summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
Diffstat (limited to 'lib')
-rw-r--r--lib/Makefile12
-rw-r--r--lib/common/bitstream.h32
-rw-r--r--lib/common/error_private.c5
-rw-r--r--lib/common/huf.h20
-rw-r--r--lib/common/mem.h14
-rw-r--r--lib/common/pool.c12
-rw-r--r--lib/common/pool.h5
-rw-r--r--lib/common/threading.c1
-rw-r--r--lib/common/zstd_common.c43
-rw-r--r--lib/common/zstd_errors.h22
-rw-r--r--lib/common/zstd_internal.h68
-rw-r--r--lib/compress/huf_compress.c10
-rw-r--r--lib/compress/zstd_compress.c1569
-rw-r--r--lib/compress/zstd_opt.h45
-rw-r--r--lib/compress/zstdmt_compress.c520
-rw-r--r--lib/compress/zstdmt_compress.h62
-rw-r--r--lib/decompress/huf_decompress.c176
-rw-r--r--lib/decompress/zstd_decompress.c638
-rw-r--r--lib/dictBuilder/cover.c60
-rw-r--r--lib/dictBuilder/zdict.c70
-rw-r--r--lib/dictBuilder/zdict.h199
-rw-r--r--lib/legacy/zstd_v04.c21
-rw-r--r--lib/legacy/zstd_v05.c33
-rw-r--r--lib/legacy/zstd_v06.c25
-rw-r--r--lib/legacy/zstd_v07.c27
-rw-r--r--lib/zstd.h673
26 files changed, 2945 insertions, 1417 deletions
diff --git a/lib/Makefile b/lib/Makefile
index d8d8e179d2058..5845cf170e718 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -22,9 +22,11 @@ VERSION?= $(LIBVER)
CPPFLAGS+= -I. -I./common -DXXH_NAMESPACE=ZSTD_
CFLAGS ?= -O3
-DEBUGFLAGS = -g -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
- -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
- -Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security
+DEBUGFLAGS = -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
+ -Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
+ -Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security \
+ -Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
+ -Wredundant-decls
CFLAGS += $(DEBUGFLAGS) $(MOREFLAGS)
FLAGS = $(CPPFLAGS) $(CFLAGS)
@@ -71,7 +73,7 @@ libzstd.a: $(ZSTD_OBJ)
@echo compiling static library
@$(AR) $(ARFLAGS) $@ $^
-libzstd.a-mt: CPPFLAGS += -DZSTD_MULTHREAD
+libzstd.a-mt: CPPFLAGS += -DZSTD_MULTITHREAD
libzstd.a-mt: libzstd.a
$(LIBZSTD): LDFLAGS += -shared -fPIC -fvisibility=hidden
@@ -147,7 +149,7 @@ install: libzstd.a libzstd libzstd.pc
@$(INSTALL) -d -m 755 $(DESTDIR)$(PKGCONFIGDIR)/ $(DESTDIR)$(INCLUDEDIR)/
@$(INSTALL_DATA) libzstd.pc $(DESTDIR)$(PKGCONFIGDIR)/
@echo Installing libraries
- @$(INSTALL_LIB) libzstd.a $(DESTDIR)$(LIBDIR)
+ @$(INSTALL_DATA) libzstd.a $(DESTDIR)$(LIBDIR)
@$(INSTALL_LIB) libzstd.$(SHARED_EXT_VER) $(DESTDIR)$(LIBDIR)
@ln -sf libzstd.$(SHARED_EXT_VER) $(DESTDIR)$(LIBDIR)/libzstd.$(SHARED_EXT_MAJOR)
@ln -sf libzstd.$(SHARED_EXT_VER) $(DESTDIR)$(LIBDIR)/libzstd.$(SHARED_EXT)
diff --git a/lib/common/bitstream.h b/lib/common/bitstream.h
index ca42850df3244..07b85026c95bc 100644
--- a/lib/common/bitstream.h
+++ b/lib/common/bitstream.h
@@ -39,7 +39,6 @@
extern "C" {
#endif
-
/*
* This API consists of small unitary functions, which must be inlined for best performance.
* Since link-time-optimization is not available for all compilers,
@@ -59,7 +58,9 @@ extern "C" {
#if defined(BIT_DEBUG) && (BIT_DEBUG>=1)
# include <assert.h>
#else
-# define assert(condition) ((void)0)
+# ifndef assert
+# define assert(condition) ((void)0)
+# endif
#endif
@@ -74,6 +75,7 @@ extern "C" {
#define STREAM_ACCUMULATOR_MIN_64 57
#define STREAM_ACCUMULATOR_MIN ((U32)(MEM_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64))
+
/*-******************************************
* bitStream encoding API (write forward)
********************************************/
@@ -303,13 +305,25 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si
bitD->bitContainer = *(const BYTE*)(bitD->start);
switch(srcSize)
{
- case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
- case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
- case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
- case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
- case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
- case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8;
- default:;
+ case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
+ /* fall-through */
+
+ case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
+ /* fall-through */
+
+ case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
+ /* fall-through */
+
+ case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
+ /* fall-through */
+
+ case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
+ /* fall-through */
+
+ case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8;
+ /* fall-through */
+
+ default: break;
}
{ BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0;
diff --git a/lib/common/error_private.c b/lib/common/error_private.c
index b3287245f1ee0..2d752cd23a721 100644
--- a/lib/common/error_private.c
+++ b/lib/common/error_private.c
@@ -24,7 +24,8 @@ const char* ERR_getErrorString(ERR_enum code)
case PREFIX(frameParameter_unsupported): return "Unsupported frame parameter";
case PREFIX(frameParameter_unsupportedBy32bits): return "Frame parameter unsupported in 32-bits mode";
case PREFIX(frameParameter_windowTooLarge): return "Frame requires too much memory for decoding";
- case PREFIX(compressionParameter_unsupported): return "Compression parameter is out of bound";
+ case PREFIX(compressionParameter_unsupported): return "Compression parameter is not supported";
+ case PREFIX(compressionParameter_outOfBound): return "Compression parameter is out of bound";
case PREFIX(init_missing): return "Context should be init first";
case PREFIX(memory_allocation): return "Allocation error : not enough memory";
case PREFIX(stage_wrong): return "Operation not authorized at current processing stage";
@@ -38,6 +39,8 @@ const char* ERR_getErrorString(ERR_enum code)
case PREFIX(dictionary_corrupted): return "Dictionary is corrupted";
case PREFIX(dictionary_wrong): return "Dictionary mismatch";
case PREFIX(dictionaryCreation_failed): return "Cannot create Dictionary from provided samples";
+ case PREFIX(frameIndex_tooLarge): return "Frame index is too large";
+ case PREFIX(seekableIO): return "An I/O error occurred when reading/seeking";
case PREFIX(maxCode):
default: return notErrorCode;
}
diff --git a/lib/common/huf.h b/lib/common/huf.h
index 7873ca3d42a57..dabd359915a77 100644
--- a/lib/common/huf.h
+++ b/lib/common/huf.h
@@ -111,6 +111,18 @@ HUF_PUBLIC_API size_t HUF_compress2 (void* dst, size_t dstCapacity, const void*
#define HUF_WORKSPACE_SIZE_U32 (HUF_WORKSPACE_SIZE / sizeof(U32))
HUF_PUBLIC_API size_t HUF_compress4X_wksp (void* dst, size_t dstCapacity, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
+/**
+ * The minimum workspace size for the `workSpace` used in
+ * HUF_readDTableX2_wksp() and HUF_readDTableX4_wksp().
+ *
+ * The space used depends on HUF_TABLELOG_MAX, ranging from ~1500 bytes when
+ * HUF_TABLE_LOG_MAX=12 to ~1850 bytes when HUF_TABLE_LOG_MAX=15.
+ * Buffer overflow errors may potentially occur if code modifications result in
+ * a required workspace size greater than that specified in the following
+ * macro.
+ */
+#define HUF_DECOMPRESS_WORKSPACE_SIZE (2 << 10)
+#define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32))
/* ******************************************************************
@@ -170,8 +182,11 @@ size_t HUF_decompress4X4 (void* dst, size_t dstSize, const void* cSrc, size_t cS
size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< decodes RLE and uncompressed */
size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< considers RLE and uncompressed as errors */
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< considers RLE and uncompressed as errors */
size_t HUF_decompress4X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< single-symbol decoder */
+size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< single-symbol decoder */
size_t HUF_decompress4X4_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< double-symbols decoder */
+size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< double-symbols decoder */
/* ****************************************
@@ -243,7 +258,9 @@ HUF_decompress() does the following:
U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize);
size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize);
+size_t HUF_readDTableX2_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
size_t HUF_readDTableX4 (HUF_DTable* DTable, const void* src, size_t srcSize);
+size_t HUF_readDTableX4_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
size_t HUF_decompress4X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
@@ -266,8 +283,11 @@ size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cS
size_t HUF_decompress1X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /* double-symbol decoder */
size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);
+size_t HUF_decompress1X_DCtx_wksp (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);
size_t HUF_decompress1X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< single-symbol decoder */
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< single-symbol decoder */
size_t HUF_decompress1X4_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< double-symbols decoder */
+size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< double-symbols decoder */
size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); /**< automatic selection of sing or double symbol decoder, based on DTable */
size_t HUF_decompress1X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
diff --git a/lib/common/mem.h b/lib/common/mem.h
index 4773a8b9309ef..b0e5bf60b43b2 100644
--- a/lib/common/mem.h
+++ b/lib/common/mem.h
@@ -352,20 +352,6 @@ MEM_STATIC void MEM_writeBEST(void* memPtr, size_t val)
}
-/* function safe only for comparisons */
-MEM_STATIC U32 MEM_readMINMATCH(const void* memPtr, U32 length)
-{
- switch (length)
- {
- default :
- case 4 : return MEM_read32(memPtr);
- case 3 : if (MEM_isLittleEndian())
- return MEM_read32(memPtr)<<8;
- else
- return MEM_read32(memPtr)>>8;
- }
-}
-
#if defined (__cplusplus)
}
#endif
diff --git a/lib/common/pool.c b/lib/common/pool.c
index e439fe1b0dd6b..749fa4f2f7b41 100644
--- a/lib/common/pool.c
+++ b/lib/common/pool.c
@@ -146,6 +146,13 @@ void POOL_free(POOL_ctx *ctx) {
free(ctx);
}
+size_t POOL_sizeof(POOL_ctx *ctx) {
+ if (ctx==NULL) return 0; /* supports sizeof NULL */
+ return sizeof(*ctx)
+ + ctx->queueSize * sizeof(POOL_job)
+ + ctx->numThreads * sizeof(pthread_t);
+}
+
void POOL_add(void *ctxVoid, POOL_function function, void *opaque) {
POOL_ctx *ctx = (POOL_ctx *)ctxVoid;
if (!ctx) { return; }
@@ -191,4 +198,9 @@ void POOL_add(void *ctx, POOL_function function, void *opaque) {
function(opaque);
}
+size_t POOL_sizeof(POOL_ctx *ctx) {
+ if (ctx==NULL) return 0; /* supports sizeof NULL */
+ return sizeof(*ctx);
+}
+
#endif /* ZSTD_MULTITHREAD */
diff --git a/lib/common/pool.h b/lib/common/pool.h
index 50cb25b12c9f1..386cd674b7c06 100644
--- a/lib/common/pool.h
+++ b/lib/common/pool.h
@@ -32,6 +32,11 @@ POOL_ctx *POOL_create(size_t numThreads, size_t queueSize);
*/
void POOL_free(POOL_ctx *ctx);
+/*! POOL_sizeof() :
+ return memory usage of pool returned by POOL_create().
+*/
+size_t POOL_sizeof(POOL_ctx *ctx);
+
/*! POOL_function :
The function type that can be added to a thread pool.
*/
diff --git a/lib/common/threading.c b/lib/common/threading.c
index 32d58796a9ea0..141376c56199c 100644
--- a/lib/common/threading.c
+++ b/lib/common/threading.c
@@ -1,4 +1,3 @@
-
/**
* Copyright (c) 2016 Tino Reichardt
* All rights reserved.
diff --git a/lib/common/zstd_common.c b/lib/common/zstd_common.c
index 8408a589ae8d9..f68167238158d 100644
--- a/lib/common/zstd_common.c
+++ b/lib/common/zstd_common.c
@@ -12,16 +12,19 @@
/*-*************************************
* Dependencies
***************************************/
-#include <stdlib.h> /* malloc */
+#include <stdlib.h> /* malloc, calloc, free */
+#include <string.h> /* memset */
#include "error_private.h"
#define ZSTD_STATIC_LINKING_ONLY
-#include "zstd.h" /* declaration of ZSTD_isError, ZSTD_getErrorName, ZSTD_getErrorCode, ZSTD_getErrorString, ZSTD_versionNumber */
+#include "zstd.h"
/*-****************************************
* Version
******************************************/
-unsigned ZSTD_versionNumber (void) { return ZSTD_VERSION_NUMBER; }
+unsigned ZSTD_versionNumber(void) { return ZSTD_VERSION_NUMBER; }
+
+const char* ZSTD_versionString(void) { return ZSTD_VERSION_STRING; }
/*-****************************************
@@ -47,27 +50,31 @@ const char* ZSTD_getErrorString(ZSTD_ErrorCode code) { return ERR_getErrorString
/*=**************************************************************
* Custom allocator
****************************************************************/
-/* default uses stdlib */
-void* ZSTD_defaultAllocFunction(void* opaque, size_t size)
-{
- void* address = malloc(size);
- (void)opaque;
- return address;
-}
-
-void ZSTD_defaultFreeFunction(void* opaque, void* address)
+void* ZSTD_malloc(size_t size, ZSTD_customMem customMem)
{
- (void)opaque;
- free(address);
+ if (customMem.customAlloc)
+ return customMem.customAlloc(customMem.opaque, size);
+ return malloc(size);
}
-void* ZSTD_malloc(size_t size, ZSTD_customMem customMem)
+void* ZSTD_calloc(size_t size, ZSTD_customMem customMem)
{
- return customMem.customAlloc(customMem.opaque, size);
+ if (customMem.customAlloc) {
+ /* calloc implemented as malloc+memset;
+ * not as efficient as calloc, but next best guess for custom malloc */
+ void* const ptr = customMem.customAlloc(customMem.opaque, size);
+ memset(ptr, 0, size);
+ return ptr;
+ }
+ return calloc(1, size);
}
void ZSTD_free(void* ptr, ZSTD_customMem customMem)
{
- if (ptr!=NULL)
- customMem.customFree(customMem.opaque, ptr);
+ if (ptr!=NULL) {
+ if (customMem.customFree)
+ customMem.customFree(customMem.opaque, ptr);
+ else
+ free(ptr);
+ }
}
diff --git a/lib/common/zstd_errors.h b/lib/common/zstd_errors.h
index 3d579d9693630..19f1597aa340d 100644
--- a/lib/common/zstd_errors.h
+++ b/lib/common/zstd_errors.h
@@ -19,10 +19,12 @@ extern "C" {
/* ===== ZSTDERRORLIB_API : control library symbols visibility ===== */
-#if defined(__GNUC__) && (__GNUC__ >= 4)
-# define ZSTDERRORLIB_VISIBILITY __attribute__ ((visibility ("default")))
-#else
-# define ZSTDERRORLIB_VISIBILITY
+#ifndef ZSTDERRORLIB_VISIBILITY
+# if defined(__GNUC__) && (__GNUC__ >= 4)
+# define ZSTDERRORLIB_VISIBILITY __attribute__ ((visibility ("default")))
+# else
+# define ZSTDERRORLIB_VISIBILITY
+# endif
#endif
#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1)
# define ZSTDERRORLIB_API __declspec(dllexport) ZSTDERRORLIB_VISIBILITY
@@ -33,8 +35,11 @@ extern "C" {
#endif
/*-****************************************
-* error codes list
-******************************************/
+ * error codes list
+ * note : this API is still considered unstable
+ * it should not be used with a dynamic library
+ * only static linking is allowed
+ ******************************************/
typedef enum {
ZSTD_error_no_error,
ZSTD_error_GENERIC,
@@ -45,6 +50,7 @@ typedef enum {
ZSTD_error_frameParameter_unsupportedBy32bits,
ZSTD_error_frameParameter_windowTooLarge,
ZSTD_error_compressionParameter_unsupported,
+ ZSTD_error_compressionParameter_outOfBound,
ZSTD_error_init_missing,
ZSTD_error_memory_allocation,
ZSTD_error_stage_wrong,
@@ -58,12 +64,14 @@ typedef enum {
ZSTD_error_dictionary_corrupted,
ZSTD_error_dictionary_wrong,
ZSTD_error_dictionaryCreation_failed,
+ ZSTD_error_frameIndex_tooLarge,
+ ZSTD_error_seekableIO,
ZSTD_error_maxCode
} ZSTD_ErrorCode;
/*! ZSTD_getErrorCode() :
convert a `size_t` function result into a `ZSTD_ErrorCode` enum type,
- which can be used to compare directly with enum list published into "error_public.h" */
+ which can be used to compare with enum list published above */
ZSTDERRORLIB_API ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult);
ZSTDERRORLIB_API const char* ZSTD_getErrorString(ZSTD_ErrorCode code);
diff --git a/lib/common/zstd_internal.h b/lib/common/zstd_internal.h
index 2533333ba83cc..f2c4e6249fb89 100644
--- a/lib/common/zstd_internal.h
+++ b/lib/common/zstd_internal.h
@@ -18,6 +18,7 @@
# include <intrin.h> /* For Visual 2005 */
# pragma warning(disable : 4100) /* disable: C4100: unreferenced formal parameter */
# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
+# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */
# pragma warning(disable : 4324) /* disable: C4324: padded structure */
#else
# if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */
@@ -50,9 +51,42 @@
#define ZSTD_STATIC_LINKING_ONLY
#include "zstd.h"
#ifndef XXH_STATIC_LINKING_ONLY
-# define XXH_STATIC_LINKING_ONLY /* XXH64_state_t */
+# define XXH_STATIC_LINKING_ONLY /* XXH64_state_t */
+#endif
+#include "xxhash.h" /* XXH_reset, update, digest */
+
+
+/*-*************************************
+* Debug
+***************************************/
+#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=1)
+# include <assert.h>
+#else
+# ifndef assert
+# define assert(condition) ((void)0)
+# endif
+#endif
+
+#define ZSTD_STATIC_ASSERT(c) { enum { ZSTD_static_assert = 1/(int)(!!(c)) }; }
+
+#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=2)
+# include <stdio.h>
+/* recommended values for ZSTD_DEBUG display levels :
+ * 1 : no display, enables assert() only
+ * 2 : reserved for currently active debugging path
+ * 3 : events once per object lifetime (CCtx, CDict)
+ * 4 : events once per frame
+ * 5 : events once per block
+ * 6 : events once per sequence (*very* verbose) */
+# define DEBUGLOG(l, ...) { \
+ if (l<=ZSTD_DEBUG) { \
+ fprintf(stderr, __FILE__ ": "); \
+ fprintf(stderr, __VA_ARGS__); \
+ fprintf(stderr, " \n"); \
+ } }
+#else
+# define DEBUGLOG(l, ...) {} /* disabled */
#endif
-#include "xxhash.h" /* XXH_reset, update, digest */
/*-*************************************
@@ -70,7 +104,6 @@
* Common constants
***************************************/
#define ZSTD_OPT_NUM (1<<12)
-#define ZSTD_DICT_MAGIC 0xEC30A437 /* v0.7+ */
#define ZSTD_REP_NUM 3 /* number of repcodes */
#define ZSTD_REP_CHECK (ZSTD_REP_NUM) /* number of repcodes to check by the optimal parser */
@@ -235,15 +268,10 @@ typedef struct {
const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx);
void ZSTD_seqToCodes(const seqStore_t* seqStorePtr);
-int ZSTD_isSkipFrame(ZSTD_DCtx* dctx);
/* custom memory allocation functions */
-void* ZSTD_defaultAllocFunction(void* opaque, size_t size);
-void ZSTD_defaultFreeFunction(void* opaque, void* address);
-#ifndef ZSTD_DLL_IMPORT
-static const ZSTD_customMem defaultCustomMem = { ZSTD_defaultAllocFunction, ZSTD_defaultFreeFunction, NULL };
-#endif
void* ZSTD_malloc(size_t size, ZSTD_customMem customMem);
+void* ZSTD_calloc(size_t size, ZSTD_customMem customMem);
void ZSTD_free(void* ptr, ZSTD_customMem customMem);
@@ -281,4 +309,26 @@ MEM_STATIC U32 ZSTD_highbit32(U32 val)
void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx);
+/*! ZSTD_initCStream_internal() :
+ * Private use only. Init streaming operation.
+ * expects params to be valid.
+ * must receive dict, or cdict, or none, but not both.
+ * @return : 0, or an error code */
+size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
+ const void* dict, size_t dictSize,
+ const ZSTD_CDict* cdict,
+ ZSTD_parameters params, unsigned long long pledgedSrcSize);
+
+/*! ZSTD_compressStream_generic() :
+ * Private use only. To be called from zstdmt_compress.c in single-thread mode. */
+size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
+ ZSTD_outBuffer* output,
+ ZSTD_inBuffer* input,
+ ZSTD_EndDirective const flushMode);
+
+/*! ZSTD_getParamsFromCDict() :
+ * as the name implies */
+ZSTD_parameters ZSTD_getParamsFromCDict(const ZSTD_CDict* cdict);
+
+
#endif /* ZSTD_CCOMMON_H_MODULE */
diff --git a/lib/compress/huf_compress.c b/lib/compress/huf_compress.c
index fe11aafb8f140..7af0789a9c58e 100644
--- a/lib/compress/huf_compress.c
+++ b/lib/compress/huf_compress.c
@@ -266,7 +266,8 @@ static U32 HUF_setMaxHeight(nodeElt* huffNode, U32 lastNonNull, U32 maxNbBits)
if (highTotal <= lowTotal) break;
} }
/* only triggered when no more rank 1 symbol left => find closest one (note : there is necessarily at least one !) */
- while ((nBitsToDecrease<=HUF_TABLELOG_MAX) && (rankLast[nBitsToDecrease] == noSymbol)) /* HUF_MAX_TABLELOG test just to please gcc 5+; but it should not be necessary */
+ /* HUF_MAX_TABLELOG test just to please gcc 5+; but it should not be necessary */
+ while ((nBitsToDecrease<=HUF_TABLELOG_MAX) && (rankLast[nBitsToDecrease] == noSymbol))
nBitsToDecrease ++;
totalCost -= 1 << (nBitsToDecrease-1);
if (rankLast[nBitsToDecrease-1] == noSymbol)
@@ -463,12 +464,15 @@ size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, si
{
case 3 : HUF_encodeSymbol(&bitC, ip[n+ 2], CTable);
HUF_FLUSHBITS_2(&bitC);
+ /* fall-through */
case 2 : HUF_encodeSymbol(&bitC, ip[n+ 1], CTable);
HUF_FLUSHBITS_1(&bitC);
+ /* fall-through */
case 1 : HUF_encodeSymbol(&bitC, ip[n+ 0], CTable);
HUF_FLUSHBITS(&bitC);
- case 0 :
- default: ;
+ /* fall-through */
+ case 0 : /* fall-through */
+ default: break;
}
for (; n>0; n-=4) { /* note : n&3==0 at this stage */
diff --git a/lib/compress/zstd_compress.c b/lib/compress/zstd_compress.c
index c08b315dab935..9300357f2d388 100644
--- a/lib/compress/zstd_compress.c
+++ b/lib/compress/zstd_compress.c
@@ -9,6 +9,14 @@
/*-*************************************
+* Tuning parameters
+***************************************/
+#ifndef ZSTD_CLEVEL_DEFAULT
+# define ZSTD_CLEVEL_DEFAULT 3
+#endif
+
+
+/*-*************************************
* Dependencies
***************************************/
#include <string.h> /* memset */
@@ -18,26 +26,7 @@
#define HUF_STATIC_LINKING_ONLY
#include "huf.h"
#include "zstd_internal.h" /* includes zstd.h */
-
-
-/*-*************************************
-* Debug
-***************************************/
-#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=1)
-# include <assert.h>
-#else
-# define assert(condition) ((void)0)
-#endif
-
-#define ZSTD_STATIC_ASSERT(c) { enum { ZSTD_static_assert = 1/(int)(!!(c)) }; }
-
-#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=2)
-# include <stdio.h>
- static unsigned g_debugLevel = ZSTD_DEBUG;
-# define DEBUGLOG(l, ...) if (l<=g_debugLevel) { fprintf(stderr, __FILE__ ": "); fprintf(stderr, __VA_ARGS__); fprintf(stderr, " \n"); }
-#else
-# define DEBUGLOG(l, ...) {} /* disabled */
-#endif
+#include "zstdmt_compress.h"
/*-*************************************
@@ -79,6 +68,15 @@ static void ZSTD_resetSeqStore(seqStore_t* ssPtr)
/*-*************************************
* Context memory management
***************************************/
+typedef enum { zcss_init=0, zcss_load, zcss_flush } ZSTD_cStreamStage;
+
+struct ZSTD_CDict_s {
+ void* dictBuffer;
+ const void* dictContent;
+ size_t dictContentSize;
+ ZSTD_CCtx* refContext;
+}; /* typedef'd to ZSTD_CDict within "zstd.h" */
+
struct ZSTD_CCtx_s {
const BYTE* nextSrc; /* next block here to continue on current prefix */
const BYTE* base; /* All regular indexes relative to this position */
@@ -90,19 +88,21 @@ struct ZSTD_CCtx_s {
U32 hashLog3; /* dispatch table : larger == faster, more memory */
U32 loadedDictEnd; /* index of end of dictionary */
U32 forceWindow; /* force back-references to respect limit of 1<<wLog, even for dictionary */
- U32 forceRawDict; /* Force loading dictionary in "content-only" mode (no header analysis) */
ZSTD_compressionStage_e stage;
U32 rep[ZSTD_REP_NUM];
U32 repToConfirm[ZSTD_REP_NUM];
U32 dictID;
- ZSTD_parameters params;
+ int compressionLevel;
+ ZSTD_parameters requestedParams;
+ ZSTD_parameters appliedParams;
void* workSpace;
size_t workSpaceSize;
size_t blockSize;
- U64 frameContentSize;
+ U64 pledgedSrcSizePlusOne; /* this way, 0 (default) == unknown */
U64 consumedSrcSize;
XXH64_state_t xxhState;
ZSTD_customMem customMem;
+ size_t staticSize;
seqStore_t seqStore; /* sequences storage ptrs */
U32* hashTable;
@@ -115,31 +115,92 @@ struct ZSTD_CCtx_s {
FSE_CTable* matchlengthCTable;
FSE_CTable* litlengthCTable;
unsigned* entropyScratchSpace;
+
+ /* streaming */
+ char* inBuff;
+ size_t inBuffSize;
+ size_t inToCompress;
+ size_t inBuffPos;
+ size_t inBuffTarget;
+ char* outBuff;
+ size_t outBuffSize;
+ size_t outBuffContentSize;
+ size_t outBuffFlushedSize;
+ ZSTD_cStreamStage streamStage;
+ U32 frameEnded;
+
+ /* Dictionary */
+ ZSTD_dictMode_e dictMode; /* select restricting dictionary to "rawContent" or "fullDict" only */
+ U32 dictContentByRef;
+ ZSTD_CDict* cdictLocal;
+ const ZSTD_CDict* cdict;
+ const void* prefix;
+ size_t prefixSize;
+
+ /* Multi-threading */
+ U32 nbThreads;
+ ZSTDMT_CCtx* mtctx;
};
+
ZSTD_CCtx* ZSTD_createCCtx(void)
{
- return ZSTD_createCCtx_advanced(defaultCustomMem);
+ return ZSTD_createCCtx_advanced(ZSTD_defaultCMem);
}
ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem)
{
ZSTD_CCtx* cctx;
- if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
- if (!customMem.customAlloc || !customMem.customFree) return NULL;
+ if (!customMem.customAlloc ^ !customMem.customFree) return NULL;
- cctx = (ZSTD_CCtx*) ZSTD_malloc(sizeof(ZSTD_CCtx), customMem);
+ cctx = (ZSTD_CCtx*) ZSTD_calloc(sizeof(ZSTD_CCtx), customMem);
if (!cctx) return NULL;
- memset(cctx, 0, sizeof(ZSTD_CCtx));
cctx->customMem = customMem;
+ cctx->compressionLevel = ZSTD_CLEVEL_DEFAULT;
+ ZSTD_STATIC_ASSERT(zcss_init==0);
+ ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN==(0ULL - 1));
+ return cctx;
+}
+
+ZSTD_CCtx* ZSTD_initStaticCCtx(void *workspace, size_t workspaceSize)
+{
+ ZSTD_CCtx* cctx = (ZSTD_CCtx*) workspace;
+ if (workspaceSize <= sizeof(ZSTD_CCtx)) return NULL; /* minimum size */
+ if ((size_t)workspace & 7) return NULL; /* must be 8-aligned */
+ memset(workspace, 0, workspaceSize); /* may be a bit generous, could memset be smaller ? */
+ cctx->staticSize = workspaceSize;
+ cctx->workSpace = (void*)(cctx+1);
+ cctx->workSpaceSize = workspaceSize - sizeof(ZSTD_CCtx);
+
+ /* entropy space (never moves) */
+ /* note : this code should be shared with resetCCtx, rather than copy/pasted */
+ { void* ptr = cctx->workSpace;
+ cctx->hufCTable = (HUF_CElt*)ptr;
+ ptr = (char*)cctx->hufCTable + hufCTable_size;
+ cctx->offcodeCTable = (FSE_CTable*) ptr;
+ ptr = (char*)ptr + offcodeCTable_size;
+ cctx->matchlengthCTable = (FSE_CTable*) ptr;
+ ptr = (char*)ptr + matchlengthCTable_size;
+ cctx->litlengthCTable = (FSE_CTable*) ptr;
+ ptr = (char*)ptr + litlengthCTable_size;
+ assert(((size_t)ptr & 3) == 0); /* ensure correct alignment */
+ cctx->entropyScratchSpace = (unsigned*) ptr;
+ }
+
return cctx;
}
size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx)
{
if (cctx==NULL) return 0; /* support free on NULL */
+ if (cctx->staticSize) return ERROR(memory_allocation); /* not compatible with static CCtx */
ZSTD_free(cctx->workSpace, cctx->customMem);
+ cctx->workSpace = NULL;
+ ZSTD_freeCDict(cctx->cdictLocal);
+ cctx->cdictLocal = NULL;
+ ZSTDMT_freeCCtx(cctx->mtctx);
+ cctx->mtctx = NULL;
ZSTD_free(cctx, cctx->customMem);
return 0; /* reserved as a potential error code in the future */
}
@@ -147,46 +208,294 @@ size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx)
size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx)
{
if (cctx==NULL) return 0; /* support sizeof on NULL */
- return sizeof(*cctx) + cctx->workSpaceSize;
+ DEBUGLOG(5, "sizeof(*cctx) : %u", (U32)sizeof(*cctx));
+ DEBUGLOG(5, "workSpaceSize : %u", (U32)cctx->workSpaceSize);
+ DEBUGLOG(5, "streaming buffers : %u", (U32)(cctx->outBuffSize + cctx->inBuffSize));
+ DEBUGLOG(5, "inner MTCTX : %u", (U32)ZSTDMT_sizeof_CCtx(cctx->mtctx));
+ return sizeof(*cctx) + cctx->workSpaceSize
+ + ZSTD_sizeof_CDict(cctx->cdictLocal)
+ + cctx->outBuffSize + cctx->inBuffSize
+ + ZSTDMT_sizeof_CCtx(cctx->mtctx);
}
+size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs)
+{
+ return ZSTD_sizeof_CCtx(zcs); /* same object */
+}
+
+/* private API call, for dictBuilder only */
+const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx) { return &(ctx->seqStore); }
+
+static ZSTD_parameters ZSTD_getParamsFromCCtx(const ZSTD_CCtx* cctx) { return cctx->appliedParams; }
+
+/* older variant; will be deprecated */
size_t ZSTD_setCCtxParameter(ZSTD_CCtx* cctx, ZSTD_CCtxParameter param, unsigned value)
{
switch(param)
{
case ZSTD_p_forceWindow : cctx->forceWindow = value>0; cctx->loadedDictEnd = 0; return 0;
- case ZSTD_p_forceRawDict : cctx->forceRawDict = value>0; return 0;
+ ZSTD_STATIC_ASSERT(ZSTD_dm_auto==0);
+ ZSTD_STATIC_ASSERT(ZSTD_dm_rawContent==1);
+ case ZSTD_p_forceRawDict : cctx->dictMode = (ZSTD_dictMode_e)(value>0); return 0;
default: return ERROR(parameter_unknown);
}
}
-const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx) /* hidden interface */
+
+#define ZSTD_CLEVEL_CUSTOM 999
+static void ZSTD_cLevelToCParams(ZSTD_CCtx* cctx)
{
- return &(ctx->seqStore);
+ if (cctx->compressionLevel==ZSTD_CLEVEL_CUSTOM) return;
+ cctx->requestedParams.cParams = ZSTD_getCParams(cctx->compressionLevel,
+ cctx->pledgedSrcSizePlusOne-1, 0);
+ cctx->compressionLevel = ZSTD_CLEVEL_CUSTOM;
}
-static ZSTD_parameters ZSTD_getParamsFromCCtx(const ZSTD_CCtx* cctx)
+#define CLAMPCHECK(val,min,max) { \
+ if (((val)<(min)) | ((val)>(max))) { \
+ return ERROR(compressionParameter_outOfBound); \
+} }
+
+size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, unsigned value)
{
- return cctx->params;
+ if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
+
+ switch(param)
+ {
+ case ZSTD_p_compressionLevel :
+ if ((int)value > ZSTD_maxCLevel()) value = ZSTD_maxCLevel(); /* cap max compression level */
+ if (value == 0) return 0; /* special value : 0 means "don't change anything" */
+ if (cctx->cdict) return ERROR(stage_wrong);
+ cctx->compressionLevel = value;
+ return 0;
+
+ case ZSTD_p_windowLog :
+ DEBUGLOG(5, "setting ZSTD_p_windowLog = %u (cdict:%u)",
+ value, (cctx->cdict!=NULL));
+ if (value == 0) return 0; /* special value : 0 means "don't change anything" */
+ if (cctx->cdict) return ERROR(stage_wrong);
+ CLAMPCHECK(value, ZSTD_WINDOWLOG_MIN, ZSTD_WINDOWLOG_MAX);
+ ZSTD_cLevelToCParams(cctx);
+ cctx->requestedParams.cParams.windowLog = value;
+ return 0;
+
+ case ZSTD_p_hashLog :
+ if (value == 0) return 0; /* special value : 0 means "don't change anything" */
+ if (cctx->cdict) return ERROR(stage_wrong);
+ CLAMPCHECK(value, ZSTD_HASHLOG_MIN, ZSTD_HASHLOG_MAX);
+ ZSTD_cLevelToCParams(cctx);
+ cctx->requestedParams.cParams.hashLog = value;
+ return 0;
+
+ case ZSTD_p_chainLog :
+ if (value == 0) return 0; /* special value : 0 means "don't change anything" */
+ if (cctx->cdict) return ERROR(stage_wrong);
+ CLAMPCHECK(value, ZSTD_CHAINLOG_MIN, ZSTD_CHAINLOG_MAX);
+ ZSTD_cLevelToCParams(cctx);
+ cctx->requestedParams.cParams.chainLog = value;
+ return 0;
+
+ case ZSTD_p_searchLog :
+ if (value == 0) return 0; /* special value : 0 means "don't change anything" */
+ if (cctx->cdict) return ERROR(stage_wrong);
+ CLAMPCHECK(value, ZSTD_SEARCHLOG_MIN, ZSTD_SEARCHLOG_MAX);
+ ZSTD_cLevelToCParams(cctx);
+ cctx->requestedParams.cParams.searchLog = value;
+ return 0;
+
+ case ZSTD_p_minMatch :
+ if (value == 0) return 0; /* special value : 0 means "don't change anything" */
+ if (cctx->cdict) return ERROR(stage_wrong);
+ CLAMPCHECK(value, ZSTD_SEARCHLENGTH_MIN, ZSTD_SEARCHLENGTH_MAX);
+ ZSTD_cLevelToCParams(cctx);
+ cctx->requestedParams.cParams.searchLength = value;
+ return 0;
+
+ case ZSTD_p_targetLength :
+ if (value == 0) return 0; /* special value : 0 means "don't change anything" */
+ if (cctx->cdict) return ERROR(stage_wrong);
+ CLAMPCHECK(value, ZSTD_TARGETLENGTH_MIN, ZSTD_TARGETLENGTH_MAX);
+ ZSTD_cLevelToCParams(cctx);
+ cctx->requestedParams.cParams.targetLength = value;
+ return 0;
+
+ case ZSTD_p_compressionStrategy :
+ if (value == 0) return 0; /* special value : 0 means "don't change anything" */
+ if (cctx->cdict) return ERROR(stage_wrong);
+ CLAMPCHECK(value, (unsigned)ZSTD_fast, (unsigned)ZSTD_btultra);
+ ZSTD_cLevelToCParams(cctx);
+ cctx->requestedParams.cParams.strategy = (ZSTD_strategy)value;
+ return 0;
+
+ case ZSTD_p_contentSizeFlag :
+ DEBUGLOG(5, "set content size flag = %u", (value>0));
+ /* Content size written in frame header _when known_ (default:1) */
+ cctx->requestedParams.fParams.contentSizeFlag = value>0;
+ return 0;
+
+ case ZSTD_p_checksumFlag :
+ /* A 32-bits content checksum will be calculated and written at end of frame (default:0) */
+ cctx->requestedParams.fParams.checksumFlag = value>0;
+ return 0;
+
+ case ZSTD_p_dictIDFlag : /* When applicable, dictionary's dictID is provided in frame header (default:1) */
+ DEBUGLOG(5, "set dictIDFlag = %u", (value>0));
+ cctx->requestedParams.fParams.noDictIDFlag = (value==0);
+ return 0;
+
+ /* Dictionary parameters */
+ case ZSTD_p_dictMode :
+ if (cctx->cdict) return ERROR(stage_wrong); /* must be set before loading */
+ /* restrict dictionary mode, to "rawContent" or "fullDict" only */
+ ZSTD_STATIC_ASSERT((U32)ZSTD_dm_fullDict > (U32)ZSTD_dm_rawContent);
+ if (value > (unsigned)ZSTD_dm_fullDict)
+ return ERROR(compressionParameter_outOfBound);
+ cctx->dictMode = (ZSTD_dictMode_e)value;
+ return 0;
+
+ case ZSTD_p_refDictContent :
+ if (cctx->cdict) return ERROR(stage_wrong); /* must be set before loading */
+ /* dictionary content will be referenced, instead of copied */
+ cctx->dictContentByRef = value>0;
+ return 0;
+
+ case ZSTD_p_forceMaxWindow : /* Force back-references to remain < windowSize,
+ * even when referencing into Dictionary content
+ * default : 0 when using a CDict, 1 when using a Prefix */
+ cctx->forceWindow = value>0;
+ cctx->loadedDictEnd = 0;
+ return 0;
+
+ case ZSTD_p_nbThreads:
+ if (value==0) return 0;
+ DEBUGLOG(5, " setting nbThreads : %u", value);
+#ifndef ZSTD_MULTITHREAD
+ if (value > 1) return ERROR(compressionParameter_unsupported);
+#endif
+ if ((value>1) && (cctx->nbThreads != value)) {
+ if (cctx->staticSize) /* MT not compatible with static alloc */
+ return ERROR(compressionParameter_unsupported);
+ ZSTDMT_freeCCtx(cctx->mtctx);
+ cctx->nbThreads = 1;
+ cctx->mtctx = ZSTDMT_createCCtx(value);
+ if (cctx->mtctx == NULL) return ERROR(memory_allocation);
+ }
+ cctx->nbThreads = value;
+ return 0;
+
+ case ZSTD_p_jobSize:
+ if (cctx->nbThreads <= 1) return ERROR(compressionParameter_unsupported);
+ assert(cctx->mtctx != NULL);
+ return ZSTDMT_setMTCtxParameter(cctx->mtctx, ZSTDMT_p_sectionSize, value);
+
+ case ZSTD_p_overlapSizeLog:
+ DEBUGLOG(5, " setting overlap with nbThreads == %u", cctx->nbThreads);
+ if (cctx->nbThreads <= 1) return ERROR(compressionParameter_unsupported);
+ assert(cctx->mtctx != NULL);
+ return ZSTDMT_setMTCtxParameter(cctx->mtctx, ZSTDMT_p_overlapSectionLog, value);
+
+ default: return ERROR(parameter_unknown);
+ }
+}
+
+ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize)
+{
+ DEBUGLOG(5, " setting pledgedSrcSize to %u", (U32)pledgedSrcSize);
+ if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
+ cctx->pledgedSrcSizePlusOne = pledgedSrcSize+1;
+ return 0;
+}
+
+ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize)
+{
+ if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
+ if (cctx->staticSize) return ERROR(memory_allocation); /* no malloc for static CCtx */
+ DEBUGLOG(5, "load dictionary of size %u", (U32)dictSize);
+ ZSTD_freeCDict(cctx->cdictLocal); /* in case one already exists */
+ if (dict==NULL || dictSize==0) { /* no dictionary mode */
+ cctx->cdictLocal = NULL;
+ cctx->cdict = NULL;
+ } else {
+ ZSTD_compressionParameters const cParams =
+ cctx->compressionLevel == ZSTD_CLEVEL_CUSTOM ?
+ cctx->requestedParams.cParams :
+ ZSTD_getCParams(cctx->compressionLevel, 0, dictSize);
+ cctx->cdictLocal = ZSTD_createCDict_advanced(
+ dict, dictSize,
+ cctx->dictContentByRef, cctx->dictMode,
+ cParams, cctx->customMem);
+ cctx->cdict = cctx->cdictLocal;
+ if (cctx->cdictLocal == NULL)
+ return ERROR(memory_allocation);
+ }
+ return 0;
+}
+
+size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict)
+{
+ if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
+ cctx->cdict = cdict;
+ cctx->prefix = NULL; /* exclusive */
+ cctx->prefixSize = 0;
+ return 0;
+}
+
+size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize)
+{
+ if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
+ cctx->cdict = NULL; /* prefix discards any prior cdict */
+ cctx->prefix = prefix;
+ cctx->prefixSize = prefixSize;
+ return 0;
+}
+
+static void ZSTD_startNewCompression(ZSTD_CCtx* cctx)
+{
+ cctx->streamStage = zcss_init;
+ cctx->pledgedSrcSizePlusOne = 0;
}
+/*! ZSTD_CCtx_reset() :
+ * Also dumps dictionary */
+void ZSTD_CCtx_reset(ZSTD_CCtx* cctx)
+{
+ ZSTD_startNewCompression(cctx);
+ cctx->cdict = NULL;
+}
-/** ZSTD_checkParams() :
- ensure param values remain within authorized range.
+/** ZSTD_checkCParams() :
+ control CParam values remain within authorized range.
@return : 0, or an error code if one value is beyond authorized range */
size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams)
{
-# define CLAMPCHECK(val,min,max) { if ((val<min) | (val>max)) return ERROR(compressionParameter_unsupported); }
CLAMPCHECK(cParams.windowLog, ZSTD_WINDOWLOG_MIN, ZSTD_WINDOWLOG_MAX);
CLAMPCHECK(cParams.chainLog, ZSTD_CHAINLOG_MIN, ZSTD_CHAINLOG_MAX);
CLAMPCHECK(cParams.hashLog, ZSTD_HASHLOG_MIN, ZSTD_HASHLOG_MAX);
CLAMPCHECK(cParams.searchLog, ZSTD_SEARCHLOG_MIN, ZSTD_SEARCHLOG_MAX);
CLAMPCHECK(cParams.searchLength, ZSTD_SEARCHLENGTH_MIN, ZSTD_SEARCHLENGTH_MAX);
CLAMPCHECK(cParams.targetLength, ZSTD_TARGETLENGTH_MIN, ZSTD_TARGETLENGTH_MAX);
- if ((U32)(cParams.strategy) > (U32)ZSTD_btopt2) return ERROR(compressionParameter_unsupported);
+ if ((U32)(cParams.strategy) > (U32)ZSTD_btultra) return ERROR(compressionParameter_unsupported);
return 0;
}
+/** ZSTD_clampCParams() :
+ * make CParam values within valid range.
+ * @return : valid CParams */
+static ZSTD_compressionParameters ZSTD_clampCParams(ZSTD_compressionParameters cParams)
+{
+# define CLAMP(val,min,max) { \
+ if (val<min) val=min; \
+ else if (val>max) val=max; \
+ }
+ CLAMP(cParams.windowLog, ZSTD_WINDOWLOG_MIN, ZSTD_WINDOWLOG_MAX);
+ CLAMP(cParams.chainLog, ZSTD_CHAINLOG_MIN, ZSTD_CHAINLOG_MAX);
+ CLAMP(cParams.hashLog, ZSTD_HASHLOG_MIN, ZSTD_HASHLOG_MAX);
+ CLAMP(cParams.searchLog, ZSTD_SEARCHLOG_MIN, ZSTD_SEARCHLOG_MAX);
+ CLAMP(cParams.searchLength, ZSTD_SEARCHLENGTH_MIN, ZSTD_SEARCHLENGTH_MAX);
+ CLAMP(cParams.targetLength, ZSTD_TARGETLENGTH_MIN, ZSTD_TARGETLENGTH_MAX);
+ if ((U32)(cParams.strategy) > (U32)ZSTD_btultra) cParams.strategy = ZSTD_btultra;
+ return cParams;
+}
/** ZSTD_cycleLog() :
* condition for correct operation : hashLog > 1 */
@@ -196,14 +505,15 @@ static U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat)
return hashLog - btScale;
}
-/** ZSTD_adjustCParams() :
+/** ZSTD_adjustCParams_internal() :
optimize `cPar` for a given input (`srcSize` and `dictSize`).
mostly downsizing to reduce memory consumption and initialization.
Both `srcSize` and `dictSize` are optional (use 0 if unknown),
but if both are 0, no optimization can be done.
