mirror of
https://github.com/facebook/zstd.git
synced 2025-07-30 22:23:13 +03:00
Merge branch 'dev' into benchfn
This commit is contained in:
16
.cirrus.yml
Normal file
16
.cirrus.yml
Normal file
@ -0,0 +1,16 @@
|
||||
env:
|
||||
CIRRUS_CLONE_DEPTH: 1
|
||||
ARCH: amd64
|
||||
|
||||
task:
|
||||
freebsd_instance:
|
||||
matrix:
|
||||
image: freebsd-12-0-release-amd64
|
||||
image: freebsd-11-2-release-amd64
|
||||
install_script:
|
||||
- sed -i.bak -e 's,pkg+http://pkg.FreeBSD.org/\${ABI}/quarterly,pkg+http://pkg.FreeBSD.org/\${ABI}/latest,' /etc/pkg/FreeBSD.conf
|
||||
- pkg upgrade -y
|
||||
- pkg install -y gmake coreutils
|
||||
script: |
|
||||
MOREFLAGS="-Werror" gmake -j all
|
||||
gmake shortest
|
@ -1,3 +1,7 @@
|
||||
dev
|
||||
api : Rename ZSTD_CCtxParam_getParameter to ZSTD_CCtxParams_getParameter
|
||||
api : Rename ZSTD_CCtxParam_setParameter to ZSTD_CCtxParams_setParameter
|
||||
|
||||
v1.3.8
|
||||
perf: better decompression speed on large files (+7%) and cold dictionaries (+15%)
|
||||
perf: slightly better compression ratio at high compression modes
|
||||
|
@ -14,6 +14,7 @@ a list of known ports and bindings is provided on [Zstandard homepage](http://ww
|
||||
[![Build Status][travisDevBadge]][travisLink]
|
||||
[![Build status][AppveyorDevBadge]][AppveyorLink]
|
||||
[![Build status][CircleDevBadge]][CircleLink]
|
||||
[![Build status][CirrusDevBadge]][CirrusLink]
|
||||
|
||||
[travisDevBadge]: https://travis-ci.org/facebook/zstd.svg?branch=dev "Continuous Integration test suite"
|
||||
[travisLink]: https://travis-ci.org/facebook/zstd
|
||||
@ -21,6 +22,8 @@ a list of known ports and bindings is provided on [Zstandard homepage](http://ww
|
||||
[AppveyorLink]: https://ci.appveyor.com/project/YannCollet/zstd-p0yf0
|
||||
[CircleDevBadge]: https://circleci.com/gh/facebook/zstd/tree/dev.svg?style=shield "Short test suite"
|
||||
[CircleLink]: https://circleci.com/gh/facebook/zstd
|
||||
[CirrusDevBadge]: https://api.cirrus-ci.com/github/facebook/zstd.svg?branch=dev
|
||||
[CirrusLink]: https://cirrus-ci.com/github/facebook/zstd
|
||||
|
||||
## Benchmarks
|
||||
|
||||
|
@ -149,7 +149,8 @@ if (ZSTD_BUILD_SHARED)
|
||||
libzstd_shared
|
||||
PROPERTIES
|
||||
OUTPUT_NAME zstd
|
||||
SOVERSION ${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH})
|
||||
VERSION ${zstd_VERSION_MAJOR}.${zstd_VERSION_MINOR}.${zstd_VERSION_PATCH}
|
||||
SOVERSION ${zstd_VERSION_MAJOR})
|
||||
endif ()
|
||||
|
||||
if (ZSTD_BUILD_STATIC)
|
||||
|
@ -98,7 +98,7 @@ if use_debug
|
||||
if cc_id == compiler_gcc or cc_id == compiler_clang
|
||||
libzstd_debug_cflags = ['-Wstrict-aliasing=1', '-Wswitch-enum',
|
||||
'-Wdeclaration-after-statement', '-Wstrict-prototypes',
|
||||
'-Wundef', '-Wpointer-arith', '-Wformat-security', '-Wvla',
|
||||
'-Wundef', '-Wpointer-arith', '-Wvla',
|
||||
'-Wformat=2', '-Winit-self', '-Wfloat-equal', '-Wwrite-strings',
|
||||
'-Wredundant-decls', '-Wmissing-prototypes', '-Wc++-compat']
|
||||
endif
|
||||
|
@ -13,7 +13,7 @@ CPPFLAGS += -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(ZSTDDIR)/compress \
|
||||
CFLAGS ?= -O3
|
||||
CFLAGS += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
|
||||
-Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
|
||||
-Wstrict-prototypes -Wundef -Wformat-security \
|
||||
-Wstrict-prototypes -Wundef \
|
||||
-Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
|
||||
-Wredundant-decls
|
||||
CFLAGS += $(DEBUGFLAGS)
|
||||
|
@ -18,7 +18,7 @@ CFLAGS ?= -O3
|
||||
CFLAGS += -std=gnu99
|
||||
DEBUGFLAGS= -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
|
||||
-Wstrict-aliasing=1 -Wswitch-enum \
|
||||
-Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security \
|
||||
-Wstrict-prototypes -Wundef -Wpointer-arith \
|
||||
-Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
|
||||
-Wredundant-decls
|
||||
CFLAGS += $(DEBUGFLAGS) $(MOREFLAGS)
|
||||
|
@ -7,7 +7,7 @@ CPPFLAGS += -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(ZSTDDIR)/compress \
|
||||
CFLAGS ?= -O3
|
||||
CFLAGS += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
|
||||
-Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
|
||||
-Wstrict-prototypes -Wundef -Wformat-security \
|
||||
-Wstrict-prototypes -Wundef \
|
||||
-Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
|
||||
-Wredundant-decls
|
||||
CFLAGS += $(DEBUGFLAGS)
|
||||
|
@ -25,28 +25,28 @@ all: simple_compression simple_decompression \
|
||||
$(LIB) :
|
||||
$(MAKE) -C ../lib libzstd.a
|
||||
|
||||
simple_compression : simple_compression.c utils.h $(LIB)
|
||||
simple_compression : simple_compression.c common.h $(LIB)
|
||||
$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@
|
||||
|
||||
simple_decompression : simple_decompression.c utils.h $(LIB)
|
||||
simple_decompression : simple_decompression.c common.h $(LIB)
|
||||
$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@
|
||||
|
||||
multiple_simple_compression : multiple_simple_compression.c utils.h $(LIB)
|
||||
multiple_simple_compression : multiple_simple_compression.c common.h $(LIB)
|
||||
$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@
|
||||
|
||||
dictionary_compression : dictionary_compression.c utils.h $(LIB)
|
||||
dictionary_compression : dictionary_compression.c common.h $(LIB)
|
||||
$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@
|
||||
|
||||
dictionary_decompression : dictionary_decompression.c utils.h $(LIB)
|
||||
dictionary_decompression : dictionary_decompression.c common.h $(LIB)
|
||||
$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@
|
||||
|
||||
streaming_compression : streaming_compression.c utils.h $(LIB)
|
||||
streaming_compression : streaming_compression.c common.h $(LIB)
|
||||
$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@
|
||||
|
||||
multiple_streaming_compression : multiple_streaming_compression.c utils.h $(LIB)
|
||||
multiple_streaming_compression : multiple_streaming_compression.c common.h $(LIB)
|
||||
$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@
|
||||
|
||||
streaming_decompression : streaming_decompression.c utils.h $(LIB)
|
||||
streaming_decompression : streaming_decompression.c common.h $(LIB)
|
||||
$(CC) $(CPPFLAGS) $(CFLAGS) $< $(LIB) $(LDFLAGS) -o $@
|
||||
|
||||
streaming_memory_usage : streaming_memory_usage.c $(LIB)
|
||||
|
@ -11,15 +11,15 @@
|
||||
/*
|
||||
* This header file has common utility functions used in examples.
|
||||
*/
|
||||
#ifndef UTILS_H
|
||||
#define UTILS_H
|
||||
#ifndef COMMON_H
|
||||
#define COMMON_H
|
||||
|
||||
#include <stdlib.h> // malloc, free, exit
|
||||
#include <stdio.h> // fprintf, perror, fopen, etc.
|
||||
#include <string.h> // strlen, strcat, memset, strerror
|
||||
#include <string.h> // strerror
|
||||
#include <errno.h> // errno
|
||||
#include <assert.h> // assert
|
||||
#include <sys/stat.h> // stat
|
||||
#include <zstd.h>
|
||||
|
||||
/*
|
||||
* Define the returned error code from utility functions.
|
||||
@ -34,7 +34,34 @@ typedef enum {
|
||||
ERROR_saveFile = 7,
|
||||
ERROR_malloc = 8,
|
||||
ERROR_largeFile = 9,
|
||||
} UTILS_ErrorCode;
|
||||
} COMMON_ErrorCode;
|
||||
|
||||
/*! CHECK
|
||||
* Check that the condition holds. If it doesn't print a message and die.
|
||||
*/
|
||||
#define CHECK(cond, ...) \
|
||||
do { \
|
||||
if (!(cond)) { \
|
||||
fprintf(stderr, \
|
||||
"%s:%d CHECK(%s) failed: ", \
|
||||
__FILE__, \
|
||||
__LINE__, \
|
||||
#cond); \
|
||||
fprintf(stderr, "" __VA_ARGS__); \
|
||||
fprintf(stderr, "\n"); \
|
||||
exit(1); \
|
||||
} \
|
||||
} while (0)
|
||||
|
||||
/*! CHECK_ZSTD
|
||||
* Check the zstd error code and die if an error occurred after printing a
|
||||
* message.
|
||||
*/
|
||||
#define CHECK_ZSTD(fn, ...) \
|
||||
do { \
|
||||
size_t const err = (fn); \
|
||||
CHECK(!ZSTD_isError(err), "%s", ZSTD_getErrorName(err)); \
|
||||
} while (0)
|
||||
|
||||
/*! fsize_orDie() :
|
||||
* Get the size of a given file path.
|
||||
@ -153,7 +180,7 @@ static void* malloc_orDie(size_t size)
|
||||
static size_t loadFile_orDie(const char* fileName, void* buffer, size_t bufferSize)
|
||||
{
|
||||
size_t const fileSize = fsize_orDie(fileName);
|
||||
assert(fileSize <= bufferSize);
|
||||
CHECK(fileSize <= bufferSize, "File too large!");
|
||||
|
||||
FILE* const inFile = fopen_orDie(fileName, "rb");
|
||||
size_t const readSize = fread(buffer, 1, fileSize, inFile);
|
@ -7,13 +7,11 @@
|
||||
* in the COPYING file in the root directory of this source tree).
|
||||
* You may select, at your option, one of the above-listed licenses.
|
||||
*/
|
||||
#include <stdlib.h> // malloc, exit
|
||||
#include <stdio.h> // printf
|
||||
#include <string.h> // strerror
|
||||
#include <errno.h> // errno
|
||||
#include <sys/stat.h> // stat
|
||||
#include <stdlib.h> // free
|
||||
#include <string.h> // memset, strcat
|
||||
#include <zstd.h> // presumes zstd library is installed
|
||||
#include "utils.h"
|
||||
#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD()
|
||||
|
||||
/* createDict() :
|
||||
`dictFileName` is supposed to have been created using `zstd --train` */
|
||||
@ -23,10 +21,7 @@ static ZSTD_CDict* createCDict_orDie(const char* dictFileName, int cLevel)
|
||||
printf("loading dictionary %s \n", dictFileName);
|
||||
void* const dictBuffer = mallocAndLoadFile_orDie(dictFileName, &dictSize);
|
||||
ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, cLevel);
|
||||
if (!cdict) {
|
||||
fprintf(stderr, "ZSTD_createCDict error \n");
|
||||
exit(7);
|
||||
}
|
||||
CHECK(cdict != NULL, "ZSTD_createCDict() failed!");
|
||||
free(dictBuffer);
|
||||
return cdict;
|
||||
}
|
||||
@ -39,13 +34,16 @@ static void compress(const char* fname, const char* oname, const ZSTD_CDict* cdi
|
||||
size_t const cBuffSize = ZSTD_compressBound(fSize);
|
||||
void* const cBuff = malloc_orDie(cBuffSize);
|
||||
|
||||
/* Compress using the dictionary.
|
||||
* This function writes the dictionary id, and content size into the header.
|
||||
* But, it doesn't use a checksum. You can control these options using the
|
||||
* advanced API: ZSTD_CCtx_setParameter(), ZSTD_CCtx_refCDict(),
|
||||
* and ZSTD_compress2().
|
||||
*/
|
||||
ZSTD_CCtx* const cctx = ZSTD_createCCtx();
|
||||
if (cctx==NULL) { fprintf(stderr, "ZSTD_createCCtx() error \n"); exit(10); }
|
||||
CHECK(cctx != NULL, "ZSTD_createCCtx() failed!");
|
||||
size_t const cSize = ZSTD_compress_usingCDict(cctx, cBuff, cBuffSize, fBuff, fSize, cdict);
|
||||
if (ZSTD_isError(cSize)) {
|
||||
fprintf(stderr, "error compressing %s : %s \n", fname, ZSTD_getErrorName(cSize));
|
||||
exit(7);
|
||||
}
|
||||
CHECK_ZSTD(cSize);
|
||||
|
||||
saveFile_orDie(oname, cBuff, cSize);
|
||||
|
||||
|
@ -9,15 +9,10 @@
|
||||
*/
|
||||
|
||||
|
||||
|
||||
#include <stdlib.h> // malloc, exit
|
||||
#include <stdio.h> // printf
|
||||
#include <string.h> // strerror
|
||||
#include <errno.h> // errno
|
||||
#include <sys/stat.h> // stat
|
||||
#define ZSTD_STATIC_LINKING_ONLY // ZSTD_findDecompressedSize
|
||||
#include <stdlib.h> // free
|
||||
#include <zstd.h> // presumes zstd library is installed
|
||||
#include "utils.h"
|
||||
#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD()
|
||||
|
||||
/* createDict() :
|
||||
`dictFileName` is supposed to have been created using `zstd --train` */
|
||||
@ -27,7 +22,7 @@ static ZSTD_DDict* createDict_orDie(const char* dictFileName)
|
||||
printf("loading dictionary %s \n", dictFileName);
|
||||
void* const dictBuffer = mallocAndLoadFile_orDie(dictFileName, &dictSize);
|
||||
ZSTD_DDict* const ddict = ZSTD_createDDict(dictBuffer, dictSize);
|
||||
if (ddict==NULL) { fprintf(stderr, "ZSTD_createDDict error \n"); exit(5); }
|
||||
CHECK(ddict != NULL, "ZSTD_createDDict() failed!");
|
||||
free(dictBuffer);
|
||||
return ddict;
|
||||
}
|
||||
@ -36,24 +31,40 @@ static void decompress(const char* fname, const ZSTD_DDict* ddict)
|
||||
{
|
||||
size_t cSize;
|
||||
void* const cBuff = mallocAndLoadFile_orDie(fname, &cSize);
|
||||
unsigned long long const rSize = ZSTD_findDecompressedSize(cBuff, cSize);
|
||||
if (rSize==ZSTD_CONTENTSIZE_ERROR) {
|
||||
fprintf(stderr, "%s : it was not compressed by zstd.\n", fname);
|
||||
exit(5);
|
||||
} else if (rSize==ZSTD_CONTENTSIZE_UNKNOWN) {
|
||||
fprintf(stderr, "%s : original size unknown \n", fname);
|
||||
exit(6);
|
||||
}
|
||||
|
||||
/* Read the content size from the frame header. For simplicity we require
|
||||
* that it is always present. By default, zstd will write the content size
|
||||
* in the header when it is known. If you can't guarantee that the frame
|
||||
* content size is always written into the header, either use streaming
|
||||
* decompression, or ZSTD_decompressBound().
|
||||
*/
|
||||
unsigned long long const rSize = ZSTD_getFrameContentSize(cBuff, cSize);
|
||||
CHECK(rSize != ZSTD_CONTENTSIZE_ERROR, "%s: not compressed by zstd!", fname);
|
||||
CHECK(rSize != ZSTD_CONTENTSIZE_UNKNOWN, "%s: original size unknown!", fname);
|
||||
void* const rBuff = malloc_orDie((size_t)rSize);
|
||||
|
||||
/* Check that the dictionary ID matches.
|
||||
* If a non-zstd dictionary is used, then both will be zero.
|
||||
* By default zstd always writes the dictionary ID into the frame.
|
||||
* Zstd will check if there is a dictionary ID mismatch as well.
|
||||
*/
|
||||
unsigned const expectedDictID = ZSTD_getDictID_fromDDict(ddict);
|
||||
unsigned const actualDictID = ZSTD_getDictID_fromFrame(cBuff, cSize);
|
||||
CHECK(actualDictID == expectedDictID,
|
||||
"DictID mismatch: expected %u got %u",
|
||||
expectedDictID,
|
||||
actualDictID);
|
||||
|
||||
/* Decompress using the dictionary.
|
||||
* If you need to control the decompression parameters, then use the
|
||||
* advanced API: ZSTD_DCtx_setParameter(), ZSTD_DCtx_refDDict(), and
|
||||
* ZSTD_decompressDCtx().
|
||||
*/
|
||||
ZSTD_DCtx* const dctx = ZSTD_createDCtx();
|
||||
if (dctx==NULL) { fprintf(stderr, "ZSTD_createDCtx() error \n"); exit(10); }
|
||||
CHECK(dctx != NULL, "ZSTD_createDCtx() failed!");
|
||||
size_t const dSize = ZSTD_decompress_usingDDict(dctx, rBuff, rSize, cBuff, cSize, ddict);
|
||||
if (dSize != rSize) {
|
||||
fprintf(stderr, "error decoding %s : %s \n", fname, ZSTD_getErrorName(dSize));
|
||||
exit(7);
|
||||
}
|
||||
CHECK_ZSTD(dSize);
|
||||
/* When zstd knows the content size, it will error if it doesn't match. */
|
||||
CHECK(dSize == rSize, "Impossible because zstd will check this condition!");
|
||||
|
||||
/* success */
|
||||
printf("%25s : %6u -> %7u \n", fname, (unsigned)cSize, (unsigned)rSize);
|
||||
|
@ -8,13 +8,11 @@
|
||||
* You may select, at your option, one of the above-listed licenses.
|
||||
*/
|
||||
|
||||
#include <stdlib.h> // malloc, free, exit
|
||||
#include <stdio.h> // fprintf, perror, fopen, etc.
|
||||
#include <string.h> // strlen, strcat, memset, strerror
|
||||
#include <errno.h> // errno
|
||||
#include <sys/stat.h> // stat
|
||||
#include <stdio.h> // printf
|
||||
#include <stdlib.h> // free
|
||||
#include <string.h> // memcpy, strlen
|
||||
#include <zstd.h> // presumes zstd library is installed
|
||||
#include "utils.h"
|
||||
#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD()
|
||||
|
||||
typedef struct {
|
||||
void* fBuffer;
|
||||
@ -52,7 +50,7 @@ static resources createResources_orDie(int argc, const char** argv, char **ofn,
|
||||
ress.fBuffer = malloc_orDie(ress.fBufferSize);
|
||||
ress.cBuffer = malloc_orDie(ress.cBufferSize);
|
||||
ress.cctx = ZSTD_createCCtx();
|
||||
if (ress.cctx==NULL) { fprintf(stderr, "ZSTD_createCCtx() error \n"); exit(10); }
|
||||
CHECK(ress.cctx != NULL, "ZSTD_createCCtx() failed!");
|
||||
return ress;
|
||||
}
|
||||
|
||||
@ -69,16 +67,17 @@ static void compressFile_orDie(resources ress, const char* fname, const char* on
|
||||
{
|
||||
size_t fSize = loadFile_orDie(fname, ress.fBuffer, ress.fBufferSize);
|
||||
|
||||
/* Compress using the context.
|
||||
* If you need more control over parameters, use the advanced API:
|
||||
* ZSTD_CCtx_setParameter(), and ZSTD_compress2().
|
||||
*/
|
||||
size_t const cSize = ZSTD_compressCCtx(ress.cctx, ress.cBuffer, ress.cBufferSize, ress.fBuffer, fSize, 1);
|
||||
if (ZSTD_isError(cSize)) {
|
||||
fprintf(stderr, "error compressing %s : %s \n", fname, ZSTD_getErrorName(cSize));
|
||||
exit(8);
|
||||
}
|
||||
CHECK_ZSTD(cSize);
|
||||
|
||||
saveFile_orDie(oname, ress.cBuffer, cSize);
|
||||
|
||||
/* success */
|
||||
// printf("%25s : %6u -> %7u - %s \n", fname, (unsigned)fSize, (unsigned)cSize, oname);
|
||||
printf("%25s : %6u -> %7u - %s \n", fname, (unsigned)fSize, (unsigned)cSize, oname);
|
||||
}
|
||||
|
||||
int main(int argc, const char** argv)
|
||||
@ -102,7 +101,7 @@ int main(int argc, const char** argv)
|
||||
for (argNb = 1; argNb < argc; argNb++) {
|
||||
const char* const inFilename = argv[argNb];
|
||||
size_t const inFilenameLen = strlen(inFilename);
|
||||
assert(inFilenameLen + 5 <= outFilenameBufferLen);
|
||||
CHECK(inFilenameLen + 5 <= outFilenameBufferLen, "File name too long!");
|
||||
memcpy(outFilename, inFilename, inFilenameLen);
|
||||
memcpy(outFilename+inFilenameLen, ".zst", 5);
|
||||
compressFile_orDie(ress, inFilename, outFilename);
|
||||
|
@ -14,66 +14,80 @@
|
||||
* All structures and buffers will be created only once,
|
||||
* and shared across all compression operations */
|
||||
|
||||
#include <stdlib.h> // malloc, exit
|
||||
#include <stdio.h> // fprintf, perror, feof
|
||||
#include <string.h> // strerror
|
||||
#include <errno.h> // errno
|
||||
#define ZSTD_STATIC_LINKING_ONLY // streaming API defined as "experimental" for the time being
|
||||
#include <stdio.h> // printf
|
||||
#include <stdlib.h> // free
|
||||
#include <string.h> // memset, strcat
|
||||
#include <zstd.h> // presumes zstd library is installed
|
||||
#include "utils.h"
|
||||
#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD()
|
||||
|
||||
typedef struct {
|
||||
void* buffIn;
|
||||
void* buffOut;
|
||||
size_t buffInSize;
|
||||
size_t buffOutSize;
|
||||
ZSTD_CStream* cstream;
|
||||
} resources ;
|
||||
ZSTD_CCtx* cctx;
|
||||
} resources;
|
||||
|
||||
static resources createResources_orDie()
|
||||
static resources createResources_orDie(int cLevel)
|
||||
{
|
||||
resources ress;
|
||||
ress.buffInSize = ZSTD_CStreamInSize(); /* can always read one full block */
|
||||
ress.buffOutSize= ZSTD_CStreamOutSize(); /* can always flush a full block */
|
||||
ress.buffIn = malloc_orDie(ress.buffInSize);
|
||||
ress.buffOut= malloc_orDie(ress.buffOutSize);
|
||||
ress.cstream = ZSTD_createCStream();
|
||||
if (ress.cstream==NULL) { fprintf(stderr, "ZSTD_createCStream() error \n"); exit(10); }
|
||||
ress.cctx = ZSTD_createCCtx();
|
||||
CHECK(ress.cctx != NULL, "ZSTD_createCCtx() failed!");
|
||||
|
||||
/* Set any compression parameters you want here.
|
||||
* They will persist for every compression operation.
|
||||
* Here we set the compression level, and enable the checksum.
|
||||
*/
|
||||
CHECK_ZSTD( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_compressionLevel, cLevel) );
|
||||
CHECK_ZSTD( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_checksumFlag, 1) );
|
||||
return ress;
|
||||
}
|
||||
|
||||
static void freeResources(resources ress)
|
||||
{
|
||||
ZSTD_freeCStream(ress.cstream);
|
||||
ZSTD_freeCCtx(ress.cctx);
|
||||
free(ress.buffIn);
|
||||
free(ress.buffOut);
|
||||
}
|
||||
|
||||
static void compressFile_orDie(resources ress, const char* fname, const char* outName, int cLevel)
|
||||
static void compressFile_orDie(resources ress, const char* fname, const char* outName)
|
||||
{
|
||||
// Open the input and output files.
|
||||
FILE* const fin = fopen_orDie(fname, "rb");
|
||||
FILE* const fout = fopen_orDie(outName, "wb");
|
||||
|
||||
size_t const initResult = ZSTD_initCStream(ress.cstream, cLevel);
|
||||
if (ZSTD_isError(initResult)) { fprintf(stderr, "ZSTD_initCStream() error : %s \n", ZSTD_getErrorName(initResult)); exit(11); }
|
||||
/* Reset the context to a clean state to start a new compression operation.
|
||||
* The parameters are sticky, so we keep the compression level and extra
|
||||
* parameters that we set in createResources_orDie().
|
||||
*/
|
||||
CHECK_ZSTD( ZSTD_CCtx_reset(ress.cctx, ZSTD_reset_session_only) );
|
||||
|
||||
size_t const toRead = ress.buffInSize;
|
||||
size_t read;
|
||||
while ( (read = fread_orDie(ress.buffIn, toRead, fin)) ) {
|
||||
/* This loop is the same as streaming_compression.c.
|
||||
* See that file for detailed comments.
|
||||
*/
|
||||
int const lastChunk = (read < toRead);
|
||||
ZSTD_EndDirective const mode = lastChunk ? ZSTD_e_end : ZSTD_e_continue;
|
||||
|
||||
size_t read, toRead = ress.buffInSize;
|
||||
while( (read = fread_orDie(ress.buffIn, toRead, fin)) ) {
|
||||
ZSTD_inBuffer input = { ress.buffIn, read, 0 };
|
||||
while (input.pos < input.size) {
|
||||
int finished;
|
||||
do {
|
||||
ZSTD_outBuffer output = { ress.buffOut, ress.buffOutSize, 0 };
|
||||
toRead = ZSTD_compressStream(ress.cstream, &output , &input); /* toRead is guaranteed to be <= ZSTD_CStreamInSize() */
|
||||
if (ZSTD_isError(toRead)) { fprintf(stderr, "ZSTD_compressStream() error : %s \n", ZSTD_getErrorName(toRead)); exit(12); }
|
||||
if (toRead > ress.buffInSize) toRead = ress.buffInSize; /* Safely handle when `buffInSize` is manually changed to a smaller value */
|
||||
size_t const remaining = ZSTD_compressStream2(ress.cctx, &output, &input, mode);
|
||||
CHECK_ZSTD(remaining);
|
||||
fwrite_orDie(ress.buffOut, output.pos, fout);
|
||||
}
|
||||
finished = lastChunk ? (remaining == 0) : (input.pos == input.size);
|
||||
} while (!finished);
|
||||
CHECK(input.pos == input.size,
|
||||
"Impossible: zstd only returns 0 when the input is completely consumed!");
|
||||
}
|
||||
|
||||
ZSTD_outBuffer output = { ress.buffOut, ress.buffOutSize, 0 };
|
||||
size_t const remainingToFlush = ZSTD_endStream(ress.cstream, &output); /* close frame */
|
||||
if (remainingToFlush) { fprintf(stderr, "not fully flushed"); exit(13); }
|
||||
fwrite_orDie(ress.buffOut, output.pos, fout);
|
||||
|
||||
fclose_orDie(fout);
|
||||
fclose_orDie(fin);
|
||||
}
|
||||
@ -89,7 +103,8 @@ int main(int argc, const char** argv)
|
||||
return 1;
|
||||
}
|
||||
|
||||
resources const ress = createResources_orDie();
|
||||
int const cLevel = 7;
|
||||
resources const ress = createResources_orDie(cLevel);
|
||||
void* ofnBuffer = NULL;
|
||||
size_t ofnbSize = 0;
|
||||
|
||||
@ -106,7 +121,7 @@ int main(int argc, const char** argv)
|
||||
memset(ofnBuffer, 0, ofnSize);
|
||||
strcat(ofnBuffer, ifn);
|
||||
strcat(ofnBuffer, ".zst");
|
||||
compressFile_orDie(ress, ifn, ofnBuffer, 7);
|
||||
compressFile_orDie(ress, ifn, ofnBuffer);
|
||||
}
|
||||
|
||||
freeResources(ress);
|
||||
|
@ -8,13 +8,11 @@
|
||||
* You may select, at your option, one of the above-listed licenses.
|
||||
*/
|
||||
|
||||
#include <stdlib.h> // malloc, free, exit
|
||||
#include <stdio.h> // fprintf, perror, fopen, etc.
|
||||
#include <string.h> // strlen, strcat, memset, strerror
|
||||
#include <errno.h> // errno
|
||||
#include <sys/stat.h> // stat
|
||||
#include <stdio.h> // printf
|
||||
#include <stdlib.h> // free
|
||||
#include <string.h> // strlen, strcat, memset
|
||||
#include <zstd.h> // presumes zstd library is installed
|
||||
#include "utils.h"
|
||||
#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD()
|
||||
|
||||
static void compress_orDie(const char* fname, const char* oname)
|
||||
{
|
||||
@ -23,11 +21,12 @@ static void compress_orDie(const char* fname, const char* oname)
|
||||
size_t const cBuffSize = ZSTD_compressBound(fSize);
|
||||
void* const cBuff = malloc_orDie(cBuffSize);
|
||||
|
||||
/* Compress.
|
||||
* If you are doing many compressions, you may want to reuse the context.
|
||||
* See the multiple_simple_compression.c example.
|
||||
*/
|
||||
size_t const cSize = ZSTD_compress(cBuff, cBuffSize, fBuff, fSize, 1);
|
||||
if (ZSTD_isError(cSize)) {
|
||||
fprintf(stderr, "error compressing %s : %s \n", fname, ZSTD_getErrorName(cSize));
|
||||
exit(8);
|
||||
}
|
||||
CHECK_ZSTD(cSize);
|
||||
|
||||
saveFile_orDie(oname, cBuff, cSize);
|
||||
|
||||
|
@ -8,37 +8,36 @@
|
||||
* You may select, at your option, one of the above-listed licenses.
|
||||
*/
|
||||
|
||||
#include <stdlib.h> // malloc, exit
|
||||
#include <stdio.h> // printf
|
||||
#include <string.h> // strerror
|
||||
#include <errno.h> // errno
|
||||
#include <sys/stat.h> // stat
|
||||
#define ZSTD_STATIC_LINKING_ONLY // ZSTD_findDecompressedSize
|
||||
#include <stdlib.h> // free
|
||||
#include <zstd.h> // presumes zstd library is installed
|
||||
#include "utils.h"
|
||||
#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD()
|
||||
|
||||
static void decompress(const char* fname)
|
||||
{
|
||||
size_t cSize;
|
||||
void* const cBuff = mallocAndLoadFile_orDie(fname, &cSize);
|
||||
unsigned long long const rSize = ZSTD_findDecompressedSize(cBuff, cSize);
|
||||
if (rSize==ZSTD_CONTENTSIZE_ERROR) {
|
||||
fprintf(stderr, "%s : it was not compressed by zstd.\n", fname);
|
||||
exit(5);
|
||||
} else if (rSize==ZSTD_CONTENTSIZE_UNKNOWN) {
|
||||
fprintf(stderr,
|
||||
"%s : original size unknown. Use streaming decompression instead.\n", fname);
|
||||
exit(6);
|
||||
}
|
||||
/* Read the content size from the frame header. For simplicity we require
|
||||
* that it is always present. By default, zstd will write the content size
|
||||
* in the header when it is known. If you can't guarantee that the frame
|
||||
* content size is always written into the header, either use streaming
|
||||
* decompression, or ZSTD_decompressBound().
|
||||
*/
|
||||
unsigned long long const rSize = ZSTD_getFrameContentSize(cBuff, cSize);
|
||||
CHECK(rSize != ZSTD_CONTENTSIZE_ERROR, "%s: not compressed by zstd!", fname);
|
||||
CHECK(rSize != ZSTD_CONTENTSIZE_UNKNOWN, "%s: original size unknown!", fname);
|
||||
|
||||
void* const rBuff = malloc_orDie((size_t)rSize);
|
||||
|
||||
/* Decompress.
|
||||
* If you are doing many decompressions, you may want to reuse the context
|
||||
* and use ZSTD_decompressDCtx(). If you want to set advanced parameters,
|
||||
* use ZSTD_DCtx_setParameter().
|
||||
*/
|
||||
size_t const dSize = ZSTD_decompress(rBuff, rSize, cBuff, cSize);
|
||||
|
||||
if (dSize != rSize) {
|
||||
fprintf(stderr, "error decoding %s : %s \n", fname, ZSTD_getErrorName(dSize));
|
||||
exit(7);
|
||||
}
|
||||
CHECK_ZSTD(dSize);
|
||||
/* When zstd knows the content size, it will error if it doesn't match. */
|
||||
CHECK(dSize == rSize, "Impossible because zstd will check this condition!");
|
||||
|
||||
/* success */
|
||||
printf("%25s : %6u -> %7u \n", fname, (unsigned)cSize, (unsigned)rSize);
|
||||
|
@ -9,54 +9,79 @@
|
||||
*/
|
||||
|
||||
|
||||
#include <stdlib.h> // malloc, free, exit
|
||||
#include <stdio.h> // fprintf, perror, feof, fopen, etc.
|
||||
#include <string.h> // strlen, memset, strcat
|
||||
#include <stdio.h> // printf
|
||||
#include <stdlib.h> // free
|
||||
#include <string.h> // memset, strcat, strlen
|
||||
#include <zstd.h> // presumes zstd library is installed
|
||||
#include "utils.h"
|
||||
#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD()
|
||||
|
||||
|
||||
static void compressFile_orDie(const char* fname, const char* outName, int cLevel)
|
||||
{
|
||||
/* Open the input and output files. */
|
||||
FILE* const fin = fopen_orDie(fname, "rb");
|
||||
FILE* const fout = fopen_orDie(outName, "wb");
|
||||
size_t const buffInSize = ZSTD_CStreamInSize(); /* can always read one full block */
|
||||
/* Create the input and output buffers.
|
||||
* They may be any size, but we recommend using these functions to size them.
|
||||
* Performance will only suffer significantly for very tiny buffers.
|
||||
*/
|
||||
size_t const buffInSize = ZSTD_CStreamInSize();
|
||||
void* const buffIn = malloc_orDie(buffInSize);
|
||||
size_t const buffOutSize = ZSTD_CStreamOutSize(); /* can always flush a full block */
|
||||
size_t const buffOutSize = ZSTD_CStreamOutSize();
|
||||
void* const buffOut = malloc_orDie(buffOutSize);
|
||||
|
||||
ZSTD_CStream* const cstream = ZSTD_createCStream();
|
||||
if (cstream==NULL) { fprintf(stderr, "ZSTD_createCStream() error \n"); exit(10); }
|
||||
size_t const initResult = ZSTD_initCStream(cstream, cLevel);
|
||||
if (ZSTD_isError(initResult)) {
|
||||
fprintf(stderr, "ZSTD_initCStream() error : %s \n",
|
||||
ZSTD_getErrorName(initResult));
|
||||
exit(11);
|
||||
}
|
||||
/* Create the context. */
|
||||
ZSTD_CCtx* const cctx = ZSTD_createCCtx();
|
||||
CHECK(cctx != NULL, "ZSTD_createCCtx() failed!");
|
||||
|
||||
size_t read, toRead = buffInSize;
|
||||
while( (read = fread_orDie(buffIn, toRead, fin)) ) {
|
||||
/* Set any parameters you want.
|
||||
* Here we set the compression level, and enable the checksum.
|
||||
*/
|
||||
CHECK_ZSTD( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, cLevel) );
|
||||
CHECK_ZSTD( ZSTD_CCtx_setParameter(cctx, ZSTD_c_checksumFlag, 1) );
|
||||
|
||||
/* This loop read from the input file, compresses that entire chunk,
|
||||
* and writes all output produced to the output file.
|
||||
*/
|
||||
size_t const toRead = buffInSize;
|
||||
size_t read;
|
||||
while ((read = fread_orDie(buffIn, toRead, fin))) {
|
||||
/* Select the flush mode.
|
||||
* If the read may not be finished (read == toRead) we use
|
||||
* ZSTD_e_continue. If this is the last chunk, we use ZSTD_e_end.
|
||||
* Zstd optimizes the case where the first flush mode is ZSTD_e_end,
|
||||
* since it knows it is compressing the entire source in one pass.
|
||||
*/
|
||||
int const lastChunk = (read < toRead);
|
||||
ZSTD_EndDirective const mode = lastChunk ? ZSTD_e_end : ZSTD_e_continue;
|
||||
/* Set the input buffer to what we just read.
|
||||
* We compress until the input buffer is empty, each time flushing the
|
||||
* output.
|
||||
*/
|
||||
ZSTD_inBuffer input = { buffIn, read, 0 };
|
||||
while (input.pos < input.size) {
|
||||
int finished;
|
||||
do {
|
||||
/* Compress into the output buffer and write all of the output to
|
||||
* the file so we can reuse the buffer next iteration.
|
||||
*/
|
||||
ZSTD_outBuffer output = { buffOut, buffOutSize, 0 };
|
||||
toRead = ZSTD_compressStream(cstream, &output , &input); /* toRead is guaranteed to be <= ZSTD_CStreamInSize() */
|
||||
if (ZSTD_isError(toRead)) {
|
||||
fprintf(stderr, "ZSTD_compressStream() error : %s \n",
|
||||
ZSTD_getErrorName(toRead));
|
||||
exit(12);
|
||||
}
|
||||
if (toRead > buffInSize) toRead = buffInSize; /* Safely handle case when `buffInSize` is manually changed to a value < ZSTD_CStreamInSize()*/
|
||||
size_t const remaining = ZSTD_compressStream2(cctx, &output , &input, mode);
|
||||
CHECK_ZSTD(remaining);
|
||||
fwrite_orDie(buffOut, output.pos, fout);
|
||||
}
|
||||
/* If we're on the last chunk we're finished when zstd returns 0,
|
||||
* which means its consumed all the input AND finished the frame.
|
||||
* Otherwise, we're finished when we've consumed all the input.
