExtDict */ const size_t dictSize /* note : = 0 if noDict */ ) { - /* Local Variables */ - const BYTE* ip = (const BYTE*) source; - const BYTE* const iend = ip + inputSize; + const BYTE* ip = (const BYTE*) src; + const BYTE* const iend = ip + srcSize; - BYTE* op = (BYTE*) dest; + BYTE* op = (BYTE*) dst; BYTE* const oend = op + outputSize; BYTE* cpy; - BYTE* oexit = op + targetOutputSize; - const BYTE* const lowLimit = lowPrefix - dictSize; const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize; - const unsigned dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; - const int dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3}; + const unsigned inc32table[8] = {0, 1, 2, 1, 0, 4, 4, 4}; + const int dec64table[8] = {0, 0, 0, -1, -4, 1, 2, 3}; const int safeDecode = (endOnInput==endOnInputSize); const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB))); + /* Set up the "end" pointers for the shortcut. */ + const BYTE* const shortiend = iend - (endOnInput ? 14 : 8) /*maxLL*/ - 2 /*offset*/; + const BYTE* const shortoend = oend - (endOnInput ? 14 : 8) /*maxLL*/ - 18 /*maxML*/; + + DEBUGLOG(5, "LZ4_decompress_generic (srcSize:%i, dstSize:%i)", srcSize, outputSize); /* 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 ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1); + assert(lowPrefix <= op); + assert(src != NULL); + if ((endOnInput) && (unlikely(outputSize==0))) return ((srcSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */ + if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0 ? 1 : -1); + if ((endOnInput) && unlikely(srcSize==0)) return -1; /* Main Loop : decode sequences */ while (1) { - size_t length; const BYTE* match; size_t offset; - /* get literal length */ unsigned const token = *ip++; - if ((length=(token>>ML_BITS)) == RUN_MASK) { + size_t length = token >> ML_BITS; /* literal length */ + + assert(!endOnInput || ip <= iend); /* ip < iend before the increment */ + + /* A two-stage shortcut for the most common case: + * 1) If the literal length is 0..14, and there is enough space, + * enter the shortcut and copy 16 bytes on behalf of the literals + * (in the fast mode, only 8 bytes can be safely copied this way). + * 2) Further if the match length is 4..18, copy 18 bytes in a similar + * manner; but we ensure that there's enough space in the output for + * those 18 bytes earlier, upon entering the shortcut (in other words, + * there is a combined check for both stages). + */ + if ( (endOnInput ? length != RUN_MASK : length <= 8) + /* strictly "less than" on input, to re-enter the loop with at least one byte */ + && likely((endOnInput ? ip < shortiend : 1) & (op <= shortoend)) ) { + /* Copy the literals */ + memcpy(op, ip, endOnInput ? 16 : 8); + op += length; ip += length; + + /* The second stage: prepare for match copying, decode full info. + * If it doesn't work out, the info won't be wasted. */ + length = token & ML_MASK; /* match length */ + offset = LZ4_readLE16(ip); ip += 2; + match = op - offset; + assert(match <= op); /* check overflow */ + + /* Do not deal with overlapping matches. */ + if ( (length != ML_MASK) + && (offset >= 8) + && (dict==withPrefix64k || match >= lowPrefix) ) { + /* Copy the match. */ + memcpy(op + 0, match + 0, 8); + memcpy(op + 8, match + 8, 8); + memcpy(op +16, match +16, 2); + op += length + MINMATCH; + /* Both stages worked, load the next token. */ + continue; + } + + /* The second stage didn't work out, but the info is ready. + * Propel it right to the point of match copying. */ + goto _copy_match; + } + + /* decode literal length */ + if (length == RUN_MASK) { unsigned s; + if (unlikely(endOnInput ? ip >= iend-RUN_MASK : 0)) goto _output_error; /* overflow detection */ do { s = *ip++; length += s; @@ -1144,11 +1506,12 @@ FORCE_INLINE int LZ4_decompress_generic( /* copy literals */ cpy = op+length; - if ( ((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) ) - || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) ) + LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH); + if ( ((endOnInput) && ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) ) + || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) ) { if (partialDecoding) { - if (cpy > oend) goto _output_error; /* Error : write attempt beyond end of output buffer */ + if (cpy > oend) { cpy = oend; length = oend-op; } /* Partial decoding : stop in the middle of literal segment */ if ((endOnInput) && (ip+length > iend)) goto _output_error; /* Error : read attempt beyond end of input buffer */ } else { if ((!endOnInput) && (cpy != oend)) goto _output_error; /* Error : block decoding must stop exactly there */ @@ -1157,19 +1520,31 @@ FORCE_INLINE int LZ4_decompress_generic( memcpy(op, ip, length); ip += length; op += length; - break; /* Necessarily EOF, due to parsing restrictions */ + if (!partialDecoding || (cpy == oend)) { + /* Necessarily EOF, due to parsing restrictions */ + break; + } + + } else { + LZ4_wildCopy(op, ip, cpy); /* may overwrite up to WILDCOPYLENGTH beyond cpy */ + ip += length; op = cpy; } - LZ4_wildCopy(op, ip, cpy); - ip += length; op = cpy; /* get offset */ offset = LZ4_readLE16(ip); ip+=2; match = op - offset; - if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error; /* Error : offset outside buffers */ - LZ4_write32(op, (U32)offset); /* costs ~1%; silence an msan warning when offset==0 */ /* get matchlength */ length = token & ML_MASK; + +_copy_match: + if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */ + if (!partialDecoding) { + assert(oend > op); + assert(oend - op >= 4); + LZ4_write32(op, 0); /* silence an msan warning when offset==0; costs <1%; */ + } /* note : when partialDecoding, there is no guarantee that at least 4 bytes remain available in output buffer */ + if (length == ML_MASK) { unsigned s; do { @@ -1181,21 +1556,24 @@ FORCE_INLINE int LZ4_decompress_generic( } length += MINMATCH; - /* check external dictionary */ + /* match starting within external dictionary */ if ((dict==usingExtDict) && (match < lowPrefix)) { - if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error; /* doesn't respect parsing restriction */ + if (unlikely(op+length > oend-LASTLITERALS)) { + if (partialDecoding) length = MIN(length, (size_t)(oend-op)); + else goto _output_error; /* doesn't respect parsing restriction */ + } if (length <= (size_t)(lowPrefix-match)) { - /* match can be copied as a single segment from external dictionary */ + /* match fits entirely within external dictionary : just copy */ memmove(op, dictEnd - (lowPrefix-match), length); op += length; } else { - /* match encompass external dictionary and current block */ - size_t const copySize = (size_t)(lowPrefix-match); + /* match stretches into both external dictionary and current block */ + size_t const copySize = (size_t)(lowPrefix - match); size_t const restSize = length - copySize; memcpy(op, dictEnd - copySize, copySize); op += copySize; - if (restSize > (size_t)(op-lowPrefix)) { /* overlap copy */ + if (restSize > (size_t)(op - lowPrefix)) { /* overlap copy */ BYTE* const endOfMatch = op + restSize; const BYTE* copyFrom = lowPrefix; while (op < endOfMatch) *op++ = *copyFrom++; @@ -1208,87 +1586,180 @@ FORCE_INLINE int LZ4_decompress_generic( /* copy match within block */ cpy = op + length; + + /* partialDecoding : may not respect endBlock parsing restrictions */ + assert(op<=oend); + if (partialDecoding && (cpy > oend-MATCH_SAFEGUARD_DISTANCE)) { + size_t const mlen = MIN(length, (size_t)(oend-op)); + const BYTE* const matchEnd = match + mlen; + BYTE* const copyEnd = op + mlen; + if (matchEnd > op) { /* overlap copy */ + while (op < copyEnd) *op++ = *match++; + } else { + memcpy(op, match, mlen); + } + op = copyEnd; + if (op==oend) break; + continue; + } + if (unlikely(offset<8)) { - const int dec64 = dec64table[offset]; op[0] = match[0]; op[1] = match[1]; op[2] = match[2]; op[3] = match[3]; - match += dec32table[offset]; + match += inc32table[offset]; memcpy(op+4, match, 4); - match -= dec64; - } else { LZ4_copy8(op, match); match+=8; } + match -= dec64table[offset]; + } else { + memcpy(op, match, 8); + match += 8; + } op += 8; - if (unlikely(cpy>oend-12)) { - BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1); + if (unlikely(cpy > oend-MATCH_SAFEGUARD_DISTANCE)) { + BYTE* const oCopyLimit = oend - (WILDCOPYLENGTH-1); if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last LASTLITERALS bytes must be literals (uncompressed) */ if (op < oCopyLimit) { LZ4_wildCopy(op, match, oCopyLimit); match += oCopyLimit - op; op = oCopyLimit; } - while (op<cpy) *op++ = *match++; + while (op < cpy) *op++ = *match++; } else { - LZ4_copy8(op, match); - if (length>16) LZ4_wildCopy(op+8, match+8, cpy); + memcpy(op, match, 8); + if (length > 16) LZ4_wildCopy(op+8, match+8, cpy); } - op=cpy; /* correction */ + op = cpy; /* wildcopy correction */ } /* end of decoding */ if (endOnInput) - return (int) (((char*)op)-dest); /* Nb of output bytes decoded */ + return (int) (((char*)op)-dst); /* Nb of output bytes decoded */ else - return (int) (((const char*)ip)-source); /* Nb of input bytes read */ + return (int) (((const char*)ip)-src); /* Nb of input bytes read */ /* Overflow error detected */ _output_error: - return (int) (-(((const char*)ip)-source))-1; + return (int) (-(((const char*)ip)-src))-1; } +/*===== Instantiate the API decoding functions. =====*/ + +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize) { - return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, NULL, 0); + return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, + endOnInputSize, decode_full_block, noDict, + (BYTE*)dest, NULL, 0); } -int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize) +LZ4_FORCE_O2_GCC_PPC64LE +int LZ4_decompress_safe_partial(const char* src, char* dst, int compressedSize, int targetOutputSize, int dstCapacity) { - return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, NULL, 0); + dstCapacity = MIN(targetOutputSize, dstCapacity); + return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity, + endOnInputSize, partial_decode, + noDict, (BYTE*)dst, NULL, 0); } +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_fast(const char* source, char* dest, int originalSize) { - return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)(dest - 64 KB), NULL, 64 KB); + return LZ4_decompress_generic(source, dest, 0, originalSize, + endOnOutputSize, decode_full_block, withPrefix64k, + (BYTE*)dest - 64 KB, NULL, 0); } +/*===== Instantiate a few more decoding cases, used more than once. =====*/ -/*===== streaming decompression functions =====*/ +LZ4_FORCE_O2_GCC_PPC64LE /* Exported, an obsolete API function. */ +int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize) +{ + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + endOnInputSize, decode_full_block, withPrefix64k, + (BYTE*)dest - 64 KB, NULL, 0); +} -/* - * If you prefer dynamic allocation methods, - * LZ4_createStreamDecode() - * provides a pointer (void*) towards an initialized LZ4_streamDecode_t structure. +/* Another obsolete API function, paired with the previous one. */ +int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize) +{ + /* LZ4_decompress_fast doesn't validate match offsets, + * and thus serves well with any prefixed dictionary. */ + return LZ4_decompress_fast(source, dest, originalSize); +} + +LZ4_FORCE_O2_GCC_PPC64LE +static int LZ4_decompress_safe_withSmallPrefix(const char* source, char* dest, int compressedSize, int maxOutputSize, + size_t prefixSize) +{ + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + endOnInputSize, decode_full_block, noDict, + (BYTE*)dest-prefixSize, NULL, 0); +} + +LZ4_FORCE_O2_GCC_PPC64LE +int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, + int compressedSize, int maxOutputSize, + const void* dictStart, size_t dictSize) +{ + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + endOnInputSize, decode_full_block, usingExtDict, + (BYTE*)dest, (const BYTE*)dictStart, dictSize); +} + +LZ4_FORCE_O2_GCC_PPC64LE +static int LZ4_decompress_fast_extDict(const char* source, char* dest, int originalSize, + const void* dictStart, size_t dictSize) +{ + return LZ4_decompress_generic(source, dest, 0, originalSize, + endOnOutputSize, decode_full_block, usingExtDict, + (BYTE*)dest, (const BYTE*)dictStart, dictSize); +} + +/* The "double dictionary" mode, for use with e.g. ring buffers: the first part + * of the dictionary is passed as prefix, and the second via dictStart + dictSize. + * These routines are used only once, in LZ4_decompress_*_continue(). */ +LZ4_FORCE_INLINE +int LZ4_decompress_safe_doubleDict(const char* source, char* dest, int compressedSize, int maxOutputSize, + size_t prefixSize, const void* dictStart, size_t dictSize) +{ + return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + endOnInputSize, decode_full_block, usingExtDict, + (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize); +} + +LZ4_FORCE_INLINE +int LZ4_decompress_fast_doubleDict(const char* source, char* dest, int originalSize, + size_t prefixSize, const void* dictStart, size_t dictSize) +{ + return LZ4_decompress_generic(source, dest, 0, originalSize, + endOnOutputSize, decode_full_block, usingExtDict, + (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize); +} + +/*===== streaming decompression functions =====*/ + LZ4_streamDecode_t* LZ4_createStreamDecode(void) { - LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(1, sizeof(LZ4_streamDecode_t)); + LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t)); return lz4s; } int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream) { + if (!LZ4_stream) return 0; /* support free on NULL */ FREEMEM(LZ4_stream); return 0; } -/*! - * LZ4_setStreamDecode() : - * Use this function to instruct where to find the dictionary. - * This function is not necessary if previous data is still available where it was decoded. - * Loading a size of 0 is allowed (same effect as no dictionary). - * Return : 1 if OK, 0 if error +/*! LZ4_setStreamDecode() : + * Use this function to instruct where to find the dictionary. + * This function is not necessary if previous data is still available where it was decoded. + * Loading a size of 0 is allowed (same effect as no dictionary). + * @return : 1 if OK, 0 if error */ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize) { @@ -1300,6 +1771,25 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti return 1; } +/*! LZ4_decoderRingBufferSize() : + * when setting a ring buffer for streaming decompression (optional scenario), + * provides the minimum size of this ring buffer + * to be compatible with any source respecting maxBlockSize condition. + * Note : in a ring buffer scenario, + * blocks are presumed decompressed next to each other. + * When not enough space remains for next block (remainingSize < maxBlockSize), + * decoding resumes from beginning of ring buffer. + * @return : minimum ring buffer size, + * or 0 if there is an error (invalid maxBlockSize). + */ +int LZ4_decoderRingBufferSize(int maxBlockSize) +{ + if (maxBlockSize < 0) return 0; + if (maxBlockSize > LZ4_MAX_INPUT_SIZE) return 0; + if (maxBlockSize < 16) maxBlockSize = 16; + return LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize); +} + /* *_continue() : These decoding functions allow decompression of multiple blocks in "streaming" mode. @@ -1307,24 +1797,38 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti If it's not possible, save the relevant part of decoded data into a safe buffer, and indicate where it stands using LZ4_setStreamDecode() */ +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize) { LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; int result; - if (lz4sd->prefixEnd == (BYTE*)dest) { - result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, full, 0, - usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); + if (lz4sd->prefixSize == 0) { + /* The first call, no dictionary yet. */ + assert(lz4sd->extDictSize == 0); + result = LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize); + if (result <= 0) return result; + lz4sd->prefixSize = result; + lz4sd->prefixEnd = (BYTE*)dest + result; + } else if (lz4sd->prefixEnd == (BYTE*)dest) { + /* They're rolling the current segment. */ + if (lz4sd->prefixSize >= 64 KB - 1) + result = LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize); + else if (lz4sd->extDictSize == 0) + result = LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, + lz4sd->prefixSize); + else + result = LZ4_decompress_safe_doubleDict(source, dest, compressedSize, maxOutputSize, + lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; lz4sd->prefixSize += result; lz4sd->prefixEnd += result; } else { + /* The buffer wraps around, or they're switching to another buffer. */ lz4sd->extDictSize = lz4sd->prefixSize; lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; - result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, full, 0, - usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize); + result = LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, + lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; lz4sd->prefixSize = result; lz4sd->prefixEnd = (BYTE*)dest + result; @@ -1333,24 +1837,32 @@ int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const ch return result; } +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize) { LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; 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 (lz4sd->prefixSize == 0) { + assert(lz4sd->extDictSize == 0); + result = LZ4_decompress_fast(source, dest, originalSize); + if (result <= 0) return result; + lz4sd->prefixSize = originalSize; + lz4sd->prefixEnd = (BYTE*)dest + originalSize; + } else if (lz4sd->prefixEnd == (BYTE*)dest) { + if (lz4sd->prefixSize >= 64 KB - 1 || lz4sd->extDictSize == 0) + result = LZ4_decompress_fast(source, dest, originalSize); + else + result = LZ4_decompress_fast_doubleDict(source, dest, originalSize, + lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; lz4sd->prefixSize += originalSize; lz4sd->prefixEnd += originalSize; } else { lz4sd->extDictSize = lz4sd->prefixSize; lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; - result = LZ4_decompress_generic(source, dest, 0, originalSize, - endOnOutputSize, full, 0, - usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize); + result = LZ4_decompress_fast_extDict(source, dest, originalSize, + lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; lz4sd->prefixSize = originalSize; lz4sd->prefixEnd = (BYTE*)dest + originalSize; @@ -1367,32 +1879,23 @@ Advanced decoding functions : 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) +int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize) { if (dictSize==0) - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest, NULL, 0); + return LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize); 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); + if (dictSize >= 64 KB - 1) + return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize); + return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, dictSize); } - 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); + return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, dictSize); } int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize) { - 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); + if (dictSize==0 || dictStart+dictSize == dest) + return LZ4_decompress_fast(source, dest, originalSize); + return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, dictSize); } @@ -1400,64 +1903,67 @@ int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compres * 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); } +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 dstCapacity) +{ + return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, dstCapacity, 1); +} +int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) +{ + return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); +} /* -These function names are deprecated and should no longer be used. +These decompression functions are deprecated and should no longer be used. They are only provided here for compatibility with older user programs. - LZ4_uncompress is totally equivalent to LZ4_decompress_fast - LZ4_uncompress_unknownOutputSize is totally equivalent to LZ4_decompress_safe */ -int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); } -int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); } - +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* lz4ds, BYTE* base) -{ - MEM_INIT(lz4ds, 0, sizeof(LZ4_stream_t)); - lz4ds->internal_donotuse.bufferStart = base; -} - int LZ4_resetStreamState(void* state, char* inputBuffer) { - if ((((uptrval)state) & 3) != 0) return 1; /* Error : pointer is not aligned on 4-bytes boundary */ - LZ4_init((LZ4_stream_t*)state, (BYTE*)inputBuffer); + (void)inputBuffer; + LZ4_resetStream((LZ4_stream_t*)state); return 0; } void* LZ4_create (char* inputBuffer) { - LZ4_stream_t* lz4ds = (LZ4_stream_t*)ALLOCATOR(8, sizeof(LZ4_stream_t)); - LZ4_init (lz4ds, (BYTE*)inputBuffer); - return lz4ds; -} - -char* LZ4_slideInputBuffer (void* LZ4_Data) -{ - LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)LZ4_Data)->internal_donotuse; - int dictSize = LZ4_saveDict((LZ4_stream_t*)LZ4_Data, (char*)ctx->bufferStart, 64 KB); - return (char*)(ctx->bufferStart + dictSize); + (void)inputBuffer; + return LZ4_createStream(); } -/* 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) +char* LZ4_slideInputBuffer (void* state) { - return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB); + /* avoid const char * -> char * conversion warning */ + return (char *)(uptrval)((LZ4_stream_t*)state)->internal_donotuse.dictionary; } #endif /* LZ4_COMMONDEFS_ONLY */ @@ -1,7 +1,7 @@ /* * LZ4 - Fast LZ compression algorithm * Header File - * Copyright (C) 2011-2016, Yann Collet. + * Copyright (C) 2011-present, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -32,13 +32,13 @@ - LZ4 homepage : http://www.lz4.org - LZ4 source repository : https://github.com/lz4/lz4 */ -#ifndef LZ4_H_2983827168210 -#define LZ4_H_2983827168210 - #if defined (__cplusplus) extern "C" { #endif +#ifndef LZ4_H_2983827168210 +#define LZ4_H_2983827168210 + /* --- Dependency --- */ #include <stddef.h> /* size_t */ @@ -46,7 +46,7 @@ extern "C" { /** Introduction - LZ4 is lossless compression algorithm, providing compression speed at 400 MB/s per core, + LZ4 is lossless compression algorithm, providing compression speed at 500 MB/s per core, scalable with multi-cores CPU. It features an extremely fast decoder, with speed in multiple GB/s per core, typically reaching RAM speed limits on multi-core systems. @@ -62,8 +62,8 @@ extern "C" { An additional format, called LZ4 frame specification (doc/lz4_Frame_format.md), take care of encoding standard metadata alongside LZ4-compressed blocks. - If your application requires interoperability, it's recommended to use it. - A library is provided to take care of it, see lz4frame.h. + Frame format is required for interoperability. + It is delivered through a companion API, declared in lz4frame.h. */ /*^*************************************************************** @@ -72,20 +72,28 @@ extern "C" { /* * LZ4_DLL_EXPORT : * Enable exporting of functions when building a Windows DLL +* LZ4LIB_VISIBILITY : +* Control library symbols visibility. */ +#ifndef LZ4LIB_VISIBILITY +# if defined(__GNUC__) && (__GNUC__ >= 4) +# define LZ4LIB_VISIBILITY __attribute__ ((visibility ("default"))) +# else +# define LZ4LIB_VISIBILITY +# endif +#endif #if defined(LZ4_DLL_EXPORT) && (LZ4_DLL_EXPORT==1) -# define LZ4LIB_API __declspec(dllexport) +# define LZ4LIB_API __declspec(dllexport) LZ4LIB_VISIBILITY #elif defined(LZ4_DLL_IMPORT) && (LZ4_DLL_IMPORT==1) -# define LZ4LIB_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ +# define LZ4LIB_API __declspec(dllimport) LZ4LIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ #else -# define LZ4LIB_API +# define LZ4LIB_API LZ4LIB_VISIBILITY #endif - -/*========== Version =========== */ +/*------ 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 5 /* for tweaks, bug-fixes, or development */ +#define LZ4_VERSION_MINOR 8 /* for new (non-breaking) interface capabilities */ +#define LZ4_VERSION_RELEASE 3 /* for tweaks, bug-fixes, or development */ #define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE) @@ -94,8 +102,8 @@ extern "C" { #define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str) #define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION) -LZ4LIB_API int LZ4_versionNumber (void); -LZ4LIB_API const char* LZ4_versionString (void); +LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; useful to check dll version */ +LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; unseful to check dll version */ /*-************************************ @@ -105,40 +113,40 @@ LZ4LIB_API const char* LZ4_versionString (void); * 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 + * Reduced memory usage may improve speed, thanks to cache effect * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */ -#define LZ4_MEMORY_USAGE 14 - +#ifndef LZ4_MEMORY_USAGE +# define LZ4_MEMORY_USAGE 14 +#endif /*-************************************ * Simple Functions **************************************/ /*! 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). + Compresses 'srcSize' bytes from buffer 'src' + into already allocated 'dst' buffer of size 'dstCapacity'. + Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize). It also runs faster, so it's a recommended setting. - If the function cannot compress 'source' into a more limited 'dest' budget, + If the function cannot compress 'src' into a more limited 'dst' 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 */ -LZ4LIB_API int LZ4_compress_default(const char* source, char* dest, int sourceSize, int maxDestSize); + Note : as a consequence, 'dst' content is not valid. + Note 2 : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer). + srcSize : max supported value is LZ4_MAX_INPUT_SIZE. + dstCapacity : size of buffer 'dst' (which must be already allocated) + return : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity) + or 0 if compression fails */ +LZ4LIB_API int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity); /*! LZ4_decompress_safe() : - 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). + compressedSize : is the exact complete size of the compressed block. + dstCapacity : is the size of destination buffer, which must be already allocated. + return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity) + If destination buffer is not large enough, decoding will stop and output an error code (negative value). 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, including malicious data packets. - It never writes outside output buffer, nor reads outside input buffer. + This function is protected against malicious data packets. */ -LZ4LIB_API int LZ4_decompress_safe (const char* source, char* dest, int compressedSize, int maxDecompressedSize); +LZ4LIB_API int LZ4_decompress_safe (const char* src, char* dst, int compressedSize, int dstCapacity); /*-************************************ @@ -152,22 +160,22 @@ LZ4_compressBound() : 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) + Note that LZ4_compress_default() compresses faster when dstCapacity 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) + or 0, if input size is incorrect (too large or negative) */ LZ4LIB_API int LZ4_compressBound(int inputSize); /*! LZ4_compress_fast() : - Same as LZ4_compress_default(), but allows to select an "acceleration" factor. + Same as LZ4_compress_default(), but allows selection of "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. + Values <= 0 will be replaced by ACCELERATION_DEFAULT (currently == 1, see lz4.c). */ -LZ4LIB_API int LZ4_compress_fast (const char* source, char* dest, int sourceSize, int maxDestSize, int acceleration); +LZ4LIB_API int LZ4_compress_fast (const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); /*! @@ -175,58 +183,79 @@ LZ4_compress_fast_extState() : Same compression function, just using an externally allocated memory space to store compression state. Use LZ4_sizeofState() to know how much memory must be allocated, and allocate it on 8-bytes boundaries (using malloc() typically). - Then, provide it as 'void* state' to compression function. + Then, provide this buffer as 'void* state' to compression function. */ LZ4LIB_API int LZ4_sizeofState(void); -LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* 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 -*/ -LZ4LIB_API int LZ4_compress_destSize (const char* source, char* dest, int* sourceSizePtr, int targetDestSize); - - -/*! -LZ4_decompress_fast() : - 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 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). -*/ -LZ4LIB_API int LZ4_decompress_fast (const char* source, char* dest, int originalSize); - -/*! -LZ4_decompress_safe_partial() : - 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 <= 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 +LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); + + +/*! LZ4_compress_destSize() : + * Reverse the logic : compresses as much data as possible from 'src' buffer + * into already allocated buffer 'dst', of size >= 'targetDestSize'. + * This function either compresses the entire 'src' content into 'dst' if it's large enough, + * or fill 'dst' buffer completely with as much data as possible from 'src'. + * note: acceleration parameter is fixed to "default". + * + * *srcSizePtr : will be modified to indicate how many bytes where read from 'src' to fill 'dst'. + * New value is necessarily <= input value. + * @return : Nb bytes written into 'dst' (necessarily <= targetDestSize) + * or 0 if compression fails. */ -LZ4LIB_API int LZ4_decompress_safe_partial (const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize); +LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePtr, int targetDstSize); + + +/*! LZ4_decompress_fast() : **unsafe!