Note : cPar is considered validated at this stage. Use ZSTD_checkParams() to ensure that. */
-ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize)
+ZSTD_compressionParameters ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize)
{
+ assert(ZSTD_checkCParams(cPar)==0);
if (srcSize+dictSize == 0) return cPar; /* no size information available : no adjustment */
/* resize params, to use less memory when necessary */
@@ -223,10 +533,16 @@ ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, u
return cPar;
}
+ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize)
+{
+ cPar = ZSTD_clampCParams(cPar);
+ return ZSTD_adjustCParams_internal(cPar, srcSize, dictSize);
+}
-size_t ZSTD_estimateCCtxSize(ZSTD_compressionParameters cParams)
+
+size_t ZSTD_estimateCCtxSize_advanced(ZSTD_compressionParameters cParams)
{
- size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, (size_t)1 << cParams.windowLog);
+ size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << cParams.windowLog);
U32 const divider = (cParams.searchLength==3) ? 3 : 4;
size_t const maxNbSeq = blockSize / divider;
size_t const tokenSpace = blockSize + 11*maxNbSeq;
@@ -240,31 +556,64 @@ size_t ZSTD_estimateCCtxSize(ZSTD_compressionParameters cParams)
+ entropyScratchSpace_size;
size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32);
- size_t const optSpace = ((MaxML+1) + (MaxLL+1) + (MaxOff+1) + (1<<Litbits))*sizeof(U32)
+ size_t const optBudget = ((MaxML+1) + (MaxLL+1) + (MaxOff+1) + (1<<Litbits))*sizeof(U32)
+ (ZSTD_OPT_NUM+1)*(sizeof(ZSTD_match_t) + sizeof(ZSTD_optimal_t));
- size_t const neededSpace = entropySpace + tableSpace + tokenSpace
- + (((cParams.strategy == ZSTD_btopt) || (cParams.strategy == ZSTD_btopt2)) ? optSpace : 0);
+ size_t const optSpace = ((cParams.strategy == ZSTD_btopt) || (cParams.strategy == ZSTD_btultra)) ? optBudget : 0;
+ size_t const neededSpace = entropySpace + tableSpace + tokenSpace + optSpace;
+ DEBUGLOG(5, "sizeof(ZSTD_CCtx) : %u", (U32)sizeof(ZSTD_CCtx));
+ DEBUGLOG(5, "estimate workSpace : %u", (U32)neededSpace);
return sizeof(ZSTD_CCtx) + neededSpace;
}
+size_t ZSTD_estimateCCtxSize(int compressionLevel)
+{
+ ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, 0, 0);
+ return ZSTD_estimateCCtxSize_advanced(cParams);
+}
-static U32 ZSTD_equivalentParams(ZSTD_parameters param1, ZSTD_parameters param2)
+size_t ZSTD_estimateCStreamSize_advanced(ZSTD_compressionParameters cParams)
{
- return (param1.cParams.hashLog == param2.cParams.hashLog)
- & (param1.cParams.chainLog == param2.cParams.chainLog)
- & (param1.cParams.strategy == param2.cParams.strategy)
- & ((param1.cParams.searchLength==3) == (param2.cParams.searchLength==3));
+ size_t const CCtxSize = ZSTD_estimateCCtxSize_advanced(cParams);
+ size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << cParams.windowLog);
+ size_t const inBuffSize = ((size_t)1 << cParams.windowLog) + blockSize;
+ size_t const outBuffSize = ZSTD_compressBound(blockSize) + 1;
+ size_t const streamingSize = inBuffSize + outBuffSize;
+
+ return CCtxSize + streamingSize;
+}
+
+size_t ZSTD_estimateCStreamSize(int compressionLevel) {
+ ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, 0, 0);
+ return ZSTD_estimateCStreamSize_advanced(cParams);
+}
+
+
+static U32 ZSTD_equivalentParams(ZSTD_compressionParameters cParams1,
+ ZSTD_compressionParameters cParams2)
+{
+ U32 bslog1 = MIN(cParams1.windowLog, ZSTD_BLOCKSIZELOG_MAX);
+ U32 bslog2 = MIN(cParams2.windowLog, ZSTD_BLOCKSIZELOG_MAX);
+ return (bslog1 == bslog2) /* same block size */
+ & (cParams1.hashLog == cParams2.hashLog)
+ & (cParams1.chainLog == cParams2.chainLog)
+ & (cParams1.strategy == cParams2.strategy) /* opt parser space */
+ & ((cParams1.searchLength==3) == (cParams2.searchLength==3)); /* hashlog3 space */
}
/*! ZSTD_continueCCtx() :
- reuse CCtx without reset (note : requires no dictionary) */
-static size_t ZSTD_continueCCtx(ZSTD_CCtx* cctx, ZSTD_parameters params, U64 frameContentSize)
+ * reuse CCtx without reset (note : requires no dictionary) */
+static size_t ZSTD_continueCCtx(ZSTD_CCtx* cctx, ZSTD_parameters params, U64 pledgedSrcSize)
{
U32 const end = (U32)(cctx->nextSrc - cctx->base);
- cctx->params = params;
- cctx->frameContentSize = frameContentSize;
+ DEBUGLOG(5, "continue mode");
+ cctx->appliedParams = params;
+ cctx->pledgedSrcSizePlusOne = pledgedSrcSize+1;
cctx->consumedSrcSize = 0;
+ if (pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN)
+ cctx->appliedParams.fParams.contentSizeFlag = 0;
+ DEBUGLOG(5, "pledged content size : %u ; flag : %u",
+ (U32)pledgedSrcSize, cctx->appliedParams.fParams.contentSizeFlag);
cctx->lowLimit = end;
cctx->dictLimit = end;
cctx->nextToUpdate = end+1;
@@ -277,30 +626,39 @@ static size_t ZSTD_continueCCtx(ZSTD_CCtx* cctx, ZSTD_parameters params, U64 fra
return 0;
}
-typedef enum { ZSTDcrp_continue, ZSTDcrp_noMemset, ZSTDcrp_fullReset } ZSTD_compResetPolicy_e;
+typedef enum { ZSTDcrp_continue, ZSTDcrp_noMemset } ZSTD_compResetPolicy_e;
+typedef enum { ZSTDb_not_buffered, ZSTDb_buffered } ZSTD_buffered_policy_e;
/*! ZSTD_resetCCtx_internal() :
- note : `params` must be validated */
-static size_t ZSTD_resetCCtx_internal (ZSTD_CCtx* zc,
- ZSTD_parameters params, U64 frameContentSize,
- ZSTD_compResetPolicy_e const crp)
+ note : `params` are assumed fully validated at this stage */
+static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
+ ZSTD_parameters params, U64 pledgedSrcSize,
+ ZSTD_compResetPolicy_e const crp,
+ ZSTD_buffered_policy_e const zbuff)
{
- if (crp == ZSTDcrp_continue)
- if (ZSTD_equivalentParams(params, zc->params)) {
+ assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
+
+ if (crp == ZSTDcrp_continue) {
+ if (ZSTD_equivalentParams(params.cParams, zc->appliedParams.cParams)) {
+ DEBUGLOG(5, "ZSTD_equivalentParams()==1");
zc->fseCTables_ready = 0;
zc->hufCTable_repeatMode = HUF_repeat_none;
- return ZSTD_continueCCtx(zc, params, frameContentSize);
- }
+ return ZSTD_continueCCtx(zc, params, pledgedSrcSize);
+ } }
- { size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, (size_t)1 << params.cParams.windowLog);
+ { size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << params.cParams.windowLog);
U32 const divider = (params.cParams.searchLength==3) ? 3 : 4;
size_t const maxNbSeq = blockSize / divider;
size_t const tokenSpace = blockSize + 11*maxNbSeq;
- size_t const chainSize = (params.cParams.strategy == ZSTD_fast) ? 0 : (1 << params.cParams.chainLog);
+ size_t const chainSize = (params.cParams.strategy == ZSTD_fast) ?
+ 0 : (1 << params.cParams.chainLog);
size_t const hSize = ((size_t)1) << params.cParams.hashLog;
- U32 const hashLog3 = (params.cParams.searchLength>3) ? 0 : MIN(ZSTD_HASHLOG3_MAX, params.cParams.windowLog);
+ U32 const hashLog3 = (params.cParams.searchLength>3) ?
+ 0 : MIN(ZSTD_HASHLOG3_MAX, params.cParams.windowLog);
size_t const h3Size = ((size_t)1) << hashLog3;
size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32);
+ size_t const buffOutSize = (zbuff==ZSTDb_buffered) ? ZSTD_compressBound(blockSize)+1 : 0;
+ size_t const buffInSize = (zbuff==ZSTDb_buffered) ? ((size_t)1 << params.cParams.windowLog) + blockSize : 0;
void* ptr;
/* Check if workSpace is large enough, alloc a new one if needed */
@@ -309,9 +667,20 @@ static size_t ZSTD_resetCCtx_internal (ZSTD_CCtx* zc,
+ entropyScratchSpace_size;
size_t const optPotentialSpace = ((MaxML+1) + (MaxLL+1) + (MaxOff+1) + (1<<Litbits)) * sizeof(U32)
+ (ZSTD_OPT_NUM+1) * (sizeof(ZSTD_match_t)+sizeof(ZSTD_optimal_t));
- size_t const optSpace = ((params.cParams.strategy == ZSTD_btopt) || (params.cParams.strategy == ZSTD_btopt2)) ? optPotentialSpace : 0;
- size_t const neededSpace = entropySpace + optSpace + tableSpace + tokenSpace;
- if (zc->workSpaceSize < neededSpace) {
+ size_t const optSpace = ( (params.cParams.strategy == ZSTD_btopt)
+ || (params.cParams.strategy == ZSTD_btultra)) ?
+ optPotentialSpace : 0;
+ size_t const bufferSpace = buffInSize + buffOutSize;
+ size_t const neededSpace = entropySpace + optSpace + tableSpace
+ + tokenSpace + bufferSpace;
+
+ if (zc->workSpaceSize < neededSpace) { /* too small : resize /*/
+ DEBUGLOG(5, "Need to update workSpaceSize from %uK to %uK \n",
+ (unsigned)zc->workSpaceSize>>10,
+ (unsigned)neededSpace>>10);
+ /* static cctx : no resize, error out */
+ if (zc->staticSize) return ERROR(memory_allocation);
+
zc->workSpaceSize = 0;
ZSTD_free(zc->workSpace, zc->customMem);
zc->workSpace = ZSTD_malloc(neededSpace, zc->customMem);
@@ -333,10 +702,14 @@ static size_t ZSTD_resetCCtx_internal (ZSTD_CCtx* zc,
} }
/* init params */
- zc->params = params;
- zc->blockSize = blockSize;
- zc->frameContentSize = frameContentSize;
+ zc->appliedParams = params;
+ zc->pledgedSrcSizePlusOne = pledgedSrcSize+1;
zc->consumedSrcSize = 0;
+ if (pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN)
+ zc->appliedParams.fParams.contentSizeFlag = 0;
+ DEBUGLOG(5, "pledged content size : %u ; flag : %u",
+ (U32)pledgedSrcSize, zc->appliedParams.fParams.contentSizeFlag);
+ zc->blockSize = blockSize;
XXH64_reset(&zc->xxhState, 0);
zc->stage = ZSTDcs_init;
@@ -363,7 +736,8 @@ static size_t ZSTD_resetCCtx_internal (ZSTD_CCtx* zc,
ptr = (char*)zc->entropyScratchSpace + entropyScratchSpace_size;
/* opt parser space */
- if ((params.cParams.strategy == ZSTD_btopt) || (params.cParams.strategy == ZSTD_btopt2)) {
+ if ((params.cParams.strategy == ZSTD_btopt) || (params.cParams.strategy == ZSTD_btultra)) {
+ DEBUGLOG(5, "reserving optimal parser space");
assert(((size_t)ptr & 3) == 0); /* ensure ptr is properly aligned */
zc->seqStore.litFreq = (U32*)ptr;
zc->seqStore.litLengthFreq = zc->seqStore.litFreq + (1<<Litbits);
@@ -391,6 +765,13 @@ static size_t ZSTD_resetCCtx_internal (ZSTD_CCtx* zc,
zc->seqStore.mlCode = zc->seqStore.llCode + maxNbSeq;
zc->seqStore.ofCode = zc->seqStore.mlCode + maxNbSeq;
zc->seqStore.litStart = zc->seqStore.ofCode + maxNbSeq;
+ ptr = zc->seqStore.litStart + blockSize;
+
+ /* buffers */
+ zc->inBuffSize = buffInSize;
+ zc->inBuff = (char*)ptr;
+ zc->outBuffSize = buffOutSize;
+ zc->outBuff = zc->inBuff + buffInSize;
return 0;
}
@@ -411,21 +792,25 @@ void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx) {
* Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()).
* pledgedSrcSize=0 means "empty" if fParams.contentSizeFlag=1
* @return : 0, or an error code */
-size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx,
- ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize)
+static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx,
+ const ZSTD_CCtx* srcCCtx,
+ ZSTD_frameParameters fParams,
+ unsigned long long pledgedSrcSize,
+ ZSTD_buffered_policy_e zbuff)
{
+ DEBUGLOG(5, "ZSTD_copyCCtx_internal");
if (srcCCtx->stage!=ZSTDcs_init) return ERROR(stage_wrong);
memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem));
- { ZSTD_parameters params = srcCCtx->params;
+ { ZSTD_parameters params = srcCCtx->appliedParams;
params.fParams = fParams;
- DEBUGLOG(5, "ZSTD_resetCCtx_internal : dictIDFlag : %u \n", !fParams.noDictIDFlag);
- ZSTD_resetCCtx_internal(dstCCtx, params, pledgedSrcSize, ZSTDcrp_noMemset);
+ ZSTD_resetCCtx_internal(dstCCtx, params, pledgedSrcSize,
+ ZSTDcrp_noMemset, zbuff);
}
/* copy tables */
- { size_t const chainSize = (srcCCtx->params.cParams.strategy == ZSTD_fast) ? 0 : (1 << srcCCtx->params.cParams.chainLog);
- size_t const hSize = (size_t)1 << srcCCtx->params.cParams.hashLog;
+ { size_t const chainSize = (srcCCtx->appliedParams.cParams.strategy == ZSTD_fast) ? 0 : (1 << srcCCtx->appliedParams.cParams.chainLog);
+ size_t const hSize = (size_t)1 << srcCCtx->appliedParams.cParams.hashLog;
size_t const h3Size = (size_t)1 << srcCCtx->hashLog3;
size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32);
assert((U32*)dstCCtx->chainTable == (U32*)dstCCtx->hashTable + hSize); /* chainTable must follow hashTable */
@@ -467,9 +852,11 @@ size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx,
size_t ZSTD_copyCCtx(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx, unsigned long long pledgedSrcSize)
{
ZSTD_frameParameters fParams = { 1 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ };
+ ZSTD_buffered_policy_e const zbuff = (ZSTD_buffered_policy_e)(srcCCtx->inBuffSize>0);
+ ZSTD_STATIC_ASSERT((U32)ZSTDb_buffered==1);
fParams.contentSizeFlag = pledgedSrcSize>0;
- return ZSTD_copyCCtx_internal(dstCCtx, srcCCtx, fParams, pledgedSrcSize);
+ return ZSTD_copyCCtx_internal(dstCCtx, srcCCtx, fParams, pledgedSrcSize, zbuff);
}
@@ -488,10 +875,10 @@ static void ZSTD_reduceTable (U32* const table, U32 const size, U32 const reduce
* rescale all indexes to avoid future overflow (indexes are U32) */
static void ZSTD_reduceIndex (ZSTD_CCtx* zc, const U32 reducerValue)
{
- { U32 const hSize = 1 << zc->params.cParams.hashLog;
+ { U32 const hSize = 1 << zc->appliedParams.cParams.hashLog;
ZSTD_reduceTable(zc->hashTable, hSize, reducerValue); }
- { U32 const chainSize = (zc->params.cParams.strategy == ZSTD_fast) ? 0 : (1 << zc->params.cParams.chainLog);
+ { U32 const chainSize = (zc->appliedParams.cParams.strategy == ZSTD_fast) ? 0 : (1 << zc->appliedParams.cParams.chainLog);
ZSTD_reduceTable(zc->chainTable, chainSize, reducerValue); }
{ U32 const h3Size = (zc->hashLog3) ? 1 << zc->hashLog3 : 0;
@@ -529,10 +916,11 @@ static size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void
case 2: /* 2 - 2 - 12 */
MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
break;
- default: /*note : should not be necessary : flSize is within {1,2,3} */
case 3: /* 2 - 2 - 20 */
MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
break;
+ default: /* not necessary : flSize is {1,2,3} */
+ assert(0);
}
memcpy(ostart + flSize, src, srcSize);
@@ -554,10 +942,11 @@ static size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, cons
case 2: /* 2 - 2 - 12 */
MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
break;
- default: /*note : should not be necessary : flSize is necessarily within {1,2,3} */
case 3: /* 2 - 2 - 20 */
MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
break;
+ default: /* not necessary : flSize is {1,2,3} */
+ assert(0);
}
ostart[flSize] = *(const BYTE*)src;
@@ -587,7 +976,7 @@ static size_t ZSTD_compressLiterals (ZSTD_CCtx* zc,
if (dstCapacity < lhSize+1) return ERROR(dstSize_tooSmall); /* not enough space for compression */
{ HUF_repeat repeat = zc->hufCTable_repeatMode;
- int const preferRepeat = zc->params.cParams.strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
+ int const preferRepeat = zc->appliedParams.cParams.strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
zc->entropyScratchSpace, entropyScratchSpace_size, zc->hufCTable, &repeat, preferRepeat)
@@ -619,13 +1008,14 @@ static size_t ZSTD_compressLiterals (ZSTD_CCtx* zc,
MEM_writeLE32(ostart, lhc);
break;
}
- default: /* should not be necessary, lhSize is only {3,4,5} */
case 5: /* 2 - 2 - 18 - 18 */
{ U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
MEM_writeLE32(ostart, lhc);
ostart[4] = (BYTE)(cLitSize >> 10);
break;
}
+ default: /* not possible : lhSize is {3,4,5} */
+ assert(0);
}
return lhSize+cLitSize;
}
@@ -676,7 +1066,7 @@ MEM_STATIC size_t ZSTD_compressSequences (ZSTD_CCtx* zc,
void* dst, size_t dstCapacity,
size_t srcSize)
{
- const int longOffsets = zc->params.cParams.windowLog > STREAM_ACCUMULATOR_MIN;
+ const int longOffsets = zc->appliedParams.cParams.windowLog > STREAM_ACCUMULATOR_MIN;
const seqStore_t* seqStorePtr = &(zc->seqStore);
U32 count[MaxSeq+1];
S16 norm[MaxSeq+1];
@@ -881,12 +1271,6 @@ _check_compressibility:
return op - ostart;
}
-#if 0 /* for debug */
-# define STORESEQ_DEBUG
-#include <stdio.h> /* fprintf */
-U32 g_startDebug = 0;
-const BYTE* g_start = NULL;
-#endif
/*! ZSTD_storeSeq() :
Store a sequence (literal length, literals, offset code and match length code) into seqStore_t.
@@ -895,16 +1279,16 @@ const BYTE* g_start = NULL;
*/
MEM_STATIC void ZSTD_storeSeq(seqStore_t* seqStorePtr, size_t litLength, const void* literals, U32 offsetCode, size_t matchCode)
{
-#ifdef STORESEQ_DEBUG
- if (g_startDebug) {
- const U32 pos = (U32)((const BYTE*)literals - g_start);
- if (g_start==NULL) g_start = (const BYTE*)literals;
- if ((pos > 1895000) && (pos < 1895300))
- DEBUGLOG(5, "Cpos %6u :%5u literals & match %3u bytes at distance %6u \n",
- pos, (U32)litLength, (U32)matchCode+MINMATCH, (U32)offsetCode);
- }
+#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG >= 6)
+ static const BYTE* g_start = NULL;
+ U32 const pos = (U32)((const BYTE*)literals - g_start);
+ if (g_start==NULL) g_start = (const BYTE*)literals;
+ if ((pos > 0) && (pos < 1000000000))
+ DEBUGLOG(6, "Cpos %6u :%5u literals & match %3u bytes at distance %6u",
+ pos, (U32)litLength, (U32)matchCode+MINMATCH, (U32)offsetCode);
#endif
/* copy Literals */
+ assert(seqStorePtr->lit + litLength <= seqStorePtr->litStart + 128 KB);
ZSTD_wildcopy(seqStorePtr->lit, literals, litLength);
seqStorePtr->lit += litLength;
@@ -1078,7 +1462,7 @@ static size_t ZSTD_hashPtr(const void* p, U32 hBits, U32 mls)
static void ZSTD_fillHashTable (ZSTD_CCtx* zc, const void* end, const U32 mls)
{
U32* const hashTable = zc->hashTable;
- U32 const hBits = zc->params.cParams.hashLog;
+ U32 const hBits = zc->appliedParams.cParams.hashLog;
const BYTE* const base = zc->base;
const BYTE* ip = base + zc->nextToUpdate;
const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE;
@@ -1097,7 +1481,7 @@ void ZSTD_compressBlock_fast_generic(ZSTD_CCtx* cctx,
const U32 mls)
{
U32* const hashTable = cctx->hashTable;
- U32 const hBits = cctx->params.cParams.hashLog;
+ U32 const hBits = cctx->appliedParams.cParams.hashLog;
seqStore_t* seqStorePtr = &(cctx->seqStore);
const BYTE* const base = cctx->base;
const BYTE* const istart = (const BYTE*)src;
@@ -1182,7 +1566,7 @@ void ZSTD_compressBlock_fast_generic(ZSTD_CCtx* cctx,
static void ZSTD_compressBlock_fast(ZSTD_CCtx* ctx,
const void* src, size_t srcSize)
{
- const U32 mls = ctx->params.cParams.searchLength;
+ const U32 mls = ctx->appliedParams.cParams.searchLength;
switch(mls)
{
default: /* includes case 3 */
@@ -1203,7 +1587,7 @@ static void ZSTD_compressBlock_fast_extDict_generic(ZSTD_CCtx* ctx,
const U32 mls)
{
U32* hashTable = ctx->hashTable;
- const U32 hBits = ctx->params.cParams.hashLog;
+ const U32 hBits = ctx->appliedParams.cParams.hashLog;
seqStore_t* seqStorePtr = &(ctx->seqStore);
const BYTE* const base = ctx->base;
const BYTE* const dictBase = ctx->dictBase;
@@ -1296,7 +1680,7 @@ static void ZSTD_compressBlock_fast_extDict_generic(ZSTD_CCtx* ctx,
static void ZSTD_compressBlock_fast_extDict(ZSTD_CCtx* ctx,
const void* src, size_t srcSize)
{
- U32 const mls = ctx->params.cParams.searchLength;
+ U32 const mls = ctx->appliedParams.cParams.searchLength;
switch(mls)
{
default: /* includes case 3 */
@@ -1318,9 +1702,9 @@ static void ZSTD_compressBlock_fast_extDict(ZSTD_CCtx* ctx,
static void ZSTD_fillDoubleHashTable (ZSTD_CCtx* cctx, const void* end, const U32 mls)
{
U32* const hashLarge = cctx->hashTable;
- U32 const hBitsL = cctx->params.cParams.hashLog;
+ U32 const hBitsL = cctx->appliedParams.cParams.hashLog;
U32* const hashSmall = cctx->chainTable;
- U32 const hBitsS = cctx->params.cParams.chainLog;
+ U32 const hBitsS = cctx->appliedParams.cParams.chainLog;
const BYTE* const base = cctx->base;
const BYTE* ip = base + cctx->nextToUpdate;
const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE;
@@ -1340,9 +1724,9 @@ void ZSTD_compressBlock_doubleFast_generic(ZSTD_CCtx* cctx,
const U32 mls)
{
U32* const hashLong = cctx->hashTable;
- const U32 hBitsL = cctx->params.cParams.hashLog;
+ const U32 hBitsL = cctx->appliedParams.cParams.hashLog;
U32* const hashSmall = cctx->chainTable;
- const U32 hBitsS = cctx->params.cParams.chainLog;
+ const U32 hBitsS = cctx->appliedParams.cParams.chainLog;
seqStore_t* seqStorePtr = &(cctx->seqStore);
const BYTE* const base = cctx->base;
const BYTE* const istart = (const BYTE*)src;
@@ -1452,7 +1836,7 @@ void ZSTD_compressBlock_doubleFast_generic(ZSTD_CCtx* cctx,
static void ZSTD_compressBlock_doubleFast(ZSTD_CCtx* ctx, const void* src, size_t srcSize)
{
- const U32 mls = ctx->params.cParams.searchLength;
+ const U32 mls = ctx->appliedParams.cParams.searchLength;
switch(mls)
{
default: /* includes case 3 */
@@ -1473,9 +1857,9 @@ static void ZSTD_compressBlock_doubleFast_extDict_generic(ZSTD_CCtx* ctx,
const U32 mls)
{
U32* const hashLong = ctx->hashTable;
- U32 const hBitsL = ctx->params.cParams.hashLog;
+ U32 const hBitsL = ctx->appliedParams.cParams.hashLog;
U32* const hashSmall = ctx->chainTable;
- U32 const hBitsS = ctx->params.cParams.chainLog;
+ U32 const hBitsS = ctx->appliedParams.cParams.chainLog;
seqStore_t* seqStorePtr = &(ctx->seqStore);
const BYTE* const base = ctx->base;
const BYTE* const dictBase = ctx->dictBase;
@@ -1602,7 +1986,7 @@ static void ZSTD_compressBlock_doubleFast_extDict_generic(ZSTD_CCtx* ctx,
static void ZSTD_compressBlock_doubleFast_extDict(ZSTD_CCtx* ctx,
const void* src, size_t srcSize)
{
- U32 const mls = ctx->params.cParams.searchLength;
+ U32 const mls = ctx->appliedParams.cParams.searchLength;
switch(mls)
{
default: /* includes case 3 */
@@ -1628,10 +2012,10 @@ static U32 ZSTD_insertBt1(ZSTD_CCtx* zc, const BYTE* const ip, const U32 mls, co
U32 extDict)
{
U32* const hashTable = zc->hashTable;
- U32 const hashLog = zc->params.cParams.hashLog;
+ U32 const hashLog = zc->appliedParams.cParams.hashLog;
size_t const h = ZSTD_hashPtr(ip, hashLog, mls);
U32* const bt = zc->chainTable;
- U32 const btLog = zc->params.cParams.chainLog - 1;
+ U32 const btLog = zc->appliedParams.cParams.chainLog - 1;
U32 const btMask = (1 << btLog) - 1;
U32 matchIndex = hashTable[h];
size_t commonLengthSmaller=0, commonLengthLarger=0;
@@ -1733,10 +2117,10 @@ static size_t ZSTD_insertBtAndFindBestMatch (
U32 extDict)
{
U32* const hashTable = zc->hashTable;
- U32 const hashLog = zc->params.cParams.hashLog;
+ U32 const hashLog = zc->appliedParams.cParams.hashLog;
size_t const h = ZSTD_hashPtr(ip, hashLog, mls);
U32* const bt = zc->chainTable;
- U32 const btLog = zc->params.cParams.chainLog - 1;
+ U32 const btLog = zc->appliedParams.cParams.chainLog - 1;
U32 const btMask = (1 << btLog) - 1;
U32 matchIndex = hashTable[h];
size_t commonLengthSmaller=0, commonLengthLarger=0;
@@ -1896,9 +2280,9 @@ FORCE_INLINE
U32 ZSTD_insertAndFindFirstIndex (ZSTD_CCtx* zc, const BYTE* ip, U32 mls)
{
U32* const hashTable = zc->hashTable;
- const U32 hashLog = zc->params.cParams.hashLog;
+ const U32 hashLog = zc->appliedParams.cParams.hashLog;
U32* const chainTable = zc->chainTable;
- const U32 chainMask = (1 << zc->params.cParams.chainLog) - 1;
+ const U32 chainMask = (1 << zc->appliedParams.cParams.chainLog) - 1;
const BYTE* const base = zc->base;
const U32 target = (U32)(ip - base);
U32 idx = zc->nextToUpdate;
@@ -1915,8 +2299,8 @@ U32 ZSTD_insertAndFindFirstIndex (ZSTD_CCtx* zc, const BYTE* ip, U32 mls)
}
-
-FORCE_INLINE /* inlining is important to hardwire a hot branch (template emulation) */
+/* inlining is important to hardwire a hot branch (template emulation) */
+FORCE_INLINE
size_t ZSTD_HcFindBestMatch_generic (
ZSTD_CCtx* zc, /* Index table will be updated */
const BYTE* const ip, const BYTE* const iLimit,
@@ -1924,7 +2308,7 @@ size_t ZSTD_HcFindBestMatch_generic (
const U32 maxNbAttempts, const U32 mls, const U32 extDict)
{
U32* const chainTable = zc->chainTable;
- const U32 chainSize = (1 << zc->params.cParams.chainLog);
+ const U32 chainSize = (1 << zc->appliedParams.cParams.chainLog);
const U32 chainMask = chainSize-1;
const BYTE* const base = zc->base;
const BYTE* const dictBase = zc->dictBase;
@@ -2018,8 +2402,8 @@ void ZSTD_compressBlock_lazy_generic(ZSTD_CCtx* ctx,
const BYTE* const ilimit = iend - 8;
const BYTE* const base = ctx->base + ctx->dictLimit;
- U32 const maxSearches = 1 << ctx->params.cParams.searchLog;
- U32 const mls = ctx->params.cParams.searchLength;
+ U32 const maxSearches = 1 << ctx->appliedParams.cParams.searchLog;
+ U32 const mls = ctx->appliedParams.cParams.searchLength;
typedef size_t (*searchMax_f)(ZSTD_CCtx* zc, const BYTE* ip, const BYTE* iLimit,
size_t* offsetPtr,
@@ -2101,15 +2485,19 @@ void ZSTD_compressBlock_lazy_generic(ZSTD_CCtx* ctx,
break; /* nothing found : store previous solution */
}
+ /* NOTE:
+ * start[-offset+ZSTD_REP_MOVE-1] is undefined behavior.
+ * (-offset+ZSTD_REP_MOVE-1) is unsigned, and is added to start, which
+ * overflows the pointer, which is undefined behavior.
+ */
/* catch up */
if (offset) {
while ( (start > anchor)
&& (start > base+offset-ZSTD_REP_MOVE)
- && (start[-1] == start[-1-offset+ZSTD_REP_MOVE]) ) /* only search for offset within prefix */
+ && (start[-1] == (start-offset+ZSTD_REP_MOVE)[-1]) ) /* only search for offset within prefix */
{ start--; matchLength++; }
offset_2 = offset_1; offset_1 = (U32)(offset - ZSTD_REP_MOVE);
}
-
/* store sequence */
_storeSequence:
{ size_t const litLength = start - anchor;
@@ -2182,8 +2570,8 @@ void ZSTD_compressBlock_lazy_extDict_generic(ZSTD_CCtx* ctx,
const BYTE* const dictEnd = dictBase + dictLimit;
const BYTE* const dictStart = dictBase + ctx->lowLimit;
- const U32 maxSearches = 1 << ctx->params.cParams.searchLog;
- const U32 mls = ctx->params.cParams.searchLength;
+ const U32 maxSearches = 1 << ctx->appliedParams.cParams.searchLog;
+ const U32 mls = ctx->appliedParams.cParams.searchLength;
typedef size_t (*searchMax_f)(ZSTD_CCtx* zc, const BYTE* ip, const BYTE* iLimit,
size_t* offsetPtr,
@@ -2370,7 +2758,7 @@ static void ZSTD_compressBlock_btopt(ZSTD_CCtx* ctx, const void* src, size_t src
#endif
}
-static void ZSTD_compressBlock_btopt2(ZSTD_CCtx* ctx, const void* src, size_t srcSize)
+static void ZSTD_compressBlock_btultra(ZSTD_CCtx* ctx, const void* src, size_t srcSize)
{
#ifdef ZSTD_OPT_H_91842398743
ZSTD_compressBlock_opt_generic(ctx, src, srcSize, 1);
@@ -2390,7 +2778,7 @@ static void ZSTD_compressBlock_btopt_extDict(ZSTD_CCtx* ctx, const void* src, si
#endif
}
-static void ZSTD_compressBlock_btopt2_extDict(ZSTD_CCtx* ctx, const void* src, size_t srcSize)
+static void ZSTD_compressBlock_btultra_extDict(ZSTD_CCtx* ctx, const void* src, size_t srcSize)
{
#ifdef ZSTD_OPT_H_91842398743
ZSTD_compressBlock_opt_extDict_generic(ctx, src, srcSize, 1);
@@ -2401,26 +2789,32 @@ static void ZSTD_compressBlock_btopt2_extDict(ZSTD_CCtx* ctx, const void* src, s
}
+/* ZSTD_selectBlockCompressor() :
+ * assumption : strat is a valid strategy */
typedef void (*ZSTD_blockCompressor) (ZSTD_CCtx* ctx, const void* src, size_t srcSize);
-
static ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, int extDict)
{
- static const ZSTD_blockCompressor blockCompressor[2][8] = {
- { ZSTD_compressBlock_fast, ZSTD_compressBlock_doubleFast, ZSTD_compressBlock_greedy,
+ static const ZSTD_blockCompressor blockCompressor[2][(unsigned)ZSTD_btultra+1] = {
+ { ZSTD_compressBlock_fast /* default for 0 */,
+ ZSTD_compressBlock_fast, ZSTD_compressBlock_doubleFast, ZSTD_compressBlock_greedy,
ZSTD_compressBlock_lazy, ZSTD_compressBlock_lazy2, ZSTD_compressBlock_btlazy2,
- ZSTD_compressBlock_btopt, ZSTD_compressBlock_btopt2 },
- { ZSTD_compressBlock_fast_extDict, ZSTD_compressBlock_doubleFast_extDict, ZSTD_compressBlock_greedy_extDict,
+ ZSTD_compressBlock_btopt, ZSTD_compressBlock_btultra },
+ { ZSTD_compressBlock_fast_extDict /* default for 0 */,
+ ZSTD_compressBlock_fast_extDict, ZSTD_compressBlock_doubleFast_extDict, ZSTD_compressBlock_greedy_extDict,
ZSTD_compressBlock_lazy_extDict,ZSTD_compressBlock_lazy2_extDict, ZSTD_compressBlock_btlazy2_extDict,
- ZSTD_compressBlock_btopt_extDict, ZSTD_compressBlock_btopt2_extDict }
+ ZSTD_compressBlock_btopt_extDict, ZSTD_compressBlock_btultra_extDict }
};
+ ZSTD_STATIC_ASSERT((unsigned)ZSTD_fast == 1);
+ assert((U32)strat >= (U32)ZSTD_fast);
+ assert((U32)strat <= (U32)ZSTD_btultra);
- return blockCompressor[extDict][(U32)strat];
+ return blockCompressor[extDict!=0][(U32)strat];
}
static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
- ZSTD_blockCompressor const blockCompressor = ZSTD_selectBlockCompressor(zc->params.cParams.strategy, zc->lowLimit < zc->dictLimit);
+ ZSTD_blockCompressor const blockCompressor = ZSTD_selectBlockCompressor(zc->appliedParams.cParams.strategy, zc->lowLimit < zc->dictLimit);
const BYTE* const base = zc->base;
const BYTE* const istart = (const BYTE*)src;
const U32 current = (U32)(istart-base);
@@ -2433,14 +2827,14 @@ static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc, void* dst, size_t dstCa
}
-/*! ZSTD_compress_generic() :
+/*! ZSTD_compress_frameChunk() :
* Compress a chunk of data into one or multiple blocks.
* All blocks will be terminated, all input will be consumed.
* Function will issue an error if there is not enough `dstCapacity` to hold the compressed content.
* Frame is supposed already started (header already produced)
* @return : compressed size, or an error code
*/
-static size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
+static size_t ZSTD_compress_frameChunk (ZSTD_CCtx* cctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
U32 lastFrameChunk)
@@ -2450,9 +2844,9 @@ static size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
const BYTE* ip = (const BYTE*)src;
BYTE* const ostart = (BYTE*)dst;
BYTE* op = ostart;
- U32 const maxDist = 1 << cctx->params.cParams.windowLog;
+ U32 const maxDist = 1 << cctx->appliedParams.cParams.windowLog;
- if (cctx->params.fParams.checksumFlag && srcSize)
+ if (cctx->appliedParams.fParams.checksumFlag && srcSize)
XXH64_update(&cctx->xxhState, src, srcSize);
while (remaining) {
@@ -2465,9 +2859,9 @@ static size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
/* preemptive overflow correction */
if (cctx->lowLimit > (3U<<29)) {
- U32 const cycleMask = (1 << ZSTD_cycleLog(cctx->params.cParams.hashLog, cctx->params.cParams.strategy)) - 1;
+ U32 const cycleMask = (1 << ZSTD_cycleLog(cctx->appliedParams.cParams.hashLog, cctx->appliedParams.cParams.strategy)) - 1;
U32 const current = (U32)(ip - cctx->base);
- U32 const newCurrent = (current & cycleMask) + (1 << cctx->params.cParams.windowLog);
+ U32 const newCurrent = (current & cycleMask) + (1 << cctx->appliedParams.cParams.windowLog);
U32 const correction = current - newCurrent;
ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX_64 <= 30);
ZSTD_reduceIndex(cctx, correction);
@@ -2522,22 +2916,20 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity,
U32 const singleSegment = params.fParams.contentSizeFlag && (windowSize >= pledgedSrcSize);
BYTE const windowLogByte = (BYTE)((params.cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3);
U32 const fcsCode = params.fParams.contentSizeFlag ?
- (pledgedSrcSize>=256) + (pledgedSrcSize>=65536+256) + (pledgedSrcSize>=0xFFFFFFFFU) : /* 0-3 */
- 0;
+ (pledgedSrcSize>=256) + (pledgedSrcSize>=65536+256) + (pledgedSrcSize>=0xFFFFFFFFU) : 0; /* 0-3 */
BYTE const frameHeaderDecriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag<<2) + (singleSegment<<5) + (fcsCode<<6) );
size_t pos;
if (dstCapacity < ZSTD_frameHeaderSize_max) return ERROR(dstSize_tooSmall);
- DEBUGLOG(5, "ZSTD_writeFrameHeader : dictIDFlag : %u \n", !params.fParams.noDictIDFlag);
- DEBUGLOG(5, "ZSTD_writeFrameHeader : dictID : %u \n", dictID);
- DEBUGLOG(5, "ZSTD_writeFrameHeader : dictIDSizeCode : %u \n", dictIDSizeCode);
+ DEBUGLOG(5, "ZSTD_writeFrameHeader : dictIDFlag : %u ; dictID : %u ; dictIDSizeCode : %u",
+ !params.fParams.noDictIDFlag, dictID, dictIDSizeCode);
MEM_writeLE32(dst, ZSTD_MAGICNUMBER);
op[4] = frameHeaderDecriptionByte; pos=5;
if (!singleSegment) op[pos++] = windowLogByte;
switch(dictIDSizeCode)
{
- default: /* impossible */
+ default: assert(0); /* impossible */
case 0 : break;
case 1 : op[pos] = (BYTE)(dictID); pos++; break;
case 2 : MEM_writeLE16(op+pos, (U16)dictID); pos+=2; break;
@@ -2545,7 +2937,7 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity,
}
switch(fcsCode)
{
- default: /* impossible */
+ default: assert(0); /* impossible */
case 0 : if (singleSegment) op[pos++] = (BYTE)(pledgedSrcSize); break;
case 1 : MEM_writeLE16(op+pos, (U16)(pledgedSrcSize-256)); pos+=2; break;
case 2 : MEM_writeLE32(op+pos, (U32)(pledgedSrcSize)); pos+=4; break;
@@ -2563,10 +2955,13 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx,
const BYTE* const ip = (const BYTE*) src;
size_t fhSize = 0;
+ DEBUGLOG(5, "ZSTD_compressContinue_internal");
+ DEBUGLOG(5, "stage: %u", cctx->stage);
if (cctx->stage==ZSTDcs_created) return ERROR(stage_wrong); /* missing init (ZSTD_compressBegin) */
if (frame && (cctx->stage==ZSTDcs_init)) {
- fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->params, cctx->frameContentSize, cctx->dictID);
+ fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->appliedParams,
+ cctx->pledgedSrcSizePlusOne-1, cctx->dictID);
if (ZSTD_isError(fhSize)) return fhSize;
dstCapacity -= fhSize;
dst = (char*)dst + fhSize;
@@ -2596,7 +2991,7 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx,
if (srcSize) {
size_t const cSize = frame ?
- ZSTD_compress_generic (cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) :
+ ZSTD_compress_frameChunk (cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) :
ZSTD_compressBlock_internal (cctx, dst, dstCapacity, src, srcSize);
if (ZSTD_isError(cSize)) return cSize;
cctx->consumedSrcSize += srcSize;
@@ -2614,14 +3009,18 @@ size_t ZSTD_compressContinue (ZSTD_CCtx* cctx,
}
-size_t ZSTD_getBlockSizeMax(ZSTD_CCtx* cctx)
+size_t ZSTD_getBlockSize(const ZSTD_CCtx* cctx)
{
- return MIN (ZSTD_BLOCKSIZE_ABSOLUTEMAX, 1 << cctx->params.cParams.windowLog);
+ U32 const cLevel = cctx->compressionLevel;
+ ZSTD_compressionParameters cParams = (cLevel == ZSTD_CLEVEL_CUSTOM) ?