|
||||
*/
|
||||
finished = lastChunk ? (remaining == 0) : (input.pos == input.size);
|
||||
} while (!finished);
|
||||
CHECK(input.pos == input.size,
|
||||
"Impossible: zstd only returns 0 when the input is completely consumed!");
|
||||
}
|
||||
|
||||
ZSTD_outBuffer output = { buffOut, buffOutSize, 0 };
|
||||
size_t const remainingToFlush = ZSTD_endStream(cstream, &output); /* close frame */
|
||||
if (remainingToFlush) { fprintf(stderr, "not fully flushed"); exit(13); }
|
||||
fwrite_orDie(buffOut, output.pos, fout);
|
||||
|
||||
ZSTD_freeCStream(cstream);
|
||||
ZSTD_freeCCtx(cctx);
|
||||
fclose_orDie(fout);
|
||||
fclose_orDie(fin); free(buffIn);
|
||||
fclose_orDie(fin);
|
||||
free(buffIn);
|
||||
free(buffOut);
|
||||
}
|
||||
|
||||
|
@ -9,12 +9,10 @@
|
||||
*/
|
||||
|
||||
|
||||
#include <stdlib.h> // malloc, exit
|
||||
#include <stdio.h> // fprintf, perror, feof
|
||||
#include <string.h> // strerror
|
||||
#include <errno.h> // errno
|
||||
#include <stdio.h> // fprintf
|
||||
#include <stdlib.h> // free
|
||||
#include <zstd.h> // presumes zstd library is installed
|
||||
#include "utils.h"
|
||||
#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD()
|
||||
|
||||
static void decompressFile_orDie(const char* fname)
|
||||
{
|
||||
@ -25,26 +23,40 @@ static void decompressFile_orDie(const char* fname)
|
||||
size_t const buffOutSize = ZSTD_DStreamOutSize(); /* Guarantee to successfully flush at least one complete compressed block in all circumstances. */
|
||||
void* const buffOut = malloc_orDie(buffOutSize);
|
||||
|
||||
ZSTD_DStream* const dstream = ZSTD_createDStream();
|
||||
if (dstream==NULL) { fprintf(stderr, "ZSTD_createDStream() error \n"); exit(10); }
|
||||
ZSTD_DCtx* const dctx = ZSTD_createDCtx();
|
||||
CHECK(dctx != NULL, "ZSTD_createDCtx() failed!");
|
||||
|
||||
/* In more complex scenarios, a file may consist of multiple appended frames (ex : pzstd).
|
||||
* The following example decompresses only the first frame.
|
||||
* It is compatible with other provided streaming examples */
|
||||
size_t const initResult = ZSTD_initDStream(dstream);
|
||||
if (ZSTD_isError(initResult)) { fprintf(stderr, "ZSTD_initDStream() error : %s \n", ZSTD_getErrorName(initResult)); exit(11); }
|
||||
size_t read, toRead = initResult;
|
||||
/* This loop assumes that the input file is one or more concatenated zstd
|
||||
* streams. This example won't work if there is trailing non-zstd data at
|
||||
* the end, but streaming decompression in general handles this case.
|
||||
* ZSTD_decompressStream() returns 0 exactly when the frame is completed,
|
||||
* and doesn't consume input after the frame.
|
||||
*/
|
||||
size_t const toRead = buffInSize;
|
||||
size_t read;
|
||||
while ( (read = fread_orDie(buffIn, toRead, fin)) ) {
|
||||
ZSTD_inBuffer input = { buffIn, read, 0 };
|
||||
/* Given a valid frame, zstd won't consume the last byte of the frame
|
||||
* until it has flushed all of the decompressed data of the frame.
|
||||
* Therefore, instead of checking if the return code is 0, we can
|
||||
* decompress just check if input.pos < input.size.
|
||||
*/
|
||||
while (input.pos < input.size) {
|
||||
ZSTD_outBuffer output = { buffOut, buffOutSize, 0 };
|
||||
toRead = ZSTD_decompressStream(dstream, &output , &input); /* toRead : size of next compressed block */
|
||||
if (ZSTD_isError(toRead)) { fprintf(stderr, "ZSTD_decompressStream() error : %s \n", ZSTD_getErrorName(toRead)); exit(12); }
|
||||
/* The return code is zero if the frame is complete, but there may
|
||||
* be multiple frames concatenated together. Zstd will automatically
|
||||
* reset the context when a frame is complete. Still, calling
|
||||
* ZSTD_DCtx_reset() can be useful to reset the context to a clean
|
||||
* state, for instance if the last decompression call returned an
|
||||
* error.
|
||||
*/
|
||||
size_t const ret = ZSTD_decompressStream(dctx, &output , &input);
|
||||
CHECK_ZSTD(ret);
|
||||
fwrite_orDie(buffOut, output.pos, fout);
|
||||
}
|
||||
}
|
||||
|
||||
ZSTD_freeDStream(dstream);
|
||||
ZSTD_freeDCtx(dctx);
|
||||
fclose_orDie(fin);
|
||||
fclose_orDie(fout);
|
||||
free(buffIn);
|
||||
|
@ -16,9 +16,10 @@
|
||||
|
||||
|
||||
/*=== Dependencies ===*/
|
||||
#include <stdio.h> /* printf */
|
||||
#include <stdio.h> // printf
|
||||
#define ZSTD_STATIC_LINKING_ONLY
|
||||
#include "zstd.h"
|
||||
#include <zstd.h> // presumes zstd library is installed
|
||||
#include "common.h" // Helper functions, CHECK(), and CHECK_ZSTD()
|
||||
|
||||
|
||||
/*=== functions ===*/
|
||||
@ -61,90 +62,75 @@ int main(int argc, char const *argv[]) {
|
||||
char const dataToCompress[INPUT_SIZE] = "abcde";
|
||||
char compressedData[COMPRESSED_SIZE];
|
||||
char decompressedData[INPUT_SIZE];
|
||||
ZSTD_CStream* const cstream = ZSTD_createCStream();
|
||||
if (cstream==NULL) {
|
||||
printf("Level %i : ZSTD_CStream Memory allocation failure \n", compressionLevel);
|
||||
return 1;
|
||||
}
|
||||
/* the ZSTD_CCtx_params structure is a way to save parameters and use
|
||||
* them across multiple contexts. We use them here so we can call the
|
||||
* function ZSTD_estimateCStreamSize_usingCCtxParams().
|
||||
*/
|
||||
ZSTD_CCtx_params* const cctxParams = ZSTD_createCCtxParams();
|
||||
CHECK(cctxParams != NULL, "ZSTD_createCCtxParams() failed!");
|
||||
|
||||
/* forces compressor to use maximum memory size for given compression level,
|
||||
* by not providing any information on input size */
|
||||
ZSTD_parameters params = ZSTD_getParams(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, 0);
|
||||
if (wLog) { /* special mode : specific wLog */
|
||||
printf("Using custom compression parameter : level 1 + wLog=%u \n", wLog);
|
||||
params = ZSTD_getParams(1 /*compressionLevel*/,
|
||||
1 << wLog /*estimatedSrcSize*/,
|
||||
0 /*no dictionary*/);
|
||||
size_t const error = ZSTD_initCStream_advanced(cstream, NULL, 0, params, ZSTD_CONTENTSIZE_UNKNOWN);
|
||||
if (ZSTD_isError(error)) {
|
||||
printf("ZSTD_initCStream_advanced error : %s \n", ZSTD_getErrorName(error));
|
||||
return 1;
|
||||
}
|
||||
} else {
|
||||
size_t const error = ZSTD_initCStream(cstream, compressionLevel);
|
||||
if (ZSTD_isError(error)) {
|
||||
printf("ZSTD_initCStream error : %s \n", ZSTD_getErrorName(error));
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
/* Set the compression level. */
|
||||
CHECK_ZSTD( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_compressionLevel, compressionLevel) );
|
||||
/* Set the window log.
|
||||
* The value 0 means use the default window log, which is equivalent to
|
||||
* not setting it.
|
||||
*/
|
||||
CHECK_ZSTD( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_windowLog, wLog) );
|
||||
|
||||
/* Force the compressor to allocate the maximum memory size for a given
|
||||
* level by not providing the pledged source size, or calling
|
||||
* ZSTD_compressStream2() with ZSTD_e_end.
|
||||
*/
|
||||
ZSTD_CCtx* const cctx = ZSTD_createCCtx();
|
||||
CHECK(cctx != NULL, "ZSTD_createCCtx() failed!");
|
||||
CHECK_ZSTD( ZSTD_CCtx_setParametersUsingCCtxParams(cctx, cctxParams) );
|
||||
size_t compressedSize;
|
||||
{ ZSTD_inBuffer inBuff = { dataToCompress, sizeof(dataToCompress), 0 };
|
||||
{
|
||||
ZSTD_inBuffer inBuff = { dataToCompress, sizeof(dataToCompress), 0 };
|
||||
ZSTD_outBuffer outBuff = { compressedData, sizeof(compressedData), 0 };
|
||||
size_t const cError = ZSTD_compressStream(cstream, &outBuff, &inBuff);
|
||||
if (ZSTD_isError(cError)) {
|
||||
printf("ZSTD_compressStream error : %s \n", ZSTD_getErrorName(cError));
|
||||
return 1;
|
||||
}
|
||||
size_t const fError = ZSTD_endStream(cstream, &outBuff);
|
||||
if (ZSTD_isError(fError)) {
|
||||
printf("ZSTD_endStream error : %s \n", ZSTD_getErrorName(fError));
|
||||
return 1;
|
||||
}
|
||||
CHECK_ZSTD( ZSTD_compressStream(cctx, &outBuff, &inBuff) );
|
||||
size_t const remaining = ZSTD_endStream(cctx, &outBuff);
|
||||
CHECK_ZSTD(remaining);
|
||||
CHECK(remaining == 0, "Frame not flushed!");
|
||||
compressedSize = outBuff.pos;
|
||||
}
|
||||
|
||||
ZSTD_DStream* dstream = ZSTD_createDStream();
|
||||
if (dstream==NULL) {
|
||||
printf("Level %i : ZSTD_DStream Memory allocation failure \n", compressionLevel);
|
||||
return 1;
|
||||
}
|
||||
{ size_t const error = ZSTD_initDStream(dstream);
|
||||
if (ZSTD_isError(error)) {
|
||||
printf("ZSTD_initDStream error : %s \n", ZSTD_getErrorName(error));
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
/* forces decompressor to use maximum memory size, as decompressed size is not known */
|
||||
ZSTD_DCtx* const dctx = ZSTD_createDCtx();
|
||||
CHECK(dctx != NULL, "ZSTD_createDCtx() failed!");
|
||||
/* Set the maximum allowed window log.
|
||||
* The value 0 means use the default window log, which is equivalent to
|
||||
* not setting it.
|
||||
*/
|
||||
CHECK_ZSTD( ZSTD_DCtx_setParameter(dctx, ZSTD_d_windowLogMax, wLog) );
|
||||
/* forces decompressor to use maximum memory size, since the
|
||||
* decompressed size is not stored in the frame header.
|
||||
*/
|
||||
{ ZSTD_inBuffer inBuff = { compressedData, compressedSize, 0 };
|
||||
ZSTD_outBuffer outBuff = { decompressedData, sizeof(decompressedData), 0 };
|
||||
size_t const dResult = ZSTD_decompressStream(dstream, &outBuff, &inBuff);
|
||||
if (ZSTD_isError(dResult)) {
|
||||
printf("ZSTD_decompressStream error : %s \n", ZSTD_getErrorName(dResult));
|
||||
return 1;
|
||||
}
|
||||
if (dResult != 0) {
|
||||
printf("ZSTD_decompressStream error : unfinished decompression \n");
|
||||
return 1;
|
||||
}
|
||||
if (outBuff.pos != sizeof(dataToCompress)) {
|
||||
printf("ZSTD_decompressStream error : incorrect decompression \n");
|
||||
return 1;
|
||||
}
|
||||
size_t const remaining = ZSTD_decompressStream(dctx, &outBuff, &inBuff);
|
||||
CHECK_ZSTD(remaining);
|
||||
CHECK(remaining == 0, "Frame not complete!");
|
||||
CHECK(outBuff.pos == sizeof(dataToCompress), "Bad decompression!");
|
||||
}
|
||||
|
||||
size_t const cstreamSize = ZSTD_sizeof_CStream(cstream);
|
||||
size_t const cstreamEstimatedSize = wLog ?
|
||||
ZSTD_estimateCStreamSize_usingCParams(params.cParams) :
|
||||
ZSTD_estimateCStreamSize(compressionLevel);
|
||||
size_t const dstreamSize = ZSTD_sizeof_DStream(dstream);
|
||||
size_t const cstreamSize = ZSTD_sizeof_CStream(cctx);
|
||||
size_t const cstreamEstimatedSize = ZSTD_estimateCStreamSize_usingCCtxParams(cctxParams);
|
||||
size_t const dstreamSize = ZSTD_sizeof_DStream(dctx);
|
||||
size_t const dstreamEstimatedSize = ZSTD_estimateDStreamSize_fromFrame(compressedData, compressedSize);
|
||||
|
||||
printf("Level %2i : Compression Mem = %5u KB (estimated : %5u KB) ; Decompression Mem = %4u KB \n",
|
||||
CHECK(cstreamSize <= cstreamEstimatedSize, "Compression mem (%u) > estimated (%u)",
|
||||
(unsigned)cstreamSize, (unsigned)cstreamEstimatedSize);
|
||||
CHECK(dstreamSize <= dstreamEstimatedSize, "Decompression mem (%u) > estimated (%u)",
|
||||
(unsigned)dstreamSize, (unsigned)dstreamEstimatedSize);
|
||||
|
||||
printf("Level %2i : Compression Mem = %5u KB (estimated : %5u KB) ; Decompression Mem = %4u KB (estimated : %5u KB)\n",
|
||||
compressionLevel,
|
||||
(unsigned)(cstreamSize>>10), (unsigned)(cstreamEstimatedSize>>10), (unsigned)(dstreamSize>>10));
|
||||
(unsigned)(cstreamSize>>10), (unsigned)(cstreamEstimatedSize>>10),
|
||||
(unsigned)(dstreamSize>>10), (unsigned)(dstreamEstimatedSize>>10));
|
||||
|
||||
ZSTD_freeDStream(dstream);
|
||||
ZSTD_freeCStream(cstream);
|
||||
ZSTD_freeDCtx(dctx);
|
||||
ZSTD_freeCCtx(cctx);
|
||||
ZSTD_freeCCtxParams(cctxParams);
|
||||
if (wLog) break; /* single test */
|
||||
}
|
||||
return 0;
|
||||
|
10
lib/Makefile
10
lib/Makefile
@ -25,7 +25,7 @@ endif
|
||||
CFLAGS ?= -O3
|
||||
DEBUGFLAGS= -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
|
||||
-Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
|
||||
-Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security \
|
||||
-Wstrict-prototypes -Wundef -Wpointer-arith \
|
||||
-Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
|
||||
-Wredundant-decls -Wmissing-prototypes -Wc++-compat
|
||||
CFLAGS += $(DEBUGFLAGS) $(MOREFLAGS)
|
||||
@ -56,6 +56,7 @@ ZSTD_FORCE_DECOMPRESS_SHORT ?= 0
|
||||
ZSTD_FORCE_DECOMPRESS_LONG ?= 0
|
||||
ZSTD_NO_INLINE ?= 0
|
||||
ZSTD_STRIP_ERROR_STRINGS ?= 0
|
||||
ZSTD_LEGACY_MULTITHREADED_API ?= 0
|
||||
|
||||
ifeq ($(ZSTD_LIB_COMPRESSION), 0)
|
||||
ZSTD_LIB_DICTBUILDER = 0
|
||||
@ -107,6 +108,10 @@ ifneq ($(ZSTD_STRIP_ERROR_STRINGS), 0)
|
||||
CFLAGS += -DZSTD_STRIP_ERROR_STRINGS
|
||||
endif
|
||||
|
||||
ifneq ($(ZSTD_LEGACY_MULTITHREADED_API), 0)
|
||||
CFLAGS += -DZSTD_LEGACY_MULTITHREADED_API
|
||||
endif
|
||||
|
||||
ifneq ($(ZSTD_LEGACY_SUPPORT), 0)
|
||||
ifeq ($(shell test $(ZSTD_LEGACY_SUPPORT) -lt 8; echo $$?), 0)
|
||||
ZSTD_FILES += $(shell ls legacy/*.c | $(GREP) 'v0[$(ZSTD_LEGACY_SUPPORT)-7]')
|
||||
@ -151,8 +156,7 @@ ifneq (,$(filter Windows%,$(OS)))
|
||||
LIBZSTD = dll\libzstd.dll
|
||||
$(LIBZSTD): $(ZSTD_FILES)
|
||||
@echo compiling dynamic library $(LIBVER)
|
||||
@$(CC) $(FLAGS) -DZSTD_DLL_EXPORT=1 -shared $^ -o $@
|
||||
dlltool -D $@ -d dll\libzstd.def -l dll\libzstd.lib
|
||||
$(CC) $(FLAGS) -DZSTD_DLL_EXPORT=1 -Wl,--out-implib,dll\libzstd.lib -shared $^ -o $@
|
||||
|
||||
else
|
||||
|
||||
|
@ -31,8 +31,6 @@ note that it's necessary to request the `-pthread` flag during link stage.
|
||||
|
||||
Multithreading capabilities are exposed
|
||||
via the [advanced API defined in `lib/zstd.h`](https://github.com/facebook/zstd/blob/v1.3.8/lib/zstd.h#L592).
|
||||
This API is still labelled experimental,
|
||||
but is expected to become "stable" in the near future.
|
||||
|
||||
|
||||
#### API
|
||||
@ -110,6 +108,10 @@ The file structure is designed to make this selection manually achievable for an
|
||||
which removes the error messages that are otherwise returned by
|
||||
`ZSTD_getErrorName`.
|
||||
|
||||
- While invoking `make libzstd`, the build macro `ZSTD_LEGACY_MULTITHREADED_API=1`
|
||||
will expose the deprecated `ZSTDMT` API exposed by `zstdmt_compress.h` in
|
||||
the shared library, which is now hidden by default.
|
||||
|
||||
|
||||
#### Windows : using MinGW+MSYS to create DLL
|
||||
|
||||
|
@ -53,8 +53,50 @@ extern "C" {
|
||||
#undef MAX
|
||||
#define MIN(a,b) ((a)<(b) ? (a) : (b))
|
||||
#define MAX(a,b) ((a)>(b) ? (a) : (b))
|
||||
#define CHECK_F(f) { size_t const errcod = f; if (ERR_isError(errcod)) return errcod; } /* check and Forward error code */
|
||||
#define CHECK_E(f, e) { size_t const errcod = f; if (ERR_isError(errcod)) return ERROR(e); } /* check and send Error code */
|
||||
|
||||
/**
|
||||
* Return the specified error if the condition evaluates to true.
|
||||
*
|
||||
* In debug modes, prints additional information. In order to do that
|
||||
* (particularly, printing the conditional that failed), this can't just wrap
|
||||
* RETURN_ERROR().
|
||||
*/
|
||||
#define RETURN_ERROR_IF(cond, err, ...) \
|
||||
if (cond) { \
|
||||
RAWLOG(3, "%s:%d: ERROR!: check %s failed, returning %s", __FILE__, __LINE__, ZSTD_QUOTE(cond), ZSTD_QUOTE(ERROR(err))); \
|
||||
RAWLOG(3, ": " __VA_ARGS__); \
|
||||
RAWLOG(3, "\n"); \
|
||||
return ERROR(err); \
|
||||
}
|
||||
|
||||
/**
|
||||
* Unconditionally return the specified error.
|
||||
*
|
||||
* In debug modes, prints additional information.
|
||||
*/
|
||||
#define RETURN_ERROR(err, ...) \
|
||||
do { \
|
||||
RAWLOG(3, "%s:%d: ERROR!: unconditional check failed, returning %s", __FILE__, __LINE__, ZSTD_QUOTE(ERROR(err))); \
|
||||
RAWLOG(3, ": " __VA_ARGS__); \
|
||||
RAWLOG(3, "\n"); \
|
||||
return ERROR(err); \
|
||||
} while(0);
|
||||
|
||||
/**
|
||||
* If the provided expression evaluates to an error code, returns that error code.
|
||||
*
|
||||
* In debug modes, prints additional information.
|
||||
*/
|
||||
#define FORWARD_IF_ERROR(err, ...) \
|
||||
do { \
|
||||
size_t const err_code = (err); \
|
||||
if (ERR_isError(err_code)) { \
|
||||
RAWLOG(3, "%s:%d: ERROR!: forwarding error in %s: %s", __FILE__, __LINE__, ZSTD_QUOTE(err), ERR_getErrorName(err_code)); \
|
||||
RAWLOG(3, ": " __VA_ARGS__); \
|
||||
RAWLOG(3, "\n"); \
|
||||
return err_code; \
|
||||
} \
|
||||
} while(0);
|
||||
|
||||
|
||||
/*-*************************************
|
||||
@ -200,6 +242,17 @@ typedef struct {
|
||||
U32 longLengthPos;
|
||||
} seqStore_t;
|
||||
|
||||
/**
|
||||
* Contains the compressed frame size and an upper-bound for the decompressed frame size.
|
||||
* Note: before using `compressedSize`, check for errors using ZSTD_isError().
|
||||
* similarly, before using `decompressedBound`, check for errors using:
|
||||
* `decompressedBound != ZSTD_CONTENTSIZE_ERROR`
|
||||
*/
|
||||
typedef struct {
|
||||
size_t compressedSize;
|
||||
unsigned long long decompressedBound;
|
||||
} ZSTD_frameSizeInfo; /* decompress & legacy */
|
||||
|
||||
const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx); /* compress & dictBuilder */
|
||||
void ZSTD_seqToCodes(const seqStore_t* seqStorePtr); /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */
|
||||
|
||||
|
File diff suppressed because it is too large
Load Diff
@ -54,6 +54,14 @@ typedef struct ZSTD_prefixDict_s {
|
||||
ZSTD_dictContentType_e dictContentType;
|
||||
} ZSTD_prefixDict;
|
||||
|
||||
typedef struct {
|
||||
void* dictBuffer;
|
||||
void const* dict;
|
||||
size_t dictSize;
|
||||
ZSTD_dictContentType_e dictContentType;
|
||||
ZSTD_CDict* cdict;
|
||||
} ZSTD_localDict;
|
||||
|
||||
typedef struct {
|
||||
U32 CTable[HUF_CTABLE_SIZE_U32(255)];
|
||||
HUF_repeat repeatMode;
|
||||
@ -107,6 +115,7 @@ typedef struct {
|
||||
U32 offCodeSumBasePrice; /* to compare to log2(offreq) */
|
||||
ZSTD_OptPrice_e priceType; /* prices can be determined dynamically, or follow a pre-defined cost structure */
|
||||
const ZSTD_entropyCTables_t* symbolCosts; /* pre-calculated dictionary statistics */
|
||||
ZSTD_literalCompressionMode_e literalCompressionMode;
|
||||
} optState_t;
|
||||
|
||||
typedef struct {
|
||||
@ -188,6 +197,7 @@ struct ZSTD_CCtx_params_s {
|
||||
* 1<<wLog, even for dictionary */
|
||||
|
||||
ZSTD_dictAttachPref_e attachDictPref;
|
||||
ZSTD_literalCompressionMode_e literalCompressionMode;
|
||||
|
||||
/* Multithreading: used to pass parameters to mtctx */
|
||||
int nbWorkers;
|
||||
@ -243,7 +253,7 @@ struct ZSTD_CCtx_s {
|
||||
U32 frameEnded;
|
||||
|
||||
/* Dictionary */
|
||||
ZSTD_CDict* cdictLocal;
|
||||
ZSTD_localDict localDict;
|
||||
const ZSTD_CDict* cdict;
|
||||
ZSTD_prefixDict prefixDict; /* single-usage dictionary */
|
||||
|
||||
@ -806,13 +816,6 @@ size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
|
||||
|
||||
void ZSTD_resetSeqStore(seqStore_t* ssPtr);
|
||||
|
||||
/*! 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_getCParamsFromCDict() :
|
||||
* as the name implies */
|
||||
ZSTD_compressionParameters ZSTD_getCParamsFromCDict(const ZSTD_CDict* cdict);
|
||||
|
@ -45,7 +45,155 @@ FORCE_INLINE_TEMPLATE
|
||||
size_t ZSTD_compressBlock_fast_generic(
|
||||
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
||||
void const* src, size_t srcSize,
|
||||
U32 const mls, ZSTD_dictMode_e const dictMode)
|
||||
U32 const mls)
|
||||
{
|
||||
const ZSTD_compressionParameters* const cParams = &ms->cParams;
|
||||
U32* const hashTable = ms->hashTable;
|
||||
U32 const hlog = cParams->hashLog;
|
||||
/* support stepSize of 0 */
|
||||
size_t const stepSize = cParams->targetLength + !(cParams->targetLength) + 1;
|
||||
const BYTE* const base = ms->window.base;
|
||||
const BYTE* const istart = (const BYTE*)src;
|
||||
/* We check ip0 (ip + 0) and ip1 (ip + 1) each loop */
|
||||
const BYTE* ip0 = istart;
|
||||
const BYTE* ip1;
|
||||
const BYTE* anchor = istart;
|
||||
const U32 prefixStartIndex = ms->window.dictLimit;
|
||||
const BYTE* const prefixStart = base + prefixStartIndex;
|
||||
const BYTE* const iend = istart + srcSize;
|
||||
const BYTE* const ilimit = iend - HASH_READ_SIZE;
|
||||
U32 offset_1=rep[0], offset_2=rep[1];
|
||||
U32 offsetSaved = 0;
|
||||
|
||||
/* init */
|
||||
ip0 += (ip0 == prefixStart);
|
||||
ip1 = ip0 + 1;
|
||||
{
|
||||
U32 const maxRep = (U32)(ip0 - prefixStart);
|
||||
if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
|
||||
if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
|
||||
}
|
||||
|
||||
/* Main Search Loop */
|
||||
while (ip1 < ilimit) { /* < instead of <=, because check at ip0+2 */
|
||||
size_t mLength;
|
||||
BYTE const* ip2 = ip0 + 2;
|
||||
size_t const h0 = ZSTD_hashPtr(ip0, hlog, mls);
|
||||
U32 const val0 = MEM_read32(ip0);
|
||||
size_t const h1 = ZSTD_hashPtr(ip1, hlog, mls);
|
||||
U32 const val1 = MEM_read32(ip1);
|
||||
U32 const current0 = (U32)(ip0-base);
|
||||
U32 const current1 = (U32)(ip1-base);
|
||||
U32 const matchIndex0 = hashTable[h0];
|
||||
U32 const matchIndex1 = hashTable[h1];
|
||||
BYTE const* repMatch = ip2-offset_1;
|
||||
const BYTE* match0 = base + matchIndex0;
|
||||
const BYTE* match1 = base + matchIndex1;
|
||||
U32 offcode;
|
||||
hashTable[h0] = current0; /* update hash table */
|
||||
hashTable[h1] = current1; /* update hash table */
|
||||
|
||||
assert(ip0 + 1 == ip1);
|
||||
|
||||
if ((offset_1 > 0) & (MEM_read32(repMatch) == MEM_read32(ip2))) {
|
||||
mLength = ip2[-1] == repMatch[-1] ? 1 : 0;
|
||||
ip0 = ip2 - mLength;
|
||||
match0 = repMatch - mLength;
|
||||
offcode = 0;
|
||||
goto _match;
|
||||
}
|
||||
if ((matchIndex0 > prefixStartIndex) && MEM_read32(match0) == val0) {
|
||||
/* found a regular match */
|
||||
goto _offset;
|
||||
}
|
||||
if ((matchIndex1 > prefixStartIndex) && MEM_read32(match1) == val1) {
|
||||
/* found a regular match after one literal */
|
||||
ip0 = ip1;
|
||||
match0 = match1;
|
||||
goto _offset;
|
||||
}
|
||||
{
|
||||
size_t const step = ((ip0-anchor) >> (kSearchStrength - 1)) + stepSize;
|
||||
assert(step >= 2);
|
||||
ip0 += step;
|
||||
ip1 += step;
|
||||
continue;
|
||||
}
|
||||
_offset: /* Requires: ip0, match0 */
|
||||
/* Compute the offset code */
|
||||
offset_2 = offset_1;
|
||||
offset_1 = (U32)(ip0-match0);
|
||||
offcode = offset_1 + ZSTD_REP_MOVE;
|
||||
mLength = 0;
|
||||
/* Count the backwards match length */
|
||||
while (((ip0>anchor) & (match0>prefixStart))
|
||||
&& (ip0[-1] == match0[-1])) { ip0--; match0--; mLength++; } /* catch up */
|
||||
|
||||
_match: /* Requires: ip0, match0, offcode */
|
||||
/* Count the forward length */
|
||||
mLength += ZSTD_count(ip0+mLength+4, match0+mLength+4, iend) + 4;
|
||||
ZSTD_storeSeq(seqStore, ip0-anchor, anchor, offcode, mLength-MINMATCH);
|
||||
/* match found */
|
||||
ip0 += mLength;
|
||||
anchor = ip0;
|
||||
ip1 = ip0 + 1;
|
||||
|
||||
if (ip0 <= ilimit) {
|
||||
/* Fill Table */
|
||||
assert(base+current0+2 > istart); /* check base overflow */
|
||||
hashTable[ZSTD_hashPtr(base+current0+2, hlog, mls)] = current0+2; /* here because current+2 could be > iend-8 */
|
||||
hashTable[ZSTD_hashPtr(ip0-2, hlog, mls)] = (U32)(ip0-2-base);
|
||||
|
||||
while ( (ip0 <= ilimit)
|
||||
&& ( (offset_2>0)
|
||||
& (MEM_read32(ip0) == MEM_read32(ip0 - offset_2)) )) {
|
||||
/* store sequence */
|
||||
size_t const rLength = ZSTD_count(ip0+4, ip0+4-offset_2, iend) + 4;
|
||||
U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff; /* swap offset_2 <=> offset_1 */
|
||||
hashTable[ZSTD_hashPtr(ip0, hlog, mls)] = (U32)(ip0-base);
|
||||
ip0 += rLength;
|
||||
ip1 = ip0 + 1;
|
||||
ZSTD_storeSeq(seqStore, 0, anchor, 0, rLength-MINMATCH);
|
||||
anchor = ip0;
|
||||
continue; /* faster when present (confirmed on gcc-8) ... (?) */
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/* save reps for next block */
|
||||
rep[0] = offset_1 ? offset_1 : offsetSaved;
|
||||
rep[1] = offset_2 ? offset_2 : offsetSaved;
|
||||
|
||||
/* Return the last literals size */
|
||||
return iend - anchor;
|
||||
}
|
||||
|
||||
|
||||
size_t ZSTD_compressBlock_fast(
|
||||
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
||||
void const* src, size_t srcSize)
|
||||
{
|
||||
ZSTD_compressionParameters const* cParams = &ms->cParams;
|
||||
U32 const mls = cParams->minMatch;
|
||||
assert(ms->dictMatchState == NULL);
|
||||
switch(mls)
|
||||
{
|
||||
default: /* includes case 3 */
|
||||
case 4 :
|
||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4);
|
||||
case 5 :
|
||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5);
|
||||
case 6 :
|
||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6);
|
||||
case 7 :
|
||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7);
|
||||
}
|
||||
}
|
||||
|
||||
FORCE_INLINE_TEMPLATE
|
||||
size_t ZSTD_compressBlock_fast_dictMatchState_generic(
|
||||
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
||||
void const* src, size_t srcSize, U32 const mls)
|
||||
{
|
||||
const ZSTD_compressionParameters* const cParams = &ms->cParams;
|
||||
U32* const hashTable = ms->hashTable;
|
||||
@ -64,46 +212,26 @@ size_t ZSTD_compressBlock_fast_generic(
|
||||
U32 offsetSaved = 0;
|
||||
|
||||
const ZSTD_matchState_t* const dms = ms->dictMatchState;
|
||||
const ZSTD_compressionParameters* const dictCParams =
|
||||
dictMode == ZSTD_dictMatchState ?
|
||||
&dms->cParams : NULL;
|
||||
const U32* const dictHashTable = dictMode == ZSTD_dictMatchState ?
|
||||
dms->hashTable : NULL;
|
||||
const U32 dictStartIndex = dictMode == ZSTD_dictMatchState ?
|
||||
dms->window.dictLimit : 0;
|
||||
const BYTE* const dictBase = dictMode == ZSTD_dictMatchState ?
|
||||
dms->window.base : NULL;
|
||||
const BYTE* const dictStart = dictMode == ZSTD_dictMatchState ?
|
||||
dictBase + dictStartIndex : NULL;
|
||||
const BYTE* const dictEnd = dictMode == ZSTD_dictMatchState ?
|
||||
dms->window.nextSrc : NULL;
|
||||
const U32 dictIndexDelta = dictMode == ZSTD_dictMatchState ?
|
||||
prefixStartIndex - (U32)(dictEnd - dictBase) :
|
||||
0;
|
||||
const ZSTD_compressionParameters* const dictCParams = &dms->cParams ;
|
||||
const U32* const dictHashTable = dms->hashTable;
|
||||
const U32 dictStartIndex = dms->window.dictLimit;
|
||||
const BYTE* const dictBase = dms->window.base;
|
||||
const BYTE* const dictStart = dictBase + dictStartIndex;
|
||||
const BYTE* const dictEnd = dms->window.nextSrc;
|
||||
const U32 dictIndexDelta = prefixStartIndex - (U32)(dictEnd - dictBase);
|
||||
const U32 dictAndPrefixLength = (U32)(ip - prefixStart + dictEnd - dictStart);
|
||||
const U32 dictHLog = dictMode == ZSTD_dictMatchState ?
|
||||
dictCParams->hashLog : hlog;
|
||||
|
||||
assert(dictMode == ZSTD_noDict || dictMode == ZSTD_dictMatchState);
|
||||
const U32 dictHLog = dictCParams->hashLog;
|
||||
|
||||
/* otherwise, we would get index underflow when translating a dict index
|
||||
* into a local index */
|
||||
assert(dictMode != ZSTD_dictMatchState
|
||||
|| prefixStartIndex >= (U32)(dictEnd - dictBase));
|
||||
assert(prefixStartIndex >= (U32)(dictEnd - dictBase));
|
||||
|
||||
/* init */
|
||||
ip += (dictAndPrefixLength == 0);
|
||||
if (dictMode == ZSTD_noDict) {
|
||||
U32 const maxRep = (U32)(ip - prefixStart);
|
||||
if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
|
||||
if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
|
||||
}
|
||||
if (dictMode == ZSTD_dictMatchState) {
|
||||
/* dictMatchState repCode checks don't currently handle repCode == 0
|
||||
* disabling. */
|
||||
assert(offset_1 <= dictAndPrefixLength);
|
||||
assert(offset_2 <= dictAndPrefixLength);
|
||||
}
|
||||
/* dictMatchState repCode checks don't currently handle repCode == 0
|
||||
* disabling. */
|
||||
assert(offset_1 <= dictAndPrefixLength);
|
||||
assert(offset_2 <= dictAndPrefixLength);
|
||||
|
||||
/* Main Search Loop */
|
||||
while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */
|
||||
@ -113,50 +241,37 @@ size_t ZSTD_compressBlock_fast_generic(
|
||||
U32 const matchIndex = hashTable[h];
|
||||
const BYTE* match = base + matchIndex;
|
||||
const U32 repIndex = current + 1 - offset_1;
|
||||
const BYTE* repMatch = (dictMode == ZSTD_dictMatchState
|
||||
&& repIndex < prefixStartIndex) ?
|
||||
const BYTE* repMatch = (repIndex < prefixStartIndex) ?
|
||||
dictBase + (repIndex - dictIndexDelta) :
|
||||
base + repIndex;
|
||||
hashTable[h] = current; /* update hash table */
|
||||
|
||||
if ( (dictMode == ZSTD_dictMatchState)
|
||||
&& ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */
|
||||
if ( ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */
|
||||
&& (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
|
||||
const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
|
||||
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4;
|
||||
ip++;
|
||||
ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
|
||||
} else if ( dictMode == ZSTD_noDict
|
||||
&& ((offset_1 > 0) & (MEM_read32(ip+1-offset_1) == MEM_read32(ip+1)))) {
|
||||
mLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4;
|
||||
ip++;
|
||||
ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
|
||||
} else if ( (matchIndex <= prefixStartIndex) ) {
|
||||
if (dictMode == ZSTD_dictMatchState) {
|
||||
size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls);
|
||||
U32 const dictMatchIndex = dictHashTable[dictHash];
|
||||
const BYTE* dictMatch = dictBase + dictMatchIndex;
|
||||
if (dictMatchIndex <= dictStartIndex ||
|
||||
MEM_read32(dictMatch) != MEM_read32(ip)) {
|
||||
assert(stepSize >= 1);
|
||||
ip += ((ip-anchor) >> kSearchStrength) + stepSize;
|
||||
continue;
|
||||
} else {
|
||||
/* found a dict match */
|
||||
U32 const offset = (U32)(current-dictMatchIndex-dictIndexDelta);
|
||||
mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4;
|
||||
while (((ip>anchor) & (dictMatch>dictStart))
|
||||
&& (ip[-1] == dictMatch[-1])) {
|
||||
ip--; dictMatch--; mLength++;
|
||||
} /* catch up */
|
||||
offset_2 = offset_1;
|
||||
offset_1 = offset;
|
||||
ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
|
||||
}
|
||||
} else {
|
||||
size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls);
|
||||
U32 const dictMatchIndex = dictHashTable[dictHash];
|
||||
const BYTE* dictMatch = dictBase + dictMatchIndex;
|
||||
if (dictMatchIndex <= dictStartIndex ||
|
||||
MEM_read32(dictMatch) != MEM_read32(ip)) {
|
||||
assert(stepSize >= 1);
|
||||
ip += ((ip-anchor) >> kSearchStrength) + stepSize;
|
||||
continue;
|
||||
} else {
|
||||
/* found a dict match */
|
||||
U32 const offset = (U32)(current-dictMatchIndex-dictIndexDelta);
|
||||
mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4;
|
||||
while (((ip>anchor) & (dictMatch>dictStart))
|
||||
&& (ip[-1] == dictMatch[-1])) {
|
||||
ip--; dictMatch--; mLength++;
|
||||
} /* catch up */
|
||||
offset_2 = offset_1;
|
||||
offset_1 = offset;
|
||||
ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
|
||||
}
|
||||
} else if (MEM_read32(match) != MEM_read32(ip)) {
|
||||
/* it's not a match, and we're not going to check the dictionary */
|
||||
@ -185,41 +300,27 @@ size_t ZSTD_compressBlock_fast_generic(
|
||||
hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base);
|
||||
|
||||
/* check immediate repcode */
|
||||
if (dictMode == ZSTD_dictMatchState) {
|
||||
while (ip <= ilimit) {
|
||||
U32 const current2 = (U32)(ip-base);
|
||||
U32 const repIndex2 = current2 - offset_2;
|
||||
const BYTE* repMatch2 = repIndex2 < prefixStartIndex ?
|
||||
dictBase - dictIndexDelta + repIndex2 :
|
||||
base + repIndex2;
|
||||
if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
|
||||
&& (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
|
||||
const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
|
||||
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
|
||||
U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
|
||||
ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
|
||||
hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
|
||||
ip += repLength2;
|
||||
anchor = ip;
|
||||
continue;
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if (dictMode == ZSTD_noDict) {
|
||||
while ( (ip <= ilimit)
|
||||
&& ( (offset_2>0)
|
||||
& (MEM_read32(ip) == MEM_read32(ip - offset_2)) )) {
|
||||
/* store sequence */
|
||||
size_t const rLength = ZSTD_count(ip+4, ip+4-offset_2, iend) + 4;
|
||||
U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff; /* swap offset_2 <=> offset_1 */
|
||||
hashTable[ZSTD_hashPtr(ip, hlog, mls)] = (U32)(ip-base);
|
||||
ZSTD_storeSeq(seqStore, 0, anchor, 0, rLength-MINMATCH);
|
||||
ip += rLength;
|
||||
while (ip <= ilimit) {
|
||||
U32 const current2 = (U32)(ip-base);
|
||||
U32 const repIndex2 = current2 - offset_2;
|
||||
const BYTE* repMatch2 = repIndex2 < prefixStartIndex ?