** + * This function used to be a bit faster than LZ4_decompress_safe(), + * though situation has changed in recent versions, + * and now `LZ4_decompress_safe()` can be as fast and sometimes faster than `LZ4_decompress_fast()`. + * Moreover, LZ4_decompress_fast() is not protected vs malformed input, as it doesn't perform full validation of compressed data. + * As a consequence, this function is no longer recommended, and may be deprecated in future versions. + * It's only remaining specificity is that it can decompress data without knowing its compressed size. + * + * originalSize : is the uncompressed size to regenerate. + * `dst` must be already allocated, its size must be >= 'originalSize' bytes. + * @return : number of bytes read from source buffer (== compressed size). + * If the source stream is detected malformed, the function stops decoding and returns a negative result. + * note : This function requires uncompressed originalSize to be known in advance. + * The function never writes past the output buffer. + * However, since it doesn't know its 'src' size, it may read past the intended input. + * Also, because match offsets are not validated during decoding, + * reads from 'src' may underflow. + * Use this function in trusted environment **only**. + */ +LZ4LIB_API int LZ4_decompress_fast (const char* src, char* dst, int originalSize); + +/*! LZ4_decompress_safe_partial() : + * Decompress an LZ4 compressed block, of size 'srcSize' at position 'src', + * into destination buffer 'dst' of size 'dstCapacity'. + * Up to 'targetOutputSize' bytes will be decoded. + * The function stops decoding on reaching this objective, + * which can boost performance when only the beginning of a block is required. + * + * @return : the number of bytes decoded in `dst` (necessarily <= dstCapacity) + * If source stream is detected malformed, function returns a negative result. + * + * Note : @return can be < targetOutputSize, if compressed block contains less data. + * + * Note 2 : this function features 2 parameters, targetOutputSize and dstCapacity, + * and expects targetOutputSize <= dstCapacity. + * It effectively stops decoding on reaching targetOutputSize, + * so dstCapacity is kind of redundant. + * This is because in a previous version of this function, + * decoding operation would not "break" a sequence in the middle. + * As a consequence, there was no guarantee that decoding would stop at exactly targetOutputSize, + * it could write more bytes, though only up to dstCapacity. + * Some "margin" used to be required for this operation to work properly. + * This is no longer necessary. + * The function nonetheless keeps its signature, in an effort to not break API. + */ +LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcSize, int targetOutputSize, int dstCapacity); /*-********************************************* * Streaming Compression Functions ***********************************************/ -typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */ +typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */ /*! LZ4_createStream() and LZ4_freeStream() : * LZ4_createStream() will allocate and initialize an `LZ4_stream_t` structure. @@ -237,87 +266,219 @@ LZ4LIB_API int LZ4_freeStream (LZ4_stream_t* streamPtr); /*! LZ4_resetStream() : * An LZ4_stream_t structure can be allocated once and re-used multiple times. - * Use this function to init an allocated `LZ4_stream_t` structure and start a new compression. + * Use this function to start compressing a new stream. */ LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr); /*! LZ4_loadDict() : - * Use this function to load a static dictionary into LZ4_stream. + * Use this function to load a static dictionary into LZ4_stream_t. * 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) + * Loading a size of 0 is allowed, and is the same as reset. + * @return : dictionary size, in bytes (necessarily <= 64 KB) */ LZ4LIB_API 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 ! + * Compress 'src' content using data from previously compressed blocks, for better compression ratio. * '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. + * If dstCapacity >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster. + * + * @return : size of compressed block + * or 0 if there is an error (typically, cannot fit into 'dst'). + * + * Note 1 : Each invocation to LZ4_compress_fast_continue() generates a new block. + * Each block has precise boundaries. + * It's not possible to append blocks together and expect a single invocation of LZ4_decompress_*() to decompress them together. + * Each block must be decompressed separately, calling LZ4_decompress_*() with associated metadata. + * + * Note 2 : The previous 64KB of source data is __assumed__ to remain present, unmodified, at same address in memory! + * + * Note 3 : When input is structured as a double-buffer, each buffer can have any size, including < 64 KB. + * Make sure that buffers are separated, by at least one byte. + * This construction ensures that each block only depends on previous block. + * + * Note 4 : If input buffer is a ring-buffer, it can have any size, including < 64 KB. + * + * Note 5 : After an error, the stream status is invalid, it can only be reset or freed. */ -LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int maxDstSize, int acceleration); +LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); /*! LZ4_saveDict() : - * If previously compressed data block is not guaranteed to remain available at its memory location, + * If last 64KB data cannot be guaranteed to remain available at its current 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. + * This is schematically equivalent to a memcpy() followed by LZ4_loadDict(), + * but is much faster, because LZ4_saveDict() doesn't need to rebuild tables. + * @return : saved dictionary size in bytes (necessarily <= maxDictSize), or 0 if error. */ -LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int dictSize); +LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int maxDictSize); /*-********************************************** * Streaming Decompression Functions * Bufferless synchronous API ************************************************/ -typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* incomplete type (defined later) */ +typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* tracking context */ -/* creation / destruction of streaming decompression tracking structure */ +/*! LZ4_createStreamDecode() and LZ4_freeStreamDecode() : + * creation / destruction of streaming decompression tracking context. + * A tracking context can be re-used multiple times. + */ LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void); LZ4LIB_API 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 + * An LZ4_streamDecode_t context can be allocated once and re-used multiple times. + * Use this function to start decompression of a new stream of blocks. + * A dictionary can optionally be set. Use NULL or size 0 for a reset order. + * Dictionary is presumed stable : it must remain accessible and unmodified during next decompression. + * @return : 1 if OK, 0 if error */ LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize); -/*! -LZ4_decompress_*_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() +/*! LZ4_decoderRingBufferSize() : v1.8.2 + * Note : in a ring buffer scenario (optional), + * blocks are presumed decompressed next to each other + * up to the moment there is not enough remaining space for next block (remainingSize < maxBlockSize), + * at which stage it resumes from beginning of ring buffer. + * When setting such a ring buffer for streaming decompression, + * provides the minimum size of this ring buffer + * to be compatible with any source respecting maxBlockSize condition. + * @return : minimum ring buffer size, + * or 0 if there is an error (invalid maxBlockSize). + */ +LZ4LIB_API int LZ4_decoderRingBufferSize(int maxBlockSize); +#define LZ4_DECODER_RING_BUFFER_SIZE(mbs) (65536 + 14 + (mbs)) /* for static allocation; mbs presumed valid */ + +/*! LZ4_decompress_*_continue() : + * These decoding functions allow decompression of consecutive blocks in "streaming" mode. + * A block is an unsplittable entity, it must be presented entirely to a decompression function. + * Decompression functions only accepts one block at a time. + * The last 64KB of previously decoded data *must* remain available and unmodified at the memory position where they were decoded. + * If less than 64KB of data has been decoded, all the data must be present. + * + * Special : if decompression side sets a ring buffer, it must respect one of the following conditions : + * - Decompression buffer size is _at least_ LZ4_decoderRingBufferSize(maxBlockSize). + * maxBlockSize is the maximum size of any single block. It can have any value > 16 bytes. + * In which case, encoding and decoding buffers do not need to be synchronized. + * Actually, data can be produced by any source compliant with LZ4 format specification, and respecting maxBlockSize. + * - Synchronized mode : + * Decompression buffer size is _exactly_ the same as compression buffer size, + * and follows exactly same update rule (block boundaries at same positions), + * and decoding function is provided with exact decompressed size of each block (exception for last block of the stream), + * _then_ decoding & encoding ring buffer can have any size, including small ones ( < 64 KB). + * - Decompression buffer is larger than encoding buffer, by a minimum of maxBlockSize more bytes. + * 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). + * + * Whenever these conditions are not possible, + * save the last 64KB of decoded data into a safe buffer where it can't be modified during decompression, + * then indicate where this data is saved using LZ4_setStreamDecode(), before decompressing next block. */ -LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxDecompressedSize); -LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize); +LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int srcSize, int dstCapacity); +LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int originalSize); /*! LZ4_decompress_*_usingDict() : * These decoding functions work the same as * a combination of LZ4_setStreamDecode() followed by LZ4_decompress_*_continue() * They are stand-alone, and don't need an LZ4_streamDecode_t structure. + * Dictionary is presumed stable : it must remain accessible and unmodified during next decompression. */ -LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* source, char* dest, int compressedSize, int maxDecompressedSize, const char* dictStart, int dictSize); -LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* source, char* dest, int originalSize, const char* dictStart, int dictSize); +LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int srcSize, int dstCapcity, const char* dictStart, int dictSize); +LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int originalSize, const char* dictStart, int dictSize); /*^********************************************** * !!!!!! STATIC LINKING ONLY !!!!!! ***********************************************/ + +/*-************************************ + * Unstable declarations + ************************************** + * Declarations in this section should be considered unstable. + * Use at your own peril, etc., etc. + * They may be removed in the future. + * Their signatures may change. + **************************************/ + +#ifdef LZ4_STATIC_LINKING_ONLY + +/*! LZ4_resetStream_fast() : + * Use this, like LZ4_resetStream(), to prepare a context for a new chain of + * calls to a streaming API (e.g., LZ4_compress_fast_continue()). + * + * Note: + * Using this in advance of a non- streaming-compression function is redundant, + * and potentially bad for performance, since they all perform their own custom + * reset internally. + * + * Differences from LZ4_resetStream(): + * When an LZ4_stream_t is known to be in a internally coherent state, + * it can often be prepared for a new compression with almost no work, only + * sometimes falling back to the full, expensive reset that is always required + * when the stream is in an indeterminate state (i.e., the reset performed by + * LZ4_resetStream()). + * + * LZ4_streams are guaranteed to be in a valid state when: + * - returned from LZ4_createStream() + * - reset by LZ4_resetStream() + * - memset(stream, 0, sizeof(LZ4_stream_t)), though this is discouraged + * - the stream was in a valid state and was reset by LZ4_resetStream_fast() + * - the stream was in a valid state and was then used in any compression call + * that returned success + * - the stream was in an indeterminate state and was used in a compression + * call that fully reset the state (e.g., LZ4_compress_fast_extState()) and + * that returned success + * + * When a stream isn't known to be in a valid state, it is not safe to pass to + * any fastReset or streaming function. It must first be cleansed by the full + * LZ4_resetStream(). + */ +LZ4LIB_API void LZ4_resetStream_fast (LZ4_stream_t* streamPtr); + +/*! LZ4_compress_fast_extState_fastReset() : + * A variant of LZ4_compress_fast_extState(). + * + * Using this variant avoids an expensive initialization step. It is only safe + * to call if the state buffer is known to be correctly initialized already + * (see above comment on LZ4_resetStream_fast() for a definition of "correctly + * initialized"). From a high level, the difference is that this function + * initializes the provided state with a call to something like + * LZ4_resetStream_fast() while LZ4_compress_fast_extState() starts with a + * call to LZ4_resetStream(). + */ +LZ4LIB_API int LZ4_compress_fast_extState_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); + +/*! LZ4_attach_dictionary() : + * This is an experimental API that allows for the efficient use of a + * static dictionary many times. + * + * Rather than re-loading the dictionary buffer into a working context before + * each compression, or copying a pre-loaded dictionary's LZ4_stream_t into a + * working LZ4_stream_t, this function introduces a no-copy setup mechanism, + * in which the working stream references the dictionary stream in-place. + * + * Several assumptions are made about the state of the dictionary stream. + * Currently, only streams which have been prepared by LZ4_loadDict() should + * be expected to work. + * + * Alternatively, the provided dictionary stream pointer may be NULL, in which + * case any existing dictionary stream is unset. + * + * If a dictionary is provided, it replaces any pre-existing stream history. + * The dictionary contents are the only history that can be referenced and + * logically immediately precede the data compressed in the first subsequent + * compression call. + * + * The dictionary will only remain attached to the working stream through the + * first compression call, at the end of which it is cleared. The dictionary + * stream (and source buffer) must remain in-place / accessible / unchanged + * through the completion of the first compression call on the stream. + */ +LZ4LIB_API void LZ4_attach_dictionary(LZ4_stream_t *working_stream, const LZ4_stream_t *dictionary_stream); + +#endif + /*-************************************ * Private definitions ************************************** @@ -332,14 +493,16 @@ LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* source, char* dest, in #if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) #include <stdint.h> -typedef struct { +typedef struct LZ4_stream_t_internal LZ4_stream_t_internal; +struct LZ4_stream_t_internal { uint32_t hashTable[LZ4_HASH_SIZE_U32]; uint32_t currentOffset; - uint32_t initCheck; + uint16_t initCheck; + uint16_t tableType; const uint8_t* dictionary; - uint8_t* bufferStart; /* obsolete, used for slideInputBuffer */ + const LZ4_stream_t_internal* dictCtx; uint32_t dictSize; -} LZ4_stream_t_internal; +}; typedef struct { const uint8_t* externalDict; @@ -350,14 +513,16 @@ typedef struct { #else -typedef struct { +typedef struct LZ4_stream_t_internal LZ4_stream_t_internal; +struct LZ4_stream_t_internal { unsigned int hashTable[LZ4_HASH_SIZE_U32]; unsigned int currentOffset; - unsigned int initCheck; + unsigned short initCheck; + unsigned short tableType; const unsigned char* dictionary; - unsigned char* bufferStart; /* obsolete, used for slideInputBuffer */ + const LZ4_stream_t_internal* dictCtx; unsigned int dictSize; -} LZ4_stream_t_internal; +}; typedef struct { const unsigned char* externalDict; @@ -374,7 +539,7 @@ typedef struct { * init this structure before first use. * note : only use in association with static linking ! * this definition is not API/ABI safe, - * and may change in a future version ! + * it may change in a future version ! */ #define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4) #define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long)) @@ -400,11 +565,12 @@ union LZ4_streamDecode_u { } ; /* previously typedef'd to LZ4_streamDecode_t */ -/*=************************************ +/*-************************************ * Obsolete Functions **************************************/ -/* Deprecation warnings */ -/* Should these warnings be a problem, + +/*! Deprecation warnings + Should deprecation warnings be a problem, it is generally possible to disable them, typically with -Wno-deprecated-declarations for gcc or _CRT_SECURE_NO_WARNINGS in Visual. @@ -428,36 +594,38 @@ union LZ4_streamDecode_u { #endif /* LZ4_DISABLE_DEPRECATE_WARNINGS */ /* Obsolete compression functions */ -LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress (const char* source, char* dest, int sourceSize); -LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize); -LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize); -LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); -LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize); -LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress (const char* source, char* dest, int sourceSize); +LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize); /* Obsolete decompression functions */ -/* These function names are completely deprecated and must no longer be used. - They are only provided in lz4.c 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); */ - -/* 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); +LZ4_DEPRECATED("use LZ4_decompress_fast() instead") LZ4LIB_API int LZ4_uncompress (const char* source, char* dest, int outputSize); +LZ4_DEPRECATED("use LZ4_decompress_safe() instead") LZ4LIB_API int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize); + +/* Obsolete streaming functions; degraded functionality; do not use! + * + * In order to perform streaming compression, these functions depended on data + * that is no longer tracked in the state. They have been preserved as well as + * possible: using them will still produce a correct output. However, they don't + * actually retain any history between compression calls. The compression ratio + * achieved will therefore be no better than compressing each chunk + * independently. + */ +LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API void* LZ4_create (char* inputBuffer); +LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API int LZ4_sizeofStreamState(void); +LZ4_DEPRECATED("Use LZ4_resetStream() instead") LZ4LIB_API int LZ4_resetStreamState(void* state, char* inputBuffer); +LZ4_DEPRECATED("Use LZ4_saveDict() instead") LZ4LIB_API 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); +LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") LZ4LIB_API int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize); +LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") LZ4LIB_API int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize); + +#endif /* LZ4_H_2983827168210 */ #if defined (__cplusplus) } #endif - -#endif /* LZ4_H_2983827168210 */ diff --git a/lib/lz4frame.c b/lib/lz4frame.c index a0a625b0..08bf0fae 100644 --- a/lib/lz4frame.c +++ b/lib/lz4frame.c @@ -47,10 +47,24 @@ You can contact the author at : /*-************************************ +* Tuning parameters +**************************************/ +/* + * LZ4F_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 malloc()). + */ +#ifndef LZ4F_HEAPMODE +# define LZ4F_HEAPMODE 0 +#endif + + +/*-************************************ * Memory routines **************************************/ #include <stdlib.h> /* malloc, calloc, free */ -#define ALLOCATOR(s) calloc(1,s) +#define ALLOC(s) malloc(s) +#define ALLOC_AND_ZERO(s) calloc(1,s) #define FREEMEM free #include <string.h> /* memset, memcpy, memmove */ #define MEM_INIT memset @@ -59,17 +73,41 @@ You can contact the author at : /*-************************************ * Includes **************************************/ -#include "lz4frame_static.h" +#define LZ4F_STATIC_LINKING_ONLY +#include "lz4frame.h" +#define LZ4_STATIC_LINKING_ONLY #include "lz4.h" +#define LZ4_HC_STATIC_LINKING_ONLY #include "lz4hc.h" #define XXH_STATIC_LINKING_ONLY #include "xxhash.h" /*-************************************ -* Common Utils +* Debug **************************************/ -#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(int)(!!(c)) }; } /* use only *after* variable declarations */ +#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=1) +# include <assert.h> +#else +# ifndef assert +# define assert(condition) ((void)0) +# endif +#endif + +#define LZ4F_STATIC_ASSERT(c) { enum { LZ4F_static_assert = 1/(int)(!!(c)) }; } /* use only *after* variable declarations */ + +#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2) && !defined(DEBUGLOG) +# include <stdio.h> +static int g_debuglog_enable = 1; +# define DEBUGLOG(l, ...) { \ + if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) { \ + fprintf(stderr, __FILE__ ": "); \ + fprintf(stderr, __VA_ARGS__); \ + fprintf(stderr, " \n"); \ + } } +#else +# define DEBUGLOG(l, ...) {} /* disabled */ +#endif /*-************************************ @@ -158,7 +196,7 @@ static void LZ4F_writeLE64 (void* dst, U64 value64) #define LZ4F_BLOCKSIZEID_DEFAULT LZ4F_max64KB static const size_t minFHSize = 7; -static const size_t maxFHSize = LZ4F_HEADER_SIZE_MAX; /* 15 */ +static const size_t maxFHSize = LZ4F_HEADER_SIZE_MAX; /* 19 */ static const size_t BHSize = 4; @@ -170,6 +208,7 @@ typedef struct LZ4F_cctx_s LZ4F_preferences_t prefs; U32 version; U32 cStage; + const LZ4F_CDict* cdict; size_t maxBlockSize; size_t maxBufferSize; BYTE* tmpBuff; @@ -178,7 +217,8 @@ typedef struct LZ4F_cctx_s U64 totalInSize; XXH32_state_t xxh; void* lz4CtxPtr; - U32 lz4CtxLevel; /* 0: unallocated; 1: LZ4_stream_t; 3: LZ4_streamHC_t */ + U16 lz4CtxAlloc; /* sized for: 0 = none, 1 = lz4 ctx, 2 = lz4hc ctx */ + U16 lz4CtxState; /* in use as: 0 = none, 1 = lz4 ctx, 2 = lz4hc ctx */ } LZ4F_cctx_t; @@ -209,12 +249,15 @@ LZ4F_errorCodes LZ4F_getErrorCode(size_t functionResult) static LZ4F_errorCode_t err0r(LZ4F_errorCodes code) { - LZ4_STATIC_ASSERT(sizeof(ptrdiff_t) >= sizeof(size_t)); /* A compilation error here means sizeof(ptrdiff_t) is not large enough */ + /* A compilation error here means sizeof(ptrdiff_t) is not large enough */ + LZ4F_STATIC_ASSERT(sizeof(ptrdiff_t) >= sizeof(size_t)); return (LZ4F_errorCode_t)-(ptrdiff_t)code; } unsigned LZ4F_getVersion(void) { return LZ4F_VERSION; } +int LZ4F_compressionLevel_max(void) { return LZ4HC_CLEVEL_MAX; } + /*-************************************ * Private functions @@ -241,7 +284,8 @@ static BYTE LZ4F_headerChecksum (const void* header, size_t length) /*-************************************ * Simple-pass compression functions **************************************/ -static LZ4F_blockSizeID_t LZ4F_optimalBSID(const LZ4F_blockSizeID_t requestedBSID, const size_t srcSize) +static LZ4F_blockSizeID_t LZ4F_optimalBSID(const LZ4F_blockSizeID_t requestedBSID, + const size_t srcSize) { LZ4F_blockSizeID_t proposedBSID = LZ4F_max64KB; size_t maxBlockSize = 64 KB; @@ -254,134 +298,229 @@ static LZ4F_blockSizeID_t LZ4F_optimalBSID(const LZ4F_blockSizeID_t requestedBSI return requestedBSID; } -/* LZ4F_compressBound() : - * Provides dstCapacity given a srcSize to guarantee operation success in worst case situations. - * prefsPtr is optional : you can provide NULL as argument, preferences will be set to cover worst case scenario. - * Result is always the same for a srcSize and prefsPtr, so it can be trusted to size reusable buffers. - * When srcSize==0, LZ4F_compressBound() provides an upper bound for LZ4F_flush() and LZ4F_compressEnd() operations. +/*! LZ4F_compressBound_internal() : + * Provides dstCapacity given a srcSize to guarantee operation success in worst case situations. + * prefsPtr is optional : if NULL is provided, preferences will be set to cover worst case scenario. + * @return is always the same for a srcSize and prefsPtr, so it can be relied upon to size reusable buffers. + * When srcSize==0, LZ4F_compressBound() provides an upper bound for LZ4F_flush() and LZ4F_compressEnd() operations. */ -static size_t LZ4F_compressBound_internal(size_t srcSize, const LZ4F_preferences_t* preferencesPtr, size_t alreadyBuffered) +static size_t LZ4F_compressBound_internal(size_t srcSize, + const LZ4F_preferences_t* preferencesPtr, + size_t alreadyBuffered) { LZ4F_preferences_t prefsNull; - memset(&prefsNull, 0, sizeof(prefsNull)); + MEM_INIT(&prefsNull, 0, sizeof(prefsNull)); prefsNull.frameInfo.contentChecksumFlag = LZ4F_contentChecksumEnabled; /* worst case */ { const LZ4F_preferences_t* const prefsPtr = (preferencesPtr==NULL) ? &prefsNull : preferencesPtr; U32 const flush = prefsPtr->autoFlush | (srcSize==0); - LZ4F_blockSizeID_t const bid = prefsPtr->frameInfo.blockSizeID; - size_t const blockSize = LZ4F_getBlockSize(bid); + LZ4F_blockSizeID_t const blockID = prefsPtr->frameInfo.blockSizeID; + size_t const blockSize = LZ4F_getBlockSize(blockID); size_t const maxBuffered = blockSize - 1; size_t const bufferedSize = MIN(alreadyBuffered, maxBuffered); size_t const maxSrcSize = srcSize + bufferedSize; unsigned const nbFullBlocks = (unsigned)(maxSrcSize / blockSize); - size_t const partialBlockSize = (srcSize - (srcSize==0)) & (blockSize-1); /* 0 => -1 == MAX => blockSize-1 */ + size_t const partialBlockSize = maxSrcSize & (blockSize-1); size_t const lastBlockSize = flush ? partialBlockSize : 0; unsigned const nbBlocks = nbFullBlocks + (lastBlockSize>0); - size_t const blockHeaderSize = 4; /* default, without block CRC option (which cannot be generated with current API) */ + size_t const blockHeaderSize = 4; + size_t const blockCRCSize = 4 * prefsPtr->frameInfo.blockChecksumFlag; size_t const frameEnd = 4 + (prefsPtr->frameInfo.contentChecksumFlag*4); - return (blockHeaderSize * nbBlocks) + (blockSize * nbFullBlocks) + lastBlockSize + frameEnd;; + return ((blockHeaderSize + blockCRCSize) * nbBlocks) + + (blockSize * nbFullBlocks) + lastBlockSize + frameEnd; } } size_t LZ4F_compressFrameBound(size_t srcSize, const LZ4F_preferences_t* preferencesPtr) { LZ4F_preferences_t prefs; - size_t const headerSize = maxFHSize; /* max header size, including magic number and frame content size */ + size_t const headerSize = maxFHSize; /* max header size, including optional fields */ if (preferencesPtr!=NULL) prefs = *preferencesPtr; - else memset(&prefs, 0, sizeof(prefs)); + else MEM_INIT(&prefs, 0, sizeof(prefs)); prefs.autoFlush = 1; return headerSize + LZ4F_compressBound_internal(srcSize, &prefs, 0);; } -/*! LZ4F_compressFrame() : -* Compress an entire srcBuffer into a valid LZ4 frame, as defined by specification v1.5.0, in a single step. -* The most important rule is that dstBuffer MUST be large enough (dstMaxSize) to ensure compression completion even in worst case. -* You can get the minimum value of dstMaxSize by using LZ4F_compressFrameBound() -* If this condition is not respected, LZ4F_compressFrame() will fail (result is an errorCode) -* The LZ4F_preferences_t structure is optional : you can provide NULL as argument. All preferences will then be set to default. -* The result of the function is the number of bytes written into dstBuffer. -* The function outputs an error code if it fails (can be tested using LZ4F_isError()) -*/ -size_t LZ4F_compressFrame(void* dstBuffer, size_t dstCapacity, const void* srcBuffer, size_t srcSize, const LZ4F_preferences_t* preferencesPtr) +/*! LZ4F_compressFrame_usingCDict() : + * Compress srcBuffer using a dictionary, in a single step. + * cdict can be NULL, in which case, no dictionary is used. + * dstBuffer MUST be >= LZ4F_compressFrameBound(srcSize, preferencesPtr). + * The LZ4F_preferences_t structure is optional : you may provide NULL as argument, + * however, it's the only way to provide a dictID, so it's not recommended. + * @return : number of bytes written into dstBuffer, + * or an error code if it fails (can be tested using LZ4F_isError()) + */ +size_t LZ4F_compressFrame_usingCDict(LZ4F_cctx* cctx, + void* dstBuffer, size_t dstCapacity, + const void* srcBuffer, size_t srcSize, + const LZ4F_CDict* cdict, + const LZ4F_preferences_t* preferencesPtr) { - LZ4F_cctx_t cctxI; - LZ4_stream_t lz4ctx; LZ4F_preferences_t prefs; LZ4F_compressOptions_t options; BYTE* const dstStart = (BYTE*) dstBuffer; BYTE* dstPtr = dstStart; BYTE* const dstEnd = dstStart + dstCapacity; - memset(&cctxI, 0, sizeof(cctxI)); /* works because no allocation */ - memset(&options, 0, sizeof(options)); - - cctxI.version = LZ4F_VERSION; - cctxI.maxBufferSize = 5 MB; /* mess with real buffer size to prevent allocation; works because autoflush==1 & stableSrc==1 */ - if (preferencesPtr!=NULL) prefs = *preferencesPtr; else - memset(&prefs, 0, sizeof(prefs)); + MEM_INIT(&prefs, 0, sizeof(prefs)); if (prefs.frameInfo.contentSize != 0) prefs.frameInfo.contentSize = (U64)srcSize; /* auto-correct content size if selected (!=0) */ - if (prefs.compressionLevel < LZ4HC_CLEVEL_MIN) { - cctxI.lz4CtxPtr = &lz4ctx; - cctxI.lz4CtxLevel = 1; - } - prefs.frameInfo.blockSizeID = LZ4F_optimalBSID(prefs.frameInfo.blockSizeID, srcSize); prefs.autoFlush = 1; if (srcSize <= LZ4F_getBlockSize(prefs.frameInfo.blockSizeID)) - prefs.frameInfo.blockMode = LZ4F_blockIndependent; /* no need for linked blocks */ + prefs.frameInfo.blockMode = LZ4F_blockIndependent; /* only one block => no need for inter-block link */ + MEM_INIT(&options, 0, sizeof(options)); options.stableSrc = 1; - if (dstCapacity < LZ4F_compressFrameBound(srcSize, &prefs)) + if (dstCapacity < LZ4F_compressFrameBound(srcSize, &prefs)) /* condition to guarantee success */ return err0r(LZ4F_ERROR_dstMaxSize_tooSmall); - { size_t const headerSize = LZ4F_compressBegin(&cctxI, dstBuffer, dstCapacity, &prefs); /* write header */ + { size_t const headerSize = LZ4F_compressBegin_usingCDict(cctx, dstBuffer, dstCapacity, cdict, &prefs); /* write header */ if (LZ4F_isError(headerSize)) return headerSize; dstPtr += headerSize; /* header size */ } - { size_t const cSize = LZ4F_compressUpdate(&cctxI, dstPtr, dstEnd-dstPtr, srcBuffer, srcSize, &options); + { size_t const cSize = LZ4F_compressUpdate(cctx, dstPtr, dstEnd-dstPtr, srcBuffer, srcSize, &options); if (LZ4F_isError(cSize)) return cSize; dstPtr += cSize; } - { size_t const tailSize = LZ4F_compressEnd(&cctxI, dstPtr, dstEnd-dstPtr, &options); /* flush last block, and generate suffix */ + { size_t const tailSize = LZ4F_compressEnd(cctx, dstPtr, dstEnd-dstPtr, &options); /* flush last block, and generate suffix */ if (LZ4F_isError(tailSize)) return tailSize; dstPtr += tailSize; } - if (prefs.compressionLevel >= LZ4HC_CLEVEL_MIN) /* no allocation done with lz4 fast */ - FREEMEM(cctxI.lz4CtxPtr); - return (dstPtr - dstStart); } +/*! LZ4F_compressFrame() : + * Compress an entire srcBuffer into a valid LZ4 frame, in a single step. + * dstBuffer MUST be >= LZ4F_compressFrameBound(srcSize, preferencesPtr). + * The LZ4F_preferences_t structure is optional : you can provide NULL as argument. All preferences will be set to default. + * @return : number of bytes written into dstBuffer. + * or an error code if it fails (can be tested using LZ4F_isError()) + */ +size_t LZ4F_compressFrame(void* dstBuffer, size_t dstCapacity, + const void* srcBuffer, size_t srcSize, + const LZ4F_preferences_t* preferencesPtr) +{ + size_t result; +#if (LZ4F_HEAPMODE) + LZ4F_cctx_t *cctxPtr; + result = LZ4F_createCompressionContext(&cctxPtr, LZ4F_VERSION); + if (LZ4F_isError(result)) return result; +#else + LZ4F_cctx_t cctx; + LZ4_stream_t lz4ctx; + LZ4F_cctx_t *cctxPtr = &cctx; + + DEBUGLOG(4, "LZ4F_compressFrame"); + MEM_INIT(&cctx, 0, sizeof(cctx)); + cctx.version = LZ4F_VERSION; + cctx.maxBufferSize = 5 MB; /* mess with real buffer size to prevent dynamic allocation; works only because autoflush==1 & stableSrc==1 */ + if (preferencesPtr == NULL || + preferencesPtr->compressionLevel < LZ4HC_CLEVEL_MIN) + { + LZ4_resetStream(&lz4ctx); + cctxPtr->lz4CtxPtr = &lz4ctx; + cctxPtr->lz4CtxAlloc = 1; + cctxPtr->lz4CtxState = 1; + } +#endif + + result = LZ4F_compressFrame_usingCDict(cctxPtr, dstBuffer, dstCapacity, + srcBuffer, srcSize, + NULL, preferencesPtr); + +#if (LZ4F_HEAPMODE) + LZ4F_freeCompressionContext(cctxPtr); +#else + if (preferencesPtr != NULL && + preferencesPtr->compressionLevel >= LZ4HC_CLEVEL_MIN) + { + FREEMEM(cctxPtr->lz4CtxPtr); + } +#endif + return result; +} + + +/*-*************************************************** +* Dictionary compression +*****************************************************/ + +struct LZ4F_CDict_s { + void* dictContent; + LZ4_stream_t* fastCtx; + LZ4_streamHC_t* HCCtx; +}; /* typedef'd to LZ4F_CDict within lz4frame_static.h */ + +/*! LZ4F_createCDict() : + * When compressing multiple messages / blocks with the same dictionary, it's recommended to load it just once. + * LZ4F_createCDict() will create a digested dictionary, ready to start future compression operations without startup delay. + * LZ4F_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only. + * `dictBuffer` can be released after LZ4F_CDict creation, since its content is copied within CDict + * @return : digested dictionary for compression, or NULL if failed */ +LZ4F_CDict* LZ4F_createCDict(const void* dictBuffer, size_t dictSize) +{ + const char* dictStart = (const char*)dictBuffer; + LZ4F_CDict* cdict = (LZ4F_CDict*) ALLOC(sizeof(*cdict)); + DEBUGLOG(4, "LZ4F_createCDict"); + if (!cdict) return NULL; + if (dictSize > 64 KB) { + dictStart += dictSize - 64 KB; + dictSize = 64 KB; + } + cdict->dictContent = ALLOC(dictSize); + cdict->fastCtx = LZ4_createStream(); + cdict->HCCtx = LZ4_createStreamHC(); + if (!cdict->dictContent || !cdict->fastCtx || !cdict->HCCtx) { + LZ4F_freeCDict(cdict); + return NULL; + } + memcpy(cdict->dictContent, dictStart, dictSize); + LZ4_loadDict (cdict->fastCtx, (const char*)cdict->dictContent, (int)dictSize); + LZ4_setCompressionLevel(cdict->HCCtx, LZ4HC_CLEVEL_DEFAULT); + LZ4_loadDictHC(cdict->HCCtx, (const char*)cdict->dictContent, (int)dictSize); + return cdict; +} + +void LZ4F_freeCDict(LZ4F_CDict* cdict) +{ + if (cdict==NULL) return; /* support free on NULL */ + FREEMEM(cdict->dictContent); + LZ4_freeStream(cdict->fastCtx); + LZ4_freeStreamHC(cdict->HCCtx); + FREEMEM(cdict); +} + + /*-********************************* * Advanced compression functions ***********************************/ /*! LZ4F_createCompressionContext() : - * The first thing to do is to create a compressionContext object, which will be used in all compression operations. - * This is achieved using LZ4F_createCompressionContext(), which takes as argument a version and an LZ4F_preferences_t structure. - * The version provided MUST be LZ4F_VERSION. It is intended to track potential version differences between different binaries. - * The function will provide a pointer to an allocated LZ4F_compressionContext_t object. - * If the result LZ4F_errorCode_t is not OK_NoError, there was an error during context creation. - * Object can release its memory using LZ4F_freeCompressionContext(); + * The first thing to do is to create a compressionContext object, which will be used in all compression operations. + * This is achieved using LZ4F_createCompressionContext(), which takes as argument a version and an LZ4F_preferences_t structure. + * The version provided MUST be LZ4F_VERSION. It is intended to track potential incompatible differences between different binaries. + * The function will provide a pointer to an allocated LZ4F_compressionContext_t object. + * If the result LZ4F_errorCode_t is not OK_NoError, there was an error during context creation. + * Object can release its memory using LZ4F_freeCompressionContext(); */ LZ4F_errorCode_t LZ4F_createCompressionContext(LZ4F_compressionContext_t* LZ4F_compressionContextPtr, unsigned version) { - LZ4F_cctx_t* const cctxPtr = (LZ4F_cctx_t*)ALLOCATOR(sizeof(LZ4F_cctx_t)); + LZ4F_cctx_t* const cctxPtr = (LZ4F_cctx_t*)ALLOC_AND_ZERO(sizeof(LZ4F_cctx_t)); if (cctxPtr==NULL) return err0r(LZ4F_ERROR_allocation_failed); cctxPtr->version = version; - cctxPtr->cStage = 0; /* Next stage : write header */ + cctxPtr->cStage = 0; /* Next stage : init stream */ *LZ4F_compressionContextPtr = (LZ4F_compressionContext_t)cctxPtr; @@ -393,8 +532,8 @@ LZ4F_errorCode_t LZ4F_freeCompressionContext(LZ4F_compressionContext_t LZ4F_comp { LZ4F_cctx_t* const cctxPtr = (LZ4F_cctx_t*)LZ4F_compressionContext; - if (cctxPtr != NULL) { /* null pointers can be safely provided to this function, like free() */ - FREEMEM(cctxPtr->lz4CtxPtr); + if (cctxPtr != NULL) { /* support free on NULL */ + FREEMEM(cctxPtr->lz4CtxPtr); /* works because LZ4_streamHC_t and LZ4_stream_t are simple POD types */ FREEMEM(cctxPtr->tmpBuff); FREEMEM(LZ4F_compressionContext); } @@ -403,59 +542,110 @@ LZ4F_errorCode_t LZ4F_freeCompressionContext(LZ4F_compressionContext_t LZ4F_comp } -/*! LZ4F_compressBegin() : - * will write the frame header into dstBuffer. - * dstBuffer must be large enough to accommodate a header (dstCapacity). Maximum header size is LZ4F_HEADER_SIZE_MAX bytes. +/** + * This function prepares the internal LZ4(HC) stream for a new compression, + * resetting the context and attaching the dictionary, if there is one. + * + * It needs to be called at the beginning of each independent compression + * stream (i.e., at the beginning of a frame in blockLinked mode, or at the + * beginning of each block in blockIndependent mode). + */ +static void LZ4F_initStream(void* ctx, + const LZ4F_CDict* cdict, + int level, + LZ4F_blockMode_t blockMode) { + if (level < LZ4HC_CLEVEL_MIN) { + if (cdict != NULL || blockMode == LZ4F_blockLinked) { + /* In these cases, we will call LZ4_compress_fast_continue(), + * which needs an already reset context. Otherwise, we'll call a + * one-shot API. The non-continued APIs internally perform their own + * resets at the beginning of their calls, where they know what + * tableType they need the context to be in. So in that case this + * would be misguided / wasted work. */ + LZ4_resetStream_fast((LZ4_stream_t*)ctx); + } + LZ4_attach_dictionary((LZ4_stream_t *)ctx, cdict ? cdict->fastCtx : NULL); + } else { + LZ4_resetStreamHC_fast((LZ4_streamHC_t*)ctx, level); + LZ4_attach_HC_dictionary((LZ4_streamHC_t *)ctx, cdict ? cdict->HCCtx : NULL); + } +} + + +/*! LZ4F_compressBegin_usingCDict() : + * init streaming compression and writes frame header into dstBuffer. + * dstBuffer must be >= LZ4F_HEADER_SIZE_MAX bytes. * @return : number of bytes written into dstBuffer for the header * or an error code (can be tested using LZ4F_isError()) */ -size_t LZ4F_compressBegin(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapacity, const LZ4F_preferences_t* preferencesPtr) +size_t LZ4F_compressBegin_usingCDict(LZ4F_cctx* cctxPtr, + void* dstBuffer, size_t dstCapacity, + const LZ4F_CDict* cdict, + const LZ4F_preferences_t* preferencesPtr) { LZ4F_preferences_t prefNull; BYTE* const dstStart = (BYTE*)dstBuffer; BYTE* dstPtr = dstStart; BYTE* headerStart; - size_t requiredBuffSize; if (dstCapacity < maxFHSize) return err0r(LZ4F_ERROR_dstMaxSize_tooSmall); - if (cctxPtr->cStage != 0) return err0r(LZ4F_ERROR_GENERIC); - memset(&prefNull, 0, sizeof(prefNull)); + MEM_INIT(&prefNull, 0, sizeof(prefNull)); if (preferencesPtr == NULL) preferencesPtr = &prefNull; cctxPtr->prefs = *preferencesPtr; - /* ctx Management */ - { U32 const tableID = (cctxPtr->prefs.compressionLevel < LZ4HC_CLEVEL_MIN) ? 