+ cctx->appliedParams.cParams :
+ ZSTD_getCParams(cLevel, 0, 0);
+ return MIN (ZSTD_BLOCKSIZE_MAX, 1 << cParams.windowLog);
}
size_t ZSTD_compressBlock(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
- size_t const blockSizeMax = ZSTD_getBlockSizeMax(cctx);
+ size_t const blockSizeMax = ZSTD_getBlockSize(cctx);
if (srcSize > blockSizeMax) return ERROR(srcSize_wrong);
return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0 /* frame mode */, 0 /* last chunk */);
}
@@ -2645,32 +3044,32 @@ static size_t ZSTD_loadDictionaryContent(ZSTD_CCtx* zc, const void* src, size_t
zc->nextSrc = iend;
if (srcSize <= HASH_READ_SIZE) return 0;
- switch(zc->params.cParams.strategy)
+ switch(zc->appliedParams.cParams.strategy)
{
case ZSTD_fast:
- ZSTD_fillHashTable (zc, iend, zc->params.cParams.searchLength);
+ ZSTD_fillHashTable (zc, iend, zc->appliedParams.cParams.searchLength);
break;
case ZSTD_dfast:
- ZSTD_fillDoubleHashTable (zc, iend, zc->params.cParams.searchLength);
+ ZSTD_fillDoubleHashTable (zc, iend, zc->appliedParams.cParams.searchLength);
break;
case ZSTD_greedy:
case ZSTD_lazy:
case ZSTD_lazy2:
if (srcSize >= HASH_READ_SIZE)
- ZSTD_insertAndFindFirstIndex(zc, iend-HASH_READ_SIZE, zc->params.cParams.searchLength);
+ ZSTD_insertAndFindFirstIndex(zc, iend-HASH_READ_SIZE, zc->appliedParams.cParams.searchLength);
break;
case ZSTD_btlazy2:
case ZSTD_btopt:
- case ZSTD_btopt2:
+ case ZSTD_btultra:
if (srcSize >= HASH_READ_SIZE)
- ZSTD_updateTree(zc, iend-HASH_READ_SIZE, iend, 1 << zc->params.cParams.searchLog, zc->params.cParams.searchLength);
+ ZSTD_updateTree(zc, iend-HASH_READ_SIZE, iend, 1 << zc->appliedParams.cParams.searchLog, zc->appliedParams.cParams.searchLength);
break;
default:
- return ERROR(GENERIC); /* strategy doesn't exist; impossible */
+ assert(0); /* not possible : not a valid strategy id */
}
zc->nextToUpdate = (U32)(iend - zc->base);
@@ -2710,7 +3109,7 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_CCtx* cctx, const void* dict, size_t
BYTE scratchBuffer[1<<MAX(MLFSELog,LLFSELog)];
dictPtr += 4; /* skip magic number */
- cctx->dictID = cctx->params.fParams.noDictIDFlag ? 0 : MEM_readLE32(dictPtr);
+ cctx->dictID = cctx->appliedParams.fParams.noDictIDFlag ? 0 : MEM_readLE32(dictPtr);
dictPtr += 4;
{ size_t const hufHeaderSize = HUF_readCTable(cctx->hufCTable, 255, dictPtr, dictEnd-dictPtr);
@@ -2781,28 +3180,56 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_CCtx* cctx, const void* dict, size_t
/** ZSTD_compress_insertDictionary() :
* @return : 0, or an error code */
-static size_t ZSTD_compress_insertDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize)
+static size_t ZSTD_compress_insertDictionary(ZSTD_CCtx* cctx,
+ const void* dict, size_t dictSize,
+ ZSTD_dictMode_e dictMode)
{
+ DEBUGLOG(5, "ZSTD_compress_insertDictionary");
if ((dict==NULL) || (dictSize<=8)) return 0;
- /* dict as pure content */
- if ((MEM_readLE32(dict) != ZSTD_DICT_MAGIC) || (cctx->forceRawDict))
+ /* dict restricted modes */
+ if (dictMode==ZSTD_dm_rawContent)
return ZSTD_loadDictionaryContent(cctx, dict, dictSize);
- /* dict as zstd dictionary */
+ if (MEM_readLE32(dict) != ZSTD_MAGIC_DICTIONARY) {
+ if (dictMode == ZSTD_dm_auto) {
+ DEBUGLOG(5, "raw content dictionary detected");
+ return ZSTD_loadDictionaryContent(cctx, dict, dictSize);
+ }
+ if (dictMode == ZSTD_dm_fullDict)
+ return ERROR(dictionary_wrong);
+ assert(0); /* impossible */
+ }
+
+ /* dict as full zstd dictionary */
return ZSTD_loadZstdDictionary(cctx, dict, dictSize);
}
/*! ZSTD_compressBegin_internal() :
-* @return : 0, or an error code */
+ * @return : 0, or an error code */
static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx,
const void* dict, size_t dictSize,
- ZSTD_parameters params, U64 pledgedSrcSize)
+ ZSTD_dictMode_e dictMode,
+ const ZSTD_CDict* cdict,
+ ZSTD_parameters params, U64 pledgedSrcSize,
+ ZSTD_buffered_policy_e zbuff)
{
- ZSTD_compResetPolicy_e const crp = dictSize ? ZSTDcrp_fullReset : ZSTDcrp_continue;
+ DEBUGLOG(4, "ZSTD_compressBegin_internal");
+ DEBUGLOG(4, "dict ? %s", dict ? "dict" : (cdict ? "cdict" : "none"));
+ DEBUGLOG(4, "dictMode : %u", (U32)dictMode);
+ /* params are supposed to be fully validated at this point */
assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
- CHECK_F(ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize, crp));
- return ZSTD_compress_insertDictionary(cctx, dict, dictSize);
+ assert(!((dict) && (cdict))); /* either dict or cdict, not both */
+
+ if (cdict && cdict->dictContentSize>0) {
+ return ZSTD_copyCCtx_internal(cctx, cdict->refContext,
+ params.fParams, pledgedSrcSize,
+ zbuff);
+ }
+
+ CHECK_F( ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
+ ZSTDcrp_continue, zbuff) );
+ return ZSTD_compress_insertDictionary(cctx, dict, dictSize, dictMode);
}
@@ -2814,14 +3241,16 @@ size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx,
{
/* compression parameters verification and optimization */
CHECK_F(ZSTD_checkCParams(params.cParams));
- return ZSTD_compressBegin_internal(cctx, dict, dictSize, params, pledgedSrcSize);
+ return ZSTD_compressBegin_internal(cctx, dict, dictSize, ZSTD_dm_auto, NULL,
+ params, pledgedSrcSize, ZSTDb_not_buffered);
}
size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel)
{
ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, dictSize);
- return ZSTD_compressBegin_internal(cctx, dict, dictSize, params, 0);
+ return ZSTD_compressBegin_internal(cctx, dict, dictSize, ZSTD_dm_auto, NULL,
+ params, 0, ZSTDb_not_buffered);
}
@@ -2840,11 +3269,12 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity)
BYTE* op = ostart;
size_t fhSize = 0;
+ DEBUGLOG(5, "ZSTD_writeEpilogue");
if (cctx->stage == ZSTDcs_created) return ERROR(stage_wrong); /* init missing */
/* special case : empty frame */
if (cctx->stage == ZSTDcs_init) {
- fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->params, 0, 0);
+ fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->appliedParams, 0, 0);
if (ZSTD_isError(fhSize)) return fhSize;
dstCapacity -= fhSize;
op += fhSize;
@@ -2860,7 +3290,7 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity)
dstCapacity -= ZSTD_blockHeaderSize;
}
- if (cctx->params.fParams.checksumFlag) {
+ if (cctx->appliedParams.fParams.checksumFlag) {
U32 const checksum = (U32) XXH64_digest(&cctx->xxhState);
if (dstCapacity<4) return ERROR(dstSize_tooSmall);
MEM_writeLE32(op, checksum);
@@ -2877,13 +3307,19 @@ size_t ZSTD_compressEnd (ZSTD_CCtx* cctx,
const void* src, size_t srcSize)
{
size_t endResult;
- size_t const cSize = ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 1 /* frame mode */, 1 /* last chunk */);
+ size_t const cSize = ZSTD_compressContinue_internal(cctx,
+ dst, dstCapacity, src, srcSize,
+ 1 /* frame mode */, 1 /* last chunk */);
if (ZSTD_isError(cSize)) return cSize;
endResult = ZSTD_writeEpilogue(cctx, (char*)dst + cSize, dstCapacity-cSize);
if (ZSTD_isError(endResult)) return endResult;
- if (cctx->params.fParams.contentSizeFlag) { /* control src size */
- if (cctx->frameContentSize != cctx->consumedSrcSize) return ERROR(srcSize_wrong);
- }
+ if (cctx->appliedParams.fParams.contentSizeFlag) { /* control src size */
+ DEBUGLOG(5, "end of frame : controlling src size");
+ if (cctx->pledgedSrcSizePlusOne != cctx->consumedSrcSize+1) {
+ DEBUGLOG(5, "error : pledgedSrcSize = %u, while realSrcSize = %u",
+ (U32)cctx->pledgedSrcSizePlusOne-1, (U32)cctx->consumedSrcSize);
+ return ERROR(srcSize_wrong);
+ } }
return cSize + endResult;
}
@@ -2894,7 +3330,8 @@ static size_t ZSTD_compress_internal (ZSTD_CCtx* cctx,
const void* dict,size_t dictSize,
ZSTD_parameters params)
{
- CHECK_F(ZSTD_compressBegin_internal(cctx, dict, dictSize, params, srcSize));
+ CHECK_F( ZSTD_compressBegin_internal(cctx, dict, dictSize, ZSTD_dm_auto, NULL,
+ params, srcSize, ZSTDb_not_buffered) );
return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
}
@@ -2926,25 +3363,36 @@ size_t ZSTD_compress(void* dst, size_t dstCapacity, const void* src, size_t srcS
size_t result;
ZSTD_CCtx ctxBody;
memset(&ctxBody, 0, sizeof(ctxBody));
- memcpy(&ctxBody.customMem, &defaultCustomMem, sizeof(ZSTD_customMem));
+ ctxBody.customMem = ZSTD_defaultCMem;
result = ZSTD_compressCCtx(&ctxBody, dst, dstCapacity, src, srcSize, compressionLevel);
- ZSTD_free(ctxBody.workSpace, defaultCustomMem); /* can't free ctxBody itself, as it's on stack; free only heap content */
+ ZSTD_free(ctxBody.workSpace, ZSTD_defaultCMem); /* can't free ctxBody itself, as it's on stack; free only heap content */
return result;
}
/* ===== Dictionary API ===== */
-struct ZSTD_CDict_s {
- void* dictBuffer;
- const void* dictContent;
- size_t dictContentSize;
- ZSTD_CCtx* refContext;
-}; /* typedef'd tp ZSTD_CDict within "zstd.h" */
+/*! ZSTD_estimateCDictSize_advanced() :
+ * Estimate amount of memory that will be needed to create a dictionary with following arguments */
+size_t ZSTD_estimateCDictSize_advanced(size_t dictSize, ZSTD_compressionParameters cParams, unsigned byReference)
+{
+ DEBUGLOG(5, "sizeof(ZSTD_CDict) : %u", (U32)sizeof(ZSTD_CDict));
+ DEBUGLOG(5, "CCtx estimate : %u", (U32)ZSTD_estimateCCtxSize_advanced(cParams));
+ return sizeof(ZSTD_CDict) + ZSTD_estimateCCtxSize_advanced(cParams)
+ + (byReference ? 0 : dictSize);
+}
+
+size_t ZSTD_estimateCDictSize(size_t dictSize, int compressionLevel)
+{
+ ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, 0, dictSize);
+ return ZSTD_estimateCDictSize_advanced(dictSize, cParams, 0);
+}
size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict)
{
if (cdict==NULL) return 0; /* support sizeof on NULL */
+ DEBUGLOG(5, "sizeof(*cdict) : %u", (U32)sizeof(*cdict));
+ DEBUGLOG(5, "ZSTD_sizeof_CCtx : %u", (U32)ZSTD_sizeof_CCtx(cdict->refContext));
return ZSTD_sizeof_CCtx(cdict->refContext) + (cdict->dictBuffer ? cdict->dictContentSize : 0) + sizeof(*cdict);
}
@@ -2956,13 +3404,46 @@ static ZSTD_parameters ZSTD_makeParams(ZSTD_compressionParameters cParams, ZSTD_
return params;
}
-ZSTD_CDict* ZSTD_createCDict_advanced(const void* dictBuffer, size_t dictSize, unsigned byReference,
+static size_t ZSTD_initCDict_internal(
+ ZSTD_CDict* cdict,
+ const void* dictBuffer, size_t dictSize,
+ unsigned byReference, ZSTD_dictMode_e dictMode,
+ ZSTD_compressionParameters cParams)
+{
+ DEBUGLOG(5, "ZSTD_initCDict_internal, mode %u", (U32)dictMode);
+ if ((byReference) || (!dictBuffer) || (!dictSize)) {
+ cdict->dictBuffer = NULL;
+ cdict->dictContent = dictBuffer;
+ } else {
+ void* const internalBuffer = ZSTD_malloc(dictSize, cdict->refContext->customMem);
+ cdict->dictBuffer = internalBuffer;
+ cdict->dictContent = internalBuffer;
+ if (!internalBuffer) return ERROR(memory_allocation);
+ memcpy(internalBuffer, dictBuffer, dictSize);
+ }
+ cdict->dictContentSize = dictSize;
+
+ { ZSTD_frameParameters const fParams = { 0 /* contentSizeFlag */,
+ 0 /* checksumFlag */, 0 /* noDictIDFlag */ }; /* dummy */
+ ZSTD_parameters const params = ZSTD_makeParams(cParams, fParams);
+ CHECK_F( ZSTD_compressBegin_internal(cdict->refContext,
+ cdict->dictContent, dictSize, dictMode,
+ NULL,
+ params, ZSTD_CONTENTSIZE_UNKNOWN,
+ ZSTDb_not_buffered) );
+ }
+
+ return 0;
+}
+
+ZSTD_CDict* ZSTD_createCDict_advanced(const void* dictBuffer, size_t dictSize,
+ unsigned byReference, ZSTD_dictMode_e dictMode,
ZSTD_compressionParameters cParams, ZSTD_customMem customMem)
{
- if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
- if (!customMem.customAlloc || !customMem.customFree) return NULL;
+ DEBUGLOG(5, "ZSTD_createCDict_advanced, mode %u", (U32)dictMode);
+ if (!customMem.customAlloc ^ !customMem.customFree) return NULL;
- { ZSTD_CDict* const cdict = (ZSTD_CDict*) ZSTD_malloc(sizeof(ZSTD_CDict), customMem);
+ { ZSTD_CDict* const cdict = (ZSTD_CDict*)ZSTD_malloc(sizeof(ZSTD_CDict), customMem);
ZSTD_CCtx* const cctx = ZSTD_createCCtx_advanced(customMem);
if (!cdict || !cctx) {
@@ -2970,46 +3451,34 @@ ZSTD_CDict* ZSTD_createCDict_advanced(const void* dictBuffer, size_t dictSize, u
ZSTD_freeCCtx(cctx);
return NULL;
}
+ cdict->refContext = cctx;
- if ((byReference) || (!dictBuffer) || (!dictSize)) {
- cdict->dictBuffer = NULL;
- cdict->dictContent = dictBuffer;
- } else {
- void* const internalBuffer = ZSTD_malloc(dictSize, customMem);
- if (!internalBuffer) { ZSTD_free(cctx, customMem); ZSTD_free(cdict, customMem); return NULL; }
- memcpy(internalBuffer, dictBuffer, dictSize);
- cdict->dictBuffer = internalBuffer;
- cdict->dictContent = internalBuffer;
+ if (ZSTD_isError( ZSTD_initCDict_internal(cdict,
+ dictBuffer, dictSize,
+ byReference, dictMode,
+ cParams) )) {
+ ZSTD_freeCDict(cdict);
+ return NULL;
}
- { ZSTD_frameParameters const fParams = { 0 /* contentSizeFlag */, 0 /* checksumFlag */, 0 /* noDictIDFlag */ }; /* dummy */
- ZSTD_parameters const params = ZSTD_makeParams(cParams, fParams);
- size_t const errorCode = ZSTD_compressBegin_advanced(cctx, cdict->dictContent, dictSize, params, 0);
- if (ZSTD_isError(errorCode)) {
- ZSTD_free(cdict->dictBuffer, customMem);
- ZSTD_free(cdict, customMem);
- ZSTD_freeCCtx(cctx);
- return NULL;
- } }
-
- cdict->refContext = cctx;
- cdict->dictContentSize = dictSize;
return cdict;
}
}
ZSTD_CDict* ZSTD_createCDict(const void* dict, size_t dictSize, int compressionLevel)
{
- ZSTD_customMem const allocator = { NULL, NULL, NULL };
ZSTD_compressionParameters cParams = ZSTD_getCParams(compressionLevel, 0, dictSize);
- return ZSTD_createCDict_advanced(dict, dictSize, 0, cParams, allocator);
+ return ZSTD_createCDict_advanced(dict, dictSize,
+ 0 /* byReference */, ZSTD_dm_auto,
+ cParams, ZSTD_defaultCMem);
}
ZSTD_CDict* ZSTD_createCDict_byReference(const void* dict, size_t dictSize, int compressionLevel)
{
- ZSTD_customMem const allocator = { NULL, NULL, NULL };
ZSTD_compressionParameters cParams = ZSTD_getCParams(compressionLevel, 0, dictSize);
- return ZSTD_createCDict_advanced(dict, dictSize, 1, cParams, allocator);
+ return ZSTD_createCDict_advanced(dict, dictSize,
+ 1 /* byReference */, ZSTD_dm_auto,
+ cParams, ZSTD_defaultCMem);
}
size_t ZSTD_freeCDict(ZSTD_CDict* cdict)
@@ -3023,7 +3492,54 @@ size_t ZSTD_freeCDict(ZSTD_CDict* cdict)
}
}
-static ZSTD_parameters ZSTD_getParamsFromCDict(const ZSTD_CDict* cdict) {
+/*! ZSTD_initStaticCDict_advanced() :
+ * Generate a digested dictionary in provided memory area.
+ * workspace: The memory area to emplace the dictionary into.
+ * Provided pointer must 8-bytes aligned.
+ * It must outlive dictionary usage.
+ * workspaceSize: Use ZSTD_estimateCDictSize()
+ * to determine how large workspace must be.
+ * cParams : use ZSTD_getCParams() to transform a compression level
+ * into its relevants cParams.
+ * @return : pointer to ZSTD_CDict*, or NULL if error (size too small)
+ * Note : there is no corresponding "free" function.
+ * Since workspace was allocated externally, it must be freed externally.
+ */
+ZSTD_CDict* ZSTD_initStaticCDict(void* workspace, size_t workspaceSize,
+ const void* dict, size_t dictSize,
+ unsigned byReference, ZSTD_dictMode_e dictMode,
+ ZSTD_compressionParameters cParams)
+{
+ size_t const cctxSize = ZSTD_estimateCCtxSize_advanced(cParams);
+ size_t const neededSize = sizeof(ZSTD_CDict) + (byReference ? 0 : dictSize)
+ + cctxSize;
+ ZSTD_CDict* const cdict = (ZSTD_CDict*) workspace;
+ void* ptr;
+ DEBUGLOG(5, "(size_t)workspace & 7 : %u", (U32)(size_t)workspace & 7);
+ if ((size_t)workspace & 7) return NULL; /* 8-aligned */
+ DEBUGLOG(5, "(workspaceSize < neededSize) : (%u < %u) => %u",
+ (U32)workspaceSize, (U32)neededSize, (U32)(workspaceSize < neededSize));
+ if (workspaceSize < neededSize) return NULL;
+
+ if (!byReference) {
+ memcpy(cdict+1, dict, dictSize);
+ dict = cdict+1;
+ ptr = (char*)workspace + sizeof(ZSTD_CDict) + dictSize;
+ } else {
+ ptr = cdict+1;
+ }
+ cdict->refContext = ZSTD_initStaticCCtx(ptr, cctxSize);
+
+ if (ZSTD_isError( ZSTD_initCDict_internal(cdict,
+ dict, dictSize,
+ 1 /* byReference */, dictMode,
+ cParams) ))
+ return NULL;
+
+ return cdict;
+}
+
+ZSTD_parameters ZSTD_getParamsFromCDict(const ZSTD_CDict* cdict) {
return ZSTD_getParamsFromCCtx(cdict->refContext);
}
@@ -3033,16 +3549,16 @@ size_t ZSTD_compressBegin_usingCDict_advanced(
ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict,
ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize)
{
- if (cdict==NULL) return ERROR(GENERIC); /* does not support NULL cdict */
- DEBUGLOG(5, "ZSTD_compressBegin_usingCDict_advanced : dictIDFlag == %u \n", !fParams.noDictIDFlag);
- if (cdict->dictContentSize)
- CHECK_F( ZSTD_copyCCtx_internal(cctx, cdict->refContext, fParams, pledgedSrcSize) )
- else {
- ZSTD_parameters params = cdict->refContext->params;
+ if (cdict==NULL) return ERROR(dictionary_wrong);
+ { ZSTD_parameters params = cdict->refContext->appliedParams;
params.fParams = fParams;
- CHECK_F(ZSTD_compressBegin_internal(cctx, NULL, 0, params, pledgedSrcSize));
+ DEBUGLOG(5, "ZSTD_compressBegin_usingCDict_advanced");
+ return ZSTD_compressBegin_internal(cctx,
+ NULL, 0, ZSTD_dm_auto,
+ cdict,
+ params, pledgedSrcSize,
+ ZSTDb_not_buffered);
}
- return 0;
}
/* ZSTD_compressBegin_usingCDict() :
@@ -3051,7 +3567,7 @@ size_t ZSTD_compressBegin_usingCDict_advanced(
size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict)
{
ZSTD_frameParameters const fParams = { 0 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ };
- DEBUGLOG(5, "ZSTD_compressBegin_usingCDict : dictIDFlag == %u \n", !fParams.noDictIDFlag);
+ DEBUGLOG(5, "ZSTD_compressBegin_usingCDict : dictIDFlag == %u", !fParams.noDictIDFlag);
return ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, 0);
}
@@ -3084,176 +3600,133 @@ size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
* Streaming
********************************************************************/
-typedef enum { zcss_init, zcss_load, zcss_flush, zcss_final } ZSTD_cStreamStage;
-
-struct ZSTD_CStream_s {
- ZSTD_CCtx* cctx;
- ZSTD_CDict* cdictLocal;
- const ZSTD_CDict* cdict;
- char* inBuff;
- size_t inBuffSize;
- size_t inToCompress;
- size_t inBuffPos;
- size_t inBuffTarget;
- size_t blockSize;
- char* outBuff;
- size_t outBuffSize;
- size_t outBuffContentSize;
- size_t outBuffFlushedSize;
- ZSTD_cStreamStage stage;
- U32 checksum;
- U32 frameEnded;
- U64 pledgedSrcSize;
- ZSTD_parameters params;
- ZSTD_customMem customMem;
-}; /* typedef'd to ZSTD_CStream within "zstd.h" */
-
ZSTD_CStream* ZSTD_createCStream(void)
{
- return ZSTD_createCStream_advanced(defaultCustomMem);
+ return ZSTD_createCStream_advanced(ZSTD_defaultCMem);
}
-ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem)
+ZSTD_CStream* ZSTD_initStaticCStream(void *workspace, size_t workspaceSize)
{
- ZSTD_CStream* zcs;
-
- if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
- if (!customMem.customAlloc || !customMem.customFree) return NULL;
+ return ZSTD_initStaticCCtx(workspace, workspaceSize);
+}
- zcs = (ZSTD_CStream*)ZSTD_malloc(sizeof(ZSTD_CStream), customMem);
- if (zcs==NULL) return NULL;
- memset(zcs, 0, sizeof(ZSTD_CStream));
- memcpy(&zcs->customMem, &customMem, sizeof(ZSTD_customMem));
- zcs->cctx = ZSTD_createCCtx_advanced(customMem);
- if (zcs->cctx == NULL) { ZSTD_freeCStream(zcs); return NULL; }
- return zcs;
+ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem)
+{ /* CStream and CCtx are now same object */
+ return ZSTD_createCCtx_advanced(customMem);
}
size_t ZSTD_freeCStream(ZSTD_CStream* zcs)
{
- if (zcs==NULL) return 0; /* support free on NULL */
- { ZSTD_customMem const cMem = zcs->customMem;
- ZSTD_freeCCtx(zcs->cctx);
- zcs->cctx = NULL;
- ZSTD_freeCDict(zcs->cdictLocal);
- zcs->cdictLocal = NULL;
- ZSTD_free(zcs->inBuff, cMem);
- zcs->inBuff = NULL;
- ZSTD_free(zcs->outBuff, cMem);
- zcs->outBuff = NULL;
- ZSTD_free(zcs, cMem);
- return 0;
- }
+ return ZSTD_freeCCtx(zcs); /* same object */
}
+
/*====== Initialization ======*/
-size_t ZSTD_CStreamInSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX; }
+size_t ZSTD_CStreamInSize(void) { return ZSTD_BLOCKSIZE_MAX; }
size_t ZSTD_CStreamOutSize(void)
{
- return ZSTD_compressBound(ZSTD_BLOCKSIZE_ABSOLUTEMAX) + ZSTD_blockHeaderSize + 4 /* 32-bits hash */ ;
+ return ZSTD_compressBound(ZSTD_BLOCKSIZE_MAX) + ZSTD_blockHeaderSize + 4 /* 32-bits hash */ ;
}
-static size_t ZSTD_resetCStream_internal(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize)
+static size_t ZSTD_resetCStream_internal(ZSTD_CStream* zcs,
+ const void* dict, size_t dictSize, ZSTD_dictMode_e dictMode,
+ const ZSTD_CDict* cdict,
+ ZSTD_parameters params, unsigned long long pledgedSrcSize)
{
- if (zcs->inBuffSize==0) return ERROR(stage_wrong); /* zcs has not been init at least once => can't reset */
-
- DEBUGLOG(5, "ZSTD_resetCStream_internal : dictIDFlag == %u \n", !zcs->params.fParams.noDictIDFlag);
+ DEBUGLOG(4, "ZSTD_resetCStream_internal");
+ /* params are supposed to be fully validated at this point */
+ assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
+ assert(!((dict) && (cdict))); /* either dict or cdict, not both */
- if (zcs->cdict) CHECK_F(ZSTD_compressBegin_usingCDict_advanced(zcs->cctx, zcs->cdict, zcs->params.fParams, pledgedSrcSize))
- else CHECK_F(ZSTD_compressBegin_internal(zcs->cctx, NULL, 0, zcs->params, pledgedSrcSize));
+ CHECK_F( ZSTD_compressBegin_internal(zcs,
+ dict, dictSize, dictMode,
+ cdict,
+ params, pledgedSrcSize,
+ ZSTDb_buffered) );
zcs->inToCompress = 0;
zcs->inBuffPos = 0;
zcs->inBuffTarget = zcs->blockSize;
zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0;
- zcs->stage = zcss_load;
+ zcs->streamStage = zcss_load;
zcs->frameEnded = 0;
- zcs->pledgedSrcSize = pledgedSrcSize;
return 0; /* ready to go */
}
size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize)
{
-
- zcs->params.fParams.contentSizeFlag = (pledgedSrcSize > 0);
- DEBUGLOG(5, "ZSTD_resetCStream : dictIDFlag == %u \n", !zcs->params.fParams.noDictIDFlag);
- return ZSTD_resetCStream_internal(zcs, pledgedSrcSize);
+ ZSTD_parameters params = zcs->requestedParams;
+ params.fParams.contentSizeFlag = (pledgedSrcSize > 0);
+ DEBUGLOG(5, "ZSTD_resetCStream");
+ if (zcs->compressionLevel != ZSTD_CLEVEL_CUSTOM) {
+ params.cParams = ZSTD_getCParams(zcs->compressionLevel, pledgedSrcSize, 0 /* dictSize */);
+ }
+ return ZSTD_resetCStream_internal(zcs, NULL, 0, zcs->dictMode, zcs->cdict, params, pledgedSrcSize);
}
-/* ZSTD_initCStream_internal() :
- * params are supposed validated at this stage
- * and zcs->cdict is supposed to be correct */
-static size_t ZSTD_initCStream_stage2(ZSTD_CStream* zcs,
- const ZSTD_parameters params,
- unsigned long long pledgedSrcSize)
+/*! ZSTD_initCStream_internal() :
+ * Note : not static, but hidden (not exposed). Used by zstdmt_compress.c
+ * Assumption 1 : params are valid
+ * Assumption 2 : either dict, or cdict, is defined, not both */
+size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
+ const void* dict, size_t dictSize, const ZSTD_CDict* cdict,
+ ZSTD_parameters params, unsigned long long pledgedSrcSize)
{
+ DEBUGLOG(5, "ZSTD_initCStream_internal");
assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
+ assert(!((dict) && (cdict))); /* either dict or cdict, not both */
- /* allocate buffers */
- { size_t const neededInBuffSize = (size_t)1 << params.cParams.windowLog;
- if (zcs->inBuffSize < neededInBuffSize) {
- zcs->inBuffSize = 0;
- ZSTD_free(zcs->inBuff, zcs->customMem);
- zcs->inBuff = (char*) ZSTD_malloc(neededInBuffSize, zcs->customMem);
- if (zcs->inBuff == NULL) return ERROR(memory_allocation);
- zcs->inBuffSize = neededInBuffSize;
+ if (dict && dictSize >= 8) {
+ DEBUGLOG(5, "loading dictionary of size %u", (U32)dictSize);
+ if (zcs->staticSize) { /* static CCtx : never uses malloc */
+ /* incompatible with internal cdict creation */
+ return ERROR(memory_allocation);
}
- zcs->blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, neededInBuffSize);
- }
- if (zcs->outBuffSize < ZSTD_compressBound(zcs->blockSize)+1) {
- size_t const outBuffSize = ZSTD_compressBound(zcs->blockSize)+1;
- zcs->outBuffSize = 0;
- ZSTD_free(zcs->outBuff, zcs->customMem);
- zcs->outBuff = (char*) ZSTD_malloc(outBuffSize, zcs->customMem);
- if (zcs->outBuff == NULL) return ERROR(memory_allocation);
- zcs->outBuffSize = outBuffSize;
+ ZSTD_freeCDict(zcs->cdictLocal);
+ zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize,
+ zcs->dictContentByRef, zcs->dictMode,
+ params.cParams, zcs->customMem);
+ zcs->cdict = zcs->cdictLocal;
+ if (zcs->cdictLocal == NULL) return ERROR(memory_allocation);
+ } else {
+ if (cdict) {
+ ZSTD_parameters const cdictParams = ZSTD_getParamsFromCDict(cdict);
+ params.cParams = cdictParams.cParams; /* cParams are enforced from cdict */
+ }
+ ZSTD_freeCDict(zcs->cdictLocal);
+ zcs->cdictLocal = NULL;
+ zcs->cdict = cdict;
}
- zcs->checksum = params.fParams.checksumFlag > 0;
- zcs->params = params;
-
- DEBUGLOG(5, "ZSTD_initCStream_stage2 : dictIDFlag == %u \n", !params.fParams.noDictIDFlag);
- return ZSTD_resetCStream_internal(zcs, pledgedSrcSize);
+ zcs->requestedParams = params;
+ zcs->compressionLevel = ZSTD_CLEVEL_CUSTOM;
+ return ZSTD_resetCStream_internal(zcs, NULL, 0, zcs->dictMode, zcs->cdict, params, pledgedSrcSize);
}
/* ZSTD_initCStream_usingCDict_advanced() :
* same as ZSTD_initCStream_usingCDict(), with control over frame parameters */
-size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, unsigned long long pledgedSrcSize, ZSTD_frameParameters fParams)
-{
- if (!cdict) return ERROR(GENERIC); /* cannot handle NULL cdict (does not know what to do) */
+size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs,
+ const ZSTD_CDict* cdict,
+ ZSTD_frameParameters fParams,
+ unsigned long long pledgedSrcSize)
+{ /* cannot handle NULL cdict (does not know what to do) */
+ if (!cdict) return ERROR(dictionary_wrong);
{ ZSTD_parameters params = ZSTD_getParamsFromCDict(cdict);
params.fParams = fParams;
- zcs->cdict = cdict;
- return ZSTD_initCStream_stage2(zcs, params, pledgedSrcSize);
+ return ZSTD_initCStream_internal(zcs,
+ NULL, 0, cdict,
+ params, pledgedSrcSize);
}
}
/* note : cdict must outlive compression session */
size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict)
{
- ZSTD_frameParameters const fParams = { 0 /* content */, 0 /* checksum */, 0 /* noDictID */ };
- return ZSTD_initCStream_usingCDict_advanced(zcs, cdict, 0, fParams);
-}
-
-static size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
- const void* dict, size_t dictSize,
- ZSTD_parameters params, unsigned long long pledgedSrcSize)
-{
- assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
- zcs->cdict = NULL;
-
- if (dict && dictSize >= 8) {
- ZSTD_freeCDict(zcs->cdictLocal);
- zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize, 0 /* copy */, params.cParams, zcs->customMem);
- if (zcs->cdictLocal == NULL) return ERROR(memory_allocation);
- zcs->cdict = zcs->cdictLocal;
- }
-
- DEBUGLOG(5, "ZSTD_initCStream_internal : dictIDFlag == %u \n", !params.fParams.noDictIDFlag);
- return ZSTD_initCStream_stage2(zcs, params, pledgedSrcSize);
+ ZSTD_frameParameters const fParams = { 0 /* contentSize */, 0 /* checksum */, 0 /* hideDictID */ };
+ return ZSTD_initCStream_usingCDict_advanced(zcs, cdict, fParams, 0); /* note : will check that cdict != NULL */
}
size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs,
@@ -3261,120 +3734,180 @@ size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs,
ZSTD_parameters params, unsigned long long pledgedSrcSize)
{
CHECK_F( ZSTD_checkCParams(params.cParams) );
- DEBUGLOG(5, "ZSTD_initCStream_advanced : dictIDFlag == %u \n", !params.fParams.noDictIDFlag);
- return ZSTD_initCStream_internal(zcs, dict, dictSize, params, pledgedSrcSize);
+ zcs->requestedParams = params;
+ zcs->compressionLevel = ZSTD_CLEVEL_CUSTOM;
+ return ZSTD_initCStream_internal(zcs, dict, dictSize, NULL, params, pledgedSrcSize);
}
size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel)
{
ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, dictSize);
- return ZSTD_initCStream_internal(zcs, dict, dictSize, params, 0);
+ zcs->compressionLevel = compressionLevel;
+ return ZSTD_initCStream_internal(zcs, dict, dictSize, NULL, params, 0);
}
size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize)
{
ZSTD_parameters params = ZSTD_getParams(compressionLevel, pledgedSrcSize, 0);
params.fParams.contentSizeFlag = (pledgedSrcSize>0);
- return ZSTD_initCStream_internal(zcs, NULL, 0, params, pledgedSrcSize);
+ return ZSTD_initCStream_internal(zcs, NULL, 0, NULL, params, pledgedSrcSize);
}
size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel)
{
ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, 0);
- return ZSTD_initCStream_internal(zcs, NULL, 0, params, 0);
-}
-
-size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs)
-{
- if (zcs==NULL) return 0; /* support sizeof on NULL */
- return sizeof(*zcs) + ZSTD_sizeof_CCtx(zcs->cctx) + ZSTD_sizeof_CDict(zcs->cdictLocal) + zcs->outBuffSize + zcs->inBuffSize;
+ return ZSTD_initCStream_internal(zcs, NULL, 0, NULL, params, 0);
}
/*====== Compression ======*/
-typedef enum { zsf_gather, zsf_flush, zsf_end } ZSTD_flush_e;
-
-MEM_STATIC size_t ZSTD_limitCopy(void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+MEM_STATIC size_t ZSTD_limitCopy(void* dst, size_t dstCapacity,
+ const void* src, size_t srcSize)
{
size_t const length = MIN(dstCapacity, srcSize);
- memcpy(dst, src, length);
+ if (length) memcpy(dst, src, length);
return length;
}
-static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
- void* dst, size_t* dstCapacityPtr,
- const void* src, size_t* srcSizePtr,
- ZSTD_flush_e const flush)
+/** ZSTD_compressStream_generic():
+ * internal function for all *compressStream*() variants and *compress_generic()
+ * @return : hint size for next input */
+size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
+ ZSTD_outBuffer* output,
+ ZSTD_inBuffer* input,
+ ZSTD_EndDirective const flushMode)
{
+ const char* const istart = (const char*)input->src;
+ const char* const iend = istart + input->size;
+ const char* ip = istart + input->pos;
+ char* const ostart = (char*)output->dst;
+ char* const oend = ostart + output->size;
+ char* op = ostart + output->pos;
U32 someMoreWork = 1;
- const char* const istart = (const char*)src;
- const char* const iend = istart + *srcSizePtr;
- const char* ip = istart;
- char* const ostart = (char*)dst;
- char* const oend = ostart + *dstCapacityPtr;
- char* op = ostart;
+
+ /* check expectations */
+ DEBUGLOG(5, "ZSTD_compressStream_generic, flush=%u", (U32)flushMode);
+ assert(zcs->inBuff != NULL);
+ assert(zcs->inBuffSize>0);
+ assert(zcs->outBuff!= NULL);
+ assert(zcs->outBuffSize>0);
+ assert(output->pos <= output->size);
+ assert(input->pos <= input->size);
while (someMoreWork) {
- switch(zcs->stage)
+ switch(zcs->streamStage)
{
- case zcss_init: return ERROR(init_missing); /* call ZBUFF_compressInit() first ! */
+ case zcss_init:
+ /* call ZSTD_initCStream() first ! */
+ return ERROR(init_missing);
case zcss_load:
- /* complete inBuffer */
+ if ( (flushMode == ZSTD_e_end)
+ && ((size_t)(oend-op) >= ZSTD_compressBound(iend-ip)) /* enough dstCapacity */
+ && (zcs->inBuffPos == 0) ) {
+ /* shortcut to compression pass directly into output buffer */
+ size_t const cSize = ZSTD_compressEnd(zcs,
+ op, oend-op, ip, iend-ip);
+ DEBUGLOG(4, "ZSTD_compressEnd : %u", (U32)cSize);
+ if (ZSTD_isError(cSize)) return cSize;
+ ip = iend;
+ op += cSize;
+ zcs->frameEnded = 1;
+ ZSTD_startNewCompression(zcs);
+ someMoreWork = 0; break;
+ }
+ /* complete loading into inBuffer */
{ size_t const toLoad = zcs->inBuffTarget - zcs->inBuffPos;
- size_t const loaded = ZSTD_limitCopy(zcs->inBuff + zcs->inBuffPos, toLoad, ip, iend-ip);
+ size_t const loaded = ZSTD_limitCopy(
+ zcs->inBuff + zcs->inBuffPos, toLoad,
+ ip, iend-ip);
zcs->inBuffPos += loaded;
ip += loaded;
- if ( (zcs->inBuffPos==zcs->inToCompress) || (!flush && (toLoad != loaded)) ) {
- someMoreWork = 0; break; /* not enough input to get a full block : stop there, wait for more */
- } }
+ if ( (flushMode == ZSTD_e_continue)
+ && (zcs->inBuffPos < zcs->inBuffTarget) ) {
+ /* not enough input to fill full block : stop here */
+ someMoreWork = 0; break;
+ }
+ if ( (flushMode == ZSTD_e_flush)
+ && (zcs->inBuffPos == zcs->inToCompress) ) {
+ /* empty */
+ someMoreWork = 0; break;
+ }
+ }
/* compress current block (note : this stage cannot be stopped in the middle) */
+ DEBUGLOG(5, "stream compression stage (flushMode==%u)", flushMode);
{ void* cDst;
size_t cSize;
size_t const iSize = zcs->inBuffPos - zcs->inToCompress;
size_t oSize = oend-op;
+ unsigned const lastBlock = (flushMode == ZSTD_e_end) && (ip==iend);
if (oSize >= ZSTD_compressBound(iSize))
- cDst = op; /* compress directly into output buffer (avoid flush stage) */
+ cDst = op; /* compress into output buffer, to skip flush stage */
else
cDst = zcs->outBuff, oSize = zcs->outBuffSize;
- cSize = (flush == zsf_end) ?
- ZSTD_compressEnd(zcs->cctx, cDst, oSize, zcs->inBuff + zcs->inToCompress, iSize) :
- ZSTD_compressContinue(zcs->cctx, cDst, oSize, zcs->inBuff + zcs->inToCompress, iSize);
+ cSize = lastBlock ?
+ ZSTD_compressEnd(zcs, cDst, oSize,
+ zcs->inBuff + zcs->inToCompress, iSize) :
+ ZSTD_compressContinue(zcs, cDst, oSize,
+ zcs->inBuff + zcs->inToCompress, iSize);
if (ZSTD_isError(cSize)) return cSize;
- if (flush == zsf_end) zcs->frameEnded = 1;
+ zcs->frameEnded = lastBlock;
/* prepare next block */
zcs->inBuffTarget = zcs->inBuffPos + zcs->blockSize;
if (zcs->inBuffTarget > zcs->inBuffSize)
- zcs->inBuffPos = 0, zcs->inBuffTarget = zcs->blockSize; /* note : inBuffSize >= blockSize */
+ zcs->inBuffPos = 0, zcs->inBuffTarget = zcs->blockSize;
+ DEBUGLOG(5, "inBuffTarget:%u / inBuffSize:%u",
+ (U32)zcs->inBuffTarget, (U32)zcs->inBuffSize);
+ if (!lastBlock)
+ assert(zcs->inBuffTarget <= zcs->inBuffSize);
zcs->inToCompress = zcs->inBuffPos;
- if (cDst == op) { op += cSize; break; } /* no need to flush */
+ if (cDst == op) { /* no need to flush */
+ op += cSize;
+ if (zcs->frameEnded) {
+ DEBUGLOG(5, "Frame completed directly in outBuffer");
+ someMoreWork = 0;
+ ZSTD_startNewCompression(zcs);
+ }
+ break;
+ }
zcs->outBuffContentSize = cSize;
zcs->outBuffFlushedSize = 0;
- zcs->stage = zcss_flush; /* pass-through to flush stage */
+ zcs->streamStage = zcss_flush; /* pass-through to flush stage */
}
-
+ /* fall-through */
case zcss_flush:
+ DEBUGLOG(5, "flush stage");
{ size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
- size_t const flushed = ZSTD_limitCopy(op, oend-op, zcs->outBuff + zcs->outBuffFlushedSize, toFlush);
+ size_t const flushed = ZSTD_limitCopy(op, oend-op,
+ zcs->outBuff + zcs->outBuffFlushedSize, toFlush);
+ DEBUGLOG(5, "toFlush: %u into %u ==> flushed: %u",
+ (U32)toFlush, (U32)(oend-op), (U32)flushed);
op += flushed;
zcs->outBuffFlushedSize += flushed;
- if (toFlush!=flushed) { someMoreWork = 0; break; } /* dst too small to store flushed data : stop there */
+ if (toFlush!=flushed) {
+ /* flush not fully completed, presumably because dst is too small */
+ assert(op==oend);
+ someMoreWork = 0;
+ break;
+ }
zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0;
- zcs->stage = zcss_load;
+ if (zcs->frameEnded) {
+ DEBUGLOG(5, "Frame completed on flush");
+ someMoreWork = 0;
+ ZSTD_startNewCompression(zcs);
+ break;
+ }
+ zcs->streamStage = zcss_load;
break;
}
- case zcss_final:
- someMoreWork = 0; /* do nothing */
- break;
-
- default:
- return ERROR(GENERIC); /* impossible */
+ default: /* impossible */
+ assert(0);
}
}
- *srcSizePtr = ip - istart;
- *dstCapacityPtr = op - ostart;
+ input->pos = ip - istart;
+ output->pos = op - ostart;
if (zcs->frameEnded) return 0;
{ size_t hintInSize = zcs->inBuffTarget - zcs->inBuffPos;
if (hintInSize==0) hintInSize = zcs->blockSize;
@@ -3384,14 +3917,86 @@ static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
{
- size_t sizeRead = input->size - input->pos;
- size_t sizeWritten = output->size - output->pos;
- size_t const result = ZSTD_compressStream_generic(zcs,
- (char*)(output->dst) + output->pos, &sizeWritten,
- (const char*)(input->src) + input->pos, &sizeRead, zsf_gather);
- input->pos += sizeRead;
- output->pos += sizeWritten;
- return result;
+ /* check conditions */
+ if (output->pos > output->size) return ERROR(GENERIC);
+ if (input->pos > input->size) return ERROR(GENERIC);
+
+ return ZSTD_compressStream_generic(zcs, output, input, ZSTD_e_continue);
+}
+
+/*! ZSTDMT_initCStream_internal() :
+ * Private use only. Init streaming operation.
+ * expects params to be valid.
+ * must receive dict, or cdict, or none, but not both.
+ * @return : 0, or an error code */
+size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
+ const void* dict, size_t dictSize, const ZSTD_CDict* cdict,
+ ZSTD_parameters params, unsigned long long pledgedSrcSize);
+
+
+size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
+ ZSTD_outBuffer* output,
+ ZSTD_inBuffer* input,
+ ZSTD_EndDirective endOp)
+{
+ /* check conditions */
+ if (output->pos > output->size) return ERROR(GENERIC);
+ if (input->pos > input->size) return ERROR(GENERIC);
+ assert(cctx!=NULL);
+
+ /* transparent initialization stage */
+ if (cctx->streamStage == zcss_init) {
+ const void* const prefix = cctx->prefix;
+ size_t const prefixSize = cctx->prefixSize;
+ ZSTD_parameters params = cctx->requestedParams;
+ if (cctx->compressionLevel != ZSTD_CLEVEL_CUSTOM)
+ params.cParams = ZSTD_getCParams(cctx->compressionLevel,
+ cctx->pledgedSrcSizePlusOne-1, 0 /*dictSize*/);
+ cctx->prefix = NULL; cctx->prefixSize = 0; /* single usage */
+ assert(prefix==NULL || cctx->cdict==NULL); /* only one can be set */
+
+#ifdef ZSTD_MULTITHREAD
+ if (cctx->nbThreads > 1) {
+ DEBUGLOG(4, "call ZSTDMT_initCStream_internal as nbThreads=%u", cctx->nbThreads);
+ CHECK_F( ZSTDMT_initCStream_internal(cctx->mtctx, prefix, prefixSize, cctx->cdict, params, cctx->pledgedSrcSizePlusOne-1) );
+ cctx->streamStage = zcss_load;
+ } else
+#endif
+ {
+ CHECK_F( ZSTD_resetCStream_internal(cctx, prefix, prefixSize, cctx->dictMode, cctx->cdict, params, cctx->pledgedSrcSizePlusOne-1) );
+ } }
+
+ /* compression stage */
+#ifdef ZSTD_MULTITHREAD
+ if (cctx->nbThreads > 1) {
+ size_t const flushMin = ZSTDMT_compressStream_generic(cctx->mtctx, output, input, endOp);
+ DEBUGLOG(5, "ZSTDMT_compressStream_generic : %u", (U32)flushMin);
+ if ( ZSTD_isError(flushMin)
+ || (endOp == ZSTD_e_end && flushMin == 0) ) { /* compression completed */
+ ZSTD_startNewCompression(cctx);
+ }
+ return flushMin;
+ }
+#endif
+
+ CHECK_F( ZSTD_compressStream_generic(cctx, output, input, endOp) );
+ DEBUGLOG(5, "completed ZSTD_compress_generic");
+ return cctx->outBuffContentSize - cctx->outBuffFlushedSize; /* remaining to flush */
+}
+
+size_t ZSTD_compress_generic_simpleArgs (
+ ZSTD_CCtx* cctx,
+ void* dst, size_t dstCapacity, size_t* dstPos,
+ const void* src, size_t srcSize, size_t* srcPos,
+ ZSTD_EndDirective endOp)
+{
+ ZSTD_outBuffer output = { dst, dstCapacity, *dstPos };
+ ZSTD_inBuffer input = { src, srcSize, *srcPos };
+ /* ZSTD_compress_generic() will check validity of dstPos and srcPos */
+ size_t const cErr = ZSTD_compress_generic(cctx, &output, &input, endOp);
+ *dstPos = output.pos;
+ *srcPos = input.pos;
+ return cErr;
}
@@ -3401,89 +4006,59 @@ size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuf
* @return : amount of data remaining to flush */
size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output)
{
- size_t srcSize = 0;
- size_t sizeWritten = output->size - output->pos;
- size_t const result = ZSTD_compressStream_generic(zcs,
- (char*)(output->dst) + output->pos, &sizeWritten,
- &srcSize, &srcSize, /* use a valid src address instead of NULL */
- zsf_flush);
- output->pos += sizeWritten;
- if (ZSTD_isError(result)) return result;
- return zcs->outBuffContentSize - zcs->outBuffFlushedSize; /* remaining to flush */
+ ZSTD_inBuffer input = { NULL, 0, 0 };
+ if (output->pos > output->size) return ERROR(GENERIC);
+ CHECK_F( ZSTD_compressStream_generic(zcs, output, &input, ZSTD_e_flush) );
+ return zcs->outBuffContentSize - zcs->outBuffFlushedSize; /* remaining to flush */
}
size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output)
{
- BYTE* const ostart = (BYTE*)(output->dst) + output->pos;
- BYTE* const oend = (BYTE*)(output->dst) + output->size;
- BYTE* op = ostart;
-
- if (zcs->stage != zcss_final) {
- /* flush whatever remains */
- size_t srcSize = 0;
- size_t sizeWritten = output->size - output->pos;
- size_t const notEnded = ZSTD_compressStream_generic(zcs, ostart, &sizeWritten,
- &srcSize /* use a valid src address instead of NULL */, &srcSize, zsf_end);
- size_t const remainingToFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
- op += sizeWritten;
- if (remainingToFlush) {
- output->pos += sizeWritten;
- return remainingToFlush + ZSTD_BLOCKHEADERSIZE /* final empty block */ + (zcs->checksum * 4);
- }
- /* create epilogue */
- zcs->stage = zcss_final;
- zcs->outBuffContentSize = !notEnded ? 0 :
- /* write epilogue, including final empty block, into outBuff */
- ZSTD_compressEnd(zcs->cctx, zcs->outBuff, zcs->outBuffSize, NULL, 0);
- if (ZSTD_isError(zcs->outBuffContentSize)) return zcs->outBuffContentSize;
- }
-
- /* flush epilogue */
- { size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
- size_t const flushed = ZSTD_limitCopy(op, oend-op, zcs->outBuff + zcs->outBuffFlushedSize, toFlush);
- op += flushed;
- zcs->outBuffFlushedSize += flushed;
- output->pos += op-ostart;
- if (toFlush==flushed) zcs->stage = zcss_init; /* end reached */
- return toFlush - flushed;
+ ZSTD_inBuffer input = { NULL, 0, 0 };
+ if (output->pos > output->size) return ERROR(GENERIC);
+ CHECK_F( ZSTD_compressStream_generic(zcs, output, &input, ZSTD_e_end) );
+ { size_t const lastBlockSize = zcs->frameEnded ? 0 : ZSTD_BLOCKHEADERSIZE;
+ size_t const checksumSize = zcs->frameEnded ? 0 : zcs->appliedParams.fParams.checksumFlag * 4;
+ size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize + lastBlockSize + checksumSize;
+ DEBUGLOG(5, "ZSTD_endStream : remaining to flush : %u",
+ (unsigned)toFlush);
+ return toFlush;
}
}
-
/*-===== Pre-defined compression levels =====-*/
-#define ZSTD_DEFAULT_CLEVEL 1
#define ZSTD_MAX_CLEVEL 22
int ZSTD_maxCLevel(void) { return ZSTD_MAX_CLEVEL; }
static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEVEL+1] = {
-{ /* "default" */
+{ /* "default" - guarantees a monotonically increasing memory budget */
/* W, C, H, S, L, TL, strat */
{ 18, 12, 12, 1, 7, 16, ZSTD_fast }, /* level 0 - never used */
{ 19, 13, 14, 1, 7, 16, ZSTD_fast }, /* level 1 */
{ 19, 15, 16, 1, 6, 16, ZSTD_fast }, /* level 2 */
- { 20, 16, 17, 1, 5, 16, ZSTD_dfast }, /* level 3.*/
- { 20, 18, 18, 1, 5, 16, ZSTD_dfast }, /* level 4.*/
- { 20, 15, 18, 3, 5, 16, ZSTD_greedy }, /* level 5 */
- { 21, 16, 19, 2, 5, 16, ZSTD_lazy }, /* level 6 */
- { 21, 17, 20, 3, 5, 16, ZSTD_lazy }, /* level 7 */
+ { 20, 16, 17, 1, 5, 16, ZSTD_dfast }, /* level 3 */
+ { 20, 17, 18, 1, 5, 16, ZSTD_dfast }, /* level 4 */
+ { 20, 17, 18, 2, 5, 16, ZSTD_greedy }, /* level 5 */
+ { 21, 17, 19, 2, 5, 16, ZSTD_lazy }, /* level 6 */
+ { 21, 18, 19, 3, 5, 16, ZSTD_lazy }, /* level 7 */
{ 21, 18, 20, 3, 5, 16, ZSTD_lazy2 }, /* level 8 */
- { 21, 20, 20, 3, 5, 16, ZSTD_lazy2 }, /* level 9 */
+ { 21, 19, 20, 3, 5, 16, ZSTD_lazy2 }, /* level 9 */
{ 21, 19, 21, 4, 5, 16, ZSTD_lazy2 }, /* level 10 */
{ 22, 20, 22, 4, 5, 16, ZSTD_lazy2 }, /* level 11 */
{ 22, 20, 22, 5, 5, 16, ZSTD_lazy2 }, /* level 12 */
{ 22, 21, 22, 5, 5, 16, ZSTD_lazy2 }, /* level 13 */
{ 22, 21, 22, 6, 5, 16, ZSTD_lazy2 }, /* level 14 */
- { 22, 21, 21, 5, 5, 16, ZSTD_btlazy2 }, /* level 15 */
+ { 22, 21, 22, 5, 5, 16, ZSTD_btlazy2 }, /* level 15 */
{ 23, 22, 22, 5, 5, 16, ZSTD_btlazy2 }, /* level 16 */
- { 23, 21, 22, 4, 5, 24, ZSTD_btopt }, /* level 17 */
+ { 23, 22, 22, 4, 5, 24, ZSTD_btopt }, /* level 17 */
{ 23, 22, 22, 5, 4, 32, ZSTD_btopt }, /* level 18 */
{ 23, 23, 22, 6, 3, 48, ZSTD_btopt }, /* level 19 */
- { 25, 25, 23, 7, 3, 64, ZSTD_btopt2 }, /* level 20 */
- { 26, 26, 23, 7, 3,256, ZSTD_btopt2 }, /* level 21 */
- { 27, 27, 25, 9, 3,512, ZSTD_btopt2 }, /* level 22 */
+ { 25, 25, 23, 7, 3, 64, ZSTD_btultra }, /* level 20 */
+ { 26, 26, 24, 7, 3,256, ZSTD_btultra }, /* level 21 */
+ { 27, 27, 25, 9, 3,512, ZSTD_btultra }, /* level 22 */
},
{ /* for srcSize <= 256 KB */
/* W, C, H, S, L, T, strat */
@@ -3507,9 +4082,9 @@ static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEV
{ 18, 19, 18, 8, 3, 64, ZSTD_btopt }, /* level 17.*/
{ 18, 19, 18, 9, 3,128, ZSTD_btopt }, /* level 18.*/
{ 18, 19, 18, 10, 3,256, ZSTD_btopt }, /* level 19.*/
- { 18, 19, 18, 11, 3,512, ZSTD_btopt2 }, /* level 20.*/
- { 18, 19, 18, 12, 3,512, ZSTD_btopt2 }, /* level 21.*/
- { 18, 19, 18, 13, 3,512, ZSTD_btopt2 }, /* level 22.*/
+ { 18, 19, 18, 11, 3,512, ZSTD_btultra }, /* level 20.*/
+ { 18, 19, 18, 12, 3,512, ZSTD_btultra }, /* level 21.*/
+ { 18, 19, 18, 13, 3,512, ZSTD_btultra }, /* level 22.*/
},
{ /* for srcSize <= 128 KB */
/* W, C, H, S, L, T, strat */
@@ -3533,9 +4108,9 @@ static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEV
{ 17, 18, 17, 7, 3, 64, ZSTD_btopt }, /* level 17.*/
{ 17, 18, 17, 7, 3,256, ZSTD_btopt }, /* level 18.*/
{ 17, 18, 17, 8, 3,256, ZSTD_btopt }, /* level 19.*/
- { 17, 18, 17, 9, 3,256, ZSTD_btopt2 }, /* level 20.*/
- { 17, 18, 17, 10, 3,256, ZSTD_btopt2 }, /* level 21.*/
- { 17, 18, 17, 11, 3,512, ZSTD_btopt2 }, /* level 22.*/
+ { 17, 18, 17, 9, 3,256, ZSTD_btultra }, /* level 20.*/
+ { 17, 18, 17, 10, 3,256, ZSTD_btultra }, /* level 21.*/
+ { 17, 18, 17, 11, 3,512, ZSTD_btultra }, /* level 22.*/
},
{ /* for srcSize <= 16 KB */
/* W, C, H, S, L, T, strat */
@@ -3559,39 +4134,59 @@ static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEV
{ 14, 15, 15, 6, 3,128, ZSTD_btopt }, /* level 17.*/
{ 14, 15, 15, 6, 3,256, ZSTD_btopt }, /* level 18.*/
{ 14, 15, 15, 7, 3,256, ZSTD_btopt }, /* level 19.*/
- { 14, 15, 15, 8, 3,256, ZSTD_btopt2 }, /* level 20.*/
- { 14, 15, 15, 9, 3,256, ZSTD_btopt2 }, /* level 21.*/
- { 14, 15, 15, 10, 3,256, ZSTD_btopt2 }, /* level 22.*/
+ { 14, 15, 15, 8, 3,256, ZSTD_btultra }, /* level 20.*/
+ { 14, 15, 15, 9, 3,256, ZSTD_btultra }, /* level 21.*/
+ { 14, 15, 15, 10, 3,256, ZSTD_btultra }, /* level 22.*/
},
};
+#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=1)
+/* This function just controls
+ * the monotonic memory budget increase of ZSTD_defaultCParameters[0].