|
||||
dictBase - dictIndexDelta + repIndex2 :
|
||||
base + repIndex2;
|
||||
if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
|
||||
&& (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
|
||||
const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
|
||||
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
|
||||
U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
|
||||
ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
|
||||
hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
|
||||
ip += repLength2;
|
||||
anchor = ip;
|
||||
continue; /* faster when present ... (?) */
|
||||
} } } }
|
||||
continue;
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/* save reps for next block */
|
||||
rep[0] = offset_1 ? offset_1 : offsetSaved;
|
||||
@ -229,28 +330,6 @@ size_t ZSTD_compressBlock_fast_generic(
|
||||
return iend - anchor;
|
||||
}
|
||||
|
||||
|
||||
size_t ZSTD_compressBlock_fast(
|
||||
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
||||
void const* src, size_t srcSize)
|
||||
{
|
||||
ZSTD_compressionParameters const* cParams = &ms->cParams;
|
||||
U32 const mls = cParams->minMatch;
|
||||
assert(ms->dictMatchState == NULL);
|
||||
switch(mls)
|
||||
{
|
||||
default: /* includes case 3 */
|
||||
case 4 :
|
||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_noDict);
|
||||
case 5 :
|
||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_noDict);
|
||||
case 6 :
|
||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_noDict);
|
||||
case 7 :
|
||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_noDict);
|
||||
}
|
||||
}
|
||||
|
||||
size_t ZSTD_compressBlock_fast_dictMatchState(
|
||||
ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
|
||||
void const* src, size_t srcSize)
|
||||
@ -262,13 +341,13 @@ size_t ZSTD_compressBlock_fast_dictMatchState(
|
||||
{
|
||||
default: /* includes case 3 */
|
||||
case 4 :
|
||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_dictMatchState);
|
||||
return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 4);
|
||||
case 5 :
|
||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_dictMatchState);
|
||||
return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 5);
|
||||
case 6 :
|
||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_dictMatchState);
|
||||
return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 6);
|
||||
case 7 :
|
||||
return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_dictMatchState);
|
||||
return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 7);
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -64,9 +64,15 @@ MEM_STATIC double ZSTD_fCost(U32 price)
|
||||
}
|
||||
#endif
|
||||
|
||||
static int ZSTD_compressedLiterals(optState_t const* const optPtr)
|
||||
{
|
||||
return optPtr->literalCompressionMode != ZSTD_lcm_uncompressed;
|
||||
}
|
||||
|
||||
static void ZSTD_setBasePrices(optState_t* optPtr, int optLevel)
|
||||
{
|
||||
optPtr->litSumBasePrice = WEIGHT(optPtr->litSum, optLevel);
|
||||
if (ZSTD_compressedLiterals(optPtr))
|
||||
optPtr->litSumBasePrice = WEIGHT(optPtr->litSum, optLevel);
|
||||
optPtr->litLengthSumBasePrice = WEIGHT(optPtr->litLengthSum, optLevel);
|
||||
optPtr->matchLengthSumBasePrice = WEIGHT(optPtr->matchLengthSum, optLevel);
|
||||
optPtr->offCodeSumBasePrice = WEIGHT(optPtr->offCodeSum, optLevel);
|
||||
@ -99,6 +105,7 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
|
||||
const BYTE* const src, size_t const srcSize,
|
||||
int const optLevel)
|
||||
{
|
||||
int const compressedLiterals = ZSTD_compressedLiterals(optPtr);
|
||||
DEBUGLOG(5, "ZSTD_rescaleFreqs (srcSize=%u)", (unsigned)srcSize);
|
||||
optPtr->priceType = zop_dynamic;
|
||||
|
||||
@ -113,9 +120,10 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
|
||||
/* huffman table presumed generated by dictionary */
|
||||
optPtr->priceType = zop_dynamic;
|
||||
|
||||
assert(optPtr->litFreq != NULL);
|
||||
optPtr->litSum = 0;
|
||||
{ unsigned lit;
|
||||
if (compressedLiterals) {
|
||||
unsigned lit;
|
||||
assert(optPtr->litFreq != NULL);
|
||||
optPtr->litSum = 0;
|
||||
for (lit=0; lit<=MaxLit; lit++) {
|
||||
U32 const scaleLog = 11; /* scale to 2K */
|
||||
U32 const bitCost = HUF_getNbBits(optPtr->symbolCosts->huf.CTable, lit);
|
||||
@ -163,10 +171,11 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
|
||||
} else { /* not a dictionary */
|
||||
|
||||
assert(optPtr->litFreq != NULL);
|
||||
{ unsigned lit = MaxLit;
|
||||
if (compressedLiterals) {
|
||||
unsigned lit = MaxLit;
|
||||
HIST_count_simple(optPtr->litFreq, &lit, src, srcSize); /* use raw first block to init statistics */
|
||||
optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
|
||||
}
|
||||
optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
|
||||
|
||||
{ unsigned ll;
|
||||
for (ll=0; ll<=MaxLL; ll++)
|
||||
@ -190,7 +199,8 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
|
||||
|
||||
} else { /* new block : re-use previous statistics, scaled down */
|
||||
|
||||
optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
|
||||
if (compressedLiterals)
|
||||
optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
|
||||
optPtr->litLengthSum = ZSTD_downscaleStat(optPtr->litLengthFreq, MaxLL, 0);
|
||||
optPtr->matchLengthSum = ZSTD_downscaleStat(optPtr->matchLengthFreq, MaxML, 0);
|
||||
optPtr->offCodeSum = ZSTD_downscaleStat(optPtr->offCodeFreq, MaxOff, 0);
|
||||
@ -207,6 +217,10 @@ static U32 ZSTD_rawLiteralsCost(const BYTE* const literals, U32 const litLength,
|
||||
int optLevel)
|
||||
{
|
||||
if (litLength == 0) return 0;
|
||||
|
||||
if (!ZSTD_compressedLiterals(optPtr))
|
||||
return (litLength << 3) * BITCOST_MULTIPLIER; /* Uncompressed - 8 bytes per literal. */
|
||||
|
||||
if (optPtr->priceType == zop_predef)
|
||||
return (litLength*6) * BITCOST_MULTIPLIER; /* 6 bit per literal - no statistic used */
|
||||
|
||||
@ -310,7 +324,8 @@ static void ZSTD_updateStats(optState_t* const optPtr,
|
||||
U32 offsetCode, U32 matchLength)
|
||||
{
|
||||
/* literals */
|
||||
{ U32 u;
|
||||
if (ZSTD_compressedLiterals(optPtr)) {
|
||||
U32 u;
|
||||
for (u=0; u < litLength; u++)
|
||||
optPtr->litFreq[literals[u]] += ZSTD_LITFREQ_ADD;
|
||||
optPtr->litSum += litLength*ZSTD_LITFREQ_ADD;
|
||||
@ -1108,7 +1123,8 @@ static U32 ZSTD_upscaleStat(unsigned* table, U32 lastEltIndex, int bonus)
|
||||
/* used in 2-pass strategy */
|
||||
MEM_STATIC void ZSTD_upscaleStats(optState_t* optPtr)
|
||||
{
|
||||
optPtr->litSum = ZSTD_upscaleStat(optPtr->litFreq, MaxLit, 0);
|
||||
if (ZSTD_compressedLiterals(optPtr))
|
||||
optPtr->litSum = ZSTD_upscaleStat(optPtr->litFreq, MaxLit, 0);
|
||||
optPtr->litLengthSum = ZSTD_upscaleStat(optPtr->litLengthFreq, MaxLL, 0);
|
||||
optPtr->matchLengthSum = ZSTD_upscaleStat(optPtr->matchLengthFreq, MaxML, 0);
|
||||
optPtr->offCodeSum = ZSTD_upscaleStat(optPtr->offCodeFreq, MaxOff, 0);
|
||||
|
@ -672,7 +672,7 @@ static void ZSTDMT_compressionJob(void* jobDescription)
|
||||
if (ZSTD_isError(initError)) JOB_ERROR(initError);
|
||||
} else { /* srcStart points at reloaded section */
|
||||
U64 const pledgedSrcSize = job->firstJob ? job->fullFrameSize : job->src.size;
|
||||
{ size_t const forceWindowError = ZSTD_CCtxParam_setParameter(&jobParams, ZSTD_c_forceMaxWindow, !job->firstJob);
|
||||
{ size_t const forceWindowError = ZSTD_CCtxParams_setParameter(&jobParams, ZSTD_c_forceMaxWindow, !job->firstJob);
|
||||
if (ZSTD_isError(forceWindowError)) JOB_ERROR(forceWindowError);
|
||||
}
|
||||
{ size_t const initError = ZSTD_compressBegin_advanced_internal(cctx,
|
||||
@ -864,11 +864,7 @@ static size_t ZSTDMT_expandJobsTable (ZSTDMT_CCtx* mtctx, U32 nbWorkers) {
|
||||
* Internal use only */
|
||||
size_t ZSTDMT_CCtxParam_setNbWorkers(ZSTD_CCtx_params* params, unsigned nbWorkers)
|
||||
{
|
||||
if (nbWorkers > ZSTDMT_NBWORKERS_MAX) nbWorkers = ZSTDMT_NBWORKERS_MAX;
|
||||
params->nbWorkers = nbWorkers;
|
||||
params->overlapLog = ZSTDMT_OVERLAPLOG_DEFAULT;
|
||||
params->jobSize = 0;
|
||||
return nbWorkers;
|
||||
return ZSTD_CCtxParams_setParameter(params, ZSTD_c_nbWorkers, (int)nbWorkers);
|
||||
}
|
||||
|
||||
ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem)
|
||||
@ -986,26 +982,13 @@ ZSTDMT_CCtxParam_setMTCtxParameter(ZSTD_CCtx_params* params,
|
||||
{
|
||||
case ZSTDMT_p_jobSize :
|
||||
DEBUGLOG(4, "ZSTDMT_CCtxParam_setMTCtxParameter : set jobSize to %i", value);
|
||||
if ( value != 0 /* default */
|
||||
&& value < ZSTDMT_JOBSIZE_MIN)
|
||||
value = ZSTDMT_JOBSIZE_MIN;
|
||||
assert(value >= 0);
|
||||
if (value > ZSTDMT_JOBSIZE_MAX) value = ZSTDMT_JOBSIZE_MAX;
|
||||
params->jobSize = value;
|
||||
return value;
|
||||
|
||||
return ZSTD_CCtxParams_setParameter(params, ZSTD_c_jobSize, value);
|
||||
case ZSTDMT_p_overlapLog :
|
||||
DEBUGLOG(4, "ZSTDMT_p_overlapLog : %i", value);
|
||||
if (value < ZSTD_OVERLAPLOG_MIN) value = ZSTD_OVERLAPLOG_MIN;
|
||||
if (value > ZSTD_OVERLAPLOG_MAX) value = ZSTD_OVERLAPLOG_MAX;
|
||||
params->overlapLog = value;
|
||||
return value;
|
||||
|
||||
return ZSTD_CCtxParams_setParameter(params, ZSTD_c_overlapLog, value);
|
||||
case ZSTDMT_p_rsyncable :
|
||||
value = (value != 0);
|
||||
params->rsyncable = value;
|
||||
return value;
|
||||
|
||||
DEBUGLOG(4, "ZSTD_p_rsyncable : %i", value);
|
||||
return ZSTD_CCtxParams_setParameter(params, ZSTD_c_rsyncable, value);
|
||||
default :
|
||||
return ERROR(parameter_unsupported);
|
||||
}
|
||||
@ -1021,32 +1004,29 @@ size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter,
|
||||
{
|
||||
switch (parameter) {
|
||||
case ZSTDMT_p_jobSize:
|
||||
assert(mtctx->params.jobSize <= INT_MAX);
|
||||
*value = (int)(mtctx->params.jobSize);
|
||||
break;
|
||||
return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_jobSize, value);
|
||||
case ZSTDMT_p_overlapLog:
|
||||
*value = mtctx->params.overlapLog;
|
||||
break;
|
||||
return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_overlapLog, value);
|
||||
case ZSTDMT_p_rsyncable:
|
||||
*value = mtctx->params.rsyncable;
|
||||
break;
|
||||
return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_rsyncable, value);
|
||||
default:
|
||||
return ERROR(parameter_unsupported);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Sets parameters relevant to the compression job,
|
||||
* initializing others to default values. */
|
||||
static ZSTD_CCtx_params ZSTDMT_initJobCCtxParams(ZSTD_CCtx_params const params)
|
||||
{
|
||||
ZSTD_CCtx_params jobParams;
|
||||
memset(&jobParams, 0, sizeof(jobParams));
|
||||
|
||||
jobParams.cParams = params.cParams;
|
||||
jobParams.fParams = params.fParams;
|
||||
jobParams.compressionLevel = params.compressionLevel;
|
||||
|
||||
ZSTD_CCtx_params jobParams = params;
|
||||
/* Clear parameters related to multithreading */
|
||||
jobParams.forceWindow = 0;
|
||||
jobParams.nbWorkers = 0;
|
||||
jobParams.jobSize = 0;
|
||||
jobParams.overlapLog = 0;
|
||||
jobParams.rsyncable = 0;
|
||||
memset(&jobParams.ldmParams, 0, sizeof(ldmParams_t));
|
||||
memset(&jobParams.customMem, 0, sizeof(ZSTD_customMem));
|
||||
return jobParams;
|
||||
}
|
||||
|
||||
@ -1056,7 +1036,7 @@ static ZSTD_CCtx_params ZSTDMT_initJobCCtxParams(ZSTD_CCtx_params const params)
|
||||
static size_t ZSTDMT_resize(ZSTDMT_CCtx* mtctx, unsigned nbWorkers)
|
||||
{
|
||||
if (POOL_resize(mtctx->factory, nbWorkers)) return ERROR(memory_allocation);
|
||||
CHECK_F( ZSTDMT_expandJobsTable(mtctx, nbWorkers) );
|
||||
FORWARD_IF_ERROR( ZSTDMT_expandJobsTable(mtctx, nbWorkers) );
|
||||
mtctx->bufPool = ZSTDMT_expandBufferPool(mtctx->bufPool, nbWorkers);
|
||||
if (mtctx->bufPool == NULL) return ERROR(memory_allocation);
|
||||
mtctx->cctxPool = ZSTDMT_expandCCtxPool(mtctx->cctxPool, nbWorkers);
|
||||
@ -1263,7 +1243,7 @@ static size_t ZSTDMT_compress_advanced_internal(
|
||||
if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params, avgJobSize))
|
||||
return ERROR(memory_allocation);
|
||||
|
||||
CHECK_F( ZSTDMT_expandJobsTable(mtctx, nbJobs) ); /* only expands if necessary */
|
||||
FORWARD_IF_ERROR( ZSTDMT_expandJobsTable(mtctx, nbJobs) ); /* only expands if necessary */
|
||||
|
||||
{ unsigned u;
|
||||
for (u=0; u<nbJobs; u++) {
|
||||
@ -1396,7 +1376,7 @@ size_t ZSTDMT_initCStream_internal(
|
||||
|
||||
/* init */
|
||||
if (params.nbWorkers != mtctx->params.nbWorkers)
|
||||
CHECK_F( ZSTDMT_resize(mtctx, params.nbWorkers) );
|
||||
FORWARD_IF_ERROR( ZSTDMT_resize(mtctx, params.nbWorkers) );
|
||||
|
||||
if (params.jobSize != 0 && params.jobSize < ZSTDMT_JOBSIZE_MIN) params.jobSize = ZSTDMT_JOBSIZE_MIN;
|
||||
if (params.jobSize > (size_t)ZSTDMT_JOBSIZE_MAX) params.jobSize = ZSTDMT_JOBSIZE_MAX;
|
||||
@ -1987,7 +1967,7 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
|
||||
assert(input->pos <= input->size);
|
||||
|
||||
if (mtctx->singleBlockingThread) { /* delegate to single-thread (synchronous) */
|
||||
return ZSTD_compressStream_generic(mtctx->cctxPool->cctx[0], output, input, endOp);
|
||||
return ZSTD_compressStream2(mtctx->cctxPool->cctx[0], output, input, endOp);
|
||||
}
|
||||
|
||||
if ((mtctx->frameEnded) && (endOp==ZSTD_e_continue)) {
|
||||
@ -2051,7 +2031,7 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
|
||||
|| ((endOp == ZSTD_e_end) && (!mtctx->frameEnded)) ) { /* must finish the frame with a zero-size block */
|
||||
size_t const jobSize = mtctx->inBuff.filled;
|
||||
assert(mtctx->inBuff.filled <= mtctx->targetSectionSize);
|
||||
CHECK_F( ZSTDMT_createCompressionJob(mtctx, jobSize, endOp) );
|
||||
FORWARD_IF_ERROR( ZSTDMT_createCompressionJob(mtctx, jobSize, endOp) );
|
||||
}
|
||||
|
||||
/* check for potential compressed data ready to be flushed */
|
||||
@ -2065,7 +2045,7 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
|
||||
|
||||
size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
|
||||
{
|
||||
CHECK_F( ZSTDMT_compressStream_generic(mtctx, output, input, ZSTD_e_continue) );
|
||||
FORWARD_IF_ERROR( ZSTDMT_compressStream_generic(mtctx, output, input, ZSTD_e_continue) );
|
||||
|
||||
/* recommended next input size : fill current input buffer */
|
||||
return mtctx->targetSectionSize - mtctx->inBuff.filled; /* note : could be zero when input buffer is fully filled and no more availability to create new job */
|
||||
@ -2082,7 +2062,7 @@ static size_t ZSTDMT_flushStream_internal(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* ou
|
||||
|| ((endFrame==ZSTD_e_end) && !mtctx->frameEnded)) { /* need a last 0-size block to end frame */
|
||||
DEBUGLOG(5, "ZSTDMT_flushStream_internal : create a new job (%u bytes, end:%u)",
|
||||
(U32)srcSize, (U32)endFrame);
|
||||
CHECK_F( ZSTDMT_createCompressionJob(mtctx, srcSize, endFrame) );
|
||||
FORWARD_IF_ERROR( ZSTDMT_createCompressionJob(mtctx, srcSize, endFrame) );
|
||||
}
|
||||
|
||||
/* check if there is any data available to flush */
|
||||
|
@ -17,10 +17,21 @@
|
||||
|
||||
|
||||
/* Note : This is an internal API.
|
||||
* Some methods are still exposed (ZSTDLIB_API),
|
||||
* These APIs used to be exposed with ZSTDLIB_API,
|
||||
* because it used to be the only way to invoke MT compression.
|
||||
* Now, it's recommended to use ZSTD_compress_generic() instead.
|
||||
* These methods will stop being exposed in a future version */
|
||||
*
|
||||
* If you depend on these APIs and can't switch, then define
|
||||
* ZSTD_LEGACY_MULTITHREADED_API when making the dynamic library.
|
||||
* However, we may completely remove these functions in a future
|
||||
* release, so please switch soon.
|
||||
*/
|
||||
|
||||
#ifdef ZSTD_LEGACY_MULTITHREADED_API
|
||||
# define ZSTDMT_API ZSTDLIB_API
|
||||
#else
|
||||
# define ZSTDMT_API
|
||||
#endif
|
||||
|
||||
/* === Dependencies === */
|
||||
#include <stddef.h> /* size_t */
|
||||
@ -40,17 +51,17 @@
|
||||
|
||||
/* === Memory management === */
|
||||
typedef struct ZSTDMT_CCtx_s ZSTDMT_CCtx;
|
||||
ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers);
|
||||
ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers,
|
||||
ZSTDMT_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers);
|
||||
ZSTDMT_API ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers,
|
||||
ZSTD_customMem cMem);
|
||||
ZSTDLIB_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx);
|
||||
ZSTDMT_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx);
|
||||
|
||||
ZSTDLIB_API size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx);
|
||||
ZSTDMT_API size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx);
|
||||
|
||||
|
||||
/* === Simple one-pass compression function === */
|
||||
|
||||
ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
|
||||
ZSTDMT_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
|
||||
void* dst, size_t dstCapacity,
|
||||
const void* src, size_t srcSize,
|
||||
int compressionLevel);
|
||||
@ -59,31 +70,31 @@ ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
|
||||
|
||||
/* === Streaming functions === */
|
||||
|
||||
ZSTDLIB_API size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel);
|
||||
ZSTDLIB_API size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize); /**< if srcSize is not known at reset time, use ZSTD_CONTENTSIZE_UNKNOWN. Note: for compatibility with older programs, 0 means the same as ZSTD_CONTENTSIZE_UNKNOWN, but it will change in the future to mean "empty" */
|
||||
ZSTDMT_API size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel);
|
||||
ZSTDMT_API size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize); /**< if srcSize is not known at reset time, use ZSTD_CONTENTSIZE_UNKNOWN. Note: for compatibility with older programs, 0 means the same as ZSTD_CONTENTSIZE_UNKNOWN, but it will change in the future to mean "empty" */
|
||||
|
||||
ZSTDLIB_API size_t ZSTDMT_nextInputSizeHint(const ZSTDMT_CCtx* mtctx);
|
||||
ZSTDLIB_API size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
|
||||
ZSTDMT_API size_t ZSTDMT_nextInputSizeHint(const ZSTDMT_CCtx* mtctx);
|
||||
ZSTDMT_API size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
|
||||
|
||||
ZSTDLIB_API size_t ZSTDMT_flushStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output); /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
|
||||
ZSTDLIB_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output); /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
|
||||
ZSTDMT_API size_t ZSTDMT_flushStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output); /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
|
||||
ZSTDMT_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output); /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
|
||||
|
||||
|
||||
/* === Advanced functions and parameters === */
|
||||
|
||||
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 params,
|
||||
int overlapLog);
|
||||
ZSTDMT_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 params,
|
||||
int overlapLog);
|
||||
|
||||
ZSTDLIB_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx,
|
||||
ZSTDMT_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,
|
||||
ZSTDMT_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
|
||||
const ZSTD_CDict* cdict,
|
||||
ZSTD_frameParameters fparams,
|
||||
unsigned long long pledgedSrcSize); /* note : zero means empty */
|
||||
@ -101,12 +112,12 @@ typedef enum {
|
||||
* The function must be called typically after ZSTD_createCCtx() but __before ZSTDMT_init*() !__
|
||||
* Parameters not explicitly reset by ZSTDMT_init*() remain the same in consecutive compression sessions.
|
||||
* @return : 0, or an error code (which can be tested using ZSTD_isError()) */
|
||||
ZSTDLIB_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int value);
|
||||
ZSTDMT_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int value);
|
||||
|
||||
/* ZSTDMT_getMTCtxParameter() :
|
||||
* Query the ZSTDMT_CCtx for a parameter value.
|
||||
* @return : 0, or an error code (which can be tested using ZSTD_isError()) */
|
||||
ZSTDLIB_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int* value);
|
||||
ZSTDMT_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int* value);
|
||||
|
||||
|
||||
/*! ZSTDMT_compressStream_generic() :
|
||||
@ -116,7 +127,7 @@ ZSTDLIB_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter
|
||||
* 0 if fully flushed
|
||||
* or an error code
|
||||
* note : needs to be init using any ZSTD_initCStream*() variant */
|
||||
ZSTDLIB_API size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
|
||||
ZSTDMT_API size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
|
||||
ZSTD_outBuffer* output,
|
||||
ZSTD_inBuffer* input,
|
||||
ZSTD_EndDirective endOp);
|
||||
|
@ -105,9 +105,9 @@ ZSTD_loadEntropy_intoDDict(ZSTD_DDict* ddict,
|
||||
ddict->dictID = MEM_readLE32((const char*)ddict->dictContent + ZSTD_FRAMEIDSIZE);
|
||||
|
||||
/* load entropy tables */
|
||||
CHECK_E( ZSTD_loadDEntropy(&ddict->entropy,
|
||||
ddict->dictContent, ddict->dictSize),
|
||||
dictionary_corrupted );
|
||||
RETURN_ERROR_IF(ZSTD_isError(ZSTD_loadDEntropy(
|
||||
&ddict->entropy, ddict->dictContent, ddict->dictSize)),
|
||||
dictionary_corrupted);
|
||||
ddict->entropyPresent = 1;
|
||||
return 0;
|
||||
}
|
||||
@ -133,7 +133,7 @@ static size_t ZSTD_initDDict_internal(ZSTD_DDict* ddict,
|
||||
ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */
|
||||
|
||||
/* parse dictionary content */
|
||||
CHECK_F( ZSTD_loadEntropy_intoDDict(ddict, dictContentType) );
|
||||
FORWARD_IF_ERROR( ZSTD_loadEntropy_intoDDict(ddict, dictContentType) );
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
@ -150,7 +150,7 @@ ZSTD_DCtx* ZSTD_createDCtx(void)
|
||||
size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx)
|
||||
{
|
||||
if (dctx==NULL) return 0; /* support free on NULL */
|
||||
if (dctx->staticSize) return ERROR(memory_allocation); /* not compatible with static DCtx */
|
||||
RETURN_ERROR_IF(dctx->staticSize, memory_allocation, "not compatible with static DCtx");
|
||||
{ ZSTD_customMem const cMem = dctx->customMem;
|
||||
ZSTD_freeDDict(dctx->ddictLocal);
|
||||
dctx->ddictLocal = NULL;
|
||||
@ -203,7 +203,7 @@ unsigned ZSTD_isFrame(const void* buffer, size_t size)
|
||||
static size_t ZSTD_frameHeaderSize_internal(const void* src, size_t srcSize, ZSTD_format_e format)
|
||||
{
|
||||
size_t const minInputSize = ZSTD_startingInputLength(format);
|
||||
if (srcSize < minInputSize) return ERROR(srcSize_wrong);
|
||||
RETURN_ERROR_IF(srcSize < minInputSize, srcSize_wrong);
|
||||
|
||||
{ BYTE const fhd = ((const BYTE*)src)[minInputSize-1];
|
||||
U32 const dictID= fhd & 3;
|
||||
@ -238,7 +238,7 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s
|
||||
|
||||
memset(zfhPtr, 0, sizeof(*zfhPtr)); /* not strictly necessary, but static analyzer do not understand that zfhPtr is only going to be read only if return value is zero, since they are 2 different signals */
|
||||
if (srcSize < minInputSize) return minInputSize;
|
||||
if (src==NULL) return ERROR(GENERIC); /* invalid parameter */
|
||||
RETURN_ERROR_IF(src==NULL, GENERIC, "invalid parameter");
|
||||
|
||||
if ( (format != ZSTD_f_zstd1_magicless)
|
||||
&& (MEM_readLE32(src) != ZSTD_MAGICNUMBER) ) {
|
||||
@ -251,7 +251,7 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s
|
||||
zfhPtr->frameType = ZSTD_skippableFrame;
|
||||
return 0;
|
||||
}
|
||||
return ERROR(prefix_unknown);
|
||||
RETURN_ERROR(prefix_unknown);
|
||||
}
|
||||
|
||||
/* ensure there is enough `srcSize` to fully read/decode frame header */
|
||||
@ -269,14 +269,13 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s
|
||||
U64 windowSize = 0;
|
||||
U32 dictID = 0;
|
||||
U64 frameContentSize = ZSTD_CONTENTSIZE_UNKNOWN;
|
||||
if ((fhdByte & 0x08) != 0)
|
||||
return ERROR(frameParameter_unsupported); /* reserved bits, must be zero */
|
||||
RETURN_ERROR_IF((fhdByte & 0x08) != 0, 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);
|
||||
RETURN_ERROR_IF(windowLog > ZSTD_WINDOWLOG_MAX, frameParameter_windowTooLarge);
|
||||
windowSize = (1ULL << windowLog);
|
||||
windowSize += (windowSize >> 3) * (wlByte&7);
|
||||
}
|
||||
@ -348,12 +347,11 @@ static size_t readSkippableFrameSize(void const* src, size_t srcSize)
|
||||
size_t const skippableHeaderSize = ZSTD_SKIPPABLEHEADERSIZE;
|
||||
U32 sizeU32;
|
||||
|
||||
if (srcSize < ZSTD_SKIPPABLEHEADERSIZE)
|
||||
return ERROR(srcSize_wrong);
|
||||
RETURN_ERROR_IF(srcSize < ZSTD_SKIPPABLEHEADERSIZE, srcSize_wrong);
|
||||
|
||||
sizeU32 = MEM_readLE32((BYTE const*)src + ZSTD_FRAMEIDSIZE);
|
||||
if ((U32)(sizeU32 + ZSTD_SKIPPABLEHEADERSIZE) < sizeU32)
|
||||
return ERROR(frameParameter_unsupported);
|
||||
RETURN_ERROR_IF((U32)(sizeU32 + ZSTD_SKIPPABLEHEADERSIZE) < sizeU32,
|
||||
frameParameter_unsupported);
|
||||
|
||||
return skippableHeaderSize + sizeU32;
|
||||
}
|
||||
@ -428,13 +426,89 @@ static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t he
|
||||
{
|
||||
size_t const result = ZSTD_getFrameHeader_advanced(&(dctx->fParams), src, headerSize, dctx->format);
|
||||
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);
|
||||
RETURN_ERROR_IF(result>0, srcSize_wrong, "headerSize too small");
|
||||
#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
|
||||
/* Skip the dictID check in fuzzing mode, because it makes the search
|
||||
* harder.
|
||||
*/
|
||||
RETURN_ERROR_IF(dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID),
|
||||
dictionary_wrong);
|
||||
#endif
|
||||
if (dctx->fParams.checksumFlag) XXH64_reset(&dctx->xxhState, 0);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static ZSTD_frameSizeInfo ZSTD_errorFrameSizeInfo(size_t ret)
|
||||
{
|
||||
ZSTD_frameSizeInfo frameSizeInfo;
|
||||
frameSizeInfo.compressedSize = ret;
|
||||
frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR;
|
||||
return frameSizeInfo;
|
||||
}
|
||||
|
||||
static ZSTD_frameSizeInfo ZSTD_findFrameSizeInfo(const void* src, size_t srcSize)
|
||||
{
|
||||
ZSTD_frameSizeInfo frameSizeInfo;
|
||||
memset(&frameSizeInfo, 0, sizeof(ZSTD_frameSizeInfo));
|
||||
|
||||
#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
|
||||
if (ZSTD_isLegacy(src, srcSize))
|
||||
return ZSTD_findFrameSizeInfoLegacy(src, srcSize);
|
||||
#endif
|
||||
|
||||
if ((srcSize >= ZSTD_SKIPPABLEHEADERSIZE)
|
||||
&& (MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {
|
||||
frameSizeInfo.compressedSize = readSkippableFrameSize(src, srcSize);
|
||||
return frameSizeInfo;
|
||||
} else {
|
||||
const BYTE* ip = (const BYTE*)src;
|
||||
const BYTE* const ipstart = ip;
|
||||
size_t remainingSize = srcSize;
|
||||
size_t nbBlocks = 0;
|
||||
ZSTD_frameHeader zfh;
|
||||
|
||||
/* Extract Frame Header */
|
||||
{ size_t const ret = ZSTD_getFrameHeader(&zfh, src, srcSize);
|
||||
if (ZSTD_isError(ret))
|
||||
return ZSTD_errorFrameSizeInfo(ret);
|
||||
if (ret > 0)
|
||||
return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong));
|
||||
}
|
||||
|
||||
ip += zfh.headerSize;
|
||||
remainingSize -= zfh.headerSize;
|
||||
|
||||
/* Iterate over each block */
|
||||
while (1) {
|
||||
blockProperties_t blockProperties;
|
||||
size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
|
||||
if (ZSTD_isError(cBlockSize))
|
||||
return ZSTD_errorFrameSizeInfo(cBlockSize);
|
||||
|
||||
if (ZSTD_blockHeaderSize + cBlockSize > remainingSize)
|
||||
return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong));
|
||||
|
||||
ip += ZSTD_blockHeaderSize + cBlockSize;
|
||||
remainingSize -= ZSTD_blockHeaderSize + cBlockSize;
|
||||
nbBlocks++;
|
||||
|
||||
if (blockProperties.lastBlock) break;
|
||||
}
|
||||
|
||||
/* Final frame content checksum */
|
||||
if (zfh.checksumFlag) {
|
||||
if (remainingSize < 4)
|
||||
return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong));
|
||||
ip += 4;
|
||||
}
|
||||
|
||||
frameSizeInfo.compressedSize = ip - ipstart;
|
||||
frameSizeInfo.decompressedBound = (zfh.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN)
|
||||
? zfh.frameContentSize
|
||||
: nbBlocks * zfh.blockSizeMax;
|
||||
return frameSizeInfo;
|
||||
}
|
||||
}
|
||||
|
||||
/** ZSTD_findFrameCompressedSize() :
|
||||
* compatible with legacy mode
|
||||
@ -443,53 +517,34 @@ static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t he
|
||||
* @return : the compressed size of the frame starting at `src` */
|
||||
size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize)
|
||||
{
|
||||
#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
|
||||
if (ZSTD_isLegacy(src, srcSize))
|
||||
return ZSTD_findFrameCompressedSizeLegacy(src, srcSize);
|
||||
#endif
|
||||
if ( (srcSize >= ZSTD_SKIPPABLEHEADERSIZE)
|
||||
&& (MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START ) {
|
||||
return readSkippableFrameSize(src, srcSize);
|
||||
} else {
|
||||
const BYTE* ip = (const BYTE*)src;
|
||||
const BYTE* const ipstart = ip;
|
||||
size_t remainingSize = srcSize;
|
||||
ZSTD_frameHeader zfh;
|
||||
|
||||
/* Extract Frame Header */
|
||||
{ size_t const ret = ZSTD_getFrameHeader(&zfh, src, srcSize);
|
||||
if (ZSTD_isError(ret)) return ret;
|
||||
if (ret > 0) return ERROR(srcSize_wrong);
|
||||
}
|
||||
|
||||
ip += zfh.headerSize;
|
||||
remainingSize -= zfh.headerSize;
|
||||
|
||||
/* Loop on each block */
|
||||
while (1) {
|
||||
blockProperties_t blockProperties;
|
||||
size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
|
||||
if (ZSTD_isError(cBlockSize)) return cBlockSize;
|
||||
|
||||
if (ZSTD_blockHeaderSize + cBlockSize > remainingSize)
|
||||
return ERROR(srcSize_wrong);
|
||||
|
||||
ip += ZSTD_blockHeaderSize + cBlockSize;
|
||||
remainingSize -= ZSTD_blockHeaderSize + cBlockSize;
|
||||
|
||||
if (blockProperties.lastBlock) break;
|
||||
}
|
||||
|
||||
if (zfh.checksumFlag) { /* Final frame content checksum */
|
||||
if (remainingSize < 4) return ERROR(srcSize_wrong);
|
||||
ip += 4;
|
||||
}
|
||||
|
||||
return ip - ipstart;
|
||||
}
|
||||
ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize);
|
||||
return frameSizeInfo.compressedSize;
|
||||
}
|
||||
|
||||
|
||||
/** ZSTD_decompressBound() :
|
||||
* compatible with legacy mode
|
||||
* `src` must point to the start of a ZSTD frame or a skippeable frame
|
||||
* `srcSize` must be at least as large as the frame contained
|
||||
* @return : the maximum decompressed size of the compressed source
|
||||
*/
|
||||
unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize)
|
||||
{
|
||||
unsigned long long bound = 0;
|
||||
/* Iterate over each frame */
|
||||
while (srcSize > 0) {
|
||||
ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize);
|
||||
size_t const compressedSize = frameSizeInfo.compressedSize;
|
||||
unsigned long long const decompressedBound = frameSizeInfo.decompressedBound;
|
||||
if (ZSTD_isError(compressedSize) || decompressedBound == ZSTD_CONTENTSIZE_ERROR)
|
||||
return ZSTD_CONTENTSIZE_ERROR;
|
||||
src = (const BYTE*)src + compressedSize;
|
||||
srcSize -= compressedSize;
|
||||
bound += decompressedBound;
|
||||
}
|
||||
return bound;
|
||||
}
|
||||
|
||||
|
||||
/*-*************************************************************
|
||||
* Frame decoding
|
||||
@ -522,9 +577,9 @@ static size_t ZSTD_copyRawBlock(void* dst, size_t dstCapacity,
|
||||
DEBUGLOG(5, "ZSTD_copyRawBlock");
|
||||
if (dst == NULL) {
|
||||
if (srcSize == 0) return 0;
|
||||
return ERROR(dstBuffer_null);
|
||||
RETURN_ERROR(dstBuffer_null);
|
||||
}
|
||||
if (srcSize > dstCapacity) return ERROR(dstSize_tooSmall);
|
||||
RETURN_ERROR_IF(srcSize > dstCapacity, dstSize_tooSmall);
|
||||
memcpy(dst, src, srcSize);
|
||||
return srcSize;
|
||||
}
|
||||
@ -535,9 +590,9 @@ static size_t ZSTD_setRleBlock(void* dst, size_t dstCapacity,
|
||||
{
|
||||
if (dst == NULL) {
|
||||
if (regenSize == 0) return 0;
|
||||
return ERROR(dstBuffer_null);
|
||||
RETURN_ERROR(dstBuffer_null);
|
||||
}
|
||||
if (regenSize > dstCapacity) return ERROR(dstSize_tooSmall);
|
||||
RETURN_ERROR_IF(regenSize > dstCapacity, dstSize_tooSmall);
|
||||
memset(dst, b, regenSize);
|
||||
return regenSize;
|
||||
}
|
||||
@ -560,15 +615,16 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
|
||||
DEBUGLOG(4, "ZSTD_decompressFrame (srcSize:%i)", (int)*srcSizePtr);
|
||||
|
||||
/* check */
|
||||
if (remainingSrcSize < ZSTD_FRAMEHEADERSIZE_MIN+ZSTD_blockHeaderSize)
|
||||
return ERROR(srcSize_wrong);
|
||||
RETURN_ERROR_IF(
|
||||
remainingSrcSize < ZSTD_FRAMEHEADERSIZE_MIN+ZSTD_blockHeaderSize,
|
||||
srcSize_wrong);
|
||||
|
||||
/* Frame Header */
|
||||
{ size_t const frameHeaderSize = ZSTD_frameHeaderSize(ip, ZSTD_FRAMEHEADERSIZE_PREFIX);
|
||||
if (ZSTD_isError(frameHeaderSize)) return frameHeaderSize;
|
||||
if (remainingSrcSize < frameHeaderSize+ZSTD_blockHeaderSize)
|
||||
return ERROR(srcSize_wrong);
|
||||
CHECK_F( ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize) );
|
||||
RETURN_ERROR_IF(remainingSrcSize < frameHeaderSize+ZSTD_blockHeaderSize,
|
||||
srcSize_wrong);
|
||||
FORWARD_IF_ERROR( ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize) );
|
||||
ip += frameHeaderSize; remainingSrcSize -= frameHeaderSize;
|
||||
}
|
||||
|
||||
@ -581,7 +637,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
|
||||
|
||||
ip += ZSTD_blockHeaderSize;
|
||||
remainingSrcSize -= ZSTD_blockHeaderSize;
|
||||
if (cBlockSize > remainingSrcSize) return ERROR(srcSize_wrong);
|
||||
RETURN_ERROR_IF(cBlockSize > remainingSrcSize, srcSize_wrong);
|
||||
|
||||
switch(blockProperties.blockType)
|
||||
{
|
||||
@ -596,7 +652,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
|
||||
break;
|
||||
case bt_reserved :
|
||||
default:
|
||||
return ERROR(corruption_detected);
|
||||
RETURN_ERROR(corruption_detected);
|
||||
}
|
||||
|
||||
if (ZSTD_isError(decodedSize)) return decodedSize;
|
||||
@ -609,15 +665,15 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
|
||||
}
|
||||
|
||||
if (dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) {
|
||||
if ((U64)(op-ostart) != dctx->fParams.frameContentSize) {
|
||||
return ERROR(corruption_detected);
|
||||
} }
|
||||
RETURN_ERROR_IF((U64)(op-ostart) != dctx->fParams.frameContentSize,
|
||||
corruption_detected);
|
||||
}
|
||||
if (dctx->fParams.checksumFlag) { /* Frame content checksum verification */
|
||||
U32 const checkCalc = (U32)XXH64_digest(&dctx->xxhState);
|
||||
U32 checkRead;
|
||||
if (remainingSrcSize<4) return ERROR(checksum_wrong);
|
||||
RETURN_ERROR_IF(remainingSrcSize<4, checksum_wrong);
|
||||
checkRead = MEM_readLE32(ip);
|
||||
if (checkRead != checkCalc) return ERROR(checksum_wrong);
|
||||
RETURN_ERROR_IF(checkRead != checkCalc, checksum_wrong);
|
||||
ip += 4;
|
||||
remainingSrcSize -= 4;
|
||||
}
|
||||
@ -652,8 +708,8 @@ 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 not compatible with static dctx */
|
||||
if (dctx->staticSize) return ERROR(memory_allocation);
|
||||
RETURN_ERROR_IF(dctx->staticSize, memory_allocation,
|
||||
"legacy support is not compatible with static dctx");
|
||||
|
||||
decodedSize = ZSTD_decompressLegacy(dst, dstCapacity, src, frameSize, dict, dictSize);
|
||||
if (ZSTD_isError(decodedSize)) return decodedSize;
|
||||
@ -676,7 +732,7 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
|
||||
size_t const skippableSize = readSkippableFrameSize(src, srcSize);
|
||||
if (ZSTD_isError(skippableSize))
|
||||
return skippableSize;
|
||||
if (srcSize < skippableSize) return ERROR(srcSize_wrong);
|
||||
RETURN_ERROR_IF(srcSize < skippableSize, srcSize_wrong);
|
||||
|
||||
src = (const BYTE *)src + skippableSize;
|
||||
srcSize -= skippableSize;
|
||||
@ -685,29 +741,29 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
|
||||
|
||||
if (ddict) {
|
||||
/* we were called from ZSTD_decompress_usingDDict */
|
||||
CHECK_F(ZSTD_decompressBegin_usingDDict(dctx, ddict));
|
||||
FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(dctx, ddict));
|
||||
} else {
|
||||
/* this will initialize correctly with no dict if dict == NULL, so
|
||||
* use this in all cases but ddict */
|
||||
CHECK_F(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize));
|
||||
FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize));
|
||||
}
|
||||
ZSTD_checkContinuity(dctx, dst);
|
||||
|
||||
{ const size_t res = ZSTD_decompressFrame(dctx, dst, dstCapacity,
|
||||
&src, &srcSize);
|
||||
if ( (ZSTD_getErrorCode(res) == ZSTD_error_prefix_unknown)
|
||||
&& (moreThan1Frame==1) ) {
|
||||
/* at least one frame successfully completed,
|
||||
* but following bytes are garbage :
|
||||
* it's more likely to be a srcSize error,
|
||||
* specifying more bytes than compressed size of frame(s).