1 : 2; /* 0:nothing ; 1:LZ4 table ; 2:HC tables */ - if (cctxPtr->lz4CtxLevel < tableID) { + /* Ctx Management */ + { U16 const ctxTypeID = (cctxPtr->prefs.compressionLevel < LZ4HC_CLEVEL_MIN) ? 1 : 2; + if (cctxPtr->lz4CtxAlloc < ctxTypeID) { FREEMEM(cctxPtr->lz4CtxPtr); - if (cctxPtr->prefs.compressionLevel < LZ4HC_CLEVEL_MIN) + if (cctxPtr->prefs.compressionLevel < LZ4HC_CLEVEL_MIN) { cctxPtr->lz4CtxPtr = (void*)LZ4_createStream(); - else + } else { cctxPtr->lz4CtxPtr = (void*)LZ4_createStreamHC(); - cctxPtr->lz4CtxLevel = tableID; + } + if (cctxPtr->lz4CtxPtr == NULL) return err0r(LZ4F_ERROR_allocation_failed); + cctxPtr->lz4CtxAlloc = ctxTypeID; + cctxPtr->lz4CtxState = ctxTypeID; + } else if (cctxPtr->lz4CtxState != ctxTypeID) { + /* otherwise, a sufficient buffer is allocated, but we need to + * reset it to the correct context type */ + if (cctxPtr->prefs.compressionLevel < LZ4HC_CLEVEL_MIN) { + LZ4_resetStream((LZ4_stream_t *) cctxPtr->lz4CtxPtr); + } else { + LZ4_resetStreamHC((LZ4_streamHC_t *) cctxPtr->lz4CtxPtr, cctxPtr->prefs.compressionLevel); + } + cctxPtr->lz4CtxState = ctxTypeID; } } /* Buffer Management */ - if (cctxPtr->prefs.frameInfo.blockSizeID == 0) cctxPtr->prefs.frameInfo.blockSizeID = LZ4F_BLOCKSIZEID_DEFAULT; + if (cctxPtr->prefs.frameInfo.blockSizeID == 0) + cctxPtr->prefs.frameInfo.blockSizeID = LZ4F_BLOCKSIZEID_DEFAULT; cctxPtr->maxBlockSize = LZ4F_getBlockSize(cctxPtr->prefs.frameInfo.blockSizeID); - requiredBuffSize = cctxPtr->maxBlockSize + ((cctxPtr->prefs.frameInfo.blockMode == LZ4F_blockLinked) * 128 KB); - if (preferencesPtr->autoFlush) - requiredBuffSize = (cctxPtr->prefs.frameInfo.blockMode == LZ4F_blockLinked) * 64 KB; /* just needs dict */ + { size_t const requiredBuffSize = preferencesPtr->autoFlush ? + (cctxPtr->prefs.frameInfo.blockMode == LZ4F_blockLinked) * 64 KB : /* only needs windows size */ + cctxPtr->maxBlockSize + ((cctxPtr->prefs.frameInfo.blockMode == LZ4F_blockLinked) * 128 KB); - if (cctxPtr->maxBufferSize < requiredBuffSize) { - cctxPtr->maxBufferSize = requiredBuffSize; - FREEMEM(cctxPtr->tmpBuff); - cctxPtr->tmpBuff = (BYTE*)ALLOCATOR(requiredBuffSize); - if (cctxPtr->tmpBuff == NULL) return err0r(LZ4F_ERROR_allocation_failed); - } + if (cctxPtr->maxBufferSize < requiredBuffSize) { + cctxPtr->maxBufferSize = 0; + FREEMEM(cctxPtr->tmpBuff); + cctxPtr->tmpBuff = (BYTE*)ALLOC_AND_ZERO(requiredBuffSize); + if (cctxPtr->tmpBuff == NULL) return err0r(LZ4F_ERROR_allocation_failed); + cctxPtr->maxBufferSize = requiredBuffSize; + } } cctxPtr->tmpIn = cctxPtr->tmpBuff; cctxPtr->tmpInSize = 0; XXH32_reset(&(cctxPtr->xxh), 0); - if (cctxPtr->prefs.compressionLevel < LZ4HC_CLEVEL_MIN) - LZ4_resetStream((LZ4_stream_t*)(cctxPtr->lz4CtxPtr)); - else - LZ4_resetStreamHC((LZ4_streamHC_t*)(cctxPtr->lz4CtxPtr), cctxPtr->prefs.compressionLevel); + + /* context init */ + cctxPtr->cdict = cdict; + if (cctxPtr->prefs.frameInfo.blockMode == LZ4F_blockLinked) { + /* frame init only for blockLinked : blockIndependent will be init at each block */ + LZ4F_initStream(cctxPtr->lz4CtxPtr, cdict, cctxPtr->prefs.compressionLevel, LZ4F_blockLinked); + } + if (preferencesPtr->compressionLevel >= LZ4HC_CLEVEL_MIN) { + LZ4_favorDecompressionSpeed((LZ4_streamHC_t*)cctxPtr->lz4CtxPtr, (int)preferencesPtr->favorDecSpeed); + } /* Magic Number */ LZ4F_writeLE32(dstPtr, LZ4F_MAGICNUMBER); @@ -464,9 +654,11 @@ size_t LZ4F_compressBegin(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapacit /* FLG Byte */ *dstPtr++ = (BYTE)(((1 & _2BITS) << 6) /* Version('01') */ - + ((cctxPtr->prefs.frameInfo.blockMode & _1BIT ) << 5) /* Block mode */ - + ((cctxPtr->prefs.frameInfo.contentChecksumFlag & _1BIT ) << 2) /* Frame checksum */ - + ((cctxPtr->prefs.frameInfo.contentSize > 0) << 3)); /* Frame content size */ + + ((cctxPtr->prefs.frameInfo.blockMode & _1BIT ) << 5) + + ((cctxPtr->prefs.frameInfo.blockChecksumFlag & _1BIT ) << 4) + + ((cctxPtr->prefs.frameInfo.contentSize > 0) << 3) + + ((cctxPtr->prefs.frameInfo.contentChecksumFlag & _1BIT ) << 2) + + (cctxPtr->prefs.frameInfo.dictID > 0) ); /* BD Byte */ *dstPtr++ = (BYTE)((cctxPtr->prefs.frameInfo.blockSizeID & _3BITS) << 4); /* Optional Frame content size field */ @@ -475,20 +667,40 @@ size_t LZ4F_compressBegin(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapacit dstPtr += 8; cctxPtr->totalInSize = 0; } - /* CRC Byte */ + /* Optional dictionary ID field */ + if (cctxPtr->prefs.frameInfo.dictID) { + LZ4F_writeLE32(dstPtr, cctxPtr->prefs.frameInfo.dictID); + dstPtr += 4; + } + /* Header CRC Byte */ *dstPtr = LZ4F_headerChecksum(headerStart, dstPtr - headerStart); dstPtr++; cctxPtr->cStage = 1; /* header written, now request input data block */ - return (dstPtr - dstStart); } -/* LZ4F_compressBound() : - * @ return size of Dst buffer given a srcSize to handle worst case situations. - * The LZ4F_frameInfo_t structure is optional : if NULL, preferences will be set to cover worst case situations. - * This function cannot fail. +/*! LZ4F_compressBegin() : + * init streaming compression and writes frame header into dstBuffer. + * dstBuffer must be >= LZ4F_HEADER_SIZE_MAX bytes. + * preferencesPtr can be NULL, in which case default parameters are selected. + * @return : number of bytes written into dstBuffer for the header + * or an error code (can be tested using LZ4F_isError()) + */ +size_t LZ4F_compressBegin(LZ4F_cctx* cctxPtr, + void* dstBuffer, size_t dstCapacity, + const LZ4F_preferences_t* preferencesPtr) +{ + return LZ4F_compressBegin_usingCDict(cctxPtr, dstBuffer, dstCapacity, + NULL, preferencesPtr); +} + + +/* LZ4F_compressBound() : + * @return minimum capacity of dstBuffer for a given srcSize to handle worst case scenario. + * LZ4F_preferences_t structure is optional : if NULL, preferences will be set to cover worst case scenario. + * This function cannot fail. */ size_t LZ4F_compressBound(size_t srcSize, const LZ4F_preferences_t* preferencesPtr) { @@ -496,49 +708,75 @@ size_t LZ4F_compressBound(size_t srcSize, const LZ4F_preferences_t* preferencesP } -typedef int (*compressFunc_t)(void* ctx, const char* src, char* dst, int srcSize, int dstSize, int level); +typedef int (*compressFunc_t)(void* ctx, const char* src, char* dst, int srcSize, int dstSize, int level, const LZ4F_CDict* cdict); -static size_t LZ4F_compressBlock(void* dst, const void* src, size_t srcSize, compressFunc_t compress, void* lz4ctx, int level) + +/*! LZ4F_makeBlock(): + * compress a single block, add header and checksum + * assumption : dst buffer capacity is >= srcSize */ +static size_t LZ4F_makeBlock(void* dst, const void* src, size_t srcSize, + compressFunc_t compress, void* lz4ctx, int level, + const LZ4F_CDict* cdict, LZ4F_blockChecksum_t crcFlag) { - /* compress a single block */ BYTE* const cSizePtr = (BYTE*)dst; - U32 cSize = (U32)compress(lz4ctx, (const char*)src, (char*)(cSizePtr+4), (int)(srcSize), (int)(srcSize-1), level); + U32 cSize = (U32)compress(lz4ctx, (const char*)src, (char*)(cSizePtr+4), + (int)(srcSize), (int)(srcSize-1), + level, cdict); LZ4F_writeLE32(cSizePtr, cSize); if (cSize == 0) { /* compression failed */ cSize = (U32)srcSize; LZ4F_writeLE32(cSizePtr, cSize | LZ4F_BLOCKUNCOMPRESSED_FLAG); memcpy(cSizePtr+4, src, srcSize); } - return cSize + 4; + if (crcFlag) { + U32 const crc32 = XXH32(cSizePtr+4, cSize, 0); /* checksum of compressed data */ + LZ4F_writeLE32(cSizePtr+4+cSize, crc32); + } + return 4 + cSize + ((U32)crcFlag)*4; } -static int LZ4F_localLZ4_compress_limitedOutput_withState(void* ctx, const char* src, char* dst, int srcSize, int dstCapacity, int level) +static int LZ4F_compressBlock(void* ctx, const char* src, char* dst, int srcSize, int dstCapacity, int level, const LZ4F_CDict* cdict) +{ + int const acceleration = (level < 0) ? -level + 1 : 1; + LZ4F_initStream(ctx, cdict, level, LZ4F_blockIndependent); + if (cdict) { + return LZ4_compress_fast_continue((LZ4_stream_t*)ctx, src, dst, srcSize, dstCapacity, acceleration); + } else { + return LZ4_compress_fast_extState_fastReset(ctx, src, dst, srcSize, dstCapacity, acceleration); + } +} + +static int LZ4F_compressBlock_continue(void* ctx, const char* src, char* dst, int srcSize, int dstCapacity, int level, const LZ4F_CDict* cdict) { - (void) level; - return LZ4_compress_fast_extState(ctx, src, dst, srcSize, dstCapacity, 1); + int const acceleration = (level < 0) ? -level + 1 : 1; + (void)cdict; /* init once at beginning of frame */ + return LZ4_compress_fast_continue((LZ4_stream_t*)ctx, src, dst, srcSize, dstCapacity, acceleration); } -static int LZ4F_localLZ4_compress_limitedOutput_continue(void* ctx, const char* src, char* dst, int srcSize, int dstCapacity, int level) +static int LZ4F_compressBlockHC(void* ctx, const char* src, char* dst, int srcSize, int dstCapacity, int level, const LZ4F_CDict* cdict) { - (void) level; - return LZ4_compress_fast_continue((LZ4_stream_t*)ctx, src, dst, srcSize, dstCapacity, 1); + LZ4F_initStream(ctx, cdict, level, LZ4F_blockIndependent); + if (cdict) { + return LZ4_compress_HC_continue((LZ4_streamHC_t*)ctx, src, dst, srcSize, dstCapacity); + } + return LZ4_compress_HC_extStateHC_fastReset(ctx, src, dst, srcSize, dstCapacity, level); } -static int LZ4F_localLZ4_compressHC_limitedOutput_continue(void* ctx, const char* src, char* dst, int srcSize, int dstSize, int level) +static int LZ4F_compressBlockHC_continue(void* ctx, const char* src, char* dst, int srcSize, int dstCapacity, int level, const LZ4F_CDict* cdict) { - (void) level; - return LZ4_compress_HC_continue((LZ4_streamHC_t*)ctx, src, dst, srcSize, dstSize); + (void)level; (void)cdict; /* init once at beginning of frame */ + return LZ4_compress_HC_continue((LZ4_streamHC_t*)ctx, src, dst, srcSize, dstCapacity); } static compressFunc_t LZ4F_selectCompression(LZ4F_blockMode_t blockMode, int level) { if (level < LZ4HC_CLEVEL_MIN) { - if (blockMode == LZ4F_blockIndependent) return LZ4F_localLZ4_compress_limitedOutput_withState; - return LZ4F_localLZ4_compress_limitedOutput_continue; + if (blockMode == LZ4F_blockIndependent) return LZ4F_compressBlock; + return LZ4F_compressBlock_continue; } - if (blockMode == LZ4F_blockIndependent) return LZ4_compress_HC_extStateHC; - return LZ4F_localLZ4_compressHC_limitedOutput_continue; + if (blockMode == LZ4F_blockIndependent) return LZ4F_compressBlockHC; + return LZ4F_compressBlockHC_continue; } static int LZ4F_localSaveDict(LZ4F_cctx_t* cctxPtr) @@ -551,15 +789,16 @@ static int LZ4F_localSaveDict(LZ4F_cctx_t* cctxPtr) typedef enum { notDone, fromTmpBuffer, fromSrcBuffer } LZ4F_lastBlockStatus; /*! LZ4F_compressUpdate() : -* LZ4F_compressUpdate() can be called repetitively to compress as much data as necessary. -* The most important rule is that dstBuffer MUST be large enough (dstCapacity) to ensure compression completion even in worst case. -* If this condition is not respected, LZ4F_compress() will fail (result is an errorCode) -* You can get the minimum value of dstCapacity by using LZ4F_compressBound() -* The LZ4F_compressOptions_t structure is optional : you can provide NULL as argument. -* The result of the function is the number of bytes written into dstBuffer : it can be zero, meaning input data was just buffered. -* The function outputs an error code if it fails (can be tested using LZ4F_isError()) -*/ -size_t LZ4F_compressUpdate(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapacity, const void* srcBuffer, size_t srcSize, const LZ4F_compressOptions_t* compressOptionsPtr) + * LZ4F_compressUpdate() can be called repetitively to compress as much data as necessary. + * dstBuffer MUST be >= LZ4F_compressBound(srcSize, preferencesPtr). + * LZ4F_compressOptions_t structure is optional : you can provide NULL as argument. + * @return : the number of bytes written into dstBuffer. It can be zero, meaning input data was just buffered. + * or an error code if it fails (which can be tested using LZ4F_isError()) + */ +size_t LZ4F_compressUpdate(LZ4F_cctx* cctxPtr, + void* dstBuffer, size_t dstCapacity, + const void* srcBuffer, size_t srcSize, + const LZ4F_compressOptions_t* compressOptionsPtr) { LZ4F_compressOptions_t cOptionsNull; size_t const blockSize = cctxPtr->maxBlockSize; @@ -570,10 +809,12 @@ size_t LZ4F_compressUpdate(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapaci LZ4F_lastBlockStatus lastBlockCompressed = notDone; compressFunc_t const compress = LZ4F_selectCompression(cctxPtr->prefs.frameInfo.blockMode, cctxPtr->prefs.compressionLevel); + DEBUGLOG(4, "LZ4F_compressUpdate (srcSize=%zu)", srcSize); if (cctxPtr->cStage != 1) return err0r(LZ4F_ERROR_GENERIC); - if (dstCapacity < LZ4F_compressBound_internal(srcSize, &(cctxPtr->prefs), cctxPtr->tmpInSize)) return err0r(LZ4F_ERROR_dstMaxSize_tooSmall); - memset(&cOptionsNull, 0, sizeof(cOptionsNull)); + if (dstCapacity < LZ4F_compressBound_internal(srcSize, &(cctxPtr->prefs), cctxPtr->tmpInSize)) + return err0r(LZ4F_ERROR_dstMaxSize_tooSmall); + MEM_INIT(&cOptionsNull, 0, sizeof(cOptionsNull)); if (compressOptionsPtr == NULL) compressOptionsPtr = &cOptionsNull; /* complete tmp buffer */ @@ -591,7 +832,9 @@ size_t LZ4F_compressUpdate(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapaci memcpy(cctxPtr->tmpIn + cctxPtr->tmpInSize, srcBuffer, sizeToCopy); srcPtr += sizeToCopy; - dstPtr += LZ4F_compressBlock(dstPtr, cctxPtr->tmpIn, blockSize, compress, cctxPtr->lz4CtxPtr, cctxPtr->prefs.compressionLevel); + dstPtr += LZ4F_makeBlock(dstPtr, cctxPtr->tmpIn, blockSize, + compress, cctxPtr->lz4CtxPtr, cctxPtr->prefs.compressionLevel, + cctxPtr->cdict, cctxPtr->prefs.frameInfo.blockChecksumFlag); if (cctxPtr->prefs.frameInfo.blockMode==LZ4F_blockLinked) cctxPtr->tmpIn += blockSize; cctxPtr->tmpInSize = 0; @@ -599,16 +842,20 @@ size_t LZ4F_compressUpdate(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapaci } while ((size_t)(srcEnd - srcPtr) >= blockSize) { - /* compress full block */ + /* compress full blocks */ lastBlockCompressed = fromSrcBuffer; - dstPtr += LZ4F_compressBlock(dstPtr, srcPtr, blockSize, compress, cctxPtr->lz4CtxPtr, cctxPtr->prefs.compressionLevel); + dstPtr += LZ4F_makeBlock(dstPtr, srcPtr, blockSize, + compress, cctxPtr->lz4CtxPtr, cctxPtr->prefs.compressionLevel, + cctxPtr->cdict, cctxPtr->prefs.frameInfo.blockChecksumFlag); srcPtr += blockSize; } if ((cctxPtr->prefs.autoFlush) && (srcPtr < srcEnd)) { /* compress remaining input < blockSize */ lastBlockCompressed = fromSrcBuffer; - dstPtr += LZ4F_compressBlock(dstPtr, srcPtr, srcEnd - srcPtr, compress, cctxPtr->lz4CtxPtr, cctxPtr->prefs.compressionLevel); + dstPtr += LZ4F_makeBlock(dstPtr, srcPtr, srcEnd - srcPtr, + compress, cctxPtr->lz4CtxPtr, cctxPtr->prefs.compressionLevel, + cctxPtr->cdict, cctxPtr->prefs.frameInfo.blockChecksumFlag); srcPtr = srcEnd; } @@ -617,7 +864,7 @@ size_t LZ4F_compressUpdate(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapaci if (compressOptionsPtr->stableSrc) { cctxPtr->tmpIn = cctxPtr->tmpBuff; } else { - int realDictSize = LZ4F_localSaveDict(cctxPtr); + int const realDictSize = LZ4F_localSaveDict(cctxPtr); if (realDictSize==0) return err0r(LZ4F_ERROR_GENERIC); cctxPtr->tmpIn = cctxPtr->tmpBuff + realDictSize; } @@ -627,7 +874,7 @@ size_t LZ4F_compressUpdate(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapaci if ((cctxPtr->tmpIn + blockSize) > (cctxPtr->tmpBuff + cctxPtr->maxBufferSize) /* necessarily LZ4F_blockLinked && lastBlockCompressed==fromTmpBuffer */ && !(cctxPtr->prefs.autoFlush)) { - int realDictSize = LZ4F_localSaveDict(cctxPtr); + int const realDictSize = LZ4F_localSaveDict(cctxPtr); cctxPtr->tmpIn = cctxPtr->tmpBuff + realDictSize; } @@ -648,13 +895,13 @@ size_t LZ4F_compressUpdate(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapaci /*! LZ4F_flush() : -* Should you need to create compressed data immediately, without waiting for a block to be filled, -* you can call LZ4_flush(), which will immediately compress any remaining data stored within compressionContext. -* The result of the function is the number of bytes written into dstBuffer -* (it can be zero, this means there was no data left within compressionContext) -* The function outputs an error code if it fails (can be tested using LZ4F_isError()) -* The LZ4F_compressOptions_t structure is optional : you can provide NULL as argument. -*/ + * Should you need to create compressed data immediately, without waiting for a block to be filled, + * you can call LZ4_flush(), which will immediately compress any remaining data stored within compressionContext. + * The result of the function is the number of bytes written into dstBuffer + * (it can be zero, this means there was no data left within compressionContext) + * The function outputs an error code if it fails (can be tested using LZ4F_isError()) + * The LZ4F_compressOptions_t structure is optional : you can provide NULL as argument. + */ size_t LZ4F_flush(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapacity, const LZ4F_compressOptions_t* compressOptionsPtr) { BYTE* const dstStart = (BYTE*)dstBuffer; @@ -670,7 +917,9 @@ size_t LZ4F_flush(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapacity, const compress = LZ4F_selectCompression(cctxPtr->prefs.frameInfo.blockMode, cctxPtr->prefs.compressionLevel); /* compress tmp buffer */ - dstPtr += LZ4F_compressBlock(dstPtr, cctxPtr->tmpIn, cctxPtr->tmpInSize, compress, cctxPtr->lz4CtxPtr, cctxPtr->prefs.compressionLevel); + dstPtr += LZ4F_makeBlock(dstPtr, cctxPtr->tmpIn, cctxPtr->tmpInSize, + compress, cctxPtr->lz4CtxPtr, cctxPtr->prefs.compressionLevel, + cctxPtr->cdict, cctxPtr->prefs.frameInfo.blockChecksumFlag); if (cctxPtr->prefs.frameInfo.blockMode==LZ4F_blockLinked) cctxPtr->tmpIn += cctxPtr->tmpInSize; cctxPtr->tmpInSize = 0; @@ -685,14 +934,14 @@ size_t LZ4F_flush(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstCapacity, const /*! LZ4F_compressEnd() : -* When you want to properly finish the compressed frame, just call LZ4F_compressEnd(). -* It will flush whatever data remained within compressionContext (like LZ4_flush()) -* but also properly finalize the frame, with an endMark and a checksum. -* The result of the function is the number of bytes written into dstBuffer (necessarily >= 4 (endMark size)) -* The function outputs an error code if it fails (can be tested using LZ4F_isError()) -* The LZ4F_compressOptions_t structure is optional : you can provide NULL as argument. -* compressionContext can then be used again, starting with LZ4F_compressBegin(). The preferences will remain the same. -*/ + * When you want to properly finish the compressed frame, just call LZ4F_compressEnd(). + * It will flush whatever data remained within compressionContext (like LZ4_flush()) + * but also properly finalize the frame, with an endMark and a checksum. + * The result of the function is the number of bytes written into dstBuffer (necessarily >= 4 (endMark size)) + * The function outputs an error code if it fails (can be tested using LZ4F_isError()) + * The LZ4F_compressOptions_t structure is optional : you can provide NULL as argument. + * compressionContext can then be used again, starting with LZ4F_compressBegin(). The preferences will remain the same. + */ size_t LZ4F_compressEnd(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstMaxSize, const LZ4F_compressOptions_t* compressOptionsPtr) { BYTE* const dstStart = (BYTE*)dstBuffer; @@ -727,10 +976,22 @@ size_t LZ4F_compressEnd(LZ4F_cctx* cctxPtr, void* dstBuffer, size_t dstMaxSize, * Frame Decompression *****************************************************/ +typedef enum { + dstage_getFrameHeader=0, dstage_storeFrameHeader, + dstage_init, + dstage_getBlockHeader, dstage_storeBlockHeader, + dstage_copyDirect, dstage_getBlockChecksum, + dstage_getCBlock, dstage_storeCBlock, + dstage_flushOut, + dstage_getSuffix, dstage_storeSuffix, + dstage_getSFrameSize, dstage_storeSFrameSize, + dstage_skipSkippable +} dStage_t; + struct LZ4F_dctx_s { LZ4F_frameInfo_t frameInfo; U32 version; - U32 dStage; + dStage_t dStage; U64 frameRemainingSize; size_t maxBlockSize; size_t maxBufferSize; @@ -738,40 +999,41 @@ struct LZ4F_dctx_s { size_t tmpInSize; size_t tmpInTarget; BYTE* tmpOutBuffer; - const BYTE* dict; + const BYTE* dict; size_t dictSize; BYTE* tmpOut; size_t tmpOutSize; size_t tmpOutStart; XXH32_state_t xxh; - BYTE header[16]; + XXH32_state_t blockChecksum; + BYTE header[LZ4F_HEADER_SIZE_MAX]; }; /* typedef'd to LZ4F_dctx in lz4frame.h */ /*! LZ4F_createDecompressionContext() : -* Create a decompressionContext object, which will track all decompression operations. -* Provides a pointer to a fully allocated and initialized LZ4F_decompressionContext object. -* Object can later be released using LZ4F_freeDecompressionContext(). -* @return : if != 0, there was an error during context creation. -*/ + * Create a decompressionContext object, which will track all decompression operations. + * Provides a pointer to a fully allocated and initialized LZ4F_decompressionContext object. + * Object can later be released using LZ4F_freeDecompressionContext(). + * @return : if != 0, there was an error during context creation. + */ LZ4F_errorCode_t LZ4F_createDecompressionContext(LZ4F_dctx** LZ4F_decompressionContextPtr, unsigned versionNumber) { - LZ4F_dctx* const dctxPtr = (LZ4F_dctx*)ALLOCATOR(sizeof(LZ4F_dctx)); - if (dctxPtr==NULL) return err0r(LZ4F_ERROR_GENERIC); + LZ4F_dctx* const dctx = (LZ4F_dctx*)ALLOC_AND_ZERO(sizeof(LZ4F_dctx)); + if (dctx==NULL) return err0r(LZ4F_ERROR_GENERIC); - dctxPtr->version = versionNumber; - *LZ4F_decompressionContextPtr = dctxPtr; + dctx->version = versionNumber; + *LZ4F_decompressionContextPtr = dctx; return LZ4F_OK_NoError; } -LZ4F_errorCode_t LZ4F_freeDecompressionContext(LZ4F_dctx* const dctxPtr) +LZ4F_errorCode_t LZ4F_freeDecompressionContext(LZ4F_dctx* dctx) { LZ4F_errorCode_t result = LZ4F_OK_NoError; - if (dctxPtr != NULL) { /* can accept NULL input, like free() */ - result = (LZ4F_errorCode_t)dctxPtr->dStage; - FREEMEM(dctxPtr->tmpIn); - FREEMEM(dctxPtr->tmpOutBuffer); - FREEMEM(dctxPtr); + if (dctx != NULL) { /* can accept NULL input, like free() */ + result = (LZ4F_errorCode_t)dctx->dStage; + FREEMEM(dctx->tmpIn); + FREEMEM(dctx->tmpOutBuffer); + FREEMEM(dctx); } return result; } @@ -779,22 +1041,18 @@ LZ4F_errorCode_t LZ4F_freeDecompressionContext(LZ4F_dctx* const dctxPtr) /*==--- Streaming Decompression operations ---==*/ -typedef enum { dstage_getHeader=0, dstage_storeHeader, - dstage_getCBlockSize, dstage_storeCBlockSize, - dstage_copyDirect, - dstage_getCBlock, dstage_storeCBlock, - dstage_decodeCBlock, dstage_decodeCBlock_intoDst, - dstage_decodeCBlock_intoTmp, dstage_flushOut, - dstage_getSuffix, dstage_storeSuffix, - dstage_getSFrameSize, dstage_storeSFrameSize, - dstage_skipSkippable -} dStage_t; +void LZ4F_resetDecompressionContext(LZ4F_dctx* dctx) +{ + dctx->dStage = dstage_getFrameHeader; + dctx->dict = NULL; + dctx->dictSize = 0; +} /*! LZ4F_headerSize() : -* @return : size of frame header -* or an error code, which can be tested using LZ4F_isError() -*/ + * @return : size of frame header + * or an error code, which can be tested using LZ4F_isError() + */ static size_t LZ4F_headerSize(const void* src, size_t srcSize) { /* minimal srcSize to determine header size */ @@ -804,244 +1062,252 @@ static size_t LZ4F_headerSize(const void* src, size_t srcSize) if ((LZ4F_readLE32(src) & 0xFFFFFFF0U) == LZ4F_MAGIC_SKIPPABLE_START) return 8; /* control magic number */ - if (LZ4F_readLE32(src) != LZ4F_MAGICNUMBER) return err0r(LZ4F_ERROR_frameType_unknown); + if (LZ4F_readLE32(src) != LZ4F_MAGICNUMBER) + return err0r(LZ4F_ERROR_frameType_unknown); /* Frame Header Size */ { BYTE const FLG = ((const BYTE*)src)[4]; U32 const contentSizeFlag = (FLG>>3) & _1BIT; - return contentSizeFlag ? maxFHSize : minFHSize; + U32 const dictIDFlag = FLG & _1BIT; + return minFHSize + (contentSizeFlag*8) + (dictIDFlag*4); } } /*! LZ4F_decodeHeader() : - input : `src` points at the **beginning of the frame** - output : set internal values of dctx, such as - dctxPtr->frameInfo and dctxPtr->dStage. - Also allocates internal buffers. - @return : nb Bytes read from srcVoidPtr (necessarily <= srcSize) - or an error code (testable with LZ4F_isError()) -*/ -static size_t LZ4F_decodeHeader(LZ4F_dctx* dctxPtr, const void* src, size_t srcSize) + * input : `src` points at the **beginning of the frame** + * output : set internal values of dctx, such as + * dctx->frameInfo and dctx->dStage. + * Also allocates internal buffers. + * @return : nb Bytes read from src (necessarily <= srcSize) + * or an error code (testable with LZ4F_isError()) + */ +static size_t LZ4F_decodeHeader(LZ4F_dctx* dctx, const void* src, size_t srcSize) { - BYTE FLG, BD; - unsigned version, blockMode, blockChecksumFlag, contentSizeFlag, contentChecksumFlag, blockSizeID; + unsigned blockMode, blockChecksumFlag, contentSizeFlag, contentChecksumFlag, dictIDFlag, blockSizeID; size_t frameHeaderSize; const BYTE* srcPtr = (const BYTE*)src; /* need to decode header to get frameInfo */ if (srcSize < minFHSize) return err0r(LZ4F_ERROR_frameHeader_incomplete); /* minimal frame header size */ - memset(&(dctxPtr->frameInfo), 0, sizeof(dctxPtr->frameInfo)); + MEM_INIT(&(dctx->frameInfo), 0, sizeof(dctx->frameInfo)); /* special case : skippable frames */ if ((LZ4F_readLE32(srcPtr) & 0xFFFFFFF0U) == LZ4F_MAGIC_SKIPPABLE_START) { - dctxPtr->frameInfo.frameType = LZ4F_skippableFrame; - if (src == (void*)(dctxPtr->header)) { - dctxPtr->tmpInSize = srcSize; - dctxPtr->tmpInTarget = 8; - dctxPtr->dStage = dstage_storeSFrameSize; + dctx->frameInfo.frameType = LZ4F_skippableFrame; + if (src == (void*)(dctx->header)) { + dctx->tmpInSize = srcSize; + dctx->tmpInTarget = 8; + dctx->dStage = dstage_storeSFrameSize; return srcSize; } else { - dctxPtr->dStage = dstage_getSFrameSize; + dctx->dStage = dstage_getSFrameSize; return 4; } } /* control magic number */ - if (LZ4F_readLE32(srcPtr) != LZ4F_MAGICNUMBER) return err0r(LZ4F_ERROR_frameType_unknown); - dctxPtr->frameInfo.frameType = LZ4F_frame; + if (LZ4F_readLE32(srcPtr) != LZ4F_MAGICNUMBER) + return err0r(LZ4F_ERROR_frameType_unknown); + dctx->frameInfo.frameType = LZ4F_frame; /* Flags */ - FLG = srcPtr[4]; - version = (FLG>>6) & _2BITS; - blockMode = (FLG>>5) & _1BIT; - blockChecksumFlag = (FLG>>4) & _1BIT; - contentSizeFlag = (FLG>>3) & _1BIT; - contentChecksumFlag = (FLG>>2) & _1BIT; + { U32 const FLG = srcPtr[4]; + U32 const version = (FLG>>6) & _2BITS; + blockChecksumFlag = (FLG>>4) & _1BIT; + blockMode = (FLG>>5) & _1BIT; + contentSizeFlag = (FLG>>3) & _1BIT; + contentChecksumFlag = (FLG>>2) & _1BIT; + dictIDFlag = FLG & _1BIT; + /* validate */ + if (((FLG>>1)&_1BIT) != 0) return err0r(LZ4F_ERROR_reservedFlag_set); /* Reserved bit */ + if (version != 1) return err0r(LZ4F_ERROR_headerVersion_wrong); /* Version Number, only supported value */ + } /* Frame Header Size */ - frameHeaderSize = contentSizeFlag ? maxFHSize : minFHSize; + frameHeaderSize = minFHSize + (contentSizeFlag*8) + (dictIDFlag*4); if (srcSize < frameHeaderSize) { /* not enough input to fully decode frame header */ - if (srcPtr != dctxPtr->header) - memcpy(dctxPtr->header, srcPtr, srcSize); - dctxPtr->tmpInSize = srcSize; - dctxPtr->tmpInTarget = frameHeaderSize; - dctxPtr->dStage = dstage_storeHeader; + if (srcPtr != dctx->header) + memcpy(dctx->header, srcPtr, srcSize); + dctx->tmpInSize = srcSize; + dctx->tmpInTarget = frameHeaderSize; + dctx->dStage = dstage_storeFrameHeader; return srcSize; } - BD = srcPtr[5]; - blockSizeID = (BD>>4) & _3BITS; - - /* validate */ - if (version != 1) return err0r(LZ4F_ERROR_headerVersion_wrong); /* Version Number, only supported value */ - if (blockChecksumFlag != 0) return err0r(LZ4F_ERROR_blockChecksum_unsupported); /* Not supported for the time being */ - if (((FLG>>0)&_2BITS) != 0) return err0r(LZ4F_ERROR_reservedFlag_set); /* Reserved bits */ - if (((BD>>7)&_1BIT) != 0) return err0r(LZ4F_ERROR_reservedFlag_set); /* Reserved bit */ - if (blockSizeID < 4) return err0r(LZ4F_ERROR_maxBlockSize_invalid); /* 4-7 only supported values for the time being */ - if (((BD>>0)&_4BITS) != 0) return err0r(LZ4F_ERROR_reservedFlag_set); /* Reserved bits */ + { U32 const BD = srcPtr[5]; + blockSizeID = (BD>>4) & _3BITS; + /* validate */ + if (((BD>>7)&_1BIT) != 0) return err0r(LZ4F_ERROR_reservedFlag_set); /* Reserved bit */ + if (blockSizeID < 4) return err0r(LZ4F_ERROR_maxBlockSize_invalid); /* 4-7 only supported values for the time being */ + if (((BD>>0)&_4BITS) != 0) return err0r(LZ4F_ERROR_reservedFlag_set); /* Reserved bits */ + } /* check header */ - { BYTE const HC = LZ4F_headerChecksum(srcPtr+4, frameHeaderSize-5); - if (HC != srcPtr[frameHeaderSize-1]) return err0r(LZ4F_ERROR_headerChecksum_invalid); } + { BYTE const HC = LZ4F_headerChecksum(srcPtr+4, frameHeaderSize-5); + if (HC != srcPtr[frameHeaderSize-1]) + return err0r(LZ4F_ERROR_headerChecksum_invalid); + } /* save */ - dctxPtr->frameInfo.blockMode = (LZ4F_blockMode_t)blockMode; - dctxPtr->frameInfo.contentChecksumFlag = (LZ4F_contentChecksum_t)contentChecksumFlag; - dctxPtr->frameInfo.blockSizeID = (LZ4F_blockSizeID_t)blockSizeID; - dctxPtr->maxBlockSize = LZ4F_getBlockSize(blockSizeID); + dctx->frameInfo.blockMode = (LZ4F_blockMode_t)blockMode; + dctx->frameInfo.blockChecksumFlag = (LZ4F_blockChecksum_t)blockChecksumFlag; + dctx->frameInfo.contentChecksumFlag = (LZ4F_contentChecksum_t)contentChecksumFlag; + dctx->frameInfo.blockSizeID = (LZ4F_blockSizeID_t)blockSizeID; + dctx->maxBlockSize = LZ4F_getBlockSize(blockSizeID); if (contentSizeFlag) - dctxPtr->frameRemainingSize = dctxPtr->frameInfo.contentSize = LZ4F_readLE64(srcPtr+6); - - /* init */ - if (contentChecksumFlag) XXH32_reset(&(dctxPtr->xxh), 0); - - /* internal buffers allocation */ - { size_t const bufferNeeded = dctxPtr->maxBlockSize + ((dctxPtr->frameInfo.blockMode==LZ4F_blockLinked) * 128 KB); - if (bufferNeeded > dctxPtr->maxBufferSize) { /* tmp buffers too small */ - FREEMEM(dctxPtr->tmpIn); - dctxPtr->tmpIn = (BYTE*)ALLOCATOR(dctxPtr->maxBlockSize); - if (dctxPtr->tmpIn == NULL) return err0r(LZ4F_ERROR_allocation_failed); - FREEMEM(dctxPtr->tmpOutBuffer); - dctxPtr->maxBufferSize = 0; - dctxPtr->tmpOutBuffer= (BYTE*)ALLOCATOR(bufferNeeded); - if (dctxPtr->tmpOutBuffer== NULL) return err0r(LZ4F_ERROR_allocation_failed); - dctxPtr->maxBufferSize = bufferNeeded; - } } - dctxPtr->tmpInSize = 0; - dctxPtr->tmpInTarget = 0; - dctxPtr->dict = dctxPtr->tmpOutBuffer; - dctxPtr->dictSize = 0; - dctxPtr->tmpOut = dctxPtr->tmpOutBuffer; - dctxPtr->tmpOutStart = 0; - dctxPtr->tmpOutSize = 0; + dctx->frameRemainingSize = + dctx->frameInfo.contentSize = LZ4F_readLE64(srcPtr+6); + if (dictIDFlag) + dctx->frameInfo.dictID = LZ4F_readLE32(srcPtr + frameHeaderSize - 5); - dctxPtr->dStage = dstage_getCBlockSize; + dctx->dStage = dstage_init; return frameHeaderSize; } /*! LZ4F_getFrameInfo() : -* Decodes frame header information, such as blockSize. Usage is optional. -* The objective is to extract header information before receiving decompressed data, typically for allocation purposes. -* LZ4F_getFrameInfo() can also be used *after* starting decompression, on a valid LZ4F_decompressionContext_t. -* The number of bytes consumed from srcBuffer will be provided within *srcSizePtr (necessarily <= original value). -* Decompression must resume from where it stopped (srcBuffer + *srcSizePtr) -* @return : hint of the better `srcSize` to use for next call to LZ4F_decompress, -* or an error code which can be tested using LZ4F_isError(). -*/ -LZ4F_errorCode_t LZ4F_getFrameInfo(LZ4F_dctx* dctxPtr, LZ4F_frameInfo_t* frameInfoPtr, + * This function extracts frame parameters (max blockSize, frame checksum, etc.). + * Usage is optional. Objective is to provide relevant information for allocation purposes. + * This function works in 2 situations : + * - At the beginning of a new frame, in which case it will decode this information from `srcBuffer`, and start the decoding process. + * Amount of input data provided must be large enough to successfully decode the frame header. + * A header size is variable, but is guaranteed to be <= LZ4F_HEADER_SIZE_MAX bytes. It's possible to provide more input data than this minimum. + * - After decoding has been started. In which case, no input is read, frame parameters are extracted from dctx. + * The number of bytes consumed from srcBuffer will be updated within *srcSizePtr (necessarily <= original value). + * Decompression must resume from (srcBuffer + *srcSizePtr). + * @return : an hint about how many srcSize bytes LZ4F_decompress() expects for next call, + * or an error code which can be tested using LZ4F_isError() + * note 1 : in case of error, dctx is not modified. Decoding operations can resume from where they stopped. + * note 2 : frame parameters are *copied into* an already allocated LZ4F_frameInfo_t structure. + */ +LZ4F_errorCode_t LZ4F_getFrameInfo(LZ4F_dctx* dctx, LZ4F_frameInfo_t* frameInfoPtr, const void* srcBuffer, size_t* srcSizePtr) { - if (dctxPtr->dStage > dstage_storeHeader) { /* note : requires dstage_* header related to be at beginning of enum */ + if (dctx->dStage > dstage_storeFrameHeader) { /* assumption : dstage_* header enum at beginning of range */ /* frameInfo already decoded */ size_t o=0, i=0; *srcSizePtr = 0; - *frameInfoPtr = dctxPtr->frameInfo; - return LZ4F_decompress(dctxPtr, NULL, &o, NULL, &i, NULL); /* returns : recommended nb of bytes for LZ4F_decompress() */ + *frameInfoPtr = dctx->frameInfo; + /* returns : recommended nb of bytes for LZ4F_decompress() */ + return LZ4F_decompress(dctx, NULL, &o, NULL, &i, NULL); } else { - size_t nextSrcSize, o=0; - size_t const hSize = LZ4F_headerSize(srcBuffer, *srcSizePtr); - if (LZ4F_isError(hSize)) { *srcSizePtr=0; return hSize; } - if (*srcSizePtr < hSize) { *srcSizePtr=0; return err0r(LZ4F_ERROR_frameHeader_incomplete); } - - *srcSizePtr = hSize; - nextSrcSize = LZ4F_decompress(dctxPtr, NULL, &o, srcBuffer, srcSizePtr, NULL); - if (dctxPtr->dStage <= dstage_storeHeader) return err0r(LZ4F_ERROR_frameHeader_incomplete); /* should not happen, already checked */ - *frameInfoPtr = dctxPtr->frameInfo; - return nextSrcSize; - } -} - + if (dctx->dStage == dstage_storeFrameHeader) { + /* frame decoding already started, in the middle of header => automatic fail */ + *srcSizePtr = 0; + return err0r(LZ4F_ERROR_frameDecoding_alreadyStarted); + } else { + size_t decodeResult; + size_t const hSize = LZ4F_headerSize(srcBuffer, *srcSizePtr); + if (LZ4F_isError(hSize)) { *srcSizePtr=0; return hSize; } + if (*srcSizePtr < hSize) { + *srcSizePtr=0; + return err0r(LZ4F_ERROR_frameHeader_incomplete); + } -/* trivial redirector, for common prototype */ -static int LZ4F_decompress_safe (const char* source, char* dest, int compressedSize, int maxDecompressedSize, const char* dictStart, int dictSize) -{ - (void)dictStart; (void)dictSize; - return LZ4_decompress_safe (source, dest, compressedSize, maxDecompressedSize); + decodeResult = LZ4F_decodeHeader(dctx, srcBuffer, hSize); + if (LZ4F_isError(decodeResult)) { + *srcSizePtr = 0; + } else { + *srcSizePtr = decodeResult; + decodeResult = BHSize; /* block header size */ + } + *frameInfoPtr = dctx->frameInfo; + return decodeResult; + } } } -static void LZ4F_updateDict(LZ4F_dctx* dctxPtr, const BYTE* dstPtr, size_t dstSize, const BYTE* dstPtr0, unsigned withinTmp) +/* LZ4F_updateDict() : + * only used for LZ4F_blockLinked mode */ +static void LZ4F_updateDict(LZ4F_dctx* dctx, + const BYTE* dstPtr, size_t dstSize, const BYTE* dstBufferStart, + unsigned withinTmp) { - if (dctxPtr->dictSize==0) - dctxPtr->dict = (const BYTE*)dstPtr; /* priority to dictionary continuity */ + if (dctx->dictSize==0) + dctx->dict = (const BYTE*)dstPtr; /* priority to dictionary continuity */ - if (dctxPtr->dict + dctxPtr->dictSize == dstPtr) { /* dictionary continuity */ - dctxPtr->dictSize += dstSize; + if (dctx->dict + dctx->dictSize == dstPtr) { /* dictionary continuity, directly within dstBuffer */ + dctx->dictSize += dstSize; return; } - if (dstPtr - dstPtr0 + dstSize >= 64 KB) { /* dstBuffer large enough to become dictionary */ - dctxPtr->dict = (const BYTE*)dstPtr0; - dctxPtr->dictSize = dstPtr - dstPtr0 + dstSize; + if (dstPtr - dstBufferStart + dstSize >= 64 KB) { /* history in dstBuffer becomes large enough to become dictionary */ + dctx->dict = (const BYTE*)dstBufferStart; + dctx->dictSize = dstPtr - dstBufferStart + dstSize; return; } - if ((withinTmp) && (dctxPtr->dict == dctxPtr->tmpOutBuffer)) { - /* assumption : dctxPtr->dict + dctxPtr->dictSize == dctxPtr->tmpOut + dctxPtr->tmpOutStart */ - dctxPtr->dictSize += dstSize; + assert(dstSize < 64 KB); /* if dstSize >= 64 KB, dictionary would be set into dstBuffer directly */ + + /* dstBuffer does not contain whole useful history (64 KB), so it must be saved within tmpOut */ + + if ((withinTmp) && (dctx->dict == dctx->tmpOutBuffer)) { /* continue history within tmpOutBuffer */ + /* withinTmp expectation : content of [dstPtr,dstSize] is same as [dict+dictSize,dstSize], so we just extend it */ + assert(dctx->dict + dctx->dictSize == dctx->tmpOut + dctx->tmpOutStart); + dctx->dictSize += dstSize; return; } if (withinTmp) { /* copy relevant dict portion in front of tmpOut within tmpOutBuffer */ - size_t const preserveSize = dctxPtr->tmpOut - dctxPtr->tmpOutBuffer; - size_t copySize = 64 KB - dctxPtr->tmpOutSize; - const BYTE* const oldDictEnd = dctxPtr->dict + dctxPtr->dictSize - dctxPtr->tmpOutStart; - if (dctxPtr->tmpOutSize > 64 KB) copySize = 0; + size_t const preserveSize = dctx->tmpOut - dctx->tmpOutBuffer; + size_t copySize = 64 KB - dctx->tmpOutSize; + const BYTE* const oldDictEnd = dctx->dict + dctx->dictSize - dctx->tmpOutStart; + if (dctx->tmpOutSize > 64 KB) copySize = 0; if (copySize > preserveSize) copySize = preserveSize; - memcpy(dctxPtr->tmpOutBuffer + preserveSize - copySize, oldDictEnd - copySize, copySize); + memcpy(dctx->tmpOutBuffer + preserveSize - copySize, oldDictEnd - copySize, copySize); - dctxPtr->dict = dctxPtr->tmpOutBuffer; - dctxPtr->dictSize = preserveSize + dctxPtr->tmpOutStart + dstSize; + dctx->dict = dctx->tmpOutBuffer; + dctx->dictSize = preserveSize + dctx->tmpOutStart + dstSize; return; } - if (dctxPtr->dict == dctxPtr->tmpOutBuffer) { /* copy dst into tmp to complete dict */ - if (dctxPtr->dictSize + dstSize > dctxPtr->maxBufferSize) { /* tmp buffer not large enough */ - size_t const preserveSize = 64 KB - dstSize; /* note : dstSize < 64 KB */ - memcpy(dctxPtr->tmpOutBuffer, dctxPtr->dict + dctxPtr->dictSize - preserveSize, preserveSize); - dctxPtr->dictSize = preserveSize; + if (dctx->dict == dctx->tmpOutBuffer) { /* copy dst into tmp to complete dict */ + if (dctx->dictSize + dstSize > dctx->maxBufferSize) { /* tmp buffer not large enough */ + size_t const preserveSize = 64 KB - dstSize; + memcpy(dctx->tmpOutBuffer, dctx->dict + dctx->dictSize - preserveSize, preserveSize); + dctx->dictSize = preserveSize; } - memcpy(dctxPtr->tmpOutBuffer + dctxPtr->dictSize, dstPtr, dstSize); - dctxPtr->dictSize += dstSize; + memcpy(dctx->tmpOutBuffer + dctx->dictSize, dstPtr, dstSize); + dctx->dictSize += dstSize; return; } /* join dict & dest into tmp */ - { size_t preserveSize = 64 KB - dstSize; /* note : dstSize < 64 KB */ - if (preserveSize > dctxPtr->dictSize) preserveSize = dctxPtr->dictSize; - memcpy(dctxPtr->tmpOutBuffer, dctxPtr->dict + dctxPtr->dictSize - preserveSize, preserveSize); - memcpy(dctxPtr->tmpOutBuffer + preserveSize, dstPtr, dstSize); - dctxPtr->dict = dctxPtr->tmpOutBuffer; - dctxPtr->dictSize = preserveSize + dstSize; + { size_t preserveSize = 64 KB - dstSize; + if (preserveSize > dctx->dictSize) preserveSize = dctx->dictSize; + memcpy(dctx->tmpOutBuffer, dctx->dict + dctx->dictSize - preserveSize, preserveSize); + memcpy(dctx->tmpOutBuffer + preserveSize, dstPtr, dstSize); + dctx->dict = dctx->tmpOutBuffer; + dctx->dictSize = preserveSize + dstSize; } } /*! LZ4F_decompress() : -* Call this function repetitively to regenerate data compressed within srcBuffer. -* The function will attempt to decode up to *srcSizePtr bytes from srcBuffer, into dstBuffer of capacity *dstSizePtr. -* -* The number of bytes regenerated into dstBuffer will be provided within *dstSizePtr (necessarily <= original value). -* -* The number of bytes effectively read from srcBuffer will be provided within *srcSizePtr (necessarily <= original value). -* If the number of bytes read is < number of bytes provided, then the decompression operation is not complete. -* Remaining data will have to be presented again in a subsequent invocation. -* -* The function result is an hint of the better srcSize to use for next call to LZ4F_decompress. -* Basically, it's the size of the current (or remaining) compressed block + header of next block. -* Respecting the hint provides some boost to performance, since it allows less buffer shuffling. -* Note that this is just a hint, it's always possible to any srcSize value. -* When a frame is fully decoded, @return will be 0. -* If decompression failed, @return is an error code which can be tested using LZ4F_isError(). -*/ -size_t LZ4F_decompress(LZ4F_dctx* dctxPtr, + * Call this function repetitively to regenerate compressed data in srcBuffer. + * The function will attempt to decode up to *srcSizePtr bytes from srcBuffer + * into dstBuffer of capacity *dstSizePtr. + * + * The number of bytes regenerated into dstBuffer will be provided within *dstSizePtr (necessarily <= original value). + * + * The number of bytes effectively read from srcBuffer will be provided within *srcSizePtr (necessarily <= original value). + * If number of bytes read is < number of bytes provided, then decompression operation is not complete. + * Remaining data will have to be presented again in a subsequent invocation. + * + * The function result is an hint of the better srcSize to use for next call to LZ4F_decompress. + * Schematically, it's the size of the current (or remaining) compressed block + header of next block. + * Respecting the hint provides a small boost to performance, since it allows less buffer shuffling. + * Note that this is just a hint, and it's always possible to any srcSize value. + * When a frame is fully decoded, @return will be 0. + * If decompression failed, @return is an error code which can be tested using LZ4F_isError(). + */ +size_t LZ4F_decompress(LZ4F_dctx* dctx, void* dstBuffer, size_t* dstSizePtr, const void* srcBuffer, size_t* srcSizePtr, const LZ4F_decompressOptions_t* decompressOptionsPtr) @@ -1058,271 +1324,353 @@ size_t LZ4F_decompress(LZ4F_dctx* dctxPtr, size_t nextSrcSizeHint = 1; - memset(&optionsNull, 0, sizeof(optionsNull)); + MEM_INIT(&optionsNull, 0, sizeof(optionsNull)); if (decompressOptionsPtr==NULL) decompressOptionsPtr = &optionsNull; *srcSizePtr = 0; *dstSizePtr = 0; - /* programmed as a state machine */ + /* behaves as a state machine */ while (doAnotherStage) { - switch(dctxPtr->dStage) + switch(dctx->dStage) { - case dstage_getHeader: + case dstage_getFrameHeader: if ((size_t)(srcEnd-srcPtr) >= maxFHSize) { /* enough to decode - shortcut */ - LZ4F_errorCode_t const hSize = LZ4F_decodeHeader(dctxPtr, srcPtr, srcEnd-srcPtr); + size_t const hSize = LZ4F_decodeHeader(dctx, srcPtr, srcEnd-srcPtr); /* will update dStage appropriately */ if (LZ4F_isError(hSize)) return hSize; srcPtr += hSize; break; } - dctxPtr->tmpInSize = 0; - dctxPtr->tmpInTarget = minFHSize; /* minimum to attempt decode */ - dctxPtr->dStage = dstage_storeHeader; - /* pass-through */ - - case dstage_storeHeader: - { size_t sizeToCopy = dctxPtr->tmpInTarget - dctxPtr->tmpInSize; - if (sizeToCopy > (size_t)(srcEnd - srcPtr)) sizeToCopy = srcEnd - srcPtr; - memcpy(dctxPtr->header + dctxPtr->tmpInSize, srcPtr, sizeToCopy); - dctxPtr->tmpInSize += sizeToCopy; + dctx->tmpInSize = 0; + if (srcEnd-srcPtr == 0) return minFHSize; /* 0-size input */ + dctx->tmpInTarget = minFHSize; /* minimum size to decode header */ + dctx->dStage = dstage_storeFrameHeader; + /* fall-through */ + + case dstage_storeFrameHeader: + { size_t const sizeToCopy = MIN(dctx->tmpInTarget - dctx->tmpInSize, (size_t)(srcEnd - srcPtr)); + memcpy(dctx->header + dctx->tmpInSize, srcPtr, sizeToCopy); + dctx->tmpInSize += sizeToCopy; srcPtr += sizeToCopy; - if (dctxPtr->tmpInSize < dctxPtr->tmpInTarget) { - nextSrcSizeHint = (dctxPtr->tmpInTarget - dctxPtr->tmpInSize) + BHSize; /* rest of header + nextBlockHeader */ - doAnotherStage = 0; /* not enough src data, ask for some more */ - break; - } - { LZ4F_errorCode_t const hSize = LZ4F_decodeHeader(dctxPtr, dctxPtr->header, dctxPtr->tmpInTarget); - if (LZ4F_isError(hSize)) return hSize; - } + } + if (dctx->tmpInSize < dctx->tmpInTarget) { + nextSrcSizeHint = (dctx->tmpInTarget - dctx->tmpInSize) + BHSize; /* rest of header + nextBlockHeader */ + doAnotherStage = 0; /* not enough src data, ask for some more */ break; } + { size_t const hSize = LZ4F_decodeHeader(dctx, dctx->header, dctx->tmpInTarget); /* will update dStage appropriately */ + if (LZ4F_isError(hSize)) return hSize; + } + break; - case dstage_getCBlockSize: + case dstage_init: + if (dctx->frameInfo.contentChecksumFlag) XXH32_reset(&(dctx->xxh), 0); + /* internal buffers allocation */ + { size_t const bufferNeeded = dctx->maxBlockSize + + ((dctx->frameInfo.blockMode==LZ4F_blockLinked) * 128 KB); + if (bufferNeeded > dctx->maxBufferSize) { /* tmp buffers too small */ + dctx->maxBufferSize = 0; /* ensure allocation will be re-attempted on next entry*/ + FREEMEM(dctx->tmpIn); + dctx->tmpIn = (BYTE*)ALLOC(dctx->maxBlockSize + 4 /* block checksum */); + if (dctx->tmpIn == NULL) + return err0r(LZ4F_ERROR_allocation_failed); + FREEMEM(dctx->tmpOutBuffer); + dctx->tmpOutBuffer= (BYTE*)ALLOC(bufferNeeded); + if (dctx->tmpOutBuffer== NULL) + return err0r(LZ4F_ERROR_allocation_failed); + dctx->maxBufferSize = bufferNeeded; + } } + dctx->tmpInSize = 0; + dctx->tmpInTarget = 0; + dctx->tmpOut = dctx->tmpOutBuffer; + dctx->tmpOutStart = 0; + dctx->tmpOutSize = 0; + + dctx->dStage = dstage_getBlockHeader; + /* fall-through */ + + case dstage_getBlockHeader: if ((size_t)(srcEnd - srcPtr) >= BHSize) { selectedIn = srcPtr; srcPtr += BHSize; } else { /* not enough input to read cBlockSize field */ - dctxPtr->tmpInSize = 0; - dctxPtr->dStage = dstage_storeCBlockSize; + dctx->tmpInSize = 0; + dctx->dStage = dstage_storeBlockHeader; } - if (dctxPtr->dStage == dstage_storeCBlockSize) /* can be skipped */ - case dstage_storeCBlockSize: - { size_t sizeToCopy = BHSize - dctxPtr->tmpInSize; - if (sizeToCopy > (size_t)(srcEnd - srcPtr)) sizeToCopy = srcEnd - srcPtr; - memcpy(dctxPtr->tmpIn + dctxPtr->tmpInSize, srcPtr, sizeToCopy); + if (dctx->dStage == dstage_storeBlockHeader) /* can be skipped */ + case dstage_storeBlockHeader: + { size_t const remainingInput = (size_t)(srcEnd - srcPtr); + size_t const wantedData = BHSize - dctx->tmpInSize; + size_t const sizeToCopy = MIN(wantedData, remainingInput); + memcpy(dctx->tmpIn + dctx->tmpInSize, srcPtr, sizeToCopy); srcPtr += sizeToCopy; - dctxPtr->tmpInSize += sizeToCopy; - if (dctxPtr->tmpInSize < BHSize) { /* not enough input to get full cBlockSize; wait for more */ - nextSrcSizeHint = BHSize - dctxPtr->tmpInSize; + dctx->tmpInSize += sizeToCopy; + + if (dctx->tmpInSize < BHSize) { /* not enough input for cBlockSize */ + nextSrcSizeHint = BHSize - dctx->tmpInSize; doAnotherStage = 0; break; } - selectedIn = dctxPtr->tmpIn; - } + selectedIn = dctx->tmpIn; + } /* if (dctx->dStage == dstage_storeBlockHeader) */ - /* case dstage_decodeCBlockSize: */ /* no more direct access, to prevent scan-build warning */ + /* decode block header */ { size_t const nextCBlockSize = LZ4F_readLE32(selectedIn) & 0x7FFFFFFFU; - if (nextCBlockSize==0) { /* frameEnd signal, no more CBlock */ - dctxPtr->dStage = dstage_getSuffix; + size_t const crcSize = dctx->frameInfo.blockChecksumFlag * 4; + if (nextCBlockSize==0) { /* frameEnd signal, no more block */ + dctx->dStage = dstage_getSuffix; break; } - if (nextCBlockSize > dctxPtr->maxBlockSize) return err0r(LZ4F_ERROR_GENERIC); /* invalid cBlockSize */ - dctxPtr->tmpInTarget = nextCBlockSize; + if (nextCBlockSize > dctx->maxBlockSize) + return err0r(LZ4F_ERROR_maxBlockSize_invalid); if (LZ4F_readLE32(selectedIn) & LZ4F_BLOCKUNCOMPRESSED_FLAG) { - dctxPtr->dStage = dstage_copyDirect; + /* next block is uncompressed */ + dctx->tmpInTarget = nextCBlockSize; + if (dctx->frameInfo.blockChecksumFlag) { + XXH32_reset(&dctx->blockChecksum, 0); + } + dctx->dStage = dstage_copyDirect; break; } - dctxPtr->dStage = dstage_getCBlock; + /* next block is a compressed block */ + dctx->tmpInTarget = nextCBlockSize + crcSize; + dctx->dStage = dstage_getCBlock; if (dstPtr==dstEnd) { - nextSrcSizeHint = nextCBlockSize + BHSize; + nextSrcSizeHint = nextCBlockSize + crcSize + BHSize; doAnotherStage = 0; } break; } case dstage_copyDirect: /* uncompressed block */ - { size_t sizeToCopy = dctxPtr->tmpInTarget; - if ((size_t)(srcEnd-srcPtr) < sizeToCopy) sizeToCopy = srcEnd - srcPtr; /* not enough input to read full block */ - if ((size_t)(dstEnd-dstPtr) < sizeToCopy) sizeToCopy = dstEnd - dstPtr; + { size_t const minBuffSize = MIN((size_t)(srcEnd-srcPtr), (size_t)(dstEnd-dstPtr)); + size_t const sizeToCopy = MIN(dctx->tmpInTarget, minBuffSize); memcpy(dstPtr, srcPtr, sizeToCopy); - if (dctxPtr->frameInfo.contentChecksumFlag) XXH32_update(&(dctxPtr->xxh), srcPtr, sizeToCopy); - if (dctxPtr->frameInfo.contentSize) dctxPtr->frameRemainingSize -= sizeToCopy; + if (dctx->frameInfo.blockChecksumFlag) { + XXH32_update(&dctx->blockChecksum, srcPtr, sizeToCopy); + } + if (dctx->frameInfo.contentChecksumFlag) + XXH32_update(&dctx->xxh, srcPtr, sizeToCopy); + if (dctx->frameInfo.contentSize) + dctx->frameRemainingSize -= sizeToCopy; - /* dictionary management */ - if (dctxPtr->frameInfo.blockMode==LZ4F_blockLinked) - LZ4F_updateDict(dctxPtr, dstPtr, sizeToCopy, dstStart, 0); + /* history management (linked blocks only)*/ + if (dctx->frameInfo.blockMode == LZ4F_blockLinked) + LZ4F_updateDict(dctx, dstPtr, sizeToCopy, dstStart, 0); srcPtr += sizeToCopy; dstPtr += sizeToCopy; - if (sizeToCopy == dctxPtr->tmpInTarget) { /* all copied */ - dctxPtr->dStage = dstage_getCBlockSize; + if (sizeToCopy == dctx->tmpInTarget) { /* all done */ + if (dctx->frameInfo.blockChecksumFlag) { + dctx->tmpInSize = 0; + dctx->dStage = dstage_getBlockChecksum; + } else + dctx->dStage = dstage_getBlockHeader; /* new block */ break; } - dctxPtr->tmpInTarget -= sizeToCopy; /* still need to copy more */ - nextSrcSizeHint = dctxPtr->tmpInTarget + BHSize; + dctx->tmpInTarget -= sizeToCopy; /* need to copy more */ + nextSrcSizeHint = dctx->tmpInTarget + + + dctx->frameInfo.contentChecksumFlag * 4 /* block checksum */ + + BHSize /* next header size */; doAnotherStage = 0; break; } - case dstage_getCBlock: /* entry from dstage_decodeCBlockSize */ - if ((size_t)(srcEnd-srcPtr) < dctxPtr->tmpInTarget) { - dctxPtr->tmpInSize = 0; - dctxPtr->dStage = dstage_storeCBlock; + /* check block checksum for recently transferred uncompressed block */ + case dstage_getBlockChecksum: + { const void* crcSrc; + if ((srcEnd-srcPtr >= 4) && (dctx->tmpInSize==0)) { + crcSrc = srcPtr; + srcPtr += 4; + } else { + size_t const stillToCopy = 4 - dctx->tmpInSize; + size_t const sizeToCopy = MIN(stillToCopy, (size_t)(srcEnd-srcPtr)); + memcpy(dctx->header + dctx->tmpInSize, srcPtr, sizeToCopy); + dctx->tmpInSize += sizeToCopy; + srcPtr += sizeToCopy; + if (dctx->tmpInSize < 4) { /* all input consumed */ + doAnotherStage = 0; + break; + } + crcSrc = dctx->header; + } + { U32 const readCRC = LZ4F_readLE32(crcSrc); + U32 const calcCRC = XXH32_digest(&dctx->blockChecksum); + if (readCRC != calcCRC) + return err0r(LZ4F_ERROR_blockChecksum_invalid); + } } + dctx->dStage = dstage_getBlockHeader; /* new block */ + break; + + case dstage_getCBlock: + if ((size_t)(srcEnd-srcPtr) < dctx->tmpInTarget) { + dctx->tmpInSize = 0; + dctx->dStage = dstage_storeCBlock; break; } + /* input large enough to read full block directly */ selectedIn = srcPtr; - srcPtr += dctxPtr->tmpInTarget; - dctxPtr->dStage = dstage_decodeCBlock; - break; + srcPtr += dctx->tmpInTarget; + if (0) /* jump over next block */ case dstage_storeCBlock: - { size_t sizeToCopy = dctxPtr->tmpInTarget - dctxPtr->tmpInSize; - if (sizeToCopy > (size_t)(srcEnd-srcPtr)) sizeToCopy = srcEnd-srcPtr; - memcpy(dctxPtr->tmpIn + dctxPtr->tmpInSize, srcPtr, sizeToCopy); - dctxPtr->tmpInSize += sizeToCopy; + { size_t const wantedData = dctx->tmpInTarget - dctx->tmpInSize; + size_t const inputLeft = (size_t)(srcEnd-srcPtr); + size_t const sizeToCopy = MIN(wantedData, inputLeft); + memcpy(dctx->tmpIn + dctx->tmpInSize, srcPtr, sizeToCopy); + dctx->tmpInSize += sizeToCopy; srcPtr += sizeToCopy; - if (dctxPtr->tmpInSize < dctxPtr->tmpInTarget) { /* need more input */ - nextSrcSizeHint = (dctxPtr->tmpInTarget - dctxPtr->tmpInSize) + BHSize; + if (dctx->tmpInSize < dctx->tmpInTarget) { /* need more input */ + nextSrcSizeHint = (dctx->tmpInTarget - dctx->tmpInSize) + BHSize; doAnotherStage=0; break; } - selectedIn = dctxPtr->tmpIn; - dctxPtr->dStage = dstage_decodeCBlock; - /* pass-through */ + selectedIn = dctx->tmpIn; } - case dstage_decodeCBlock: - if ((size_t)(dstEnd-dstPtr) < dctxPtr->maxBlockSize) /* not enough place into dst : decode into tmpOut */ - dctxPtr->dStage = dstage_decodeCBlock_intoTmp; - else - dctxPtr->dStage = dstage_decodeCBlock_intoDst; - break; - - case dstage_decodeCBlock_intoDst: - { int (*decoder)(const char*, char*, int, int, const char*, int); + /* At this stage, input is large enough to decode a block */ + if (dctx->frameInfo.blockChecksumFlag) { + dctx->tmpInTarget -= 4; + assert(selectedIn != NULL); /* selectedIn is defined at this stage (either srcPtr, or dctx->tmpIn) */ + { U32 const readBlockCrc = LZ4F_readLE32(selectedIn + dctx->tmpInTarget); + U32 const calcBlockCrc = XXH32(selectedIn, dctx->tmpInTarget, 0); + if (readBlockCrc != calcBlockCrc) + return err0r(LZ4F_ERROR_blockChecksum_invalid); + } } + + if ((size_t)(dstEnd-dstPtr) >= dctx->maxBlockSize) { + const char* dict = (const char*)dctx->dict; + size_t dictSize = dctx->dictSize; int decodedSize; - - if (dctxPtr->frameInfo.blockMode == LZ4F_blockLinked) - decoder = LZ4_decompress_safe_usingDict; - else - decoder = LZ4F_decompress_safe; - - decodedSize = decoder((const char*)selectedIn, (char*)dstPtr, (int)dctxPtr->tmpInTarget, (int)dctxPtr->maxBlockSize, (const char*)dctxPtr->dict, (int)dctxPtr->dictSize); + if (dict && dictSize > 1 GB) { + /* the dictSize param is an int, avoid truncation / sign issues */ + dict += dictSize - 64 KB; + dictSize = 64 KB; + } + /* enough capacity in `dst` to decompress directly there */ + decodedSize = LZ4_decompress_safe_usingDict( + (const char*)selectedIn, (char*)dstPtr, + (int)dctx->tmpInTarget, (int)dctx->maxBlockSize, + dict, (int)dictSize); if (decodedSize < 0) return err0r(LZ4F_ERROR_GENERIC); /* decompression failed */ - if (dctxPtr->frameInfo.contentChecksumFlag) XXH32_update(&(dctxPtr->xxh), dstPtr, decodedSize); - if (dctxPtr->frameInfo.contentSize) dctxPtr->frameRemainingSize -= decodedSize; + if (dctx->frameInfo.contentChecksumFlag) + XXH32_update(&(dctx->xxh), dstPtr, decodedSize); + if (dctx->frameInfo.contentSize) + dctx->frameRemainingSize -= decodedSize; /* dictionary management */ - if (dctxPtr->frameInfo.blockMode==LZ4F_blockLinked) - LZ4F_updateDict(dctxPtr, dstPtr, decodedSize, dstStart, 0); + if (dctx->frameInfo.blockMode==LZ4F_blockLinked) + LZ4F_updateDict(dctx, dstPtr, decodedSize, dstStart, 0); dstPtr += decodedSize; - dctxPtr->dStage = dstage_getCBlockSize; + dctx->dStage = dstage_getBlockHeader; break; } - case dstage_decodeCBlock_intoTmp: /* not enough place into dst : decode into tmpOut */ - { int (*decoder)(const char*, char*, int, int, const char*, int); - int decodedSize; - - if (dctxPtr->frameInfo.blockMode == LZ4F_blockLinked) - decoder = LZ4_decompress_safe_usingDict; - else - decoder = LZ4F_decompress_safe; - - /* ensure enough place for tmpOut */ - if (dctxPtr->frameInfo.blockMode == LZ4F_blockLinked) { - if (dctxPtr->dict == dctxPtr->tmpOutBuffer) { - if (dctxPtr->dictSize > 128 KB) { - memcpy(dctxPtr->tmpOutBuffer, dctxPtr->dict + dctxPtr->dictSize - 64 KB, 64 KB); - dctxPtr->dictSize = 64 KB; - } - dctxPtr->tmpOut = dctxPtr->tmpOutBuffer + dctxPtr->dictSize; - } else { /* dict not within tmp */ - size_t reservedDictSpace = dctxPtr->dictSize; - if (reservedDictSpace > 64 KB) reservedDictSpace = 64 KB; - dctxPtr->tmpOut = dctxPtr->tmpOutBuffer + reservedDictSpace; + /* ensure enough place for tmpOut */ + if (dctx->frameInfo.blockMode == LZ4F_blockLinked) { + if (dctx->dict == dctx->tmpOutBuffer) { + if (dctx->dictSize > 128 KB) { + memcpy(dctx->tmpOutBuffer, dctx->dict + dctx->dictSize - 64 KB, 64 KB); + dctx->dictSize = 64 KB; } + dctx->tmpOut = dctx->tmpOutBuffer + dctx->dictSize; + } else { /* dict not within tmp */ + size_t const reservedDictSpace = MIN(dctx->dictSize, 64 KB); + dctx->tmpOut = dctx->tmpOutBuffer + reservedDictSpace; + } } + + /* Decode block */ + { const char* dict = (const char*)dctx->dict; + size_t dictSize = dctx->dictSize; + int decodedSize; + if (dict && dictSize > 1 GB) { + /* the dictSize param is an int, avoid truncation / sign issues */ + dict += dictSize - 64 KB; + dictSize = 64 KB; } - - /* Decode */ - decodedSize = decoder((const char*)selectedIn, (char*)dctxPtr->tmpOut, (int)dctxPtr->tmpInTarget, (int)dctxPtr->maxBlockSize, (const char*)dctxPtr->dict, (int)dctxPtr->dictSize); - if (decodedSize < 0) return err0r(LZ4F_ERROR_decompressionFailed); /* decompression failed */ - if (dctxPtr->frameInfo.contentChecksumFlag) XXH32_update(&(dctxPtr->xxh), dctxPtr->tmpOut, decodedSize); - if (dctxPtr->frameInfo.contentSize) dctxPtr->frameRemainingSize -= decodedSize; - dctxPtr->tmpOutSize = decodedSize; - dctxPtr->tmpOutStart = 0; - dctxPtr->dStage = dstage_flushOut; - break; + decodedSize = LZ4_decompress_safe_usingDict( + (const char*)selectedIn, (char*)dctx->tmpOut, + (int)dctx->tmpInTarget, (int)dctx->maxBlockSize, + dict, (int)dictSize); + if (decodedSize < 0) /* decompression failed */ + return err0r(LZ4F_ERROR_decompressionFailed); + if (dctx->frameInfo.contentChecksumFlag) + XXH32_update(&(dctx->xxh), dctx->tmpOut, decodedSize); + if (dctx->frameInfo.contentSize) + dctx->frameRemainingSize -= decodedSize; + dctx->tmpOutSize = decodedSize; + dctx->tmpOutStart = 0; + dctx->dStage = dstage_flushOut; } + /* fall-through */ case dstage_flushOut: /* flush decoded data from tmpOut to dstBuffer */ - { size_t sizeToCopy = dctxPtr->tmpOutSize - dctxPtr->tmpOutStart; - if (sizeToCopy > (size_t)(dstEnd-dstPtr)) sizeToCopy = dstEnd-dstPtr; - memcpy(dstPtr, dctxPtr->tmpOut + dctxPtr->tmpOutStart, sizeToCopy); + { size_t const sizeToCopy = MIN(dctx->tmpOutSize - dctx->tmpOutStart, (size_t)(dstEnd-dstPtr)); + memcpy(dstPtr, dctx->tmpOut + dctx->tmpOutStart, sizeToCopy); /* dictionary management */ - if (dctxPtr->frameInfo.blockMode==LZ4F_blockLinked) - LZ4F_updateDict(dctxPtr, dstPtr, sizeToCopy, dstStart, 1); + if (dctx->frameInfo.blockMode == LZ4F_blockLinked) + LZ4F_updateDict(dctx, dstPtr, sizeToCopy, dstStart, 1 /*withinTmp*/); - dctxPtr->tmpOutStart += sizeToCopy; + dctx->tmpOutStart += sizeToCopy; dstPtr += sizeToCopy; - /* end of flush ? */ - if (dctxPtr->tmpOutStart == dctxPtr->tmpOutSize) { - dctxPtr->dStage = dstage_getCBlockSize; + if (dctx->tmpOutStart == dctx->tmpOutSize) { /* all flushed */ + dctx->dStage = dstage_getBlockHeader; /* get next block */ break; } + /* could not flush everything : stop there, just request a block header */ + doAnotherStage = 0; nextSrcSizeHint = BHSize; - doAnotherStage = 0; /* still some data to flush */ break; } case dstage_getSuffix: - { size_t const suffixSize = dctxPtr->frameInfo.contentChecksumFlag * 4; - if (dctxPtr->frameRemainingSize) return err0r(LZ4F_ERROR_frameSize_wrong); /* incorrect frame size decoded */ - if (suffixSize == 0) { /* frame completed */ - nextSrcSizeHint = 0; - dctxPtr->dStage = dstage_getHeader; - doAnotherStage = 0; - break; - } - if ((srcEnd - srcPtr) < 4) { /* not enough size for entire CRC */ - dctxPtr->tmpInSize = 0; - dctxPtr->dStage = dstage_storeSuffix; - } else { - selectedIn = srcPtr; - srcPtr += 4; - } + if (dctx->frameRemainingSize) + return err0r(LZ4F_ERROR_frameSize_wrong); /* incorrect frame size decoded */ + if (!dctx->frameInfo.contentChecksumFlag) { /* no checksum, frame is completed */ + nextSrcSizeHint = 0; + LZ4F_resetDecompressionContext(dctx); + doAnotherStage = 0; + break; + } + if ((srcEnd - srcPtr) < 4) { /* not enough size for entire CRC */ + dctx->tmpInSize = 0; + dctx->dStage = dstage_storeSuffix; + } else { + selectedIn = srcPtr; + srcPtr += 4; } - if (dctxPtr->dStage == dstage_storeSuffix) /* can be skipped */ + if (dctx->dStage == dstage_storeSuffix) /* can be skipped */ case dstage_storeSuffix: - { - size_t sizeToCopy = 4 - dctxPtr->tmpInSize; - if (sizeToCopy > (size_t)(srcEnd - srcPtr)) sizeToCopy = srcEnd - srcPtr; - memcpy(dctxPtr->tmpIn + dctxPtr->tmpInSize, srcPtr, sizeToCopy); + { size_t const remainingInput = (size_t)(srcEnd - srcPtr); + size_t const wantedData = 4 - dctx->tmpInSize; + size_t const sizeToCopy = MIN(wantedData, remainingInput); + memcpy(dctx->tmpIn + dctx->tmpInSize, srcPtr, sizeToCopy); srcPtr += sizeToCopy; - dctxPtr->tmpInSize += sizeToCopy; - if (dctxPtr->tmpInSize < 4) { /* not enough input to read complete suffix */ - nextSrcSizeHint = 4 - dctxPtr->tmpInSize; + dctx->tmpInSize += sizeToCopy; + if (dctx->tmpInSize < 4) { /* not enough input to read complete suffix */ + nextSrcSizeHint = 4 - dctx->tmpInSize; doAnotherStage=0; break; } - selectedIn = dctxPtr->tmpIn; - } + selectedIn = dctx->tmpIn; + } /* if (dctx->dStage == dstage_storeSuffix) */ - /* case dstage_checkSuffix: */ /* no direct call, to avoid scan-build warning */ + /* case dstage_checkSuffix: */ /* no direct entry, avoid initialization risks */ { U32 const readCRC = LZ4F_readLE32(selectedIn); - U32 const resultCRC = XXH32_digest(&(dctxPtr->xxh)); - if (readCRC != resultCRC) return err0r(LZ4F_ERROR_contentChecksum_invalid); + U32 const resultCRC = XXH32_digest(&(dctx->xxh)); + if (readCRC != resultCRC) + return err0r(LZ4F_ERROR_contentChecksum_invalid); nextSrcSizeHint = 0; - dctxPtr->dStage = dstage_getHeader; + LZ4F_resetDecompressionContext(dctx); doAnotherStage = 0; break; } @@ -1333,77 +1681,78 @@ size_t LZ4F_decompress(LZ4F_dctx* dctxPtr, srcPtr += 4; } else { /* not enough input to read cBlockSize field */ - dctxPtr->tmpInSize = 4; - dctxPtr->tmpInTarget = 8; - dctxPtr->dStage = dstage_storeSFrameSize; + dctx->tmpInSize = 4; + dctx->tmpInTarget = 8; + dctx->dStage = dstage_storeSFrameSize; } - if (dctxPtr->dStage == dstage_storeSFrameSize) + if (dctx->dStage == dstage_storeSFrameSize) case dstage_storeSFrameSize: - { - size_t sizeToCopy = dctxPtr->tmpInTarget - dctxPtr->tmpInSize; - if (sizeToCopy > (size_t)(srcEnd - srcPtr)) sizeToCopy = srcEnd - srcPtr; - memcpy(dctxPtr->header + dctxPtr->tmpInSize, srcPtr, sizeToCopy); + { size_t const sizeToCopy = MIN(dctx->tmpInTarget - dctx->tmpInSize, + (size_t)(srcEnd - srcPtr) ); + memcpy(dctx->header + dctx->tmpInSize, srcPtr, sizeToCopy); srcPtr += sizeToCopy; - dctxPtr->tmpInSize += sizeToCopy; - if (dctxPtr->tmpInSize < dctxPtr->tmpInTarget) { /* not enough input to get full sBlockSize; wait for more */ - nextSrcSizeHint = dctxPtr->tmpInTarget - dctxPtr->tmpInSize; + dctx->tmpInSize += sizeToCopy; + if (dctx->tmpInSize < dctx->tmpInTarget) { + /* not enough input to get full sBlockSize; wait for more */ + nextSrcSizeHint = dctx->tmpInTarget - dctx->tmpInSize; doAnotherStage = 0; break; } - selectedIn = dctxPtr->header + 4; - } + selectedIn = dctx->header + 4; + } /* if (dctx->dStage == dstage_storeSFrameSize) */ - /* case dstage_decodeSFrameSize: */ /* no direct access */ + /* case dstage_decodeSFrameSize: */ /* no direct entry */ { size_t const SFrameSize = LZ4F_readLE32(selectedIn); - dctxPtr->frameInfo.contentSize = SFrameSize; - dctxPtr->tmpInTarget = SFrameSize; - dctxPtr->dStage = dstage_skipSkippable; + dctx->frameInfo.contentSize = SFrameSize; + dctx->tmpInTarget = SFrameSize; + dctx->dStage = dstage_skipSkippable; break; } case dstage_skipSkippable: - { size_t skipSize = dctxPtr->tmpInTarget; - if (skipSize > (size_t)(srcEnd-srcPtr)) skipSize = srcEnd-srcPtr; + { size_t const skipSize = MIN(dctx->tmpInTarget, (size_t)(srcEnd-srcPtr)); srcPtr += skipSize; - dctxPtr->tmpInTarget -= skipSize; + dctx->tmpInTarget -= skipSize; doAnotherStage = 0; - nextSrcSizeHint = dctxPtr->tmpInTarget; - if (nextSrcSizeHint) break; - dctxPtr->dStage = dstage_getHeader; + nextSrcSizeHint = dctx->tmpInTarget; + if (nextSrcSizeHint) break; /* still more to skip */ + /* frame fully skipped : prepare context for a new frame */ + LZ4F_resetDecompressionContext(dctx); break; } - } - } - - /* preserve dictionary within tmp if necessary */ - if ( (dctxPtr->frameInfo.blockMode==LZ4F_blockLinked) - &&(dctxPtr->dict != dctxPtr->tmpOutBuffer) - &&(!decompressOptionsPtr->stableDst) - &&((unsigned)(dctxPtr->dStage-1) < (unsigned)(dstage_getSuffix-1)) - ) + } /* switch (dctx->dStage) */ + } /* while (doAnotherStage) */ + + /* preserve history within tmp whenever necessary */ + LZ4F_STATIC_ASSERT((unsigned)dstage_init == 2); + if ( (dctx->frameInfo.blockMode==LZ4F_blockLinked) /* next block will use up to 64KB from previous ones */ + && (dctx->dict != dctx->tmpOutBuffer) /* dictionary is not already within tmp */ + && (!decompressOptionsPtr->stableDst) /* cannot rely on dst data to remain there for next call */ + && ((unsigned)(dctx->dStage)-2 < (unsigned)(dstage_getSuffix)-2) ) /* valid stages : [init ... getSuffix[ */ { - if (dctxPtr->dStage == dstage_flushOut) { - size_t preserveSize = dctxPtr->tmpOut - dctxPtr->tmpOutBuffer; - size_t copySize = 64 KB - dctxPtr->tmpOutSize; - const BYTE* oldDictEnd = dctxPtr->dict + dctxPtr->dictSize - dctxPtr->tmpOutStart; - if (dctxPtr->tmpOutSize > 64 KB) copySize = 0; + if (dctx->dStage == dstage_flushOut) { + size_t const preserveSize = dctx->tmpOut - dctx->tmpOutBuffer; + size_t copySize = 64 KB - dctx->tmpOutSize; + const BYTE* oldDictEnd = dctx->dict + dctx->dictSize - dctx->tmpOutStart; + if (dctx->tmpOutSize > 64 KB) copySize = 0; if (copySize > preserveSize) copySize = preserveSize; - memcpy(dctxPtr->tmpOutBuffer + preserveSize - copySize, oldDictEnd - copySize, copySize); + if (copySize > 0) + memcpy(dctx->tmpOutBuffer + preserveSize - copySize, oldDictEnd - copySize, copySize); - dctxPtr->dict = dctxPtr->tmpOutBuffer; - dctxPtr->dictSize = preserveSize + dctxPtr->tmpOutStart; + dctx->dict = dctx->tmpOutBuffer; + dctx->dictSize = preserveSize + dctx->tmpOutStart; } else { - size_t newDictSize = dctxPtr->dictSize; - const BYTE* oldDictEnd = dctxPtr->dict + dctxPtr->dictSize; - if ((newDictSize) > 64 KB) newDictSize = 64 KB; + const BYTE* const oldDictEnd = dctx->dict + dctx->dictSize; + size_t const newDictSize = MIN(dctx->dictSize, 64 KB); - memcpy(dctxPtr->tmpOutBuffer, oldDictEnd - newDictSize, newDictSize); + if (newDictSize > 0) + memcpy(dctx->tmpOutBuffer, oldDictEnd - newDictSize, newDictSize); - dctxPtr->dict = dctxPtr->tmpOutBuffer; - dctxPtr->dictSize = newDictSize; - dctxPtr->tmpOut = dctxPtr->tmpOutBuffer + newDictSize; + dctx->dict = dctx->tmpOutBuffer; + dctx->dictSize = newDictSize; + dctx->tmpOut = dctx->tmpOutBuffer + newDictSize; } } @@ -1411,3 +1760,23 @@ size_t LZ4F_decompress(LZ4F_dctx* dctxPtr, *dstSizePtr = (dstPtr - dstStart); return nextSrcSizeHint; } + +/*! LZ4F_decompress_usingDict() : + * Same as LZ4F_decompress(), using a predefined dictionary. + * Dictionary is used "in place", without any preprocessing. + * It must remain accessible throughout the entire frame decoding. + */ +size_t LZ4F_decompress_usingDict(LZ4F_dctx* dctx, + void* dstBuffer, size_t* dstSizePtr, + const void* srcBuffer, size_t* srcSizePtr, + const void* dict, size_t dictSize, + const LZ4F_decompressOptions_t* decompressOptionsPtr) +{ + if (dctx->dStage <= dstage_init) { + dctx->dict = (const BYTE*)dict; + dctx->dictSize = dictSize; + } + return LZ4F_decompress(dctx, dstBuffer, dstSizePtr, + srcBuffer, srcSizePtr, + decompressOptionsPtr); +} diff --git a/lib/lz4frame.h b/lib/lz4frame.h index a4a4ce65..75f1fd91 100644 --- a/lib/lz4frame.h +++ b/lib/lz4frame.h @@ -1,7 +1,7 @@ /* LZ4 auto-framing library Header File - Copyright (C) 2011-2016, Yann Collet. + Copyright (C) 2011-2017, 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 @@ -33,9 +33,10 @@ */ /* LZ4F is a stand-alone API to create LZ4-compressed frames - * conformant with specification v1.5.1. + * conformant with specification v1.6.1. * It also offers streaming capabilities. - * lz4.h is not required when using lz4frame.h. + * lz4.h is not required when using lz4frame.h, + * except to get constant such as LZ4_VERSION_NUMBER. * */ #ifndef LZ4F_H_09782039843 @@ -48,49 +49,68 @@ extern "C" { /* --- Dependency --- */ #include <stddef.h> /* size_t */ -/*-*************************************************************** -* Compiler specifics -*****************************************************************/ -/*! -* LZ4_DLL_EXPORT : -* Enable exporting of functions when building a Windows DLL + +/** + Introduction + + lz4frame.h implements LZ4 frame specification (doc/lz4_Frame_format.md). + lz4frame.h provides frame compression functions that take care + of encoding standard metadata alongside LZ4-compressed blocks. */ + +/*-*************************************************************** + * Compiler specifics + *****************************************************************/ +/* LZ4_DLL_EXPORT : + * Enable exporting of functions when building a Windows DLL + * LZ4FLIB_API : + * Control library symbols visibility. + */ #if defined(LZ4_DLL_EXPORT) && (LZ4_DLL_EXPORT==1) # define LZ4FLIB_API __declspec(dllexport) #elif defined(LZ4_DLL_IMPORT) && (LZ4_DLL_IMPORT==1) # define LZ4FLIB_API __declspec(dllimport) +#elif defined(__GNUC__) && (__GNUC__ >= 4) +# define LZ4FLIB_API __attribute__ ((__visibility__ ("default"))) #else # define LZ4FLIB_API #endif -#if defined(_MSC_VER) -# define LZ4F_DEPRECATE(x) x /* __declspec(deprecated) x - only works with C++ */ -#elif defined(__clang__) || (defined(__GNUC__) && (__GNUC__ >= 6)) -# define LZ4F_DEPRECATE(x) x __attribute__((deprecated)) +#ifdef LZ4F_DISABLE_DEPRECATE_WARNINGS +# define LZ4F_DEPRECATE(x) x #else -# define LZ4F_DEPRECATE(x) x /* no deprecation warning for this compiler */ +# if defined(_MSC_VER) +# define LZ4F_DEPRECATE(x) x /* __declspec(deprecated) x - only works with C++ */ +# elif defined(__clang__) || (defined(__GNUC__) && (__GNUC__ >= 6)) +# define LZ4F_DEPRECATE(x) x __attribute__((deprecated)) +# else +# define LZ4F_DEPRECATE(x) x /* no deprecation warning for this compiler */ +# endif #endif /*-************************************ -* Error management -**************************************/ + * Error management + **************************************/ typedef size_t LZ4F_errorCode_t; -LZ4FLIB_API unsigned LZ4F_isError(LZ4F_errorCode_t code); -LZ4FLIB_API const char* LZ4F_getErrorName(LZ4F_errorCode_t code); /* return error code string; useful for debugging */ +LZ4FLIB_API unsigned LZ4F_isError(LZ4F_errorCode_t code); /**< tells when a function result is an error code */ +LZ4FLIB_API const char* LZ4F_getErrorName(LZ4F_errorCode_t code); /**< return error code string; for debugging */ /*-************************************ -* Frame compression types -**************************************/ -/* #define LZ4F_DISABLE_OBSOLETE_ENUMS */ /* uncomment to disable obsolete enums */ -#ifndef LZ4F_DISABLE_OBSOLETE_ENUMS + * Frame compression types + **************************************/ +/* #define LZ4F_ENABLE_OBSOLETE_ENUMS // uncomment to enable obsolete enums */ +#ifdef LZ4F_ENABLE_OBSOLETE_ENUMS # define LZ4F_OBSOLETE_ENUM(x) , LZ4F_DEPRECATE(x) = LZ4F_##x #else # define LZ4F_OBSOLETE_ENUM(x) #endif +/* The larger the block size, the (slightly) better the compression ratio, + * though there are diminishing returns. + * Larger blocks also increase memory usage on both compression and decompression sides. */ typedef enum { LZ4F_default=0, LZ4F_max64KB=4, @@ -103,6 +123,9 @@ typedef enum { LZ4F_OBSOLETE_ENUM(max4MB) } LZ4F_blockSizeID_t; +/* Linked blocks sharply reduce inefficiencies when using small blocks, + * they compress better. + * However, some LZ4 decoders are only compatible with independent blocks */ typedef enum { LZ4F_blockLinked=0, LZ4F_blockIndependent @@ -118,63 +141,80 @@ typedef enum { } LZ4F_contentChecksum_t; typedef enum { + LZ4F_noBlockChecksum=0, + LZ4F_blockChecksumEnabled +} LZ4F_blockChecksum_t; + +typedef enum { LZ4F_frame=0, LZ4F_skippableFrame LZ4F_OBSOLETE_ENUM(skippableFrame) } LZ4F_frameType_t; -#ifndef LZ4F_DISABLE_OBSOLETE_ENUMS +#ifdef LZ4F_ENABLE_OBSOLETE_ENUMS typedef LZ4F_blockSizeID_t blockSizeID_t; typedef LZ4F_blockMode_t blockMode_t; typedef LZ4F_frameType_t frameType_t; typedef LZ4F_contentChecksum_t contentChecksum_t; #endif -/* LZ4F_frameInfo_t : - * makes it possible to supply detailed frame parameters to the stream interface. - * It's not required to set all fields, as long as the structure was initially memset() to zero. - * All reserved fields must be set to zero. */ +/*! LZ4F_frameInfo_t : + * makes it possible to set or read frame parameters. + * Structure must be first init to 0, using memset() or LZ4F_INIT_FRAMEINFO, + * setting all parameters to default. + * It's then possible to update selectively some parameters */ typedef struct { - LZ4F_blockSizeID_t blockSizeID; /* max64KB, max256KB, max1MB, max4MB ; 0 == default */ - LZ4F_blockMode_t blockMode; /* blockLinked, blockIndependent ; 0 == default */ - LZ4F_contentChecksum_t contentChecksumFlag; /* noContentChecksum, contentChecksumEnabled ; 0 == default */ - LZ4F_frameType_t frameType; /* LZ4F_frame, skippableFrame ; 0 == default */ - unsigned long long contentSize; /* Size of uncompressed (original) content ; 0 == unknown */ - unsigned reserved[2]; /* must be zero for forward compatibility */ + LZ4F_blockSizeID_t blockSizeID; /* max64KB, max256KB, max1MB, max4MB; 0 == default */ + LZ4F_blockMode_t blockMode; /* LZ4F_blockLinked, LZ4F_blockIndependent; 0 == default */ + LZ4F_contentChecksum_t contentChecksumFlag; /* 1: frame terminated with 32-bit checksum of decompressed data; 0: disabled (default) */ + LZ4F_frameType_t frameType; /* read-only field : LZ4F_frame or LZ4F_skippableFrame */ + unsigned long long contentSize; /* Size of uncompressed content ; 0 == unknown */ + unsigned dictID; /* Dictionary ID, sent by compressor to help decoder select correct dictionary; 0 == no dictID provided */ + LZ4F_blockChecksum_t blockChecksumFlag; /* 1: each block followed by a checksum of block's compressed data; 0: disabled (default) */ } LZ4F_frameInfo_t; -/* LZ4F_preferences_t : - * makes it possible to supply detailed compression parameters to the stream interface. - * It's not required to set all fields, as long as the structure was initially memset() to zero. - * All reserved fields must be set to zero. */ +#define LZ4F_INIT_FRAMEINFO { 0, 0, 0, 0, 0, 0, 0 } /* v1.8.3+ */ + +/*! LZ4F_preferences_t : + * makes it possible to supply advanced compression instructions to streaming interface. + * Structure must be first init to 0, using memset() or LZ4F_INIT_PREFERENCES, + * setting all parameters to default. + * All reserved fields must be set to zero. */ typedef struct { LZ4F_frameInfo_t frameInfo; - int compressionLevel; /* 0 == default (fast mode); values above 16 count as 16; values below 0 count as 0 */ - unsigned autoFlush; /* 1 == always flush (reduce usage of tmp buffer) */ - unsigned reserved[4]; /* must be zero for forward compatibility */ + int compressionLevel; /* 0: default (fast mode); values > LZ4HC_CLEVEL_MAX count as LZ4HC_CLEVEL_MAX; values < 0 trigger "fast acceleration" */ + unsigned autoFlush; /* 1: always flush; reduces usage of internal buffers */ + unsigned favorDecSpeed; /* 1: parser favors decompression speed vs compression ratio. Only works for high compression modes (>= LZ4HC_CLEVEL_OPT_MIN) */ /* v1.8.2+ */ + unsigned reserved[3]; /* must be zero for forward compatibility */ } LZ4F_preferences_t; +#define LZ4F_INIT_PREFERENCES { LZ4F_INIT_FRAMEINFO, 0, 0, 0, { 0, 0, 0 } } /* v1.8.3+ */ + /*-********************************* * Simple compression function ***********************************/ -/*!LZ4F_compressFrameBound() : - * Returns the maximum possible size of a frame compressed with LZ4F_compressFrame() given srcSize content and preferences. - * Note : this result is only usable with LZ4F_compressFrame(), not with multi-segments compression. + +LZ4FLIB_API int LZ4F_compressionLevel_max(void); + +/*! LZ4F_compressFrameBound() : + * Returns the maximum possible compressed size with LZ4F_compressFrame() given srcSize and preferences. + * `preferencesPtr` is optional. It can be replaced by NULL, in which case, the function will assume default preferences. + * Note : this result is only usable with LZ4F_compressFrame(). + * It may also be used with LZ4F_compressUpdate() _if no flush() operation_ is performed. */ LZ4FLIB_API size_t LZ4F_compressFrameBound(size_t srcSize, const LZ4F_preferences_t* preferencesPtr); -/*!LZ4F_compressFrame() : - * Compress an entire srcBuffer into a valid LZ4 frame, as defined by specification v1.5.1 - * An important rule is that dstBuffer MUST be large enough (dstCapacity) to store the result in worst case situation. - * This value is supplied by LZ4F_compressFrameBound(). - * If this condition is not respected, LZ4F_compressFrame() will fail (result is an errorCode). - * The LZ4F_preferences_t structure is optional : you can provide NULL as argument. All preferences will be set to default. +/*! LZ4F_compressFrame() : + * Compress an entire srcBuffer into a valid LZ4 frame. + * dstCapacity MUST be >= LZ4F_compressFrameBound(srcSize, preferencesPtr). + * The LZ4F_preferences_t structure is optional : you can provide NULL as argument. All preferences will be set to default. * @return : number of bytes written into dstBuffer. * or an error code if it fails (can be tested using LZ4F_isError()) */ -LZ4FLIB_API size_t LZ4F_compressFrame(void* dstBuffer, size_t dstCapacity, const void* srcBuffer, size_t srcSize, const LZ4F_preferences_t* preferencesPtr); - +LZ4FLIB_API size_t LZ4F_compressFrame(void* dstBuffer, size_t dstCapacity, + const void* srcBuffer, size_t srcSize, + const LZ4F_preferences_t* preferencesPtr); /*-*********************************** @@ -188,74 +228,90 @@ typedef struct { unsigned reserved[3]; } LZ4F_compressOptions_t; -/* Resource Management */ +/*--- Resource Management ---*/ -#define LZ4F_VERSION 100 +#define LZ4F_VERSION 100 /* This number can be used to check for an incompatible API breaking change */ LZ4FLIB_API unsigned LZ4F_getVersion(void); -LZ4FLIB_API LZ4F_errorCode_t LZ4F_createCompressionContext(LZ4F_cctx** cctxPtr, unsigned version); -LZ4FLIB_API LZ4F_errorCode_t LZ4F_freeCompressionContext(LZ4F_cctx* cctx); -/* LZ4F_createCompressionContext() : + +/*! LZ4F_createCompressionContext() : * The first thing to do is to create a compressionContext object, which will be used in all compression operations. - * This is achieved using LZ4F_createCompressionContext(), which takes as argument a version and an LZ4F_preferences_t structure. + * This is achieved using LZ4F_createCompressionContext(), which takes as argument a version. * The version provided MUST be LZ4F_VERSION. It is intended to track potential version mismatch, notably when using DLL. * The function will provide a pointer to a fully allocated LZ4F_cctx object. * If @return != zero, there was an error during context creation. * Object can release its memory using LZ4F_freeCompressionContext(); */ +LZ4FLIB_API LZ4F_errorCode_t LZ4F_createCompressionContext(LZ4F_cctx** cctxPtr, unsigned version); +LZ4FLIB_API LZ4F_errorCode_t LZ4F_freeCompressionContext(LZ4F_cctx* cctx); -/* Compression */ +/*---- Compression ----*/ -#define LZ4F_HEADER_SIZE_MAX 15 -LZ4FLIB_API size_t LZ4F_compressBegin(LZ4F_cctx* cctx, void* dstBuffer, size_t dstCapacity, const LZ4F_preferences_t* prefsPtr); -/* LZ4F_compressBegin() : - * will write the frame header into dstBuffer. - * dstCapacity must be large enough to store the header. Maximum header size is LZ4F_HEADER_SIZE_MAX bytes. +#define LZ4F_HEADER_SIZE_MAX 19 /* LZ4 Frame header size can vary from 7 to 19 bytes */ +/*! LZ4F_compressBegin() : + * will write the frame header into dstBuffer. + * dstCapacity must be >= LZ4F_HEADER_SIZE_MAX bytes. * `prefsPtr` is optional : you can provide NULL as argument, all preferences will then be set to default. * @return : number of bytes written into dstBuffer for the header * or an error code (which can be tested using LZ4F_isError()) */ - -LZ4FLIB_API size_t LZ4F_compressBound(size_t srcSize, const LZ4F_preferences_t* prefsPtr); -/* LZ4F_compressBound() : - * Provides dstCapacity given a srcSize to guarantee operation success in worst case situations. - * prefsPtr is optional : you can provide NULL as argument, preferences will be set to cover worst case scenario. - * Result is always the same for a srcSize and prefsPtr, so it can be trusted to size reusable buffers. - * When srcSize==0, LZ4F_compressBound() provides an upper bound for LZ4F_flush() and LZ4F_compressEnd() operations. +LZ4FLIB_API size_t LZ4F_compressBegin(LZ4F_cctx* cctx, + void* dstBuffer, size_t dstCapacity, + const LZ4F_preferences_t* prefsPtr); + +/*! LZ4F_compressBound() : + * Provides minimum dstCapacity required to guarantee compression success + * given a srcSize and preferences, covering worst case scenario. + * prefsPtr is optional : when NULL is provided, preferences will be set to cover worst case scenario. + * Estimation is valid for either LZ4F_compressUpdate(), LZ4F_flush() or LZ4F_compressEnd(), + * Estimation includes the possibility that internal buffer might already be filled by up to (blockSize-1) bytes. + * It also includes frame footer (ending + checksum), which would have to be generated by LZ4F_compressEnd(). + * Estimation doesn't include frame header, as it was already generated by LZ4F_compressBegin(). + * Result is always the same for a srcSize and prefsPtr, so it can be trusted to size reusable buffers. + * When srcSize==0, LZ4F_compressBound() provides an upper bound for LZ4F_flush() and LZ4F_compressEnd() operations. */ +LZ4FLIB_API size_t LZ4F_compressBound(size_t srcSize, const LZ4F_preferences_t* prefsPtr); -LZ4FLIB_API size_t LZ4F_compressUpdate(LZ4F_cctx* cctx, void* dstBuffer, size_t dstCapacity, const void* srcBuffer, size_t srcSize, const LZ4F_compressOptions_t* cOptPtr); -/* LZ4F_compressUpdate() : - * LZ4F_compressUpdate() can be called repetitively to compress as much data as necessary. - * An important rule is that dstCapacity MUST be large enough to ensure operation success even in worst case situations. - * This value is provided by LZ4F_compressBound(). - * If this condition is not respected, LZ4F_compress() will fail (result is an errorCode). - * LZ4F_compressUpdate() doesn't guarantee error recovery. When an error occurs, compression context must be freed or resized. +/*! LZ4F_compressUpdate() : + * LZ4F_compressUpdate() can be called repetitively to compress as much data as necessary. + * Important rule: dstCapacity MUST be large enough to ensure operation success even in worst case situations. + * This value is provided by LZ4F_compressBound(). + * If this condition is not respected, LZ4F_compress() will fail (result is an errorCode). + * LZ4F_compressUpdate() doesn't guarantee error recovery. + * When an error occurs, compression context must be freed or resized. * `cOptPtr` is optional : NULL can be provided, in which case all options are set to default. * @return : number of bytes written into `dstBuffer` (it can be zero, meaning input data was just buffered). * or an error code if it fails (which can be tested using LZ4F_isError()) */ - -LZ4FLIB_API size_t LZ4F_flush(LZ4F_cctx* cctx, void* dstBuffer, size_t dstCapacity, const LZ4F_compressOptions_t* cOptPtr); -/* LZ4F_flush() : - * When data must be generated and sent immediately, without waiting for a block to be completely filled, - * it's possible to call LZ4_flush(). It will immediately compress any data buffered within cctx. +LZ4FLIB_API size_t LZ4F_compressUpdate(LZ4F_cctx* cctx, + void* dstBuffer, size_t dstCapacity, + const void* srcBuffer, size_t srcSize, + const LZ4F_compressOptions_t* cOptPtr); + +/*! LZ4F_flush() : + * When data must be generated and sent immediately, without waiting for a block to be completely filled, + * it's possible to call LZ4_flush(). It will immediately compress any data buffered within cctx. * `dstCapacity` must be large enough to ensure the operation will be successful. * `cOptPtr` is optional : it's possible to provide NULL, all options will be set to default. - * @return : number of bytes written into dstBuffer (it can be zero, which means there was no data stored within cctx) + * @return : nb of bytes written into dstBuffer (can be zero, when there is no data stored within cctx) * or an error code if it fails (which can be tested using LZ4F_isError()) */ - -LZ4FLIB_API size_t LZ4F_compressEnd(LZ4F_cctx* cctx, void* dstBuffer, size_t dstCapacity, const LZ4F_compressOptions_t* cOptPtr); -/* LZ4F_compressEnd() : - * To properly finish an LZ4 frame, invoke LZ4F_compressEnd(). - * It will flush whatever data remained within `cctx` (like LZ4_flush()) - * and properly finalize the frame, with an endMark and a checksum. +LZ4FLIB_API size_t LZ4F_flush(LZ4F_cctx* cctx, + void* dstBuffer, size_t dstCapacity, + const LZ4F_compressOptions_t* cOptPtr); + +/*! LZ4F_compressEnd() : + * To properly finish an LZ4 frame, invoke LZ4F_compressEnd(). + * It will flush whatever data remained within `cctx` (like LZ4_flush()) + * and properly finalize the frame, with an endMark and a checksum. * `cOptPtr` is optional : NULL can be provided, in which case all options will be set to default. - * @return : number of bytes written into dstBuffer (necessarily >= 4 (endMark), or 8 if optional frame checksum is enabled) + * @return : nb of bytes written into dstBuffer, necessarily >= 4 (endMark), * or an error code if it fails (which can be tested using LZ4F_isError()) - * A successful call to LZ4F_compressEnd() makes `cctx` available again for another compression task. + * A successful call to LZ4F_compressEnd() makes `cctx` available again for another compression task. */ +LZ4FLIB_API size_t LZ4F_compressEnd(LZ4F_cctx* cctx, + void* dstBuffer, size_t dstCapacity, + const LZ4F_compressOptions_t* cOptPtr); /*-********************************* @@ -265,66 +321,83 @@ typedef struct LZ4F_dctx_s LZ4F_dctx; /* incomplete type */ typedef LZ4F_dctx* LZ4F_decompressionContext_t; /* compatibility with previous API versions */ typedef struct { - unsigned stableDst; /* guarantee that decompressed data will still be there on next function calls (avoid storage into tmp buffers) */ - unsigned reserved[3]; + unsigned stableDst; /* pledges that last 64KB decompressed data will remain available unmodified. This optimization skips storage operations in tmp buffers. */ + unsigned reserved[3]; /* must be set to zero for forward compatibility */ } LZ4F_decompressOptions_t; /* Resource management */ -/*!LZ4F_createDecompressionContext() : - * Create an LZ4F_decompressionContext_t object, which will be used to track all decompression operations. - * The version provided MUST be LZ4F_VERSION. It is intended to track potential breaking differences between different versions. - * The function will provide a pointer to a fully allocated and initialized LZ4F_decompressionContext_t object. - * The result is an errorCode, which can be tested using LZ4F_isError(). - * dctx memory can be released using LZ4F_freeDecompressionContext(); - * The result of LZ4F_freeDecompressionContext() is indicative of the current state of decompressionContext when being released. - * That is, it should be == 0 if decompression has been completed fully and correctly. +/*! LZ4F_createDecompressionContext() : + * Create an LZ4F_dctx object, to track all decompression operations. + * The version provided MUST be LZ4F_VERSION. + * The function provides a pointer to an allocated and initialized LZ4F_dctx object. + * The result is an errorCode, which can be tested using LZ4F_isError(). + * dctx memory can be released using LZ4F_freeDecompressionContext(); + * Result of LZ4F_freeDecompressionContext() indicates current state of decompressionContext when being released. + * That is, it should be == 0 if decompression has been completed fully and correctly. */ LZ4FLIB_API LZ4F_errorCode_t LZ4F_createDecompressionContext(LZ4F_dctx** dctxPtr, unsigned version); -LZ4FLIB_API LZ4F_errorCode_t LZ4F_freeDecompressionContext(LZ4F_dctx* const dctx); +LZ4FLIB_API LZ4F_errorCode_t LZ4F_freeDecompressionContext(LZ4F_dctx* dctx); -/*====== Decompression ======*/ +/*-*********************************** +* Streaming decompression functions +*************************************/ -/*!LZ4F_getFrameInfo() : - * This function decodes frame header information (such as max blockSize, frame checksum, etc.). - * Its usage is optional. The objective is to extract frame header information, typically for allocation purposes. - * A header size is variable and can length from 7 to 15 bytes. It's possible to provide more input bytes than that. - * The number of bytes consumed from srcBuffer will be updated within *srcSizePtr (necessarily <= original value). - * Decompression must resume from this point (srcBuffer + *srcSizePtr). - * Note that LZ4F_getFrameInfo() can also be used anytime *after* decompression is started, in which case 0 input byte can be enough. - * Frame header info is *copied into* an already allocated LZ4F_frameInfo_t structure. +/*! LZ4F_getFrameInfo() : + * This function extracts frame parameters (max blockSize, dictID, etc.). + * Its usage is optional. + * Extracted information is typically useful for allocation and dictionary. + * This function works in 2 situations : + * - At the beginning of a new frame, in which case + * it will decode information from `srcBuffer`, starting the decoding process. + * Input size must be large enough to successfully decode the entire frame header. + * Frame header size is variable, but is guaranteed to be <= LZ4F_HEADER_SIZE_MAX bytes. + * It's allowed to provide more input data than this minimum. + * - After decoding has been started. + * In which case, no input is read, frame parameters are extracted from dctx. + * - If decoding has barely started, but not yet extracted information from header, + * LZ4F_getFrameInfo() will fail. + * The number of bytes consumed from srcBuffer will be updated within *srcSizePtr (necessarily <= original value). + * Decompression must resume from (srcBuffer + *srcSizePtr). * @return : an hint about how many srcSize bytes LZ4F_decompress() expects for next call, - * or an error code which can be tested using LZ4F_isError() - * (typically, when there is not enough src bytes to fully decode the frame header) + * or an error code which can be tested using LZ4F_isError(). + * note 1 : in case of error, dctx is not modified. Decoding operation can resume from beginning safely. + * note 2 : frame parameters are *copied into* an already allocated LZ4F_frameInfo_t structure. */ LZ4FLIB_API size_t LZ4F_getFrameInfo(LZ4F_dctx* dctx, LZ4F_frameInfo_t* frameInfoPtr, const void* srcBuffer, size_t* srcSizePtr); -/*!LZ4F_decompress() : - * Call this function repetitively to regenerate data compressed within `srcBuffer`. - * The function will attempt to decode up to *srcSizePtr bytes from srcBuffer, into dstBuffer of capacity *dstSizePtr. +/*! LZ4F_decompress() : + * Call this function repetitively to regenerate compressed data from `srcBuffer`. + * The function will read up to *srcSizePtr bytes from srcBuffer, + * and decompress data into dstBuffer, of capacity *dstSizePtr. + * + * The nb of bytes consumed from srcBuffer will be written into *srcSizePtr (necessarily <= original value). + * The nb of bytes decompressed into dstBuffer will be written into *dstSizePtr (necessarily <= original value). * - * The number of bytes regenerated into dstBuffer will be provided within *dstSizePtr (necessarily <= original value). + * The function does not necessarily read all input bytes, so always check value in *srcSizePtr. + * Unconsumed source data must be presented again in subsequent invocations. * - * The number of bytes read from srcBuffer will be provided within *srcSizePtr (necessarily <= original value). - * Number of bytes read can be < number of bytes provided, meaning there is some more data to decode. - * It typically happens when dstBuffer is not large enough to contain all decoded data. - * Remaining data will have to be presented again in a subsequent invocation. + * `dstBuffer` can freely change between each consecutive function invocation. + * `dstBuffer` content will be overwritten. * - * `dstBuffer` content is expected to be flushed between each invocation, as its content will be overwritten. - * `dstBuffer` can be changed at will between each consecutive function invocation. + * @return : an hint of how many `srcSize` bytes LZ4F_decompress() expects for next call. + * Schematically, it's the size of the current (or remaining) compressed block + header of next block. + * Respecting the hint provides some small speed benefit, because it skips intermediate buffers. + * This is just a hint though, it's always possible to provide any srcSize. * - * @return is an hint of how many `srcSize` bytes LZ4F_decompress() expects for next call. - * Schematically, it's the size of the current (or remaining) compressed block + header of next block. - * Respecting the hint provides some boost to performance, since it does skip intermediate buffers. - * This is just a hint though, it's always possible to provide any srcSize. - * When a frame is fully decoded, @return will be 0 (no more data expected). - * If decompression failed, @return is an error code, which can be tested using LZ4F_isError(). + * When a frame is fully decoded, @return will be 0 (no more data expected). + * When provided with more bytes than necessary to decode a frame, + * LZ4F_decompress() will