+ * Run once, on first ZSTD_getCParams() usage, if ZSTD_DEBUG is enabled
+ */
+MEM_STATIC void ZSTD_check_compressionLevel_monotonicIncrease_memoryBudget(void)
+{
+ int level;
+ for (level=1; level<ZSTD_maxCLevel(); level++) {
+ ZSTD_compressionParameters const c1 = ZSTD_defaultCParameters[0][level];
+ ZSTD_compressionParameters const c2 = ZSTD_defaultCParameters[0][level+1];
+ assert(c1.windowLog <= c2.windowLog);
+# define ZSTD_TABLECOST(h,c) ((1<<(h)) + (1<<(c)))
+ assert(ZSTD_TABLECOST(c1.hashLog, c1.chainLog) <= ZSTD_TABLECOST(c2.hashLog, c2.chainLog));
+ }
+}
+#endif
+
/*! ZSTD_getCParams() :
* @return ZSTD_compressionParameters structure for a selected compression level, `srcSize` and `dictSize`.
* Size values are optional, provide 0 if not known or unused */
-ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSize, size_t dictSize)
+ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize)
{
- ZSTD_compressionParameters cp;
- size_t const addedSize = srcSize ? 0 : 500;
- U64 const rSize = srcSize+dictSize ? srcSize+dictSize+addedSize : (U64)-1;
+ size_t const addedSize = srcSizeHint ? 0 : 500;
+ U64 const rSize = srcSizeHint+dictSize ? srcSizeHint+dictSize+addedSize : (U64)-1;
U32 const tableID = (rSize <= 256 KB) + (rSize <= 128 KB) + (rSize <= 16 KB); /* intentional underflow for srcSizeHint == 0 */
- if (compressionLevel <= 0) compressionLevel = ZSTD_DEFAULT_CLEVEL; /* 0 == default; no negative compressionLevel yet */
- if (compressionLevel > ZSTD_MAX_CLEVEL) compressionLevel = ZSTD_MAX_CLEVEL;
- cp = ZSTD_defaultCParameters[tableID][compressionLevel];
- if (MEM_32bits()) { /* auto-correction, for 32-bits mode */
- if (cp.windowLog > ZSTD_WINDOWLOG_MAX) cp.windowLog = ZSTD_WINDOWLOG_MAX;
- if (cp.chainLog > ZSTD_CHAINLOG_MAX) cp.chainLog = ZSTD_CHAINLOG_MAX;
- if (cp.hashLog > ZSTD_HASHLOG_MAX) cp.hashLog = ZSTD_HASHLOG_MAX;
+
+#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=1)
+ static int g_monotonicTest = 1;
+ if (g_monotonicTest) {
+ ZSTD_check_compressionLevel_monotonicIncrease_memoryBudget();
+ g_monotonicTest=0;
}
- cp = ZSTD_adjustCParams(cp, srcSize, dictSize);
- return cp;
+#endif
+
+ if (compressionLevel <= 0) compressionLevel = ZSTD_CLEVEL_DEFAULT; /* 0 == default; no negative compressionLevel yet */
+ if (compressionLevel > ZSTD_MAX_CLEVEL) compressionLevel = ZSTD_MAX_CLEVEL;
+ { ZSTD_compressionParameters const cp = ZSTD_defaultCParameters[tableID][compressionLevel];
+ return ZSTD_adjustCParams_internal(cp, srcSizeHint, dictSize); }
}
/*! ZSTD_getParams() :
* same as ZSTD_getCParams(), but @return a `ZSTD_parameters` object (instead of `ZSTD_compressionParameters`).
* All fields of `ZSTD_frameParameters` are set to default (0) */
-ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSize, size_t dictSize) {
+ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize) {
ZSTD_parameters params;
- ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, srcSize, dictSize);
+ ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, srcSizeHint, dictSize);
memset(&params, 0, sizeof(params));
params.cParams = cParams;
return params;
diff --git a/lib/compress/zstd_opt.h b/lib/compress/zstd_opt.h
index 54376119121d6..e8e98915ea31b 100644
--- a/lib/compress/zstd_opt.h
+++ b/lib/compress/zstd_opt.h
@@ -43,6 +43,7 @@ MEM_STATIC void ZSTD_rescaleFreqs(seqStore_t* ssPtr, const BYTE* src, size_t src
if (ssPtr->litLengthSum == 0) {
if (srcSize <= 1024) ssPtr->staticPrices = 1;
+ assert(ssPtr->litFreq!=NULL);
for (u=0; u<=MaxLit; u++)
ssPtr->litFreq[u] = 0;
for (u=0; u<srcSize; u++)
@@ -201,6 +202,20 @@ MEM_STATIC void ZSTD_updatePrice(seqStore_t* seqStorePtr, U32 litLength, const B
}
+/* function safe only for comparisons */
+MEM_STATIC U32 ZSTD_readMINMATCH(const void* memPtr, U32 length)
+{
+ switch (length)
+ {
+ default :
+ case 4 : return MEM_read32(memPtr);
+ case 3 : if (MEM_isLittleEndian())
+ return MEM_read32(memPtr)<<8;
+ else
+ return MEM_read32(memPtr)>>8;
+ }
+}
+
/* Update hashTable3 up to ip (excluded)
Assumption : always within prefix (i.e. not within extDict) */
@@ -234,12 +249,12 @@ static U32 ZSTD_insertBtAndGetAllMatches (
{
const BYTE* const base = zc->base;
const U32 current = (U32)(ip-base);
- const U32 hashLog = zc->params.cParams.hashLog;
+ const U32 hashLog = zc->appliedParams.cParams.hashLog;
const size_t h = ZSTD_hashPtr(ip, hashLog, mls);
U32* const hashTable = zc->hashTable;
U32 matchIndex = hashTable[h];
U32* const bt = zc->chainTable;
- const U32 btLog = zc->params.cParams.chainLog - 1;
+ const U32 btLog = zc->appliedParams.cParams.chainLog - 1;
const U32 btMask= (1U << btLog) - 1;
size_t commonLengthSmaller=0, commonLengthLarger=0;
const BYTE* const dictBase = zc->dictBase;
@@ -267,7 +282,7 @@ static U32 ZSTD_insertBtAndGetAllMatches (
if (match[bestLength] == ip[bestLength]) currentMl = ZSTD_count(ip, match, iLimit);
} else {
match = dictBase + matchIndex3;
- if (MEM_readMINMATCH(match, MINMATCH) == MEM_readMINMATCH(ip, MINMATCH)) /* assumption : matchIndex3 <= dictLimit-4 (by table construction) */
+ if (ZSTD_readMINMATCH(match, MINMATCH) == ZSTD_readMINMATCH(ip, MINMATCH)) /* assumption : matchIndex3 <= dictLimit-4 (by table construction) */
currentMl = ZSTD_count_2segments(ip+MINMATCH, match+MINMATCH, iLimit, dictEnd, prefixStart) + MINMATCH;
}
@@ -410,10 +425,10 @@ void ZSTD_compressBlock_opt_generic(ZSTD_CCtx* ctx,
const BYTE* const base = ctx->base;
const BYTE* const prefixStart = base + ctx->dictLimit;
- const U32 maxSearches = 1U << ctx->params.cParams.searchLog;
- const U32 sufficient_len = ctx->params.cParams.targetLength;
- const U32 mls = ctx->params.cParams.searchLength;
- const U32 minMatch = (ctx->params.cParams.searchLength == 3) ? 3 : 4;
+ const U32 maxSearches = 1U << ctx->appliedParams.cParams.searchLog;
+ const U32 sufficient_len = ctx->appliedParams.cParams.targetLength;
+ const U32 mls = ctx->appliedParams.cParams.searchLength;
+ const U32 minMatch = (ctx->appliedParams.cParams.searchLength == 3) ? 3 : 4;
ZSTD_optimal_t* opt = seqStorePtr->priceTable;
ZSTD_match_t* matches = seqStorePtr->matchTable;
@@ -439,7 +454,7 @@ void ZSTD_compressBlock_opt_generic(ZSTD_CCtx* ctx,
for (i=(ip == anchor); i<last_i; i++) {
const S32 repCur = (i==ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : rep[i];
if ( (repCur > 0) && (repCur < (S32)(ip-prefixStart))
- && (MEM_readMINMATCH(ip, minMatch) == MEM_readMINMATCH(ip - repCur, minMatch))) {
+ && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(ip - repCur, minMatch))) {
mlen = (U32)ZSTD_count(ip+minMatch, ip+minMatch-repCur, iend) + minMatch;
if (mlen > sufficient_len || mlen >= ZSTD_OPT_NUM) {
best_mlen = mlen; best_off = i; cur = 0; last_pos = 1;
@@ -524,7 +539,7 @@ void ZSTD_compressBlock_opt_generic(ZSTD_CCtx* ctx,
for (i=(opt[cur].mlen != 1); i<last_i; i++) { /* check rep */
const S32 repCur = (i==ZSTD_REP_MOVE_OPT) ? (opt[cur].rep[0] - 1) : opt[cur].rep[i];
if ( (repCur > 0) && (repCur < (S32)(inr-prefixStart))
- && (MEM_readMINMATCH(inr, minMatch) == MEM_readMINMATCH(inr - repCur, minMatch))) {
+ && (ZSTD_readMINMATCH(inr, minMatch) == ZSTD_readMINMATCH(inr - repCur, minMatch))) {
mlen = (U32)ZSTD_count(inr+minMatch, inr+minMatch - repCur, iend) + minMatch;
if (mlen > sufficient_len || cur + mlen >= ZSTD_OPT_NUM) {
@@ -663,10 +678,10 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx,
const BYTE* const dictBase = ctx->dictBase;
const BYTE* const dictEnd = dictBase + dictLimit;
- const U32 maxSearches = 1U << ctx->params.cParams.searchLog;
- const U32 sufficient_len = ctx->params.cParams.targetLength;
- const U32 mls = ctx->params.cParams.searchLength;
- const U32 minMatch = (ctx->params.cParams.searchLength == 3) ? 3 : 4;
+ const U32 maxSearches = 1U << ctx->appliedParams.cParams.searchLog;
+ const U32 sufficient_len = ctx->appliedParams.cParams.targetLength;
+ const U32 mls = ctx->appliedParams.cParams.searchLength;
+ const U32 minMatch = (ctx->appliedParams.cParams.searchLength == 3) ? 3 : 4;
ZSTD_optimal_t* opt = seqStorePtr->priceTable;
ZSTD_match_t* matches = seqStorePtr->matchTable;
@@ -698,7 +713,7 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx,
const BYTE* const repMatch = repBase + repIndex;
if ( (repCur > 0 && repCur <= (S32)current)
&& (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex>lowestIndex)) /* intentional overflow */
- && (MEM_readMINMATCH(ip, minMatch) == MEM_readMINMATCH(repMatch, minMatch)) ) {
+ && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) {
/* repcode detected we should take it */
const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
mlen = (U32)ZSTD_count_2segments(ip+minMatch, repMatch+minMatch, iend, repEnd, prefixStart) + minMatch;
@@ -794,7 +809,7 @@ void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx* ctx,
const BYTE* const repMatch = repBase + repIndex;
if ( (repCur > 0 && repCur <= (S32)(current+cur))
&& (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex>lowestIndex)) /* intentional overflow */
- && (MEM_readMINMATCH(inr, minMatch) == MEM_readMINMATCH(repMatch, minMatch)) ) {
+ && (ZSTD_readMINMATCH(inr, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) {
/* repcode detected */
const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
mlen = (U32)ZSTD_count_2segments(inr+minMatch, repMatch+minMatch, iend, repEnd, prefixStart) + minMatch;
diff --git a/lib/compress/zstdmt_compress.c b/lib/compress/zstdmt_compress.c
index fc7f52a2902d3..0cee01eacb865 100644
--- a/lib/compress/zstdmt_compress.c
+++ b/lib/compress/zstdmt_compress.c
@@ -14,34 +14,31 @@
/* ====== Compiler specifics ====== */
#if defined(_MSC_VER)
-# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */
+# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */
#endif
/* ====== Dependencies ====== */
-#include <stdlib.h> /* malloc */
-#include <string.h> /* memcpy */
-#include "pool.h" /* threadpool */
-#include "threading.h" /* mutex */
-#include "zstd_internal.h" /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */
+#include <string.h> /* memcpy, memset */
+#include "pool.h" /* threadpool */
+#include "threading.h" /* mutex */
+#include "zstd_internal.h" /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */
#include "zstdmt_compress.h"
/* ====== Debug ====== */
-#if 0
+#if defined(ZSTD_DEBUG) && (ZSTD_DEBUG>=2)
# include <stdio.h>
# include <unistd.h>
# include <sys/times.h>
- static unsigned g_debugLevel = 5;
-# define DEBUGLOGRAW(l, ...) if (l<=g_debugLevel) { fprintf(stderr, __VA_ARGS__); }
-# define DEBUGLOG(l, ...) if (l<=g_debugLevel) { fprintf(stderr, __FILE__ ": "); fprintf(stderr, __VA_ARGS__); fprintf(stderr, " \n"); }
+# define DEBUGLOGRAW(l, ...) if (l<=ZSTD_DEBUG) { fprintf(stderr, __VA_ARGS__); }
-# define DEBUG_PRINTHEX(l,p,n) { \
- unsigned debug_u; \
- for (debug_u=0; debug_u<(n); debug_u++) \
+# define DEBUG_PRINTHEX(l,p,n) { \
+ unsigned debug_u; \
+ for (debug_u=0; debug_u<(n); debug_u++) \
DEBUGLOGRAW(l, "%02X ", ((const unsigned char*)(p))[debug_u]); \
- DEBUGLOGRAW(l, " \n"); \
+ DEBUGLOGRAW(l, " \n"); \
}
static unsigned long long GetCurrentClockTimeMicroseconds(void)
@@ -53,22 +50,22 @@ static unsigned long long GetCurrentClockTimeMicroseconds(void)
return ((((unsigned long long)newTicks)*(1000000))/_ticksPerSecond); }
}
-#define MUTEX_WAIT_TIME_DLEVEL 5
-#define PTHREAD_MUTEX_LOCK(mutex) \
-if (g_debugLevel>=MUTEX_WAIT_TIME_DLEVEL) { \
- unsigned long long const beforeTime = GetCurrentClockTimeMicroseconds(); \
- pthread_mutex_lock(mutex); \
- { unsigned long long const afterTime = GetCurrentClockTimeMicroseconds(); \
- unsigned long long const elapsedTime = (afterTime-beforeTime); \
- if (elapsedTime > 1000) { /* or whatever threshold you like; I'm using 1 millisecond here */ \
- DEBUGLOG(MUTEX_WAIT_TIME_DLEVEL, "Thread took %llu microseconds to acquire mutex %s \n", \
- elapsedTime, #mutex); \
- } } \
-} else pthread_mutex_lock(mutex);
+#define MUTEX_WAIT_TIME_DLEVEL 6
+#define PTHREAD_MUTEX_LOCK(mutex) { \
+ if (ZSTD_DEBUG>=MUTEX_WAIT_TIME_DLEVEL) { \
+ unsigned long long const beforeTime = GetCurrentClockTimeMicroseconds(); \
+ pthread_mutex_lock(mutex); \
+ { unsigned long long const afterTime = GetCurrentClockTimeMicroseconds(); \
+ unsigned long long const elapsedTime = (afterTime-beforeTime); \
+ if (elapsedTime > 1000) { /* or whatever threshold you like; I'm using 1 millisecond here */ \
+ DEBUGLOG(MUTEX_WAIT_TIME_DLEVEL, "Thread took %llu microseconds to acquire mutex %s \n", \
+ elapsedTime, #mutex); \
+ } } \
+ } else pthread_mutex_lock(mutex); \
+}
#else
-# define DEBUGLOG(l, ...) {} /* disabled */
# define PTHREAD_MUTEX_LOCK(m) pthread_mutex_lock(m)
# define DEBUG_PRINTHEX(l,p,n) {}
@@ -87,16 +84,19 @@ static const buffer_t g_nullBuffer = { NULL, 0 };
typedef struct ZSTDMT_bufferPool_s {
unsigned totalBuffers;
unsigned nbBuffers;
+ ZSTD_customMem cMem;
buffer_t bTable[1]; /* variable size */
} ZSTDMT_bufferPool;
-static ZSTDMT_bufferPool* ZSTDMT_createBufferPool(unsigned nbThreads)
+static ZSTDMT_bufferPool* ZSTDMT_createBufferPool(unsigned nbThreads, ZSTD_customMem cMem)
{
unsigned const maxNbBuffers = 2*nbThreads + 2;
- ZSTDMT_bufferPool* const bufPool = (ZSTDMT_bufferPool*)calloc(1, sizeof(ZSTDMT_bufferPool) + (maxNbBuffers-1) * sizeof(buffer_t));
+ ZSTDMT_bufferPool* const bufPool = (ZSTDMT_bufferPool*)ZSTD_calloc(
+ sizeof(ZSTDMT_bufferPool) + (maxNbBuffers-1) * sizeof(buffer_t), cMem);
if (bufPool==NULL) return NULL;
bufPool->totalBuffers = maxNbBuffers;
bufPool->nbBuffers = 0;
+ bufPool->cMem = cMem;
return bufPool;
}
@@ -105,23 +105,39 @@ static void ZSTDMT_freeBufferPool(ZSTDMT_bufferPool* bufPool)
unsigned u;
if (!bufPool) return; /* compatibility with free on NULL */
for (u=0; u<bufPool->totalBuffers; u++)
- free(bufPool->bTable[u].start);
- free(bufPool);
+ ZSTD_free(bufPool->bTable[u].start, bufPool->cMem);
+ ZSTD_free(bufPool, bufPool->cMem);
+}
+
+/* only works at initialization, not during compression */
+static size_t ZSTDMT_sizeof_bufferPool(ZSTDMT_bufferPool* bufPool)
+{
+ size_t const poolSize = sizeof(*bufPool)
+ + (bufPool->totalBuffers - 1) * sizeof(buffer_t);
+ unsigned u;
+ size_t totalBufferSize = 0;
+ for (u=0; u<bufPool->totalBuffers; u++)
+ totalBufferSize += bufPool->bTable[u].size;
+
+ return poolSize + totalBufferSize;
}
-/* assumption : invocation from main thread only ! */
+/** ZSTDMT_getBuffer() :
+ * assumption : invocation from main thread only ! */
static buffer_t ZSTDMT_getBuffer(ZSTDMT_bufferPool* pool, size_t bSize)
{
if (pool->nbBuffers) { /* try to use an existing buffer */
buffer_t const buf = pool->bTable[--(pool->nbBuffers)];
size_t const availBufferSize = buf.size;
- if ((availBufferSize >= bSize) & (availBufferSize <= 10*bSize)) /* large enough, but not too much */
+ if ((availBufferSize >= bSize) & (availBufferSize <= 10*bSize))
+ /* large enough, but not too much */
return buf;
- free(buf.start); /* size conditions not respected : scratch this buffer and create a new one */
+ /* size conditions not respected : scratch this buffer, create new one */
+ ZSTD_free(buf.start, pool->cMem);
}
/* create new buffer */
{ buffer_t buffer;
- void* const start = malloc(bSize);
+ void* const start = ZSTD_malloc(bSize, pool->cMem);
if (start==NULL) bSize = 0;
buffer.start = start; /* note : start can be NULL if malloc fails ! */
buffer.size = bSize;
@@ -138,7 +154,7 @@ static void ZSTDMT_releaseBuffer(ZSTDMT_bufferPool* pool, buffer_t buf)
return;
}
/* Reached bufferPool capacity (should not happen) */
- free(buf.start);
+ ZSTD_free(buf.start, pool->cMem);
}
@@ -147,6 +163,7 @@ static void ZSTDMT_releaseBuffer(ZSTDMT_bufferPool* pool, buffer_t buf)
typedef struct {
unsigned totalCCtx;
unsigned availCCtx;
+ ZSTD_customMem cMem;
ZSTD_CCtx* cctx[1]; /* variable size */
} ZSTDMT_CCtxPool;
@@ -158,23 +175,40 @@ static void ZSTDMT_freeCCtxPool(ZSTDMT_CCtxPool* pool)
unsigned u;
for (u=0; u<pool->totalCCtx; u++)
ZSTD_freeCCtx(pool->cctx[u]); /* note : compatible with free on NULL */
- free(pool);
+ ZSTD_free(pool, pool->cMem);
}
/* ZSTDMT_createCCtxPool() :
* implies nbThreads >= 1 , checked by caller ZSTDMT_createCCtx() */
-static ZSTDMT_CCtxPool* ZSTDMT_createCCtxPool(unsigned nbThreads)
+static ZSTDMT_CCtxPool* ZSTDMT_createCCtxPool(unsigned nbThreads,
+ ZSTD_customMem cMem)
{
- ZSTDMT_CCtxPool* const cctxPool = (ZSTDMT_CCtxPool*) calloc(1, sizeof(ZSTDMT_CCtxPool) + (nbThreads-1)*sizeof(ZSTD_CCtx*));
+ ZSTDMT_CCtxPool* const cctxPool = (ZSTDMT_CCtxPool*) ZSTD_calloc(
+ sizeof(ZSTDMT_CCtxPool) + (nbThreads-1)*sizeof(ZSTD_CCtx*), cMem);
if (!cctxPool) return NULL;
+ cctxPool->cMem = cMem;
cctxPool->totalCCtx = nbThreads;
cctxPool->availCCtx = 1; /* at least one cctx for single-thread mode */
- cctxPool->cctx[0] = ZSTD_createCCtx();
+ cctxPool->cctx[0] = ZSTD_createCCtx_advanced(cMem);
if (!cctxPool->cctx[0]) { ZSTDMT_freeCCtxPool(cctxPool); return NULL; }
- DEBUGLOG(1, "cctxPool created, with %u threads", nbThreads);
+ DEBUGLOG(3, "cctxPool created, with %u threads", nbThreads);
return cctxPool;
}
+/* only works during initialization phase, not during compression */
+static size_t ZSTDMT_sizeof_CCtxPool(ZSTDMT_CCtxPool* cctxPool)
+{
+ unsigned const nbThreads = cctxPool->totalCCtx;
+ size_t const poolSize = sizeof(*cctxPool)
+ + (nbThreads-1)*sizeof(ZSTD_CCtx*);
+ unsigned u;
+ size_t totalCCtxSize = 0;
+ for (u=0; u<nbThreads; u++)
+ totalCCtxSize += ZSTD_sizeof_CCtx(cctxPool->cctx[u]);
+
+ return poolSize + totalCCtxSize;
+}
+
static ZSTD_CCtx* ZSTDMT_getCCtx(ZSTDMT_CCtxPool* pool)
{
if (pool->availCCtx) {
@@ -218,7 +252,7 @@ typedef struct {
pthread_mutex_t* jobCompleted_mutex;
pthread_cond_t* jobCompleted_cond;
ZSTD_parameters params;
- ZSTD_CDict* cdict;
+ const ZSTD_CDict* cdict;
unsigned long long fullFrameSize;
} ZSTDMT_jobDescription;
@@ -228,11 +262,11 @@ void ZSTDMT_compressChunk(void* jobDescription)
ZSTDMT_jobDescription* const job = (ZSTDMT_jobDescription*)jobDescription;
const void* const src = (const char*)job->srcStart + job->dictSize;
buffer_t const dstBuff = job->dstBuff;
- DEBUGLOG(3, "job (first:%u) (last:%u) : dictSize %u, srcSize %u",
+ DEBUGLOG(5, "job (first:%u) (last:%u) : dictSize %u, srcSize %u",
job->firstChunk, job->lastChunk, (U32)job->dictSize, (U32)job->srcSize);
if (job->cdict) { /* should only happen for first segment */
size_t const initError = ZSTD_compressBegin_usingCDict_advanced(job->cctx, job->cdict, job->params.fParams, job->fullFrameSize);
- if (job->cdict) DEBUGLOG(3, "using CDict ");
+ DEBUGLOG(5, "using CDict");
if (ZSTD_isError(initError)) { job->cSize = initError; goto _endJob; }
} else { /* srcStart points at reloaded section */
if (!job->firstChunk) job->params.fParams.contentSizeFlag = 0; /* ensure no srcSize control */
@@ -247,12 +281,12 @@ void ZSTDMT_compressChunk(void* jobDescription)
ZSTD_invalidateRepCodes(job->cctx);
}
- DEBUGLOG(4, "Compressing : ");
+ DEBUGLOG(5, "Compressing : ");
DEBUG_PRINTHEX(4, job->srcStart, 12);
job->cSize = (job->lastChunk) ?
ZSTD_compressEnd (job->cctx, dstBuff.start, dstBuff.size, src, job->srcSize) :
ZSTD_compressContinue(job->cctx, dstBuff.start, dstBuff.size, src, job->srcSize);
- DEBUGLOG(3, "compressed %u bytes into %u bytes (first:%u) (last:%u)",
+ DEBUGLOG(5, "compressed %u bytes into %u bytes (first:%u) (last:%u)",
(unsigned)job->srcSize, (unsigned)job->cSize, job->firstChunk, job->lastChunk);
DEBUGLOG(5, "dstBuff.size : %u ; => %s", (U32)dstBuff.size, ZSTD_getErrorName(job->cSize));
@@ -271,6 +305,7 @@ _endJob:
struct ZSTDMT_CCtx_s {
POOL_ctx* factory;
+ ZSTDMT_jobDescription* jobs;
ZSTDMT_bufferPool* buffPool;
ZSTDMT_CCtxPool* cctxPool;
pthread_mutex_t jobCompleted_mutex;
@@ -292,50 +327,64 @@ struct ZSTDMT_CCtx_s {
unsigned overlapRLog;
unsigned long long frameContentSize;
size_t sectionSize;
- ZSTD_CDict* cdict;
- ZSTD_CStream* cstream;
- ZSTDMT_jobDescription jobs[1]; /* variable size (must lies at the end) */
+ ZSTD_customMem cMem;
+ ZSTD_CDict* cdictLocal;
+ const ZSTD_CDict* cdict;
};
-ZSTDMT_CCtx *ZSTDMT_createCCtx(unsigned nbThreads)
+static ZSTDMT_jobDescription* ZSTDMT_allocJobsTable(U32* nbJobsPtr, ZSTD_customMem cMem)
{
- ZSTDMT_CCtx* cctx;
- U32 const minNbJobs = nbThreads + 2;
- U32 const nbJobsLog2 = ZSTD_highbit32(minNbJobs) + 1;
+ U32 const nbJobsLog2 = ZSTD_highbit32(*nbJobsPtr) + 1;
U32 const nbJobs = 1 << nbJobsLog2;
- DEBUGLOG(5, "nbThreads : %u ; minNbJobs : %u ; nbJobsLog2 : %u ; nbJobs : %u \n",
- nbThreads, minNbJobs, nbJobsLog2, nbJobs);
+ *nbJobsPtr = nbJobs;
+ return (ZSTDMT_jobDescription*) ZSTD_calloc(
+ nbJobs * sizeof(ZSTDMT_jobDescription), cMem);
+}
+
+ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbThreads, ZSTD_customMem cMem)
+{
+ ZSTDMT_CCtx* mtctx;
+ U32 nbJobs = nbThreads + 2;
+ DEBUGLOG(3, "ZSTDMT_createCCtx_advanced");
+
if ((nbThreads < 1) | (nbThreads > ZSTDMT_NBTHREADS_MAX)) return NULL;
- cctx = (ZSTDMT_CCtx*) calloc(1, sizeof(ZSTDMT_CCtx) + nbJobs*sizeof(ZSTDMT_jobDescription));
- if (!cctx) return NULL;
- cctx->nbThreads = nbThreads;
- cctx->jobIDMask = nbJobs - 1;
- cctx->allJobsCompleted = 1;
- cctx->sectionSize = 0;
- cctx->overlapRLog = 3;
- cctx->factory = POOL_create(nbThreads, 1);
- cctx->buffPool = ZSTDMT_createBufferPool(nbThreads);
- cctx->cctxPool = ZSTDMT_createCCtxPool(nbThreads);
- if (!cctx->factory | !cctx->buffPool | !cctx->cctxPool) { /* one object was not created */
- ZSTDMT_freeCCtx(cctx);
+ if ((cMem.customAlloc!=NULL) ^ (cMem.customFree!=NULL))
+ /* invalid custom allocator */
+ return NULL;
+
+ mtctx = (ZSTDMT_CCtx*) ZSTD_calloc(sizeof(ZSTDMT_CCtx), cMem);
+ if (!mtctx) return NULL;
+ mtctx->cMem = cMem;
+ mtctx->nbThreads = nbThreads;
+ mtctx->allJobsCompleted = 1;
+ mtctx->sectionSize = 0;
+ mtctx->overlapRLog = 3;
+ mtctx->factory = POOL_create(nbThreads, 1);
+ mtctx->jobs = ZSTDMT_allocJobsTable(&nbJobs, cMem);
+ mtctx->jobIDMask = nbJobs - 1;
+ mtctx->buffPool = ZSTDMT_createBufferPool(nbThreads, cMem);
+ mtctx->cctxPool = ZSTDMT_createCCtxPool(nbThreads, cMem);
+ if (!mtctx->factory | !mtctx->jobs | !mtctx->buffPool | !mtctx->cctxPool) {
+ ZSTDMT_freeCCtx(mtctx);
return NULL;
}
- if (nbThreads==1) {
- cctx->cstream = ZSTD_createCStream();
- if (!cctx->cstream) {
- ZSTDMT_freeCCtx(cctx); return NULL;
- } }
- pthread_mutex_init(&cctx->jobCompleted_mutex, NULL); /* Todo : check init function return */
- pthread_cond_init(&cctx->jobCompleted_cond, NULL);
- DEBUGLOG(4, "mt_cctx created, for %u threads \n", nbThreads);
- return cctx;
+ pthread_mutex_init(&mtctx->jobCompleted_mutex, NULL); /* Todo : check init function return */
+ pthread_cond_init(&mtctx->jobCompleted_cond, NULL);
+ DEBUGLOG(3, "mt_cctx created, for %u threads", nbThreads);
+ return mtctx;
+}
+
+ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbThreads)
+{
+ return ZSTDMT_createCCtx_advanced(nbThreads, ZSTD_defaultCMem);
}
/* ZSTDMT_releaseAllJobResources() :
- * Ensure all workers are killed first. */
+ * note : ensure all workers are killed first ! */
static void ZSTDMT_releaseAllJobResources(ZSTDMT_CCtx* mtctx)
{
unsigned jobID;
+ DEBUGLOG(3, "ZSTDMT_releaseAllJobResources");
for (jobID=0; jobID <= mtctx->jobIDMask; jobID++) {
ZSTDMT_releaseBuffer(mtctx->buffPool, mtctx->jobs[jobID].dstBuff);
mtctx->jobs[jobID].dstBuff = g_nullBuffer;
@@ -356,15 +405,26 @@ size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx)
POOL_free(mtctx->factory);
if (!mtctx->allJobsCompleted) ZSTDMT_releaseAllJobResources(mtctx); /* stop workers first */
ZSTDMT_freeBufferPool(mtctx->buffPool); /* release job resources into pools first */
+ ZSTD_free(mtctx->jobs, mtctx->cMem);
ZSTDMT_freeCCtxPool(mtctx->cctxPool);
- ZSTD_freeCDict(mtctx->cdict);
- ZSTD_freeCStream(mtctx->cstream);
+ ZSTD_freeCDict(mtctx->cdictLocal);
pthread_mutex_destroy(&mtctx->jobCompleted_mutex);
pthread_cond_destroy(&mtctx->jobCompleted_cond);
- free(mtctx);
+ ZSTD_free(mtctx, mtctx->cMem);
return 0;
}
+size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx)
+{
+ if (mtctx == NULL) return 0; /* supports sizeof NULL */
+ return sizeof(*mtctx)
+ + POOL_sizeof(mtctx->factory)
+ + ZSTDMT_sizeof_bufferPool(mtctx->buffPool)
+ + (mtctx->jobIDMask+1) * sizeof(ZSTDMT_jobDescription)
+ + ZSTDMT_sizeof_CCtxPool(mtctx->cctxPool)
+ + ZSTD_sizeof_CDict(mtctx->cdictLocal);
+}
+
size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter, unsigned value)
{
switch(parameter)
@@ -373,7 +433,7 @@ size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter,
mtctx->sectionSize = value;
return 0;
case ZSTDMT_p_overlapSectionLog :
- DEBUGLOG(4, "ZSTDMT_p_overlapSectionLog : %u", value);
+ DEBUGLOG(5, "ZSTDMT_p_overlapSectionLog : %u", value);
mtctx->overlapRLog = (value >= 9) ? 0 : 9 - value;
return 0;
default :
@@ -386,31 +446,49 @@ size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter,
/* ===== Multi-threaded compression ===== */
/* ------------------------------------------ */
-size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
+static unsigned computeNbChunks(size_t srcSize, unsigned windowLog, unsigned nbThreads) {
+ size_t const chunkSizeTarget = (size_t)1 << (windowLog + 2);
+ size_t const chunkMaxSize = chunkSizeTarget << 2;
+ size_t const passSizeMax = chunkMaxSize * nbThreads;
+ unsigned const multiplier = (unsigned)(srcSize / passSizeMax) + 1;
+ unsigned const nbChunksLarge = multiplier * nbThreads;
+ unsigned const nbChunksMax = (unsigned)(srcSize / chunkSizeTarget) + 1;
+ unsigned const nbChunksSmall = MIN(nbChunksMax, nbThreads);
+ return (multiplier>1) ? nbChunksLarge : nbChunksSmall;
+}
+
+
+size_t ZSTDMT_compress_advanced(ZSTDMT_CCtx* mtctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
- int compressionLevel)
+ const ZSTD_CDict* cdict,
+ ZSTD_parameters const params,
+ unsigned overlapRLog)
{
- ZSTD_parameters params = ZSTD_getParams(compressionLevel, srcSize, 0);
- U32 const overlapLog = (compressionLevel >= ZSTD_maxCLevel()) ? 0 : 3;
- size_t const overlapSize = (size_t)1 << (params.cParams.windowLog - overlapLog);
- size_t const chunkTargetSize = (size_t)1 << (params.cParams.windowLog + 2);
- unsigned const nbChunksMax = (unsigned)(srcSize / chunkTargetSize) + 1;
- unsigned nbChunks = MIN(nbChunksMax, mtctx->nbThreads);
+ size_t const overlapSize = (overlapRLog>=9) ? 0 : (size_t)1 << (params.cParams.windowLog - overlapRLog);
+ unsigned nbChunks = computeNbChunks(srcSize, params.cParams.windowLog, mtctx->nbThreads);
size_t const proposedChunkSize = (srcSize + (nbChunks-1)) / nbChunks;
- size_t const avgChunkSize = ((proposedChunkSize & 0x1FFFF) < 0xFFFF) ? proposedChunkSize + 0xFFFF : proposedChunkSize; /* avoid too small last block */
- size_t remainingSrcSize = srcSize;
+ size_t const avgChunkSize = ((proposedChunkSize & 0x1FFFF) < 0x7FFF) ? proposedChunkSize + 0xFFFF : proposedChunkSize; /* avoid too small last block */
const char* const srcStart = (const char*)src;
+ size_t remainingSrcSize = srcSize;
unsigned const compressWithinDst = (dstCapacity >= ZSTD_compressBound(srcSize)) ? nbChunks : (unsigned)(dstCapacity / ZSTD_compressBound(avgChunkSize)); /* presumes avgChunkSize >= 256 KB, which should be the case */
size_t frameStartPos = 0, dstBufferPos = 0;
- DEBUGLOG(3, "windowLog : %2u => chunkTargetSize : %u bytes ", params.cParams.windowLog, (U32)chunkTargetSize);
- DEBUGLOG(2, "nbChunks : %2u (chunkSize : %u bytes) ", nbChunks, (U32)avgChunkSize);
- params.fParams.contentSizeFlag = 1;
-
+ DEBUGLOG(4, "nbChunks : %2u (chunkSize : %u bytes) ", nbChunks, (U32)avgChunkSize);
if (nbChunks==1) { /* fallback to single-thread mode */
ZSTD_CCtx* const cctx = mtctx->cctxPool->cctx[0];
- return ZSTD_compressCCtx(cctx, dst, dstCapacity, src, srcSize, compressionLevel);
+ if (cdict) return ZSTD_compress_usingCDict_advanced(cctx, dst, dstCapacity, src, srcSize, cdict, params.fParams);
+ return ZSTD_compress_advanced(cctx, dst, dstCapacity, src, srcSize, NULL, 0, params);
+ }
+ assert(avgChunkSize >= 256 KB); /* condition for ZSTD_compressBound(A) + ZSTD_compressBound(B) <= ZSTD_compressBound(A+B), which is useful to avoid allocating extra buffers */
+
+ if (nbChunks > mtctx->jobIDMask+1) { /* enlarge job table */
+ U32 nbJobs = nbChunks;
+ ZSTD_free(mtctx->jobs, mtctx->cMem);
+ mtctx->jobIDMask = 0;
+ mtctx->jobs = ZSTDMT_allocJobsTable(&nbJobs, mtctx->cMem);
+ if (mtctx->jobs==NULL) return ERROR(memory_allocation);
+ mtctx->jobIDMask = nbJobs - 1;
}
{ unsigned u;
@@ -425,15 +503,18 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
if ((cctx==NULL) || (dstBuffer.start==NULL)) {
mtctx->jobs[u].cSize = ERROR(memory_allocation); /* job result */
mtctx->jobs[u].jobCompleted = 1;
- nbChunks = u+1;
+ nbChunks = u+1; /* only wait and free u jobs, instead of initially expected nbChunks ones */
break; /* let's wait for previous jobs to complete, but don't start new ones */
}
mtctx->jobs[u].srcStart = srcStart + frameStartPos - dictSize;
mtctx->jobs[u].dictSize = dictSize;
mtctx->jobs[u].srcSize = chunkSize;
+ mtctx->jobs[u].cdict = mtctx->nextJobID==0 ? cdict : NULL;
mtctx->jobs[u].fullFrameSize = srcSize;
mtctx->jobs[u].params = params;
+ /* do not calculate checksum within sections, but write it in header for first section */
+ if (u!=0) mtctx->jobs[u].params.fParams.checksumFlag = 0;
mtctx->jobs[u].dstBuff = dstBuffer;
mtctx->jobs[u].cctx = cctx;
mtctx->jobs[u].firstChunk = (u==0);
@@ -442,27 +523,27 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
mtctx->jobs[u].jobCompleted_mutex = &mtctx->jobCompleted_mutex;
mtctx->jobs[u].jobCompleted_cond = &mtctx->jobCompleted_cond;
- DEBUGLOG(3, "posting job %u (%u bytes)", u, (U32)chunkSize);
- DEBUG_PRINTHEX(3, mtctx->jobs[u].srcStart, 12);
+ DEBUGLOG(5, "posting job %u (%u bytes)", u, (U32)chunkSize);
+ DEBUG_PRINTHEX(6, mtctx->jobs[u].srcStart, 12);
POOL_add(mtctx->factory, ZSTDMT_compressChunk, &mtctx->jobs[u]);
frameStartPos += chunkSize;
dstBufferPos += dstBufferCapacity;
remainingSrcSize -= chunkSize;
} }
- /* note : since nbChunks <= nbThreads, all jobs should be running immediately in parallel */
+ /* collect result */
{ unsigned chunkID;
size_t error = 0, dstPos = 0;
for (chunkID=0; chunkID<nbChunks; chunkID++) {
- DEBUGLOG(3, "waiting for chunk %u ", chunkID);
+ DEBUGLOG(5, "waiting for chunk %u ", chunkID);
PTHREAD_MUTEX_LOCK(&mtctx->jobCompleted_mutex);
while (mtctx->jobs[chunkID].jobCompleted==0) {
- DEBUGLOG(4, "waiting for jobCompleted signal from chunk %u", chunkID);
+ DEBUGLOG(5, "waiting for jobCompleted signal from chunk %u", chunkID);
pthread_cond_wait(&mtctx->jobCompleted_cond, &mtctx->jobCompleted_mutex);
}
pthread_mutex_unlock(&mtctx->jobCompleted_mutex);
- DEBUGLOG(3, "ready to write chunk %u ", chunkID);
+ DEBUGLOG(5, "ready to write chunk %u ", chunkID);
ZSTDMT_releaseCCtx(mtctx->cctxPool, mtctx->jobs[chunkID].cctx);
mtctx->jobs[chunkID].cctx = NULL;
@@ -470,20 +551,33 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
{ size_t const cSize = mtctx->jobs[chunkID].cSize;
if (ZSTD_isError(cSize)) error = cSize;
if ((!error) && (dstPos + cSize > dstCapacity)) error = ERROR(dstSize_tooSmall);
- if (chunkID) { /* note : chunk 0 is already written directly into dst */
+ if (chunkID) { /* note : chunk 0 is written directly at dst, which is correct position */
if (!error)
- memmove((char*)dst + dstPos, mtctx->jobs[chunkID].dstBuff.start, cSize); /* may overlap if chunk decompressed within dst */
- if (chunkID >= compressWithinDst) /* otherwise, it decompresses within dst */
+ memmove((char*)dst + dstPos, mtctx->jobs[chunkID].dstBuff.start, cSize); /* may overlap when chunk compressed within dst */
+ if (chunkID >= compressWithinDst) { /* chunk compressed into its own buffer, which must be released */
+ DEBUGLOG(5, "releasing buffer %u>=%u", chunkID, compressWithinDst);
ZSTDMT_releaseBuffer(mtctx->buffPool, mtctx->jobs[chunkID].dstBuff);
+ }
mtctx->jobs[chunkID].dstBuff = g_nullBuffer;
}
dstPos += cSize ;
}
}
- if (!error) DEBUGLOG(3, "compressed size : %u ", (U32)dstPos);
+ if (!error) DEBUGLOG(4, "compressed size : %u ", (U32)dstPos);
return error ? error : dstPos;
}
+}
+
+size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
+ void* dst, size_t dstCapacity,
+ const void* src, size_t srcSize,
+ int compressionLevel)
+{
+ U32 const overlapRLog = (compressionLevel >= ZSTD_maxCLevel()) ? 0 : 3;
+ ZSTD_parameters params = ZSTD_getParams(compressionLevel, srcSize, 0);
+ params.fParams.contentSizeFlag = 1;
+ return ZSTDMT_compress_advanced(mtctx, dst, dstCapacity, src, srcSize, NULL, params, overlapRLog);
}
@@ -491,12 +585,14 @@ size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
/* ======= Streaming API ======= */
/* ====================================== */
-static void ZSTDMT_waitForAllJobsCompleted(ZSTDMT_CCtx* zcs) {
+static void ZSTDMT_waitForAllJobsCompleted(ZSTDMT_CCtx* zcs)
+{
+ DEBUGLOG(4, "ZSTDMT_waitForAllJobsCompleted");
while (zcs->doneJobID < zcs->nextJobID) {
unsigned const jobID = zcs->doneJobID & zcs->jobIDMask;
PTHREAD_MUTEX_LOCK(&zcs->jobCompleted_mutex);
while (zcs->jobs[jobID].jobCompleted==0) {
- DEBUGLOG(4, "waiting for jobCompleted signal from chunk %u", zcs->doneJobID); /* we want to block when waiting for data to flush */
+ DEBUGLOG(5, "waiting for jobCompleted signal from chunk %u", zcs->doneJobID); /* we want to block when waiting for data to flush */
pthread_cond_wait(&zcs->jobCompleted_cond, &zcs->jobCompleted_mutex);
}
pthread_mutex_unlock(&zcs->jobCompleted_mutex);
@@ -505,33 +601,54 @@ static void ZSTDMT_waitForAllJobsCompleted(ZSTDMT_CCtx* zcs) {
}
-static size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
- const void* dict, size_t dictSize, unsigned updateDict,
- ZSTD_parameters params, unsigned long long pledgedSrcSize)
+/** ZSTDMT_initCStream_internal() :
+ * internal usage only */
+size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
+ const void* dict, size_t dictSize, const ZSTD_CDict* cdict,
+ ZSTD_parameters params, unsigned long long pledgedSrcSize)
{
- ZSTD_customMem const cmem = { NULL, NULL, NULL };
- DEBUGLOG(3, "Started new compression, with windowLog : %u", params.cParams.windowLog);
- if (zcs->nbThreads==1) return ZSTD_initCStream_advanced(zcs->cstream, dict, dictSize, params, pledgedSrcSize);
- if (zcs->allJobsCompleted == 0) { /* previous job not correctly finished */
+ DEBUGLOG(4, "ZSTDMT_initCStream_internal");
+ /* params are supposed to be fully validated at this point */
+ assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
+ assert(!((dict) && (cdict))); /* either dict or cdict, not both */
+
+ if (zcs->nbThreads==1) {
+ DEBUGLOG(4, "single thread mode");
+ return ZSTD_initCStream_internal(zcs->cctxPool->cctx[0],
+ dict, dictSize, cdict,
+ params, pledgedSrcSize);
+ }
+
+ if (zcs->allJobsCompleted == 0) { /* previous compression not correctly finished */
ZSTDMT_waitForAllJobsCompleted(zcs);
ZSTDMT_releaseAllJobResources(zcs);
zcs->allJobsCompleted = 1;
}
+
zcs->params = params;
- if (updateDict) {
- ZSTD_freeCDict(zcs->cdict); zcs->cdict = NULL;
- if (dict && dictSize) {
- zcs->cdict = ZSTD_createCDict_advanced(dict, dictSize, 0, params.cParams, cmem);
- if (zcs->cdict == NULL) return ERROR(memory_allocation);
- } }
zcs->frameContentSize = pledgedSrcSize;
+ if (dict) {
+ DEBUGLOG(4,"cdictLocal: %08X", (U32)(size_t)zcs->cdictLocal);
+ ZSTD_freeCDict(zcs->cdictLocal);
+ zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize,
+ 0 /* byRef */, ZSTD_dm_auto, /* note : a loadPrefix becomes an internal CDict */
+ params.cParams, zcs->cMem);
+ zcs->cdict = zcs->cdictLocal;
+ if (zcs->cdictLocal == NULL) return ERROR(memory_allocation);
+ } else {
+ DEBUGLOG(4,"cdictLocal: %08X", (U32)(size_t)zcs->cdictLocal);
+ ZSTD_freeCDict(zcs->cdictLocal);
+ zcs->cdictLocal = NULL;
+ zcs->cdict = cdict;
+ }
+
zcs->targetDictSize = (zcs->overlapRLog>=9) ? 0 : (size_t)1 << (zcs->params.cParams.windowLog - zcs->overlapRLog);
DEBUGLOG(4, "overlapRLog : %u ", zcs->overlapRLog);
- DEBUGLOG(3, "overlap Size : %u KB", (U32)(zcs->targetDictSize>>10));
+ DEBUGLOG(4, "overlap Size : %u KB", (U32)(zcs->targetDictSize>>10));