|
||||
* This error message replaces ERROR(prefix_unknown),
|
||||
* which would be confusing, as the first header is actually correct.
|
||||
* Note that one could be unlucky, it might be a corruption error instead,
|
||||
* happening right at the place where we expect zstd magic bytes.
|
||||
* But this is _much_ less likely than a srcSize field error. */
|
||||
return ERROR(srcSize_wrong);
|
||||
}
|
||||
RETURN_ERROR_IF(
|
||||
(ZSTD_getErrorCode(res) == ZSTD_error_prefix_unknown)
|
||||
&& (moreThan1Frame==1),
|
||||
srcSize_wrong,
|
||||
"at least one frame successfully completed, but following "
|
||||
"bytes are garbage: it's more likely to be a srcSize error, "
|
||||
"specifying more bytes than compressed size of frame(s). This "
|
||||
"error message replaces ERROR(prefix_unknown), which would be "
|
||||
"confusing, as the first header is actually correct. Note that "
|
||||
"one could be unlucky, it might be a corruption error instead, "
|
||||
"happening right at the place where we expect zstd magic "
|
||||
"bytes. But this is _much_ less likely than a srcSize field "
|
||||
"error.");
|
||||
if (ZSTD_isError(res)) return res;
|
||||
assert(res <= dstCapacity);
|
||||
dst = (BYTE*)dst + res;
|
||||
@ -716,7 +772,7 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
|
||||
moreThan1Frame = 1;
|
||||
} /* while (srcSize >= ZSTD_frameHeaderSize_prefix) */
|
||||
|
||||
if (srcSize) return ERROR(srcSize_wrong); /* input not entirely consumed */
|
||||
RETURN_ERROR_IF(srcSize, srcSize_wrong, "input not entirely consumed");
|
||||
|
||||
return (BYTE*)dst - (BYTE*)dststart;
|
||||
}
|
||||
@ -732,7 +788,7 @@ size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
|
||||
|
||||
size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
|
||||
{
|
||||
return ZSTD_decompress_usingDict(dctx, dst, dstCapacity, src, srcSize, NULL, 0);
|
||||
return ZSTD_decompress_usingDDict(dctx, dst, dstCapacity, src, srcSize, dctx->ddict);
|
||||
}
|
||||
|
||||
|
||||
@ -741,7 +797,7 @@ size_t ZSTD_decompress(void* dst, size_t dstCapacity, const void* src, size_t sr
|
||||
#if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE>=1)
|
||||
size_t regenSize;
|
||||
ZSTD_DCtx* const dctx = ZSTD_createDCtx();
|
||||
if (dctx==NULL) return ERROR(memory_allocation);
|
||||
RETURN_ERROR_IF(dctx==NULL, memory_allocation);
|
||||
regenSize = ZSTD_decompressDCtx(dctx, dst, dstCapacity, src, srcSize);
|
||||
ZSTD_freeDCtx(dctx);
|
||||
return regenSize;
|
||||
@ -791,8 +847,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
|
||||
{
|
||||
DEBUGLOG(5, "ZSTD_decompressContinue (srcSize:%u)", (unsigned)srcSize);
|
||||
/* Sanity check */
|
||||
if (srcSize != dctx->expected)
|
||||
return ERROR(srcSize_wrong); /* not allowed */
|
||||
RETURN_ERROR_IF(srcSize != dctx->expected, srcSize_wrong, "not allowed");
|
||||
if (dstCapacity) ZSTD_checkContinuity(dctx, dst);
|
||||
|
||||
switch (dctx->stage)
|
||||
@ -817,7 +872,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
|
||||
case ZSTDds_decodeFrameHeader:
|
||||
assert(src != NULL);
|
||||
memcpy(dctx->headerBuffer + (dctx->headerSize - srcSize), src, srcSize);
|
||||
CHECK_F(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize));
|
||||
FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize));
|
||||
dctx->expected = ZSTD_blockHeaderSize;
|
||||
dctx->stage = ZSTDds_decodeBlockHeader;
|
||||
return 0;
|
||||
@ -867,7 +922,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
|
||||
break;
|
||||
case bt_reserved : /* should never happen */
|
||||
default:
|
||||
return ERROR(corruption_detected);
|
||||
RETURN_ERROR(corruption_detected);
|
||||
}
|
||||
if (ZSTD_isError(rSize)) return rSize;
|
||||
DEBUGLOG(5, "ZSTD_decompressContinue: decoded size from block : %u", (unsigned)rSize);
|
||||
@ -876,10 +931,10 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
|
||||
|
||||
if (dctx->stage == ZSTDds_decompressLastBlock) { /* end of frame */
|
||||
DEBUGLOG(4, "ZSTD_decompressContinue: decoded size from frame : %u", (unsigned)dctx->decodedSize);
|
||||
if (dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) {
|
||||
if (dctx->decodedSize != dctx->fParams.frameContentSize) {
|
||||
return ERROR(corruption_detected);
|
||||
} }
|
||||
RETURN_ERROR_IF(
|
||||
dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN
|
||||
&& dctx->decodedSize != dctx->fParams.frameContentSize,
|
||||
corruption_detected);
|
||||
if (dctx->fParams.checksumFlag) { /* another round for frame checksum */
|
||||
dctx->expected = 4;
|
||||
dctx->stage = ZSTDds_checkChecksum;
|
||||
@ -900,7 +955,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
|
||||
{ U32 const h32 = (U32)XXH64_digest(&dctx->xxhState);
|
||||
U32 const check32 = MEM_readLE32(src);
|
||||
DEBUGLOG(4, "ZSTD_decompressContinue: checksum : calculated %08X :: %08X read", (unsigned)h32, (unsigned)check32);
|
||||
if (check32 != h32) return ERROR(checksum_wrong);
|
||||
RETURN_ERROR_IF(check32 != h32, checksum_wrong);
|
||||
dctx->expected = 0;
|
||||
dctx->stage = ZSTDds_getFrameHeaderSize;
|
||||
return 0;
|
||||
@ -921,7 +976,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
|
||||
|
||||
default:
|
||||
assert(0); /* impossible */
|
||||
return ERROR(GENERIC); /* some compiler require default to do something */
|
||||
RETURN_ERROR(GENERIC); /* some compiler require default to do something */
|
||||
}
|
||||
}
|
||||
|
||||
@ -945,7 +1000,7 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
|
||||
const BYTE* dictPtr = (const BYTE*)dict;
|
||||
const BYTE* const dictEnd = dictPtr + dictSize;
|
||||
|
||||
if (dictSize <= 8) return ERROR(dictionary_corrupted);
|
||||
RETURN_ERROR_IF(dictSize <= 8, dictionary_corrupted);
|
||||
assert(MEM_readLE32(dict) == ZSTD_MAGIC_DICTIONARY); /* dict must be valid */
|
||||
dictPtr += 8; /* skip header = magic + dictID */
|
||||
|
||||
@ -964,16 +1019,16 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
|
||||
dictPtr, dictEnd - dictPtr,
|
||||
workspace, workspaceSize);
|
||||
#endif
|
||||
if (HUF_isError(hSize)) return ERROR(dictionary_corrupted);
|
||||
RETURN_ERROR_IF(HUF_isError(hSize), dictionary_corrupted);
|
||||
dictPtr += hSize;
|
||||
}
|
||||
|
||||
{ short offcodeNCount[MaxOff+1];
|
||||
unsigned offcodeMaxValue = MaxOff, offcodeLog;
|
||||
size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd-dictPtr);
|
||||
if (FSE_isError(offcodeHeaderSize)) return ERROR(dictionary_corrupted);
|
||||
if (offcodeMaxValue > MaxOff) return ERROR(dictionary_corrupted);
|
||||
if (offcodeLog > OffFSELog) return ERROR(dictionary_corrupted);
|
||||
RETURN_ERROR_IF(FSE_isError(offcodeHeaderSize), dictionary_corrupted);
|
||||
RETURN_ERROR_IF(offcodeMaxValue > MaxOff, dictionary_corrupted);
|
||||
RETURN_ERROR_IF(offcodeLog > OffFSELog, dictionary_corrupted);
|
||||
ZSTD_buildFSETable( entropy->OFTable,
|
||||
offcodeNCount, offcodeMaxValue,
|
||||
OF_base, OF_bits,
|
||||
@ -984,9 +1039,9 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
|
||||
{ short matchlengthNCount[MaxML+1];
|
||||
unsigned matchlengthMaxValue = MaxML, matchlengthLog;
|
||||
size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd-dictPtr);
|
||||
if (FSE_isError(matchlengthHeaderSize)) return ERROR(dictionary_corrupted);
|
||||
if (matchlengthMaxValue > MaxML) return ERROR(dictionary_corrupted);
|
||||
if (matchlengthLog > MLFSELog) return ERROR(dictionary_corrupted);
|
||||
RETURN_ERROR_IF(FSE_isError(matchlengthHeaderSize), dictionary_corrupted);
|
||||
RETURN_ERROR_IF(matchlengthMaxValue > MaxML, dictionary_corrupted);
|
||||
RETURN_ERROR_IF(matchlengthLog > MLFSELog, dictionary_corrupted);
|
||||
ZSTD_buildFSETable( entropy->MLTable,
|
||||
matchlengthNCount, matchlengthMaxValue,
|
||||
ML_base, ML_bits,
|
||||
@ -997,9 +1052,9 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
|
||||
{ short litlengthNCount[MaxLL+1];
|
||||
unsigned litlengthMaxValue = MaxLL, litlengthLog;
|
||||
size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd-dictPtr);
|
||||
if (FSE_isError(litlengthHeaderSize)) return ERROR(dictionary_corrupted);
|
||||
if (litlengthMaxValue > MaxLL) return ERROR(dictionary_corrupted);
|
||||
if (litlengthLog > LLFSELog) return ERROR(dictionary_corrupted);
|
||||
RETURN_ERROR_IF(FSE_isError(litlengthHeaderSize), dictionary_corrupted);
|
||||
RETURN_ERROR_IF(litlengthMaxValue > MaxLL, dictionary_corrupted);
|
||||
RETURN_ERROR_IF(litlengthLog > LLFSELog, dictionary_corrupted);
|
||||
ZSTD_buildFSETable( entropy->LLTable,
|
||||
litlengthNCount, litlengthMaxValue,
|
||||
LL_base, LL_bits,
|
||||
@ -1007,12 +1062,13 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
|
||||
dictPtr += litlengthHeaderSize;
|
||||
}
|
||||
|
||||
if (dictPtr+12 > dictEnd) return ERROR(dictionary_corrupted);
|
||||
RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted);
|
||||
{ int i;
|
||||
size_t const dictContentSize = (size_t)(dictEnd - (dictPtr+12));
|
||||
for (i=0; i<3; i++) {
|
||||
U32 const rep = MEM_readLE32(dictPtr); dictPtr += 4;
|
||||
if (rep==0 || rep >= dictContentSize) return ERROR(dictionary_corrupted);
|
||||
RETURN_ERROR_IF(rep==0 || rep >= dictContentSize,
|
||||
dictionary_corrupted);
|
||||
entropy->rep[i] = rep;
|
||||
} }
|
||||
|
||||
@ -1030,7 +1086,7 @@ static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx* dctx, const void* dict
|
||||
|
||||
/* load entropy tables */
|
||||
{ size_t const eSize = ZSTD_loadDEntropy(&dctx->entropy, dict, dictSize);
|
||||
if (ZSTD_isError(eSize)) return ERROR(dictionary_corrupted);
|
||||
RETURN_ERROR_IF(ZSTD_isError(eSize), dictionary_corrupted);
|
||||
dict = (const char*)dict + eSize;
|
||||
dictSize -= eSize;
|
||||
}
|
||||
@ -1064,9 +1120,11 @@ size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx)
|
||||
|
||||
size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize)
|
||||
{
|
||||
CHECK_F( ZSTD_decompressBegin(dctx) );
|
||||
FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) );
|
||||
if (dict && dictSize)
|
||||
CHECK_E(ZSTD_decompress_insertDictionary(dctx, dict, dictSize), dictionary_corrupted);
|
||||
RETURN_ERROR_IF(
|
||||
ZSTD_isError(ZSTD_decompress_insertDictionary(dctx, dict, dictSize)),
|
||||
dictionary_corrupted);
|
||||
return 0;
|
||||
}
|
||||
|
||||
@ -1085,7 +1143,7 @@ size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict)
|
||||
DEBUGLOG(4, "DDict is %s",
|
||||
dctx->ddictIsCold ? "~cold~" : "hot!");
|
||||
}
|
||||
CHECK_F( ZSTD_decompressBegin(dctx) );
|
||||
FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) );
|
||||
if (ddict) { /* NULL ddict is equivalent to no dictionary */
|
||||
ZSTD_copyDDictParameters(dctx, ddict);
|
||||
}
|
||||
@ -1176,11 +1234,11 @@ size_t ZSTD_DCtx_loadDictionary_advanced(ZSTD_DCtx* dctx,
|
||||
ZSTD_dictLoadMethod_e dictLoadMethod,
|
||||
ZSTD_dictContentType_e dictContentType)
|
||||
{
|
||||
if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
|
||||
RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
|
||||
ZSTD_freeDDict(dctx->ddictLocal);
|
||||
if (dict && dictSize >= 8) {
|
||||
dctx->ddictLocal = ZSTD_createDDict_advanced(dict, dictSize, dictLoadMethod, dictContentType, dctx->customMem);
|
||||
if (dctx->ddictLocal == NULL) return ERROR(memory_allocation);
|
||||
RETURN_ERROR_IF(dctx->ddictLocal == NULL, memory_allocation);
|
||||
} else {
|
||||
dctx->ddictLocal = NULL;
|
||||
}
|
||||
@ -1217,7 +1275,7 @@ size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t di
|
||||
DEBUGLOG(4, "ZSTD_initDStream_usingDict");
|
||||
zds->streamStage = zdss_init;
|
||||
zds->noForwardProgress = 0;
|
||||
CHECK_F( ZSTD_DCtx_loadDictionary(zds, dict, dictSize) );
|
||||
FORWARD_IF_ERROR( ZSTD_DCtx_loadDictionary(zds, dict, dictSize) );
|
||||
return ZSTD_FRAMEHEADERSIZE_PREFIX;
|
||||
}
|
||||
|
||||
@ -1254,7 +1312,7 @@ size_t ZSTD_resetDStream(ZSTD_DStream* dctx)
|
||||
|
||||
size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict)
|
||||
{
|
||||
if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
|
||||
RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
|
||||
dctx->ddict = ddict;
|
||||
return 0;
|
||||
}
|
||||
@ -1267,9 +1325,9 @@ size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize)
|
||||
ZSTD_bounds const bounds = ZSTD_dParam_getBounds(ZSTD_d_windowLogMax);
|
||||
size_t const min = (size_t)1 << bounds.lowerBound;
|
||||
size_t const max = (size_t)1 << bounds.upperBound;
|
||||
if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
|
||||
if (maxWindowSize < min) return ERROR(parameter_outOfBound);
|
||||
if (maxWindowSize > max) return ERROR(parameter_outOfBound);
|
||||
RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
|
||||
RETURN_ERROR_IF(maxWindowSize < min, parameter_outOfBound);
|
||||
RETURN_ERROR_IF(maxWindowSize > max, parameter_outOfBound);
|
||||
dctx->maxWindowSize = maxWindowSize;
|
||||
return 0;
|
||||
}
|
||||
@ -1311,15 +1369,15 @@ static int ZSTD_dParam_withinBounds(ZSTD_dParameter dParam, int value)
|
||||
}
|
||||
|
||||
#define CHECK_DBOUNDS(p,v) { \
|
||||
if (!ZSTD_dParam_withinBounds(p, v)) \
|
||||
return ERROR(parameter_outOfBound); \
|
||||
RETURN_ERROR_IF(!ZSTD_dParam_withinBounds(p, v), parameter_outOfBound); \
|
||||
}
|
||||
|
||||
size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter dParam, int value)
|
||||
{
|
||||
if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
|
||||
RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
|
||||
switch(dParam) {
|
||||
case ZSTD_d_windowLogMax:
|
||||
if (value == 0) value = ZSTD_WINDOWLOG_LIMIT_DEFAULT;
|
||||
CHECK_DBOUNDS(ZSTD_d_windowLogMax, value);
|
||||
dctx->maxWindowSize = ((size_t)1) << value;
|
||||
return 0;
|
||||
@ -1329,7 +1387,7 @@ size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter dParam, int value
|
||||
return 0;
|
||||
default:;
|
||||
}
|
||||
return ERROR(parameter_unsupported);
|
||||
RETURN_ERROR(parameter_unsupported);
|
||||
}
|
||||
|
||||
size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset)
|
||||
@ -1340,8 +1398,7 @@ size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset)
|
||||
}
|
||||
if ( (reset == ZSTD_reset_parameters)
|
||||
|| (reset == ZSTD_reset_session_and_parameters) ) {
|
||||
if (dctx->streamStage != zdss_init)
|
||||
return ERROR(stage_wrong);
|
||||
RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
|
||||
dctx->format = ZSTD_f_zstd1;
|
||||
dctx->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
|
||||
}
|
||||
@ -1360,7 +1417,8 @@ size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long
|
||||
unsigned long long const neededRBSize = windowSize + blockSize + (WILDCOPY_OVERLENGTH * 2);
|
||||
unsigned long long const neededSize = MIN(frameContentSize, neededRBSize);
|
||||
size_t const minRBSize = (size_t) neededSize;
|
||||
if ((unsigned long long)minRBSize != neededSize) return ERROR(frameParameter_windowTooLarge);
|
||||
RETURN_ERROR_IF((unsigned long long)minRBSize != neededSize,
|
||||
frameParameter_windowTooLarge);
|
||||
return minRBSize;
|
||||
}
|
||||
|
||||
@ -1378,9 +1436,9 @@ size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize)
|
||||
ZSTD_frameHeader zfh;
|
||||
size_t const err = ZSTD_getFrameHeader(&zfh, src, srcSize);
|
||||
if (ZSTD_isError(err)) return err;
|
||||
if (err>0) return ERROR(srcSize_wrong);
|
||||
if (zfh.windowSize > windowSizeMax)
|
||||
return ERROR(frameParameter_windowTooLarge);
|
||||
RETURN_ERROR_IF(err>0, srcSize_wrong);
|
||||
RETURN_ERROR_IF(zfh.windowSize > windowSizeMax,
|
||||
frameParameter_windowTooLarge);
|
||||
return ZSTD_estimateDStreamSize((size_t)zfh.windowSize);
|
||||
}
|
||||
|
||||
@ -1406,16 +1464,16 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
|
||||
U32 someMoreWork = 1;
|
||||
|
||||
DEBUGLOG(5, "ZSTD_decompressStream");
|
||||
if (input->pos > input->size) { /* forbidden */
|
||||
DEBUGLOG(5, "in: pos: %u vs size: %u",
|
||||
(U32)input->pos, (U32)input->size);
|
||||
return ERROR(srcSize_wrong);
|
||||
}
|
||||
if (output->pos > output->size) { /* forbidden */
|
||||
DEBUGLOG(5, "out: pos: %u vs size: %u",
|
||||
(U32)output->pos, (U32)output->size);
|
||||
return ERROR(dstSize_tooSmall);
|
||||
}
|
||||
RETURN_ERROR_IF(
|
||||
input->pos > input->size,
|
||||
srcSize_wrong,
|
||||
"forbidden. in: pos: %u vs size: %u",
|
||||
(U32)input->pos, (U32)input->size);
|
||||
RETURN_ERROR_IF(
|
||||
output->pos > output->size,
|
||||
dstSize_tooSmall,
|
||||
"forbidden. out: pos: %u vs size: %u",
|
||||
(U32)output->pos, (U32)output->size);
|
||||
DEBUGLOG(5, "input size : %u", (U32)(input->size - input->pos));
|
||||
|
||||
while (someMoreWork) {
|
||||
@ -1430,8 +1488,8 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
|
||||
DEBUGLOG(5, "stage zdss_loadHeader (srcSize : %u)", (U32)(iend - ip));
|
||||
#if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
|
||||
if (zds->legacyVersion) {
|
||||
/* legacy support is incompatible with static dctx */
|
||||
if (zds->staticSize) return ERROR(memory_allocation);
|
||||
RETURN_ERROR_IF(zds->staticSize, memory_allocation,
|
||||
"legacy support is incompatible with static dctx");
|
||||
{ size_t const hint = ZSTD_decompressLegacyStream(zds->legacyContext, zds->legacyVersion, output, input);
|
||||
if (hint==0) zds->streamStage = zdss_init;
|
||||
return hint;
|
||||
@ -1446,9 +1504,9 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
|
||||
const void* const dict = zds->ddict ? ZSTD_DDict_dictContent(zds->ddict) : NULL;
|
||||
size_t const dictSize = zds->ddict ? ZSTD_DDict_dictSize(zds->ddict) : 0;
|
||||
DEBUGLOG(5, "ZSTD_decompressStream: detected legacy version v0.%u", legacyVersion);
|
||||
/* legacy support is incompatible with static dctx */
|
||||
if (zds->staticSize) return ERROR(memory_allocation);
|
||||
CHECK_F(ZSTD_initLegacyStream(&zds->legacyContext,
|
||||
RETURN_ERROR_IF(zds->staticSize, memory_allocation,
|
||||
"legacy support is incompatible with static dctx");
|
||||
FORWARD_IF_ERROR(ZSTD_initLegacyStream(&zds->legacyContext,
|
||||
zds->previousLegacyVersion, legacyVersion,
|
||||
dict, dictSize));
|
||||
zds->legacyVersion = zds->previousLegacyVersion = legacyVersion;
|
||||
@ -1495,13 +1553,13 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
|
||||
|
||||
/* Consume header (see ZSTDds_decodeFrameHeader) */
|
||||
DEBUGLOG(4, "Consume header");
|
||||
CHECK_F(ZSTD_decompressBegin_usingDDict(zds, zds->ddict));
|
||||
FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(zds, zds->ddict));
|
||||
|
||||
if ((MEM_readLE32(zds->headerBuffer) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */
|
||||
zds->expected = MEM_readLE32(zds->headerBuffer + ZSTD_FRAMEIDSIZE);
|
||||
zds->stage = ZSTDds_skipFrame;
|
||||
} else {
|
||||
CHECK_F(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize));
|
||||
FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize));
|
||||
zds->expected = ZSTD_blockHeaderSize;
|
||||
zds->stage = ZSTDds_decodeBlockHeader;
|
||||
}
|
||||
@ -1511,7 +1569,8 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
|
||||
(U32)(zds->fParams.windowSize >>10),
|
||||
(U32)(zds->maxWindowSize >> 10) );
|
||||
zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN);
|
||||
if (zds->fParams.windowSize > zds->maxWindowSize) return ERROR(frameParameter_windowTooLarge);
|
||||
RETURN_ERROR_IF(zds->fParams.windowSize > zds->maxWindowSize,
|
||||
frameParameter_windowTooLarge);
|
||||
|
||||
/* Adapt buffer sizes to frame header instructions */
|
||||
{ size_t const neededInBuffSize = MAX(zds->fParams.blockSizeMax, 4 /* frame checksum */);
|
||||
@ -1525,14 +1584,15 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
|
||||
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);
|
||||
RETURN_ERROR_IF(
|
||||
bufferSize > zds->staticSize - sizeof(ZSTD_DCtx),
|
||||
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);
|
||||
RETURN_ERROR_IF(zds->inBuff == NULL, memory_allocation);
|
||||
}
|
||||
zds->inBuffSize = neededInBuffSize;
|
||||
zds->outBuff = zds->inBuff + zds->inBuffSize;
|
||||
@ -1574,7 +1634,9 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
|
||||
if (isSkipFrame) {
|
||||
loadedSize = MIN(toLoad, (size_t)(iend-ip));
|
||||
} else {
|
||||
if (toLoad > zds->inBuffSize - zds->inPos) return ERROR(corruption_detected); /* should never happen */
|
||||
RETURN_ERROR_IF(toLoad > zds->inBuffSize - zds->inPos,
|
||||
corruption_detected,
|
||||
"should never happen");
|
||||
loadedSize = ZSTD_limitCopy(zds->inBuff + zds->inPos, toLoad, ip, iend-ip);
|
||||
}
|
||||
ip += loadedSize;
|
||||
@ -1615,7 +1677,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
|
||||
|
||||
default:
|
||||
assert(0); /* impossible */
|
||||
return ERROR(GENERIC); /* some compiler require default to do something */
|
||||
RETURN_ERROR(GENERIC); /* some compiler require default to do something */
|
||||
} }
|
||||
|
||||
/* result */
|
||||
@ -1624,8 +1686,8 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
|
||||
if ((ip==istart) && (op==ostart)) { /* no forward progress */
|
||||
zds->noForwardProgress ++;
|
||||
if (zds->noForwardProgress >= ZSTD_NO_FORWARD_PROGRESS_MAX) {
|
||||
if (op==oend) return ERROR(dstSize_tooSmall);
|
||||
if (ip==iend) return ERROR(srcSize_wrong);
|
||||
RETURN_ERROR_IF(op==oend, dstSize_tooSmall);
|
||||
RETURN_ERROR_IF(ip==iend, srcSize_wrong);
|
||||
assert(0);
|
||||
}
|
||||
} else {
|
||||
|
@ -56,14 +56,15 @@ static void ZSTD_copy4(void* dst, const void* src) { memcpy(dst, src, 4); }
|
||||
size_t ZSTD_getcBlockSize(const void* src, size_t srcSize,
|
||||
blockProperties_t* bpPtr)
|
||||
{
|
||||
if (srcSize < ZSTD_blockHeaderSize) return ERROR(srcSize_wrong);
|
||||
RETURN_ERROR_IF(srcSize < ZSTD_blockHeaderSize, srcSize_wrong);
|
||||
|
||||
{ U32 const cBlockHeader = MEM_readLE24(src);
|
||||
U32 const cSize = cBlockHeader >> 3;
|
||||
bpPtr->lastBlock = cBlockHeader & 1;
|
||||
bpPtr->blockType = (blockType_e)((cBlockHeader >> 1) & 3);
|
||||
bpPtr->origSize = cSize; /* only useful for RLE */
|
||||
if (bpPtr->blockType == bt_rle) return 1;
|
||||
if (bpPtr->blockType == bt_reserved) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(bpPtr->blockType == bt_reserved, corruption_detected);
|
||||
return cSize;
|
||||
}
|
||||
}
|
||||
@ -78,7 +79,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
|
||||
size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
|
||||
const void* src, size_t srcSize) /* note : srcSize < BLOCKSIZE */
|
||||
{
|
||||
if (srcSize < MIN_CBLOCK_SIZE) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(srcSize < MIN_CBLOCK_SIZE, corruption_detected);
|
||||
|
||||
{ const BYTE* const istart = (const BYTE*) src;
|
||||
symbolEncodingType_e const litEncType = (symbolEncodingType_e)(istart[0] & 3);
|
||||
@ -86,11 +87,11 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
|
||||
switch(litEncType)
|
||||
{
|
||||
case set_repeat:
|
||||
if (dctx->litEntropy==0) return ERROR(dictionary_corrupted);
|
||||
RETURN_ERROR_IF(dctx->litEntropy==0, dictionary_corrupted);
|
||||
/* fall-through */
|
||||
|
||||
case set_compressed:
|
||||
if (srcSize < 5) return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3 */
|
||||
RETURN_ERROR_IF(srcSize < 5, corruption_detected, "srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3");
|
||||
{ size_t lhSize, litSize, litCSize;
|
||||
U32 singleStream=0;
|
||||
U32 const lhlCode = (istart[0] >> 2) & 3;
|
||||
@ -118,8 +119,8 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
|
||||
litCSize = (lhc >> 22) + (istart[4] << 10);
|
||||
break;
|
||||
}
|
||||
if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected);
|
||||
if (litCSize + lhSize > srcSize) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected);
|
||||
RETURN_ERROR_IF(litCSize + lhSize > srcSize, corruption_detected);
|
||||
|
||||
/* prefetch huffman table if cold */
|
||||
if (dctx->ddictIsCold && (litSize > 768 /* heuristic */)) {
|
||||
@ -157,7 +158,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
|
||||
}
|
||||
}
|
||||
|
||||
if (HUF_isError(hufSuccess)) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(HUF_isError(hufSuccess), corruption_detected);
|
||||
|
||||
dctx->litPtr = dctx->litBuffer;
|
||||
dctx->litSize = litSize;
|
||||
@ -187,7 +188,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
|
||||
}
|
||||
|
||||
if (lhSize+litSize+WILDCOPY_OVERLENGTH > srcSize) { /* risk reading beyond src buffer with wildcopy */
|
||||
if (litSize+lhSize > srcSize) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(litSize+lhSize > srcSize, corruption_detected);
|
||||
memcpy(dctx->litBuffer, istart+lhSize, litSize);
|
||||
dctx->litPtr = dctx->litBuffer;
|
||||
dctx->litSize = litSize;
|
||||
@ -216,17 +217,17 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
|
||||
case 3:
|
||||
lhSize = 3;
|
||||
litSize = MEM_readLE24(istart) >> 4;
|
||||
if (srcSize<4) return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4 */
|
||||
RETURN_ERROR_IF(srcSize<4, corruption_detected, "srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4");
|
||||
break;
|
||||
}
|
||||
if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected);
|
||||
memset(dctx->litBuffer, istart[lhSize], litSize + WILDCOPY_OVERLENGTH);
|
||||
dctx->litPtr = dctx->litBuffer;
|
||||
dctx->litSize = litSize;
|
||||
return lhSize+1;
|
||||
}
|
||||
default:
|
||||
return ERROR(corruption_detected); /* impossible */
|
||||
RETURN_ERROR(corruption_detected, "impossible");
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -436,8 +437,8 @@ static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymb
|
||||
switch(type)
|
||||
{
|
||||
case set_rle :
|
||||
if (!srcSize) return ERROR(srcSize_wrong);
|
||||
if ( (*(const BYTE*)src) > max) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(!srcSize, srcSize_wrong);
|
||||
RETURN_ERROR_IF((*(const BYTE*)src) > max, corruption_detected);
|
||||
{ U32 const symbol = *(const BYTE*)src;
|
||||
U32 const baseline = baseValue[symbol];
|
||||
U32 const nbBits = nbAdditionalBits[symbol];
|
||||
@ -449,7 +450,7 @@ static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymb
|
||||
*DTablePtr = defaultTable;
|
||||
return 0;
|
||||
case set_repeat:
|
||||
if (!flagRepeatTable) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(!flagRepeatTable, corruption_detected);
|
||||
/* prefetch FSE table if used */
|
||||
if (ddictIsCold && (nbSeq > 24 /* heuristic */)) {
|
||||
const void* const pStart = *DTablePtr;
|
||||
@ -461,15 +462,15 @@ static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymb
|
||||
{ unsigned tableLog;
|
||||
S16 norm[MaxSeq+1];
|
||||
size_t const headerSize = FSE_readNCount(norm, &max, &tableLog, src, srcSize);
|
||||
if (FSE_isError(headerSize)) return ERROR(corruption_detected);
|
||||
if (tableLog > maxLog) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(FSE_isError(headerSize), corruption_detected);
|
||||
RETURN_ERROR_IF(tableLog > maxLog, corruption_detected);
|
||||
ZSTD_buildFSETable(DTableSpace, norm, max, baseValue, nbAdditionalBits, tableLog);
|
||||
*DTablePtr = DTableSpace;
|
||||
return headerSize;
|
||||
}
|
||||
default : /* impossible */
|
||||
default :
|
||||
assert(0);
|
||||
return ERROR(GENERIC);
|
||||
RETURN_ERROR(GENERIC, "impossible");
|
||||
}
|
||||
}
|
||||
|
||||
@ -483,28 +484,28 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
|
||||
DEBUGLOG(5, "ZSTD_decodeSeqHeaders");
|
||||
|
||||
/* check */
|
||||
if (srcSize < MIN_SEQUENCES_SIZE) return ERROR(srcSize_wrong);
|
||||
RETURN_ERROR_IF(srcSize < MIN_SEQUENCES_SIZE, srcSize_wrong);
|
||||
|
||||
/* SeqHead */
|
||||
nbSeq = *ip++;
|
||||
if (!nbSeq) {
|
||||
*nbSeqPtr=0;
|
||||
if (srcSize != 1) return ERROR(srcSize_wrong);
|
||||
RETURN_ERROR_IF(srcSize != 1, srcSize_wrong);
|
||||
return 1;
|
||||
}
|
||||
if (nbSeq > 0x7F) {
|
||||
if (nbSeq == 0xFF) {
|
||||
if (ip+2 > iend) return ERROR(srcSize_wrong);
|
||||
RETURN_ERROR_IF(ip+2 > iend, srcSize_wrong);
|
||||
nbSeq = MEM_readLE16(ip) + LONGNBSEQ, ip+=2;
|
||||
} else {
|
||||
if (ip >= iend) return ERROR(srcSize_wrong);
|
||||
RETURN_ERROR_IF(ip >= iend, srcSize_wrong);
|
||||
nbSeq = ((nbSeq-0x80)<<8) + *ip++;
|
||||
}
|
||||
}
|
||||
*nbSeqPtr = nbSeq;
|
||||
|
||||
/* FSE table descriptors */
|
||||
if (ip+4 > iend) return ERROR(srcSize_wrong); /* minimum possible size */
|
||||
RETURN_ERROR_IF(ip+4 > iend, srcSize_wrong); /* minimum possible size */
|
||||
{ symbolEncodingType_e const LLtype = (symbolEncodingType_e)(*ip >> 6);
|
||||
symbolEncodingType_e const OFtype = (symbolEncodingType_e)((*ip >> 4) & 3);
|
||||
symbolEncodingType_e const MLtype = (symbolEncodingType_e)((*ip >> 2) & 3);
|
||||
@ -517,7 +518,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
|
||||
LL_base, LL_bits,
|
||||
LL_defaultDTable, dctx->fseEntropy,
|
||||
dctx->ddictIsCold, nbSeq);
|
||||
if (ZSTD_isError(llhSize)) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(ZSTD_isError(llhSize), corruption_detected);
|
||||
ip += llhSize;
|
||||
}
|
||||
|
||||
@ -527,7 +528,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
|
||||
OF_base, OF_bits,
|
||||
OF_defaultDTable, dctx->fseEntropy,
|
||||
dctx->ddictIsCold, nbSeq);
|
||||
if (ZSTD_isError(ofhSize)) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(ZSTD_isError(ofhSize), corruption_detected);
|
||||
ip += ofhSize;
|
||||
}
|
||||
|
||||
@ -537,7 +538,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
|
||||
ML_base, ML_bits,
|
||||
ML_defaultDTable, dctx->fseEntropy,
|
||||
dctx->ddictIsCold, nbSeq);
|
||||
if (ZSTD_isError(mlhSize)) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(ZSTD_isError(mlhSize), corruption_detected);
|
||||
ip += mlhSize;
|
||||
}
|
||||
}
|
||||
@ -590,8 +591,8 @@ size_t ZSTD_execSequenceLast7(BYTE* op,
|
||||
const BYTE* match = oLitEnd - sequence.offset;
|
||||
|
||||
/* check */
|
||||
if (oMatchEnd>oend) return ERROR(dstSize_tooSmall); /* last match must fit within dstBuffer */
|
||||
if (iLitEnd > litLimit) return ERROR(corruption_detected); /* try to read beyond literal buffer */
|
||||
RETURN_ERROR_IF(oMatchEnd>oend, dstSize_tooSmall, "last match must fit within dstBuffer");
|
||||
RETURN_ERROR_IF(iLitEnd > litLimit, corruption_detected, "try to read beyond literal buffer");
|
||||
|
||||
/* copy literals */
|
||||
while (op < oLitEnd) *op++ = *(*litPtr)++;
|
||||
@ -599,7 +600,7 @@ size_t ZSTD_execSequenceLast7(BYTE* op,
|
||||
/* copy Match */
|
||||
if (sequence.offset > (size_t)(oLitEnd - base)) {
|
||||
/* offset beyond prefix */
|
||||
if (sequence.offset > (size_t)(oLitEnd - vBase)) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - vBase),corruption_detected);
|
||||
match = dictEnd - (base-match);
|
||||
if (match + sequence.matchLength <= dictEnd) {
|
||||
memmove(oLitEnd, match, sequence.matchLength);
|
||||
@ -631,8 +632,8 @@ size_t ZSTD_execSequence(BYTE* op,
|
||||
const BYTE* match = oLitEnd - sequence.offset;
|
||||
|
||||
/* check */
|
||||
if (oMatchEnd>oend) return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
|
||||
if (iLitEnd > litLimit) return ERROR(corruption_detected); /* over-read beyond lit buffer */
|
||||
RETURN_ERROR_IF(oMatchEnd>oend, dstSize_tooSmall, "last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend");
|
||||
RETURN_ERROR_IF(iLitEnd > litLimit, corruption_detected, "over-read beyond lit buffer");
|
||||
if (oLitEnd>oend_w) return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, prefixStart, virtualStart, dictEnd);
|
||||
|
||||
/* copy Literals */
|
||||
@ -645,8 +646,7 @@ size_t ZSTD_execSequence(BYTE* op,
|
||||
/* copy Match */
|
||||
if (sequence.offset > (size_t)(oLitEnd - prefixStart)) {
|
||||
/* offset beyond prefix -> go into extDict */
|
||||
if (sequence.offset > (size_t)(oLitEnd - virtualStart))
|
||||
return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - virtualStart), corruption_detected);
|
||||
match = dictEnd + (match - prefixStart);
|
||||
if (match + sequence.matchLength <= dictEnd) {
|
||||
memmove(oLitEnd, match, sequence.matchLength);
|
||||
@ -712,8 +712,8 @@ size_t ZSTD_execSequenceLong(BYTE* op,
|
||||
const BYTE* match = sequence.match;
|
||||
|
||||
/* check */
|
||||
if (oMatchEnd > oend) return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
|
||||
if (iLitEnd > litLimit) return ERROR(corruption_detected); /* over-read beyond lit buffer */
|
||||
RETURN_ERROR_IF(oMatchEnd > oend, dstSize_tooSmall, "last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend");
|
||||
RETURN_ERROR_IF(iLitEnd > litLimit, corruption_detected, "over-read beyond lit buffer");
|
||||
if (oLitEnd > oend_w) return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, prefixStart, dictStart, dictEnd);
|
||||
|
||||
/* copy Literals */
|
||||
@ -726,7 +726,7 @@ size_t ZSTD_execSequenceLong(BYTE* op,
|
||||
/* copy Match */
|
||||
if (sequence.offset > (size_t)(oLitEnd - prefixStart)) {
|
||||
/* offset beyond prefix */
|
||||
if (sequence.offset > (size_t)(oLitEnd - dictStart)) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - dictStart), corruption_detected);
|
||||
if (match + sequence.matchLength <= dictEnd) {
|
||||
memmove(oLitEnd, match, sequence.matchLength);
|
||||
return sequenceLength;
|
||||
@ -911,7 +911,9 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
|
||||
seqState_t seqState;
|
||||
dctx->fseEntropy = 1;
|
||||
{ U32 i; for (i=0; i<ZSTD_REP_NUM; i++) seqState.prevOffset[i] = dctx->entropy.rep[i]; }
|
||||
CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend-ip), corruption_detected);
|
||||
RETURN_ERROR_IF(
|
||||
ERR_isError(BIT_initDStream(&seqState.DStream, ip, iend-ip)),
|
||||
corruption_detected);
|
||||
ZSTD_initFseState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr);
|
||||
ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
|
||||
ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);
|
||||
@ -927,14 +929,14 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
|
||||
|
||||
/* check if reached exact end */
|
||||
DEBUGLOG(5, "ZSTD_decompressSequences_body: after decode loop, remaining nbSeq : %i", nbSeq);
|
||||
if (nbSeq) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(nbSeq, 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]); }
|
||||
}
|
||||
|
||||
/* last literal segment */
|
||||
{ size_t const lastLLSize = litEnd - litPtr;
|
||||
if (lastLLSize > (size_t)(oend-op)) return ERROR(dstSize_tooSmall);
|
||||
RETURN_ERROR_IF(lastLLSize > (size_t)(oend-op), dstSize_tooSmall);
|
||||
memcpy(op, litPtr, lastLLSize);
|
||||
op += lastLLSize;
|
||||
}
|
||||
@ -1066,7 +1068,9 @@ ZSTD_decompressSequencesLong_body(
|
||||
seqState.pos = (size_t)(op-prefixStart);
|
||||
seqState.dictEnd = dictEnd;
|
||||
assert(iend >= ip);
|
||||
CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend-ip), corruption_detected);
|
||||
RETURN_ERROR_IF(
|
||||
ERR_isError(BIT_initDStream(&seqState.DStream, ip, iend-ip)),
|
||||
corruption_detected);
|
||||
ZSTD_initFseState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr);
|
||||
ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
|
||||
ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);
|
||||
@ -1076,7 +1080,7 @@ ZSTD_decompressSequencesLong_body(
|
||||
sequences[seqNb] = ZSTD_decodeSequenceLong(&seqState, isLongOffset);
|
||||
PREFETCH_L1(sequences[seqNb].match); PREFETCH_L1(sequences[seqNb].match + sequences[seqNb].matchLength - 1); /* note : it's safe to invoke PREFETCH() on any memory address, including invalid ones */
|
||||
}
|
||||
if (seqNb<seqAdvance) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(seqNb<seqAdvance, corruption_detected);
|
||||
|
||||
/* decode and decompress */
|
||||
for ( ; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && (seqNb<nbSeq) ; seqNb++) {
|
||||
@ -1087,7 +1091,7 @@ ZSTD_decompressSequencesLong_body(
|
||||
sequences[seqNb & STORED_SEQS_MASK] = sequence;
|
||||
op += oneSeqSize;
|
||||
}
|
||||
if (seqNb<nbSeq) return ERROR(corruption_detected);
|
||||
RETURN_ERROR_IF(seqNb<nbSeq, corruption_detected);
|
||||
|
||||
/* finish queue */
|
||||
seqNb -= seqAdvance;
|
||||
@ -1103,7 +1107,7 @@ ZSTD_decompressSequencesLong_body(
|
||||
|
||||
/* last literal segment */
|
||||
{ size_t const lastLLSize = litEnd - litPtr;
|
||||
if (lastLLSize > (size_t)(oend-op)) return ERROR(dstSize_tooSmall);
|
||||
RETURN_ERROR_IF(lastLLSize > (size_t)(oend-op), dstSize_tooSmall);
|
||||
memcpy(op, litPtr, lastLLSize);
|
||||
op += lastLLSize;
|
||||
}
|
||||
@ -1240,7 +1244,7 @@ ZSTD_decompressBlock_internal(ZSTD_DCtx* dctx,
|
||||
ZSTD_longOffset_e const isLongOffset = (ZSTD_longOffset_e)(MEM_32bits() && (!frame || (dctx->fParams.windowSize > (1ULL << STREAM_ACCUMULATOR_MIN))));
|
||||
DEBUGLOG(5, "ZSTD_decompressBlock_internal (size : %u)", (U32)srcSize);
|
||||
|
||||
if (srcSize >= ZSTD_BLOCKSIZE_MAX) return ERROR(srcSize_wrong);
|
||||
RETURN_ERROR_IF(srcSize >= ZSTD_BLOCKSIZE_MAX, srcSize_wrong);
|
||||
|
||||
/* Decode literals section */
|
||||
{ size_t const litCSize = ZSTD_decodeLiteralsBlock(dctx, src, srcSize);
|
||||
|
@ -627,6 +627,39 @@ static int COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer,
|
||||
return 1;
|
||||
}
|
||||
|
||||
void COVER_warnOnSmallCorpus(size_t maxDictSize, size_t nbDmers, int displayLevel)
|
||||
{
|
||||
const double ratio = (double)nbDmers / maxDictSize;
|
||||
if (ratio >= 10) {
|
||||
return;
|
||||
}
|
||||
LOCALDISPLAYLEVEL(displayLevel, 1,
|
||||
"WARNING: The maximum dictionary size %u is too large "
|
||||
"compared to the source size %u! "
|
||||
"size(source)/size(dictionary) = %f, but it should be >= "
|
||||
"10! This may lead to a subpar dictionary! We recommend "
|
||||
"training on sources at least 10x, and up to 100x the "
|
||||
"size of the dictionary!\n", (U32)maxDictSize,
|
||||
(U32)nbDmers, ratio);
|
||||
}
|
||||
|
||||
COVER_epoch_info_t COVER_computeEpochs(U32 maxDictSize,
|
||||
U32 nbDmers, U32 k, U32 passes)
|
||||
{
|
||||
const U32 minEpochSize = k * 10;
|
||||
COVER_epoch_info_t epochs;
|
||||
epochs.num = MAX(1, maxDictSize / k / passes);
|
||||
epochs.size = nbDmers / epochs.num;
|
||||
if (epochs.size >= minEpochSize) {
|
||||
assert(epochs.size * epochs.num <= nbDmers);
|
||||
return epochs;
|
||||
}
|
||||
epochs.size = MIN(minEpochSize, nbDmers);
|
||||
epochs.num = nbDmers / epochs.size;
|
||||
assert(epochs.size * epochs.num <= nbDmers);
|
||||
return epochs;
|
||||
}
|
||||
|
||||
/**
|
||||
* Given the prepared context build the dictionary.