stop reading exactly at end of current frame, and @return 0. * - * After a frame is fully decoded, dctx can be used again to decompress another frame. + * If decompression failed, @return is an error code, which can be tested using LZ4F_isError(). + * After a decompression error, the `dctx` context is not resumable. + * Use LZ4F_resetDecompressionContext() to return to clean state. + * + * After a frame is fully decoded, dctx can be used again to decompress another frame. */ LZ4FLIB_API size_t LZ4F_decompress(LZ4F_dctx* dctx, void* dstBuffer, size_t* dstSizePtr, @@ -332,9 +405,137 @@ LZ4FLIB_API size_t LZ4F_decompress(LZ4F_dctx* dctx, const LZ4F_decompressOptions_t* dOptPtr); +/*! LZ4F_resetDecompressionContext() : added in v1.8.0 + * In case of an error, the context is left in "undefined" state. + * In which case, it's necessary to reset it, before re-using it. + * This method can also be used to abruptly stop any unfinished decompression, + * and start a new one using same context resources. */ +LZ4FLIB_API void LZ4F_resetDecompressionContext(LZ4F_dctx* dctx); /* always successful */ + + #if defined (__cplusplus) } #endif #endif /* LZ4F_H_09782039843 */ + +#if defined(LZ4F_STATIC_LINKING_ONLY) && !defined(LZ4F_H_STATIC_09782039843) +#define LZ4F_H_STATIC_09782039843 + +#if defined (__cplusplus) +extern "C" { +#endif + +/* These declarations are not stable and may change in the future. They are + * therefore only safe to depend on when the caller is statically linked + * against the library. To access their declarations, define + * LZ4F_STATIC_LINKING_ONLY. + * + * There is a further protection mechanism where these symbols aren't published + * into shared/dynamic libraries. You can override this behavior and force + * them to be published by defining LZ4F_PUBLISH_STATIC_FUNCTIONS. Use at + * your own risk. + */ +#ifdef LZ4F_PUBLISH_STATIC_FUNCTIONS +#define LZ4FLIB_STATIC_API LZ4FLIB_API +#else +#define LZ4FLIB_STATIC_API +#endif + + +/* --- Error List --- */ +#define LZ4F_LIST_ERRORS(ITEM) \ + ITEM(OK_NoError) \ + ITEM(ERROR_GENERIC) \ + ITEM(ERROR_maxBlockSize_invalid) \ + ITEM(ERROR_blockMode_invalid) \ + ITEM(ERROR_contentChecksumFlag_invalid) \ + ITEM(ERROR_compressionLevel_invalid) \ + ITEM(ERROR_headerVersion_wrong) \ + ITEM(ERROR_blockChecksum_invalid) \ + ITEM(ERROR_reservedFlag_set) \ + ITEM(ERROR_allocation_failed) \ + ITEM(ERROR_srcSize_tooLarge) \ + ITEM(ERROR_dstMaxSize_tooSmall) \ + ITEM(ERROR_frameHeader_incomplete) \ + ITEM(ERROR_frameType_unknown) \ + ITEM(ERROR_frameSize_wrong) \ + ITEM(ERROR_srcPtr_wrong) \ + ITEM(ERROR_decompressionFailed) \ + ITEM(ERROR_headerChecksum_invalid) \ + ITEM(ERROR_contentChecksum_invalid) \ + ITEM(ERROR_frameDecoding_alreadyStarted) \ + ITEM(ERROR_maxCode) + +#define LZ4F_GENERATE_ENUM(ENUM) LZ4F_##ENUM, + +/* enum list is exposed, to handle specific errors */ +typedef enum { LZ4F_LIST_ERRORS(LZ4F_GENERATE_ENUM) } LZ4F_errorCodes; + +LZ4FLIB_STATIC_API LZ4F_errorCodes LZ4F_getErrorCode(size_t functionResult); + + + +/********************************** + * Bulk processing dictionary API + *********************************/ +typedef struct LZ4F_CDict_s LZ4F_CDict; + +/*! LZ4_createCDict() : + * When compressing multiple messages / blocks with the same dictionary, it's recommended to load it just once. + * LZ4_createCDict() will create a digested dictionary, ready to start future compression operations without startup delay. + * LZ4_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only. + * `dictBuffer` can be released after LZ4_CDict creation, since its content is copied within CDict */ +LZ4FLIB_STATIC_API LZ4F_CDict* LZ4F_createCDict(const void* dictBuffer, size_t dictSize); +LZ4FLIB_STATIC_API void LZ4F_freeCDict(LZ4F_CDict* CDict); + + +/*! LZ4_compressFrame_usingCDict() : + * Compress an entire srcBuffer into a valid LZ4 frame using a digested Dictionary. + * cctx must point to a context created by LZ4F_createCompressionContext(). + * If cdict==NULL, compress without a dictionary. + * dstBuffer MUST be >= LZ4F_compressFrameBound(srcSize, preferencesPtr). + * If this condition is not respected, function will fail (@return an errorCode). + * The LZ4F_preferences_t structure is optional : you may provide NULL as argument, + * but it's not recommended, as it's the only way to provide dictID in the frame header. + * @return : number of bytes written into dstBuffer. + * or an error code if it fails (can be tested using LZ4F_isError()) */ +LZ4FLIB_STATIC_API size_t LZ4F_compressFrame_usingCDict( + LZ4F_cctx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const LZ4F_CDict* cdict, + const LZ4F_preferences_t* preferencesPtr); + + +/*! LZ4F_compressBegin_usingCDict() : + * Inits streaming dictionary compression, and writes the frame header into dstBuffer. + * dstCapacity must be >= LZ4F_HEADER_SIZE_MAX bytes. + * `prefsPtr` is optional : you may provide NULL as argument, + * however, it's the only way to provide dictID in the frame header. + * @return : number of bytes written into dstBuffer for the header, + * or an error code (which can be tested using LZ4F_isError()) */ +LZ4FLIB_STATIC_API size_t LZ4F_compressBegin_usingCDict( + LZ4F_cctx* cctx, + void* dstBuffer, size_t dstCapacity, + const LZ4F_CDict* cdict, + const LZ4F_preferences_t* prefsPtr); + + +/*! LZ4F_decompress_usingDict() : + * Same as LZ4F_decompress(), using a predefined dictionary. + * Dictionary is used "in place", without any preprocessing. + * It must remain accessible throughout the entire frame decoding. */ +LZ4FLIB_STATIC_API size_t LZ4F_decompress_usingDict( + LZ4F_dctx* dctxPtr, + void* dstBuffer, size_t* dstSizePtr, + const void* srcBuffer, size_t* srcSizePtr, + const void* dict, size_t dictSize, + const LZ4F_decompressOptions_t* decompressOptionsPtr); + +#if defined (__cplusplus) +} +#endif + +#endif /* defined(LZ4F_STATIC_LINKING_ONLY) && !defined(LZ4F_H_STATIC_09782039843) */ diff --git a/lib/lz4frame_static.h b/lib/lz4frame_static.h index f2228a5b..925a2c5c 100644 --- a/lib/lz4frame_static.h +++ b/lib/lz4frame_static.h @@ -36,47 +36,12 @@ #ifndef LZ4FRAME_STATIC_H_0398209384 #define LZ4FRAME_STATIC_H_0398209384 -#if defined (__cplusplus) -extern "C" { -#endif +/* The declarations that formerly were made here have been merged into + * lz4frame.h, protected by the LZ4F_STATIC_LINKING_ONLY macro. Going forward, + * it is recommended to simply include that header directly. + */ -/* lz4frame_static.h should be used solely in the context of static linking. - * It contains definitions which are not stable and may change in the future. - * Never use it in the context of DLL linking. - * */ - - -/* --- Dependency --- */ +#define LZ4F_STATIC_LINKING_ONLY #include "lz4frame.h" - -/* --- Error List --- */ -#define LZ4F_LIST_ERRORS(ITEM) \ - ITEM(OK_NoError) ITEM(ERROR_GENERIC) \ - ITEM(ERROR_maxBlockSize_invalid) ITEM(ERROR_blockMode_invalid) ITEM(ERROR_contentChecksumFlag_invalid) \ - ITEM(ERROR_compressionLevel_invalid) \ - ITEM(ERROR_headerVersion_wrong) ITEM(ERROR_blockChecksum_unsupported) ITEM(ERROR_reservedFlag_set) \ - ITEM(ERROR_allocation_failed) \ - ITEM(ERROR_srcSize_tooLarge) ITEM(ERROR_dstMaxSize_tooSmall) \ - ITEM(ERROR_frameHeader_incomplete) ITEM(ERROR_frameType_unknown) ITEM(ERROR_frameSize_wrong) \ - ITEM(ERROR_srcPtr_wrong) \ - ITEM(ERROR_decompressionFailed) \ - ITEM(ERROR_headerChecksum_invalid) ITEM(ERROR_contentChecksum_invalid) \ - ITEM(ERROR_maxCode) - -#define LZ4F_DISABLE_OLD_ENUMS /* comment to enable deprecated enums */ -#ifndef LZ4F_DISABLE_OLD_ENUMS -# define LZ4F_GENERATE_ENUM(ENUM) LZ4F_##ENUM, ENUM = LZ4F_##ENUM, -#else -# define LZ4F_GENERATE_ENUM(ENUM) LZ4F_##ENUM, -#endif -typedef enum { LZ4F_LIST_ERRORS(LZ4F_GENERATE_ENUM) } LZ4F_errorCodes; /* enum is exposed, to handle specific errors; compare function result to -enum value */ - -LZ4F_errorCodes LZ4F_getErrorCode(size_t functionResult); - - -#if defined (__cplusplus) -} -#endif - #endif /* LZ4FRAME_STATIC_H_0398209384 */ diff --git a/lib/lz4hc.c b/lib/lz4hc.c index 5d4ea3e6..e913ee7b 100644 --- a/lib/lz4hc.c +++ b/lib/lz4hc.c @@ -1,6 +1,6 @@ /* LZ4 HC - High Compression Mode of LZ4 - Copyright (C) 2011-2016, Yann Collet. + Copyright (C) 2011-2017, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -38,77 +38,79 @@ * Tuning Parameter ***************************************/ -/*! - * HEAPMODE : - * Select how default compression function will allocate workplace memory, - * in stack (0:fastest), or in heap (1:requires malloc()). - * Since workplace is rather large, heap mode is recommended. +/*! HEAPMODE : + * Select how default compression function will allocate workplace memory, + * in stack (0:fastest), or in heap (1:requires malloc()). + * Since workplace is rather large, heap mode is recommended. */ #ifndef LZ4HC_HEAPMODE # define LZ4HC_HEAPMODE 1 #endif -/* ************************************* -* Dependency -***************************************/ +/*=== Dependency ===*/ +#define LZ4_HC_STATIC_LINKING_ONLY #include "lz4hc.h" -/* ************************************* -* Local Compiler Options -***************************************/ +/*=== Common LZ4 definitions ===*/ #if defined(__GNUC__) # pragma GCC diagnostic ignored "-Wunused-function" #endif - #if defined (__clang__) # pragma clang diagnostic ignored "-Wunused-function" #endif - -/* ************************************* -* Common LZ4 definition -***************************************/ #define LZ4_COMMONDEFS_ONLY -#include "lz4.c" +#include "lz4.c" /* LZ4_count, constants, mem */ -/* ************************************* -* Local Constants -***************************************/ +/*=== Constants ===*/ #define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH) +#define LZ4_OPT_NUM (1<<12) -/************************************** -* Local Macros -**************************************/ -#define HASH_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH*8)-LZ4HC_HASH_LOG)) -#define DELTANEXTMAXD(p) chainTable[(p) & LZ4HC_MAXD_MASK] /* flexible, LZ4HC_MAXD dependent */ -#define DELTANEXTU16(p) chainTable[(U16)(p)] /* faster */ +/*=== Macros ===*/ +#define MIN(a,b) ( (a) < (b) ? (a) : (b) ) +#define MAX(a,b) ( (a) > (b) ? (a) : (b) ) +#define HASH_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH*8)-LZ4HC_HASH_LOG)) +#define DELTANEXTMAXD(p) chainTable[(p) & LZ4HC_MAXD_MASK] /* flexible, LZ4HC_MAXD dependent */ +#define DELTANEXTU16(table, pos) table[(U16)(pos)] /* faster */ static U32 LZ4HC_hashPtr(const void* ptr) { return HASH_FUNCTION(LZ4_read32(ptr)); } +/*=== Enums ===*/ +typedef enum { noDictCtx, usingDictCtx } dictCtx_directive; /************************************** * HC Compression **************************************/ -static void LZ4HC_init (LZ4HC_CCtx_internal* hc4, const BYTE* start) +static void LZ4HC_clearTables (LZ4HC_CCtx_internal* hc4) { MEM_INIT((void*)hc4->hashTable, 0, sizeof(hc4->hashTable)); MEM_INIT(hc4->chainTable, 0xFF, sizeof(hc4->chainTable)); - hc4->nextToUpdate = 64 KB; - hc4->base = start - 64 KB; +} + +static void LZ4HC_init (LZ4HC_CCtx_internal* hc4, const BYTE* start) +{ + uptrval startingOffset = hc4->end - hc4->base; + if (startingOffset > 1 GB) { + LZ4HC_clearTables(hc4); + startingOffset = 0; + } + startingOffset += 64 KB; + hc4->nextToUpdate = (U32) startingOffset; + hc4->base = start - startingOffset; hc4->end = start; - hc4->dictBase = start - 64 KB; - hc4->dictLimit = 64 KB; - hc4->lowLimit = 64 KB; + hc4->dictBase = start - startingOffset; + hc4->dictLimit = (U32) startingOffset; + hc4->lowLimit = (U32) startingOffset; } /* Update chains up to ip (excluded) */ -FORCE_INLINE void LZ4HC_Insert (LZ4HC_CCtx_internal* hc4, const BYTE* ip) +LZ4_FORCE_INLINE void LZ4HC_Insert (LZ4HC_CCtx_internal* hc4, const BYTE* ip) { U16* const chainTable = hc4->chainTable; U32* const hashTable = hc4->hashTable; @@ -120,7 +122,7 @@ FORCE_INLINE void LZ4HC_Insert (LZ4HC_CCtx_internal* hc4, const BYTE* ip) U32 const h = LZ4HC_hashPtr(base+idx); size_t delta = idx - hashTable[h]; if (delta>MAX_DISTANCE) delta = MAX_DISTANCE; - DELTANEXTU16(idx) = (U16)delta; + DELTANEXTU16(chainTable, idx) = (U16)delta; hashTable[h] = idx; idx++; } @@ -128,56 +130,80 @@ FORCE_INLINE void LZ4HC_Insert (LZ4HC_CCtx_internal* hc4, const BYTE* ip) hc4->nextToUpdate = target; } - -FORCE_INLINE int LZ4HC_InsertAndFindBestMatch (LZ4HC_CCtx_internal* hc4, /* Index table will be updated */ - const BYTE* ip, const BYTE* const iLimit, - const BYTE** matchpos, - const int maxNbAttempts) +/** LZ4HC_countBack() : + * @return : negative value, nb of common bytes before ip/match */ +LZ4_FORCE_INLINE +int LZ4HC_countBack(const BYTE* const ip, const BYTE* const match, + const BYTE* const iMin, const BYTE* const mMin) { - U16* const chainTable = hc4->chainTable; - U32* const HashTable = hc4->hashTable; - const BYTE* const base = hc4->base; - const BYTE* const dictBase = hc4->dictBase; - const U32 dictLimit = hc4->dictLimit; - const U32 lowLimit = (hc4->lowLimit + 64 KB > (U32)(ip-base)) ? hc4->lowLimit : (U32)(ip - base) - (64 KB - 1); - U32 matchIndex; - int nbAttempts=maxNbAttempts; - size_t ml=0; + int back = 0; + int const min = (int)MAX(iMin - ip, mMin - match); + assert(min <= 0); + assert(ip >= iMin); assert((size_t)(ip-iMin) < (1U<<31)); + assert(match >= mMin); assert((size_t)(match - mMin) < (1U<<31)); + while ( (back > min) + && (ip[back-1] == match[back-1]) ) + back--; + return back; +} - /* HC4 match finder */ - LZ4HC_Insert(hc4, ip); - matchIndex = HashTable[LZ4HC_hashPtr(ip)]; +/* LZ4HC_countPattern() : + * pattern32 must be a sample of repetitive pattern of length 1, 2 or 4 (but not 3!) */ +static unsigned +LZ4HC_countPattern(const BYTE* ip, const BYTE* const iEnd, U32 const pattern32) +{ + const BYTE* const iStart = ip; + reg_t const pattern = (sizeof(pattern)==8) ? (reg_t)pattern32 + (((reg_t)pattern32) << 32) : pattern32; + + while (likely(ip < iEnd-(sizeof(pattern)-1))) { + reg_t const diff = LZ4_read_ARCH(ip) ^ pattern; + if (!diff) { ip+=sizeof(pattern); continue; } + ip += LZ4_NbCommonBytes(diff); + return (unsigned)(ip - iStart); + } - while ((matchIndex>=lowLimit) && (nbAttempts)) { - nbAttempts--; - if (matchIndex >= dictLimit) { - const BYTE* const match = base + matchIndex; - if (*(match+ml) == *(ip+ml) - && (LZ4_read32(match) == LZ4_read32(ip))) - { - size_t const mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, iLimit) + MINMATCH; - if (mlt > ml) { ml = mlt; *matchpos = match; } - } - } else { - const BYTE* const match = dictBase + matchIndex; - if (LZ4_read32(match) == LZ4_read32(ip)) { - size_t mlt; - const BYTE* vLimit = ip + (dictLimit - matchIndex); - if (vLimit > iLimit) vLimit = iLimit; - mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, vLimit) + MINMATCH; - if ((ip+mlt == vLimit) && (vLimit < iLimit)) - mlt += LZ4_count(ip+mlt, base+dictLimit, iLimit); - if (mlt > ml) { ml = mlt; *matchpos = base + matchIndex; } /* virtual matchpos */ - } + if (LZ4_isLittleEndian()) { + reg_t patternByte = pattern; + while ((ip<iEnd) && (*ip == (BYTE)patternByte)) { + ip++; patternByte >>= 8; + } + } else { /* big endian */ + U32 bitOffset = (sizeof(pattern)*8) - 8; + while (ip < iEnd) { + BYTE const byte = (BYTE)(pattern >> bitOffset); + if (*ip != byte) break; + ip ++; bitOffset -= 8; } - matchIndex -= DELTANEXTU16(matchIndex); } - return (int)ml; + return (unsigned)(ip - iStart); +} + +/* LZ4HC_reverseCountPattern() : + * pattern must be a sample of repetitive pattern of length 1, 2 or 4 (but not 3!) + * read using natural platform endianess */ +static unsigned +LZ4HC_reverseCountPattern(const BYTE* ip, const BYTE* const iLow, U32 pattern) +{ + const BYTE* const iStart = ip; + + while (likely(ip >= iLow+4)) { + if (LZ4_read32(ip-4) != pattern) break; + ip -= 4; + } + { const BYTE* bytePtr = (const BYTE*)(&pattern) + 3; /* works for any endianess */ + while (likely(ip>iLow)) { + if (ip[-1] != *bytePtr) break; + ip--; bytePtr--; + } } + return (unsigned)(iStart - ip); } +typedef enum { rep_untested, rep_not, rep_confirmed } repeat_state_e; +typedef enum { favorCompressionRatio=0, favorDecompressionSpeed } HCfavor_e; -FORCE_INLINE int LZ4HC_InsertAndGetWiderMatch ( +LZ4_FORCE_INLINE int +LZ4HC_InsertAndGetWiderMatch ( LZ4HC_CCtx_internal* hc4, const BYTE* const ip, const BYTE* const iLowLimit, @@ -185,114 +211,259 @@ FORCE_INLINE int LZ4HC_InsertAndGetWiderMatch ( int longest, const BYTE** matchpos, const BYTE** startpos, - const int maxNbAttempts) + const int maxNbAttempts, + const int patternAnalysis, + const int chainSwap, + const dictCtx_directive dict, + const HCfavor_e favorDecSpeed) { U16* const chainTable = hc4->chainTable; U32* const HashTable = hc4->hashTable; + const LZ4HC_CCtx_internal * const dictCtx = hc4->dictCtx; const BYTE* const base = hc4->base; const U32 dictLimit = hc4->dictLimit; const BYTE* const lowPrefixPtr = base + dictLimit; - const U32 lowLimit = (hc4->lowLimit + 64 KB > (U32)(ip-base)) ? hc4->lowLimit : (U32)(ip - base) - (64 KB - 1); + const U32 ipIndex = (U32)(ip - base); + const U32 lowestMatchIndex = (hc4->lowLimit + 64 KB > ipIndex) ? hc4->lowLimit : ipIndex - MAX_DISTANCE; const BYTE* const dictBase = hc4->dictBase; - U32 matchIndex; + int const lookBackLength = (int)(ip-iLowLimit); int nbAttempts = maxNbAttempts; - int delta = (int)(ip-iLowLimit); - + int matchChainPos = 0; + U32 const pattern = LZ4_read32(ip); + U32 matchIndex; + U32 dictMatchIndex; + repeat_state_e repeat = rep_untested; + size_t srcPatternLength = 0; + DEBUGLOG(7, "LZ4HC_InsertAndGetWiderMatch"); /* First Match */ LZ4HC_Insert(hc4, ip); matchIndex = HashTable[LZ4HC_hashPtr(ip)]; + DEBUGLOG(7, "First match at index %u / %u (lowestMatchIndex)", + matchIndex, lowestMatchIndex); - while ((matchIndex>=lowLimit) && (nbAttempts)) { + while ((matchIndex>=lowestMatchIndex) && (nbAttempts)) { + int matchLength=0; nbAttempts--; - if (matchIndex >= dictLimit) { - const BYTE* matchPtr = base + matchIndex; - if (*(iLowLimit + longest) == *(matchPtr - delta + longest)) { - if (LZ4_read32(matchPtr) == LZ4_read32(ip)) { - int mlt = MINMATCH + LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, iHighLimit); - int back = 0; - - while ((ip+back > iLowLimit) - && (matchPtr+back > lowPrefixPtr) - && (ip[back-1] == matchPtr[back-1])) - back--; - - mlt -= back; - - if (mlt > longest) { - longest = (int)mlt; - *matchpos = matchPtr+back; - *startpos = ip+back; - } - } - } - } else { + assert(matchIndex < ipIndex); + if (favorDecSpeed && (ipIndex - matchIndex < 8)) { + /* do nothing */ + } else if (matchIndex >= dictLimit) { /* within current Prefix */ + const BYTE* const matchPtr = base + matchIndex; + assert(matchPtr >= lowPrefixPtr); + assert(matchPtr < ip); + assert(longest >= 1); + if (LZ4_read16(iLowLimit + longest - 1) == LZ4_read16(matchPtr - lookBackLength + longest - 1)) { + if (LZ4_read32(matchPtr) == pattern) { + int const back = lookBackLength ? LZ4HC_countBack(ip, matchPtr, iLowLimit, lowPrefixPtr) : 0; + matchLength = MINMATCH + LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, iHighLimit); + matchLength -= back; + if (matchLength > longest) { + longest = matchLength; + *matchpos = matchPtr + back; + *startpos = ip + back; + } } } + } else { /* lowestMatchIndex <= matchIndex < dictLimit */ const BYTE* const matchPtr = dictBase + matchIndex; - if (LZ4_read32(matchPtr) == LZ4_read32(ip)) { - size_t mlt; - int back=0; + if (LZ4_read32(matchPtr) == pattern) { + const BYTE* const dictStart = dictBase + hc4->lowLimit; + int back = 0; const BYTE* vLimit = ip + (dictLimit - matchIndex); if (vLimit > iHighLimit) vLimit = iHighLimit; + matchLength = LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, vLimit) + MINMATCH; + if ((ip+matchLength == vLimit) && (vLimit < iHighLimit)) + matchLength += LZ4_count(ip+matchLength, lowPrefixPtr, iHighLimit); + back = lookBackLength ? LZ4HC_countBack(ip, matchPtr, iLowLimit, dictStart) : 0; + matchLength -= back; + if (matchLength > longest) { + longest = matchLength; + *matchpos = base + matchIndex + back; /* virtual pos, relative to ip, to retrieve offset */ + *startpos = ip + back; + } } } + + if (chainSwap && matchLength==longest) { /* better match => select a better chain */ + assert(lookBackLength==0); /* search forward only */ + if (matchIndex + longest <= ipIndex) { + U32 distanceToNextMatch = 1; + int pos; + for (pos = 0; pos <= longest - MINMATCH; pos++) { + U32 const candidateDist = DELTANEXTU16(chainTable, matchIndex + pos); + if (candidateDist > distanceToNextMatch) { + distanceToNextMatch = candidateDist; + matchChainPos = pos; + } } + if (distanceToNextMatch > 1) { + if (distanceToNextMatch > matchIndex) break; /* avoid overflow */ + matchIndex -= distanceToNextMatch; + continue; + } } } + + { U32 const distNextMatch = DELTANEXTU16(chainTable, matchIndex); + if (patternAnalysis && distNextMatch==1 && matchChainPos==0) { + U32 const matchCandidateIdx = matchIndex-1; + /* may be a repeated pattern */ + if (repeat == rep_untested) { + if ( ((pattern & 0xFFFF) == (pattern >> 16)) + & ((pattern & 0xFF) == (pattern >> 24)) ) { + repeat = rep_confirmed; + srcPatternLength = LZ4HC_countPattern(ip+sizeof(pattern), iHighLimit, pattern) + sizeof(pattern); + } else { + repeat = rep_not; + } } + if ( (repeat == rep_confirmed) + && (matchCandidateIdx >= dictLimit) ) { /* same segment only */ + const BYTE* const matchPtr = base + matchCandidateIdx; + if (LZ4_read32(matchPtr) == pattern) { /* good candidate */ + size_t const forwardPatternLength = LZ4HC_countPattern(matchPtr+sizeof(pattern), iHighLimit, pattern) + sizeof(pattern); + const BYTE* const lowestMatchPtr = (lowPrefixPtr + MAX_DISTANCE >= ip) ? lowPrefixPtr : ip - MAX_DISTANCE; + size_t const backLength = LZ4HC_reverseCountPattern(matchPtr, lowestMatchPtr, pattern); + size_t const currentSegmentLength = backLength + forwardPatternLength; + + if ( (currentSegmentLength >= srcPatternLength) /* current pattern segment large enough to contain full srcPatternLength */ + && (forwardPatternLength <= srcPatternLength) ) { /* haven't reached this position yet */ + matchIndex = matchCandidateIdx + (U32)forwardPatternLength - (U32)srcPatternLength; /* best position, full pattern, might be followed by more match */ + } else { + matchIndex = matchCandidateIdx - (U32)backLength; /* farthest position in current segment, will find a match of length currentSegmentLength + maybe some back */ + if (lookBackLength==0) { /* no back possible */ + size_t const maxML = MIN(currentSegmentLength, srcPatternLength); + if ((size_t)longest < maxML) { + assert(base + matchIndex < ip); + if (ip - (base+matchIndex) > MAX_DISTANCE) break; + assert(maxML < 2 GB); + longest = (int)maxML; + *matchpos = base + matchIndex; /* virtual pos, relative to ip, to retrieve offset */ + *startpos = ip; + } + { U32 const distToNextPattern = DELTANEXTU16(chainTable, matchIndex); + if (distToNextPattern > matchIndex) break; /* avoid overflow */ + matchIndex -= distToNextPattern; + } } } + continue; + } } + } } /* PA optimization */ + + /* follow current chain */ + matchIndex -= DELTANEXTU16(chainTable, matchIndex+matchChainPos); + + } /* while ((matchIndex>=lowestMatchIndex) && (nbAttempts)) */ + + if (dict == usingDictCtx && nbAttempts && ipIndex - lowestMatchIndex < MAX_DISTANCE) { + size_t const dictEndOffset = dictCtx->end - dictCtx->base; + assert(dictEndOffset <= 1 GB); + dictMatchIndex = dictCtx->hashTable[LZ4HC_hashPtr(ip)]; + matchIndex = dictMatchIndex + lowestMatchIndex - (U32)dictEndOffset; + while (ipIndex - matchIndex <= MAX_DISTANCE && nbAttempts--) { + const BYTE* const matchPtr = dictCtx->base + dictMatchIndex; + + if (LZ4_read32(matchPtr) == pattern) { + int mlt; + int back = 0; + const BYTE* vLimit = ip + (dictEndOffset - dictMatchIndex); + if (vLimit > iHighLimit) vLimit = iHighLimit; mlt = LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, vLimit) + MINMATCH; - if ((ip+mlt == vLimit) && (vLimit < iHighLimit)) - mlt += LZ4_count(ip+mlt, base+dictLimit, iHighLimit); - while ((ip+back > iLowLimit) && (matchIndex+back > lowLimit) && (ip[back-1] == matchPtr[back-1])) back--; + back = lookBackLength ? LZ4HC_countBack(ip, matchPtr, iLowLimit, dictCtx->base + dictCtx->dictLimit) : 0; mlt -= back; - if ((int)mlt > longest) { longest = (int)mlt; *matchpos = base + matchIndex + back; *startpos = ip+back; } + if (mlt > longest) { + longest = mlt; + *matchpos = base + matchIndex + back; + *startpos = ip + back; + } + } + + { U32 const nextOffset = DELTANEXTU16(dictCtx->chainTable, dictMatchIndex); + dictMatchIndex -= nextOffset; + matchIndex -= nextOffset; } } - matchIndex -= DELTANEXTU16(matchIndex); } return longest; } +LZ4_FORCE_INLINE +int LZ4HC_InsertAndFindBestMatch(LZ4HC_CCtx_internal* const hc4, /* Index table will be updated */ + const BYTE* const ip, const BYTE* const iLimit, + const BYTE** matchpos, + const int maxNbAttempts, + const int patternAnalysis, + const dictCtx_directive dict) +{ + const BYTE* uselessPtr = ip; + /* note : LZ4HC_InsertAndGetWiderMatch() is able to modify the starting position of a match (*startpos), + * but this won't be the case here, as we define iLowLimit==ip, + * so LZ4HC_InsertAndGetWiderMatch() won't be allowed to search past ip */ + return LZ4HC_InsertAndGetWiderMatch(hc4, ip, ip, iLimit, MINMATCH-1, matchpos, &uselessPtr, maxNbAttempts, patternAnalysis, 0 /*chainSwap*/, dict, favorCompressionRatio); +} -typedef enum { noLimit = 0, limitedOutput = 1 } limitedOutput_directive; -#define LZ4HC_DEBUG 0 -#if LZ4HC_DEBUG -static unsigned debug = 0; -#endif -FORCE_INLINE int LZ4HC_encodeSequence ( +typedef enum { + noLimit = 0, + limitedOutput = 1, + limitedDestSize = 2, +} limitedOutput_directive; + +/* LZ4HC_encodeSequence() : + * @return : 0 if ok, + * 1 if buffer issue detected */ +LZ4_FORCE_INLINE int LZ4HC_encodeSequence ( const BYTE** ip, BYTE** op, const BYTE** anchor, int matchLength, const BYTE* const match, - limitedOutput_directive limitedOutputBuffer, + limitedOutput_directive limit, BYTE* oend) { - int length; - BYTE* token; - -#if LZ4HC_DEBUG - if (debug) printf("literal : %u -- match : %u -- offset : %u\n", (U32)(*ip - *anchor), (U32)matchLength, (U32)(*ip-match)); + size_t length; + BYTE* const token = (*op)++; + +#if defined(LZ4_DEBUG) && (LZ4_DEBUG >= 6) + static const BYTE* start = NULL; + static U32 totalCost = 0; + U32 const pos = (start==NULL) ? 0 : (U32)(*anchor - start); + U32 const ll = (U32)(*ip - *anchor); + U32 const llAdd = (ll>=15) ? ((ll-15) / 255) + 1 : 0; + U32 const mlAdd = (matchLength>=19) ? ((matchLength-19) / 255) + 1 : 0; + U32 const cost = 1 + llAdd + ll + 2 + mlAdd; + if (start==NULL) start = *anchor; /* only works for single segment */ + /* g_debuglog_enable = (pos >= 2228) & (pos <= 2262); */ + DEBUGLOG(6, "pos:%7u -- literals:%3u, match:%4i, offset:%5u, cost:%3u + %u", + pos, + (U32)(*ip - *anchor), matchLength, (U32)(*ip-match), + cost, totalCost); + totalCost += cost; #endif /* Encode Literal length */ - length = (int)(*ip - *anchor); - token = (*op)++; - if ((limitedOutputBuffer) && ((*op + (length>>8) + length + (2 + 1 + LASTLITERALS)) > oend)) return 1; /* Check output limit */ - if (length>=(int)RUN_MASK) { int len; *token=(RUN_MASK<<ML_BITS); len = length-RUN_MASK; for(; len > 254 ; len-=255) *(*op)++ = 255; *(*op)++ = (BYTE)len; } - else *token = (BYTE)(length<<ML_BITS); + length = (size_t)(*ip - *anchor); + if ((limit) && ((*op + (length >> 8) + length + (2 + 1 + LASTLITERALS)) > oend)) return 1; /* Check output limit */ + if (length >= RUN_MASK) { + size_t len = length - RUN_MASK; + *token = (RUN_MASK << ML_BITS); + for(; len >= 255 ; len -= 255) *(*op)++ = 255; + *(*op)++ = (BYTE)len; + } else { + *token = (BYTE)(length << ML_BITS); + } /* Copy Literals */ LZ4_wildCopy(*op, *anchor, (*op) + length); *op += length; /* Encode Offset */ + assert( (*ip - match) <= MAX_DISTANCE ); /* note : consider providing offset as a value, rather than as a pointer difference */ LZ4_writeLE16(*op, (U16)(*ip-match)); *op += 2; /* Encode MatchLength */ - length = (int)(matchLength-MINMATCH); - if ((limitedOutputBuffer) && (*op + (length>>8) + (1 + LASTLITERALS) > oend)) return 1; /* Check output limit */ - if (length>=(int)ML_MASK) { + assert(matchLength >= MINMATCH); + length = (size_t)(matchLength - MINMATCH); + if ((limit) && (*op + (length >> 8) + (1 + LASTLITERALS) > oend)) return 1; /* Check output limit */ + if (length >= ML_MASK) { *token += ML_MASK; length -= ML_MASK; - for(; length > 509 ; length-=510) { *(*op)++ = 255; *(*op)++ = 255; } - if (length > 254) { length-=255; *(*op)++ = 255; } + for(; length >= 510 ; length -= 510) { *(*op)++ = 255; *(*op)++ = 255; } + if (length >= 255) { length -= 255; *(*op)++ = 255; } *(*op)++ = (BYTE)length; } else { *token += (BYTE)(length); @@ -305,68 +476,71 @@ FORCE_INLINE int LZ4HC_encodeSequence ( return 0; } -#include "lz4opt.h" - -static int LZ4HC_compress_hashChain ( +LZ4_FORCE_INLINE int LZ4HC_compress_hashChain ( LZ4HC_CCtx_internal* const ctx, const char* const source, char* const dest, - int const inputSize, + int* srcSizePtr, int const maxOutputSize, unsigned maxNbAttempts, - limitedOutput_directive limit + const limitedOutput_directive limit, + const dictCtx_directive dict ) { + const int inputSize = *srcSizePtr; + const int patternAnalysis = (maxNbAttempts > 128); /* levels 9+ */ + const BYTE* ip = (const BYTE*) source; const BYTE* anchor = ip; const BYTE* const iend = ip + inputSize; const BYTE* const mflimit = iend - MFLIMIT; const BYTE* const matchlimit = (iend - LASTLITERALS); + BYTE* optr = (BYTE*) dest; BYTE* op = (BYTE*) dest; - BYTE* const oend = op + maxOutputSize; + BYTE* oend = op + maxOutputSize; - int ml, ml2, ml3, ml0; + int ml0, ml, ml2, ml3; + const BYTE* start0; + const BYTE* ref0; const BYTE* ref = NULL; const BYTE* start2 = NULL; const BYTE* ref2 = NULL; const BYTE* start3 = NULL; const BYTE* ref3 = NULL; - const BYTE* start0; - const BYTE* ref0; /* init */ - ctx->end += inputSize; - - ip++; + *srcSizePtr = 0; + if (limit == limitedDestSize) oend -= LASTLITERALS; /* Hack for support LZ4 format restriction */ + if (inputSize < LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ /* Main Loop */ - while (ip < mflimit) { - ml = LZ4HC_InsertAndFindBestMatch (ctx, ip, matchlimit, (&ref), maxNbAttempts); - if (!ml) { ip++; continue; } + while (ip <= mflimit) { + ml = LZ4HC_InsertAndFindBestMatch (ctx, ip, matchlimit, &ref, maxNbAttempts, patternAnalysis, dict); + if (ml<MINMATCH) { ip++; continue; } /* saved, in case we would skip too much */ - start0 = ip; - ref0 = ref; - ml0 = ml; + start0 = ip; ref0 = ref; ml0 = ml; _Search2: - if (ip+ml < mflimit) - ml2 = LZ4HC_InsertAndGetWiderMatch(ctx, ip + ml - 2, ip + 0, matchlimit, ml, &ref2, &start2, maxNbAttempts); - else ml2 = ml; + if (ip+ml <= mflimit) { + ml2 = LZ4HC_InsertAndGetWiderMatch(ctx, + ip + ml - 2, ip + 0, matchlimit, ml, &ref2, &start2, + maxNbAttempts, patternAnalysis, 0, dict, favorCompressionRatio); + } else { + ml2 = ml; + } - if (ml2 == ml) { /* No better match */ - if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0; + if (ml2 == ml) { /* No better match => encode ML1 */ + optr = op; + if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) goto _dest_overflow; continue; } - if (start0 < ip) { - if (start2 < ip + ml0) { /* empirical */ - ip = start0; - ref = ref0; - ml = ml0; - } - } + if (start0 < ip) { /* first match was skipped at least once */ + if (start2 < ip + ml0) { /* squeezing ML1 between ML0(original ML1) and ML2 */ + ip = start0; ref = ref0; ml = ml0; /* restore initial ML1 */ + } } /* Here, start0==ip */ if ((start2 - ip) < 3) { /* First Match too small : removed */ @@ -377,11 +551,9 @@ _Search2: } _Search3: - /* - * Currently we have : - * ml2 > ml1, and - * ip1+3 <= ip2 (usually < ip1+ml1) - */ + /* At this stage, we have : + * ml2 > ml1, and + * ip1+3 <= ip2 (usually < ip1+ml1) */ if ((start2 - ip) < OPTIMAL_ML) { int correction; int new_ml = ml; @@ -396,17 +568,23 @@ _Search3: } /* Now, we have start2 = ip+new_ml, with new_ml = min(ml, OPTIMAL_ML=18) */ - if (start2 + ml2 < mflimit) - ml3 = LZ4HC_InsertAndGetWiderMatch(ctx, start2 + ml2 - 3, start2, matchlimit, ml2, &ref3, &start3, maxNbAttempts); - else ml3 = ml2; + if (start2 + ml2 <= mflimit) { + ml3 = LZ4HC_InsertAndGetWiderMatch(ctx, + start2 + ml2 - 3, start2, matchlimit, ml2, &ref3, &start3, + maxNbAttempts, patternAnalysis, 0, dict, favorCompressionRatio); + } else { + ml3 = ml2; + } - if (ml3 == ml2) { /* No better match : 2 sequences to encode */ + if (ml3 == ml2) { /* No better match => encode ML1 and ML2 */ /* ip & ref are known; Now for ml */ if (start2 < ip+ml) ml = (int)(start2 - ip); /* Now, encode 2 sequences */ - if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0; + optr = op; + if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) goto _dest_overflow; ip = start2; - if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml2, ref2, limit, oend)) return 0; + optr = op; + if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml2, ref2, limit, oend)) goto _dest_overflow; continue; } @@ -424,7 +602,8 @@ _Search3: } } - if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0; + optr = op; + if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) goto _dest_overflow; ip = start3; ref = ref3; ml = ml3; @@ -442,11 +621,12 @@ _Search3: } /* - * OK, now we have 3 ascending matches; let's write at least the first one - * ip & ref are known; Now for ml + * OK, now we have 3 ascending matches; + * let's write the first one ML1. + * ip & ref are known; Now decide ml. */ if (start2 < ip+ml) { - if ((start2 - ip) < (int)ML_MASK) { + if ((start2 - ip) < OPTIMAL_ML) { int correction; if (ml > OPTIMAL_ML) ml = OPTIMAL_ML; if (ip + ml > start2 + ml2 - MINMATCH) ml = (int)(start2 - ip) + ml2 - MINMATCH; @@ -460,136 +640,309 @@ _Search3: ml = (int)(start2 - ip); } } - if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0; + optr = op; + if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) goto _dest_overflow; - ip = start2; - ref = ref2; - ml = ml2; + /* ML2 becomes ML1 */ + ip = start2; ref = ref2; ml = ml2; - start2 = start3; - ref2 = ref3; - ml2 = ml3; + /* ML3 becomes ML2 */ + start2 = start3; ref2 = ref3; ml2 = ml3; + /* let's find a new ML3 */ goto _Search3; } +_last_literals: /* Encode Last Literals */ - { int lastRun = (int)(iend - anchor); - if ((limit) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize)) return 0; /* Check output limit */ - if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun > 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; } - else *op++ = (BYTE)(lastRun<<ML_BITS); - memcpy(op, anchor, iend - anchor); - op += iend-anchor; + { size_t lastRunSize = (size_t)(iend - anchor); /* literals */ + size_t litLength = (lastRunSize + 255 - RUN_MASK) / 255; + size_t const totalSize = 1 + litLength + lastRunSize; + if (limit == limitedDestSize) oend += LASTLITERALS; /* restore correct value */ + if (limit && (op + totalSize > oend)) { + if (limit == limitedOutput) return 0; /* Check output limit */ + /* adapt lastRunSize to fill 'dest' */ + lastRunSize = (size_t)(oend - op) - 1; + litLength = (lastRunSize + 255 - RUN_MASK) / 255; + lastRunSize -= litLength; + } + 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 << ML_BITS); + } + memcpy(op, anchor, lastRunSize); + op += lastRunSize; } /* End */ + *srcSizePtr = (int) (((const char*)ip) - source); return (int) (((char*)op)-dest); + +_dest_overflow: + if (limit == limitedDestSize) { + op = optr; /* restore correct out pointer */ + goto _last_literals; + } + return 0; } -static int LZ4HC_getSearchNum(int compressionLevel) + +static int LZ4HC_compress_optimal( LZ4HC_CCtx_internal* ctx, + const char* const source, char* dst, + int* srcSizePtr, int dstCapacity, + int const nbSearches, size_t sufficient_len, + const limitedOutput_directive limit, int const fullUpdate, + const dictCtx_directive dict, + HCfavor_e favorDecSpeed); + + +LZ4_FORCE_INLINE int LZ4HC_compress_generic_internal ( + LZ4HC_CCtx_internal* const ctx, + const char* const src, + char* const dst, + int* const srcSizePtr, + int const dstCapacity, + int cLevel, + const limitedOutput_directive limit, + const dictCtx_directive dict + ) { - switch (compressionLevel) { - default: return 0; /* unused */ - case 11: return 128; - case 12: return 1<<10; + typedef enum { lz4hc, lz4opt } lz4hc_strat_e; + typedef struct { + lz4hc_strat_e strat; + U32 nbSearches; + U32 targetLength; + } cParams_t; + static const cParams_t clTable[LZ4HC_CLEVEL_MAX+1] = { + { lz4hc, 2, 16 }, /* 0, unused */ + { lz4hc, 2, 16 }, /* 1, unused */ + { lz4hc, 2, 16 }, /* 2, unused */ + { lz4hc, 4, 16 }, /* 3 */ + { lz4hc, 8, 16 }, /* 4 */ + { lz4hc, 16, 16 }, /* 5 */ + { lz4hc, 32, 16 }, /* 6 */ + { lz4hc, 64, 16 }, /* 7 */ + { lz4hc, 128, 16 }, /* 8 */ + { lz4hc, 256, 16 }, /* 9 */ + { lz4opt, 96, 64 }, /*10==LZ4HC_CLEVEL_OPT_MIN*/ + { lz4opt, 512,128 }, /*11 */ + { lz4opt,16384,LZ4_OPT_NUM }, /* 12==LZ4HC_CLEVEL_MAX */ + }; + + DEBUGLOG(4, "LZ4HC_compress_generic(%p, %p, %d)", ctx, src, *srcSizePtr); + + if (limit == limitedDestSize && dstCapacity < 1) return 0; /* Impossible to store anything */ + if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size (too large or negative) */ + + ctx->end += *srcSizePtr; + if (cLevel < 1) cLevel = LZ4HC_CLEVEL_DEFAULT; /* note : convention is different from lz4frame, maybe something to review */ + cLevel = MIN(LZ4HC_CLEVEL_MAX, cLevel); + { cParams_t const cParam = clTable[cLevel]; + HCfavor_e const favor = ctx->favorDecSpeed ? favorDecompressionSpeed : favorCompressionRatio; + if (cParam.strat == lz4hc) + return LZ4HC_compress_hashChain(ctx, + src, dst, srcSizePtr, dstCapacity, + cParam.nbSearches, limit, dict); + assert(cParam.strat == lz4opt); + return LZ4HC_compress_optimal(ctx, + src, dst, srcSizePtr, dstCapacity, + cParam.nbSearches, cParam.targetLength, limit, + cLevel == LZ4HC_CLEVEL_MAX, /* ultra mode */ + dict, favor); + } +} + +static void LZ4HC_setExternalDict(LZ4HC_CCtx_internal* ctxPtr, const BYTE* newBlock); + +static int LZ4HC_compress_generic_noDictCtx ( + LZ4HC_CCtx_internal* const ctx, + const char* const src, + char* const dst, + int* const srcSizePtr, + int const dstCapacity, + int cLevel, + limitedOutput_directive limit + ) +{ + assert(ctx->dictCtx == NULL); + return LZ4HC_compress_generic_internal(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit, noDictCtx); +} + +static int LZ4HC_compress_generic_dictCtx ( + LZ4HC_CCtx_internal* const ctx, + const char* const src, + char* const dst, + int* const srcSizePtr, + int const dstCapacity, + int cLevel, + limitedOutput_directive limit + ) +{ + const size_t position = ctx->end - ctx->base - ctx->lowLimit; + assert(ctx->dictCtx != NULL); + if (position >= 64 KB) { + ctx->dictCtx = NULL; + return LZ4HC_compress_generic_noDictCtx(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit); + } else if (position == 0 && *srcSizePtr > 4 KB) { + memcpy(ctx, ctx->dictCtx, sizeof(LZ4HC_CCtx_internal)); + LZ4HC_setExternalDict(ctx, (const BYTE *)src); + ctx->compressionLevel = (short)cLevel; + return LZ4HC_compress_generic_noDictCtx(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit); + } else { + return LZ4HC_compress_generic_internal(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit, usingDictCtx); } } static int LZ4HC_compress_generic ( LZ4HC_CCtx_internal* const ctx, - const char* const source, - char* const dest, - int const inputSize, - int const maxOutputSize, - int compressionLevel, + const char* const src, + char* const dst, + int* const srcSizePtr, + int const dstCapacity, + int cLevel, limitedOutput_directive limit ) { - if (compressionLevel < 1) compressionLevel = LZ4HC_CLEVEL_DEFAULT; - if (compressionLevel > 9) { - switch (compressionLevel) { - case 10: return LZ4HC_compress_hashChain(ctx, source, dest, inputSize, maxOutputSize, 1 << (16-1), limit); - case 11: ctx->searchNum = LZ4HC_getSearchNum(compressionLevel); return LZ4HC_compress_optimal(ctx, source, dest, inputSize, maxOutputSize, limit, 128, 0); - default: - case 12: ctx->searchNum = LZ4HC_getSearchNum(compressionLevel); return LZ4HC_compress_optimal(ctx, source, dest, inputSize, maxOutputSize, limit, LZ4_OPT_NUM, 1); - } + if (ctx->dictCtx == NULL) { + return LZ4HC_compress_generic_noDictCtx(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit); + } else { + return LZ4HC_compress_generic_dictCtx(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit); } - return LZ4HC_compress_hashChain(ctx, source, dest, inputSize, maxOutputSize, 1 << (compressionLevel-1), limit); } int LZ4_sizeofStateHC(void) { return sizeof(LZ4_streamHC_t); } -int LZ4_compress_HC_extStateHC (void* state, const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel) +int LZ4_compress_HC_extStateHC_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int compressionLevel) { - LZ4HC_CCtx_internal* ctx = &((LZ4_streamHC_t*)state)->internal_donotuse; + LZ4HC_CCtx_internal* const ctx = &((LZ4_streamHC_t*)state)->internal_donotuse; if (((size_t)(state)&(sizeof(void*)-1)) != 0) return 0; /* Error : state is not aligned for pointers (32 or 64 bits) */ + LZ4_resetStreamHC_fast((LZ4_streamHC_t*)state, compressionLevel); LZ4HC_init (ctx, (const BYTE*)src); - if (maxDstSize < LZ4_compressBound(srcSize)) - return LZ4HC_compress_generic (ctx, src, dst, srcSize, maxDstSize, compressionLevel, limitedOutput); + if (dstCapacity < LZ4_compressBound(srcSize)) + return LZ4HC_compress_generic (ctx, src, dst, &srcSize, dstCapacity, compressionLevel, limitedOutput); else - return LZ4HC_compress_generic (ctx, src, dst, srcSize, maxDstSize, compressionLevel, noLimit); + return LZ4HC_compress_generic (ctx, src, dst, &srcSize, dstCapacity, compressionLevel, noLimit); +} + +int LZ4_compress_HC_extStateHC (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int compressionLevel) +{ + if (((size_t)(state)&(sizeof(void*)-1)) != 0) return 0; /* Error : state is not aligned for pointers (32 or 64 bits) */ + LZ4_resetStreamHC ((LZ4_streamHC_t*)state, compressionLevel); + return LZ4_compress_HC_extStateHC_fastReset(state, src, dst, srcSize, dstCapacity, compressionLevel); } -int LZ4_compress_HC(const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel) +int LZ4_compress_HC(const char* src, char* dst, int srcSize, int dstCapacity, int compressionLevel) { #if defined(LZ4HC_HEAPMODE) && LZ4HC_HEAPMODE==1 - LZ4_streamHC_t* const statePtr = (LZ4_streamHC_t*)malloc(sizeof(LZ4_streamHC_t)); + LZ4_streamHC_t* const statePtr = (LZ4_streamHC_t*)ALLOC(sizeof(LZ4_streamHC_t)); #else LZ4_streamHC_t state; LZ4_streamHC_t* const statePtr = &state; #endif - int const cSize = LZ4_compress_HC_extStateHC(statePtr, src, dst, srcSize, maxDstSize, compressionLevel); + int const cSize = LZ4_compress_HC_extStateHC(statePtr, src, dst, srcSize, dstCapacity, compressionLevel); #if defined(LZ4HC_HEAPMODE) && LZ4HC_HEAPMODE==1 free(statePtr); #endif return cSize; } +/* LZ4_compress_HC_destSize() : + * only compatible with regular HC parser */ +int LZ4_compress_HC_destSize(void* LZ4HC_Data, const char* source, char* dest, int* sourceSizePtr, int targetDestSize, int cLevel) +{ + LZ4HC_CCtx_internal* const ctx = &((LZ4_streamHC_t*)LZ4HC_Data)->internal_donotuse; + LZ4_resetStreamHC((LZ4_streamHC_t*)LZ4HC_Data, cLevel); + LZ4HC_init(ctx, (const BYTE*) source); + return LZ4HC_compress_generic(ctx, source, dest, sourceSizePtr, targetDestSize, cLevel, limitedDestSize); +} + /************************************** * Streaming Functions **************************************/ /* allocation */ -LZ4_streamHC_t* LZ4_createStreamHC(void) { return (LZ4_streamHC_t*)malloc(sizeof(LZ4_streamHC_t)); } -int LZ4_freeStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr) { free(LZ4_streamHCPtr); return 0; } +LZ4_streamHC_t* LZ4_createStreamHC(void) { + LZ4_streamHC_t* const LZ4_streamHCPtr = (LZ4_streamHC_t*)ALLOC(sizeof(LZ4_streamHC_t)); + if (LZ4_streamHCPtr==NULL) return NULL; + LZ4_resetStreamHC(LZ4_streamHCPtr, LZ4HC_CLEVEL_DEFAULT); + return LZ4_streamHCPtr; +} + +int LZ4_freeStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr) { + DEBUGLOG(4, "LZ4_freeStreamHC(%p)", LZ4_streamHCPtr); + if (!LZ4_streamHCPtr) return 0; /* support free on NULL */ + free(LZ4_streamHCPtr); + return 0; +} /* initialization */ void LZ4_resetStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel) { LZ4_STATIC_ASSERT(sizeof(LZ4HC_CCtx_internal) <= sizeof(size_t) * LZ4_STREAMHCSIZE_SIZET); /* if compilation fails here, LZ4_STREAMHCSIZE must be increased */ + DEBUGLOG(4, "LZ4_resetStreamHC(%p, %d)", LZ4_streamHCPtr, compressionLevel); + LZ4_streamHCPtr->internal_donotuse.end = (const BYTE *)(ptrdiff_t)-1; + LZ4_streamHCPtr->internal_donotuse.base = NULL; + LZ4_streamHCPtr->internal_donotuse.dictCtx = NULL; + LZ4_streamHCPtr->internal_donotuse.favorDecSpeed = 0; + LZ4_setCompressionLevel(LZ4_streamHCPtr, compressionLevel); +} + +void LZ4_resetStreamHC_fast (LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel) +{ + DEBUGLOG(4, "LZ4_resetStreamHC_fast(%p, %d)", LZ4_streamHCPtr, compressionLevel); + LZ4_streamHCPtr->internal_donotuse.end -= (uptrval)LZ4_streamHCPtr->internal_donotuse.base; LZ4_streamHCPtr->internal_donotuse.base = NULL; - LZ4_streamHCPtr->internal_donotuse.compressionLevel = (unsigned)compressionLevel; - LZ4_streamHCPtr->internal_donotuse.searchNum = LZ4HC_getSearchNum(compressionLevel); + LZ4_streamHCPtr->internal_donotuse.dictCtx = NULL; + LZ4_setCompressionLevel(LZ4_streamHCPtr, compressionLevel); +} + +void LZ4_setCompressionLevel(LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel) +{ + if (compressionLevel < 1) compressionLevel = LZ4HC_CLEVEL_DEFAULT; + if (compressionLevel > LZ4HC_CLEVEL_MAX) compressionLevel = LZ4HC_CLEVEL_MAX; + LZ4_streamHCPtr->internal_donotuse.compressionLevel = (short)compressionLevel; +} + +void LZ4_favorDecompressionSpeed(LZ4_streamHC_t* LZ4_streamHCPtr, int favor) +{ + LZ4_streamHCPtr->internal_donotuse.favorDecSpeed = (favor!=0); } int LZ4_loadDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, const char* dictionary, int dictSize) { - LZ4HC_CCtx_internal* ctxPtr = &LZ4_streamHCPtr->internal_donotuse; + LZ4HC_CCtx_internal* const ctxPtr = &LZ4_streamHCPtr->internal_donotuse; + DEBUGLOG(4, "LZ4_loadDictHC(%p, %p, %d)", LZ4_streamHCPtr, dictionary, dictSize); if (dictSize > 64 KB) { dictionary += dictSize - 64 KB; dictSize = 64 KB; } + LZ4_resetStreamHC(LZ4_streamHCPtr, ctxPtr->compressionLevel); LZ4HC_init (ctxPtr, (const BYTE*)dictionary); ctxPtr->end = (const BYTE*)dictionary + dictSize; - if (ctxPtr->compressionLevel >= LZ4HC_CLEVEL_OPT_MIN) - LZ4HC_updateBinTree(ctxPtr, ctxPtr->end - MFLIMIT, ctxPtr->end - LASTLITERALS); - else - if (dictSize >= 4) LZ4HC_Insert (ctxPtr, ctxPtr->end-3); + if (dictSize >= 4) LZ4HC_Insert (ctxPtr, ctxPtr->end-3); return dictSize; } +void LZ4_attach_HC_dictionary(LZ4_streamHC_t *working_stream, const LZ4_streamHC_t *dictionary_stream) { + working_stream->internal_donotuse.dictCtx = dictionary_stream != NULL ? &(dictionary_stream->internal_donotuse) : NULL; +} /* compression */ static void LZ4HC_setExternalDict(LZ4HC_CCtx_internal* ctxPtr, const BYTE* newBlock) { - if (ctxPtr->compressionLevel >= LZ4HC_CLEVEL_OPT_MIN) - LZ4HC_updateBinTree(ctxPtr, ctxPtr->end - MFLIMIT, ctxPtr->end - LASTLITERALS); - else - if (ctxPtr->end >= ctxPtr->base + 4) LZ4HC_Insert (ctxPtr, ctxPtr->end-3); /* Referencing remaining dictionary content */ + DEBUGLOG(4, "LZ4HC_setExternalDict(%p, %p)", ctxPtr, newBlock); + if (ctxPtr->end >= ctxPtr->base + ctxPtr->dictLimit + 4) + LZ4HC_Insert (ctxPtr, ctxPtr->end-3); /* Referencing remaining dictionary content */ /* Only one memory segment for extDict, so any previous extDict is lost at this stage */ ctxPtr->lowLimit = ctxPtr->dictLimit; @@ -601,12 +954,14 @@ static void LZ4HC_setExternalDict(LZ4HC_CCtx_internal* ctxPtr, const BYTE* newBl } static int LZ4_compressHC_continue_generic (LZ4_streamHC_t* LZ4_streamHCPtr, - const char* source, char* dest, - int inputSize, int maxOutputSize, limitedOutput_directive limit) + const char* src, char* dst, + int* srcSizePtr, int dstCapacity, + limitedOutput_directive limit) { - LZ4HC_CCtx_internal* ctxPtr = &LZ4_streamHCPtr->internal_donotuse; + LZ4HC_CCtx_internal* const ctxPtr = &LZ4_streamHCPtr->internal_donotuse; + DEBUGLOG(4, "LZ4_compressHC_continue_generic(%p, %p, %d)", LZ4_streamHCPtr, src, *srcSizePtr); /* auto-init if forgotten */ - if (ctxPtr->base == NULL) LZ4HC_init (ctxPtr, (const BYTE*) source); + if (ctxPtr->base == NULL) LZ4HC_init (ctxPtr, (const BYTE*) src); /* Check overflow */ if ((size_t)(ctxPtr->end - ctxPtr->base) > 2 GB) { @@ -616,37 +971,44 @@ static int LZ4_compressHC_continue_generic (LZ4_streamHC_t* LZ4_streamHCPtr, } /* Check if blocks follow each other */ - if ((const BYTE*)source != ctxPtr->end) LZ4HC_setExternalDict(ctxPtr, (const BYTE*)source); + if ((const BYTE*)src != ctxPtr->end) LZ4HC_setExternalDict(ctxPtr, (const BYTE*)src); /* Check overlapping input/dictionary space */ - { const BYTE* sourceEnd = (const BYTE*) source + inputSize; + { const BYTE* sourceEnd = (const BYTE*) src + *srcSizePtr; const BYTE* const dictBegin = ctxPtr->dictBase + ctxPtr->lowLimit; const BYTE* const dictEnd = ctxPtr->dictBase + ctxPtr->dictLimit; - if ((sourceEnd > dictBegin) && ((const BYTE*)source < dictEnd)) { + if ((sourceEnd > dictBegin) && ((const BYTE*)src < dictEnd)) { if (sourceEnd > dictEnd) sourceEnd = dictEnd; ctxPtr->lowLimit = (U32)(sourceEnd - ctxPtr->dictBase); if (ctxPtr->dictLimit - ctxPtr->lowLimit < 4) ctxPtr->lowLimit = ctxPtr->dictLimit; } } - return LZ4HC_compress_generic (ctxPtr, source, dest, inputSize, maxOutputSize, ctxPtr->compressionLevel, limit); + return LZ4HC_compress_generic (ctxPtr, src, dst, srcSizePtr, dstCapacity, ctxPtr->compressionLevel, limit); } -int LZ4_compress_HC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize) +int LZ4_compress_HC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* src, char* dst, int srcSize, int dstCapacity) { - if (maxOutputSize < LZ4_compressBound(inputSize)) - return LZ4_compressHC_continue_generic (LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, limitedOutput); + if (dstCapacity < LZ4_compressBound(srcSize)) + return LZ4_compressHC_continue_generic (LZ4_streamHCPtr, src, dst, &srcSize, dstCapacity, limitedOutput); else - return LZ4_compressHC_continue_generic (LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, noLimit); + return LZ4_compressHC_continue_generic (LZ4_streamHCPtr, src, dst, &srcSize, dstCapacity, noLimit); +} + +int LZ4_compress_HC_continue_destSize (LZ4_streamHC_t* LZ4_streamHCPtr, const char* src, char* dst, int* srcSizePtr, int targetDestSize) +{ + return LZ4_compressHC_continue_generic(LZ4_streamHCPtr, src, dst, srcSizePtr, targetDestSize, limitedDestSize); } + /* dictionary saving */ int LZ4_saveDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, char* safeBuffer, int dictSize) { LZ4HC_CCtx_internal* const streamPtr = &LZ4_streamHCPtr->internal_donotuse; int const prefixSize = (int)(streamPtr->end - (streamPtr->base + streamPtr->dictLimit)); + DEBUGLOG(4, "LZ4_saveDictHC(%p, %p, %d)", LZ4_streamHCPtr, safeBuffer, dictSize); if (dictSize > 64 KB) dictSize = 64 KB; if (dictSize < 4) dictSize = 0; if (dictSize > prefixSize) dictSize = prefixSize; @@ -686,35 +1048,365 @@ int LZ4_resetStreamStateHC(void* state, char* inputBuffer) { LZ4HC_CCtx_internal *ctx = &((LZ4_streamHC_t*)state)->internal_donotuse; if ((((size_t)state) & (sizeof(void*)-1)) != 0) return 1; /* Error : pointer is not aligned for pointer (32 or 64 bits) */ + LZ4_resetStreamHC((LZ4_streamHC_t*)state, ((LZ4_streamHC_t*)state)->internal_donotuse.compressionLevel); LZ4HC_init(ctx, (const BYTE*)inputBuffer); - ctx->inputBuffer = (BYTE*)inputBuffer; return 0; } -void* LZ4_createHC (char* inputBuffer) +void* LZ4_createHC (const char* inputBuffer) { - LZ4_streamHC_t* hc4 = (LZ4_streamHC_t*)ALLOCATOR(1, sizeof(LZ4_streamHC_t)); + LZ4_streamHC_t* hc4 = (LZ4_streamHC_t*)ALLOC(sizeof(LZ4_streamHC_t)); if (hc4 == NULL) return NULL; /* not enough memory */ + LZ4_resetStreamHC(hc4, 0 /* compressionLevel */); LZ4HC_init (&hc4->internal_donotuse, (const BYTE*)inputBuffer); - hc4->internal_donotuse.inputBuffer = (BYTE*)inputBuffer; return hc4; } -int LZ4_freeHC (void* LZ4HC_Data) { FREEMEM(LZ4HC_Data); return 0; } +int LZ4_freeHC (void* LZ4HC_Data) { + if (!LZ4HC_Data) return 0; /* support free on NULL */ + FREEMEM(LZ4HC_Data); + return 0; +} -int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel) +int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* src, char* dst, int srcSize, int cLevel) { - return LZ4HC_compress_generic (&((LZ4_streamHC_t*)LZ4HC_Data)->internal_donotuse, source, dest, inputSize, 0, compressionLevel, noLimit); + return LZ4HC_compress_generic (&((LZ4_streamHC_t*)LZ4HC_Data)->internal_donotuse, src, dst, &srcSize, 0, cLevel, noLimit); } -int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel) +int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* src, char* dst, int srcSize, int dstCapacity, int cLevel) { - return LZ4HC_compress_generic (&((LZ4_streamHC_t*)LZ4HC_Data)->internal_donotuse, source, dest, inputSize, maxOutputSize, compressionLevel, limitedOutput); + return LZ4HC_compress_generic (&((LZ4_streamHC_t*)LZ4HC_Data)->internal_donotuse, src, dst, &srcSize, dstCapacity, cLevel, limitedOutput); } char* LZ4_slideInputBufferHC(void* LZ4HC_Data) { - LZ4HC_CCtx_internal* const hc4 = &((LZ4_streamHC_t*)LZ4HC_Data)->internal_donotuse; - int const dictSize = LZ4_saveDictHC((LZ4_streamHC_t*)LZ4HC_Data, (char*)(hc4->inputBuffer), 64 KB); - return (char*)(hc4->inputBuffer + dictSize); + LZ4_streamHC_t *ctx = (LZ4_streamHC_t*)LZ4HC_Data; + const BYTE *bufferStart = ctx->internal_donotuse.base + ctx->internal_donotuse.lowLimit; + LZ4_resetStreamHC_fast(ctx, ctx->internal_donotuse.compressionLevel); + /* avoid const char * -> char * conversion warning :( */ + return (char *)(uptrval)bufferStart; +} + + +/* ================================================ + * LZ4 Optimal parser (levels 10-12) + * ===============================================*/ +typedef struct { + int price; + int off; + int mlen; + int litlen; +} LZ4HC_optimal_t; + +/* price in bytes */ +LZ4_FORCE_INLINE int LZ4HC_literalsPrice(int const litlen) +{ + int price = litlen; + if (litlen >= (int)RUN_MASK) + price += 1 + (litlen-RUN_MASK)/255; + return price; } + + +/* requires mlen >= MINMATCH */ +LZ4_FORCE_INLINE int LZ4HC_sequencePrice(int litlen, int mlen) +{ + int price = 1 + 2 ; /* token + 16-bit offset */ + + price += LZ4HC_literalsPrice(litlen); + + if (mlen >= (int)(ML_MASK+MINMATCH)) + price += 1 + (mlen-(ML_MASK+MINMATCH))/255; + + return price; +} + + +typedef struct { + int off; + int len; +} LZ4HC_match_t; + +LZ4_FORCE_INLINE LZ4HC_match_t +LZ4HC_FindLongerMatch(LZ4HC_CCtx_internal* const ctx, + const BYTE* ip, const BYTE* const iHighLimit, + int minLen, int nbSearches, + const dictCtx_directive dict, + const HCfavor_e favorDecSpeed) +{ + LZ4HC_match_t match = { 0 , 0 }; + const BYTE* matchPtr = NULL; + /* note : LZ4HC_InsertAndGetWiderMatch() is able to modify the starting position of a match (*startpos), + * but this won't be the case here, as we define iLowLimit==ip, + * so LZ4HC_InsertAndGetWiderMatch() won't be allowed to search past ip */ + int matchLength = LZ4HC_InsertAndGetWiderMatch(ctx, ip, ip, iHighLimit, minLen, &matchPtr, &ip, nbSearches, 1 /*patternAnalysis*/, 1 /*chainSwap*/, dict, favorDecSpeed); + if (matchLength <= minLen) return match; + if (favorDecSpeed) { + if ((matchLength>18) & (matchLength<=36)) matchLength=18; /* favor shortcut */ + } + match.len = matchLength; + match.off = (int)(ip-matchPtr); + return match; +} + + +static int LZ4HC_compress_optimal ( LZ4HC_CCtx_internal* ctx, + const char* const source, + char* dst, + int* srcSizePtr, + int dstCapacity, + int const nbSearches, + size_t sufficient_len, + const limitedOutput_directive limit, + int const fullUpdate, + const dictCtx_directive dict, + const HCfavor_e favorDecSpeed) +{ +#define TRAILING_LITERALS 3 + LZ4HC_optimal_t opt[LZ4_OPT_NUM + TRAILING_LITERALS]; /* ~64 KB, which is a bit large for stack... */ + + const BYTE* ip = (const BYTE*) source; + 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* opSaved = (BYTE*) dst; + BYTE* oend = op + dstCapacity; + + /* init */ + DEBUGLOG(5, "LZ4HC_compress_optimal"); + *srcSizePtr = 0; + if (limit == limitedDestSize) oend -= LASTLITERALS; /* Hack for support LZ4 format restriction */ + if (sufficient_len >= LZ4_OPT_NUM) sufficient_len = LZ4_OPT_NUM-1; + + /* Main Loop */ + assert(ip - anchor < LZ4_MAX_INPUT_SIZE); + while (ip <= mflimit) { + int const llen = (int)(ip - anchor); + int best_mlen, best_off; + int cur, last_match_pos = 0; + + LZ4HC_match_t const firstMatch = LZ4HC_FindLongerMatch(ctx, ip, matchlimit, MINMATCH-1, nbSearches, dict, favorDecSpeed); + if (firstMatch.len==0) { ip++; continue; } + + if ((size_t)firstMatch.len > sufficient_len) { + /* good enough solution : immediate encoding */ + int const firstML = firstMatch.len; + const BYTE* const matchPos = ip - firstMatch.off; + opSaved = op; + if ( LZ4HC_encodeSequence(&ip, &op, &anchor, firstML, matchPos, limit, oend) ) /* updates ip, op and anchor */ + goto _dest_overflow; + continue; + } + + /* set prices for first positions (literals) */ + { int rPos; + for (rPos = 0 ; rPos < MINMATCH ; rPos++) { + int const cost = LZ4HC_literalsPrice(llen + rPos); + opt[rPos].mlen = 1; + opt[rPos].off = 0; + opt[rPos].litlen = llen + rPos; + opt[rPos].price = cost; + DEBUGLOG(7, "rPos:%3i => price:%3i (litlen=%i) -- initial setup", + rPos, cost, opt[rPos].litlen); + } } + /* set prices using initial match */ + { int mlen = MINMATCH; + int const matchML = firstMatch.len; /* necessarily < sufficient_len < LZ4_OPT_NUM */ + int const offset = firstMatch.off; + assert(matchML < LZ4_OPT_NUM); + for ( ; mlen <= matchML ; mlen++) { + int const cost = LZ4HC_sequencePrice(llen, mlen); + opt[mlen].mlen = mlen; + opt[mlen].off = offset; + opt[mlen].litlen = llen; + opt[mlen].price = cost; + DEBUGLOG(7, "rPos:%3i => price:%3i (matchlen=%i) -- initial setup", + mlen, cost, mlen); + } } + last_match_pos = firstMatch.len; + { int addLit; + for (addLit = 1; addLit <= TRAILING_LITERALS; addLit ++) { + opt[last_match_pos+addLit].mlen = 1; /* literal */ + opt[last_match_pos+addLit].off = 0; + opt[last_match_pos+addLit].litlen = addLit; + opt[last_match_pos+addLit].price = opt[last_match_pos].price + LZ4HC_literalsPrice(addLit); + DEBUGLOG(7, "rPos:%3i => price:%3i (litlen=%i) -- initial setup", + last_match_pos+addLit, opt[last_match_pos+addLit].price, addLit); + } } + + /* check further positions */ + for (cur = 1; cur < last_match_pos; cur++) { + const BYTE* const curPtr = ip + cur; + LZ4HC_match_t newMatch; + + if (curPtr > mflimit) break; + DEBUGLOG(7, "rPos:%u[%u] vs [%u]%u", + cur, opt[cur].price, opt[cur+1].price, cur+1); + if (fullUpdate) { + /* not useful to search here if next position has same (or lower) cost */ + if ( (opt[cur+1].price <= opt[cur].price) + /* in some cases, next position has same cost, but cost rises sharply after, so a small match would still be beneficial */ + && (opt[cur+MINMATCH].price < opt[cur].price + 3/*min seq price*/) ) + continue; + } else { + /* not useful to search here if next position has same (or lower) cost */ + if (opt[cur+1].price <= opt[cur].price) continue; + } + + DEBUGLOG(7, "search at rPos:%u", cur); + if (fullUpdate) + newMatch = LZ4HC_FindLongerMatch(ctx, curPtr, matchlimit, MINMATCH-1, nbSearches, dict, favorDecSpeed); + else + /* only test matches of minimum length; slightly faster, but misses a few bytes */ + newMatch = LZ4HC_FindLongerMatch(ctx, curPtr, matchlimit, last_match_pos - cur, nbSearches, dict, favorDecSpeed); + if (!newMatch.len) continue; + + if ( ((size_t)newMatch.len > sufficient_len) + || (newMatch.len + cur >= LZ4_OPT_NUM) ) { + /* immediate encoding */ + best_mlen = newMatch.len; + best_off = newMatch.off; + last_match_pos = cur + 1; + goto encode; + } + + /* before match : set price with literals at beginning */ + { int const baseLitlen = opt[cur].litlen; + int litlen; + for (litlen = 1; litlen < MINMATCH; litlen++) { + int const price = opt[cur].price - LZ4HC_literalsPrice(baseLitlen) + LZ4HC_literalsPrice(baseLitlen+litlen); + int const pos = cur + litlen; + if (price < opt[pos].price) { + opt[pos].mlen = 1; /* literal */ + opt[pos].off = 0; + opt[pos].litlen = baseLitlen+litlen; + opt[pos].price = price; + DEBUGLOG(7, "rPos:%3i => price:%3i (litlen=%i)", + pos, price, opt[pos].litlen); + } } } + + /* set prices using match at position = cur */ + { int const matchML = newMatch.len; + int ml = MINMATCH; + + assert(cur + newMatch.len < LZ4_OPT_NUM); + for ( ; ml <= matchML ; ml++) { + int const pos = cur + ml; + int const offset = newMatch.off; + int price; + int ll; + DEBUGLOG(7, "testing price rPos %i (last_match_pos=%i)", + pos, last_match_pos); + if (opt[cur].mlen == 1) { + ll = opt[cur].litlen; + price = ((cur > ll) ? opt[cur - ll].price : 0) + + LZ4HC_sequencePrice(ll, ml); + } else { + ll = 0; + price = opt[cur].price + LZ4HC_sequencePrice(0, ml); + } + + assert((U32)favorDecSpeed <= 1); + if (pos > last_match_pos+TRAILING_LITERALS + || price <= opt[pos].price - (int)favorDecSpeed) { + DEBUGLOG(7, "rPos:%3i => price:%3i (matchlen=%i)", + pos, price, ml); + assert(pos < LZ4_OPT_NUM); + if ( (ml == matchML) /* last pos of last match */ + && (last_match_pos < pos) ) + last_match_pos = pos; + opt[pos].mlen = ml; + opt[pos].off = offset; + opt[pos].litlen = ll; + opt[pos].price = price; + } } } + /* complete following positions with literals */ + { int addLit; + for (addLit = 1; addLit <= TRAILING_LITERALS; addLit ++) { + opt[last_match_pos+addLit].mlen = 1; /* literal */ + opt[last_match_pos+addLit].off = 0; + opt[last_match_pos+addLit].litlen = addLit; + opt[last_match_pos+addLit].price = opt[last_match_pos].price + LZ4HC_literalsPrice(addLit); + DEBUGLOG(7, "rPos:%3i => price:%3i (litlen=%i)", last_match_pos+addLit, opt[last_match_pos+addLit].price, addLit); + } } + } /* for (cur = 1; cur <= last_match_pos; cur++) */ + + best_mlen = opt[last_match_pos].mlen; + best_off = opt[last_match_pos].off; + cur = last_match_pos - best_mlen; + + encode: /* cur, last_match_pos, best_mlen, best_off must be set */ + assert(cur < LZ4_OPT_NUM); + assert(last_match_pos >= 1); /* == 1 when only one candidate */ + DEBUGLOG(6, "reverse traversal, looking for shortest path (last_match_pos=%i)", last_match_pos); + { int candidate_pos = cur; + int selected_matchLength = best_mlen; + int selected_offset = best_off; + while (1) { /* from end to beginning */ + int const next_matchLength = opt[candidate_pos].mlen; /* can be 1, means literal */ + int const next_offset = opt[candidate_pos].off; + DEBUGLOG(7, "pos %i: sequence length %i", candidate_pos, selected_matchLength); + opt[candidate_pos].mlen = selected_matchLength; + opt[candidate_pos].off = selected_offset; + selected_matchLength = next_matchLength; + selected_offset = next_offset; + if (next_matchLength > candidate_pos) break; /* last match elected, first match to encode */ + assert(next_matchLength > 0); /* can be 1, means literal */ + candidate_pos -= next_matchLength; + } } + + /* encode all recorded sequences in order */ + { int rPos = 0; /* relative position (to ip) */ + while (rPos < last_match_pos) { + int const ml = opt[rPos].mlen; + int const offset = opt[rPos].off; + if (ml == 1) { ip++; rPos++; continue; } /* literal; note: can end up with several literals, in which case, skip them */ + rPos += ml; + assert(ml >= MINMATCH); + assert((offset >= 1) && (offset <= MAX_DISTANCE)); + opSaved = op; + if ( LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ip - offset, limit, oend) ) /* updates ip, op and anchor */ + goto _dest_overflow; + } } + } /* while (ip <= mflimit) */ + + _last_literals: + /* Encode Last Literals */ + { size_t lastRunSize = (size_t)(iend - anchor); /* literals */ + size_t litLength = (lastRunSize + 255 - RUN_MASK) / 255; + size_t const totalSize = 1 + litLength + lastRunSize; + if (limit == limitedDestSize) oend += LASTLITERALS; /* restore correct value */ + if (limit && (op + totalSize > oend)) { + if (limit == limitedOutput) return 0; /* Check output limit */ + /* adapt lastRunSize to fill 'dst' */ + lastRunSize = (size_t)(oend - op) - 1; + litLength = (lastRunSize + 255 - RUN_MASK) / 255; + lastRunSize -= litLength; + } + 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 << ML_BITS); + } + memcpy(op, anchor, lastRunSize); + op += lastRunSize; + } + + /* End */ + *srcSizePtr = (int) (((const char*)ip) - source); + return (int) ((char*)op-dst); + + _dest_overflow: + if (limit == limitedDestSize) { + op = opSaved; /* restore correct out pointer */ + goto _last_literals; + } + return 0; + } diff --git a/lib/lz4hc.h b/lib/lz4hc.h index 1036fd0b..970fa396 100644 --- a/lib/lz4hc.h +++ b/lib/lz4hc.h @@ -1,7 +1,7 @@ /* LZ4 HC - High Compression Mode of LZ4 Header File - Copyright (C) 2011-2016, Yann Collet. + Copyright (C) 2011-2017, 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 @@ -39,14 +39,14 @@ extern "C" { #endif /* --- Dependency --- */ -/* note : lz4hc is not an independent module, it requires lz4.h/lz4.c for proper compilation */ +/* note : lz4hc requires lz4.h/lz4.c for compilation */ #include "lz4.h" /* stddef, LZ4LIB_API, LZ4_DEPRECATED */ /* --- Useful constants --- */ #define LZ4HC_CLEVEL_MIN 3 #define LZ4HC_CLEVEL_DEFAULT 9 -#define LZ4HC_CLEVEL_OPT_MIN 11 +#define LZ4HC_CLEVEL_OPT_MIN 10 #define LZ4HC_CLEVEL_MAX 12 @@ -54,12 +54,12 @@ extern "C" { * Block Compression **************************************/ /*! LZ4_compress_HC() : - * Compress data from `src` into `dst`, using the more powerful but slower "HC" algorithm. + * Compress data from `src` into `dst`, using the more powerful but slower "HC" algorithm. * `dst` must be already allocated. - * Compression is guaranteed to succeed if `dstCapacity >= LZ4_compressBound(srcSize)` (see "lz4.h") - * Max supported `srcSize` value is LZ4_MAX_INPUT_SIZE (see "lz4.h") - * `compressionLevel` : Recommended values are between 4 and 9, although any value between 1 and LZ4HC_MAX_CLEVEL will work. - * Values >LZ4HC_MAX_CLEVEL behave the same as LZ4HC_MAX_CLEVEL. + * Compression is guaranteed to succeed if `dstCapacity >= LZ4_compressBound(srcSize)` (see "lz4.h") + * Max supported `srcSize` value is LZ4_MAX_INPUT_SIZE (see "lz4.h") + * `compressionLevel` : any value between 1 and LZ4HC_CLEVEL_MAX will work. + * Values > LZ4HC_CLEVEL_MAX behave the same as LZ4HC_CLEVEL_MAX. * @return : the number of bytes written into 'dst' * or 0 if compression fails. */ @@ -72,12 +72,12 @@ LZ4LIB_API int LZ4_compress_HC (const char* src, char* dst, int srcSize, int dst /*! LZ4_compress_HC_extStateHC() : - * Same as LZ4_compress_HC(), but using an externally allocated memory segment for `state`. + * Same as LZ4_compress_HC(), but using an externally allocated memory segment for `state`. * `state` size is provided by LZ4_sizeofStateHC(). - * Memory segment must be aligned on 8-bytes boundaries (which a normal malloc() will do properly). + * Memory segment must be aligned on 8-bytes boundaries (which a normal malloc() should do properly). */ -LZ4LIB_API int LZ4_compress_HC_extStateHC(void* state, const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel); LZ4LIB_API int LZ4_sizeofStateHC(void); +LZ4LIB_API int LZ4_compress_HC_extStateHC(void* state, const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel); /*-************************************ @@ -87,10 +87,10 @@ LZ4LIB_API int LZ4_sizeofStateHC(void); typedef union LZ4_streamHC_u LZ4_streamHC_t; /* incomplete type (defined later) */ /*! LZ4_createStreamHC() and LZ4_freeStreamHC() : - * These functions create and release memory for LZ4 HC streaming state. - * Newly created states are automatically initialized. - * Existing states can be re-used several times, using LZ4_resetStreamHC(). - * These methods are API and ABI stable, they can be used in combination with a DLL. + * These functions create and release memory for LZ4 HC streaming state. + * Newly created states are automatically initialized. + * Existing states can be re-used several times, using LZ4_resetStreamHC(). + * These methods are API and ABI stable, they can be used in combination with a DLL. */ LZ4LIB_API LZ4_streamHC_t* LZ4_createStreamHC(void); LZ4LIB_API int LZ4_freeStreamHC (LZ4_streamHC_t* streamHCPtr); @@ -113,25 +113,23 @@ LZ4LIB_API int LZ4_saveDictHC (LZ4_streamHC_t* streamHCPtr, char* safeBuffer, in Then, use LZ4_compress_HC_continue() to compress each successive block. Previous memory blocks (including initial dictionary when present) must remain accessible and unmodified during compression. - 'dst' buffer should be sized to handle worst case scenarios, using LZ4_compressBound(), to ensure operation success. + 'dst' buffer should be sized to handle worst case scenarios (see LZ4_compressBound()), to ensure operation success. + Because in case of failure, the API does not guarantee context recovery, and context will have to be reset. + If `dst` buffer budget cannot be >= LZ4_compressBound(), consider using LZ4_compress_HC_continue_destSize() instead. - If, for any reason, previous data blocks can't be preserved unmodified in memory during next compression block, - you must save it to a safer memory space, using LZ4_saveDictHC(). + If, for any reason, previous data block can't be preserved unmodified in memory for next compression block, + you can save it to a more stable memory space, using LZ4_saveDictHC(). Return value of LZ4_saveDictHC() is the size of dictionary effectively saved into 'safeBuffer'. */ -/*-****************************************** - * !!!!! STATIC LINKING ONLY !!!!! - *******************************************/ - - /*-************************************* +/*-************************************************************** * PRIVATE DEFINITIONS : * Do not use these definitions. * They are exposed to allow static allocation of `LZ4_streamHC_t`. * Using these definitions makes the code vulnerable to potential API break when upgrading LZ4 - **************************************/ -#define LZ4HC_DICTIONARY_LOGSIZE 17 + ****************************************************************/ +#define LZ4HC_DICTIONARY_LOGSIZE 16 #define LZ4HC_MAXD (1<<LZ4HC_DICTIONARY_LOGSIZE) #define LZ4HC_MAXD_MASK (LZ4HC_MAXD - 1) @@ -143,41 +141,43 @@ LZ4LIB_API int LZ4_saveDictHC (LZ4_streamHC_t* streamHCPtr, char* safeBuffer, in #if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) #include <stdint.h> -typedef struct +typedef struct LZ4HC_CCtx_internal LZ4HC_CCtx_internal; +struct LZ4HC_CCtx_internal { uint32_t hashTable[LZ4HC_HASHTABLESIZE]; uint16_t chainTable[LZ4HC_MAXD]; - const uint8_t* end; /* next block here to continue on current prefix */ - const uint8_t* base; /* All index relative to this position */ - const uint8_t* dictBase; /* alternate base for extDict */ - uint8_t* inputBuffer; /* deprecated */ - uint32_t dictLimit; /* below that point, need extDict */ - uint32_t lowLimit; /* below that point, no more dict */ - uint32_t nextToUpdate; /* index from which to continue dictionary update */ - uint32_t searchNum; /* only for optimal parser */ - uint32_t compressionLevel; -} LZ4HC_CCtx_internal; + const uint8_t* end; /* next block here to continue on current prefix */ + const uint8_t* base; /* All index relative to this position */ + const uint8_t* dictBase; /* alternate base for extDict */ + uint32_t dictLimit; /* below that point, need extDict */ + uint32_t lowLimit; /* below that point, no more dict */ + uint32_t nextToUpdate; /* index from which to continue dictionary update */ + short compressionLevel; + short favorDecSpeed; + const LZ4HC_CCtx_internal* dictCtx; +}; #else -typedef struct +typedef struct LZ4HC_CCtx_internal LZ4HC_CCtx_internal; +struct LZ4HC_CCtx_internal { unsigned int hashTable[LZ4HC_HASHTABLESIZE]; - unsigned short chainTable[LZ4HC_MAXD]; + unsigned short chainTable[LZ4HC_MAXD]; const unsigned char* end; /* next block here to continue on current prefix */ const unsigned char* base; /* All index relative to this position */ const unsigned char* dictBase; /* alternate base for extDict */ - unsigned char* inputBuffer; /* deprecated */ unsigned int dictLimit; /* below that point, need extDict */ unsigned int lowLimit; /* below that point, no more dict */ unsigned int nextToUpdate; /* index from which to continue dictionary update */ - unsigned int searchNum; /* only for optimal parser */ - unsigned int compressionLevel; -} LZ4HC_CCtx_internal; + short compressionLevel; + short favorDecSpeed; + const LZ4HC_CCtx_internal* dictCtx; +}; #endif -#define LZ4_STREAMHCSIZE (4*LZ4HC_HASHTABLESIZE + 2*LZ4HC_MAXD + 56) /* 393268 */ +#define LZ4_STREAMHCSIZE (4*LZ4HC_HASHTABLESIZE + 2*LZ4HC_MAXD + 56) /* 262200 */ #define LZ4_STREAMHCSIZE_SIZET (LZ4_STREAMHCSIZE / sizeof(size_t)) union LZ4_streamHC_u { size_t table[LZ4_STREAMHCSIZE_SIZET]; @@ -199,26 +199,32 @@ union LZ4_streamHC_u { /* see lz4.h LZ4_DISABLE_DEPRECATE_WARNINGS to turn off deprecation warnings */ /* deprecated compression functions */ -/* these functions will trigger warning messages in future releases */ -LZ4_DEPRECATED("use LZ4_compress_HC() instead") int LZ4_compressHC (const char* source, char* dest, int inputSize); -LZ4_DEPRECATED("use LZ4_compress_HC() instead") int LZ4_compressHC_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize); -LZ4_DEPRECATED("use LZ4_compress_HC() instead") int LZ4_compressHC2 (const char* source, char* dest, int inputSize, int compressionLevel); -LZ4_DEPRECATED("use LZ4_compress_HC() instead") int LZ4_compressHC2_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); -LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") int LZ4_compressHC_withStateHC (void* state, const char* source, char* dest, int inputSize); -LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") int LZ4_compressHC_limitedOutput_withStateHC (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); -LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") int LZ4_compressHC2_withStateHC (void* state, const char* source, char* dest, int inputSize, int compressionLevel); -LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") int LZ4_compressHC2_limitedOutput_withStateHC(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); -LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize); -LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize); - -/* Deprecated Streaming functions using older model; should no longer be used */ -LZ4_DEPRECATED("use LZ4_createStreamHC() instead") void* LZ4_createHC (char* inputBuffer); -LZ4_DEPRECATED("use LZ4_saveDictHC() instead") char* LZ4_slideInputBufferHC (void* LZ4HC_Data); -LZ4_DEPRECATED("use LZ4_freeStreamHC() instead") int LZ4_freeHC (void* LZ4HC_Data); -LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel); -LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); -LZ4_DEPRECATED("use LZ4_createStreamHC() instead") int LZ4_sizeofStreamStateHC(void); -LZ4_DEPRECATED("use LZ4_resetStreamHC() instead") int LZ4_resetStreamStateHC(void* state, char* inputBuffer); +LZ4_DEPRECATED("use LZ4_compress_HC() instead") LZ4LIB_API int LZ4_compressHC (const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_HC() instead") LZ4LIB_API int LZ4_compressHC_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_HC() instead") LZ4LIB_API int LZ4_compressHC2 (const char* source, char* dest, int inputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_compress_HC() instead") LZ4LIB_API int LZ4_compressHC2_limitedOutput (const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") LZ4LIB_API int LZ4_compressHC_withStateHC (void* state, const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") LZ4LIB_API int LZ4_compressHC_limitedOutput_withStateHC (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") LZ4LIB_API int LZ4_compressHC2_withStateHC (void* state, const char* source, char* dest, int inputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_compress_HC_extStateHC() instead") LZ4LIB_API int LZ4_compressHC2_limitedOutput_withStateHC(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize); + +/* Obsolete streaming functions; degraded functionality; do not use! + * + * In order to perform streaming compression, these functions depended on data + * that is no longer tracked in the state. They have been preserved as well as + * possible: using them will still produce a correct output. However, use of + * LZ4_slideInputBufferHC() will truncate the history of the stream, rather + * than preserve a window-sized chunk of history. + */ +LZ4_DEPRECATED("use LZ4_createStreamHC() instead") LZ4LIB_API void* LZ4_createHC (const char* inputBuffer); +LZ4_DEPRECATED("use LZ4_saveDictHC() instead") LZ4LIB_API char* LZ4_slideInputBufferHC (void* LZ4HC_Data); +LZ4_DEPRECATED("use LZ4_freeStreamHC() instead") LZ4LIB_API int LZ4_freeHC (void* LZ4HC_Data); +LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel); +LZ4_DEPRECATED("use LZ4_createStreamHC() instead") LZ4LIB_API int LZ4_sizeofStreamStateHC(void); +LZ4_DEPRECATED("use LZ4_resetStreamHC() instead") LZ4LIB_API int LZ4_resetStreamStateHC(void* state, char* inputBuffer); #if defined (__cplusplus) @@ -226,3 +232,124 @@ LZ4_DEPRECATED("use LZ4_resetStreamHC() instead") int LZ4_resetStreamStateHC( #endif #endif /* LZ4_HC_H_19834876238432 */ + + +/*-************************************************** + * !!!!! STATIC LINKING ONLY !!!!! + * Following definitions are considered experimental. + * They should not be linked from DLL, + * as there is no guarantee of API stability yet. + * Prototypes will be promoted to "stable" status + * after successfull usage in real-life scenarios. + ***************************************************/ +#ifdef LZ4_HC_STATIC_LINKING_ONLY /* protection macro */ +#ifndef LZ4_HC_SLO_098092834 +#define LZ4_HC_SLO_098092834 + +#if defined (__cplusplus) +extern "C" { +#endif + +/*! LZ4_compress_HC_destSize() : v1.8.0 (experimental) + * Will try to compress as much data from `src` as possible + * that can fit into `targetDstSize` budget. + * Result is provided in 2 parts : + * @return : the number of bytes written into 'dst' + * or 0 if compression fails. + * `srcSizePtr` : value will be updated to indicate how much bytes were read from `src` + */ +int LZ4_compress_HC_destSize(void* LZ4HC_Data, + const char* src, char* dst, + int* srcSizePtr, int targetDstSize, + int compressionLevel); + +/*! LZ4_compress_HC_continue_destSize() : v1.8.0 (experimental) + * Similar as LZ4_compress_HC_continue(), + * but will read a variable nb of bytes from `src` + * to fit into `targetDstSize` budget. + * Result is provided in 2 parts : + * @return : the number of bytes written into 'dst' + * or 0 if compression fails. + * `srcSizePtr` : value will be updated to indicate how much bytes were read from `src`. + */ +int LZ4_compress_HC_continue_destSize(LZ4_streamHC_t* LZ4_streamHCPtr, + const char* src, char* dst, + int* srcSizePtr, int targetDstSize); + +/*! LZ4_setCompressionLevel() : v1.8.0 (experimental) + * It's possible to change compression level between 2 invocations of LZ4_compress_HC_continue*() + */ +void LZ4_setCompressionLevel(LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel); + +/*! LZ4_favorDecompressionSpeed() : v1.8.2 (experimental) + * Parser will select decisions favoring decompression over compression ratio. + * Only work at highest compression settings (level >= LZ4HC_CLEVEL_OPT_MIN) + */ +void LZ4_favorDecompressionSpeed(LZ4_streamHC_t* LZ4_streamHCPtr, int favor); + +/*! LZ4_resetStreamHC_fast() : + * When an LZ4_streamHC_t is known to be in a internally coherent state, + * it can often be prepared for a new compression with almost no work, only + * sometimes falling back to the full, expensive reset that is always required + * when the stream is in an indeterminate state (i.e., the reset performed by + * LZ4_resetStreamHC()). + * + * LZ4_streamHCs are guaranteed to be in a valid state when: + * - returned from LZ4_createStreamHC() + * - reset by LZ4_resetStreamHC() + * - memset(stream, 0, sizeof(LZ4_streamHC_t)) + * - the stream was in a valid state and was reset by LZ4_resetStreamHC_fast() + * - the stream was in a valid state and was then used in any compression call + * that returned success + * - the stream was in an indeterminate state and was used in a compression + * call that fully reset the state (LZ4_compress_HC_extStateHC()) and that + * returned success + */ +void LZ4_resetStreamHC_fast(LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLevel); + +/*! LZ4_compress_HC_extStateHC_fastReset() : + * A variant of LZ4_compress_HC_extStateHC(). + * + * Using this variant avoids an expensive initialization step. It is only safe + * to call if the state buffer is known to be correctly initialized already + * (see above comment on LZ4_resetStreamHC_fast() for a definition of + * "correctly initialized"). From a high level, the difference is that this + * function initializes the provided state with a call to + * LZ4_resetStreamHC_fast() while LZ4_compress_HC_extStateHC() starts with a + * call to LZ4_resetStreamHC(). + */ +int LZ4_compress_HC_extStateHC_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int compressionLevel); + +/*! LZ4_attach_HC_dictionary() : + * This is an experimental API that allows for the efficient use of a + * static dictionary many times. + * + * Rather than re-loading the dictionary buffer into a working context before + * each compression, or copying a pre-loaded dictionary's LZ4_streamHC_t into a + * working LZ4_streamHC_t, this function introduces a no-copy setup mechanism, + * in which the working stream references the dictionary stream in-place. + * + * Several assumptions are made about the state of the dictionary stream. + * Currently, only streams which have been prepared by LZ4_loadDictHC() should + * be expected to work. + * + * Alternatively, the provided dictionary stream pointer may be NULL, in which + * case any existing dictionary stream is unset. + * + * A dictionary should only be attached to a stream without any history (i.e., + * a stream that has just been reset). + * + * The dictionary will remain attached to the working stream only for the + * current stream session. Calls to LZ4_resetStreamHC(_fast) will remove the + * dictionary context association from the working stream. The dictionary + * stream (and source buffer) must remain in-place / accessible / unchanged + * through the lifetime of the stream session. + */ +LZ4LIB_API void LZ4_attach_HC_dictionary(LZ4_streamHC_t *working_stream, const LZ4_streamHC_t *dictionary_stream); + +#if defined (__cplusplus) +} +#endif + +#endif /* LZ4_HC_SLO_098092834 */ +#endif /* LZ4_HC_STATIC_LINKING_ONLY */ diff --git a/lib/lz4opt.h b/lib/lz4opt.h deleted file mode 100644 index d1913fe1..00000000 --- a/lib/lz4opt.h +++ /dev/null @@ -1,363 +0,0 @@ -/* - lz4opt.h - Optimal Mode of LZ4 - Copyright (C) 2015-2016, Przemyslaw Skibinski <inikep@gmail.com> - Note : this file is intended to be included within lz4hc.c - - BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) - - Redistribution and use in source and binary forms, with or without - modification, are permitted provided that the following conditions are - met: - - * Redistributions of source code must retain the above copyright - notice, this list of conditions and the following disclaimer. - * Redistributions in binary form must reproduce the above - copyright notice, this list of conditions and the following disclaimer - in the documentation and/or other materials provided with the - distribution. - - THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - - You can contact the author at : - - LZ4 source repository : https://github.com/lz4/lz4 - - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c -*/ - -#define LZ4_OPT_NUM (1<<12) - - -typedef struct -{ - int off; - int len; -} LZ4HC_match_t; - -typedef struct -{ - int price; - int off; - int mlen; - int litlen; -} LZ4HC_optimal_t; - - -/* price in bits */ -FORCE_INLINE size_t LZ4HC_literalsPrice(size_t litlen) -{ - size_t price = 8*litlen; - if (litlen >= (size_t)RUN_MASK) price+=8*(1+(litlen-RUN_MASK)/255); - return price; -} - - -/* requires mlen >= MINMATCH */ -FORCE_INLINE size_t LZ4HC_sequencePrice(size_t litlen, size_t mlen) -{ - size_t price = 16 + 8; /* 16-bit offset + token */ - - price += LZ4HC_literalsPrice(litlen); - - mlen -= MINMATCH; - if (mlen >= (size_t)ML_MASK) price+=8*(1+(mlen-ML_MASK)/255); - - return price; -} - - -/*-************************************* -* Binary Tree search -***************************************/ -FORCE_INLINE int LZ4HC_BinTree_InsertAndGetAllMatches ( - LZ4HC_CCtx_internal* ctx, - const BYTE* const ip, - const BYTE* const iHighLimit, - size_t best_mlen, - LZ4HC_match_t* matches, - int* matchNum) -{ - U16* const chainTable = ctx->chainTable; - U32* const HashTable = ctx->hashTable; - const BYTE* const base = ctx->base; - const U32 dictLimit = ctx->dictLimit; - const U32 current = (U32)(ip - base); - const U32 lowLimit = (ctx->lowLimit + MAX_DISTANCE > current) ? ctx->lowLimit : current - (MAX_DISTANCE - 1); - const BYTE* const dictBase = ctx->dictBase; - const BYTE* match; - int nbAttempts = ctx->searchNum; - int mnum = 0; - U16 *ptr0, *ptr1, delta0, delta1; - U32 matchIndex; - size_t matchLength = 0; - U32* HashPos; - - if (ip + MINMATCH > iHighLimit) return 1; - - /* HC4 match finder */ - HashPos = &HashTable[LZ4HC_hashPtr(ip)]; - matchIndex = *HashPos; - *HashPos = current; - - ptr0 = &DELTANEXTMAXD(current*2+1); - ptr1 = &DELTANEXTMAXD(current*2); - delta0 = delta1 = (U16)(current - matchIndex); - - while ((matchIndex < current) && (matchIndex>=lowLimit) && (nbAttempts)) { - nbAttempts--; - if (matchIndex >= dictLimit) { - match = base + matchIndex; - matchLength = LZ4_count(ip, match, iHighLimit); - } else { - const BYTE* vLimit = ip + (dictLimit - matchIndex); - match = dictBase + matchIndex; - if (vLimit > iHighLimit) vLimit = iHighLimit; - matchLength = LZ4_count(ip, match, vLimit); - if ((ip+matchLength == vLimit) && (vLimit < iHighLimit)) - matchLength += LZ4_count(ip+matchLength, base+dictLimit, iHighLimit); - } - - if (matchLength > best_mlen) { - best_mlen = matchLength; - if (matches) { - if (matchIndex >= dictLimit) - matches[mnum].off = (int)(ip - match); - else - matches[mnum].off = (int)(ip - (base + matchIndex)); /* virtual matchpos */ - matches[mnum].len = (int)matchLength; - mnum++; - } - if (best_mlen > LZ4_OPT_NUM) break; - } - - if (ip+matchLength >= iHighLimit) /* equal : no way to know if inf or sup */ - break; /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt the tree */ - - if (*(ip+matchLength) < *(match+matchLength)) { - *ptr0 = delta0; - ptr0 = &DELTANEXTMAXD(matchIndex*2); - if (*ptr0 == (U16)-1) break; - delta0 = *ptr0; - delta1 += delta0; - matchIndex -= delta0; - } else { - *ptr1 = delta1; - ptr1 = &DELTANEXTMAXD(matchIndex*2+1); - if (*ptr1 == (U16)-1) break; - delta1 = *ptr1; - delta0 += delta1; - matchIndex -= delta1; - } - } - - *ptr0 = (U16)-1; - *ptr1 = (U16)-1; - if (matchNum) *matchNum = mnum; - /* if (best_mlen > 8) return best_mlen-8; */ - if (!matchNum) return 1; - return 1; -} - - -FORCE_INLINE void LZ4HC_updateBinTree(LZ4HC_CCtx_internal* ctx, const BYTE* const ip, const BYTE* const iHighLimit) -{ - const BYTE* const base = ctx->base; - const U32 target = (U32)(ip - base); - U32 idx = ctx->nextToUpdate; - while(idx < target) - idx += LZ4HC_BinTree_InsertAndGetAllMatches(ctx, base+idx, iHighLimit, 8, NULL, NULL); -} - - -/** Tree updater, providing best match */ -FORCE_INLINE int LZ4HC_BinTree_GetAllMatches ( - LZ4HC_CCtx_internal* ctx, - const BYTE* const ip, const BYTE* const iHighLimit, - size_t best_mlen, LZ4HC_match_t* matches, const int fullUpdate) -{ - int mnum = 0; - if (ip < ctx->base + ctx->nextToUpdate) return 0; /* skipped area */ - if (fullUpdate) LZ4HC_updateBinTree(ctx, ip, iHighLimit); - best_mlen = LZ4HC_BinTree_InsertAndGetAllMatches(ctx, ip, iHighLimit, best_mlen, matches, &mnum); - ctx->nextToUpdate = (U32)(ip - ctx->base + best_mlen); - return mnum; -} - - -#define SET_PRICE(pos, mlen, offset, litlen, price) \ -{ \ - while (last_pos < pos) { opt[last_pos+1].price = 1<<30; last_pos++; } \ - opt[pos].mlen = (int)mlen; \ - opt[pos].off = (int)offset; \ - opt[pos].litlen = (int)litlen; \ - opt[pos].price = (int)price; \ -} - - -static int LZ4HC_compress_optimal ( - LZ4HC_CCtx_internal* ctx, - const char* const source, - char* dest, - int inputSize, - int maxOutputSize, - limitedOutput_directive limit, - const size_t sufficient_len, - const int fullUpdate - ) -{ - LZ4HC_optimal_t opt[LZ4_OPT_NUM + 1]; - LZ4HC_match_t matches[LZ4_OPT_NUM + 1]; - const BYTE *inr = NULL; - size_t res, cur, cur2; - size_t i, llen, litlen, mlen, best_mlen, price, offset, best_off, match_num, last_pos; - - const BYTE* ip = (const BYTE*) source; - const BYTE* anchor = ip; - 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; - - /* init */ - ctx->end += inputSize; - ip++; - - /* Main Loop */ - while (ip < mflimit) { - memset(opt, 0, sizeof(LZ4HC_optimal_t)); - last_pos = 0; - llen = ip - anchor; - match_num = LZ4HC_BinTree_GetAllMatches(ctx, ip, matchlimit, MINMATCH-1, matches, fullUpdate); - if (!match_num) { ip++; continue; } - - if ((size_t)matches[match_num-1].len > sufficient_len) { - best_mlen = matches[match_num-1].len; - best_off = matches[match_num-1].off; - cur = 0; - last_pos = 1; - goto encode; - } - - /* set prices using matches at position = 0 */ - for (i = 0; i < match_num; i++) { - mlen = (i>0) ? (size_t)matches[i-1].len+1 : MINMATCH; - best_mlen = (matches[i].len < LZ4_OPT_NUM) ? matches[i].len : LZ4_OPT_NUM; - while (mlen <= best_mlen) { - litlen = 0; - price = LZ4HC_sequencePrice(llen + litlen, mlen) - LZ4HC_literalsPrice(llen); - SET_PRICE(mlen, mlen, matches[i].off, litlen, price); - mlen++; - } - } - - if (last_pos < MINMATCH) { ip++; continue; } - - /* check further positions */ - opt[0].mlen = opt[1].mlen = 1; - for (cur = 1; cur <= last_pos; cur++) { - inr = ip + cur; - - if (opt[cur-1].mlen == 1) { - litlen = opt[cur-1].litlen + 1; - if (cur != litlen) { - price = opt[cur - litlen].price + LZ4HC_literalsPrice(litlen); - } else { - price = LZ4HC_literalsPrice(llen + litlen) - LZ4HC_literalsPrice(llen); - } - } else { - litlen = 1; - price = opt[cur - 1].price + LZ4HC_literalsPrice(litlen); - } - - mlen = 1; - best_mlen = 0; - if (cur > last_pos || price < (size_t)opt[cur].price) - SET_PRICE(cur, mlen, best_mlen, litlen, price); - - if (cur == last_pos || inr >= mflimit) break; - - match_num = LZ4HC_BinTree_GetAllMatches(ctx, inr, matchlimit, MINMATCH-1, matches, fullUpdate); - if (match_num > 0 && (size_t)matches[match_num-1].len > sufficient_len) { - best_mlen = matches[match_num-1].len; - best_off = matches[match_num-1].off; - last_pos = cur + 1; - goto encode; - } - - /* set prices using matches at position = cur */ - for (i = 0; i < match_num; i++) { - mlen = (i>0) ? (size_t)matches[i-1].len+1 : MINMATCH; - cur2 = cur; - best_mlen = (cur2 + matches[i].len < LZ4_OPT_NUM) ? (size_t)matches[i].len : LZ4_OPT_NUM - cur2; - - while (mlen <= best_mlen) { - if (opt[cur2].mlen == 1) { - litlen = opt[cur2].litlen; - - if (cur2 != litlen) - price = opt[cur2 - litlen].price + LZ4HC_sequencePrice(litlen, mlen); - else - price = LZ4HC_sequencePrice(llen + litlen, mlen) - LZ4HC_literalsPrice(llen); - } else { - litlen = 0; - price = opt[cur2].price + LZ4HC_sequencePrice(litlen, mlen); - } - - if (cur2 + mlen > last_pos || price < (size_t)opt[cur2 + mlen].price) { // || (((int)price == opt[cur2 + mlen].price) && (opt[cur2 + mlen-1].mlen == 1))) { - SET_PRICE(cur2 + mlen, mlen, matches[i].off, litlen, price); - } - mlen++; - } - } - } /* for (cur = 1; cur <= last_pos; cur++) */ - - best_mlen = opt[last_pos].mlen; - best_off = opt[last_pos].off; - cur = last_pos - best_mlen; - -encode: /* cur, last_pos, best_mlen, best_off have to be set */ - opt[0].mlen = 1; - while (1) { - mlen = opt[cur].mlen; - offset = opt[cur].off; - opt[cur].mlen = (int)best_mlen; - opt[cur].off = (int)best_off; - best_mlen = mlen; - best_off = offset; - if (mlen > cur) break; - cur -= mlen; - } - - cur = 0; - while (cur < last_pos) { - mlen = opt[cur].mlen; - if (mlen == 1) { ip++; cur++; continue; } - offset = opt[cur].off; - cur += mlen; - - res = LZ4HC_encodeSequence(&ip, &op, &anchor, (int)mlen, ip - offset, limit, oend); - if (res) return 0; - } - } - - /* Encode Last Literals */ - { int lastRun = (int)(iend - anchor); - if ((limit) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize)) return 0; /* Check output limit */ - if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun > 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; } - else *op++ = (BYTE)(lastRun<<ML_BITS); - memcpy(op, anchor, iend - anchor); - op += iend-anchor; - } - - /* End */ - return (int) ((char*)op-dest); -} diff --git a/lib/xxhash.c b/lib/xxhash.c index e9ff2d42..3fc97fd2 100644 --- a/lib/xxhash.c +++ b/lib/xxhash.c @@ -52,7 +52,7 @@ #ifndef XXH_FORCE_MEMORY_ACCESS /* can be defined externally, on command line for example */ # if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) ) # define XXH_FORCE_MEMORY_ACCESS 2 -# elif defined(__INTEL_COMPILER) || \ +# elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || \ (defined(__GNUC__) && ( defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) || defined(__ARM_ARCH_7S__) )) # define XXH_FORCE_MEMORY_ACCESS 1 # endif @@ -113,19 +113,24 @@ static void* XXH_memcpy(void* dest, const void* src, size_t size) { return memcp ***************************************/ #ifdef _MSC_VER /* Visual Studio */ # pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ -# define FORCE_INLINE static __forceinline -#else -# if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */ -# ifdef __GNUC__ -# define FORCE_INLINE static inline __attribute__((always_inline)) -# else -# define FORCE_INLINE static inline -# endif -# else -# define FORCE_INLINE static -# endif /* __STDC_VERSION__ */ #endif +#ifndef XXH_FORCE_INLINE +# ifdef _MSC_VER /* Visual Studio */ +# define XXH_FORCE_INLINE static __forceinline +# else +# if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */ +# ifdef __GNUC__ +# define XXH_FORCE_INLINE static inline __attribute__((always_inline)) +# else +# define XXH_FORCE_INLINE static inline +# endif +# else +# define XXH_FORCE_INLINE static +# endif /* __STDC_VERSION__ */ +# endif /* _MSC_VER */ +#endif /* XXH_FORCE_INLINE */ + /* ************************************* * Basic Types @@ -218,7 +223,7 @@ typedef enum { XXH_bigEndian=0, XXH_littleEndian=1 } XXH_endianess; *****************************/ typedef enum { XXH_aligned, XXH_unaligned } XXH_alignment; -FORCE_INLINE U32 XXH_readLE32_align(const void* ptr, XXH_endianess endian, XXH_alignment align) +XXH_FORCE_INLINE U32 XXH_readLE32_align(const void* ptr, XXH_endianess endian, XXH_alignment align) { if (align==XXH_unaligned) return endian==XXH_littleEndian ? XXH_read32(ptr) : XXH_swap32(XXH_read32(ptr)); @@ -226,7 +231,7 @@ FORCE_INLINE U32 XXH_readLE32_align(const void* ptr, XXH_endianess endian, XXH_a return endian==XXH_littleEndian ? *(const U32*)ptr : XXH_swap32(*(const U32*)ptr); } -FORCE_INLINE U32 XXH_readLE32(const void* ptr, XXH_endianess endian) +XXH_FORCE_INLINE U32 XXH_readLE32(const void* ptr, XXH_endianess endian) { return XXH_readLE32_align(ptr, endian, XXH_unaligned); } @@ -261,7 +266,7 @@ static U32 XXH32_round(U32 seed, U32 input) return seed; } -FORCE_INLINE U32 XXH32_endian_align(const void* input, size_t len, U32 seed, XXH_endianess endian, XXH_alignment align) +XXH_FORCE_INLINE U32 XXH32_endian_align(const void* input, size_t len, U32 seed, XXH_endianess endian, XXH_alignment align) { const BYTE* p = (const BYTE*)input; const BYTE* bEnd = p + len; @@ -376,7 +381,7 @@ XXH_PUBLIC_API XXH_errorcode XXH32_reset(XXH32_state_t* statePtr, unsigned int s } -FORCE_INLINE XXH_errorcode XXH32_update_endian (XXH32_state_t* state, const void* input, size_t len, XXH_endianess endian) +XXH_FORCE_INLINE XXH_errorcode XXH32_update_endian (XXH32_state_t* state, const void* input, size_t len, XXH_endianess endian) { const BYTE* p = (const BYTE*)input; const BYTE* const bEnd = p + len; @@ -446,7 +451,7 @@ XXH_PUBLIC_API XXH_errorcode XXH32_update (XXH32_state_t* state_in, const void* -FORCE_INLINE U32 XXH32_digest_endian (const XXH32_state_t* state, XXH_endianess endian) +XXH_FORCE_INLINE U32 XXH32_digest_endian (const XXH32_state_t* state, XXH_endianess endian) { const BYTE * p = (const BYTE*)state->mem32; const BYTE* const bEnd = (const BYTE*)(state->mem32) + state->memsize; @@ -578,7 +583,7 @@ static U64 XXH_swap64 (U64 x) } #endif -FORCE_INLINE U64 XXH_readLE64_align(const void* ptr, XXH_endianess endian, XXH_alignment align) +XXH_FORCE_INLINE U64 XXH_readLE64_align(const void* ptr, XXH_endianess endian, XXH_alignment align) { if (align==XXH_unaligned) return endian==XXH_littleEndian ? XXH_read64(ptr) : XXH_swap64(XXH_read64(ptr)); @@ -586,7 +591,7 @@ FORCE_INLINE U64 XXH_readLE64_align(const void* ptr, XXH_endianess endian, XXH_a return endian==XXH_littleEndian ? *(const U64*)ptr : XXH_swap64(*(const U64*)ptr); } -FORCE_INLINE U64 XXH_readLE64(const void* ptr, XXH_endianess endian) +XXH_FORCE_INLINE U64 XXH_readLE64(const void* ptr, XXH_endianess endian) { return XXH_readLE64_align(ptr, endian, XXH_unaligned); } @@ -621,7 +626,7 @@ static U64 XXH64_mergeRound(U64 acc, U64 val) return acc; } -FORCE_INLINE U64 XXH64_endian_align(const void* input, size_t len, U64 seed, XXH_endianess endian, XXH_alignment align) +XXH_FORCE_INLINE U64 XXH64_endian_align(const void* input, size_t len, U64 seed, XXH_endianess endian, XXH_alignment align) { const BYTE* p = (const BYTE*)input; const BYTE* const bEnd = p + len; @@ -745,7 +750,7 @@ XXH_PUBLIC_API XXH_errorcode XXH64_reset(XXH64_state_t* statePtr, unsigned long return XXH_OK; } -FORCE_INLINE XXH_errorcode XXH64_update_endian (XXH64_state_t* state, const void* input, size_t len, XXH_endianess endian) +XXH_FORCE_INLINE XXH_errorcode XXH64_update_endian (XXH64_state_t* state, const void* input, size_t len, XXH_endianess endian) { const BYTE* p = (const BYTE*)input; const BYTE* const bEnd = p + len; @@ -810,7 +815,7 @@ XXH_PUBLIC_API XXH_errorcode XXH64_update (XXH64_state_t* state_in, const void* return XXH64_update_endian(state_in, input, len, XXH_bigEndian); } -FORCE_INLINE U64 XXH64_digest_endian (const XXH64_state_t* state, XXH_endianess endian) +XXH_FORCE_INLINE U64 XXH64_digest_endian (const XXH64_state_t* state, XXH_endianess endian) { const BYTE * p = (const BYTE*)state->mem64; const BYTE* const bEnd = (const BYTE*)state->mem64 + state->memsize; |