zcs->targetSectionSize = zcs->sectionSize ? zcs->sectionSize : (size_t)1 << (zcs->params.cParams.windowLog + 2);
zcs->targetSectionSize = MAX(ZSTDMT_SECTION_SIZE_MIN, zcs->targetSectionSize);
zcs->targetSectionSize = MAX(zcs->targetDictSize, zcs->targetSectionSize);
- DEBUGLOG(3, "Section Size : %u KB", (U32)(zcs->targetSectionSize>>10));
+ DEBUGLOG(4, "Section Size : %u KB", (U32)(zcs->targetSectionSize>>10));
zcs->marginSize = zcs->targetSectionSize >> 2;
zcs->inBuffSize = zcs->targetDictSize + zcs->targetSectionSize + zcs->marginSize;
zcs->inBuff.buffer = ZSTDMT_getBuffer(zcs->buffPool, zcs->inBuffSize);
@@ -546,24 +663,39 @@ static size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs,
return 0;
}
-size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* zcs,
+size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx,
const void* dict, size_t dictSize,
ZSTD_parameters params, unsigned long long pledgedSrcSize)
{
- return ZSTDMT_initCStream_internal(zcs, dict, dictSize, 1, params, pledgedSrcSize);
+ DEBUGLOG(5, "ZSTDMT_initCStream_advanced");
+ return ZSTDMT_initCStream_internal(mtctx, dict, dictSize, NULL, params, pledgedSrcSize);
}
+size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
+ const ZSTD_CDict* cdict,
+ ZSTD_frameParameters fParams,
+ unsigned long long pledgedSrcSize)
+{
+ ZSTD_parameters params = ZSTD_getParamsFromCDict(cdict);
+ if (cdict==NULL) return ERROR(dictionary_wrong); /* method incompatible with NULL cdict */
+ params.fParams = fParams;
+ return ZSTDMT_initCStream_internal(mtctx, NULL, 0 /*dictSize*/, cdict,
+ params, pledgedSrcSize);
+}
+
+
/* ZSTDMT_resetCStream() :
* pledgedSrcSize is optional and can be zero == unknown */
size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* zcs, unsigned long long pledgedSrcSize)
{
- if (zcs->nbThreads==1) return ZSTD_resetCStream(zcs->cstream, pledgedSrcSize);
+ if (zcs->nbThreads==1)
+ return ZSTD_resetCStream(zcs->cctxPool->cctx[0], pledgedSrcSize);
return ZSTDMT_initCStream_internal(zcs, NULL, 0, 0, zcs->params, pledgedSrcSize);
}
size_t ZSTDMT_initCStream(ZSTDMT_CCtx* zcs, int compressionLevel) {
ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, 0);
- return ZSTDMT_initCStream_internal(zcs, NULL, 0, 1, params, 0);
+ return ZSTDMT_initCStream_internal(zcs, NULL, 0, NULL, params, 0);
}
@@ -582,13 +714,16 @@ static size_t ZSTDMT_createCompressionJob(ZSTDMT_CCtx* zcs, size_t srcSize, unsi
return ERROR(memory_allocation);
}
- DEBUGLOG(4, "preparing job %u to compress %u bytes with %u preload ", zcs->nextJobID, (U32)srcSize, (U32)zcs->dictSize);
+ DEBUGLOG(4, "preparing job %u to compress %u bytes with %u preload ",
+ zcs->nextJobID, (U32)srcSize, (U32)zcs->dictSize);
zcs->jobs[jobID].src = zcs->inBuff.buffer;
zcs->jobs[jobID].srcStart = zcs->inBuff.buffer.start;
zcs->jobs[jobID].srcSize = srcSize;
- zcs->jobs[jobID].dictSize = zcs->dictSize; /* note : zcs->inBuff.filled is presumed >= srcSize + dictSize */
+ zcs->jobs[jobID].dictSize = zcs->dictSize;
+ assert(zcs->inBuff.filled >= srcSize + zcs->dictSize);
zcs->jobs[jobID].params = zcs->params;
- if (zcs->nextJobID) zcs->jobs[jobID].params.fParams.checksumFlag = 0; /* do not calculate checksum within sections, just keep it in header for first section */
+ /* do not calculate checksum within sections, but write it in header for first section */
+ if (zcs->nextJobID) zcs->jobs[jobID].params.fParams.checksumFlag = 0;
zcs->jobs[jobID].cdict = zcs->nextJobID==0 ? zcs->cdict : NULL;
zcs->jobs[jobID].fullFrameSize = zcs->frameContentSize;
zcs->jobs[jobID].dstBuff = dstBuffer;
@@ -603,6 +738,7 @@ static size_t ZSTDMT_createCompressionJob(ZSTDMT_CCtx* zcs, size_t srcSize, unsi
/* get a new buffer for next input */
if (!endFrame) {
size_t const newDictSize = MIN(srcSize + zcs->dictSize, zcs->targetDictSize);
+ DEBUGLOG(5, "ZSTDMT_createCompressionJob::endFrame = %u", endFrame);
zcs->inBuff.buffer = ZSTDMT_getBuffer(zcs->buffPool, zcs->inBuffSize);
if (zcs->inBuff.buffer.start == NULL) { /* not enough memory to allocate next input buffer */
zcs->jobs[jobID].jobCompleted = 1;
@@ -611,22 +747,33 @@ static size_t ZSTDMT_createCompressionJob(ZSTDMT_CCtx* zcs, size_t srcSize, unsi
ZSTDMT_releaseAllJobResources(zcs);
return ERROR(memory_allocation);
}
- DEBUGLOG(5, "inBuff filled to %u", (U32)zcs->inBuff.filled);
+ DEBUGLOG(5, "inBuff currently filled to %u", (U32)zcs->inBuff.filled);
zcs->inBuff.filled -= srcSize + zcs->dictSize - newDictSize;
- DEBUGLOG(5, "new job : filled to %u, with %u dict and %u src", (U32)zcs->inBuff.filled, (U32)newDictSize, (U32)(zcs->inBuff.filled - newDictSize));
- memmove(zcs->inBuff.buffer.start, (const char*)zcs->jobs[jobID].srcStart + zcs->dictSize + srcSize - newDictSize, zcs->inBuff.filled);
+ DEBUGLOG(5, "new job : inBuff filled to %u, with %u dict and %u src",
+ (U32)zcs->inBuff.filled, (U32)newDictSize,
+ (U32)(zcs->inBuff.filled - newDictSize));
+ memmove(zcs->inBuff.buffer.start,
+ (const char*)zcs->jobs[jobID].srcStart + zcs->dictSize + srcSize - newDictSize,
+ zcs->inBuff.filled);
DEBUGLOG(5, "new inBuff pre-filled");
zcs->dictSize = newDictSize;
- } else {
+ } else { /* if (endFrame==1) */
+ DEBUGLOG(5, "ZSTDMT_createCompressionJob::endFrame = %u", endFrame);
zcs->inBuff.buffer = g_nullBuffer;
zcs->inBuff.filled = 0;
zcs->dictSize = 0;
zcs->frameEnded = 1;
if (zcs->nextJobID == 0)
- zcs->params.fParams.checksumFlag = 0; /* single chunk : checksum is calculated directly within worker thread */
+ /* single chunk exception : checksum is calculated directly within worker thread */
+ zcs->params.fParams.checksumFlag = 0;
}
- DEBUGLOG(3, "posting job %u : %u bytes (end:%u) (note : doneJob = %u=>%u)", zcs->nextJobID, (U32)zcs->jobs[jobID].srcSize, zcs->jobs[jobID].lastChunk, zcs->doneJobID, zcs->doneJobID & zcs->jobIDMask);
+ DEBUGLOG(4, "posting job %u : %u bytes (end:%u) (note : doneJob = %u=>%u)",
+ zcs->nextJobID,
+ (U32)zcs->jobs[jobID].srcSize,
+ zcs->jobs[jobID].lastChunk,
+ zcs->doneJobID,
+ zcs->doneJobID & zcs->jobIDMask);
POOL_add(zcs->factory, ZSTDMT_compressChunk, &zcs->jobs[jobID]); /* this call is blocking when thread worker pool is exhausted */
zcs->nextJobID++;
return 0;
@@ -664,7 +811,7 @@ static size_t ZSTDMT_flushNextJob(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, unsi
XXH64_update(&zcs->xxhState, (const char*)job.srcStart + job.dictSize, job.srcSize);
if (zcs->frameEnded && (zcs->doneJobID+1 == zcs->nextJobID)) { /* write checksum at end of last section */
U32 const checksum = (U32)XXH64_digest(&zcs->xxhState);
- DEBUGLOG(4, "writing checksum : %08X \n", checksum);
+ DEBUGLOG(5, "writing checksum : %08X \n", checksum);
MEM_writeLE32((char*)job.dstBuff.start + job.cSize, checksum);
job.cSize += 4;
zcs->jobs[wJobID].cSize += 4;
@@ -675,7 +822,7 @@ static size_t ZSTDMT_flushNextJob(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, unsi
zcs->jobs[wJobID].jobScanned = 1;
}
{ size_t const toWrite = MIN(job.cSize - job.dstFlushed, output->size - output->pos);
- DEBUGLOG(4, "Flushing %u bytes from job %u ", (U32)toWrite, zcs->doneJobID);
+ DEBUGLOG(5, "Flushing %u bytes from job %u ", (U32)toWrite, zcs->doneJobID);
memcpy((char*)output->dst + output->pos, (const char*)job.dstBuff.start + job.dstFlushed, toWrite);
output->pos += toWrite;
job.dstFlushed += toWrite;
@@ -696,26 +843,81 @@ static size_t ZSTDMT_flushNextJob(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, unsi
} }
-size_t ZSTDMT_compressStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
+/** ZSTDMT_compressStream_generic() :
+ * internal use only
+ * assumption : output and input are valid (pos <= size)
+ * @return : minimum amount of data remaining to flush, 0 if none */
+size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
+ ZSTD_outBuffer* output,
+ ZSTD_inBuffer* input,
+ ZSTD_EndDirective endOp)
{
- size_t const newJobThreshold = zcs->dictSize + zcs->targetSectionSize + zcs->marginSize;
- if (zcs->frameEnded) return ERROR(stage_wrong); /* current frame being ended. Only flush is allowed. Restart with init */
- if (zcs->nbThreads==1) return ZSTD_compressStream(zcs->cstream, output, input);
+ size_t const newJobThreshold = mtctx->dictSize + mtctx->targetSectionSize + mtctx->marginSize;
+ assert(output->pos <= output->size);
+ assert(input->pos <= input->size);
+ if ((mtctx->frameEnded) && (endOp==ZSTD_e_continue)) {
+ /* current frame being ended. Only flush/end are allowed. Or start new frame with init */
+ return ERROR(stage_wrong);
+ }
+ if (mtctx->nbThreads==1) {
+ return ZSTD_compressStream_generic(mtctx->cctxPool->cctx[0], output, input, endOp);
+ }
+
+ /* single-pass shortcut (note : this is blocking-mode) */
+ if ( (mtctx->nextJobID==0) /* just started */
+ && (mtctx->inBuff.filled==0) /* nothing buffered */
+ && (endOp==ZSTD_e_end) /* end order */
+ && (output->size - output->pos >= ZSTD_compressBound(input->size - input->pos)) ) { /* enough room */
+ size_t const cSize = ZSTDMT_compress_advanced(mtctx,
+ (char*)output->dst + output->pos, output->size - output->pos,
+ (const char*)input->src + input->pos, input->size - input->pos,
+ mtctx->cdict, mtctx->params, mtctx->overlapRLog);
+ if (ZSTD_isError(cSize)) return cSize;
+ input->pos = input->size;
+ output->pos += cSize;
+ ZSTDMT_releaseBuffer(mtctx->buffPool, mtctx->inBuff.buffer); /* was allocated in initStream */
+ mtctx->allJobsCompleted = 1;
+ mtctx->frameEnded = 1;
+ return 0;
+ }
/* fill input buffer */
- { size_t const toLoad = MIN(input->size - input->pos, zcs->inBuffSize - zcs->inBuff.filled);
- memcpy((char*)zcs->inBuff.buffer.start + zcs->inBuff.filled, input->src, toLoad);
+ if ((input->src) && (mtctx->inBuff.buffer.start)) { /* support NULL input */
+ size_t const toLoad = MIN(input->size - input->pos, mtctx->inBuffSize - mtctx->inBuff.filled);
+ DEBUGLOG(2, "inBuff:%08X; inBuffSize=%u; ToCopy=%u", (U32)(size_t)mtctx->inBuff.buffer.start, (U32)mtctx->inBuffSize, (U32)toLoad);
+ memcpy((char*)mtctx->inBuff.buffer.start + mtctx->inBuff.filled, (const char*)input->src + input->pos, toLoad);
input->pos += toLoad;
- zcs->inBuff.filled += toLoad;
+ mtctx->inBuff.filled += toLoad;
}
- if ( (zcs->inBuff.filled >= newJobThreshold) /* filled enough : let's compress */
- && (zcs->nextJobID <= zcs->doneJobID + zcs->jobIDMask) ) { /* avoid overwriting job round buffer */
- CHECK_F( ZSTDMT_createCompressionJob(zcs, zcs->targetSectionSize, 0) );
+ if ( (mtctx->inBuff.filled >= newJobThreshold) /* filled enough : let's compress */
+ && (mtctx->nextJobID <= mtctx->doneJobID + mtctx->jobIDMask) ) { /* avoid overwriting job round buffer */
+ CHECK_F( ZSTDMT_createCompressionJob(mtctx, mtctx->targetSectionSize, 0 /* endFrame */) );
}
- /* check for data to flush */
- CHECK_F( ZSTDMT_flushNextJob(zcs, output, (zcs->inBuff.filled == zcs->inBuffSize)) ); /* block if it wasn't possible to create new job due to saturation */
+ /* check for potential compressed data ready to be flushed */
+ CHECK_F( ZSTDMT_flushNextJob(mtctx, output, (mtctx->inBuff.filled == mtctx->inBuffSize) /* blockToFlush */) ); /* block if it wasn't possible to create new job due to saturation */
+
+ if (input->pos < input->size) /* input not consumed : do not flush yet */
+ endOp = ZSTD_e_continue;
+
+ switch(endOp)
+ {
+ case ZSTD_e_flush:
+ return ZSTDMT_flushStream(mtctx, output);
+ case ZSTD_e_end:
+ return ZSTDMT_endStream(mtctx, output);
+ case ZSTD_e_continue:
+ return 1;
+ default:
+ return ERROR(GENERIC); /* invalid endDirective */
+ }
+}
+
+
+size_t ZSTDMT_compressStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
+{
+ CHECK_F( ZSTDMT_compressStream_generic(zcs, output, input, ZSTD_e_continue) );
/* recommended next input size : fill current input buffer */
return zcs->inBuffSize - zcs->inBuff.filled; /* note : could be zero when input buffer is fully filled and no more availability to create new job */
@@ -726,26 +928,28 @@ static size_t ZSTDMT_flushStream_internal(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* outp
{
size_t const srcSize = zcs->inBuff.filled - zcs->dictSize;
- if (srcSize) DEBUGLOG(4, "flushing : %u bytes left to compress", (U32)srcSize);
if ( ((srcSize > 0) || (endFrame && !zcs->frameEnded))
&& (zcs->nextJobID <= zcs->doneJobID + zcs->jobIDMask) ) {
CHECK_F( ZSTDMT_createCompressionJob(zcs, srcSize, endFrame) );
}
/* check if there is any data available to flush */
- DEBUGLOG(5, "zcs->doneJobID : %u ; zcs->nextJobID : %u ", zcs->doneJobID, zcs->nextJobID);
- return ZSTDMT_flushNextJob(zcs, output, 1);
+ return ZSTDMT_flushNextJob(zcs, output, 1 /* blockToFlush */);
}
size_t ZSTDMT_flushStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output)
{
- if (zcs->nbThreads==1) return ZSTD_flushStream(zcs->cstream, output);
- return ZSTDMT_flushStream_internal(zcs, output, 0);
+ DEBUGLOG(5, "ZSTDMT_flushStream");
+ if (zcs->nbThreads==1)
+ return ZSTD_flushStream(zcs->cctxPool->cctx[0], output);
+ return ZSTDMT_flushStream_internal(zcs, output, 0 /* endFrame */);
}
size_t ZSTDMT_endStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output)
{
- if (zcs->nbThreads==1) return ZSTD_endStream(zcs->cstream, output);
- return ZSTDMT_flushStream_internal(zcs, output, 1);
+ DEBUGLOG(4, "ZSTDMT_endStream");
+ if (zcs->nbThreads==1)
+ return ZSTD_endStream(zcs->cctxPool->cctx[0], output);
+ return ZSTDMT_flushStream_internal(zcs, output, 1 /* endFrame */);
}
diff --git a/lib/compress/zstdmt_compress.h b/lib/compress/zstdmt_compress.h
index 27f78ee0314aa..fad63b6d8610b 100644
--- a/lib/compress/zstdmt_compress.h
+++ b/lib/compress/zstdmt_compress.h
@@ -15,25 +15,34 @@
#endif
-/* Note : All prototypes defined in this file shall be considered experimental.
- * There is no guarantee of API continuity (yet) on any of these prototypes */
+/* Note : All prototypes defined in this file are labelled experimental.
+ * No guarantee of API continuity is provided on any of them.
+ * In fact, the expectation is that these prototypes will be replaced
+ * by ZSTD_compress_generic() API in the near future */
/* === Dependencies === */
-#include <stddef.h> /* size_t */
+#include <stddef.h> /* size_t */
#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_parameters */
-#include "zstd.h" /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTDLIB_API */
+#include "zstd.h" /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTDLIB_API */
-/* === Simple one-pass functions === */
-
+/* === Memory management === */
typedef struct ZSTDMT_CCtx_s ZSTDMT_CCtx;
ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbThreads);
-ZSTDLIB_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* cctx);
+ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbThreads,
+ ZSTD_customMem cMem);
+ZSTDLIB_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx);
+
+ZSTDLIB_API size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx);
+
+
+/* === Simple buffer-to-butter one-pass function === */
+
+ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
+ void* dst, size_t dstCapacity,
+ const void* src, size_t srcSize,
+ int compressionLevel);
-ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* cctx,
- void* dst, size_t dstCapacity,
- const void* src, size_t srcSize,
- int compressionLevel);
/* === Streaming functions === */
@@ -53,8 +62,22 @@ ZSTDLIB_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);
# define ZSTDMT_SECTION_SIZE_MIN (1U << 20) /* 1 MB - Minimum size of each compression job */
#endif
-ZSTDLIB_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx, const void* dict, size_t dictSize, /**< dict can be released after init, a local copy is preserved within zcs */
- ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize is optional and can be zero == unknown */
+ZSTDLIB_API size_t ZSTDMT_compress_advanced(ZSTDMT_CCtx* mtctx,
+ void* dst, size_t dstCapacity,
+ const void* src, size_t srcSize,
+ const ZSTD_CDict* cdict,
+ ZSTD_parameters const params,
+ unsigned overlapRLog);
+
+ZSTDLIB_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx,
+ const void* dict, size_t dictSize, /* dict can be released after init, a local copy is preserved within zcs */
+ ZSTD_parameters params,
+ unsigned long long pledgedSrcSize); /* pledgedSrcSize is optional and can be zero == unknown */
+
+ZSTDLIB_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
+ const ZSTD_CDict* cdict,
+ ZSTD_frameParameters fparams,
+ unsigned long long pledgedSrcSize); /* note : zero means empty */
/* ZSDTMT_parameter :
* List of parameters that can be set using ZSTDMT_setMTCtxParameter() */
@@ -71,6 +94,19 @@ typedef enum {
ZSTDLIB_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter, unsigned value);
+/*! ZSTDMT_compressStream_generic() :
+ * Combines ZSTDMT_compressStream() with ZSTDMT_flushStream() or ZSTDMT_endStream()
+ * depending on flush directive.
+ * @return : minimum amount of data still to be flushed
+ * 0 if fully flushed
+ * or an error code */
+ZSTDLIB_API size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
+ ZSTD_outBuffer* output,
+ ZSTD_inBuffer* input,
+ ZSTD_EndDirective endOp);
+
+
+
#if defined (__cplusplus)
}
#endif
diff --git a/lib/decompress/huf_decompress.c b/lib/decompress/huf_decompress.c
index ea35c36201761..2a1b70ea5ef25 100644
--- a/lib/decompress/huf_decompress.c
+++ b/lib/decompress/huf_decompress.c
@@ -67,6 +67,12 @@
#define HUF_STATIC_ASSERT(c) { enum { HUF_static_assert = 1/(int)(!!(c)) }; } /* use only *after* variable declarations */
+/* **************************************************************
+* Byte alignment for workSpace management
+****************************************************************/
+#define HUF_ALIGN(x, a) HUF_ALIGN_MASK((x), (a) - 1)
+#define HUF_ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask))
+
/*-***************************/
/* generic DTableDesc */
/*-***************************/
@@ -87,16 +93,28 @@ static DTableDesc HUF_getDTableDesc(const HUF_DTable* table)
typedef struct { BYTE byte; BYTE nbBits; } HUF_DEltX2; /* single-symbol decoding */
-size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize)
+size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize)
{
- BYTE huffWeight[HUF_SYMBOLVALUE_MAX + 1];
- U32 rankVal[HUF_TABLELOG_ABSOLUTEMAX + 1]; /* large enough for values from 0 to 16 */
U32 tableLog = 0;
U32 nbSymbols = 0;
size_t iSize;
void* const dtPtr = DTable + 1;
HUF_DEltX2* const dt = (HUF_DEltX2*)dtPtr;
+ U32* rankVal;
+ BYTE* huffWeight;
+ size_t spaceUsed32 = 0;
+
+ rankVal = (U32 *)workSpace + spaceUsed32;
+ spaceUsed32 += HUF_TABLELOG_ABSOLUTEMAX + 1;
+ huffWeight = (BYTE *)((U32 *)workSpace + spaceUsed32);
+ spaceUsed32 += HUF_ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
+
+ if ((spaceUsed32 << 2) > wkspSize)
+ return ERROR(tableLog_tooLarge);
+ workSpace = (U32 *)workSpace + spaceUsed32;
+ wkspSize -= (spaceUsed32 << 2);
+
HUF_STATIC_ASSERT(sizeof(DTableDesc) == sizeof(HUF_DTable));
/* memset(huffWeight, 0, sizeof(huffWeight)); */ /* is not necessary, even though some analyzer complain ... */
@@ -135,6 +153,13 @@ size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize)
return iSize;
}
+size_t HUF_readDTableX2(HUF_DTable* DTable, const void* src, size_t srcSize)
+{
+ U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+ return HUF_readDTableX2_wksp(DTable, src, srcSize,
+ workSpace, sizeof(workSpace));
+}
+
static BYTE HUF_decodeSymbolX2(BIT_DStream_t* Dstream, const HUF_DEltX2* dt, const U32 dtLog)
{
@@ -212,11 +237,13 @@ size_t HUF_decompress1X2_usingDTable(
return HUF_decompress1X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
}
-size_t HUF_decompress1X2_DCtx (HUF_DTable* DCtx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize,
+ const void* cSrc, size_t cSrcSize,
+ void* workSpace, size_t wkspSize)
{
const BYTE* ip = (const BYTE*) cSrc;
- size_t const hSize = HUF_readDTableX2 (DCtx, cSrc, cSrcSize);
+ size_t const hSize = HUF_readDTableX2_wksp(DCtx, cSrc, cSrcSize, workSpace, wkspSize);
if (HUF_isError(hSize)) return hSize;
if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
ip += hSize; cSrcSize -= hSize;
@@ -224,6 +251,15 @@ size_t HUF_decompress1X2_DCtx (HUF_DTable* DCtx, void* dst, size_t dstSize, cons
return HUF_decompress1X2_usingDTable_internal (dst, dstSize, ip, cSrcSize, DCtx);
}
+
+size_t HUF_decompress1X2_DCtx(HUF_DTable* DCtx, void* dst, size_t dstSize,
+ const void* cSrc, size_t cSrcSize)
+{
+ U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+ return HUF_decompress1X2_DCtx_wksp(DCtx, dst, dstSize, cSrc, cSrcSize,
+ workSpace, sizeof(workSpace));
+}
+
size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
{
HUF_CREATE_STATIC_DTABLEX2(DTable, HUF_TABLELOG_MAX);
@@ -335,11 +371,14 @@ size_t HUF_decompress4X2_usingDTable(
}
-size_t HUF_decompress4X2_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+ const void* cSrc, size_t cSrcSize,
+ void* workSpace, size_t wkspSize)
{
const BYTE* ip = (const BYTE*) cSrc;
- size_t const hSize = HUF_readDTableX2 (dctx, cSrc, cSrcSize);
+ size_t const hSize = HUF_readDTableX2_wksp (dctx, cSrc, cSrcSize,
+ workSpace, wkspSize);
if (HUF_isError(hSize)) return hSize;
if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
ip += hSize; cSrcSize -= hSize;
@@ -347,6 +386,13 @@ size_t HUF_decompress4X2_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, cons
return HUF_decompress4X2_usingDTable_internal (dst, dstSize, ip, cSrcSize, dctx);
}
+
+size_t HUF_decompress4X2_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+ U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+ return HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+ workSpace, sizeof(workSpace));
+}
size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
{
HUF_CREATE_STATIC_DTABLEX2(DTable, HUF_TABLELOG_MAX);
@@ -403,7 +449,8 @@ static void HUF_fillDTableX4Level2(HUF_DEltX4* DTable, U32 sizeLog, const U32 co
} }
}
-typedef U32 rankVal_t[HUF_TABLELOG_MAX][HUF_TABLELOG_MAX + 1];
+typedef U32 rankValCol_t[HUF_TABLELOG_MAX + 1];
+typedef rankValCol_t rankVal_t[HUF_TABLELOG_MAX];
static void HUF_fillDTableX4(HUF_DEltX4* DTable, const U32 targetLog,
const sortedSymbol_t* sortedList, const U32 sortedListSize,
@@ -447,20 +494,43 @@ static void HUF_fillDTableX4(HUF_DEltX4* DTable, const U32 targetLog,
}
}
-size_t HUF_readDTableX4 (HUF_DTable* DTable, const void* src, size_t srcSize)
+size_t HUF_readDTableX4_wksp(HUF_DTable* DTable, const void* src,
+ size_t srcSize, void* workSpace,
+ size_t wkspSize)
{
- BYTE weightList[HUF_SYMBOLVALUE_MAX + 1];
- sortedSymbol_t sortedSymbol[HUF_SYMBOLVALUE_MAX + 1];
- U32 rankStats[HUF_TABLELOG_MAX + 1] = { 0 };
- U32 rankStart0[HUF_TABLELOG_MAX + 2] = { 0 };
- U32* const rankStart = rankStart0+1;
- rankVal_t rankVal;
U32 tableLog, maxW, sizeOfSort, nbSymbols;
DTableDesc dtd = HUF_getDTableDesc(DTable);
U32 const maxTableLog = dtd.maxTableLog;
size_t iSize;
void* dtPtr = DTable+1; /* force compiler to avoid strict-aliasing */
HUF_DEltX4* const dt = (HUF_DEltX4*)dtPtr;
+ U32 *rankStart;
+
+ rankValCol_t* rankVal;
+ U32* rankStats;
+ U32* rankStart0;
+ sortedSymbol_t* sortedSymbol;
+ BYTE* weightList;
+ size_t spaceUsed32 = 0;
+
+ rankVal = (rankValCol_t *)((U32 *)workSpace + spaceUsed32);
+ spaceUsed32 += (sizeof(rankValCol_t) * HUF_TABLELOG_MAX) >> 2;
+ rankStats = (U32 *)workSpace + spaceUsed32;
+ spaceUsed32 += HUF_TABLELOG_MAX + 1;
+ rankStart0 = (U32 *)workSpace + spaceUsed32;
+ spaceUsed32 += HUF_TABLELOG_MAX + 2;
+ sortedSymbol = (sortedSymbol_t *)workSpace + (spaceUsed32 * sizeof(U32)) / sizeof(sortedSymbol_t);
+ spaceUsed32 += HUF_ALIGN(sizeof(sortedSymbol_t) * (HUF_SYMBOLVALUE_MAX + 1), sizeof(U32)) >> 2;
+ weightList = (BYTE *)((U32 *)workSpace + spaceUsed32);
+ spaceUsed32 += HUF_ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
+
+ if ((spaceUsed32 << 2) > wkspSize)
+ return ERROR(tableLog_tooLarge);
+ workSpace = (U32 *)workSpace + spaceUsed32;
+ wkspSize -= (spaceUsed32 << 2);
+
+ rankStart = rankStart0 + 1;
+ memset(rankStats, 0, sizeof(U32) * (2 * HUF_TABLELOG_MAX + 2 + 1));
HUF_STATIC_ASSERT(sizeof(HUF_DEltX4) == sizeof(HUF_DTable)); /* if compiler fails here, assertion is wrong */
if (maxTableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge);
@@ -527,6 +597,12 @@ size_t HUF_readDTableX4 (HUF_DTable* DTable, const void* src, size_t srcSize)
return iSize;
}
+size_t HUF_readDTableX4(HUF_DTable* DTable, const void* src, size_t srcSize)
+{
+ U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+ return HUF_readDTableX4_wksp(DTable, src, srcSize,
+ workSpace, sizeof(workSpace));
+}
static U32 HUF_decodeSymbolX4(void* op, BIT_DStream_t* DStream, const HUF_DEltX4* dt, const U32 dtLog)
{
@@ -545,7 +621,8 @@ static U32 HUF_decodeLastSymbolX4(void* op, BIT_DStream_t* DStream, const HUF_DE
if (DStream->bitsConsumed < (sizeof(DStream->bitContainer)*8)) {
BIT_skipBits(DStream, dt[val].nbBits);
if (DStream->bitsConsumed > (sizeof(DStream->bitContainer)*8))
- DStream->bitsConsumed = (sizeof(DStream->bitContainer)*8); /* ugly hack; works only because it's the last symbol. Note : can't easily extract nbBits from just this symbol */
+ /* ugly hack; works only because it's the last symbol. Note : can't easily extract nbBits from just this symbol */
+ DStream->bitsConsumed = (sizeof(DStream->bitContainer)*8);
} }
return 1;
}
@@ -626,11 +703,14 @@ size_t HUF_decompress1X4_usingDTable(
return HUF_decompress1X4_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
}
-size_t HUF_decompress1X4_DCtx (HUF_DTable* DCtx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize,
+ const void* cSrc, size_t cSrcSize,
+ void* workSpace, size_t wkspSize)
{
const BYTE* ip = (const BYTE*) cSrc;
- size_t const hSize = HUF_readDTableX4 (DCtx, cSrc, cSrcSize);
+ size_t const hSize = HUF_readDTableX4_wksp(DCtx, cSrc, cSrcSize,
+ workSpace, wkspSize);
if (HUF_isError(hSize)) return hSize;
if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
ip += hSize; cSrcSize -= hSize;
@@ -638,6 +718,15 @@ size_t HUF_decompress1X4_DCtx (HUF_DTable* DCtx, void* dst, size_t dstSize, cons
return HUF_decompress1X4_usingDTable_internal (dst, dstSize, ip, cSrcSize, DCtx);
}
+
+size_t HUF_decompress1X4_DCtx(HUF_DTable* DCtx, void* dst, size_t dstSize,
+ const void* cSrc, size_t cSrcSize)
+{
+ U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+ return HUF_decompress1X4_DCtx_wksp(DCtx, dst, dstSize, cSrc, cSrcSize,
+ workSpace, sizeof(workSpace));
+}
+
size_t HUF_decompress1X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
{
HUF_CREATE_STATIC_DTABLEX4(DTable, HUF_TABLELOG_MAX);
@@ -748,11 +837,14 @@ size_t HUF_decompress4X4_usingDTable(
}
-size_t HUF_decompress4X4_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+ const void* cSrc, size_t cSrcSize,
+ void* workSpace, size_t wkspSize)
{
const BYTE* ip = (const BYTE*) cSrc;
- size_t hSize = HUF_readDTableX4 (dctx, cSrc, cSrcSize);
+ size_t hSize = HUF_readDTableX4_wksp(dctx, cSrc, cSrcSize,
+ workSpace, wkspSize);
if (HUF_isError(hSize)) return hSize;
if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
ip += hSize; cSrcSize -= hSize;
@@ -760,6 +852,15 @@ size_t HUF_decompress4X4_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, cons
return HUF_decompress4X4_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx);
}
+
+size_t HUF_decompress4X4_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize,
+ const void* cSrc, size_t cSrcSize)
+{
+ U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+ return HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+ workSpace, sizeof(workSpace));
+}
+
size_t HUF_decompress4X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
{
HUF_CREATE_STATIC_DTABLEX4(DTable, HUF_TABLELOG_MAX);
@@ -861,19 +962,32 @@ size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const
}
}
-size_t HUF_decompress4X_hufOnly (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+ U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+ return HUF_decompress4X_hufOnly_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+ workSpace, sizeof(workSpace));
+}
+
+
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst,
+ size_t dstSize, const void* cSrc,
+ size_t cSrcSize, void* workSpace,
+ size_t wkspSize)
{
/* validation checks */
if (dstSize == 0) return ERROR(dstSize_tooSmall);
if ((cSrcSize >= dstSize) || (cSrcSize <= 1)) return ERROR(corruption_detected); /* invalid */
{ U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
- return algoNb ? HUF_decompress4X4_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) :
- HUF_decompress4X2_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) ;
+ return algoNb ? HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize):
+ HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
}
}
-size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress1X_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+ const void* cSrc, size_t cSrcSize,
+ void* workSpace, size_t wkspSize)
{
/* validation checks */
if (dstSize == 0) return ERROR(dstSize_tooSmall);
@@ -882,7 +996,17 @@ size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const
if (cSrcSize == 1) { memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; } /* RLE */
{ U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
- return algoNb ? HUF_decompress1X4_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) :
- HUF_decompress1X2_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) ;
+ return algoNb ? HUF_decompress1X4_DCtx_wksp(dctx, dst, dstSize, cSrc,
+ cSrcSize, workSpace, wkspSize):
+ HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
+ cSrcSize, workSpace, wkspSize);
}
}
+
+size_t HUF_decompress1X_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize,
+ const void* cSrc, size_t cSrcSize)
+{
+ U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+ return HUF_decompress1X_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+ workSpace, sizeof(workSpace));
+}
diff --git a/lib/decompress/zstd_decompress.c b/lib/decompress/zstd_decompress.c
index 910f9ab783c31..003d703a5eb36 100644
--- a/lib/decompress/zstd_decompress.c
+++ b/lib/decompress/zstd_decompress.c
@@ -53,8 +53,7 @@
# include "zstd_legacy.h"
#endif
-
-#if defined(_MSC_VER)
+#if defined(_MSC_VER) && !defined(_M_IA64) /* _mm_prefetch() is not defined for ia64 */
# include <mmintrin.h> /* https://msdn.microsoft.com/fr-fr/library/84szxsww(v=vs.90).aspx */
# define ZSTD_PREFETCH(ptr) _mm_prefetch((const char*)ptr, _MM_HINT_T0)
#elif defined(__GNUC__)
@@ -63,8 +62,9 @@
# define ZSTD_PREFETCH(ptr) /* disabled */
#endif
+
/*-*************************************
-* Macros
+* Errors
***************************************/
#define ZSTD_isError ERR_isError /* for inlining */
#define FSE_isError ERR_isError
@@ -85,11 +85,15 @@ typedef enum { ZSTDds_getFrameHeaderSize, ZSTDds_decodeFrameHeader,
ZSTDds_decompressLastBlock, ZSTDds_checkChecksum,
ZSTDds_decodeSkippableHeader, ZSTDds_skipFrame } ZSTD_dStage;
+typedef enum { zdss_init=0, zdss_loadHeader,
+ zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage;
+
typedef struct {
FSE_DTable LLTable[FSE_DTABLE_SIZE_U32(LLFSELog)];
FSE_DTable OFTable[FSE_DTABLE_SIZE_U32(OffFSELog)];
FSE_DTable MLTable[FSE_DTABLE_SIZE_U32(MLFSELog)];
HUF_DTable hufTable[HUF_DTABLE_SIZE(HufLog)]; /* can accommodate HUF_decompress4X */
+ U32 workspace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
U32 rep[ZSTD_REP_NUM];
} ZSTD_entropyTables_t;
@@ -105,7 +109,7 @@ struct ZSTD_DCtx_s
const void* vBase; /* virtual start of previous segment if it was just before current one */
const void* dictEnd; /* end of previous segment */
size_t expected;
- ZSTD_frameParams fParams;
+ ZSTD_frameHeader fParams;
blockType_e bType; /* used in ZSTD_decompressContinue(), to transfer blockType between header decoding and block decoding stages */
ZSTD_dStage stage;
U32 litEntropy;
@@ -117,11 +121,39 @@ struct ZSTD_DCtx_s
ZSTD_customMem customMem;
size_t litSize;
size_t rleSize;
- BYTE litBuffer[ZSTD_BLOCKSIZE_ABSOLUTEMAX + WILDCOPY_OVERLENGTH];
+ size_t staticSize;
+
+ /* streaming */
+ ZSTD_DDict* ddictLocal;
+ const ZSTD_DDict* ddict;
+ ZSTD_dStreamStage streamStage;
+ char* inBuff;
+ size_t inBuffSize;
+ size_t inPos;
+ size_t maxWindowSize;
+ char* outBuff;
+ size_t outBuffSize;
+ size_t outStart;
+ size_t outEnd;
+ size_t blockSize;
+ size_t lhSize;
+ void* legacyContext;
+ U32 previousLegacyVersion;
+ U32 legacyVersion;
+ U32 hostageByte;
+
+ /* workspace */
+ BYTE litBuffer[ZSTD_BLOCKSIZE_MAX + WILDCOPY_OVERLENGTH];
BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX];
}; /* typedef'd to ZSTD_DCtx within "zstd.h" */
-size_t ZSTD_sizeof_DCtx (const ZSTD_DCtx* dctx) { return (dctx==NULL) ? 0 : sizeof(ZSTD_DCtx); }
+size_t ZSTD_sizeof_DCtx (const ZSTD_DCtx* dctx)
+{
+ if (dctx==NULL) return 0; /* support sizeof NULL */
+ return sizeof(*dctx)
+ + ZSTD_sizeof_DDict(dctx->ddictLocal)
+ + dctx->inBuffSize + dctx->outBuffSize;
+}
size_t ZSTD_estimateDCtxSize(void) { return sizeof(ZSTD_DCtx); }
@@ -145,40 +177,76 @@ size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx)
return 0;
}
+static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx)
+{
+ ZSTD_decompressBegin(dctx); /* cannot fail */
+ dctx->staticSize = 0;
+ dctx->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
+ dctx->ddict = NULL;
+ dctx->ddictLocal = NULL;
+ dctx->inBuff = NULL;
+ dctx->inBuffSize = 0;
+ dctx->outBuffSize= 0;
+ dctx->streamStage = zdss_init;
+}
+
ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem)
{
- ZSTD_DCtx* dctx;
+ if (!customMem.customAlloc ^ !customMem.customFree) return NULL;
- if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
- if (!customMem.customAlloc || !customMem.customFree) return NULL;
+ { ZSTD_DCtx* const dctx = (ZSTD_DCtx*)ZSTD_malloc(sizeof(*dctx), customMem);
+ if (!dctx) return NULL;
+ dctx->customMem = customMem;
+ dctx->legacyContext = NULL;
+ dctx->previousLegacyVersion = 0;
+ ZSTD_initDCtx_internal(dctx);
+ return dctx;
+ }
+}
- dctx = (ZSTD_DCtx*)ZSTD_malloc(sizeof(ZSTD_DCtx), customMem);
- if (!dctx) return NULL;
- memcpy(&dctx->customMem, &customMem, sizeof(customMem));
- ZSTD_decompressBegin(dctx);
+ZSTD_DCtx* ZSTD_initStaticDCtx(void *workspace, size_t workspaceSize)
+{
+ ZSTD_DCtx* dctx = (ZSTD_DCtx*) workspace;
+
+ if ((size_t)workspace & 7) return NULL; /* 8-aligned */
+ if (workspaceSize < sizeof(ZSTD_DCtx)) return NULL; /* minimum size */
+
+ ZSTD_initDCtx_internal(dctx);
+ dctx->staticSize = workspaceSize;
+ dctx->inBuff = (char*)(dctx+1);
return dctx;
}
ZSTD_DCtx* ZSTD_createDCtx(void)
{
- return ZSTD_createDCtx_advanced(defaultCustomMem);
+ return ZSTD_createDCtx_advanced(ZSTD_defaultCMem);
}
size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx)
{
if (dctx==NULL) return 0; /* support free on NULL */
- ZSTD_free(dctx, dctx->customMem);
- return 0; /* reserved as a potential error code in the future */
+ if (dctx->staticSize) return ERROR(memory_allocation); /* not compatible with static DCtx */
+ { ZSTD_customMem const cMem = dctx->customMem;
+ ZSTD_freeDDict(dctx->ddictLocal);
+ dctx->ddictLocal = NULL;
+ ZSTD_free(dctx->inBuff, cMem);
+ dctx->inBuff = NULL;
+#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
+ if (dctx->legacyContext)
+ ZSTD_freeLegacyStreamContext(dctx->legacyContext, dctx->previousLegacyVersion);
+#endif
+ ZSTD_free(dctx, cMem);
+ return 0;
+ }
}
+/* no longer useful */
void ZSTD_copyDCtx(ZSTD_DCtx* dstDCtx, const ZSTD_DCtx* srcDCtx)
{
- size_t const workSpaceSize = (ZSTD_BLOCKSIZE_ABSOLUTEMAX+WILDCOPY_OVERLENGTH) + ZSTD_frameHeaderSize_max;
- memcpy(dstDCtx, srcDCtx, sizeof(ZSTD_DCtx) - workSpaceSize); /* no need to copy workspace */
+ size_t const toCopy = (size_t)((char*)(&dstDCtx->inBuff) - (char*)dstDCtx);
+ memcpy(dstDCtx, srcDCtx, toCopy); /* no need to copy workspace */
}
-static void ZSTD_refDDict(ZSTD_DCtx* dstDCtx, const ZSTD_DDict* ddict);
-
/*-*************************************************************
* Decompression section
@@ -206,7 +274,7 @@ unsigned ZSTD_isFrame(const void* buffer, size_t size)
/** ZSTD_frameHeaderSize() :
* srcSize must be >= ZSTD_frameHeaderSize_prefix.