|
||||
*/
|
||||
@ -636,28 +669,34 @@ static size_t COVER_buildDictionary(const COVER_ctx_t *ctx, U32 *freqs,
|
||||
ZDICT_cover_params_t parameters) {
|
||||
BYTE *const dict = (BYTE *)dictBuffer;
|
||||
size_t tail = dictBufferCapacity;
|
||||
/* Divide the data up into epochs of equal size.
|
||||
* We will select at least one segment from each epoch.
|
||||
*/
|
||||
const unsigned epochs = MAX(1, (U32)(dictBufferCapacity / parameters.k / 4));
|
||||
const unsigned epochSize = (U32)(ctx->suffixSize / epochs);
|
||||
/* Divide the data into epochs. We will select one segment from each epoch. */
|
||||
const COVER_epoch_info_t epochs = COVER_computeEpochs(
|
||||
(U32)dictBufferCapacity, (U32)ctx->suffixSize, parameters.k, 4);
|
||||
const size_t maxZeroScoreRun = MAX(10, MIN(100, epochs.num >> 3));
|
||||
size_t zeroScoreRun = 0;
|
||||
size_t epoch;
|
||||
DISPLAYLEVEL(2, "Breaking content into %u epochs of size %u\n",
|
||||
epochs, epochSize);
|
||||
(U32)epochs.num, (U32)epochs.size);
|
||||
/* Loop through the epochs until there are no more segments or the dictionary
|
||||
* is full.
|
||||
*/
|
||||
for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs) {
|
||||
const U32 epochBegin = (U32)(epoch * epochSize);
|
||||
const U32 epochEnd = epochBegin + epochSize;
|
||||
for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs.num) {
|
||||
const U32 epochBegin = (U32)(epoch * epochs.size);
|
||||
const U32 epochEnd = epochBegin + epochs.size;
|
||||
size_t segmentSize;
|
||||
/* Select a segment */
|
||||
COVER_segment_t segment = COVER_selectSegment(
|
||||
ctx, freqs, activeDmers, epochBegin, epochEnd, parameters);
|
||||
/* If the segment covers no dmers, then we are out of content */
|
||||
/* If the segment covers no dmers, then we are out of content.
|
||||
* There may be new content in other epochs, for continue for some time.
|
||||
*/
|
||||
if (segment.score == 0) {
|
||||
break;
|
||||
if (++zeroScoreRun >= maxZeroScoreRun) {
|
||||
break;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
zeroScoreRun = 0;
|
||||
/* Trim the segment if necessary and if it is too small then we are done */
|
||||
segmentSize = MIN(segment.end - segment.begin + parameters.d - 1, tail);
|
||||
if (segmentSize < parameters.d) {
|
||||
@ -706,6 +745,7 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover(
|
||||
parameters.d, parameters.splitPoint)) {
|
||||
return ERROR(GENERIC);
|
||||
}
|
||||
COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.suffixSize, g_displayLevel);
|
||||
if (!COVER_map_init(&activeDmers, parameters.k - parameters.d + 1)) {
|
||||
DISPLAYLEVEL(1, "Failed to allocate dmer map: out of memory\n");
|
||||
COVER_ctx_destroy(&ctx);
|
||||
@ -977,6 +1017,7 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
|
||||
unsigned k;
|
||||
COVER_best_t best;
|
||||
POOL_ctx *pool = NULL;
|
||||
int warned = 0;
|
||||
|
||||
/* Checks */
|
||||
if (splitPoint <= 0 || splitPoint > 1) {
|
||||
@ -1019,6 +1060,10 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
|
||||
POOL_free(pool);
|
||||
return ERROR(GENERIC);
|
||||
}
|
||||
if (!warned) {
|
||||
COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.suffixSize, displayLevel);
|
||||
warned = 1;
|
||||
}
|
||||
/* Loop through k reusing the same context */
|
||||
for (k = kMinK; k <= kMaxK; k += kStepSize) {
|
||||
/* Prepare the arguments */
|
||||
|
@ -38,6 +38,35 @@ typedef struct {
|
||||
U32 score;
|
||||
} COVER_segment_t;
|
||||
|
||||
/**
|
||||
*Number of epochs and size of each epoch.
|
||||
*/
|
||||
typedef struct {
|
||||
U32 num;
|
||||
U32 size;
|
||||
} COVER_epoch_info_t;
|
||||
|
||||
/**
|
||||
* Computes the number of epochs and the size of each epoch.
|
||||
* We will make sure that each epoch gets at least 10 * k bytes.
|
||||
*
|
||||
* The COVER algorithms divide the data up into epochs of equal size and
|
||||
* select one segemnt from each epoch.
|
||||
*
|
||||
* @param maxDictSize The maximum allowed dictioary size.
|
||||
* @param nbDmers The number of dmers we are training on.
|
||||
* @param k The parameter k (segment size).
|
||||
* @param passes The target number of passes over the dmer corpus.
|
||||
* More passes means a better dictionary.
|
||||
*/
|
||||
COVER_epoch_info_t COVER_computeEpochs(U32 maxDictSize, U32 nbDmers,
|
||||
U32 k, U32 passes);
|
||||
|
||||
/**
|
||||
* Warns the user when their corpus is too small.
|
||||
*/
|
||||
void COVER_warnOnSmallCorpus(size_t maxDictSize, size_t nbDmers, int displayLevel);
|
||||
|
||||
/**
|
||||
* Checks total compressed size of a dictionary
|
||||
*/
|
||||
|
@ -386,29 +386,35 @@ FASTCOVER_buildDictionary(const FASTCOVER_ctx_t* ctx,
|
||||
{
|
||||
BYTE *const dict = (BYTE *)dictBuffer;
|
||||
size_t tail = dictBufferCapacity;
|
||||
/* Divide the data up into epochs of equal size.
|
||||
* We will select at least one segment from each epoch.
|
||||
*/
|
||||
const unsigned epochs = MAX(1, (U32)(dictBufferCapacity / parameters.k));
|
||||
const unsigned epochSize = (U32)(ctx->nbDmers / epochs);
|
||||
/* Divide the data into epochs. We will select one segment from each epoch. */
|
||||
const COVER_epoch_info_t epochs = COVER_computeEpochs(
|
||||
(U32)dictBufferCapacity, (U32)ctx->nbDmers, parameters.k, 1);
|
||||
const size_t maxZeroScoreRun = 10;
|
||||
size_t zeroScoreRun = 0;
|
||||
size_t epoch;
|
||||
DISPLAYLEVEL(2, "Breaking content into %u epochs of size %u\n",
|
||||
epochs, epochSize);
|
||||
(U32)epochs.num, (U32)epochs.size);
|
||||
/* Loop through the epochs until there are no more segments or the dictionary
|
||||
* is full.
|
||||
*/
|
||||
for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs) {
|
||||
const U32 epochBegin = (U32)(epoch * epochSize);
|
||||
const U32 epochEnd = epochBegin + epochSize;
|
||||
for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs.num) {
|
||||
const U32 epochBegin = (U32)(epoch * epochs.size);
|
||||
const U32 epochEnd = epochBegin + epochs.size;
|
||||
size_t segmentSize;
|
||||
/* Select a segment */
|
||||
COVER_segment_t segment = FASTCOVER_selectSegment(
|
||||
ctx, freqs, epochBegin, epochEnd, parameters, segmentFreqs);
|
||||
|
||||
/* If the segment covers no dmers, then we are out of content */
|
||||
/* If the segment covers no dmers, then we are out of content.
|
||||
* There may be new content in other epochs, for continue for some time.
|
||||
*/
|
||||
if (segment.score == 0) {
|
||||
break;
|
||||
if (++zeroScoreRun >= maxZeroScoreRun) {
|
||||
break;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
zeroScoreRun = 0;
|
||||
|
||||
/* Trim the segment if necessary and if it is too small then we are done */
|
||||
segmentSize = MIN(segment.end - segment.begin + parameters.d - 1, tail);
|
||||
@ -564,6 +570,7 @@ ZDICT_trainFromBuffer_fastCover(void* dictBuffer, size_t dictBufferCapacity,
|
||||
DISPLAYLEVEL(1, "Failed to initialize context\n");
|
||||
return ERROR(GENERIC);
|
||||
}
|
||||
COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.nbDmers, g_displayLevel);
|
||||
/* Build the dictionary */
|
||||
DISPLAYLEVEL(2, "Building dictionary\n");
|
||||
{
|
||||
@ -616,6 +623,7 @@ ZDICT_optimizeTrainFromBuffer_fastCover(
|
||||
unsigned k;
|
||||
COVER_best_t best;
|
||||
POOL_ctx *pool = NULL;
|
||||
int warned = 0;
|
||||
/* Checks */
|
||||
if (splitPoint <= 0 || splitPoint > 1) {
|
||||
LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect splitPoint\n");
|
||||
@ -664,6 +672,10 @@ ZDICT_optimizeTrainFromBuffer_fastCover(
|
||||
POOL_free(pool);
|
||||
return ERROR(GENERIC);
|
||||
}
|
||||
if (!warned) {
|
||||
COVER_warnOnSmallCorpus(dictBufferCapacity, ctx.nbDmers, displayLevel);
|
||||
warned = 1;
|
||||
}
|
||||
/* Loop through k reusing the same context */
|
||||
for (k = kMinK; k <= kMaxK; k += kStepSize) {
|
||||
/* Prepare the arguments */
|
||||
|
@ -46,7 +46,12 @@ extern "C" {
|
||||
* 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.
|
||||
* Note: Dictionary training will fail if there are not enough samples to construct a
|
||||
* dictionary, or if most of the samples are too small (< 8 bytes being the lower limit).
|
||||
* If dictionary training fails, you should use zstd without a dictionary, as the dictionary
|
||||
* would've been ineffective anyways. If you believe your samples would benefit from a dictionary
|
||||
* please open an issue with details, and we can look into it.
|
||||
* Note: ZDICT_trainFromBuffer()'s memory usage is about 6 MB.
|
||||
* Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
|
||||
* It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`.
|
||||
* In general, it's recommended to provide a few thousands samples, though this can vary a lot.
|
||||
@ -110,6 +115,7 @@ typedef struct {
|
||||
* 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().
|
||||
* See ZDICT_trainFromBuffer() for details on failure modes.
|
||||
* 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 possible to select smaller or larger size, just by specifying `dictBufferCapacity`.
|
||||
@ -133,8 +139,9 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_cover(
|
||||
* If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [50, 2000].
|
||||
*
|
||||
* @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.
|
||||
* or an error code, which can be tested with ZDICT_isError().
|
||||
* On success `*parameters` contains the parameters selected.
|
||||
* See ZDICT_trainFromBuffer() for details on failure modes.
|
||||
* 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(
|
||||
@ -151,7 +158,8 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_cover(
|
||||
* 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_fastCover() requires about 1 bytes of memory for each input byte and additionally another 6 * 2^f bytes of memory .
|
||||
* See ZDICT_trainFromBuffer() for details on failure modes.
|
||||
* Note: ZDICT_trainFromBuffer_fastCover() requires 6 * 2^f bytes of memory.
|
||||
* Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
|
||||
* It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`.
|
||||
* In general, it's recommended to provide a few thousands samples, though this can vary a lot.
|
||||
@ -175,9 +183,10 @@ ZDICTLIB_API size_t ZDICT_trainFromBuffer_fastCover(void *dictBuffer,
|
||||
* If accel is zero, default value of 1 is used.
|
||||
*
|
||||
* @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_fastCover() requires about 1 byte of memory for each input byte and additionally another 6 * 2^f bytes of memory for each thread.
|
||||
* or an error code, which can be tested with ZDICT_isError().
|
||||
* On success `*parameters` contains the parameters selected.
|
||||
* See ZDICT_trainFromBuffer() for details on failure modes.
|
||||
* Note: ZDICT_optimizeTrainFromBuffer_fastCover() requires about 6 * 2^f bytes of memory for each thread.
|
||||
*/
|
||||
ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_fastCover(void* dictBuffer,
|
||||
size_t dictBufferCapacity, const void* samplesBuffer,
|
||||
@ -195,7 +204,7 @@ ZDICTLIB_API size_t ZDICT_optimizeTrainFromBuffer_fastCover(void* dictBuffer,
|
||||
* 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().
|
||||
* 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
|
||||
*/
|
||||
@ -219,6 +228,7 @@ typedef struct {
|
||||
* `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().
|
||||
* See ZDICT_trainFromBuffer() for details on failure modes.
|
||||
* Tips: In general, a reasonable dictionary has a size of ~ 100 KB.
|
||||
* It's possible to select smaller or larger size, just by specifying `dictBufferCapacity`.
|
||||
* In general, it's recommended to provide a few thousands samples, though this can vary a lot.
|
||||
|
@ -6,14 +6,15 @@ COPY programs\datagen.h bin\example\
|
||||
COPY programs\util.h bin\example\
|
||||
COPY programs\platform.h bin\example\
|
||||
COPY lib\common\mem.h bin\example\
|
||||
COPY lib\common\zstd_errors.h bin\example\
|
||||
COPY lib\common\zstd_internal.h bin\example\
|
||||
COPY lib\common\error_private.h bin\example\
|
||||
COPY lib\common\xxhash.h bin\example\
|
||||
COPY lib\zstd.h bin\include\
|
||||
COPY lib\libzstd.a bin\static\libzstd_static.lib
|
||||
COPY lib\dll\libzstd.* bin\dll\
|
||||
COPY lib\dll\example\Makefile bin\example\
|
||||
COPY lib\dll\example\fullbench-dll.* bin\example\
|
||||
COPY lib\dll\example\README.md bin\
|
||||
COPY lib\zstd.h bin\include\
|
||||
COPY lib\common\zstd_errors.h bin\include\
|
||||
COPY lib\dictBuilder\zdict.h bin\include\
|
||||
COPY programs\zstd.exe bin\zstd.exe
|
||||
|
@ -1,87 +0,0 @@
|
||||
LIBRARY libzstd.dll
|
||||
EXPORTS
|
||||
ZDICT_getDictID
|
||||
ZDICT_getErrorName
|
||||
ZDICT_isError
|
||||
ZDICT_trainFromBuffer
|
||||
ZSTD_CStreamInSize
|
||||
ZSTD_CStreamOutSize
|
||||
ZSTD_DStreamInSize
|
||||
ZSTD_DStreamOutSize
|
||||
ZSTD_adjustCParams
|
||||
ZSTD_checkCParams
|
||||
ZSTD_compress
|
||||
ZSTD_compressBegin
|
||||
ZSTD_compressBegin_advanced
|
||||
ZSTD_compressBegin_usingDict
|
||||
ZSTD_compressBlock
|
||||
ZSTD_compressBound
|
||||
ZSTD_compressCCtx
|
||||
ZSTD_compressContinue
|
||||
ZSTD_compressEnd
|
||||
ZSTD_compressStream
|
||||
ZSTD_compress_advanced
|
||||
ZSTD_compress_usingCDict
|
||||
ZSTD_compress_usingDict
|
||||
ZSTD_copyCCtx
|
||||
ZSTD_copyDCtx
|
||||
ZSTD_createCCtx
|
||||
ZSTD_createCCtx_advanced
|
||||
ZSTD_createCDict
|
||||
ZSTD_createCDict_advanced
|
||||
ZSTD_createCStream
|
||||
ZSTD_createCStream_advanced
|
||||
ZSTD_createDCtx
|
||||
ZSTD_createDCtx_advanced
|
||||
ZSTD_createDDict
|
||||
ZSTD_createDStream
|
||||
ZSTD_createDStream_advanced
|
||||
ZSTD_decompress
|
||||
ZSTD_decompressBegin
|
||||
ZSTD_decompressBegin_usingDict
|
||||
ZSTD_decompressBlock
|
||||
ZSTD_decompressContinue
|
||||
ZSTD_decompressDCtx
|
||||
ZSTD_decompressStream
|
||||
ZSTD_decompress_usingDDict
|
||||
ZSTD_decompress_usingDict
|
||||
ZSTD_endStream
|
||||
ZSTD_estimateCCtxSize
|
||||
ZSTD_estimateDCtxSize
|
||||
ZSTD_flushStream
|
||||
ZSTD_freeCCtx
|
||||
ZSTD_freeCDict
|
||||
ZSTD_freeCStream
|
||||
ZSTD_freeDCtx
|
||||
ZSTD_freeDDict
|
||||
ZSTD_freeDStream
|
||||
ZSTD_getBlockSizeMax
|
||||
ZSTD_getCParams
|
||||
ZSTD_getDecompressedSize
|
||||
ZSTD_findDecompressedSize
|
||||
ZSTD_getFrameContentSize
|
||||
ZSTD_getErrorName
|
||||
ZSTD_getFrameParams
|
||||
ZSTD_getParams
|
||||
ZSTD_initCStream
|
||||
ZSTD_initCStream_advanced
|
||||
ZSTD_initCStream_usingCDict
|
||||
ZSTD_initCStream_usingDict
|
||||
ZSTD_initDStream
|
||||
ZSTD_initDStream_usingDDict
|
||||
ZSTD_initDStream_usingDict
|
||||
ZSTD_insertBlock
|
||||
ZSTD_isError
|
||||
ZSTD_isFrame
|
||||
ZSTD_maxCLevel
|
||||
ZSTD_nextInputType
|
||||
ZSTD_nextSrcSizeToDecompress
|
||||
ZSTD_resetCStream
|
||||
ZSTD_resetDStream
|
||||
ZSTD_sizeof_CCtx
|
||||
ZSTD_sizeof_CDict
|
||||
ZSTD_sizeof_CStream
|
||||
ZSTD_sizeof_DCtx
|
||||
ZSTD_sizeof_DDict
|
||||
ZSTD_sizeof_DStream
|
||||
ZSTD_versionNumber
|
@ -20,7 +20,7 @@ extern "C" {
|
||||
***************************************/
|
||||
#include "mem.h" /* MEM_STATIC */
|
||||
#include "error_private.h" /* ERROR */
|
||||
#include "zstd.h" /* ZSTD_inBuffer, ZSTD_outBuffer */
|
||||
#include "zstd_internal.h" /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTD_frameSizeInfo */
|
||||
|
||||
#if !defined (ZSTD_LEGACY_SUPPORT) || (ZSTD_LEGACY_SUPPORT == 0)
|
||||
# undef ZSTD_LEGACY_SUPPORT
|
||||
@ -178,43 +178,73 @@ MEM_STATIC size_t ZSTD_decompressLegacy(
|
||||
}
|
||||
}
|
||||
|
||||
MEM_STATIC size_t ZSTD_findFrameCompressedSizeLegacy(const void *src,
|
||||
size_t compressedSize)
|
||||
MEM_STATIC ZSTD_frameSizeInfo ZSTD_findFrameSizeInfoLegacy(const void *src, size_t srcSize)
|
||||
{
|
||||
U32 const version = ZSTD_isLegacy(src, compressedSize);
|
||||
ZSTD_frameSizeInfo frameSizeInfo;
|
||||
U32 const version = ZSTD_isLegacy(src, srcSize);
|
||||
switch(version)
|
||||
{
|
||||
#if (ZSTD_LEGACY_SUPPORT <= 1)
|
||||
case 1 :
|
||||
return ZSTDv01_findFrameCompressedSize(src, compressedSize);
|
||||
ZSTDv01_findFrameSizeInfoLegacy(src, srcSize,
|
||||
&frameSizeInfo.compressedSize,
|
||||
&frameSizeInfo.decompressedBound);
|
||||
break;
|
||||
#endif
|
||||
#if (ZSTD_LEGACY_SUPPORT <= 2)
|
||||
case 2 :
|
||||
return ZSTDv02_findFrameCompressedSize(src, compressedSize);
|
||||
ZSTDv02_findFrameSizeInfoLegacy(src, srcSize,
|
||||
&frameSizeInfo.compressedSize,
|
||||
&frameSizeInfo.decompressedBound);
|
||||
break;
|
||||
#endif
|
||||
#if (ZSTD_LEGACY_SUPPORT <= 3)
|
||||
case 3 :
|
||||
return ZSTDv03_findFrameCompressedSize(src, compressedSize);
|
||||
ZSTDv03_findFrameSizeInfoLegacy(src, srcSize,
|
||||
&frameSizeInfo.compressedSize,
|
||||
&frameSizeInfo.decompressedBound);
|
||||
break;
|
||||
#endif
|
||||
#if (ZSTD_LEGACY_SUPPORT <= 4)
|
||||
case 4 :
|
||||
return ZSTDv04_findFrameCompressedSize(src, compressedSize);
|
||||
ZSTDv04_findFrameSizeInfoLegacy(src, srcSize,
|
||||
&frameSizeInfo.compressedSize,
|
||||
&frameSizeInfo.decompressedBound);
|
||||
break;
|
||||
#endif
|
||||
#if (ZSTD_LEGACY_SUPPORT <= 5)
|
||||
case 5 :
|
||||
return ZSTDv05_findFrameCompressedSize(src, compressedSize);
|
||||
ZSTDv05_findFrameSizeInfoLegacy(src, srcSize,
|
||||
&frameSizeInfo.compressedSize,
|
||||
&frameSizeInfo.decompressedBound);
|
||||
break;
|
||||
#endif
|
||||
#if (ZSTD_LEGACY_SUPPORT <= 6)
|
||||
case 6 :
|
||||
return ZSTDv06_findFrameCompressedSize(src, compressedSize);
|
||||
ZSTDv06_findFrameSizeInfoLegacy(src, srcSize,
|
||||
&frameSizeInfo.compressedSize,
|
||||
&frameSizeInfo.decompressedBound);
|
||||
break;
|
||||
#endif
|
||||
#if (ZSTD_LEGACY_SUPPORT <= 7)
|
||||
case 7 :
|
||||
return ZSTDv07_findFrameCompressedSize(src, compressedSize);
|
||||
ZSTDv07_findFrameSizeInfoLegacy(src, srcSize,
|
||||
&frameSizeInfo.compressedSize,
|
||||
&frameSizeInfo.decompressedBound);
|
||||
break;
|
||||
#endif
|
||||
default :
|
||||
return ERROR(prefix_unknown);
|
||||
frameSizeInfo.compressedSize = ERROR(prefix_unknown);
|
||||
frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR;
|
||||
break;
|
||||
}
|
||||
return frameSizeInfo;
|
||||
}
|
||||
|
||||
MEM_STATIC size_t ZSTD_findFrameCompressedSizeLegacy(const void *src, size_t srcSize)
|
||||
{
|
||||
ZSTD_frameSizeInfo frameSizeInfo = ZSTD_findFrameSizeInfoLegacy(src, srcSize);
|
||||
return frameSizeInfo.compressedSize;
|
||||
}
|
||||
|
||||
MEM_STATIC size_t ZSTD_freeLegacyStreamContext(void* legacyContext, U32 version)
|
||||
|
@ -1336,6 +1336,8 @@ static const U32 ZSTD_magicNumber = 0xFD2FB51E; /* 3rd version : seqNb header
|
||||
#define LITERAL_NOENTROPY 63
|
||||
#define COMMAND_NOENTROPY 7 /* to remove */
|
||||
|
||||
#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2)
|
||||
|
||||
static const size_t ZSTD_blockHeaderSize = 3;
|
||||
static const size_t ZSTD_frameHeaderSize = 4;
|
||||
|
||||
@ -1999,36 +2001,59 @@ size_t ZSTDv01_decompress(void* dst, size_t maxDstSize, const void* src, size_t
|
||||
return ZSTDv01_decompressDCtx(&ctx, dst, maxDstSize, src, srcSize);
|
||||
}
|
||||
|
||||
size_t ZSTDv01_findFrameCompressedSize(const void* src, size_t srcSize)
|
||||
/* ZSTD_errorFrameSizeInfoLegacy() :
|
||||
assumes `cSize` and `dBound` are _not_ NULL */
|
||||
static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
|
||||
{
|
||||
*cSize = ret;
|
||||
*dBound = ZSTD_CONTENTSIZE_ERROR;
|
||||
}
|
||||
|
||||
void ZSTDv01_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
|
||||
{
|
||||
const BYTE* ip = (const BYTE*)src;
|
||||
size_t remainingSize = srcSize;
|
||||
size_t nbBlocks = 0;
|
||||
U32 magicNumber;
|
||||
blockProperties_t blockProperties;
|
||||
|
||||
/* Frame Header */
|
||||
if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) return ERROR(srcSize_wrong);
|
||||
if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
magicNumber = ZSTD_readBE32(src);
|
||||
if (magicNumber != ZSTD_magicNumber) return ERROR(prefix_unknown);
|
||||
if (magicNumber != ZSTD_magicNumber) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
|
||||
return;
|
||||
}
|
||||
ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize;
|
||||
|
||||
/* Loop on each block */
|
||||
while (1)
|
||||
{
|
||||
size_t blockSize = ZSTDv01_getcBlockSize(ip, remainingSize, &blockProperties);
|
||||
if (ZSTDv01_isError(blockSize)) return blockSize;
|
||||
if (ZSTDv01_isError(blockSize)) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, blockSize);
|
||||
return;
|
||||
}
|
||||
|
||||
ip += ZSTD_blockHeaderSize;
|
||||
remainingSize -= ZSTD_blockHeaderSize;
|
||||
if (blockSize > remainingSize) return ERROR(srcSize_wrong);
|
||||
if (blockSize > remainingSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
|
||||
if (blockSize == 0) break; /* bt_end */
|
||||
|
||||
ip += blockSize;
|
||||
remainingSize -= blockSize;
|
||||
nbBlocks++;
|
||||
}
|
||||
|
||||
return ip - (const BYTE*)src;
|
||||
*cSize = ip - (const BYTE*)src;
|
||||
*dBound = nbBlocks * BLOCKSIZE;
|
||||
}
|
||||
|
||||
/*******************************
|
||||
|
@ -35,13 +35,18 @@ ZSTDv01_decompress() : decompress ZSTD frames compliant with v0.1.x format
|
||||
size_t ZSTDv01_decompress( void* dst, size_t maxOriginalSize,
|
||||
const void* src, size_t compressedSize);
|
||||
|
||||
/**
|
||||
ZSTDv01_getFrameSrcSize() : get the source length of a ZSTD frame compliant with v0.1.x format
|
||||
compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
return : the number of bytes that would be read to decompress this frame
|
||||
or an errorCode if it fails (which can be tested using ZSTDv01_isError())
|
||||
*/
|
||||
size_t ZSTDv01_findFrameCompressedSize(const void* src, size_t compressedSize);
|
||||
/**
|
||||
ZSTDv01_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.1.x format
|
||||
srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
cSize (output parameter) : the number of bytes that would be read to decompress this frame
|
||||
or an error code if it fails (which can be tested using ZSTDv01_isError())
|
||||
dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
|
||||
or ZSTD_CONTENTSIZE_ERROR if an error occurs
|
||||
|
||||
note : assumes `cSize` and `dBound` are _not_ NULL.
|
||||
*/
|
||||
void ZSTDv01_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
|
||||
size_t* cSize, unsigned long long* dBound);
|
||||
|
||||
/**
|
||||
ZSTDv01_isError() : tells if the result of ZSTDv01_decompress() is an error
|
||||
|
@ -2728,6 +2728,8 @@ static size_t HUF_decompress (void* dst, size_t dstSize, const void* cSrc, size_
|
||||
#define LITERAL_NOENTROPY 63
|
||||
#define COMMAND_NOENTROPY 7 /* to remove */
|
||||
|
||||
#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2)
|
||||
|
||||
static const size_t ZSTD_blockHeaderSize = 3;
|
||||
static const size_t ZSTD_frameHeaderSize = 4;
|
||||
|
||||
@ -3312,37 +3314,59 @@ static size_t ZSTD_decompress(void* dst, size_t maxDstSize, const void* src, siz
|
||||
return ZSTD_decompressDCtx(&ctx, dst, maxDstSize, src, srcSize);
|
||||
}
|
||||
|
||||
static size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize)
|
||||
/* ZSTD_errorFrameSizeInfoLegacy() :
|
||||
assumes `cSize` and `dBound` are _not_ NULL */
|
||||
static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
|
||||
{
|
||||
*cSize = ret;
|
||||
*dBound = ZSTD_CONTENTSIZE_ERROR;
|
||||
}
|
||||
|
||||
void ZSTDv02_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
|
||||
{
|
||||
const BYTE* ip = (const BYTE*)src;
|
||||
size_t remainingSize = srcSize;
|
||||
size_t nbBlocks = 0;
|
||||
U32 magicNumber;
|
||||
blockProperties_t blockProperties;
|
||||
|
||||
/* Frame Header */
|
||||
if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) return ERROR(srcSize_wrong);
|
||||
if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
magicNumber = MEM_readLE32(src);
|
||||
if (magicNumber != ZSTD_magicNumber) return ERROR(prefix_unknown);
|
||||
if (magicNumber != ZSTD_magicNumber) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
|
||||
return;
|
||||
}
|
||||
ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize;
|
||||
|
||||
/* Loop on each block */
|
||||
while (1)
|
||||
{
|
||||
size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
|
||||
if (ZSTD_isError(cBlockSize)) return cBlockSize;
|
||||
if (ZSTD_isError(cBlockSize)) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize);
|
||||
return;
|
||||
}
|
||||
|
||||
ip += ZSTD_blockHeaderSize;
|
||||
remainingSize -= ZSTD_blockHeaderSize;
|
||||
if (cBlockSize > remainingSize) return ERROR(srcSize_wrong);
|
||||
if (cBlockSize > remainingSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
|
||||
if (cBlockSize == 0) break; /* bt_end */
|
||||
|
||||
ip += cBlockSize;
|
||||
remainingSize -= cBlockSize;
|
||||
nbBlocks++;
|
||||
}
|
||||
|
||||
return ip - (const BYTE*)src;
|
||||
*cSize = ip - (const BYTE*)src;
|
||||
*dBound = nbBlocks * BLOCKSIZE;
|
||||
}
|
||||
|
||||
/*******************************
|
||||
@ -3458,11 +3482,6 @@ size_t ZSTDv02_decompress( void* dst, size_t maxOriginalSize,
|
||||
return ZSTD_decompress(dst, maxOriginalSize, src, compressedSize);
|
||||
}
|
||||
|
||||
size_t ZSTDv02_findFrameCompressedSize(const void *src, size_t compressedSize)
|
||||
{
|
||||
return ZSTD_findFrameCompressedSize(src, compressedSize);
|
||||
}
|
||||
|
||||
ZSTDv02_Dctx* ZSTDv02_createDCtx(void)
|
||||
{
|
||||
return (ZSTDv02_Dctx*)ZSTD_createDCtx();
|
||||
|
@ -35,13 +35,18 @@ ZSTDv02_decompress() : decompress ZSTD frames compliant with v0.2.x format
|
||||
size_t ZSTDv02_decompress( void* dst, size_t maxOriginalSize,
|
||||
const void* src, size_t compressedSize);
|
||||
|
||||
/**
|
||||
ZSTDv02_getFrameSrcSize() : get the source length of a ZSTD frame compliant with v0.2.x format
|
||||
compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
return : the number of bytes that would be read to decompress this frame
|
||||
or an errorCode if it fails (which can be tested using ZSTDv02_isError())
|
||||
*/
|
||||
size_t ZSTDv02_findFrameCompressedSize(const void* src, size_t compressedSize);
|
||||
/**
|
||||
ZSTDv02_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.2.x format
|
||||
srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
cSize (output parameter) : the number of bytes that would be read to decompress this frame
|
||||
or an error code if it fails (which can be tested using ZSTDv01_isError())
|
||||
dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
|
||||
or ZSTD_CONTENTSIZE_ERROR if an error occurs
|
||||
|
||||
note : assumes `cSize` and `dBound` are _not_ NULL.
|
||||
*/
|
||||
void ZSTDv02_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
|
||||
size_t* cSize, unsigned long long* dBound);
|
||||
|
||||
/**
|
||||
ZSTDv02_isError() : tells if the result of ZSTDv02_decompress() is an error
|
||||
|
@ -2369,6 +2369,8 @@ static size_t HUF_decompress (void* dst, size_t dstSize, const void* cSrc, size_
|
||||
#define LITERAL_NOENTROPY 63
|
||||
#define COMMAND_NOENTROPY 7 /* to remove */
|
||||
|
||||
#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2)
|
||||
|
||||
static const size_t ZSTD_blockHeaderSize = 3;
|
||||
static const size_t ZSTD_frameHeaderSize = 4;
|
||||
|
||||
@ -2953,36 +2955,59 @@ static size_t ZSTD_decompress(void* dst, size_t maxDstSize, const void* src, siz
|
||||
return ZSTD_decompressDCtx(&ctx, dst, maxDstSize, src, srcSize);
|
||||
}
|
||||
|
||||
static size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize)
|
||||
/* ZSTD_errorFrameSizeInfoLegacy() :
|
||||
assumes `cSize` and `dBound` are _not_ NULL */
|
||||
MEM_STATIC void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
|
||||
{
|
||||
*cSize = ret;
|
||||
*dBound = ZSTD_CONTENTSIZE_ERROR;
|
||||
}
|
||||
|
||||
void ZSTDv03_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
|
||||
{
|
||||
const BYTE* ip = (const BYTE*)src;
|
||||
size_t remainingSize = srcSize;
|
||||
size_t nbBlocks = 0;
|
||||
U32 magicNumber;
|
||||
blockProperties_t blockProperties;
|
||||
|
||||
/* Frame Header */
|
||||
if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) return ERROR(srcSize_wrong);
|
||||
if (srcSize < ZSTD_frameHeaderSize+ZSTD_blockHeaderSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
magicNumber = MEM_readLE32(src);
|
||||
if (magicNumber != ZSTD_magicNumber) return ERROR(prefix_unknown);
|
||||
if (magicNumber != ZSTD_magicNumber) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
|
||||
return;
|
||||
}
|
||||
ip += ZSTD_frameHeaderSize; remainingSize -= ZSTD_frameHeaderSize;
|
||||
|
||||
/* Loop on each block */
|
||||
while (1)
|
||||
{
|
||||
size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
|
||||
if (ZSTD_isError(cBlockSize)) return cBlockSize;
|
||||
if (ZSTD_isError(cBlockSize)) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize);
|
||||
return;
|
||||
}
|
||||
|
||||
ip += ZSTD_blockHeaderSize;
|
||||
remainingSize -= ZSTD_blockHeaderSize;
|
||||
if (cBlockSize > remainingSize) return ERROR(srcSize_wrong);
|
||||
if (cBlockSize > remainingSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
|
||||
if (cBlockSize == 0) break; /* bt_end */
|
||||
|
||||
ip += cBlockSize;
|
||||
remainingSize -= cBlockSize;
|
||||
nbBlocks++;
|
||||
}
|
||||
|
||||
return ip - (const BYTE*)src;
|
||||
*cSize = ip - (const BYTE*)src;
|
||||
*dBound = nbBlocks * BLOCKSIZE;
|
||||
}
|
||||
|
||||
|
||||
@ -3099,11 +3124,6 @@ size_t ZSTDv03_decompress( void* dst, size_t maxOriginalSize,
|
||||
return ZSTD_decompress(dst, maxOriginalSize, src, compressedSize);
|
||||
}
|
||||
|
||||
size_t ZSTDv03_findFrameCompressedSize(const void* src, size_t srcSize)
|
||||
{
|
||||
return ZSTD_findFrameCompressedSize(src, srcSize);
|
||||
}
|
||||
|
||||
ZSTDv03_Dctx* ZSTDv03_createDCtx(void)
|
||||
{
|
||||
return (ZSTDv03_Dctx*)ZSTD_createDCtx();
|
||||
|
@ -35,13 +35,18 @@ ZSTDv03_decompress() : decompress ZSTD frames compliant with v0.3.x format
|
||||
size_t ZSTDv03_decompress( void* dst, size_t maxOriginalSize,
|
||||
const void* src, size_t compressedSize);
|
||||
|
||||
/**
|
||||
ZSTDv03_getFrameSrcSize() : get the source length of a ZSTD frame compliant with v0.3.x format
|
||||
compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
return : the number of bytes that would be read to decompress this frame
|
||||
or an errorCode if it fails (which can be tested using ZSTDv03_isError())
|
||||
*/
|
||||
size_t ZSTDv03_findFrameCompressedSize(const void* src, size_t compressedSize);
|
||||
/**
|
||||
ZSTDv03_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.3.x format
|
||||
srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
cSize (output parameter) : the number of bytes that would be read to decompress this frame
|
||||
or an error code if it fails (which can be tested using ZSTDv01_isError())
|
||||
dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
|
||||
or ZSTD_CONTENTSIZE_ERROR if an error occurs
|
||||
|
||||
note : assumes `cSize` and `dBound` are _not_ NULL.
|
||||
*/
|
||||
void ZSTDv03_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
|
||||
size_t* cSize, unsigned long long* dBound);
|
||||
|
||||
/**
|
||||
ZSTDv03_isError() : tells if the result of ZSTDv03_decompress() is an error
|
||||
|
@ -373,6 +373,8 @@ static const size_t ZSTD_frameHeaderSize_min = 5;
|
||||
#define MIN_SEQUENCES_SIZE (2 /*seqNb*/ + 2 /*dumps*/ + 3 /*seqTables*/ + 1 /*bitStream*/)
|
||||
#define MIN_CBLOCK_SIZE (3 /*litCSize*/ + MIN_SEQUENCES_SIZE)
|
||||
|
||||
#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2)
|
||||
|
||||
typedef enum { bt_compressed, bt_raw, bt_rle, bt_end } blockType_t;
|
||||
|
||||
|
||||
@ -3119,34 +3121,57 @@ static size_t ZSTD_decompress_usingDict(ZSTD_DCtx* ctx,
|
||||
return op-ostart;
|
||||
}
|
||||
|
||||
static size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize)
|
||||
/* ZSTD_errorFrameSizeInfoLegacy() :
|
||||
assumes `cSize` and `dBound` are _not_ NULL */
|
||||
static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
|
||||
{
|
||||
*cSize = ret;
|
||||
*dBound = ZSTD_CONTENTSIZE_ERROR;
|
||||
}
|
||||
|
||||
void ZSTDv04_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
|
||||
{
|
||||
const BYTE* ip = (const BYTE*)src;
|
||||
size_t remainingSize = srcSize;
|
||||
size_t nbBlocks = 0;
|
||||
blockProperties_t blockProperties;
|
||||
|
||||
/* Frame Header */
|
||||
if (srcSize < ZSTD_frameHeaderSize_min) return ERROR(srcSize_wrong);
|
||||
if (MEM_readLE32(src) != ZSTD_MAGICNUMBER) return ERROR(prefix_unknown);
|
||||
if (srcSize < ZSTD_frameHeaderSize_min) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
if (MEM_readLE32(src) != ZSTD_MAGICNUMBER) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
|
||||
return;
|
||||
}
|
||||
ip += ZSTD_frameHeaderSize_min; remainingSize -= ZSTD_frameHeaderSize_min;
|
||||
|
||||
/* Loop on each block */
|
||||
while (1)
|
||||
{
|
||||
size_t cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
|
||||
if (ZSTD_isError(cBlockSize)) return cBlockSize;
|
||||
if (ZSTD_isError(cBlockSize)) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize);
|
||||
return;
|
||||
}
|
||||
|
||||
ip += ZSTD_blockHeaderSize;
|
||||
remainingSize -= ZSTD_blockHeaderSize;
|
||||
if (cBlockSize > remainingSize) return ERROR(srcSize_wrong);
|
||||
if (cBlockSize > remainingSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
|
||||
if (cBlockSize == 0) break; /* bt_end */
|
||||
|
||||
ip += cBlockSize;
|
||||
remainingSize -= cBlockSize;
|
||||
nbBlocks++;
|
||||
}
|
||||
|
||||
return ip - (const BYTE*)src;
|
||||
*cSize = ip - (const BYTE*)src;
|
||||
*dBound = nbBlocks * BLOCKSIZE;
|
||||
}
|
||||
|
||||
/* ******************************
|
||||
@ -3578,11 +3603,6 @@ size_t ZSTDv04_decompress(void* dst, size_t maxDstSize, const void* src, size_t
|
||||
#endif
|
||||
}
|
||||
|
||||
size_t ZSTDv04_findFrameCompressedSize(const void* src, size_t srcSize)
|
||||
{
|
||||
return ZSTD_findFrameCompressedSize(src, srcSize);
|
||||
}
|
||||
|
||||
size_t ZSTDv04_resetDCtx(ZSTDv04_Dctx* dctx) { return ZSTD_resetDCtx(dctx); }
|
||||
|
||||
size_t ZSTDv04_nextSrcSizeToDecompress(ZSTDv04_Dctx* dctx)
|
||||
|
@ -35,13 +35,18 @@ ZSTDv04_decompress() : decompress ZSTD frames compliant with v0.4.x format
|
||||
size_t ZSTDv04_decompress( void* dst, size_t maxOriginalSize,
|
||||
const void* src, size_t compressedSize);
|
||||
|
||||
/**
|
||||
ZSTDv04_getFrameSrcSize() : get the source length of a ZSTD frame compliant with v0.4.x format
|
||||
compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
return : the number of bytes that would be read to decompress this frame
|
||||
or an errorCode if it fails (which can be tested using ZSTDv04_isError())
|
||||
*/
|
||||
size_t ZSTDv04_findFrameCompressedSize(const void* src, size_t compressedSize);
|
||||
/**
|
||||
ZSTDv04_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.4.x format
|
||||
srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
cSize (output parameter) : the number of bytes that would be read to decompress this frame
|
||||
or an error code if it fails (which can be tested using ZSTDv01_isError())
|
||||
dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
|
||||
or ZSTD_CONTENTSIZE_ERROR if an error occurs
|
||||
|
||||
note : assumes `cSize` and `dBound` are _not_ NULL.
|
||||
*/
|
||||
void ZSTDv04_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
|
||||
size_t* cSize, unsigned long long* dBound);
|
||||
|
||||
/**
|
||||
ZSTDv04_isError() : tells if the result of ZSTDv04_decompress() is an error
|
||||
|
@ -491,6 +491,8 @@ static const size_t ZSTDv05_frameHeaderSize_min = 5;
|
||||
|
||||
#define WILDCOPY_OVERLENGTH 8
|
||||
|
||||
#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2)
|
||||
|
||||
typedef enum { bt_compressed, bt_raw, bt_rle, bt_end } blockType_t;
|
||||
|
||||
|
||||
@ -3508,34 +3510,57 @@ size_t ZSTDv05_decompress(void* dst, size_t maxDstSize, const void* src, size_t
|
||||
#endif
|
||||
}
|
||||
|
||||
size_t ZSTDv05_findFrameCompressedSize(const void *src, size_t srcSize)
|
||||
/* ZSTD_errorFrameSizeInfoLegacy() :
|
||||
assumes `cSize` and `dBound` are _not_ NULL */
|
||||
static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
|
||||
{
|
||||
*cSize = ret;
|
||||
*dBound = ZSTD_CONTENTSIZE_ERROR;
|
||||
}
|
||||
|
||||
void ZSTDv05_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
|
||||
{
|
||||
const BYTE* ip = (const BYTE*)src;
|
||||
size_t remainingSize = srcSize;
|
||||
size_t nbBlocks = 0;
|
||||
blockProperties_t blockProperties;
|
||||
|
||||
/* Frame Header */
|
||||
if (srcSize < ZSTDv05_frameHeaderSize_min) return ERROR(srcSize_wrong);
|
||||
if (MEM_readLE32(src) != ZSTDv05_MAGICNUMBER) return ERROR(prefix_unknown);
|
||||
if (srcSize < ZSTDv05_frameHeaderSize_min) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
if (MEM_readLE32(src) != ZSTDv05_MAGICNUMBER) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
|
||||
return;
|
||||
}
|
||||
ip += ZSTDv05_frameHeaderSize_min; remainingSize -= ZSTDv05_frameHeaderSize_min;
|
||||
|
||||
/* Loop on each block */
|
||||
while (1)
|
||||
{
|
||||
size_t cBlockSize = ZSTDv05_getcBlockSize(ip, remainingSize, &blockProperties);
|
||||
if (ZSTDv05_isError(cBlockSize)) return cBlockSize;
|
||||
if (ZSTDv05_isError(cBlockSize)) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize);
|
||||
return;
|
||||
}
|
||||
|
||||
ip += ZSTDv05_blockHeaderSize;
|
||||
remainingSize -= ZSTDv05_blockHeaderSize;
|
||||
if (cBlockSize > remainingSize) return ERROR(srcSize_wrong);
|
||||
if (cBlockSize > remainingSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
|
||||
if (cBlockSize == 0) break; /* bt_end */
|
||||
|
||||
ip += cBlockSize;
|
||||
remainingSize -= cBlockSize;
|
||||
nbBlocks++;
|
||||
}
|
||||
|
||||
return ip - (const BYTE*)src;
|
||||
*cSize = ip - (const BYTE*)src;
|
||||
*dBound = nbBlocks * BLOCKSIZE;
|
||||
}
|
||||
|
||||
/* ******************************
|
||||
|
@ -33,13 +33,18 @@ extern "C" {
|
||||
size_t ZSTDv05_decompress( void* dst, size_t dstCapacity,
|
||||
const void* src, size_t compressedSize);
|
||||
|
||||
/**
|
||||
ZSTDv05_getFrameSrcSize() : get the source length of a ZSTD frame
|
||||
compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
return : the number of bytes that would be read to decompress this frame
|
||||
or an errorCode if it fails (which can be tested using ZSTDv05_isError())
|
||||
*/
|
||||
size_t ZSTDv05_findFrameCompressedSize(const void* src, size_t compressedSize);
|
||||
/**
|
||||
ZSTDv05_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.5.x format
|
||||
srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
cSize (output parameter) : the number of bytes that would be read to decompress this frame
|
||||
or an error code if it fails (which can be tested using ZSTDv01_isError())
|
||||
dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
|
||||
or ZSTD_CONTENTSIZE_ERROR if an error occurs
|
||||
|
||||
note : assumes `cSize` and `dBound` are _not_ NULL.
|
||||
*/
|
||||
void ZSTDv05_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
|
||||
size_t* cSize, unsigned long long* dBound);
|
||||
|
||||
/* *************************************
|
||||
* Helper functions
|
||||
|
@ -506,6 +506,8 @@ typedef enum { bt_compressed, bt_raw, bt_rle, bt_end } blockType_t;
|
||||
#define FSEv06_ENCODING_STATIC 2
|
||||
#define FSEv06_ENCODING_DYNAMIC 3
|
||||
|
||||
#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2)
|
||||
|
||||
static const U32 LL_bits[MaxLL+1] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
1, 1, 1, 1, 2, 2, 3, 3, 4, 6, 7, 8, 9,10,11,12,
|
||||
13,14,15,16 };
|
||||
@ -3654,36 +3656,62 @@ size_t ZSTDv06_decompress(void* dst, size_t dstCapacity, const void* src, size_t
|
||||
#endif
|
||||
}
|
||||
|
||||
size_t ZSTDv06_findFrameCompressedSize(const void* src, size_t srcSize)
|
||||
/* ZSTD_errorFrameSizeInfoLegacy() :
|
||||
assumes `cSize` and `dBound` are _not_ NULL */
|
||||
static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
|
||||
{
|
||||
*cSize = ret;
|
||||
*dBound = ZSTD_CONTENTSIZE_ERROR;
|
||||
}
|
||||
|
||||
void ZSTDv06_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
|
||||
{
|
||||
const BYTE* ip = (const BYTE*)src;
|
||||
size_t remainingSize = srcSize;
|
||||
size_t nbBlocks = 0;
|
||||
blockProperties_t blockProperties = { bt_compressed, 0 };
|
||||
|
||||
/* Frame Header */
|
||||
{ size_t const frameHeaderSize = ZSTDv06_frameHeaderSize(src, ZSTDv06_frameHeaderSize_min);
|
||||
if (ZSTDv06_isError(frameHeaderSize)) return frameHeaderSize;
|
||||
if (MEM_readLE32(src) != ZSTDv06_MAGICNUMBER) return ERROR(prefix_unknown);
|
||||
if (srcSize < frameHeaderSize+ZSTDv06_blockHeaderSize) return ERROR(srcSize_wrong);
|
||||
if (ZSTDv06_isError(frameHeaderSize)) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, frameHeaderSize);
|
||||
return;
|
||||
}
|
||||
if (MEM_readLE32(src) != ZSTDv06_MAGICNUMBER) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
|
||||
return;
|
||||
}
|
||||
if (srcSize < frameHeaderSize+ZSTDv06_blockHeaderSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
ip += frameHeaderSize; remainingSize -= frameHeaderSize;
|
||||
}
|
||||
|
||||
/* Loop on each block */
|
||||
while (1) {
|
||||
size_t const cBlockSize = ZSTDv06_getcBlockSize(ip, remainingSize, &blockProperties);
|
||||
if (ZSTDv06_isError(cBlockSize)) return cBlockSize;
|
||||
if (ZSTDv06_isError(cBlockSize)) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize);
|
||||
return;
|
||||
}
|
||||
|
||||
ip += ZSTDv06_blockHeaderSize;
|
||||
remainingSize -= ZSTDv06_blockHeaderSize;
|
||||
if (cBlockSize > remainingSize) return ERROR(srcSize_wrong);
|
||||
if (cBlockSize > remainingSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
|
||||
if (cBlockSize == 0) break; /* bt_end */
|
||||
|
||||
ip += cBlockSize;
|
||||
remainingSize -= cBlockSize;
|
||||
nbBlocks++;
|
||||
}
|
||||
|
||||
return ip - (const BYTE*)src;
|
||||
*cSize = ip - (const BYTE*)src;
|
||||
*dBound = nbBlocks * ZSTDv06_BLOCKSIZE_MAX;
|
||||
}
|
||||
|
||||
/*_******************************
|
||||
|
@ -43,12 +43,17 @@ ZSTDLIBv06_API size_t ZSTDv06_decompress( void* dst, size_t dstCapacity,
|
||||
const void* src, size_t compressedSize);
|
||||
|
||||
/**
|
||||
ZSTDv06_getFrameSrcSize() : get the source length of a ZSTD frame
|
||||
compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
return : the number of bytes that would be read to decompress this frame
|
||||
or an errorCode if it fails (which can be tested using ZSTDv06_isError())
|
||||
ZSTDv06_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.6.x format
|
||||
srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
cSize (output parameter) : the number of bytes that would be read to decompress this frame
|
||||
or an error code if it fails (which can be tested using ZSTDv01_isError())
|
||||
dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
|
||||
or ZSTD_CONTENTSIZE_ERROR if an error occurs
|
||||
|
||||
note : assumes `cSize` and `dBound` are _not_ NULL.
|
||||
*/
|
||||
size_t ZSTDv06_findFrameCompressedSize(const void* src, size_t compressedSize);
|
||||
void ZSTDv06_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
|
||||
size_t* cSize, unsigned long long* dBound);
|
||||
|
||||
/* *************************************
|
||||
* Helper functions
|
||||
|
@ -2740,6 +2740,8 @@ typedef enum { lbt_huffman, lbt_repeat, lbt_raw, lbt_rle } litBlockType_t;
|
||||
#define FSEv07_ENCODING_STATIC 2
|
||||
#define FSEv07_ENCODING_DYNAMIC 3
|
||||
|
||||
#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2)
|
||||
|
||||
static const U32 LL_bits[MaxLL+1] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
1, 1, 1, 1, 2, 2, 3, 3, 4, 6, 7, 8, 9,10,11,12,
|
||||
13,14,15,16 };
|
||||
@ -3895,19 +3897,40 @@ size_t ZSTDv07_decompress(void* dst, size_t dstCapacity, const void* src, size_t
|
||||
#endif
|
||||
}
|
||||
|
||||
size_t ZSTDv07_findFrameCompressedSize(const void* src, size_t srcSize)
|
||||
/* ZSTD_errorFrameSizeInfoLegacy() :
|
||||
assumes `cSize` and `dBound` are _not_ NULL */
|
||||
static void ZSTD_errorFrameSizeInfoLegacy(size_t* cSize, unsigned long long* dBound, size_t ret)
|
||||
{
|
||||
*cSize = ret;
|
||||
*dBound = ZSTD_CONTENTSIZE_ERROR;
|
||||
}
|
||||
|
||||
void ZSTDv07_findFrameSizeInfoLegacy(const void *src, size_t srcSize, size_t* cSize, unsigned long long* dBound)
|
||||
{
|
||||
const BYTE* ip = (const BYTE*)src;
|
||||
size_t remainingSize = srcSize;
|
||||
size_t nbBlocks = 0;
|
||||
|
||||
/* check */
|
||||
if (srcSize < ZSTDv07_frameHeaderSize_min+ZSTDv07_blockHeaderSize) return ERROR(srcSize_wrong);
|
||||
if (srcSize < ZSTDv07_frameHeaderSize_min+ZSTDv07_blockHeaderSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
|
||||
/* Frame Header */
|
||||
{ size_t const frameHeaderSize = ZSTDv07_frameHeaderSize(src, ZSTDv07_frameHeaderSize_min);
|
||||
if (ZSTDv07_isError(frameHeaderSize)) return frameHeaderSize;
|
||||
if (MEM_readLE32(src) != ZSTDv07_MAGICNUMBER) return ERROR(prefix_unknown);
|
||||
if (srcSize < frameHeaderSize+ZSTDv07_blockHeaderSize) return ERROR(srcSize_wrong);
|
||||
if (ZSTDv07_isError(frameHeaderSize)) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, frameHeaderSize);
|
||||
return;
|
||||
}
|
||||
if (MEM_readLE32(src) != ZSTDv07_MAGICNUMBER) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(prefix_unknown));
|
||||
return;
|
||||
}
|
||||
if (srcSize < frameHeaderSize+ZSTDv07_blockHeaderSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
ip += frameHeaderSize; remainingSize -= frameHeaderSize;
|
||||
}
|
||||
|
||||
@ -3915,20 +3938,28 @@ size_t ZSTDv07_findFrameCompressedSize(const void* src, size_t srcSize)
|
||||
while (1) {
|
||||
blockProperties_t blockProperties;
|
||||
size_t const cBlockSize = ZSTDv07_getcBlockSize(ip, remainingSize, &blockProperties);
|
||||
if (ZSTDv07_isError(cBlockSize)) return cBlockSize;
|
||||
if (ZSTDv07_isError(cBlockSize)) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, cBlockSize);
|
||||
return;
|
||||
}
|
||||
|
||||
ip += ZSTDv07_blockHeaderSize;
|
||||
remainingSize -= ZSTDv07_blockHeaderSize;
|
||||
|
||||
if (blockProperties.blockType == bt_end) break;
|
||||
|
||||
if (cBlockSize > remainingSize) return ERROR(srcSize_wrong);
|
||||
if (cBlockSize > remainingSize) {
|
||||
ZSTD_errorFrameSizeInfoLegacy(cSize, dBound, ERROR(srcSize_wrong));
|
||||
return;
|
||||
}
|
||||
|
||||
ip += cBlockSize;
|
||||
remainingSize -= cBlockSize;
|
||||
nbBlocks++;
|
||||
}
|
||||
|
||||
return ip - (const BYTE*)src;
|
||||
*cSize = ip - (const BYTE*)src;
|
||||
*dBound = nbBlocks * ZSTDv07_BLOCKSIZE_ABSOLUTEMAX;
|
||||
}
|
||||
|
||||
/*_******************************
|
||||
|
@ -50,12 +50,17 @@ ZSTDLIBv07_API size_t ZSTDv07_decompress( void* dst, size_t dstCapacity,
|
||||
const void* src, size_t compressedSize);
|
||||
|
||||
/**
|
||||
ZSTDv07_getFrameSrcSize() : get the source length of a ZSTD frame
|
||||
compressedSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
return : the number of bytes that would be read to decompress this frame
|
||||
or an errorCode if it fails (which can be tested using ZSTDv07_isError())
|
||||
ZSTDv07_findFrameSizeInfoLegacy() : get the source length and decompressed bound of a ZSTD frame compliant with v0.7.x format
|
||||
srcSize : The size of the 'src' buffer, at least as large as the frame pointed to by 'src'
|
||||
cSize (output parameter) : the number of bytes that would be read to decompress this frame
|
||||
or an error code if it fails (which can be tested using ZSTDv01_isError())
|
||||
dBound (output parameter) : an upper-bound for the decompressed size of the data in the frame
|
||||
or ZSTD_CONTENTSIZE_ERROR if an error occurs
|
||||
|
||||
note : assumes `cSize` and `dBound` are _not_ NULL.
|
||||
*/
|
||||
size_t ZSTDv07_findFrameCompressedSize(const void* src, size_t compressedSize);
|
||||
void ZSTDv07_findFrameSizeInfoLegacy(const void *src, size_t srcSize,
|
||||
size_t* cSize, unsigned long long* dBound);
|
||||
|
||||
/*====== Helper functions ======*/
|
||||
ZSTDLIBv07_API unsigned ZSTDv07_isError(size_t code); /*!< tells if a `size_t` function result is an error code */
|
||||
|
975
lib/zstd.h
975
lib/zstd.h
File diff suppressed because it is too large
Load Diff
@ -51,7 +51,7 @@ endif
|
||||
CFLAGS ?= -O3
|
||||
DEBUGFLAGS+=-Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
|
||||
-Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
|
||||
-Wstrict-prototypes -Wundef -Wpointer-arith -Wformat-security \
|
||||
-Wstrict-prototypes -Wundef -Wpointer-arith \
|
||||
-Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
|
||||
-Wredundant-decls -Wmissing-prototypes -Wc++-compat
|
||||
CFLAGS += $(DEBUGFLAGS) $(MOREFLAGS)
|
||||
|
@ -135,7 +135,8 @@ BMK_advancedParams_t BMK_initAdvancedParams(void) {
|
||||
0, /* ldmMinMatch */
|
||||
0, /* ldmHashLog */
|
||||
0, /* ldmBuckSizeLog */
|
||||
0 /* ldmHashRateLog */
|
||||
0, /* ldmHashRateLog */
|
||||
ZSTD_lcm_auto /* literalCompressionMode */
|
||||
};
|
||||
return res;
|
||||
}
|
||||
@ -184,6 +185,7 @@ BMK_initCCtx(ZSTD_CCtx* ctx,
|
||||
CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_searchLog, (int)comprParams->searchLog));
|
||||
CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_minMatch, (int)comprParams->minMatch));
|
||||
CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_targetLength, (int)comprParams->targetLength));
|
||||
CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_literalCompressionMode, (int)adv->literalCompressionMode));
|
||||
CHECK_Z(ZSTD_CCtx_setParameter(ctx, ZSTD_c_strategy, comprParams->strategy));
|
||||
CHECK_Z(ZSTD_CCtx_loadDictionary(ctx, dictBuffer, dictBufferSize));
|
||||
}
|
||||
|
@ -116,6 +116,7 @@ typedef struct {
|
||||
int ldmHashLog;
|
||||
int ldmBucketSizeLog;
|
||||
int ldmHashRateLog;
|
||||
ZSTD_literalCompressionMode_e literalCompressionMode;
|
||||
} BMK_advancedParams_t;
|
||||
|
||||
/* returns default parameters used by nonAdvanced functions */
|
||||
|
@ -24,7 +24,7 @@
|
||||
* Includes
|
||||
***************************************/
|
||||
#include "platform.h" /* Large Files support, SET_BINARY_MODE */
|
||||
#include "util.h" /* UTIL_getFileSize, UTIL_isRegularFile */
|
||||
#include "util.h" /* UTIL_getFileSize, UTIL_isRegularFile, UTIL_isSameFile */
|
||||
#include <stdio.h> /* fprintf, fopen, fread, _fileno, stdin, stdout */
|
||||
#include <stdlib.h> /* malloc, free */
|
||||
#include <string.h> /* strcmp, strlen */
|
||||
@ -296,6 +296,7 @@ struct FIO_prefs_s {
|
||||
int ldmMinMatch;
|
||||
int ldmBucketSizeLog;
|
||||
int ldmHashRateLog;
|
||||
ZSTD_literalCompressionMode_e literalCompressionMode;
|
||||
|
||||
/* IO preferences */
|
||||
U32 removeSrcFile;
|
||||
@ -339,6 +340,7 @@ FIO_prefs_t* FIO_createPreferences(void)
|
||||
ret->ldmMinMatch = 0;
|
||||
ret->ldmBucketSizeLog = FIO_LDM_PARAM_NOTSET;
|
||||
ret->ldmHashRateLog = FIO_LDM_PARAM_NOTSET;
|
||||
ret->literalCompressionMode = ZSTD_lcm_auto;
|
||||
return ret;
|
||||
}
|
||||
|
||||
@ -406,6 +408,12 @@ void FIO_setRsyncable(FIO_prefs_t* const prefs, int rsyncable) {
|
||||
prefs->rsyncable = rsyncable;
|
||||
}
|
||||
|
||||
void FIO_setLiteralCompressionMode(
|
||||
FIO_prefs_t* const prefs,
|
||||
ZSTD_literalCompressionMode_e mode) {
|
||||
prefs->literalCompressionMode = mode;
|
||||
}
|
||||
|
||||
void FIO_setAdaptMin(FIO_prefs_t* const prefs, int minCLevel)
|
||||
{
|
||||
#ifndef ZSTD_NOCOMPRESS
|
||||
@ -507,28 +515,10 @@ static FILE* FIO_openDstFile(FIO_prefs_t* const prefs, const char* srcFileName,
|
||||
return stdout;
|
||||
}
|
||||
|
||||
/* ensure dst is not the same file as src */
|
||||
if (srcFileName != NULL) {
|
||||
#ifdef _MSC_VER
|
||||
/* note : Visual does not support file identification by inode.
|
||||
* The following work-around is limited to detecting exact name repetition only,
|
||||
* aka `filename` is considered different from `subdir/../filename` */
|
||||
if (!strcmp(srcFileName, dstFileName)) {
|
||||
DISPLAYLEVEL(1, "zstd: Refusing to open a output file which will overwrite the input file \n");
|
||||
return NULL;
|
||||
}
|
||||
#else
|
||||
stat_t srcStat;
|
||||
stat_t dstStat;
|
||||
if (UTIL_getFileStat(srcFileName, &srcStat)
|
||||
&& UTIL_getFileStat(dstFileName, &dstStat)) {
|
||||
if (srcStat.st_dev == dstStat.st_dev
|
||||
&& srcStat.st_ino == dstStat.st_ino) {
|
||||
DISPLAYLEVEL(1, "zstd: Refusing to open a output file which will overwrite the input file \n");
|
||||
return NULL;
|
||||
}
|
||||
}
|
||||
#endif
|
||||
/* ensure dst is not the same as src */
|
||||
if (srcFileName != NULL && UTIL_isSameFile(srcFileName, dstFileName)) {
|
||||
DISPLAYLEVEL(1, "zstd: Refusing to open an output file which will overwrite the input file \n");
|
||||
return NULL;
|
||||
}
|
||||
|
||||
if (prefs->sparseFileSupport == 1) {
|
||||
@ -620,6 +610,7 @@ typedef struct {
|
||||
size_t srcBufferSize;
|
||||
void* dstBuffer;
|
||||
size_t dstBufferSize;
|
||||
const char* dictFileName;
|
||||
ZSTD_CStream* cctx;
|
||||
} cRess_t;
|
||||
|
||||
@ -647,6 +638,7 @@ static cRess_t FIO_createCResources(FIO_prefs_t* const prefs,
|
||||
size_t const dictBuffSize = FIO_createDictBuffer(&dictBuffer, dictFileName); /* works with dictFileName==NULL */
|
||||
if (dictFileName && (dictBuffer==NULL))
|
||||
EXM_THROW(32, "allocation error : can't create dictBuffer");
|
||||
ress.dictFileName = dictFileName;
|
||||
|
||||
if (prefs->adaptiveMode && !prefs->ldmFlag && !comprParams.windowLog)
|
||||
comprParams.windowLog = ADAPT_WINDOWLOG_DEFAULT;
|
||||
@ -674,6 +666,7 @@ static cRess_t FIO_createCResources(FIO_prefs_t* const prefs,
|
||||
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_minMatch, (int)comprParams.minMatch) );
|
||||
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_targetLength, (int)comprParams.targetLength) );
|
||||
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_strategy, comprParams.strategy) );
|
||||
CHECK( ZSTD_CCtx_setParameter(ress.cctx, ZSTD_c_literalCompressionMode, (int)prefs->literalCompressionMode) );
|
||||
/* multi-threading */
|
||||
#ifdef ZSTD_MULTITHREAD
|
||||
DISPLAYLEVEL(5,"set nb workers = %u \n", prefs->nbWorkers);
|
||||
@ -1299,12 +1292,18 @@ FIO_compressFilename_srcFile(FIO_prefs_t* const prefs,
|
||||
{
|
||||
int result;
|
||||
|
||||
/* File check */
|
||||
/* ensure src is not a directory */
|
||||
if (UTIL_isDirectory(srcFileName)) {
|
||||
DISPLAYLEVEL(1, "zstd: %s is a directory -- ignored \n", srcFileName);
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* ensure src is not the same as dict (if present) */
|
||||
if (ress.dictFileName != NULL && UTIL_isSameFile(srcFileName, ress.dictFileName)) {
|
||||
DISPLAYLEVEL(1, "zstd: cannot use %s as an input file and dictionary \n", srcFileName);
|
||||
return 1;
|
||||
}
|
||||
|
||||
ress.srcFile = FIO_openSrcFile(srcFileName);
|
||||
if (ress.srcFile == NULL) return 1; /* srcFile could not be opened */
|
||||
|
||||
|
@ -71,6 +71,9 @@ void FIO_setOverlapLog(FIO_prefs_t* const prefs, int overlapLog);
|
||||
void FIO_setRemoveSrcFile(FIO_prefs_t* const prefs, unsigned flag);
|
||||
void FIO_setSparseWrite(FIO_prefs_t* const prefs, unsigned sparse); /**< 0: no sparse; 1: disable on stdout; 2: always enabled */
|
||||
void FIO_setRsyncable(FIO_prefs_t* const prefs, int rsyncable);
|
||||
void FIO_setLiteralCompressionMode(
|
||||
FIO_prefs_t* const prefs,
|
||||
ZSTD_literalCompressionMode_e mode);
|
||||
|
||||
void FIO_setNoProgress(unsigned noProgress);
|
||||
void FIO_setNotificationLevel(int level);
|
||||
|
@ -87,6 +87,23 @@ U32 UTIL_isDirectory(const char* infilename)
|
||||
return 0;
|
||||
}
|
||||
|
||||
int UTIL_isSameFile(const char* file1, const char* file2)
|
||||
{
|
||||
#if defined(_MSC_VER)
|
||||
/* note : Visual does not support file identification by inode.