* @return : size of the Frame Header */
-static size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize)
+size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize)
{
if (srcSize < ZSTD_frameHeaderSize_prefix) return ERROR(srcSize_wrong);
{ BYTE const fhd = ((const BYTE*)src)[4];
@@ -219,22 +287,24 @@ static size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize)
}
-/** ZSTD_getFrameParams() :
+/** ZSTD_getFrameHeader() :
* decode Frame Header, or require larger `srcSize`.
-* @return : 0, `fparamsPtr` is correctly filled,
+* @return : 0, `zfhPtr` is correctly filled,
* >0, `srcSize` is too small, result is expected `srcSize`,
* or an error code, which can be tested using ZSTD_isError() */
-size_t ZSTD_getFrameParams(ZSTD_frameParams* fparamsPtr, const void* src, size_t srcSize)
+size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize)
{
const BYTE* ip = (const BYTE*)src;
-
if (srcSize < ZSTD_frameHeaderSize_prefix) return ZSTD_frameHeaderSize_prefix;
+
if (MEM_readLE32(src) != ZSTD_MAGICNUMBER) {
if ((MEM_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
- if (srcSize < ZSTD_skippableHeaderSize) return ZSTD_skippableHeaderSize; /* magic number + skippable frame length */
- memset(fparamsPtr, 0, sizeof(*fparamsPtr));
- fparamsPtr->frameContentSize = MEM_readLE32((const char *)src + 4);
- fparamsPtr->windowSize = 0; /* windowSize==0 means a frame is skippable */
+ /* skippable frame */
+ if (srcSize < ZSTD_skippableHeaderSize)
+ return ZSTD_skippableHeaderSize; /* magic number + frame length */
+ memset(zfhPtr, 0, sizeof(*zfhPtr));
+ zfhPtr->frameContentSize = MEM_readLE32((const char *)src + 4);
+ zfhPtr->windowSize = 0; /* windowSize==0 means a frame is skippable */
return 0;
}
return ERROR(prefix_unknown);
@@ -254,11 +324,13 @@ size_t ZSTD_getFrameParams(ZSTD_frameParams* fparamsPtr, const void* src, size_t
U32 windowSize = 0;
U32 dictID = 0;
U64 frameContentSize = 0;
- if ((fhdByte & 0x08) != 0) return ERROR(frameParameter_unsupported); /* reserved bits, which must be zero */
+ if ((fhdByte & 0x08) != 0)
+ return ERROR(frameParameter_unsupported); /* reserved bits, must be zero */
if (!singleSegment) {
BYTE const wlByte = ip[pos++];
U32 const windowLog = (wlByte >> 3) + ZSTD_WINDOWLOG_ABSOLUTEMIN;
- if (windowLog > ZSTD_WINDOWLOG_MAX) return ERROR(frameParameter_windowTooLarge); /* avoids issue with 1 << windowLog */
+ if (windowLog > ZSTD_WINDOWLOG_MAX)
+ return ERROR(frameParameter_windowTooLarge);
windowSize = (1U << windowLog);
windowSize += (windowSize >> 3) * (wlByte&7);
}
@@ -281,10 +353,10 @@ size_t ZSTD_getFrameParams(ZSTD_frameParams* fparamsPtr, const void* src, size_t
}
if (!windowSize) windowSize = (U32)frameContentSize;
if (windowSize > windowSizeMax) return ERROR(frameParameter_windowTooLarge);
- fparamsPtr->frameContentSize = frameContentSize;
- fparamsPtr->windowSize = windowSize;
- fparamsPtr->dictID = dictID;
- fparamsPtr->checksumFlag = checksumFlag;
+ zfhPtr->frameContentSize = frameContentSize;
+ zfhPtr->windowSize = windowSize;
+ zfhPtr->dictID = dictID;
+ zfhPtr->checksumFlag = checksumFlag;
}
return 0;
}
@@ -302,9 +374,8 @@ unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize)
return ret == 0 ? ZSTD_CONTENTSIZE_UNKNOWN : ret;
}
#endif
- {
- ZSTD_frameParams fParams;
- if (ZSTD_getFrameParams(&fParams, src, srcSize) != 0) return ZSTD_CONTENTSIZE_ERROR;
+ { ZSTD_frameHeader fParams;
+ if (ZSTD_getFrameHeader(&fParams, src, srcSize) != 0) return ZSTD_CONTENTSIZE_ERROR;
if (fParams.windowSize == 0) {
/* Either skippable or empty frame, size == 0 either way */
return 0;
@@ -323,51 +394,48 @@ unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize)
* @return : decompressed size of the frames contained */
unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize)
{
- {
- unsigned long long totalDstSize = 0;
- while (srcSize >= ZSTD_frameHeaderSize_prefix) {
- const U32 magicNumber = MEM_readLE32(src);
+ unsigned long long totalDstSize = 0;
- if ((magicNumber & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
- size_t skippableSize;
- if (srcSize < ZSTD_skippableHeaderSize)
- return ERROR(srcSize_wrong);
- skippableSize = MEM_readLE32((const BYTE *)src + 4) +
- ZSTD_skippableHeaderSize;
- if (srcSize < skippableSize) {
- return ZSTD_CONTENTSIZE_ERROR;
- }
-
- src = (const BYTE *)src + skippableSize;
- srcSize -= skippableSize;
- continue;
+ while (srcSize >= ZSTD_frameHeaderSize_prefix) {
+ const U32 magicNumber = MEM_readLE32(src);
+
+ if ((magicNumber & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
+ size_t skippableSize;
+ if (srcSize < ZSTD_skippableHeaderSize)
+ return ERROR(srcSize_wrong);
+ skippableSize = MEM_readLE32((const BYTE *)src + 4) +
+ ZSTD_skippableHeaderSize;
+ if (srcSize < skippableSize) {
+ return ZSTD_CONTENTSIZE_ERROR;
}
- {
- unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize);
- if (ret >= ZSTD_CONTENTSIZE_ERROR) return ret;
+ src = (const BYTE *)src + skippableSize;
+ srcSize -= skippableSize;
+ continue;
+ }
- /* check for overflow */
- if (totalDstSize + ret < totalDstSize) return ZSTD_CONTENTSIZE_ERROR;
- totalDstSize += ret;
- }
- {
- size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize);
- if (ZSTD_isError(frameSrcSize)) {
- return ZSTD_CONTENTSIZE_ERROR;
- }
+ { unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize);
+ if (ret >= ZSTD_CONTENTSIZE_ERROR) return ret;
- src = (const BYTE *)src + frameSrcSize;
- srcSize -= frameSrcSize;
- }
+ /* check for overflow */
+ if (totalDstSize + ret < totalDstSize) return ZSTD_CONTENTSIZE_ERROR;
+ totalDstSize += ret;
}
+ { size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize);
+ if (ZSTD_isError(frameSrcSize)) {
+ return ZSTD_CONTENTSIZE_ERROR;
+ }
- if (srcSize) {
- return ZSTD_CONTENTSIZE_ERROR;
+ src = (const BYTE *)src + frameSrcSize;
+ srcSize -= frameSrcSize;
}
+ }
- return totalDstSize;
+ if (srcSize) {
+ return ZSTD_CONTENTSIZE_ERROR;
}
+
+ return totalDstSize;
}
/** ZSTD_getDecompressedSize() :
@@ -389,7 +457,7 @@ unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize)
* @return : 0 if success, or an error code, which can be tested using ZSTD_isError() */
static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t headerSize)
{
- size_t const result = ZSTD_getFrameParams(&(dctx->fParams), src, headerSize);
+ size_t const result = ZSTD_getFrameHeader(&(dctx->fParams), src, headerSize);
if (ZSTD_isError(result)) return result; /* invalid header */
if (result>0) return ERROR(srcSize_wrong); /* headerSize too small */
if (dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID)) return ERROR(dictionary_wrong);
@@ -485,7 +553,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
litCSize = (lhc >> 22) + (istart[4] << 10);
break;
}
- if (litSize > ZSTD_BLOCKSIZE_ABSOLUTEMAX) return ERROR(corruption_detected);
+ if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected);
if (litCSize + lhSize > srcSize) return ERROR(corruption_detected);
if (HUF_isError((litEncType==set_repeat) ?
@@ -493,8 +561,10 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
HUF_decompress1X_usingDTable(dctx->litBuffer, litSize, istart+lhSize, litCSize, dctx->HUFptr) :
HUF_decompress4X_usingDTable(dctx->litBuffer, litSize, istart+lhSize, litCSize, dctx->HUFptr) ) :
( singleStream ?
- HUF_decompress1X2_DCtx(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart+lhSize, litCSize) :
- HUF_decompress4X_hufOnly (dctx->entropy.hufTable, dctx->litBuffer, litSize, istart+lhSize, litCSize)) ))
+ HUF_decompress1X2_DCtx_wksp(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart+lhSize, litCSize,
+ dctx->entropy.workspace, sizeof(dctx->entropy.workspace)) :
+ HUF_decompress4X_hufOnly_wksp(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart+lhSize, litCSize,
+ dctx->entropy.workspace, sizeof(dctx->entropy.workspace)))))
return ERROR(corruption_detected);
dctx->litPtr = dctx->litBuffer;
@@ -557,7 +627,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
if (srcSize<4) return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4 */
break;
}
- if (litSize > ZSTD_BLOCKSIZE_ABSOLUTEMAX) return ERROR(corruption_detected);
+ if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected);
memset(dctx->litBuffer, istart[lhSize], litSize + WILDCOPY_OVERLENGTH);
dctx->litPtr = dctx->litBuffer;
dctx->litSize = litSize;
@@ -684,6 +754,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
const BYTE* const istart = (const BYTE* const)src;
const BYTE* const iend = istart + srcSize;
const BYTE* ip = istart;
+ DEBUGLOG(5, "ZSTD_decodeSeqHeaders");
/* check */
if (srcSize < MIN_SEQUENCES_SIZE) return ERROR(srcSize_wrong);
@@ -864,12 +935,18 @@ static seq_t ZSTD_decodeSequence(seqState_t* seqState)
seq.offset = offset;
}
- seq.matchLength = ML_base[mlCode] + ((mlCode>31) ? BIT_readBitsFast(&seqState->DStream, mlBits) : 0); /* <= 16 bits */
+ seq.matchLength = ML_base[mlCode]
+ + ((mlCode>31) ? BIT_readBitsFast(&seqState->DStream, mlBits) : 0); /* <= 16 bits */
if (MEM_32bits() && (mlBits+llBits>24)) BIT_reloadDStream(&seqState->DStream);
- seq.litLength = LL_base[llCode] + ((llCode>15) ? BIT_readBitsFast(&seqState->DStream, llBits) : 0); /* <= 16 bits */
- if (MEM_32bits() ||
- (totalBits > 64 - 7 - (LLFSELog+MLFSELog+OffFSELog)) ) BIT_reloadDStream(&seqState->DStream);
+ seq.litLength = LL_base[llCode]
+ + ((llCode>15) ? BIT_readBitsFast(&seqState->DStream, llBits) : 0); /* <= 16 bits */
+ if ( MEM_32bits()
+ || (totalBits > 64 - 7 - (LLFSELog+MLFSELog+OffFSELog)) )
+ BIT_reloadDStream(&seqState->DStream);
+
+ DEBUGLOG(6, "seq: litL=%u, matchL=%u, offset=%u",
+ (U32)seq.litLength, (U32)seq.matchLength, (U32)seq.offset);
/* ANS state update */
FSE_updateState(&seqState->stateLL, &seqState->DStream); /* <= 9 bits */
@@ -909,7 +986,8 @@ size_t ZSTD_execSequence(BYTE* op,
/* copy Match */
if (sequence.offset > (size_t)(oLitEnd - base)) {
/* offset beyond prefix -> go into extDict */
- if (sequence.offset > (size_t)(oLitEnd - vBase)) return ERROR(corruption_detected);
+ if (sequence.offset > (size_t)(oLitEnd - vBase))
+ return ERROR(corruption_detected);
match = dictEnd + (match - base);
if (match + sequence.matchLength <= dictEnd) {
memmove(oLitEnd, match, sequence.matchLength);
@@ -977,9 +1055,12 @@ static size_t ZSTD_decompressSequences(
const BYTE* const vBase = (const BYTE*) (dctx->vBase);
const BYTE* const dictEnd = (const BYTE*) (dctx->dictEnd);
int nbSeq;
+ DEBUGLOG(5, "ZSTD_decompressSequences");
/* Build Decoding Tables */
{ size_t const seqHSize = ZSTD_decodeSeqHeaders(dctx, &nbSeq, ip, seqSize);
+ DEBUGLOG(5, "ZSTD_decodeSeqHeaders: size=%u, nbSeq=%i",
+ (U32)seqHSize, nbSeq);
if (ZSTD_isError(seqHSize)) return seqHSize;
ip += seqHSize;
}
@@ -998,11 +1079,13 @@ static size_t ZSTD_decompressSequences(
nbSeq--;
{ seq_t const sequence = ZSTD_decodeSequence(&seqState);
size_t const oneSeqSize = ZSTD_execSequence(op, oend, sequence, &litPtr, litEnd, base, vBase, dictEnd);
+ DEBUGLOG(6, "regenerated sequence size : %u", (U32)oneSeqSize);
if (ZSTD_isError(oneSeqSize)) return oneSeqSize;
op += oneSeqSize;
} }
/* check if reached exact end */
+ DEBUGLOG(5, "after decode loop, remaining nbSeq : %i", nbSeq);
if (nbSeq) return ERROR(corruption_detected);
/* save reps for next block */
{ U32 i; for (i=0; i<ZSTD_REP_NUM; i++) dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]); }
@@ -1216,7 +1299,7 @@ static size_t ZSTD_decompressSequencesLong(
const BYTE* const base = (const BYTE*) (dctx->base);
const BYTE* const vBase = (const BYTE*) (dctx->vBase);
const BYTE* const dictEnd = (const BYTE*) (dctx->dictEnd);
- unsigned const windowSize = dctx->fParams.windowSize;
+ unsigned const windowSize32 = (unsigned)dctx->fParams.windowSize;
int nbSeq;
/* Build Decoding Tables */
@@ -1246,13 +1329,13 @@ static size_t ZSTD_decompressSequencesLong(
/* prepare in advance */
for (seqNb=0; (BIT_reloadDStream(&seqState.DStream) <= BIT_DStream_completed) && seqNb<seqAdvance; seqNb++) {
- sequences[seqNb] = ZSTD_decodeSequenceLong(&seqState, windowSize);
+ sequences[seqNb] = ZSTD_decodeSequenceLong(&seqState, windowSize32);
}
if (seqNb<seqAdvance) return ERROR(corruption_detected);
/* decode and decompress */
for ( ; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && seqNb<nbSeq ; seqNb++) {
- seq_t const sequence = ZSTD_decodeSequenceLong(&seqState, windowSize);
+ seq_t const sequence = ZSTD_decodeSequenceLong(&seqState, windowSize32);
size_t const oneSeqSize = ZSTD_execSequenceLong(op, oend, sequences[(seqNb-ADVANCED_SEQS) & STOSEQ_MASK], &litPtr, litEnd, base, vBase, dictEnd);
if (ZSTD_isError(oneSeqSize)) return oneSeqSize;
ZSTD_PREFETCH(sequence.match);
@@ -1289,11 +1372,13 @@ static size_t ZSTD_decompressBlock_internal(ZSTD_DCtx* dctx,
const void* src, size_t srcSize)
{ /* blockType == blockCompressed */
const BYTE* ip = (const BYTE*)src;
+ DEBUGLOG(5, "ZSTD_decompressBlock_internal");
- if (srcSize >= ZSTD_BLOCKSIZE_ABSOLUTEMAX) return ERROR(srcSize_wrong);
+ if (srcSize >= ZSTD_BLOCKSIZE_MAX) return ERROR(srcSize_wrong);
/* Decode literals section */
{ size_t const litCSize = ZSTD_decodeLiteralsBlock(dctx, src, srcSize);
+ DEBUGLOG(5, "ZSTD_decodeLiteralsBlock : %u", (U32)litCSize);
if (ZSTD_isError(litCSize)) return litCSize;
ip += litCSize;
srcSize -= litCSize;
@@ -1364,13 +1449,13 @@ size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize)
const BYTE* ip = (const BYTE*)src;
const BYTE* const ipstart = ip;
size_t remainingSize = srcSize;
- ZSTD_frameParams fParams;
+ ZSTD_frameHeader fParams;
size_t const headerSize = ZSTD_frameHeaderSize(ip, remainingSize);
if (ZSTD_isError(headerSize)) return headerSize;
/* Frame Header */
- { size_t const ret = ZSTD_getFrameParams(&fParams, ip, remainingSize);
+ { size_t const ret = ZSTD_getFrameHeader(&fParams, ip, remainingSize);
if (ZSTD_isError(ret)) return ret;
if (ret > 0) return ERROR(srcSize_wrong);
}
@@ -1505,6 +1590,8 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
size_t decodedSize;
size_t const frameSize = ZSTD_findFrameCompressedSizeLegacy(src, srcSize);
if (ZSTD_isError(frameSize)) return frameSize;
+ /* legacy support is incompatible with static dctx */
+ if (dctx->staticSize) return ERROR(memory_allocation);
decodedSize = ZSTD_decompressLegacy(dst, dstCapacity, src, frameSize, dict, dictSize);
@@ -1540,7 +1627,7 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
if (ddict) {
/* we were called from ZSTD_decompress_usingDDict */
- ZSTD_refDDict(dctx, ddict);
+ CHECK_F(ZSTD_decompressBegin_usingDDict(dctx, ddict));
} else {
/* this will initialize correctly with no dict if dict == NULL, so
* use this in all cases but ddict */
@@ -1580,7 +1667,7 @@ size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const
size_t ZSTD_decompress(void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
-#if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE==1)
+#if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE>=1)
size_t regenSize;
ZSTD_DCtx* const dctx = ZSTD_createDCtx();
if (dctx==NULL) return ERROR(memory_allocation);
@@ -1604,6 +1691,7 @@ ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx) {
switch(dctx->stage)
{
default: /* should not happen */
+ assert(0);
case ZSTDds_getFrameHeaderSize:
case ZSTDds_decodeFrameHeader:
return ZSTDnit_frameHeader;
@@ -1621,21 +1709,24 @@ ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx) {
}
}
-int ZSTD_isSkipFrame(ZSTD_DCtx* dctx) { return dctx->stage == ZSTDds_skipFrame; } /* for zbuff */
+static int ZSTD_isSkipFrame(ZSTD_DCtx* dctx) { return dctx->stage == ZSTDds_skipFrame; }
/** ZSTD_decompressContinue() :
-* @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity)
-* or an error code, which can be tested using ZSTD_isError() */
+ * srcSize : must be the exact nb of bytes expected (see ZSTD_nextSrcSizeToDecompress())
+ * @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity)
+ * or an error code, which can be tested using ZSTD_isError() */
size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
+ DEBUGLOG(5, "ZSTD_decompressContinue");
/* Sanity check */
- if (srcSize != dctx->expected) return ERROR(srcSize_wrong);
+ if (srcSize != dctx->expected) return ERROR(srcSize_wrong); /* unauthorized */
if (dstCapacity) ZSTD_checkContinuity(dctx, dst);
switch (dctx->stage)
{
case ZSTDds_getFrameHeaderSize :
- if (srcSize != ZSTD_frameHeaderSize_prefix) return ERROR(srcSize_wrong); /* impossible */
+ if (srcSize != ZSTD_frameHeaderSize_prefix) return ERROR(srcSize_wrong); /* unauthorized */
+ assert(src != NULL);
if ((MEM_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */
memcpy(dctx->headerBuffer, src, ZSTD_frameHeaderSize_prefix);
dctx->expected = ZSTD_skippableHeaderSize - ZSTD_frameHeaderSize_prefix; /* magic number + skippable frame length */
@@ -1653,6 +1744,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
dctx->expected = 0; /* not necessary to copy more */
case ZSTDds_decodeFrameHeader:
+ assert(src != NULL);
memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected);
CHECK_F(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize));
dctx->expected = ZSTD_blockHeaderSize;
@@ -1680,17 +1772,19 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
dctx->stage = ZSTDds_getFrameHeaderSize;
}
} else {
- dctx->expected = 3; /* go directly to next header */
+ dctx->expected = ZSTD_blockHeaderSize; /* jump to next header */
dctx->stage = ZSTDds_decodeBlockHeader;
}
return 0;
}
case ZSTDds_decompressLastBlock:
case ZSTDds_decompressBlock:
+ DEBUGLOG(5, "case ZSTDds_decompressBlock");
{ size_t rSize;
switch(dctx->bType)
{
case bt_compressed:
+ DEBUGLOG(5, "case bt_compressed");
rSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize);
break;
case bt_raw :
@@ -1730,7 +1824,8 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
return 0;
}
case ZSTDds_decodeSkippableHeader:
- { memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected);
+ { assert(src != NULL);
+ memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected);
dctx->expected = MEM_readLE32(dctx->headerBuffer + 4);
dctx->stage = ZSTDds_skipFrame;
return 0;
@@ -1767,7 +1862,9 @@ static size_t ZSTD_loadEntropy(ZSTD_entropyTables_t* entropy, const void* const
dictPtr += 8; /* skip header = magic + dictID */
- { size_t const hSize = HUF_readDTableX4(entropy->hufTable, dictPtr, dictEnd-dictPtr);
+ { size_t const hSize = HUF_readDTableX4_wksp(
+ entropy->hufTable, dictPtr, dictEnd - dictPtr,
+ entropy->workspace, sizeof(entropy->workspace));
if (HUF_isError(hSize)) return ERROR(dictionary_corrupted);
dictPtr += hSize;
}
@@ -1815,7 +1912,7 @@ static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx* dctx, const void* dict
{
if (dictSize < 8) return ZSTD_refDictContent(dctx, dict, dictSize);
{ U32 const magic = MEM_readLE32(dict);
- if (magic != ZSTD_DICT_MAGIC) {
+ if (magic != ZSTD_MAGIC_DICTIONARY) {
return ZSTD_refDictContent(dctx, dict, dictSize); /* pure content mode */
} }
dctx->dictID = MEM_readLE32((const char*)dict + 4);
@@ -1862,10 +1959,10 @@ static size_t ZSTD_DDictDictSize(const ZSTD_DDict* ddict)
return ddict->dictSize;
}
-static void ZSTD_refDDict(ZSTD_DCtx* dstDCtx, const ZSTD_DDict* ddict)
+size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dstDCtx, const ZSTD_DDict* ddict)
{
- ZSTD_decompressBegin(dstDCtx); /* init */
- if (ddict) { /* support refDDict on NULL */
+ CHECK_F(ZSTD_decompressBegin(dstDCtx));
+ if (ddict) { /* support begin on NULL */
dstDCtx->dictID = ddict->dictID;
dstDCtx->base = ddict->dictContent;
dstDCtx->vBase = ddict->dictContent;
@@ -1886,6 +1983,7 @@ static void ZSTD_refDDict(ZSTD_DCtx* dstDCtx, const ZSTD_DDict* ddict)
dstDCtx->fseEntropy = 0;
}
}
+ return 0;
}
static size_t ZSTD_loadEntropy_inDDict(ZSTD_DDict* ddict)
@@ -1894,7 +1992,7 @@ static size_t ZSTD_loadEntropy_inDDict(ZSTD_DDict* ddict)
ddict->entropyPresent = 0;
if (ddict->dictSize < 8) return 0;
{ U32 const magic = MEM_readLE32(ddict->dictContent);
- if (magic != ZSTD_DICT_MAGIC) return 0; /* pure content mode */
+ if (magic != ZSTD_MAGIC_DICTIONARY) return 0; /* pure content mode */
}
ddict->dictID = MEM_readLE32((const char*)ddict->dictContent + 4);
@@ -1905,33 +2003,39 @@ static size_t ZSTD_loadEntropy_inDDict(ZSTD_DDict* ddict)
}
+static size_t ZSTD_initDDict_internal(ZSTD_DDict* ddict, const void* dict, size_t dictSize, unsigned byReference)
+{
+ if ((byReference) || (!dict) || (!dictSize)) {
+ ddict->dictBuffer = NULL;
+ ddict->dictContent = dict;
+ } else {
+ void* const internalBuffer = ZSTD_malloc(dictSize, ddict->cMem);
+ ddict->dictBuffer = internalBuffer;
+ ddict->dictContent = internalBuffer;
+ if (!internalBuffer) return ERROR(memory_allocation);
+ memcpy(internalBuffer, dict, dictSize);
+ }
+ ddict->dictSize = dictSize;
+ ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */
+
+ /* parse dictionary content */
+ CHECK_F( ZSTD_loadEntropy_inDDict(ddict) );
+
+ return 0;
+}
+
ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize, unsigned byReference, ZSTD_customMem customMem)
{
- if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
- if (!customMem.customAlloc || !customMem.customFree) return NULL;
+ if (!customMem.customAlloc ^ !customMem.customFree) return NULL;
{ ZSTD_DDict* const ddict = (ZSTD_DDict*) ZSTD_malloc(sizeof(ZSTD_DDict), customMem);
if (!ddict) return NULL;
ddict->cMem = customMem;
- if ((byReference) || (!dict) || (!dictSize)) {
- ddict->dictBuffer = NULL;
- ddict->dictContent = dict;
- } else {
- void* const internalBuffer = ZSTD_malloc(dictSize, customMem);
- if (!internalBuffer) { ZSTD_freeDDict(ddict); return NULL; }
- memcpy(internalBuffer, dict, dictSize);
- ddict->dictBuffer = internalBuffer;
- ddict->dictContent = internalBuffer;
+ if (ZSTD_isError( ZSTD_initDDict_internal(ddict, dict, dictSize, byReference) )) {
+ ZSTD_freeDDict(ddict);
+ return NULL;
}
- ddict->dictSize = dictSize;
- ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */
- /* parse dictionary content */
- { size_t const errorCode = ZSTD_loadEntropy_inDDict(ddict);
- if (ZSTD_isError(errorCode)) {
- ZSTD_freeDDict(ddict);
- return NULL;
- } }
return ddict;
}
@@ -1947,7 +2051,6 @@ ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize)
return ZSTD_createDDict_advanced(dict, dictSize, 0, allocator);
}
-
/*! ZSTD_createDDict_byReference() :
* Create a digested dictionary, to start decompression without startup delay.
* Dictionary content is simply referenced, it will be accessed during decompression.
@@ -1959,6 +2062,26 @@ ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize
}
+ZSTD_DDict* ZSTD_initStaticDDict(void* workspace, size_t workspaceSize,
+ const void* dict, size_t dictSize,
+ unsigned byReference)
+{
+ size_t const neededSpace = sizeof(ZSTD_DDict) + (byReference ? 0 : dictSize);
+ ZSTD_DDict* const ddict = (ZSTD_DDict*)workspace;
+ assert(workspace != NULL);
+ assert(dict != NULL);
+ if ((size_t)workspace & 7) return NULL; /* 8-aligned */
+ if (workspaceSize < neededSpace) return NULL;
+ if (!byReference) {
+ memcpy(ddict+1, dict, dictSize); /* local copy */
+ dict = ddict+1;
+ }
+ if (ZSTD_isError( ZSTD_initDDict_internal(ddict, dict, dictSize, 1 /* byRef */) ))
+ return NULL;
+ return ddict;
+}
+
+
size_t ZSTD_freeDDict(ZSTD_DDict* ddict)
{
if (ddict==NULL) return 0; /* support free on NULL */
@@ -1969,6 +2092,14 @@ size_t ZSTD_freeDDict(ZSTD_DDict* ddict)
}
}
+/*! ZSTD_estimateDDictSize() :
+ * Estimate amount of memory that will be needed to create a dictionary for decompression.
+ * Note : dictionary created "byReference" are smaller */
+size_t ZSTD_estimateDDictSize(size_t dictSize, unsigned byReference)
+{
+ return sizeof(ZSTD_DDict) + (byReference ? 0 : dictSize);
+}
+
size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict)
{
if (ddict==NULL) return 0; /* support sizeof on NULL */
@@ -1982,7 +2113,7 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict)
unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize)
{
if (dictSize < 8) return 0;
- if (MEM_readLE32(dict) != ZSTD_DICT_MAGIC) return 0;
+ if (MEM_readLE32(dict) != ZSTD_MAGIC_DICTIONARY) return 0;
return MEM_readLE32((const char*)dict + 4);
}
@@ -2008,11 +2139,11 @@ unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict)
* Note : possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`.
* - This is not a Zstandard frame.
* When identifying the exact failure cause, it's possible to use
- * ZSTD_getFrameParams(), which will provide a more precise error code. */
+ * ZSTD_getFrameHeader(), which will provide a more precise error code. */
unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize)
{
- ZSTD_frameParams zfp = { 0 , 0 , 0 , 0 };
- size_t const hError = ZSTD_getFrameParams(&zfp, src, srcSize);
+ ZSTD_frameHeader zfp = { 0 , 0 , 0 , 0 };
+ size_t const hError = ZSTD_getFrameHeader(&zfp, src, srcSize);
if (ZSTD_isError(hError)) return 0;
return zfp.dictID;
}
@@ -2037,88 +2168,35 @@ size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
* Streaming decompression
*====================================*/
-typedef enum { zdss_init, zdss_loadHeader,
- zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage;
-
-/* *** Resource management *** */
-struct ZSTD_DStream_s {
- ZSTD_DCtx* dctx;
- ZSTD_DDict* ddictLocal;
- const ZSTD_DDict* ddict;
- ZSTD_frameParams fParams;
- ZSTD_dStreamStage stage;
- char* inBuff;
- size_t inBuffSize;
- size_t inPos;
- size_t maxWindowSize;
- char* outBuff;
- size_t outBuffSize;
- size_t outStart;
- size_t outEnd;
- size_t blockSize;
- BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX]; /* tmp buffer to store frame header */
- size_t lhSize;
- ZSTD_customMem customMem;
- void* legacyContext;
- U32 previousLegacyVersion;
- U32 legacyVersion;
- U32 hostageByte;
-}; /* typedef'd to ZSTD_DStream within "zstd.h" */
-
-
ZSTD_DStream* ZSTD_createDStream(void)
{
- return ZSTD_createDStream_advanced(defaultCustomMem);
+ return ZSTD_createDStream_advanced(ZSTD_defaultCMem);
}
-ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem)
+ZSTD_DStream* ZSTD_initStaticDStream(void *workspace, size_t workspaceSize)
{
- ZSTD_DStream* zds;
-
- if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem;
- if (!customMem.customAlloc || !customMem.customFree) return NULL;
+ return ZSTD_initStaticDCtx(workspace, workspaceSize);
+}
- zds = (ZSTD_DStream*) ZSTD_malloc(sizeof(ZSTD_DStream), customMem);
- if (zds==NULL) return NULL;
- memset(zds, 0, sizeof(ZSTD_DStream));
- memcpy(&zds->customMem, &customMem, sizeof(ZSTD_customMem));
- zds->dctx = ZSTD_createDCtx_advanced(customMem);
- if (zds->dctx == NULL) { ZSTD_freeDStream(zds); return NULL; }
- zds->stage = zdss_init;
- zds->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
- return zds;
+ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem)
+{
+ return ZSTD_createDCtx_advanced(customMem);
}
size_t ZSTD_freeDStream(ZSTD_DStream* zds)
{
- if (zds==NULL) return 0; /* support free on null */
- { ZSTD_customMem const cMem = zds->customMem;
- ZSTD_freeDCtx(zds->dctx);
- zds->dctx = NULL;
- ZSTD_freeDDict(zds->ddictLocal);
- zds->ddictLocal = NULL;
- ZSTD_free(zds->inBuff, cMem);
- zds->inBuff = NULL;
- ZSTD_free(zds->outBuff, cMem);
- zds->outBuff = NULL;
-#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
- if (zds->legacyContext)
- ZSTD_freeLegacyStreamContext(zds->legacyContext, zds->previousLegacyVersion);
-#endif
- ZSTD_free(zds, cMem);
- return 0;
- }
+ return ZSTD_freeDCtx(zds);
}
/* *** Initialization *** */
-size_t ZSTD_DStreamInSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX + ZSTD_blockHeaderSize; }
-size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX; }
+size_t ZSTD_DStreamInSize(void) { return ZSTD_BLOCKSIZE_MAX + ZSTD_blockHeaderSize; }
+size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_MAX; }
size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize)
{
- zds->stage = zdss_loadHeader;
+ zds->streamStage = zdss_loadHeader;
zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
ZSTD_freeDDict(zds->ddictLocal);
if (dict && dictSize >= 8) {
@@ -2147,7 +2225,7 @@ size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict)
size_t ZSTD_resetDStream(ZSTD_DStream* zds)
{
- zds->stage = zdss_loadHeader;
+ zds->streamStage = zdss_loadHeader;
zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
zds->legacyVersion = 0;
zds->hostageByte = 0;
@@ -2168,11 +2246,24 @@ size_t ZSTD_setDStreamParameter(ZSTD_DStream* zds,
size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds)
{
- if (zds==NULL) return 0; /* support sizeof NULL */
- return sizeof(*zds)
- + ZSTD_sizeof_DCtx(zds->dctx)
- + ZSTD_sizeof_DDict(zds->ddictLocal)
- + zds->inBuffSize + zds->outBuffSize;
+ return ZSTD_sizeof_DCtx(zds);
+}
+
+size_t ZSTD_estimateDStreamSize(size_t windowSize)
+{
+ size_t const blockSize = MIN(windowSize, ZSTD_BLOCKSIZE_MAX);
+ size_t const inBuffSize = blockSize; /* no block can be larger */
+ size_t const outBuffSize = windowSize + blockSize + (WILDCOPY_OVERLENGTH * 2);
+ return sizeof(ZSTD_DStream) + ZSTD_estimateDCtxSize() + inBuffSize + outBuffSize;
+}
+
+ZSTDLIB_API size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize)
+{
+ ZSTD_frameHeader fh;
+ size_t const err = ZSTD_getFrameHeader(&fh, src, srcSize);
+ if (ZSTD_isError(err)) return err;
+ if (err>0) return ERROR(srcSize_wrong);
+ return ZSTD_estimateDStreamSize(fh.windowSize);
}
@@ -2196,44 +2287,55 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
char* op = ostart;
U32 someMoreWork = 1;
+ DEBUGLOG(5, "ZSTD_decompressStream");
+ DEBUGLOG(5, "input size : %u", (U32)(input->size - input->pos));
#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
- if (zds->legacyVersion)
+ if (zds->legacyVersion) {
+ /* legacy support is incompatible with static dctx */
+ if (zds->staticSize) return ERROR(memory_allocation);
return ZSTD_decompressLegacyStream(zds->legacyContext, zds->legacyVersion, output, input);
+ }
#endif
while (someMoreWork) {
- switch(zds->stage)
+ switch(zds->streamStage)
{
case zdss_init :
ZSTD_resetDStream(zds); /* transparent reset on starting decoding a new frame */
/* fall-through */
case zdss_loadHeader :
- { size_t const hSize = ZSTD_getFrameParams(&zds->fParams, zds->headerBuffer, zds->lhSize);
- if (ZSTD_isError(hSize))
+ { size_t const hSize = ZSTD_getFrameHeader(&zds->fParams, zds->headerBuffer, zds->lhSize);
+ if (ZSTD_isError(hSize)) {
#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
- { U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart);
+ U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart);
if (legacyVersion) {
const void* const dict = zds->ddict ? zds->ddict->dictContent : NULL;
size_t const dictSize = zds->ddict ? zds->ddict->dictSize : 0;
+ /* legacy support is incompatible with static dctx */
+ if (zds->staticSize) return ERROR(memory_allocation);
CHECK_F(ZSTD_initLegacyStream(&zds->legacyContext, zds->previousLegacyVersion, legacyVersion,
dict, dictSize));
zds->legacyVersion = zds->previousLegacyVersion = legacyVersion;
return ZSTD_decompressLegacyStream(zds->legacyContext, zds->legacyVersion, output, input);
} else {
return hSize; /* error */
- } }
+ }
#else
- return hSize;
+ return hSize;
#endif
+ }
if (hSize != 0) { /* need more input */
size_t const toLoad = hSize - zds->lhSize; /* if hSize!=0, hSize > zds->lhSize */
if (toLoad > (size_t)(iend-ip)) { /* not enough input to load full header */
- memcpy(zds->headerBuffer + zds->lhSize, ip, iend-ip);
- zds->lhSize += iend-ip;
+ if (iend-ip > 0) {
+ memcpy(zds->headerBuffer + zds->lhSize, ip, iend-ip);
+ zds->lhSize += iend-ip;
+ }
input->pos = input->size;
return (MAX(ZSTD_frameHeaderSize_min, hSize) - zds->lhSize) + ZSTD_blockHeaderSize; /* remaining header bytes + next block header */
}
+ assert(ip != NULL);
memcpy(zds->headerBuffer + zds->lhSize, ip, toLoad); zds->lhSize = hSize; ip += toLoad;
break;
} }
@@ -2243,74 +2345,90 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
&& (U64)(size_t)(oend-op) >= zds->fParams.frameContentSize) {
size_t const cSize = ZSTD_findFrameCompressedSize(istart, iend-istart);
if (cSize <= (size_t)(iend-istart)) {
- size_t const decompressedSize = ZSTD_decompress_usingDDict(zds->dctx, op, oend-op, istart, cSize, zds->ddict);
+ size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, oend-op, istart, cSize, zds->ddict);
if (ZSTD_isError(decompressedSize)) return decompressedSize;
ip = istart + cSize;
op += decompressedSize;
- zds->dctx->expected = 0;
- zds->stage = zdss_init;
+ zds->expected = 0;
+ zds->streamStage = zdss_init;
someMoreWork = 0;
break;
} }
- /* Consume header */
- ZSTD_refDDict(zds->dctx, zds->ddict);
- { size_t const h1Size = ZSTD_nextSrcSizeToDecompress(zds->dctx); /* == ZSTD_frameHeaderSize_prefix */
- CHECK_F(ZSTD_decompressContinue(zds->dctx, NULL, 0, zds->headerBuffer, h1Size));
- { size_t const h2Size = ZSTD_nextSrcSizeToDecompress(zds->dctx);
- CHECK_F(ZSTD_decompressContinue(zds->dctx, NULL, 0, zds->headerBuffer+h1Size, h2Size));
- } }
+ /* Consume header (see ZSTDds_decodeFrameHeader) */
+ DEBUGLOG(4, "Consume header");
+ CHECK_F(ZSTD_decompressBegin_usingDDict(zds, zds->ddict));
+
+ if ((MEM_readLE32(zds->headerBuffer) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */
+ zds->expected = MEM_readLE32(zds->headerBuffer + 4);
+ zds->stage = ZSTDds_skipFrame;
+ } else {
+ CHECK_F(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize));
+ zds->expected = ZSTD_blockHeaderSize;
+ zds->stage = ZSTDds_decodeBlockHeader;
+ }
+ /* control buffer memory usage */
+ DEBUGLOG(4, "Control max buffer memory usage");
zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN);
if (zds->fParams.windowSize > zds->maxWindowSize) return ERROR(frameParameter_windowTooLarge);
/* Adapt buffer sizes to frame header instructions */
- { size_t const blockSize = MIN(zds->fParams.windowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX);
+ { size_t const blockSize = MIN(zds->fParams.windowSize, ZSTD_BLOCKSIZE_MAX);
size_t const neededOutSize = zds->fParams.windowSize + blockSize + WILDCOPY_OVERLENGTH * 2;
zds->blockSize = blockSize;
- if (zds->inBuffSize < blockSize) {
- ZSTD_free(zds->inBuff, zds->customMem);
- zds->inBuffSize = 0;
- zds->inBuff = (char*)ZSTD_malloc(blockSize, zds->customMem);
- if (zds->inBuff == NULL) return ERROR(memory_allocation);
+ if ((zds->inBuffSize < blockSize) || (zds->outBuffSize < neededOutSize)) {
+ size_t const bufferSize = blockSize + neededOutSize;
+ DEBUGLOG(4, "inBuff : from %u to %u",
+ (U32)zds->inBuffSize, (U32)blockSize);
+ DEBUGLOG(4, "outBuff : from %u to %u",
+ (U32)zds->outBuffSize, (U32)neededOutSize);
+ if (zds->staticSize) { /* static DCtx */
+ DEBUGLOG(4, "staticSize : %u", (U32)zds->staticSize);
+ assert(zds->staticSize >= sizeof(ZSTD_DCtx)); /* controlled at init */
+ if (bufferSize > zds->staticSize - sizeof(ZSTD_DCtx))
+ return ERROR(memory_allocation);
+ } else {
+ ZSTD_free(zds->inBuff, zds->customMem);
+ zds->inBuffSize = 0;
+ zds->outBuffSize = 0;
+ zds->inBuff = (char*)ZSTD_malloc(bufferSize, zds->customMem);
+ if (zds->inBuff == NULL) return ERROR(memory_allocation);
+ }
zds->inBuffSize = blockSize;
- }
- if (zds->outBuffSize < neededOutSize) {
- ZSTD_free(zds->outBuff, zds->customMem);
- zds->outBuffSize = 0;
- zds->outBuff = (char*)ZSTD_malloc(neededOutSize, zds->customMem);
- if (zds->outBuff == NULL) return ERROR(memory_allocation);
+ zds->outBuff = zds->inBuff + zds->inBuffSize;
zds->outBuffSize = neededOutSize;
} }
- zds->stage = zdss_read;
+ zds->streamStage = zdss_read;
/* pass-through */
case zdss_read:
- { size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
+ DEBUGLOG(5, "stage zdss_read");
+ { size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds);
+ DEBUGLOG(5, "neededInSize = %u", (U32)neededInSize);
if (neededInSize==0) { /* end of frame */
- zds->stage = zdss_init;
+ zds->streamStage = zdss_init;
someMoreWork = 0;
break;
}
if ((size_t)(iend-ip) >= neededInSize) { /* decode directly from src */
- const int isSkipFrame = ZSTD_isSkipFrame(zds->dctx);
- size_t const decodedSize = ZSTD_decompressContinue(zds->dctx,
+ int const isSkipFrame = ZSTD_isSkipFrame(zds);
+ size_t const decodedSize = ZSTD_decompressContinue(zds,
zds->outBuff + zds->outStart, (isSkipFrame ? 0 : zds->outBuffSize - zds->outStart),
ip, neededInSize);
if (ZSTD_isError(decodedSize)) return decodedSize;
ip += neededInSize;
if (!decodedSize && !isSkipFrame) break; /* this was just a header */
zds->outEnd = zds->outStart + decodedSize;
- zds->stage = zdss_flush;
+ zds->streamStage = zdss_flush;
break;
- }
- if (ip==iend) { someMoreWork = 0; break; } /* no more input */
- zds->stage = zdss_load;
- /* pass-through */
- }
+ } }
+ if (ip==iend) { someMoreWork = 0; break; } /* no more input */
+ zds->streamStage = zdss_load;
+ /* pass-through */
case zdss_load:
- { size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
+ { size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds);
size_t const toLoad = neededInSize - zds->inPos; /* should always be <= remaining space within inBuff */
size_t loadedSize;
if (toLoad > zds->inBuffSize - zds->inPos) return ERROR(corruption_detected); /* should never happen */
@@ -2320,17 +2438,17 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
if (loadedSize < toLoad) { someMoreWork = 0; break; } /* not enough input, wait for more */
/* decode loaded input */
- { const int isSkipFrame = ZSTD_isSkipFrame(zds->dctx);
- size_t const decodedSize = ZSTD_decompressContinue(zds->dctx,
+ { const int isSkipFrame = ZSTD_isSkipFrame(zds);
+ size_t const decodedSize = ZSTD_decompressContinue(zds,
zds->outBuff + zds->outStart, zds->outBuffSize - zds->outStart,
zds->inBuff, neededInSize);
if (ZSTD_isError(decodedSize)) return decodedSize;
zds->inPos = 0; /* input is consumed */
- if (!decodedSize && !isSkipFrame) { zds->stage = zdss_read; break; } /* this was just a header */
+ if (!decodedSize && !isSkipFrame) { zds->streamStage = zdss_read; break; } /* this was just a header */
zds->outEnd = zds->outStart + decodedSize;
- zds->stage = zdss_flush;
- /* pass-through */
} }
+ zds->streamStage = zdss_flush;
+ /* pass-through */
case zdss_flush:
{ size_t const toFlushSize = zds->outEnd - zds->outStart;
@@ -2338,37 +2456,41 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
op += flushedSize;
zds->outStart += flushedSize;
if (flushedSize == toFlushSize) { /* flush completed */
- zds->stage = zdss_read;
+ zds->streamStage = zdss_read;
if (zds->outStart + zds->blockSize > zds->outBuffSize)
zds->outStart = zds->outEnd = 0;
break;
- }
- /* cannot complete flush */
- someMoreWork = 0;
- break;
- }
+ } }
+ /* cannot complete flush */
+ someMoreWork = 0;
+ break;
+
default: return ERROR(GENERIC); /* impossible */
} }
/* result */
input->pos += (size_t)(ip-istart);
output->pos += (size_t)(op-ostart);
- { size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds->dctx);
+ { size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds);
if (!nextSrcSizeHint) { /* frame fully decoded */
if (zds->outEnd == zds->outStart) { /* output fully flushed */
if (zds->hostageByte) {
- if (input->pos >= input->size) { zds->stage = zdss_read; return 1; } /* can't release hostage (not present) */
+ if (input->pos >= input->size) {
+ /* can't release hostage (not present) */
+ zds->streamStage = zdss_read;
+ return 1;
+ }
input->pos++; /* release hostage */
- }
+ } /* zds->hostageByte */
return 0;
- }
+ } /* zds->outEnd == zds->outStart */
if (!zds->hostageByte) { /* output not fully flushed; keep last byte as hostage; will be released when all output is flushed */
input->pos--; /* note : pos > 0, otherwise, impossible to finish reading last block */
zds->hostageByte=1;
}
return 1;
- }
- nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds->dctx) == ZSTDnit_block); /* preload header of next block */
+ } /* nextSrcSizeHint==0 */
+ nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds) == ZSTDnit_block); /* preload header of next block */
if (zds->inPos > nextSrcSizeHint) return ERROR(GENERIC); /* should never happen */
nextSrcSizeHint -= zds->inPos; /* already loaded*/
return nextSrcSizeHint;
diff --git a/lib/dictBuilder/cover.c b/lib/dictBuilder/cover.c
index 1863c8f34542e..06c1b9fadb7ae 100644
--- a/lib/dictBuilder/cover.c
+++ b/lib/dictBuilder/cover.c
@@ -398,7 +398,8 @@ typedef struct {
*/
static COVER_segment_t COVER_selectSegment(const COVER_ctx_t *ctx, U32 *freqs,
COVER_map_t *activeDmers, U32 begin,
- U32 end, COVER_params_t parameters) {
+ U32 end,
+ ZDICT_cover_params_t parameters) {
/* Constants */
const U32 k = parameters.k;
const U32 d = parameters.d;
@@ -478,7 +479,7 @@ static COVER_segment_t COVER_selectSegment(const COVER_ctx_t *ctx, U32 *freqs,
* Check the validity of the parameters.