|
||||
* The following work-around is limited to detecting exact name repetition only,
|
||||
* aka `filename` is considered different from `subdir/../filename` */
|
||||
return !strcmp(file1, file2);
|
||||
#else
|
||||
stat_t file1Stat;
|
||||
stat_t file2Stat;
|
||||
return UTIL_getFileStat(file1, &file1Stat)
|
||||
&& UTIL_getFileStat(file2, &file2Stat)
|
||||
&& (file1Stat.st_dev == file2Stat.st_dev)
|
||||
&& (file1Stat.st_ino == file2Stat.st_ino);
|
||||
#endif
|
||||
}
|
||||
|
||||
U32 UTIL_isLink(const char* infilename)
|
||||
{
|
||||
/* macro guards, as defined in : https://linux.die.net/man/2/lstat */
|
||||
@ -95,7 +112,9 @@ U32 UTIL_isLink(const char* infilename)
|
||||
|| (defined(_XOPEN_SOURCE) && (_XOPEN_SOURCE >= 500)) \
|
||||
|| (defined(_XOPEN_SOURCE) && defined(_XOPEN_SOURCE_EXTENDED)) \
|
||||
|| (defined(_POSIX_C_SOURCE) && (_POSIX_C_SOURCE >= 200112L)) \
|
||||
|| (defined(__APPLE__) && defined(__MACH__))
|
||||
|| (defined(__APPLE__) && defined(__MACH__)) \
|
||||
|| defined(__OpenBSD__) \
|
||||
|| defined(__FreeBSD__)
|
||||
int r;
|
||||
stat_t statbuf;
|
||||
r = lstat(infilename, &statbuf);
|
||||
|
@ -174,6 +174,7 @@ int UTIL_isRegularFile(const char* infilename);
|
||||
int UTIL_setFileStat(const char* filename, stat_t* statbuf);
|
||||
U32 UTIL_isDirectory(const char* infilename);
|
||||
int UTIL_getFileStat(const char* infilename, stat_t* statbuf);
|
||||
int UTIL_isSameFile(const char* file1, const char* file2);
|
||||
|
||||
U32 UTIL_isLink(const char* infilename);
|
||||
#define UTIL_FILESIZE_UNKNOWN ((U64)(-1))
|
||||
|
@ -164,7 +164,7 @@ keep source file(s) after successful compression or decompression\. This is the
|
||||
.
|
||||
.TP
|
||||
\fB\-r\fR
|
||||
operate recursively on dictionaries
|
||||
operate recursively on directories
|
||||
.
|
||||
.TP
|
||||
\fB\-\-format=FORMAT\fR
|
||||
|
@ -178,7 +178,7 @@ the last one takes effect.
|
||||
keep source file(s) after successful compression or decompression.
|
||||
This is the default behavior.
|
||||
* `-r`:
|
||||
operate recursively on dictionaries
|
||||
operate recursively on directories
|
||||
* `--format=FORMAT`:
|
||||
compress and decompress in other formats. If compiled with
|
||||
support, zstd can compress to or decompress from other compression algorithm
|
||||
|
@ -148,6 +148,7 @@ static int usage_advanced(const char* programName)
|
||||
#endif
|
||||
DISPLAY( "--no-dictID : don't write dictID into header (dictionary compression)\n");
|
||||
DISPLAY( "--[no-]check : integrity check (default: enabled) \n");
|
||||
DISPLAY( "--[no-]compress-literals : force (un)compressed literals \n");
|
||||
#endif
|
||||
#ifdef UTIL_HAS_CREATEFILELIST
|
||||
DISPLAY( " -r : operate recursively on directories \n");
|
||||
@ -569,6 +570,7 @@ int main(int argCount, const char* argv[])
|
||||
#ifndef ZSTD_NOBENCH
|
||||
BMK_advancedParams_t benchParams = BMK_initAdvancedParams();
|
||||
#endif
|
||||
ZSTD_literalCompressionMode_e literalCompressionMode = ZSTD_lcm_auto;
|
||||
|
||||
|
||||
/* init */
|
||||
@ -661,6 +663,8 @@ int main(int argCount, const char* argv[])
|
||||
if (!strcmp(argument, "--format=lz4")) { suffix = LZ4_EXTENSION; FIO_setCompressionType(prefs, FIO_lz4Compression); continue; }
|
||||
#endif
|
||||
if (!strcmp(argument, "--rsyncable")) { rsyncable = 1; continue; }
|
||||
if (!strcmp(argument, "--compress-literals")) { literalCompressionMode = ZSTD_lcm_huffman; continue; }
|
||||
if (!strcmp(argument, "--no-compress-literals")) { literalCompressionMode = ZSTD_lcm_uncompressed; continue; }
|
||||
if (!strcmp(argument, "--no-progress")) { FIO_setNoProgress(1); continue; }
|
||||
|
||||
/* long commands with arguments */
|
||||
@ -953,6 +957,8 @@ int main(int argCount, const char* argv[])
|
||||
filenameTable[fileNamesNb++] = filenameTable[u];
|
||||
}
|
||||
}
|
||||
if (fileNamesNb == 0 && filenameIdx > 0)
|
||||
CLEAN_RETURN(1);
|
||||
filenameIdx = fileNamesNb;
|
||||
}
|
||||
if (recursive) { /* at this stage, filenameTable is a list of paths, which can contain both files and directories */
|
||||
@ -995,6 +1001,7 @@ int main(int argCount, const char* argv[])
|
||||
if (g_ldmHashRateLog != LDM_PARAM_DEFAULT) {
|
||||
benchParams.ldmHashRateLog = g_ldmHashRateLog;
|
||||
}
|
||||
benchParams.literalCompressionMode = literalCompressionMode;
|
||||
|
||||
if (cLevel > ZSTD_maxCLevel()) cLevel = ZSTD_maxCLevel();
|
||||
if (cLevelLast > ZSTD_maxCLevel()) cLevelLast = ZSTD_maxCLevel();
|
||||
@ -1108,6 +1115,7 @@ int main(int argCount, const char* argv[])
|
||||
FIO_setAdaptMin(prefs, adaptMin);
|
||||
FIO_setAdaptMax(prefs, adaptMax);
|
||||
FIO_setRsyncable(prefs, rsyncable);
|
||||
FIO_setLiteralCompressionMode(prefs, literalCompressionMode);
|
||||
if (adaptMin > cLevel) cLevel = adaptMin;
|
||||
if (adaptMax < cLevel) cLevel = adaptMax;
|
||||
|
||||
@ -1116,7 +1124,7 @@ int main(int argCount, const char* argv[])
|
||||
else
|
||||
operationResult = FIO_compressMultipleFilenames(prefs, filenameTable, filenameIdx, outFileName, suffix, dictFileName, cLevel, compressionParams);
|
||||
#else
|
||||
(void)suffix; (void)adapt; (void)rsyncable; (void)ultra; (void)cLevel; (void)ldmFlag; /* not used when ZSTD_NOCOMPRESS set */
|
||||
(void)suffix; (void)adapt; (void)rsyncable; (void)ultra; (void)cLevel; (void)ldmFlag; (void)literalCompressionMode; /* not used when ZSTD_NOCOMPRESS set */
|
||||
DISPLAY("Compression not supported \n");
|
||||
#endif
|
||||
} else { /* decompression or test */
|
||||
|
@ -33,7 +33,7 @@ endif
|
||||
CFLAGS ?= -O3
|
||||
CFLAGS += -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
|
||||
-Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
|
||||
-Wstrict-prototypes -Wundef -Wformat-security \
|
||||
-Wstrict-prototypes -Wundef \
|
||||
-Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
|
||||
-Wredundant-decls -Wmissing-prototypes
|
||||
CFLAGS += $(DEBUGFLAGS) $(MOREFLAGS)
|
||||
|
@ -938,7 +938,9 @@ static size_t writeSequences(U32* seed, frame_t* frame, seqStore_t* seqStorePtr,
|
||||
FSE_CState_t stateOffsetBits;
|
||||
FSE_CState_t stateLitLength;
|
||||
|
||||
CHECK_E(BIT_initCStream(&blockStream, op, oend-op), dstSize_tooSmall); /* not enough space remaining */
|
||||
RETURN_ERROR_IF(
|
||||
ERR_isError(BIT_initCStream(&blockStream, op, oend-op)),
|
||||
dstSize_tooSmall, "not enough space remaining");
|
||||
|
||||
/* first symbols */
|
||||
FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]);
|
||||
|
@ -27,16 +27,16 @@ PRGDIR = ../../programs
|
||||
|
||||
FUZZ_CPPFLAGS := -I$(ZSTDDIR) -I$(ZSTDDIR)/common -I$(ZSTDDIR)/compress \
|
||||
-I$(ZSTDDIR)/dictBuilder -I$(ZSTDDIR)/deprecated -I$(PRGDIR) \
|
||||
$(CPPFLAGS)
|
||||
-DZSTD_MULTITHREAD $(CPPFLAGS)
|
||||
FUZZ_EXTRA_FLAGS := -Wall -Wextra -Wcast-qual -Wcast-align -Wshadow \
|
||||
-Wstrict-aliasing=1 -Wswitch-enum -Wdeclaration-after-statement \
|
||||
-Wstrict-prototypes -Wundef -Wformat-security \
|
||||
-Wstrict-prototypes -Wundef \
|
||||
-Wvla -Wformat=2 -Winit-self -Wfloat-equal -Wwrite-strings \
|
||||
-Wredundant-decls \
|
||||
-g -fno-omit-frame-pointer
|
||||
FUZZ_CFLAGS := $(FUZZ_EXTRA_FLAGS) $(CFLAGS)
|
||||
FUZZ_CXXFLAGS := $(FUZZ_EXTRA_FLAGS) -std=c++11 $(CXXFLAGS)
|
||||
FUZZ_LDFLAGS := $(LDFLAGS)
|
||||
FUZZ_LDFLAGS := -pthread $(LDFLAGS)
|
||||
FUZZ_ARFLAGS := $(ARFLAGS)
|
||||
FUZZ_TARGET_FLAGS = $(FUZZ_CPPFLAGS) $(FUZZ_CXXFLAGS) $(FUZZ_LDFLAGS)
|
||||
|
||||
@ -46,11 +46,13 @@ FUZZ_SRC := $(PRGDIR)/util.c zstd_helpers.c
|
||||
ZSTDCOMMON_SRC := $(ZSTDDIR)/common/*.c
|
||||
ZSTDCOMP_SRC := $(ZSTDDIR)/compress/*.c
|
||||
ZSTDDECOMP_SRC := $(ZSTDDIR)/decompress/*.c
|
||||
ZSTDDICT_SRC := $(ZSTDDIR)/dictBuilder/*.c
|
||||
FUZZ_SRC := \
|
||||
$(FUZZ_SRC) \
|
||||
$(ZSTDDECOMP_SRC) \
|
||||
$(ZSTDCOMMON_SRC) \
|
||||
$(ZSTDCOMP_SRC)
|
||||
$(ZSTDCOMP_SRC) \
|
||||
$(ZSTDDICT_SRC)
|
||||
|
||||
FUZZ_OBJ := $(patsubst %.c,%.o, $(wildcard $(FUZZ_SRC)))
|
||||
|
||||
@ -65,7 +67,9 @@ FUZZ_TARGETS := \
|
||||
block_round_trip \
|
||||
simple_decompress \
|
||||
stream_decompress \
|
||||
block_decompress
|
||||
block_decompress \
|
||||
dictionary_round_trip \
|
||||
dictionary_decompress
|
||||
|
||||
all: $(FUZZ_TARGETS)
|
||||
|
||||
@ -90,6 +94,12 @@ stream_decompress: $(FUZZ_HEADERS) $(FUZZ_OBJ) stream_decompress.o
|
||||
block_decompress: $(FUZZ_HEADERS) $(FUZZ_OBJ) block_decompress.o
|
||||
$(CXX) $(FUZZ_TARGET_FLAGS) $(FUZZ_OBJ) block_decompress.o $(LIB_FUZZING_ENGINE) -o $@
|
||||
|
||||
dictionary_round_trip: $(FUZZ_HEADERS) $(FUZZ_OBJ) dictionary_round_trip.o
|
||||
$(CXX) $(FUZZ_TARGET_FLAGS) $(FUZZ_OBJ) dictionary_round_trip.o $(LIB_FUZZING_ENGINE) -o $@
|
||||
|
||||
dictionary_decompress: $(FUZZ_HEADERS) $(FUZZ_OBJ) dictionary_decompress.o
|
||||
$(CXX) $(FUZZ_TARGET_FLAGS) $(FUZZ_OBJ) dictionary_decompress.o $(LIB_FUZZING_ENGINE) -o $@
|
||||
|
||||
libregression.a: $(FUZZ_HEADERS) $(PRGDIR)/util.h $(PRGDIR)/util.c regression_driver.o
|
||||
$(AR) $(FUZZ_ARFLAGS) $@ regression_driver.o
|
||||
|
||||
|
64
tests/fuzz/dictionary_decompress.c
Normal file
64
tests/fuzz/dictionary_decompress.c
Normal file
@ -0,0 +1,64 @@
|
||||
/*
|
||||
* Copyright (c) 2016-present, Facebook, Inc.
|
||||
* All rights reserved.
|
||||
*
|
||||
* This source code is licensed under both the BSD-style license (found in the
|
||||
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
|
||||
* in the COPYING file in the root directory of this source tree).
|
||||
*/
|
||||
|
||||
/**
|
||||
* This fuzz target attempts to decompress the fuzzed data with the dictionary
|
||||
* decompression function to ensure the decompressor never crashes. It does not
|
||||
* fuzz the dictionary.
|
||||
*/
|
||||
|
||||
#include <stddef.h>
|
||||
#include <stdlib.h>
|
||||
#include <stdio.h>
|
||||
#include "fuzz_helpers.h"
|
||||
#include "zstd_helpers.h"
|
||||
|
||||
static ZSTD_DCtx *dctx = NULL;
|
||||
static void* rBuf = NULL;
|
||||
static size_t bufSize = 0;
|
||||
|
||||
int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
|
||||
{
|
||||
FUZZ_dict_t dict;
|
||||
size_t neededBufSize;
|
||||
|
||||
uint32_t seed = FUZZ_seed(&src, &size);
|
||||
neededBufSize = MAX(20 * size, (size_t)256 << 10);
|
||||
|
||||
/* Allocate all buffers and contexts if not already allocated */
|
||||
if (neededBufSize > bufSize) {
|
||||
free(rBuf);
|
||||
rBuf = malloc(neededBufSize);
|
||||
bufSize = neededBufSize;
|
||||
FUZZ_ASSERT(rBuf);
|
||||
}
|
||||
if (!dctx) {
|
||||
dctx = ZSTD_createDCtx();
|
||||
FUZZ_ASSERT(dctx);
|
||||
}
|
||||
dict = FUZZ_train(src, size, &seed);
|
||||
if (FUZZ_rand32(&seed, 0, 1) == 0) {
|
||||
ZSTD_decompress_usingDict(dctx,
|
||||
rBuf, neededBufSize,
|
||||
src, size,
|
||||
dict.buff, dict.size);
|
||||
} else {
|
||||
FUZZ_ZASSERT(ZSTD_DCtx_loadDictionary_advanced(
|
||||
dctx, dict.buff, dict.size,
|
||||
(ZSTD_dictLoadMethod_e)FUZZ_rand32(&seed, 0, 1),
|
||||
(ZSTD_dictContentType_e)FUZZ_rand32(&seed, 0, 2)));
|
||||
ZSTD_decompressDCtx(dctx, rBuf, neededBufSize, src, size);
|
||||
}
|
||||
|
||||
free(dict.buff);
|
||||
#ifndef STATEFUL_FUZZING
|
||||
ZSTD_freeDCtx(dctx); dctx = NULL;
|
||||
#endif
|
||||
return 0;
|
||||
}
|
106
tests/fuzz/dictionary_round_trip.c
Normal file
106
tests/fuzz/dictionary_round_trip.c
Normal file
@ -0,0 +1,106 @@
|
||||
/*
|
||||
* Copyright (c) 2016-present, Facebook, Inc.
|
||||
* All rights reserved.
|
||||
*
|
||||
* This source code is licensed under both the BSD-style license (found in the
|
||||
* LICENSE file in the root directory of this source tree) and the GPLv2 (found
|
||||
* in the COPYING file in the root directory of this source tree).
|
||||
*/
|
||||
|
||||
/**
|
||||
* This fuzz target performs a zstd round-trip test (compress & decompress) with
|
||||
* a dictionary, compares the result with the original, and calls abort() on
|
||||
* corruption.
|
||||
*/
|
||||
|
||||
#include <stddef.h>
|
||||
#include <stdlib.h>
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include "fuzz_helpers.h"
|
||||
#include "zstd_helpers.h"
|
||||
|
||||
static const int kMaxClevel = 19;
|
||||
|
||||
static ZSTD_CCtx *cctx = NULL;
|
||||
static ZSTD_DCtx *dctx = NULL;
|
||||
static uint32_t seed;
|
||||
|
||||
static size_t roundTripTest(void *result, size_t resultCapacity,
|
||||
void *compressed, size_t compressedCapacity,
|
||||
const void *src, size_t srcSize)
|
||||
{
|
||||
ZSTD_dictContentType_e dictContentType = ZSTD_dct_auto;
|
||||
FUZZ_dict_t dict = FUZZ_train(src, srcSize, &seed);
|
||||
size_t cSize;
|
||||
if ((FUZZ_rand(&seed) & 15) == 0) {
|
||||
int const cLevel = FUZZ_rand(&seed) % kMaxClevel;
|
||||
|
||||
cSize = ZSTD_compress_usingDict(cctx,
|
||||
compressed, compressedCapacity,
|
||||
src, srcSize,
|
||||
dict.buff, dict.size,
|
||||
cLevel);
|
||||
} else {
|
||||
dictContentType = FUZZ_rand32(&seed, 0, 2);
|
||||
FUZZ_setRandomParameters(cctx, srcSize, &seed);
|
||||
/* Disable checksum so we can use sizes smaller than compress bound. */
|
||||
FUZZ_ZASSERT(ZSTD_CCtx_setParameter(cctx, ZSTD_c_checksumFlag, 0));
|
||||
FUZZ_ZASSERT(ZSTD_CCtx_loadDictionary_advanced(
|
||||
cctx, dict.buff, dict.size,
|
||||
(ZSTD_dictLoadMethod_e)FUZZ_rand32(&seed, 0, 1),
|
||||
dictContentType));
|
||||
cSize = ZSTD_compress2(cctx, compressed, compressedCapacity, src, srcSize);
|
||||
}
|
||||
FUZZ_ZASSERT(cSize);
|
||||
FUZZ_ZASSERT(ZSTD_DCtx_loadDictionary_advanced(
|
||||
dctx, dict.buff, dict.size,
|
||||
(ZSTD_dictLoadMethod_e)FUZZ_rand32(&seed, 0, 1),
|
||||
dictContentType));
|
||||
{
|
||||
size_t const ret = ZSTD_decompressDCtx(
|
||||
dctx, result, resultCapacity, compressed, cSize);
|
||||
free(dict.buff);
|
||||
return ret;
|
||||
}
|
||||
}
|
||||
|
||||
int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
|
||||
{
|
||||
size_t const rBufSize = size;
|
||||
void* rBuf = malloc(rBufSize);
|
||||
size_t cBufSize = ZSTD_compressBound(size);
|
||||
void* cBuf;
|
||||
|
||||
seed = FUZZ_seed(&src, &size);
|
||||
/* Half of the time fuzz with a 1 byte smaller output size.
|
||||
* This will still succeed because we force the checksum to be disabled,
|
||||
* giving us 4 bytes of overhead.
|
||||
*/
|
||||
cBufSize -= FUZZ_rand32(&seed, 0, 1);
|
||||
cBuf = malloc(cBufSize);
|
||||
|
||||
if (!cctx) {
|
||||
cctx = ZSTD_createCCtx();
|
||||
FUZZ_ASSERT(cctx);
|
||||
}
|
||||
if (!dctx) {
|
||||
dctx = ZSTD_createDCtx();
|
||||
FUZZ_ASSERT(dctx);
|
||||
}
|
||||
|
||||
{
|
||||
size_t const result =
|
||||
roundTripTest(rBuf, rBufSize, cBuf, cBufSize, src, size);
|
||||
FUZZ_ZASSERT(result);
|
||||
FUZZ_ASSERT_MSG(result == size, "Incorrect regenerated size");
|
||||
FUZZ_ASSERT_MSG(!memcmp(src, rBuf, size), "Corruption!");
|
||||
}
|
||||
free(rBuf);
|
||||
free(cBuf);
|
||||
#ifndef STATEFUL_FUZZING
|
||||
ZSTD_freeCCtx(cctx); cctx = NULL;
|
||||
ZSTD_freeDCtx(dctx); dctx = NULL;
|
||||
#endif
|
||||
return 0;
|
||||
}
|
@ -34,6 +34,8 @@ TARGETS = [
|
||||
'simple_decompress',
|
||||
'stream_decompress',
|
||||
'block_decompress',
|
||||
'dictionary_round_trip',
|
||||
'dictionary_decompress',
|
||||
]
|
||||
ALL_TARGETS = TARGETS + ['all']
|
||||
FUZZ_RNG_SEED_SIZE = 4
|
||||
@ -192,11 +194,21 @@ def build_parser(args):
|
||||
default=LIB_FUZZING_ENGINE,
|
||||
help=('The fuzzing engine to use e.g. /path/to/libFuzzer.a '
|
||||
"(default: $LIB_FUZZING_ENGINE='{})".format(LIB_FUZZING_ENGINE)))
|
||||
parser.add_argument(
|
||||
|
||||
fuzz_group = parser.add_mutually_exclusive_group()
|
||||
fuzz_group.add_argument(
|
||||
'--enable-coverage',
|
||||
dest='coverage',
|
||||
action='store_true',
|
||||
help='Enable coverage instrumentation (-fsanitize-coverage)')
|
||||
fuzz_group.add_argument(
|
||||
'--enable-fuzzer',
|
||||
dest='fuzzer',
|
||||
action='store_true',
|
||||
help=('Enable clang fuzzer (-fsanitize=fuzzer). When enabled '
|
||||
'LIB_FUZZING_ENGINE is ignored')
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'--enable-asan', dest='asan', action='store_true', help='Enable UBSAN')
|
||||
parser.add_argument(
|
||||
@ -364,13 +376,17 @@ def build(args):
|
||||
'-DFUZZ_RNG_SEED_SIZE={}'.format(args.fuzz_rng_seed_size),
|
||||
]
|
||||
|
||||
mflags += ['LIB_FUZZING_ENGINE={}'.format(args.lib_fuzzing_engine)]
|
||||
|
||||
# Set flags for options
|
||||
assert not (args.fuzzer and args.coverage)
|
||||
if args.coverage:
|
||||
common_flags += [
|
||||
'-fsanitize-coverage=trace-pc-guard,indirect-calls,trace-cmp'
|
||||
]
|
||||
if args.fuzzer:
|
||||
common_flags += ['-fsanitize=fuzzer']
|
||||
args.lib_fuzzing_engine = ''
|
||||
|
||||
mflags += ['LIB_FUZZING_ENGINE={}'.format(args.lib_fuzzing_engine)]
|
||||
|
||||
if args.sanitize_recover:
|
||||
recover_flags = ['-fsanitize-recover=all']
|
||||
|
@ -40,8 +40,13 @@ int main(int argc, char const **argv) {
|
||||
size_t readSize;
|
||||
FILE *file;
|
||||
|
||||
/* Check that it is a regular file, and that the fileSize is valid */
|
||||
FUZZ_ASSERT_MSG(UTIL_isRegularFile(fileName), fileName);
|
||||
/* Check that it is a regular file, and that the fileSize is valid.
|
||||
* If it is not a regular file, then it may have been deleted since we
|
||||
* constructed the list, so just skip it.
|
||||
*/
|
||||
if (!UTIL_isRegularFile(fileName)) {
|
||||
continue;
|
||||
}
|
||||
FUZZ_ASSERT_MSG(fileSize <= kMaxFileSize, fileName);
|
||||
/* Ensure we have a large enough buffer allocated */
|
||||
if (fileSize > bufferSize) {
|
||||
|
@ -25,9 +25,6 @@ static const int kMaxClevel = 19;
|
||||
|
||||
static ZSTD_CCtx *cctx = NULL;
|
||||
static ZSTD_DCtx *dctx = NULL;
|
||||
static void* cBuf = NULL;
|
||||
static void* rBuf = NULL;
|
||||
static size_t bufSize = 0;
|
||||
static uint32_t seed;
|
||||
|
||||
static size_t roundTripTest(void *result, size_t resultCapacity,
|
||||
@ -36,16 +33,8 @@ static size_t roundTripTest(void *result, size_t resultCapacity,
|
||||
{
|
||||
size_t cSize;
|
||||
if (FUZZ_rand(&seed) & 1) {
|
||||
ZSTD_inBuffer in = {src, srcSize, 0};
|
||||
ZSTD_outBuffer out = {compressed, compressedCapacity, 0};
|
||||
size_t err;
|
||||
|
||||
ZSTD_CCtx_reset(cctx, ZSTD_reset_session_only);
|
||||
FUZZ_setRandomParameters(cctx, srcSize, &seed);
|
||||
err = ZSTD_compressStream2(cctx, &out, &in, ZSTD_e_end);
|
||||
FUZZ_ZASSERT(err);
|
||||
FUZZ_ASSERT(err == 0);
|
||||
cSize = out.pos;
|
||||
cSize = ZSTD_compress2(cctx, compressed, compressedCapacity, src, srcSize);
|
||||
} else {
|
||||
int const cLevel = FUZZ_rand(&seed) % kMaxClevel;
|
||||
cSize = ZSTD_compressCCtx(
|
||||
@ -57,20 +46,21 @@ static size_t roundTripTest(void *result, size_t resultCapacity,
|
||||
|
||||
int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
|
||||
{
|
||||
size_t neededBufSize;
|
||||
size_t const rBufSize = size;
|
||||
void* rBuf = malloc(rBufSize);
|
||||
size_t cBufSize = ZSTD_compressBound(size);
|
||||
void* cBuf;
|
||||
|
||||
seed = FUZZ_seed(&src, &size);
|
||||
neededBufSize = ZSTD_compressBound(size);
|
||||
/* Half of the time fuzz with a 1 byte smaller output size.
|
||||
* This will still succeed because we don't use a dictionary, so the dictID
|
||||
* field is empty, giving us 4 bytes of overhead.
|
||||
*/
|
||||
cBufSize -= FUZZ_rand32(&seed, 0, 1);
|
||||
cBuf = malloc(cBufSize);
|
||||
|
||||
FUZZ_ASSERT(cBuf && rBuf);
|
||||
|
||||
/* Allocate all buffers and contexts if not already allocated */
|
||||
if (neededBufSize > bufSize) {
|
||||
free(cBuf);
|
||||
free(rBuf);
|
||||
cBuf = malloc(neededBufSize);
|
||||
rBuf = malloc(neededBufSize);
|
||||
bufSize = neededBufSize;
|
||||
FUZZ_ASSERT(cBuf && rBuf);
|
||||
}
|
||||
if (!cctx) {
|
||||
cctx = ZSTD_createCCtx();
|
||||
FUZZ_ASSERT(cctx);
|
||||
@ -82,11 +72,13 @@ int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
|
||||
|
||||
{
|
||||
size_t const result =
|
||||
roundTripTest(rBuf, neededBufSize, cBuf, neededBufSize, src, size);
|
||||
roundTripTest(rBuf, rBufSize, cBuf, cBufSize, src, size);
|
||||
FUZZ_ZASSERT(result);
|
||||
FUZZ_ASSERT_MSG(result == size, "Incorrect regenerated size");
|
||||
FUZZ_ASSERT_MSG(!memcmp(src, rBuf, size), "Corruption!");
|
||||
}
|
||||
free(rBuf);
|
||||
free(cBuf);
|
||||
#ifndef STATEFUL_FUZZING
|
||||
ZSTD_freeCCtx(cctx); cctx = NULL;
|
||||
ZSTD_freeDCtx(dctx); dctx = NULL;
|
||||
|
@ -62,9 +62,8 @@ int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
|
||||
if (!dstream) {
|
||||
dstream = ZSTD_createDStream();
|
||||
FUZZ_ASSERT(dstream);
|
||||
FUZZ_ASSERT(!ZSTD_isError(ZSTD_initDStream(dstream)));
|
||||
} else {
|
||||
FUZZ_ASSERT(!ZSTD_isError(ZSTD_resetDStream(dstream)));
|
||||
FUZZ_ZASSERT(ZSTD_DCtx_reset(dstream, ZSTD_reset_session_only));
|
||||
}
|
||||
|
||||
while (size > 0) {
|
||||
@ -73,7 +72,6 @@ int LLVMFuzzerTestOneInput(const uint8_t *src, size_t size)
|
||||
ZSTD_outBuffer out = makeOutBuffer();
|
||||
size_t const rc = ZSTD_decompressStream(dstream, &out, &in);
|
||||
if (ZSTD_isError(rc)) goto error;
|
||||
if (rc == 0) FUZZ_ASSERT(!ZSTD_isError(ZSTD_resetDStream(dstream)));
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -63,7 +63,7 @@ static size_t compress(uint8_t *dst, size_t capacity,
|
||||
ZSTD_inBuffer in = makeInBuffer(&src, &srcSize);
|
||||
/* Mode controls the action. If mode == -1 we pick a new mode */
|
||||
int mode = -1;
|
||||
while (in.pos < in.size) {
|
||||
while (in.pos < in.size || mode != -1) {
|
||||
ZSTD_outBuffer out = makeOutBuffer(dst, capacity);
|
||||
/* Previous action finished, pick a new mode. */
|
||||
if (mode == -1) mode = FUZZ_rand(&seed) % 10;
|
||||
|
@ -8,10 +8,14 @@
|
||||
*/
|
||||
|
||||
#define ZSTD_STATIC_LINKING_ONLY
|
||||
#define ZDICT_STATIC_LINKING_ONLY
|
||||
|
||||
#include <string.h>
|
||||
|
||||
#include "zstd_helpers.h"
|
||||
#include "fuzz_helpers.h"
|
||||
#include "zstd.h"
|
||||
#include "zdict.h"
|
||||
|
||||
static void set(ZSTD_CCtx *cctx, ZSTD_cParameter param, int value)
|
||||
{
|
||||
@ -71,7 +75,6 @@ void FUZZ_setRandomParameters(ZSTD_CCtx *cctx, size_t srcSize, uint32_t *state)
|
||||
setRand(cctx, ZSTD_c_contentSizeFlag, 0, 1, state);
|
||||
setRand(cctx, ZSTD_c_checksumFlag, 0, 1, state);
|
||||
setRand(cctx, ZSTD_c_dictIDFlag, 0, 1, state);
|
||||
setRand(cctx, ZSTD_c_forceAttachDict, 0, 2, state);
|
||||
/* Select long distance matchig parameters */
|
||||
setRand(cctx, ZSTD_c_enableLongDistanceMatching, 0, 1, state);
|
||||
setRand(cctx, ZSTD_c_ldmHashLog, ZSTD_HASHLOG_MIN, 16, state);
|
||||
@ -81,4 +84,54 @@ void FUZZ_setRandomParameters(ZSTD_CCtx *cctx, size_t srcSize, uint32_t *state)
|
||||
state);
|
||||
setRand(cctx, ZSTD_c_ldmHashRateLog, ZSTD_LDM_HASHRATELOG_MIN,
|
||||
ZSTD_LDM_HASHRATELOG_MAX, state);
|
||||
/* Set misc parameters */
|
||||
setRand(cctx, ZSTD_c_nbWorkers, 0, 2, state);
|
||||
setRand(cctx, ZSTD_c_rsyncable, 0, 1, state);
|
||||
setRand(cctx, ZSTD_c_forceMaxWindow, 0, 1, state);
|
||||
setRand(cctx, ZSTD_c_literalCompressionMode, 0, 2, state);
|
||||
setRand(cctx, ZSTD_c_forceAttachDict, 0, 2, state);
|
||||
}
|
||||
|
||||
FUZZ_dict_t FUZZ_train(void const* src, size_t srcSize, uint32_t *state)
|
||||
{
|
||||
size_t const dictSize = MAX(srcSize / 8, 1024);
|
||||
size_t const totalSampleSize = dictSize * 11;
|
||||
FUZZ_dict_t dict = { malloc(dictSize), dictSize };
|
||||
char* const samples = (char*)malloc(totalSampleSize);
|
||||
unsigned nbSamples = 100;
|
||||
size_t* const samplesSizes = (size_t*)malloc(sizeof(size_t) * nbSamples);
|
||||
size_t pos = 0;
|
||||
size_t sample = 0;
|
||||
ZDICT_fastCover_params_t params;
|
||||
FUZZ_ASSERT(dict.buff && samples && samplesSizes);
|
||||
|
||||
for (sample = 0; sample < nbSamples; ++sample) {
|
||||
size_t const remaining = totalSampleSize - pos;
|
||||
size_t const offset = FUZZ_rand32(state, 0, MAX(srcSize, 1) - 1);
|
||||
size_t const limit = MIN(srcSize - offset, remaining);
|
||||
size_t const toCopy = MIN(limit, remaining / (nbSamples - sample));
|
||||
memcpy(samples + pos, src + offset, toCopy);
|
||||
pos += toCopy;
|
||||
samplesSizes[sample] = toCopy;
|
||||
|
||||
}
|
||||
memset(samples + pos, 0, totalSampleSize - pos);
|
||||
|
||||
memset(¶ms, 0, sizeof(params));
|
||||
params.accel = 5;
|
||||
params.k = 40;
|
||||
params.d = 8;
|
||||
params.f = 14;
|
||||
params.zParams.compressionLevel = 1;
|
||||
dict.size = ZDICT_trainFromBuffer_fastCover(dict.buff, dictSize,
|
||||
samples, samplesSizes, nbSamples, params);
|
||||
if (ZSTD_isError(dict.size)) {
|
||||
free(dict.buff);
|
||||
memset(&dict, 0, sizeof(dict));
|
||||
}
|
||||
|
||||
free(samplesSizes);
|
||||
free(samples);
|
||||
|
||||
return dict;
|
||||
}
|
||||
|
@ -14,6 +14,8 @@
|
||||
#ifndef ZSTD_HELPERS_H
|
||||
#define ZSTD_HELPERS_H
|
||||
|
||||
#define ZSTD_STATIC_LINKING_ONLY
|
||||
|
||||
#include "zstd.h"
|
||||
#include <stdint.h>
|
||||
|
||||
@ -27,6 +29,17 @@ ZSTD_compressionParameters FUZZ_randomCParams(size_t srcSize, uint32_t *state);
|
||||
ZSTD_frameParameters FUZZ_randomFParams(uint32_t *state);
|
||||
ZSTD_parameters FUZZ_randomParams(size_t srcSize, uint32_t *state);
|
||||
|
||||
typedef struct {
|
||||
void* buff;
|
||||
size_t size;
|
||||
} FUZZ_dict_t;
|
||||
|
||||
/* Quickly train a dictionary from a source for fuzzing.
|
||||
* NOTE: Don't use this to train production dictionaries, it is only optimized
|
||||
* for speed, and doesn't care about dictionary quality.
|
||||
*/
|
||||
FUZZ_dict_t FUZZ_train(void const* src, size_t srcSize, uint32_t *state);
|
||||
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
|
253
tests/fuzzer.c
253
tests/fuzzer.c
@ -124,12 +124,14 @@ static U32 FUZ_highbit32(U32 v32)
|
||||
#define CHECK(fn) { CHECK_V(err, fn); }
|
||||
#define CHECKPLUS(var, fn, more) { CHECK_V(var, fn); more; }
|
||||
|
||||
#define CHECK_EQ(lhs, rhs) { \
|
||||
if ((lhs) != (rhs)) { \
|
||||
DISPLAY("Error L%u => %s != %s ", __LINE__, #lhs, #rhs); \
|
||||
#define CHECK_OP(op, lhs, rhs) { \
|
||||
if (!((lhs) op (rhs))) { \
|
||||
DISPLAY("Error L%u => FAILED %s %s %s ", __LINE__, #lhs, #op, #rhs); \
|
||||
goto _output_error; \
|
||||
} \
|
||||
}
|
||||
#define CHECK_EQ(lhs, rhs) CHECK_OP(==, lhs, rhs)
|
||||
#define CHECK_LT(lhs, rhs) CHECK_OP(<, lhs, rhs)
|
||||
|
||||
|
||||
/*=============================================
|
||||
@ -374,6 +376,20 @@ static int basicUnitTests(U32 seed, double compressibility)
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : tight ZSTD_decompressBound test : ", testNb++);
|
||||
{
|
||||
unsigned long long bound = ZSTD_decompressBound(compressedBuffer, cSize);
|
||||
if (bound != CNBuffSize) goto _output_error;
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : ZSTD_decompressBound test with invalid srcSize : ", testNb++);
|
||||
{
|
||||
unsigned long long bound = ZSTD_decompressBound(compressedBuffer, cSize - 1);
|
||||
if (bound != ZSTD_CONTENTSIZE_ERROR) goto _output_error;
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : decompress %u bytes : ", testNb++, (unsigned)CNBuffSize);
|
||||
{ size_t const r = ZSTD_decompress(decodedBuffer, CNBuffSize, compressedBuffer, cSize);
|
||||
if (r != CNBuffSize) goto _output_error; }
|
||||
@ -429,6 +445,27 @@ static int basicUnitTests(U32 seed, double compressibility)
|
||||
if (ZSTD_getErrorCode(r) != ZSTD_error_srcSize_wrong) goto _output_error; }
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : ZSTD_decompressBound test with content size missing : ", testNb++);
|
||||
{ /* create compressed buffer with content size missing */
|
||||
ZSTD_CCtx* cctx = ZSTD_createCCtx();
|
||||
CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_contentSizeFlag, 0) );
|
||||
CHECKPLUS(r, ZSTD_compress2(cctx,
|
||||
compressedBuffer, compressedBufferSize,
|
||||
CNBuffer, CNBuffSize),
|
||||
cSize=r );
|
||||
ZSTD_freeCCtx(cctx);
|
||||
}
|
||||
{ /* ensure frame content size is missing */
|
||||
ZSTD_frameHeader zfh;
|
||||
size_t const ret = ZSTD_getFrameHeader(&zfh, compressedBuffer, compressedBufferSize);
|
||||
if (ret != 0 || zfh.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) goto _output_error;
|
||||
}
|
||||
{ /* ensure CNBuffSize <= decompressBound */
|
||||
unsigned long long const bound = ZSTD_decompressBound(compressedBuffer, compressedBufferSize);
|
||||
if (CNBuffSize > bound) goto _output_error;
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3d : check CCtx size after compressing empty input : ", testNb++);
|
||||
{ ZSTD_CCtx* const cctx = ZSTD_createCCtx();
|
||||
size_t const r = ZSTD_compressCCtx(cctx, compressedBuffer, compressedBufferSize, NULL, 0, 19);
|
||||
@ -828,6 +865,59 @@ static int basicUnitTests(U32 seed, double compressibility)
|
||||
ZSTDMT_freeCCtx(mtctx);
|
||||
}
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : compress -T2 with/without literals compression : ", testNb++)
|
||||
{ ZSTD_CCtx* cctx = ZSTD_createCCtx();
|
||||
size_t cSize1, cSize2;
|
||||
CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 1) );
|
||||
CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_nbWorkers, 2) );
|
||||
cSize1 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, CNBuffSize);
|
||||
CHECK(cSize1);
|
||||
CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_literalCompressionMode, ZSTD_lcm_uncompressed) );
|
||||
cSize2 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, CNBuffSize);
|
||||
CHECK(cSize2);
|
||||
CHECK_LT(cSize1, cSize2);
|
||||
ZSTD_freeCCtx(cctx);
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : Multithreaded ZSTD_compress2() with rsyncable : ", testNb++)
|
||||
{ ZSTD_CCtx* cctx = ZSTD_createCCtx();
|
||||
/* Set rsyncable and don't give the ZSTD_compressBound(CNBuffSize) so
|
||||
* ZSTDMT is forced to not take the shortcut.