* Returns non-zero if the parameters are valid and 0 otherwise.
*/
-static int COVER_checkParameters(COVER_params_t parameters) {
+static int COVER_checkParameters(ZDICT_cover_params_t parameters) {
/* k and d are required parameters */
if (parameters.d == 0 || parameters.k == 0) {
return 0;
@@ -600,7 +601,7 @@ static int COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer,
static size_t COVER_buildDictionary(const COVER_ctx_t *ctx, U32 *freqs,
COVER_map_t *activeDmers, void *dictBuffer,
size_t dictBufferCapacity,
- COVER_params_t parameters) {
+ ZDICT_cover_params_t parameters) {
BYTE *const dict = (BYTE *)dictBuffer;
size_t tail = dictBufferCapacity;
/* Divide the data up into epochs of equal size.
@@ -639,22 +640,10 @@ static size_t COVER_buildDictionary(const COVER_ctx_t *ctx, U32 *freqs,
return tail;
}
-/**
- * Translate from COVER_params_t to ZDICT_params_t required for finalizing the
- * dictionary.
- */
-static ZDICT_params_t COVER_translateParams(COVER_params_t parameters) {
- ZDICT_params_t zdictParams;
- memset(&zdictParams, 0, sizeof(zdictParams));
- zdictParams.notificationLevel = 1;
- zdictParams.dictID = parameters.dictID;
- zdictParams.compressionLevel = parameters.compressionLevel;
- return zdictParams;
-}
-
-ZDICTLIB_API size_t COVER_trainFromBuffer(
+ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover(
void *dictBuffer, size_t dictBufferCapacity, const void *samplesBuffer,
- const size_t *samplesSizes, unsigned nbSamples, COVER_params_t parameters) {
+ const size_t *samplesSizes, unsigned nbSamples,
+ ZDICT_cover_params_t parameters) {
BYTE *const dict = (BYTE *)dictBuffer;
COVER_ctx_t ctx;
COVER_map_t activeDmers;
@@ -673,7 +662,7 @@ ZDICTLIB_API size_t COVER_trainFromBuffer(
return ERROR(dstSize_tooSmall);
}
/* Initialize global data */
- g_displayLevel = parameters.notificationLevel;
+ g_displayLevel = parameters.zParams.notificationLevel;
/* Initialize context and activeDmers */
if (!COVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples,
parameters.d)) {
@@ -690,10 +679,9 @@ ZDICTLIB_API size_t COVER_trainFromBuffer(
const size_t tail =
COVER_buildDictionary(&ctx, ctx.freqs, &activeDmers, dictBuffer,
dictBufferCapacity, parameters);
- ZDICT_params_t zdictParams = COVER_translateParams(parameters);
const size_t dictionarySize = ZDICT_finalizeDictionary(
dict, dictBufferCapacity, dict + tail, dictBufferCapacity - tail,
- samplesBuffer, samplesSizes, nbSamples, zdictParams);
+ samplesBuffer, samplesSizes, nbSamples, parameters.zParams);
if (!ZSTD_isError(dictionarySize)) {
DISPLAYLEVEL(2, "Constructed dictionary of size %u\n",
(U32)dictionarySize);
@@ -718,7 +706,7 @@ typedef struct COVER_best_s {
size_t liveJobs;
void *dict;
size_t dictSize;
- COVER_params_t parameters;
+ ZDICT_cover_params_t parameters;
size_t compressedSize;
} COVER_best_t;
@@ -786,7 +774,7 @@ static void COVER_best_start(COVER_best_t *best) {
* If this dictionary is the best so far save it and its parameters.
*/
static void COVER_best_finish(COVER_best_t *best, size_t compressedSize,
- COVER_params_t parameters, void *dict,
+ ZDICT_cover_params_t parameters, void *dict,
size_t dictSize) {
if (!best) {
return;
@@ -830,7 +818,7 @@ typedef struct COVER_tryParameters_data_s {
const COVER_ctx_t *ctx;
COVER_best_t *best;
size_t dictBufferCapacity;
- COVER_params_t parameters;
+ ZDICT_cover_params_t parameters;
} COVER_tryParameters_data_t;
/**
@@ -842,7 +830,7 @@ static void COVER_tryParameters(void *opaque) {
/* Save parameters as local variables */
COVER_tryParameters_data_t *const data = (COVER_tryParameters_data_t *)opaque;
const COVER_ctx_t *const ctx = data->ctx;
- const COVER_params_t parameters = data->parameters;
+ const ZDICT_cover_params_t parameters = data->parameters;
size_t dictBufferCapacity = data->dictBufferCapacity;
size_t totalCompressedSize = ERROR(GENERIC);
/* Allocate space for hash table, dict, and freqs */
@@ -863,10 +851,10 @@ static void COVER_tryParameters(void *opaque) {
{
const size_t tail = COVER_buildDictionary(ctx, freqs, &activeDmers, dict,
dictBufferCapacity, parameters);
- const ZDICT_params_t zdictParams = COVER_translateParams(parameters);
dictBufferCapacity = ZDICT_finalizeDictionary(
dict, dictBufferCapacity, dict + tail, dictBufferCapacity - tail,
- ctx->samples, ctx->samplesSizes, (unsigned)ctx->nbSamples, zdictParams);
+ ctx->samples, ctx->samplesSizes, (unsigned)ctx->nbSamples,
+ parameters.zParams);
if (ZDICT_isError(dictBufferCapacity)) {
DISPLAYLEVEL(1, "Failed to finalize dictionary\n");
goto _cleanup;
@@ -892,8 +880,8 @@ static void COVER_tryParameters(void *opaque) {
}
/* Create the cctx and cdict */
cctx = ZSTD_createCCtx();
- cdict =
- ZSTD_createCDict(dict, dictBufferCapacity, parameters.compressionLevel);
+ cdict = ZSTD_createCDict(dict, dictBufferCapacity,
+ parameters.zParams.compressionLevel);
if (!dst || !cctx || !cdict) {
goto _compressCleanup;
}
@@ -930,12 +918,10 @@ _cleanup:
}
}
-ZDICTLIB_API size_t COVER_optimizeTrainFromBuffer(void *dictBuffer,
- size_t dictBufferCapacity,
- const void *samplesBuffer,
- const size_t *samplesSizes,
- unsigned nbSamples,
- COVER_params_t *parameters) {
+ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
+ void *dictBuffer, size_t dictBufferCapacity, const void *samplesBuffer,
+ const size_t *samplesSizes, unsigned nbSamples,
+ ZDICT_cover_params_t *parameters) {
/* constants */
const unsigned nbThreads = parameters->nbThreads;
const unsigned kMinD = parameters->d == 0 ? 6 : parameters->d;
@@ -947,7 +933,7 @@ ZDICTLIB_API size_t COVER_optimizeTrainFromBuffer(void *dictBuffer,
const unsigned kIterations =
(1 + (kMaxD - kMinD) / 2) * (1 + (kMaxK - kMinK) / kStepSize);
/* Local variables */
- const int displayLevel = parameters->notificationLevel;
+ const int displayLevel = parameters->zParams.notificationLevel;
unsigned iteration = 1;
unsigned d;
unsigned k;
@@ -976,7 +962,7 @@ ZDICTLIB_API size_t COVER_optimizeTrainFromBuffer(void *dictBuffer,
/* Initialization */
COVER_best_init(&best);
/* Turn down global display level to clean up display at level 2 and below */
- g_displayLevel = parameters->notificationLevel - 1;
+ g_displayLevel = parameters->zParams.notificationLevel - 1;
/* Loop through d first because each new value needs a new context */
LOCALDISPLAYLEVEL(displayLevel, 2, "Trying %u different sets of parameters\n",
kIterations);
diff --git a/lib/dictBuilder/zdict.c b/lib/dictBuilder/zdict.c
index 179e02effa4db..742586eacdd23 100644
--- a/lib/dictBuilder/zdict.c
+++ b/lib/dictBuilder/zdict.c
@@ -94,7 +94,7 @@ const char* ZDICT_getErrorName(size_t errorCode) { return ERR_getErrorName(error
unsigned ZDICT_getDictID(const void* dictBuffer, size_t dictSize)
{
if (dictSize < 8) return 0;
- if (MEM_readLE32(dictBuffer) != ZSTD_DICT_MAGIC) return 0;
+ if (MEM_readLE32(dictBuffer) != ZSTD_MAGIC_DICTIONARY) return 0;
return MEM_readLE32((const char*)dictBuffer + 4);
}
@@ -487,7 +487,7 @@ static U32 ZDICT_dictSize(const dictItem* dictList)
}
-static size_t ZDICT_trainBuffer(dictItem* dictList, U32 dictListSize,
+static size_t ZDICT_trainBuffer_legacy(dictItem* dictList, U32 dictListSize,
const void* const buffer, size_t bufferSize, /* buffer must end with noisy guard band */
const size_t* fileSizes, unsigned nbFiles,
U32 minRatio, U32 notificationLevel)
@@ -576,7 +576,7 @@ typedef struct
{
ZSTD_CCtx* ref;
ZSTD_CCtx* zc;
- void* workPlace; /* must be ZSTD_BLOCKSIZE_ABSOLUTEMAX allocated */
+ void* workPlace; /* must be ZSTD_BLOCKSIZE_MAX allocated */
} EStats_ress_t;
#define MAXREPOFFSET 1024
@@ -585,14 +585,14 @@ static void ZDICT_countEStats(EStats_ress_t esr, ZSTD_parameters params,
U32* countLit, U32* offsetcodeCount, U32* matchlengthCount, U32* litlengthCount, U32* repOffsets,
const void* src, size_t srcSize, U32 notificationLevel)
{
- size_t const blockSizeMax = MIN (ZSTD_BLOCKSIZE_ABSOLUTEMAX, 1 << params.cParams.windowLog);
+ size_t const blockSizeMax = MIN (ZSTD_BLOCKSIZE_MAX, 1 << params.cParams.windowLog);
size_t cSize;
if (srcSize > blockSizeMax) srcSize = blockSizeMax; /* protection vs large samples */
{ size_t const errorCode = ZSTD_copyCCtx(esr.zc, esr.ref, 0);
if (ZSTD_isError(errorCode)) { DISPLAYLEVEL(1, "warning : ZSTD_copyCCtx failed \n"); return; }
}
- cSize = ZSTD_compressBlock(esr.zc, esr.workPlace, ZSTD_BLOCKSIZE_ABSOLUTEMAX, src, srcSize);
+ cSize = ZSTD_compressBlock(esr.zc, esr.workPlace, ZSTD_BLOCKSIZE_MAX, src, srcSize);
if (ZSTD_isError(cSize)) { DISPLAYLEVEL(3, "warning : could not compress sample size %u \n", (U32)srcSize); return; }
if (cSize) { /* if == 0; block is not compressible */
@@ -634,17 +634,6 @@ static void ZDICT_countEStats(EStats_ress_t esr, ZSTD_parameters params,
} } }
}
-/*
-static size_t ZDICT_maxSampleSize(const size_t* fileSizes, unsigned nbFiles)
-{
- unsigned u;
- size_t max=0;
- for (u=0; u<nbFiles; u++)
- if (max < fileSizes[u]) max = fileSizes[u];
- return max;
-}
-*/
-
static size_t ZDICT_totalSampleSize(const size_t* fileSizes, unsigned nbFiles)
{
size_t total=0;
@@ -700,7 +689,7 @@ static size_t ZDICT_analyzeEntropy(void* dstBuffer, size_t maxDstSize,
/* init */
esr.ref = ZSTD_createCCtx();
esr.zc = ZSTD_createCCtx();
- esr.workPlace = malloc(ZSTD_BLOCKSIZE_ABSOLUTEMAX);
+ esr.workPlace = malloc(ZSTD_BLOCKSIZE_MAX);
if (!esr.ref || !esr.zc || !esr.workPlace) {
eSize = ERROR(memory_allocation);
DISPLAYLEVEL(1, "Not enough memory \n");
@@ -865,7 +854,7 @@ size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity,
if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) return ERROR(dstSize_tooSmall);
/* dictionary header */
- MEM_writeLE32(header, ZSTD_DICT_MAGIC);
+ MEM_writeLE32(header, ZSTD_MAGIC_DICTIONARY);
{ U64 const randomID = XXH64(customDictContent, dictContentSize, 0);
U32 const compliantID = (randomID % ((1U<<31)-32768)) + 32768;
U32 const dictID = params.dictID ? params.dictID : compliantID;
@@ -917,7 +906,7 @@ size_t ZDICT_addEntropyTablesFromBuffer_advanced(void* dictBuffer, size_t dictCo
}
/* add dictionary header (after entropy tables) */
- MEM_writeLE32(dictBuffer, ZSTD_DICT_MAGIC);
+ MEM_writeLE32(dictBuffer, ZSTD_MAGIC_DICTIONARY);
{ U64 const randomID = XXH64((char*)dictBuffer + dictBufferCapacity - dictContentSize, dictContentSize, 0);
U32 const compliantID = (randomID % ((1U<<31)-32768)) + 32768;
U32 const dictID = params.dictID ? params.dictID : compliantID;
@@ -930,14 +919,14 @@ size_t ZDICT_addEntropyTablesFromBuffer_advanced(void* dictBuffer, size_t dictCo
}
-/*! ZDICT_trainFromBuffer_unsafe() :
+/*! ZDICT_trainFromBuffer_unsafe_legacy() :
* Warning : `samplesBuffer` must be followed by noisy guard band.
* @return : size of dictionary, or an error code which can be tested with ZDICT_isError()
*/
-size_t ZDICT_trainFromBuffer_unsafe(
+size_t ZDICT_trainFromBuffer_unsafe_legacy(
void* dictBuffer, size_t maxDictSize,
const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
- ZDICT_params_t params)
+ ZDICT_legacy_params_t params)
{
U32 const dictListSize = MAX(MAX(DICTLISTSIZE_DEFAULT, nbSamples), (U32)(maxDictSize/16));
dictItem* const dictList = (dictItem*)malloc(dictListSize * sizeof(*dictList));
@@ -946,7 +935,7 @@ size_t ZDICT_trainFromBuffer_unsafe(
size_t const targetDictSize = maxDictSize;
size_t const samplesBuffSize = ZDICT_totalSampleSize(samplesSizes, nbSamples);
size_t dictSize = 0;
- U32 const notificationLevel = params.notificationLevel;
+ U32 const notificationLevel = params.zParams.notificationLevel;
/* checks */
if (!dictList) return ERROR(memory_allocation);
@@ -957,13 +946,13 @@ size_t ZDICT_trainFromBuffer_unsafe(
ZDICT_initDictItem(dictList);
/* build dictionary */
- ZDICT_trainBuffer(dictList, dictListSize,
- samplesBuffer, samplesBuffSize,
- samplesSizes, nbSamples,
- minRep, notificationLevel);
+ ZDICT_trainBuffer_legacy(dictList, dictListSize,
+ samplesBuffer, samplesBuffSize,
+ samplesSizes, nbSamples,
+ minRep, notificationLevel);
/* display best matches */
- if (params.notificationLevel>= 3) {
+ if (params.zParams.notificationLevel>= 3) {
U32 const nb = MIN(25, dictList[0].pos);
U32 const dictContentSize = ZDICT_dictSize(dictList);
U32 u;
@@ -1026,7 +1015,7 @@ size_t ZDICT_trainFromBuffer_unsafe(
dictSize = ZDICT_addEntropyTablesFromBuffer_advanced(dictBuffer, dictContentSize, maxDictSize,
samplesBuffer, samplesSizes, nbSamples,
- params);
+ params.zParams);
}
/* clean up */
@@ -1037,9 +1026,9 @@ size_t ZDICT_trainFromBuffer_unsafe(
/* issue : samplesBuffer need to be followed by a noisy guard band.
* work around : duplicate the buffer, and add the noise */
-size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacity,
- const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
- ZDICT_params_t params)
+size_t ZDICT_trainFromBuffer_legacy(void* dictBuffer, size_t dictBufferCapacity,
+ const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
+ ZDICT_legacy_params_t params)
{
size_t result;
void* newBuff;
@@ -1052,10 +1041,9 @@ size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacit
memcpy(newBuff, samplesBuffer, sBuffSize);
ZDICT_fillNoise((char*)newBuff + sBuffSize, NOISELENGTH); /* guard band, for end of buffer condition */
- result = ZDICT_trainFromBuffer_unsafe(
- dictBuffer, dictBufferCapacity,
- newBuff, samplesSizes, nbSamples,
- params);
+ result =
+ ZDICT_trainFromBuffer_unsafe_legacy(dictBuffer, dictBufferCapacity, newBuff,
+ samplesSizes, nbSamples, params);
free(newBuff);
return result;
}
@@ -1064,11 +1052,13 @@ size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacit
size_t ZDICT_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples)
{
- ZDICT_params_t params;
+ ZDICT_cover_params_t params;
memset(&params, 0, sizeof(params));
- return ZDICT_trainFromBuffer_advanced(dictBuffer, dictBufferCapacity,
- samplesBuffer, samplesSizes, nbSamples,
- params);
+ params.d = 8;
+ params.steps = 4;
+ return ZDICT_optimizeTrainFromBuffer_cover(dictBuffer, dictBufferCapacity,
+ samplesBuffer, samplesSizes,
+ nbSamples, &params);
}
size_t ZDICT_addEntropyTablesFromBuffer(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity,
diff --git a/lib/dictBuilder/zdict.h b/lib/dictBuilder/zdict.h
index 9b53de3465276..7bfbb351a1ddf 100644
--- a/lib/dictBuilder/zdict.h
+++ b/lib/dictBuilder/zdict.h
@@ -20,10 +20,12 @@ extern "C" {
/* ===== ZDICTLIB_API : control library symbols visibility ===== */
-#if defined(__GNUC__) && (__GNUC__ >= 4)
-# define ZDICTLIB_VISIBILITY __attribute__ ((visibility ("default")))
-#else
-# define ZDICTLIB_VISIBILITY
+#ifndef ZDICTLIB_VISIBILITY
+# if defined(__GNUC__) && (__GNUC__ >= 4)
+# define ZDICTLIB_VISIBILITY __attribute__ ((visibility ("default")))
+# else
+# define ZDICTLIB_VISIBILITY
+# endif
#endif
#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1)
# define ZDICTLIB_API __declspec(dllexport) ZDICTLIB_VISIBILITY
@@ -34,18 +36,20 @@ extern "C" {
#endif
-/*! ZDICT_trainFromBuffer() :
- Train a dictionary from an array of samples.
- Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
- supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
- The resulting dictionary will be saved into `dictBuffer`.
- @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
- or an error code, which can be tested with ZDICT_isError().
- Tips : In general, a reasonable dictionary has a size of ~ 100 KB.
- It's obviously possible to target smaller or larger ones, just by specifying different `dictBufferCapacity`.
- In general, it's recommended to provide a few thousands samples, but this can vary a lot.
- It's recommended that total size of all samples be about ~x100 times the target size of dictionary.
-*/
+/*! ZDICT_trainFromBuffer():
+ * Train a dictionary from an array of samples.
+ * Uses ZDICT_optimizeTrainFromBuffer_cover() single-threaded, with d=8 and steps=4.
+ * Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
+ * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
+ * The resulting dictionary will be saved into `dictBuffer`.
+ * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
+ * or an error code, which can be tested with ZDICT_isError().
+ * Note: ZDICT_trainFromBuffer() requires about 9 bytes of memory for each input byte.
+ * Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
+ * It's obviously possible to target smaller or larger ones, just by specifying different `dictBufferCapacity`.
+ * In general, it's recommended to provide a few thousands samples, but this can vary a lot.
+ * It's recommended that total size of all samples be about ~x100 times the target size of dictionary.
+ */
ZDICTLIB_API size_t ZDICT_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples);
@@ -67,94 +71,78 @@ ZDICTLIB_API const char* ZDICT_getErrorName(size_t errorCode);
* ==================================================================================== */
typedef struct {
- unsigned selectivityLevel; /* 0 means default; larger => select more => larger dictionary */
int compressionLevel; /* 0 means default; target a specific zstd compression level */
unsigned notificationLevel; /* Write to stderr; 0 = none (default); 1 = errors; 2 = progression; 3 = details; 4 = debug; */
unsigned dictID; /* 0 means auto mode (32-bits random value); other : force dictID value */
- unsigned reserved[2]; /* reserved space for future parameters */
} ZDICT_params_t;
-
-/*! ZDICT_trainFromBuffer_advanced() :
- Same as ZDICT_trainFromBuffer() with control over more parameters.
- `parameters` is optional and can be provided with values set to 0 to mean "default".
- @return : size of dictionary stored into `dictBuffer` (<= `dictBufferSize`),
- or an error code, which can be tested by ZDICT_isError().
- note : ZDICT_trainFromBuffer_advanced() will send notifications into stderr if instructed to, using notificationLevel>0.
-*/
-ZDICTLIB_API size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacity,
- const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
- ZDICT_params_t parameters);
-
-/*! COVER_params_t :
- For all values 0 means default.
- k and d are the only required parameters.
-*/
+/*! ZDICT_cover_params_t:
+ * For all values 0 means default.
+ * k and d are the only required parameters.
+ */
typedef struct {
unsigned k; /* Segment size : constraint: 0 < k : Reasonable range [16, 2048+] */
unsigned d; /* dmer size : constraint: 0 < d <= k : Reasonable range [6, 16] */
unsigned steps; /* Number of steps : Only used for optimization : 0 means default (32) : Higher means more parameters checked */
-
unsigned nbThreads; /* Number of threads : constraint: 0 < nbThreads : 1 means single-threaded : Only used for optimization : Ignored if ZSTD_MULTITHREAD is not defined */
- unsigned notificationLevel; /* Write to stderr; 0 = none (default); 1 = errors; 2 = progression; 3 = details; 4 = debug; */
- unsigned dictID; /* 0 means auto mode (32-bits random value); other : force dictID value */
- int compressionLevel; /* 0 means default; target a specific zstd compression level */
-} COVER_params_t;
-
-
-/*! COVER_trainFromBuffer() :
- Train a dictionary from an array of samples using the COVER algorithm.
- Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
- supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
- The resulting dictionary will be saved into `dictBuffer`.
- @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
- or an error code, which can be tested with ZDICT_isError().
- Note : COVER_trainFromBuffer() requires about 9 bytes of memory for each input byte.
- Tips : In general, a reasonable dictionary has a size of ~ 100 KB.
- It's obviously possible to target smaller or larger ones, just by specifying different `dictBufferCapacity`.
- In general, it's recommended to provide a few thousands samples, but this can vary a lot.
- It's recommended that total size of all samples be about ~x100 times the target size of dictionary.
-*/
-ZDICTLIB_API size_t COVER_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
- const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
- COVER_params_t parameters);
-
-/*! COVER_optimizeTrainFromBuffer() :
- The same requirements as above hold for all the parameters except `parameters`.
- This function tries many parameter combinations and picks the best parameters.
- `*parameters` is filled with the best parameters found, and the dictionary
- constructed with those parameters is stored in `dictBuffer`.
-
- All of the parameters d, k, steps are optional.
- If d is non-zero then we don't check multiple values of d, otherwise we check d = {6, 8, 10, 12, 14, 16}.
- if steps is zero it defaults to its default value.
- If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [16, 2048].
-
- @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
- or an error code, which can be tested with ZDICT_isError().
- On success `*parameters` contains the parameters selected.
- Note : COVER_optimizeTrainFromBuffer() requires about 8 bytes of memory for each input byte and additionally another 5 bytes of memory for each byte of memory for each thread.
-*/
-ZDICTLIB_API size_t COVER_optimizeTrainFromBuffer(void* dictBuffer, size_t dictBufferCapacity,
- const void* samplesBuffer, const size_t *samplesSizes, unsigned nbSamples,
- COVER_params_t *parameters);
-
-/*! ZDICT_finalizeDictionary() :
-
- Given a custom content as a basis for dictionary, and a set of samples,
- finalize dictionary by adding headers and statistics.
-
- Samples must be stored concatenated in a flat buffer `samplesBuffer`,
- supplied with an array of sizes `samplesSizes`, providing the size of each sample in order.
-
- dictContentSize must be >= ZDICT_CONTENTSIZE_MIN bytes.
- maxDictSize must be >= dictContentSize, and must be >= ZDICT_DICTSIZE_MIN bytes.
-
- @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`),
- or an error code, which can be tested by ZDICT_isError().
- note : ZDICT_finalizeDictionary() will push notifications into stderr if instructed to, using notificationLevel>0.
- note 2 : dictBuffer and dictContent can overlap
-*/
+ ZDICT_params_t zParams;
+} ZDICT_cover_params_t;
+
+
+/*! ZDICT_trainFromBuffer_cover():
+ * Train a dictionary from an array of samples using the COVER algorithm.
+ * Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
+ * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
+ * The resulting dictionary will be saved into `dictBuffer`.
+ * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
+ * or an error code, which can be tested with ZDICT_isError().
+ * Note: ZDICT_trainFromBuffer_cover() requires about 9 bytes of memory for each input byte.
+ * Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
+ * It's obviously possible to target smaller or larger ones, just by specifying different `dictBufferCapacity`.
+ * In general, it's recommended to provide a few thousands samples, but this can vary a lot.
+ * It's recommended that total size of all samples be about ~x100 times the target size of dictionary.
+ */
+ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover(
+ void *dictBuffer, size_t dictBufferCapacity, const void *samplesBuffer,
+ const size_t *samplesSizes, unsigned nbSamples,
+ ZDICT_cover_params_t parameters);
+
+/*! ZDICT_optimizeTrainFromBuffer_cover():
+ * The same requirements as above hold for all the parameters except `parameters`.
+ * This function tries many parameter combinations and picks the best parameters.
+ * `*parameters` is filled with the best parameters found, and the dictionary
+ * constructed with those parameters is stored in `dictBuffer`.
+ *
+ * All of the parameters d, k, steps are optional.
+ * If d is non-zero then we don't check multiple values of d, otherwise we check d = {6, 8, 10, 12, 14, 16}.
+ * if steps is zero it defaults to its default value.
+ * If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [16, 2048].
+ *
+ * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
+ * or an error code, which can be tested with ZDICT_isError().
+ * On success `*parameters` contains the parameters selected.
+ * Note: ZDICT_optimizeTrainFromBuffer_cover() requires about 8 bytes of memory for each input byte and additionally another 5 bytes of memory for each byte of memory for each thread.
+ */
+ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
+ void *dictBuffer, size_t dictBufferCapacity, const void *samplesBuffer,
+ const size_t *samplesSizes, unsigned nbSamples,
+ ZDICT_cover_params_t *parameters);
+
+/*! ZDICT_finalizeDictionary():
+ * Given a custom content as a basis for dictionary, and a set of samples,
+ * finalize dictionary by adding headers and statistics.
+ *
+ * Samples must be stored concatenated in a flat buffer `samplesBuffer`,
+ * supplied with an array of sizes `samplesSizes`, providing the size of each sample in order.
+ *
+ * dictContentSize must be >= ZDICT_CONTENTSIZE_MIN bytes.
+ * maxDictSize must be >= dictContentSize, and must be >= ZDICT_DICTSIZE_MIN bytes.
+ *
+ * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`),
+ * or an error code, which can be tested by ZDICT_isError().
+ * Note: ZDICT_finalizeDictionary() will push notifications into stderr if instructed to, using notificationLevel>0.
+ * Note 2: dictBuffer and dictContent can overlap
+ */
#define ZDICT_CONTENTSIZE_MIN 128
#define ZDICT_DICTSIZE_MIN 256
ZDICTLIB_API size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity,
@@ -162,7 +150,28 @@ ZDICTLIB_API size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBuffer
const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples,
ZDICT_params_t parameters);
-
+typedef struct {
+ unsigned selectivityLevel; /* 0 means default; larger => select more => larger dictionary */
+ ZDICT_params_t zParams;
+} ZDICT_legacy_params_t;
+
+/*! ZDICT_trainFromBuffer_legacy():
+ * Train a dictionary from an array of samples.
+ * Samples must be stored concatenated in a single flat buffer `samplesBuffer`,
+ * supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order.
+ * The resulting dictionary will be saved into `dictBuffer`.
+ * `parameters` is optional and can be provided with values set to 0 to mean "default".
+ * @return: size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`)
+ * or an error code, which can be tested with ZDICT_isError().
+ * Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
+ * It's obviously possible to target smaller or larger ones, just by specifying different `dictBufferCapacity`.
+ * In general, it's recommended to provide a few thousands samples, but this can vary a lot.
+ * It's recommended that total size of all samples be about ~x100 times the target size of dictionary.
+ * Note: ZDICT_trainFromBuffer_legacy() will send notifications into stderr if instructed to, using notificationLevel>0.
+ */
+ZDICTLIB_API size_t ZDICT_trainFromBuffer_legacy(
+ void *dictBuffer, size_t dictBufferCapacity, const void *samplesBuffer,
+ const size_t *samplesSizes, unsigned nbSamples, ZDICT_legacy_params_t parameters);
/* Deprecation warnings */
/* It is generally possible to disable deprecation warnings from compiler,
diff --git a/lib/legacy/zstd_v04.c b/lib/legacy/zstd_v04.c
index 1a29da92d1e84..8b8e23cb09cb4 100644
--- a/lib/legacy/zstd_v04.c
+++ b/lib/legacy/zstd_v04.c
@@ -816,13 +816,13 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si
bitD->bitContainer = *(const BYTE*)(bitD->start);
switch(srcSize)
{
- case 7: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[6]) << (sizeof(size_t)*8 - 16);
- case 6: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[5]) << (sizeof(size_t)*8 - 24);
- case 5: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[4]) << (sizeof(size_t)*8 - 32);
- case 4: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[3]) << 24;
- case 3: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[2]) << 16;
- case 2: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[1]) << 8;
- default:;
+ case 7: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[6]) << (sizeof(size_t)*8 - 16);/* fall-through */
+ case 6: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[5]) << (sizeof(size_t)*8 - 24);/* fall-through */
+ case 5: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[4]) << (sizeof(size_t)*8 - 32);/* fall-through */
+ case 4: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[3]) << 24; /* fall-through */
+ case 3: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[2]) << 16; /* fall-through */
+ case 2: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[1]) << 8; /* fall-through */
+ default: break;
}
contain32 = ((const BYTE*)srcBuffer)[srcSize-1];
if (contain32 == 0) return ERROR(GENERIC); /* endMark not present */
@@ -3665,7 +3665,7 @@ static size_t ZBUFF_decompressContinue(ZBUFF_DCtx* zbc, void* dst, size_t* maxDs
break;
}
zbc->stage = ZBUFFds_read;
-
+ /* fall-through */
case ZBUFFds_read:
{
size_t neededInSize = ZSTD_nextSrcSizeToDecompress(zbc->zc);
@@ -3691,7 +3691,7 @@ static size_t ZBUFF_decompressContinue(ZBUFF_DCtx* zbc, void* dst, size_t* maxDs
if (ip==iend) { notDone = 0; break; } /* no more input */
zbc->stage = ZBUFFds_load;
}
-
+ /* fall-through */
case ZBUFFds_load:
{
size_t neededInSize = ZSTD_nextSrcSizeToDecompress(zbc->zc);
@@ -3711,9 +3711,10 @@ static size_t ZBUFF_decompressContinue(ZBUFF_DCtx* zbc, void* dst, size_t* maxDs
if (!decodedSize) { zbc->stage = ZBUFFds_read; break; } /* this was just a header */
zbc->outEnd = zbc->outStart + decodedSize;
zbc->stage = ZBUFFds_flush;
- // break; /* ZBUFFds_flush follows */
+ /* ZBUFFds_flush follows */
}
}
+ /* fall-through */
case ZBUFFds_flush:
{
size_t toFlushSize = zbc->outEnd - zbc->outStart;
diff --git a/lib/legacy/zstd_v05.c b/lib/legacy/zstd_v05.c
index 674f5b0e4a8e7..e929618a3bf52 100644
--- a/lib/legacy/zstd_v05.c
+++ b/lib/legacy/zstd_v05.c
@@ -326,13 +326,6 @@ size_t ZSTDv05_decompress_usingPreparedDCtx(
* Streaming functions (direct mode)
****************************************/
size_t ZSTDv05_decompressBegin(ZSTDv05_DCtx* dctx);
-size_t ZSTDv05_decompressBegin_usingDict(ZSTDv05_DCtx* dctx, const void* dict, size_t dictSize);
-void ZSTDv05_copyDCtx(ZSTDv05_DCtx* dctx, const ZSTDv05_DCtx* preparedDCtx);
-
-size_t ZSTDv05_getFrameParams(ZSTDv05_parameters* params, const void* src, size_t srcSize);
-
-size_t ZSTDv05_nextSrcSizeToDecompress(ZSTDv05_DCtx* dctx);
-size_t ZSTDv05_decompressContinue(ZSTDv05_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
/*
Streaming decompression, direct mode (bufferless)
@@ -818,13 +811,13 @@ MEM_STATIC size_t BITv05_initDStream(BITv05_DStream_t* bitD, const void* srcBuff
bitD->bitContainer = *(const BYTE*)(bitD->start);
switch(srcSize)
{
- case 7: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[6]) << (sizeof(size_t)*8 - 16);
- case 6: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[5]) << (sizeof(size_t)*8 - 24);
- case 5: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[4]) << (sizeof(size_t)*8 - 32);
- case 4: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[3]) << 24;
- case 3: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[2]) << 16;
- case 2: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[1]) << 8;
- default:;
+ case 7: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[6]) << (sizeof(size_t)*8 - 16);/* fall-through */
+ case 6: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[5]) << (sizeof(size_t)*8 - 24);/* fall-through */
+ case 5: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[4]) << (sizeof(size_t)*8 - 32);/* fall-through */
+ case 4: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[3]) << 24; /* fall-through */
+ case 3: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[2]) << 16; /* fall-through */
+ case 2: bitD->bitContainer += (size_t)(((const BYTE*)(bitD->start))[1]) << 8; /* fall-through */
+ default: break;
}
contain32 = ((const BYTE*)srcBuffer)[srcSize-1];
if (contain32 == 0) return ERROR(GENERIC); /* endMark not present */
@@ -3955,7 +3948,7 @@ size_t ZBUFFv05_decompressContinue(ZBUFFv05_DCtx* zbc, void* dst, size_t* maxDst
zbc->stage = ZBUFFv05ds_decodeHeader;
break;
}
-
+ /* fall-through */
case ZBUFFv05ds_loadHeader:
/* complete header from src */
{
@@ -3973,7 +3966,7 @@ size_t ZBUFFv05_decompressContinue(ZBUFFv05_DCtx* zbc, void* dst, size_t* maxDst
}
// zbc->stage = ZBUFFv05ds_decodeHeader; break; /* useless : stage follows */
}
-
+ /* fall-through */
case ZBUFFv05ds_decodeHeader:
/* apply header to create / resize buffers */
{
@@ -4000,7 +3993,7 @@ size_t ZBUFFv05_decompressContinue(ZBUFFv05_DCtx* zbc, void* dst, size_t* maxDst
break;
}
zbc->stage = ZBUFFv05ds_read;
-
+ /* fall-through */
case ZBUFFv05ds_read:
{
size_t neededInSize = ZSTDv05_nextSrcSizeToDecompress(zbc->zc);
@@ -4024,7 +4017,7 @@ size_t ZBUFFv05_decompressContinue(ZBUFFv05_DCtx* zbc, void* dst, size_t* maxDst
if (ip==iend) { notDone = 0; break; } /* no more input */
zbc->stage = ZBUFFv05ds_load;
}
-
+ /* fall-through */
case ZBUFFv05ds_load:
{
size_t neededInSize = ZSTDv05_nextSrcSizeToDecompress(zbc->zc);
@@ -4045,7 +4038,9 @@ size_t ZBUFFv05_decompressContinue(ZBUFFv05_DCtx* zbc, void* dst, size_t* maxDst
zbc->outEnd = zbc->outStart + decodedSize;
zbc->stage = ZBUFFv05ds_flush;
// break; /* ZBUFFv05ds_flush follows */
- } }
+ }
+ }
+ /* fall-through */
case ZBUFFv05ds_flush:
{
size_t toFlushSize = zbc->outEnd - zbc->outStart;
diff --git a/lib/legacy/zstd_v06.c b/lib/legacy/zstd_v06.c
index ad8c4cd3186d0..26f0929da6fd4 100644
--- a/lib/legacy/zstd_v06.c
+++ b/lib/legacy/zstd_v06.c
@@ -910,13 +910,13 @@ MEM_STATIC size_t BITv06_initDStream(BITv06_DStream_t* bitD, const void* srcBuff
bitD->bitContainer = *(const BYTE*)(bitD->start);
switch(srcSize)
{
- case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
- case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
- case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
- case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
- case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
- case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8;
- default:;
+ case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);/* fall-through */
+ case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);/* fall-through */
+ case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);/* fall-through */
+ case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24; /* fall-through */
+ case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16; /* fall-through */
+ case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8; /* fall-through */
+ default: break;
}
{ BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
if (lastByte == 0) return ERROR(GENERIC); /* endMark not present */
@@ -3789,7 +3789,7 @@ size_t ZSTDv06_decompressContinue(ZSTDv06_DCtx* dctx, void* dst, size_t dstCapac
return 0;
}
dctx->expected = 0; /* not necessary to copy more */
-
+ /* fall-through */
case ZSTDds_decodeFrameHeader:
{ size_t result;
memcpy(dctx->headerBuffer + ZSTDv06_frameHeaderSize_min, src, dctx->expected);
@@ -4116,7 +4116,7 @@ size_t ZBUFFv06_decompressContinue(ZBUFFv06_DCtx* zbd,
if (zbd->outBuff == NULL) return ERROR(memory_allocation);
} } }
zbd->stage = ZBUFFds_read;
-
+ /* fall-through */
case ZBUFFds_read:
{ size_t const neededInSize = ZSTDv06_nextSrcSizeToDecompress(zbd->zd);
if (neededInSize==0) { /* end of frame */
@@ -4138,7 +4138,7 @@ size_t ZBUFFv06_decompressContinue(ZBUFFv06_DCtx* zbd,
if (ip==iend) { notDone = 0; break; } /* no more input */
zbd->stage = ZBUFFds_load;
}
-
+ /* fall-through */
case ZBUFFds_load:
{ size_t const neededInSize = ZSTDv06_nextSrcSizeToDecompress(zbd->zd);
size_t const toLoad = neededInSize - zbd->inPos; /* should always be <= remaining space within inBuff */
@@ -4159,8 +4159,9 @@ size_t ZBUFFv06_decompressContinue(ZBUFFv06_DCtx* zbd,
zbd->outEnd = zbd->outStart + decodedSize;
zbd->stage = ZBUFFds_flush;
// break; /* ZBUFFds_flush follows */
- } }
-
+ }
+ }
+ /* fall-through */
case ZBUFFds_flush:
{ size_t const toFlushSize = zbd->outEnd - zbd->outStart;
size_t const flushedSize = ZBUFFv06_limitCopy(op, oend-op, zbd->outBuff + zbd->outStart, toFlushSize);
diff --git a/lib/legacy/zstd_v07.c b/lib/legacy/zstd_v07.c
index a54ad0ffdba92..6669b71cea40b 100644
--- a/lib/legacy/zstd_v07.c
+++ b/lib/legacy/zstd_v07.c
@@ -580,13 +580,13 @@ MEM_STATIC size_t BITv07_initDStream(BITv07_DStream_t* bitD, const void* srcBuff
bitD->bitContainer = *(const BYTE*)(bitD->start);
switch(srcSize)
{
- case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
- case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
- case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
- case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
- case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
- case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8;
- default:;
+ case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);/* fall-through */
+ case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);/* fall-through */
+ case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);/* fall-through */
+ case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24; /* fall-through */
+ case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16; /* fall-through */
+ case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8; /* fall-through */
+ default: break;
}
{ BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
bitD->bitsConsumed = lastByte ? 8 - BITv07_highbit32(lastByte) : 0;
@@ -2920,8 +2920,6 @@ typedef struct {
void ZSTDv07_seqToCodes(const seqStore_t* seqStorePtr, size_t const nbSeq);
/* custom memory allocation functions */
-void* ZSTDv07_defaultAllocFunction(void* opaque, size_t size);
-void ZSTDv07_defaultFreeFunction(void* opaque, void* address);
static const ZSTDv07_customMem defaultCustomMem = { ZSTDv07_defaultAllocFunction, ZSTDv07_defaultFreeFunction, NULL };
#endif /* ZSTDv07_CCOMMON_H_MODULE */
@@ -4047,7 +4045,7 @@ size_t ZSTDv07_decompressContinue(ZSTDv07_DCtx* dctx, void* dst, size_t dstCapac
return 0;
}
dctx->expected = 0; /* not necessary to copy more */
-
+ /* fall-through */
case ZSTDds_decodeFrameHeader:
{ size_t result;
memcpy(dctx->headerBuffer + ZSTDv07_frameHeaderSize_min, src, dctx->expected);
@@ -4494,7 +4492,7 @@ size_t ZBUFFv07_decompressContinue(ZBUFFv07_DCtx* zbd,
} } }
zbd->stage = ZBUFFds_read;
/* pass-through */
-
+ /* fall-through */
case ZBUFFds_read:
{ size_t const neededInSize = ZSTDv07_nextSrcSizeToDecompress(zbd->zd);
if (neededInSize==0) { /* end of frame */
@@ -4517,7 +4515,7 @@ size_t ZBUFFv07_decompressContinue(ZBUFFv07_DCtx* zbd,
if (ip==iend) { notDone = 0; break; } /* no more input */
zbd->stage = ZBUFFds_load;
}
-
+ /* fall-through */
case ZBUFFds_load:
{ size_t const neededInSize = ZSTDv07_nextSrcSizeToDecompress(zbd->zd);
size_t const toLoad = neededInSize - zbd->inPos; /* should always be <= remaining space within inBuff */
@@ -4540,8 +4538,9 @@ size_t ZBUFFv07_decompressContinue(ZBUFFv07_DCtx* zbd,
zbd->stage = ZBUFFds_flush;
/* break; */
/* pass-through */
- } }
-
+ }
+ }
+ /* fall-through */
case ZBUFFds_flush:
{ size_t const toFlushSize = zbd->outEnd - zbd->outStart;
size_t const flushedSize = ZBUFFv07_limitCopy(op, oend-op, zbd->outBuff + zbd->outStart, toFlushSize);
diff --git a/lib/zstd.h b/lib/zstd.h
index f8050c1361044..58e9a5606db8e 100644
--- a/lib/zstd.h
+++ b/lib/zstd.h
@@ -19,10 +19,12 @@ extern "C" {
/* ===== ZSTDLIB_API : control library symbols visibility ===== */
-#if defined(__GNUC__) && (__GNUC__ >= 4)
-# define ZSTDLIB_VISIBILITY __attribute__ ((visibility ("default")))
-#else
-# define ZSTDLIB_VISIBILITY
+#ifndef ZSTDLIB_VISIBILITY
+# if defined(__GNUC__) && (__GNUC__ >= 4)
+# define ZSTDLIB_VISIBILITY __attribute__ ((visibility ("default")))
+# else
+# define ZSTDLIB_VISIBILITY
+# endif
#endif
#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1)
# define ZSTDLIB_API __declspec(dllexport) ZSTDLIB_VISIBILITY
@@ -36,35 +38,37 @@ extern "C" {
/*******************************************************************************************************
Introduction
- zstd, short for Zstandard, is a fast lossless compression algorithm, targeting real-time compression scenarios
- at zlib-level and better compression ratios. The zstd compression library provides in-memory compression and
- decompression functions. The library supports compression levels from 1 up to ZSTD_maxCLevel() which is 22.
+ zstd, short for Zstandard, is a fast lossless compression algorithm,
+ targeting real-time compression scenarios at zlib-level and better compression ratios.
+ The zstd compression library provides in-memory compression and decompression functions.
+ The library supports compression levels from 1 up to ZSTD_maxCLevel() which is currently 22.
Levels >= 20, labeled `--ultra`, should be used with caution, as they require more memory.
Compression can be done in:
- a single step (described as Simple API)
- a single step, reusing a context (described as Explicit memory management)
- unbounded multiple steps (described as Streaming compression)
- The compression ratio achievable on small data can be highly improved using compression with a dictionary in:
+ The compression ratio achievable on small data can be highly improved using a dictionary in:
- a single step (described as Simple dictionary API)
- a single step, reusing a dictionary (described as Fast dictionary API)
Advanced experimental functions can be accessed using #define ZSTD_STATIC_LINKING_ONLY before including zstd.h.
- These APIs shall never be used with a dynamic library.
+ Advanced experimental APIs shall never be used with a dynamic library.
They are not "stable", their definition may change in the future. Only static linking is allowed.