|
||||
*/
|
||||
CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 1) );
|
||||
CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_nbWorkers, 1) );
|
||||
CHECK( ZSTD_CCtx_setParameter(cctx, ZSTD_c_rsyncable, 1) );
|
||||
CHECK( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize - 1, CNBuffer, CNBuffSize) );
|
||||
ZSTD_freeCCtx(cctx);
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : setting multithreaded parameters : ", testNb++)
|
||||
{ ZSTD_CCtx_params* params = ZSTD_createCCtxParams();
|
||||
int value;
|
||||
/* Check that the overlap log and job size are unset. */
|
||||
CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_overlapLog, &value) );
|
||||
CHECK_EQ(value, 0);
|
||||
CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_jobSize, &value) );
|
||||
CHECK_EQ(value, 0);
|
||||
/* Set and check the overlap log and job size. */
|
||||
CHECK( ZSTD_CCtxParams_setParameter(params, ZSTD_c_overlapLog, 5) );
|
||||
CHECK( ZSTD_CCtxParams_setParameter(params, ZSTD_c_jobSize, 2 MB) );
|
||||
CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_overlapLog, &value) );
|
||||
CHECK_EQ(value, 5);
|
||||
CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_jobSize, &value) );
|
||||
CHECK_EQ(value, 2 MB);
|
||||
/* Set the number of worksers and check the overlap log and job size. */
|
||||
CHECK( ZSTD_CCtxParams_setParameter(params, ZSTD_c_nbWorkers, 2) );
|
||||
CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_overlapLog, &value) );
|
||||
CHECK_EQ(value, 5);
|
||||
CHECK( ZSTD_CCtxParams_getParameter(params, ZSTD_c_jobSize, &value) );
|
||||
CHECK_EQ(value, 2 MB);
|
||||
ZSTD_freeCCtxParams(params);
|
||||
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
/* Simple API multiframe test */
|
||||
DISPLAYLEVEL(3, "test%3i : compress multiple frames : ", testNb++);
|
||||
@ -859,6 +949,11 @@ static int basicUnitTests(U32 seed, double compressibility)
|
||||
if (r != CNBuffSize / 2) goto _output_error; }
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : get tight decompressed bound of multiple frames : ", testNb++);
|
||||
{ unsigned long long const bound = ZSTD_decompressBound(compressedBuffer, cSize);
|
||||
if (bound != CNBuffSize / 2) goto _output_error; }
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : decompress multiple frames : ", testNb++);
|
||||
{ CHECK_V(r, ZSTD_decompress(decodedBuffer, CNBuffSize, compressedBuffer, cSize));
|
||||
if (r != CNBuffSize / 2) goto _output_error; }
|
||||
@ -1203,9 +1298,13 @@ static int basicUnitTests(U32 seed, double compressibility)
|
||||
{
|
||||
size_t ret;
|
||||
MEM_writeLE32((char*)dictBuffer+2, ZSTD_MAGIC_DICTIONARY);
|
||||
/* Either operation is allowed to fail, but one must fail. */
|
||||
ret = ZSTD_CCtx_loadDictionary_advanced(
|
||||
cctx, (const char*)dictBuffer+2, dictSize-2, ZSTD_dlm_byRef, ZSTD_dct_auto);
|
||||
if (!ZSTD_isError(ret)) goto _output_error;
|
||||
if (!ZSTD_isError(ret)) {
|
||||
ret = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100));
|
||||
if (!ZSTD_isError(ret)) goto _output_error;
|
||||
}
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
@ -1216,6 +1315,152 @@ static int basicUnitTests(U32 seed, double compressibility)
|
||||
ret = ZSTD_CCtx_loadDictionary_advanced(
|
||||
cctx, (const char*)dictBuffer+2, dictSize-2, ZSTD_dlm_byRef, ZSTD_dct_rawContent);
|
||||
if (ZSTD_isError(ret)) goto _output_error;
|
||||
ret = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100));
|
||||
if (ZSTD_isError(ret)) goto _output_error;
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : ZSTD_CCtx_refCDict() then set parameters : ", testNb++);
|
||||
{ ZSTD_CDict* const cdict = ZSTD_createCDict(CNBuffer, dictSize, 1);
|
||||
CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 1) );
|
||||
CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_hashLog, 12 ));
|
||||
CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) );
|
||||
CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 1) );
|
||||
CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_hashLog, 12 ));
|
||||
ZSTD_freeCDict(cdict);
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : Loading dictionary before setting parameters is the same as loading after : ", testNb++);
|
||||
{
|
||||
size_t size1, size2;
|
||||
ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters);
|
||||
CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 7) );
|
||||
CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, CNBuffer, MIN(CNBuffSize, 10 KB)) );
|
||||
size1 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
|
||||
if (ZSTD_isError(size1)) goto _output_error;
|
||||
|
||||
ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters);
|
||||
CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, CNBuffer, MIN(CNBuffSize, 10 KB)) );
|
||||
CHECK_Z( ZSTD_CCtx_setParameter(cctx, ZSTD_c_compressionLevel, 7) );
|
||||
size2 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
|
||||
if (ZSTD_isError(size2)) goto _output_error;
|
||||
|
||||
if (size1 != size2) goto _output_error;
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : Loading a dictionary clears the prefix : ", testNb++);
|
||||
{
|
||||
CHECK_Z( ZSTD_CCtx_refPrefix(cctx, (const char*)dictBuffer, dictSize) );
|
||||
CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, (const char*)dictBuffer, dictSize) );
|
||||
CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) );
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : Loading a dictionary clears the cdict : ", testNb++);
|
||||
{
|
||||
ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, 1);
|
||||
CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) );
|
||||
CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, (const char*)dictBuffer, dictSize) );
|
||||
CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) );
|
||||
ZSTD_freeCDict(cdict);
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : Loading a cdict clears the prefix : ", testNb++);
|
||||
{
|
||||
ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, 1);
|
||||
CHECK_Z( ZSTD_CCtx_refPrefix(cctx, (const char*)dictBuffer, dictSize) );
|
||||
CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) );
|
||||
CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) );
|
||||
ZSTD_freeCDict(cdict);
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : Loading a cdict clears the dictionary : ", testNb++);
|
||||
{
|
||||
ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, 1);
|
||||
CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, (const char*)dictBuffer, dictSize) );
|
||||
CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) );
|
||||
CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) );
|
||||
ZSTD_freeCDict(cdict);
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : Loading a prefix clears the dictionary : ", testNb++);
|
||||
{
|
||||
CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, (const char*)dictBuffer, dictSize) );
|
||||
CHECK_Z( ZSTD_CCtx_refPrefix(cctx, (const char*)dictBuffer, dictSize) );
|
||||
CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) );
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : Loading a prefix clears the cdict : ", testNb++);
|
||||
{
|
||||
ZSTD_CDict* const cdict = ZSTD_createCDict(dictBuffer, dictSize, 1);
|
||||
CHECK_Z( ZSTD_CCtx_refCDict(cctx, cdict) );
|
||||
CHECK_Z( ZSTD_CCtx_refPrefix(cctx, (const char*)dictBuffer, dictSize) );
|
||||
CHECK_Z( ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100)) );
|
||||
ZSTD_freeCDict(cdict);
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : Loaded dictionary persists across reset session : ", testNb++);
|
||||
{
|
||||
size_t size1, size2;
|
||||
ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters);
|
||||
CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, CNBuffer, MIN(CNBuffSize, 10 KB)) );
|
||||
size1 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
|
||||
if (ZSTD_isError(size1)) goto _output_error;
|
||||
|
||||
ZSTD_CCtx_reset(cctx, ZSTD_reset_session_only);
|
||||
size2 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
|
||||
if (ZSTD_isError(size2)) goto _output_error;
|
||||
|
||||
if (size1 != size2) goto _output_error;
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : Loaded dictionary is cleared after resetting parameters : ", testNb++);
|
||||
{
|
||||
size_t size1, size2;
|
||||
ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters);
|
||||
CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, CNBuffer, MIN(CNBuffSize, 10 KB)) );
|
||||
size1 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
|
||||
if (ZSTD_isError(size1)) goto _output_error;
|
||||
|
||||
ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters);
|
||||
size2 = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
|
||||
if (ZSTD_isError(size2)) goto _output_error;
|
||||
|
||||
if (size1 == size2) goto _output_error;
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
ZSTD_CCtx_reset(cctx, ZSTD_reset_session_and_parameters);
|
||||
CHECK_Z( ZSTD_CCtx_loadDictionary(cctx, dictBuffer, dictSize) );
|
||||
cSize = ZSTD_compress2(cctx, compressedBuffer, compressedBufferSize, CNBuffer, MIN(CNBuffSize, 100 KB));
|
||||
CHECK_Z(cSize);
|
||||
DISPLAYLEVEL(3, "test%3i : ZSTD_decompressDCtx() with dictionary : ", testNb++);
|
||||
{
|
||||
ZSTD_DCtx* dctx = ZSTD_createDCtx();
|
||||
size_t ret;
|
||||
/* We should fail to decompress without a dictionary. */
|
||||
ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
|
||||
ret = ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize);
|
||||
if (!ZSTD_isError(ret)) goto _output_error;
|
||||
/* We should succeed to decompress with the dictionary. */
|
||||
ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
|
||||
CHECK_Z( ZSTD_DCtx_loadDictionary(dctx, dictBuffer, dictSize) );
|
||||
CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize) );
|
||||
/* The dictionary should presist across calls. */
|
||||
CHECK_Z( ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize) );
|
||||
/* When we reset the context the dictionary is cleared. */
|
||||
ZSTD_DCtx_reset(dctx, ZSTD_reset_session_and_parameters);
|
||||
ret = ZSTD_decompressDCtx(dctx, decodedBuffer, CNBuffSize, compressedBuffer, cSize);
|
||||
if (!ZSTD_isError(ret)) goto _output_error;
|
||||
ZSTD_freeDCtx(dctx);
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
|
||||
|
@ -16,10 +16,11 @@
|
||||
/*===========================================
|
||||
* Dependencies
|
||||
*==========================================*/
|
||||
#include <stddef.h> /* size_t */
|
||||
#include <stdlib.h> /* malloc, free */
|
||||
#include <stdio.h> /* fprintf */
|
||||
#include <string.h> /* strlen */
|
||||
#include <stddef.h> /* size_t */
|
||||
#include <stdlib.h> /* malloc, free */
|
||||
#include <stdio.h> /* fprintf */
|
||||
#include <string.h> /* strlen */
|
||||
#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_decompressBound */
|
||||
#include "zstd.h"
|
||||
#include "zstd_errors.h"
|
||||
|
||||
@ -130,12 +131,41 @@ static int testStreamingAPI(void)
|
||||
return error_code;
|
||||
}
|
||||
|
||||
static int testFrameDecoding(void)
|
||||
{
|
||||
if (strlen(EXPECTED) > ZSTD_decompressBound(COMPRESSED, COMPRESSED_SIZE)) {
|
||||
DISPLAY("ERROR: ZSTD_decompressBound: decompressed bound too small\n");
|
||||
return 1;
|
||||
}
|
||||
{ const char* ip = COMPRESSED;
|
||||
size_t remainingSize = COMPRESSED_SIZE;
|
||||
while (1) {
|
||||
size_t frameSize = ZSTD_findFrameCompressedSize(ip, remainingSize);
|
||||
if (ZSTD_isError(frameSize)) {
|
||||
DISPLAY("ERROR: ZSTD_findFrameCompressedSize: %s\n", ZSTD_getErrorName(frameSize));
|
||||
return 1;
|
||||
}
|
||||
if (frameSize > remainingSize) {
|
||||
DISPLAY("ERROR: ZSTD_findFrameCompressedSize: expected frameSize to align with src buffer");
|
||||
return 1;
|
||||
}
|
||||
ip += frameSize;
|
||||
remainingSize -= frameSize;
|
||||
if (remainingSize == 0) break;
|
||||
}
|
||||
}
|
||||
DISPLAY("Frame Decoding OK\n");
|
||||
return 0;
|
||||
}
|
||||
|
||||
int main(void)
|
||||
{
|
||||
{ int const ret = testSimpleAPI();
|
||||
if (ret) return ret; }
|
||||
{ int const ret = testStreamingAPI();
|
||||
if (ret) return ret; }
|
||||
{ int const ret = testFrameDecoding();
|
||||
if (ret) return ret; }
|
||||
|
||||
DISPLAY("OK\n");
|
||||
return 0;
|
||||
|
@ -200,6 +200,15 @@ $ZSTD tmp -fo tmp && die "zstd compression overwrote the input file"
|
||||
$ZSTD tmp.zst -dfo tmp.zst && die "zstd decompression overwrote the input file"
|
||||
$ECHO "test: detect that input file does not exist"
|
||||
$ZSTD nothere && die "zstd hasn't detected that input file does not exist"
|
||||
$ECHO "test: --[no-]compress-literals"
|
||||
$ZSTD tmp -c --no-compress-literals -1 | $ZSTD -t
|
||||
$ZSTD tmp -c --no-compress-literals --fast=1 | $ZSTD -t
|
||||
$ZSTD tmp -c --no-compress-literals -19 | $ZSTD -t
|
||||
$ZSTD tmp -c --compress-literals -1 | $ZSTD -t
|
||||
$ZSTD tmp -c --compress-literals --fast=1 | $ZSTD -t
|
||||
$ZSTD tmp -c --compress-literals -19 | $ZSTD -t
|
||||
$ZSTD -b --fast=1 -i1e1 tmp --compress-literals
|
||||
$ZSTD -b --fast=1 -i1e1 tmp --no-compress-literals
|
||||
|
||||
$ECHO "test : file removal"
|
||||
$ZSTD -f --rm tmp
|
||||
@ -314,18 +323,28 @@ $ECHO foo | $ZSTD > /dev/full && die "write error not detected!"
|
||||
$ECHO "$ECHO foo | $ZSTD | $ZSTD -d > /dev/full"
|
||||
$ECHO foo | $ZSTD | $ZSTD -d > /dev/full && die "write error not detected!"
|
||||
|
||||
fi
|
||||
|
||||
|
||||
if [ "$isWindows" = false ] && [ "$UNAME" != 'SunOS' ] ; then
|
||||
|
||||
$ECHO "\n===> symbolic link test "
|
||||
|
||||
rm -f hello.tmp world.tmp hello.tmp.zst world.tmp.zst
|
||||
rm -f hello.tmp world.tmp world2.tmp hello.tmp.zst world.tmp.zst
|
||||
$ECHO "hello world" > hello.tmp
|
||||
ln -s hello.tmp world.tmp
|
||||
$ZSTD world.tmp hello.tmp
|
||||
ln -s hello.tmp world2.tmp
|
||||
$ZSTD world.tmp hello.tmp || true
|
||||
test -f hello.tmp.zst # regular file should have been compressed!
|
||||
test ! -f world.tmp.zst # symbolic link should not have been compressed!
|
||||
$ZSTD world.tmp || true
|
||||
test ! -f world.tmp.zst # symbolic link should not have been compressed!
|
||||
$ZSTD world.tmp world2.tmp || true
|
||||
test ! -f world.tmp.zst # symbolic link should not have been compressed!
|
||||
test ! -f world2.tmp.zst # symbolic link should not have been compressed!
|
||||
$ZSTD world.tmp hello.tmp -f
|
||||
test -f world.tmp.zst # symbolic link should have been compressed with --force
|
||||
rm -f hello.tmp world.tmp hello.tmp.zst world.tmp.zst
|
||||
rm -f hello.tmp world.tmp world2.tmp hello.tmp.zst world.tmp.zst
|
||||
|
||||
fi
|
||||
|
||||
@ -391,6 +410,8 @@ $ECHO "- Create first dictionary "
|
||||
TESTFILE=../programs/zstdcli.c
|
||||
$ZSTD --train *.c ../programs/*.c -o tmpDict
|
||||
cp $TESTFILE tmp
|
||||
$ECHO "- Test dictionary compression with tmpDict as an input file and dictionary"
|
||||
$ZSTD -f tmpDict -D tmpDict && die "compression error not detected!"
|
||||
$ECHO "- Dictionary compression roundtrip"
|
||||
$ZSTD -f tmp -D tmpDict
|
||||
$ZSTD -d tmp.zst -D tmpDict -fo result
|
||||
@ -815,7 +836,7 @@ FULL_COMPRESSED_FILE=${TEST_DATA_FILE}.zst
|
||||
TRUNCATED_COMPRESSED_FILE=truncated-input.txt.zst
|
||||
./datagen -g50000 > $TEST_DATA_FILE
|
||||
$ZSTD -f $TEST_DATA_FILE -o $FULL_COMPRESSED_FILE
|
||||
head -c 100 $FULL_COMPRESSED_FILE > $TRUNCATED_COMPRESSED_FILE
|
||||
dd bs=1 count=100 if=$FULL_COMPRESSED_FILE of=$TRUNCATED_COMPRESSED_FILE status=none
|
||||
$ZSTD --list $TRUNCATED_COMPRESSED_FILE && die "-l must fail on truncated file"
|
||||
|
||||
rm $TEST_DATA_FILE
|
||||
|
@ -90,6 +90,17 @@ static config_t mt_ldm = {
|
||||
.param_values = PARAM_VALUES(mt_ldm_param_values),
|
||||
};
|
||||
|
||||
static param_value_t mt_advanced_param_values[] = {
|
||||
{.param = ZSTD_c_nbWorkers, .value = 2},
|
||||
{.param = ZSTD_c_literalCompressionMode, .value = ZSTD_lcm_uncompressed},
|
||||
};
|
||||
|
||||
static config_t mt_advanced = {
|
||||
.name = "multithreaded with advanced params",
|
||||
.cli_args = "-T2 --no-compress-literals",
|
||||
.param_values = PARAM_VALUES(mt_advanced_param_values),
|
||||
};
|
||||
|
||||
static param_value_t const small_wlog_param_values[] = {
|
||||
{.param = ZSTD_c_windowLog, .value = 10},
|
||||
};
|
||||
@ -122,6 +133,39 @@ static config_t small_clog = {
|
||||
.param_values = PARAM_VALUES(small_clog_param_values),
|
||||
};
|
||||
|
||||
static param_value_t const uncompressed_literals_param_values[] = {
|
||||
{.param = ZSTD_c_compressionLevel, .value = 3},
|
||||
{.param = ZSTD_c_literalCompressionMode, .value = ZSTD_lcm_uncompressed},
|
||||
};
|
||||
|
||||
static config_t uncompressed_literals = {
|
||||
.name = "uncompressed literals",
|
||||
.cli_args = "-3 --no-compress-literals",
|
||||
.param_values = PARAM_VALUES(uncompressed_literals_param_values),
|
||||
};
|
||||
|
||||
static param_value_t const uncompressed_literals_opt_param_values[] = {
|
||||
{.param = ZSTD_c_compressionLevel, .value = 19},
|
||||
{.param = ZSTD_c_literalCompressionMode, .value = ZSTD_lcm_uncompressed},
|
||||
};
|
||||
|
||||
static config_t uncompressed_literals_opt = {
|
||||
.name = "uncompressed literals optimal",
|
||||
.cli_args = "-19 --no-compress-literals",
|
||||
.param_values = PARAM_VALUES(uncompressed_literals_opt_param_values),
|
||||
};
|
||||
|
||||
static param_value_t const huffman_literals_param_values[] = {
|
||||
{.param = ZSTD_c_compressionLevel, .value = -1},
|
||||
{.param = ZSTD_c_literalCompressionMode, .value = ZSTD_lcm_huffman},
|
||||
};
|
||||
|
||||
static config_t huffman_literals = {
|
||||
.name = "huffman literals",
|
||||
.cli_args = "--fast=1 --compress-literals",
|
||||
.param_values = PARAM_VALUES(huffman_literals_param_values),
|
||||
};
|
||||
|
||||
static param_value_t const explicit_params_param_values[] = {
|
||||
{.param = ZSTD_c_checksumFlag, .value = 1},
|
||||
{.param = ZSTD_c_contentSizeFlag, .value = 0},
|
||||
@ -155,6 +199,10 @@ static config_t const* g_configs[] = {
|
||||
&small_hlog,
|
||||
&small_clog,
|
||||
&explicit_params,
|
||||
&uncompressed_literals,
|
||||
&uncompressed_literals_opt,
|
||||
&huffman_literals,
|
||||
&mt_advanced,
|
||||
NULL,
|
||||
};
|
||||
|
||||
|
@ -175,8 +175,8 @@ static result_t compress_cctx_compress(
|
||||
state->compressed.capacity,
|
||||
input.data,
|
||||
input.size,
|
||||
state->dictionary.data,
|
||||
state->dictionary.size,
|
||||
config->use_dictionary ? state->dictionary.data : NULL,
|
||||
config->use_dictionary ? state->dictionary.size : 0,
|
||||
params);
|
||||
else if (config->use_dictionary)
|
||||
state->compressed.size = ZSTD_compress_usingDict(
|
||||
@ -432,77 +432,158 @@ out:
|
||||
return result;
|
||||
}
|
||||
|
||||
static result_t old_streaming_compress(
|
||||
method_state_t* base,
|
||||
config_t const* config) {
|
||||
buffer_state_t* state = container_of(base, buffer_state_t, base);
|
||||
|
||||
if (buffer_state_bad(state, config))
|
||||
return result_error(result_error_system_error);
|
||||
|
||||
int const level = config_get_level(config);
|
||||
if (level == CONFIG_NO_LEVEL)
|
||||
return result_error(result_error_skip);
|
||||
|
||||
ZSTD_CStream* zcs = ZSTD_createCStream();
|
||||
result_t result;
|
||||
if (zcs == NULL) {
|
||||
result = result_error(result_error_compression_error);
|
||||
goto out;
|
||||
}
|
||||
static int init_cstream(
|
||||
buffer_state_t* state,
|
||||
ZSTD_CStream* zcs,
|
||||
config_t const* config,
|
||||
int const advanced,
|
||||
ZSTD_CDict** cdict)
|
||||
{
|
||||
size_t zret;
|
||||
if (config->use_dictionary) {
|
||||
zret = ZSTD_initCStream_usingDict(
|
||||
zcs, state->dictionary.data, state->dictionary.size, level);
|
||||
if (advanced) {
|
||||
ZSTD_parameters const params = config_get_zstd_params(config, 0, 0);
|
||||
ZSTD_CDict* dict = NULL;
|
||||
if (cdict) {
|
||||
*cdict = ZSTD_createCDict_advanced(
|
||||
state->dictionary.data,
|
||||
state->dictionary.size,
|
||||
ZSTD_dlm_byRef,
|
||||
ZSTD_dct_auto,
|
||||
params.cParams,
|
||||
ZSTD_defaultCMem);
|
||||
if (!*cdict) {
|
||||
return 1;
|
||||
}
|
||||
zret = ZSTD_initCStream_usingCDict_advanced(
|
||||
zcs, *cdict, params.fParams, ZSTD_CONTENTSIZE_UNKNOWN);
|
||||
} else {
|
||||
zret = ZSTD_initCStream_advanced(
|
||||
zcs,
|
||||
state->dictionary.data,
|
||||
state->dictionary.size,
|
||||
params,
|
||||
ZSTD_CONTENTSIZE_UNKNOWN);
|
||||
}
|
||||
} else {
|
||||
zret = ZSTD_initCStream(zcs, level);
|
||||
int const level = config_get_level(config);
|
||||
if (cdict) {
|
||||
*cdict = ZSTD_createCDict(
|
||||
state->dictionary.data,
|
||||
state->dictionary.size,
|
||||
level);
|
||||
if (!*cdict) {
|
||||
return 1;
|
||||
}
|
||||
zret = ZSTD_initCStream_usingCDict(zcs, *cdict);
|
||||
} else if (config->use_dictionary) {
|
||||
zret = ZSTD_initCStream_usingDict(
|
||||
zcs, state->dictionary.data, state->dictionary.size, level);
|
||||
} else {
|
||||
zret = ZSTD_initCStream(zcs, level);
|
||||
}
|
||||
}
|
||||
if (ZSTD_isError(zret)) {
|
||||
result = result_error(result_error_compression_error);
|
||||
goto out;
|
||||
return 1;
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
static result_t old_streaming_compress_internal(
|
||||
method_state_t* base,
|
||||
config_t const* config,
|
||||
int const advanced,
|
||||
int const cdict) {
|
||||
buffer_state_t* state = container_of(base, buffer_state_t, base);
|
||||
|
||||
if (buffer_state_bad(state, config))
|
||||
return result_error(result_error_system_error);
|
||||
|
||||
|
||||
ZSTD_CStream* zcs = ZSTD_createCStream();
|
||||
ZSTD_CDict* cd = NULL;
|
||||
result_t result;
|
||||
if (zcs == NULL) {
|
||||
result = result_error(result_error_compression_error);
|
||||
goto out;
|
||||
}
|
||||
if (init_cstream(state, zcs, config, advanced, cdict ? &cd : NULL)) {
|
||||
result = result_error(result_error_compression_error);
|
||||
goto out;
|
||||
}
|
||||
|
||||
result_data_t data = {.total_size = 0};
|
||||
for (size_t i = 0; i < state->inputs.size; ++i) {
|
||||
data_buffer_t input = state->inputs.buffers[i];
|
||||
size_t zret = ZSTD_resetCStream(
|
||||
zcs,
|
||||
config->no_pledged_src_size ? ZSTD_CONTENTSIZE_UNKNOWN : input.size);
|
||||
if (ZSTD_isError(zret)) {
|
||||
result = result_error(result_error_compression_error);
|
||||
goto out;
|
||||
}
|
||||
|
||||
result_data_t data = {.total_size = 0};
|
||||
for (size_t i = 0; i < state->inputs.size; ++i) {
|
||||
data_buffer_t input = state->inputs.buffers[i];
|
||||
zret = ZSTD_resetCStream(
|
||||
zcs,
|
||||
config->no_pledged_src_size ? ZSTD_CONTENTSIZE_UNKNOWN
|
||||
: input.size);
|
||||
while (input.size > 0) {
|
||||
ZSTD_inBuffer in = {input.data, MIN(input.size, 4096)};
|
||||
input.data += in.size;
|
||||
input.size -= in.size;
|
||||
ZSTD_EndDirective const op =
|
||||
input.size > 0 ? ZSTD_e_continue : ZSTD_e_end;
|
||||
zret = 0;
|
||||
while (in.pos < in.size || (op == ZSTD_e_end && zret != 0)) {
|
||||
ZSTD_outBuffer out = {state->compressed.data,
|
||||
MIN(state->compressed.capacity, 1024)};
|
||||
if (op == ZSTD_e_continue || in.pos < in.size)
|
||||
zret = ZSTD_compressStream(zcs, &out, &in);
|
||||
else
|
||||
zret = ZSTD_endStream(zcs, &out);
|
||||
if (ZSTD_isError(zret)) {
|
||||
result = result_error(result_error_compression_error);
|
||||
goto out;
|
||||
}
|
||||
|
||||
while (input.size > 0) {
|
||||
ZSTD_inBuffer in = {input.data, MIN(input.size, 4096)};
|
||||
input.data += in.size;
|
||||
input.size -= in.size;
|
||||
ZSTD_EndDirective const op =
|
||||
input.size > 0 ? ZSTD_e_continue : ZSTD_e_end;
|
||||
zret = 0;
|
||||
while (in.pos < in.size || (op == ZSTD_e_end && zret != 0)) {
|
||||
ZSTD_outBuffer out = {state->compressed.data,
|
||||
MIN(state->compressed.capacity, 1024)};
|
||||
if (op == ZSTD_e_continue || in.pos < in.size)
|
||||
zret = ZSTD_compressStream(zcs, &out, &in);
|
||||
else
|
||||
zret = ZSTD_endStream(zcs, &out);
|
||||
if (ZSTD_isError(zret)) {
|
||||
result = result_error(result_error_compression_error);
|
||||
goto out;
|
||||
}
|
||||
data.total_size += out.pos;
|
||||
}
|
||||
result = result_error(result_error_compression_error);
|
||||
goto out;
|
||||
}
|
||||
data.total_size += out.pos;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
result = result_data(data);
|
||||
result = result_data(data);
|
||||
out:
|
||||
ZSTD_freeCStream(zcs);
|
||||
ZSTD_freeCDict(cd);
|
||||
return result;
|
||||
}
|
||||
|
||||
static result_t old_streaming_compress(
|
||||
method_state_t* base,
|
||||
config_t const* config)
|
||||
{
|
||||
return old_streaming_compress_internal(
|
||||
base, config, /* advanced */ 0, /* cdict */ 0);
|
||||
}
|
||||
|
||||
static result_t old_streaming_compress_advanced(
|
||||
method_state_t* base,
|
||||
config_t const* config)
|
||||
{
|
||||
return old_streaming_compress_internal(
|
||||
base, config, /* advanced */ 1, /* cdict */ 0);
|
||||
}
|
||||
|
||||
static result_t old_streaming_compress_cdict(
|
||||
method_state_t* base,
|
||||
config_t const* config)
|
||||
{
|
||||
return old_streaming_compress_internal(
|
||||
base, config, /* advanced */ 0, /* cdict */ 1);
|
||||
}
|
||||
|
||||
static result_t old_streaming_compress_cdict_advanced(
|
||||
method_state_t* base,
|
||||
config_t const* config)
|
||||
{
|
||||
return old_streaming_compress_internal(
|
||||
base, config, /* advanced */ 1, /* cdict */ 1);
|
||||
}
|
||||
|
||||
method_t const simple = {
|
||||
.name = "compress simple",
|
||||
.create = buffer_state_create,
|
||||
@ -545,6 +626,27 @@ method_t const old_streaming = {
|
||||
.destroy = buffer_state_destroy,
|
||||
};
|
||||
|
||||
method_t const old_streaming_advanced = {
|
||||
.name = "old streaming advanced",
|
||||
.create = buffer_state_create,
|
||||
.compress = old_streaming_compress,
|
||||
.destroy = buffer_state_destroy,
|
||||
};
|
||||
|
||||
method_t const old_streaming_cdict = {
|
||||
.name = "old streaming cdcit",
|
||||
.create = buffer_state_create,
|
||||
.compress = old_streaming_compress,
|
||||
.destroy = buffer_state_destroy,
|
||||
};
|
||||
|
||||
method_t const old_streaming_advanced_cdict = {
|
||||
.name = "old streaming advanced cdict",
|
||||
.create = buffer_state_create,
|
||||
.compress = old_streaming_compress,
|
||||
.destroy = buffer_state_destroy,
|
||||
};
|
||||
|
||||
method_t const cli = {
|
||||
.name = "zstdcli",
|
||||
.create = method_state_create,
|
||||
@ -560,6 +662,9 @@ static method_t const* g_methods[] = {
|
||||
&advanced_one_pass_small_out,
|
||||
&advanced_streaming,
|
||||
&old_streaming,
|
||||
&old_streaming_advanced,
|
||||
&old_streaming_cdict,
|
||||
&old_streaming_advanced_cdict,
|
||||
NULL,
|
||||
};
|
||||
|
||||
|
File diff suppressed because it is too large
Load Diff
@ -93,9 +93,9 @@ static size_t cctxParamRoundTripTest(void* resultBuff, size_t resultBuffCapacity
|
||||
int const cLevel = h32 % maxClevel;
|
||||
|
||||
/* Set parameters */
|
||||
CHECK_Z( ZSTD_CCtxParam_setParameter(cctxParams, ZSTD_c_compressionLevel, cLevel) );
|
||||
CHECK_Z( ZSTD_CCtxParam_setParameter(cctxParams, ZSTD_c_nbWorkers, 2) );
|
||||
CHECK_Z( ZSTD_CCtxParam_setParameter(cctxParams, ZSTD_c_overlapLog, 5) );
|
||||
CHECK_Z( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_compressionLevel, cLevel) );
|
||||
CHECK_Z( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_nbWorkers, 2) );
|
||||
CHECK_Z( ZSTD_CCtxParams_setParameter(cctxParams, ZSTD_c_overlapLog, 5) );
|
||||
|
||||
|
||||
/* Apply parameters */
|
||||
|
@ -31,6 +31,7 @@ static const void *symbols[] = {
|
||||
&ZSTD_getFrameContentSize,
|
||||
&ZSTD_maxCLevel,
|
||||
&ZSTD_compressBound,
|
||||
&ZSTD_decompressBound,
|
||||
&ZSTD_isError,
|
||||
&ZSTD_getErrorName,
|
||||
&ZSTD_createCCtx,
|
||||
|
@ -344,6 +344,20 @@ static int basicUnitTests(U32 seed, double compressibility)
|
||||
DISPLAYLEVEL(3, "OK (%u bytes) \n", (unsigned)(cstreamSize + cdictSize));
|
||||
}
|
||||
|
||||
/* context size functions */
|
||||
DISPLAYLEVEL(3, "test%3i : estimate CStream size using CCtxParams : ", testNb++);
|
||||
{ ZSTD_CCtx_params* const params = ZSTD_createCCtxParams();
|
||||
size_t cstreamSize, cctxSize;
|
||||
CHECK_Z( ZSTD_CCtxParams_setParameter(params, ZSTD_c_compressionLevel, 19) );
|
||||
cstreamSize = ZSTD_estimateCStreamSize_usingCCtxParams(params);
|
||||
CHECK_Z(cstreamSize);
|
||||
cctxSize = ZSTD_estimateCCtxSize_usingCCtxParams(params);
|
||||
CHECK_Z(cctxSize);
|
||||
if (cstreamSize <= cctxSize + 2 * ZSTD_BLOCKSIZE_MAX) goto _output_error;
|
||||
ZSTD_freeCCtxParams(params);
|
||||
DISPLAYLEVEL(3, "OK \n");
|
||||
}
|
||||
|
||||
DISPLAYLEVEL(3, "test%3i : check actual CStream size : ", testNb++);
|
||||
{ size_t const s = ZSTD_sizeof_CStream(zc);
|
||||
if (ZSTD_isError(s)) goto _output_error;
|
||||
@ -495,7 +509,7 @@ static int basicUnitTests(U32 seed, double compressibility)
|
||||
|
||||
/* _srcSize compression test */
|
||||
DISPLAYLEVEL(3, "test%3i : compress_srcSize %u bytes : ", testNb++, COMPRESSIBLE_NOISE_LENGTH);
|
||||
ZSTD_initCStream_srcSize(zc, 1, CNBufferSize);
|
||||
CHECK_Z( ZSTD_initCStream_srcSize(zc, 1, CNBufferSize) );
|
||||
outBuff.dst = (char*)(compressedBuffer);
|
||||
outBuff.size = compressedBufferSize;
|
||||
outBuff.pos = 0;
|
||||
@ -503,11 +517,14 @@ static int basicUnitTests(U32 seed, double compressibility)
|
||||
inBuff.size = CNBufferSize;
|
||||
inBuff.pos = 0;
|
||||
CHECK_Z( ZSTD_compressStream(zc, &outBuff, &inBuff) );
|
||||
if (inBuff.pos != inBuff.size) goto _output_error; /* entire input should be consumed */
|
||||
{ size_t const r = ZSTD_endStream(zc, &outBuff);
|
||||
if (r != 0) goto _output_error; } /* error, or some data not flushed */
|
||||
{ unsigned long long origSize = ZSTD_findDecompressedSize(outBuff.dst, outBuff.pos);
|
||||
if ((size_t)origSize != CNBufferSize) goto _output_error; } /* exact original size must be present */
|
||||
CHECK(inBuff.pos != inBuff.size, "Entire input should be consumed");
|
||||
{ size_t const r = ZSTD_endStream(zc, &outBuff);
|
||||
CHECK(r != 0, "Error or some data not flushed (ret=%zu)", r);
|
||||
}
|
||||
{ unsigned long long origSize = ZSTD_findDecompressedSize(outBuff.dst, outBuff.pos);
|
||||
CHECK(origSize == ZSTD_CONTENTSIZE_UNKNOWN, "Unknown!");
|
||||
CHECK((size_t)origSize != CNBufferSize, "Exact original size must be present (got %llu)", origSize);
|
||||
}
|
||||
DISPLAYLEVEL(3, "OK (%u bytes : %.2f%%)\n", (unsigned)cSize, (double)cSize/COMPRESSIBLE_NOISE_LENGTH*100);
|
||||
|
||||
/* wrong _srcSize compression test */
|
||||
@ -1703,7 +1720,7 @@ static size_t setCCtxParameter(ZSTD_CCtx* zc, ZSTD_CCtx_params* cctxParams,
|
||||
int useOpaqueAPI)
|
||||
{
|
||||
if (useOpaqueAPI) {
|
||||
return ZSTD_CCtxParam_setParameter(cctxParams, param, value);
|
||||
return ZSTD_CCtxParams_setParameter(cctxParams, param, value);
|
||||
} else {
|
||||
return ZSTD_CCtx_setParameter(zc, param, value);
|
||||
}
|
||||
@ -1930,16 +1947,6 @@ static int fuzzerTests_newAPI(U32 seed, int nbTests, int startTest,
|
||||
} else {
|
||||
CHECK_Z( ZSTD_CCtx_loadDictionary_byReference(zc, dict, dictSize) );
|
||||
}
|
||||
if (dict && dictSize) {
|
||||
/* test that compression parameters are rejected (correctly) after loading a non-NULL dictionary */
|
||||
if (opaqueAPI) {
|
||||
size_t const setError = ZSTD_CCtx_setParametersUsingCCtxParams(zc, cctxParams);
|
||||
CHECK(!ZSTD_isError(setError), "ZSTD_CCtx_setParametersUsingCCtxParams should have failed");
|
||||
} else {
|
||||
size_t const setError = ZSTD_CCtx_setParameter(zc, ZSTD_c_windowLog, cParams.windowLog-1);
|
||||
CHECK(!ZSTD_isError(setError), "ZSTD_CCtx_setParameter should have failed");
|
||||
}
|
||||
}
|
||||
} else {
|
||||
CHECK_Z( ZSTD_CCtx_refPrefix(zc, dict, dictSize) );
|
||||
}
|
||||
|
Reference in New Issue
Block a user