*********************************************************************************************************/
/*------ Version ------*/
#define ZSTD_VERSION_MAJOR 1
-#define ZSTD_VERSION_MINOR 2
+#define ZSTD_VERSION_MINOR 3
#define ZSTD_VERSION_RELEASE 0
+#define ZSTD_VERSION_NUMBER (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE)
+ZSTDLIB_API unsigned ZSTD_versionNumber(void); /**< useful to check dll version */
+
#define ZSTD_LIB_VERSION ZSTD_VERSION_MAJOR.ZSTD_VERSION_MINOR.ZSTD_VERSION_RELEASE
#define ZSTD_QUOTE(str) #str
#define ZSTD_EXPAND_AND_QUOTE(str) ZSTD_QUOTE(str)
#define ZSTD_VERSION_STRING ZSTD_EXPAND_AND_QUOTE(ZSTD_LIB_VERSION)
-
-#define ZSTD_VERSION_NUMBER (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE)
-ZSTDLIB_API unsigned ZSTD_versionNumber(void); /**< library version number; to be used when checking dll version */
+ZSTDLIB_API const char* ZSTD_versionString(void); /* v1.3.0 */
/***************************************
@@ -81,38 +85,48 @@ ZSTDLIB_API size_t ZSTD_compress( void* dst, size_t dstCapacity,
/*! ZSTD_decompress() :
* `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames.
- * `dstCapacity` is an upper bound of originalSize.
+ * `dstCapacity` is an upper bound of originalSize to regenerate.
* If user cannot imply a maximum upper bound, it's better to use streaming mode to decompress data.
* @return : the number of bytes decompressed into `dst` (<= `dstCapacity`),
* or an errorCode if it fails (which can be tested using ZSTD_isError()). */
ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity,
const void* src, size_t compressedSize);
-/*! ZSTD_getDecompressedSize() :
- * NOTE: This function is planned to be obsolete, in favour of ZSTD_getFrameContentSize.
- * ZSTD_getFrameContentSize functions the same way, returning the decompressed size of a single
- * frame, but distinguishes empty frames from frames with an unknown size, or errors.
- *
- * Additionally, ZSTD_findDecompressedSize can be used instead. It can handle multiple
- * concatenated frames in one buffer, and so is more general.
- * As a result however, it requires more computation and entire frames to be passed to it,
- * as opposed to ZSTD_getFrameContentSize which requires only a single frame's header.
- *
- * 'src' is the start of a zstd compressed frame.
- * @return : content size to be decompressed, as a 64-bits value _if known_, 0 otherwise.
- * note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode.
- * When `return==0`, data to decompress could be any size.
+/*! ZSTD_getFrameContentSize() : v1.3.0
+ * `src` should point to the start of a ZSTD encoded frame.
+ * `srcSize` must be at least as large as the frame header.
+ * hint : any size >= `ZSTD_frameHeaderSize_max` is large enough.
+ * @return : - decompressed size of the frame in `src`, if known
+ * - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined
+ * - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small)
+ * note 1 : a 0 return value means the frame is valid but "empty".
+ * note 2 : decompressed size is an optional field, it may not be present, typically in streaming mode.
+ * When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size.
* In which case, it's necessary to use streaming mode to decompress data.
- * Optionally, application can still use ZSTD_decompress() while relying on implied limits.
- * (For example, data may be necessarily cut into blocks <= 16 KB).
- * note 2 : decompressed size is always present when compression is done with ZSTD_compress()
- * note 3 : decompressed size can be very large (64-bits value),
+ * Optionally, application can rely on some implicit limit,
+ * as ZSTD_decompress() only needs an upper bound of decompressed size.
+ * (For example, data could be necessarily cut into blocks <= 16 KB).
+ * note 3 : decompressed size is always present when compression is done with ZSTD_compress()
+ * note 4 : decompressed size can be very large (64-bits value),
* potentially larger than what local system can handle as a single memory segment.
* In which case, it's necessary to use streaming mode to decompress data.
- * note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified.
- * Always ensure result fits within application's authorized limits.
+ * note 5 : If source is untrusted, decompressed size could be wrong or intentionally modified.
+ * Always ensure return value fits within application's authorized limits.
* Each application can set its own limits.
- * note 5 : when `return==0`, if precise failure cause is needed, use ZSTD_getFrameParams() to know more. */
+ * note 6 : This function replaces ZSTD_getDecompressedSize() */
+#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1)
+#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2)
+ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize);
+
+/*! ZSTD_getDecompressedSize() :
+ * NOTE: This function is now obsolete, in favor of ZSTD_getFrameContentSize().
+ * Both functions work the same way,
+ * but ZSTD_getDecompressedSize() blends
+ * "empty", "unknown" and "error" results in the same return value (0),
+ * while ZSTD_getFrameContentSize() distinguishes them.
+ *
+ * 'src' is the start of a zstd compressed frame.
+ * @return : content size to be decompressed, as a 64-bits value _if known and not empty_, 0 otherwise. */
ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize);
@@ -137,29 +151,35 @@ ZSTDLIB_API size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx);
/*! ZSTD_compressCCtx() :
* Same as ZSTD_compress(), requires an allocated ZSTD_CCtx (see ZSTD_createCCtx()). */
-ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize, int compressionLevel);
+ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* ctx,
+ void* dst, size_t dstCapacity,
+ const void* src, size_t srcSize,
+ int compressionLevel);
/*= Decompression context
* When decompressing many times,
- * it is recommended to allocate a context just once, and re-use it for each successive compression operation.
+ * it is recommended to allocate a context only once,
+ * and re-use it for each successive compression operation.
* This will make workload friendlier for system's memory.
- * Use one context per thread for parallel execution in multi-threaded environments. */
+ * Use one context per thread for parallel execution. */
typedef struct ZSTD_DCtx_s ZSTD_DCtx;
ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx(void);
ZSTDLIB_API size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx);
/*! ZSTD_decompressDCtx() :
- * Same as ZSTD_decompress(), requires an allocated ZSTD_DCtx (see ZSTD_createDCtx()). */
-ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* ctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+ * Same as ZSTD_decompress(), requires an allocated ZSTD_DCtx (see ZSTD_createDCtx()) */
+ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* ctx,
+ void* dst, size_t dstCapacity,
+ const void* src, size_t srcSize);
/**************************
* Simple dictionary API
***************************/
/*! ZSTD_compress_usingDict() :
-* Compression using a predefined Dictionary (see dictBuilder/zdict.h).
-* Note : This function loads the dictionary, resulting in significant startup delay.
-* Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
+ * Compression using a predefined Dictionary (see dictBuilder/zdict.h).
+ * Note : This function loads the dictionary, resulting in significant startup delay.
+ * Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
@@ -167,30 +187,31 @@ ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
int compressionLevel);
/*! ZSTD_decompress_usingDict() :
-* Decompression using a predefined Dictionary (see dictBuilder/zdict.h).
-* Dictionary must be identical to the one used during compression.
-* Note : This function loads the dictionary, resulting in significant startup delay.
-* Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
+ * Decompression using a predefined Dictionary (see dictBuilder/zdict.h).
+ * Dictionary must be identical to the one used during compression.
+ * Note : This function loads the dictionary, resulting in significant startup delay.
+ * Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
const void* dict,size_t dictSize);
-/****************************
-* Fast dictionary API
-****************************/
+/**********************************
+ * Bulk processing dictionary API
+ *********************************/
typedef struct ZSTD_CDict_s ZSTD_CDict;
/*! ZSTD_createCDict() :
-* When compressing multiple messages / blocks with the same dictionary, it's recommended to load it just once.
-* ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup delay.
-* ZSTD_CDict can be created once and used by multiple threads concurrently, as its usage is read-only.
-* `dictBuffer` can be released after ZSTD_CDict creation, as its content is copied within CDict */
-ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, int compressionLevel);
+ * When compressing multiple messages / blocks with the same dictionary, it's recommended to load it just once.
+ * ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup delay.
+ * ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only.
+ * `dictBuffer` can be released after ZSTD_CDict creation, since its content is copied within CDict */
+ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize,
+ int compressionLevel);
/*! ZSTD_freeCDict() :
-* Function frees memory allocated by ZSTD_createCDict(). */
+ * Function frees memory allocated by ZSTD_createCDict(). */
ZSTDLIB_API size_t ZSTD_freeCDict(ZSTD_CDict* CDict);
/*! ZSTD_compress_usingCDict() :
@@ -207,17 +228,17 @@ ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
typedef struct ZSTD_DDict_s ZSTD_DDict;
/*! ZSTD_createDDict() :
-* Create a digested dictionary, ready to start decompression operation without startup delay.
-* dictBuffer can be released after DDict creation, as its content is copied inside DDict */
+ * Create a digested dictionary, ready to start decompression operation without startup delay.
+ * dictBuffer can be released after DDict creation, as its content is copied inside DDict */
ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize);
/*! ZSTD_freeDDict() :
-* Function frees memory allocated with ZSTD_createDDict() */
+ * Function frees memory allocated with ZSTD_createDDict() */
ZSTDLIB_API size_t ZSTD_freeDDict(ZSTD_DDict* ddict);
/*! ZSTD_decompress_usingDDict() :
-* Decompression using a digested Dictionary.
-* Faster startup than ZSTD_decompress_usingDict(), recommended when same dictionary is used multiple times. */
+ * Decompression using a digested Dictionary.
+ * Faster startup than ZSTD_decompress_usingDict(), recommended when same dictionary is used multiple times. */
ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
@@ -274,14 +295,17 @@ typedef struct ZSTD_outBuffer_s {
* ZSTD_endStream() instructs to finish a frame.
* It will perform a flush and write frame epilogue.
* The epilogue is required for decoders to consider a frame completed.
-* Similar to ZSTD_flushStream(), it may not be able to flush the full content if `output->size` is too small.
+* ZSTD_endStream() may not be able to flush full data if `output->size` is too small.
* In which case, call again ZSTD_endStream() to complete the flush.
-* @return : nb of bytes still present within internal buffer (0 if it's empty, hence compression completed)
+* @return : 0 if frame fully completed and fully flushed,
+ or >0 if some data is still present within internal buffer
+ (value is minimum size estimation for remaining data to flush, but it could be more)
* or an error code, which can be tested using ZSTD_isError().
*
* *******************************************************************/
-typedef struct ZSTD_CStream_s ZSTD_CStream;
+typedef ZSTD_CCtx ZSTD_CStream; /**< CCtx and CStream are now effectively same object (>= v1.3.0) */
+ /* Continue to distinguish them for compatibility with versions <= v1.2.0 */
/*===== ZSTD_CStream management functions =====*/
ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void);
ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs);
@@ -319,7 +343,8 @@ ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /**< recommended size for output
* The return value is a suggested next input size (a hint to improve latency) that will never load more than the current frame.
* *******************************************************************************/
-typedef struct ZSTD_DStream_s ZSTD_DStream;
+typedef ZSTD_DCtx ZSTD_DStream; /**< DCtx and DStream are now effectively same object (>= v1.3.0) */
+ /* Continue to distinguish them for compatibility with versions <= v1.2.0 */
/*===== ZSTD_DStream management functions =====*/
ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void);
ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds);
@@ -334,23 +359,22 @@ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output
#endif /* ZSTD_H_235446 */
-#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY)
-#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY
/****************************************************************************************
* START OF ADVANCED AND EXPERIMENTAL FUNCTIONS
* The definitions in this section are considered experimental.
- * They should never be used with a dynamic library, as they may change in the future.
- * They are provided for advanced usages.
+ * They should never be used with a dynamic library, as prototypes may change in the future.
+ * They are provided for advanced scenarios.
* Use them only in association with static linking.
* ***************************************************************************************/
+#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY)
+#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY
+
/* --- Constants ---*/
#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */
#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U
-
-#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1)
-#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2)
+#define ZSTD_MAGIC_DICTIONARY 0xEC30A437 /* v0.7+ */
#define ZSTD_WINDOWLOG_MAX_32 27
#define ZSTD_WINDOWLOG_MAX_64 27
@@ -370,14 +394,15 @@ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output
#define ZSTD_FRAMEHEADERSIZE_MAX 18 /* for static allocation */
#define ZSTD_FRAMEHEADERSIZE_MIN 6
-static const size_t ZSTD_frameHeaderSize_prefix = 5;
-static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN;
+static const size_t ZSTD_frameHeaderSize_prefix = 5; /* minimum input size to know frame header size */
static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX;
+static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN;
static const size_t ZSTD_skippableHeaderSize = 8; /* magic number + skippable frame length */
/*--- Advanced types ---*/
-typedef enum { ZSTD_fast, ZSTD_dfast, ZSTD_greedy, ZSTD_lazy, ZSTD_lazy2, ZSTD_btlazy2, ZSTD_btopt, ZSTD_btopt2 } ZSTD_strategy; /* from faster to stronger */
+typedef enum { ZSTD_fast=1, ZSTD_dfast, ZSTD_greedy, ZSTD_lazy, ZSTD_lazy2,
+ ZSTD_btlazy2, ZSTD_btopt, ZSTD_btultra } ZSTD_strategy; /* from faster to stronger */
typedef struct {
unsigned windowLog; /**< largest match distance : larger == more compression, more memory needed during decompression */
@@ -400,76 +425,141 @@ typedef struct {
ZSTD_frameParameters fParams;
} ZSTD_parameters;
+typedef struct {
+ unsigned long long frameContentSize;
+ size_t windowSize;
+ unsigned dictID;
+ unsigned checksumFlag;
+} ZSTD_frameHeader;
+
/*= Custom memory allocation functions */
typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size);
typedef void (*ZSTD_freeFunction) (void* opaque, void* address);
typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem;
+/* use this constant to defer to stdlib's functions */
+static const ZSTD_customMem ZSTD_defaultCMem = { NULL, NULL, NULL };
+
/***************************************
-* Compressed size functions
+* Frame size functions
***************************************/
/*! ZSTD_findFrameCompressedSize() :
* `src` should point to the start of a ZSTD encoded frame or skippable frame
* `srcSize` must be at least as large as the frame
- * @return : the compressed size of the frame pointed to by `src`, suitable to pass to
- * `ZSTD_decompress` or similar, or an error code if given invalid input. */
+ * @return : the compressed size of the first frame starting at `src`,
+ * suitable to pass to `ZSTD_decompress` or similar,
+ * or an error code if input is invalid */
ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize);
+/*! ZSTD_findDecompressedSize() :
+ * `src` should point the start of a series of ZSTD encoded and/or skippable frames
+ * `srcSize` must be the _exact_ size of this series
+ * (i.e. there should be a frame boundary exactly at `srcSize` bytes after `src`)
+ * @return : - decompressed size of all data in all successive frames
+ * - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN
+ * - if an error occurred: ZSTD_CONTENTSIZE_ERROR
+ *
+ * note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode.
+ * When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size.
+ * In which case, it's necessary to use streaming mode to decompress data.
+ * note 2 : decompressed size is always present when compression is done with ZSTD_compress()
+ * note 3 : decompressed size can be very large (64-bits value),
+ * potentially larger than what local system can handle as a single memory segment.
+ * In which case, it's necessary to use streaming mode to decompress data.
+ * note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified.
+ * Always ensure result fits within application's authorized limits.
+ * Each application can set its own limits.
+ * note 5 : ZSTD_findDecompressedSize handles multiple frames, and so it must traverse the input to
+ * read each contained frame header. This is fast as most of the data is skipped,
+ * however it does mean that all frame data must be present and valid. */
+ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize);
+
+/*! ZSTD_frameHeaderSize() :
+* `src` should point to the start of a ZSTD frame
+* `srcSize` must be >= ZSTD_frameHeaderSize_prefix.
+* @return : size of the Frame Header */
+ZSTDLIB_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize);
+
+
/***************************************
-* Decompressed size functions
+* Context memory usage
***************************************/
-/*! ZSTD_getFrameContentSize() :
-* `src` should point to the start of a ZSTD encoded frame
-* `srcSize` must be at least as large as the frame header. A value greater than or equal
-* to `ZSTD_frameHeaderSize_max` is guaranteed to be large enough in all cases.
-* @return : decompressed size of the frame pointed to be `src` if known, otherwise
-* - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined
-* - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) */
-ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize);
-/*! ZSTD_findDecompressedSize() :
-* `src` should point the start of a series of ZSTD encoded and/or skippable frames
-* `srcSize` must be the _exact_ size of this series
-* (i.e. there should be a frame boundary exactly `srcSize` bytes after `src`)
-* @return : the decompressed size of all data in the contained frames, as a 64-bit value _if known_
-* - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN
-* - if an error occurred: ZSTD_CONTENTSIZE_ERROR
-*
-* note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode.
-* When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size.
-* In which case, it's necessary to use streaming mode to decompress data.
-* Optionally, application can still use ZSTD_decompress() while relying on implied limits.
-* (For example, data may be necessarily cut into blocks <= 16 KB).
-* note 2 : decompressed size is always present when compression is done with ZSTD_compress()
-* note 3 : decompressed size can be very large (64-bits value),
-* potentially larger than what local system can handle as a single memory segment.
-* In which case, it's necessary to use streaming mode to decompress data.
-* note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified.
-* Always ensure result fits within application's authorized limits.
-* Each application can set its own limits.
-* note 5 : ZSTD_findDecompressedSize handles multiple frames, and so it must traverse the input to
-* read each contained frame header. This is efficient as most of the data is skipped,
-* however it does mean that all frame data must be present and valid. */
-ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize);
+/*! ZSTD_sizeof_*() :
+ * These functions give the current memory usage of selected object.
+ * Object memory usage can evolve if it's re-used multiple times. */
+ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
+ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
+ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);
+ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
+ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
+ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
+
+/*! ZSTD_estimate*() :
+ * These functions make it possible to estimate memory usage
+ * of a future {D,C}Ctx, before its creation.
+ * ZSTD_estimateCCtxSize() will provide a budget large enough for any compression level up to selected one.
+ * It will also consider src size to be arbitrarily "large", which is worst case.
+ * If srcSize is known to always be small, ZSTD_estimateCCtxSize_advanced() can provide a tighter estimation.
+ * ZSTD_estimateCCtxSize_advanced() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel.
+ * Note : CCtx estimation is only correct for single-threaded compression */
+ZSTDLIB_API size_t ZSTD_estimateCCtxSize(int compressionLevel);
+ZSTDLIB_API size_t ZSTD_estimateCCtxSize_advanced(ZSTD_compressionParameters cParams);
+ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void);
+
+/*! ZSTD_estimate?StreamSize() :
+ * ZSTD_estimateCStreamSize() will provide a budget large enough for any compression level up to selected one.
+ * It will also consider src size to be arbitrarily "large", which is worst case.
+ * If srcSize is known to always be small, ZSTD_estimateCStreamSize_advanced() can provide a tighter estimation.
+ * ZSTD_estimateCStreamSize_advanced() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel.
+ * Note : CStream estimation is only correct for single-threaded compression.
+ * ZSTD_DStream memory budget depends on window Size.
+ * This information can be passed manually, using ZSTD_estimateDStreamSize,
+ * or deducted from a valid frame Header, using ZSTD_estimateDStreamSize_fromFrame();
+ * Note : if streaming is init with function ZSTD_init?Stream_usingDict(),
+ * an internal ?Dict will be created, which additional size is not estimated here.
+ * In this case, get total size by adding ZSTD_estimate?DictSize */
+ZSTDLIB_API size_t ZSTD_estimateCStreamSize(int compressionLevel);
+ZSTDLIB_API size_t ZSTD_estimateCStreamSize_advanced(ZSTD_compressionParameters cParams);
+ZSTDLIB_API size_t ZSTD_estimateDStreamSize(size_t windowSize);
+ZSTDLIB_API size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize);
+
+/*! ZSTD_estimate?DictSize() :
+ * ZSTD_estimateCDictSize() will bet that src size is relatively "small", and content is copied, like ZSTD_createCDict().
+ * ZSTD_estimateCStreamSize_advanced() makes it possible to control precisely compression parameters, like ZSTD_createCDict_advanced().
+ * Note : dictionary created "byReference" are smaller */
+ZSTDLIB_API size_t ZSTD_estimateCDictSize(size_t dictSize, int compressionLevel);
+ZSTDLIB_API size_t ZSTD_estimateCDictSize_advanced(size_t dictSize, ZSTD_compressionParameters cParams, unsigned byReference);
+ZSTDLIB_API size_t ZSTD_estimateDDictSize(size_t dictSize, unsigned byReference);
/***************************************
* Advanced compression functions
***************************************/
-/*! ZSTD_estimateCCtxSize() :
- * Gives the amount of memory allocated for a ZSTD_CCtx given a set of compression parameters.
- * `frameContentSize` is an optional parameter, provide `0` if unknown */
-ZSTDLIB_API size_t ZSTD_estimateCCtxSize(ZSTD_compressionParameters cParams);
-
/*! ZSTD_createCCtx_advanced() :
* Create a ZSTD compression context using external alloc and free functions */
ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem);
-/*! ZSTD_sizeofCCtx() :
- * Gives the amount of memory used by a given ZSTD_CCtx */
-ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
+/*! ZSTD_initStaticCCtx() : initialize a fixed-size zstd compression context
+ * workspace: The memory area to emplace the context into.
+ * Provided pointer must 8-bytes aligned.
+ * It must outlive context usage.
+ * workspaceSize: Use ZSTD_estimateCCtxSize() or ZSTD_estimateCStreamSize()
+ * to determine how large workspace must be to support scenario.
+ * @return : pointer to ZSTD_CCtx*, or NULL if error (size too small)
+ * Note : zstd will never resize nor malloc() when using a static cctx.
+ * If it needs more memory than available, it will simply error out.
+ * Note 2 : there is no corresponding "free" function.
+ * Since workspace was allocated externally, it must be freed externally too.
+ * Limitation 1 : currently not compatible with internal CDict creation, such as
+ * ZSTD_CCtx_loadDictionary() or ZSTD_initCStream_usingDict().
+ * Limitation 2 : currently not compatible with multi-threading
+ */
+ZSTDLIB_API ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize);
+
+/* !!! To be deprecated !!! */
typedef enum {
ZSTD_p_forceWindow, /* Force back-references to remain < windowSize, even when referencing Dictionary content (default:0) */
ZSTD_p_forceRawDict /* Force loading dictionary in "content-only" mode (no header analysis) */
@@ -479,20 +569,43 @@ typedef enum {
* @result : 0, or an error code (which can be tested with ZSTD_isError()) */
ZSTDLIB_API size_t ZSTD_setCCtxParameter(ZSTD_CCtx* cctx, ZSTD_CCtxParameter param, unsigned value);
+
/*! ZSTD_createCDict_byReference() :
* Create a digested dictionary for compression
* Dictionary content is simply referenced, and therefore stays in dictBuffer.
* It is important that dictBuffer outlives CDict, it must remain read accessible throughout the lifetime of CDict */
ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel);
+
+typedef enum { ZSTD_dm_auto=0, /* dictionary is "full" if it starts with ZSTD_MAGIC_DICTIONARY, otherwise it is "rawContent" */
+ ZSTD_dm_rawContent, /* ensures dictionary is always loaded as rawContent, even if it starts with ZSTD_MAGIC_DICTIONARY */
+ ZSTD_dm_fullDict /* refuses to load a dictionary if it does not respect Zstandard's specification */
+} ZSTD_dictMode_e;
/*! ZSTD_createCDict_advanced() :
* Create a ZSTD_CDict using external alloc and free, and customized compression parameters */
-ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, unsigned byReference,
- ZSTD_compressionParameters cParams, ZSTD_customMem customMem);
-
-/*! ZSTD_sizeof_CDict() :
- * Gives the amount of memory used by a given ZSTD_sizeof_CDict */
-ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
+ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize,
+ unsigned byReference, ZSTD_dictMode_e dictMode,
+ ZSTD_compressionParameters cParams,
+ ZSTD_customMem customMem);
+
+/*! ZSTD_initStaticCDict_advanced() :
+ * Generate a digested dictionary in provided memory area.
+ * workspace: The memory area to emplace the dictionary into.
+ * Provided pointer must 8-bytes aligned.
+ * It must outlive dictionary usage.
+ * workspaceSize: Use ZSTD_estimateCDictSize()
+ * to determine how large workspace must be.
+ * cParams : use ZSTD_getCParams() to transform a compression level
+ * into its relevants cParams.
+ * @return : pointer to ZSTD_CDict*, or NULL if error (size too small)
+ * Note : there is no corresponding "free" function.
+ * Since workspace was allocated externally, it must be freed externally.
+ */
+ZSTDLIB_API ZSTD_CDict* ZSTD_initStaticCDict(
+ void* workspace, size_t workspaceSize,
+ const void* dict, size_t dictSize,
+ unsigned byReference, ZSTD_dictMode_e dictMode,
+ ZSTD_compressionParameters cParams);
/*! ZSTD_getCParams() :
* @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize.
@@ -509,8 +622,8 @@ ZSTDLIB_API ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long l
ZSTDLIB_API size_t ZSTD_checkCParams(ZSTD_compressionParameters params);
/*! ZSTD_adjustCParams() :
-* optimize params for a given `srcSize` and `dictSize`.
-* both values are optional, select `0` if unknown. */
+ * optimize params for a given `srcSize` and `dictSize`.
+ * both values are optional, select `0` if unknown. */
ZSTDLIB_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize);
/*! ZSTD_compress_advanced() :
@@ -538,22 +651,32 @@ ZSTDLIB_API size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx,
* Note 3 : Skippable Frame Identifiers are considered valid. */
ZSTDLIB_API unsigned ZSTD_isFrame(const void* buffer, size_t size);
-/*! ZSTD_estimateDCtxSize() :
- * Gives the potential amount of memory allocated to create a ZSTD_DCtx */
-ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void);
-
/*! ZSTD_createDCtx_advanced() :
* Create a ZSTD decompression context using external alloc and free functions */
ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem);
-/*! ZSTD_sizeof_DCtx() :
- * Gives the amount of memory used by a given ZSTD_DCtx */
-ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
+/*! ZSTD_initStaticDCtx() : initialize a fixed-size zstd decompression context
+ * workspace: The memory area to emplace the context into.
+ * Provided pointer must 8-bytes aligned.
+ * It must outlive context usage.
+ * workspaceSize: Use ZSTD_estimateDCtxSize() or ZSTD_estimateDStreamSize()
+ * to determine how large workspace must be to support scenario.
+ * @return : pointer to ZSTD_DCtx*, or NULL if error (size too small)
+ * Note : zstd will never resize nor malloc() when using a static dctx.
+ * If it needs more memory than available, it will simply error out.
+ * Note 2 : static dctx is incompatible with legacy support
+ * Note 3 : there is no corresponding "free" function.
+ * Since workspace was allocated externally, it must be freed externally.
+ * Limitation : currently not compatible with internal DDict creation,
+ * such as ZSTD_initDStream_usingDict().
+ */
+ZSTDLIB_API ZSTD_DCtx* ZSTD_initStaticDCtx(void* workspace, size_t workspaceSize);
/*! ZSTD_createDDict_byReference() :
* Create a digested dictionary, ready to start decompression operation without startup delay.
- * Dictionary content is simply referenced, and therefore stays in dictBuffer.
- * It is important that dictBuffer outlives DDict, it must remain read accessible throughout the lifetime of DDict */
+ * Dictionary content is referenced, and therefore stays in dictBuffer.
+ * It is important that dictBuffer outlives DDict,
+ * it must remain read accessible throughout the lifetime of DDict */
ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize);
/*! ZSTD_createDDict_advanced() :
@@ -561,9 +684,20 @@ ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, siz
ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize,
unsigned byReference, ZSTD_customMem customMem);
-/*! ZSTD_sizeof_DDict() :
- * Gives the amount of memory used by a given ZSTD_DDict */
-ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
+/*! ZSTD_initStaticDDict() :
+ * Generate a digested dictionary in provided memory area.
+ * workspace: The memory area to emplace the dictionary into.
+ * Provided pointer must 8-bytes aligned.
+ * It must outlive dictionary usage.
+ * workspaceSize: Use ZSTD_estimateDDictSize()
+ * to determine how large workspace must be.
+ * @return : pointer to ZSTD_DDict*, or NULL if error (size too small)
+ * Note : there is no corresponding "free" function.
+ * Since workspace was allocated externally, it must be freed externally.
+ */
+ZSTDLIB_API ZSTD_DDict* ZSTD_initStaticDDict(void* workspace, size_t workspaceSize,
+ const void* dict, size_t dictSize,
+ unsigned byReference);
/*! ZSTD_getDictID_fromDict() :
* Provides the dictID stored within dictionary.
@@ -586,7 +720,7 @@ ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
* Note : this use case also happens when using a non-conformant dictionary.
* - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
* - This is not a Zstandard frame.
- * When identifying the exact failure cause, it's possible to use ZSTD_getFrameParams(), which will provide a more precise error code. */
+ * When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. */
ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
@@ -596,13 +730,13 @@ ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
/*===== Advanced Streaming compression functions =====*/
ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem);
-ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs); /**< size of CStream is variable, depending primarily on compression level */
+ZSTDLIB_API ZSTD_CStream* ZSTD_initStaticCStream(void* workspace, size_t workspaceSize); /**< same as ZSTD_initStaticCCtx() */
ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); /**< pledgedSrcSize must be correct, a size of 0 means unknown. for a frame size of 0 use initCStream_advanced */
-ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< note: a dict will not be used if dict == NULL or dictSize < 8 */
+ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< creates of an internal CDict (incompatible with static CCtx), except if dict == NULL or dictSize < 8, in which case no dict is used. */
ZSTDLIB_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize,
ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize is optional and can be 0 (meaning unknown). note: if the contentSizeFlag is set, pledgedSrcSize == 0 means the source size is actually 0 */
ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); /**< note : cdict will just be referenced, and must outlive compression session */
-ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, unsigned long long pledgedSrcSize, ZSTD_frameParameters fParams); /**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters */
+ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize); /**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters */
/*! ZSTD_resetCStream() :
* start a new compression job, using same parameters from previous job.
@@ -617,11 +751,11 @@ ZSTDLIB_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledg
/*===== Advanced Streaming decompression functions =====*/
typedef enum { DStream_p_maxWindowSize } ZSTD_DStreamParameter_e;
ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem);
-ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); /**< note: a dict will not be used if dict == NULL or dictSize < 8 */
+ZSTDLIB_API ZSTD_DStream* ZSTD_initStaticDStream(void* workspace, size_t workspaceSize); /**< same as ZSTD_initStaticDCtx() */
ZSTDLIB_API size_t ZSTD_setDStreamParameter(ZSTD_DStream* zds, ZSTD_DStreamParameter_e paramType, unsigned paramValue);
+ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); /**< note: a dict will not be used if dict == NULL or dictSize < 8 */
ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict); /**< note : ddict will just be referenced, and must outlive decompression session */
ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); /**< re-use decompression parameters from previous init; saves dictionary loading */
-ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
/*********************************************************************
@@ -683,21 +817,24 @@ ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapaci
Use ZSTD_createDCtx() / ZSTD_freeDCtx() to manage it.
A ZSTD_DCtx object can be re-used multiple times.
- First typical operation is to retrieve frame parameters, using ZSTD_getFrameParams().
- It fills a ZSTD_frameParams structure which provide important information to correctly decode the frame,
- such as the minimum rolling buffer size to allocate to decompress data (`windowSize`),
- and the dictionary ID used.
+ First typical operation is to retrieve frame parameters, using ZSTD_getFrameHeader().
+ It fills a ZSTD_frameHeader structure with important information to correctly decode the frame,
+ such as minimum rolling buffer size to allocate to decompress data (`windowSize`),
+ and the dictionary ID in use.
(Note : content size is optional, it may not be present. 0 means : content size unknown).
Note that these values could be wrong, either because of data malformation, or because an attacker is spoofing deliberate false information.
As a consequence, check that values remain within valid application range, especially `windowSize`, before allocation.
- Each application can set its own limit, depending on local restrictions. For extended interoperability, it is recommended to support at least 8 MB.
- Frame parameters are extracted from the beginning of the compressed frame.
- Data fragment must be large enough to ensure successful decoding, typically `ZSTD_frameHeaderSize_max` bytes.
- @result : 0 : successful decoding, the `ZSTD_frameParams` structure is correctly filled.
+ Each application can set its own limit, depending on local restrictions.
+ For extended interoperability, it is recommended to support windowSize of at least 8 MB.
+ Frame header is extracted from the beginning of compressed frame, so providing only the frame's beginning is enough.
+ Data fragment must be large enough to ensure successful decoding.
+ `ZSTD_frameHeaderSize_max` bytes is guaranteed to always be large enough.
+ @result : 0 : successful decoding, the `ZSTD_frameHeader` structure is correctly filled.
>0 : `srcSize` is too small, please provide at least @result bytes on next attempt.
errorCode, which can be tested using ZSTD_isError().
- Start decompression, with ZSTD_decompressBegin() or ZSTD_decompressBegin_usingDict().
+ Start decompression, with ZSTD_decompressBegin().
+ If decompression requires a dictionary, use ZSTD_decompressBegin_usingDict() or ZSTD_decompressBegin_usingDDict().
Alternatively, you can copy a prepared context, using ZSTD_copyDCtx().
Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() alternatively.
@@ -729,30 +866,233 @@ ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapaci
b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits
c) Frame Content - any content (User Data) of length equal to Frame Size
For skippable frames ZSTD_decompressContinue() always returns 0.
- For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 what means that a frame is skippable.
+ For skippable frames ZSTD_getFrameHeader() returns fparamsPtr->windowLog==0 what means that a frame is skippable.
Note : If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might actually be a Zstd encoded frame with no content.
For purposes of decompression, it is valid in both cases to skip the frame using
ZSTD_findFrameCompressedSize to find its size in bytes.
It also returns Frame Size as fparamsPtr->frameContentSize.
*/
-typedef struct {
- unsigned long long frameContentSize;
- unsigned windowSize;
- unsigned dictID;
- unsigned checksumFlag;
-} ZSTD_frameParams;
-
/*===== Buffer-less streaming decompression functions =====*/
-ZSTDLIB_API size_t ZSTD_getFrameParams(ZSTD_frameParams* fparamsPtr, const void* src, size_t srcSize); /**< doesn't consume input, see details below */
+ZSTDLIB_API size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize); /**< doesn't consume input */
ZSTDLIB_API size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx);
ZSTDLIB_API size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize);
+ZSTDLIB_API size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict);
ZSTDLIB_API void ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx);
+
ZSTDLIB_API size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx);
ZSTDLIB_API size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e;
ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
+
+
+/*=== New advanced API (experimental, and compression only) ===*/
+
+/* notes on API design :
+ * In this proposal, parameters are pushed one by one into an existing CCtx,
+ * and then applied on all subsequent compression jobs.
+ * When no parameter is ever provided, CCtx is created with compression level ZSTD_CLEVEL_DEFAULT.
+ *
+ * This API is intended to replace all others experimental API.
+ * It can basically do all other use cases, and even new ones.
+ * It stands a good chance to become "stable",
+ * after a reasonable testing period.
+ */
+
+/* note on naming convention :
+ * Initially, the API favored names like ZSTD_setCCtxParameter() .
+ * In this proposal, convention is changed towards ZSTD_CCtx_setParameter() .
+ * The main driver is that it identifies more clearly the target object type.
+ * It feels clearer in light of potential variants :
+ * ZSTD_CDict_setParameter() (rather than ZSTD_setCDictParameter())
+ * ZSTD_DCtx_setParameter() (rather than ZSTD_setDCtxParameter() )
+ * Left variant feels easier to distinguish.
+ */
+
+/* note on enum design :
+ * All enum will be manually set to explicit values before reaching "stable API" status */
+
+typedef enum {
+ /* compression parameters */
+ ZSTD_p_compressionLevel=100, /* Update all compression parameters according to pre-defined cLevel table
+ * Default level is ZSTD_CLEVEL_DEFAULT==3.
+ * Special: value 0 means "do not change cLevel". */
+ ZSTD_p_windowLog, /* Maximum allowed back-reference distance, expressed as power of 2.
+ * Must be clamped between ZSTD_WINDOWLOG_MIN and ZSTD_WINDOWLOG_MAX.
+ * Special: value 0 means "do not change windowLog". */
+ ZSTD_p_hashLog, /* Size of the probe table, as a power of 2.
+ * Resulting table size is (1 << (hashLog+2)).
+ * Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX.
+ * Larger tables improve compression ratio of strategies <= dFast,
+ * and improve speed of strategies > dFast.
+ * Special: value 0 means "do not change hashLog". */
+ ZSTD_p_chainLog, /* Size of the full-search table, as a power of 2.
+ * Resulting table size is (1 << (chainLog+2)).
+ * Larger tables result in better and slower compression.
+ * This parameter is useless when using "fast" strategy.
+ * Special: value 0 means "do not change chainLog". */
+ ZSTD_p_searchLog, /* Number of search attempts, as a power of 2.
+ * More attempts result in better and slower compression.
+ * This parameter is useless when using "fast" and "dFast" strategies.
+ * Special: value 0 means "do not change searchLog". */
+ ZSTD_p_minMatch, /* Minimum size of searched matches (note : repCode matches can be smaller).
+ * Larger values make faster compression and decompression, but decrease ratio.
+ * Must be clamped between ZSTD_SEARCHLENGTH_MIN and ZSTD_SEARCHLENGTH_MAX.
+ * Note that currently, for all strategies < btopt, effective minimum is 4.
+ * Note that currently, for all strategies > fast, effective maximum is 6.
+ * Special: value 0 means "do not change minMatchLength". */
+ ZSTD_p_targetLength, /* Only useful for strategies >= btopt.
+ * Length of Match considered "good enough" to stop search.
+ * Larger values make compression stronger and slower.
+ * Special: value 0 means "do not change targetLength". */
+ ZSTD_p_compressionStrategy, /* See ZSTD_strategy enum definition.
+ * Cast selected strategy as unsigned for ZSTD_CCtx_setParameter() compatibility.
+ * The higher the value of selected strategy, the more complex it is,
+ * resulting in stronger and slower compression.
+ * Special: value 0 means "do not change strategy". */
+
+ /* frame parameters */
+ ZSTD_p_contentSizeFlag=200, /* Content size is written into frame header _whenever known_ (default:1) */
+ ZSTD_p_checksumFlag, /* A 32-bits checksum of content is written at end of frame (default:0) */
+ ZSTD_p_dictIDFlag, /* When applicable, dictID of dictionary is provided in frame header (default:1) */
+
+ /* dictionary parameters (must be set before ZSTD_CCtx_loadDictionary) */
+ ZSTD_p_dictMode=300, /* Select how dictionary content must be interpreted. Value must be from type ZSTD_dictMode_e.
+ * default : 0==auto : dictionary will be "full" if it respects specification, otherwise it will be "rawContent" */
+ ZSTD_p_refDictContent, /* Dictionary content will be referenced, instead of copied (default:0==byCopy).
+ * It requires that dictionary buffer outlives its users */
+
+ /* multi-threading parameters */
+ ZSTD_p_nbThreads=400, /* Select how many threads a compression job can spawn (default:1)
+ * More threads improve speed, but also increase memory usage.
+ * Can only receive a value > 1 if ZSTD_MULTITHREAD is enabled.
+ * Special: value 0 means "do not change nbThreads" */
+ ZSTD_p_jobSize, /* Size of a compression job. Each compression job is completed in parallel.
+ * 0 means default, which is dynamically determined based on compression parameters.
+ * Job size must be a minimum of overlapSize, or 1 KB, whichever is largest
+ * The minimum size is automatically and transparently enforced */
+ ZSTD_p_overlapSizeLog, /* Size of previous input reloaded at the beginning of each job.
+ * 0 => no overlap, 6(default) => use 1/8th of windowSize, >=9 => use full windowSize */
+
+ /* advanced parameters - may not remain available after API update */
+ ZSTD_p_forceMaxWindow=1100, /* Force back-reference distances to remain < windowSize,
+ * even when referencing into Dictionary content (default:0) */
+
+} ZSTD_cParameter;
+
+
+/*! ZSTD_CCtx_setParameter() :
+ * Set one compression parameter, selected by enum ZSTD_cParameter.
+ * Note : when `value` is an enum, cast it to unsigned for proper type checking.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()). */
+ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, unsigned value);
+
+/*! ZSTD_CCtx_setPledgedSrcSize() :
+ * Total input data size to be compressed as a single frame.
+ * This value will be controlled at the end, and result in error if not respected.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ * Note 1 : 0 means zero, empty.
+ * In order to mean "unknown content size", pass constant ZSTD_CONTENTSIZE_UNKNOWN.
+ * Note that ZSTD_CONTENTSIZE_UNKNOWN is default value for new compression jobs.
+ * Note 2 : If all data is provided and consumed in a single round,
+ * this value is overriden by srcSize instead. */
+ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize);
+
+/*! ZSTD_CCtx_loadDictionary() :
+ * Create an internal CDict from dict buffer.
+ * Decompression will have to use same buffer.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ * Special : Adding a NULL (or 0-size) dictionary invalidates any previous dictionary,
+ * meaning "return to no-dictionary mode".
+ * Note 1 : `dict` content will be copied internally,
+ * except if ZSTD_p_refDictContent is set before loading.
+ * Note 2 : Loading a dictionary involves building tables, which are dependent on compression parameters.
+ * For this reason, compression parameters cannot be changed anymore after loading a dictionary.
+ * It's also a CPU-heavy operation, with non-negligible impact on latency.
+ * Note 3 : Dictionary will be used for all future compression jobs.
+ * To return to "no-dictionary" situation, load a NULL dictionary */
+ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize);
+
+/*! ZSTD_CCtx_refCDict() :
+ * Reference a prepared dictionary, to be used for all next compression jobs.
+ * Note that compression parameters are enforced from within CDict,
+ * and supercede any compression parameter previously set within CCtx.
+ * The dictionary will remain valid for future compression jobs using same CCtx.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ * Special : adding a NULL CDict means "return to no-dictionary mode".
+ * Note 1 : Currently, only one dictionary can be managed.
+ * Adding a new dictionary effectively "discards" any previous one.
+ * Note 2 : CDict is just referenced, its lifetime must outlive CCtx.
+ */
+ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict);
+
+/*! ZSTD_CCtx_refPrefix() :
+ * Reference a prefix (single-usage dictionary) for next compression job.
+ * Decompression need same prefix to properly regenerate data.
+ * Prefix is **only used once**. Tables are discarded at end of compression job.
+ * Subsequent compression jobs will be done without prefix (if none is explicitly referenced).
+ * If there is a need to use same prefix multiple times, consider embedding it into a ZSTD_CDict instead.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ * Special : Adding any prefix (including NULL) invalidates any previous prefix or dictionary
+ * Note 1 : Prefix buffer is referenced. It must outlive compression job.
+ * Note 2 : Referencing a prefix involves building tables, which are dependent on compression parameters.
+ * It's a CPU-heavy operation, with non-negligible impact on latency.
+ * Note 3 : it's possible to alter ZSTD_p_dictMode using ZSTD_CCtx_setParameter() */
+ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize);
+
+
+
+typedef enum {
+ ZSTD_e_continue=0, /* collect more data, encoder transparently decides when to output result, for optimal conditions */
+ ZSTD_e_flush, /* flush any data provided so far - frame will continue, future data can still reference previous data for better compression */
+ ZSTD_e_end /* flush any remaining data and ends current frame. Any future compression starts a new frame. */
+} ZSTD_EndDirective;
+
+/*! ZSTD_compress_generic() :
+ * Behave about the same as ZSTD_compressStream. To note :
+ * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_setParameter()
+ * - Compression parameters cannot be changed once compression is started.
+ * - *dstPos must be <= dstCapacity, *srcPos must be <= srcSize
+ * - *dspPos and *srcPos will be updated. They are guaranteed to remain below their respective limit.
+ * - @return provides the minimum amount of data still to flush from internal buffers
+ * or an error code, which can be tested using ZSTD_isError().
+ * if @return != 0, flush is not fully completed, there is some data left within internal buffers.
+ * - after a ZSTD_e_end directive, if internal buffer is not fully flushed,
+ * only ZSTD_e_end or ZSTD_e_flush operations are allowed.
+ * It is necessary to fully flush internal buffers
+ * before starting a new compression job, or changing compression parameters.
+ */
+ZSTDLIB_API size_t ZSTD_compress_generic (ZSTD_CCtx* cctx,
+ ZSTD_outBuffer* output,
+ ZSTD_inBuffer* input,
+ ZSTD_EndDirective endOp);
+
+/*! ZSTD_CCtx_reset() :
+ * Return a CCtx to clean state.
+ * Useful after an error, or to interrupt an ongoing compression job and start a new one.
+ * Any internal data not yet flushed is cancelled.
+ * Dictionary (if any) is dropped.
+ * It's possible to modify compression parameters after a reset.
+ */
+ZSTDLIB_API void ZSTD_CCtx_reset(ZSTD_CCtx* cctx); /* Not ready yet ! */
+
+
+/*! ZSTD_compress_generic_simpleArgs() :
+ * Same as ZSTD_compress_generic(),
+ * but using only integral types as arguments.
+ * Argument list is larger and less expressive than ZSTD_{in,out}Buffer,
+ * but can be helpful for binders from dynamic languages
+ * which have troubles handling structures containing memory pointers.
+ */
+size_t ZSTD_compress_generic_simpleArgs (
+ ZSTD_CCtx* cctx,
+ void* dst, size_t dstCapacity, size_t* dstPos,
+ const void* src, size_t srcSize, size_t* srcPos,
+ ZSTD_EndDirective endOp);
+
+
+
/**
Block functions
@@ -767,7 +1107,7 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
+ compression : any ZSTD_compressBegin*() variant, including with dictionary
+ decompression : any ZSTD_decompressBegin*() variant, including with dictionary
+ copyCCtx() and copyDCtx() can be used too
- - Block size is limited, it must be <= ZSTD_getBlockSizeMax() <= ZSTD_BLOCKSIZE_ABSOLUTEMAX
+ - Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX
+ If input is larger than a block size, it's necessary to split input data into multiple blocks
+ For inputs larger than a single block size, consider using the regular ZSTD_compress() instead.
Frame metadata is not that costly, and quickly becomes negligible as source size grows larger.
@@ -780,9 +1120,10 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
Use ZSTD_insertBlock() for such a case.
*/
-#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024) /* define, for static allocation */
+#define ZSTD_BLOCKSIZELOG_MAX 17
+#define ZSTD_BLOCKSIZE_MAX (1<<ZSTD_BLOCKSIZELOG_MAX) /* define, for static allocation */
/*===== Raw zstd block functions =====*/
-ZSTDLIB_API size_t ZSTD_getBlockSizeMax(ZSTD_CCtx* cctx);
+ZSTDLIB_API size_t ZSTD_getBlockSize (const ZSTD_CCtx* cctx);
ZSTDLIB_API size_t ZSTD_compressBlock (ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
ZSTDLIB_API size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
ZSTDLIB_API size_t ZSTD_insertBlock(ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize); /**< insert block into `dctx` history. Useful for uncompressed blocks */
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-08 11:33:42 +0000